Indicate fatal error for each RAS block and NBIO.
Signed-off-by: Tao Zhou <[email protected]>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 1 +
drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c | 1 +
2 files changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 77566dcc0852..183eae22b687 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2114,6 +2114,7 @@ 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.
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index b8fc9e126e0d..9446bf6f82c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -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);
}
--
2.34.1
