Commit 296e236e authored by Davide Libenzi's avatar Davide Libenzi Committed by Linus Torvalds
Browse files

epoll: fix epoll's own poll (update) 



Signed-off-by: default avatarDavide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 5071f97e

fs/eventpoll.c

+57 −53
Original line number Diff line number Diff line
@@ -454,9 +454,7 @@ static int ep_scan_ready_list(struct eventpoll *ep, 
	int error, pwake = 0;

	unsigned long flags;

	struct epitem *epi, *nepi;

	struct list_head txlist;



	INIT_LIST_HEAD(&txlist);

	LIST_HEAD(txlist);



	/*

	 * We need to lock this because we could be hit by
@@ -473,8 +471,7 @@ static int ep_scan_ready_list(struct eventpoll *ep, 
	 * in a lockless way.

	 */

	spin_lock_irqsave(&ep->lock, flags);

	list_splice(&ep->rdllist, &txlist);

	INIT_LIST_HEAD(&ep->rdllist);

	list_splice_init(&ep->rdllist, &txlist);

	ep->ovflist = NULL;

	spin_unlock_irqrestore(&ep->lock, flags);
@@ -514,8 +511,8 @@ static int ep_scan_ready_list(struct eventpoll *ep, 


	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).

		 * 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);
@@ -632,7 +629,8 @@ static int ep_eventpoll_release(struct inode *inode, struct file *file) 
	return 0;

}



static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head, void *priv)

static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,

			       void *priv)

{

	struct epitem *epi, *tmp;
@@ -640,7 +638,7 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head, voi 
		if (epi->ffd.file->f_op->poll(epi->ffd.file, NULL) &

		    epi->event.events)

			return POLLIN | POLLRDNORM;

		else

		else {

			/*

			 * Item has been dropped into the ready list by the poll

			 * callback, but it's not actually ready, as far as
@@ -648,6 +646,7 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head, voi 
			 */

			list_del_init(&epi->rdllink);

		}

	}



	return 0;

}
@@ -872,10 +871,11 @@ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead, 
		add_wait_queue(whead, &pwq->wait);

		list_add_tail(&pwq->llink, &epi->pwqlist);

		epi->nwait++;

	} else

	} else {

		/* We have to signal that an error occurred */

		epi->nwait = -1;

	}

}



static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi)

{
@@ -1055,7 +1055,8 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even 
	return 0;

}



static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, void *priv)

static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head,

			       void *priv)

{

	struct ep_send_events_data *esed = priv;

	int eventcnt;
@@ -1091,26 +1092,28 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, voi 
			uevent++;

			if (epi->event.events & EPOLLONESHOT)

				epi->event.events &= EP_PRIVATE_BITS;

  			else if (!(epi->event.events & EPOLLET))

  				/*

				 * 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.

			else if (!(epi->event.events & EPOLLET)) {

				/*

				 * 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;

}



static int ep_send_events(struct eventpoll *ep, struct epoll_event __user *events,

			  int maxevents)

static int ep_send_events(struct eventpoll *ep,

			  struct epoll_event __user *events, int maxevents)

{

	struct ep_send_events_data esed;
@@ -1194,40 +1197,41 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, 
 */

SYSCALL_DEFINE1(epoll_create1, int, flags)

{

	int error;

	struct eventpoll *ep = NULL;

	int error, fd = -1;

	struct eventpoll *ep;



	/* Check the EPOLL_* constant for consistency.  */

	BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);



	if (flags & ~EPOLL_CLOEXEC)

		return -EINVAL;



	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d)\n",

		     current, flags));



	error = -EINVAL;

	if (flags & ~EPOLL_CLOEXEC)

		goto error_return;



	/*

	 * Create the internal data structure ( "struct eventpoll" ).

	 */

	error = ep_alloc(&ep);

	if (error < 0)

	if (error < 0) {

		fd = error;

		goto error_return;

	}



	/*

	 * Creates all the items needed to setup an eventpoll file. That is,

	 * a file structure and a free file descriptor.

	 */

	error = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep,

	fd = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep,

			      flags & O_CLOEXEC);

	if (error < 0)

	if (fd < 0)

		ep_free(ep);



error_return:

	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",

		     current, flags, error));

		     current, flags, fd));



	return error;

	return fd;

}



SYSCALL_DEFINE1(epoll_create, int, size)