On Tue, 2014-07-15 at 20:40 -0400, Konrad Rzeszutek Wilk wrote:
> On July 15, 2014 5:23:24 PM EDT, Toshi Kani <toshi.kani@hp.com> wrote:
> >On Tue, 2014-07-15 at 13:09 -0700, H. Peter Anvin wrote:
> >> On 07/15/2014 12:34 PM, Toshi Kani wrote:
 :
> >> 
> >> I have given this piece of feedback at least three times now,
> >possibly
> >> to different people, and I'm getting a bit grumpy about it:
> >> 
> >> We already have an issue with Xen, because Xen assigned mappings
> >> differently and it is incompatible with the use of PAT in Linux.  As
> >a
> >> result we get requests for hacks to work around this, which is
> >something
> >> I really don't want to see.  I would like to see a design involving a
> >> "reverse PAT" table where the kernel can hold the mapping between
> >memory
> >> types and page table encodings (including the two different ones for
> >> small and large pages.)
> >
> >Thanks for pointing this out! (And sorry for making you repeat it three
> >time...)  I was not aware of the issue with Xen.  I will look into the
> >email archive to see what the Xen issue is, and how it can be
> >addressed.
> 
> https://lkml.org/lkml/2011/11/8/406

Thanks Konrad for the pointer!

Since [__]change_page_attr_set_clr() and __change_page_attr() have no
knowledge about PAT and simply work with specified PTE flags, they do
not seem to fit well with additional PAT abstraction table...

I think the root of this issue is that the kernel ignores the PAT bit.
Since __change_page_attr() only supports 4K pages, set_memory_<type>()
can set the PAT bit into the clear mask.

Attached is a patch with this approach (apply on top of this series -
not tested).  The kernel still does not support the PAT bit, but it
behaves slightly better.

Thanks,
-Toshi