public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: "David S. Miller" <davem@redhat.com>
To: groudier@free.fr
Cc: gibbs@scsiguy.com, axboe@suse.de, skraw@ithnet.com,
	phillips@bonn-fries.net, linux-kernel@vger.kernel.org
Subject: Re: With Daniel Phillips Patch
Date: Wed, 22 Aug 2001 11:32:36 -0700 (PDT)	[thread overview]
Message-ID: <20010822.113236.48384121.davem@redhat.com> (raw)
In-Reply-To: <20010822195804.R610-100000@gerard>
In-Reply-To: <20010822.080540.35030343.davem@redhat.com> <20010822195804.R610-100000@gerard>

   From: G廨ard Roudier <groudier@free.fr>
   Date: Wed, 22 Aug 2001 20:21:50 +0200 (CEST)
   
   First, let me thank you a LLLOOOOOOTTTTT, David, for you PCI 64 bit
   addressing DMA-mapping. I didn't have looked yet into your patch and
   documentation update, but I will do so ASAP.
   
You're very welcome. :-)

   OTOH, it is a great pleasure for me to hear that you didn't forget what I
   told you about the current limitation of the SYM53C8XX driver. For now,
   the driver would be only able to use 40 bit addresses with all upper bits
   set to zero. This doesn't fit PCI 64 bit implementation of the Alpha
   Monster window for example, and probably doesn't fit most other non-Intel
   PCI 64 bit implementations.
   
It is fully known, in fact, I converted the sym53c8xx.c driver as
one of the examples in the patch.

Alpha can use it, in cases where memory in the system is less than
the addressing limitation of device.

Such logic would reside for Alpha port in pci_dac_cycles_ok()
definition.  IA64 and x86 could act similarly.  This was in fact
how I intended ports to implement pci_dac_cycles_ok().

   But there is an alternate solution for the SYM53C8XX driver by using up to
   16 x 32 bit segment registers. This would (will) allow to address for DMA
   16 x 4GB segments with all upper bits being settable for each 4GB segment.

Note, it relies on no 4GB crossing every occuring.  Jens and I have
decided that we will make this guarentee for devices always.  I know
of 2 devices already which have problems with this (Qlogic,FC and some
buggy variants of Tigon3 chips).

   I have this in my todo-list since months, but haven't had strong reasons
   for implementing it. The strongest reasons would be that I had access to
   64 bit machines with 64 bit PCI, but this isn't possible.

Look for someone to borrow a sparc64 system from.  Or, alternatively
send the patch to me for testing.

On sparc64, you will always be "testing all the bits" since each
DAC address to physical memory has:

	0xfffc000000000000

on the top bits.

Later,
David S. Miller
davem@redhat.com

  reply	other threads:[~2001-08-22 18:32 UTC|newest]

Thread overview: 75+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2001-08-20  8:36 aic7xxx errors with 2.4.8-ac7 on 440gx mobo Yusuf Goolamabbas
2001-08-20  8:55 ` Cliff Albert
2001-08-20 10:37   ` Alan Cox
2001-08-20 10:56     ` Yusuf Goolamabbas
2001-08-20 10:56       ` Alan Cox
2001-08-20 11:13         ` Yusuf Goolamabbas
2001-08-20 11:09           ` Alan Cox
2001-08-20 16:43             ` Doug Ledford
2001-08-20 12:46     ` Stefan Fleiter
2001-08-20 15:19       ` Ville Herva
2001-08-20 20:33         ` Justin T. Gibbs
2001-08-20 16:45       ` Doug Ledford
2001-08-20 17:23         ` Stefan Fleiter
2001-08-20 20:28       ` Justin T. Gibbs
2001-08-21 20:24         ` Stefan Fleiter
2001-08-20 16:21     ` Cliff Albert
2001-08-20 17:23       ` Peter T. Breuer
2001-08-20 17:28         ` Cliff Albert
2001-08-20 20:27   ` Justin T. Gibbs
2001-08-20 20:45     ` Cliff Albert
2001-08-20 21:04       ` Cliff Albert
2001-08-20 21:09         ` Cliff Albert
2001-08-20 21:45           ` Justin T. Gibbs
2001-08-20 22:36             ` aic7xxx with 2.4.9 on 7899P Sven Heinicke
2001-08-21 14:42               ` With Daniel Phillips Patch (was: aic7xxx with 2.4.9 on 7899P) Sven Heinicke
2001-08-21 15:08                 ` Daniel Phillips
2001-08-21 16:48                   ` Sven Heinicke
2001-08-21 17:18                     ` Justin T. Gibbs
2001-08-21 22:49                       ` Sven Heinicke
2001-08-22 13:06                         ` Gérard Roudier
2001-08-21 17:26                     ` Daniel Phillips
2001-08-21 17:55                       ` Stephan von Krawczynski
2001-08-21 18:33                         ` Justin T. Gibbs
2001-08-22  6:46                           ` Jens Axboe
2001-08-22 13:24                             ` Justin T. Gibbs
2001-08-22 15:05                               ` With Daniel Phillips Patch David S. Miller
2001-08-22 18:21                                 ` Gérard Roudier
2001-08-22 18:32                                   ` David S. Miller [this message]
2001-08-22 18:32                                 ` Justin T. Gibbs
2001-08-22 18:46                                   ` David S. Miller
2001-08-22 19:41                                     ` Justin T. Gibbs
2001-08-22 20:19                                       ` David S. Miller
2001-08-22 21:07                                     ` Gérard Roudier
2001-08-22 21:14                                       ` David S. Miller
2001-08-22 21:14                                       ` David S. Miller
2001-08-22 21:40                                       ` Justin T. Gibbs
2001-08-22 23:09                                         ` David S. Miller
2001-08-23  0:01                                           ` Justin T. Gibbs
2001-08-23  0:40                                             ` David S. Miller
2001-08-23  0:55                                               ` Justin T. Gibbs
2001-08-23  1:03                                                 ` Matthew Jacob
2001-08-23  1:08                                                 ` David S. Miller
2001-08-23  1:32                                                   ` Justin T. Gibbs
2001-08-23  1:39                                                     ` David S. Miller
2001-08-23  1:49                                                       ` Justin T. Gibbs
2001-08-21 22:44                       ` With Daniel Phillips Patch (was: aic7xxx with 2.4.9 on 7899P) Sven Heinicke
2001-08-22  0:58                         ` Daniel Phillips
2001-08-22 10:25                 ` Marcelo Tosatti
2001-08-22 16:09                   ` Sven Heinicke
2001-08-22 15:42                     ` Marcelo Tosatti
2001-08-22 20:25                       ` Sven Heinicke
2001-08-29  7:30                       ` Andrey Nekrasov
2001-09-03 14:58                         ` Marcelo Tosatti
2001-08-20 22:55             ` aic7xxx errors with 2.4.8-ac7 on 440gx mobo Cliff Albert
2001-08-21  0:36               ` Justin T. Gibbs
2001-08-21 15:34                 ` Gérard Roudier
2001-08-20 21:44         ` Justin T. Gibbs
2001-08-20 21:48           ` Cliff Albert
2001-08-25  7:15           ` Cliff Albert
  -- strict thread matches above, loose matches on Subject: below --
2001-08-23  1:06 With Daniel Phillips Patch Van Maren, Kevin
2001-08-23  1:31 ` David S. Miller
2001-08-23  1:40   ` Justin T. Gibbs
2001-08-23  1:45     ` David S. Miller
2001-08-23  2:22 Van Maren, Kevin
2001-08-23  2:26 ` David S. Miller

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=20010822.113236.48384121.davem@redhat.com \
    --to=davem@redhat.com \
    --cc=axboe@suse.de \
    --cc=gibbs@scsiguy.com \
    --cc=groudier@free.fr \
    --cc=linux-kernel@vger.kernel.org \
    --cc=phillips@bonn-fries.net \
    --cc=skraw@ithnet.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