Messages in this thread |  | | | Date | Tue, 14 Dec 2010 22:17:29 -0800 | | From | "H. Peter Anvin" <> | | Subject | Re: [PATCH] - Mapping ACPI tables as CACHED |
| |
On 12/14/2010 08:35 PM, Len Brown wrote: > > I'm not sure the concept of checking against E820 > is better than simply calling ioremap_cache() always. >
I don't think it is. On most systems, non-RAM will be forced uncachable by the MTRRs anyway, and if we find systems which have problems, we should be doing this forcing in the PAT subsystem, not in ACPI.
-hpa
-- H. Peter Anvin, Intel Open Source Technology Center I work for Intel. I don't speak on their behalf.
|  |