struct drm_device *dev = pci_get_drvdata(pdev);
struct amdgpu_device *adev = drm_to_adev(dev);
+ amdgpu_ras_eeprom_check_and_recover(adev);
amdgpu_xcp_dev_unplug(adev);
amdgpu_gmc_prepare_nps_mode_change(adev);
drm_dev_unplug(dev);
return res < 0 ? res : 0;
}
+
+void amdgpu_ras_eeprom_check_and_recover(struct amdgpu_device *adev)
+{
+ struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+ struct amdgpu_ras_eeprom_control *control;
+ int res;
+
+ if (!__is_ras_eeprom_supported(adev) || !ras)
+ return;
+ control = &ras->eeprom_control;
+ if (!control->is_eeprom_valid)
+ return;
+ res = __verify_ras_table_checksum(control);
+ if (res) {
+ dev_warn(adev->dev,
+ "RAS table incorrect checksum or error:%d, try to recover\n",
+ res);
+ if (!amdgpu_ras_eeprom_reset_table(control))
+ if (!amdgpu_ras_save_bad_pages(adev, NULL))
+ if (!__verify_ras_table_checksum(control)) {
+ dev_info(adev->dev, "RAS table recovery succeed\n");
+ return;
+ }
+ dev_err(adev->dev, "RAS table recovery failed\n");
+ control->is_eeprom_valid = false;
+ }
+ return;
+}
\ No newline at end of file
int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control);
+void amdgpu_ras_eeprom_check_and_recover(struct amdgpu_device *adev);
+
extern const struct file_operations amdgpu_ras_debugfs_eeprom_size_ops;
extern const struct file_operations amdgpu_ras_debugfs_eeprom_table_ops;