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 S932240AbdK1Tgg (ORCPT <rfc822;w@1wt.eu>);
        Tue, 28 Nov 2017 14:36:36 -0500
Received: from merlin.infradead.org ([205.233.59.134]:57698 "EHLO
        merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1752828AbdK1Tgc (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 28 Nov 2017 14:36:32 -0500
Date: Tue, 28 Nov 2017 20:36:23 +0100
From: Peter Zijlstra <peterz@infradead.org>
To: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@amacapital.net>, Ingo Molnar <mingo@kernel.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        "H . Peter Anvin" <hpa@zytor.com>, Borislav Petkov <bp@alien8.de>,
        Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [PATCH 15/24] x86/mm: Allow flushing for future ASID switches
Message-ID: <20171128193623.f4ify7yielg6fwn5@hirez.programming.kicks-ass.net>
References: <20171127104923.14378-1-mingo@kernel.org>
 <20171127104923.14378-16-mingo@kernel.org>
 <CALCETrUFfpDLEP78K9V4GsbHWS5=M6k8ndv0p+R0ud0=xxbaMg@mail.gmail.com>
 <20171128163908.e3gj6zgq6kcbdlxe@hirez.programming.kicks-ass.net>
 <1c9a32ed-e754-9d91-98f7-b72c07b2c0dc@linux.intel.com>
 <20171128190505.pqip2v2ewb3isjhd@hirez.programming.kicks-ass.net>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20171128190505.pqip2v2ewb3isjhd@hirez.programming.kicks-ass.net>
User-Agent: NeoMutt/20170609 (1.8.3)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Tue, Nov 28, 2017 at 08:05:05PM +0100, Peter Zijlstra wrote:
> I'm now staring at the RESTORE_CR3 stuff, and that appears to be called
> in the NMI handling where the stack is not to be used (if I read it
> right), so that's going to be a little more tricky.

As I just mentioned on IRC; I just realized that RESTORE_CR3 is always
flushing. So what I just wrote is effectively an optimization that
allows a nonflush.