From: Heiko Carstens <heiko.carstens@de.ibm.com>
To: rusty@rustcorp.com.au, jens.axboe@oracle.com, schwidefsky@de.ibm.com
Cc: linux-kernel@vger.kernel.org, Heiko Carstens <heiko.carstens@de.ibm.com>
Subject: [PATCH/RFC 1/4] stop_machine: atomic update for combined return value
Date: Fri, 03 Oct 2008 12:56:33 +0200 [thread overview]
Message-ID: <20081003105752.247421935@de.ibm.com> (raw)
In-Reply-To: 20081003105632.357231142@de.ibm.com
[-- Attachment #1: stopmachine_atomic.diff --]
[-- Type: text/plain, Size: 1207 bytes --]
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Using |= for updating a value which might be updated on several cpus
concurrently will not always work since we need to make sure that the
update happens atomically. So let's use a cmpxchg loop instead.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
kernel/stop_machine.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
Index: linux-2.6/kernel/stop_machine.c
===================================================================
--- linux-2.6.orig/kernel/stop_machine.c
+++ linux-2.6/kernel/stop_machine.c
@@ -65,6 +65,7 @@ static void ack_state(void)
static int stop_cpu(struct stop_machine_data *smdata)
{
enum stopmachine_state curstate = STOPMACHINE_NONE;
+ int *frp, fnret, old;
/* Simple state machine */
do {
@@ -80,7 +81,11 @@ static int stop_cpu(struct stop_machine_
case STOPMACHINE_RUN:
/* |= allows error detection if functions on
* multiple CPUs. */
- smdata->fnret |= smdata->fn(smdata->data);
+ fnret = smdata->fn(smdata->data);
+ frp = &smdata->fnret;
+ do {
+ old = *frp;
+ } while (cmpxchg(frp, old, old | fnret) != old);
break;
default:
break;
--
next prev parent reply other threads:[~2008-10-03 10:59 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-10-03 10:56 [PATCH/RFC 0/4] Add stop_machine_get/put_threads to stop_machine infrastructrue Heiko Carstens
2008-10-03 10:56 ` Heiko Carstens [this message]
2008-10-03 10:56 ` [PATCH/RFC 2/4] stop_machine: add stop_machine_get/put_threads interface Heiko Carstens
2008-10-03 10:56 ` [PATCH/RFC 3/4] s390: convert etr/stp to stop_machine interface Heiko Carstens
2008-10-03 10:56 ` [PATCH/RFC 4/4] s390: convert to generic IPI infrstructure Heiko Carstens
2008-10-06 4:42 ` [PATCH/RFC 0/4] Add stop_machine_get/put_threads to stop_machine infrastructrue Rusty Russell
2008-10-06 20:16 ` Heiko Carstens
2008-10-07 1:39 ` Rusty Russell
2008-10-07 15:38 ` Heiko Carstens
2008-10-08 0:27 ` Rusty Russell
2008-10-08 10:14 ` Heiko Carstens
2008-10-09 0:18 ` Rusty Russell
2008-10-09 16:25 ` Heiko Carstens
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=20081003105752.247421935@de.ibm.com \
--to=heiko.carstens@de.ibm.com \
--cc=jens.axboe@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=rusty@rustcorp.com.au \
--cc=schwidefsky@de.ibm.com \
/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.