From mboxrd@z Thu Jan  1 00:00:00 1970
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Subject: Re: Don't mount hardware performance counter using
	xenoprof
Date: Mon, 10 Jan 2011 12:22:01 -0500
Message-ID: <20110110172201.GA30164@dumpdata.com>
References: <AANLkTi=dtNkeRzeZT=-9kUCUEZpfGSKU-NQw28D6Mm0m@mail.gmail.com>
	<AANLkTinyjtACFR510800EsSuOtP13H+OGCJ9TSU5FGWC@mail.gmail.com>
	<20110110142646.GA5019@dumpdata.com>
	<AANLkTi=7BwPHrUGYnxHUUGWhZz0e9w0wdy-LH8RtDL=k@mail.gmail.com>
	<20110110152206.GB9732@dumpdata.com>
	<AANLkTikn=NokCwMAQjXN1r=j=ZnAWSCcGKNku44848Z0@mail.gmail.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Return-path: <xen-devel-bounces@lists.xensource.com>
Content-Disposition: inline
In-Reply-To: <AANLkTikn=NokCwMAQjXN1r=j=ZnAWSCcGKNku44848Z0@mail.gmail.com>
List-Unsubscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
List-Post: <mailto:xen-devel@lists.xensource.com>
List-Help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-Subscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
Sender: xen-devel-bounces@lists.xensource.com
Errors-To: xen-devel-bounces@lists.xensource.com
To: Yuto Nakai <yuto.k2c@gmail.com>
Cc: xen-devel@lists.xensource.com
List-Id: xen-devel@lists.xenproject.org

On Tue, Jan 11, 2011 at 12:34:58AM +0900, Yuto Nakai wrote:
> 2011/1/11 Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
> 
> > > > Do they exist when booting a baremetal kernel?
> > > >
> > > >
> > > Thank you for your response.
> > >
> > >
> > > Does booting a baremetal kernel means booting Dom0?
> >
> > No. Baremetal means booting the same kernel but without the Xen hypervisor.
> >
> 
> I understood.
> 
> They exist when booting a baremetal kernel.

Ok, then the answer is that nobody has looked in a long time (I think
since 2.6.18) to hook up the oprofile (or rather the code that
that gets invoked when a perf counter is triggered) to the Xen hypervisor.

It might make sense to look at how 2.6.18 did it (especially what were
the hypercalls and where) and see how to port it over to a pvops kernel.