linux/arch/x86/include/asm/mce.h

177 lines
5.5 KiB
C
Raw Normal View History

#ifndef _ASM_X86_MCE_H
#define _ASM_X86_MCE_H
#include <linux/types.h>
#include <asm/ioctls.h>
/*
* Machine Check support for x86
*/
#define MCG_BANKCNT_MASK 0xff /* Number of Banks */
#define MCG_CTL_P (1ULL<<8) /* MCG_CAP register available */
#define MCG_EXT_P (1ULL<<9) /* Extended registers available */
#define MCG_CMCI_P (1ULL<<10) /* CMCI supported */
#define MCG_EXT_CNT_MASK 0xff0000 /* Number of Extended registers */
#define MCG_EXT_CNT_SHIFT 16
#define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
#define MCG_SER_P (1ULL<<24) /* MCA recovery/new status bits */
#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 */
#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 */
#define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */
#define MCI_STATUS_AR (1ULL<<55) /* Action required */
/* MISC register defines */
#define MCM_ADDR_SEGOFF 0 /* segment offset */
#define MCM_ADDR_LINEAR 1 /* linear address */
#define MCM_ADDR_PHYS 2 /* physical address */
#define MCM_ADDR_MEM 3 /* memory address */
#define MCM_ADDR_GENERIC 7 /* generic */
/* Fields are zero when not available */
struct mce {
__u64 status;
__u64 misc;
__u64 addr;
__u64 mcgstatus;
__u64 ip;
__u64 tsc; /* cpu time stamp counter */
x86, mce: extend struct mce user interface with more information. Experience has shown that struct mce which is used to pass an machine check to the user space daemon currently a few limitations. Also some data which is useful to print at panic level is also missing. This patch addresses most of them. The same information is also printed out together with mce panic. struct mce can be painlessly extended in a compatible way, the mcelog user space code just ignores additional fields with a warning. - It doesn't provide a wall time timestamp. There have been a few complaints about that. Fix that by adding a 64bit time_t - It doesn't provide the exact CPU identification. This makes it awkward for mcelog to decode the event correctly, especially when there are variations in the supported MCE codes on different CPU models or when mcelog is running on a different host after a panic. Previously the administrator had to specify the correct CPU when mcelog ran on a different host, but with the more variation in machine checks now it's better to auto detect that. It's also useful for more detailed analysis of CPU events. Pass CPUID 1.EAX and the cpu vendor (as encoded in processor.h) instead. - Socket ID and initial APIC ID are useful to report because they allow to identify the failing CPU in some (not all) cases. This is also especially useful for the panic situation. This addresses one of the complaints from Thomas Gleixner earlier. - The MCG capabilities MSR needs to be reported for some advanced error processing in mcelog Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-05-27 21:56:56 +02:00
__u64 time; /* wall time_t when error was detected */
__u8 cpuvendor; /* cpu vendor as encoded in system.h */
__u8 pad1;
__u16 pad2;
__u32 cpuid; /* CPUID 1 EAX */
__u8 cs; /* code segment */
__u8 bank; /* machine check bank */
__u8 cpu; /* cpu number; obsolete; use extcpu now */
__u8 finished; /* entry is valid */
__u32 extcpu; /* linux cpu number that detected the error */
x86, mce: extend struct mce user interface with more information. Experience has shown that struct mce which is used to pass an machine check to the user space daemon currently a few limitations. Also some data which is useful to print at panic level is also missing. This patch addresses most of them. The same information is also printed out together with mce panic. struct mce can be painlessly extended in a compatible way, the mcelog user space code just ignores additional fields with a warning. - It doesn't provide a wall time timestamp. There have been a few complaints about that. Fix that by adding a 64bit time_t - It doesn't provide the exact CPU identification. This makes it awkward for mcelog to decode the event correctly, especially when there are variations in the supported MCE codes on different CPU models or when mcelog is running on a different host after a panic. Previously the administrator had to specify the correct CPU when mcelog ran on a different host, but with the more variation in machine checks now it's better to auto detect that. It's also useful for more detailed analysis of CPU events. Pass CPUID 1.EAX and the cpu vendor (as encoded in processor.h) instead. - Socket ID and initial APIC ID are useful to report because they allow to identify the failing CPU in some (not all) cases. This is also especially useful for the panic situation. This addresses one of the complaints from Thomas Gleixner earlier. - The MCG capabilities MSR needs to be reported for some advanced error processing in mcelog Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-05-27 21:56:56 +02:00
__u32 socketid; /* CPU socket ID */
__u32 apicid; /* CPU initial apic ID */
__u64 mcgcap; /* MCGCAP MSR: machine check capabilities of CPU */
};
/*
* 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 recordlen; /* length of struct mce */
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__
extern int mce_disabled;
#include <asm/atomic.h>
#include <linux/percpu.h>
void mce_setup(struct mce *m);
void mce_log(struct mce *m);
DECLARE_PER_CPU(struct sys_device, mce_dev);
extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
/*
* To support more than 128 would need to escape the predefined
* Linux defined extended banks first.
*/
#define MAX_NR_BANKS (MCE_EXTENDED_BANK - 1)
#ifdef CONFIG_X86_MCE_INTEL
void mce_intel_feature_init(struct cpuinfo_x86 *c);
x86, mce, cmci: add CMCI support Impact: Major new feature Intel CMCI (Corrected Machine Check Interrupt) is a new feature on Nehalem CPUs. It allows the CPU to trigger interrupts on corrected events, which allows faster reaction to them instead of with the traditional polling timer. Also use CMCI to discover shared banks. Machine check banks can be shared by CPU threads or even cores. Using the CMCI enable bit it is possible to detect the fact that another CPU already saw a specific bank. Use this to assign shared banks only to one CPU to avoid reporting duplicated events. On CPU hot unplug bank sharing is re discovered. This is done using a thread that cycles through all the CPUs. To avoid races between the poller and CMCI we only poll for banks that are not CMCI capable and only check CMCI owned banks on a interrupt. The shared banks ownership information is currently only used for CMCI interrupts, not polled banks. The sharing discovery code follows the algorithm recommended in the IA32 SDM Vol3a 14.5.2.1 The CMCI interrupt handler just calls the machine check poller to pick up the machine check event that caused the interrupt. I decided not to implement a separate threshold event like the AMD version has, because the threshold is always one currently and adding another event didn't seem to add any value. Some code inspired by Yunhong Jiang's Xen implementation, which was in term inspired by a earlier CMCI implementation by me. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-02-12 13:49:36 +01:00
void cmci_clear(void);
void cmci_reenable(void);
void cmci_rediscover(int dying);
void cmci_recheck(void);
#else
static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
x86, mce, cmci: add CMCI support Impact: Major new feature Intel CMCI (Corrected Machine Check Interrupt) is a new feature on Nehalem CPUs. It allows the CPU to trigger interrupts on corrected events, which allows faster reaction to them instead of with the traditional polling timer. Also use CMCI to discover shared banks. Machine check banks can be shared by CPU threads or even cores. Using the CMCI enable bit it is possible to detect the fact that another CPU already saw a specific bank. Use this to assign shared banks only to one CPU to avoid reporting duplicated events. On CPU hot unplug bank sharing is re discovered. This is done using a thread that cycles through all the CPUs. To avoid races between the poller and CMCI we only poll for banks that are not CMCI capable and only check CMCI owned banks on a interrupt. The shared banks ownership information is currently only used for CMCI interrupts, not polled banks. The sharing discovery code follows the algorithm recommended in the IA32 SDM Vol3a 14.5.2.1 The CMCI interrupt handler just calls the machine check poller to pick up the machine check event that caused the interrupt. I decided not to implement a separate threshold event like the AMD version has, because the threshold is always one currently and adding another event didn't seem to add any value. Some code inspired by Yunhong Jiang's Xen implementation, which was in term inspired by a earlier CMCI implementation by me. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-02-12 13:49:36 +01:00
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) {}
#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
int mce_available(struct cpuinfo_x86 *c);
x86, mce, cmci: add CMCI support Impact: Major new feature Intel CMCI (Corrected Machine Check Interrupt) is a new feature on Nehalem CPUs. It allows the CPU to trigger interrupts on corrected events, which allows faster reaction to them instead of with the traditional polling timer. Also use CMCI to discover shared banks. Machine check banks can be shared by CPU threads or even cores. Using the CMCI enable bit it is possible to detect the fact that another CPU already saw a specific bank. Use this to assign shared banks only to one CPU to avoid reporting duplicated events. On CPU hot unplug bank sharing is re discovered. This is done using a thread that cycles through all the CPUs. To avoid races between the poller and CMCI we only poll for banks that are not CMCI capable and only check CMCI owned banks on a interrupt. The shared banks ownership information is currently only used for CMCI interrupts, not polled banks. The sharing discovery code follows the algorithm recommended in the IA32 SDM Vol3a 14.5.2.1 The CMCI interrupt handler just calls the machine check poller to pick up the machine check event that caused the interrupt. I decided not to implement a separate threshold event like the AMD version has, because the threshold is always one currently and adding another event didn't seem to add any value. Some code inspired by Yunhong Jiang's Xen implementation, which was in term inspired by a earlier CMCI implementation by me. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-02-12 13:49:36 +01:00
DECLARE_PER_CPU(unsigned, mce_exception_count);
DECLARE_PER_CPU(unsigned, mce_poll_count);
void mce_log_therm_throt_event(__u64 status);
extern atomic_t mce_entry;
void do_machine_check(struct pt_regs *, long);
typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS);
DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
enum mcp_flags {
MCP_TIMESTAMP = (1 << 0), /* log time stamp */
MCP_UC = (1 << 1), /* log uncorrected errors */
MCP_DONTLOG = (1 << 2), /* only clear, don't log */
};
void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
int mce_notify_irq(void);
DECLARE_PER_CPU(struct mce, injectm);
extern struct file_operations mce_chrdev_ops;
#ifdef CONFIG_X86_MCE
void mcheck_init(struct cpuinfo_x86 *c);
#else
#define mcheck_init(c) do { } while (0)
#endif
extern void (*mce_threshold_vector)(void);
#endif /* __KERNEL__ */
#endif /* _ASM_X86_MCE_H */