X-Git-Url: http://git.agner.ch/gitweb/?a=blobdiff_plain;f=kernel%2Fsoftlockup.c;h=0131e296ffb416435f7c54a935657c624a09d0c5;hb=aba297927d1d558c7a94548135133bdf9172708a;hp=50afeb813305d76435e8c6852a80b5b9dc5c8cd9;hpb=0cd43f83d381c4246a08cd775834833d6fd64805;p=linux-drm-fsl-dcu.git diff --git a/kernel/softlockup.c b/kernel/softlockup.c index 50afeb813305..0131e296ffb4 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -34,12 +34,32 @@ 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(void) +{ + return sched_clock() >> 30; /* 2^30 ~= 10^9 */ +} + void touch_softlockup_watchdog(void) { - __raw_get_cpu_var(touch_timestamp) = jiffies; + __raw_get_cpu_var(touch_timestamp) = get_timestamp(); } 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); + /* * This callback runs from the timer interrupt, and checks * whether the watchdog thread has hung or not: @@ -48,9 +68,18 @@ void softlockup_tick(void) { int this_cpu = smp_processor_id(); unsigned long touch_timestamp = per_cpu(touch_timestamp, this_cpu); + unsigned long print_timestamp; + unsigned long now; + + if (touch_timestamp == 0) { + touch_softlockup_watchdog(); + return; + } + + print_timestamp = per_cpu(print_timestamp, this_cpu); - /* prevent double reports: */ - if (per_cpu(print_timestamp, this_cpu) == touch_timestamp || + /* report at most once a second */ + if (print_timestamp < (touch_timestamp + 1) || did_panic || !per_cpu(watchdog_task, this_cpu)) return; @@ -61,12 +90,14 @@ void softlockup_tick(void) return; } + now = get_timestamp(); + /* Wake up the high-prio watchdog task every second: */ - if (time_after(jiffies, touch_timestamp + HZ)) + if (now > (touch_timestamp + 1)) wake_up_process(per_cpu(watchdog_task, this_cpu)); /* Warn about unreasonable 10+ seconds delays: */ - if (time_after(jiffies, touch_timestamp + 10*HZ)) { + if (now > (touch_timestamp + 10)) { per_cpu(print_timestamp, this_cpu) = touch_timestamp; spin_lock(&print_lock); @@ -82,11 +113,14 @@ void softlockup_tick(void) */ static int watchdog(void * __bind_cpu) { - struct sched_param param = { .sched_priority = 99 }; + 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(); + /* * Run briefly once per second to reset the softlockup timestamp. * If this gets delayed for more than 10 seconds then the @@ -112,27 +146,31 @@ 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); return NOTIFY_BAD; } - per_cpu(touch_timestamp, hotcpu) = jiffies; + per_cpu(touch_timestamp, hotcpu) = 0; per_cpu(watchdog_task, hotcpu) = p; kthread_bind(p, hotcpu); 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)); case CPU_DEAD: + case CPU_DEAD_FROZEN: p = per_cpu(watchdog_task, hotcpu); per_cpu(watchdog_task, hotcpu) = NULL; kthread_stop(p);