From mboxrd@z Thu Jan  1 00:00:00 1970
From: Paul Brook <paul@codesourcery.com>
Subject: Re: [RFC PATCH 4/7] ide: IOMMU support
Date: Wed, 14 Jul 2010 14:53:03 +0100
Message-ID: <201007141453.06131.paul@codesourcery.com>
References: <1279086307-9596-1-git-send-email-eduard.munteanu@linux360.ro> <1279086307-9596-5-git-send-email-eduard.munteanu@linux360.ro>
Mime-Version: 1.0
Content-Type: Text/Plain;
  charset="iso-8859-15"
Content-Transfer-Encoding: 7bit
Cc: joro@8bytes.org, avi@redhat.com, kvm@vger.kernel.org,
	qemu-devel@nongnu.org
To: "Eduard - Gabriel Munteanu" <eduard.munteanu@linux360.ro>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mail.codesourcery.com ([38.113.113.100]:58672 "EHLO
	mail.codesourcery.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1751951Ab0GNNxJ (ORCPT <rfc822;kvm@vger.kernel.org>);
	Wed, 14 Jul 2010 09:53:09 -0400
In-Reply-To: <1279086307-9596-5-git-send-email-eduard.munteanu@linux360.ro>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

> Memory accesses must go through the IOMMU layer.

No. Devices should not know or care whether an IOMMU is present.

You should be adding a DeviceState argument to cpu_physical_memory_{rw,map}. 
This should then handle IOMMU translation transparently.

You also need to accomodate the the case where multiple IOMMU are present.

Paul