From mboxrd@z Thu Jan  1 00:00:00 1970
From: Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
Subject: Re: remove redundant VM Exit for non-aligned guest pte
 write or part of pte write.
Date: Sun, 06 Jan 2008 10:50:56 +0200
Message-ID: <47809670.9090706@qumranet.com>
References: <10EA09EFD8728347A513008B6B0DA77A028A6DB2@pdsmsx411.ccr.corp.intel.com>	<476A3436.1000900@qumranet.com>
	<10EA09EFD8728347A513008B6B0DA77A029B5503@pdsmsx411.ccr.corp.intel.com>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Cc: kvm-devel <kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org>
To: "Dong, Eddie" <eddie.dong-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Return-path: <kvm-devel-bounces-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org>
In-Reply-To: <10EA09EFD8728347A513008B6B0DA77A029B5503-wq7ZOvIWXbNpB2pF5aRoyrfspsVTdybXVpNB7YpNyf8@public.gmane.org>
List-Unsubscribe: <https://lists.sourceforge.net/lists/listinfo/kvm-devel>,
	<mailto:kvm-devel-request-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org?subject=unsubscribe>
List-Archive: <http://sourceforge.net/mailarchive/forum.php?forum_name=kvm-devel>
List-Post: <mailto:kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org>
List-Help: <mailto:kvm-devel-request-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org?subject=help>
List-Subscribe: <https://lists.sourceforge.net/lists/listinfo/kvm-devel>,
	<mailto:kvm-devel-request-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org?subject=subscribe>
Sender: kvm-devel-bounces-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org
Errors-To: kvm-devel-bounces-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org
List-Id: kvm.vger.kernel.org

Dong, Eddie wrote:
> Avi Kivity wrote:
>   
>> Dong, Eddie wrote:
>>     
>>> I observed 1-2 seconds faster in Windows XPSP2 ACPI bootup with
>>> total of 23 seconds.
>>> I can;t say it is exactly caused by this patch, but anyway it
>>> simplifies the logic and code w/o any additional complexity.
>>> thx,eddie 
>>>
>>>
>>>
>>>       
>> Patch looks good, but will delay so that the guest scaling patch can
>> be merged.  kvm_read_guest() will need to change to
>> kvm_read_guest_inatomic(), since the mmu is becoming spinlocked.  
>>     
>
> Rebased.
> Thx, eddie
>
> A guest non-aligned pte write or part of pte
> update will leave shadow_trap_nonpresent_pte
> in spte, which expects a new VM Exit at next
> access time.
>
> This patch fixed this by reading guest pte
> in advance and thus be able to update spte
> and reduce next VM Exit.
>
>   

Wrong patch attached...

-- 
error compiling committee.c: too many arguments to function


-------------------------------------------------------------------------
This SF.net email is sponsored by: Microsoft
Defy all challenges. Microsoft(R) Visual Studio 2005.
http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/