22 messages in com.xensource.lists.xen-ia64-develRe: [Xen-ia64-devel] [RFC][PATCH] [RE...
FromSent OnAttachments
Dietmar Hahn27 Jun 2007 04:56.patch
Dietmar Hahn27 Jun 2007 05:40 
Dietmar Hahn28 Jun 2007 05:51.patch, .patch
Tristan Gingold28 Jun 2007 18:47 
Dietmar Hahn28 Jun 2007 23:40 
tgin...@free.fr29 Jun 2007 00:52 
Dietmar Hahn29 Jun 2007 01:43 
Alex Williamson02 Jul 2007 11:10 
Dietmar Hahn03 Jul 2007 01:01 
Xu, Anthony03 Jul 2007 22:10 
Dietmar Hahn04 Jul 2007 00:35 
Xu, Anthony04 Jul 2007 18:31 
Dietmar Hahn04 Jul 2007 23:10 
Dietmar Hahn05 Jul 2007 03:32 
Xu, Anthony05 Jul 2007 18:00 
Alex Williamson05 Jul 2007 18:35 
Xu, Anthony05 Jul 2007 20:05 
Dietmar Hahn06 Jul 2007 06:36.patch, .patch
Tristan Gingold07 Jul 2007 07:02 
Dietmar Hahn08 Jul 2007 23:15 
Dietmar Hahn09 Jul 2007 04:11.patch, .patch
Alex Williamson09 Jul 2007 11:27 
Subject:Re: [Xen-ia64-devel] [RFC][PATCH] [RESEND] support special guest optimisations in the hypervisor
From:Tristan Gingold (tgin@free.fr)
Date:06/28/2007 06:47:36 PM
List:com.xensource.lists.xen-ia64-devel

On Thu, Jun 28, 2007 at 02:52:05PM +0200, Dietmar Hahn wrote:

Hi,

attached to this mail are 2 patches: - opt_feature_xen.patch implements the new hypercall __HYPERVISOR_opt_feature in the hypervisor. - opt_feature_linux.patch implements the usage of the hypercall.

I think the hypercall interface is a little bit overkill but who knows about the future?

The xen - patch has real effects in vcpu_translate() on inserting identity mappings in the vhpt/tlb. I'am not sure about some performance impacts. But without such a patch correct future protection key handling is impossible.

I don't understand why. Isn't PK 0 supposed to be always enabled ? (But I think it should be possible to disable the auto id mapping insertion).

Tristan.

_______________________________________________ Xen-ia64-devel mailing list Xen-@lists.xensource.com http://lists.xensource.com/xen-ia64-devel