diff options
Diffstat (limited to 'arch/x86/kernel/cpu/mcheck/mce.c')
-rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce.c | 200 |
1 files changed, 120 insertions, 80 deletions
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index a7fdf453d895..132e1ec67da0 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -43,6 +43,7 @@ #include <linux/export.h> #include <linux/jump_label.h> +#include <asm/intel-family.h> #include <asm/processor.h> #include <asm/traps.h> #include <asm/tlbflush.h> @@ -135,6 +136,9 @@ void mce_setup(struct mce *m) m->socketid = cpu_data(m->extcpu).phys_proc_id; m->apicid = cpu_data(m->extcpu).initial_apicid; rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap); + + if (this_cpu_has(X86_FEATURE_INTEL_PPIN)) + rdmsrl(MSR_PPIN, m->ppin); } DEFINE_PER_CPU(struct mce, injectm); @@ -207,8 +211,12 @@ EXPORT_SYMBOL_GPL(mce_inject_log); static struct notifier_block mce_srao_nb; +static atomic_t num_notifiers; + void mce_register_decode_chain(struct notifier_block *nb) { + atomic_inc(&num_notifiers); + /* Ensure SRAO notifier has the highest priority in the decode chain. */ if (nb != &mce_srao_nb && nb->priority == INT_MAX) nb->priority -= 1; @@ -219,6 +227,8 @@ EXPORT_SYMBOL_GPL(mce_register_decode_chain); void mce_unregister_decode_chain(struct notifier_block *nb) { + atomic_dec(&num_notifiers); + atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb); } EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); @@ -270,17 +280,17 @@ struct mca_msr_regs msr_ops = { .misc = misc_reg }; -static void print_mce(struct mce *m) +static void __print_mce(struct mce *m) { - int ret = 0; - - pr_emerg(HW_ERR "CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n", - m->extcpu, m->mcgstatus, m->bank, m->status); + pr_emerg(HW_ERR "CPU %d: Machine Check%s: %Lx Bank %d: %016Lx\n", + m->extcpu, + (m->mcgstatus & MCG_STATUS_MCIP ? " Exception" : ""), + m->mcgstatus, m->bank, m->status); if (m->ip) { pr_emerg(HW_ERR "RIP%s %02x:<%016Lx> ", !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "", - m->cs, m->ip); + m->cs, m->ip); if (m->cs == __KERNEL_CS) print_symbol("{%s}", m->ip); @@ -308,6 +318,13 @@ static void print_mce(struct mce *m) pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n", m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid, cpu_data(m->extcpu).microcode); +} + +static void print_mce(struct mce *m) +{ + int ret = 0; + + __print_mce(m); /* * Print out human-readable details about the MCE error, @@ -569,6 +586,32 @@ static struct notifier_block mce_srao_nb = { .priority = INT_MAX, }; +static int mce_default_notifier(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *m = (struct mce *)data; + + if (!m) + return NOTIFY_DONE; + + /* + * Run the default notifier if we have only the SRAO + * notifier and us registered. + */ + if (atomic_read(&num_notifiers) > 2) + return NOTIFY_DONE; + + __print_mce(m); + + return NOTIFY_DONE; +} + +static struct notifier_block mce_default_nb = { + .notifier_call = mce_default_notifier, + /* lowest prio, we want it to run last. */ + .priority = 0, +}; + /* * Read ADDR and MISC registers. */ @@ -667,6 +710,15 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) mce_gather_info(&m, NULL); + /* + * m.tsc was set in mce_setup(). Clear it if not requested. + * + * FIXME: Propagate @flags to mce_gather_info/mce_setup() to avoid + * that dance. + */ + if (!(flags & MCP_TIMESTAMP)) + m.tsc = 0; + for (i = 0; i < mca_cfg.banks; i++) { if (!mce_banks[i].ctl || !test_bit(i, *b)) continue; @@ -674,14 +726,12 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) m.misc = 0; m.addr = 0; m.bank = i; - m.tsc = 0; barrier(); m.status = mce_rdmsrl(msr_ops.status(i)); if (!(m.status & MCI_STATUS_VAL)) continue; - /* * Uncorrected or signalled events are handled by the exception * handler when it is enabled, so don't process those here. @@ -696,9 +746,6 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) mce_read_aux(&m, i); - if (!(flags & MCP_TIMESTAMP)) - m.tsc = 0; - severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) @@ -1355,7 +1402,7 @@ static void mce_timer_fn(unsigned long data) iv = __this_cpu_read(mce_next_interval); if (mce_available(this_cpu_ptr(&cpu_info))) { - machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_poll_banks)); + machine_check_poll(0, this_cpu_ptr(&mce_poll_banks)); if (mce_intel_cmci_poll()) { iv = mce_adjust_timer(iv); @@ -1745,6 +1792,14 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t) add_timer_on(t, cpu); } +static void __mcheck_cpu_setup_timer(void) +{ + struct timer_list *t = this_cpu_ptr(&mce_timer); + unsigned int cpu = smp_processor_id(); + + setup_pinned_timer(t, mce_timer_fn, cpu); +} + static void __mcheck_cpu_init_timer(void) { struct timer_list *t = this_cpu_ptr(&mce_timer); @@ -1796,7 +1851,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(c); __mcheck_cpu_init_clear_banks(); - __mcheck_cpu_init_timer(); + __mcheck_cpu_setup_timer(); } /* @@ -2138,6 +2193,7 @@ int __init mcheck_init(void) { mcheck_intel_therm_init(); mce_register_decode_chain(&mce_srao_nb); + mce_register_decode_chain(&mce_default_nb); mcheck_vendor_init_severity(); INIT_WORK(&mce_work, mce_process_work); @@ -2255,8 +2311,6 @@ static struct bus_type mce_subsys = { DEFINE_PER_CPU(struct device *, mce_device); -void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu); - static inline struct mce_bank *attr_to_bank(struct device_attribute *attr) { return container_of(attr, struct mce_bank, attr); @@ -2409,6 +2463,10 @@ static int mce_device_create(unsigned int cpu) if (!mce_available(&boot_cpu_data)) return -EIO; + dev = per_cpu(mce_device, cpu); + if (dev) + return 0; + dev = kzalloc(sizeof *dev, GFP_KERNEL); if (!dev) return -ENOMEM; @@ -2468,28 +2526,25 @@ static void mce_device_remove(unsigned int cpu) } /* Make sure there are no machine checks on offlined CPUs. */ -static void mce_disable_cpu(void *h) +static void mce_disable_cpu(void) { - unsigned long action = *(unsigned long *)h; - if (!mce_available(raw_cpu_ptr(&cpu_info))) return; - if (!(action & CPU_TASKS_FROZEN)) + if (!cpuhp_tasks_frozen) cmci_clear(); vendor_disable_error_reporting(); } -static void mce_reenable_cpu(void *h) +static void mce_reenable_cpu(void) { - unsigned long action = *(unsigned long *)h; int i; if (!mce_available(raw_cpu_ptr(&cpu_info))) return; - if (!(action & CPU_TASKS_FROZEN)) + if (!cpuhp_tasks_frozen) cmci_reenable(); for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; @@ -2499,45 +2554,43 @@ static void mce_reenable_cpu(void *h) } } -/* Get notified when a cpu comes on/off. Be hotplug friendly. */ -static int -mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) +static int mce_cpu_dead(unsigned int cpu) +{ + mce_intel_hcpu_update(cpu); + + /* intentionally ignoring frozen here */ + if (!cpuhp_tasks_frozen) + cmci_rediscover(); + return 0; +} + +static int mce_cpu_online(unsigned int cpu) { - unsigned int cpu = (unsigned long)hcpu; struct timer_list *t = &per_cpu(mce_timer, cpu); + int ret; - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_ONLINE: - mce_device_create(cpu); - if (threshold_cpu_callback) - threshold_cpu_callback(action, cpu); - break; - case CPU_DEAD: - if (threshold_cpu_callback) - threshold_cpu_callback(action, cpu); - mce_device_remove(cpu); - mce_intel_hcpu_update(cpu); + mce_device_create(cpu); - /* intentionally ignoring frozen here */ - if (!(action & CPU_TASKS_FROZEN)) - cmci_rediscover(); - break; - case CPU_DOWN_PREPARE: - smp_call_function_single(cpu, mce_disable_cpu, &action, 1); - del_timer_sync(t); - break; - case CPU_DOWN_FAILED: - smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); - mce_start_timer(cpu, t); - break; + ret = mce_threshold_create_device(cpu); + if (ret) { + mce_device_remove(cpu); + return ret; } - - return NOTIFY_OK; + mce_reenable_cpu(); + mce_start_timer(cpu, t); + return 0; } -static struct notifier_block mce_cpu_notifier = { - .notifier_call = mce_cpu_callback, -}; +static int mce_cpu_pre_down(unsigned int cpu) +{ + struct timer_list *t = &per_cpu(mce_timer, cpu); + + mce_disable_cpu(); + del_timer_sync(t); + mce_threshold_remove_device(cpu); + mce_device_remove(cpu); + return 0; +} static __init void mce_init_banks(void) { @@ -2559,8 +2612,8 @@ static __init void mce_init_banks(void) static __init int mcheck_init_device(void) { + enum cpuhp_state hp_online; int err; - int i = 0; if (!mce_available(&boot_cpu_data)) { err = -EIO; @@ -2578,23 +2631,16 @@ static __init int mcheck_init_device(void) if (err) goto err_out_mem; - cpu_notifier_register_begin(); - for_each_online_cpu(i) { - err = mce_device_create(i); - if (err) { - /* - * Register notifier anyway (and do not unreg it) so - * that we don't leave undeleted timers, see notifier - * callback above. - */ - __register_hotcpu_notifier(&mce_cpu_notifier); - cpu_notifier_register_done(); - goto err_device_create; - } - } + err = cpuhp_setup_state(CPUHP_X86_MCE_DEAD, "x86/mce:dead", NULL, + mce_cpu_dead); + if (err) + goto err_out_mem; - __register_hotcpu_notifier(&mce_cpu_notifier); - cpu_notifier_register_done(); + err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/mce:online", + mce_cpu_online, mce_cpu_pre_down); + if (err < 0) + goto err_out_online; + hp_online = err; register_syscore_ops(&mce_syscore_ops); @@ -2607,16 +2653,10 @@ static __init int mcheck_init_device(void) err_register: unregister_syscore_ops(&mce_syscore_ops); + cpuhp_remove_state(hp_online); -err_device_create: - /* - * We didn't keep track of which devices were created above, but - * even if we had, the set of online cpus might have changed. - * Play safe and remove for every possible cpu, since - * mce_device_remove() will do the right thing. - */ - for_each_possible_cpu(i) - mce_device_remove(i); +err_out_online: + cpuhp_remove_state(CPUHP_X86_MCE_DEAD); err_out_mem: free_cpumask_var(mce_device_initialized); |