X-Git-Url: http://ftp.safe.ca/?p=safe%2Fjmp%2Flinux-2.6;a=blobdiff_plain;f=kernel%2Fsoftlockup.c;h=81324d12eb35a5db7fae8a0ae3d18c76ca38ce67;hp=708d4882c0c391bffa47a24ae0153bccabd0a1c7;hb=822a6961112f0c9101d3359d8524604c3309ee6c;hpb=831441862956fffa17b9801db37e6ea1650b0f69 diff --git a/kernel/softlockup.c b/kernel/softlockup.c index 708d488..81324d1 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -8,12 +8,17 @@ */ #include #include +#include #include #include #include #include +#include #include #include +#include + +#include static DEFINE_SPINLOCK(print_lock); @@ -21,7 +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) @@ -40,14 +61,21 @@ static struct notifier_block panic_block = { * resolution, and we don't need to waste time with a big divide when * 2^30ns == 1.074s. */ -static unsigned long get_timestamp(void) +static unsigned long get_timestamp(int this_cpu) +{ + return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */ +} + +static void __touch_softlockup_watchdog(void) { - return sched_clock() >> 30; /* 2^30 ~= 10^9 */ + 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) = get_timestamp(); + __raw_get_cpu_var(touch_timestamp) = 0; } EXPORT_SYMBOL(touch_softlockup_watchdog); @@ -61,6 +89,14 @@ void touch_all_softlockup_watchdogs(void) } 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: @@ -70,67 +106,93 @@ 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; + } + if (touch_timestamp == 0) { - touch_softlockup_watchdog(); + __touch_softlockup_watchdog(); return; } print_timestamp = per_cpu(print_timestamp, this_cpu); /* report at most once a second */ - if (print_timestamp < (touch_timestamp + 1) || - did_panic || - !per_cpu(watchdog_task, this_cpu)) + 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; } - now = get_timestamp(); + now = get_timestamp(this_cpu); - /* Wake up the high-prio watchdog task every second: */ - if (now > (touch_timestamp + 1)) + /* + * 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 (now > (touch_timestamp + 10)) { - 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); /* initialize timestamp */ - touch_softlockup_watchdog(); + __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; } @@ -150,13 +212,13 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) 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) = 0; - 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)); @@ -168,7 +230,7 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) 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); @@ -176,7 +238,7 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) kthread_stop(p); break; #endif /* CONFIG_HOTPLUG_CPU */ - } + } return NOTIFY_OK; } @@ -184,14 +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; - BUG_ON(err == NOTIFY_BAD); + if (nosoftlockup) + return 0; + + 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);