diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index f25c2c7c389c3f2c1116b5f128ad1ffbf2787bb4..3c85464ff177729ca3fd1f298292aad150f07c52 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -535,8 +535,10 @@ int mce_usable_address(struct mce *m) if (!(m->status & MCI_STATUS_ADDRV)) return 0; - /* Checks after this one are Intel-specific: */ - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + /* Checks after this one are Intel/Zhaoxin-specific: */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && + boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN && + boot_cpu_data.x86_vendor != X86_VENDOR_CENTAUR) return 1; if (!(m->status & MCI_STATUS_MISCV)) @@ -554,10 +556,14 @@ EXPORT_SYMBOL_GPL(mce_usable_address); bool mce_is_memory_error(struct mce *m) { - if (m->cpuvendor == X86_VENDOR_AMD || - m->cpuvendor == X86_VENDOR_HYGON) { + switch (m->cpuvendor) { + case X86_VENDOR_AMD: + case X86_VENDOR_HYGON: return amd_mce_is_memory_error(m); - } else if (m->cpuvendor == X86_VENDOR_INTEL) { + + case X86_VENDOR_INTEL: + case X86_VENDOR_ZHAOXIN: + case X86_VENDOR_CENTAUR: /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes * @@ -574,9 +580,10 @@ bool mce_is_memory_error(struct mce *m) return (m->status & 0xef80) == BIT(7) || (m->status & 0xef00) == BIT(8) || (m->status & 0xeffc) == 0xc; - } - return false; + default: + return false; + } } EXPORT_SYMBOL_GPL(mce_is_memory_error); @@ -1154,6 +1161,13 @@ static bool __mc_check_crashing_cpu(int cpu) u64 mcgstatus; mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + + if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN || + boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR) { + if (mcgstatus & MCG_STATUS_LMCES) + return false; + } + if (mcgstatus & MCG_STATUS_RIPV) { mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); return true; @@ -1379,9 +1393,11 @@ void do_machine_check(struct pt_regs *regs, long error_code) /* * Check if this MCE is signaled to only this logical processor, - * on Intel only. + * on Intel, Zhaoxin only. */ - if (m.cpuvendor == X86_VENDOR_INTEL) + if (m.cpuvendor == X86_VENDOR_INTEL || + m.cpuvendor == X86_VENDOR_ZHAOXIN || + m.cpuvendor == X86_VENDOR_CENTAUR) lmce = m.mcgstatus & MCG_STATUS_LMCES; /* @@ -1815,6 +1831,19 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (c->x86 == 6 && c->x86_model == 45) quirk_no_way_out = quirk_sandybridge_ifu; } + + if (c->x86_vendor == X86_VENDOR_ZHAOXIN || + c->x86_vendor == X86_VENDOR_CENTAUR) { + /* + * All newer Zhaoxin CPUs support MCE broadcasting. Enable + * synchronization with a one second timeout. + */ + if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) { + if (cfg->monarch_timeout < 0) + cfg->monarch_timeout = USEC_PER_SEC; + } + } + if (cfg->monarch_timeout < 0) cfg->monarch_timeout = 0; if (cfg->bootlog != 0) @@ -1863,19 +1892,33 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c) } } -static void mce_centaur_feature_init(struct cpuinfo_x86 *c) +static void mce_zhaoxin_feature_init(struct cpuinfo_x86 *c) { - struct mca_config *cfg = &mca_cfg; + struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); - /* - * All newer Centaur CPUs support MCE broadcasting. Enable - * synchronization with a one second timeout. - */ - if ((c->x86 == 6 && c->x86_model == 0xf && c->x86_stepping >= 0xe) || - c->x86 > 6) { - if (cfg->monarch_timeout < 0) - cfg->monarch_timeout = USEC_PER_SEC; + /* + * These CPUs have MCA bank 8 which reports only one error type called + * SVAD (System View Address Decoder). The reporting of that error is + * controlled by IA32_MC8.CTL.0. + * + * If enabled, prefetching on these CPUs will cause SVAD MCE when + * virtual machines start and result in a system panic. Always disable + * bank 8 SVAD error by default. + */ + if ((c->x86 == 7 && c->x86_model == 0x1b) || + (c->x86_model == 0x19 || c->x86_model == 0x1f)) { + if (this_cpu_read(mce_num_banks) > 8) + mce_banks[8].ctl = 0; } + + intel_init_cmci(); + intel_init_lmce(); + mce_adjust_timer = cmci_intel_adjust_timer; +} + +static void mce_zhaoxin_feature_clear(struct cpuinfo_x86 *c) +{ + intel_clear_lmce(); } static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) @@ -1896,7 +1939,8 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) break; case X86_VENDOR_CENTAUR: - mce_centaur_feature_init(c); + case X86_VENDOR_ZHAOXIN: + mce_zhaoxin_feature_init(c); break; default: @@ -1910,6 +1954,12 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c) case X86_VENDOR_INTEL: mce_intel_feature_clear(c); break; + + case X86_VENDOR_ZHAOXIN: + case X86_VENDOR_CENTAUR: + mce_zhaoxin_feature_clear(c); + break; + default: break; } @@ -2135,15 +2185,17 @@ static void mce_disable_error_reporting(void) static void vendor_disable_error_reporting(void) { /* - * Don't clear on Intel or AMD or Hygon CPUs. Some of these MSRs - * are socket-wide. - * Disabling them for just a single offlined CPU is bad, since it will - * inhibit reporting for all shared resources on the socket like the - * last level cache (LLC), the integrated memory controller (iMC), etc. + * Don't clear on Intel or AMD or Hygon or Zhaoxin CPUs. Some of these + * MSRs are socket-wide. Disabling them for just a single offlined CPU + * is bad, since it will inhibit reporting for all shared resources on + * the socket like the last level cache (LLC), the integrated memory + * controller (iMC), etc. */ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON || - boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN || + boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR) return; mce_disable_error_reporting(); diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index f2350967a898a3c06890d4c454ae5a500d7d24dd..3ead5228bd84d76f0e8c2de11d8ab5447a6efd31 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -85,8 +85,11 @@ static int cmci_supported(int *banks) * initialization is vendor keyed and this * makes sure none of the backdoors are entered otherwise. */ - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && + boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN && + boot_cpu_data.x86_vendor != X86_VENDOR_CENTAUR) return 0; + if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6) return 0; rdmsrl(MSR_IA32_MCG_CAP, cap); @@ -423,7 +426,7 @@ void cmci_disable_bank(int bank) raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); } -static void intel_init_cmci(void) +void intel_init_cmci(void) { int banks; @@ -442,7 +445,7 @@ static void intel_init_cmci(void) cmci_recheck(); } -static void intel_init_lmce(void) +void intel_init_lmce(void) { u64 val; @@ -455,7 +458,7 @@ static void intel_init_lmce(void) wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN); } -static void intel_clear_lmce(void) +void intel_clear_lmce(void) { u64 val; diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 4f90f720b28151cffe9bba6cc8554dc2e84302b9..9aa1276f4066e0c7acd29dbd4c6f308f92d3b4fa 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -46,11 +46,17 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval); bool mce_intel_cmci_poll(void); void mce_intel_hcpu_update(unsigned long cpu); void cmci_disable_bank(int bank); +void intel_init_cmci(void); +void intel_init_lmce(void); +void intel_clear_lmce(void); #else # define cmci_intel_adjust_timer mce_adjust_timer_default static inline bool mce_intel_cmci_poll(void) { return false; } static inline void mce_intel_hcpu_update(unsigned long cpu) { } static inline void cmci_disable_bank(int bank) { } +static inline void intel_init_cmci(void) { } +static inline void intel_init_lmce(void) { } +static inline void intel_clear_lmce(void) { } #endif void mce_timer_kick(unsigned long interval);