bybrooklyn/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-05-02 13:32:40 -04:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: Implement unrecoverable error message handling for VFs

Browse Source 
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>
This commit is contained in:
Ellen Pan
2025-04-29 17:18:44 -04:00
committed by Alex Deucher
parent 6be34e1d1f
commit 086809c82c
5 changed files with 52 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
View File

@@ -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);