Merge tag 'drm-next-2021-04-28' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "The usual lots of work all over the place.

  i915 has gotten some Alderlake work and prelim DG1 code, along with a
  major locking rework over the GEM code, and brings back the property
  of timing out long running jobs using a watchdog. amdgpu has some
  Alderbran support (new GPU), freesync HDMI support along with a lot
  other fixes.

  Outside of the drm, there is a new printf specifier added which should
  have all the correct acks/sobs:

   - printk fourcc modifier support added %p4cc

  Summary:

  core:
   - drm_crtc_commit_wait
   - atomic plane state helpers reworked for full state
   - dma-buf heaps API rework
   - edid: rework and improvements for displayid

  dp-mst:
   - better topology logging

  bridge:
   - Chipone ICN6211
   - Lontium LT8912B
   - anx7625 regulator support

  panel:
   - fix lt9611 4k panels handling

  simple-kms:
   - add plane state helpers

  ttm:
   - debugfs support
   - removal of unused sysfs
   - ignore signaled moved fences
   - ioremap buffer according to mem caching

  i915:
   - Alderlake S enablement
   - Conversion to dma_resv_locking
   - Bring back watchdog timeout support
   - legacy ioctl cleanups
   - add GEM TDDO and RFC process
   - DG1 LMEM preparation work
   - intel_display.c refactoring
   - Gen9/TGL PCH combination support
   - eDP MSO Support
   - multiple PSR instance support
   - Link training debug updates
   - Disable PSR2 support on JSL/EHL
   - DDR5/LPDDR5 support for bw calcs
   - LSPCON limited to gen9/10 platforms
   - HSW/BDW async flip/VTd corruption workaround
   - SAGV watermark fixes
   - SNB hard hang on ring resume fix
   - Limit imported dma-buf size
   - move to use new tasklet API
   - refactor KBL/TGL/ADL-S display/gt steppings
   - refactoring legacy DP/HDMI, FB plane code out

  amdgpu:
   - uapi: add ioctl to query video capabilities
   - Iniital AMD Freesync HDMI support
   - Initial Adebaran support
   - 10bpc dithering improvements
   - DCN secure display support
   - Drop legacy IO BAR requirements
   - PCIE/S0ix/RAS/Prime/Reset fixes
   - Display ASSR support
   - SMU gfx busy queues for RV/PCO
   - Initial LTTPR display work

  amdkfd:
   - MMU notifier fixes
   - APU fixes

  radeon:
   - debugfs cleanps
   - fw error handling ifix
   - Flexible array cleanups

  msm:
   - big DSI phy/pll cleanup
   - sc7280 initial support
   - commong bandwidth scaling path
   - shrinker locking contention fixes
   - unpin/swap support for GEM objcets

  ast:
   - cursor plane handling reworked

  tegra:
   - don't register DP AUX channels before connectors

  zynqmp:
   - fix OOB struct padding memset

  gma500:
   - drop ttm and medfield support

  exynos:
   - request_irq cleanup function

  mediatek:
   - fine tune line time for EOTp
   - MT8192 dpi support
   - atomic crtc config updates
   - don't support HDMI connector creation

  mxsdb:
   - imx8mm support

  panfrost:
   - MMU IRQ handling rework

  qxl:
   - locking fixes
   - resource deallocation changes

  sun4i:
   - add alpha properties to UI/VI layers

  vc4:
   - RPi4 CEC support

  vmwgfx:
   - doc cleanups

  arc:
   - moved to drm/tiny"

* tag 'drm-next-2021-04-28' of git://anongit.freedesktop.org/drm/drm: (1390 commits)
  drm/ttm: Don't count pages in SG BOs against pages_limit
  drm/ttm: fix return value check
  drm/bridge: lt8912b: fix incorrect handling of of_* return values
  drm: bridge: fix LONTIUM use of mipi_dsi_() functions
  drm: bridge: fix ANX7625 use of mipi_dsi_() functions
  drm/amdgpu: page retire over debugfs mechanism
  drm/radeon: Fix a missing check bug in radeon_dp_mst_detect()
  drm/amd/display: Fix the Wunused-function warning
  drm/radeon/r600: Fix variables that are not used after assignment
  drm/amdgpu/smu7: fix CAC setting on TOPAZ
  drm/amd/display: Update DCN302 SR Exit Latency
  drm/amdgpu: enable ras eeprom on aldebaran
  drm/amdgpu: RAS harvest on driver load
  drm/amdgpu: add ras aldebaran ras eeprom driver
  drm/amd/pm: increase time out value when sending msg to SMU
  drm/amdgpu: add DMUB outbox event IRQ source define/complete/debug flag
  drm/amd/pm: add the callback to get vbios bootup values for vangogh
  drm/radeon: Fix size overflow
  drm/amdgpu: Fix size overflow
  drm/amdgpu: move mmhub ras_func init to ip specific file
  ...

1 files changed, 37 insertions, 12 deletions

diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 1bfe214a47e9..270f6cd37650 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -26,7 +26,9 @@
 #define I915_REQUEST_H
 
 #include <linux/dma-fence.h>
+#include <linux/hrtimer.h>
 #include <linux/irq_work.h>
+#include <linux/llist.h>
 #include <linux/lockdep.h>
 
 #include "gem/i915_gem_context_types.h"
@@ -237,16 +239,6 @@ struct i915_request {
 	 */
 	const u32 *hwsp_seqno;
 
-	/*
-	 * If we need to access the timeline's seqno for this request in
-	 * another request, we need to keep a read reference to this associated
-	 * cacheline, so that we do not free and recycle it before the foreign
-	 * observers have completed. Hence, we keep a pointer to the cacheline
-	 * inside the timeline's HWSP vma, but it is only valid while this
-	 * request has not completed and guarded by the timeline mutex.
-	 */
-	struct intel_timeline_cacheline __rcu *hwsp_cacheline;
-
 	/** Position in the ring of the start of the request */
 	u32 head;
 
@@ -287,6 +279,12 @@ struct i915_request {
 	/** timeline->request entry for this request */
 	struct list_head link;
 
+	/** Watchdog support fields. */
+	struct i915_request_watchdog {
+		struct llist_node link;
+		struct hrtimer timer;
+	} watchdog;
+
 	I915_SELFTEST_DECLARE(struct {
 		struct list_head link;
 		unsigned long delay;
@@ -310,8 +308,8 @@ struct i915_request * __must_check
 i915_request_create(struct intel_context *ce);
 
 void __i915_request_skip(struct i915_request *rq);
-void i915_request_set_error_once(struct i915_request *rq, int error);
-void i915_request_mark_eio(struct i915_request *rq);
+bool i915_request_set_error_once(struct i915_request *rq, int error);
+struct i915_request *i915_request_mark_eio(struct i915_request *rq);
 
 struct i915_request *__i915_request_commit(struct i915_request *request);
 void __i915_request_queue(struct i915_request *rq,
@@ -366,6 +364,8 @@ void i915_request_submit(struct i915_request *request);
 void __i915_request_unsubmit(struct i915_request *request);
 void i915_request_unsubmit(struct i915_request *request);
 
+void i915_request_cancel(struct i915_request *rq, int error);
+
 long i915_request_wait(struct i915_request *rq,
 		       unsigned int flags,
 		       long timeout)
@@ -616,4 +616,29 @@ i915_request_active_timeline(const struct i915_request *rq)
 					 lockdep_is_held(&rq->engine->active.lock));
 }
 
+static inline u32
+i915_request_active_seqno(const struct i915_request *rq)
+{
+	u32 hwsp_phys_base =
+		page_mask_bits(i915_request_active_timeline(rq)->hwsp_offset);
+	u32 hwsp_relative_offset = offset_in_page(rq->hwsp_seqno);
+
+	/*
+	 * Because of wraparound, we cannot simply take tl->hwsp_offset,
+	 * but instead use the fact that the relative for vaddr is the
+	 * offset as for hwsp_offset. Take the top bits from tl->hwsp_offset
+	 * and combine them with the relative offset in rq->hwsp_seqno.
+	 *
+	 * As rw->hwsp_seqno is rewritten when signaled, this only works
+	 * when the request isn't signaled yet, but at that point you
+	 * no longer need the offset.
+	 */
+
+	return hwsp_phys_base + hwsp_relative_offset;
+}
+
+bool
+i915_request_active_engine(struct i915_request *rq,
+			   struct intel_engine_cs **active);
+
 #endif /* I915_REQUEST_H */