2008-10-23 05:26:29 +00:00
|
|
|
#ifndef _ASM_X86_MCE_H
|
|
|
|
#define _ASM_X86_MCE_H
|
2007-10-17 16:04:40 +00:00
|
|
|
|
2012-12-14 22:37:13 +00:00
|
|
|
#include <uapi/asm/mce.h>
|
2007-10-17 16:04:40 +00:00
|
|
|
|
2012-12-21 16:03:58 +00:00
|
|
|
/*
|
|
|
|
* Machine Check support for x86
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* MCG_CAP register defines */
|
|
|
|
#define MCG_BANKCNT_MASK 0xff /* Number of Banks */
|
|
|
|
#define MCG_CTL_P (1ULL<<8) /* MCG_CTL 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 */
|
2013-10-21 21:29:25 +00:00
|
|
|
#define MCG_ELOG_P (1ULL<<26) /* Extended error log supported */
|
2015-06-04 16:55:22 +00:00
|
|
|
#define MCG_LMCE_P (1ULL<<27) /* Local machine check supported */
|
2012-12-21 16:03:58 +00:00
|
|
|
|
|
|
|
/* MCG_STATUS register defines */
|
|
|
|
#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 */
|
2015-06-04 16:55:22 +00:00
|
|
|
#define MCG_STATUS_LMCES (1ULL<<3) /* LMCE signaled */
|
|
|
|
|
|
|
|
/* MCG_EXT_CTL register defines */
|
|
|
|
#define MCG_EXT_CTL_LMCE_EN (1ULL<<0) /* Enable LMCE */
|
2012-12-21 16:03:58 +00:00
|
|
|
|
|
|
|
/* MCi_STATUS register defines */
|
|
|
|
#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 */
|
2013-07-24 20:54:20 +00:00
|
|
|
|
2014-11-18 02:09:19 +00:00
|
|
|
/* AMD-specific bits */
|
2016-09-12 07:59:28 +00:00
|
|
|
#define MCI_STATUS_TCC (1ULL<<55) /* Task context corrupt */
|
|
|
|
#define MCI_STATUS_SYNDV (1ULL<<53) /* synd reg. valid */
|
2016-03-07 13:02:20 +00:00
|
|
|
#define MCI_STATUS_DEFERRED (1ULL<<44) /* uncorrected error, deferred exception */
|
2014-11-18 02:09:19 +00:00
|
|
|
#define MCI_STATUS_POISON (1ULL<<43) /* access poisonous data */
|
2016-03-07 13:02:18 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* McaX field if set indicates a given bank supports MCA extensions:
|
|
|
|
* - Deferred error interrupt type is specifiable by bank.
|
|
|
|
* - MCx_MISC0[BlkPtr] field indicates presence of extended MISC registers,
|
|
|
|
* But should not be used to determine MSR numbers.
|
|
|
|
* - TCC bit is present in MCx_STATUS.
|
|
|
|
*/
|
|
|
|
#define MCI_CONFIG_MCAX 0x1
|
|
|
|
#define MCI_IPID_MCATYPE 0xFFFF0000
|
|
|
|
#define MCI_IPID_HWID 0xFFF
|
2014-11-18 02:09:19 +00:00
|
|
|
|
2013-07-24 20:54:20 +00:00
|
|
|
/*
|
|
|
|
* Note that the full MCACOD field of IA32_MCi_STATUS MSR is
|
|
|
|
* bits 15:0. But bit 12 is the 'F' bit, defined for corrected
|
|
|
|
* errors to indicate that errors are being filtered by hardware.
|
|
|
|
* We should mask out bit 12 when looking for specific signatures
|
|
|
|
* of uncorrected errors - so the F bit is deliberately skipped
|
|
|
|
* in this #define.
|
|
|
|
*/
|
|
|
|
#define MCACOD 0xefff /* MCA Error Code */
|
2012-12-21 16:03:58 +00:00
|
|
|
|
|
|
|
/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */
|
|
|
|
#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */
|
2013-07-24 20:54:20 +00:00
|
|
|
#define MCACOD_SCRUBMSK 0xeff0 /* Skip bit 12 ('F' bit) */
|
2012-12-21 16:03:58 +00:00
|
|
|
#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */
|
|
|
|
#define MCACOD_DATA 0x0134 /* Data Load */
|
|
|
|
#define MCACOD_INSTR 0x0150 /* Instruction Fetch */
|
|
|
|
|
|
|
|
/* MCi_MISC register defines */
|
|
|
|
#define MCI_MISC_ADDR_LSB(m) ((m) & 0x3f)
|
|
|
|
#define MCI_MISC_ADDR_MODE(m) (((m) >> 6) & 7)
|
|
|
|
#define MCI_MISC_ADDR_SEGOFF 0 /* segment offset */
|
|
|
|
#define MCI_MISC_ADDR_LINEAR 1 /* linear address */
|
|
|
|
#define MCI_MISC_ADDR_PHYS 2 /* physical address */
|
|
|
|
#define MCI_MISC_ADDR_MEM 3 /* memory address */
|
|
|
|
#define MCI_MISC_ADDR_GENERIC 7 /* generic */
|
|
|
|
|
|
|
|
/* CTL2 register defines */
|
|
|
|
#define MCI_CTL2_CMCI_EN (1ULL << 30)
|
|
|
|
#define MCI_CTL2_CMCI_THRESHOLD_MASK 0x7fffULL
|
|
|
|
|
|
|
|
#define MCJ_CTX_MASK 3
|
|
|
|
#define MCJ_CTX(flags) ((flags) & MCJ_CTX_MASK)
|
|
|
|
#define MCJ_CTX_RANDOM 0 /* inject context: random */
|
|
|
|
#define MCJ_CTX_PROCESS 0x1 /* inject context: process */
|
|
|
|
#define MCJ_CTX_IRQ 0x2 /* inject context: IRQ */
|
|
|
|
#define MCJ_NMI_BROADCAST 0x4 /* do NMI broadcasting */
|
|
|
|
#define MCJ_EXCEPTION 0x8 /* raise as exception */
|
2013-06-04 18:54:14 +00:00
|
|
|
#define MCJ_IRQ_BROADCAST 0x10 /* do IRQ broadcasting */
|
2012-12-21 16:03:58 +00:00
|
|
|
|
|
|
|
#define MCE_OVERFLOW 0 /* bit 0 in flags means overflow */
|
|
|
|
|
|
|
|
/* Software defined banks */
|
|
|
|
#define MCE_EXTENDED_BANK 128
|
|
|
|
#define MCE_THERMAL_BANK (MCE_EXTENDED_BANK + 0)
|
|
|
|
|
|
|
|
#define MCE_LOG_LEN 32
|
|
|
|
#define MCE_LOG_SIGNATURE "MACHINECHECK"
|
|
|
|
|
2016-03-07 13:02:17 +00:00
|
|
|
/* AMD Scalable MCA */
|
2016-04-30 12:33:54 +00:00
|
|
|
#define MSR_AMD64_SMCA_MC0_CTL 0xc0002000
|
|
|
|
#define MSR_AMD64_SMCA_MC0_STATUS 0xc0002001
|
|
|
|
#define MSR_AMD64_SMCA_MC0_ADDR 0xc0002002
|
2016-03-07 13:02:19 +00:00
|
|
|
#define MSR_AMD64_SMCA_MC0_MISC0 0xc0002003
|
2016-03-07 13:02:17 +00:00
|
|
|
#define MSR_AMD64_SMCA_MC0_CONFIG 0xc0002004
|
2016-03-07 13:02:18 +00:00
|
|
|
#define MSR_AMD64_SMCA_MC0_IPID 0xc0002005
|
2016-09-12 07:59:28 +00:00
|
|
|
#define MSR_AMD64_SMCA_MC0_SYND 0xc0002006
|
2016-05-11 12:58:23 +00:00
|
|
|
#define MSR_AMD64_SMCA_MC0_DESTAT 0xc0002008
|
|
|
|
#define MSR_AMD64_SMCA_MC0_DEADDR 0xc0002009
|
2016-03-07 13:02:19 +00:00
|
|
|
#define MSR_AMD64_SMCA_MC0_MISC1 0xc000200a
|
2016-04-30 12:33:54 +00:00
|
|
|
#define MSR_AMD64_SMCA_MCx_CTL(x) (MSR_AMD64_SMCA_MC0_CTL + 0x10*(x))
|
|
|
|
#define MSR_AMD64_SMCA_MCx_STATUS(x) (MSR_AMD64_SMCA_MC0_STATUS + 0x10*(x))
|
|
|
|
#define MSR_AMD64_SMCA_MCx_ADDR(x) (MSR_AMD64_SMCA_MC0_ADDR + 0x10*(x))
|
2016-03-07 13:02:19 +00:00
|
|
|
#define MSR_AMD64_SMCA_MCx_MISC(x) (MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x))
|
2016-03-07 13:02:17 +00:00
|
|
|
#define MSR_AMD64_SMCA_MCx_CONFIG(x) (MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x))
|
2016-03-07 13:02:18 +00:00
|
|
|
#define MSR_AMD64_SMCA_MCx_IPID(x) (MSR_AMD64_SMCA_MC0_IPID + 0x10*(x))
|
2016-09-12 07:59:28 +00:00
|
|
|
#define MSR_AMD64_SMCA_MCx_SYND(x) (MSR_AMD64_SMCA_MC0_SYND + 0x10*(x))
|
2016-05-11 12:58:23 +00:00
|
|
|
#define MSR_AMD64_SMCA_MCx_DESTAT(x) (MSR_AMD64_SMCA_MC0_DESTAT + 0x10*(x))
|
|
|
|
#define MSR_AMD64_SMCA_MCx_DEADDR(x) (MSR_AMD64_SMCA_MC0_DEADDR + 0x10*(x))
|
2016-03-07 13:02:19 +00:00
|
|
|
#define MSR_AMD64_SMCA_MCx_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x)))
|
2016-03-07 13:02:17 +00:00
|
|
|
|
2012-12-21 16:03:58 +00:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
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];
|
|
|
|
};
|
2012-10-15 16:03:57 +00:00
|
|
|
|
|
|
|
struct mca_config {
|
|
|
|
bool dont_log_ce;
|
2012-10-15 18:25:17 +00:00
|
|
|
bool cmci_disabled;
|
2015-06-04 16:55:23 +00:00
|
|
|
bool lmce_disabled;
|
2012-10-15 18:25:17 +00:00
|
|
|
bool ignore_ce;
|
2012-10-17 10:05:33 +00:00
|
|
|
bool disabled;
|
|
|
|
bool ser;
|
2016-02-17 18:20:13 +00:00
|
|
|
bool recovery;
|
2012-10-17 10:05:33 +00:00
|
|
|
bool bios_cmci_threshold;
|
2012-10-15 16:03:57 +00:00
|
|
|
u8 banks;
|
2012-10-15 17:59:18 +00:00
|
|
|
s8 bootlog;
|
2012-10-15 16:03:57 +00:00
|
|
|
int tolerant;
|
2012-10-15 17:59:18 +00:00
|
|
|
int monarch_timeout;
|
2012-10-15 18:25:17 +00:00
|
|
|
int panic_timeout;
|
2012-10-15 17:59:18 +00:00
|
|
|
u32 rip_msr;
|
2012-10-15 16:03:57 +00:00
|
|
|
};
|
|
|
|
|
2015-03-23 15:42:52 +00:00
|
|
|
struct mce_vendor_flags {
|
2015-10-30 12:11:37 +00:00
|
|
|
/*
|
|
|
|
* Indicates that overflow conditions are not fatal, when set.
|
|
|
|
*/
|
|
|
|
__u64 overflow_recov : 1,
|
|
|
|
|
|
|
|
/*
|
|
|
|
* (AMD) SUCCOR stands for S/W UnCorrectable error COntainment and
|
|
|
|
* Recovery. It indicates support for data poisoning in HW and deferred
|
|
|
|
* error interrupts.
|
|
|
|
*/
|
|
|
|
succor : 1,
|
|
|
|
|
|
|
|
/*
|
|
|
|
* (AMD) SMCA: This bit indicates support for Scalable MCA which expands
|
|
|
|
* the register space for each MCA bank and also increases number of
|
|
|
|
* banks. Also, to accommodate the new banks and registers, the MCA
|
|
|
|
* register space is moved to a new MSR range.
|
|
|
|
*/
|
|
|
|
smca : 1,
|
|
|
|
|
|
|
|
__reserved_0 : 61;
|
2015-03-23 15:42:52 +00:00
|
|
|
};
|
2016-04-30 12:33:54 +00:00
|
|
|
|
|
|
|
struct mca_msr_regs {
|
|
|
|
u32 (*ctl) (int bank);
|
|
|
|
u32 (*status) (int bank);
|
|
|
|
u32 (*addr) (int bank);
|
|
|
|
u32 (*misc) (int bank);
|
|
|
|
};
|
|
|
|
|
2015-03-23 15:42:52 +00:00
|
|
|
extern struct mce_vendor_flags mce_flags;
|
|
|
|
|
2012-10-15 18:25:17 +00:00
|
|
|
extern struct mca_config mca_cfg;
|
2016-04-30 12:33:54 +00:00
|
|
|
extern struct mca_msr_regs msr_ops;
|
2015-08-12 16:29:38 +00:00
|
|
|
extern void mce_register_decode_chain(struct notifier_block *nb);
|
2011-12-04 14:12:09 +00:00
|
|
|
extern void mce_unregister_decode_chain(struct notifier_block *nb);
|
2010-01-04 16:17:21 +00:00
|
|
|
|
2009-06-15 08:22:15 +00:00
|
|
|
#include <linux/percpu.h>
|
2011-07-26 23:09:06 +00:00
|
|
|
#include <linux/atomic.h>
|
2009-06-15 08:22:15 +00:00
|
|
|
|
2009-06-15 08:22:49 +00:00
|
|
|
extern int mce_p5_enabled;
|
2007-10-17 16:04:40 +00:00
|
|
|
|
2009-06-15 08:27:47 +00:00
|
|
|
#ifdef CONFIG_X86_MCE
|
2009-11-10 01:38:24 +00:00
|
|
|
int mcheck_init(void);
|
2009-10-16 10:31:32 +00:00
|
|
|
void mcheck_cpu_init(struct cpuinfo_x86 *c);
|
2015-08-12 16:29:40 +00:00
|
|
|
void mcheck_cpu_clear(struct cpuinfo_x86 *c);
|
2015-03-23 15:42:53 +00:00
|
|
|
void mcheck_vendor_init_severity(void);
|
2009-06-15 08:27:47 +00:00
|
|
|
#else
|
2009-11-10 01:38:24 +00:00
|
|
|
static inline int mcheck_init(void) { return 0; }
|
2009-10-16 10:31:32 +00:00
|
|
|
static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {}
|
2015-08-12 16:29:40 +00:00
|
|
|
static inline void mcheck_cpu_clear(struct cpuinfo_x86 *c) {}
|
2015-03-23 15:42:53 +00:00
|
|
|
static inline void mcheck_vendor_init_severity(void) {}
|
2009-06-15 08:27:47 +00:00
|
|
|
#endif
|
|
|
|
|
2009-06-15 08:22:15 +00:00
|
|
|
#ifdef CONFIG_X86_ANCIENT_MCE
|
|
|
|
void intel_p5_mcheck_init(struct cpuinfo_x86 *c);
|
|
|
|
void winchip_mcheck_init(struct cpuinfo_x86 *c);
|
2009-06-15 08:22:49 +00:00
|
|
|
static inline void enable_p5_mce(void) { mce_p5_enabled = 1; }
|
2009-06-15 08:22:15 +00:00
|
|
|
#else
|
|
|
|
static inline void intel_p5_mcheck_init(struct cpuinfo_x86 *c) {}
|
|
|
|
static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {}
|
2009-06-15 08:22:49 +00:00
|
|
|
static inline void enable_p5_mce(void) {}
|
2009-06-15 08:22:15 +00:00
|
|
|
#endif
|
|
|
|
|
2009-02-12 12:43:22 +00:00
|
|
|
void mce_setup(struct mce *m);
|
2007-10-17 16:04:40 +00:00
|
|
|
void mce_log(struct mce *m);
|
2012-01-26 23:49:14 +00:00
|
|
|
DECLARE_PER_CPU(struct device *, mce_device);
|
2007-10-17 16:04:40 +00:00
|
|
|
|
2009-02-12 12:49:30 +00:00
|
|
|
/*
|
2009-07-08 22:31:45 +00:00
|
|
|
* Maximum banks number.
|
|
|
|
* This is the limit of the current register layout on
|
|
|
|
* Intel CPUs.
|
2009-02-12 12:49:30 +00:00
|
|
|
*/
|
2009-07-08 22:31:45 +00:00
|
|
|
#define MAX_NR_BANKS 32
|
2009-02-12 12:49:30 +00:00
|
|
|
|
2007-10-17 16:04:40 +00:00
|
|
|
#ifdef CONFIG_X86_MCE_INTEL
|
|
|
|
void mce_intel_feature_init(struct cpuinfo_x86 *c);
|
2015-08-12 16:29:40 +00:00
|
|
|
void mce_intel_feature_clear(struct cpuinfo_x86 *c);
|
2009-02-12 12:49:36 +00:00
|
|
|
void cmci_clear(void);
|
|
|
|
void cmci_reenable(void);
|
2013-03-20 10:01:29 +00:00
|
|
|
void cmci_rediscover(void);
|
2009-02-12 12:49:36 +00:00
|
|
|
void cmci_recheck(void);
|
2007-10-17 16:04:40 +00:00
|
|
|
#else
|
|
|
|
static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
|
2015-08-12 16:29:40 +00:00
|
|
|
static inline void mce_intel_feature_clear(struct cpuinfo_x86 *c) { }
|
2009-02-12 12:49:36 +00:00
|
|
|
static inline void cmci_clear(void) {}
|
|
|
|
static inline void cmci_reenable(void) {}
|
2013-03-20 10:01:29 +00:00
|
|
|
static inline void cmci_rediscover(void) {}
|
2009-02-12 12:49:36 +00:00
|
|
|
static inline void cmci_recheck(void) {}
|
2007-10-17 16:04:40 +00:00
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifdef CONFIG_X86_MCE_AMD
|
|
|
|
void mce_amd_feature_init(struct cpuinfo_x86 *c);
|
2016-11-17 22:57:27 +00:00
|
|
|
int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr);
|
2007-10-17 16:04:40 +00:00
|
|
|
#else
|
|
|
|
static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
|
2016-11-17 22:57:27 +00:00
|
|
|
static inline int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) { return -EINVAL; };
|
2007-10-17 16:04:40 +00:00
|
|
|
#endif
|
|
|
|
|
2009-05-28 17:05:33 +00:00
|
|
|
int mce_available(struct cpuinfo_x86 *c);
|
2009-02-12 12:49:36 +00:00
|
|
|
|
2009-05-27 19:56:52 +00:00
|
|
|
DECLARE_PER_CPU(unsigned, mce_exception_count);
|
2009-05-27 19:56:57 +00:00
|
|
|
DECLARE_PER_CPU(unsigned, mce_poll_count);
|
2009-05-27 19:56:52 +00:00
|
|
|
|
2009-02-12 12:49:34 +00:00
|
|
|
typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS);
|
|
|
|
DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
|
|
|
|
|
2009-02-12 12:43:23 +00:00
|
|
|
enum mcp_flags {
|
x86/MCE/intel: Cleanup CMCI storm logic
Initially, this started with the yet another report about a race
condition in the CMCI storm adaptive period length thing. Yes, we have
to admit, it is fragile and error prone. So let's simplify it.
The simpler logic is: now, after we enter storm mode, we go straight to
polling with CMCI_STORM_INTERVAL, i.e. once a second. We remain in storm
mode as long as we see errors being logged while polling.
Theoretically, if we see an uninterrupted error stream, we will remain
in storm mode indefinitely and keep polling the MSRs.
However, when the storm is actually a burst of errors, once we have
logged them all, we back out of it after ~5 mins of polling and no more
errors logged.
If we encounter an error during those 5 minutes, we reset the polling
interval to 5 mins.
Making machine_check_poll() return a bool and denoting whether it has
seen an error or not lets us simplify a bunch of code and move the storm
handling private to mce_intel.c.
Some minor cleanups while at it.
Reported-by: Calvin Owens <calvinowens@fb.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: http://lkml.kernel.org/r/1417746575-23299-1-git-send-email-calvinowens@fb.com
Signed-off-by: Borislav Petkov <bp@suse.de>
2015-01-13 14:08:51 +00:00
|
|
|
MCP_TIMESTAMP = BIT(0), /* log time stamp */
|
|
|
|
MCP_UC = BIT(1), /* log uncorrected errors */
|
|
|
|
MCP_DONTLOG = BIT(2), /* only clear, don't log */
|
2009-02-12 12:43:23 +00:00
|
|
|
};
|
x86/MCE/intel: Cleanup CMCI storm logic
Initially, this started with the yet another report about a race
condition in the CMCI storm adaptive period length thing. Yes, we have
to admit, it is fragile and error prone. So let's simplify it.
The simpler logic is: now, after we enter storm mode, we go straight to
polling with CMCI_STORM_INTERVAL, i.e. once a second. We remain in storm
mode as long as we see errors being logged while polling.
Theoretically, if we see an uninterrupted error stream, we will remain
in storm mode indefinitely and keep polling the MSRs.
However, when the storm is actually a burst of errors, once we have
logged them all, we back out of it after ~5 mins of polling and no more
errors logged.
If we encounter an error during those 5 minutes, we reset the polling
interval to 5 mins.
Making machine_check_poll() return a bool and denoting whether it has
seen an error or not lets us simplify a bunch of code and move the storm
handling private to mce_intel.c.
Some minor cleanups while at it.
Reported-by: Calvin Owens <calvinowens@fb.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: http://lkml.kernel.org/r/1417746575-23299-1-git-send-email-calvinowens@fb.com
Signed-off-by: Borislav Petkov <bp@suse.de>
2015-01-13 14:08:51 +00:00
|
|
|
bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
|
2009-02-12 12:43:23 +00:00
|
|
|
|
2009-05-27 19:56:58 +00:00
|
|
|
int mce_notify_irq(void);
|
2007-10-17 16:04:40 +00:00
|
|
|
|
2009-04-29 17:31:00 +00:00
|
|
|
DECLARE_PER_CPU(struct mce, injectm);
|
2011-11-03 18:46:47 +00:00
|
|
|
|
|
|
|
extern void register_mce_write_callback(ssize_t (*)(struct file *filp,
|
|
|
|
const char __user *ubuf,
|
|
|
|
size_t usize, loff_t *off));
|
2009-04-29 17:31:00 +00:00
|
|
|
|
2013-07-01 15:38:47 +00:00
|
|
|
/* Disable CMCI/polling for MCA bank claimed by firmware */
|
|
|
|
extern void mce_disable_bank(int bank);
|
|
|
|
|
2009-06-15 08:27:47 +00:00
|
|
|
/*
|
|
|
|
* Exception handler
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* Call the installed machine check handler for this CPU setup. */
|
|
|
|
extern void (*machine_check_vector)(struct pt_regs *, long error_code);
|
|
|
|
void do_machine_check(struct pt_regs *, long);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Threshold handler
|
|
|
|
*/
|
2007-10-17 16:04:40 +00:00
|
|
|
|
2009-02-12 12:49:31 +00:00
|
|
|
extern void (*mce_threshold_vector)(void);
|
2009-06-15 08:27:47 +00:00
|
|
|
extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
|
2009-02-12 12:49:31 +00:00
|
|
|
|
2015-05-06 11:58:56 +00:00
|
|
|
/* Deferred error interrupt handler */
|
|
|
|
extern void (*deferred_error_int_vector)(void);
|
|
|
|
|
2009-06-15 08:24:40 +00:00
|
|
|
/*
|
|
|
|
* Thermal handler
|
|
|
|
*/
|
|
|
|
|
|
|
|
void intel_init_thermal(struct cpuinfo_x86 *c);
|
|
|
|
|
|
|
|
void mce_log_therm_throt_event(__u64 status);
|
2009-11-10 01:38:24 +00:00
|
|
|
|
2011-01-03 11:52:04 +00:00
|
|
|
/* Interrupt Handler for core thermal thresholds */
|
|
|
|
extern int (*platform_thermal_notify)(__u64 msr_val);
|
|
|
|
|
2013-05-17 23:42:01 +00:00
|
|
|
/* Interrupt Handler for package thermal thresholds */
|
|
|
|
extern int (*platform_thermal_package_notify)(__u64 msr_val);
|
|
|
|
|
|
|
|
/* Callback support of rate control, return true, if
|
|
|
|
* callback has rate control */
|
|
|
|
extern bool (*platform_thermal_package_rate_control)(void);
|
|
|
|
|
2009-11-10 01:38:24 +00:00
|
|
|
#ifdef CONFIG_X86_THERMAL_VECTOR
|
|
|
|
extern void mcheck_intel_therm_init(void);
|
|
|
|
#else
|
|
|
|
static inline void mcheck_intel_therm_init(void) { }
|
|
|
|
#endif
|
|
|
|
|
ACPI, APEI, Generic Hardware Error Source memory error support
Generic Hardware Error Source provides a way to report platform
hardware errors (such as that from chipset). It works in so called
"Firmware First" mode, that is, hardware errors are reported to
firmware firstly, then reported to Linux by firmware. This way, some
non-standard hardware error registers or non-standard hardware link
can be checked by firmware to produce more valuable hardware error
information for Linux.
Now, only SCI notification type and memory errors are supported. More
notification type and hardware error type will be added later. These
memory errors are reported to user space through /dev/mcelog via
faking a corrected Machine Check, so that the error memory page can be
offlined by /sbin/mcelog if the error count for one page is beyond the
threshold.
On some machines, Machine Check can not report physical address for
some corrected memory errors, but GHES can do that. So this simplified
GHES is implemented firstly.
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>
2010-05-18 06:35:20 +00:00
|
|
|
/*
|
|
|
|
* Used by APEI to report memory error via /dev/mcelog
|
|
|
|
*/
|
|
|
|
|
|
|
|
struct cper_sec_mem_err;
|
|
|
|
extern void apei_mce_report_mem_error(int corrected,
|
|
|
|
struct cper_sec_mem_err *mem_err);
|
|
|
|
|
2016-03-07 13:02:18 +00:00
|
|
|
/*
|
|
|
|
* Enumerate new IP types and HWID values in AMD processors which support
|
|
|
|
* Scalable MCA.
|
|
|
|
*/
|
|
|
|
#ifdef CONFIG_X86_MCE_AMD
|
|
|
|
|
2016-09-12 07:59:34 +00:00
|
|
|
/* These may be used by multiple smca_hwid_mcatypes */
|
|
|
|
enum smca_bank_types {
|
2016-03-07 13:02:18 +00:00
|
|
|
SMCA_LS = 0, /* Load Store */
|
|
|
|
SMCA_IF, /* Instruction Fetch */
|
2016-09-12 07:59:34 +00:00
|
|
|
SMCA_L2_CACHE, /* L2 Cache */
|
|
|
|
SMCA_DE, /* Decoder Unit */
|
|
|
|
SMCA_EX, /* Execution Unit */
|
2016-03-07 13:02:18 +00:00
|
|
|
SMCA_FP, /* Floating Point */
|
2016-09-12 07:59:34 +00:00
|
|
|
SMCA_L3_CACHE, /* L3 Cache */
|
|
|
|
SMCA_CS, /* Coherent Slave */
|
|
|
|
SMCA_PIE, /* Power, Interrupts, etc. */
|
|
|
|
SMCA_UMC, /* Unified Memory Controller */
|
|
|
|
SMCA_PB, /* Parameter Block */
|
|
|
|
SMCA_PSP, /* Platform Security Processor */
|
|
|
|
SMCA_SMU, /* System Management Unit */
|
|
|
|
N_SMCA_BANK_TYPES
|
|
|
|
};
|
|
|
|
|
x86/mce/AMD: Fix HWID_MCATYPE calculation by grouping arguments
The calculation of the hwid_mcatype value in get_smca_bank_info()
became incorrect after applying the following commit:
1ce9cd7f9f0b ("x86/RAS: Simplify SMCA HWID descriptor struct")
This causes the function to not match a bank to its type.
Disassembly of hwid_mcatype calculation after change:
db: 8b 45 e0 mov -0x20(%rbp),%eax
de: 41 89 c4 mov %eax,%r12d
e1: 25 00 00 ff 0f and $0xfff0000,%eax
e6: 41 c1 ec 10 shr $0x10,%r12d
ea: 41 09 c4 or %eax,%r12d
Disassembly of hwid_mcatype calculation in original code:
286: 8b 45 d0 mov -0x30(%rbp),%eax
289: 41 89 c5 mov %eax,%r13d
28c: c1 e8 10 shr $0x10,%eax
28f: 41 81 e5 ff 0f 00 00 and $0xfff,%r13d
296: 41 c1 e5 10 shl $0x10,%r13d
29a: 41 09 c5 or %eax,%r13d
Grouping the arguments to the HWID_MCATYPE() macro fixes the issue.
( Boris suggested adding parentheses in the macro. )
Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com>
Cc: Aravind Gopalakrishnan <aravindksg.lkml@gmail.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-edac@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-11-10 20:32:35 +00:00
|
|
|
#define HWID_MCATYPE(hwid, mcatype) (((hwid) << 16) | (mcatype))
|
2016-03-07 13:02:18 +00:00
|
|
|
|
2016-11-02 11:48:01 +00:00
|
|
|
struct smca_hwid {
|
2016-09-12 07:59:34 +00:00
|
|
|
unsigned int bank_type; /* Use with smca_bank_types for easy indexing. */
|
|
|
|
u32 hwid_mcatype; /* (hwid,mcatype) tuple */
|
|
|
|
u32 xec_bitmap; /* Bitmap of valid ExtErrorCodes; current max is 21. */
|
2016-03-07 13:02:18 +00:00
|
|
|
};
|
|
|
|
|
2016-11-01 16:33:00 +00:00
|
|
|
struct smca_bank {
|
2016-11-02 11:48:01 +00:00
|
|
|
struct smca_hwid *hwid;
|
2016-11-01 16:33:00 +00:00
|
|
|
/* Instance ID */
|
|
|
|
u32 id;
|
2016-09-12 07:59:34 +00:00
|
|
|
};
|
|
|
|
|
2016-11-01 16:33:00 +00:00
|
|
|
extern struct smca_bank smca_banks[MAX_NR_BANKS];
|
2016-09-12 07:59:34 +00:00
|
|
|
|
2016-11-03 20:12:33 +00:00
|
|
|
extern const char *smca_get_long_name(enum smca_bank_types t);
|
2016-03-07 13:02:18 +00:00
|
|
|
#endif
|
|
|
|
|
2008-10-23 05:26:29 +00:00
|
|
|
#endif /* _ASM_X86_MCE_H */
|