From: Nick Piggin <npiggin@suse.de>
To: Paul Mackerras <paulus@samba.org>
Cc: linuxppc-dev@ozlabs.org
Subject: Re: [patch 1/2] powerpc: rmb fix
Date: Fri, 23 May 2008 07:48:47 +0200 [thread overview]
Message-ID: <20080523054846.GA4520@wotan.suse.de> (raw)
In-Reply-To: <18486.19905.421960.700640@cargo.ozlabs.ibm.com>
On Fri, May 23, 2008 at 02:53:21PM +1000, Paul Mackerras wrote:
> Nick Piggin writes:
>
> > There don't seem to actually be read*_relaxed calls that also use rmb
> > in the same file (although there is no reason why they might not appear).
> > But I must be thinking of are the raw_read accessors. They aren't ordered
> > on powerpc, and a few drivers appear to hope rmb() will order them.
>
> Which drivers?
net/macb.c, net/sfc/falcon_io.c... hmm, I thought there was a couple
more but maybe I was thinking of write side.
Anyway, even if there were zero, then the point is still that you
implement that API, so you should either strongly order your
__raw_ and _relaxed then you can weaken your rmb, or you have to
strengthen your rmb to match your weak read ops.
Saying it doesn't matter because there are no drivers is likely to
cause more headaches in future...
next prev parent reply other threads:[~2008-05-23 5:48 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-05-21 14:10 [patch 1/2] powerpc: rmb fix Nick Piggin
2008-05-21 14:12 ` [patch 2/2] powerpc: optimise smp_wmb Nick Piggin
2008-05-21 15:26 ` Benjamin Herrenschmidt
2008-05-21 15:34 ` Nick Piggin
2008-05-21 15:43 ` Benjamin Herrenschmidt
2008-05-21 15:47 ` Nick Piggin
2008-05-21 16:02 ` Benjamin Herrenschmidt
2008-05-21 20:51 ` Segher Boessenkool
2008-05-21 16:01 ` Nick Piggin
2008-05-21 20:12 ` Segher Boessenkool
2008-05-21 20:44 ` Benjamin Herrenschmidt
2008-05-21 22:07 ` Segher Boessenkool
2008-05-22 0:30 ` Nick Piggin
2008-05-21 20:16 ` Segher Boessenkool
2008-05-21 15:27 ` [patch 1/2] powerpc: rmb fix Benjamin Herrenschmidt
2008-05-21 15:32 ` Nick Piggin
2008-05-21 15:43 ` Benjamin Herrenschmidt
2008-05-23 2:14 ` Paul Mackerras
2008-05-23 4:40 ` Nick Piggin
2008-05-23 4:53 ` Paul Mackerras
2008-05-23 5:48 ` Nick Piggin [this message]
2008-05-23 6:40 ` Paul Mackerras
2008-05-26 1:38 ` Nick Piggin
-- strict thread matches above, loose matches on Subject: below --
2007-08-21 2:11 Nick Piggin
2007-08-21 19:07 ` Joel Schopp
2007-08-21 19:43 ` Segher Boessenkool
2007-08-21 21:42 ` Linas Vepstas
2007-08-22 1:16 ` Nick Piggin
2007-08-22 3:29 ` Segher Boessenkool
2007-08-22 3:55 ` Nick Piggin
2007-08-23 17:57 ` Segher Boessenkool
2007-08-24 2:47 ` Nick Piggin
2007-08-22 3:15 ` Nick Piggin
2007-08-22 3:33 ` Segher Boessenkool
2007-08-22 4:05 ` Nick Piggin
2007-08-23 17:49 ` Segher Boessenkool
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20080523054846.GA4520@wotan.suse.de \
--to=npiggin@suse.de \
--cc=linuxppc-dev@ozlabs.org \
--cc=paulus@samba.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).