linux内核定时器

/**
 * struct hrtimer - the basic hrtimer structure
 * @node:	timerqueue node, which also manages node.expires,
 *		the absolute expiry time in the hrtimers internal
 *		representation. The time is related to the clock on
 *		which the timer is based. Is setup by adding
 *		slack to the _softexpires value. For non range timers
 *		identical to _softexpires.
 * @_softexpires: the absolute earliest expiry time of the hrtimer.
 *		The time which was given as expiry time when the timer
 *		was armed.
 * @function:	timer expiry callback function
 * @base:	pointer to the timer base (per cpu and per clock)
 * @state:	state information (See bit values above)
 * @start_site:	timer statistics field to store the site where the timer
 *		was started
 * @start_comm: timer statistics field to store the name of the process which
 *		started the timer
 * @start_pid: timer statistics field to store the pid of the task which
 *		started the timer
 *
 * The hrtimer structure must be initialized by hrtimer_init()
 */
struct hrtimer {
	struct timerqueue_node		node; //请求队列中的节点
	ktime_t				_softexpires; //过期时间
	enum hrtimer_restart		(*function)(struct hrtimer *); //回调函数
	struct hrtimer_clock_base	*base; //时间基
	unsigned long			state; //hrtimer的状态，包括是否可用、在队列上、正在执行等
#ifdef CONFIG_TIMER_STATS
	int				start_pid;
	void				*start_site;
	char				start_comm[16];
#endif
};

enum  hrtimer_base_type { //不同类型的基准时间
	HRTIMER_BASE_MONOTONIC,
	HRTIMER_BASE_REALTIME,
	HRTIMER_BASE_BOOTTIME,
	HRTIMER_MAX_CLOCK_BASES,
};

struct hrtimer_clock_base {
	struct hrtimer_cpu_base	*cpu_base; //一个全局控制的实例
	int			index; //clock base在hrtimer_cpu_base的clock_base数组中的索引
	clockid_t		clockid; //clock base的类型
	struct timerqueue_head	active; //hrtimer红黑树的根节点
	ktime_t			resolution; //定时器的精度
	ktime_t			(*get_time)(void); //获取不同类型基准时间的时钟时间
	ktime_t			softirq_time; //基准时间
	ktime_t			offset; /*使用这个成员获得一个单调递增的时间，保证在验证定时器是否过期的时候基准时间不会往回走*/
};

struct hrtimer_cpu_base {
	raw_spinlock_t			lock;
	unsigned long			active_bases; //一个flag值，表示哪种类型clock_base是可以使用
#ifdef CONFIG_HIGH_RES_TIMERS
	ktime_t				expires_next; //下一个timer event来的绝对时间，就是下一次的过期时间
	int				hres_active; //高精度定时器是否有效
	int				hang_detected; //最后一次响应中断时是否被挂起
	unsigned long			nr_events; //timer event的个数
	unsigned long			nr_retries; //在响应hrtimer软中断时失败重试的次数
	unsigned long			nr_hangs; //总的挂起的次数
	ktime_t				max_hang_time; //挂起时，中断响应最大运行时间
#endif
	struct hrtimer_clock_base	clock_base[HRTIMER_MAX_CLOCK_BASES]; //不同类型的基准时钟对象
};

static int hrtimer_reprogram(struct hrtimer *timer,
			     struct hrtimer_clock_base *base)
{
	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); //获得当前cpu的cpu_base对象
	ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset); /*获得一个精确的和单调基准时间匹配的过期时间*/
	int res;

	WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);

	/*
	 * When the callback is running, we do not reprogram the clock event
	 * device. The timer callback is either running on a different CPU or
	 * the callback is executed in the hrtimer_interrupt context. The
	 * reprogramming is handled either by the softirq, which called the
	 * callback or at the end of the hrtimer_interrupt.
	 */
	if (hrtimer_callback_running(timer)) //当前定时器正在运行，则直接返回，没什么东西可以检测的
		return 0;

	/*
	 * CLOCK_REALTIME timer might be requested with an absolute
	 * expiry time which is less than base->offset. Nothing wrong
	 * about that, just avoid to call into the tick code, which
	 * has now objections against negative expiry values.
	 */
	if (expires.tv64 < 0)
		return -ETIME;

	if (expires.tv64 >= cpu_base->expires_next.tv64) //如果过期时间在下一次过期时间之后，则肯定没过期
		return 0;

	/*
	 * If a hang was detected in the last timer interrupt then we
	 * do not schedule a timer which is earlier than the expiry
	 * which we enforced in the hang detection. We want the system
	 * to make progress.
	 */
	if (cpu_base->hang_detected) 
		return 0;

	/*
	 * Clockevents returns -ETIME, when the event was in the past.
	 */
	res = tick_program_event(expires, 0); /*从时间设备验证定时器的过期时间是否是过去的时间，不是过去的时间则设置expires为下一次的timer event的时间，若是则返回出错*/
	if (!IS_ERR_VALUE(res))
		cpu_base->expires_next = expires; //不是过去的时间，且比下一次过期时间早，因此重设下一次的过期时间
	return res;
}

static int hrtimer_switch_to_hres(void)
{
	int i, cpu = smp_processor_id();
	struct hrtimer_cpu_base *base = &per_cpu(hrtimer_bases, cpu);
	unsigned long flags;

	if (base->hres_active)
		return 1;

	local_irq_save(flags);

	if (tick_init_highres()) { //切换到高精度模式，就是将时钟设备的事件响应函数设为后面的hrtimer_interrupt
		local_irq_restore(flags);
		printk(KERN_WARNING "Could not switch to high resolution "
				    "mode on CPU %dn", cpu);
		return 0;
	}
	base->hres_active = 1; //设置状态，已经激活
	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
		base->clock_base[i].resolution = KTIME_HIGH_RES;

	tick_setup_sched_timer();

	/* "Retrigger" the interrupt to get things going */
	retrigger_next_event(NULL); //调整每个基准时钟的offset，并且对时钟设备重编程，设置新的expire_next值
	local_irq_restore(flags);
	return 1;
}

int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
		unsigned long delta_ns, const enum hrtimer_mode mode,
		int wakeup)
{
	struct hrtimer_clock_base *base, *new_base;
	unsigned long flags;
	int ret, leftmost;

	base = lock_hrtimer_base(timer, &flags); 

	/* Remove an active timer from the queue: */
	ret = remove_hrtimer(timer, base); //如果已经在队列上，从队列删除，没有再队列上什么都不做

	/* Switch the timer base, if necessary: */
	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); /*如果基准时钟需要切换，则切换基准时钟,会尽量将任务切换到当前cpu的基准时钟下*/

	if (mode & HRTIMER_MODE_REL) {//如果设置的是相对的过期时间，则计算绝对时间*/
		tim = ktime_add_safe(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_safe(tim, base->resolution);
#endif
	}

	hrtimer_set_expires_range_ns(timer, tim, delta_ns); //设置timer的过期时间

	timer_stats_hrtimer_set_start_info(timer);

	leftmost = enqueue_hrtimer(timer, new_base); /* 将timer对象加入到红黑树，并且如果加入到红黑树中是最左边的对象，也就是说是新加入的定时器是过期时间最早的，就返回1，否则返回0 */

	/*
	 * Only allow reprogramming if the new base is on this CPU.
	 * (it might still be on another CPU if the timer was pending)
	 *
	 * XXX send_remote_softirq() ?
	 */
	if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases))
		hrtimer_enqueue_reprogram(timer, new_base, wakeup); /* 由于是最早的，需要对时钟设备重编程*/

	unlock_hrtimer_base(timer, &flags);

	return ret;
}

void hrtimer_interrupt(struct clock_event_device *dev)
{
	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
	ktime_t expires_next, now, entry_time, delta;
	int i, retries = 0;

	BUG_ON(!cpu_base->hres_active);
	cpu_base->nr_events++;
	dev->next_event.tv64 = KTIME_MAX;

	entry_time = now = ktime_get(); //获得当前时间
retry:
	expires_next.tv64 = KTIME_MAX;

	raw_spin_lock(&cpu_base->lock);
	/*
	 * We set expires_next to KTIME_MAX here with cpu_base->lock
	 * held to prevent that a timer is enqueued in our queue via
	 * the migration code. This does not affect enqueueing of
	 * timers which run their callback and need to be requeued on
	 * this CPU.
	 */
	cpu_base->expires_next.tv64 = KTIME_MAX;

	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
		struct hrtimer_clock_base *base;
		struct timerqueue_node *node;
		ktime_t basenow;

		if (!(cpu_base->active_bases & (1 << i)))
			continue;

		base = cpu_base->clock_base + i;
		basenow = ktime_add(now, base->offset); //修正获得一个递增的时间

		while ((node = timerqueue_getnext(&base->active))) { /*从红黑树上获得最左边的节点，这个指针缓存在timer_queue结构中，直接返回即可*/
			struct hrtimer *timer;

			timer = container_of(node, struct hrtimer, node); //contain_of机制获得timer对象

			/*
			 * The immediate goal for using the softexpires is
			 * minimizing wakeups, not running timers at the
			 * earliest interrupt after their soft expiration.
			 * This allows us to avoid using a Priority Search
			 * Tree, which can answer a stabbing querry for
			 * overlapping intervals and instead use the simple
			 * BST we already have.
			 * We don't add extra wakeups by delaying timers that
			 * are right-of a not yet expired timer, because that
			 * timer will have to trigger a wakeup anyway.
			 */

			if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) { /*过期时间比当前时间晚则在这个clock_base上不存在过期的对象，直接跳过这个clock_base，返回for循环*/
				ktime_t expires;

				expires = ktime_sub(hrtimer_get_expires(timer),
						    base->offset);
				if (expires.tv64 < expires_next.tv64)
					expires_next = expires;
				break;
			}

			__run_hrtimer(timer, &basenow); //执行回调函数并且删除timer对象
		}
	}

	/*
	 * Store the new expiry value so the migration code can verify
	 * against it.
	 */
	cpu_base->expires_next = expires_next; //由上面得出新的下一次过期时间
	raw_spin_unlock(&cpu_base->lock);

	/* Reprogramming necessary ? */
	if (expires_next.tv64 == KTIME_MAX || /*对时间设备重编程，若由于过长的回调函数消耗时间等原因导致expires_next是过去的时间，则重编程失败*/
	    !tick_program_event(expires_next, 0)) {
		cpu_base->hang_detected = 0;
		return;
	}

	/*
	 * The next timer was already expired due to:
	 * - tracing
	 * - long lasting callbacks
	 * - being scheduled away when running in a VM
	 *
	 * We need to prevent that we loop forever in the hrtimer
	 * interrupt routine. We give it 3 attempts to avoid
	 * overreacting on some spurious event.
	 */
	now = ktime_get(); //重编程失败，则重试3次
	cpu_base->nr_retries++;
	if (++retries < 3)
		goto retry;
	/*
	 * Give the system a chance to do something else than looping
	 * here. We stored the entry time, so we know exactly how long
	 * we spent here. We schedule the next event this amount of
	 * time away.
	 */
	cpu_base->nr_hangs++; //如果三次重试都失败，则当前cpu_base挂起
	cpu_base->hang_detected = 1;
	delta = ktime_sub(now, entry_time);
	if (delta.tv64 > cpu_base->max_hang_time.tv64)
		cpu_base->max_hang_time = delta;
	/*
	 * Limit it to a sensible value as we enforce a longer
	 * delay. Give the CPU at least 100ms to catch up.
	 */
	if (delta.tv64 > 100 * NSEC_PER_MSEC)
		expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
	else
		expires_next = ktime_add(now, delta);
	tick_program_event(expires_next, 1);/*给CPU最大100ms的时间的来处理cpu_base挂起，重编程时钟设备，在最多100ms后重新产生事件*/
	printk_once(KERN_WARNING "hrtimer: interrupt took %llu nsn",
		    ktime_to_ns(delta));
}