From: Xishi Qiu <qiuxishi@huawei.com>
To: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Mel Gorman <mgorman@techsingularity.net>,
Yaowei Bai <baiyaowei@cmss.chinamobile.com>,
Linux MM <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>,
Yisheng Xie <xieyisheng1@huawei.com>
Subject: Re: [RFC PATCH] mm: use ACCESS_ONCE in page_cpupid_xchg_last()
Date: Mon, 5 Dec 2016 17:22:23 +0800 [thread overview]
Message-ID: <584531CF.9030204@huawei.com> (raw)
In-Reply-To: <0cc3c2bb-e292-2d7b-8d44-16c8e6c19899@de.ibm.com>
On 2016/12/5 16:50, Christian Borntraeger wrote:
> On 12/05/2016 09:31 AM, Christian Borntraeger wrote:
>> On 12/05/2016 09:23 AM, Xishi Qiu wrote:
>>> By reading the code, I find the following code maybe optimized by
>>> compiler, maybe page->flags and old_flags use the same register,
>>> so use ACCESS_ONCE in page_cpupid_xchg_last() to fix the problem.
>>
>> please use READ_ONCE instead of ACCESS_ONCE for future patches.
>>
>>>
>>> Signed-off-by: Xishi Qiu <qiuxishi@huawei.com>
>>> ---
>>> mm/mmzone.c | 2 +-
>>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>>
>>> diff --git a/mm/mmzone.c b/mm/mmzone.c
>>> index 5652be8..e0b698e 100644
>>> --- a/mm/mmzone.c
>>> +++ b/mm/mmzone.c
>>> @@ -102,7 +102,7 @@ int page_cpupid_xchg_last(struct page *page, int cpupid)
>>> int last_cpupid;
>>>
>>> do {
>>> - old_flags = flags = page->flags;
>>> + old_flags = flags = ACCESS_ONCE(page->flags);
>>> last_cpupid = page_cpupid_last(page);
>>>
>>> flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT);
>>
>>
>> I dont thing that this is actually a problem. The code below does
>>
>> } while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags))
>>
>> and the cmpxchg should be an atomic op that should already take care of everything
>> (page->flags is passed as a pointer).
>>
>
> Reading the code again, you might be right, but I think your patch description
> is somewhat misleading. I think the problem is that old_flags and flags are
> not necessarily the same.
>
> So what about
>
> a compiler could re-read "old_flags" from the memory location after reading
> and calculation "flags" and passes a newer value into the cmpxchg making
> the comparison succeed while it should actually fail.
>
Hi Christian,
I'll resend v2, thanks!
>
>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Xishi Qiu <qiuxishi@huawei.com>
To: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Mel Gorman <mgorman@techsingularity.net>,
Yaowei Bai <baiyaowei@cmss.chinamobile.com>,
Linux MM <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>,
"Yisheng Xie" <xieyisheng1@huawei.com>
Subject: Re: [RFC PATCH] mm: use ACCESS_ONCE in page_cpupid_xchg_last()
Date: Mon, 5 Dec 2016 17:22:23 +0800 [thread overview]
Message-ID: <584531CF.9030204@huawei.com> (raw)
In-Reply-To: <0cc3c2bb-e292-2d7b-8d44-16c8e6c19899@de.ibm.com>
On 2016/12/5 16:50, Christian Borntraeger wrote:
> On 12/05/2016 09:31 AM, Christian Borntraeger wrote:
>> On 12/05/2016 09:23 AM, Xishi Qiu wrote:
>>> By reading the code, I find the following code maybe optimized by
>>> compiler, maybe page->flags and old_flags use the same register,
>>> so use ACCESS_ONCE in page_cpupid_xchg_last() to fix the problem.
>>
>> please use READ_ONCE instead of ACCESS_ONCE for future patches.
>>
>>>
>>> Signed-off-by: Xishi Qiu <qiuxishi@huawei.com>
>>> ---
>>> mm/mmzone.c | 2 +-
>>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>>
>>> diff --git a/mm/mmzone.c b/mm/mmzone.c
>>> index 5652be8..e0b698e 100644
>>> --- a/mm/mmzone.c
>>> +++ b/mm/mmzone.c
>>> @@ -102,7 +102,7 @@ int page_cpupid_xchg_last(struct page *page, int cpupid)
>>> int last_cpupid;
>>>
>>> do {
>>> - old_flags = flags = page->flags;
>>> + old_flags = flags = ACCESS_ONCE(page->flags);
>>> last_cpupid = page_cpupid_last(page);
>>>
>>> flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT);
>>
>>
>> I dont thing that this is actually a problem. The code below does
>>
>> } while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags))
>>
>> and the cmpxchg should be an atomic op that should already take care of everything
>> (page->flags is passed as a pointer).
>>
>
> Reading the code again, you might be right, but I think your patch description
> is somewhat misleading. I think the problem is that old_flags and flags are
> not necessarily the same.
>
> So what about
>
> a compiler could re-read "old_flags" from the memory location after reading
> and calculation "flags" and passes a newer value into the cmpxchg making
> the comparison succeed while it should actually fail.
>
Hi Christian,
I'll resend v2, thanks!
>
>
next prev parent reply other threads:[~2016-12-05 9:24 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-05 8:23 [RFC PATCH] mm: use ACCESS_ONCE in page_cpupid_xchg_last() Xishi Qiu
2016-12-05 8:23 ` Xishi Qiu
2016-12-05 8:31 ` Christian Borntraeger
2016-12-05 8:31 ` Christian Borntraeger
2016-12-05 8:50 ` Christian Borntraeger
2016-12-05 8:50 ` Christian Borntraeger
2016-12-05 9:22 ` Xishi Qiu [this message]
2016-12-05 9:22 ` Xishi Qiu
2016-12-05 9:26 ` [RFC PATCH v2] " Xishi Qiu
2016-12-05 9:26 ` Xishi Qiu
2016-12-05 9:44 ` Christian Borntraeger
2016-12-05 9:44 ` Christian Borntraeger
2016-12-06 1:53 ` [RFC PATCH v3] mm: use READ_ONCE " Xishi Qiu
2016-12-06 1:53 ` Xishi Qiu
2016-12-07 8:39 ` Vlastimil Babka
2016-12-07 8:39 ` Vlastimil Babka
2016-12-07 8:43 ` Michal Hocko
2016-12-07 8:43 ` Michal Hocko
2016-12-07 8:48 ` Vlastimil Babka
2016-12-07 8:48 ` Vlastimil Babka
2016-12-07 8:58 ` Michal Hocko
2016-12-07 8:58 ` Michal Hocko
2016-12-07 9:29 ` Vlastimil Babka
2016-12-07 9:29 ` Vlastimil Babka
2016-12-07 9:40 ` Christian Borntraeger
2016-12-07 9:40 ` Christian Borntraeger
2016-12-07 9:59 ` Michal Hocko
2016-12-07 9:59 ` Michal Hocko
2016-12-07 10:03 ` Christian Borntraeger
2016-12-07 10:03 ` Christian Borntraeger
2016-12-07 22:16 ` Rasmus Villemoes
2016-12-07 22:16 ` Rasmus Villemoes
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=584531CF.9030204@huawei.com \
--to=qiuxishi@huawei.com \
--cc=akpm@linux-foundation.org \
--cc=baiyaowei@cmss.chinamobile.com \
--cc=borntraeger@de.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@techsingularity.net \
--cc=xieyisheng1@huawei.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.