[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20161207084305.GA20350@dhcp22.suse.cz>
Date: Wed, 7 Dec 2016 09:43:05 +0100
From: Michal Hocko <mhocko@...nel.org>
To: Xishi Qiu <qiuxishi@...wei.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>,
Mel Gorman <mgorman@...hsingularity.net>,
Yaowei Bai <baiyaowei@...s.chinamobile.com>,
Christian Borntraeger <borntraeger@...ibm.com>,
Linux MM <linux-mm@...ck.org>,
LKML <linux-kernel@...r.kernel.org>,
Yisheng Xie <xieyisheng1@...wei.com>
Subject: Re: [RFC PATCH v3] mm: use READ_ONCE in page_cpupid_xchg_last()
On Tue 06-12-16 09:53:14, Xishi Qiu wrote:
> 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.
>
> Signed-off-by: Xishi Qiu <qiuxishi@...wei.com>
> Suggested-by: Christian Borntraeger <borntraeger@...ibm.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 = READ_ONCE(page->flags);
> last_cpupid = page_cpupid_last(page);
what prevents compiler from doing?
old_flags = READ_ONCE(page->flags);
flags = READ_ONCE(page->flags);
Or this doesn't matter?
>
> flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT);
> --
> 1.8.3.1
>
--
Michal Hocko
SUSE Labs
Powered by blists - more mailing lists