Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 | #ifndef _ASM_X86_MCE_H #define _ASM_X86_MCE_H #include <uapi/asm/mce.h> /* * 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 */ #define MCG_ELOG_P (1ULL<<26) /* Extended error log supported */ #define MCG_LMCE_P (1ULL<<27) /* Local machine check supported */ /* 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 */ #define MCG_STATUS_LMCES (1ULL<<3) /* LMCE signaled */ /* MCG_EXT_CTL register defines */ #define MCG_EXT_CTL_LMCE_EN (1ULL<<0) /* Enable LMCE */ /* 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 */ /* AMD-specific bits */ #define MCI_STATUS_DEFERRED (1ULL<<44) /* declare an uncorrected error */ #define MCI_STATUS_POISON (1ULL<<43) /* access poisonous data */ /* * 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 */ /* Architecturally defined codes from SDM Vol. 3B Chapter 15 */ #define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */ #define MCACOD_SCRUBMSK 0xeff0 /* Skip bit 12 ('F' bit) */ #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 */ #define MCJ_IRQ_BROADCAST 0x10 /* do IRQ broadcasting */ #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" /* * 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]; }; struct mca_config { bool dont_log_ce; bool cmci_disabled; bool lmce_disabled; bool ignore_ce; bool disabled; bool ser; bool bios_cmci_threshold; u8 banks; s8 bootlog; int tolerant; int monarch_timeout; int panic_timeout; u32 rip_msr; }; struct mce_vendor_flags { /* * overflow recovery cpuid bit indicates that overflow * conditions are not fatal */ __u64 overflow_recov : 1, /* * SUCCOR stands for S/W UnCorrectable error COntainment * and Recovery. It indicates support for data poisoning * in HW and deferred error interrupts. */ succor : 1, __reserved_0 : 62; }; extern struct mce_vendor_flags mce_flags; extern struct mca_config mca_cfg; extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); #include <linux/percpu.h> #include <linux/atomic.h> extern int mce_p5_enabled; #ifdef CONFIG_X86_MCE int mcheck_init(void); void mcheck_cpu_init(struct cpuinfo_x86 *c); void mcheck_cpu_clear(struct cpuinfo_x86 *c); void mcheck_vendor_init_severity(void); #else static inline int mcheck_init(void) { return 0; } 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) {} #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); 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 #ifdef CONFIG_X86_MCE_INTEL void mce_intel_feature_init(struct cpuinfo_x86 *c); void mce_intel_feature_clear(struct cpuinfo_x86 *c); void cmci_clear(void); void cmci_reenable(void); void cmci_rediscover(void); void cmci_recheck(void); #else static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { } static inline void mce_intel_feature_clear(struct cpuinfo_x86 *c) { } static inline void cmci_clear(void) {} static inline void cmci_reenable(void) {} static inline void cmci_rediscover(void) {} 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); DECLARE_PER_CPU(unsigned, mce_exception_count); DECLARE_PER_CPU(unsigned, mce_poll_count); typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS); 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 */ }; bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b); int mce_notify_irq(void); DECLARE_PER_CPU(struct mce, injectm); extern void register_mce_write_callback(ssize_t (*)(struct file *filp, const char __user *ubuf, size_t usize, loff_t *off)); /* Disable CMCI/polling for MCA bank claimed by firmware */ extern void mce_disable_bank(int bank); /* * 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 */ extern void (*mce_threshold_vector)(void); extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu); /* Deferred error interrupt handler */ extern void (*deferred_error_int_vector)(void); /* * Thermal handler */ void intel_init_thermal(struct cpuinfo_x86 *c); void mce_log_therm_throt_event(__u64 status); /* 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 */ struct cper_sec_mem_err; extern void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err); #endif /* _ASM_X86_MCE_H */ |