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-ia64-devel] Uncached offset: Region 6 -> lower half ofVTi-reser

To: "Magenheimer, Dan \(HP Labs Fort Collins\)" <dan.magenheimer@xxxxxx>, <xen-ia64-devel@xxxxxxxxxxxxxxxxxxx>
Subject: RE: [Xen-ia64-devel] Uncached offset: Region 6 -> lower half ofVTi-reserved VM space
From: "Tian, Kevin" <kevin.tian@xxxxxxxxx>
Date: Tue, 14 Jun 2005 13:51:02 +0800
Delivery-date: Tue, 14 Jun 2005 05:50:07 +0000
Envelope-to: www-data@xxxxxxxxxxxxxxxxxxx
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: AcVwX+CR8RimBlWdTgqhrwBuwdjrAAAQYluQ
Thread-topic: [Xen-ia64-devel] Uncached offset: Region 6 -> lower half ofVTi-reserved VM space
>-----Original Message-----
>From: xen-ia64-devel-bounces@xxxxxxxxxxxxxxxxxxx
>[mailto:xen-ia64-devel-bounces@xxxxxxxxxxxxxxxxxxx] On Behalf Of
>Magenheimer, Dan (HP Labs Fort Collins)
>Sent: Tuesday, June 14, 2005 5:36 AM
>I've just pushed a patch to xeno-unstable-ia64.bk which finishes
>the virtual address changes submitted by Intel (Kevin, I think)
>some months ago, where the Xen-reserved VA space was changed from
>       0xf000000000000000-0xf7ffffffffffffff
>               to
>       0xe800000000000000-0xf7ffffffffffffff
>to correspond to one less bit in the guest's virtual address

You change seems clean to understand. Before submitting a patch for VTI,
I'd like to confirm one thing: whether you want to split cache/uncache
access in different region, or in same region? It seems cleaner to stay
with different region, as Linux currently does. Then if still in region
6 for "uncached" area, 0xd000000000000000 is just same effect as
0xf000000000000000 to hide one bit to guest.

>The "uncached" portion of Xen's virtual address space was
>still mapped at 0xd000000000000000.  I have moved it
>to 0xe800000000000000 to properly correspond with the
>one-less-bit-guest-VA space.
>A couple of changes were required in ivt.S so corresponding
>changes need to be made in vmx_ivt.S.  The only other change
>was the constant value in io.h (a patched file) for
>Note that I also cleaned up a test to ensure that guest
>data accesses are properly checked against the legal
>address range.  (Not a problem on VTI as these addresses
>could never be generated.)
>See changeset 1.1711.  If someone at Intel could submit
>the corresponding vmx_ivt.S change, I would appreciate it.
>Xen-ia64-devel mailing list

Xen-ia64-devel mailing list

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