Re: swapping with MMU Notifiers V2

["Joerg Roedel" <joerg.roedel-5C7GfCeVMHo@public.gmane.org>]

On Tue, Jan 29, 2008 at 07:02:52PM +0200, Avi Kivity wrote:
> Carsten Otte wrote:
> >Avi Kivity wrote:
> >>Every arch except s390 needs it.  An ugly #ifndef CONFIG_KVM_HARDWARE_TLB_SYNC is preferred to duplicating 
> >>the code.
> >BTW, from reading AMDs spec I don't expect NPT to need this vehicle for swapping either. They can just let 
> >core-vm page out guest pages and will receive a proper page fault in the host. Jörg can you confirm that?
> >
> 
> No, that doesn't work:
> 
> - even though npt can use the same pagetable for guest and host, that isn't workable for kvm as npt doesn't 
> have an offset/size thing.  so kvm uses a separate pagetable for guest and host.

Right. We can't reuse page tables from the Linux MM for Nested Paging.

> - npt doesn't have a dual-tagged tlb, where a host tlb invalidate also invalidates all guest tlbs that point 
> to the same page

Since we have our own page table for Nested Paging this is also true.

Joerg

-- 
           |           AMD Saxony Limited Liability Company & Co. KG
 Operating |         Wilschdorfer Landstr. 101, 01109 Dresden, Germany
 System    |                  Register Court Dresden: HRA 4896
 Research  |              General Partner authorized to represent:
 Center    |             AMD Saxony LLC (Wilmington, Delaware, US)
           | General Manager of AMD Saxony LLC: Dr. Hans-R. Deppe, Thomas McCoy



-------------------------------------------------------------------------
This SF.net email is sponsored by: Microsoft
Defy all challenges. Microsoft(R) Visual Studio 2008.
http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/
_______________________________________________
kvm-devel mailing list
kvm-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/kvm-devel