[PATCH v2] Revert "drm/scheduler: Avoid accessing freed bad job."

[Jingwen Chen]

[Why]
for bailing job, this commit will delete it from pending list thus the
bailing job will never have a chance to be resubmitted even in advance
tdr mode.

[How]
after embeded hw_fence into amdgpu_job is done, the race condition that
this commit tries to work around is completely solved.So revert this
commit.
This reverts commit 135517d3565b48f4def3b1b82008bc17eb5d1c90.
v2:
add dma_fence_get/put() around timedout_job to avoid concurrent delete
during processing timedout_job

Signed-off-by: Jingwen Chen <Jingwen.Chen2 at amd.com>
---
 drivers/gpu/drm/scheduler/sched_main.c | 23 +++++------------------
 1 file changed, 5 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index a2a953693b45..f9b9b3aefc4a 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;
+	struct dma_fence *fence;
 	enum drm_gpu_sched_stat status = DRM_GPU_SCHED_STAT_NOMINAL;
 
 	sched = container_of(work, struct drm_gpu_scheduler, work_tdr.work);
@@ -325,11 +326,10 @@ static void drm_sched_job_timedout(struct work_struct *work)
 
 	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.
+		 * Get job->s_fence->parent here to avoid concurrent delete during
+		 * processing timedout_job
 		 */
-		list_del_init(&job->list);
+		fence = dma_fence_get(job->s_fence->parent);
 		spin_unlock(&sched->job_list_lock);
 
 		status = job->sched->ops->timedout_job(job);
@@ -342,6 +342,7 @@ static void drm_sched_job_timedout(struct work_struct *work)
 			job->sched->ops->free_job(job);
 			sched->free_guilty = false;
 		}
+		dma_fence_put(fence);
 	} else {
 		spin_unlock(&sched->job_list_lock);
 	}
@@ -392,20 +393,6 @@ 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->list, &sched->pending_list);
-
 	/*
 	 * Iterate the job list from later to  earlier one and either deactive
 	 * their HW callbacks or remove them from pending list if they already
-- 
2.25.1