drm/amdgpu: Implement unrecoverable error message handling for VFs

This notification may arrive in VF mailbox while polling for response from
another event.

This patches covers the following scenarios:

- If VF is already in RMA state, then do not attempt to contact the host.
  Host will ignore the VF after sending the notification.

- If the notification is detected during polling, then set the RMA status,
  and return error to caller.

- If the notification arrives by interrupt, then set the RMA status and
  queue a reset.  This reset will fail and VF will stop runtime services.

Reviewed-by: Shravan Kumar Gande <Shravankumar.Gande@amd.com>
Signed-off-by: Victor Skvortsov <victor.skvortsov@amd.com>
Signed-off-by: Ellen Pan <yunru.pan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 14 insertions, 3 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index f2a74aa76b56..48101a34e049 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -324,6 +324,7 @@ static int xgpu_ai_mailbox_rcv_irq(struct amdgpu_device *adev,
 				   struct amdgpu_iv_entry *entry)
 {
 	enum idh_event event = xgpu_ai_mailbox_peek_msg(adev);
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
 	switch (event) {
 	case IDH_RAS_BAD_PAGES_NOTIFICATION:
@@ -331,12 +332,22 @@ static int xgpu_ai_mailbox_rcv_irq(struct amdgpu_device *adev,
 		if (amdgpu_sriov_runtime(adev))
 			schedule_work(&adev->virt.bad_pages_work);
 		break;
+	case IDH_UNRECOV_ERR_NOTIFICATION:
+		xgpu_ai_mailbox_send_ack(adev);
+		ras->is_rma = true;
+		dev_err(adev->dev, "VF is in an unrecoverable state. Runtime Services are halted.\n");
+		if (amdgpu_sriov_runtime(adev))
+			WARN_ONCE(!amdgpu_reset_domain_schedule(adev->reset_domain,
+					&adev->virt.flr_work),
+					"Failed to queue work! at %s",
+					__func__);
+		break;
 	case IDH_FLR_NOTIFICATION:
 		if (amdgpu_sriov_runtime(adev))
 			WARN_ONCE(!amdgpu_reset_domain_schedule(adev->reset_domain,
-								&adev->virt.flr_work),
-				  "Failed to queue work! at %s",
-				  __func__);
+						&adev->virt.flr_work),
+					"Failed to queue work! at %s",
+					__func__);
 		break;
 	case IDH_QUERY_ALIVE:
 		xgpu_ai_mailbox_send_ack(adev);