Date: Tue, 9 Jan 2018 16:12:53 +0100
From: Peter Zijlstra <peterz@infradead.org>
To: Vince Weaver <vincent.weaver@maine.edu>
Cc: Ingo Molnar <mingo@kernel.org>, linux-kernel@vger.kernel.org,
        Ingo Molnar <mingo@redhat.com>,
        Arnaldo Carvalho de Melo <acme@kernel.org>,
        Thomas Gleixner <tglx@linutronix.de>
Subject: Re: perf: perf_fuzzer quickly locks up on 4.15-rc7
Message-ID: <20180109151253.GK6176@hirez.programming.kicks-ass.net>
References: <alpine.DEB.2.21.1801081105570.319@macbook-air>
 <20180108173005.lkglqrixb2ota6g2@gmail.com>
 <alpine.DEB.2.21.1801081528110.14364@macbook-air>
 <20180109102507.GG6176@hirez.programming.kicks-ass.net>
 <20180109132602.GA2369@hirez.programming.kicks-ass.net>
 <alpine.DEB.2.21.1801090841300.15884@macbook-air>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <alpine.DEB.2.21.1801090841300.15884@macbook-air>
User-Agent: Mutt/1.9.2 (2017-12-15)
Sender: linux-kernel-owner@vger.kernel.org

On Tue, Jan 09, 2018 at 08:44:23AM -0500, Vince Weaver wrote:
> On Tue, 9 Jan 2018, Peter Zijlstra wrote:
> 
> > So remind me again, how are you running that fuzzer? I'm running
> > ./fast_repro99.sh as root.
> 
> I'm running ./fast_repro98.sh on a regular haswell machine with paranoid 
> set to "0".
> 
> I'll try your patch and see if it makes a difference.

I suspect not, it shouldn't be PTI specific.

> I can also try on a few other machines.  I started setting up a fuzzing 
> cluster for this kind of thing but the multiport serial card I got for 
> logging the serial consoles crashes fairly quickly under load and I 
> haven't had time to track that down.

So I don't think HSW has PT, which is something I cannot test on my IVB.
OTOH HSW has PEBS real_ip, but that uses _less_ magic.

In any case, I found yet another lockdep splat, trying to figure out wth
to do about that. Will then continue running with fast_repro98.