lkml.org 
[lkml]   [2009]   [Oct]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: 2.6.32-rc4: Reported regressions from 2.6.31
> That involves allocating a _shitload_ of page tables for a 1:1 mapping
> of all of physical memory. We used to do that to pander to broken
> graphics drivers, and the AMD guys asked me to stop because it was
> actually quite painful for them to do the same.

SMM isn't going to be touching high pages. In fact I wouldn't be the
least suprised if simply mapping the low 1MB including EBDA/ISA space and
the ACPI reserved areas worked simply because if it touches any other RAM
in SMM mode its going to be peeing over our memory spaces.

And if I remember rightly the magic SMM remapped memory area is quite
small (64K) and low down too plus not DMAable (because otherwise DMA in
the real OS to the pages SMM aliases over will go kersplat if an SMM
occurs)

Alan


\
 
 \ /
  Last update: 2009-10-12 18:31    [W:0.079 / U:0.028 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site