482908b49e
Traditionally, fatal MCE will cause Linux print error log to console then reboot. Because MCE registers will preserve their content after warm reboot, the hardware error can be logged to disk or network after reboot. But system may fail to warm reboot, then you may lose the hardware error log. ERST can help here. Through saving the hardware error log into flash via ERST before go panic, the hardware error log can be gotten from the flash after system boot successful again. The fatal MCE processing procedure with ERST involved is as follow: - Hardware detect error, MCE raised - MCE read MCE registers, check error severity (fatal), prepare error record - Write MCE error record into flash via ERST - Go panic, then trigger system reboot - System reboot, /sbin/mcelog run, it reads /dev/mcelog to check flash for error record of previous boot via ERST, and output and clear them if available - /sbin/mcelog logs error records into disk or network ERST only accepts CPER record format, but there is no pre-defined CPER section can accommodate all information in struct mce, so a customized section type is defined to hold struct mce inside a CPER record as an error section. Signed-off-by: Huang Ying <ying.huang@intel.com> Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Len Brown <len.brown@intel.com>
54 lines
1.1 KiB
C
54 lines
1.1 KiB
C
#include <linux/sysdev.h>
|
|
#include <asm/mce.h>
|
|
|
|
enum severity_level {
|
|
MCE_NO_SEVERITY,
|
|
MCE_KEEP_SEVERITY,
|
|
MCE_SOME_SEVERITY,
|
|
MCE_AO_SEVERITY,
|
|
MCE_UC_SEVERITY,
|
|
MCE_AR_SEVERITY,
|
|
MCE_PANIC_SEVERITY,
|
|
};
|
|
|
|
#define ATTR_LEN 16
|
|
|
|
/* One object for each MCE bank, shared by all CPUs */
|
|
struct mce_bank {
|
|
u64 ctl; /* subevents to enable */
|
|
unsigned char init; /* initialise bank? */
|
|
struct sysdev_attribute attr; /* sysdev attribute */
|
|
char attrname[ATTR_LEN]; /* attribute name */
|
|
};
|
|
|
|
int mce_severity(struct mce *a, int tolerant, char **msg);
|
|
struct dentry *mce_get_debugfs_dir(void);
|
|
|
|
extern int mce_ser;
|
|
|
|
extern struct mce_bank *mce_banks;
|
|
|
|
#ifdef CONFIG_ACPI_APEI
|
|
int apei_write_mce(struct mce *m);
|
|
ssize_t apei_read_mce(struct mce *m, u64 *record_id);
|
|
int apei_check_mce(void);
|
|
int apei_clear_mce(u64 record_id);
|
|
#else
|
|
static inline int apei_write_mce(struct mce *m)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
static inline ssize_t apei_read_mce(struct mce *m, u64 *record_id)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int apei_check_mce(void)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int apei_clear_mce(u64 record_id)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
#endif
|