From: Robert Hancock <hancockr@shaw.ca>
To: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Pavel Machek <pavel@ucw.cz>,
Linus Torvalds <torvalds@linux-foundation.org>,
Rene Herman <rene.herman@keyaccess.nl>,
Ingo Molnar <mingo@elte.hu>,
dpreed@reed.com, Islam Amer <pharon@gmail.com>,
hpa@zytor.com, Ingo Molnar <mingo@redhat.com>,
Andi Kleen <andi@firstfloor.org>,
Thomas Gleixner <tglx@linutronix.de>,
Linux Kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] x86: provide a DMI based port 0x80 I/O delay override
Date: Mon, 31 Dec 2007 12:21:12 -0600 [thread overview]
Message-ID: <47793318.3090803@shaw.ca> (raw)
In-Reply-To: <fa.KbCnGLPlUEYe/Ibajd+hTY7A7Qw@ifi.uio.no>
Alan Cox wrote:
>> "You plug in PCI DEBUG card and it overclocks your machine" is bad
>> scenario.. (I don't know if it does... can PCI card emulate ISA timings?)
>
> Easily. Its a bit more restricted by later spec revisions but it can halt
> your box of a week or two if it wants. Video cards used to pull this
> stunt for marketing benchmark numbers.
The drivers, specifically (the old "don't check if the command FIFO is
full before writing, just write anyway and if it's full let the whole
PCI bus stall while the FIFO empties out" trick).
I rather doubt any of those PCI POST debug cards would bother to
accurately emulate the ISA timings of normal port 0x80 accesses,
however. Most likely if you plug those in, port 0x80 accesses suddenly
become lots faster now that the writes are completing on the PCI bus
before ever hitting ISA/LPC..
--
Robert Hancock Saskatoon, SK, Canada
To email, remove "nospam" from hancockr@nospamshaw.ca
Home Page: http://www.roberthancock.com/
next prev parent reply other threads:[~2007-12-31 18:21 UTC|newest]
Thread overview: 186+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <fa.PuxU73ceCfHAUeWLO4W21Zbrm7A@ifi.uio.no>
[not found] ` <fa.ipKZdmvkNYmQ40C0cO+2u3eYohw@ifi.uio.no>
[not found] ` <fa.ppsa4qOLo1V8UlDNTucnaqIJmKA@ifi.uio.no>
[not found] ` <fa.3IG7z0AfHuLo9eQjn7Gkl/+/lnA@ifi.uio.no>
[not found] ` <fa.slc2tTnUBrTGO2aTi/C5UGHEEEM@ifi.uio.no>
[not found] ` <fa.8g+KfLLge6wS5cEnKhZJmdkIVAI@ifi.uio.no>
2007-12-30 18:22 ` [PATCH] x86: provide a DMI based port 0x80 I/O delay override Robert Hancock
[not found] ` <fa.XY5q1SY4QX+yjnE6p8T3kbTt/8I@ifi.uio.no>
[not found] ` <fa.KEBfnq5vGkAJSEhZSx7+yy+Hdbs@ifi.uio.no>
[not found] ` <fa.MLKgXLxgzIKzm4bQXjEOqg9oDwU@ifi.uio.no>
[not found] ` <fa.KbCnGLPlUEYe/Ibajd+hTY7A7Qw@ifi.uio.no>
2007-12-31 18:21 ` Robert Hancock [this message]
[not found] <9BdU5-1YW-9@gated-at.bofh.it>
[not found] ` <9BeZN-3Gf-5@gated-at.bofh.it>
[not found] ` <9BnTB-1As-31@gated-at.bofh.it>
[not found] ` <9BrX4-8go-1@gated-at.bofh.it>
[not found] ` <9BuBG-4eR-51@gated-at.bofh.it>
[not found] ` <9BvRd-6aL-71@gated-at.bofh.it>
[not found] ` <9GRQW-1DX-13@gated-at.bofh.it>
[not found] ` <9GSah-23W-1@gated-at.bofh.it>
[not found] ` <9GSDy-2GD-23@gated-at.bofh.it>
[not found] ` <9GTpK-40d-15@gated-at.bofh.it>
[not found] ` <9GUvy-5H2-11@gated-at.bofh.it>
[not found] ` <9GVKU-7SS-25@gated-at.bofh.it>
2008-01-07 19:38 ` Bodo Eggert
2008-01-07 19:46 ` H. Peter Anvin
2008-01-07 22:02 ` Bodo Eggert
2008-01-07 22:10 ` H. Peter Anvin
2008-01-07 22:27 ` Bodo Eggert
2008-01-07 22:59 ` Rene Herman
2008-01-07 23:24 ` H. Peter Anvin
2008-01-07 23:26 ` Rene Herman
2008-01-08 0:10 ` [linux-kernel] " David P. Reed
2008-01-09 21:01 ` Matthieu castet
2008-01-08 12:51 ` Bodo Eggert
2008-01-08 14:09 ` Rene Herman
2008-01-08 14:31 ` Alan Cox
2008-01-07 23:25 ` Alan Cox
2008-01-08 13:17 ` Bodo Eggert
2008-01-08 14:38 ` Alan Cox
2008-01-08 3:15 ` Christer Weinigel
[not found] <9FXbU-3M4-11@gated-at.bofh.it>
[not found] ` <9G2Om-4hg-1@gated-at.bofh.it>
[not found] ` <9G7O3-3O2-7@gated-at.bofh.it>
[not found] ` <9G8qN-4TX-13@gated-at.bofh.it>
2007-12-30 17:50 ` Bodo Eggert
2007-12-30 18:10 ` Ingo Molnar
2007-12-30 20:56 ` H. Peter Anvin
2007-12-30 21:00 ` Ingo Molnar
2007-12-30 21:32 ` Bodo Eggert
2007-12-30 21:33 ` Alan Cox
2007-12-30 22:02 ` Ingo Molnar
2007-12-30 21:44 ` H. Peter Anvin
2007-12-30 21:58 ` Rene Herman
2007-12-30 20:53 ` H. Peter Anvin
2007-12-30 21:31 ` Alan Cox
2007-12-31 14:39 ` Bodo Eggert
2007-12-31 15:56 ` Alan Cox
2007-12-30 3:34 Rene Herman
2007-12-30 9:30 ` Linus Torvalds
2007-12-30 12:48 ` Andi Kleen
2007-12-30 13:05 ` Ingo Molnar
2007-12-30 16:08 ` Andi Kleen
2007-12-30 16:28 ` Ingo Molnar
2007-12-30 18:21 ` Andi Kleen
2007-12-30 13:03 ` Ingo Molnar
2007-12-30 14:14 ` Rene Herman
2007-12-30 14:47 ` Alan Cox
2007-12-30 15:28 ` Ingo Molnar
2007-12-30 15:38 ` Alan Cox
2007-12-30 16:01 ` Ingo Molnar
2007-12-30 16:48 ` Alan Cox
2007-12-30 17:08 ` Ingo Molnar
2007-12-30 18:14 ` Rene Herman
2007-12-30 18:39 ` Alan Cox
2007-12-30 19:33 ` Rene Herman
2007-12-30 20:00 ` Linus Torvalds
2007-12-30 20:09 ` Rene Herman
2007-12-30 21:20 ` David P. Reed
2007-12-30 21:36 ` Alan Cox
2007-12-30 23:14 ` David P. Reed
2007-12-31 0:23 ` H. Peter Anvin
2007-12-31 11:59 ` Alan Cox
2007-12-31 18:19 ` H. Peter Anvin
2007-12-31 12:23 ` Alan Cox
2007-12-31 14:35 ` Rene Herman
2007-12-31 15:56 ` Alan Cox
2007-12-31 20:22 ` Ondrej Zary
2007-12-31 21:25 ` Alan Cox
2007-12-31 21:47 ` H. Peter Anvin
2007-12-31 23:24 ` Alan Cox
2007-12-31 23:41 ` H. Peter Anvin
2008-01-02 3:01 ` Rene Herman
2007-12-30 17:10 ` Juergen Beisert
2007-12-30 20:50 ` H. Peter Anvin
2007-12-31 1:03 ` David P. Reed
2007-12-31 1:40 ` H. Peter Anvin
2007-12-30 15:47 ` Rene Herman
2007-12-30 16:07 ` Ingo Molnar
2007-12-30 16:27 ` Rene Herman
2007-12-30 17:06 ` Ingo Molnar
2007-12-30 17:54 ` Rene Herman
2007-12-30 18:29 ` Alan Cox
2007-12-30 18:43 ` Andi Kleen
2007-12-30 20:46 ` Ingo Molnar
2007-12-30 21:07 ` Rene Herman
2007-12-30 21:25 ` Ingo Molnar
2007-12-30 21:29 ` Alan Cox
2007-12-30 22:03 ` Ingo Molnar
2007-12-31 13:11 ` Pavel Machek
2008-01-01 16:48 ` Ingo Molnar
2007-12-30 18:40 ` Linus Torvalds
2007-12-30 20:34 ` Ingo Molnar
2007-12-30 21:28 ` Alan Cox
2007-12-30 21:54 ` Ingo Molnar
2007-12-30 21:13 ` Alan Cox
2007-12-31 15:29 ` Christer Weinigel
2007-12-31 13:21 ` Pavel Machek
2007-12-31 12:29 ` Alan Cox
[not found] <469578CD.3080609@reed.com>
[not found] ` <1184216528.12353.203.camel@chaos>
[not found] ` <1184218962.12353.209.camel@chaos>
[not found] ` <46964352.7040301@reed.com>
[not found] ` <1184253339.12353.223.camel@chaos>
[not found] ` <469697C6.50903@reed.com>
[not found] ` <1184274754.12353.254.camel@chaos>
2007-12-14 2:59 ` [PATCH] x86_64: fix problems due to use of "outb" to port 80 on some AMD64x2 laptops, etc David P. Reed
2007-12-14 13:15 ` Ingo Molnar
2007-12-14 18:02 ` H. Peter Anvin
2007-12-14 21:06 ` Pavel Machek
2007-12-14 22:13 ` H. Peter Anvin
2007-12-14 23:29 ` Alan Cox
2007-12-15 8:08 ` Paul Rolland
2007-12-15 8:13 ` Rene Herman
2007-12-15 20:27 ` H. Peter Anvin
2007-12-15 23:26 ` [PATCH] x86: " Rene Herman
2007-12-15 23:51 ` H. Peter Anvin
2007-12-16 13:15 ` [PATCH] x86: provide a DMI based port 0x80 I/O delay override Rene Herman
2007-12-16 15:22 ` Ingo Molnar
2007-12-17 1:43 ` Rene Herman
2007-12-17 2:05 ` H. Peter Anvin
2007-12-17 2:19 ` Rene Herman
2007-12-17 3:35 ` H. Peter Anvin
2007-12-17 13:02 ` Rene Herman
2007-12-17 17:14 ` H. Peter Anvin
2007-12-17 19:43 ` David P. Reed
2007-12-17 19:55 ` H. Peter Anvin
2007-12-17 21:02 ` David P. Reed
2007-12-17 21:17 ` H. Peter Anvin
2007-12-17 21:25 ` Alan Cox
2008-01-01 15:57 ` David P. Reed
2008-01-01 21:16 ` H. Peter Anvin
2008-01-01 15:59 ` David P. Reed
2008-01-01 16:15 ` Alan Cox
2008-01-01 16:43 ` Ingo Molnar
2008-01-01 17:32 ` Alan Cox
2008-01-01 18:45 ` Ingo Molnar
2008-01-01 20:14 ` Christer Weinigel
2008-01-01 21:13 ` Alan Cox
2008-01-01 21:07 ` Alan Cox
2008-01-02 10:04 ` Ingo Molnar
2008-01-02 13:47 ` Alan Cox
2008-01-02 15:35 ` Rene Herman
2008-01-02 15:50 ` Rene Herman
2008-01-01 17:32 ` Christer Weinigel
2008-01-01 18:46 ` Ingo Molnar
2008-01-01 19:35 ` Christer Weinigel
2008-01-01 19:59 ` Rene Herman
2008-01-01 20:55 ` Christer Weinigel
2008-01-01 21:24 ` H. Peter Anvin
2008-01-01 21:01 ` Ingo Molnar
2008-01-01 21:26 ` Alan Cox
2008-01-01 21:42 ` Christer Weinigel
2008-01-01 21:42 ` Rene Herman
2008-01-01 21:50 ` H. Peter Anvin
2008-01-01 21:21 ` H. Peter Anvin
2008-01-01 23:05 ` Christer Weinigel
2008-01-01 23:12 ` Alan Cox
2008-01-02 0:23 ` Christer Weinigel
2008-01-02 10:00 ` Ingo Molnar
2008-01-01 17:32 ` David P. Reed
2008-01-01 17:38 ` Alan Cox
2008-01-01 21:15 ` H. Peter Anvin
2008-01-01 21:35 ` Rene Herman
2008-01-01 21:44 ` H. Peter Anvin
2008-01-01 22:35 ` Rene Herman
2008-01-01 22:39 ` H. Peter Anvin
2008-01-01 23:11 ` Rene Herman
2008-01-02 0:25 ` Rene Herman
2008-01-02 0:55 ` Christer Weinigel
2008-01-02 1:00 ` Rene Herman
2008-01-02 2:27 ` H. Peter Anvin
2008-01-09 17:27 ` Maciej W. Rozycki
2008-01-09 18:18 ` H. Peter Anvin
2008-01-01 17:31 ` Pavel Machek
2008-01-01 17:33 ` David P. Reed
2007-12-17 4:09 ` H. Peter Anvin
2007-12-17 10:57 ` Ingo Molnar
2007-12-17 11:29 ` Ingo Molnar
2007-12-17 13:34 ` David P. Reed
2007-12-17 12:15 ` Rene Herman
2007-12-17 13:09 ` Ingo Molnar
2007-12-17 13:22 ` Rene Herman
2007-12-17 13:31 ` Pavel Machek
2007-12-17 13:31 ` Rene Herman
2007-12-17 13:32 ` David P. Reed
2007-12-17 13:36 ` Rene Herman
2007-12-17 14:39 ` Ingo Molnar
2007-12-17 16:12 ` Alan Cox
2007-12-17 16:48 ` Ingo Molnar
2007-12-17 20:48 ` Rene Herman
2007-12-17 20:57 ` H. Peter Anvin
2007-12-17 21:33 ` Rene Herman
2007-12-17 21:40 ` H. Peter Anvin
2007-12-17 21:46 ` Ingo Molnar
2007-12-17 21:50 ` Rene Herman
2007-12-17 21:41 ` Ingo Molnar
2007-12-17 21:47 ` Rene Herman
2007-12-17 21:56 ` Ingo Molnar
2007-12-17 22:01 ` Rene Herman
2007-12-17 22:18 ` David P. Reed
2007-12-17 19:38 ` David P. Reed
2007-12-17 19:55 ` H. Peter Anvin
2007-12-17 21:28 ` Ingo Molnar
2007-12-16 21:42 ` H. Peter Anvin
2007-12-17 1:48 ` Rene Herman
2007-12-17 1:53 ` H. Peter Anvin
2007-12-16 23:12 ` David P. Reed
2007-12-17 1:56 ` Rene Herman
2007-12-17 2:04 ` H. Peter Anvin
2007-12-17 2:15 ` Rene Herman
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=47793318.3090803@shaw.ca \
--to=hancockr@shaw.ca \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=andi@firstfloor.org \
--cc=dpreed@reed.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=mingo@redhat.com \
--cc=pavel@ucw.cz \
--cc=pharon@gmail.com \
--cc=rene.herman@keyaccess.nl \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.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).