[PATCH] powerpc: PCI Error Recovery: PPC64 core recovery routines

Various PCI bus errors can be signaled by newer PCI controllers.  The
core error recovery routines are architecture dependent.  This patch adds
a recovery infrastructure for the  PPC64 pSeries systems.

Signed-off-by: Linas Vepstas <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
(cherry picked from e8ca11b460c4c9c7fa6b529be221529ebd770e38 commit)
This commit is contained in:
Linas Vepstas 2005-11-03 18:52:49 -06:00 • committed by Paul Mackerras
commit 77bd741561
7 changed files with 413 additions and 35 deletions

View file

@ -34,9 +34,11 @@ struct device_node;
extern int eeh_subsystem_enabled;
/* Values for eeh_mode bits in device_node */
#define EEH_MODE_SUPPORTED (1<<0)
#define EEH_MODE_NOCHECK (1<<1)
#define EEH_MODE_ISOLATED (1<<2)
#define EEH_MODE_SUPPORTED (1<<0)
#define EEH_MODE_NOCHECK (1<<1)
#define EEH_MODE_ISOLATED (1<<2)
#define EEH_MODE_RECOVERING (1<<3)
#define EEH_MODE_IRQ_DISABLED (1<<4)
/* Max number of EEH freezes allowed before we consider the device
* to be permanently disabled. */

View file

@ -30,7 +30,7 @@ struct eeh_event {
struct list_head list;
struct device_node *dn; /* struct device node */
struct pci_dev *dev; /* affected device */
int state;
enum pci_channel_state state; /* PCI bus state for the affected device */
int time_unavail; /* milliseconds until device might be available */
};
@ -47,8 +47,11 @@ struct eeh_event {
*/
int eeh_send_failure_event (struct device_node *dn,
struct pci_dev *dev,
int reset_state,
enum pci_channel_state state,
int time_unavail);
/* Main recovery function */
void handle_eeh_events (struct eeh_event *);
#endif /* __KERNEL__ */
#endif /* ASM_PPC64_EEH_EVENT_H */

View file

@ -52,6 +52,15 @@ extern unsigned long pci_probe_only;
/* ---- EEH internal-use-only related routines ---- */
#ifdef CONFIG_EEH
/**
* eeh_slot_error_detail -- record and EEH error condition to the log
* @severity: 1 if temporary, 2 if permanent failure.
*
* Obtains the the EEH error details from the RTAS subsystem,
* and then logs these details with the RTAS error log system.
*/
void eeh_slot_error_detail (struct pci_dn *pdn, int severity);
/**
* rtas_set_slot_reset -- unfreeze a frozen slot
*