linux-kernel - [PATCH 2/2] fs/epoll: deal with wait

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20181114182532.27981-2-dave@stgolabs.net>
Date:   Wed, 14 Nov 2018 10:25:32 -0800
From:   Davidlohr Bueso <dave@...olabs.net>
To:     akpm@...ux-foundation.org
Cc:     jbaron@...mai.com, viro@...iv.linux.org.uk,
        linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org,
        dave@...olabs.net, Davidlohr Bueso <dbueso@...e.de>
Subject: [PATCH 2/2] fs/epoll: deal with wait_queue only once

There is no reason why we rearm the waitiqueue upon every
fetch_events retry (for when events are found yet send_events()
fails). If nothing else, this saves four lock operations per
retry, and furthermore reduces the scope of the lock even
further.

Signed-off-by: Davidlohr Bueso <dbueso@...e.de>
---
 fs/eventpoll.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 7e2b5f3d6b3e..25b0c94cc091 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1749,6 +1749,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 {
 	int res = 0, eavail, timed_out = 0;
 	u64 slack = 0;
+	bool waiter = false;
 	wait_queue_entry_t wait;
 	ktime_t expires, *to = NULL;
 
@@ -1786,6 +1787,15 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 	if (eavail)
 		goto send_events;
 
+	if (!waiter) {
+		waiter = true;
+		init_waitqueue_entry(&wait, current);
+
+		spin_lock_irq(&ep->wq.lock);
+		__add_wait_queue_exclusive(&ep->wq, &wait);
+		spin_unlock_irq(&ep->wq.lock);
+	}
+
 	/*
 	 * Busy poll timed out.  Drop NAPI ID for now, we can add
 	 * it back in when we have moved a socket with a valid NAPI
@@ -1798,10 +1808,6 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 	 * 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);
-	spin_lock_irq(&ep->wq.lock);
-	__add_wait_queue_exclusive(&ep->wq, &wait);
-	spin_unlock_irq(&ep->wq.lock);
 
 	for (;;) {
 		/*
@@ -1836,10 +1842,6 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 
 	__set_current_state(TASK_RUNNING);
 
-	spin_lock_irq(&ep->wq.lock);
-	__remove_wait_queue(&ep->wq, &wait);
-	spin_unlock_irq(&ep->wq.lock);
-
 send_events:
 	/*
 	 * Try to transfer events to user space. In case we get 0 events and
@@ -1850,6 +1852,12 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 	    !(res = ep_send_events(ep, events, maxevents)) && !timed_out)
 		goto fetch_events;
 
+	if (waiter) {
+		spin_lock_irq(&ep->wq.lock);
+		__remove_wait_queue(&ep->wq, &wait);
+		spin_unlock_irq(&ep->wq.lock);
+	}
+
 	return res;
 }
 
-- 
2.16.4