From a3291b8f85d4fe8c56dad02557d52bf95a93a01f Mon Sep 17 00:00:00 2001
From: Tao Zhou <tao.zhou1@amd.com>
Date: Wed, 21 Sep 2022 17:03:00 +0800
Subject: drm/amdgpu: add page retirement handling for CPU RAS
Git-commit: 5e1fdf76cf9b1b764d6061d78c29901d774fc061
Patch-mainline: v6.1-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225 jsc#PED-2849
Do RAS page retirement in poison consumption handler unconditionally.
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>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 6 +-----
1 file changed, 1 insertion(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index c7b1a2dfde13..9e98f3866edc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -756,11 +756,7 @@ void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev, bo
{
struct ras_err_data err_data = {0, 0, 0, NULL};
- /* CPU MCA will handle page retirement if connected_to_cpu is 1 */
- if (!adev->gmc.xgmi.connected_to_cpu)
- amdgpu_umc_poison_handler(adev, &err_data, reset);
- else if (reset)
- amdgpu_amdkfd_gpu_reset(adev);
+ amdgpu_umc_poison_handler(adev, &err_data, reset);
}
bool amdgpu_amdkfd_ras_query_utcl2_poison_status(struct amdgpu_device *adev)
--
2.38.1