drm/amdgpu: fix race condition in amd_sched_entity_push_job

As soon as we leave the spinlock after the job has been added to the job
queue, we can no longer rely on the job's data to be available.

I have seen a null-pointer dereference due to sched == NULL in
amd_sched_wakeup via amd_sched_entity_push_job and
amd_sched_ib_submit_kernel_helper. Since the latter initializes
sched_job->sched with the address of the ring scheduler, which is
guaranteed to be non-NULL, this race appears to be a likely culprit.

Signed-off-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Bugzilla: https://bugs.freedesktop.org/attachment.cgi?bugid=93079
Reviewed-by: Christian König <christian.koenig@amd.com>

1 files changed, 3 insertions, 2 deletions

diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index 651129f2ec1d..3a4820e863ec 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -288,6 +288,7 @@ amd_sched_entity_pop_job(struct amd_sched_entity *entity)
  */
 static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
 {
+        struct amd_gpu_scheduler *sched = sched_job->sched;
         struct amd_sched_entity *entity = sched_job->s_entity;
         bool added, first = false;
 
@@ -302,7 +303,7 @@ static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
 
         /* first job wakes up scheduler */
         if (first)
-                amd_sched_wakeup(sched_job->sched);
+                amd_sched_wakeup(sched);
 
         return added;
 }
@@ -318,9 +319,9 @@ void amd_sched_entity_push_job(struct amd_sched_job *sched_job)
 {
         struct amd_sched_entity *entity = sched_job->s_entity;
 
+        trace_amd_sched_job(sched_job);
         wait_event(entity->sched->job_scheduled,
                    amd_sched_entity_in(sched_job));
-        trace_amd_sched_job(sched_job);
 }
 
 /**