From mboxrd@z Thu Jan  1 00:00:00 1970
From: "Zhang, Yanmin" <yanmin_zhang@linux.intel.com>
Subject: Re: KVM PMU virtualization
Date: Fri, 26 Feb 2010 10:55:17 +0800
Message-ID: <1267152917.1726.82.camel@localhost>
References: <4B86917C.4070102@redhat.com> <20100225173423.GB4246@8bytes.org>
Mime-Version: 1.0
Content-Type: text/plain; charset="ISO-8859-1"
Content-Transfer-Encoding: 7bit
Cc: Jes Sorensen <Jes.Sorensen@redhat.com>,
	KVM General <kvm@vger.kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Avi Kivity <avi@redhat.com>,
	Zachary Amsden <zamsden@redhat.com>,
	Gleb Natapov <gleb@redhat.com>, Ingo Molnar <mingo@elte.hu>,
	ming.m.lin@intel.com
To: Joerg Roedel <joro@8bytes.org>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mga12.intel.com ([143.182.124.36]:29207 "EHLO
	azsmga102.ch.intel.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org
	with ESMTP id S934984Ab0BZCw7 (ORCPT <rfc822;kvm@vger.kernel.org>);
	Thu, 25 Feb 2010 21:52:59 -0500
In-Reply-To: <20100225173423.GB4246@8bytes.org>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On Thu, 2010-02-25 at 18:34 +0100, Joerg Roedel wrote:
> On Thu, Feb 25, 2010 at 04:04:28PM +0100, Jes Sorensen wrote:
> 
> > 1) Add support to perf to allow it to monitor a KVM guest from the
> >    host.
> 
> This shouldn't be a big problem. The PMU of AMD Fam10 processors can be
> configured to count only when in guest mode. Perf needs to be aware of
> that and fetch the rip from a different place when monitoring a guest.
The idea is we want to measure both host and guest at the same time, and
compare all the hot functions fairly.


> 
> > 2) Allow guests access to the PMU (or an emulated PMU), making it
> >    possible to run perf on applications running within the guest.
> 
> The biggest problem I see here is teaching the guest about the available
> events. The available event sets are dependent on the processor family
> (at least on AMD).
> A simple approach would be shadowing the perf msrs which is a simple
> thing to do. More problematic is the reinjection of performance
> interrupts and performance nmis.
> 
> I personally don't like a self-defined event-set as the only solution
> because that would probably only work with linux and perf. I think we
> should have a way (additionally to a soft-event interface) which allows
> to expose the host pmu events to the guest.
> 
> 	Joerg
>