From: Eric Wong <normalperson@yhbt.net>
To: linux-kernel@vger.kernel.org
Cc: Eric Wong <normalperson@yhbt.net>,
Hans Verkuil <hans.verkuil@cisco.com>,
Jiri Olsa <jolsa@redhat.com>, Jonathan Corbet <corbet@lwn.net>,
Al Viro <viro@zeniv.linux.org.uk>,
Davide Libenzi <davidel@xmailserver.org>,
Hans de Goede <hdegoede@redhat.com>,
Mauro Carvalho Chehab <mchehab@infradead.org>,
David Miller <davem@davemloft.net>,
Eric Dumazet <eric.dumazet@gmail.com>,
Andrew Morton <akpm@linux-foundation.org>,
Linus Torvalds <torvalds@linux-foundation.org>,
Andreas Voellmy <andreas.voellmy@yale.edu>,
"Junchang(Jason) Wang" <junchang.wang@yale.edu>,
netdev@vger.kernel.org, linux-fsdevel@vger.kernel.org
Subject: [PATCH] poll: prevent missed events if _qproc is NULL
Date: Mon, 31 Dec 2012 13:21:00 +0000 [thread overview]
Message-ID: <1356960060-1263-1-git-send-email-normalperson@yhbt.net> (raw)
In-Reply-To: <20121228014503.GA5017@dcvr.yhbt.net>
This patch seems to fix my issue with ppoll() being stuck on my
SMP machine: http://article.gmane.org/gmane.linux.file-systems/70414
The change to sock_poll_wait() in
commit 626cf236608505d376e4799adb4f7eb00a8594af
(poll: add poll_requested_events() and poll_does_not_wait() functions)
seems to have allowed additional cases where the SMP memory barrier
is not issued before checking for readiness.
In my case, this affects the select()-family of functions
which register descriptors once and set _qproc to NULL before
checking events again (after poll_schedule_timeout() returns).
The set_mb() barrier in poll_schedule_timeout() appears to be
insufficient on my SMP x86-64 machine (as it's only an xchg()).
This may also be related to the epoll issue described by
Andreas Voellmy in http://thread.gmane.org/gmane.linux.kernel/1408782/
Signed-off-by: Eric Wong <normalperson@yhbt.net>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Davide Libenzi <davidel@xmailserver.org>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Mauro Carvalho Chehab <mchehab@infradead.org>
Cc: David Miller <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andreas Voellmy <andreas.voellmy@yale.edu>
Cc: "Junchang(Jason) Wang" <junchang.wang@yale.edu>
Cc: netdev@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org
---
If this patch is correct, I think we can just drop the
poll_does_not_wait() function entirely since poll_wait()
does the same check anyways...
include/net/sock.h | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index c945fba..1923e48 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1925,8 +1925,9 @@ static inline bool wq_has_sleeper(struct socket_wq *wq)
static inline void sock_poll_wait(struct file *filp,
wait_queue_head_t *wait_address, poll_table *p)
{
- if (!poll_does_not_wait(p) && wait_address) {
- poll_wait(filp, wait_address, p);
+ if (wait_address) {
+ if (!poll_does_not_wait(p))
+ poll_wait(filp, wait_address, p);
/* We need to be sure we are in sync with the
* socket flags modification.
*
--
Eric Wong
next prev parent reply other threads:[~2012-12-31 13:21 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-12-28 1:45 ppoll() stuck on POLLIN while TCP peer is sending Eric Wong
2012-12-28 7:06 ` Eric Wong
2012-12-29 11:34 ` Eric Wong
2012-12-31 13:21 ` Eric Wong [this message]
2012-12-31 23:24 ` [PATCH] poll: prevent missed events if _qproc is NULL Eric Wong
2013-01-01 16:58 ` Junchang(Jason) Wang
2013-01-01 18:42 ` Eric Dumazet
2013-01-01 21:00 ` Eric Wong
2013-01-01 21:17 ` Eric Wong
2013-01-01 22:53 ` Linus Torvalds
2013-01-01 23:21 ` Junchang(Jason) Wang
2013-01-01 23:56 ` [PATCH] epoll: prevent missed events on EPOLL_CTL_MOD Eric Wong
2013-01-02 17:45 ` Eric Dumazet
2013-01-02 18:40 ` Eric Wong
2013-01-02 19:03 ` Eric Dumazet
2013-01-02 19:32 ` Eric Wong
2013-01-02 22:08 ` Eric Dumazet
2013-01-02 21:16 ` Eric Wong
2013-01-02 20:08 ` ppoll() stuck on POLLIN while TCP peer is sending Eric Wong
2013-01-02 20:47 ` Eric Wong
2013-01-03 13:41 ` Eric Dumazet
2013-01-03 18:32 ` Eric Wong
2013-01-03 23:45 ` Eric Wong
2013-01-04 0:26 ` Eric Wong
2013-01-04 3:52 ` Eric Wong
2013-01-04 16:01 ` Mel Gorman
2013-01-04 17:15 ` Eric Dumazet
2013-01-04 17:59 ` Eric Wong
2013-01-05 1:07 ` Eric Wong
2013-01-06 12:07 ` Eric Wong
2013-01-07 12:25 ` Mel Gorman
2013-01-07 22:38 ` Eric Dumazet
2013-01-08 0:21 ` Eric Wong
2013-01-07 22:38 ` Eric Wong
2013-01-08 20:14 ` Eric Wong
2013-01-08 22:43 ` Mel Gorman
2013-01-08 23:23 ` Eric Wong
2013-01-09 2:14 ` Eric Dumazet
2013-01-09 2:32 ` Eric Dumazet
2013-01-09 2:54 ` Eric Dumazet
2013-01-09 3:55 ` Eric Wong
2013-01-09 8:42 ` Eric Wong
2013-01-09 8:51 ` Eric Wong
2013-01-09 13:42 ` Mel Gorman
2013-01-09 13:37 ` Mel Gorman
2013-01-09 13:50 ` Mel Gorman
2013-01-10 9:25 ` Eric Wong
2013-01-10 19:42 ` Mel Gorman
2013-01-10 20:03 ` Eric Wong
2013-01-10 20:58 ` Eric Dumazet
2013-01-11 0:51 ` Eric Wong
2013-01-11 9:30 ` Mel Gorman
2013-01-09 21:29 ` Eric Wong
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1356960060-1263-1-git-send-email-normalperson@yhbt.net \
--to=normalperson@yhbt.net \
--cc=akpm@linux-foundation.org \
--cc=andreas.voellmy@yale.edu \
--cc=corbet@lwn.net \
--cc=davem@davemloft.net \
--cc=davidel@xmailserver.org \
--cc=eric.dumazet@gmail.com \
--cc=hans.verkuil@cisco.com \
--cc=hdegoede@redhat.com \
--cc=jolsa@redhat.com \
--cc=junchang.wang@yale.edu \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mchehab@infradead.org \
--cc=netdev@vger.kernel.org \
--cc=torvalds@linux-foundation.org \
--cc=viro@zeniv.linux.org.uk \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®