From mboxrd@z Thu Jan  1 00:00:00 1970
From: Keir Fraser <keir@xen.org>
Subject: Re: [PATCH] Enble 6 argument hypercalls for HVMs
Date: Wed, 15 Dec 2010 13:20:46 +0000
Message-ID: <C92E712E.CF5C%keir@xen.org>
References: <4D08BEA102000078000281FE@vpn.id2.novell.com>
Mime-Version: 1.0
Content-Type: text/plain;
	charset="US-ASCII"
Content-Transfer-Encoding: 7bit
Return-path: <xen-devel-bounces@lists.xensource.com>
In-Reply-To: <4D08BEA102000078000281FE@vpn.id2.novell.com>
List-Unsubscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
List-Post: <mailto:xen-devel@lists.xensource.com>
List-Help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-Subscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
Sender: xen-devel-bounces@lists.xensource.com
Errors-To: xen-devel-bounces@lists.xensource.com
To: Jan Beulich <JBeulich@novell.com>
Cc: "xen-devel@lists.xensource.com" <xen-devel@lists.xensource.com>
List-Id: xen-devel@lists.xenproject.org

On 15/12/2010 12:12, "Jan Beulich" <JBeulich@novell.com> wrote:

>>>> On 15.12.10 at 12:43, Keir Fraser <keir@xen.org> wrote:
>> On 15/12/2010 10:40, "Jan Beulich" <JBeulich@novell.com> wrote:
>>> Looking at this code also makes me wonder once again whether
>>> it really is a good idea to have a generally not taken forward
>>> branch here.
>> 
>> Which generally not-taken branch? The 'je 1f' instruction generally *will*
>> be taken!
> 
> Oops, of course - it being taken is the problem, as it'll be statically
> mis-predicted.

Well, moving the trace code out of line, perhaps into the fixup section,
would be good for cache locality. And then we would have a rarely taken
forward branch (since the fixup section comes after normal text).

I'm sure there are a bunch of places in our asm code where we could do this.
Feel free to fix them all up, if you like.

 -- Keir

> Jan
>