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/
Home Products Support Community News


Re: [Xen-devel] vmx & efer

To: Jan Beulich <jbeulich@xxxxxxxxxx>
Subject: Re: [Xen-devel] vmx & efer
From: Keir Fraser <Keir.Fraser@xxxxxxxxxxxx>
Date: Mon, 07 May 2007 13:39:00 +0100
Cc: xen-devel@xxxxxxxxxxxxxxxxxxx
Delivery-date: Mon, 07 May 2007 05:35:47 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxx
In-reply-to: <463F16B9.76E4.0078.0@xxxxxxxxxx>
List-help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-id: Xen developer discussion <xen-devel.lists.xensource.com>
List-post: <mailto:xen-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
Sender: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx
Thread-index: AceQpK+x7nQ5ivyXEdu5fwAWy6hiGQ==
Thread-topic: [Xen-devel] vmx & efer
User-agent: Microsoft-Entourage/
On 7/5/07 11:08, "Jan Beulich" <jbeulich@xxxxxxxxxx> wrote:

>> That I'm not sure about. We always ensure the shadow PAE CR3 is in low 4GB,
>> so we don't have to worry about this. I guess it depends whether PAE CR3 is
> Because it happens to sit in the vcpu structure? That's one more thing to
> remember when folding the Xen heap into the domain heap on x86-64 then.
> (I have to admit that I dislike all these hidden address range dependencies.)

I'm very inclined to turn 'Xen heap' allocations into 'allocate below 4GB'
allocations by default. Then remove that restriction at allocation sites
one-by-one. We do so little Xen-heap allocation (after all we live with
~12MB heap right now) that this will be absolutely fine.

 -- Keir

Xen-devel mailing list

<Prev in Thread] Current Thread [Next in Thread>