From f5ee8a39f03e51a17c42f93708f9d3251519988c Mon Sep 17 00:00:00 2001 From: "Lin.Cao" Date: Thu, 17 Jul 2025 16:44:53 +0800 Subject: [PATCH] drm/sched: Remove optimization that causes hang when killing dependent jobs MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit commit 15f77764e90a713ee3916ca424757688e4f565b9 upstream. 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: 777dbd458c89 ("drm/amdgpu: drop a dummy wakeup scheduler") Cc: stable@vger.kernel.org # v4.6+ Signed-off-by: Lin.Cao Reviewed-by: Christian König Signed-off-by: Philipp Stanner Link: https://lore.kernel.org/r/20250717084453.921097-1-lincao12@amd.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/scheduler/sched_entity.c | 21 ++------------------- 1 file changed, 2 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index c9c50e3b18a2..3e75fc1f6607 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -368,17 +368,6 @@ 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 @@ -389,7 +378,8 @@ 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); } @@ -442,13 +432,6 @@ 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, -- 2.47.2