Re: [PATCH v2 1/5] Introduce Xe Uncorrectable Error Handling

[kernel test robot <lkp@intel.com>]

Hi Mallesh,

kernel test robot noticed the following build errors:

[auto build test ERROR on drm-xe/drm-xe-next]
[also build test ERROR on drm-misc/drm-misc-next drm/drm-next next-20260319]
[cannot apply to linus/master v7.0-rc4]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Mallesh-Koujalagi/Introduce-Xe-Uncorrectable-Error-Handling/20260318-153303
base:   https://gitlab.freedesktop.org/drm/xe/kernel.git drm-xe-next
patch link:    https://lore.kernel.org/r/20260318064016.374656-8-mallesh.koujalagi%40intel.com
patch subject: [PATCH v2 1/5] Introduce Xe Uncorrectable Error Handling
config: i386-randconfig-017-20260319 (https://download.01.org/0day-ci/archive/20260320/202603200358.BacRkqob-lkp@intel.com/config)
compiler: clang version 20.1.8 (https://github.com/llvm/llvm-project 87f0227cb60147a26a1eeb4fb06e3b505e9c7261)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20260320/202603200358.BacRkqob-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202603200358.BacRkqob-lkp@intel.com/

All errors (new ones prefixed by >>):

>> drivers/gpu/drm/xe/xe_ras.c:241:4: error: variable 'action' is used uninitialized whenever switch default is taken [-Werror,-Wsometimes-uninitialized]
     241 |                         default:
         |                         ^~~~~~~
   drivers/gpu/drm/xe/xe_ras.c:250:8: note: uninitialized use occurs here
     250 |                         if (action > final_action)
         |                             ^~~~~~
   drivers/gpu/drm/xe/xe_ras.c:227:4: note: variable 'action' is declared here
     227 |                         enum xe_ras_recovery_action action;
         |                         ^
   1 error generated.


vim +/action +241 drivers/gpu/drm/xe/xe_ras.c

   177	
   178	/**
   179	 * xe_ras_process_errors - Process and contain hardware errors
   180	 * @xe: xe device instance
   181	 *
   182	 * Get error details from system controller and return recovery
   183	 * method. Called only from PCI error handling.
   184	 *
   185	 * Returns: recovery action to be taken
   186	 */
   187	enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe)
   188	{
   189		struct xe_sysctrl_mailbox_command command = {0};
   190		struct xe_ras_get_error_response response;
   191		enum xe_ras_recovery_action final_action;
   192		size_t rlen;
   193		int ret;
   194	
   195		/* Default action */
   196		final_action = XE_RAS_RECOVERY_ACTION_RECOVERED;
   197	
   198		if (!xe->info.has_sysctrl)
   199			return XE_RAS_RECOVERY_ACTION_RESET;
   200	
   201		xe_ras_prepare_sysctrl_command(&command, XE_SYSCTRL_CMD_GET_SOC_ERROR, NULL, 0,
   202					       &response, sizeof(response));
   203	
   204		do {
   205			memset(&response, 0, sizeof(response));
   206			rlen = 0;
   207	
   208			ret = xe_sysctrl_send_command(xe, &command, &rlen);
   209			if (ret || !rlen) {
   210				xe_err(xe, "[RAS]: Sysctrl error ret %d\n", ret);
   211				goto err;
   212			}
   213	
   214			if (rlen != sizeof(response)) {
   215				xe_err(xe, "[RAS]: Sysctrl response does not match len!!\n");
   216				goto err;
   217			}
   218	
   219			if (response.num_errors > XE_RAS_NUM_ERROR_ARR) {
   220				xe_err(xe, "[RAS]: Number of errors out of bound (%d)\n",
   221				       XE_RAS_NUM_ERROR_ARR);
   222				goto err;
   223			}
   224	
   225			for (int i = 0; i < response.num_errors; i++) {
   226				struct xe_ras_error_array arr = response.error_arr[i];
   227				enum xe_ras_recovery_action action;
   228				struct xe_ras_error_class error_class;
   229				u8 component;
   230	
   231				error_class = arr.error_class;
   232				component = error_class.common.component;
   233	
   234				switch (component) {
   235				case XE_RAS_COMPONENT_CORE_COMPUTE:
   236					action = handle_compute_errors(xe, &arr);
   237					break;
   238				case XE_RAS_COMPONENT_SOC_INTERNAL:
   239					action = handle_soc_internal_errors(xe, &arr);
   240					break;
 > 241				default:
   242					xe_err(xe, "[RAS]: Unknown error component %u\n", component);
   243					break;
   244				}
   245	
   246				/*
   247				 * Retain the highest severity action. Process and log all errors
   248				 * and then take appropriate recovery action
   249				 */
   250				if (action > final_action)
   251					final_action = action;
   252			}
   253	
   254		} while (response.additional_errors);
   255	
   256		return final_action;
   257	
   258	err:
   259		return XE_RAS_RECOVERY_ACTION_RESET;
   260	}
   261	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki