X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fsoftlockup.c;h=81324d12eb35a5db7fae8a0ae3d18c76ca38ce67;hb=fbfecd3712f917ca210a55c157233d88b785896b;hp=81d43caa2012feed6eff4a95f3cd6b1369483fe5;hpb=02fb6149f7a64c62934c035e7635321cb9a8cf2e;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/softlockup.c b/kernel/softlockup.c index 81d43ca..81324d1 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -8,11 +8,17 @@ */ #include #include +#include #include #include +#include #include +#include #include #include +#include + +#include static DEFINE_SPINLOCK(print_lock); @@ -20,7 +26,23 @@ static DEFINE_PER_CPU(unsigned long, touch_timestamp); static DEFINE_PER_CPU(unsigned long, print_timestamp); static DEFINE_PER_CPU(struct task_struct *, watchdog_task); -static int did_panic = 0; +static int __read_mostly did_panic; +int __read_mostly softlockup_thresh = 60; + +/* + * Should we panic (and reboot, if panic_timeout= is set) when a + * soft-lockup occurs: + */ +unsigned int __read_mostly softlockup_panic = + CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; + +static int __init softlockup_panic_setup(char *str) +{ + softlockup_panic = simple_strtoul(str, NULL, 0); + + return 1; +} +__setup("softlockup_panic=", softlockup_panic_setup); static int softlock_panic(struct notifier_block *this, unsigned long event, void *ptr) @@ -34,12 +56,47 @@ static struct notifier_block panic_block = { .notifier_call = softlock_panic, }; +/* + * Returns seconds, approximately. We don't need nanosecond + * resolution, and we don't need to waste time with a big divide when + * 2^30ns == 1.074s. + */ +static unsigned long get_timestamp(int this_cpu) +{ + return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */ +} + +static void __touch_softlockup_watchdog(void) +{ + int this_cpu = raw_smp_processor_id(); + + __raw_get_cpu_var(touch_timestamp) = get_timestamp(this_cpu); +} + void touch_softlockup_watchdog(void) { - __raw_get_cpu_var(touch_timestamp) = jiffies; + __raw_get_cpu_var(touch_timestamp) = 0; } EXPORT_SYMBOL(touch_softlockup_watchdog); +void touch_all_softlockup_watchdogs(void) +{ + int cpu; + + /* Cause each CPU to re-update its timestamp rather than complain */ + for_each_online_cpu(cpu) + per_cpu(touch_timestamp, cpu) = 0; +} +EXPORT_SYMBOL(touch_all_softlockup_watchdogs); + +int proc_dosoftlockup_thresh(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + touch_all_softlockup_watchdogs(); + return proc_dointvec_minmax(table, write, buffer, lenp, ppos); +} + /* * This callback runs from the timer interrupt, and checks * whether the watchdog thread has hung or not: @@ -48,55 +105,94 @@ void softlockup_tick(void) { int this_cpu = smp_processor_id(); unsigned long touch_timestamp = per_cpu(touch_timestamp, this_cpu); + unsigned long print_timestamp; + struct pt_regs *regs = get_irq_regs(); + unsigned long now; + + /* Is detection switched off? */ + if (!per_cpu(watchdog_task, this_cpu) || softlockup_thresh <= 0) { + /* Be sure we don't false trigger if switched back on */ + if (touch_timestamp) + per_cpu(touch_timestamp, this_cpu) = 0; + return; + } - /* prevent double reports: */ - if (per_cpu(print_timestamp, this_cpu) == touch_timestamp || - did_panic || - !per_cpu(watchdog_task, this_cpu)) + if (touch_timestamp == 0) { + __touch_softlockup_watchdog(); + return; + } + + print_timestamp = per_cpu(print_timestamp, this_cpu); + + /* report at most once a second */ + if (print_timestamp == touch_timestamp || did_panic) return; /* do not print during early bootup: */ if (unlikely(system_state != SYSTEM_RUNNING)) { - touch_softlockup_watchdog(); + __touch_softlockup_watchdog(); return; } - /* Wake up the high-prio watchdog task every second: */ - if (time_after(jiffies, touch_timestamp + HZ)) + now = get_timestamp(this_cpu); + + /* + * Wake up the high-prio watchdog task twice per + * threshold timespan. + */ + if (now > touch_timestamp + softlockup_thresh/2) wake_up_process(per_cpu(watchdog_task, this_cpu)); - /* Warn about unreasonable 10+ seconds delays: */ - if (time_after(jiffies, touch_timestamp + 10*HZ)) { - per_cpu(print_timestamp, this_cpu) = touch_timestamp; + /* Warn about unreasonable delays: */ + if (now <= (touch_timestamp + softlockup_thresh)) + return; + + per_cpu(print_timestamp, this_cpu) = touch_timestamp; - spin_lock(&print_lock); - printk(KERN_ERR "BUG: soft lockup detected on CPU#%d!\n", - this_cpu); + spin_lock(&print_lock); + printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %lus! [%s:%d]\n", + this_cpu, now - touch_timestamp, + current->comm, task_pid_nr(current)); + print_modules(); + print_irqtrace_events(current); + if (regs) + show_regs(regs); + else dump_stack(); - spin_unlock(&print_lock); - } + spin_unlock(&print_lock); + + if (softlockup_panic) + panic("softlockup: hung tasks"); } /* * The watchdog thread - runs every second and touches the timestamp. */ -static int watchdog(void * __bind_cpu) +static int watchdog(void *__bind_cpu) { struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; sched_setscheduler(current, SCHED_FIFO, ¶m); - current->flags |= PF_NOFREEZE; + /* initialize timestamp */ + __touch_softlockup_watchdog(); + + set_current_state(TASK_INTERRUPTIBLE); /* * Run briefly once per second to reset the softlockup timestamp. - * If this gets delayed for more than 10 seconds then the + * If this gets delayed for more than 60 seconds then the * debug-printout triggers in softlockup_tick(). */ while (!kthread_should_stop()) { - set_current_state(TASK_INTERRUPTIBLE); - touch_softlockup_watchdog(); + __touch_softlockup_watchdog(); schedule(); + + if (kthread_should_stop()) + break; + + set_current_state(TASK_INTERRUPTIBLE); } + __set_current_state(TASK_RUNNING); return 0; } @@ -112,33 +208,37 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) switch (action) { case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: BUG_ON(per_cpu(watchdog_task, hotcpu)); p = kthread_create(watchdog, hcpu, "watchdog/%d", hotcpu); if (IS_ERR(p)) { - printk("watchdog for %i failed\n", hotcpu); + printk(KERN_ERR "watchdog for %i failed\n", hotcpu); return NOTIFY_BAD; } - per_cpu(touch_timestamp, hotcpu) = jiffies; - per_cpu(watchdog_task, hotcpu) = p; + per_cpu(touch_timestamp, hotcpu) = 0; + per_cpu(watchdog_task, hotcpu) = p; kthread_bind(p, hotcpu); - break; + break; case CPU_ONLINE: + case CPU_ONLINE_FROZEN: wake_up_process(per_cpu(watchdog_task, hotcpu)); break; #ifdef CONFIG_HOTPLUG_CPU case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: if (!per_cpu(watchdog_task, hotcpu)) break; /* Unbind so it can run. Fall thru. */ kthread_bind(per_cpu(watchdog_task, hotcpu), - any_online_cpu(cpu_online_map)); + cpumask_any(cpu_online_mask)); case CPU_DEAD: + case CPU_DEAD_FROZEN: p = per_cpu(watchdog_task, hotcpu); per_cpu(watchdog_task, hotcpu) = NULL; kthread_stop(p); break; #endif /* CONFIG_HOTPLUG_CPU */ - } + } return NOTIFY_OK; } @@ -146,14 +246,33 @@ static struct notifier_block __cpuinitdata cpu_nfb = { .notifier_call = cpu_callback }; -__init void spawn_softlockup_task(void) +static int __initdata nosoftlockup; + +static int __init nosoftlockup_setup(char *str) +{ + nosoftlockup = 1; + return 1; +} +__setup("nosoftlockup", nosoftlockup_setup); + +static int __init spawn_softlockup_task(void) { void *cpu = (void *)(long)smp_processor_id(); - int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); + int err; + + if (nosoftlockup) + return 0; - BUG_ON(err == NOTIFY_BAD); + err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); + if (err == NOTIFY_BAD) { + BUG(); + return 1; + } cpu_callback(&cpu_nfb, CPU_ONLINE, cpu); register_cpu_notifier(&cpu_nfb); atomic_notifier_chain_register(&panic_notifier_list, &panic_block); + + return 0; } +early_initcall(spawn_softlockup_task);