From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756993AbZBAUFz (ORCPT ); Sun, 1 Feb 2009 15:05:55 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755389AbZBAUEd (ORCPT ); Sun, 1 Feb 2009 15:04:33 -0500 Received: from x35.xmailserver.org ([64.71.152.41]:47046 "EHLO x35.xmailserver.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754719AbZBAUEc (ORCPT ); Sun, 1 Feb 2009 15:04:32 -0500 X-AuthUser: davidel@xmailserver.org From: Davide Libenzi To: Linux Kernel Mailing List Cc: Andrew Morton , Linus Torvalds , Alan Cox , Ingo Molnar , David Miller Date: Sun, 01 Feb 2009 12:04:23 -0800 Subject: [patch 4/6] epoll keyed wakeups v2 - teach epoll about hints coming with the wakeup key MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Message-ID: Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The follwing patch uses 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). Signed-off-by: Davide Libenzi - Davide --- fs/eventpoll.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) Index: linux-2.6.mod/fs/eventpoll.c =================================================================== --- linux-2.6.mod.orig/fs/eventpoll.c 2009-01-31 14:55:21.000000000 -0800 +++ linux-2.6.mod/fs/eventpoll.c 2009-01-31 15:35:31.000000000 -0800 @@ -372,7 +372,8 @@ static int ep_call_nested(struct nested_ static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests) { - wake_up_nested((wait_queue_head_t *) cookie, 1 + call_nests); + wake_up_nested_poll((wait_queue_head_t *) cookie, POLLIN, + 1 + call_nests); return 0; } @@ -785,6 +786,15 @@ static int ep_poll_callback(wait_queue_t if (!(epi->event.events & ~EP_PRIVATE_BITS)) 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() @@ -1260,7 +1270,6 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, in case EPOLL_CTL_ADD: if (!epi) { epds.events |= POLLERR | POLLHUP; - error = ep_insert(ep, &epds, tfile, fd); } else error = -EEXIST;