2005-04-16 18:20:36 -04:00
|
|
|
#ifndef _ASM_MCE_H
|
|
|
|
#define _ASM_MCE_H 1
|
|
|
|
|
|
|
|
#include <asm/ioctls.h>
|
|
|
|
#include <asm/types.h>
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Machine Check support for x86
|
|
|
|
*/
|
|
|
|
|
|
|
|
#define MCG_CTL_P (1UL<<8) /* MCG_CAP register available */
|
|
|
|
|
|
|
|
#define MCG_STATUS_RIPV (1UL<<0) /* restart ip valid */
|
|
|
|
#define MCG_STATUS_EIPV (1UL<<1) /* eip points to correct instruction */
|
|
|
|
#define MCG_STATUS_MCIP (1UL<<2) /* machine check in progress */
|
|
|
|
|
|
|
|
#define MCI_STATUS_VAL (1UL<<63) /* valid error */
|
|
|
|
#define MCI_STATUS_OVER (1UL<<62) /* previous errors lost */
|
|
|
|
#define MCI_STATUS_UC (1UL<<61) /* uncorrected error */
|
|
|
|
#define MCI_STATUS_EN (1UL<<60) /* error enabled */
|
|
|
|
#define MCI_STATUS_MISCV (1UL<<59) /* misc error reg. valid */
|
|
|
|
#define MCI_STATUS_ADDRV (1UL<<58) /* addr reg. valid */
|
|
|
|
#define MCI_STATUS_PCC (1UL<<57) /* processor context corrupt */
|
|
|
|
|
|
|
|
/* Fields are zero when not available */
|
|
|
|
struct mce {
|
|
|
|
__u64 status;
|
|
|
|
__u64 misc;
|
|
|
|
__u64 addr;
|
|
|
|
__u64 mcgstatus;
|
|
|
|
__u64 rip;
|
|
|
|
__u64 tsc; /* cpu time stamp counter */
|
|
|
|
__u64 res1; /* for future extension */
|
|
|
|
__u64 res2; /* dito. */
|
|
|
|
__u8 cs; /* code segment */
|
|
|
|
__u8 bank; /* machine check bank */
|
|
|
|
__u8 cpu; /* cpu that raised the error */
|
|
|
|
__u8 finished; /* entry is valid */
|
|
|
|
__u32 pad;
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This structure contains all data related to the MCE log.
|
|
|
|
* Also carries a signature to make it easier to find from external debugging tools.
|
|
|
|
* Each entry is only valid when its finished flag is set.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#define MCE_LOG_LEN 32
|
|
|
|
|
|
|
|
struct mce_log {
|
|
|
|
char signature[12]; /* "MACHINECHECK" */
|
|
|
|
unsigned len; /* = MCE_LOG_LEN */
|
|
|
|
unsigned next;
|
|
|
|
unsigned flags;
|
|
|
|
unsigned pad0;
|
|
|
|
struct mce entry[MCE_LOG_LEN];
|
|
|
|
};
|
|
|
|
|
|
|
|
#define MCE_OVERFLOW 0 /* bit 0 in flags means overflow */
|
|
|
|
|
|
|
|
#define MCE_LOG_SIGNATURE "MACHINECHECK"
|
|
|
|
|
|
|
|
#define MCE_GET_RECORD_LEN _IOR('M', 1, int)
|
|
|
|
#define MCE_GET_LOG_LEN _IOR('M', 2, int)
|
|
|
|
#define MCE_GETCLEAR_FLAGS _IOR('M', 3, int)
|
|
|
|
|
|
|
|
/* Software defined banks */
|
|
|
|
#define MCE_EXTENDED_BANK 128
|
|
|
|
#define MCE_THERMAL_BANK MCE_EXTENDED_BANK + 0
|
2006-06-26 07:58:53 -04:00
|
|
|
|
|
|
|
#define K8_MCE_THRESHOLD_BASE (MCE_EXTENDED_BANK + 1) /* MCE_AMD */
|
|
|
|
#define K8_MCE_THRESHOLD_BANK_0 (MCE_THRESHOLD_BASE + 0 * 9)
|
|
|
|
#define K8_MCE_THRESHOLD_BANK_1 (MCE_THRESHOLD_BASE + 1 * 9)
|
|
|
|
#define K8_MCE_THRESHOLD_BANK_2 (MCE_THRESHOLD_BASE + 2 * 9)
|
|
|
|
#define K8_MCE_THRESHOLD_BANK_3 (MCE_THRESHOLD_BASE + 3 * 9)
|
|
|
|
#define K8_MCE_THRESHOLD_BANK_4 (MCE_THRESHOLD_BASE + 4 * 9)
|
|
|
|
#define K8_MCE_THRESHOLD_BANK_5 (MCE_THRESHOLD_BASE + 5 * 9)
|
|
|
|
#define K8_MCE_THRESHOLD_DRAM_ECC (MCE_THRESHOLD_BANK_4 + 0)
|
2005-04-16 18:20:36 -04:00
|
|
|
|
2006-04-07 13:49:57 -04:00
|
|
|
#ifdef __KERNEL__
|
|
|
|
#include <asm/atomic.h>
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
void mce_log(struct mce *m);
|
2006-06-26 07:58:50 -04:00
|
|
|
DECLARE_PER_CPU(struct sys_device, device_mce);
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
#ifdef CONFIG_X86_MCE_INTEL
|
|
|
|
void mce_intel_feature_init(struct cpuinfo_x86 *c);
|
|
|
|
#else
|
|
|
|
static inline void mce_intel_feature_init(struct cpuinfo_x86 *c)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2005-11-05 11:25:53 -05:00
|
|
|
#ifdef CONFIG_X86_MCE_AMD
|
|
|
|
void mce_amd_feature_init(struct cpuinfo_x86 *c);
|
|
|
|
#else
|
|
|
|
static inline void mce_amd_feature_init(struct cpuinfo_x86 *c)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2006-09-26 04:52:42 -04:00
|
|
|
void mce_log_therm_throt_event(unsigned int cpu, __u64 status);
|
|
|
|
|
2006-04-07 13:49:57 -04:00
|
|
|
extern atomic_t mce_entry;
|
|
|
|
|
2007-02-13 07:26:23 -05:00
|
|
|
extern void do_machine_check(struct pt_regs *, long);
|
|
|
|
|
x86_64: support poll() on /dev/mcelog
Background:
/dev/mcelog is typically polled manually. This is less than optimal for
situations where accurate accounting of MCEs is important. Calling
poll() on /dev/mcelog does not work.
Description:
This patch adds support for poll() to /dev/mcelog. This results in
immediate wakeup of user apps whenever the poller finds MCEs. Because
the exception handler can not take any locks, it can not call the wakeup
itself. Instead, it uses a thread_info flag (TIF_MCE_NOTIFY) which is
caught at the next return from interrupt or exit from idle, calling the
mce_user_notify() routine. This patch also disables the "fake panic"
path of the mce_panic(), because it results in printk()s in the exception
handler and crashy systems.
This patch also does some small cleanup for essentially unused variables,
and moves the user notification into the body of the poller, so it is
only called once per poll, rather than once per CPU.
Result:
Applications can now poll() on /dev/mcelog. When an error is logged
(whether through the poller or through an exception) the applications are
woken up promptly. This should not affect any previous behaviors. If no
MCEs are being logged, there is no overhead.
Alternatives:
I considered simply supporting poll() through the poller and not using
TIF_MCE_NOTIFY at all. However, the time between an uncorrectable error
happening and the user application being notified is *the*most* critical
window for us. Many uncorrectable errors can be logged to the network if
given a chance.
I also considered doing the MCE poll directly from the idle notifier, but
decided that was overkill.
Testing:
I used an error-injecting DIMM to create lots of correctable DRAM errors
and verified that my user app is woken up in sync with the polling interval.
I also used the northbridge to inject uncorrectable ECC errors, and
verified (printk() to the rescue) that the notify routine is called and the
user app does wake up. I built with PREEMPT on and off, and verified
that my machine survives MCEs.
[wli@holomorphy.com: build fix]
Signed-off-by: Tim Hockin <thockin@google.com>
Signed-off-by: William Irwin <bill.irwin@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-21 11:10:36 -04:00
|
|
|
extern int mce_notify_user(void);
|
|
|
|
|
2006-04-07 13:49:57 -04:00
|
|
|
#endif
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
#endif
|