Re: [RFC PATCH 6/6] cxl: Add mce notifier to emit aliased address for extended linear cache

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

Hi Dave,

[This is a private test report for your RFC patch.]
kernel test robot noticed the following build errors:

[auto build test ERROR on driver-core/driver-core-testing]
[also build test ERROR on driver-core/driver-core-next driver-core/driver-core-linus tip/x86/core tip/x86/mm v6.11]
[cannot apply to rafael-pm/linux-next rafael-pm/bleeding-edge cxl/next linus/master cxl/pending next-20240927]
[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/Dave-Jiang/ACPICA-actbl1-h-Add-extended-linear-address-mode-to-MSCIS/20240927-222421
base:   driver-core/driver-core-testing
patch link:    https://lore.kernel.org/r/20240927142108.1156362-7-dave.jiang%40intel.com
patch subject: [RFC PATCH 6/6] cxl: Add mce notifier to emit aliased address for extended linear cache
config: powerpc-allyesconfig (https://download.01.org/0day-ci/archive/20240928/202409280948.0QFDTcPb-lkp@intel.com/config)
compiler: clang version 20.0.0git (https://github.com/llvm/llvm-project 7773243d9916f98ba0ffce0c3a960e4aa9f03e81)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240928/202409280948.0QFDTcPb-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/202409280948.0QFDTcPb-lkp@intel.com/

All errors (new ones prefixed by >>):

   In file included from drivers/cxl/core/mbox.c:3:
   In file included from include/linux/security.h:33:
   In file included from include/linux/mm.h:2228:
   include/linux/vmstat.h:503:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     503 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     504 |                            item];
         |                            ~~~~
   include/linux/vmstat.h:510:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     510 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     511 |                            NR_VM_NUMA_EVENT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~~
   include/linux/vmstat.h:517:36: warning: arithmetic between different enumeration types ('enum node_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
     517 |         return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_"
         |                               ~~~~~~~~~~~ ^ ~~~
   include/linux/vmstat.h:523:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     523 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     524 |                            NR_VM_NUMA_EVENT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~~
>> drivers/cxl/core/mbox.c:1461:15: error: call to undeclared function 'mce_usable_address'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
    1461 |         if (!mce || !mce_usable_address(mce))
         |                      ^
>> drivers/cxl/core/mbox.c:1464:11: error: incomplete definition of type 'struct mce'
    1464 |         spa = mce->addr & MCI_ADDR_PHYSADDR;
         |               ~~~^
   drivers/cxl/core/mbox.c:1457:9: note: forward declaration of 'struct mce'
    1457 |         struct mce *mce = (struct mce *)data;
         |                ^
>> drivers/cxl/core/mbox.c:1464:20: error: use of undeclared identifier 'MCI_ADDR_PHYSADDR'
    1464 |         spa = mce->addr & MCI_ADDR_PHYSADDR;
         |                           ^
>> drivers/cxl/core/mbox.c:1508:31: error: use of undeclared identifier 'MCE_PRIO_CXL'
    1508 |         mds->mce_notifier.priority = MCE_PRIO_CXL;
         |                                      ^
>> drivers/cxl/core/mbox.c:1509:2: error: call to undeclared function 'mce_register_decode_chain'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
    1509 |         mce_register_decode_chain(&mds->mce_notifier);
         |         ^
   4 warnings and 5 errors generated.


vim +/mce_usable_address +1461 drivers/cxl/core/mbox.c

  1449	
  1450	static int cxl_handle_mce(struct notifier_block *nb, unsigned long val,
  1451				  void *data)
  1452	{
  1453		struct cxl_memdev_state *mds = container_of(nb, struct cxl_memdev_state,
  1454							    mce_notifier);
  1455		struct cxl_memdev *cxlmd = mds->cxlds.cxlmd;
  1456		struct cxl_port *endpoint = cxlmd->endpoint;
  1457		struct mce *mce = (struct mce *)data;
  1458		u64 spa, spa_alias;
  1459		unsigned long pfn;
  1460	
> 1461		if (!mce || !mce_usable_address(mce))
  1462			return NOTIFY_DONE;
  1463	
> 1464		spa = mce->addr & MCI_ADDR_PHYSADDR;
  1465	
  1466		pfn = spa >> PAGE_SHIFT;
  1467		if (!pfn_valid(pfn))
  1468			return NOTIFY_DONE;
  1469	
  1470		spa_alias = cxl_port_get_spa_cache_alias(endpoint, spa);
  1471		if (!spa_alias)
  1472			return NOTIFY_DONE;
  1473	
  1474		pfn = spa_alias >> PAGE_SHIFT;
  1475	
  1476		/*
  1477		 * Take down the aliased memory page. The original memory page flagged
  1478		 * by the MCE will be taken cared of by the standard MCE handler.
  1479		 */
  1480		dev_emerg(mds->cxlds.dev, "Offlining aliased SPA address: %#llx\n",
  1481			  spa_alias);
  1482		if (!memory_failure(pfn, 0))
  1483			set_mce_nospec(pfn);
  1484	
  1485		return NOTIFY_OK;
  1486	}
  1487	
  1488	struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev)
  1489	{
  1490		struct cxl_memdev_state *mds;
  1491	
  1492		mds = devm_kzalloc(dev, sizeof(*mds), GFP_KERNEL);
  1493		if (!mds) {
  1494			dev_err(dev, "No memory available\n");
  1495			return ERR_PTR(-ENOMEM);
  1496		}
  1497	
  1498		mutex_init(&mds->mbox_mutex);
  1499		mutex_init(&mds->event.log_lock);
  1500		mds->cxlds.dev = dev;
  1501		mds->cxlds.reg_map.host = dev;
  1502		mds->cxlds.reg_map.resource = CXL_RESOURCE_NONE;
  1503		mds->cxlds.type = CXL_DEVTYPE_CLASSMEM;
  1504		mds->ram_perf.qos_class = CXL_QOS_CLASS_INVALID;
  1505		mds->pmem_perf.qos_class = CXL_QOS_CLASS_INVALID;
  1506	
  1507		mds->mce_notifier.notifier_call = cxl_handle_mce;
> 1508		mds->mce_notifier.priority = MCE_PRIO_CXL;
> 1509		mce_register_decode_chain(&mds->mce_notifier);
  1510	
  1511		return mds;
  1512	}
  1513	EXPORT_SYMBOL_NS_GPL(cxl_memdev_state_create, CXL);
  1514	

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