1 files changed, 31 insertions, 2 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 3c57e84222ca..71ce6215956f 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -92,6 +92,7 @@ void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
 	if (!list_empty(&entity->list))
 		return;
 	spin_lock(&rq->lock);
+	atomic_inc(&rq->sched->score);
 	list_add_tail(&entity->list, &rq->entities);
 	spin_unlock(&rq->lock);
 }
@@ -110,6 +111,7 @@ void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
 	if (list_empty(&entity->list))
 		return;
 	spin_lock(&rq->lock);
+	atomic_dec(&rq->sched->score);
 	list_del_init(&entity->list);
 	if (rq->current_entity == entity)
 		rq->current_entity = NULL;
@@ -287,10 +289,21 @@ static void drm_sched_job_timedout(struct work_struct *work)
 	unsigned long flags;
 
 	sched = container_of(work, struct drm_gpu_scheduler, work_tdr.work);
+
+	/* Protects against concurrent deletion in drm_sched_get_cleanup_job */
+	spin_lock_irqsave(&sched->job_list_lock, flags);
 	job = list_first_entry_or_null(&sched->ring_mirror_list,
 				       struct drm_sched_job, node);
 
 	if (job) {
+		/*
+		 * Remove the bad job so it cannot be freed by concurrent
+		 * drm_sched_cleanup_jobs. It will be reinserted back after sched->thread
+		 * is parked at which point it's safe.
+		 */
+		list_del_init(&job->node);
+		spin_unlock_irqrestore(&sched->job_list_lock, flags);
+
 		job->sched->ops->timedout_job(job);
 
 		/*
@@ -301,6 +314,8 @@ static void drm_sched_job_timedout(struct work_struct *work)
 			job->sched->ops->free_job(job);
 			sched->free_guilty = false;
 		}
+	} else {
+		spin_unlock_irqrestore(&sched->job_list_lock, flags);
 	}
 
 	spin_lock_irqsave(&sched->job_list_lock, flags);
@@ -373,6 +388,20 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
 	kthread_park(sched->thread);
 
 	/*
+	 * Reinsert back the bad job here - now it's safe as
+	 * drm_sched_get_cleanup_job cannot race against us and release the
+	 * bad job at this point - we parked (waited for) any in progress
+	 * (earlier) cleanups and drm_sched_get_cleanup_job will not be called
+	 * now until the scheduler thread is unparked.
+	 */
+	if (bad && bad->sched == sched)
+		/*
+		 * Add at the head of the queue to reflect it was the earliest
+		 * job extracted.
+		 */
+		list_add(&bad->node, &sched->ring_mirror_list);
+
+	/*
 	 * Iterate the job list from later to  earlier one and either deactive
 	 * their HW callbacks or remove them from mirror list if they already
 	 * signaled.
@@ -628,7 +657,7 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb)
 	struct drm_gpu_scheduler *sched = s_fence->sched;
 
 	atomic_dec(&sched->hw_rq_count);
-	atomic_dec(&sched->num_jobs);
+	atomic_dec(&sched->score);
 
 	trace_drm_sched_process_job(s_fence);
 
@@ -803,7 +832,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 	spin_lock_init(&sched->job_list_lock);
 	atomic_set(&sched->hw_rq_count, 0);
 	INIT_DELAYED_WORK(&sched->work_tdr, drm_sched_job_timedout);
-	atomic_set(&sched->num_jobs, 0);
+	atomic_set(&sched->score, 0);
 	atomic64_set(&sched->job_id_count, 0);
 
 	/* Each scheduler will run on a seperate kernel thread */