diff options
Diffstat (limited to 'arch/x86/include/asm/mce.h')
| -rw-r--r-- | arch/x86/include/asm/mce.h | 197 |
1 files changed, 116 insertions, 81 deletions
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index cf503824529c..2d98886de09a 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -13,6 +13,7 @@ #define MCG_CTL_P BIT_ULL(8) /* MCG_CTL register available */ #define MCG_EXT_P BIT_ULL(9) /* Extended registers available */ #define MCG_CMCI_P BIT_ULL(10) /* CMCI supported */ +#define MCG_SEAM_NR BIT_ULL(12) /* MCG_STATUS_SEAM_NR 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) @@ -25,6 +26,7 @@ #define MCG_STATUS_EIPV BIT_ULL(1) /* ip points to correct instruction */ #define MCG_STATUS_MCIP BIT_ULL(2) /* machine check in progress */ #define MCG_STATUS_LMCES BIT_ULL(3) /* LMCE signaled */ +#define MCG_STATUS_SEAM_NR BIT_ULL(12) /* Machine check inside SEAM non-root mode */ /* MCG_EXT_CTL register defines */ #define MCG_EXT_CTL_LMCE_EN BIT_ULL(0) /* Enable LMCE */ @@ -42,9 +44,11 @@ #define MCI_STATUS_CEC_SHIFT 38 /* Corrected Error Count */ #define MCI_STATUS_CEC_MASK GENMASK_ULL(52,38) #define MCI_STATUS_CEC(c) (((c) & MCI_STATUS_CEC_MASK) >> MCI_STATUS_CEC_SHIFT) +#define MCI_STATUS_MSCOD(m) (((m) >> 16) & 0xffff) /* AMD-specific bits */ #define MCI_STATUS_TCC BIT_ULL(55) /* Task context corrupt */ +#define MCI_STATUS_PADDRV BIT_ULL(54) /* Valid System Physical Address */ #define MCI_STATUS_SYNDV BIT_ULL(53) /* synd reg. valid */ #define MCI_STATUS_DEFERRED BIT_ULL(44) /* uncorrected error, deferred exception */ #define MCI_STATUS_POISON BIT_ULL(43) /* access poisonous data */ @@ -58,6 +62,8 @@ * - TCC bit is present in MCx_STATUS. */ #define MCI_CONFIG_MCAX 0x1 +#define MCI_CONFIG_FRUTEXT BIT_ULL(9) +#define MCI_CONFIG_PADDRV BIT_ULL(11) #define MCI_IPID_MCATYPE 0xFFFF0000 #define MCI_IPID_HWID 0xFFF @@ -87,6 +93,9 @@ #define MCI_MISC_ADDR_MEM 3 /* memory address */ #define MCI_MISC_ADDR_GENERIC 7 /* generic */ +/* MCi_ADDR register defines */ +#define MCI_ADDR_PHYSADDR GENMASK_ULL(boot_cpu_data.x86_phys_bits - 1, 0) + /* CTL2 register defines */ #define MCI_CTL2_CMCI_EN BIT_ULL(30) #define MCI_CTL2_CMCI_THRESHOLD_MASK 0x7fffULL @@ -116,6 +125,9 @@ #define MSR_AMD64_SMCA_MC0_DESTAT 0xc0002008 #define MSR_AMD64_SMCA_MC0_DEADDR 0xc0002009 #define MSR_AMD64_SMCA_MC0_MISC1 0xc000200a +/* Registers MISC2 to MISC4 are at offsets B to D. */ +#define MSR_AMD64_SMCA_MC0_SYND1 0xc000200e +#define MSR_AMD64_SMCA_MC0_SYND2 0xc000200f #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)) @@ -126,6 +138,8 @@ #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)) #define MSR_AMD64_SMCA_MCx_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x))) +#define MSR_AMD64_SMCA_MCx_SYND1(x) (MSR_AMD64_SMCA_MC0_SYND1 + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_SYND2(x) (MSR_AMD64_SMCA_MC0_SYND2 + 0x10*(x)) #define XEC(x, mask) (((x) >> 16) & mask) @@ -136,9 +150,30 @@ #define MCE_HANDLED_NFIT BIT_ULL(3) #define MCE_HANDLED_EDAC BIT_ULL(4) #define MCE_HANDLED_MCELOG BIT_ULL(5) + +/* + * Indicates an MCE which has happened in kernel space but from + * which the kernel can recover simply by executing fixup_exception() + * so that an error is returned to the caller of the function that + * hit the machine check. + */ #define MCE_IN_KERNEL_RECOV BIT_ULL(6) /* + * Indicates an MCE that happened in kernel space while copying data + * from user. In this case fixup_exception() gets the kernel to the + * error exit for the copy function. Machine check handler can then + * treat it like a fault taken in user mode. + */ +#define MCE_IN_KERNEL_COPYIN BIT_ULL(7) + +/* + * Indicates that handler should check and clear Deferred error registers + * rather than common ones. + */ +#define MCE_CHECK_DFR_REGS BIT_ULL(8) + +/* * 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 @@ -162,9 +197,36 @@ enum mce_notifier_prios { MCE_PRIO_EXTLOG, MCE_PRIO_UC, MCE_PRIO_EARLY, - MCE_PRIO_CEC + MCE_PRIO_CEC, + MCE_PRIO_HIGHEST = MCE_PRIO_CEC }; +/** + * struct mce_hw_err - Hardware Error Record. + * @m: Machine Check record. + * @vendor: Vendor-specific error information. + * + * Vendor-specific fields should not be added to struct mce. Instead, vendors + * should export their vendor-specific data through their structure in the + * vendor union below. + * + * AMD's vendor data is parsed by error decoding tools for supplemental error + * information. Thus, current offsets of existing fields must be maintained. + * Only add new fields at the end of AMD's vendor structure. + */ +struct mce_hw_err { + struct mce m; + + union vendor_info { + struct { + u64 synd1; /* MCA_SYND1 MSR */ + u64 synd2; /* MCA_SYND2 MSR */ + } amd; + } vendor; +}; + +#define to_mce_hw_err(mce) container_of(mce, struct mce_hw_err, m) + struct notifier_block; extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); @@ -174,38 +236,39 @@ extern void mce_unregister_decode_chain(struct notifier_block *nb); extern int mce_p5_enabled; +#ifdef CONFIG_ARCH_HAS_COPY_MC +extern void enable_copy_mc_fragile(void); +unsigned long __must_check copy_mc_fragile(void *dst, const void *src, unsigned cnt); +#else +static inline void enable_copy_mc_fragile(void) +{ +} +#endif + +struct cper_ia_proc_ctx; + #ifdef CONFIG_X86_MCE int mcheck_init(void); +void mca_bsp_init(struct cpuinfo_x86 *c); void mcheck_cpu_init(struct cpuinfo_x86 *c); void mcheck_cpu_clear(struct cpuinfo_x86 *c); -void mcheck_vendor_init_severity(void); +int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, + u64 lapic_id); #else static inline int mcheck_init(void) { return 0; } +static inline void mca_bsp_init(struct cpuinfo_x86 *c) {} static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {} static inline void mcheck_cpu_clear(struct cpuinfo_x86 *c) {} -static inline void mcheck_vendor_init_severity(void) {} +static inline int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, + u64 lapic_id) { return -EINVAL; } #endif -#ifdef CONFIG_X86_ANCIENT_MCE -void intel_p5_mcheck_init(struct cpuinfo_x86 *c); -void winchip_mcheck_init(struct cpuinfo_x86 *c); -static inline void enable_p5_mce(void) { mce_p5_enabled = 1; } -#else -static inline void intel_p5_mcheck_init(struct cpuinfo_x86 *c) {} -static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {} -static inline void enable_p5_mce(void) {} -#endif - -void mce_setup(struct mce *m); -void mce_log(struct mce *m); +void mce_prep_record(struct mce_hw_err *err); +void mce_log(struct mce_hw_err *err); DECLARE_PER_CPU(struct device *, mce_device); -/* - * Maximum banks number. - * This is the limit of the current register layout on - * Intel CPUs. - */ -#define MAX_NR_BANKS 32 +/* Maximum number of MCA banks per CPU. */ +#define MAX_NR_BANKS 64 #ifdef CONFIG_X86_MCE_INTEL void mce_intel_feature_init(struct cpuinfo_x86 *c); @@ -223,10 +286,10 @@ static inline void cmci_rediscover(void) {} static inline void cmci_recheck(void) {} #endif -int mce_available(struct cpuinfo_x86 *c); +bool mce_available(struct cpuinfo_x86 *c); bool mce_is_memory_error(struct mce *m); bool mce_is_correctable(struct mce *m); -int mce_usable_address(struct mce *m); +bool mce_usable_address(struct mce *m); DECLARE_PER_CPU(unsigned, mce_exception_count); DECLARE_PER_CPU(unsigned, mce_poll_count); @@ -237,17 +300,22 @@ DECLARE_PER_CPU(mce_banks_t, mce_poll_banks); enum mcp_flags { MCP_TIMESTAMP = BIT(0), /* log time stamp */ MCP_UC = BIT(1), /* log uncorrected errors */ - MCP_DONTLOG = BIT(2), /* only clear, don't log */ + MCP_QUEUE_LOG = BIT(2), /* only queue to genpool */ }; -bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b); -int mce_notify_irq(void); +void machine_check_poll(enum mcp_flags flags, mce_banks_t *b); DECLARE_PER_CPU(struct mce, injectm); /* Disable CMCI/polling for MCA bank claimed by firmware */ extern void mce_disable_bank(int bank); +#ifdef CONFIG_X86_MCE_THRESHOLD +void mce_save_apei_thr_limit(u32 thr_limit); +#else +static inline void mce_save_apei_thr_limit(u32 thr_limit) { } +#endif /* CONFIG_X86_MCE_THRESHOLD */ + /* * Exception handler */ @@ -262,28 +330,6 @@ extern void (*mce_threshold_vector)(void); extern void (*deferred_error_int_vector)(void); /* - * Thermal handler - */ - -void intel_init_thermal(struct cpuinfo_x86 *c); - -/* Interrupt Handler for core thermal thresholds */ -extern int (*platform_thermal_notify)(__u64 msr_val); - -/* 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); - -#ifdef CONFIG_X86_THERMAL_VECTOR -extern void mcheck_intel_therm_init(void); -#else -static inline void mcheck_intel_therm_init(void) { } -#endif - -/* * Used by APEI to report memory error via /dev/mcelog */ @@ -300,7 +346,7 @@ extern void apei_mce_report_mem_error(int corrected, /* These may be used by multiple smca_hwid_mcatypes */ enum smca_bank_types { SMCA_LS = 0, /* Load Store */ - SMCA_LS_V2, /* Load Store */ + SMCA_LS_V2, SMCA_IF, /* Instruction Fetch */ SMCA_L2_CACHE, /* L2 Cache */ SMCA_DE, /* Decoder Unit */ @@ -309,55 +355,44 @@ enum smca_bank_types { SMCA_FP, /* Floating Point */ SMCA_L3_CACHE, /* L3 Cache */ SMCA_CS, /* Coherent Slave */ - SMCA_CS_V2, /* Coherent Slave */ + SMCA_CS_V2, SMCA_PIE, /* Power, Interrupts, etc. */ SMCA_UMC, /* Unified Memory Controller */ + SMCA_UMC_V2, + SMCA_MA_LLC, /* Memory Attached Last Level Cache */ SMCA_PB, /* Parameter Block */ SMCA_PSP, /* Platform Security Processor */ - SMCA_PSP_V2, /* Platform Security Processor */ + SMCA_PSP_V2, SMCA_SMU, /* System Management Unit */ - SMCA_SMU_V2, /* System Management Unit */ + SMCA_SMU_V2, SMCA_MP5, /* Microprocessor 5 Unit */ + SMCA_MPDMA, /* MPDMA Unit */ SMCA_NBIO, /* Northbridge IO Unit */ SMCA_PCIE, /* PCI Express Unit */ + SMCA_PCIE_V2, + SMCA_XGMI_PCS, /* xGMI PCS Unit */ + SMCA_NBIF, /* NBIF Unit */ + SMCA_SHUB, /* System HUB Unit */ + SMCA_SATA, /* SATA Unit */ + SMCA_USB, /* USB Unit */ + SMCA_USR_DP, /* Ultra Short Reach Data Plane Controller */ + SMCA_USR_CP, /* Ultra Short Reach Control Plane Controller */ + SMCA_GMI_PCS, /* GMI PCS Unit */ + SMCA_XGMI_PHY, /* xGMI PHY Unit */ + SMCA_WAFL_PHY, /* WAFL PHY Unit */ + SMCA_GMI_PHY, /* GMI PHY Unit */ N_SMCA_BANK_TYPES }; -#define HWID_MCATYPE(hwid, mcatype) (((hwid) << 16) | (mcatype)) - -struct smca_hwid { - 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. */ - u8 count; /* Number of instances. */ -}; - -struct smca_bank { - struct smca_hwid *hwid; - u32 id; /* Value of MCA_IPID[InstanceId]. */ - u8 sysfs_id; /* Value used for sysfs name. */ -}; - -extern struct smca_bank smca_banks[MAX_NR_BANKS]; - -extern const char *smca_get_long_name(enum smca_bank_types t); extern bool amd_mce_is_memory_error(struct mce *m); -extern int mce_threshold_create_device(unsigned int cpu); -extern int mce_threshold_remove_device(unsigned int cpu); - void mce_amd_feature_init(struct cpuinfo_x86 *c); -int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr); - +enum smca_bank_types smca_get_bank_type(unsigned int cpu, unsigned int bank); #else - -static inline int mce_threshold_create_device(unsigned int cpu) { return 0; }; -static inline int mce_threshold_remove_device(unsigned int cpu) { return 0; }; static inline bool amd_mce_is_memory_error(struct mce *m) { return false; }; static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { } -static inline int -umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) { return -EINVAL; }; #endif -static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_amd_feature_init(c); } +unsigned long copy_mc_fragile_handle_tail(char *to, char *from, unsigned len); + #endif /* _ASM_X86_MCE_H */ |