From: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
To: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>,
Linus Torvalds <torvalds@transmeta.com>,
davidm@hpl.hp.com, linux-kernel@vger.kernel.org
Subject: Re: PATCH 2.5.x disable BAR when sizing
Date: Mon, 23 Dec 2002 00:05:42 +0300 [thread overview]
Message-ID: <20021223000542.C30070@localhost.park.msu.ru> (raw)
In-Reply-To: <m1of7dltso.fsf@frodo.biederman.org>; from ebiederm@xmission.com on Sun, Dec 22, 2002 at 12:47:51PM -0700
On Sun, Dec 22, 2002 at 12:47:51PM -0700, Eric W. Biederman wrote:
> Not if it is an NMI or an SCI interrupt. The latter on x86 places
> the cpu in System Management Mode, and what the cpu does from that
> point forward is out of our control.
>
> Though disabling cpu controlled IRQs help if you are dealing
> with any normal IRQs.
I meant the timer interrupt in the first place. I assumed it's the
only one that does matter on this stage of the boot process.
What else could happen (in the real world terms)?
> The window needs to be small from the PCI bus perspective, not in cpu
> clocks. Write, Read, Write is only something like 9 PCI bus clocks.
No, the window is huge from the PCI bus perspective.
IIRC, PCI config read/write on x86 works like this (I may be wrong though):
i/o port write (BAR address) ~1us
i/o port read (BAR value after writing ~0) ~1us
i/o port write (BAR address) ~1us
i/o port write (saved BAR value) ~1us
It's a little bit more than 9 PCI clocks. Am I missing something?
Ivan.
next prev parent reply other threads:[~2002-12-22 20:57 UTC|newest]
Thread overview: 78+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-12-19 21:37 PATCH 2.5.x disable BAR when sizing Grant Grundler
2002-12-20 2:54 ` Alan Cox
2002-12-20 2:27 ` David Mosberger
2002-12-20 6:05 ` Linus Torvalds
2002-12-20 19:50 ` Grant Grundler
2002-12-20 20:14 ` Linus Torvalds
2002-12-20 21:22 ` Grant Grundler
2002-12-21 18:34 ` Maciej W. Rozycki
2002-12-20 20:37 ` Richard B. Johnson
2002-12-20 21:29 ` Grant Grundler
2002-12-20 5:57 ` Linus Torvalds
2002-12-20 9:42 ` David Mosberger
2002-12-20 12:53 ` Ivan Kokshaysky
2002-12-20 17:05 ` Linus Torvalds
2002-12-20 18:26 ` David Mosberger
2002-12-20 19:28 ` Linus Torvalds
2002-12-21 22:06 ` Eric W. Biederman
2002-12-21 22:44 ` Linus Torvalds
2002-12-22 7:15 ` Paul Mackerras
2002-12-22 15:03 ` Benjamin Herrenschmidt
2002-12-22 19:21 ` Ivan Kokshaysky
2002-12-23 0:29 ` Paul Mackerras
2002-12-23 15:26 ` Ivan Kokshaysky
2003-01-05 12:37 ` [patch 2.5] PCI: allow alternative methods for probing the BARs Ivan Kokshaysky
2003-01-06 0:29 ` Anton Blanchard
2003-01-06 4:14 ` Linus Torvalds
2003-01-06 5:22 ` Eric W. Biederman
2003-01-06 10:31 ` Benjamin Herrenschmidt
2003-01-06 11:32 ` Andrew Walrond
2003-01-06 22:01 ` Grant Grundler
2003-01-06 19:45 ` Grant Grundler
2003-01-07 17:05 ` Ivan Kokshaysky
2003-01-07 17:46 ` Linus Torvalds
2003-01-07 20:17 ` Grant Grundler
2003-01-08 14:47 ` Ivan Kokshaysky
2003-01-08 22:34 ` Grant Grundler
2003-01-06 15:33 ` Ivan Kokshaysky
2003-01-06 21:52 ` Grant Grundler
2003-01-06 23:19 ` Linus Torvalds
2003-01-07 0:13 ` Grant Grundler
2003-01-07 12:33 ` Alan Cox
2003-01-07 17:27 ` Ivan Kokshaysky
2003-01-07 18:46 ` Alan Cox
2003-01-07 17:44 ` Linus Torvalds
2003-01-08 16:55 ` Ivan Kokshaysky
2003-01-09 17:46 ` [patch 2.5] 2-pass PCI probing, generic part Ivan Kokshaysky
2003-01-09 17:52 ` Benjamin Herrenschmidt
2003-01-09 22:09 ` Ivan Kokshaysky
2003-01-09 22:16 ` Linus Torvalds
2003-01-09 22:26 ` Benjamin Herrenschmidt
2003-01-10 3:49 ` Alan Cox
2003-01-09 23:19 ` Ivan Kokshaysky
2003-01-09 23:35 ` Linus Torvalds
2003-01-10 1:09 ` Grant Grundler
2003-01-10 7:56 ` Eric W. Biederman
2003-01-10 19:00 ` Grant Grundler
2003-01-10 21:42 ` Ivan Kokshaysky
2003-01-10 23:07 ` Grant Grundler
2003-01-11 19:39 ` Scott Murray
2003-01-12 7:19 ` Greg KH
2003-01-13 6:28 ` Scott Murray
2003-01-10 13:35 ` Ivan Kokshaysky
2003-01-14 16:39 ` Ivan Kokshaysky
2003-01-09 18:36 ` David Mosberger
2003-01-09 19:52 ` Grant Grundler
2003-01-09 22:40 ` Ivan Kokshaysky
2003-01-09 17:48 ` [patch 2.5] 2-pass PCI probing, hotplug changes Ivan Kokshaysky
2003-01-09 17:51 ` [patch 2.5] 2-pass PCI probing, i386 USB quirk Ivan Kokshaysky
2003-01-07 17:12 ` [patch 2.5] PCI: allow alternative methods for probing the BARs Ivan Kokshaysky
2003-01-07 17:06 ` Ivan Kokshaysky
2002-12-22 19:51 ` PATCH 2.5.x disable BAR when sizing Linus Torvalds
2002-12-22 19:57 ` Eric W. Biederman
2002-12-22 10:38 ` Eric W. Biederman
2002-12-22 18:39 ` Ivan Kokshaysky
2002-12-22 19:47 ` Eric W. Biederman
2002-12-22 21:05 ` Ivan Kokshaysky [this message]
2002-12-20 18:50 ` Ivan Kokshaysky
2002-12-20 19:11 ` 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=20021223000542.C30070@localhost.park.msu.ru \
--to=ink@jurassic.park.msu.ru \
--cc=davidm@hpl.hp.com \
--cc=ebiederm@xmission.com \
--cc=linux-kernel@vger.kernel.org \
--cc=torvalds@transmeta.com \
/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