2008-10-23 13:26:29 +08:00
|
|
|
#ifndef _ASM_X86_MCE_H
|
|
|
|
#define _ASM_X86_MCE_H
|
2007-10-18 00:04:40 +08:00
|
|
|
|
2009-01-31 01:17:27 +08:00
|
|
|
#include <linux/types.h>
|
2007-10-18 00:04:40 +08:00
|
|
|
#include <asm/ioctls.h>
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Machine Check support for x86
|
|
|
|
*/
|
|
|
|
|
2009-04-08 18:31:25 +08:00
|
|
|
#define MCG_CTL_P (1ULL<<8) /* MCG_CAP register available */
|
2009-02-12 20:49:35 +08:00
|
|
|
#define MCG_EXT_P (1ULL<<9) /* Extended registers available */
|
|
|
|
#define MCG_CMCI_P (1ULL<<10) /* CMCI supported */
|
2007-10-18 00:04:40 +08:00
|
|
|
|
2009-04-08 18:31:25 +08:00
|
|
|
#define MCG_STATUS_RIPV (1ULL<<0) /* restart ip valid */
|
|
|
|
#define MCG_STATUS_EIPV (1ULL<<1) /* ip points to correct instruction */
|
|
|
|
#define MCG_STATUS_MCIP (1ULL<<2) /* machine check in progress */
|
2007-10-18 00:04:40 +08:00
|
|
|
|
2009-04-08 18:31:25 +08:00
|
|
|
#define MCI_STATUS_VAL (1ULL<<63) /* valid error */
|
|
|
|
#define MCI_STATUS_OVER (1ULL<<62) /* previous errors lost */
|
|
|
|
#define MCI_STATUS_UC (1ULL<<61) /* uncorrected error */
|
|
|
|
#define MCI_STATUS_EN (1ULL<<60) /* error enabled */
|
|
|
|
#define MCI_STATUS_MISCV (1ULL<<59) /* misc error reg. valid */
|
|
|
|
#define MCI_STATUS_ADDRV (1ULL<<58) /* addr reg. valid */
|
|
|
|
#define MCI_STATUS_PCC (1ULL<<57) /* processor context corrupt */
|
2007-10-18 00:04:40 +08:00
|
|
|
|
|
|
|
/* Fields are zero when not available */
|
|
|
|
struct mce {
|
|
|
|
__u64 status;
|
|
|
|
__u64 misc;
|
|
|
|
__u64 addr;
|
|
|
|
__u64 mcgstatus;
|
2008-01-30 20:30:56 +08:00
|
|
|
__u64 ip;
|
2007-10-18 00:04:40 +08:00
|
|
|
__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
|
|
|
|
|
|
|
|
#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)
|
|
|
|
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
|
2007-10-11 17:20:03 +08:00
|
|
|
#ifdef CONFIG_X86_32
|
2007-10-18 00:04:40 +08:00
|
|
|
extern int mce_disabled;
|
2009-04-08 18:31:25 +08:00
|
|
|
#endif
|
2007-10-18 00:04:40 +08:00
|
|
|
|
|
|
|
#include <asm/atomic.h>
|
|
|
|
|
2009-02-12 20:43:22 +08:00
|
|
|
void mce_setup(struct mce *m);
|
2007-10-18 00:04:40 +08:00
|
|
|
void mce_log(struct mce *m);
|
|
|
|
DECLARE_PER_CPU(struct sys_device, device_mce);
|
x86 MCE: Fix CPU hotplug problem with multiple multicore AMD CPUs
During CPU hot-remove the sysfs directory created by
threshold_create_bank(), defined in
arch/x86/kernel/cpu/mcheck/mce_amd_64.c, has to be removed before
its parent directory, created by mce_create_device(), defined in
arch/x86/kernel/cpu/mcheck/mce_64.c . Moreover, when the CPU in
question is hotplugged again, obviously the latter has to be created
before the former. At present, the right ordering is not enforced,
because all of these operations are carried out by CPU hotplug
notifiers which are not appropriately ordered with respect to each
other. This leads to serious problems on systems with two or more
multicore AMD CPUs, among other things during suspend and hibernation.
Fix the problem by placing threshold bank CPU hotplug callbacks in
mce_cpu_callback(), so that they are invoked at the right places,
if defined. Additionally, use kobject_del() to remove the sysfs
directory associated with the kobject created by
kobject_create_and_add() in threshold_create_bank(), to prevent the
kernel from crashing during CPU hotplug operations on systems with
two or more multicore AMD CPUs.
This patch fixes bug #11337.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Andi Kleen <andi@firstfloor.org>
Tested-by: Mark Langsdorf <mark.langsdorf@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-23 04:23:09 +08:00
|
|
|
extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
|
2007-10-18 00:04:40 +08:00
|
|
|
|
2009-02-12 20:49:30 +08:00
|
|
|
/*
|
|
|
|
* To support more than 128 would need to escape the predefined
|
|
|
|
* Linux defined extended banks first.
|
|
|
|
*/
|
|
|
|
#define MAX_NR_BANKS (MCE_EXTENDED_BANK - 1)
|
|
|
|
|
2007-10-18 00:04:40 +08:00
|
|
|
#ifdef CONFIG_X86_MCE_INTEL
|
|
|
|
void mce_intel_feature_init(struct cpuinfo_x86 *c);
|
2009-02-12 20:49:36 +08:00
|
|
|
void cmci_clear(void);
|
|
|
|
void cmci_reenable(void);
|
|
|
|
void cmci_rediscover(int dying);
|
|
|
|
void cmci_recheck(void);
|
2007-10-18 00:04:40 +08:00
|
|
|
#else
|
|
|
|
static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
|
2009-02-12 20:49:36 +08:00
|
|
|
static inline void cmci_clear(void) {}
|
|
|
|
static inline void cmci_reenable(void) {}
|
|
|
|
static inline void cmci_rediscover(int dying) {}
|
|
|
|
static inline void cmci_recheck(void) {}
|
2007-10-18 00:04:40 +08:00
|
|
|
#endif
|
|
|
|
|
|
|
|
#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
|
|
|
|
|
2009-02-12 20:49:36 +08:00
|
|
|
extern int mce_available(struct cpuinfo_x86 *c);
|
|
|
|
|
2009-02-12 20:43:22 +08:00
|
|
|
void mce_log_therm_throt_event(__u64 status);
|
2007-10-18 00:04:40 +08:00
|
|
|
|
|
|
|
extern atomic_t mce_entry;
|
|
|
|
|
|
|
|
extern void do_machine_check(struct pt_regs *, long);
|
2009-02-12 20:43:23 +08:00
|
|
|
|
2009-02-12 20:49:34 +08:00
|
|
|
typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS);
|
|
|
|
DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
|
|
|
|
|
2009-02-12 20:43:23 +08:00
|
|
|
enum mcp_flags {
|
|
|
|
MCP_TIMESTAMP = (1 << 0), /* log time stamp */
|
|
|
|
MCP_UC = (1 << 1), /* log uncorrected errors */
|
2009-04-07 23:06:55 +08:00
|
|
|
MCP_DONTLOG = (1 << 2), /* only clear, don't log */
|
2009-02-12 20:43:23 +08:00
|
|
|
};
|
2009-02-12 20:49:34 +08:00
|
|
|
extern void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
|
2009-02-12 20:43:23 +08:00
|
|
|
|
2007-10-18 00:04:40 +08:00
|
|
|
extern int mce_notify_user(void);
|
|
|
|
|
2008-01-30 20:30:17 +08:00
|
|
|
#ifdef CONFIG_X86_MCE
|
|
|
|
extern void mcheck_init(struct cpuinfo_x86 *c);
|
|
|
|
#else
|
|
|
|
#define mcheck_init(c) do { } while (0)
|
|
|
|
#endif
|
2007-10-18 00:04:40 +08:00
|
|
|
|
2009-02-12 20:49:31 +08:00
|
|
|
extern void (*mce_threshold_vector)(void);
|
|
|
|
|
2007-10-18 00:04:40 +08:00
|
|
|
#endif /* __KERNEL__ */
|
2008-10-23 13:26:29 +08:00
|
|
|
#endif /* _ASM_X86_MCE_H */
|