Esempio n. 1
0
int nmi_watchdog_tick (struct pt_regs * regs)
{

	/*
	 * Since current_thread_info()-> is always on the stack, and we
	 * always switch the stack NMI-atomically, it's safe to use
	 * smp_processor_id().
	 */
	int sum, cpu = smp_processor_id(), rc = 0;

	sum = irq_stat[cpu].apic_timer_irqs;

	if (last_irq_sums[cpu] == sum) {
		/*
		 * Ayiee, looks like this CPU is stuck ...
		 * wait a few IRQs (5 seconds) before doing the oops ...
		 */
		alert_counter[cpu]++;
		if (alert_counter[cpu] == 30*nmi_hz)
			die_nmi(regs, "NMI Watchdog detected LOCKUP");
	} else {
		last_irq_sums[cpu] = sum;
		alert_counter[cpu] = 0;
	}
	/* see if the nmi watchdog went off */
	if (!__get_cpu_var(wd_enabled))
		return rc;
	switch (nmi_watchdog) {
	case NMI_LOCAL_APIC:
		rc |= lapic_wd_event(nmi_hz);
		break;
	case NMI_IO_APIC:
		/*
		 * don't know how to accurately check for this.
		 * just assume it was a watchdog timer interrupt
		 * This matches the old behaviour.
		 */
		rc = 1;
		break;
	}
	return rc;
}
Esempio n. 2
0
notrace __kprobes int
nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
{
	/*
	 * Since current_thread_info()-> is always on the stack, and we
	 * always switch the stack NMI-atomically, it's safe to use
	 * smp_processor_id().
	 */
	unsigned int sum;
	int touched = 0;
	int cpu = smp_processor_id();
	int rc = 0;

	/* check for other users first */
	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
			== NOTIFY_STOP) {
		rc = 1;
		touched = 1;
	}

	sum = get_timer_irqs(cpu);

	if (__get_cpu_var(nmi_touch)) {
		__get_cpu_var(nmi_touch) = 0;
		touched = 1;
	}

	/* We can be called before check_nmi_watchdog, hence NULL check. */
	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
		static DEFINE_RAW_SPINLOCK(lock); /* Serialise the printks */

		raw_spin_lock(&lock);
		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
		show_regs(regs);
		dump_stack();
		raw_spin_unlock(&lock);
		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));

		rc = 1;
	}

	/* Could check oops_in_progress here too, but it's safer not to */
	if (mce_in_progress())
		touched = 1;

	/* if the none of the timers isn't firing, this cpu isn't doing much */
	if (!touched && __get_cpu_var(last_irq_sum) == sum) {
		/*
		 * Ayiee, looks like this CPU is stuck ...
		 * wait a few IRQs (5 seconds) before doing the oops ...
		 */
		__this_cpu_inc(alert_counter);
		if (__this_cpu_read(alert_counter) == 5 * nmi_hz)
			/*
			 * die_nmi will return ONLY if NOTIFY_STOP happens..
			 */
			die_nmi("BUG: NMI Watchdog detected LOCKUP",
				regs, panic_on_timeout);
	} else {
		__get_cpu_var(last_irq_sum) = sum;
		__this_cpu_write(alert_counter, 0);
	}

	/* see if the nmi watchdog went off */
	if (!__get_cpu_var(wd_enabled))
		return rc;
	switch (nmi_watchdog) {
	case NMI_LOCAL_APIC:
		rc |= lapic_wd_event(nmi_hz);
		break;
	case NMI_IO_APIC:
		/*
		 * don't know how to accurately check for this.
		 * just assume it was a watchdog timer interrupt
		 * This matches the old behaviour.
		 */
		rc = 1;
		break;
	}
	return rc;
}