drm/amdgpu: change to save bad pages in UMC error interrupt callback

Instead of saving bad pages in amdgpu_ras_reset_gpu, it will reduce
the unnecessary calling of amdgpu_ras_save_bad_pages.
Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Reviewed-by: Hawking Zhang <hawking.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c

@@ -1668,7 +1668,7 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
  * write error record array to eeprom, the function should be
  * protected by recovery_lock
  */
-static int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev)
+int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_err_handler_data *data;
@@ -1841,9 +1841,6 @@ int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev)
 		data->last_reserved = i + 1;
 		bo = NULL;
 	}
-
-	/* continue to save bad pages to eeprom even reesrve_vram fails */
-	ret = amdgpu_ras_save_bad_pages(adev);
 out:
 	mutex_unlock(&con->recovery_lock);
 	return ret;

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h

@@ -506,6 +506,7 @@ bool amdgpu_ras_check_err_threshold(struct amdgpu_device *adev);
 int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
 		struct eeprom_table_record *bps, int pages);
 
+int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev);
 int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev);
 
 static inline int amdgpu_ras_reset_gpu(struct amdgpu_device *adev)

drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c

@@ -126,10 +126,11 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
 				err_data->ue_count);
 
 		if ((amdgpu_bad_page_threshold != 0) &&
-			err_data->err_addr_cnt &&
+			err_data->err_addr_cnt) {
 			amdgpu_ras_add_bad_pages(adev, err_data->err_addr,
-						err_data->err_addr_cnt))
-			dev_warn(adev->dev, "Failed to add ras bad page!\n");
+						err_data->err_addr_cnt);
+			amdgpu_ras_save_bad_pages(adev);
+		}
 
 		amdgpu_ras_reset_gpu(adev);
 	}