1 files changed, 26 insertions, 21 deletions

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 0f9c073d78d5..70ecf02cdca2 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1827,7 +1827,6 @@ 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;
 
@@ -1872,21 +1871,23 @@ 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 woken by ep_poll_callback() when events
-	 * become available.
-	 */
-	if (!waiter) {
-		waiter = true;
-		init_waitqueue_entry(&wait, current);
-
-		spin_lock_irq(&ep->wq.lock);
+	do {
+		/*
+		 * Internally init_wait() uses autoremove_wake_function(),
+		 * thus wait entry is removed from the wait queue on each
+		 * wakeup. Why it is important? In case of several waiters
+		 * each new wakeup will hit the next waiter, giving it the
+		 * chance to harvest new event. Otherwise wakeup can be
+		 * lost. This is also good performance-wise, because on
+		 * normal wakeup path no need to call __remove_wait_queue()
+		 * explicitly, thus ep->lock is not taken, which halts the
+		 * event delivery.
+		 */
+		init_wait(&wait);
+		write_lock_irq(&ep->lock);
 		__add_wait_queue_exclusive(&ep->wq, &wait);
-		spin_unlock_irq(&ep->wq.lock);
-	}
+		write_unlock_irq(&ep->lock);
 
-	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
@@ -1916,10 +1917,20 @@ fetch_events:
 			timed_out = 1;
 			break;
 		}
-	}
+
+		/* We were woken up, thus go and try to harvest some events */
+		eavail = 1;
+
+	} while (0);
 
 	__set_current_state(TASK_RUNNING);
 
+	if (!list_empty_careful(&wait.entry)) {
+		write_lock_irq(&ep->lock);
+		__remove_wait_queue(&ep->wq, &wait);
+		write_unlock_irq(&ep->lock);
+	}
+
 send_events:
 	/*
 	 * Try to transfer events to user space. In case we get 0 events and
@@ -1930,12 +1941,6 @@ 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;
 }