1 files changed, 74 insertions, 22 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index e0a8890a62e2..a42763e1429d 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -72,7 +72,7 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
 	entity->num_sched_list = num_sched_list;
 	entity->priority = priority;
 	entity->sched_list = num_sched_list > 1 ? sched_list : NULL;
-	entity->last_scheduled = NULL;
+	RCU_INIT_POINTER(entity->last_scheduled, NULL);
 	RB_CLEAR_NODE(&entity->rb_tree_node);
 
 	if(num_sched_list)
@@ -140,11 +140,32 @@ bool drm_sched_entity_is_ready(struct drm_sched_entity *entity)
 	return true;
 }
 
+/**
+ * drm_sched_entity_error - return error of last scheduled job
+ * @entity: scheduler entity to check
+ *
+ * Opportunistically return the error of the last scheduled job. Result can
+ * change any time when new jobs are pushed to the hw.
+ */
+int drm_sched_entity_error(struct drm_sched_entity *entity)
+{
+	struct dma_fence *fence;
+	int r;
+
+	rcu_read_lock();
+	fence = rcu_dereference(entity->last_scheduled);
+	r = fence ? fence->error : 0;
+	rcu_read_unlock();
+
+	return r;
+}
+EXPORT_SYMBOL(drm_sched_entity_error);
+
 static void drm_sched_entity_kill_jobs_work(struct work_struct *wrk)
 {
 	struct drm_sched_job *job = container_of(wrk, typeof(*job), work);
 
-	drm_sched_fence_finished(job->s_fence);
+	drm_sched_fence_finished(job->s_fence, -ESRCH);
 	WARN_ON(job->s_fence->parent);
 	job->sched->ops->free_job(job);
 }
@@ -155,16 +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);
@@ -191,12 +228,12 @@ static void drm_sched_entity_kill(struct drm_sched_entity *entity)
 	/* Make sure this entity is not used by the scheduler at the moment */
 	wait_for_completion(&entity->entity_idle);
 
-	prev = dma_fence_get(entity->last_scheduled);
+	/* The entity is guaranteed to not be used by the scheduler */
+	prev = rcu_dereference_check(entity->last_scheduled, true);
+	dma_fence_get(prev);
 	while ((job = to_drm_sched_job(spsc_queue_pop(&entity->job_queue)))) {
 		struct drm_sched_fence *s_fence = job->s_fence;
 
-		dma_fence_set_error(&s_fence->finished, -ESRCH);
-
 		dma_fence_get(&s_fence->finished);
 		if (!prev || dma_fence_add_callback(prev, &job->finish_cb,
 					   drm_sched_entity_kill_jobs_cb))
@@ -280,8 +317,8 @@ void drm_sched_entity_fini(struct drm_sched_entity *entity)
 		entity->dependency = NULL;
 	}
 
-	dma_fence_put(entity->last_scheduled);
-	entity->last_scheduled = NULL;
+	dma_fence_put(rcu_dereference_check(entity->last_scheduled, true));
+	RCU_INIT_POINTER(entity->last_scheduled, NULL);
 }
 EXPORT_SYMBOL(drm_sched_entity_fini);
 
@@ -321,7 +358,7 @@ static void drm_sched_entity_wakeup(struct dma_fence *f,
 		container_of(cb, struct drm_sched_entity, cb);
 
 	drm_sched_entity_clear_dep(f, cb);
-	drm_sched_wakeup(entity->rq->sched);
+	drm_sched_wakeup_if_can_queue(entity->rq->sched);
 }
 
 /**
@@ -363,7 +400,7 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
 	}
 
 	s_fence = to_drm_sched_fence(fence);
-	if (s_fence && s_fence->sched == sched &&
+	if (!fence->error && s_fence && s_fence->sched == sched &&
 	    !test_bit(DRM_SCHED_FENCE_DONT_PIPELINE, &fence->flags)) {
 
 		/*
@@ -394,8 +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);
@@ -423,9 +469,9 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 	if (entity->guilty && atomic_read(entity->guilty))
 		dma_fence_set_error(&sched_job->s_fence->finished, -ECANCELED);
 
-	dma_fence_put(entity->last_scheduled);
-
-	entity->last_scheduled = dma_fence_get(&sched_job->s_fence->finished);
+	dma_fence_put(rcu_dereference_check(entity->last_scheduled, true));
+	rcu_assign_pointer(entity->last_scheduled,
+			   dma_fence_get(&sched_job->s_fence->finished));
 
 	/*
 	 * If the queue is empty we allow drm_sched_entity_select_rq() to
@@ -448,6 +494,12 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 			drm_sched_rq_update_fifo(entity, next->submit_ts);
 	}
 
+	/* Jobs and entities might have different lifecycles. Since we're
+	 * removing the job from the entities queue, set the jobs entity pointer
+	 * to NULL to prevent any future access of the entity through this job.
+	 */
+	sched_job->entity = NULL;
+
 	return sched_job;
 }
 
@@ -473,7 +525,7 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity)
 	 */
 	smp_rmb();
 
-	fence = entity->last_scheduled;
+	fence = rcu_dereference_check(entity->last_scheduled, true);
 
 	/* stay on the same engine if the previous job hasn't finished */
 	if (fence && !dma_fence_is_signaled(fence))
@@ -538,7 +590,7 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
 		if (drm_sched_policy == DRM_SCHED_POLICY_FIFO)
 			drm_sched_rq_update_fifo(entity, submit_ts);
 
-		drm_sched_wakeup(entity->rq->sched);
+		drm_sched_wakeup_if_can_queue(entity->rq->sched);
 	}
 }
 EXPORT_SYMBOL(drm_sched_entity_push_job);