drm/sched: Fix racy access to drm_sched_entity.dependency

The drm_sched_job_unschedulable trace point can access
entity->dependency after it was cleared by the callback
installed in drm_sched_entity_add_dependency_cb, causing:

BUG: kernel NULL pointer dereference, address: 0000000000000020
[...]
Workqueue: comp_1.1.0 drm_sched_run_job_work [gpu_sched]
RIP: 0010:trace_event_raw_event_drm_sched_job_unschedulable+0x70/0xd0 [gpu_sched]

To fix this we either need to keep a reference to the fence before
setting up the callbacks, or move the trace_drm_sched_job_unschedulable
calls into drm_sched_entity_add_dependency_cb where they can be
done earlier.

Fixes: 76d97c870f29 ("drm/sched: Trace dependencies for GPU jobs")
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Philipp Stanner <phasta@kernel.org>
Link: https://lore.kernel.org/r/20250901124032.1955-1-pierre-eric.pelloux-prayer@amd.com
(cherry picked from commit b2b8af21fec35be417a3199b5a6c354605dd222a)
Signed-off-by: Maxime Ripard <mripard@kernel.org>

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 8867b95ab089ce6f8df5f3c42df7f42c7820e868..3d06f72531ba24c604bb097589a6691d7643a6f2 100644 (file)
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -391,7 +391,8 @@ EXPORT_SYMBOL(drm_sched_entity_set_priority);
  * Add a callback to the current dependency of the entity to wake up the
  * scheduler when the entity becomes available.
  */
-static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
+static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity,
+                                              struct drm_sched_job *sched_job)
 {
        struct drm_gpu_scheduler *sched = entity->rq->sched;
        struct dma_fence *fence = entity->dependency;
@@ -421,6 +422,10 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
                entity->dependency = fence;
        }
 
+       if (trace_drm_sched_job_unschedulable_enabled() &&
+           !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &entity->dependency->flags))
+               trace_drm_sched_job_unschedulable(sched_job, entity->dependency);
+
        if (!dma_fence_add_callback(entity->dependency, &entity->cb,
                                    drm_sched_entity_wakeup))
                return true;
@@ -461,10 +466,8 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 
        while ((entity->dependency =
                        drm_sched_job_dependency(sched_job, entity))) {
-               if (drm_sched_entity_add_dependency_cb(entity)) {
-                       trace_drm_sched_job_unschedulable(sched_job, entity->dependency);
+               if (drm_sched_entity_add_dependency_cb(entity, sched_job))
                        return NULL;
-               }
        }
 
        /* skip jobs from entity that marked guilty */