netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: Jeff Garzik <jeff@garzik.org>
Cc: Ingo Oeser <netdev@axxeo.de>, Anton Blanchard <anton@samba.org>,
	Brice Goglin <brice@myri.com>,
	netdev@vger.kernel.org, gallatin@myri.com,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH 3/4] myri10ge - Driver core
Date: Fri, 26 May 2006 20:56:04 +1000	[thread overview]
Message-ID: <1148640964.8089.147.camel@localhost.localdomain> (raw)
In-Reply-To: <4476D8E3.40101@garzik.org>

On Fri, 2006-05-26 at 06:30 -0400, Jeff Garzik wrote:
> Benjamin Herrenschmidt wrote:
> >>> No proper interface exposed, he'll have to do an #ifdef powerpc here or
> >>> such and use __ioremap with explicit page attributes. I have a hack to
> >>> do that automatically for memory covered by prefetchable PCI BARs when
> >>> mmap'ing from userland but not for kernel ioremap.
> >> Stupid question: pci_iomap() is NOT what you are looking for, right?
> >>
> >> Implementation is at the end of lib/iomap.c
> > 
> > No, there is no difference there, pci_iomap won't help for passing in
> > platform specific page attributes for things like write combining.
> 
> Since we already have ioremap_nocache(), maybe adding ioremap_wcomb() is 
> appropriate?

Yes, but be careful there.. on ppc, not setting the page "guarded" bit
will enable write combining on various CPUs but will also enable
speculative reads, prefetch, etc... so it's not "just" WC, you have to
know for sure what you are doing with that memory (basically, enable
side-effects).

Ben.



  reply	other threads:[~2006-05-26 10:56 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-05-17 22:02 [PATCH 0/4] myri10ge - Myri-10G Ethernet driver - v2 Brice Goglin
2006-05-17 22:03 ` [PATCH 1/4] myri10ge - Revive pci_find_ext_capability Brice Goglin
2006-05-17 22:04 ` [PATCH 2/4] myri10ge - Driver header files Brice Goglin
2006-05-17 22:28   ` Randy.Dunlap
2006-05-18 23:36     ` Brice Goglin
2006-05-17 22:06 ` [PATCH 3/4] myri10ge - Driver core Brice Goglin
2006-05-17 22:36   ` Roland Dreier
2006-05-18 23:38     ` Brice Goglin
2006-05-17 23:08   ` Arnd Bergmann
2006-05-18 23:56     ` Brice Goglin
2006-05-19  1:55       ` Arnd Bergmann
2006-05-19  2:25         ` Brice Goglin
2006-05-19 10:00           ` Arnd Bergmann
2006-05-19 11:09             ` Andi Kleen
2006-05-19 15:48               ` Brice Goglin
2006-05-20  7:58                 ` Brice Goglin
2006-05-19 14:39     ` Brice Goglin
2006-05-19 23:15     ` Brice Goglin
2006-05-20  0:01       ` Andi Kleen
2006-05-23 15:39   ` Anton Blanchard
2006-05-24  8:04     ` Brice Goglin
2006-05-24 21:21       ` Anton Blanchard
2006-05-25  7:59       ` Benjamin Herrenschmidt
2006-05-25  9:07         ` Brice Goglin
2006-05-25  7:56     ` Benjamin Herrenschmidt
2006-05-26  9:49       ` Ingo Oeser
2006-05-26 10:02         ` Benjamin Herrenschmidt
2006-05-26 10:30           ` Jeff Garzik
2006-05-26 10:56             ` Benjamin Herrenschmidt [this message]
2006-05-17 22:07 ` [PATCH 4/4] myri10ge - Kconfig and Makefile Brice Goglin

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=1148640964.8089.147.camel@localhost.localdomain \
    --to=benh@kernel.crashing.org \
    --cc=anton@samba.org \
    --cc=brice@myri.com \
    --cc=gallatin@myri.com \
    --cc=jeff@garzik.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@axxeo.de \
    --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).