From: Tao Zhou Date: Wed, 31 Jul 2024 07:54:27 +0000 (+0800) Subject: drm/amdgpu: report bad status in GPU recovery X-Git-Tag: v6.12-rc1~126^2~17^2~201 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=b3a3c9a6b27b68310f1d4d486f47556808c7c855;p=thirdparty%2Fkernel%2Fstable.git 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 Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index f595ba6ba7c77..29a4adee92864 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -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));