hrtimers: allow the hot-unplugging of all cpus

Impact: fix CPU hotplug hang on Power6 testbox

On architectures that support offlining all cpus (at least powerpc/pseries),
hot-unpluging the tick_do_timer_cpu can result in a system hang.

This comes from the fact that if the cpu going down happens to be the
cpu doing the tick, then as the tick_do_timer_cpu handover happens after the
cpu is dead (via the CPU_DEAD notification), we're left without ticks,
jiffies are frozen and any task relying on timers (msleep, ...) is stuck.
That's particularly the case for the cpu looping in __cpu_die() waiting
for the dying cpu to be dead.

This patch addresses this by having the tick_do_timer_cpu handover happen
earlier during the CPU_DYING notification. For this, a new clockevent
notification type is introduced (CLOCK_EVT_NOTIFY_CPU_DYING) which is triggered
in hrtimer_cpu_notify().

Signed-off-by: Sebastien Dugue <sebastien.dugue@bull.net>
Cc: <stable@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Sebastien Dugue 2008-12-01 14:09:07 +01:00 committed by Ingo Molnar
parent 7f22391cbe
commit 94df7de028
3 changed files with 24 additions and 7 deletions

View File

@ -36,6 +36,7 @@ enum clock_event_nofitiers {
CLOCK_EVT_NOTIFY_BROADCAST_EXIT,
CLOCK_EVT_NOTIFY_SUSPEND,
CLOCK_EVT_NOTIFY_RESUME,
CLOCK_EVT_NOTIFY_CPU_DYING,
CLOCK_EVT_NOTIFY_CPU_DEAD,
};

View File

@ -1608,6 +1608,10 @@ static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_DYING:
case CPU_DYING_FROZEN:
clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu);
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
{

View File

@ -273,6 +273,21 @@ static int tick_check_new_device(struct clock_event_device *newdev)
return ret;
}
/*
* Transfer the do_timer job away from a dying cpu.
*
* Called with interrupts disabled.
*/
static void tick_handover_do_timer(int *cpup)
{
if (*cpup == tick_do_timer_cpu) {
int cpu = cpumask_first(cpu_online_mask);
tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
TICK_DO_TIMER_NONE;
}
}
/*
* Shutdown an event device on a given cpu:
*
@ -297,13 +312,6 @@ static void tick_shutdown(unsigned int *cpup)
clockevents_exchange_device(dev, NULL);
td->evtdev = NULL;
}
/* Transfer the do_timer job away from this cpu */
if (*cpup == tick_do_timer_cpu) {
int cpu = cpumask_first(cpu_online_mask);
tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
TICK_DO_TIMER_NONE;
}
spin_unlock_irqrestore(&tick_device_lock, flags);
}
@ -357,6 +365,10 @@ static int tick_notify(struct notifier_block *nb, unsigned long reason,
tick_broadcast_oneshot_control(reason);
break;
case CLOCK_EVT_NOTIFY_CPU_DYING:
tick_handover_do_timer(dev);
break;
case CLOCK_EVT_NOTIFY_CPU_DEAD:
tick_shutdown_broadcast_oneshot(dev);
tick_shutdown_broadcast(dev);