public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Jeremy Higdon <jeremy@sgi.com>
To: Greg KH <greg@kroah.com>
Cc: Jesse Barnes <jbarnes@sgi.com>,
	Grant Grundler <grundler@parisc-linux.org>,
	Matthew Wilcox <willy@debian.org>,
	linux-pci@atrey.karlin.mff.cuni.cz, linux-kernel@vger.kernel.org
Subject: Re: [RFC] Relaxed PIO read vs. DMA write ordering
Date: Wed, 7 Jan 2004 16:08:51 -0800	[thread overview]
Message-ID: <20040108000850.GA339772@sgi.com> (raw)
In-Reply-To: <20040107232754.GA2807@kroah.com>

On Wed, Jan 07, 2004 at 03:27:54PM -0800, Greg KH wrote:
> On Wed, Jan 07, 2004 at 03:07:12PM -0800, Jesse Barnes wrote:
> > 
> >   1) add pcix_enable_relaxed() and read_relaxed() (read() would always be
> >      ordered)
> 
> This probably preserves the current situation best, enabling driver
> writers to be explicit in knowing what is happening.
> 
> thanks,
> 
> greg k-h

I like this best too.  That way, a driver can enable a relaxed read
in the performance path and not have to audit the other reads.

So in a generic PCI driver, you'd call pcix_enable_relaxed() and
then use read() for initialization, error recovery, etc., and
use read_relaxed() in the main execution path where it is determined
to be safe.

The default would be the standard behavior that we have.

One question I have is what the need for pcix_enable_relaxed() is.
Are we thinking that this sets some bit in one or more registers?
What happens if you use read_relaxed() and you didn't call
pcix_enable_relaxed() previously?

jeremy

  parent reply	other threads:[~2004-01-08  0:09 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2004-01-07 17:58 [RFC] Relaxed PIO read vs. DMA write ordering Jesse Barnes
2004-01-07 19:02 ` Matthew Wilcox
2004-01-07 22:21   ` Grant Grundler
2004-01-07 23:07     ` Jesse Barnes
2004-01-07 23:27       ` Greg KH
2004-01-07 23:56         ` Jesse Barnes
2004-01-08  0:34           ` Jesse Barnes
2004-01-08  0:08         ` Jeremy Higdon [this message]
2004-01-08 10:01         ` Jes Sorensen
2004-01-08  6:38       ` Grant Grundler
2004-01-08 16:23         ` Leonid Grossman
2004-01-08 17:39           ` Jesse Barnes
2004-01-08 17:54           ` Christoph Hellwig
2004-01-08 19:48             ` Leonid Grossman
2004-01-08 17:36         ` Jesse Barnes
2004-01-08 18:44           ` Grant Grundler
2004-01-09  7:13             ` Jeremy Higdon
2004-01-09 19:51               ` Jesse Barnes
2004-01-09 23:15                 ` Jesse Barnes
2004-01-09 20:02               ` Grant Grundler
2004-01-11 14:34             ` James Bottomley
2004-01-09  7:39           ` Jochen Friedrich
2004-01-09 20:27             ` Grant Grundler
2004-01-09 22:12               ` Ivan Kokshaysky
2004-01-07 22:58   ` 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=20040108000850.GA339772@sgi.com \
    --to=jeremy@sgi.com \
    --cc=greg@kroah.com \
    --cc=grundler@parisc-linux.org \
    --cc=jbarnes@sgi.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@atrey.karlin.mff.cuni.cz \
    --cc=willy@debian.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