Subject: RE: PXA250 Xscale and page tables
To: Allen Briggs <>
From: Colin Cook <>
List: tech-kern
Date: 02/01/2003 16:00:27
Ok, so It's supposed to be there. I still don't get why, but that is ok, I
am not a NetBSD developer. I just need the processor to use the i-Cache when
running my program.

So what do I do next? Can someone tell me the "right" way to fix this
problem? And possibly what will crash if I were to just leave that line
commented out, because currently the system is running fine, and fast I
might add.

CC :)

-----Original Message-----
From: Allen Briggs []
Sent: Saturday, February 01, 2003 12:51 PM
To: Martin Husemann
Cc: Colin Cook;
Subject: Re: PXA250 Xscale and page tables

On Sat, Feb 01, 2003 at 08:43:16PM +0100, Martin Husemann wrote:
> On Sat, Feb 01, 2003 at 10:13:55AM -0700, Colin Cook wrote:
> > What I want to know is why was this in there in the first place. Turning
> > the cache is a very bad thing to do.
> I think it's there to avoid illegal cache aliases, PVF_NC means
> mapping is non-cacheable, there are multiple mappings (for this VA).

Precisely.  See the comments above pmap_vac_me_harder() earlier in the

> But at first glance it's not clear to me if the test for this bit is
> inverted.

The test there isn't inverted, but it's still possible that something's
awry if all user pages end up that way.  Simply removing that line is
certainly not the correct solution, but if the code's ending up there
when it shouldn't, there is something wrong.


 Allen Briggs               Quality NetBSD CDs, Sales, Support,
NetBSD development for Alpha, ARM, M68K, MIPS, PowerPC, SuperH, XScale,