From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1753413AbbJSJMa (ORCPT <rfc822;w@1wt.eu>);
	Mon, 19 Oct 2015 05:12:30 -0400
Received: from casper.infradead.org ([85.118.1.10]:50770 "EHLO
	casper.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1751103AbbJSJM2 (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Mon, 19 Oct 2015 05:12:28 -0400
Date: Mon, 19 Oct 2015 11:12:25 +0200
From: Peter Zijlstra <peterz@infradead.org>
To: Stephane Eranian <eranian@google.com>
Cc: LKML <linux-kernel@vger.kernel.org>, "mingo@elte.hu" <mingo@elte.hu>,
        "ak@linux.intel.com" <ak@linux.intel.com>,
        Eric Dumazet <edumazet@google.com>,
        Arnaldo Carvalho de Melo <acme@redhat.com>
Subject: Re: [PATCH] perf/core: fix RCU issues with cgroup monitoring mode
Message-ID: <20151019091225.GH3816@twins.programming.kicks-ass.net>
References: <20151017012811.GA18581@thinkpad>
 <20151017095651.GE3816@twins.programming.kicks-ass.net>
 <CABPqkBS88_p7DZwVPKgEz0HSqth5zzhFjpRzeF8O9HhYByEJmg@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CABPqkBS88_p7DZwVPKgEz0HSqth5zzhFjpRzeF8O9HhYByEJmg@mail.gmail.com>
User-Agent: Mutt/1.5.21 (2012-12-30)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Mon, Oct 19, 2015 at 12:58:47AM -0700, Stephane Eranian wrote:
> Peter,
> 
> On Sat, Oct 17, 2015 at 2:56 AM, Peter Zijlstra <peterz@infradead.org> wrote:
> >
> > On Sat, Oct 17, 2015 at 03:28:11AM +0200, Stephane Eranian wrote:
> > >
> > > This patch eliminates all known RCU violations detected
> > > by the RCU  checker (PROVE_RCU). The impact code paths
> > > were all related to cgroup mode monitoring and involved
> > > access a task's cgrp.
> >
> > But were they right? This patch provides no clues.
> >
> I am assuming that is the checker detects something suspicious there is likely
> a problem.
> 
> Take for instance:
>  perf_cgroup_sched_out()->perf_cgroup_from_task() ->task_subsys_state()
> 
> That one fires the checker. I think because we are accessing the css
> state without
> protection.
> 
> The other places are similar.

But perf_cgroup_attach()->perf_cgroup_switch() takes ctx->lock().

Therefore; if you hold ctx->lock, the cgroup is pinned.

And the above sequence very much holds ctx->lock.

Right?

So it looks to me that we should teach perf_cgroup_from_task() about
ctx->lock or something.