X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fsoftlockup.c;h=cb838ee93a82000bc5b313271487836e9fb5804e;hb=171ac6ae94e31d0fcb5ae922efd4a77a7e48b4e5;hp=02f0ad5344419d73e8716a7af48d0822efcd5b59;hpb=82a1fcb90287052aabfa235e7ffc693ea003fe69;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/softlockup.c b/kernel/softlockup.c index 02f0ad5..cb838ee 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -24,8 +25,23 @@ 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; -int softlockup_thresh = 60; +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) @@ -49,12 +65,17 @@ 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) @@ -79,28 +100,40 @@ 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; @@ -111,24 +144,29 @@ 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); + + if (softlockup_panic) + panic("softlockup: hung tasks"); } /* * Have a reasonable limit on the number of tasks checked: */ -unsigned long sysctl_hung_task_check_count = 1024; +unsigned long __read_mostly sysctl_hung_task_check_count = 1024; /* * Zero means infinite timeout - no checking done: */ -unsigned long sysctl_hung_task_timeout_secs = 120; +unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120; -long sysctl_hung_task_warnings = 10; +unsigned long __read_mostly sysctl_hung_task_warnings = 10; /* * Only do the hung-tasks check on one CPU: @@ -168,6 +206,9 @@ static void check_hung_task(struct task_struct *t, unsigned long now) t->last_switch_timestamp = now; touch_nmi_watchdog(); + + if (softlockup_panic) + panic("softlockup: blocked tasks"); } /* @@ -191,11 +232,12 @@ static void check_hung_uninterruptible_tasks(int this_cpu) read_lock(&tasklist_lock); do_each_thread(g, t) { if (!--max_count) - break; - if (t->state & TASK_UNINTERRUPTIBLE) + goto unlock; + /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */ + if (t->state == TASK_UNINTERRUPTIBLE) check_hung_task(t, now); } while_each_thread(g, t); - + unlock: read_unlock(&tasklist_lock); } @@ -210,23 +252,29 @@ static int watchdog(void *__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); + if (this_cpu == check_cpu) { + if (sysctl_hung_task_timeout_secs) + check_hung_uninterruptible_tasks(this_cpu); + } + + set_current_state(TASK_INTERRUPTIBLE); } + __set_current_state(TASK_RUNNING); return 0; } @@ -259,13 +307,6 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) 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)); case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: if (hotcpu == check_cpu) { @@ -275,6 +316,14 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) check_cpu = any_online_cpu(temp_cpu_online_map); } break; + + 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)); case CPU_DEAD: case CPU_DEAD_FROZEN: p = per_cpu(watchdog_task, hotcpu); @@ -290,14 +339,33 @@ 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);