X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fsoftlockup.c;h=81324d12eb35a5db7fae8a0ae3d18c76ca38ce67;hb=260c64d23532caf19abb77e696971da05c388489;hp=c1d76552446e592bc132d8de37073ecb589a1629;hpb=90739081ef8d5495d50abba9c5d333be9acd872a;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/softlockup.c b/kernel/softlockup.c index c1d7655..81324d1 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -13,8 +13,10 @@ #include #include #include +#include #include #include +#include #include @@ -25,7 +27,22 @@ static DEFINE_PER_CPU(unsigned long, print_timestamp); static DEFINE_PER_CPU(struct task_struct *, watchdog_task); static int __read_mostly did_panic; -unsigned long __read_mostly softlockup_thresh = 60; +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) @@ -49,12 +66,17 @@ static unsigned long get_timestamp(int this_cpu) return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */ } -void touch_softlockup_watchdog(void) +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) = 0; +} EXPORT_SYMBOL(touch_softlockup_watchdog); void touch_all_softlockup_watchdogs(void) @@ -67,6 +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: @@ -79,28 +109,40 @@ void softlockup_tick(void) 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 && - 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(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 delays: */ if (now <= (touch_timestamp + softlockup_thresh)) return; @@ -111,92 +153,16 @@ void softlockup_tick(void) 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); -} - -/* - * Have a reasonable limit on the number of tasks checked: - */ -unsigned long __read_mostly sysctl_hung_task_check_count = 1024; -/* - * Zero means infinite timeout - no checking done: - */ -unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120; - -unsigned long __read_mostly sysctl_hung_task_warnings = 10; - -/* - * Only do the hung-tasks check on one CPU: - */ -static int check_cpu __read_mostly = -1; - -static void check_hung_task(struct task_struct *t, unsigned long now) -{ - unsigned long switch_count = t->nvcsw + t->nivcsw; - - if (t->flags & PF_FROZEN) - return; - - if (switch_count != t->last_switch_count || !t->last_switch_timestamp) { - t->last_switch_count = switch_count; - t->last_switch_timestamp = now; - return; - } - if ((long)(now - t->last_switch_timestamp) < - sysctl_hung_task_timeout_secs) - return; - if (sysctl_hung_task_warnings < 0) - return; - sysctl_hung_task_warnings--; - - /* - * Ok, the task did not get scheduled for more than 2 minutes, - * complain: - */ - printk(KERN_ERR "INFO: task %s:%d blocked for more than " - "%ld seconds.\n", t->comm, t->pid, - sysctl_hung_task_timeout_secs); - printk(KERN_ERR "\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\"" - " disables this message.\n"); - sched_show_task(t); - __debug_show_held_locks(t); - - t->last_switch_timestamp = now; - touch_nmi_watchdog(); -} - -/* - * Check whether a TASK_UNINTERRUPTIBLE does not get woken up for - * a really long time (120 seconds). If that happens, print out - * a warning. - */ -static void check_hung_uninterruptible_tasks(int this_cpu) -{ - int max_count = sysctl_hung_task_check_count; - unsigned long now = get_timestamp(this_cpu); - struct task_struct *g, *t; - - /* - * If the system crashed already then all bets are off, - * do not report extra hung tasks: - */ - if ((tainted & TAINT_DIE) || did_panic) - return; - - read_lock(&tasklist_lock); - do_each_thread(g, t) { - if (!--max_count) - break; - if (t->state & TASK_UNINTERRUPTIBLE) - check_hung_task(t, now); - } while_each_thread(g, t); - - read_unlock(&tasklist_lock); + if (softlockup_panic) + panic("softlockup: hung tasks"); } /* @@ -205,28 +171,28 @@ static void check_hung_uninterruptible_tasks(int this_cpu) static int watchdog(void *__bind_cpu) { struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; - int this_cpu = (long)__bind_cpu; 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 60 seconds then the * debug-printout triggers in softlockup_tick(). */ while (!kthread_should_stop()) { - touch_softlockup_watchdog(); - msleep_interruptible(10000); + __touch_softlockup_watchdog(); + schedule(); - if (this_cpu != check_cpu) - continue; + if (kthread_should_stop()) + break; - if (sysctl_hung_task_timeout_secs) - check_hung_uninterruptible_tasks(this_cpu); + set_current_state(TASK_INTERRUPTIBLE); } + __set_current_state(TASK_RUNNING); return 0; } @@ -255,7 +221,6 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) break; case CPU_ONLINE: case CPU_ONLINE_FROZEN: - check_cpu = any_online_cpu(cpu_online_map); wake_up_process(per_cpu(watchdog_task, hotcpu)); break; #ifdef CONFIG_HOTPLUG_CPU @@ -265,16 +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)); - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - if (hotcpu == check_cpu) { - cpumask_t temp_cpu_online_map = cpu_online_map; - - cpu_clear(hotcpu, temp_cpu_online_map); - check_cpu = any_online_cpu(temp_cpu_online_map); - } - break; + cpumask_any(cpu_online_mask)); case CPU_DEAD: case CPU_DEAD_FROZEN: p = per_cpu(watchdog_task, hotcpu); @@ -290,14 +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);