From 5762ba1873b0bb9faa631aaa02f533c2b9837f82 Mon Sep 17 00:00:00 2001 From: Sebastien Dugue Date: Mon, 1 Dec 2008 14:09:07 +0100 Subject: 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 Cc: Signed-off-by: Ingo Molnar --- kernel/time/tick-common.c | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index df12434b43c..457d281258e 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -273,6 +273,21 @@ out_bc: 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 = first_cpu(cpu_online_map); + + tick_do_timer_cpu = (cpu != NR_CPUS) ? 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 = first_cpu(cpu_online_map); - - tick_do_timer_cpu = (cpu != NR_CPUS) ? 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); -- cgit v1.2.3 From 2d68259db26ad57fd9643f1c69b5181ec9836ca9 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Fri, 16 Jan 2009 17:14:38 +0900 Subject: clockevents: let set_mode() setup delta information Allow the set_mode() clockevent callback to decide and fill in delta details such as shift, mult, max_delta_ns and min_delta_ns. With this change the clockevent can be registered without delta details which allows us to keep the parent clock disabled until the clockevent gets setup using set_mode(). Letting set_mode() fill in or update delta details allows us to save power by disabling the parent clock while the clockevent is unused. This may however make the parent clock rate change, so next time the clockevent gets enabled we need let set_mode() to update the detla details accordingly. Doing it at registration time is not enough. Furthermore, the delta details seem unused in the case of periodic-only clockevent drivers, so this change also allows registration of such drivers without the delta details filled in. Signed-off-by: Magnus Damm Signed-off-by: Thomas Gleixner --- kernel/time/clockevents.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index ea2f48af83c..d13be216a79 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -68,6 +68,17 @@ void clockevents_set_mode(struct clock_event_device *dev, if (dev->mode != mode) { dev->set_mode(mode, dev); dev->mode = mode; + + /* + * A nsec2cyc multiplicator of 0 is invalid and we'd crash + * on it, so fix it up and emit a warning: + */ + if (mode == CLOCK_EVT_MODE_ONESHOT) { + if (unlikely(!dev->mult)) { + dev->mult = 1; + WARN_ON(1); + } + } } } @@ -168,15 +179,6 @@ void clockevents_register_device(struct clock_event_device *dev) BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); BUG_ON(!dev->cpumask); - /* - * A nsec2cyc multiplicator of 0 is invalid and we'd crash - * on it, so fix it up and emit a warning: - */ - if (unlikely(!dev->mult)) { - dev->mult = 1; - WARN_ON(1); - } - spin_lock(&clockevents_lock); list_add(&dev->list, &clockevent_devices); -- cgit v1.2.3