[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20111107162207.GK8670@redhat.com>
Date: Mon, 7 Nov 2011 18:22:07 +0200
From: Gleb Natapov <gleb@...hat.com>
To: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Cc: kvm@...r.kernel.org, avi@...hat.com, mtosatti@...hat.com,
linux-kernel@...r.kernel.org, mingo@...e.hu,
acme@...stprotocols.net
Subject: Re: [PATCHv2 6/9] perf: expose perf capability to other modules.
On Mon, Nov 07, 2011 at 05:01:11PM +0100, Peter Zijlstra wrote:
> On Mon, 2011-11-07 at 17:53 +0200, Gleb Natapov wrote:
> > I removed branch-miss-retired here because for perf user it exists. Perf
> > approximates it by other event but perf user shouldn't know that. A
> > guest is not always runs with exactly same cpu model number as a host,
> > so if we will not drop the bit here if guest will see cpu model other
> > than the one that has this quirk it will not be able to use the event.
>
> Right, so what model number do you expose? Anyway I don't really mind
Depends on what management wants. You can specify -cpu Nehalem or -cpu
Conroe or even override model manually by doing -cpu host,model=15.
> masking the thing as long as we grow an ebx iteration,
>
> > BTW why perf does not check event mask to see if architectural event is
> > available before programming it?
>
> No idea why not.. just one of those things nobody noticed/got around to
> doing or so.
--
Gleb.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists