From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([208.118.235.92]:58345)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <benh@kernel.crashing.org>) id 1SWbcO-00079k-FR
	for qemu-devel@nongnu.org; Mon, 21 May 2012 19:02:25 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <benh@kernel.crashing.org>) id 1SWbcM-0000VZ-Ro
	for qemu-devel@nongnu.org; Mon, 21 May 2012 19:02:24 -0400
Received: from gate.crashing.org ([63.228.1.57]:54306)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <benh@kernel.crashing.org>) id 1SWbcM-0000VH-J7
	for qemu-devel@nongnu.org; Mon, 21 May 2012 19:02:22 -0400
Message-ID: <1337641331.2779.128.camel@pasglop>
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 22 May 2012 09:02:11 +1000
In-Reply-To: <20120521224436.GL17031@redhat.com>
References: <4FB60EFF.6070205@redhat.com> <1337379992.2513.17.camel@pasglop>
	<4FB74AB0.7090608@redhat.com> <1337549768.2458.0.camel@pasglop>
	<1337565405.2458.12.camel@pasglop> <4FB9F89A.90702@redhat.com>
	<20120521083132.GI4674@redhat.com> <4FBABF2D.2020200@codemonkey.ws>
	<1337639166.2779.117.camel@pasglop> <4FBAC22A.5010708@codemonkey.ws>
	<20120521224436.GL17031@redhat.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: 7bit
Mime-Version: 1.0
Subject: Re: [Qemu-devel] [PATCH] Add a memory barrier to guest memory
	access functions
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: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>, qemu-devel@nongnu.org, Anthony Liguori <anthony@codemonkey.ws>, David Gibson <david@gibson.dropbear.id.au>

On Tue, 2012-05-22 at 01:44 +0300, Michael S. Tsirkin wrote:
> 
> OK. Just not another level of indirect function callbacks please.  Make
> it a library so each bus can do the right thing.  There are not so many
> buses. 

I think we are a long way from having to deal with subtly different
ordering rules, at this stage I'm keen on just sticking it in the inline
dma_ accessor, period.

We can always have flags in the dma context to indicate the sort of
ordering, avoids indirect pointer calls which can be costly (often
mispredicted).

Ben.