*/
#include <linux/mm.h>
#include <linux/cpu.h>
+#include <linux/nmi.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/freezer.h>
#include <linux/notifier.h>
#include <linux/module.h>
+#include <asm/irq_regs.h>
+
static DEFINE_SPINLOCK(print_lock);
static DEFINE_PER_CPU(unsigned long, touch_timestamp);
static DEFINE_PER_CPU(unsigned long, print_timestamp);
static DEFINE_PER_CPU(struct task_struct *, watchdog_task);
-static int did_panic = 0;
+static int __read_mostly did_panic;
+unsigned long __read_mostly softlockup_thresh = 60;
static int
softlock_panic(struct notifier_block *this, unsigned long event, void *ptr)
*/
static unsigned long get_timestamp(int this_cpu)
{
- return cpu_clock(this_cpu) >> 30; /* 2^30 ~= 10^9 */
+ return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */
}
void touch_softlockup_watchdog(void)
int this_cpu = smp_processor_id();
unsigned long touch_timestamp = per_cpu(touch_timestamp, this_cpu);
unsigned long print_timestamp;
+ struct pt_regs *regs = get_irq_regs();
unsigned long now;
if (touch_timestamp == 0) {
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))
+ if ((print_timestamp >= touch_timestamp &&
+ print_timestamp < (touch_timestamp + 1)) ||
+ did_panic || !per_cpu(watchdog_task, this_cpu)) {
return;
+ }
/* do not print during early bootup: */
if (unlikely(system_state != SYSTEM_RUNNING)) {
if (now > (touch_timestamp + 1))
wake_up_process(per_cpu(watchdog_task, this_cpu));
- /* Warn about unreasonable 10+ seconds delays: */
- if (now > (touch_timestamp + 10)) {
- per_cpu(print_timestamp, this_cpu) = touch_timestamp;
+ /* Warn about unreasonable delays: */
+ if (now <= (touch_timestamp + softlockup_thresh))
+ return;
+
+ per_cpu(print_timestamp, this_cpu) = touch_timestamp;
- spin_lock(&print_lock);
- printk(KERN_ERR "BUG: soft lockup detected on CPU#%d!\n",
- this_cpu);
+ spin_lock(&print_lock);
+ printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %lus! [%s:%d]\n",
+ this_cpu, now - touch_timestamp,
+ current->comm, task_pid_nr(current));
+ if (regs)
+ show_regs(regs);
+ else
dump_stack();
- spin_unlock(&print_lock);
+ spin_unlock(&print_lock);
+}
+
+/*
+ * Have a reasonable limit on the number of tasks checked:
+ */
+unsigned long __read_mostly sysctl_hung_task_check_count = 1024;
+
+/*
+ * Zero means infinite timeout - no checking done:
+ */
+unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120;
+
+unsigned long __read_mostly sysctl_hung_task_warnings = 10;
+
+/*
+ * Only do the hung-tasks check on one CPU:
+ */
+static int check_cpu __read_mostly = -1;
+
+static void check_hung_task(struct task_struct *t, unsigned long now)
+{
+ unsigned long switch_count = t->nvcsw + t->nivcsw;
+
+ if (t->flags & PF_FROZEN)
+ return;
+
+ if (switch_count != t->last_switch_count || !t->last_switch_timestamp) {
+ t->last_switch_count = switch_count;
+ t->last_switch_timestamp = now;
+ return;
}
+ if ((long)(now - t->last_switch_timestamp) <
+ sysctl_hung_task_timeout_secs)
+ return;
+ if (sysctl_hung_task_warnings < 0)
+ return;
+ sysctl_hung_task_warnings--;
+
+ /*
+ * Ok, the task did not get scheduled for more than 2 minutes,
+ * complain:
+ */
+ printk(KERN_ERR "INFO: task %s:%d blocked for more than "
+ "%ld seconds.\n", t->comm, t->pid,
+ sysctl_hung_task_timeout_secs);
+ printk(KERN_ERR "\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
+ " disables this message.\n");
+ sched_show_task(t);
+ __debug_show_held_locks(t);
+
+ t->last_switch_timestamp = now;
+ touch_nmi_watchdog();
+}
+
+/*
+ * Check whether a TASK_UNINTERRUPTIBLE does not get woken up for
+ * a really long time (120 seconds). If that happens, print out
+ * a warning.
+ */
+static void check_hung_uninterruptible_tasks(int this_cpu)
+{
+ int max_count = sysctl_hung_task_check_count;
+ unsigned long now = get_timestamp(this_cpu);
+ struct task_struct *g, *t;
+
+ /*
+ * If the system crashed already then all bets are off,
+ * do not report extra hung tasks:
+ */
+ if ((tainted & TAINT_DIE) || did_panic)
+ return;
+
+ read_lock(&tasklist_lock);
+ do_each_thread(g, t) {
+ if (!--max_count)
+ goto unlock;
+ if (t->state & TASK_UNINTERRUPTIBLE)
+ check_hung_task(t, now);
+ } while_each_thread(g, t);
+ unlock:
+ read_unlock(&tasklist_lock);
}
/*
* The watchdog thread - runs every second and touches the timestamp.
*/
-static int watchdog(void * __bind_cpu)
+static int watchdog(void *__bind_cpu)
{
struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
+ int this_cpu = (long)__bind_cpu;
sched_setscheduler(current, SCHED_FIFO, ¶m);
/* initialize timestamp */
touch_softlockup_watchdog();
+ set_current_state(TASK_INTERRUPTIBLE);
/*
* Run briefly once per second to reset the softlockup timestamp.
- * If this gets delayed for more than 10 seconds then the
+ * If this gets delayed for more than 60 seconds then the
* debug-printout triggers in softlockup_tick().
*/
while (!kthread_should_stop()) {
- set_current_state(TASK_INTERRUPTIBLE);
touch_softlockup_watchdog();
schedule();
+
+ if (kthread_should_stop())
+ break;
+
+ if (this_cpu == check_cpu) {
+ if (sysctl_hung_task_timeout_secs)
+ check_hung_uninterruptible_tasks(this_cpu);
+ }
+
+ set_current_state(TASK_INTERRUPTIBLE);
}
+ __set_current_state(TASK_RUNNING);
return 0;
}
BUG_ON(per_cpu(watchdog_task, hotcpu));
p = kthread_create(watchdog, hcpu, "watchdog/%d", hotcpu);
if (IS_ERR(p)) {
- printk("watchdog for %i failed\n", hotcpu);
+ printk(KERN_ERR "watchdog for %i failed\n", hotcpu);
return NOTIFY_BAD;
}
- per_cpu(touch_timestamp, hotcpu) = 0;
- per_cpu(watchdog_task, hotcpu) = p;
+ per_cpu(touch_timestamp, hotcpu) = 0;
+ per_cpu(watchdog_task, hotcpu) = p;
kthread_bind(p, hotcpu);
- break;
+ break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
+ check_cpu = any_online_cpu(cpu_online_map);
wake_up_process(per_cpu(watchdog_task, hotcpu));
break;
#ifdef CONFIG_HOTPLUG_CPU
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ if (hotcpu == check_cpu) {
+ cpumask_t temp_cpu_online_map = cpu_online_map;
+
+ cpu_clear(hotcpu, temp_cpu_online_map);
+ check_cpu = any_online_cpu(temp_cpu_online_map);
+ }
+ break;
+
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
if (!per_cpu(watchdog_task, hotcpu))
kthread_stop(p);
break;
#endif /* CONFIG_HOTPLUG_CPU */
- }
+ }
return NOTIFY_OK;
}