/**
* wait_queue_t of Linux (version < 2.6.34) is a FIFO list for exclusively
* waiting threads, which is not always desirable because all threads will
* be waken up again and again, even user only needs a few of them to be
* active most time. This is not good for performance because cache can
* be polluted by different threads.
*
* LIFO list can resolve this problem because we always wakeup the most
* recent active thread by default.
*
* NB: please don't call non-exclusive & exclusive wait on the same
* waitq if add_wait_queue_exclusive_head is used.
*/
void
add_wait_queue_exclusive_head(wait_queue_head_t *waitq, wait_queue_t *link)
{
unsigned long flags;
spin_lock_irqsave(&LINUX_WAITQ_HEAD(waitq)->lock, flags);
__add_wait_queue_exclusive(LINUX_WAITQ_HEAD(waitq), LINUX_WAITQ(link));
spin_unlock_irqrestore(&LINUX_WAITQ_HEAD(waitq)->lock, flags);
}
/**
* wait_queue_t of Linux (version < 2.6.34) is a FIFO list for exclusively
* waiting threads, which is not always desirable because all threads will
* be waken up again and again, even user only needs a few of them to be
* active most time. This is not good for performance because cache can
* be polluted by different threads.
*
* LIFO list can resolve this problem because we always wakeup the most
* recent active thread by default.
*
* NB: please don't call non-exclusive & exclusive wait on the same
* waitq if add_wait_queue_exclusive_head is used.
*/
void
add_wait_queue_exclusive_head(wait_queue_head_t *waitq, wait_queue_t *link)
{
unsigned long flags;
spin_lock_irqsave(&waitq->lock, flags);
__add_wait_queue_exclusive(waitq, link);
spin_unlock_irqrestore(&waitq->lock, flags);
}
/* 这个函数真正将执行epoll_wait的进程带入睡眠状态... */
static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
int maxevents, long timeout)
{
int res, eavail;
unsigned long flags;
long jtimeout;
wait_queue_t wait;
/*
* Calculate the timeout by checking for the "infinite" value (-1)
* and the overflow condition. The passed timeout is in milliseconds,
* that why (t * HZ) / 1000.
*/
/* 计算睡觉时间, 毫秒要转换为HZ */
jtimeout = (timeout < 0 || timeout >= EP_MAX_MSTIMEO) ?
MAX_SCHEDULE_TIMEOUT : (timeout * HZ + 999) / 1000;
retry:
spin_lock_irqsave(&ep->lock, flags);
res = 0;
/* 如果ready list不为空, 就不睡了, 直接干活... */
if (list_empty(&ep->rdllist)) {
/*
* We don't have any available event to return to the caller.
* We need to sleep here, and we will be wake up by
* ep_poll_callback() when events will become available.
*/
/* OK, 初始化一个等待队列, 准备直接把自己挂起,
* 注意current是一个宏, 代表当前进程 */
init_waitqueue_entry(&wait, current);
__add_wait_queue_exclusive(&ep->wq, &wait);
for (;;) {
/*
* We don't want to sleep if the ep_poll_callback() sends us
* a wakeup in between. That's why we set the task state
* to TASK_INTERRUPTIBLE before doing the checks.
*/
/* 将当前进程设置位睡眠, 但是可以被信号唤醒的状态,
* 注意这个设置是"将来时", 我们此刻还没睡! */
set_current_state(TASK_INTERRUPTIBLE);
/* 如果这个时候, ready list里面有成员了,
* 或者睡眠时间已经过了, 就直接不睡了... */
if (!list_empty(&ep->rdllist) || !jtimeout)
break;
/* 如果有信号产生, 也起床... */
if (signal_pending(current)) {
res = -EINTR;
break;
}
/* 啥事都没有,解锁, 睡觉... */
spin_unlock_irqrestore(&ep->lock, flags);
/* jtimeout这个时间后, 会被唤醒,
* ep_poll_callback()如果此时被调用,
* 那么我们就会直接被唤醒, 不用等时间了...
* 再次强调一下ep_poll_callback()的调用时机是由被监听的fd
* 的具体实现, 比如socket或者某个设备驱动来决定的,
* 因为等待队列头是他们持有的, epoll和当前进程
* 只是单纯的等待...
**/
jtimeout = schedule_timeout(jtimeout);
spin_lock_irqsave(&ep->lock, flags);
}
__remove_wait_queue(&ep->wq, &wait);
/* OK 我们醒来了... */
set_current_state(TASK_RUNNING);
}
/* Is it worth to try to dig for events ? */
eavail = !list_empty(&ep->rdllist) || ep->ovflist != EP_UNACTIVE_PTR;
spin_unlock_irqrestore(&ep->lock, flags);
/*
* Try to transfer events to user space. In case we get 0 events and
* there's still timeout left over, we go trying again in search of
* more luck.
*/
/* 如果一切正常, 有event发生, 就开始准备数据copy给用户空间了... */
if (!res && eavail &&
!(res = ep_send_events(ep, events, maxevents)) && jtimeout)
goto retry;
return res;
}