mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Dan Maas" <dmaas@dcine.com>
To: "Jesse Barnes" <jbarnes@sgi.com>, "David Mosberger" <davidm@hpl.hp.com>
Cc: <linux-kernel@vger.kernel.org>,
	"Benjamin Herrenschmidt" <benh@kernel.crashing.org>,
	"Ben Collins" <bcollins@debian.org>
Subject: Re: readl/writel and memory barriers
Date: Tue, 19 Feb 2002 15:11:45 -0500	[thread overview]
Message-ID: <0a5301c1b981$a921f820$1a01a8c0@allyourbase> (raw)
In-Reply-To: <092401c1b8e7$1d190660$1a01a8c0@allyourbase> <15474.34580.625864.963930@napali.hpl.hp.com> <20020219103506.A1511175@sgi.com>

Jesse Barnes wrote:
> To avoid the overhead of having I/O flushed on every
> memory barrier and readX/writeX operation, we've introduced
> mmiob() on ia64, which explicity orders I/O space accesses.
> Some ports have chosen to take the performance hit in every
> readX/writeX, memory barrier, and spinlock however
> (e.g. PPC64, MIPS).

I have a hunch that many drivers will break if you change the semantics of
readX/writeX from in-order to out-of-order - lots of drivers are only
developed & tested on x86, which completely hides the issue...

If you consider the performance cost of in-order readX/writeX to be
significant, then I would suggest adding another group of readX/writeX APIs
that explicitly allow out-of-order PCI access. (__raw_readX/__raw_writeX
seem to offer this already on some platforms...)

Regards,
Dan


  reply	other threads:[~2002-02-19 20:11 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2002-02-19  1:45 Dan Maas
2002-02-19  9:31 ` Alan Cox
2002-02-19 17:10 ` David Mosberger
2002-02-19 18:35   ` Jesse Barnes
2002-02-19 20:11     ` Dan Maas [this message]
2002-02-19 20:23       ` Jesse Barnes
2002-02-19 22:05     ` Keith Owens
2002-02-19 22:17       ` Jesse Barnes
2002-02-21  0:29       ` Randy.Dunlap
2002-02-23  4:48         ` Daniel Phillips
2002-02-25 16:19           ` Randy.Dunlap
2002-02-19 19:33   ` David Mosberger
2002-02-19 19:42     ` Jesse Barnes

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='0a5301c1b981$a921f820$1a01a8c0@allyourbase' \
    --to=dmaas@dcine.com \
    --cc=bcollins@debian.org \
    --cc=benh@kernel.crashing.org \
    --cc=davidm@hpl.hp.com \
    --cc=jbarnes@sgi.com \
    --cc=linux-kernel@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

all inboxes | Powered by JetHome®