Re: [PATCH 00/11] Alternate p2m: support multiple copies of host p2m

[Tim Deegan <tim@xen.org>]

At 12:32 -0800 on 16 Jan (1421407932), Ed White wrote:
> > 
> >> As I said in discussion with Andrew, my aim was to make it possible
> >> for these same changes to be extensible to AMD processors if they
> >> support multiple copies of whatever their EPT equivalent is, by
> >> simply emulating VMFUNC and #VE. That's why there are some wrappers
> >> in the implementation that appear redundant.
> > 
> > Yep, understood, and thank you for that.  But I think there was one
> > function (to find a p2m by eptp) that's defined in vmx.c and only ever
> > called from there -- that doesn't need an arch-specific wrapper,
> > because an eventual AMD equivalent would also be entirely contained
> > within svm.c.
> > 
> 
> I think you're referring to p2m_find_altp2m_by_eptp(), defined in
> p2m.c but only called from vmx.c. That might more properly be
> p2m_find_altp2m_by_whatever_the_hardware_uses(), which is why I
> put it there. I assumed it would have value for AMD.

Ah, I had misread it, sorry.  Yes, that path is fine, I think.  It
would be nice to have a more arch-neutral name but I can;t think of
anything particularly good right now.  p2m_find_altp2m_by_table()
seems close to other similar thinkgs, but it's not excatly inspiring.

Tim.