drm/amdgpu: set RAS fed status for more cases

Indicate fatal error for each RAS block and NBIO.

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 2024-06-06 11:20:57 +08:00 committed by Alex Deucher
parent 7e4371676e
commit 09a3d8202d
2 changed files with 2 additions and 0 deletions

View File

@ -2131,6 +2131,7 @@ static void amdgpu_ras_interrupt_umc_handler(struct ras_manager *obj,
/* Let IP handle its data, maybe we need get the output
* from the callback to update the error type/count, etc
*/
amdgpu_ras_set_fed(obj->adev, true);
ret = data->cb(obj->adev, &err_data, entry);
/* ue will trigger an interrupt, and in that case
* we need do a reset to recovery the whole system.

View File

@ -414,6 +414,7 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
/* ras_controller_int is dedicated for nbif ras error,
* not the global interrupt for sync flood
*/
amdgpu_ras_set_fed(adev, true);
amdgpu_ras_reset_gpu(adev);
}