diff options
| author | Lijo Lazar <[email protected]> | 2024-12-09 03:44:53 +0000 |
|---|---|---|
| committer | Alex Deucher <[email protected]> | 2024-12-11 22:30:59 +0000 |
| commit | fccb446f82b9155c05758d1fa30af4a06494e0ec (patch) | |
| tree | 6c5f95e1fa748135a58d153abc208d4f91ed7a6b /drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | |
| parent | drm/amdgpu/sdma7: implement queue reset callback for sdma7 (diff) | |
| download | kernel-fccb446f82b9155c05758d1fa30af4a06494e0ec.tar.gz kernel-fccb446f82b9155c05758d1fa30af4a06494e0ec.zip | |
drm/amdgpu: Avoid VF for RAS recovery source check
VF device sets the RAS flag when mailbox data can't be read properly.
There is no conclusive way to tell if the real source is RAS error.
Therefore VF schedules a KFD based reset which doesn't set RAS source.
SKip checking RAS source for any VF scheduled recovery.
Signed-off-by: Lijo Lazar <[email protected]>
Reported-by: Vojislav Tomasevic <[email protected]>
Reviewed-by: Yiqing Yao <[email protected]>
Tested-by: Yiqing Yao <[email protected]>
Fixes: e1ee2111ca48 ("drm/amdgpu: Prefer RAS recovery for scheduler hang")
Signed-off-by: Alex Deucher <[email protected]>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_device.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 144295da9e4c..e22fc7a8101f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5866,6 +5866,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, * detected at the same time, let RAS recovery take care of it. */ if (amdgpu_ras_is_err_state(adev, AMDGPU_RAS_BLOCK__ANY) && + !amdgpu_sriov_vf(adev) && reset_context->src != AMDGPU_RESET_SRC_RAS) { dev_dbg(adev->dev, "Gpu recovery from source: %d yielding to RAS error recovery handling", |