linux epoll_ctl

linux epoll_ctl函数对应系统调用sys_epoll_ctl

asmlinkage long
sys_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;

	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_ctl(%d, %d, %d, %p)\n",
		     current, epfd, op, fd, event));

	error = -EFAULT;
	if (copy_from_user(&epds, event, sizeof(struct epoll_event)))
		goto eexit_1;

	/* Get the "struct file *" for the eventpoll file */
	error = -EBADF;
	file = fget(epfd);
	if (!file)
		goto eexit_1;

	/* Get the "struct file *" for the target file */
	tfile = fget(fd);
	if (!tfile)
		goto eexit_2;

	/* The target file descriptor must support poll */
	error = -EPERM;
	if (!tfile->f_op || !tfile->f_op->poll)
		goto eexit_3;

	/*
	 * 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.
	 */
	error = -EINVAL;
	if (file == tfile || !IS_FILE_EPOLL(file))
		goto eexit_3;

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

	down_write(&ep->sem);

	/* Try to lookup the file inside our hash table */
	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;
		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;
	}

	/*
	 * The function ep_find() increments the usage count of the structure
	 * so, if this is not NULL, we need to release it.
	 */
	if (epi)
		ep_release_epitem(epi);

	up_write(&ep->sem);

eexit_3:
	fput(tfile);
eexit_2:
	fput(file);
eexit_1:
	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_ctl(%d, %d, %d, %p) = %d\n",
		     current, epfd, op, fd, event, error));

	return error;
}

static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
		     struct file *tfile, int fd)
{
	int error, revents, pwake = 0;
	unsigned long flags;
	struct epitem *epi;
	struct ep_pqueue epq;

	error = -ENOMEM;
	if (!(epi = EPI_MEM_ALLOC()))
		goto eexit_1;

	/* Item initialization follow here ... */
	INIT_LIST_HEAD(&epi->llink);
	INIT_LIST_HEAD(&epi->rdllink);
	INIT_LIST_HEAD(&epi->fllink);
	INIT_LIST_HEAD(&epi->txlink);
	INIT_LIST_HEAD(&epi->pwqlist);
	epi->ep = ep;
	epi->file = tfile;
	epi->fd = fd;
	epi->event = *event;
	atomic_set(&epi->usecnt, 1);
	epi->nwait = 0;

	/* Initialize the poll table using the queue callback */
	epq.epi = epi;
	init_poll_funcptr(&epq.pt, ep_ptable_queue_proc);

	/*
	 * Attach the item to the poll hooks and get current event bits.
	 * We can safely use the file* here because its usage count has
	 * been increased by the caller of this function.
	 */
	revents = tfile->f_op->poll(tfile, &epq.pt);

	/*
	 * We have to check if something went wrong during the poll wait queue
	 * install process. Namely an allocation for a wait queue failed due
	 * high memory pressure.
	 */
	if (epi->nwait < 0)
		goto eexit_2;

	/* Add the current item to the list of active epoll hook for this file */
	spin_lock(&tfile->f_ep_lock);
	list_add_tail(&epi->fllink, &tfile->f_ep_links);
	spin_unlock(&tfile->f_ep_lock);

	/* We have to drop the new item inside our item list to keep track of it */
	write_lock_irqsave(&ep->lock, flags);

	/* Add the current item to the hash table */
	list_add(&epi->llink, ep_hash_entry(ep, ep_hash_index(ep, tfile, fd)));

	/* If the file is already "ready" we drop it inside the ready list */
	if ((revents & event->events) && !EP_IS_LINKED(&epi->rdllink)) {
		list_add_tail(&epi->rdllink, &ep->rdllist);

		/* Notify waiting tasks that events are available */
		if (waitqueue_active(&ep->wq))
			wake_up(&ep->wq);
		if (waitqueue_active(&ep->poll_wait))
			pwake++;
	}

	write_unlock_irqrestore(&ep->lock, flags);

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

	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_insert(%p, %p, %d)\n",
		     current, ep, tfile, fd));

	return 0;

eexit_2:
	ep_unregister_pollwait(ep, epi);

	/*
	 * We need to do this because an event could have been arrived on some
	 * allocated wait queue.
	 */
	write_lock_irqsave(&ep->lock, flags);
	if (EP_IS_LINKED(&epi->rdllink))
		EP_LIST_DEL(&epi->rdllink);
	write_unlock_irqrestore(&ep->lock, flags);

	EPI_MEM_FREE(epi);
eexit_1:
	return error;
}