From mboxrd@z Thu Jan  1 00:00:00 1970
From: Glauber Costa <glommer@parallels.com>
Subject: Re: [patch 13/18] KVM: x86: pass host_tsc to read_l1_tsc
Date: Mon, 29 Oct 2012 19:04:59 +0400
Message-ID: <508E9B1B.20902@parallels.com>
References: <20121024131340.742340256@redhat.com> <20121024131621.890469944@redhat.com>
Mime-Version: 1.0
Content-Type: text/plain; charset="ISO-8859-1"
Content-Transfer-Encoding: 7bit
Cc: <kvm@vger.kernel.org>, <johnstul@us.ibm.com>, <jeremy@goop.org>,
	<zamsden@gmail.com>, <gleb@redhat.com>, <avi@redhat.com>,
	<pbonzini@redhat.com>
To: Marcelo Tosatti <mtosatti@redhat.com>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx2.parallels.com ([64.131.90.16]:46939 "EHLO mx2.parallels.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1757442Ab2J2PFH (ORCPT <rfc822;kvm@vger.kernel.org>);
	Mon, 29 Oct 2012 11:05:07 -0400
In-Reply-To: <20121024131621.890469944@redhat.com>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On 10/24/2012 05:13 PM, Marcelo Tosatti wrote:
> Allow the caller to pass host tsc value to kvm_x86_ops->read_l1_tsc().
> 
> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Would you mind explaining why?

it seems to me that rdtscll() here would be perfectly safe: the only
case in which they wouldn't, is in a nested-vm environment running
paravirt-linux with a paravirt tsc. In this case, it is quite likely
that we'll want rdtscll *anyway*, instead of going to tsc directly.