epoll: prevent missed events on EPOLL_CTL_MOD

[karo-tx-linux.git] / fs / eventpoll.c

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index be56b21435f8c4e5170fdb2c0963abdd24dc9291..9fec1836057a9298ad9f121afcea03c64388eb88 100644 (file)
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1313,7 +1313,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
         * otherwise we might miss an event that happens between the
         * f_op->poll() call and the new event set registering.
         */
-       epi->event.events = event->events;
+       epi->event.events = event->events; /* need barrier below */
        pt._key = event->events;
        epi->event.data = event->data; /* protected by mtx */
        if (epi->event.events & EPOLLWAKEUP) {
@@ -1323,6 +1323,26 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
                ep_destroy_wakeup_source(epi);
        }
 
+       /*
+        * The following barrier has two effects:
+        *
+        * 1) Flush epi changes above to other CPUs.  This ensures
+        *    we do not miss events from ep_poll_callback if an
+        *    event occurs immediately after we call f_op->poll().
+        *    We need this because we did not take ep->lock while
+        *    changing epi above (but ep_poll_callback does take
+        *    ep->lock).
+        *
+        * 2) We also need to ensure we do not miss _past_ events
+        *    when calling f_op->poll().  This barrier also
+        *    pairs with the barrier in wq_has_sleeper (see
+        *    comments for wq_has_sleeper).
+        *
+        * This barrier will now guarantee ep_poll_callback or f_op->poll
+        * (or both) will notice the readiness of an item.
+        */
+       smp_mb();
+
        /*
         * Get current event bits. We can safely use the file* here because
         * its usage count has been increased by the caller of this function.