3 files changed, 59 insertions, 25 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index b2bbc8a68b30..a42763e1429d 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -176,16 +176,32 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
 {
 	struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
 						 finish_cb);
-	int r;
+	unsigned long index;
 
 	dma_fence_put(f);
 
 	/* Wait for all dependencies to avoid data corruptions */
-	while (!xa_empty(&job->dependencies)) {
-		f = xa_erase(&job->dependencies, job->last_dependency++);
-		r = dma_fence_add_callback(f, &job->finish_cb,
-					   drm_sched_entity_kill_jobs_cb);
-		if (!r)
+	xa_for_each(&job->dependencies, index, f) {
+		struct drm_sched_fence *s_fence = to_drm_sched_fence(f);
+
+		if (s_fence && f == &s_fence->scheduled) {
+			/* The dependencies array had a reference on the scheduled
+			 * fence, and the finished fence refcount might have
+			 * dropped to zero. Use dma_fence_get_rcu() so we get
+			 * a NULL fence in that case.
+			 */
+			f = dma_fence_get_rcu(&s_fence->finished);
+
+			/* Now that we have a reference on the finished fence,
+			 * we can release the reference the dependencies array
+			 * had on the scheduled fence.
+			 */
+			dma_fence_put(&s_fence->scheduled);
+		}
+
+		xa_erase(&job->dependencies, index);
+		if (f && !dma_fence_add_callback(f, &job->finish_cb,
+						 drm_sched_entity_kill_jobs_cb))
 			return;
 
 		dma_fence_put(f);
@@ -415,8 +431,17 @@ static struct dma_fence *
 drm_sched_job_dependency(struct drm_sched_job *job,
 			 struct drm_sched_entity *entity)
 {
-	if (!xa_empty(&job->dependencies))
-		return xa_erase(&job->dependencies, job->last_dependency++);
+	struct dma_fence *f;
+
+	/* We keep the fence around, so we can iterate over all dependencies
+	 * in drm_sched_entity_kill_jobs_cb() to ensure all deps are signaled
+	 * before killing the job.
+	 */
+	f = xa_load(&job->dependencies, job->last_dependency);
+	if (f) {
+		job->last_dependency++;
+		return dma_fence_get(f);
+	}
 
 	if (job->sched->ops->prepare_job)
 		return job->sched->ops->prepare_job(job, entity);
diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c
index ef120475e7c6..06cedfe4b486 100644
--- a/drivers/gpu/drm/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/scheduler/sched_fence.c
@@ -48,8 +48,32 @@ static void __exit drm_sched_fence_slab_fini(void)
 	kmem_cache_destroy(sched_fence_slab);
 }
 
-void drm_sched_fence_scheduled(struct drm_sched_fence *fence)
+static void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence,
+				       struct dma_fence *fence)
 {
+	/*
+	 * smp_store_release() to ensure another thread racing us
+	 * in drm_sched_fence_set_deadline_finished() sees the
+	 * fence's parent set before test_bit()
+	 */
+	smp_store_release(&s_fence->parent, dma_fence_get(fence));
+	if (test_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT,
+		     &s_fence->finished.flags))
+		dma_fence_set_deadline(fence, s_fence->deadline);
+}
+
+void drm_sched_fence_scheduled(struct drm_sched_fence *fence,
+			       struct dma_fence *parent)
+{
+	/* Set the parent before signaling the scheduled fence, such that,
+	 * any waiter expecting the parent to be filled after the job has
+	 * been scheduled (which is the case for drivers delegating waits
+	 * to some firmware) doesn't have to busy wait for parent to show
+	 * up.
+	 */
+	if (!IS_ERR_OR_NULL(parent))
+		drm_sched_fence_set_parent(fence, parent);
+
 	dma_fence_signal(&fence->scheduled);
 }
 
@@ -181,20 +205,6 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f)
 }
 EXPORT_SYMBOL(to_drm_sched_fence);
 
-void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence,
-				struct dma_fence *fence)
-{
-	/*
-	 * smp_store_release() to ensure another thread racing us
-	 * in drm_sched_fence_set_deadline_finished() sees the
-	 * fence's parent set before test_bit()
-	 */
-	smp_store_release(&s_fence->parent, dma_fence_get(fence));
-	if (test_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT,
-		     &s_fence->finished.flags))
-		dma_fence_set_deadline(fence, s_fence->deadline);
-}
-
 struct drm_sched_fence *drm_sched_fence_alloc(struct drm_sched_entity *entity,
 					      void *owner)
 {
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 7b2bfc10c1a5..506371c42745 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -1043,10 +1043,9 @@ static int drm_sched_main(void *param)
 		trace_drm_run_job(sched_job, entity);
 		fence = sched->ops->run_job(sched_job);
 		complete_all(&entity->entity_idle);
-		drm_sched_fence_scheduled(s_fence);
+		drm_sched_fence_scheduled(s_fence, fence);
 
 		if (!IS_ERR_OR_NULL(fence)) {
-			drm_sched_fence_set_parent(s_fence, fence);
 			/* Drop for original kref_init of the fence */
 			dma_fence_put(fence);