From c5f66e99b7cb091e3d51ae8e8156892e8feb7fa3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 8 Aug 2012 11:10:28 -0700 Subject: timer: Implement TIMER_IRQSAFE Timer internals are protected with irq-safe locks but timer execution isn't, so a timer being dequeued for execution and its execution aren't atomic against IRQs. This makes it impossible to wait for its completion from IRQ handlers and difficult to shoot down a timer from IRQ handlers. This issue caused some issues for delayed_work interface. Because there's no way to reliably shoot down delayed_work->timer from IRQ handlers, __cancel_delayed_work() can't share the logic to steal the target delayed_work with cancel_delayed_work_sync(), and can only steal delayed_works which are on queued on timer. Similarly, the pending mod_delayed_work() can't be used from IRQ handlers. This patch adds a new timer flag TIMER_IRQSAFE, which makes the timer to be executed without enabling IRQ after dequeueing such that its dequeueing and execution are atomic against IRQ handlers. This makes it safe to wait for the timer's completion from IRQ handlers, for example, using del_timer_sync(). It can never be executing on the local CPU and if executing on other CPUs it won't be interrupted until done. This will enable simplifying delayed_work cancel/mod interface. Signed-off-by: Tejun Heo Cc: torvalds@linux-foundation.org Cc: peterz@infradead.org Link: http://lkml.kernel.org/r/1344449428-24962-5-git-send-email-tj@kernel.org Signed-off-by: Thomas Gleixner --- kernel/timer.c | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) (limited to 'kernel/timer.c') diff --git a/kernel/timer.c b/kernel/timer.c index 8d185a1677cc..706fe4c53e82 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -95,6 +95,11 @@ static inline unsigned int tbase_get_deferrable(struct tvec_base *base) return ((unsigned int)(unsigned long)base & TIMER_DEFERRABLE); } +static inline unsigned int tbase_get_irqsafe(struct tvec_base *base) +{ + return ((unsigned int)(unsigned long)base & TIMER_IRQSAFE); +} + static inline struct tvec_base *tbase_get_base(struct tvec_base *base) { return ((struct tvec_base *)((unsigned long)base & ~TIMER_FLAG_MASK)); @@ -1002,14 +1007,14 @@ EXPORT_SYMBOL(try_to_del_timer_sync); * * Synchronization rules: Callers must prevent restarting of the timer, * otherwise this function is meaningless. It must not be called from - * interrupt contexts. The caller must not hold locks which would prevent - * completion of the timer's handler. The timer's handler must not call - * add_timer_on(). Upon exit the timer is not queued and the handler is - * not running on any CPU. + * interrupt contexts unless the timer is an irqsafe one. The caller must + * not hold locks which would prevent completion of the timer's + * handler. The timer's handler must not call add_timer_on(). Upon exit the + * timer is not queued and the handler is not running on any CPU. * - * Note: You must not hold locks that are held in interrupt context - * while calling this function. Even if the lock has nothing to do - * with the timer in question. Here's why: + * Note: For !irqsafe timers, you must not hold locks that are held in + * interrupt context while calling this function. Even if the lock has + * nothing to do with the timer in question. Here's why: * * CPU0 CPU1 * ---- ---- @@ -1046,7 +1051,7 @@ int del_timer_sync(struct timer_list *timer) * don't use it in hardirq context, because it * could lead to deadlock. */ - WARN_ON(in_irq()); + WARN_ON(in_irq() && !tbase_get_irqsafe(timer->base)); for (;;) { int ret = try_to_del_timer_sync(timer); if (ret >= 0) @@ -1153,19 +1158,27 @@ static inline void __run_timers(struct tvec_base *base) while (!list_empty(head)) { void (*fn)(unsigned long); unsigned long data; + bool irqsafe; timer = list_first_entry(head, struct timer_list,entry); fn = timer->function; data = timer->data; + irqsafe = tbase_get_irqsafe(timer->base); timer_stats_account_timer(timer); base->running_timer = timer; detach_expired_timer(timer, base); - spin_unlock_irq(&base->lock); - call_timer_fn(timer, fn, data); - spin_lock_irq(&base->lock); + if (irqsafe) { + spin_unlock(&base->lock); + call_timer_fn(timer, fn, data); + spin_lock(&base->lock); + } else { + spin_unlock_irq(&base->lock); + call_timer_fn(timer, fn, data); + spin_lock_irq(&base->lock); + } } } base->running_timer = NULL; -- cgit v1.2.3