timer.c

linux 2.6.19 kernel source code before patching

 *
 * 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)
{
	tvec_base_t *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(tvec_base_t *base, tvec_t *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(tvec_base_t *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_WARNING "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);
}

#if defined(CONFIG_NO_IDLE_HZ) || defined(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(tvec_base_t *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;
	tvec_t *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++) {
		tvec_t *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;
}

/**
 * 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)
{
	tvec_base_t *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);
}

#ifdef CONFIG_NO_IDLE_HZ
unsigned long next_timer_interrupt(void)
{
	return get_next_timer_interrupt(jiffies);
}
#endif

#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. */
	if (user_tick)
		account_user_time(p, jiffies_to_cputime(1));
	else
		account_system_time(p, HARDIRQ_OFFSET, jiffies_to_cputime(1));
	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);
			count += LOAD_FREQ;
		} while (count < 0);
	}
}

/*
 * This function runs timers and the timer-tq in bottom half context.
 */
static void run_timer_softirq(struct softirq_action *h)
{
	tvec_base_t *base = __get_cpu_var(tvec_bases);

	hrtimer_run_queues();

	if (time_after_eq(jiffies, base->timer_jiffies))
		__run_timers(base);
}

/*
 * Called by the local, per-CPU timer interrupt on SMP.
 */
void run_local_timers(void)
{
	raise_softirq(TIMER_SOFTIRQ);
	softlockup_tick();
}

/*
 * Called by the timer interrupt. xtime_lock must already be taken
 * by the timer IRQ!
 */
static inline void update_times(unsigned long ticks)
{
	update_wall_time();
	calc_load(ticks);
}
  
/*
 * The 64-bit jiffies value is not atomic - you MUST NOT read it
 * without sampling the sequence number in xtime_lock.
 * jiffies is defined in the linker script...
 */

void do_timer(unsigned long ticks)
{
	jiffies_64 += ticks;
	update_times(ticks);
}

#ifdef __ARCH_WANT_SYS_ALARM

/*
 * For backwards compatibility?  This can be done in libc so Alpha
 * and all newer ports shouldn't need it.
 */
asmlinkage unsigned long sys_alarm(unsigned int seconds)
{
	return alarm_setitimer(seconds);
}

#endif

#ifndef __alpha__

/*
 * The Alpha uses getxpid, getxuid, and getxgid instead.  Maybe this
 * should be moved into arch/i386 instead?
 */

/**
 * sys_getpid - return the thread group id of the current process
 *
 * Note, despite the name, this returns the tgid not the pid.  The tgid and
 * the pid are identical unless CLONE_THREAD was specified on clone() in
 * which case the tgid is the same in all threads of the same group.
 *
 * This is SMP safe as current->tgid does not change.
 */
asmlinkage long sys_getpid(void)
{
	return current->tgid;
}

/*
 * Accessing ->real_parent is not SMP-safe, it could
 * change from under us. However, we can use a stale
 * value of ->real_parent under rcu_read_lock(), see
 * release_task()->call_rcu(delayed_put_task_struct).
 */
asmlinkage long sys_getppid(void)
{
	int pid;

	rcu_read_lock();
	pid = rcu_dereference(current->real_parent)->tgid;
	rcu_read_unlock();

	return pid;
}

asmlinkage long sys_getuid(void)
{
	/* Only we change this so SMP safe */
	return current->uid;
}

asmlinkage long sys_geteuid(void)
{
	/* Only we change this so SMP safe */
	return current->euid;
}

asmlinkage long sys_getgid(void)
{
	/* Only we change this so SMP safe */
	return current->gid;
}

asmlinkage long sys_getegid(void)
{
	/* Only we change this so SMP safe */
	return  current->egid;
}

#endif

static void process_timeout(unsigned long __data)
{
	wake_up_process((struct task_struct *)__data);
}

/**
 * schedule_timeout - sleep until timeout
 * @timeout: timeout value in jiffies
 *
 * Make the current task sleep until @timeout jiffies have
 * elapsed. The routine will return immediately unless
 * the current task state has been set (see set_current_state()).
 *
 * You can set the task state as follows -
 *
 * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to
 * pass before the routine returns. The routine will return 0
 *
 * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
 * delivered to the current task. In this case the remaining time
 * in jiffies will be returned, or 0 if the timer expired in time
 *
 * The current task state is guaranteed to be TASK_RUNNING when this
 * routine returns.
 *
 * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule
 * the CPU away without a bound on the timeout. In this case the return
 * value will be %MAX_SCHEDULE_TIMEOUT.
 *
 * In all cases the return value is guaranteed to be non-negative.
 */
fastcall signed long __sched schedule_timeout(signed long timeout)
{
	struct timer_list timer;
	unsigned long expire;

	switch (timeout)
	{
	case MAX_SCHEDULE_TIMEOUT:
		/*
		 * These two special cases are useful to be comfortable
		 * in the caller. Nothing more. We could take
		 * MAX_SCHEDULE_TIMEOUT from one of the negative value
		 * but I' d like to return a valid offset (>=0) to allow
		 * the caller to do everything it want with the retval.
		 */
		schedule();
		goto out;
	default: