In response to this thread I'll add my observation...
Intel has a document that lists the errata for a CPU... and I found a
LOT of issues regarding VT on the Presler (vmread vmptrld vmcs, etc.):
"Intel(r) Pentium(r) D Processor 900Δ Sequence and Intel(r) Pentium(r)
Processor Extreme Edition 955Δ Specification Update"
http://www.intel.com/design/Pentiumxe/specupdt/310307.htm
The similar document for the new laptop chips:
"Intel(r) Core™ Duo Processor and Intel(r) Core™ Solo Processor on 65
nm Process Specification Update"
http://www.intel.com/design/mobile/specupdt/309222.htm
I note a complete absence of errata (defects) relating the VT on the
laptop chips... so it makes me wonder if they got VT perfect or what? 
Or just not documented yet (a document update is mentioned to be
coming January 18, 2006)?
The speedstep power saving mode seems to be a problem on the new
Pentium D series... and it is 64-bit vs 32-bit. Maybe the two
implementations of VT have nothing in common in regards to errata. Of
course, I am curious if these BIOS workarounds mentioned in the
Pentium D errata actually are implemented properly - I wonder if a
series of Xen 'tests' could be devised to see if a particular BIOS has
the required workarounds.
Can you tell I've been doing too much reading about VT hardware lately :) ?
 Stephen Gutknecht

_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users