#include <linux/delay.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
+#include <linux/lockdep.h>
#include <linux/notifier.h>
#include <linux/module.h>
static DEFINE_PER_CPU(struct task_struct *, watchdog_task);
static int __read_mostly did_panic;
-unsigned long __read_mostly softlockup_thresh = 60;
+int __read_mostly softlockup_thresh = 60;
+
+/*
+ * Should we panic (and reboot, if panic_timeout= is set) when a
+ * soft-lockup occurs:
+ */
+unsigned int __read_mostly softlockup_panic =
+ CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
+
+static int __init softlockup_panic_setup(char *str)
+{
+ softlockup_panic = simple_strtoul(str, NULL, 0);
+
+ return 1;
+}
+__setup("softlockup_panic=", softlockup_panic_setup);
static int
softlock_panic(struct notifier_block *this, unsigned long event, void *ptr)
return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */
}
-void touch_softlockup_watchdog(void)
+static void __touch_softlockup_watchdog(void)
{
int this_cpu = raw_smp_processor_id();
__raw_get_cpu_var(touch_timestamp) = get_timestamp(this_cpu);
}
+
+void touch_softlockup_watchdog(void)
+{
+ __raw_get_cpu_var(touch_timestamp) = 0;
+}
EXPORT_SYMBOL(touch_softlockup_watchdog);
void touch_all_softlockup_watchdogs(void)
struct pt_regs *regs = get_irq_regs();
unsigned long now;
+ /* Is detection switched off? */
+ if (!per_cpu(watchdog_task, this_cpu) || softlockup_thresh <= 0) {
+ /* Be sure we don't false trigger if switched back on */
+ if (touch_timestamp)
+ per_cpu(touch_timestamp, this_cpu) = 0;
+ return;
+ }
+
if (touch_timestamp == 0) {
- touch_softlockup_watchdog();
+ __touch_softlockup_watchdog();
return;
}
print_timestamp = per_cpu(print_timestamp, this_cpu);
/* report at most once a second */
- if ((print_timestamp >= touch_timestamp &&
- print_timestamp < (touch_timestamp + 1)) ||
- did_panic || !per_cpu(watchdog_task, this_cpu)) {
+ if (print_timestamp == touch_timestamp || did_panic)
return;
- }
/* do not print during early bootup: */
if (unlikely(system_state != SYSTEM_RUNNING)) {
- touch_softlockup_watchdog();
+ __touch_softlockup_watchdog();
return;
}
now = get_timestamp(this_cpu);
- /* Wake up the high-prio watchdog task every second: */
- if (now > (touch_timestamp + 1))
+ /*
+ * Wake up the high-prio watchdog task twice per
+ * threshold timespan.
+ */
+ if (now > touch_timestamp + softlockup_thresh/2)
wake_up_process(per_cpu(watchdog_task, this_cpu));
/* Warn about unreasonable delays: */
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));
+ print_modules();
+ print_irqtrace_events(current);
if (regs)
show_regs(regs);
else
dump_stack();
spin_unlock(&print_lock);
+
+ if (softlockup_panic)
+ panic("softlockup: hung tasks");
}
/*
/*
* Zero means infinite timeout - no checking done:
*/
-unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120;
+unsigned long __read_mostly sysctl_hung_task_timeout_secs = 480;
unsigned long __read_mostly sysctl_hung_task_warnings = 10;
if ((long)(now - t->last_switch_timestamp) <
sysctl_hung_task_timeout_secs)
return;
- if (sysctl_hung_task_warnings < 0)
+ if (!sysctl_hung_task_warnings)
return;
sysctl_hung_task_warnings--;
t->last_switch_timestamp = now;
touch_nmi_watchdog();
+
+ if (softlockup_panic)
+ panic("softlockup: blocked tasks");
}
/*
* If the system crashed already then all bets are off,
* do not report extra hung tasks:
*/
- if ((tainted & TAINT_DIE) || did_panic)
+ if (test_taint(TAINT_DIE) || did_panic)
return;
read_lock(&tasklist_lock);
do_each_thread(g, t) {
if (!--max_count)
goto unlock;
- if (t->state & TASK_UNINTERRUPTIBLE)
+ /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
+ if (t->state == TASK_UNINTERRUPTIBLE)
check_hung_task(t, now);
} while_each_thread(g, t);
unlock:
sched_setscheduler(current, SCHED_FIFO, ¶m);
/* initialize timestamp */
- touch_softlockup_watchdog();
+ __touch_softlockup_watchdog();
set_current_state(TASK_INTERRUPTIBLE);
/*
* debug-printout triggers in softlockup_tick().
*/
while (!kthread_should_stop()) {
- touch_softlockup_watchdog();
+ __touch_softlockup_watchdog();
schedule();
if (kthread_should_stop())
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
- check_cpu = any_online_cpu(cpu_online_map);
+ check_cpu = cpumask_any(cpu_online_mask);
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);
+ /* Pick any other online cpu. */
+ check_cpu = cpumask_any_but(cpu_online_mask, hotcpu);
}
break;
break;
/* Unbind so it can run. Fall thru. */
kthread_bind(per_cpu(watchdog_task, hotcpu),
- any_online_cpu(cpu_online_map));
+ cpumask_any(cpu_online_mask));
case CPU_DEAD:
case CPU_DEAD_FROZEN:
p = per_cpu(watchdog_task, hotcpu);
.notifier_call = cpu_callback
};
-__init void spawn_softlockup_task(void)
+static int __initdata nosoftlockup;
+
+static int __init nosoftlockup_setup(char *str)
+{
+ nosoftlockup = 1;
+ return 1;
+}
+__setup("nosoftlockup", nosoftlockup_setup);
+
+static int __init spawn_softlockup_task(void)
{
void *cpu = (void *)(long)smp_processor_id();
- int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
+ int err;
+
+ if (nosoftlockup)
+ return 0;
- BUG_ON(err == NOTIFY_BAD);
+ err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
+ if (err == NOTIFY_BAD) {
+ BUG();
+ return 1;
+ }
cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
register_cpu_notifier(&cpu_nfb);
atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
+
+ return 0;
}
+early_initcall(spawn_softlockup_task);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff