.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:
{
int this_cpu = smp_processor_id();
unsigned long touch_timestamp = per_cpu(touch_timestamp, this_cpu);
+ unsigned long print_timestamp;
+ unsigned long now;
- /* prevent double reports: */
- if (per_cpu(print_timestamp, this_cpu) == touch_timestamp ||
+ 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 + 1) ||
did_panic ||
!per_cpu(watchdog_task, this_cpu))
return;
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);
*/
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
/*
* Create/destroy watchdog threads as CPUs come and go:
*/
-static int
+static int __cpuinit
cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
int hotcpu = (unsigned long)hcpu;
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;
return NOTIFY_OK;
}
-static struct notifier_block cpu_nfb = {
+static struct notifier_block __cpuinitdata cpu_nfb = {
.notifier_call = cpu_callback
};
__init void spawn_softlockup_task(void)
{
void *cpu = (void *)(long)smp_processor_id();
+ int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
- cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
+ BUG_ON(err == NOTIFY_BAD);
cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
register_cpu_notifier(&cpu_nfb);