: powerpc/pseries: Increment fail counter in PCI recovery
Subsystems (2)
PATCH 1/1 : powerpc/pseries: Increment fail counter in PCI recovery
Paul,
A small medium-priority patch; please send upstream as appropriate.
--linas
[PATCH]: powerpc/pseries: Increment fail counter in PCI recovery
When a PCI device driver does not support PCI error recovery, the powerpc/pseries code takes a walk through a branch of code that resets the failure counter. Because of this, if a broken PCI card is present, the kernel will attempt to reset it an infinite number of times. (This is annoying but mostly harmless:
each reset takes about 10-20 seconds, and uses almost no CPU time).
This patch preserves the failure count across resets.
Signed-off-by Linas Vepstas <[email protected]>
----
arch/powerpc/platforms/pseries/eeh_driver.c | 7 ++++++- 1 files changed, 6 insertions(+), 1 deletion(-)
arch/powerpc/platforms/pseries/eeh_driver.c +6 -1
@@ -201,7 +201,11 @@ static void eeh_report_failure(struct pcstatic int eeh_reset_device (struct pci_dn *pe_dn,struct pci_bus *bus) { -int rc; +int cnt, rc; + +/* pcibios will clear the counter; save the value */ + cnt = pe_dn->eeh_freeze_count; +if (bus)pcibios_remove_pci_devices (bus);
@@ -240,6 +244,7 @@ static int eeh_reset_device (struct pci_ssleep (5 );pcibios_add_pci_devices (bus); } + pe_dn->eeh_freeze_count = cnt;return 0 ; }