Re: [Xen-devel] [PATCH 00/11] x86: support up to 16Tb

[Keir Fraser <keir.xen@xxxxxxxxx>]

On 22/01/2013 10:45, "Jan Beulich" <JBeulich@xxxxxxxx> wrote:

> This series enables Xen to support up to 16Tb.
> 
> 01: x86: introduce virt_to_xen_l1e()
> 02: x86: extend frame table virtual space
> 03: x86: re-introduce map_domain_page() et al
> 04: x86: properly use map_domain_page() when building Dom0
> 05: x86: consolidate initialization of PV guest L4 page tables
> 06: x86: properly use map_domain_page() during domain creation/destruction
> 07: x86: properly use map_domain_page() during page table manipulation
> 08: x86: properly use map_domain_page() in nested HVM code
> 09: x86: properly use map_domain_page() in miscellaneous places
> 10: tmem: partial adjustments for x86 16Tb support
> 11: x86: support up to 16Tb

I will take a look at these tomorrow.

 -- Keir

> As I don't have a 16Tb system around, I used the following
> debugging patch to simulate the most critical aspect the changes
> above would have on a system with this much memory: Not all of
> the 1:1 mapping being accessible when in PV guest context. To do
> so, a command line option to pull the split point down is being
> added. The patch is being provided in the raw form I used it, but
> has pieces properly formatted and not marked "//temp" which I
> would think might be worth considering to add. The other pieces
> are likely less worthwhile, but if others think differently I could
> certainly also put them into "normal" shape.
> 
> 12: x86: debugging code for testing 16Tb support on smaller memory systems
> 
> Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
> 
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@xxxxxxxxxxxxx
> http://lists.xen.org/xen-devel



_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel