drm/amdgpu: report bad status in GPU recovery

Instead of printing GPU reset failed.

v2: add check for reset_context->src.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Tao Zhou 2024-07-31 15:54:27 +08:00 committed by Alex Deucher
parent dd3e296289
commit b3a3c9a6b2

View File

@ -5876,8 +5876,14 @@ skip_hw_reset:
tmp_adev->asic_reset_res = 0;
if (r) {
/* bad news, how to tell it to userspace ? */
dev_info(tmp_adev->dev, "GPU reset(%d) failed\n", atomic_read(&tmp_adev->gpu_reset_counter));
/* bad news, how to tell it to userspace ?
* for ras error, we should report GPU bad status instead of
* reset failure
*/
if (reset_context->src != AMDGPU_RESET_SRC_RAS ||
!amdgpu_ras_eeprom_check_err_threshold(tmp_adev))
dev_info(tmp_adev->dev, "GPU reset(%d) failed\n",
atomic_read(&tmp_adev->gpu_reset_counter));
amdgpu_vf_error_put(tmp_adev, AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r);
} else {
dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n", atomic_read(&tmp_adev->gpu_reset_counter));