From: Linas Vepstas 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 Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton --- arch/powerpc/platforms/pseries/eeh_driver.c | 7 ++++++- 1 files changed, 6 insertions(+), 1 deletion(-) diff -puN arch/powerpc/platforms/pseries/eeh_driver.c~powerpc-pseries-increment-fail-counter-in-pci-recovery arch/powerpc/platforms/pseries/eeh_driver.c --- 25/arch/powerpc/platforms/pseries/eeh_driver.c~powerpc-pseries-increment-fail-counter-in-pci-recovery Mon May 8 12:36:40 2006 +++ 25-akpm/arch/powerpc/platforms/pseries/eeh_driver.c Mon May 8 12:36:40 2006 @@ -201,7 +201,11 @@ static void eeh_report_failure(struct pc static 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; } _