[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] RFC: [0/2] Remove netloop by lazy copying in netback

On 27/3/07 11:25, "Herbert Xu" <herbert@xxxxxxxxxxxxxxxxxxx> wrote:

> Actually we can just mark the PTEs as not present in that case.  The
> hypervisor can then mark the PTEs as present on the first fault.
> Just as grant table operations currently work on virtual addresses for
> non-translated guests and physical addresses for translated guests,
> such an operation would work on PTEs for non-translated guests and
> p2m entries for translated guests.

Yeah, but: how does Xen efficiently work out whether a not-present fault is
due to a lazy grant mapping and, if so, what it is that needs to be demand
mapped? PV guests can store what they like in not-present pagetable entries.
Perhaps we could make use of reserved bits in ptes instead (not that there
are any in non-pae x86, but I'd very much like to obsolete non-pae x86 Xen
after 3.0.5 anyway -- I don't think anyone actually ships a product with
non-pae bits).

 -- Keir

Xen-devel mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.