linux-kernel - Re: [PATCH] mm:memcg: add __GFP_NOWARN in __memcg_schedule_kmem_cache

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 for Android: free password hash cracker in your pocket

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

Date:   Wed, 18 Apr 2018 09:54:37 +0200
From:   Michal Hocko <mhocko@...nel.org>
To:     Minchan Kim <minchan@...nel.org>
Cc:     Andrew Morton <akpm@...ux-foundation.org>,
        LKML <linux-kernel@...r.kernel.org>,
        linux-mm <linux-mm@...ck.org>,
        Johannes Weiner <hannes@...xchg.org>,
        Vladimir Davydov <vdavydov.dev@...il.com>
Subject: Re: [PATCH] mm:memcg: add __GFP_NOWARN in
 __memcg_schedule_kmem_cache_create

On Wed 18-04-18 16:41:17, Minchan Kim wrote:
> On Wed, Apr 18, 2018 at 09:20:02AM +0200, Michal Hocko wrote:
> > On Wed 18-04-18 11:29:12, Minchan Kim wrote:
[...]
> > > Let's not make user scared.
> > 
> > This is not a proper explanation. So what exactly happens when this
> > allocation fails? I would suggest something like the following
> > "
> > __memcg_schedule_kmem_cache_create tries to create a shadow slab cache
> > and the worker allocation failure is not really critical because we will
> > retry on the next kmem charge. We might miss some charges but that
> > shouldn't be critical. The excessive allocation failure report is not
> > very much helpful. Replace it with a rate limited single line output so
> > that we know that there is a lot of these failures and that we need to
> > do something about it in future.
> > "
> > 
> > With the last part to be implemented of course.
> 
> If you want to see warning and catch on it in future, I don't see any reason
> to change it. Because I didn't see any excessive warning output that it could
> make system slow unless we did ratelimiting.

Yeah, but a single line would be as much informative and less scary to
users.

> It was a just report from non-MM guys who have a concern that somethings
> might go wrong on the system. I just wanted them relax since it's not
> critical.

I do agree with __GFP_NOWARN but I think a single line warning is due
and helpful for further debugging.

-- 
Michal Hocko
SUSE Labs