On 26/01/2009 13:33, "Keir Fraser" <keir.fraser@xxxxxxxxxxxxx> wrote:
> As for the general issue, why fudge around it when for any modern system we
> can just fix it? By which I mean, x64 systems with CMPXCHG16 support
> (everything but ancient Opterons?) can have a full domain pointer and a long
> count_info in struct page_info, and still update both atomically.
Actually I think we could do without CX16. I'm not sure count_info and
domain need to be checked/updated at the same time. I think it would suffice
to update count_info, then check domain and undo on mismatch. That'd get rid
of the existing ugly open-coded cmpxchg8b operations too.
I think I'll look into this bit at least...
 -- Keir
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel