drm/amdgpu: add RAS poison consumption handler for SRIOV

Send message to PF if VF receives RAS poison consumption interrupt.

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>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index f76c19fc03926fb5c77fba1e9c940e114134acc5..1c7fcb4f238089c888516d071f2349977a5cc736 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -169,25 +169,33 @@ int amdgpu_umc_poison_handler(struct amdgpu_device *adev, bool reset)
 {
        int ret = AMDGPU_RAS_SUCCESS;
 
-       if (!adev->gmc.xgmi.connected_to_cpu) {
-               struct ras_err_data err_data = {0, 0, 0, NULL};
-               struct ras_common_if head = {
-                       .block = AMDGPU_RAS_BLOCK__UMC,
-               };
-               struct ras_manager *obj = amdgpu_ras_find_obj(adev, &head);
-
-               ret = amdgpu_umc_do_page_retirement(adev, &err_data, NULL, reset);
-
-               if (ret == AMDGPU_RAS_SUCCESS && obj) {
-                       obj->err_data.ue_count += err_data.ue_count;
-                       obj->err_data.ce_count += err_data.ce_count;
+       if (!amdgpu_sriov_vf(adev)) {
+               if (!adev->gmc.xgmi.connected_to_cpu) {
+                       struct ras_err_data err_data = {0, 0, 0, NULL};
+                       struct ras_common_if head = {
+                               .block = AMDGPU_RAS_BLOCK__UMC,
+                       };
+                       struct ras_manager *obj = amdgpu_ras_find_obj(adev, &head);
+
+                       ret = amdgpu_umc_do_page_retirement(adev, &err_data, NULL, reset);
+
+                       if (ret == AMDGPU_RAS_SUCCESS && obj) {
+                               obj->err_data.ue_count += err_data.ue_count;
+                               obj->err_data.ce_count += err_data.ce_count;
+                       }
+               } else if (reset) {
+                       /* MCA poison handler is only responsible for GPU reset,
+                        * let MCA notifier do page retirement.
+                        */
+                       kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
+                       amdgpu_ras_reset_gpu(adev);
                }
-       } else if (reset) {
-               /* MCA poison handler is only responsible for GPU reset,
-                * let MCA notifier do page retirement.
-                */
-               kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
-               amdgpu_ras_reset_gpu(adev);
+       } else {
+               if (adev->virt.ops && adev->virt.ops->ras_poison_handler)
+                       adev->virt.ops->ras_poison_handler(adev);
+               else
+                       dev_warn(adev->dev,
+                               "No ras_poison_handler interface in SRIOV!\n");
        }
 
        return ret;