WARNING - OLD ARCHIVES

This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
   
 
 
Xen 
 
Home Products Support Community News
 
   
 

xen-ia64-devel

[RESEND]RE: [Xen-ia64-devel][PATCH] optimize entry and exit path

To: <ahs3@xxxxxxxxx>
Subject: [RESEND]RE: [Xen-ia64-devel][PATCH] optimize entry and exit path
From: "Xu, Anthony" <anthony.xu@xxxxxxxxx>
Date: Wed, 12 Jul 2006 12:51:08 +0800
Cc: xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
Delivery-date: Tue, 11 Jul 2006 21:51:57 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxx
List-help: <mailto:xen-ia64-devel-request@lists.xensource.com?subject=help>
List-id: Discussion of the ia64 port of Xen <xen-ia64-devel.lists.xensource.com>
List-post: <mailto:xen-ia64-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-ia64-devel>, <mailto:xen-ia64-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-ia64-devel>, <mailto:xen-ia64-devel-request@lists.xensource.com?subject=unsubscribe>
Sender: xen-ia64-devel-bounces@xxxxxxxxxxxxxxxxxxx
Thread-index: AcakZPMnvvOePQZyR8KXe94hNWrHawBCaUOg
Thread-topic: [RESEND]RE: [Xen-ia64-devel][PATCH] optimize entry and exit path
VMM save/restore r4~r7 and unat to handle virtualization fault and mmio access,
but it is not necessary for other faults to save/restore these registers.
This patch is to save/restore these registers only when dtlb and virtualization 
fault happen.

Signed-off-by: Anthony Xu < anthony.xu@xxxxxxxxx>

>-----Original Message-----
>From: Al Stone [mailto:ahs3@xxxxxxxxx]
>Sent: 2006?7?11? 5:07
>To: Xu, Anthony
>Cc: xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
>Subject: Re: [Xen-ia64-devel][PATCH] optimize entry and exit path
>
>On Mon, 2006-07-10 at 15:24 +0800, Xu, Anthony wrote:
>> VMM save/restore r4~r7 and unat to handle virtualization fault and mmio 
>> access,
>> but it is not necessary for other faults to save/restore these registers.
>> This patch is to save/restore these registers only when dtlb and 
>> virtualization
>fault happen.
>
>If I understand this patch correctly, and I'm not sure I do, so please
>bear with me, it looks like I now have two entry points into the same
>block of code -- GLOBAL_ENTRY(ia64_leave_hypervisor_prepare) and a few
>instructions later, GLOBAL_ENTRY(ia64_leave_hypervisor).  That makes
>sense if the goal is to shave off some instructions that are not always
>necessary.  I've used that trick many times myself.
>
>What puzzles me, though, is what happens to the unwind info?  Without
>an END for ia64_leave_hypervisor_prepare, am I losing unwind info, or
>possibly confusing the info for ia64_leave_hypervisor?  Or am I just
>not seeing something obvious?
>
>I'm still trying to grok Xen, so be gentle :)...
>
>--
>Ciao,
>al
>----------------------------------------------------------------------
>Al Stone                                      Alter Ego:
>Open Source and Linux R&D                     Debian Developer
>Hewlett-Packard Company                       http://www.debian.org
>E-mail: ahs3@xxxxxxxxx                        ahs3@xxxxxxxxxx
>----------------------------------------------------------------------

Attachment: entry_exit_path_optimize2.patch
Description: entry_exit_path_optimize2.patch

_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ia64-devel
<Prev in Thread] Current Thread [Next in Thread>