linux-kernel - Re: [PATCH] sched/numa: fix unsafe get_task_struct() in task_numa

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

Message-ID: <20141018211840.GA16931@redhat.com>
Date:	Sat, 18 Oct 2014 23:18:40 +0200
From:	Oleg Nesterov <oleg@...hat.com>
To:	Peter Zijlstra <peterz@...radead.org>
Cc:	Kirill Tkhai <tkhai@...dex.ru>,
	Kirill Tkhai <ktkhai@...allels.com>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	Ingo Molnar <mingo@...hat.com>,
	Vladimir Davydov <vdavydov@...allels.com>
Subject: Re: [PATCH] sched/numa: fix unsafe get_task_struct() in
	task_numa_assign()

On 10/18, Peter Zijlstra wrote:
>
> So you worry about the refcount doing 0->1 ? In which case the above is
> still wrong and we should be using atomic_inc_not_zero() in order to
> acquire the reference count.

It is actually worse, please see my reply to Kirill. We simply can't
dereference foreign_rq->curr lockless.

Again, task_struct is only protected by RCU if it was found on a RCU
protected list. rq->curr is not protected by rcu. Perhaps we have to
change this... but this will be a bit unfortunate.

Oleg.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/