|
|
|
|
|
|
|
|
|
|
xen-ia64-devel
[Xen-ia64-devel] RE: PATCH: get rid of dcr bit 63 trick
You *really* don't like that dcr bit 63 test, do you? :-)
One disadvantage of your "cpl!=0" test is that it
gives the "wrong" answer for a fully-virtualized
domain. Arun Sharma (before he left Intel) was looking
at ways of combining paravirtualization performance
into a fully-virtualized domain.
Also, per the last time this was discussed, I think there
are plans in future Itaniums to architect the
discovery of a virtualization layer, which will
undoubtedly be different than both the dcr-bit-63 and
cpl!=0 method, so we will just have to change it again
in the future.
Dan
> -----Original Message-----
> From: Tristan Gingold [mailto:Tristan.Gingold@xxxxxxxx]
> Sent: Friday, May 12, 2006 7:32 AM
> To: xen-ia64-devel@xxxxxxxxxxxxxxxxxxx; Magenheimer, Dan (HP
> Labs Fort Collins); Williamson, Alex (Linux Kernel Dev)
> Subject: PATCH: get rid of dcr bit 63 trick
>
> Hi,
>
> instead of testing dcr bit 63 for running_on_xen, check
> ar.rsc.pl, which
> cannot be paravirtualized.
>
> Testing on Xen and without Xen.
>
> Tristan.
>
_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ia64-devel
|
<Prev in Thread] |
Current Thread |
[Next in Thread>
|
- [Xen-ia64-devel] RE: PATCH: get rid of dcr bit 63 trick,
Magenheimer, Dan (HP Labs Fort Collins) <=
|
|
|
|
|