drm/scheduler: fix fence ref counting

We leaked dependency fences when processes were beeing killed.

Additional to that grab a reference to the last scheduled fence.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220929180151.139751-1-christian.koenig@amd.com

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 6137537aaea4df7db983da2bbcf9700bc49ca2f1..4b913dbb7d7b6bc8899afc6a5b2b201d64771e5a 100644 (file)
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -207,6 +207,7 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
        struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
                                                 finish_cb);
 
+       dma_fence_put(f);
        INIT_WORK(&job->work, drm_sched_entity_kill_jobs_work);
        schedule_work(&job->work);
 }
@@ -234,8 +235,10 @@ static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity)
                struct drm_sched_fence *s_fence = job->s_fence;
 
                /* Wait for all dependencies to avoid data corruptions */
-               while ((f = drm_sched_job_dependency(job, entity)))
+               while ((f = drm_sched_job_dependency(job, entity))) {
                        dma_fence_wait(f, false);
+                       dma_fence_put(f);
+               }
 
                drm_sched_fence_scheduled(s_fence);
                dma_fence_set_error(&s_fence->finished, -ESRCH);
@@ -250,6 +253,7 @@ static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity)
                        continue;
                }
 
+               dma_fence_get(entity->last_scheduled);
                r = dma_fence_add_callback(entity->last_scheduled,
                                           &job->finish_cb,
                                           drm_sched_entity_kill_jobs_cb);