From mboxrd@z Thu Jan  1 00:00:00 1970
From: Gleb Natapov <gleb@redhat.com>
Subject: Re: KVM call minutes for Sept 21
Date: Mon, 27 Sep 2010 16:18:59 +0200
Message-ID: <20100927141859.GG11145@redhat.com>
References: <20100921180506.GI28009@x200.localdomain>
 <20100922000438.GA2844@fermat.math.technion.ac.il>
 <20100922090248.GD11145@redhat.com>
 <20100922162900.GA12492@fermat.math.technion.ac.il>
 <20100922174706.GA18005@redhat.com>
 <20100922192038.GK15338@8bytes.org>
 <4C9F52A1.1060306@redhat.com>
 <20100926202554.GN15338@8bytes.org>
 <4CA057A9.7030800@redhat.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: Joerg Roedel <joro@8bytes.org>,
	"Nadav Har'El" <nyh@math.technion.ac.il>,
	Chris Wright <chrisw@redhat.com>, kvm@vger.kernel.org
To: Avi Kivity <avi@redhat.com>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx1.redhat.com ([209.132.183.28]:50980 "EHLO mx1.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1756154Ab0I0OTI (ORCPT <rfc822;kvm@vger.kernel.org>);
	Mon, 27 Sep 2010 10:19:08 -0400
Content-Disposition: inline
In-Reply-To: <4CA057A9.7030800@redhat.com>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On Mon, Sep 27, 2010 at 10:36:57AM +0200, Avi Kivity wrote:
>  On 09/26/2010 10:25 PM, Joerg Roedel wrote:
> >>  btw, speaking of drastic changes to nsvm, one thing I'd like to see is
> >>  the replacement of those kmaps with something like put_user_try() and
> >>  put_user_catch().  It should be as fast (or faster) than kmaps, and not
> >>  affect preemptibility.
> >
> >Yes, I want to get rid of them too. I thought about using
> >copy_from/to_user in the vmrun/vmexit path. I need to measure if this
> >has any performance impact, though.
> 
> copy_to_user() is slow since it is very generic.  put_user()
> generally translates to one instruction (perhaps a range check as
> well).  We can avoid the range check if we do it once for the entire
> vmcb page.
> 
> Gleb had something along those lines, it's useful for kvmclock as well.
> 
Well, since you asked to make it generic it uses copy_to_user() now :)
It tracks slot version so gfn_to_hva() translation is omitted most of
the times.

--
			Gleb.