diff options
Diffstat (limited to 'arch/x86/kernel/cpu/mce')
| -rw-r--r-- | arch/x86/kernel/cpu/mce/amd.c | 6 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/core.c | 72 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/inject.c | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/intel.c | 15 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/internal.h | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/therm_throt.c | 11 |
6 files changed, 49 insertions, 59 deletions
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 5167bd2bb6b1..b3a50d962851 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -78,6 +78,7 @@ struct smca_bank_name { static struct smca_bank_name smca_names[] = { [SMCA_LS] = { "load_store", "Load Store Unit" }, + [SMCA_LS_V2] = { "load_store", "Load Store Unit" }, [SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" }, [SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" }, [SMCA_DE] = { "decode_unit", "Decode Unit" }, @@ -138,6 +139,7 @@ static struct smca_hwid smca_hwid_mcatypes[] = { /* ZN Core (HWID=0xB0) MCA types */ { SMCA_LS, HWID_MCATYPE(0xB0, 0x0), 0x1FFFFF }, + { SMCA_LS_V2, HWID_MCATYPE(0xB0, 0x10), 0xFFFFFF }, { SMCA_IF, HWID_MCATYPE(0xB0, 0x1), 0x3FFF }, { SMCA_L2_CACHE, HWID_MCATYPE(0xB0, 0x2), 0xF }, { SMCA_DE, HWID_MCATYPE(0xB0, 0x3), 0x1FF }, @@ -266,10 +268,10 @@ static void smca_configure(unsigned int bank, unsigned int cpu) smca_set_misc_banks_map(bank, cpu); /* Return early if this bank was already initialized. */ - if (smca_banks[bank].hwid) + if (smca_banks[bank].hwid && smca_banks[bank].hwid->hwid_mcatype != 0) return; - if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { + if (rdmsr_safe(MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { pr_warn("Failed to read MCA_IPID for bank %d\n", bank); return; } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 5f42f25bac8f..2c4f949611e4 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -53,8 +53,6 @@ #include "internal.h" -static DEFINE_MUTEX(mce_log_mutex); - /* sysfs synchronization */ static DEFINE_MUTEX(mce_sysfs_mutex); @@ -156,19 +154,10 @@ void mce_log(struct mce *m) if (!mce_gen_pool_add(m)) irq_work_queue(&mce_irq_work); } - -void mce_inject_log(struct mce *m) -{ - mutex_lock(&mce_log_mutex); - mce_log(m); - mutex_unlock(&mce_log_mutex); -} -EXPORT_SYMBOL_GPL(mce_inject_log); - -static struct notifier_block mce_srao_nb; +EXPORT_SYMBOL_GPL(mce_log); /* - * We run the default notifier if we have only the SRAO, the first and the + * We run the default notifier if we have only the UC, the first and the * default notifier registered. I.e., the mandatory NUM_DEFAULT_NOTIFIERS * notifiers registered on the chain. */ @@ -594,26 +583,29 @@ static struct notifier_block first_nb = { .priority = MCE_PRIO_FIRST, }; -static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, - void *data) +static int uc_decode_notifier(struct notifier_block *nb, unsigned long val, + void *data) { struct mce *mce = (struct mce *)data; unsigned long pfn; - if (!mce) + if (!mce || !mce_usable_address(mce)) return NOTIFY_DONE; - if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { - pfn = mce->addr >> PAGE_SHIFT; - if (!memory_failure(pfn, 0)) - set_mce_nospec(pfn); - } + if (mce->severity != MCE_AO_SEVERITY && + mce->severity != MCE_DEFERRED_SEVERITY) + return NOTIFY_DONE; + + pfn = mce->addr >> PAGE_SHIFT; + if (!memory_failure(pfn, 0)) + set_mce_nospec(pfn); return NOTIFY_OK; } -static struct notifier_block mce_srao_nb = { - .notifier_call = srao_decode_notifier, - .priority = MCE_PRIO_SRAO, + +static struct notifier_block mce_uc_nb = { + .notifier_call = uc_decode_notifier, + .priority = MCE_PRIO_UC, }; static int mce_default_notifier(struct notifier_block *nb, unsigned long val, @@ -763,26 +755,22 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) log_it: error_seen = true; - mce_read_aux(&m, i); + if (flags & MCP_DONTLOG) + goto clear_it; + mce_read_aux(&m, i); m.severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); - /* * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) - mce_log(&m); - else if (mce_usable_address(&m)) { - /* - * Although we skipped logging this, we still want - * to take action. Add to the pool so the registered - * notifiers will see it. - */ - if (!mce_gen_pool_add(&m)) - mce_schedule_work(); - } + if (mca_cfg.dont_log_ce && !mce_usable_address(&m)) + goto clear_it; + + mce_log(&m); + +clear_it: /* * Clear state for this bank. */ @@ -807,7 +795,7 @@ EXPORT_SYMBOL_GPL(machine_check_poll); static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, struct pt_regs *regs) { - char *tmp; + char *tmp = *msg; int i; for (i = 0; i < this_cpu_read(mce_num_banks); i++) { @@ -819,8 +807,8 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, if (quirk_no_way_out) quirk_no_way_out(i, m, regs); + m->bank = i; if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { - m->bank = i; mce_read_aux(m, i); *msg = tmp; return 1; @@ -1232,8 +1220,8 @@ void do_machine_check(struct pt_regs *regs, long error_code) DECLARE_BITMAP(toclear, MAX_NR_BANKS); struct mca_config *cfg = &mca_cfg; int cpu = smp_processor_id(); - char *msg = "Unknown"; struct mce m, *final; + char *msg = NULL; int worst = 0; /* @@ -1365,7 +1353,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) ist_end_non_atomic(); } else { if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0)) - mce_panic("Failed kernel mode recovery", &m, NULL); + mce_panic("Failed kernel mode recovery", &m, msg); } out_ist: @@ -2041,7 +2029,7 @@ int __init mcheck_init(void) { mcheck_intel_therm_init(); mce_register_decode_chain(&first_nb); - mce_register_decode_chain(&mce_srao_nb); + mce_register_decode_chain(&mce_uc_nb); mce_register_decode_chain(&mce_default_nb); mcheck_vendor_init_severity(); diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 1f30117b24ba..3413b41b8d55 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -494,7 +494,7 @@ static void do_inject(void) i_mce.status |= MCI_STATUS_SYNDV; if (inj_type == SW_INJ) { - mce_inject_log(&i_mce); + mce_log(&i_mce); return; } diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index e270d0770134..5627b1091b85 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -115,15 +115,16 @@ static bool lmce_supported(void) /* * BIOS should indicate support for LMCE by setting bit 20 in - * IA32_FEATURE_CONTROL without which touching MCG_EXT_CTL will - * generate a #GP fault. + * IA32_FEAT_CTL without which touching MCG_EXT_CTL will generate a #GP + * fault. The MSR must also be locked for LMCE_ENABLED to take effect. + * WARN if the MSR isn't locked as init_ia32_feat_ctl() unconditionally + * locks the MSR in the event that it wasn't already locked by BIOS. */ - rdmsrl(MSR_IA32_FEATURE_CONTROL, tmp); - if ((tmp & (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) == - (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) - return true; + rdmsrl(MSR_IA32_FEAT_CTL, tmp); + if (WARN_ON_ONCE(!(tmp & FEAT_CTL_LOCKED))) + return false; - return false; + return tmp & FEAT_CTL_LMCE_ENABLED; } bool mce_intel_cmci_poll(void) diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 842b273bce31..b785c0d0b590 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -84,8 +84,6 @@ static inline int apei_clear_mce(u64 record_id) } #endif -void mce_inject_log(struct mce *m); - /* * We consider records to be equivalent if bank+status+addr+misc all match. * This is only used when the system is going down because of a fatal error diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c index b38010b541d6..58b4ee3cda77 100644 --- a/arch/x86/kernel/cpu/mce/therm_throt.c +++ b/arch/x86/kernel/cpu/mce/therm_throt.c @@ -235,7 +235,7 @@ static void get_therm_status(int level, bool *proc_hot, u8 *temp) *temp = (msr_val >> 16) & 0x7F; } -static void throttle_active_work(struct work_struct *work) +static void __maybe_unused throttle_active_work(struct work_struct *work) { struct _thermal_state *state = container_of(to_delayed_work(work), struct _thermal_state, therm_work); @@ -467,6 +467,7 @@ static int thermal_throttle_online(unsigned int cpu) { struct thermal_state *state = &per_cpu(thermal_state, cpu); struct device *dev = get_cpu_device(cpu); + u32 l; state->package_throttle.level = PACKAGE_LEVEL; state->core_throttle.level = CORE_LEVEL; @@ -474,6 +475,10 @@ static int thermal_throttle_online(unsigned int cpu) INIT_DELAYED_WORK(&state->package_throttle.therm_work, throttle_active_work); INIT_DELAYED_WORK(&state->core_throttle.therm_work, throttle_active_work); + /* Unmask the thermal vector after the above workqueues are initialized. */ + l = apic_read(APIC_LVTTHMR); + apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED); + return thermal_throttle_add_dev(dev, cpu); } @@ -722,10 +727,6 @@ void intel_init_thermal(struct cpuinfo_x86 *c) rdmsr(MSR_IA32_MISC_ENABLE, l, h); wrmsr(MSR_IA32_MISC_ENABLE, l | MSR_IA32_MISC_ENABLE_TM1, h); - /* Unmask the thermal vector: */ - l = apic_read(APIC_LVTTHMR); - apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED); - pr_info_once("CPU0: Thermal monitoring enabled (%s)\n", tm2 ? "TM2" : "TM1"); |