drm/scheduler: move last_sched fence updating prior to job popping (v2)

Make sure main thread won't update last_sched fence when entity
is cleanup.

Fix a racing issue which is caused by putting last_sched fence
twice. Running vulkaninfo in tight loop can produce this issue
as seeing wild fence pointer.

v2: squash in build fix (Christian)

Signed-off-by: Pixel Ding <Pixel.Ding@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Monk Liu <Monk.Liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index 4968867..088ff2b 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -402,6 +402,9 @@ drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 	if (entity->guilty && atomic_read(entity->guilty))
 		dma_fence_set_error(&sched_job->s_fence->finished, -ECANCELED);
 
+	dma_fence_put(entity->last_scheduled);
+	entity->last_scheduled = dma_fence_get(&sched_job->s_fence->finished);
+
 	spsc_queue_pop(&entity->job_queue);
 	return sched_job;
 }
@@ -715,9 +718,6 @@ static int drm_sched_main(void *param)
 		fence = sched->ops->run_job(sched_job);
 		drm_sched_fence_scheduled(s_fence);
 
-		dma_fence_put(entity->last_scheduled);
-		entity->last_scheduled = dma_fence_get(&s_fence->finished);
-
 		if (fence) {
 			s_fence->parent = dma_fence_get(fence);
 			r = dma_fence_add_callback(fence, &s_fence->cb,