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.

[akpm@linux-foundation.org: restore code to original position, fix and reflow comment]
Link: http://lkml.kernel.org/r/20181114182532.27981-2-dave@stgolabs.net
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

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;
 
@@ -1794,14 +1795,18 @@ fetch_events:
 	ep_reset_busy_poll_napi_id(ep);
 
 	/*
-	 * 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.
+	 * We don't have any available event to return to the caller.  We need
+	 * to sleep here, and we will be woken by ep_poll_callback() when events
+	 * become available.
 	 */
+	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);
+	}
 
 	for (;;) {
 		/*
@@ -1837,10 +1842,6 @@ fetch_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
@@ -1851,6 +1852,12 @@ send_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;
 }