From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from [140.186.70.92] (port=52906 helo=eggs.gnu.org)
	by lists.gnu.org with esmtp (Exim 4.43) id 1OrCKp-0000bD-10
	for qemu-devel@nongnu.org; Thu, 02 Sep 2010 12:08:21 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.69)
	(envelope-from <avi@redhat.com>) id 1OrCKc-0007MW-Ag
	for qemu-devel@nongnu.org; Thu, 02 Sep 2010 12:08:07 -0400
Received: from mx1.redhat.com ([209.132.183.28]:50702)
	by eggs.gnu.org with esmtp (Exim 4.69)
	(envelope-from <avi@redhat.com>) id 1OrCKc-0007MM-27
	for qemu-devel@nongnu.org; Thu, 02 Sep 2010 12:08:06 -0400
Message-ID: <4C7FCBC3.1060006@redhat.com>
Date: Thu, 02 Sep 2010 19:07:31 +0300
From: Avi Kivity <avi@redhat.com>
MIME-Version: 1.0
References: <1283007298-10942-1-git-send-email-eduard.munteanu@linux360.ro>
	<1283007298-10942-5-git-send-email-eduard.munteanu@linux360.ro>
	<20100902051911.GA4273@redhat.com>
	<20100902091200.GB7319@localhost>
	<20100902095813.GB9085@redhat.com>
	<20100902150135.GA7136@localhost> <4C7FC1A9.3080800@redhat.com>
	<20100902153934.GE18182@redhat.com>
In-Reply-To: <20100902153934.GE18182@redhat.com>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Subject: [Qemu-devel] Re: [PATCH 4/7] ide: use the PCI memory access
	interface
List-Id: qemu-devel.nongnu.org
List-Unsubscribe: <http://lists.nongnu.org/mailman/listinfo/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: <http://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: kvm@vger.kernel.org, joro@8bytes.org, qemu-devel@nongnu.org, blauwirbel@gmail.com, yamahata@valinux.co.jp, paul@codesourcery.com, Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>

  On 09/02/2010 06:39 PM, Michael S. Tsirkin wrote:
> On Thu, Sep 02, 2010 at 06:24:25PM +0300, Avi Kivity wrote:
>> That's not a practical long term solution.  Eventually everything
>> gets turned on.
> That's why I wanted a simple !iommu check and fallback.
> This way unless it's really used there's no overhead.
>

It's not very different from an indirect function call.  Modern branch 
predictors store the target function address and supply it ahead of time.

I've never seen a function call instruction in a profile.

-- 
error compiling committee.c: too many arguments to function