timer.c

Kernel code of linux kernel

		base = tbase_get_base(prelock_base);
		if (likely(base != NULL)) {
			spin_lock_irqsave(&base->lock, *flags);
			if (likely(prelock_base == timer->base))
				return base;
			/* The timer has migrated to another CPU */
			spin_unlock_irqrestore(&base->lock, *flags);
		}
		cpu_relax();
	}
}

int __mod_timer(struct timer_list *timer, unsigned long expires)
{
	struct tvec_base *base, *new_base;
	unsigned long flags;
	int ret = 0;

	timer_stats_timer_set_start_info(timer);
	BUG_ON(!timer->function);

	base = lock_timer_base(timer, &flags);

	if (timer_pending(timer)) {
		detach_timer(timer, 0);
		ret = 1;
	}

	debug_timer_activate(timer);

	new_base = __get_cpu_var(tvec_bases);

	if (base != new_base) {
		/*
		 * We are trying to schedule the timer on the local CPU.
		 * However we can't change timer's base while it is running,
		 * otherwise del_timer_sync() can't detect that the timer's
		 * handler yet has not finished. This also guarantees that
		 * the timer is serialized wrt itself.
		 */
		if (likely(base->running_timer != timer)) {
			/* See the comment in lock_timer_base() */
			timer_set_base(timer, NULL);
			spin_unlock(&base->lock);
			base = new_base;
			spin_lock(&base->lock);
			timer_set_base(timer, base);
		}
	}

	timer->expires = expires;
	internal_add_timer(base, timer);
	spin_unlock_irqrestore(&base->lock, flags);

	return ret;
}

EXPORT_SYMBOL(__mod_timer);

/**
 * add_timer_on - start a timer on a particular CPU
 * @timer: the timer to be added
 * @cpu: the CPU to start it on
 *
 * This is not very scalable on SMP. Double adds are not possible.
 */
void add_timer_on(struct timer_list *timer, int cpu)
{
	struct tvec_base *base = per_cpu(tvec_bases, cpu);
	unsigned long flags;

	timer_stats_timer_set_start_info(timer);
	BUG_ON(timer_pending(timer) || !timer->function);
	spin_lock_irqsave(&base->lock, flags);
	timer_set_base(timer, base);
	debug_timer_activate(timer);
	internal_add_timer(base, timer);
	/*
	 * Check whether the other CPU is idle and needs to be
	 * triggered to reevaluate the timer wheel when nohz is
	 * active. We are protected against the other CPU fiddling
	 * with the timer by holding the timer base lock. This also
	 * makes sure that a CPU on the way to idle can not evaluate
	 * the timer wheel.
	 */
	wake_up_idle_cpu(cpu);
	spin_unlock_irqrestore(&base->lock, flags);
}

/**
 * mod_timer - modify a timer's timeout
 * @timer: the timer to be modified
 * @expires: new timeout in jiffies
 *
 * mod_timer() is a more efficient way to update the expire field of an
 * active timer (if the timer is inactive it will be activated)
 *
 * mod_timer(timer, expires) is equivalent to:
 *
 *     del_timer(timer); timer->expires = expires; add_timer(timer);
 *
 * Note that if there are multiple unserialized concurrent users of the
 * same timer, then mod_timer() is the only safe way to modify the timeout,
 * since add_timer() cannot modify an already running timer.
 *
 * The function returns whether it has modified a pending timer or not.
 * (ie. mod_timer() of an inactive timer returns 0, mod_timer() of an
 * active timer returns 1.)
 */
int mod_timer(struct timer_list *timer, unsigned long expires)
{
	BUG_ON(!timer->function);

	timer_stats_timer_set_start_info(timer);
	/*
	 * This is a common optimization triggered by the
	 * networking code - if the timer is re-modified
	 * to be the same thing then just return:
	 */
	if (timer->expires == expires && timer_pending(timer))
		return 1;

	return __mod_timer(timer, expires);
}

EXPORT_SYMBOL(mod_timer);

/**
 * del_timer - deactive a timer.
 * @timer: the timer to be deactivated
 *
 * del_timer() deactivates a timer - this works on both active and inactive
 * timers.
 *
 * The function returns whether it has deactivated a pending timer or not.
 * (ie. del_timer() of an inactive timer returns 0, del_timer() of an
 * active timer returns 1.)
 */
int del_timer(struct timer_list *timer)
{
	struct tvec_base *base;
	unsigned long flags;
	int ret = 0;

	timer_stats_timer_clear_start_info(timer);
	if (timer_pending(timer)) {
		base = lock_timer_base(timer, &flags);
		if (timer_pending(timer)) {
			detach_timer(timer, 1);
			ret = 1;
		}
		spin_unlock_irqrestore(&base->lock, flags);
	}

	return ret;
}

EXPORT_SYMBOL(del_timer);

#ifdef CONFIG_SMP
/**
 * try_to_del_timer_sync - Try to deactivate a timer
 * @timer: timer do del
 *
 * This function tries to deactivate a timer. Upon successful (ret >= 0)
 * exit the timer is not queued and the handler is not running on any CPU.
 *
 * It must not be called from interrupt contexts.
 */
int try_to_del_timer_sync(struct timer_list *timer)
{
	struct tvec_base *base;
	unsigned long flags;
	int ret = -1;

	base = lock_timer_base(timer, &flags);

	if (base->running_timer == timer)
		goto out;

	ret = 0;
	if (timer_pending(timer)) {
		detach_timer(timer, 1);
		ret = 1;
	}
out:
	spin_unlock_irqrestore(&base->lock, flags);

	return ret;
}

EXPORT_SYMBOL(try_to_del_timer_sync);

/**
 * del_timer_sync - deactivate a timer and wait for the handler to finish.
 * @timer: the timer to be deactivated
 *
 * This function only differs from del_timer() on SMP: besides deactivating
 * the timer it also makes sure the handler has finished executing on other
 * CPUs.
 *
 * 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.
 *
 * The function returns whether it has deactivated a pending timer or not.
 */
int del_timer_sync(struct timer_list *timer)
{
	for (;;) {
		int ret = try_to_del_timer_sync(timer);
		if (ret >= 0)
			return ret;
		cpu_relax();
	}
}

EXPORT_SYMBOL(del_timer_sync);
#endif

static int cascade(struct tvec_base *base, struct tvec *tv, int index)
{
	/* cascade all the timers from tv up one level */
	struct timer_list *timer, *tmp;
	struct list_head tv_list;

	list_replace_init(tv->vec + index, &tv_list);

	/*
	 * We are removing _all_ timers from the list, so we
	 * don't have to detach them individually.
	 */
	list_for_each_entry_safe(timer, tmp, &tv_list, entry) {
		BUG_ON(tbase_get_base(timer->base) != base);
		internal_add_timer(base, timer);
	}

	return index;
}

#define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK)

/**
 * __run_timers - run all expired timers (if any) on this CPU.
 * @base: the timer vector to be processed.
 *
 * This function cascades all vectors and executes all expired timer
 * vectors.
 */
static inline void __run_timers(struct tvec_base *base)
{
	struct timer_list *timer;

	spin_lock_irq(&base->lock);
	while (time_after_eq(jiffies, base->timer_jiffies)) {
		struct list_head work_list;
		struct list_head *head = &work_list;
		int index = base->timer_jiffies & TVR_MASK;

		/*
		 * Cascade timers:
		 */
		if (!index &&
			(!cascade(base, &base->tv2, INDEX(0))) &&
				(!cascade(base, &base->tv3, INDEX(1))) &&
					!cascade(base, &base->tv4, INDEX(2)))
			cascade(base, &base->tv5, INDEX(3));
		++base->timer_jiffies;
		list_replace_init(base->tv1.vec + index, &work_list);
		while (!list_empty(head)) {
			void (*fn)(unsigned long);
			unsigned long data;

			timer = list_first_entry(head, struct timer_list,entry);
			fn = timer->function;
			data = timer->data;

			timer_stats_account_timer(timer);

			set_running_timer(base, timer);
			detach_timer(timer, 1);
			spin_unlock_irq(&base->lock);
			{
				int preempt_count = preempt_count();
				fn(data);
				if (preempt_count != preempt_count()) {
					printk(KERN_ERR "huh, entered %p "
					       "with preempt_count %08x, exited"
					       " with %08x?\n",
					       fn, preempt_count,
					       preempt_count());
					BUG();
				}
			}
			spin_lock_irq(&base->lock);
		}
	}
	set_running_timer(base, NULL);
	spin_unlock_irq(&base->lock);
}

#ifdef CONFIG_NO_HZ
/*
 * Find out when the next timer event is due to happen. This
 * is used on S/390 to stop all activity when a cpus is idle.
 * This functions needs to be called disabled.
 */
static unsigned long __next_timer_interrupt(struct tvec_base *base)
{
	unsigned long timer_jiffies = base->timer_jiffies;
	unsigned long expires = timer_jiffies + NEXT_TIMER_MAX_DELTA;
	int index, slot, array, found = 0;
	struct timer_list *nte;
	struct tvec *varray[4];

	/* Look for timer events in tv1. */
	index = slot = timer_jiffies & TVR_MASK;
	do {
		list_for_each_entry(nte, base->tv1.vec + slot, entry) {
			if (tbase_get_deferrable(nte->base))
				continue;

			found = 1;
			expires = nte->expires;
			/* Look at the cascade bucket(s)? */
			if (!index || slot < index)
				goto cascade;
			return expires;
		}
		slot = (slot + 1) & TVR_MASK;
	} while (slot != index);

cascade:
	/* Calculate the next cascade event */
	if (index)
		timer_jiffies += TVR_SIZE - index;
	timer_jiffies >>= TVR_BITS;

	/* Check tv2-tv5. */
	varray[0] = &base->tv2;
	varray[1] = &base->tv3;
	varray[2] = &base->tv4;
	varray[3] = &base->tv5;

	for (array = 0; array < 4; array++) {
		struct tvec *varp = varray[array];

		index = slot = timer_jiffies & TVN_MASK;
		do {
			list_for_each_entry(nte, varp->vec + slot, entry) {
				found = 1;
				if (time_before(nte->expires, expires))
					expires = nte->expires;
			}
			/*
			 * Do we still search for the first timer or are
			 * we looking up the cascade buckets ?
			 */
			if (found) {
				/* Look at the cascade bucket(s)? */
				if (!index || slot < index)
					break;
				return expires;
			}
			slot = (slot + 1) & TVN_MASK;
		} while (slot != index);

		if (index)
			timer_jiffies += TVN_SIZE - index;
		timer_jiffies >>= TVN_BITS;
	}
	return expires;
}

/*
 * Check, if the next hrtimer event is before the next timer wheel
 * event:
 */
static unsigned long cmp_next_hrtimer_event(unsigned long now,
					    unsigned long expires)
{
	ktime_t hr_delta = hrtimer_get_next_event();
	struct timespec tsdelta;
	unsigned long delta;

	if (hr_delta.tv64 == KTIME_MAX)
		return expires;

	/*
	 * Expired timer available, let it expire in the next tick
	 */
	if (hr_delta.tv64 <= 0)
		return now + 1;

	tsdelta = ktime_to_timespec(hr_delta);
	delta = timespec_to_jiffies(&tsdelta);

	/*
	 * Limit the delta to the max value, which is checked in
	 * tick_nohz_stop_sched_tick():
	 */
	if (delta > NEXT_TIMER_MAX_DELTA)
		delta = NEXT_TIMER_MAX_DELTA;

	/*
	 * Take rounding errors in to account and make sure, that it
	 * expires in the next tick. Otherwise we go into an endless
	 * ping pong due to tick_nohz_stop_sched_tick() retriggering
	 * the timer softirq
	 */
	if (delta < 1)
		delta = 1;
	now += delta;
	if (time_before(now, expires))
		return now;
	return expires;
}

/**
 * get_next_timer_interrupt - return the jiffy of the next pending timer
 * @now: current time (in jiffies)
 */
unsigned long get_next_timer_interrupt(unsigned long now)
{
	struct tvec_base *base = __get_cpu_var(tvec_bases);
	unsigned long expires;

	spin_lock(&base->lock);
	expires = __next_timer_interrupt(base);
	spin_unlock(&base->lock);

	if (time_before_eq(expires, now))
		return now;

	return cmp_next_hrtimer_event(now, expires);
}
#endif

#ifndef CONFIG_VIRT_CPU_ACCOUNTING
void account_process_tick(struct task_struct *p, int user_tick)
{
	cputime_t one_jiffy = jiffies_to_cputime(1);

	if (user_tick) {
		account_user_time(p, one_jiffy);
		account_user_time_scaled(p, cputime_to_scaled(one_jiffy));
	} else {
		account_system_time(p, HARDIRQ_OFFSET, one_jiffy);
		account_system_time_scaled(p, cputime_to_scaled(one_jiffy));
	}
}
#endif

/*
 * Called from the timer interrupt handler to charge one tick to the current
 * process.  user_tick is 1 if the tick is user time, 0 for system.
 */
void update_process_times(int user_tick)
{
	struct task_struct *p = current;
	int cpu = smp_processor_id();

	/* Note: this timer irq context must be accounted for as well. */
	account_process_tick(p, user_tick);
	run_local_timers();
	if (rcu_pending(cpu))
		rcu_check_callbacks(cpu, user_tick);
	scheduler_tick();
	run_posix_cpu_timers(p);
}

/*
 * Nr of active tasks - counted in fixed-point numbers
 */
static unsigned long count_active_tasks(void)
{
	return nr_active() * FIXED_1;
}

/*
 * Hmm.. Changed this, as the GNU make sources (load.c) seems to
 * imply that avenrun[] is the standard name for this kind of thing.
 * Nothing else seems to be standardized: the fractional size etc
 * all seem to differ on different machines.
 *
 * Requires xtime_lock to access.
 */
unsigned long avenrun[3];

EXPORT_SYMBOL(avenrun);

/*
 * calc_load - given tick count, update the avenrun load estimates.
 * This is called while holding a write_lock on xtime_lock.
 */
static inline void calc_load(unsigned long ticks)
{
	unsigned long active_tasks; /* fixed-point */
	static int count = LOAD_FREQ;

	count -= ticks;
	if (unlikely(count < 0)) {
		active_tasks = count_active_tasks();
		do {
			CALC_LOAD(avenrun[0], EXP_1, active_tasks);
			CALC_LOAD(avenrun[1], EXP_5, active_tasks);
			CALC_LOAD(avenrun[2], EXP_15, active_tasks);