lkml.org 
[lkml]   [2012]   [Jun]   [29]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [Xen-devel] [PATCH] x86 fixes for 3.3 impacting distros (v1).
On 06/29/2012 02:52 PM, Cyclonus J wrote:
>
> Peter,
>
> hmm, It looks like option 1 doesn't have any perf regression, but it is still
> not acceptable? That is fine. If you prefer to have a software PAT table lookup, could you provide
> some details so I can try to get something align that direction?
>

It has no perf regression, but it really buries deep in the code a
strange abstraction which only happens to work on Xen and is confusing
as hell.

The idea with a software PAT table is that the PAT numbers used by the
kernel should come from a table in the kernel instead of being
hard-coded. That might take some work, and it remains to be seen if it
is practical.

It *may* be that we need to hard-code 0 as WB, still, but that should be
true on any sane platform.

-hpa


\
 
 \ /
  Last update: 2012-06-30 01:01    [W:0.079 / U:1.572 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site