diff options
Diffstat (limited to 'arch/x86/kernel/cpu/mcheck/mce.c')
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce.c | 72 |
1 files changed, 50 insertions, 22 deletions
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 68317c80de7f..bd9ccda8087f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -60,8 +60,6 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); #define SPINUNIT 100 /* 100ns */ -atomic_t mce_entry; - DEFINE_PER_CPU(unsigned, mce_exception_count); struct mce_bank *mce_banks __read_mostly; @@ -704,8 +702,7 @@ static int mce_timed_out(u64 *t) if (!mca_cfg.monarch_timeout) goto out; if ((s64)*t < SPINUNIT) { - /* CHECKME: Make panic default for 1 too? */ - if (mca_cfg.tolerant < 1) + if (mca_cfg.tolerant <= 1) mce_panic("Timeout synchronizing machine check over CPUs", NULL, NULL); cpu_missing = 1; @@ -1041,8 +1038,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); char *msg = "Unknown"; - atomic_inc(&mce_entry); - this_cpu_inc(mce_exception_count); if (!cfg->banks) @@ -1172,7 +1167,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) mce_report_event(regs); mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); out: - atomic_dec(&mce_entry); sync_core(); } EXPORT_SYMBOL_GPL(do_machine_check); @@ -2142,7 +2136,7 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr, { u64 new; - if (strict_strtoull(buf, 0, &new) < 0) + if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; attr_to_bank(attr)->ctl = new; @@ -2180,7 +2174,7 @@ static ssize_t set_ignore_ce(struct device *s, { u64 new; - if (strict_strtoull(buf, 0, &new) < 0) + if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; if (mca_cfg.ignore_ce ^ !!new) { @@ -2204,7 +2198,7 @@ static ssize_t set_cmci_disabled(struct device *s, { u64 new; - if (strict_strtoull(buf, 0, &new) < 0) + if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; if (mca_cfg.cmci_disabled ^ !!new) { @@ -2391,6 +2385,10 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) threshold_cpu_callback(action, cpu); mce_device_remove(cpu); mce_intel_hcpu_update(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); @@ -2402,11 +2400,6 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) break; } - if (action == CPU_POST_DEAD) { - /* intentionally ignoring frozen here */ - cmci_rediscover(); - } - return NOTIFY_OK; } @@ -2437,32 +2430,67 @@ static __init int mcheck_init_device(void) int err; int i = 0; - if (!mce_available(&boot_cpu_data)) - return -EIO; + if (!mce_available(&boot_cpu_data)) { + err = -EIO; + goto err_out; + } - zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL); + if (!zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL)) { + err = -ENOMEM; + goto err_out; + } mce_init_banks(); err = subsys_system_register(&mce_subsys, NULL); if (err) - return 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(); - return err; + goto err_device_create; } } - register_syscore_ops(&mce_syscore_ops); __register_hotcpu_notifier(&mce_cpu_notifier); cpu_notifier_register_done(); + register_syscore_ops(&mce_syscore_ops); + /* register character device /dev/mcelog */ - misc_register(&mce_chrdev_device); + err = misc_register(&mce_chrdev_device); + if (err) + goto err_register; + + return 0; + +err_register: + unregister_syscore_ops(&mce_syscore_ops); + +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_mem: + free_cpumask_var(mce_device_initialized); + +err_out: + pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err); return err; } |