[PATCH] eeh: Fixing a bug when pci structure is null

[Breno Leitao]

 During a EEH recover, the pci_dev structure can be null, mainly if an
 eeh event is detected during cpi config operation. In this case, the
 pci_dev will not be known (and will be null) and the kernel will crash
 with the following message:
 
 Unable to handle kernel paging request for data at address 0x000000a0
 Faulting instruction address: 0xc00000000006b8b4
 Oops: Kernel access of bad area, sig: 11 [#1]
 
 NIP [c00000000006b8b4] .eeh_event_handler+0x10c/0x1a0
 LR [c00000000006b8a8] .eeh_event_handler+0x100/0x1a0
 Call Trace:
 [c0000003a80dff00] [c00000000006b8a8] .eeh_event_handler+0x100/0x1a0
 [c0000003a80dff90] [c000000000031f1c] .kernel_thread+0x54/0x70
 
 The bug occurs because pci_name() tries to access a null pointer.
 This patch just guarantee that pci_name() is not called on Null pointers.
 
 Signed-off-by: Breno Leitao <leitao at linux.vnet.ibm.com>
 Signed-off-by: Linas Vepstas <linasvepstas at gmail.com>
 ---
  arch/powerpc/include/asm/ppc-pci.h          |    7 +++++++
  arch/powerpc/platforms/pseries/eeh.c        |    4 ++--
  arch/powerpc/platforms/pseries/eeh_driver.c |    4 ++--
  arch/powerpc/platforms/pseries/eeh_event.c  |    2 +-
  4 files changed, 12 insertions(+), 5 deletions(-)
 
 diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
 index 2828f9d..724dbe2 100644
 --- a/arch/powerpc/include/asm/ppc-pci.h
 +++ b/arch/powerpc/include/asm/ppc-pci.h
 @@ -137,6 +137,13 @@ struct device_node * find_device_pe(struct device_node *dn);
  void eeh_sysfs_add_device(struct pci_dev *pdev);
  void eeh_sysfs_remove_device(struct pci_dev *pdev);
 
 +static inline const char *eeh_pci_name(struct pci_dev *pdev) 
 +{ 
 +	if (NULL==pdev) 
 +		return "<null>"; 
 +	return pci_name(pdev); 
 +} 
 +
  #endif /* CONFIG_EEH */
 
  #else /* CONFIG_PCI */
 diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
 index ccd8dd0..f9360fe 100644
 --- a/arch/powerpc/platforms/pseries/eeh.c
 +++ b/arch/powerpc/platforms/pseries/eeh.c
 @@ -491,7 +491,7 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
  	    pdn->eeh_mode & EEH_MODE_NOCHECK) {
  		ignored_check++;
  		pr_debug("EEH: Ignored check (%x) for %s %s\n",
 -			 pdn->eeh_mode, pci_name (dev), dn->full_name);
 +			 pdn->eeh_mode, eeh_pci_name (dev), dn->full_name);
  		return 0;
  	}
 
 @@ -515,7 +515,7 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
  			printk (KERN_ERR "EEH: %d reads ignored for recovering device at "
  				"location=%s driver=%s pci addr=%s\n",
  				pdn->eeh_check_count, location,
 -				dev->driver->name, pci_name(dev));
 +				dev->driver->name, eeh_pci_name(dev));
  			printk (KERN_ERR "EEH: Might be infinite loop in %s driver\n",
  				dev->driver->name);
  			dump_stack();
 diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c
 index ef8e454..8f948a0 100644
 --- a/arch/powerpc/platforms/pseries/eeh_driver.c
 +++ b/arch/powerpc/platforms/pseries/eeh_driver.c
 @@ -337,7 +337,7 @@ struct pci_dn * handle_eeh_events (struct eeh_event *event)
  		location = location ? location : "unknown";
  		printk(KERN_ERR "EEH: Error: Cannot find partition endpoint "
  		                "for location=%s pci addr=%s\n",
 -		        location, pci_name(event->dev));
 +		        location, eeh_pci_name(event->dev));
  		return NULL;
  	}
 
 @@ -368,7 +368,7 @@ struct pci_dn * handle_eeh_events (struct eeh_event *event)
  		pci_str = pci_name (frozen_pdn->pcidev);
  		drv_str = pcid_name (frozen_pdn->pcidev);
  	} else {
 -		pci_str = pci_name (event->dev);
 +		pci_str = eeh_pci_name (event->dev);
  		drv_str = pcid_name (event->dev);
  	}
  	
 diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c
 index ddb80f5..ec5df8f 100644
 --- a/arch/powerpc/platforms/pseries/eeh_event.c
 +++ b/arch/powerpc/platforms/pseries/eeh_event.c
 @@ -80,7 +80,7 @@ static int eeh_event_handler(void * dummy)
  	eeh_mark_slot(event->dn, EEH_MODE_RECOVERING);
 
  	printk(KERN_INFO "EEH: Detected PCI bus error on device %s\n",
 -	       pci_name(event->dev));
 +	       eeh_pci_name(event->dev));
 
  	pdn = handle_eeh_events(event);