From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:46283)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <edgar.iglesias@gmail.com>) id 1YlELl-0003qs-PF
	for qemu-devel@nongnu.org; Thu, 23 Apr 2015 06:27:18 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <edgar.iglesias@gmail.com>) id 1YlELk-0001zl-Uq
	for qemu-devel@nongnu.org; Thu, 23 Apr 2015 06:27:17 -0400
Received: from mail-ie0-x231.google.com ([2607:f8b0:4001:c03::231]:33368)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <edgar.iglesias@gmail.com>) id 1YlELk-0001zf-Pg
	for qemu-devel@nongnu.org; Thu, 23 Apr 2015 06:27:16 -0400
Received: by iecrt8 with SMTP id rt8so57301119iec.0
	for <qemu-devel@nongnu.org>; Thu, 23 Apr 2015 03:27:16 -0700 (PDT)
MIME-Version: 1.0
In-Reply-To: <CAFEAcA9rtsRi4o-xeGPSPdWogiyXCmRDgOLCdf8UbeSvC3HbOQ@mail.gmail.com>
References: <1429722561-12651-1-git-send-email-greg.bellows@linaro.org>
	<20150423033737.GD17116@toto>
	<CAFEAcA9rtsRi4o-xeGPSPdWogiyXCmRDgOLCdf8UbeSvC3HbOQ@mail.gmail.com>
Date: Thu, 23 Apr 2015 20:27:16 +1000
Message-ID: <CAJy5ezqWE2TFSgqYsM5piYw-sQC1jGnDM9Q_pBX2p8nr1DCAFA@mail.gmail.com>
From: "Edgar E. Iglesias" <edgar.iglesias@gmail.com>
Content-Type: multipart/alternative; boundary=001a11c2e33e4641c0051461b925
Subject: Re: [Qemu-devel] [PATCH v2 0/9] target-arm: EL3 trap support
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Peter Maydell <peter.maydell@linaro.org>
Cc: Sergey Fedorov <serge.fdrv@gmail.com>, =?UTF-8?B?QWxleCBCZW5uw6ll?= <alex.bennee@linaro.org>, QEMU Developers <qemu-devel@nongnu.org>, Greg Bellows <greg.bellows@linaro.org>

--001a11c2e33e4641c0051461b925
Content-Type: text/plain; charset=UTF-8

---
Sent from my phone
On 23/04/2015 8:10 pm, "Peter Maydell" <peter.maydell@linaro.org> wrote:
>
> On 23 April 2015 at 04:37, Edgar E. Iglesias <edgar.iglesias@gmail.com>
wrote:
> > I had a comment on the trapping of WFX, I recall not checking for
> > has_work was causing a lot of exception round-trips when running
> > XEN. To the point were things almost stopped working.
>
> For traps on WFE, or traps on WFI? If the former, we should
> probably implement that as "never trap" since we don't actually
> go into a 'low power state' for WFE (execution will always
> continue even if there's no pending WFE event).
>
> -- PMM

Hi,

I think it was for both, I can retest it to double check.

Our (xilinx) tree tracks wfe wakeups.

I agree that without tracking we better not trap..

When running emulated SMP with multiple nested SMP guests there are a lot
of these events fired. The exception code paths down to hypervisors involve
fairly long round trips.

Cheers,
Edgar

--001a11c2e33e4641c0051461b925
Content-Type: text/html; charset=UTF-8

<p dir="ltr"></p>
<p dir="ltr">---<br>
Sent from my phone<br>
On 23/04/2015 8:10 pm, &quot;Peter Maydell&quot; &lt;<a href="mailto:peter.maydell@linaro.org">peter.maydell@linaro.org</a>&gt; wrote:<br>
&gt;<br>
&gt; On 23 April 2015 at 04:37, Edgar E. Iglesias &lt;<a href="mailto:edgar.iglesias@gmail.com">edgar.iglesias@gmail.com</a>&gt; wrote:<br>
&gt; &gt; I had a comment on the trapping of WFX, I recall not checking for<br>
&gt; &gt; has_work was causing a lot of exception round-trips when running<br>
&gt; &gt; XEN. To the point were things almost stopped working.<br>
&gt;<br>
&gt; For traps on WFE, or traps on WFI? If the former, we should<br>
&gt; probably implement that as &quot;never trap&quot; since we don&#39;t actually<br>
&gt; go into a &#39;low power state&#39; for WFE (execution will always<br>
&gt; continue even if there&#39;s no pending WFE event).<br>
&gt;<br>
&gt; -- PMM</p>
<p dir="ltr">Hi,</p>
<p dir="ltr">I think it was for both, I can retest it to double check.</p>
<p dir="ltr">Our (xilinx) tree tracks wfe wakeups.</p>
<p dir="ltr">I agree that without tracking we better not trap..</p>
<p dir="ltr">When running emulated SMP with multiple nested SMP guests there are a lot of these events fired. The exception code paths down to hypervisors involve fairly long round trips.</p>
<p dir="ltr">Cheers,<br>
Edgar<br>
</p>

--001a11c2e33e4641c0051461b925--