epoll

linux源码：http://ftp.sjtu.edu.cn/sites/ftp.kernel.org/pub/linux/kernel/v2.6/

转：http://oldblog.donghao.org/2009/08/linuxiapolliepollaueouaeaeeio.html

转：http://blog.chinaunix.net/uid-27024249-id-3988524.html

fs/eventpoll.c中

1、epoll_create函数：

SYSCALL_DEFINE1(epoll_create1, int, flags)
{
	int error;
	struct eventpoll *ep = NULL;

	/* Check the EPOLL_* constant for consistency.  */
	BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);
	
	//O_CLOEXEC 就等于EPOLL_CLOEXEC (打开的文件描述符在执行exec调用新程序中关闭，且为原子操作)	
	if (flags & ~EPOLL_CLOEXEC)
		return -EINVAL;
	/*
	 * Create the internal data structure ("struct eventpoll").
	 * 创建内核数据结构体 struct eventpoll
	 */
	error = ep_alloc(&ep);
	if (error < 0)
		return error;
	/*
	 * Creates all the items needed to setup an eventpoll file. That is,
	 * a file structure and a free file descriptor.
	 * 创建的所有iteam(fd,file) 都需要安装一个eventpool文件
	  File callbacks that implement the eventpoll file behaviour 
	static const struct file_operations eventpoll_fops = {
		.release	= ep_eventpoll_release,
		.poll		= ep_eventpoll_poll
	};
	创建一个fd,和一个file,将eventpoll_fops绑在file->f_op上,将ep绑在file->private_data上
	 */
	error = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep,
				 flags & O_CLOEXEC);
	if (error < 0)
		ep_free(ep);

	return error;
}

anon_inode_getfd //找到

int anon_inode_getfd(const char *name, const struct file_operations *fops,
		     void *priv, int flags)
{
	int error, fd;
	struct file *file;
	//获取一个未使用的fd
	error = get_unused_fd_flags(flags);
	if (error < 0)
		return error;
	fd = error;

	// 将ep做为参数priv设置到file的结构中 file->private_data = priv;
	// 将fops作为新建文件的file -> f_op 注意是fs.h中的struct file
	file = anon_inode_getfile(name, fops, priv, flags);
	if (IS_ERR(file)) {
		error = PTR_ERR(file);
		goto err_put_unused_fd;
	}
	//将file和fd关联起来，fdt->fd[fd]=file
	fd_install(fd, file);

	return fd;

err_put_unused_fd:
	put_unused_fd(fd);
	return error;
}

//创建file并且绑定一些数据priv-->eventpoll

struct file *anon_inode_getfile(const char *name,
				const struct file_operations *fops,
				void *priv, int flags)
{
	struct qstr this;
	struct dentry *dentry;
	struct file *file;
	int error;

	if (IS_ERR(anon_inode_inode))
		return ERR_PTR(-ENODEV);

	if (fops->owner && !try_module_get(fops->owner))
		return ERR_PTR(-ENOENT);

	/*
	 * Link the inode to a directory entry by creating a unique name
	 * using the inode sequence number.
	 */
	error = -ENOMEM;
	this.name = name;
	this.len = strlen(name);
	this.hash = 0;
	dentry = d_alloc(anon_inode_mnt->mnt_sb->s_root, &this);
	if (!dentry)
		goto err_module;

	/*
	 * We know the anon_inode inode count is always greater than zero,
	 * so we can avoid doing an igrab() and we can use an open-coded
	 * atomic_inc().
	 */
	atomic_inc(&anon_inode_inode->i_count);

	dentry->d_op = &anon_inodefs_dentry_operations;
	/* Do not publish this dentry inside the global dentry hash table */
	dentry->d_flags &= ~DCACHE_UNHASHED;
	d_instantiate(dentry, anon_inode_inode);

	error = -ENFILE;
	file = alloc_file(anon_inode_mnt, dentry,
			  FMODE_READ | FMODE_WRITE, fops);
	if (!file)
		goto err_dput;
	file->f_mapping = anon_inode_inode->i_mapping;

	file->f_pos = 0;
	file->f_flags = O_RDWR | (flags & O_NONBLOCK);
	file->f_version = 0;
	file->private_data = priv;

	return file;

err_dput:
	dput(dentry);
err_module:
	module_put(fops->owner);
	return ERR_PTR(error);
}

2、插入是红黑树，查找是相当的快

epoll_ctl函数：

SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
		struct epoll_event __user *, event)
{
	int error;
	struct file *file, *tfile;
	struct eventpoll *ep;
	struct epitem *epi;
	struct epoll_event epds;

	error = -EFAULT;
	// 如果不是EPOLL_CTL_DEL操作 将用户态的数据event拷贝到内核态的对象epds上
	if (ep_op_has_event(op) &&
	    copy_from_user(&epds, event, sizeof(struct epoll_event)))
		goto error_return;

	/* Get the "struct file *" for the eventpoll file */
	error = -EBADF;
	file = fget(epfd); // 还记得关联函数吗? fd_install(newfd, newfile);
	if (!file)
		goto error_return;

	/* Get the "struct file *" for the target file */
	tfile = fget(fd);
	if (!tfile)
		goto error_fput;

	/* The target file descriptor must support poll */
	// 由accept->tipc_create f_op如果是TCP则是 stream_ops 如果是UDP则是 msg_ops 对应的poll都是系统poll
	error = -EPERM;
	if (!tfile->f_op || !tfile->f_op->poll)
		goto error_tgt_fput;
	
	/*
	 * We have to check that the file structure underneath the file descriptor
	 * the user passed to us _is_ an eventpoll file. And also we do not permit
	 * adding an epoll file descriptor inside itself.
	 */
	// 防止修改自己,file必须是eventpoll file
	/*
	static inline int is_file_epoll(struct file *f)
	{
		return f->f_op == &eventpoll_fops;
	}
	*/
	error = -EINVAL;
	if (file == tfile || !is_file_epoll(file))
		goto error_tgt_fput;

	/*
	 * At this point it is safe to assume that the "private_data" contains
	 * our own data structure.
	 取出eventpool
	 */
	ep = file->private_data;

	mutex_lock(&ep->mtx);

	/*
	 * Try to lookup the file inside our RB tree, Since we grabbed "mtx"
	 * above, we can be sure to be able to use the item looked up by
	 * ep_find() till we release the mutex.
	 */
	epi = ep_find(ep, tfile, fd);

	error = -EINVAL;
	switch (op) {
	case EPOLL_CTL_ADD:
		if (!epi) {
			epds.events |= POLLERR | POLLHUP;
			error = ep_insert(ep, &epds, tfile, fd);
		} else
			error = -EEXIST; // 如果epi在ep->rbr(红黑树)中了，表示已经存在插入操作失败
		break;
	case EPOLL_CTL_DEL:
		if (epi)
			error = ep_remove(ep, epi);
		else
			error = -ENOENT;
		break;
	case EPOLL_CTL_MOD:
		if (epi) {
			epds.events |= POLLERR | POLLHUP;
			error = ep_modify(ep, epi, &epds);
		} else
			error = -ENOENT;
		break;
	}
	mutex_unlock(&ep->mtx);

error_tgt_fput:
	fput(tfile);
error_fput:
	fput(file);
error_return:

	return error;
}

3、

epoll_wait函数：

SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events,
		int, maxevents, int, timeout)
{
	int error;
	struct file *file;
	struct eventpoll *ep;

	/* The maximum number of event must be greater than zero */
	if (maxevents <= 0 || maxevents > EP_MAX_EVENTS)
		return -EINVAL;

	/* Verify that the area passed by the user is writeable */
	if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event))) {
		error = -EFAULT;
		goto error_return;
	}

	/* Get the "struct file *" for the eventpoll file */
	error = -EBADF;
	file = fget(epfd);
	if (!file)
		goto error_return;

	/*
	 * We have to check that the file structure underneath the fd
	 * the user passed to us _is_ an eventpoll file.
	 */
	error = -EINVAL;
	if (!is_file_epoll(file))
		goto error_fput;

	/*
	 * At this point it is safe to assume that the "private_data" contains
	 * our own data structure.
	 */
	ep = file->private_data;

	/* Time to fish for events ... */
	error = ep_poll(ep, events, maxevents, timeout);

error_fput:
	fput(file);
error_return:

	return error;
}

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.
	 */
	jtimeout = (timeout < 0 || timeout >= EP_MAX_MSTIMEO) ?
		MAX_SCHEDULE_TIMEOUT : (timeout * HZ + 999) / 1000;

retry:
	spin_lock_irqsave(&ep->lock, flags);

	res = 0;
	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.
		 */
		init_waitqueue_entry(&wait, current);
		wait.flags |= WQ_FLAG_EXCLUSIVE;
		__add_wait_queue(&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.
			 */
			set_current_state(TASK_INTERRUPTIBLE);
			if (!list_empty(&ep->rdllist) || !jtimeout)
				break;
			if (signal_pending(current)) {
				res = -EINTR;
				break;
			}

			spin_unlock_irqrestore(&ep->lock, flags);
			jtimeout = schedule_timeout(jtimeout);
			spin_lock_irqsave(&ep->lock, flags);
		}
		__remove_wait_queue(&ep->wq, &wait);

		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.
	 */
	if (!res && eavail &&
	    !(res = ep_send_events(ep, events, maxevents)) && jtimeout)
		goto retry;

	return res;
}

static int ep_send_events(struct eventpoll *ep,
			  struct epoll_event __user *events, int maxevents)
{
	struct ep_send_events_data esed;

	esed.maxevents = maxevents;
	esed.events = events;

	return ep_scan_ready_list(ep, ep_send_events_proc, &esed);
}

static int ep_scan_ready_list(struct eventpoll *ep,
			      int (*sproc)(struct eventpoll *,
					   struct list_head *, void *),
			      void *priv)
{
	int error, pwake = 0;
	unsigned long flags;
	struct epitem *epi, *nepi;
	LIST_HEAD(txlist);

	/*
	 * We need to lock this because we could be hit by
	 * eventpoll_release_file() and epoll_ctl().
	 */
	mutex_lock(&ep->mtx);

	/*
	 * Steal the ready list, and re-init the original one to the
	 * empty list. Also, set ep->ovflist to NULL so that events
	 * happening while looping w/out locks, are not lost. We cannot
	 * have the poll callback to queue directly on ep->rdllist,
	 * because we want the "sproc" callback to be able to do it
	 * in a lockless way.
	 */
	spin_lock_irqsave(&ep->lock, flags);
	list_splice_init(&ep->rdllist, &txlist);
	ep->ovflist = NULL;
	spin_unlock_irqrestore(&ep->lock, flags);

	/*
	 * Now call the callback function. 
	 */
	error = (*sproc)(ep, &txlist, priv);//ep_send_events_proc

	spin_lock_irqsave(&ep->lock, flags);
	/*
	 * During the time we spent inside the "sproc" callback, some
	 * other events might have been queued by the poll callback.
	 * We re-insert them inside the main ready-list here.
	 */
	for (nepi = ep->ovflist; (epi = nepi) != NULL;
	     nepi = epi->next, epi->next = EP_UNACTIVE_PTR) {
		/*
		 * We need to check if the item is already in the list.
		 * During the "sproc" callback execution time, items are
		 * queued into ->ovflist but the "txlist" might already
		 * contain them, and the list_splice() below takes care of them.
		 */
		if (!ep_is_linked(&epi->rdllink))
			list_add_tail(&epi->rdllink, &ep->rdllist);
	}
	/*
	 * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after
	 * releasing the lock, events will be queued in the normal way inside
	 * ep->rdllist.
	 */
	ep->ovflist = EP_UNACTIVE_PTR;

	/*
	 * Quickly re-inject items left on "txlist".
	 */
	list_splice(&txlist, &ep->rdllist);

	if (!list_empty(&ep->rdllist)) {
		/*
		 * Wake up (if active) both the eventpoll wait list and
		 * the ->poll() wait list (delayed after we release the lock).
		 */
		if (waitqueue_active(&ep->wq))
			wake_up_locked(&ep->wq);
		if (waitqueue_active(&ep->poll_wait))
			pwake++;
	}
	spin_unlock_irqrestore(&ep->lock, flags);

	mutex_unlock(&ep->mtx);

	/* We have to call this outside the lock */
	if (pwake)
		ep_poll_safewake(&ep->poll_wait);

	return error;
}

3.2、默认是LT水平触发模式，ET边缘触发模式需要自己指定

static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head,
			       void *priv)
{
	struct ep_send_events_data *esed = priv;
	int eventcnt;
	unsigned int revents;
	struct epitem *epi;
	struct epoll_event __user *uevent;

	/*
	 * We can loop without lock because we are passed a task private list.
	 * Items cannot vanish during the loop because ep_scan_ready_list() is
	 * holding "mtx" during this call.
	 */
	for (eventcnt = 0, uevent = esed->events;
	     !list_empty(head) && eventcnt < esed->maxevents;) {
		epi = list_first_entry(head, struct epitem, rdllink);

		list_del_init(&epi->rdllink);
		// 由accept->tipc_create f_op对应(stream_ops/msg_ops)其中poll就是socket.c中的poll函数
		revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL) &
			epi->event.events;

		/*
		 * If the event mask intersect the caller-requested one,
		 * deliver the event to userspace. Again, ep_scan_ready_list()
		 * is holding "mtx", so no operations coming from userspace
		 * can change the item.
		 */
		if (revents) {
			if (__put_user(revents, &uevent->events) ||
			    __put_user(epi->event.data, &uevent->data)) {
				list_add(&epi->rdllink, head);
				return eventcnt ? eventcnt : -EFAULT;
			}
			eventcnt++;
			uevent++;
			if (epi->event.events & EPOLLONESHOT)
				epi->event.events &= EP_PRIVATE_BITS;
			else if (!(epi->event.events & EPOLLET)) { //意思是只要不是ET模式(即默认是LT模式)则继续加入rdlist列表，如果设置了ET则不再加入
				/*
				 * If this file has been added with Level
				 * Trigger mode, we need to insert back inside
				 * the ready list, so that the next call to
				 * epoll_wait() will check again the events
				 * availability. At this point, noone can insert
				 * into ep->rdllist besides us. The epoll_ctl()
				 * callers are locked out by
				 * ep_scan_ready_list() holding "mtx" and the
				 * poll callback will queue them in ep->ovflist.
				 */
				list_add_tail(&epi->rdllink, &ep->rdllist);
			}
		}
	}

	return eventcnt;
}

其中POLLXX 系列和EPOLLXX宏数值是一样的，可以自己 测试

看下socket.c中的poll函数

static unsigned int poll(struct file *file, struct socket *sock,
			 poll_table *wait)
{
	struct sock *sk = sock->sk;
	u32 mask;

	poll_wait(file, sk->sk_sleep, wait);

	if (!skb_queue_empty(&sk->sk_receive_queue) ||
	    (sock->state == SS_UNCONNECTED) ||
	    (sock->state == SS_DISCONNECTING))
		mask = (POLLRDNORM | POLLIN);
	else
		mask = 0;

	if (sock->state == SS_DISCONNECTING)
		mask |= POLLHUP;
	else
		mask |= POLLOUT;

	return mask;
}