From: David Miller <davem@davemloft.net>
To: benh@kernel.crashing.org
Cc: eric.lemoine@gmail.com, netdev@vger.kernel.org
Subject: Re: [patch sungem] improved locking
Date: Tue, 28 Nov 2006 15:43:50 -0800 (PST) [thread overview]
Message-ID: <20061128.154350.02290212.davem@davemloft.net> (raw)
In-Reply-To: <1164754644.5350.110.camel@localhost.localdomain>
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Wed, 29 Nov 2006 09:57:24 +1100
>
> > This looks mostly fine.
> >
> > I was thinking about the lockless stuff, and I wonder if there
> > is a clever way you can get it back down to one PIO on the
> > GREG_STAT register.
> >
> > I think you'd need to have the ->poll() clear gp->status, then
> > do a smp_wb(), right before it re-enables interrupts.
> >
> > Then in the interrupt handler, you need to find a way to safely
> > OR-in any unset bits in gp->status in a race-free manner.
>
> Having it atomic might work at a slightly smaller cost than a lock,
> though atomics don't have strong ordering requirements so you'd still
> have to be a bit careful.
At least in theory the atomic + any necessary memory barriers
would be cheaper than the extra PIO read we need otherwise.
next prev parent reply other threads:[~2006-11-28 23:43 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-11-09 21:33 [patch sungem] improved locking Eric Lemoine
2006-11-09 23:04 ` David Miller
2006-11-10 13:28 ` Eric Lemoine
2006-11-10 20:37 ` Benjamin Herrenschmidt
2006-11-10 20:42 ` David Miller
2006-11-12 23:11 ` Eric Lemoine
2006-11-14 0:46 ` David Miller
2006-11-14 7:28 ` Eric Lemoine
2006-11-14 7:44 ` David Miller
2006-11-14 21:54 ` Eric Lemoine
2006-11-28 22:49 ` David Miller
2006-11-28 22:57 ` Benjamin Herrenschmidt
2006-11-28 23:43 ` David Miller [this message]
2006-11-29 0:19 ` Benjamin Herrenschmidt
2006-11-29 10:16 ` Eric Lemoine
2006-11-29 10:56 ` Eric Lemoine
2006-11-29 22:37 ` Eric Lemoine
2006-12-13 3:12 ` Benjamin Herrenschmidt
2006-12-13 3:24 ` Benjamin Herrenschmidt
2006-12-13 4:03 ` David Miller
2006-12-13 4:07 ` Benjamin Herrenschmidt
2006-12-29 5:05 ` David Miller
2006-12-29 21:36 ` Benjamin Herrenschmidt
2006-12-29 23:20 ` David Miller
2006-12-12 1:43 ` David Miller
2006-12-12 5:33 ` Eric Lemoine
2006-12-12 5:36 ` Benjamin Herrenschmidt
2006-12-12 5:49 ` Eric Lemoine
2006-12-15 0:59 ` Benjamin Herrenschmidt
2006-12-18 1:15 ` David Miller
2006-12-18 1:41 ` Benjamin Herrenschmidt
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=20061128.154350.02290212.davem@davemloft.net \
--to=davem@davemloft.net \
--cc=benh@kernel.crashing.org \
--cc=eric.lemoine@gmail.com \
--cc=netdev@vger.kernel.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).