epoll keyed wakeups: teach epoll about hints coming with the wakeup key

Use the events hint now sent by some devices, to avoid unnecessary wakeups
for events that are of no interest for the caller.  This code handles both
devices that are sending keyed events, and the ones that are not (and
event the ones that sometimes send events, and sometimes don't).

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: David Miller <davem@davemloft.net>
Cc: William Lee Irwin III <wli@movementarian.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 336fdb8..a89f370 100644 (file)
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -371,9 +371,28 @@ static int ep_call_nested(struct nested_calls *ncalls, int max_nests,
        return error;
 }
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static inline void ep_wake_up_nested(wait_queue_head_t *wqueue,
+                                    unsigned long events, int subclass)
+{
+       unsigned long flags;
+
+       spin_lock_irqsave_nested(&wqueue->lock, flags, subclass);
+       wake_up_locked_poll(wqueue, events);
+       spin_unlock_irqrestore(&wqueue->lock, flags);
+}
+#else
+static inline void ep_wake_up_nested(wait_queue_head_t *wqueue,
+                                    unsigned long events, int subclass)
+{
+       wake_up_poll(wqueue, events);
+}
+#endif
+
 static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests)
 {
-       wake_up_nested((wait_queue_head_t *) cookie, 1 + call_nests);
+       ep_wake_up_nested((wait_queue_head_t *) cookie, POLLIN,
+                         1 + call_nests);
        return 0;
 }
 
@@ -783,6 +802,15 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
                goto out_unlock;
 
        /*
+        * Check the events coming with the callback. At this stage, not
+        * every device reports the events in the "key" parameter of the
+        * callback. We need to be able to handle both cases here, hence the
+        * test for "key" != NULL before the event match test.
+        */
+       if (key && !((unsigned long) key & epi->event.events))
+               goto out_unlock;
+
+       /*
         * If we are trasfering events to userspace, we can hold no locks
         * (because we're accessing user memory, and because of linux f_op->poll()
         * semantics). All the events that happens during that period of time are
@@ -1254,7 +1282,6 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
        case EPOLL_CTL_ADD:
                if (!epi) {
                        epds.events |= POLLERR | POLLHUP;
-
                        error = ep_insert(ep, &epds, tfile, fd);
                } else
                        error = -EEXIST;