drm/amdgpu:fix random missing of FLR NOTIFY

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 11 insertions, 3 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index c32d0b0868e8..d31259e5bb45 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -282,9 +282,17 @@ static int xgpu_ai_mailbox_rcv_irq(struct amdgpu_device *adev,
                 /* see what event we get */
                 r = xgpu_ai_mailbox_rcv_msg(adev, IDH_FLR_NOTIFICATION);
 
-                /* only handle FLR_NOTIFY now */
-                if (!r)
-                        schedule_work(&adev->virt.flr_work);
+                /* sometimes the interrupt is delayed to inject to VM, so under such case
+                 * the IDH_FLR_NOTIFICATION is overwritten by VF FLR from GIM side, thus
+                 * above recieve message could be failed, we should schedule the flr_work
+                 * anyway
+                 */
+                if (r) {
+                        DRM_ERROR("FLR_NOTIFICATION is missed\n");
+                        xgpu_ai_mailbox_send_ack(adev);
+                }
+
+                schedule_work(&adev->virt.flr_work);
         }
 
         return 0;