linux/arch/x86/kernel/apic/hw_nmi.c
Mandeep Singh Baines 4eec42f392 watchdog: Change the default timeout and configure nmi watchdog period based on watchdog_thresh
Before the conversion of the NMI watchdog to perf event, the
watchdog timeout was 5 seconds. Now it is 60 seconds. For my
particular application, netbooks, 5 seconds was a better
timeout. With a short timeout, we catch faults earlier and are
able to send back a panic. With a 60 second timeout, the user is
unlikely to wait and will instead hit the power button, causing
us to lose the panic info.

This change configures the NMI period to watchdog_thresh and
sets the softlockup_thresh to watchdog_thresh * 2. In addition,
watchdog_thresh was reduced to 10 seconds as suggested by Ingo
Molnar.

Signed-off-by: Mandeep Singh Baines <msb@chromium.org>
Cc: Marcin Slusarz <marcin.slusarz@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/1306127423-3347-4-git-send-email-msb@chromium.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
LKML-Reference: <20110517071642.GF22305@elte.hu>
2011-05-23 11:58:59 +02:00

108 lines
2.4 KiB
C

/*
* HW NMI watchdog support
*
* started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
*
* Arch specific calls to support NMI watchdog
*
* Bits copied from original nmi.c file
*
*/
#include <asm/apic.h>
#include <linux/cpumask.h>
#include <linux/kdebug.h>
#include <linux/notifier.h>
#include <linux/kprobes.h>
#include <linux/nmi.h>
#include <linux/module.h>
#include <linux/delay.h>
#ifdef CONFIG_HARDLOCKUP_DETECTOR
u64 hw_nmi_get_sample_period(int watchdog_thresh)
{
return (u64)(cpu_khz) * 1000 * watchdog_thresh;
}
#endif
#ifdef arch_trigger_all_cpu_backtrace
/* For reliability, we're prepared to waste bits here. */
static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
/* "in progress" flag of arch_trigger_all_cpu_backtrace */
static unsigned long backtrace_flag;
void arch_trigger_all_cpu_backtrace(void)
{
int i;
if (test_and_set_bit(0, &backtrace_flag))
/*
* If there is already a trigger_all_cpu_backtrace() in progress
* (backtrace_flag == 1), don't output double cpu dump infos.
*/
return;
cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
printk(KERN_INFO "sending NMI to all CPUs:\n");
apic->send_IPI_all(NMI_VECTOR);
/* Wait for up to 10 seconds for all CPUs to do the backtrace */
for (i = 0; i < 10 * 1000; i++) {
if (cpumask_empty(to_cpumask(backtrace_mask)))
break;
mdelay(1);
}
clear_bit(0, &backtrace_flag);
smp_mb__after_clear_bit();
}
static int __kprobes
arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
unsigned long cmd, void *__args)
{
struct die_args *args = __args;
struct pt_regs *regs;
int cpu;
switch (cmd) {
case DIE_NMI:
break;
default:
return NOTIFY_DONE;
}
regs = args->regs;
cpu = smp_processor_id();
if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;
arch_spin_lock(&lock);
printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
show_regs(regs);
arch_spin_unlock(&lock);
cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
return NOTIFY_STOP;
}
return NOTIFY_DONE;
}
static __read_mostly struct notifier_block backtrace_notifier = {
.notifier_call = arch_trigger_all_cpu_backtrace_handler,
.next = NULL,
.priority = NMI_LOCAL_LOW_PRIOR,
};
static int __init register_trigger_all_cpu_backtrace(void)
{
register_die_notifier(&backtrace_notifier);
return 0;
}
early_initcall(register_trigger_all_cpu_backtrace);
#endif