Matt Thomas <matt@3am-software.com> writes:
> At 04:11 PM 9/1/99 , Chris G. Demetriou wrote:
> >In other words, getting right of the 'cacheable' check is probably
> >right:
> >
> >         * 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.


cgd
-- 
Chris Demetriou - cgd@netbsd.org - http://www.netbsd.org/People/Pages/cgd.html
Disclaimer: Not speaking for NetBSD, just expressing my own opinion.