From mboxrd@z Thu Jan  1 00:00:00 1970
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1757323AbeAINLM (ORCPT <rfc822;ralf@linux-mips.org> + 1 other);
        Tue, 9 Jan 2018 08:11:12 -0500
Received: from bombadil.infradead.org ([65.50.211.133]:33089 "EHLO
        bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1757155AbeAINLJ (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 9 Jan 2018 08:11:09 -0500
Date: Tue, 9 Jan 2018 14:10:59 +0100
From: Peter Zijlstra <peterz@infradead.org>
To: David Woodhouse <dwmw2@infradead.org>
Cc: Andy Lutomirski <luto@amacapital.net>,
        Andrew Cooper <andrew.cooper3@citrix.com>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Andi Kleen <ak@linux.intel.com>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "tim.c.chen@linux.intel.com" <tim.c.chen@linux.intel.com>,
        "tglx@linutronix.de" <tglx@linutronix.de>,
        "riel@redhat.com" <riel@redhat.com>,
        "keescook@google.com" <keescook@google.com>,
        "gnomes@lxorguk.ukuu.org.uk" <gnomes@lxorguk.ukuu.org.uk>,
        "pjt@google.com" <pjt@google.com>,
        "dave.hansen@intel.com" <dave.hansen@intel.com>,
        "jikos@kernel.org" <jikos@kernel.org>,
        "gregkh@linux-foundation.org" <gregkh@linux-foundation.org>
Subject: Re: [PATCH v6 11/10] x86/retpoline: Avoid return buffer underflows
 on context switch
Message-ID: <20180109131059.GI6176@hirez.programming.kicks-ass.net>
References: <1515363085-4219-1-git-send-email-dwmw@amazon.co.uk>
 <1515455051.15588.7.camel@infradead.org>
 <CA+55aFwJLjNTDXBo-OkBhJ7ddrY+30MZY_HiY6TAc_tJNaL9-A@mail.gmail.com>
 <1515455902.4423.59.camel@amazon.co.uk>
 <CA+55aFztN+nGBnb1Wjvygvgkg2MfN9m88egsostaNJ5LoSQx7A@mail.gmail.com>
 <20180109004415.GG6718@tassilo.jf.intel.com>
 <CA+55aFy3sCY5xUwZtOYL1MLhRwYe1sU=5d8sWPZqAnEZ71u8-w@mail.gmail.com>
 <3aadb8a0-08c8-bdf9-7b91-0fa774a9e1ab@citrix.com>
 <FC895787-D674-4BC5-B660-DD946EA9825A@amacapital.net>
 <1515503060.22302.19.camel@infradead.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <1515503060.22302.19.camel@infradead.org>
User-Agent: Mutt/1.9.2 (2017-12-15)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
Return-Path: <linux-kernel-owner@vger.kernel.org>

On Tue, Jan 09, 2018 at 01:04:20PM +0000, David Woodhouse wrote:
> On Mon, 2018-01-08 at 19:27 -0800, Andy Lutomirski wrote:
> > > 
> > > If SMEP is not active, speculation can go anywhere, including to a user
> > > controlled gadget which can reload any registers it needs, including
> > > with immediate constants.
> > 
> > I thought that, even on pre-SMEP hardware, the CPU wouldn't
> > speculatively execute from NX pages.  And PTI marks user memory NX
> > in kernel mode.
> 
> Hm, now that could be useful. 
> 
> Do *all* the KPTI backports (some of which are reimplementations rather
> than strictly backports) mark user memory NX?

That doesn't really matter for upstream though; but see here:

  https://lkml.kernel.org/r/1515502580-12261-5-git-send-email-w@1wt.eu