Date: Thu, 17 Mar 2016 00:10:42 +0100
From: Peter Zijlstra <peterz@infradead.org>
To: Vince Weaver <vince@deater.net>
Cc: mingo@kernel.org, alexander.shishkin@linux.intel.com, eranian@google.com,
        linux-kernel@vger.kernel.org, dvyukov@google.com, andi@firstfloor.org,
        jolsa@redhat.com, panand@redhat.com, sasha.levin@oracle.com,
        oleg@redhat.com, Borislav Petkov <bp@alien8.de>
Subject: Re: [PATCH 00/12] perf: more fixes
Message-ID: <20160316231042.GT6375@twins.programming.kicks-ass.net>
References: <20160224174539.570749654@infradead.org>
 <20160310143924.GR6356@twins.programming.kicks-ass.net>
 <alpine.DEB.2.11.1603100943060.7775@pianoman.cluster.toy>
 <20160315153830.GA6356@twins.programming.kicks-ass.net>
 <20160316225933.GS6375@twins.programming.kicks-ass.net>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20160316225933.GS6375@twins.programming.kicks-ass.net>
User-Agent: Mutt/1.5.21 (2012-12-30)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1505
Lines: 37

On Wed, Mar 16, 2016 at 11:59:33PM +0100, Peter Zijlstra wrote:
> Subject: perf, ibs: Fix race with IBS_STARTING state
> From: Peter Zijlstra <peterz@infradead.org>
> Date: Wed Mar 16 23:55:21 CET 2016
> 
> While tracing the IBS bits I saw the NMI hitting between clearing
> IBS_STARTING and the actual MSR writes to disable the counter.
> 
> Since IBS_STARTING was cleared, the handler assumed these were spurious
> NMIs and because STOPPING wasn't set yet either, insta-triggered an
> "Unknown NMI".
> 
> Cure this by clearing IBS_STARTING after disabling the hardware.
> 
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> ---
>  arch/x86/events/amd/ibs.c |   32 +++++++++++++++++++++++++++++---
>  1 file changed, 29 insertions(+), 3 deletions(-)
> 
> --- a/arch/x86/events/amd/ibs.c
> +++ b/arch/x86/events/amd/ibs.c
> @@ -376,7 +376,13 @@ static void perf_ibs_start(struct perf_e
>  	hwc->state = 0;
>  
>  	perf_ibs_set_period(perf_ibs, hwc, &period);
> +	/*
> +	 * Set STARTED before enabling the hardware, such that
> +	 * a subsequent NMI must observe it. Then clear STOPPING
> +	 * such that we don't consume NMIs by accident.
> +	 */
>  	set_bit(IBS_STARTED, pcpu->state);
> +	clear_bit(IBS_STOPPING, pcpu->state);
>  	perf_ibs_enable_event(perf_ibs, hwc, period >> 4);

Also, all those atomic ops are probably entirely overkill and we could
use the non-atomic ops. This is all strictly cpu local. But I didn't
want to change too much at once, esp. while there's still problems.