From mboxrd@z Thu Jan  1 00:00:00 1970
From: Avi Kivity <avi@redhat.com>
Subject: Re: deactivate fpu when cr0.PE ON?
Date: Sat, 11 Apr 2009 14:43:19 +0300
Message-ID: <49E08257.9090503@redhat.com>
References: <9832F13BD22FB94A829F798DA4A8280501A4041722@pdsmsx503.ccr.corp.intel.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Cc: "kvm@vger.kernel.org" <kvm@vger.kernel.org>
To: "Dong, Eddie" <eddie.dong@intel.com>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx2.redhat.com ([66.187.237.31]:38039 "EHLO mx2.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1751587AbZDKLnl (ORCPT <rfc822;kvm@vger.kernel.org>);
	Sat, 11 Apr 2009 07:43:41 -0400
In-Reply-To: <9832F13BD22FB94A829F798DA4A8280501A4041722@pdsmsx503.ccr.corp.intel.com>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

Dong, Eddie wrote:
> 	Following code deactivate fpu when CR0.PE is on, any  explaination? Rest of code active/deactive fpu based on cr0.TS bit.
> 	
>
>   

The idea is, if the guest is doing a context switch, then it will likely 
set its own lazy fpu code, so we anticipate it and deactivate the cpu.

When cr0.pe is cleared, lazy fpu usually doesn't work so we leave it 
enabled.

However the mechanism of deactivating the fpu on cr3 write doesn't work 
with npt or ept, I'd like to replace it with something better.

-- 
Do not meddle in the internals of kernels, for they are subtle and quick to panic.