1 files changed, 36 insertions, 31 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index e2cda28a1af4..46119aacb809 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -349,37 +349,16 @@ static void drm_sched_run_job_queue(struct drm_gpu_scheduler *sched)
 }
 
 /**
- * __drm_sched_run_free_queue - enqueue free-job work
+ * drm_sched_run_free_queue - enqueue free-job work
  * @sched: scheduler instance
  */
-static void __drm_sched_run_free_queue(struct drm_gpu_scheduler *sched)
+static void drm_sched_run_free_queue(struct drm_gpu_scheduler *sched)
 {
 	if (!READ_ONCE(sched->pause_submit))
 		queue_work(sched->submit_wq, &sched->work_free_job);
 }
 
 /**
- * drm_sched_run_free_queue - enqueue free-job work if ready
- * @sched: scheduler instance
- */
-static void drm_sched_run_free_queue(struct drm_gpu_scheduler *sched)
-{
-	struct drm_sched_job *job;
-
-	job = list_first_entry_or_null(&sched->pending_list,
-				       struct drm_sched_job, list);
-	if (job && dma_fence_is_signaled(&job->s_fence->finished))
-		__drm_sched_run_free_queue(sched);
-}
-
-static void drm_sched_run_free_queue_unlocked(struct drm_gpu_scheduler *sched)
-{
-	spin_lock(&sched->job_list_lock);
-	drm_sched_run_free_queue(sched);
-	spin_unlock(&sched->job_list_lock);
-}
-
-/**
  * drm_sched_job_done - complete a job
  * @s_job: pointer to the job which is done
  *
@@ -398,7 +377,7 @@ static void drm_sched_job_done(struct drm_sched_job *s_job, int result)
 	dma_fence_get(&s_fence->finished);
 	drm_sched_fence_finished(s_fence, result);
 	dma_fence_put(&s_fence->finished);
-	__drm_sched_run_free_queue(sched);
+	drm_sched_run_free_queue(sched);
 }
 
 /**
@@ -1134,12 +1113,16 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
  * drm_sched_get_finished_job - fetch the next finished job to be destroyed
  *
  * @sched: scheduler instance
+ * @have_more: are there more finished jobs on the list
+ *
+ * Informs the caller through @have_more whether there are more finished jobs
+ * besides the returned one.
  *
  * Returns the next finished job from the pending list (if there is one)
  * ready for it to be destroyed.
  */
 static struct drm_sched_job *
-drm_sched_get_finished_job(struct drm_gpu_scheduler *sched)
+drm_sched_get_finished_job(struct drm_gpu_scheduler *sched, bool *have_more)
 {
 	struct drm_sched_job *job, *next;
 
@@ -1147,22 +1130,25 @@ drm_sched_get_finished_job(struct drm_gpu_scheduler *sched)
 
 	job = list_first_entry_or_null(&sched->pending_list,
 				       struct drm_sched_job, list);
-
 	if (job && dma_fence_is_signaled(&job->s_fence->finished)) {
 		/* remove job from pending_list */
 		list_del_init(&job->list);
 
 		/* cancel this job's TO timer */
 		cancel_delayed_work(&sched->work_tdr);
-		/* make the scheduled timestamp more accurate */
+
+		*have_more = false;
 		next = list_first_entry_or_null(&sched->pending_list,
 						typeof(*next), list);
-
 		if (next) {
+			/* make the scheduled timestamp more accurate */
 			if (test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT,
 				     &next->s_fence->scheduled.flags))
 				next->s_fence->scheduled.timestamp =
 					dma_fence_timestamp(&job->s_fence->finished);
+
+			*have_more = dma_fence_is_signaled(&next->s_fence->finished);
+
 			/* start TO timer for next job */
 			drm_sched_start_timeout(sched);
 		}
@@ -1221,12 +1207,15 @@ static void drm_sched_free_job_work(struct work_struct *w)
 	struct drm_gpu_scheduler *sched =
 		container_of(w, struct drm_gpu_scheduler, work_free_job);
 	struct drm_sched_job *job;
+	bool have_more;
 
-	job = drm_sched_get_finished_job(sched);
-	if (job)
+	job = drm_sched_get_finished_job(sched, &have_more);
+	if (job) {
 		sched->ops->free_job(job);
+		if (have_more)
+			drm_sched_run_free_queue(sched);
+	}
 
-	drm_sched_run_free_queue_unlocked(sched);
 	drm_sched_run_job_queue(sched);
 }
 
@@ -1435,6 +1424,22 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched)
 			 * Prevents reinsertion and marks job_queue as idle,
 			 * it will be removed from the rq in drm_sched_entity_fini()
 			 * eventually
+			 *
+			 * FIXME:
+			 * This lacks the proper spin_lock(&s_entity->lock) and
+			 * is, therefore, a race condition. Most notably, it
+			 * can race with drm_sched_entity_push_job(). The lock
+			 * cannot be taken here, however, because this would
+			 * lead to lock inversion -> deadlock.
+			 *
+			 * The best solution probably is to enforce the life
+			 * time rule of all entities having to be torn down
+			 * before their scheduler. Then, however, locking could
+			 * be dropped alltogether from this function.
+			 *
+			 * For now, this remains a potential race in all
+			 * drivers that keep entities alive for longer than
+			 * the scheduler.
 			 */
 			s_entity->stopped = true;
 		spin_unlock(&rq->lock);