From: Alan Cox <alan@lxorguk.ukuu.org.uk>
To: Robert Hancock <hancockr@shaw.ca>
Cc: Linus Torvalds <torvalds@osdl.org>,
linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: Memory barriers and spin_unlock safety
Date: Sun, 12 Mar 2006 18:09:12 +0000 [thread overview]
Message-ID: <1142186952.20056.8.camel@localhost.localdomain> (raw)
In-Reply-To: <441225B7.5010003@shaw.ca>
On Gwe, 2006-03-10 at 19:19 -0600, Robert Hancock wrote:
> PCI I/O writes are allowed to be posted by the host bus bridge (not
> other bridges) according to the PCI 2.2 spec. Maybe no x86 platform
> actually does this, but it's allowed, so technically a device would need
> to do a read in order to ensure that I/O writes have arrived at the
> device as well.
Existing Linux drivers largely believe that PCI I/O cycles as opposed to
MMIO cycles are not posted. At least one MIPS platform that did post
them ended up ensuring PCI I/O cycle posting didn't occur to get a
running Linux system - so its quite a deep assumption.
next prev parent reply other threads:[~2006-03-12 18:03 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <5Ml19-2Ki-19@gated-at.bofh.it>
[not found] ` <5MlO0-3JU-13@gated-at.bofh.it>
[not found] ` <5MCF0-2TS-27@gated-at.bofh.it>
[not found] ` <5MITJ-2l4-15@gated-at.bofh.it>
[not found] ` <5NXxl-6WZ-9@gated-at.bofh.it>
[not found] ` <5NY0h-7wa-1@gated-at.bofh.it>
2006-03-11 1:19 ` Robert Hancock
2006-03-12 18:09 ` Alan Cox [this message]
2006-03-03 16:03 David Howells
2006-03-03 16:45 ` David Howells
2006-03-03 17:03 ` Linus Torvalds
2006-03-06 9:06 ` Helge Hafting
2006-03-03 20:02 ` Arjan van de Ven
2006-03-03 20:17 ` David Howells
2006-03-03 21:34 ` Linus Torvalds
2006-03-03 21:51 ` Benjamin LaHaise
2006-03-03 22:21 ` Linus Torvalds
2006-03-03 22:36 ` Linus Torvalds
2006-03-07 17:36 ` David Howells
2006-03-07 17:40 ` Matthew Wilcox
2006-03-07 17:56 ` Jesse Barnes
2006-03-07 18:18 ` Alan Cox
2006-03-07 18:28 ` Linus Torvalds
2006-03-07 18:55 ` Alan Cox
2006-03-07 20:21 ` Linus Torvalds
2006-03-03 16:55 ` Linus Torvalds
2006-03-03 21:06 ` Benjamin Herrenschmidt
2006-03-03 21:18 ` Hollis Blanchard
2006-03-03 21:52 ` David S. Miller
2006-03-03 22:04 ` Linus Torvalds
2006-03-04 10:58 ` Paul Mackerras
2006-03-04 22:49 ` Benjamin Herrenschmidt
2006-03-04 10:58 ` Paul Mackerras
2006-03-04 17:28 ` Linus Torvalds
2006-03-08 3:20 ` Paul Mackerras
2006-03-08 3:54 ` Linus Torvalds
2006-03-08 13:12 ` Alan Cox
2006-03-08 15:30 ` Linus Torvalds
2006-03-05 2:04 ` Michael Buesch
2006-03-03 20:15 ` David Howells
2006-03-03 21:31 ` Linus Torvalds
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=1142186952.20056.8.camel@localhost.localdomain \
--to=alan@lxorguk.ukuu.org.uk \
--cc=hancockr@shaw.ca \
--cc=linux-kernel@vger.kernel.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
Powered by JetHome