diff options
| author | Dave Airlie <airlied@redhat.com> | 2020-04-10 06:42:52 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2020-04-10 06:42:53 +1000 |
| commit | 74bd4f0c921cc9cf5f99ba4129dafe35496de6f3 (patch) | |
| tree | 45f17b3da19fca4f6fdc2d12f702da6c4a0e6268 /drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | |
| parent | 1287c880ba45924ab41166cdf02766b2e3ac9d56 (diff) | |
| parent | 7e7ea24f0b46cd3078bc9af29d1c1aced89d1c8e (diff) | |
Merge tag 'amd-drm-fixes-5.7-2020-04-08' of git://people.freedesktop.org/~agd5f/linux into drm-next
amd-drm-fixes-5.7-2020-04-08:
amdgpu:
- Various Renoir fixes
- Fix gfx clockgating sequence on gfx10
- RAS fixes
- Avoid MST property creation after registration
- Various cursor/viewport fixes
- Fix a confusing log message about optional firmwares
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200408222240.3942-1-alexander.deucher@amd.com
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 20 |
1 files changed, 15 insertions, 5 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 3c32a94d2424..ab379b44679c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1424,12 +1424,22 @@ static void amdgpu_ras_do_recovery(struct work_struct *work) { struct amdgpu_ras *ras = container_of(work, struct amdgpu_ras, recovery_work); + struct amdgpu_device *remote_adev = NULL; + struct amdgpu_device *adev = ras->adev; + struct list_head device_list, *device_list_handle = NULL; + struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, false); + + /* Build list of devices to query RAS related errors */ + if (hive && adev->gmc.xgmi.num_physical_nodes > 1) { + device_list_handle = &hive->device_list; + } else { + list_add_tail(&adev->gmc.xgmi.head, &device_list); + device_list_handle = &device_list; + } - /* - * Query and print non zero error counter per IP block for - * awareness before recovering GPU. - */ - amdgpu_ras_log_on_err_counter(ras->adev); + list_for_each_entry(remote_adev, device_list_handle, gmc.xgmi.head) { + amdgpu_ras_log_on_err_counter(remote_adev); + } if (amdgpu_device_should_recover_gpu(ras->adev)) amdgpu_device_gpu_recover(ras->adev, 0); |