Merge tag 'drm-next-2019-12-06' of git://anongit.freedesktop.org/drm/drm

Pull more drm updates from Dave Airlie:
 "Rob pointed out I missed his pull request for msm-next, it's been in
  next for a while outside of my tree so shouldn't cause any unexpected
  issues, it has some OCMEM support in drivers/soc that is acked by
  other maintainers as it's outside my tree.

  Otherwise it's a usual fixes pull, i915, amdgpu, the main ones, with
  some tegra, omap, mgag200 and one core fix.

  Summary:

  msm-next:
   - OCMEM support for a3xx and a4xx GPUs.
   - a510 support + display support

  core:
   - mst payload deletion fix

  i915:
   - uapi alignment fix
   - fix for power usage regression due to security fixes
   - change default preemption timeout to 640ms from 100ms
   - EHL voltage level display fixes
   - TGL DGL PHY fix
   - gvt - MI_ATOMIC cmd parser fix, CFL non-priv warning
   - CI spotted deadlock fix
   - EHL port D programming fix

  amdgpu:
   - VRAM lost fixes on BACO for CI/VI
   - navi14 DC fixes
   - misc SR-IOV, gfx10 fixes
   - XGMI fixes for arcturus
   - SRIOV fixes

  amdkfd:
   - KFD on ppc64le enabled
   - page table optimisations

  radeon:
   - fix for r1xx/2xx register checker.

  tegra:
   - displayport regression fixes
   - DMA API regression fixes

  mgag200:
   - fix devices that can't scanout except at 0 addr

  omap:
   - fix dma_addr refcounting"

* tag 'drm-next-2019-12-06' of git://anongit.freedesktop.org/drm/drm: (100 commits)
  drm/dp_mst: Correct the bug in drm_dp_update_payload_part1()
  drm/omap: fix dma_addr refcounting
  drm/tegra: Run hub cleanup on ->remove()
  drm/tegra: sor: Make the +5V HDMI supply optional
  drm/tegra: Silence expected errors on IOMMU attach
  drm/tegra: vic: Export module device table
  drm/tegra: sor: Implement system suspend/resume
  drm/tegra: Use proper IOVA address for cursor image
  drm/tegra: gem: Remove premature import restrictions
  drm/tegra: gem: Properly pin imported buffers
  drm/tegra: hub: Remove bogus connection mutex check
  ia64: agp: Replace empty define with do while
  agp: Add bridge parameter documentation
  agp: remove unused variable num_segments
  agp: move AGPGART_MINOR to include/linux/miscdevice.h
  agp: remove unused variable size in agp_generic_create_gatt_table
  drm/dp_mst: Fix build on systems with STACKTRACE_SUPPORT=n
  drm/radeon: fix r1xx/r2xx register checker for POT textures
  drm/amdgpu: fix GFX10 missing CSIB set(v3)
  drm/amdgpu: should stop GFX ring in hw_fini
  ...

1 files changed, 58 insertions, 9 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 874d82677179..c1dd0cd3efc7 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -73,8 +73,42 @@ static inline void __timeline_mark_unlock(struct intel_context *ce,
 
 #endif /* !IS_ENABLED(CONFIG_LOCKDEP) */
 
+static void
+__queue_and_release_pm(struct i915_request *rq,
+		       struct intel_timeline *tl,
+		       struct intel_engine_cs *engine)
+{
+	struct intel_gt_timelines *timelines = &engine->gt->timelines;
+
+	GEM_TRACE("%s\n", engine->name);
+
+	/*
+	 * We have to serialise all potential retirement paths with our
+	 * submission, as we don't want to underflow either the
+	 * engine->wakeref.counter or our timeline->active_count.
+	 *
+	 * Equally, we cannot allow a new submission to start until
+	 * after we finish queueing, nor could we allow that submitter
+	 * to retire us before we are ready!
+	 */
+	spin_lock(&timelines->lock);
+
+	/* Let intel_gt_retire_requests() retire us (acquired under lock) */
+	if (!atomic_fetch_inc(&tl->active_count))
+		list_add_tail(&tl->link, &timelines->active_list);
+
+	/* Hand the request over to HW and so engine_retire() */
+	__i915_request_queue(rq, NULL);
+
+	/* Let new submissions commence (and maybe retire this timeline) */
+	__intel_wakeref_defer_park(&engine->wakeref);
+
+	spin_unlock(&timelines->lock);
+}
+
 static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 {
+	struct intel_context *ce = engine->kernel_context;
 	struct i915_request *rq;
 	unsigned long flags;
 	bool result = true;
@@ -98,16 +132,31 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	 * This should hold true as we can only park the engine after
 	 * retiring the last request, thus all rings should be empty and
 	 * all timelines idle.
+	 *
+	 * For unlocking, there are 2 other parties and the GPU who have a
+	 * stake here.
+	 *
+	 * A new gpu user will be waiting on the engine-pm to start their
+	 * engine_unpark. New waiters are predicated on engine->wakeref.count
+	 * and so intel_wakeref_defer_park() acts like a mutex_unlock of the
+	 * engine->wakeref.
+	 *
+	 * The other party is intel_gt_retire_requests(), which is walking the
+	 * list of active timelines looking for completions. Meanwhile as soon
+	 * as we call __i915_request_queue(), the GPU may complete our request.
+	 * Ergo, if we put ourselves on the timelines.active_list
+	 * (se intel_timeline_enter()) before we increment the
+	 * engine->wakeref.count, we may see the request completion and retire
+	 * it causing an undeflow of the engine->wakeref.
 	 */
-	flags = __timeline_mark_lock(engine->kernel_context);
+	flags = __timeline_mark_lock(ce);
+	GEM_BUG_ON(atomic_read(&ce->timeline->active_count) < 0);
 
-	rq = __i915_request_create(engine->kernel_context, GFP_NOWAIT);
+	rq = __i915_request_create(ce, GFP_NOWAIT);
 	if (IS_ERR(rq))
 		/* Context switch failed, hope for the best! Maybe reset? */
 		goto out_unlock;
 
-	intel_timeline_enter(i915_request_timeline(rq));
-
 	/* Check again on the next retirement. */
 	engine->wakeref_serial = engine->serial + 1;
 	i915_request_add_active_barriers(rq);
@@ -116,13 +165,12 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	rq->sched.attr.priority = I915_PRIORITY_BARRIER;
 	__i915_request_commit(rq);
 
-	/* Release our exclusive hold on the engine */
-	__intel_wakeref_defer_park(&engine->wakeref);
-	__i915_request_queue(rq, NULL);
+	/* Expose ourselves to the world */
+	__queue_and_release_pm(rq, ce->timeline, engine);
 
 	result = false;
 out_unlock:
-	__timeline_mark_unlock(engine->kernel_context, flags);
+	__timeline_mark_unlock(ce, flags);
 	return result;
 }
 
@@ -177,7 +225,8 @@ static int __engine_park(struct intel_wakeref *wf)
 
 	engine->execlists.no_priolist = false;
 
-	intel_gt_pm_put(engine->gt);
+	/* While gt calls i915_vma_parked(), we have to break the lock cycle */
+	intel_gt_pm_put_async(engine->gt);
 	return 0;
 }