diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt index c54b4f503e2a..de38429beb71 100644 --- a/Documentation/x86/x86_64/boot-options.txt +++ b/Documentation/x86/x86_64/boot-options.txt @@ -50,6 +50,13 @@ Machine check monarchtimeout: Sets the time in us to wait for other CPUs on machine checks. 0 to disable. + mce=bios_cmci_threshold + Don't overwrite the bios-set CMCI threshold. This boot option + prevents Linux from overwriting the CMCI threshold set by the + bios. Without this option, Linux always sets the CMCI + threshold to 1. Enabling this may make memory predictive failure + analysis less effective if the bios sets thresholds for memory + errors since we will not see details for all errors. nomce (for compatibility with i386): same as mce=off diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 57fecc1db94d..6cd6f24e1223 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -874,6 +874,7 @@ config X86_REROUTE_FOR_BROKEN_BOOT_IRQS config X86_MCE bool "Machine Check / overheating reporting" + default y ---help--- Machine Check support allows the processor to notify the kernel if it detects a problem (e.g. overheating, data corruption). diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index a3ac52b29cbf..54d73b1f00a0 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -116,19 +116,9 @@ struct mce_log { /* Software defined banks */ #define MCE_EXTENDED_BANK 128 #define MCE_THERMAL_BANK MCE_EXTENDED_BANK + 0 - -#define K8_MCE_THRESHOLD_BASE (MCE_EXTENDED_BANK + 1) /* MCE_AMD */ -#define K8_MCE_THRESHOLD_BANK_0 (MCE_THRESHOLD_BASE + 0 * 9) -#define K8_MCE_THRESHOLD_BANK_1 (MCE_THRESHOLD_BASE + 1 * 9) -#define K8_MCE_THRESHOLD_BANK_2 (MCE_THRESHOLD_BASE + 2 * 9) -#define K8_MCE_THRESHOLD_BANK_3 (MCE_THRESHOLD_BASE + 3 * 9) -#define K8_MCE_THRESHOLD_BANK_4 (MCE_THRESHOLD_BASE + 4 * 9) -#define K8_MCE_THRESHOLD_BANK_5 (MCE_THRESHOLD_BASE + 5 * 9) -#define K8_MCE_THRESHOLD_DRAM_ECC (MCE_THRESHOLD_BANK_4 + 0) - +#define K8_MCE_THRESHOLD_BASE (MCE_EXTENDED_BANK + 1) #ifdef __KERNEL__ - extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); @@ -171,6 +161,7 @@ DECLARE_PER_CPU(struct device *, mce_device); #ifdef CONFIG_X86_MCE_INTEL extern int mce_cmci_disabled; extern int mce_ignore_ce; +extern int mce_bios_cmci_threshold; void mce_intel_feature_init(struct cpuinfo_x86 *c); void cmci_clear(void); void cmci_reenable(void); diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index fc4beb393577..ddc72f839332 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -78,6 +78,7 @@ static void raise_exception(struct mce *m, struct pt_regs *pregs) } static cpumask_var_t mce_inject_cpumask; +static DEFINE_MUTEX(mce_inject_mutex); static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs) { @@ -194,7 +195,11 @@ static void raise_mce(struct mce *m) put_online_cpus(); } else #endif + { + preempt_disable(); raise_local(); + preempt_enable(); + } } /* Error injection interface */ @@ -225,7 +230,10 @@ static ssize_t mce_write(struct file *filp, const char __user *ubuf, * so do it a jiffie or two later everywhere. */ schedule_timeout(2); + + mutex_lock(&mce_inject_mutex); raise_mce(&m); + mutex_unlock(&mce_inject_mutex); return usize; } diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index ed44c8a65858..6a05c1d327a9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -28,6 +28,18 @@ extern int mce_ser; extern struct mce_bank *mce_banks; +#ifdef CONFIG_X86_MCE_INTEL +unsigned long mce_intel_adjust_timer(unsigned long interval); +void mce_intel_cmci_poll(void); +void mce_intel_hcpu_update(unsigned long cpu); +#else +# define mce_intel_adjust_timer mce_adjust_timer_default +static inline void mce_intel_cmci_poll(void) { } +static inline void mce_intel_hcpu_update(unsigned long cpu) { } +#endif + +void mce_timer_kick(unsigned long interval); + #ifdef CONFIG_ACPI_APEI int apei_write_mce(struct mce *m); ssize_t apei_read_mce(struct mce *m, u64 *record_id); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 292d0258311c..29e87d3b2843 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -83,6 +83,7 @@ static int mce_dont_log_ce __read_mostly; int mce_cmci_disabled __read_mostly; int mce_ignore_ce __read_mostly; int mce_ser __read_mostly; +int mce_bios_cmci_threshold __read_mostly; struct mce_bank *mce_banks __read_mostly; @@ -1266,6 +1267,14 @@ static unsigned long check_interval = 5 * 60; /* 5 minutes */ static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ static DEFINE_PER_CPU(struct timer_list, mce_timer); +static unsigned long mce_adjust_timer_default(unsigned long interval) +{ + return interval; +} + +static unsigned long (*mce_adjust_timer)(unsigned long interval) = + mce_adjust_timer_default; + static void mce_timer_fn(unsigned long data) { struct timer_list *t = &__get_cpu_var(mce_timer); @@ -1276,6 +1285,7 @@ static void mce_timer_fn(unsigned long data) if (mce_available(__this_cpu_ptr(&cpu_info))) { machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_poll_banks)); + mce_intel_cmci_poll(); } /* @@ -1283,14 +1293,38 @@ static void mce_timer_fn(unsigned long data) * polling interval, otherwise increase the polling interval. */ iv = __this_cpu_read(mce_next_interval); - if (mce_notify_irq()) + if (mce_notify_irq()) { iv = max(iv / 2, (unsigned long) HZ/100); - else + } else { iv = min(iv * 2, round_jiffies_relative(check_interval * HZ)); + iv = mce_adjust_timer(iv); + } __this_cpu_write(mce_next_interval, iv); + /* Might have become 0 after CMCI storm subsided */ + if (iv) { + t->expires = jiffies + iv; + add_timer_on(t, smp_processor_id()); + } +} - t->expires = jiffies + iv; - add_timer_on(t, smp_processor_id()); +/* + * Ensure that the timer is firing in @interval from now. + */ +void mce_timer_kick(unsigned long interval) +{ + struct timer_list *t = &__get_cpu_var(mce_timer); + unsigned long when = jiffies + interval; + unsigned long iv = __this_cpu_read(mce_next_interval); + + if (timer_pending(t)) { + if (time_before(when, t->expires)) + mod_timer_pinned(t, when); + } else { + t->expires = round_jiffies(when); + add_timer_on(t, smp_processor_id()); + } + if (interval < iv) + __this_cpu_write(mce_next_interval, interval); } /* Must not be called in IRQ context where del_timer_sync() can deadlock */ @@ -1585,6 +1619,7 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) switch (c->x86_vendor) { case X86_VENDOR_INTEL: mce_intel_feature_init(c); + mce_adjust_timer = mce_intel_adjust_timer; break; case X86_VENDOR_AMD: mce_amd_feature_init(c); @@ -1594,21 +1629,26 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) } } +static void mce_start_timer(unsigned int cpu, struct timer_list *t) +{ + unsigned long iv = mce_adjust_timer(check_interval * HZ); + + __this_cpu_write(mce_next_interval, iv); + + if (mce_ignore_ce || !iv) + return; + + t->expires = round_jiffies(jiffies + iv); + add_timer_on(t, smp_processor_id()); +} + static void __mcheck_cpu_init_timer(void) { struct timer_list *t = &__get_cpu_var(mce_timer); - unsigned long iv = check_interval * HZ; + unsigned int cpu = smp_processor_id(); - setup_timer(t, mce_timer_fn, smp_processor_id()); - - if (mce_ignore_ce) - return; - - __this_cpu_write(mce_next_interval, iv); - if (!iv) - return; - t->expires = round_jiffies(jiffies + iv); - add_timer_on(t, smp_processor_id()); + setup_timer(t, mce_timer_fn, cpu); + mce_start_timer(cpu, t); } /* Handle unconfigured int18 (should never happen) */ @@ -1907,6 +1947,7 @@ static struct miscdevice mce_chrdev_device = { * check, or 0 to not wait * mce=bootlog Log MCEs from before booting. Disabled by default on AMD. * mce=nobootlog Don't log MCEs from before booting. + * mce=bios_cmci_threshold Don't program the CMCI threshold */ static int __init mcheck_enable(char *str) { @@ -1926,6 +1967,8 @@ static int __init mcheck_enable(char *str) mce_ignore_ce = 1; else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) mce_bootlog = (str[0] == 'b'); + else if (!strcmp(str, "bios_cmci_threshold")) + mce_bios_cmci_threshold = 1; else if (isdigit(str[0])) { get_option(&str, &tolerant); if (*str == ',') { @@ -2166,6 +2209,11 @@ static struct dev_ext_attribute dev_attr_cmci_disabled = { &mce_cmci_disabled }; +static struct dev_ext_attribute dev_attr_bios_cmci_threshold = { + __ATTR(bios_cmci_threshold, 0444, device_show_int, NULL), + &mce_bios_cmci_threshold +}; + static struct device_attribute *mce_device_attrs[] = { &dev_attr_tolerant.attr, &dev_attr_check_interval.attr, @@ -2174,6 +2222,7 @@ static struct device_attribute *mce_device_attrs[] = { &dev_attr_dont_log_ce.attr, &dev_attr_ignore_ce.attr, &dev_attr_cmci_disabled.attr, + &dev_attr_bios_cmci_threshold.attr, NULL }; @@ -2294,38 +2343,33 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) unsigned int cpu = (unsigned long)hcpu; struct timer_list *t = &per_cpu(mce_timer, cpu); - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: - case CPU_ONLINE_FROZEN: mce_device_create(cpu); if (threshold_cpu_callback) threshold_cpu_callback(action, cpu); break; case CPU_DEAD: - case CPU_DEAD_FROZEN: if (threshold_cpu_callback) threshold_cpu_callback(action, cpu); mce_device_remove(cpu); + mce_intel_hcpu_update(cpu); break; case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - del_timer_sync(t); smp_call_function_single(cpu, mce_disable_cpu, &action, 1); + del_timer_sync(t); break; case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - if (!mce_ignore_ce && check_interval) { - t->expires = round_jiffies(jiffies + - per_cpu(mce_next_interval, cpu)); - add_timer_on(t, cpu); - } smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); - break; - case CPU_POST_DEAD: - /* intentionally ignoring frozen here */ - cmci_rediscover(cpu); + mce_start_timer(cpu, t); break; } + + if (action == CPU_POST_DEAD) { + /* intentionally ignoring frozen here */ + cmci_rediscover(cpu); + } + return NOTIFY_OK; } diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 38e49bc95ffc..5f88abf07e9c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -15,6 +15,8 @@ #include #include +#include "mce-internal.h" + /* * Support for Intel Correct Machine Check Interrupts. This allows * the CPU to raise an interrupt when a corrected machine check happened. @@ -30,7 +32,22 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned); */ static DEFINE_RAW_SPINLOCK(cmci_discover_lock); -#define CMCI_THRESHOLD 1 +#define CMCI_THRESHOLD 1 +#define CMCI_POLL_INTERVAL (30 * HZ) +#define CMCI_STORM_INTERVAL (1 * HZ) +#define CMCI_STORM_THRESHOLD 15 + +static DEFINE_PER_CPU(unsigned long, cmci_time_stamp); +static DEFINE_PER_CPU(unsigned int, cmci_storm_cnt); +static DEFINE_PER_CPU(unsigned int, cmci_storm_state); + +enum { + CMCI_STORM_NONE, + CMCI_STORM_ACTIVE, + CMCI_STORM_SUBSIDED, +}; + +static atomic_t cmci_storm_on_cpus; static int cmci_supported(int *banks) { @@ -53,6 +70,93 @@ static int cmci_supported(int *banks) return !!(cap & MCG_CMCI_P); } +void mce_intel_cmci_poll(void) +{ + if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE) + return; + machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); +} + +void mce_intel_hcpu_update(unsigned long cpu) +{ + if (per_cpu(cmci_storm_state, cpu) == CMCI_STORM_ACTIVE) + atomic_dec(&cmci_storm_on_cpus); + + per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE; +} + +unsigned long mce_intel_adjust_timer(unsigned long interval) +{ + int r; + + if (interval < CMCI_POLL_INTERVAL) + return interval; + + switch (__this_cpu_read(cmci_storm_state)) { + case CMCI_STORM_ACTIVE: + /* + * We switch back to interrupt mode once the poll timer has + * silenced itself. That means no events recorded and the + * timer interval is back to our poll interval. + */ + __this_cpu_write(cmci_storm_state, CMCI_STORM_SUBSIDED); + r = atomic_sub_return(1, &cmci_storm_on_cpus); + if (r == 0) + pr_notice("CMCI storm subsided: switching to interrupt mode\n"); + /* FALLTHROUGH */ + + case CMCI_STORM_SUBSIDED: + /* + * We wait for all cpus to go back to SUBSIDED + * state. When that happens we switch back to + * interrupt mode. + */ + if (!atomic_read(&cmci_storm_on_cpus)) { + __this_cpu_write(cmci_storm_state, CMCI_STORM_NONE); + cmci_reenable(); + cmci_recheck(); + } + return CMCI_POLL_INTERVAL; + default: + /* + * We have shiny weather. Let the poll do whatever it + * thinks. + */ + return interval; + } +} + +static bool cmci_storm_detect(void) +{ + unsigned int cnt = __this_cpu_read(cmci_storm_cnt); + unsigned long ts = __this_cpu_read(cmci_time_stamp); + unsigned long now = jiffies; + int r; + + if (__this_cpu_read(cmci_storm_state) != CMCI_STORM_NONE) + return true; + + if (time_before_eq(now, ts + CMCI_STORM_INTERVAL)) { + cnt++; + } else { + cnt = 1; + __this_cpu_write(cmci_time_stamp, now); + } + __this_cpu_write(cmci_storm_cnt, cnt); + + if (cnt <= CMCI_STORM_THRESHOLD) + return false; + + cmci_clear(); + __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE); + r = atomic_add_return(1, &cmci_storm_on_cpus); + mce_timer_kick(CMCI_POLL_INTERVAL); + + if (r == 1) + pr_notice("CMCI storm detected: switching to poll mode\n"); + return true; +} + /* * The interrupt handler. This is called on every event. * Just call the poller directly to log any events. @@ -61,33 +165,28 @@ static int cmci_supported(int *banks) */ static void intel_threshold_interrupt(void) { + if (cmci_storm_detect()) + return; machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); mce_notify_irq(); } -static void print_update(char *type, int *hdr, int num) -{ - if (*hdr == 0) - printk(KERN_INFO "CPU %d MCA banks", smp_processor_id()); - *hdr = 1; - printk(KERN_CONT " %s:%d", type, num); -} - /* * Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks * on this CPU. Use the algorithm recommended in the SDM to discover shared * banks. */ -static void cmci_discover(int banks, int boot) +static void cmci_discover(int banks) { unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned); unsigned long flags; - int hdr = 0; int i; + int bios_wrong_thresh = 0; raw_spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { u64 val; + int bios_zero_thresh = 0; if (test_bit(i, owned)) continue; @@ -96,29 +195,52 @@ static void cmci_discover(int banks, int boot) /* Already owned by someone else? */ if (val & MCI_CTL2_CMCI_EN) { - if (test_and_clear_bit(i, owned) && !boot) - print_update("SHD", &hdr, i); + clear_bit(i, owned); __clear_bit(i, __get_cpu_var(mce_poll_banks)); continue; } - val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; - val |= MCI_CTL2_CMCI_EN | CMCI_THRESHOLD; + if (!mce_bios_cmci_threshold) { + val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; + val |= CMCI_THRESHOLD; + } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) { + /* + * If bios_cmci_threshold boot option was specified + * but the threshold is zero, we'll try to initialize + * it to 1. + */ + bios_zero_thresh = 1; + val |= CMCI_THRESHOLD; + } + + val |= MCI_CTL2_CMCI_EN; wrmsrl(MSR_IA32_MCx_CTL2(i), val); rdmsrl(MSR_IA32_MCx_CTL2(i), val); /* Did the enable bit stick? -- the bank supports CMCI */ if (val & MCI_CTL2_CMCI_EN) { - if (!test_and_set_bit(i, owned) && !boot) - print_update("CMCI", &hdr, i); + set_bit(i, owned); __clear_bit(i, __get_cpu_var(mce_poll_banks)); + /* + * We are able to set thresholds for some banks that + * had a threshold of 0. This means the BIOS has not + * set the thresholds properly or does not work with + * this boot option. Note down now and report later. + */ + if (mce_bios_cmci_threshold && bios_zero_thresh && + (val & MCI_CTL2_CMCI_THRESHOLD_MASK)) + bios_wrong_thresh = 1; } else { WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks))); } } raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); - if (hdr) - printk(KERN_CONT "\n"); + if (mce_bios_cmci_threshold && bios_wrong_thresh) { + pr_info_once( + "bios_cmci_threshold: Some banks do not have valid thresholds set\n"); + pr_info_once( + "bios_cmci_threshold: Make sure your BIOS supports this boot option\n"); + } } /* @@ -156,7 +278,7 @@ void cmci_clear(void) continue; /* Disable CMCI */ rdmsrl(MSR_IA32_MCx_CTL2(i), val); - val &= ~(MCI_CTL2_CMCI_EN|MCI_CTL2_CMCI_THRESHOLD_MASK); + val &= ~MCI_CTL2_CMCI_EN; wrmsrl(MSR_IA32_MCx_CTL2(i), val); __clear_bit(i, __get_cpu_var(mce_banks_owned)); } @@ -186,7 +308,7 @@ void cmci_rediscover(int dying) continue; /* Recheck banks in case CPUs don't all have the same */ if (cmci_supported(&banks)) - cmci_discover(banks, 0); + cmci_discover(banks); } set_cpus_allowed_ptr(current, old); @@ -200,7 +322,7 @@ void cmci_reenable(void) { int banks; if (cmci_supported(&banks)) - cmci_discover(banks, 0); + cmci_discover(banks); } static void intel_init_cmci(void) @@ -211,7 +333,7 @@ static void intel_init_cmci(void) return; mce_threshold_vector = intel_threshold_interrupt; - cmci_discover(banks, 1); + cmci_discover(banks); /* * For CPU #0 this runs with still disabled APIC, but that's * ok because only the vector is set up. We still do another