diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 339453ac834c..7e11135bc915 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1803,6 +1803,21 @@ 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);
+
+	list_del_init(&wq_entry->entry);
+	return ret;
+}
+
 /**
  * ep_poll - Retrieves ready events, and delivers them to the caller supplied
  *           event buffer.
@@ -1880,8 +1895,15 @@ 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);