Date: Fri, 10 Sep 2010 00:14:30 -0600 (MDT) From: "M. Warner Losh" <imp@bsdimp.com> To: neelnatu@gmail.com Cc: gonzo@freebsd.org, freebsd-mips@freebsd.org Subject: Re: busdma_machdep.c with more than 512M memory Message-ID: <20100910.001430.1149370768114483729.imp@bsdimp.com> In-Reply-To: <AANLkTikOKU8KOaw6aFd1dMqpcZW%2BcMkU72mrDBcUncVq@mail.gmail.com> References: <AANLkTim2gqj=cbgM35rD5oyMD43rWFY1cjyY4A4CoR99@mail.gmail.com> <AANLkTim7zDxy9bYYvPT31t-mRB37NPpONsBHhouBPpG_@mail.gmail.com> <AANLkTikOKU8KOaw6aFd1dMqpcZW%2BcMkU72mrDBcUncVq@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
In message: <AANLkTikOKU8KOaw6aFd1dMqpcZW+cMkU72mrDBcUncVq@mail.gmail.com>
Neel Natu <neelnatu@gmail.com> writes:
: This assumes that pmap_mapdev() always returns an uncached mapping
: which is true for n64 kernels but not for o32 kernels with memory
: beyond 512MB.
:
: Any objections if I commit the following patch that makes
: pmap_mapdev() always return an uncached mapping.
Is there ever a time on MIPS you'd want to make a device you are
talking to cached?
I'd say it is a vanishingly rare event, if ever. If we come up with
one, we, at that time, should implement a way to do that mapping.
I have no objections to this patch, but I've not gone over it with a
fine tooth comb.
Warner
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20100910.001430.1149370768114483729.imp>