#include <linux/cpumask.h>
#include <linux/kernel_stat.h>
#include <linux/kdebug.h>
+#include <linux/slab.h>
#include <asm/smp.h>
#include <asm/nmi.h>
+#include <asm/timer.h>
#include "mach_traps.h"
}
#endif
-static int __init check_nmi_watchdog(void)
+int __init check_nmi_watchdog(void)
{
unsigned int *prev_nmi_count;
int cpu;
prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL);
if (!prev_nmi_count)
- return -1;
+ goto error;
printk(KERN_INFO "Testing NMI watchdog ... ");
if (!atomic_read(&nmi_active)) {
kfree(prev_nmi_count);
atomic_set(&nmi_active, -1);
- return -1;
+ goto error;
}
printk("OK.\n");
kfree(prev_nmi_count);
return 0;
+error:
+ timer_ack = !cpu_has_tsc;
+
+ return -1;
}
-/* This needs to happen later in boot so counters are working */
-late_initcall(check_nmi_watchdog);
static int __init setup_nmi_watchdog(char *str)
{
* here too!]
*/
-static unsigned int
- last_irq_sums [NR_CPUS],
- alert_counter [NR_CPUS];
+static DEFINE_PER_CPU(unsigned, last_irq_sum);
+static DEFINE_PER_CPU(local_t, alert_counter);
+static DEFINE_PER_CPU(int, nmi_touch);
void touch_nmi_watchdog(void)
{
unsigned cpu;
/*
- * Just reset the alert counters, (other CPUs might be
- * spinning on locks we hold):
+ * Tell other CPUs to reset their alert counters. We cannot
+ * do it ourselves because the alert count increase is not
+ * atomic.
*/
for_each_present_cpu(cpu) {
- if (alert_counter[cpu])
- alert_counter[cpu] = 0;
+ if (per_cpu(nmi_touch, cpu) != 1)
+ per_cpu(nmi_touch, cpu) = 1;
}
}
}
EXPORT_SYMBOL(touch_nmi_watchdog);
-extern void die_nmi(struct pt_regs *, const char *msg);
-
-__kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
+notrace __kprobes int
+nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
{
/*
*/
sum = per_cpu(irq_stat, cpu).apic_timer_irqs +
per_cpu(irq_stat, cpu).irq0_irqs;
+ if (__get_cpu_var(nmi_touch)) {
+ __get_cpu_var(nmi_touch) = 0;
+ touched = 1;
+ }
/* if the none of the timers isn't firing, this cpu isn't doing much */
- if (!touched && last_irq_sums[cpu] == sum) {
+ 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 ...
*/
- alert_counter[cpu]++;
- if (alert_counter[cpu] == 5*nmi_hz)
+ local_inc(&__get_cpu_var(alert_counter));
+ if (local_read(&__get_cpu_var(alert_counter)) == 5*nmi_hz)
/*
* die_nmi will return ONLY if NOTIFY_STOP happens..
*/
- die_nmi(regs, "BUG: NMI Watchdog detected LOCKUP");
+ die_nmi("BUG: NMI Watchdog detected LOCKUP",
+ regs, 0);
} else {
- last_irq_sums[cpu] = sum;
- alert_counter[cpu] = 0;
+ __get_cpu_var(last_irq_sum) = sum;
+ local_set(&__get_cpu_var(alert_counter), 0);
}
/* see if the nmi watchdog went off */
if (!__get_cpu_var(wd_enabled))
char buf[64];
sprintf(buf, "NMI received for unknown reason %02x\n", reason);
- die_nmi(regs, buf);
+ die_nmi(buf, regs, 0);
return 0;
}