From 471db2c2d4f80ee94225a1ef246e4f5011733e50 Mon Sep 17 00:00:00 2001 From: "Lin.Cao" Date: Thu, 15 May 2025 10:07:13 +0800 Subject: [PATCH] drm/scheduler: signal scheduled fence when kill job MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit When an entity from application B is killed, drm_sched_entity_kill() removes all jobs belonging to that entity through drm_sched_entity_kill_jobs_work(). If application A's job depends on a scheduled fence from application B's job, and that fence is not properly signaled during the killing process, application A's dependency cannot be cleared. This leads to application A hanging indefinitely while waiting for a dependency that will never be resolved. Fix this issue by ensuring that scheduled fences are properly signaled when an entity is killed, allowing dependent applications to continue execution. Signed-off-by: Lin.Cao Reviewed-by: Philipp Stanner Signed-off-by: Christian König Link: https://lore.kernel.org/r/20250515020713.1110476-1-lincao12@amd.com --- drivers/gpu/drm/scheduler/sched_entity.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index bd39db7bb240..e671aa241720 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -176,6 +176,7 @@ 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_scheduled(job->s_fence, NULL); drm_sched_fence_finished(job->s_fence, -ESRCH); WARN_ON(job->s_fence->parent); job->sched->ops->free_job(job); -- 2.25.1