Merge tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for v4.15.

  Core:
   - Atomic object lifetime fixes
   - Atomic iterator improvements
   - Sparse/smatch fixes
   - Legacy kms ioctls to be interruptible
   - EDID override improvements
   - fb/gem helper cleanups
   - Simple outreachy patches
   - Documentation improvements
   - Fix dma-buf rcu races
   - DRM mode object leasing for improving VR use cases.
   - vgaarb improvements for non-x86 platforms.

  New driver:
   - tve200: Faraday Technology TVE200 block.

     This "TV Encoder" encodes a ITU-T BT.656 stream and can be found in
     the StorLink SL3516 (later Cortina Systems CS3516) as well as the
     Grain Media GM8180.

  New bridges:
   - SiI9234 support

  New panels:
   - S6E63J0X03, OTM8009A, Seiko 43WVF1G, 7" rpi touch panel, Toshiba
     LT089AC19000, Innolux AT043TN24

  i915:
   - Remove Coffeelake from alpha support
   - Cannonlake workarounds
   - Infoframe refactoring for DisplayPort
   - VBT updates
   - DisplayPort vswing/emph/buffer translation refactoring
   - CCS fixes
   - Restore GPU clock boost on missed vblanks
   - Scatter list updates for userptr allocations
   - Gen9+ transition watermarks
   - Display IPC (Isochronous Priority Control)
   - Private PAT management
   - GVT: improved error handling and pci config sanitizing
   - Execlist refactoring
   - Transparent Huge Page support
   - User defined priorities support
   - HuC/GuC firmware refactoring
   - DP MST fixes
   - eDP power sequencing fixes
   - Use RCU instead of stop_machine
   - PSR state tracking support
   - Eviction fixes
   - BDW DP aux channel timeout fixes
   - LSPCON fixes
   - Cannonlake PLL fixes

  amdgpu:
   - Per VM BO support
   - Powerplay cleanups
   - CI powerplay support
   - PASID mgr for kfd
   - SR-IOV fixes
   - initial GPU reset for vega10
   - Prime mmap support
   - TTM updates
   - Clock query interface for Raven
   - Fence to handle ioctl
   - UVD encode ring support on Polaris
   - Transparent huge page DMA support
   - Compute LRU pipe tweaks
   - BO flag to allow buffers to opt out of implicit sync
   - CTX priority setting API
   - VRAM lost infrastructure plumbing

  qxl:
   - fix flicker since atomic rework

  amdkfd:
   - Further improvements from internal AMD tree
   - Usermode events
   - Drop radeon support

  nouveau:
   - Pascal temperature sensor support
   - Improved BAR2 handling
   - MMU rework to support Pascal MMU

  exynos:
   - Improved HDMI/mixer support
   - HDMI audio interface support

  tegra:
   - Prep work for tegra186
   - Cleanup/fixes

  msm:
   - Preemption support for a5xx
   - Display fixes for 8x96 (snapdragon 820)
   - Async cursor plane fixes
   - FW loading rework
   - GPU debugging improvements

  vc4:
   - Prep for DSI panels
   - fix T-format tiling scanout
   - New madvise ioctl

  Rockchip:
   - LVDS support

  omapdrm:
   - omap4 HDMI CEC support

  etnaviv:
   - GPU performance counters groundwork

  sun4i:
   - refactor driver load + TCON backend
   - HDMI improvements
   - A31 support
   - Misc fixes

  udl:
   - Probe/EDID read fixes.

  tilcdc:
   - Misc fixes.

  pl111:
   - Support more variants

  adv7511:
   - Improve EDID handling.
   - HDMI CEC support

  sii8620:
   - Add remote control support"

* tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux: (1480 commits)
  drm/rockchip: analogix_dp: Use mutex rather than spinlock
  drm/mode_object: fix documentation for object lookups.
  drm/i915: Reorder context-close to avoid calling i915_vma_close() under RCU
  drm/i915: Move init_clock_gating() back to where it was
  drm/i915: Prune the reservation shared fence array
  drm/i915: Idle the GPU before shinking everything
  drm/i915: Lock llist_del_first() vs llist_del_all()
  drm/i915: Calculate ironlake intermediate watermarks correctly, v2.
  drm/i915: Disable lazy PPGTT page table optimization for vGPU
  drm/i915/execlists: Remove the priority "optimisation"
  drm/i915: Filter out spurious execlists context-switch interrupts
  drm/amdgpu: use irq-safe lock for kiq->ring_lock
  drm/amdgpu: bypass lru touch for KIQ ring submission
  drm/amdgpu: Potential uninitialized variable in amdgpu_vm_update_directories()
  drm/amdgpu: potential uninitialized variable in amdgpu_vce_ring_parse_cs()
  drm/amd/powerplay: initialize a variable before using it
  drm/amd/powerplay: suppress KASAN out of bounds warning in vega10_populate_all_memory_levels
  drm/amd/amdgpu: fix evicted VRAM bo adjudgement condition
  drm/vblank: Tune drm_crtc_accurate_vblank_count() WARN down to a debug
  drm/rockchip: add CONFIG_OF dependency for lvds
  ...

2 files changed, 72 insertions, 13 deletions

diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index a25f6c7..92ec663 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -133,6 +133,7 @@ int amd_sched_entity_init(struct amd_gpu_scheduler *sched,
 	entity->rq = rq;
 	entity->sched = sched;
 
+	spin_lock_init(&entity->rq_lock);
 	spin_lock_init(&entity->queue_lock);
 	r = kfifo_alloc(&entity->job_queue, jobs * sizeof(void *), GFP_KERNEL);
 	if (r)
@@ -204,18 +205,38 @@ static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity)
 void amd_sched_entity_fini(struct amd_gpu_scheduler *sched,
 			   struct amd_sched_entity *entity)
 {
-	struct amd_sched_rq *rq = entity->rq;
+	int r;
 
 	if (!amd_sched_entity_is_initialized(sched, entity))
 		return;
-
 	/**
 	 * The client will not queue more IBs during this fini, consume existing
-	 * queued IBs
+	 * queued IBs or discard them on SIGKILL
 	*/
-	wait_event(sched->job_scheduled, amd_sched_entity_is_idle(entity));
+	if ((current->flags & PF_SIGNALED) && current->exit_code == SIGKILL)
+		r = -ERESTARTSYS;
+	else
+		r = wait_event_killable(sched->job_scheduled,
+					amd_sched_entity_is_idle(entity));
+	amd_sched_entity_set_rq(entity, NULL);
+	if (r) {
+		struct amd_sched_job *job;
+
+		/* Park the kernel for a moment to make sure it isn't processing
+		 * our enity.
+		 */
+		kthread_park(sched->thread);
+		kthread_unpark(sched->thread);
+		while (kfifo_out(&entity->job_queue, &job, sizeof(job))) {
+			struct amd_sched_fence *s_fence = job->s_fence;
+			amd_sched_fence_scheduled(s_fence);
+			dma_fence_set_error(&s_fence->finished, -ESRCH);
+			amd_sched_fence_finished(s_fence);
+			dma_fence_put(&s_fence->finished);
+			sched->ops->free_job(job);
+		}
 
-	amd_sched_rq_remove_entity(rq, entity);
+	}
 	kfifo_free(&entity->job_queue);
 }
 
@@ -236,6 +257,24 @@ static void amd_sched_entity_clear_dep(struct dma_fence *f, struct dma_fence_cb
 	dma_fence_put(f);
 }
 
+void amd_sched_entity_set_rq(struct amd_sched_entity *entity,
+			     struct amd_sched_rq *rq)
+{
+	if (entity->rq == rq)
+		return;
+
+	spin_lock(&entity->rq_lock);
+
+	if (entity->rq)
+		amd_sched_rq_remove_entity(entity->rq, entity);
+
+	entity->rq = rq;
+	if (rq)
+		amd_sched_rq_add_entity(rq, entity);
+
+	spin_unlock(&entity->rq_lock);
+}
+
 bool amd_sched_dependency_optimized(struct dma_fence* fence,
 				    struct amd_sched_entity *entity)
 {
@@ -293,7 +332,7 @@ static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity)
 }
 
 static struct amd_sched_job *
-amd_sched_entity_pop_job(struct amd_sched_entity *entity)
+amd_sched_entity_peek_job(struct amd_sched_entity *entity)
 {
 	struct amd_gpu_scheduler *sched = entity->sched;
 	struct amd_sched_job *sched_job;
@@ -333,14 +372,15 @@ static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
 	/* first job wakes up scheduler */
 	if (first) {
 		/* Add the entity to the run queue */
+		spin_lock(&entity->rq_lock);
 		amd_sched_rq_add_entity(entity->rq, entity);
+		spin_unlock(&entity->rq_lock);
 		amd_sched_wakeup(sched);
 	}
 	return added;
 }
 
-/* job_finish is called after hw fence signaled, and
- * the job had already been deleted from ring_mirror_list
+/* job_finish is called after hw fence signaled
  */
 static void amd_sched_job_finish(struct work_struct *work)
 {
@@ -366,6 +406,7 @@ static void amd_sched_job_finish(struct work_struct *work)
 			schedule_delayed_work(&next->work_tdr, sched->timeout);
 	}
 	spin_unlock(&sched->job_list_lock);
+	dma_fence_put(&s_job->s_fence->finished);
 	sched->ops->free_job(s_job);
 }
 
@@ -381,6 +422,9 @@ static void amd_sched_job_begin(struct amd_sched_job *s_job)
 {
 	struct amd_gpu_scheduler *sched = s_job->sched;
 
+	dma_fence_add_callback(&s_job->s_fence->finished, &s_job->finish_cb,
+			       amd_sched_job_finish_cb);
+
 	spin_lock(&sched->job_list_lock);
 	list_add_tail(&s_job->node, &sched->ring_mirror_list);
 	if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
@@ -473,8 +517,6 @@ void amd_sched_entity_push_job(struct amd_sched_job *sched_job)
 	struct amd_sched_entity *entity = sched_job->s_entity;
 
 	trace_amd_sched_job(sched_job);
-	dma_fence_add_callback(&sched_job->s_fence->finished, &sched_job->finish_cb,
-			       amd_sched_job_finish_cb);
 	wait_event(entity->sched->job_scheduled,
 		   amd_sched_entity_in(sched_job));
 }
@@ -545,6 +587,7 @@ static void amd_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb)
 		container_of(cb, struct amd_sched_fence, cb);
 	struct amd_gpu_scheduler *sched = s_fence->sched;
 
+	dma_fence_get(&s_fence->finished);
 	atomic_dec(&sched->hw_rq_count);
 	amd_sched_fence_finished(s_fence);
 
@@ -585,7 +628,7 @@ static int amd_sched_main(void *param)
 		if (!entity)
 			continue;
 
-		sched_job = amd_sched_entity_pop_job(entity);
+		sched_job = amd_sched_entity_peek_job(entity);
 		if (!sched_job)
 			continue;
 
@@ -596,6 +639,7 @@ static int amd_sched_main(void *param)
 
 		fence = sched->ops->run_job(sched_job);
 		amd_sched_fence_scheduled(s_fence);
+
 		if (fence) {
 			s_fence->parent = dma_fence_get(fence);
 			r = dma_fence_add_callback(fence, &s_fence->cb,
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
index f9d8f28..52c8e54 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
@@ -39,6 +39,7 @@ struct amd_sched_rq;
 struct amd_sched_entity {
 	struct list_head		list;
 	struct amd_sched_rq		*rq;
+	spinlock_t			rq_lock;
 	struct amd_gpu_scheduler	*sched;
 
 	spinlock_t			queue_lock;
@@ -115,9 +116,14 @@ struct amd_sched_backend_ops {
 
 enum amd_sched_priority {
 	AMD_SCHED_PRIORITY_MIN,
-	AMD_SCHED_PRIORITY_NORMAL = AMD_SCHED_PRIORITY_MIN,
+	AMD_SCHED_PRIORITY_LOW = AMD_SCHED_PRIORITY_MIN,
+	AMD_SCHED_PRIORITY_NORMAL,
+	AMD_SCHED_PRIORITY_HIGH_SW,
+	AMD_SCHED_PRIORITY_HIGH_HW,
 	AMD_SCHED_PRIORITY_KERNEL,
-	AMD_SCHED_PRIORITY_MAX
+	AMD_SCHED_PRIORITY_MAX,
+	AMD_SCHED_PRIORITY_INVALID = -1,
+	AMD_SCHED_PRIORITY_UNSET = -2
 };
 
 /**
@@ -150,6 +156,8 @@ int amd_sched_entity_init(struct amd_gpu_scheduler *sched,
 void amd_sched_entity_fini(struct amd_gpu_scheduler *sched,
 			   struct amd_sched_entity *entity);
 void amd_sched_entity_push_job(struct amd_sched_job *sched_job);
+void amd_sched_entity_set_rq(struct amd_sched_entity *entity,
+			     struct amd_sched_rq *rq);
 
 int amd_sched_fence_slab_init(void);
 void amd_sched_fence_slab_fini(void);
@@ -167,4 +175,11 @@ void amd_sched_job_recovery(struct amd_gpu_scheduler *sched);
 bool amd_sched_dependency_optimized(struct dma_fence* fence,
 				    struct amd_sched_entity *entity);
 void amd_sched_job_kickout(struct amd_sched_job *s_job);
+
+static inline enum amd_sched_priority
+amd_sched_get_job_priority(struct amd_sched_job *job)
+{
+	return (job->s_entity->rq - job->sched->sched_rq);
+}
+
 #endif