From: Lai Jiangshan <laijs@cn.fujitsu.com>
To: Tejun Heo <tj@kernel.org>, linux-kernel@vger.kernel.org
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Subject: [PATCH 01/11 V5] workqueue: ensure the wq_worker_sleeping() see the right flags
Date: Wed, 5 Sep 2012 18:37:38 +0800 [thread overview]
Message-ID: <1346841475-4422-2-git-send-email-laijs@cn.fujitsu.com> (raw)
In-Reply-To: <1346841475-4422-1-git-send-email-laijs@cn.fujitsu.com>
The compiler may compile this code into TWO write/modify instructions.
worker->flags &= ~WORKER_UNBOUND;
worker->flags |= WORKER_REBIND;
so the other CPU may see the temporary of worker->flags which has
not WORKER_UNBOUND nor WORKER_REBIND, it will wrongly do local wake up.
so we use one write/modify instruction explicitly instead.
This bug will not occur on idle workers, because they have another
WORKER_NOT_RUNNING flags.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
---
kernel/workqueue.c | 7 +++++--
1 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 85bd340..050b2a5 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1739,10 +1739,13 @@ retry:
for_each_busy_worker(worker, i, pos, gcwq) {
struct work_struct *rebind_work = &worker->rebind_work;
struct workqueue_struct *wq;
+ unsigned long worker_flags = worker->flags;
/* morph UNBOUND to REBIND */
- worker->flags &= ~WORKER_UNBOUND;
- worker->flags |= WORKER_REBIND;
+ worker_flags &= ~WORKER_UNBOUND;
+ worker_flags |= WORKER_REBIND;
+ /* ensure the wq_worker_sleeping() see the right flags */
+ ACCESS_ONCE(worker->flags) = worker_flags;
if (test_and_set_bit(WORK_STRUCT_PENDING_BIT,
work_data_bits(rebind_work)))
--
1.7.4.4
next prev parent reply other threads:[~2012-09-05 10:36 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-09-05 10:37 [PATCH 00/11 V5] workqueue: reimplement unbind/rebind Lai Jiangshan
2012-09-05 10:37 ` Lai Jiangshan [this message]
2012-09-05 10:37 ` [PATCH 02/11 V5] workqueue: async idle rebinding Lai Jiangshan
2012-09-05 18:06 ` Tejun Heo
2012-09-06 1:28 ` Lai Jiangshan
2012-09-05 10:37 ` [PATCH 03/11 V5] workqueue: new day don't need WORKER_REBIND for busy rebinding Lai Jiangshan
2012-09-05 18:31 ` Tejun Heo
2012-09-06 2:10 ` Lai Jiangshan
2012-09-05 10:37 ` [PATCH 04/11 V5] workqueue: remove WORKER_REBIND Lai Jiangshan
2012-09-05 10:37 ` [PATCH 05/11 V5] workqueue: Add @bind arguement back without change any thing Lai Jiangshan
2012-09-05 19:49 ` Tejun Heo
2012-09-06 1:04 ` Lai Jiangshan
2012-09-06 16:51 ` Tejun Heo
2012-09-07 2:11 ` Lai Jiangshan
2012-09-07 19:37 ` Tejun Heo
2012-09-05 10:37 ` [PATCH 06/11 V5] workqueue: unbind manager Lai Jiangshan
2012-09-05 10:37 ` [PATCH 07/11 V5] workqueue: rebind manager Lai Jiangshan
2012-09-05 10:37 ` [PATCH 08/11 V5] workqueue: unbind newly created worker Lai Jiangshan
2012-09-05 10:37 ` [PATCH 09/11 V5] workqueue: rebind " Lai Jiangshan
2012-09-05 16:19 ` Lai Jiangshan
2012-09-05 10:37 ` [PATCH 10/11 V5] workqueue: unbind/rebind without manager_mutex Lai Jiangshan
2012-09-05 20:04 ` Tejun Heo
2012-09-06 10:44 ` Lai Jiangshan
2012-09-06 17:00 ` Tejun Heo
2012-09-05 10:37 ` [PATCH 11/11 V5] workqueue: remove manager_mutex Lai Jiangshan
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=1346841475-4422-2-git-send-email-laijs@cn.fujitsu.com \
--to=laijs@cn.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=tj@kernel.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.