From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:48545)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <benh@kernel.crashing.org>) id 1bhOIV-0000f3-90
	for qemu-devel@nongnu.org; Tue, 06 Sep 2016 17:52:53 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <benh@kernel.crashing.org>) id 1bhOIR-00046I-7h
	for qemu-devel@nongnu.org; Tue, 06 Sep 2016 17:52:50 -0400
Message-ID: <1473198749.8689.43.camel@kernel.crashing.org>
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Wed, 07 Sep 2016 07:52:29 +1000
In-Reply-To: <762703d0-bb32-8b9f-a538-5541890c9781@redhat.com>
References: <1473133253-17598-1-git-send-email-david@gibson.dropbear.id.au>
	<CAFEAcA9bgaD2JNNh4qXYF=OuuV8iTbY-Y2eSiR7H8ZLn=W8O_g@mail.gmail.com>
	<762703d0-bb32-8b9f-a538-5541890c9781@redhat.com>
Content-Type: text/plain; charset="UTF-8"
Mime-Version: 1.0
Content-Transfer-Encoding: quoted-printable
Subject: Re: [Qemu-devel] [PULL 00/66] ppc-for-2.8 queue 20160906
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: Thomas Huth <thuth@redhat.com>, Peter Maydell <peter.maydell@linaro.org>, David Gibson <david@gibson.dropbear.id.au>
Cc: peter.maydell@linearo.org, "qemu-ppc@nongnu.org" <qemu-ppc@nongnu.org>, Alexander Graf <agraf@suse.de>, QEMU Developers <qemu-devel@nongnu.org>

On Tue, 2016-09-06 at 23:09 +0200, Thomas Huth wrote:
> The bad commit is: "ppc: Speed up load/store multiple"
>=20
> There are two "#if defined(HOST_WORDS_BIGENDIAN)" sections in this patc=
h
> which are both bad: The memcpy tries to copy 32-bit values into 64-bit
> registers, which of course does not work (unless you compile this code
> for a 32-bit host only where the size of a gpr is only 32-bit).

The instruction does that. It only copies 32-bits. I think it's
correct.=C2=A0=09

> I'd suggest to remove the "#if defined(HOST_WORDS_BIGENDIAN)" part and
> use cpu_to_be32() and friends instead of the bswap32() here?

I tried that but it prevents the faster memcpy, the whole point was to
speed things up...

Cheers,
Ben.