From mboxrd@z Thu Jan  1 00:00:00 1970
From: Paolo Bonzini <pbonzini@redhat.com>
Subject: Re: Seeking a KVM benchmark
Date: Mon, 17 Nov 2014 12:18:12 +0100
Message-ID: <5469D974.4030008@redhat.com>
References: <CALCETrUHYGnjraS2Jn-eGtbbS2osbtZVJ2SKfQKtWXTgOOxbtw@mail.gmail.com> <545C7222.4070605@redhat.com> <CALCETrWmJkDE9Mqho21mtohtnGFxc-EWHZ_n8N5jcPWv2Oqnbg@mail.gmail.com> <20141108120125.GB2654@minantech.com> <CALCETrUHpAomRqrTN1KbgHdOhNcwip3v0+67CjiqVF5PaR8nuQ@mail.gmail.com> <CALCETrWhT4zp7Br2DV-9BmrJSY0xWTJ_9ybM_cWiCiOitCyvCg@mail.gmail.com> <20141109085238.GA26187@minantech.com> <CALCETrXG4WvJWfjsnH7AmXHDKjt+kmiQqvG4X2VZz+g_fARTLA@mail.gmail.com> <54608D77.2090907@redhat.com> <20141110104531.GB26187@minantech.com> <5460AC7C.8040409@redhat.com> <5460CA71.2050701@gmail.com> <5460F5B9.8030902@redhat.com> <5469D934.4080405@gmail.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=windows-1252
Content-Transfer-Encoding: 7bit
Cc: Andy Lutomirski <luto@amacapital.net>,
	kvm list <kvm@vger.kernel.org>
To: Wanpeng Li <kernellwp@gmail.com>,
	Avi Kivity <avi.kivity@gmail.com>,
	Gleb Natapov <gleb@kernel.org>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx1.redhat.com ([209.132.183.28]:53520 "EHLO mx1.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1752353AbaKQLSV (ORCPT <rfc822;kvm@vger.kernel.org>);
	Mon, 17 Nov 2014 06:18:21 -0500
In-Reply-To: <5469D934.4080405@gmail.com>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>



On 17/11/2014 12:17, Wanpeng Li wrote:
>>
>>> It's not surprising [1].  Since the meaning of some PTE bits change [2],
>>> the TLB has to be flushed.  In VMX we have VPIDs, so we only need to flush
>>> if EFER changed between two invocations of the same VPID, which isn't
>>> the case.
> 
> If there need a TLB flush if guest is UP?

The wrmsr is in the host, and the TLB flush is done in the processor
microcode.

Paolo