drm/amdgpu: support ras on SRIOV

support umc/gfx/sdma ras on guest side

Changed from V1:
    move sriov judgment in amdgpu_ras_interrupt_fatal_error_handler

Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Stanley.Yang
2022-04-27 12:16:51 +08:00
committed by Alex Deucher
parent 2c270d3e71
commit 950d64250f
4 changed files with 43 additions and 14 deletions

View File

@@ -5219,6 +5219,10 @@ retry: /* Rest of adevs pre asic reset from XGMI hive. */
r = amdgpu_device_reset_sriov(adev, job ? false : true);
if (r)
adev->asic_reset_res = r;
/* Aldebaran supports ras in SRIOV, so need resume ras during reset */
if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2))
amdgpu_ras_resume(adev);
} else {
r = amdgpu_do_asic_reset(device_list_handle, &reset_context);
if (r && r == -EAGAIN)