drm_sched_job_init() is just racing when checking an entity's runqueue, without taking the proper spinlock.
Add the lock.
Cc: stable@vger.kernel.org # 6.7+ Fixes: 56e449603f0a ("drm/sched: Convert the GPU scheduler to variable number of run-queues") Signed-off-by: Philipp Stanner phasta@kernel.org --- drivers/gpu/drm/scheduler/sched_main.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 7f938f491b6f..30028054385f 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -799,7 +799,12 @@ int drm_sched_job_init(struct drm_sched_job *job, u32 credits, void *owner, uint64_t drm_client_id) { - if (!entity->rq) { + struct drm_sched_rq *rq; + + spin_lock(&entity->lock); + rq = entity->rq; + spin_unlock(&entity->lock); + if (!rq) { /* This will most likely be followed by missing frames * or worse--a blank screen--leave a trail in the * logs, so this can be debugged easier.