From mboxrd@z Thu Jan  1 00:00:00 1970
From: Wang Hui <john.whui1985@gmail.com>
Subject: Re: [PATCH] KVM/X86: vpmu migration, make perf_event associated with
 vcpu thread
Date: Sat, 30 Nov 2013 19:47:53 +0800
Message-ID: <5299D069.3090108@gmail.com>
References: <5298D5FC.8030709@gmail.com> <5299C741.40609@redhat.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Cc: Gleb Natapov <gleb@redhat.com>, kvm <kvm@vger.kernel.org>
To: Paolo Bonzini <pbonzini@redhat.com>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mail-pd0-f195.google.com ([209.85.192.195]:35851 "EHLO
	mail-pd0-f195.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1751249Ab3K3LsD (ORCPT <rfc822;kvm@vger.kernel.org>);
	Sat, 30 Nov 2013 06:48:03 -0500
Received: by mail-pd0-f195.google.com with SMTP id v10so4808445pde.10
        for <kvm@vger.kernel.org>; Sat, 30 Nov 2013 03:48:02 -0800 (PST)
In-Reply-To: <5299C741.40609@redhat.com>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On 2013/11/30 19:08, Paolo Bonzini wrote:
> Il 29/11/2013 18:59, Wang Hui ha scritto:
>> But when I wrote a test module to make IA32_PMC1 to count the event of unhalted
>> cpu-cycles, after migration the value of IA32_PMC1 never grows up again. I found
>> that after migration perf_event was created exactly, but when it was created,
>> "current" is qemu's main thread which won't enter no-root mode, so the count of
>> perf_event will never increase.
> 
> I think the fix is to apply the MSRs in QEMU's VCPU thread, through
> run_on_cpu.  Interesting that I could not reproduce this when testing my
> patches.
> 
> Paolo
> 
Thank you for your advice, Paolo. I will try run_on_cpu.

And my qemu version was 1.5.1, maybe it is too old. I will try the latest version.

Thanks
Wang Hui