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 S1754044Ab3GKQnD (ORCPT <rfc822;w@1wt.eu>);
	Thu, 11 Jul 2013 12:43:03 -0400
Received: from merlin.infradead.org ([205.233.59.134]:48082 "EHLO
	merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1751477Ab3GKQnB (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Thu, 11 Jul 2013 12:43:01 -0400
Date: Thu, 11 Jul 2013 18:42:04 +0200
From: Peter Zijlstra <peterz@infradead.org>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: Sasha Levin <sasha.levin@oracle.com>, Dave Jones <davej@redhat.com>,
        Tejun Heo <tj@kernel.org>, tglx@linutronix.de,
        LKML <linux-kernel@vger.kernel.org>, trinity@vger.kernel.org
Subject: Re: timer: lockup in run_timer_softirq()
Message-ID: <20130711164204.GK25631@dyad.programming.kicks-ass.net>
References: <51DC902F.3070403@oracle.com>
 <20130709224706.GA13855@redhat.com>
 <51DC9379.9050408@oracle.com>
 <20130709230316.GB13855@redhat.com>
 <51DC983F.2010409@oracle.com>
 <20130710095210.GD17211@twins.programming.kicks-ass.net>
 <1373459254.7458.49.camel@gandalf.local.home>
 <20130710124245.GT25631@dyad.programming.kicks-ass.net>
 <1373461091.7458.55.camel@gandalf.local.home>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <1373461091.7458.55.camel@gandalf.local.home>
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 Wed, Jul 10, 2013 at 08:58:11AM -0400, Steven Rostedt wrote:
> On Wed, 2013-07-10 at 14:42 +0200, Peter Zijlstra wrote:
> 
> > but but but preempt_disable_notrace() isn't an rcu_read_lock().. You can only
> > do that for rcu_sched.
> 
> Right. And not even rcu_sched is safe, as function tracing can trace
> functions out of rcu scope. That's why I had to add that code to do a
> schedule_on_each_cpu() in ftrace.
> 
> > 
> > Anyway, I don't see a nice way out of this mess :/ the entire perf core uses
> > regular RCU and converting all that is going to me a nasty big patch.
> 
> There is an easier way. We can add a way to have perf not trace specific
> functions. Now there's already infrastructure there to pick and choose
> what to trace and what not to for individual function tracing users like
> perf. The trick will be how to annotate them.
> 
> If there's a way to mark a function without moving it to a section, this
> would be possible. Perhaps similar to EXPORT_SYMBOL(). We could add a
> PERF_NOTRACE().
> 
> static void __local_bh_enable()
> {
> 	[...]
> }
> PERF_NOTRACE(__local_bh_enable);
> 
> And add these to a black list of functions that perf should not trace.
> 
> How's that sound?

I'm afraid this is going to be hard to create and hard to keep correct :/

Other than that, a function tracer environment that is safer to use might be
useful for other people as well.