public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: Albert Cahalan <acahalan@gmail.com>
Cc: jbarnes@virtuousgeek.org, alan@lxorguk.ukuu.org.uk,
	davem@davemloft.net, jeff@garzik.org, paulus@samba.org,
	torvalds@osdl.org, linux-kernel@vger.kernel.org, akpm@osdl.org,
	segher@kernel.crashing.org
Subject: Re: Opinion on ordering of writel vs. stores to RAM
Date: Tue, 12 Sep 2006 17:17:00 +1000	[thread overview]
Message-ID: <1158045420.15465.97.camel@localhost.localdomain> (raw)
In-Reply-To: <787b0d920609120009q7b7bf47dw9d320e838cf191a@mail.gmail.com>


> If I see an io_to_io_barrier(), how am I to tell if it is
> read to read, write to write, read to write, write to read,
> read/write to read, read/write to write, read to read/write,
> write to read/write, or read/write to read/write?
> 
> Considering just reads and writes to MMIO, there are
> 9 possible types of fence. SPARC seems to cover a
> decent number of these distinctly; the instruction takes
> an immediate value as flags.

We need to decide wether a single one doing a full MMIO fence (and not
memory) is enough or if the performance different justifies maybe having
io_to_io_{wmb,rmb,mb}. I don't see any real use for more combinations.

David ? It's your call here. What do you think ?

Ben.



  reply	other threads:[~2006-09-12  7:17 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-09-12  4:30 Opinion on ordering of writel vs. stores to RAM Albert Cahalan
2006-09-12  5:30 ` Benjamin Herrenschmidt
2006-09-12  6:04   ` Albert Cahalan
2006-09-12  6:12     ` Benjamin Herrenschmidt
2006-09-12  7:09       ` Albert Cahalan
2006-09-12  7:17         ` Benjamin Herrenschmidt [this message]
2006-09-12  7:21           ` Albert Cahalan
  -- strict thread matches above, loose matches on Subject: below --
2006-09-11  5:03 Michael Chan
2006-09-11  5:21 ` Benjamin Herrenschmidt
2006-09-09  2:03 Paul Mackerras
2006-09-09  2:42 ` Linus Torvalds
2006-09-09  3:02   ` Paul Mackerras
2006-09-09  3:54     ` Linus Torvalds
2006-09-09  7:24     ` Benjamin Herrenschmidt
2006-09-09  9:34     ` David Miller
2006-09-09  9:55       ` Jeff Garzik
2006-09-09 10:08         ` David Miller
2006-09-10 17:18           ` Jesse Barnes
2006-09-10 19:35             ` Alan Cox
2006-09-10 21:25               ` Benjamin Herrenschmidt
2006-09-10 22:23                 ` Alan Cox
2006-09-10 22:18                   ` Benjamin Herrenschmidt
2006-09-11 13:19                     ` Jes Sorensen
2006-09-10 23:35                 ` Segher Boessenkool
2006-09-11  0:12                   ` Benjamin Herrenschmidt
2006-09-11  0:34                     ` Jesse Barnes
2006-09-11  1:04                       ` Benjamin Herrenschmidt
2006-09-11  1:13                       ` Segher Boessenkool
2006-09-11  1:35                         ` Benjamin Herrenschmidt
2006-09-11  9:02                     ` Alan Cox
2006-09-11  9:23                       ` Benjamin Herrenschmidt
2006-09-11  0:25                 ` Jesse Barnes
2006-09-11  0:54                   ` Segher Boessenkool
2006-09-11  1:10                     ` Benjamin Herrenschmidt
2006-09-11  1:48                       ` Segher Boessenkool
2006-09-11  3:53                         ` Benjamin Herrenschmidt
2006-09-11 18:12                     ` Jesse Barnes
2006-09-11  1:00                   ` Benjamin Herrenschmidt
2006-09-11 18:08                     ` Jesse Barnes
2006-09-11 21:32                       ` Benjamin Herrenschmidt
2006-09-10 20:01             ` Segher Boessenkool
2006-09-11 13:21               ` David Miller
2006-09-11 14:17                 ` Segher Boessenkool
2006-09-12  0:32                   ` David Miller
2006-09-12  0:49                     ` Benjamin Herrenschmidt
2006-09-12 16:47                       ` Segher Boessenkool
2006-09-12  0:54                     ` Roland Dreier
2006-09-09 11:16       ` Paul Mackerras
2006-09-09  7:23   ` Benjamin Herrenschmidt
2006-09-09  9:38     ` David Miller
2006-09-09 15:09     ` Alan Cox
2006-09-10 17:19       ` Jesse Barnes
2006-09-10 17:35         ` Michael Buesch
2006-09-10 17:49           ` Linus Torvalds
2006-09-10 18:02             ` Michael Buesch
2006-09-09 15:08   ` Alan Cox
2006-09-09 18:34   ` Auke Kok
2006-09-09 19:10     ` Patrick McFarland
2006-09-09 15:06 ` Alan Cox

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=1158045420.15465.97.camel@localhost.localdomain \
    --to=benh@kernel.crashing.org \
    --cc=acahalan@gmail.com \
    --cc=akpm@osdl.org \
    --cc=alan@lxorguk.ukuu.org.uk \
    --cc=davem@davemloft.net \
    --cc=jbarnes@virtuousgeek.org \
    --cc=jeff@garzik.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=paulus@samba.org \
    --cc=segher@kernel.crashing.org \
    --cc=torvalds@osdl.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