From: "Richard B. Johnson" <root@chaos.analogic.com>
To: Vladimir Kondratiev <vladimir.kondratiev@intel.com>
Cc: arjanv@redhat.com, Jeff Garzik <jgarzik@pobox.com>,
Linus Torvalds <torvalds@osdl.org>,
greg@kroah.com, linux-kernel@vger.kernel.org,
Alan Cox <alan@redhat.com>,
Marcelo Tosatti <marcelo@conectiva.com.br>,
Martin Mares <mj@ucw.cz>
Subject: Re: PCI Express support for 2.4 kernel
Date: Tue, 16 Dec 2003 19:12:23 -0500 (EST) [thread overview]
Message-ID: <Pine.LNX.4.53.0312161906340.23063@chaos> (raw)
In-Reply-To: <3FDF898D.2060902@intel.com>
On Wed, 17 Dec 2003, Vladimir Kondratiev wrote:
> Arjan van de Ven wrote:
>
> >>>+ /* dummy read to flush PCI write */
> >>>+ readb(addr);
> >>>
> >>>
> >>This is going to choke some hardware, I guarantee.
> >>
> >>You always want to make sure your flush is of the same size at the
> >>write. Reading a byte from an address that the hardware defines as
> >>"32-bit writes only" can get ugly real quick ;-)
> >>
> >>
> >
> >also reading back addr might not be the best choice in case some
> >registers have side effects on reading, it's probably better to read
> >back an address that is known to be ok to read (like the vendor ID
> >field)
> >
> >
> >
> Good idea!
You should not abitrarily flush all the writes with a read
after each write. The PCI/Bus is a FIFO, stuff will get to
the hardware in the order written. If you "flush" every write,
you will seriously hurt the performance. I don't like that
MACRO/Function, whatever it is with the switch shown previously.
All that code just for a "@(*^&$(*^(" write will screw up
performance. I've looked at the result of some the the MACRO
expansions, in particular the get_user, put_user, and copy_to/from
macros where there is a switch. It is not pre-processed out.
Cheers,
Dick Johnson
Penguin : Linux version 2.4.22 on an i686 machine (797.90 BogoMips).
Note 96.31% of all statistics are fiction.
next prev parent reply other threads:[~2003-12-17 0:09 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-12-14 20:00 PCI Express support for 2.4 kernel Vladimir Kondratiev
2003-12-14 20:46 ` Jeff Garzik
2003-12-15 10:01 ` Vladimir Kondratiev
2003-12-15 10:31 ` Gabriel Paubert
2003-12-15 12:44 ` Vladimir Kondratiev
2003-12-15 13:15 ` Arjan van de Ven
2003-12-15 13:58 ` Vladimir Kondratiev
2003-12-15 14:31 ` Arjan van de Ven
2003-12-15 14:44 ` Brian Gerst
2003-12-15 18:40 ` Greg KH
2003-12-15 19:23 ` Alan Cox
2003-12-15 20:00 ` Linus Torvalds
2003-12-16 10:20 ` Vladimir Kondratiev
2003-12-16 16:47 ` Linus Torvalds
2003-12-17 6:30 ` Vladimir Kondratiev
2003-12-17 6:46 ` Linus Torvalds
2003-12-17 6:55 ` Jeff Garzik
2003-12-17 7:24 ` Vladimir Kondratiev
2003-12-17 16:17 ` Linus Torvalds
2003-12-17 8:22 ` Arjan van de Ven
2003-12-17 10:35 ` Martin Mares
2003-12-17 23:06 ` Alan Cox
2003-12-17 10:08 ` Geert Uytterhoeven
2003-12-17 15:54 ` Linus Torvalds
2003-12-17 16:14 ` Geert Uytterhoeven
2003-12-17 17:44 ` Dan Hopper
2003-12-17 18:14 ` Vladimir Kondratiev
2003-12-17 21:44 ` Martin Mares
2003-12-16 17:10 ` Jeff Garzik
2003-12-16 17:48 ` Arjan van de Ven
2003-12-16 17:55 ` Jeff Garzik
2003-12-16 22:39 ` Vladimir Kondratiev
2003-12-17 0:12 ` Richard B. Johnson [this message]
2003-12-16 21:59 ` Vladimir Kondratiev
2003-12-16 17:45 ` Greg KH
2003-12-16 22:14 ` Vladimir Kondratiev
2003-12-17 10:05 ` Geert Uytterhoeven
2003-12-15 15:57 ` Vladimir Kondratiev
2003-12-15 10:42 ` Martin Mares
2003-12-15 10:07 ` Greg KH
2003-12-15 11:20 ` Vladimir Kondratiev
[not found] <12InT-wQ-5@gated-at.bofh.it>
[not found] ` <135Nw-5gv-3@gated-at.bofh.it>
[not found] ` <137wc-q1-23@gated-at.bofh.it>
2003-12-15 21:56 ` Andi Kleen
2003-12-15 22:48 ` Vladimir Kondratiev
2003-12-15 23:06 ` Andi Kleen
2003-12-15 23:14 ` Greg KH
-- strict thread matches above, loose matches on Subject: below --
2003-12-15 20:08 Nakajima, Jun
[not found] <Pine.LNX.4.44.0312150917170.32061-100000@coffee.psychology.mcmaster.ca>
2003-12-15 15:52 ` Vladimir Kondratiev
2003-12-15 16:08 ` Kevin P. Fleming
2003-12-15 16:38 ` Vladimir Kondratiev
2003-12-15 16:55 ` Richard B. Johnson
2003-12-15 17:08 ` Tomas Szepe
2003-12-15 18:03 ` Richard B. Johnson
2003-12-15 18:15 ` Tomas Szepe
2003-12-15 18:35 ` Richard B. Johnson
2003-12-15 18:43 ` Keith Owens
2003-12-15 18:45 ` Tomas Szepe
2003-12-15 17:24 ` Vladimir Kondratiev
2003-12-15 17:22 ` Randy.Dunlap
2003-12-15 18:16 ` Greg KH
2003-12-15 18:20 ` Richard B. Johnson
2003-12-15 17:09 ` Keith Owens
2003-12-15 17:38 ` Tomas Szepe
2003-12-15 18:16 ` Keith Owens
2003-12-15 18:23 ` Tomas Szepe
[not found] <12KJ6-4F2-13@gated-at.bofh.it>
[not found] ` <12Lvu-5X5-5@gated-at.bofh.it>
[not found] ` <12XQ2-7Vs-9@gated-at.bofh.it>
2003-12-15 10:17 ` Andi Kleen
[not found] ` <12YsA-nt-1@gated-at.bofh.it>
[not found] ` <130kQ-3A0-13@gated-at.bofh.it>
[not found] ` <130Xy-4Ia-3@gated-at.bofh.it>
[not found] ` <131Ac-5Qy-3@gated-at.bofh.it>
[not found] ` <137cD-8eg-9@gated-at.bofh.it>
[not found] ` <13kD2-1kF-11@gated-at.bofh.it>
2003-12-16 17:44 ` Andi Kleen
[not found] ` <13r1S-3FB-11@gated-at.bofh.it>
[not found] ` <13vyg-43O-7@gated-at.bofh.it>
2003-12-16 22:18 ` Andi Kleen
[not found] ` <13qIi-31G-1@gated-at.bofh.it>
[not found] ` <13DvZ-2RY-9@gated-at.bofh.it>
[not found] ` <13DFw-3a8-9@gated-at.bofh.it>
[not found] ` <13DPq-3s4-7@gated-at.bofh.it>
[not found] ` <13Fem-6iy-7@gated-at.bofh.it>
[not found] ` <13SY1-35z-19@gated-at.bofh.it>
2003-12-17 23:22 ` Andi Kleen
2003-12-17 23:38 ` Alan Cox
[not found] ` <12XQc-7Vs-29@gated-at.bofh.it>
[not found] ` <12Z5u-1tG-11@gated-at.bofh.it>
2003-12-15 14:58 ` Andi Kleen
2003-12-15 15:40 ` Vladimir Kondratiev
[not found] <3FDCA569.5070006@pobox.com>
2003-12-15 4:47 ` Pete Zaitcev
2003-12-14 17:28 Vladimir Kondratiev
2003-12-15 7:48 ` Christoph Hellwig
2003-12-15 18:26 ` Linus Torvalds
2003-12-15 20:03 ` Jeff Garzik
2003-12-15 22:00 ` Linus Torvalds
2003-12-16 4:53 ` Jeff Garzik
2003-12-15 20:21 ` Vladimir Kondratiev
2003-12-15 20:36 ` Jeff Garzik
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=Pine.LNX.4.53.0312161906340.23063@chaos \
--to=root@chaos.analogic.com \
--cc=alan@redhat.com \
--cc=arjanv@redhat.com \
--cc=greg@kroah.com \
--cc=jgarzik@pobox.com \
--cc=linux-kernel@vger.kernel.org \
--cc=marcelo@conectiva.com.br \
--cc=mj@ucw.cz \
--cc=torvalds@osdl.org \
--cc=vladimir.kondratiev@intel.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;
as well as URLs for NNTP newsgroup(s).