eeh: Fixing a bug when pci structure is null
Subsystems (2)
A message that is not in the archive (sent off-list or not yet received): [email protected]
PATCH 1/1 eeh: Fixing a bug when pci structure is null
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.
---
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);
Quoted 35 lines · Breno Leitao
During a EEH recover, the
pci_devstructure can be null, mainly if an eeh event is detected during cpi config operation. In this case, thepci_devwill 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+0x100/0x1a0Call Trace: [c0000003a80dff00] [c00000000006b8a8] .eeh_event_handler+0x100/0x1a0 [c0000003a80dff90] [c000000000031f1c] .kernel_thread+0x54/0x70The bug occurs because
pci_name()tries to access a null pointer. This patch just guarantee thatpci_name()is not called on Null pointers.Signed-off-by Breno Leitao <[email protected]>Signed-off-by Linas Vepstas <[email protected]>---
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.hb/arch/powerpc/include/asm/ppc-pci.hindex 2828f9d..724dbe2 100644
---a/arch/powerpc/include/asm/ppc-pci.h
+++b/arch/powerpc/include/asm/ppc-pci.h
@@ -137,6 +137,13 @@ structdevice_node*find_device_pe(struct device_node *dn);
voideeh_sysfs_add_device(struct pci_dev *pdev);
voideeh_sysfs_remove_device(struct pci_dev *pdev);
Quoted 5 lines
+static inline const char *eeh_pci_name(struct
pci_dev*pdev) +{
+ if (NULL==pdev)
+ return "<null>";
+ returnpci_name(pdev);
What about:
return pdev ? pci_name(pdev) : "<null>";
Quoted 4 lines
+}
+
#endif /*CONFIG_EEH*/
Quoted 11 lines
#else /*
CONFIG_PCI*/
diff --gita/arch/powerpc/platforms/pseries/eeh.cb/arch/powerpc/platforms/pseries/eeh.cindex ccd8dd0..f9360fe 100644
---a/arch/powerpc/platforms/pseries/eeh.c
+++b/arch/powerpc/platforms/pseries/eeh.c
@@ -491,7 +491,7 @@ inteeh_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);
No space after function name, please.
Quoted 9 lines
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));
ditto
Quoted 16 lines
printk (
KERN_ERR"EEH: Might be infinite loop in %s driver\n",
dev->driver->name);
dump_stack();
diff --gita/arch/powerpc/platforms/pseries/eeh_driver.cb/arch/powerpc/platforms/pseries/eeh_driver.cindex ef8e454..8f948a0 100644
---a/arch/powerpc/platforms/pseries/eeh_driver.c
+++b/arch/powerpc/platforms/pseries/eeh_driver.c
@@ -337,7 +337,7 @@ structpci_dn*handle_eeh_events(structeeh_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;
}
Quoted 6 lines
@@ -368,7 +368,7 @@ struct
pci_dn*handle_eeh_events(structeeh_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);
ditto
Quoted 19 lines
drv_str = pcid_name (event->dev); }diff --git
a/arch/powerpc/platforms/pseries/eeh_event.cb/arch/powerpc/platforms/pseries/eeh_event.cindex ddb80f5..ec5df8f 100644
---a/arch/powerpc/platforms/pseries/eeh_event.c
+++b/arch/powerpc/platforms/pseries/eeh_event.c
@@ -80,7 +80,7 @@ static inteeh_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);
_______________________________________________
Linuxppc-dev mailing list
[email protected]
https://lists.ozlabs.org/listinfo/linuxppc-dev
Signature · 2 lines
Pengutronix e.K. | Wolfram Sang | Industrial Linux Solutions | http://www.pengutronix.de/ |
PATCH 1/1 eeh: Fixing a bug when pci structure is null
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) 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.
--- arch/powerpc/include/asm/ppc-pci.h | 5 +++++ 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, 10 insertions(+), 5 deletions(-)
arch/powerpc/include/asm/ppc-pci.h +5 -0
@@ -137,6 +137,11 @@ 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) +{ +return pdev ?pci_name (pdev) :"<null>" ; +} +#endif /* CONFIG_EEH */ #else /* CONFIG_PCI */
arch/powerpc/platforms/pseries/eeh.c +2 -2
@@ -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 ();
arch/powerpc/platforms/pseries/eeh_driver.c +2 -2
@@ -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); }
arch/powerpc/platforms/pseries/eeh_event.c +1 -1
@@ -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);
Signature · 1 line
1.6.0.2
Hi Ben,
I'd like to ask about this patch ? Should I re-submit ?
Thanks,
Quoted 4 lines · Breno Leitao
During a EEH recover, the
pci_devstructure can be null, mainly if an eeh event is detected during cpi config operation. In this case, thepci_devwill not be known (and will be null) the kernel will crash with the following message:
Hi Paul, Breno,
Some confusion -- I've been out of the loop for a while -- I assume its still Paul who is pushing
these patches upstream, and not Ben? So Breno, maybe you should resend the patch to Paul?
--linas
Quoted 12 lines · Breno Leitao
Hi Ben,
I'd like to ask about this patch ? Should I re-submit ?
Thanks,
Quoted 4 lines · Breno Leitao
During a EEH recover, the
pci_devstructure can be null, mainly if an eeh event is detected during cpi config operation. In this case, thepci_devwill not be known (and will be null) the kernel will crash with the following message:
Quoted 5 lines · Linas Vepstas
Some confusion -- I've been out of the loop for a while -- I assume its still Paul who is pushing
these patches upstream, and not Ben? So Breno, maybe you should resend the patch to Paul?
No, it's me.
Cheers,
Ben.
Quoted 11 lines · Breno Leitao
Hi Ben,
I'd like to ask about this patch ? Should I re-submit ?
Thanks,
Quoted 4 lines · Breno Leitao
During a EEH recover, the
pci_devstructure can be null, mainly if an eeh event is detected during cpi config operation. In this case, thepci_devwill not be known (and will be null) the kernel will crash with the following message:
It should be in -next, can you dbl check ?
Cheers,
Ben.
Quoted 7 lines · Benjamin Herrenschmidt
Quoted 6 lines · Breno Leitao
Hi Ben,
I'd like to ask about this patch ? Should I re-submit ?
Thanks,
Quoted 7 lines
Quoted 5 lines
Quoted 4 lines · Breno Leitao
During a EEH recover, the
pci_devstructure can be null, mainly if an eeh event is detected during cpi config operation. In this case, thepci_devwill not be known (and will be null) the kernel will crash with the following message:It should be in -next, can you dbl check ?
I just confirmed the patch is in the -next tree.
Mike
Quoted 9 lines
Cheers,
Ben._______________________________________________
Linuxppc-dev mailing list
[email protected]
https://lists.ozlabs.org/listinfo/linuxppc-dev