Re: [PATCH] pci_crash: capture PCI config space at panic time

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

Hi hangej,

kernel test robot noticed the following build errors:

[auto build test ERROR on pci/next]
[also build test ERROR on pci/for-linus linus/master v7.1-rc3 next-20260508]
[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/hangej/pci_crash-capture-PCI-config-space-at-panic-time/20260514-000653
base:   https://git.kernel.org/pub/scm/linux/kernel/git/pci/pci.git next
patch link:    https://lore.kernel.org/r/20260512162402.1929687-1-hangej%40amazon.com
patch subject: [PATCH] pci_crash: capture PCI config space at panic time
config: i386-randconfig-r071-20260514 (https://download.01.org/0day-ci/archive/20260514/202605140501.1tSG7lxR-lkp@intel.com/config)
compiler: gcc-14 (Debian 14.2.0-19) 14.2.0
smatch: v0.5.0-9185-gbcc58b9c
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20260514/202605140501.1tSG7lxR-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/202605140501.1tSG7lxR-lkp@intel.com/

All errors (new ones prefixed by >>):

   kernel/pci_crash.c: In function 'pci_crash_save':
>> kernel/pci_crash.c:661:53: error: 'struct pci_dev' has no member named 'aer_cap'; did you mean 'acs_cap'?
     661 |                                 if (!pdev || !pdev->aer_cap)
         |                                                     ^~~~~~~
         |                                                     acs_cap
   kernel/pci_crash.c:666:68: error: 'struct pci_dev' has no member named 'aer_cap'; did you mean 'acs_cap'?
     666 |                                                              pdev->aer_cap + PCI_ERR_ROOT_STATUS,
         |                                                                    ^~~~~~~
         |                                                                    acs_cap


vim +661 kernel/pci_crash.c

   599	
   600	/**
   601	 * pci_crash_save() - Capture PCI config space at crash time
   602	 *
   603	 * Called from crash_save_vmcoreinfo() inside __crash_kexec(), which
   604	 * runs before machine_kexec() boots the crash kernel.  This is the
   605	 * only reliable capture point -- panic notifiers run AFTER kexec by
   606	 * default (crash_kexec_post_notifiers=0).
   607	 *
   608	 * Capture check (capture param):
   609	 *   always  -- capture unconditionally
   610	 *   aer     -- quick-scan root port AER ROOT_STATUS for uncorrectable
   611	 *             errors; skip if none found
   612	 *
   613	 * When capture=always, captures on every panic.
   614	 * This is useful for cascading failures: a PCI link-down can cause
   615	 * an MCE or NMI watchdog timeout before DPC/AER fires, so the crash
   616	 * reason is UNKNOWN but AER registers may still hold error state.
   617	 *
   618	 * Reads config space fresh -- successful reads get current register
   619	 * state, failed reads (offline devices) write 0xFFFFFFFF.
   620	 *
   621	 * Flushes both buffer and pagemap from CPU cache to RAM so data
   622	 * survives kexec into crash kernel.
   623	 */
   624	void pci_crash_save(void)
   625	{
   626		struct pci_crash_pagemap *pm;
   627		unsigned long cflags;
   628		unsigned int num_devs;
   629		size_t pm_size;
   630		size_t buf_size;
   631		void *buffer;
   632	
   633		num_devs = READ_ONCE(pci_crash_num_devs);
   634		if (num_devs == 0)
   635			return;
   636	
   637		/* Pairs with smp_wmb() in rebuild -- ensures buffer/pagemap visible */
   638		smp_rmb();
   639	
   640		buffer = READ_ONCE(pci_crash_buffer);
   641		buf_size = READ_ONCE(pci_crash_buffer_size);
   642		pm = READ_ONCE(pci_crash_pagemap);
   643		pm_size = READ_ONCE(pci_crash_pagemap_size);
   644		if (!buffer || buf_size == 0)
   645			return;
   646	
   647		cflags = READ_ONCE(capture_flags);
   648		if (!(cflags & PCI_CRASH_CAPTURE_ALWAYS)) {
   649			if (cflags & PCI_CRASH_CAPTURE_AER) {
   650				struct pci_dev **devs = READ_ONCE(pci_crash_devs);
   651				unsigned int i;
   652				bool pci_error_found = false;
   653	
   654				if (!devs)
   655					return;
   656	
   657				for (i = 0; i < num_devs; i++) {
   658					struct pci_dev *pdev = devs[i];
   659					u32 status;
   660	
 > 661					if (!pdev || !pdev->aer_cap)
   662						continue;
   663	
   664					if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT) {
   665						pci_read_config_dword(pdev,
   666								     pdev->aer_cap + PCI_ERR_ROOT_STATUS,
   667								     &status);
   668						if (status & PCI_ERR_ROOT_UNCOR_RCV) {
   669							pci_error_found = true;
   670							break;
   671						}
   672					}
   673				}
   674	
   675				if (!pci_error_found) {
   676					pr_emerg("no PCI errors detected, skipping capture\n");
   677					return;
   678				}
   679			} else {
   680				return;
   681			}
   682		}
   683	
   684		pci_crash_fill_buffer(buffer, num_devs);
   685	
   686		/*
   687		 * Flush buffer and pagemap from CPU cache to RAM so the
   688		 * crash kernel sees our writes after kexec.
   689		 */
   690		pci_crash_flush_dcache(buffer, buf_size);
   691	
   692		if (pm && pm_size > 0)
   693			pci_crash_flush_dcache(pm, pm_size);
   694	
   695		pr_emerg("CAPTURE: %u devices, %zu bytes\n",
   696			 num_devs, buf_size);
   697	}
   698	EXPORT_SYMBOL_GPL(pci_crash_save);
   699	

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