On 15/3/07 09:53, "Isaku Yamahata" <yamahata@xxxxxxxxxxxxx> wrote:
> This patch fixes memory exchange hypercall which has been broken on ia64.
> Especially the error recovery path.
> Dropping _PGC_allocated bit and guest_physmap_remove_page() must be done
> before stealing page because The ia64 p2m table increments page
> refcount and guest_physmap_remove_page() behaves depending on _PGC_allocated.
Do the p2m semantics of the two architectures really need to differ? Can't
ia64 match x86 semantics (or vice versa)? Otherwise you're going to be
continually getting broken and having to implement skanky workarounds.
 -- Keir
> So far there is work around code in ia64, however the c/s 13366:ed73ff8440d8
> of xen-unstable.hg revealed that the work around is broken.
> The c/s passes dma bit argument of memory exchange so that it results
> in hypercall error.
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel