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 S1754692AbcKUOhm (ORCPT <rfc822;w@1wt.eu>);
        Mon, 21 Nov 2016 09:37:42 -0500
Received: from bombadil.infradead.org ([198.137.202.9]:51172 "EHLO
        bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1753928AbcKUOhl (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Mon, 21 Nov 2016 09:37:41 -0500
Date: Mon, 21 Nov 2016 15:37:16 +0100
From: Peter Zijlstra <peterz@infradead.org>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: Jiri Olsa <jolsa@redhat.com>,
        "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
        linux-kernel@vger.kernel.org, Ingo Molnar <mingo@kernel.org>,
        Josh Triplett <josh@joshtriplett.org>,
        Andi Kleen <andi@firstfloor.org>, Jan Stancek <jstancek@redhat.com>,
        Borislav Petkov <bp@alien8.de>
Subject: Re: [BUG] msr-trace.h:42 suspicious rcu_dereference_check() usage!
Message-ID: <20161121143716.GG3092@twins.programming.kicks-ass.net>
References: <20161121005343.GB1891@krava>
 <20161121092850.GF3102@twins.programming.kicks-ass.net>
 <20161121093424.GA9814@krava>
 <20161121125830.GE3092@twins.programming.kicks-ass.net>
 <20161121091543.45f49945@gandalf.local.home>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20161121091543.45f49945@gandalf.local.home>
User-Agent: Mutt/1.5.23.1 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Mon, Nov 21, 2016 at 09:15:43AM -0500, Steven Rostedt wrote:
> On Mon, 21 Nov 2016 13:58:30 +0100
> Peter Zijlstra <peterz@infradead.org> wrote:
> 
> > On Mon, Nov 21, 2016 at 10:34:25AM +0100, Jiri Olsa wrote:
> > 
> > > > diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
> > > > index 0888a879120f..d6c6aa80675f 100644
> > > > --- a/arch/x86/kernel/process.c
> > > > +++ b/arch/x86/kernel/process.c
> > > > @@ -357,7 +357,7 @@ static void amd_e400_idle(void)
> > > >  	if (!amd_e400_c1e_detected) {
> > > >  		u32 lo, hi;
> > > >  
> > > > -		rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
> > > > +		RCU_NONIDLE(rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi));
> > > >  
> > > >  		if (lo & K8_INTP_C1E_ACTIVE_MASK) {
> > > >  			amd_e400_c1e_detected = true;  
> > 
> > OK, so while looking at this again, I don't like this ether :/
> > 
> > Problem with this one is that it always adds the RCU fiddling overhead,
> > even when we're not tracing.
> > 
> > I could do an rdmsr_notrace() for this one, dunno if its important.
> 
> But that would neglect the point of tracing rdmsr. What about:
> 
> 	/* tracepoints require RCU enabled */
> 	if (trace_read_msr_enabled())
> 		RCU_NONIDLE(rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi));
> 	else
> 		rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);

Yeah, but this one does a printk() when it hits the contidion it checks
for, so not tracing it would be fine I think.

Also, Boris, why do we need to redo that rdmsr until we see that bit
set? Can't we simply do the rdmsr once and then be done with it?