linux-kernel - Re: [PATCH] memcg: Fix data-race KCSAN bug in rstats

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date: Tue, 7 May 2024 09:03:00 -0700
From: Breno Leitao <leitao@...ian.org>
To: Michal Hocko <mhocko@...e.com>
Cc: Johannes Weiner <hannes@...xchg.org>,
	Roman Gushchin <roman.gushchin@...ux.dev>,
	Shakeel Butt <shakeel.butt@...ux.dev>,
	Muchun Song <muchun.song@...ux.dev>,
	Andrew Morton <akpm@...ux-foundation.org>, leit@...a.com,
	"open list:CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)" <cgroups@...r.kernel.org>,
	"open list:CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)" <linux-mm@...ck.org>,
	open list <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] memcg: Fix data-race KCSAN bug in rstats

Hello Michal,

On Fri, May 03, 2024 at 01:27:41PM +0200, Michal Hocko wrote:
> On Wed 24-04-24 05:59:39, Breno Leitao wrote:
> > The race occurs because two code paths access the same "stats_updates"
> > location. Although "stats_updates" is a per-CPU variable, it is remotely
> > accessed by another CPU at
> > cgroup_rstat_flush_locked()->mem_cgroup_css_rstat_flush(), leading to
> > the data race mentioned.
> 
> It is worth mentioning that the race is harmless.

Are you suggesting that the race consistently avoids producing corrupt
data, or even if corruption occurs, it's inconsequential because it only
affects statistics?

If there's no data corruption, does it incur any performance drawbacks?

Thanks!