drm/amdgpu: stop scheduler when calling hw_fini (v2)

This gurantees no more work on the ring can be submitted
to hardware in suspend/resume case, otherwise a potential
race will occur and the ring will get no chance to stay
empty before suspend.

v2: Call drm_sched_resubmit_job before drm_sched_start to
restart jobs from the pending list.

Suggested-by: Andrey Grodzovsky <[email protected]>
Suggested-by: Christian König <[email protected]>
Signed-off-by: Guchun Chen <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
Cc: [email protected]

Author: Guchun Chen

drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c

@@ -552,6 +552,9 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev)
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
 
+		if (!ring->no_scheduler)
+			drm_sched_stop(&ring->sched, NULL);
+
 		/* You can't wait for HW to signal if it's gone */
 		if (!drm_dev_is_unplugged(&adev->ddev))
 			r = amdgpu_fence_wait_empty(ring);
@@ -611,6 +614,11 @@ void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev)
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
 
+		if (!ring->no_scheduler) {
+			drm_sched_resubmit_jobs(&ring->sched);
+			drm_sched_start(&ring->sched, true);
+		}
+
 		/* enable the interrupt */
 		if (ring->fence_drv.irq_src)
 			amdgpu_irq_get(adev, ring->fence_drv.irq_src,