drm/sched: Remove optimization that causes hang when killing dependent jobs

[ Upstream commit 15f77764e9 ]

When application A submits jobs and application B submits a job with a
dependency on A's fence, the normal flow wakes up the scheduler after
processing each job. However, the optimization in
drm_sched_entity_add_dependency_cb() uses a callback that only clears
dependencies without waking up the scheduler.

When application A is killed before its jobs can run, the callback gets
triggered but only clears the dependency without waking up the scheduler,
causing the scheduler to enter sleep state and application B to hang.

Remove the optimization by deleting drm_sched_entity_clear_dep() and its
usage, ensuring the scheduler is always woken up when dependencies are
cleared.

Fixes: 777dbd458c ("drm/amdgpu: drop a dummy wakeup scheduler")
Cc: stable@vger.kernel.org # v4.6+
Signed-off-by: Lin.Cao <lincao12@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Philipp Stanner <phasta@kernel.org>
Link: https://lore.kernel.org/r/20250717084453.921097-1-lincao12@amd.com
[ Changed drm_sched_wakeup_if_can_queue() calls to drm_sched_wakeup() ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Lin.Cao 2025-07-29 12:16:38 -04:00 committed by Greg Kroah-Hartman
parent 7c5a13c76d
commit 6188d61ba7

View File

@ -317,21 +317,8 @@ void drm_sched_entity_destroy(struct drm_sched_entity *entity)
EXPORT_SYMBOL(drm_sched_entity_destroy);
/*
* drm_sched_entity_clear_dep - callback to clear the entities dependency
*/
static void drm_sched_entity_clear_dep(struct dma_fence *f,
struct dma_fence_cb *cb)
{
struct drm_sched_entity *entity =
container_of(cb, struct drm_sched_entity, cb);
entity->dependency = NULL;
dma_fence_put(f);
}
/*
* drm_sched_entity_clear_dep - callback to clear the entities dependency and
* wake up scheduler
* drm_sched_entity_wakeup - callback to clear the entity's dependency and
* wake up the scheduler
*/
static void drm_sched_entity_wakeup(struct dma_fence *f,
struct dma_fence_cb *cb)
@ -339,7 +326,8 @@ static void drm_sched_entity_wakeup(struct dma_fence *f,
struct drm_sched_entity *entity =
container_of(cb, struct drm_sched_entity, cb);
drm_sched_entity_clear_dep(f, cb);
entity->dependency = NULL;
dma_fence_put(f);
drm_sched_wakeup(entity->rq->sched);
}
@ -395,13 +383,6 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
fence = dma_fence_get(&s_fence->scheduled);
dma_fence_put(entity->dependency);
entity->dependency = fence;
if (!dma_fence_add_callback(fence, &entity->cb,
drm_sched_entity_clear_dep))
return true;
/* Ignore it when it is already scheduled */
dma_fence_put(fence);
return false;
}
if (!dma_fence_add_callback(entity->dependency, &entity->cb,