1 files changed, 31 insertions, 4 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index f4f474944169..a2a953693b45 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -314,6 +314,7 @@ static void drm_sched_job_timedout(struct work_struct *work)
 {
 	struct drm_gpu_scheduler *sched;
 	struct drm_sched_job *job;
+	enum drm_gpu_sched_stat status = DRM_GPU_SCHED_STAT_NOMINAL;
 
 	sched = container_of(work, struct drm_gpu_scheduler, work_tdr.work);
 
@@ -331,7 +332,7 @@ static void drm_sched_job_timedout(struct work_struct *work)
 		list_del_init(&job->list);
 		spin_unlock(&sched->job_list_lock);
 
-		job->sched->ops->timedout_job(job);
+		status = job->sched->ops->timedout_job(job);
 
 		/*
 		 * Guilty job did complete and hence needs to be manually removed
@@ -345,9 +346,11 @@ static void drm_sched_job_timedout(struct work_struct *work)
 		spin_unlock(&sched->job_list_lock);
 	}
 
-	spin_lock(&sched->job_list_lock);
-	drm_sched_start_timeout(sched);
-	spin_unlock(&sched->job_list_lock);
+	if (status != DRM_GPU_SCHED_STAT_ENODEV) {
+		spin_lock(&sched->job_list_lock);
+		drm_sched_start_timeout(sched);
+		spin_unlock(&sched->job_list_lock);
+	}
 }
 
  /**
@@ -895,9 +898,33 @@ EXPORT_SYMBOL(drm_sched_init);
  */
 void drm_sched_fini(struct drm_gpu_scheduler *sched)
 {
+	struct drm_sched_entity *s_entity;
+	int i;
+
 	if (sched->thread)
 		kthread_stop(sched->thread);
 
+	for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
+		struct drm_sched_rq *rq = &sched->sched_rq[i];
+
+		if (!rq)
+			continue;
+
+		spin_lock(&rq->lock);
+		list_for_each_entry(s_entity, &rq->entities, list)
+			/*
+			 * Prevents reinsertion and marks job_queue as idle,
+			 * it will removed from rq in drm_sched_entity_fini
+			 * eventually
+			 */
+			s_entity->stopped = true;
+		spin_unlock(&rq->lock);
+
+	}
+
+	/* Wakeup everyone stuck in drm_sched_entity_flush for this scheduler */
+	wake_up_all(&sched->job_scheduled);
+
 	/* Confirm no work left behind accessing device structures */
 	cancel_delayed_work_sync(&sched->work_tdr);