hrtimer.c

linux 2.6.19 kernel source code before patching

/*
 * Remove a timer from the callback pending list
 */
static inline void hrtimer_remove_cb_pending(struct hrtimer *timer)
{
	list_del_init(&timer->cb_entry);
}

/*
 * Initialize the high resolution related parts of cpu_base
 */
static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
{
	base->expires_next.tv64 = KTIME_MAX;
	base->hres_active = 0;
	INIT_LIST_HEAD(&base->cb_pending);
}

/*
 * Initialize the high resolution related parts of a hrtimer
 */
static inline void hrtimer_init_timer_hres(struct hrtimer *timer)
{
	INIT_LIST_HEAD(&timer->cb_entry);
}

/*
 * When High resolution timers are active, try to reprogram. Note, that in case
 * the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry
 * check happens. The timer gets enqueued into the rbtree. The reprogramming
 * and expiry check is done in the hrtimer_interrupt or in the softirq.
 */
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
					    struct hrtimer_clock_base *base)
{
	if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {

		/* Timer is expired, act upon the callback mode */
		switch(timer->cb_mode) {
		case HRTIMER_CB_IRQSAFE_NO_RESTART:
			/*
			 * We can call the callback from here. No restart
			 * happens, so no danger of recursion
			 */
			BUG_ON(timer->function(timer) != HRTIMER_NORESTART);
			return 1;
		case HRTIMER_CB_IRQSAFE_NO_SOFTIRQ:
			/*
			 * This is solely for the sched tick emulation with
			 * dynamic tick support to ensure that we do not
			 * restart the tick right on the edge and end up with
			 * the tick timer in the softirq ! The calling site
			 * takes care of this.
			 */
			return 1;
		case HRTIMER_CB_IRQSAFE:
		case HRTIMER_CB_SOFTIRQ:
			/*
			 * Move everything else into the softirq pending list !
			 */
			list_add_tail(&timer->cb_entry,
				      &base->cpu_base->cb_pending);
			timer->state = HRTIMER_STATE_PENDING;
			raise_softirq(HRTIMER_SOFTIRQ);
			return 1;
		default:
			BUG();
		}
	}
	return 0;
}

/*
 * Switch to high resolution mode
 */
static int hrtimer_switch_to_hres(void)
{
	struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases);
	unsigned long flags;

	if (base->hres_active)
		return 1;

	local_irq_save(flags);

	if (tick_init_highres()) {
		local_irq_restore(flags);
		return 0;
	}
	base->hres_active = 1;
	base->clock_base[CLOCK_REALTIME].resolution = KTIME_HIGH_RES;
	base->clock_base[CLOCK_MONOTONIC].resolution = KTIME_HIGH_RES;

	tick_setup_sched_timer();

	/* "Retrigger" the interrupt to get things going */
	retrigger_next_event(NULL);
	local_irq_restore(flags);
	printk(KERN_INFO "Switched to high resolution mode on CPU %d\n",
	       smp_processor_id());
	return 1;
}

#else

static inline int hrtimer_hres_active(void) { return 0; }
static inline int hrtimer_is_hres_enabled(void) { return 0; }
static inline int hrtimer_switch_to_hres(void) { return 0; }
static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base) { }
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
					    struct hrtimer_clock_base *base)
{
	return 0;
}
static inline int hrtimer_cb_pending(struct hrtimer *timer) { return 0; }
static inline void hrtimer_remove_cb_pending(struct hrtimer *timer) { }
static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { }

#endif /* CONFIG_HIGH_RES_TIMERS */

#ifdef CONFIG_TIMER_STATS
void __timer_stats_hrtimer_set_start_info(struct hrtimer *timer, void *addr)
{
	if (timer->start_site)
		return;

	timer->start_site = addr;
	memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
	timer->start_pid = current->pid;
}
#endif

/*
 * Counterpart to lock_timer_base above:
 */
static inline
void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
{
	spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags);
}

/**
 * hrtimer_forward - forward the timer expiry
 * @timer:	hrtimer to forward
 * @now:	forward past this time
 * @interval:	the interval to forward
 *
 * Forward the timer expiry so it will expire in the future.
 * Returns the number of overruns.
 */
unsigned long
hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
{
	unsigned long orun = 1;
	ktime_t delta;

	delta = ktime_sub(now, timer->expires);

	if (delta.tv64 < 0)
		return 0;

	if (interval.tv64 < timer->base->resolution.tv64)
		interval.tv64 = timer->base->resolution.tv64;

	if (unlikely(delta.tv64 >= interval.tv64)) {
		s64 incr = ktime_to_ns(interval);

		orun = ktime_divns(delta, incr);
		timer->expires = ktime_add_ns(timer->expires, incr * orun);
		if (timer->expires.tv64 > now.tv64)
			return orun;
		/*
		 * This (and the ktime_add() below) is the
		 * correction for exact:
		 */
		orun++;
	}
	timer->expires = ktime_add(timer->expires, interval);
	/*
	 * Make sure, that the result did not wrap with a very large
	 * interval.
	 */
	if (timer->expires.tv64 < 0)
		timer->expires = ktime_set(KTIME_SEC_MAX, 0);

	return orun;
}
EXPORT_SYMBOL_GPL(hrtimer_forward);

/*
 * enqueue_hrtimer - internal function to (re)start a timer
 *
 * The timer is inserted in expiry order. Insertion into the
 * red black tree is O(log(n)). Must hold the base lock.
 */
static void enqueue_hrtimer(struct hrtimer *timer,
			    struct hrtimer_clock_base *base, int reprogram)
{
	struct rb_node **link = &base->active.rb_node;
	struct rb_node *parent = NULL;
	struct hrtimer *entry;

	/*
	 * Find the right place in the rbtree:
	 */
	while (*link) {
		parent = *link;
		entry = rb_entry(parent, struct hrtimer, node);
		/*
		 * We dont care about collisions. Nodes with
		 * the same expiry time stay together.
		 */
		if (timer->expires.tv64 < entry->expires.tv64)
			link = &(*link)->rb_left;
		else
			link = &(*link)->rb_right;
	}

	/*
	 * Insert the timer to the rbtree and check whether it
	 * replaces the first pending timer
	 */
	if (!base->first || timer->expires.tv64 <
	    rb_entry(base->first, struct hrtimer, node)->expires.tv64) {
		/*
		 * Reprogram the clock event device. When the timer is already
		 * expired hrtimer_enqueue_reprogram has either called the
		 * callback or added it to the pending list and raised the
		 * softirq.
		 *
		 * This is a NOP for !HIGHRES
		 */
		if (reprogram && hrtimer_enqueue_reprogram(timer, base))
			return;

		base->first = &timer->node;
	}

	rb_link_node(&timer->node, parent, link);
	rb_insert_color(&timer->node, &base->active);
	/*
	 * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
	 * state of a possibly running callback.
	 */
	timer->state |= HRTIMER_STATE_ENQUEUED;
}

/*
 * __remove_hrtimer - internal function to remove a timer
 *
 * Caller must hold the base lock.
 *
 * High resolution timer mode reprograms the clock event device when the
 * timer is the one which expires next. The caller can disable this by setting
 * reprogram to zero. This is useful, when the context does a reprogramming
 * anyway (e.g. timer interrupt)
 */
static void __remove_hrtimer(struct hrtimer *timer,
			     struct hrtimer_clock_base *base,
			     unsigned long newstate, int reprogram)
{
	/* High res. callback list. NOP for !HIGHRES */
	if (hrtimer_cb_pending(timer))
		hrtimer_remove_cb_pending(timer);
	else {
		/*
		 * Remove the timer from the rbtree and replace the
		 * first entry pointer if necessary.
		 */
		if (base->first == &timer->node) {
			base->first = rb_next(&timer->node);
			/* Reprogram the clock event device. if enabled */
			if (reprogram && hrtimer_hres_active())
				hrtimer_force_reprogram(base->cpu_base);
		}
		rb_erase(&timer->node, &base->active);
	}
	timer->state = newstate;
}

/*
 * remove hrtimer, called with base lock held
 */
static inline int
remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
{
	if (hrtimer_is_queued(timer)) {
		int reprogram;

		/*
		 * Remove the timer and force reprogramming when high
		 * resolution mode is active and the timer is on the current
		 * CPU. If we remove a timer on another CPU, reprogramming is
		 * skipped. The interrupt event on this CPU is fired and
		 * reprogramming happens in the interrupt handler. This is a
		 * rare case and less expensive than a smp call.
		 */
		timer_stats_hrtimer_clear_start_info(timer);
		reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
		__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE,
				 reprogram);
		return 1;
	}
	return 0;
}

/**
 * hrtimer_start - (re)start an relative timer on the current CPU
 * @timer:	the timer to be added
 * @tim:	expiry time
 * @mode:	expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
 *
 * Returns:
 *  0 on success
 *  1 when the timer was active
 */
int
hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
{
	struct hrtimer_clock_base *base, *new_base;
	unsigned long flags;
	int ret;

	base = lock_hrtimer_base(timer, &flags);

	/* Remove an active timer from the queue: */
	ret = remove_hrtimer(timer, base);

	/* Switch the timer base, if necessary: */
	new_base = switch_hrtimer_base(timer, base);

	if (mode == HRTIMER_MODE_REL) {
		tim = ktime_add(tim, new_base->get_time());
		/*
		 * CONFIG_TIME_LOW_RES is a temporary way for architectures
		 * to signal that they simply return xtime in
		 * do_gettimeoffset(). In this case we want to round up by
		 * resolution when starting a relative timer, to avoid short
		 * timeouts. This will go away with the GTOD framework.
		 */
#ifdef CONFIG_TIME_LOW_RES
		tim = ktime_add(tim, base->resolution);
#endif
	}
	timer->expires = tim;

	timer_stats_hrtimer_set_start_info(timer);

	/*
	 * Only allow reprogramming if the new base is on this CPU.
	 * (it might still be on another CPU if the timer was pending)
	 */
	enqueue_hrtimer(timer, new_base,
			new_base->cpu_base == &__get_cpu_var(hrtimer_bases));

	unlock_hrtimer_base(timer, &flags);

	return ret;
}
EXPORT_SYMBOL_GPL(hrtimer_start);

/**
 * hrtimer_try_to_cancel - try to deactivate a timer
 * @timer:	hrtimer to stop
 *
 * Returns:
 *  0 when the timer was not active
 *  1 when the timer was active
 * -1 when the timer is currently excuting the callback function and
 *    cannot be stopped
 */
int hrtimer_try_to_cancel(struct hrtimer *timer)
{
	struct hrtimer_clock_base *base;
	unsigned long flags;
	int ret = -1;

	base = lock_hrtimer_base(timer, &flags);

	if (!hrtimer_callback_running(timer))
		ret = remove_hrtimer(timer, base);

	unlock_hrtimer_base(timer, &flags);

	return ret;

}
EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel);

/**
 * hrtimer_cancel - cancel a timer and wait for the handler to finish.
 * @timer:	the timer to be cancelled
 *
 * Returns:
 *  0 when the timer was not active
 *  1 when the timer was active
 */
int hrtimer_cancel(struct hrtimer *timer)
{
	for (;;) {
		int ret = hrtimer_try_to_cancel(timer);

		if (ret >= 0)
			return ret;
		cpu_relax();
	}
}
EXPORT_SYMBOL_GPL(hrtimer_cancel);

/**
 * hrtimer_get_remaining - get remaining time for the timer
 * @timer:	the timer to read
 */
ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
{
	struct hrtimer_clock_base *base;
	unsigned long flags;
	ktime_t rem;

	base = lock_hrtimer_base(timer, &flags);
	rem = ktime_sub(timer->expires, base->get_time());
	unlock_hrtimer_base(timer, &flags);

	return rem;
}
EXPORT_SYMBOL_GPL(hrtimer_get_remaining);

#if defined(CONFIG_NO_IDLE_HZ) || defined(CONFIG_NO_HZ)
/**
 * hrtimer_get_next_event - get the time until next expiry event
 *
 * Returns the delta to the next expiry event or KTIME_MAX if no timer
 * is pending.
 */
ktime_t hrtimer_get_next_event(void)
{
	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
	struct hrtimer_clock_base *base = cpu_base->clock_base;
	ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
	unsigned long flags;
	int i;

	spin_lock_irqsave(&cpu_base->lock, flags);

	if (!hrtimer_hres_active()) {
		for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
			struct hrtimer *timer;

			if (!base->first)
				continue;

			timer = rb_entry(base->first, struct hrtimer, node);
			delta.tv64 = timer->expires.tv64;
			delta = ktime_sub(delta, base->get_time());
			if (delta.tv64 < mindelta.tv64)
				mindelta.tv64 = delta.tv64;
		}
	}

	spin_unlock_irqrestore(&cpu_base->lock, flags);

	if (mindelta.tv64 < 0)
		mindelta.tv64 = 0;
	return mindelta;
}
#endif

/**
 * hrtimer_init - initialize a timer to the given clock
 * @timer:	the timer to be initialized
 * @clock_id:	the clock to be used
 * @mode:	timer mode abs/rel
 */
void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
		  enum hrtimer_mode mode)
{
	struct hrtimer_cpu_base *cpu_base;

	memset(timer, 0, sizeof(struct hrtimer));

	cpu_base = &__raw_get_cpu_var(hrtimer_bases);