static int __init setup_nmi_watchdog(char *str)
{
- if (!strncmp(str, "panic", 5)) {
- panic_on_timeout = 1;
- str = strchr(str, ',');
- if (!str)
- return 1;
- ++str;
- }
- return 1;
+ if (!strncmp(str, "panic", 5)) {
+ panic_on_timeout = 1;
+ str = strchr(str, ',');
+ if (!str)
+ return 1;
+ ++str;
+ }
+ return 1;
}
__setup("nmi_watchdog=", setup_nmi_watchdog);
+struct perf_event_attr wd_hw_attr = {
+ .type = PERF_TYPE_HARDWARE,
+ .config = PERF_COUNT_HW_CPU_CYCLES,
+ .size = sizeof(struct perf_event_attr),
+ .pinned = 1,
+ .disabled = 1,
+};
+
+struct perf_event_attr wd_sw_attr = {
+ .type = PERF_TYPE_SOFTWARE,
+ .config = PERF_COUNT_SW_CPU_CLOCK,
+ .size = sizeof(struct perf_event_attr),
+ .pinned = 1,
+ .disabled = 1,
+};
+
+void wd_overflow(struct perf_event *event, int nmi,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ int cpu = smp_processor_id();
+ int touched = 0;
+
+ if (__get_cpu_var(nmi_watchdog_touch)) {
+ per_cpu(nmi_watchdog_touch, cpu) = 0;
+ touched = 1;
+ }
+
+ /* check to see if the cpu is doing anything */
+ if (!touched && hw_nmi_is_cpu_stuck(regs)) {
+ /*
+ * Ayiee, looks like this CPU is stuck ...
+ * wait a few IRQs (5 seconds) before doing the oops ...
+ */
+ per_cpu(alert_counter, cpu) += 1;
+ if (per_cpu(alert_counter, cpu) == 5) {
+ if (panic_on_timeout)
+ panic("NMI Watchdog detected LOCKUP on cpu %d", cpu);
+ else
+ WARN(1, "NMI Watchdog detected LOCKUP on cpu %d", cpu);
+ }
+ } else {
+ per_cpu(alert_counter, cpu) = 0;
+ }
+
+ return;
+}
+
+static int enable_nmi_watchdog(int cpu)
+{
+ struct perf_event *event;
+ struct perf_event_attr *wd_attr;
+
+ event = per_cpu(nmi_watchdog_ev, cpu);
+ if (event && event->state > PERF_EVENT_STATE_OFF)
+ return 0;
+
+ if (event == NULL) {
+ /* Try to register using hardware perf events first */
+ wd_attr = &wd_hw_attr;
+ wd_attr->sample_period = hw_nmi_get_sample_period();
+ event = perf_event_create_kernel_counter(wd_attr, cpu, -1, wd_overflow);
+ if (IS_ERR(event)) {
+ /* hardware doesn't exist or not supported, fallback to software events */
+ printk(KERN_INFO "nmi_watchdog: hardware not available, trying software events\n");
+ wd_attr = &wd_sw_attr;
+ wd_attr->sample_period = NSEC_PER_SEC;
+ event = perf_event_create_kernel_counter(wd_attr, cpu, -1, wd_overflow);
+ if (IS_ERR(event)) {
+ printk(KERN_ERR "nmi watchdog failed to create perf event on %i: %p\n", cpu, event);
+ return -1;
+ }
+ }
+ per_cpu(nmi_watchdog_ev, cpu) = event;
+ }
+ perf_event_enable(per_cpu(nmi_watchdog_ev, cpu));
+ return 0;
+}
+
+static void disable_nmi_watchdog(int cpu)
+{
+ struct perf_event *event;
+
+ event = per_cpu(nmi_watchdog_ev, cpu);
+ if (event) {
+ perf_event_disable(per_cpu(nmi_watchdog_ev, cpu));
+ per_cpu(nmi_watchdog_ev, cpu) = NULL;
+ perf_event_release_kernel(event);
+ }
+}
+
#ifdef CONFIG_SYSCTL
/*
* proc handler for /proc/sys/kernel/nmi_watchdog
struct perf_event *event;
for_each_online_cpu(cpu) {
event = per_cpu(nmi_watchdog_ev, cpu);
- if (event->state > PERF_EVENT_STATE_OFF) {
+ if (event && event->state > PERF_EVENT_STATE_OFF) {
nmi_watchdog_enabled = 1;
break;
}
return 0;
}
- if (per_cpu(nmi_watchdog_ev, smp_processor_id()) == NULL) {
- nmi_watchdog_enabled = 0;
- proc_dointvec(table, write, buffer, length, ppos);
- printk("NMI watchdog failed configuration, can not be enabled\n");
- return 0;
- }
-
touch_all_nmi_watchdog();
proc_dointvec(table, write, buffer, length, ppos);
- if (nmi_watchdog_enabled)
+ if (nmi_watchdog_enabled) {
for_each_online_cpu(cpu)
- perf_event_enable(per_cpu(nmi_watchdog_ev, cpu));
- else
+ if (enable_nmi_watchdog(cpu)) {
+ printk(KERN_ERR "NMI watchdog failed configuration, "
+ " can not be enabled\n");
+ }
+ } else {
for_each_online_cpu(cpu)
- perf_event_disable(per_cpu(nmi_watchdog_ev, cpu));
+ disable_nmi_watchdog(cpu);
+ }
return 0;
}
#endif /* CONFIG_SYSCTL */
-struct perf_event_attr wd_attr = {
- .type = PERF_TYPE_HARDWARE,
- .config = PERF_COUNT_HW_CPU_CYCLES,
- .size = sizeof(struct perf_event_attr),
- .pinned = 1,
- .disabled = 1,
-};
-
-void wd_overflow(struct perf_event *event, int nmi,
- struct perf_sample_data *data,
- struct pt_regs *regs)
-{
- int cpu = smp_processor_id();
- int touched = 0;
-
- if (__get_cpu_var(nmi_watchdog_touch)) {
- per_cpu(nmi_watchdog_touch, cpu) = 0;
- touched = 1;
- }
-
- /* check to see if the cpu is doing anything */
- if (!touched && hw_nmi_is_cpu_stuck(regs)) {
- /*
- * Ayiee, looks like this CPU is stuck ...
- * wait a few IRQs (5 seconds) before doing the oops ...
- */
- per_cpu(alert_counter,cpu) += 1;
- if (per_cpu(alert_counter,cpu) == 5) {
- if (panic_on_timeout) {
- panic("NMI Watchdog detected LOCKUP on cpu %d", cpu);
- } else {
- WARN(1, "NMI Watchdog detected LOCKUP on cpu %d", cpu);
- }
- }
- } else {
- per_cpu(alert_counter,cpu) = 0;
- }
-
- return;
-}
-
/*
* Create/destroy watchdog threads as CPUs come and go:
*/
cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
int hotcpu = (unsigned long)hcpu;
- struct perf_event *event;
switch (action) {
case CPU_UP_PREPARE:
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
- /* originally wanted the below chunk to be in CPU_UP_PREPARE, but caps is unpriv for non-CPU0 */
- wd_attr.sample_period = hw_nmi_get_sample_period();
- event = perf_event_create_kernel_counter(&wd_attr, hotcpu, -1, wd_overflow);
- if (IS_ERR(event)) {
- printk(KERN_ERR "nmi watchdog failed to create perf event on %i: %p\n", hotcpu, event);
+ if (enable_nmi_watchdog(hotcpu))
return NOTIFY_BAD;
- }
- per_cpu(nmi_watchdog_ev, hotcpu) = event;
- perf_event_enable(per_cpu(nmi_watchdog_ev, hotcpu));
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
- perf_event_disable(per_cpu(nmi_watchdog_ev, hotcpu));
+ disable_nmi_watchdog(hotcpu);
case CPU_DEAD:
case CPU_DEAD_FROZEN:
- event = per_cpu(nmi_watchdog_ev, hotcpu);
- per_cpu(nmi_watchdog_ev, hotcpu) = NULL;
- perf_event_release_kernel(event);
break;
#endif /* CONFIG_HOTPLUG_CPU */
}
if (nonmi_watchdog)
return 0;
+ printk(KERN_INFO "NMI watchdog enabled, takes one hw-pmu counter.\n");
+
err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
if (err == NOTIFY_BAD) {
BUG();