powerpc/pseries: clear PCI failure counter if no new failures.
Subsystems (2)
PATCH 1/1 powerpc/pseries: clear PCI failure counter if no new failures.
[PATCH] powerpc/pseries: clear PCI failure counter if no new failures.
The current PCI error recovery system keeps track of the number of PCI card resets, and refuses to bring a card back up if this number is too large. The goal of doing this was to avoid an infinite loop of resets if a card is obviously dead. However, if the failures are rare, but the machine has a high uptime, this mechanism might still be triggered; this is too harsh.
This patch will avoids this problem by decrementing the fail count after an hour. Thus, as long as a pci card BSOD's less than 6 times an hour, it will continue to be reset indefinitely. If it's failure rate is greater than that, it will be taken off-line permanently.
This patch is larger than it might otherwise be because it changes indentation by removing a pointless while-loop. The while loop is not needed, as the handler is invoked once fo each event (by schedule_work()); the loop is leftover cruft from an earlier implementation.
----
arch/powerpc/platforms/pseries/eeh_driver.c | 13 +++--- arch/powerpc/platforms/pseries/eeh_event.c | 60 +++++++++++++++------------- include/asm-powerpc/eeh_event.h | 10 ++-- 3 files changed, 45 insertions(+), 38 deletions(-)
arch/powerpc/platforms/pseries/eeh_driver.c +7 -6
@@ -23,9 +23,8 @@* */ #include <linux/delay.h> -#include <linux/irq.h> #include <linux/interrupt.h> -#include <linux/notifier.h> +#include <linux/irq.h> #include <linux/pci.h> #include <asm/eeh.h> #include <asm/eeh_event.h>
@@ -250,7 +249,7 @@ static int eeh_reset_device (struct pci_*/ #define MAX_WAIT_FOR_RECOVERY 15 -void handle_eeh_events (struct eeh_event *event) +struct pci_dn *handle_eeh_events (struct eeh_event *event) {struct device_node *frozen_dn;struct pci_dn *frozen_pdn;
@@ -265,7 +264,7 @@ void handle_eeh_events (struct eeh_eventif (!frozen_dn) {printk (KERN_ERR "EEH: Error: Cannot find partition endpoint for %s\n" ,pci_name (event->dev)); -return ; +return NULL ; }/* There are two different styles for coming up with the PE.
@@ -280,7 +279,7 @@ void handle_eeh_events (struct eeh_eventif (!frozen_bus) {printk (KERN_ERR "EEH: Cannot find PCI bus for %s\n" , frozen_dn->full_name); -return ; +return NULL ; }#if 0
@@ -355,7 +354,7 @@ void handle_eeh_events (struct eeh_event/* Tell all device drivers that they can resume operations */ pci_walk_bus (frozen_bus, eeh_report_resume,NULL ); -return ; +return frozen_pdn; excess_failures:/*
@@ -384,6 +383,8 @@ perm_error:/* Shut down the device drivers for good. */ pcibios_remove_pci_devices (frozen_bus); + +return NULL ; }/* ---------- end of file ---------- */
arch/powerpc/platforms/pseries/eeh_event.c +33 -27
77 lines not on this page · raw message
include/asm-powerpc/eeh_event.h +5 -5
@@ -18,8 +18,8 @@* Copyright (c) 2005 Linas Vepstas <[email protected]> */ -#ifndef ASM_PPC64_EEH_EVENT_H -#define ASM_PPC64_EEH_EVENT_H +#ifndef ASM_POWERPC_EEH_EVENT_H +#define ASM_POWERPC_EEH_EVENT_H #ifdef __KERNEL__/** EEH event -- structure holding pci controller data that describes
@@ -39,7 +39,7 @@ struct eeh_event {* @dev pci device * * This routine builds a PCI error event which will be delivered -* to all listeners on the peh_notifier_chain. +* to all listeners on the eeh_notifier_chain. * * This routine can be called within an interrupt context; * the actual event will be delivered in a normal context
@@ -51,7 +51,7 @@ int eeh_send_failure_event (struct devic int time_unavail);/* Main recovery function */ -void handle_eeh_events (struct eeh_event *); +struct pci_dn *handle_eeh_events (struct eeh_event *);#endif /* __KERNEL__ */ -#endif /* ASM_PPC64_EEH_EVENT_H */ +#endif /* ASM_POWERPC_EEH_EVENT_H */