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 S1754673AbbBBSL0 (ORCPT <rfc822;w@1wt.eu>);
	Mon, 2 Feb 2015 13:11:26 -0500
Received: from mga14.intel.com ([192.55.52.115]:57516 "EHLO mga14.intel.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S932133AbbBBSLZ (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Mon, 2 Feb 2015 13:11:25 -0500
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="5.09,507,1418112000"; 
   d="scan'208";a="679801163"
Message-ID: <54CFBDCB.9070005@linux.intel.com>
Date: Mon, 02 Feb 2015 10:11:23 -0800
From: Dave Hansen <dave.hansen@linux.intel.com>
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.3.0
MIME-Version: 1.0
To: Rik van Riel <riel@redhat.com>, Oleg Nesterov <oleg@redhat.com>
CC: Suresh Siddha <sbsiddha@gmail.com>, Andy Lutomirski <luto@amacapital.net>,
        Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@redhat.com>,
        "H. Peter Anvin" <hpa@zytor.com>, Fenghua Yu <fenghua.yu@intel.com>,
        the arch/x86 maintainers <x86@kernel.org>,
        linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 0/3]: x86, fpu: unlazy_fpu fixes/cleanups
References: <54C2A245.4010307@redhat.com> <20150129210723.GA31584@redhat.com> <54CAA357.1070108@linux.intel.com> <20150129213346.GA32511@redhat.com> <54CAA973.4050401@linux.intel.com> <20150129215638.GB1045@redhat.com> <54CAC190.30905@linux.intel.com> <54CADF72.5070507@redhat.com>
In-Reply-To: <54CADF72.5070507@redhat.com>
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On 01/29/2015 05:33 PM, Rik van Riel wrote:
>> > Hmm, if the the thread was not using the FPU, and this fails to
>> > save anything in to the xsave_buf, what will bndcsr point to?
> If the thread was not using the FPU, can we reach the
> bound range exception?
> 
> I believe the MPX feature uses information in the xstate.

There are really two kinds of bounds exceptions.  There is an "old"
'BOUND' instruction that will generate #BR's as well as the new MPX
instructions.  The new ones require xstate and poking the FPU, etc...
The old one did not.

So, we _can_ as far as I know get in to do_bounds() without using the FPU.