drm/amdgpu: only uncorrectable error needs gpu reset

we only read error information for correctable error in interrupt
handler, gpu reset is unnecessary since there is no data lost
in correctable error

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index c7647c6988dffa94b1ce63c3f62d8bcbf52548c2..a3575522f83d56ad1bdbce0fba16e9a3f51ff43c 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -254,7 +254,11 @@ static int gmc_v9_0_process_ras_data_cb(struct amdgpu_device *adev,
         */
        if (adev->umc.funcs->query_ras_error_address)
                adev->umc.funcs->query_ras_error_address(adev, err_data);
-       amdgpu_ras_reset_gpu(adev, 0);
+
+       /* only uncorrectable error needs gpu reset */
+       if (err_data->ue_count)
+               amdgpu_ras_reset_gpu(adev, 0);
+
        return AMDGPU_RAS_UE;
 }