linux-mips
[Top] [All Lists]

Re: Please pull drivers/scsi/dec_esp.c from Linus' git

To: "Maciej W. Rozycki" <macro@linux-mips.org>
Subject: Re: Please pull drivers/scsi/dec_esp.c from Linus' git
From: Jes Sorensen <jes@sgi.com>
Date: 17 Feb 2006 04:12:12 -0500
Cc: Ralf Baechle <ralf@linux-mips.org>, Martin Michlmayr <tbm@cyrius.com>, linux-mips@linux-mips.org
In-reply-to: <Pine.LNX.4.64N.0602161504230.7169@blysk.ds.pg.gda.pl>
Original-recipient: rfc822;linux-mips@linux-mips.org
References: <20060213225331.GA5315@deprecation.cyrius.com> <20060215150839.GA27719@linux-mips.org> <Pine.LNX.4.64N.0602161016260.7169@blysk.ds.pg.gda.pl> <20060216145931.GA1633@linux-mips.org> <Pine.LNX.4.64N.0602161504230.7169@blysk.ds.pg.gda.pl>
Sender: linux-mips-bounce@linux-mips.org
User-agent: Gnus/5.09 (Gnus v5.9.0) Emacs/21.4
>>>>> "Maciej" == Maciej W Rozycki <macro@linux-mips.org> writes:

Maciej> On Thu, 16 Feb 2006, Ralf Baechle wrote:
>> That still leaves below gem to sort out.

Maciej>  Yeah -- there is that mmiowb() macro that is supposed to fit
Maciej> here, but some MIPS-based hardware is ordered weakly (and
Maciej> strangely) enough for this single macro to be a bit
Maciej> insufficient.  I think we should have at least mmiowb() and
Maciej> mmiob() (corresponding to wmb() and mb(), respectively) as
Maciej> there is a system we support that does writes in order, but
Maciej> snoops the writeback buffer (the R3220).  Another one is worse
Maciej> yet as does all of that plus byte gathering (the R2020).  At
Maciej> least the latter cannot have the NCR/Emulex SCSI chip and uses
Maciej> DEC's own design instead (a DC7061 gate array highly suspected
Maciej> to also support DSSI if appropriately configured).

Maciej>  I'm not sure if we really need mmiorb() -- probably not.

Just make mmiowb() strong enough on those platforms. There's really no
reason to introduce yet another variation at this point.

Jes



<Prev in Thread] Current Thread [Next in Thread>