1 files changed, 67 insertions, 27 deletions

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 339453ac834c..8c0e94183186 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1803,6 +1803,25 @@ static inline struct timespec64 ep_set_mstimeout(long ms)
 	return timespec64_add_safe(now, ts);
 }
 
+/*
+ * autoremove_wake_function, but remove even on failure to wake up, because we
+ * know that default_wake_function/ttwu will only fail if the thread is already
+ * woken, and in that case the ep_poll loop will remove the entry anyways, not
+ * try to reuse it.
+ */
+static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry,
+				       unsigned int mode, int sync, void *key)
+{
+	int ret = default_wake_function(wq_entry, mode, sync, key);
+
+	/*
+	 * Pairs with list_empty_careful in ep_poll, and ensures future loop
+	 * iterations see the cause of this wakeup.
+	 */
+	list_del_init_careful(&wq_entry->entry);
+	return ret;
+}
+
 /**
  * ep_poll - Retrieves ready events, and delivers them to the caller supplied
  *           event buffer.
@@ -1880,56 +1899,77 @@ fetch_events:
 		 * normal wakeup path no need to call __remove_wait_queue()
 		 * explicitly, thus ep->lock is not taken, which halts the
 		 * event delivery.
+		 *
+		 * In fact, we now use an even more aggressive function that
+		 * unconditionally removes, because we don't reuse the wait
+		 * entry between loop iterations. This lets us also avoid the
+		 * performance issue if a process is killed, causing all of its
+		 * threads to wake up without being removed normally.
 		 */
 		init_wait(&wait);
+		wait.func = ep_autoremove_wake_function;
 		write_lock_irq(&ep->lock);
-		__add_wait_queue_exclusive(&ep->wq, &wait);
-		write_unlock_irq(&ep->lock);
-
 		/*
-		 * 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
-		 * to TASK_INTERRUPTIBLE before doing the checks.
+		 * Barrierless variant, waitqueue_active() is called under
+		 * the same lock on wakeup ep_poll_callback() side, so it
+		 * is safe to avoid an explicit barrier.
 		 */
-		set_current_state(TASK_INTERRUPTIBLE);
+		__set_current_state(TASK_INTERRUPTIBLE);
+
 		/*
-		 * Always short-circuit for fatal signals to allow
-		 * threads to make a timely exit without the chance of
-		 * finding more events available and fetching
-		 * repeatedly.
+		 * Do the final check under the lock. ep_scan_ready_list()
+		 * plays with two lists (->rdllist and ->ovflist) and there
+		 * is always a race when both lists are empty for short
+		 * period of time although events are pending, so lock is
+		 * important.
 		 */
-		if (fatal_signal_pending(current)) {
-			res = -EINTR;
-			break;
-		}
-
 		eavail = ep_events_available(ep);
-		if (eavail)
-			break;
-		if (signal_pending(current)) {
-			res = -EINTR;
-			break;
+		if (!eavail) {
+			if (signal_pending(current))
+				res = -EINTR;
+			else
+				__add_wait_queue_exclusive(&ep->wq, &wait);
 		}
+		write_unlock_irq(&ep->lock);
 
-		if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) {
-			timed_out = 1;
-			break;
-		}
+		if (!eavail && !res)
+			timed_out = !schedule_hrtimeout_range(to, slack,
+							      HRTIMER_MODE_ABS);
 
-		/* We were woken up, thus go and try to harvest some events */
+		/*
+		 * We were woken up, thus go and try to harvest some events.
+		 * If timed out and still on the wait queue, recheck eavail
+		 * carefully under lock, below.
+		 */
 		eavail = 1;
-
 	} while (0);
 
 	__set_current_state(TASK_RUNNING);
 
 	if (!list_empty_careful(&wait.entry)) {
 		write_lock_irq(&ep->lock);
+		/*
+		 * If the thread timed out and is not on the wait queue, it
+		 * means that the thread was woken up after its timeout expired
+		 * before it could reacquire the lock. Thus, when wait.entry is
+		 * empty, it needs to harvest events.
+		 */
+		if (timed_out)
+			eavail = list_empty(&wait.entry);
 		__remove_wait_queue(&ep->wq, &wait);
 		write_unlock_irq(&ep->lock);
 	}
 
 send_events:
+	if (fatal_signal_pending(current)) {
+		/*
+		 * Always short-circuit for fatal signals to allow
+		 * threads to make a timely exit without the chance of
+		 * finding more events available and fetching
+		 * repeatedly.
+		 */
+		res = -EINTR;
+	}
 	/*
 	 * Try to transfer events to user space. In case we get 0 events and
 	 * there's still timeout left over, we go trying again in search of