Subject: Re: linear and non-cacheable mapping vs bwx
To: Matt Thomas <firstname.lastname@example.org>
From: Chris G. Demetriou <email@example.com>
Date: 09/01/1999 19:53:17
Matt Thomas <firstname.lastname@example.org> writes:
> At 04:11 PM 9/1/99 , Chris G. Demetriou wrote:
> >In other words, getting right of the 'cacheable' check is probably
> > * if you're compiling the kernel (and userland, if device
> > space mapping is ever exported from the kernel in some sane
> > manner) with BWX extensions, and
> FWIW I've been running a BWX kernel for several weeks with no problems
> that I can tell.
right, but that doesn't necessarily mean that the compiler is
generating the byte and 2-byte accesses in all of the places that it'd
have to to properly implement "linear" mapping semantics with via BWX
access to devices.
I would _hope_ that it does the right thing, but somebody should go
through and check.
Chris Demetriou - email@example.com - http://www.netbsd.org/People/Pages/cgd.html
Disclaimer: Not speaking for NetBSD, just expressing my own opinion.