Merge branch 'drm-next-4.15' of git://people.freedesktop.org/~agd5f/linux into drm-next

Last set of features for 4.15.  Highlights:
- Add a bo flag to allow buffers to opt out of implicit sync
- Add ctx priority setting interface
- Lots more powerplay cleanups
- Start to plumb through vram lost infrastructure for gpu reset
- ttm support for huge pages
- misc cleanups and bug fixes

* 'drm-next-4.15' of git://people.freedesktop.org/~agd5f/linux: (73 commits)
  drm/amd/powerplay: Place the constant on the right side of the test
  drm/amd/powerplay: Remove useless variable
  drm/amd/powerplay: Don't cast kzalloc() return value
  drm/amdgpu: allow GTT overcommit during bind
  drm/amdgpu: linear validate first then bind to GART
  drm/amd/pp: Fix overflow when setup decf/pix/disp dpm table.
  drm/amd/pp: thermal control not enabled on vega10.
  drm/amdgpu: busywait KIQ register accessing (v4)
  drm/amdgpu: report more amdgpu_fence_info
  drm/amdgpu:don't check soft_reset for sriov
  drm/amdgpu:fix duplicated setting job's vram_lost
  drm/amdgpu:reduce wb to 512 slot
  drm/amdgpu: fix regresstion on SR-IOV gpu reset failed
  drm/amd/powerplay: Tidy up cz_dpm_powerup_vce()
  drm/amd/powerplay: Tidy up cz_dpm_powerdown_vce()
  drm/amd/powerplay: Tidy up cz_dpm_update_vce_dpm()
  drm/amd/powerplay: Tidy up cz_dpm_update_uvd_dpm()
  drm/amd/powerplay: Tidy up cz_dpm_powerup_uvd()
  drm/amd/powerplay: Tidy up cz_dpm_powerdown_uvd()
  drm/amd/powerplay: Tidy up cz_start_dpm()
  ...

1 files changed, 24 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index 08e1332d814a..e4d3b4ec4e92 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)
@@ -204,7 +205,6 @@ 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))
@@ -218,7 +218,7 @@ void amd_sched_entity_fini(struct amd_gpu_scheduler *sched,
 	else
 		r = wait_event_killable(sched->job_scheduled,
 					amd_sched_entity_is_idle(entity));
-	amd_sched_rq_remove_entity(rq, entity);
+	amd_sched_entity_set_rq(entity, NULL);
 	if (r) {
 		struct amd_sched_job *job;
 
@@ -257,6 +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)
 {
@@ -354,7 +372,9 @@ 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;
@@ -386,6 +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);
 }
 
@@ -566,6 +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);
 
@@ -618,9 +640,6 @@ static int amd_sched_main(void *param)
 		fence = sched->ops->run_job(sched_job);
 		amd_sched_fence_scheduled(s_fence);
 
-		/* amd_sched_process_job drops the job's reference of the fence. */
-		sched_job->s_fence = NULL;
-
 		if (fence) {
 			s_fence->parent = dma_fence_get(fence);
 			r = dma_fence_add_callback(fence, &s_fence->cb,