Re: port-sgimips/38932: sgimips bus_dmamap_sync() is incorrect

[Manuel Bouyer <bouyer%antioche.eu.org@localhost>]

The following reply was made to PR port-sgimips/38932; it has been noted by 
GNATS.

From: Manuel Bouyer <bouyer%antioche.eu.org@localhost>
To: Izumi Tsutsui <tsutsui%ceres.dti.ne.jp@localhost>
Cc: gnats-bugs%NetBSD.org@localhost, 
port-sgimips-maintainer%NetBSD.org@localhost,
        gnats-admin%NetBSD.org@localhost, netbsd-bugs%NetBSD.org@localhost
Subject: Re: port-sgimips/38932: sgimips bus_dmamap_sync() is incorrect
Date: Tue, 10 Jun 2008 22:11:14 +0200

 On Wed, Jun 11, 2008 at 05:05:50AM +0900, Izumi Tsutsui wrote:
 > > I see your point. But I'm not sure such devices can work reliably
 > > with a write-back cache if regions are not cacheline-aligned.
 > > For example, I'm almost sure an uchi/ehci can't work reliably on hosts
 > > with write-back caches (unless the descriptors are mappped uncached).
 > > I suspect re(4) has the same issue with re_desc->re_cmdstat (the updated
 > > re_cmdstat from a descriptor may be lost if the host writes another
 > > descriptor in the same cache line).
 > 
 > Yes, ideally we can allocate only one descriptor per each cacheline
 > to avoid race, but not all devices (for PC) assume such hardware.
 > In such case, BUS_DMA_COHERENT is mandatory.
 > 
 > But anyway we can't invalidate cache in POSTREAD/POSTWRITE
 > because they have the same problems even on data xfers.
 
 On second though I think you're right on this. Please close the PR.
 
 -- 
 Manuel Bouyer <bouyer%antioche.eu.org@localhost>
      NetBSD: 26 ans d'experience feront toujours la difference
 --