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 S934022AbcLPIxc (ORCPT <rfc822;w@1wt.eu>);
        Fri, 16 Dec 2016 03:53:32 -0500
Received: from Galois.linutronix.de ([146.0.238.70]:48875 "EHLO
        Galois.linutronix.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1759627AbcLPIwy (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Fri, 16 Dec 2016 03:52:54 -0500
Date: Fri, 16 Dec 2016 09:50:04 +0100 (CET)
From: Thomas Gleixner <tglx@linutronix.de>
To: Andy Lutomirski <luto@amacapital.net>
cc: LKML <linux-kernel@vger.kernel.org>, X86 ML <x86@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>, Kyle Huey <khuey@kylehuey.com>,
        Andy Lutomirski <luto@kernel.org>
Subject: Re: [patch 3/3] x86/process: Optimize TIF_NOTSC switch
In-Reply-To: <CALCETrUbzDAfjnLqsFpAdOkx9qK0ircasXXqUzQ4ON-oq31fRg@mail.gmail.com>
Message-ID: <alpine.DEB.2.20.1612160947410.3470@nanos>
References: <20161215162648.061449202@linutronix.de> <20161215164240.904945084@linutronix.de> <CALCETrUbzDAfjnLqsFpAdOkx9qK0ircasXXqUzQ4ON-oq31fRg@mail.gmail.com>
User-Agent: Alpine 2.20 (DEB 67 2015-01-07)
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Thu, 15 Dec 2016, Andy Lutomirski wrote:
> On Thu, Dec 15, 2016 at 8:44 AM, Thomas Gleixner <tglx@linutronix.de> wrote:
> > +static inline void cr4_toggle_bits(unsigned long mask)
> > +{
> > +       unsigned long cr4;
> > +
> > +       cr4 = this_cpu_read(cpu_tlbstate.cr4);
> > +       cr4 ^= mask;
> > +       this_cpu_write(cpu_tlbstate.cr4, cr4);
> > +       __write_cr4(cr4);
> > +}
> 
> This scares me for the same reason as BTF, although this should at
> least be less fragile.  But how about:

If that is fragile then all cr4 manipulation code is fragile because it
relies on cpu_tlbstate.cr4. The TIF flag and that per cpu thing are kept in
sync.

Thanks,

	tglx