drm/amdgpu: SRIOV flr_work should use down_write

Host initiated VF FLR may fail if someone else is
already holding a read_lock. Change from down_write_trylock
to down_write to guarantee the reset goes through.

Signed-off-by: Victor Skvortsov <[email protected]>
Reviewed by: Shaoyun.liu <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

Author: vskvorts

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

@@ -252,11 +252,12 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	 * otherwise the mailbox msg will be ruined/reseted by
 	 * the VF FLR.
 	 */
-	if (!down_write_trylock(&adev->reset_sem))
+	if (atomic_cmpxchg(&adev->in_gpu_reset, 0, 1) != 0)
 		return;
 
+	down_write(&adev->reset_sem);
+
 	amdgpu_virt_fini_data_exchange(adev);
-	atomic_set(&adev->in_gpu_reset, 1);
 
 	xgpu_ai_mailbox_trans_msg(adev, IDH_READY_TO_RESET, 0, 0, 0);
 

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

@@ -281,11 +281,12 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 	 * otherwise the mailbox msg will be ruined/reseted by
 	 * the VF FLR.
 	 */
-	if (!down_write_trylock(&adev->reset_sem))
+	if (atomic_cmpxchg(&adev->in_gpu_reset, 0, 1) != 0)
 		return;
 
+	down_write(&adev->reset_sem);
+
 	amdgpu_virt_fini_data_exchange(adev);
-	atomic_set(&adev->in_gpu_reset, 1);
 
 	xgpu_nv_mailbox_trans_msg(adev, IDH_READY_TO_RESET, 0, 0, 0);