public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Larry Finger <Larry.Finger@lwfinger.net>
To: Alan <alan@lxorguk.ukuu.org.uk>
Cc: Ray Lee <ray-lk@madrabbit.org>, LKML <linux-kernel@vger.kernel.org>
Subject: Re: Problem with DMA on x86_64 with 3 GB RAM
Date: Tue, 21 Nov 2006 10:34:56 -0600	[thread overview]
Message-ID: <45632AB0.60507@lwfinger.net> (raw)
In-Reply-To: <20061121112829.19a9c043@localhost.localdomain>

Alan wrote:
>> Confused. As in, once the bcm43xx module initcall happens? Or without bcm43xx
>> at all? If the former, is the behavior different when built as a module versus
>> built-in? (ie, are there ordering problems.)
> 
> The pci_dma code on the x86_64 platform is broken for the case of PCI
> devices with < 32bit DMA. Has been forever, this is a problem with
> various devices, although most of the others are obsolete except for the
> bcm43xx and b44 (the latter has hacks to work around the x86-64
> brokenness).
> 
> At the very least the pci_set_dma_mask should error in this situation or
> switch to using GFP_DMA (24bit) memory spaces. Having it error isn't the
> whole solution as you still need some way to handle the "what do I do
> next". 

I agree that pci_set_dma_mask should at least return an error. That will protect the ignorant!

Thanks for the pointer to the b44 code. I'll try to fix bcm43xx the same way.

Larry

  reply	other threads:[~2006-11-21 16:35 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-11-15 19:01 bcm43xx regression 2.6.19rc3 -> rc5, rtnl_lock trouble? Ray Lee
2006-11-15 19:15 ` Michael Buesch
2006-11-15 19:41   ` Ray Lee
2006-11-16  2:51     ` Larry Finger
2006-11-16  5:51       ` Ray Lee
2006-11-18 11:24 ` Joseph Fannin
2006-11-18 16:55   ` Johannes Berg
2006-11-18 17:05     ` Larry Finger
2006-11-18 17:27       ` Ray Lee
2006-11-18 18:30         ` Adrian Bunk
2006-11-21  6:21           ` Ray Lee
2006-11-18 19:02         ` Larry Finger
2006-11-19 16:01           ` Michael Buesch
2006-12-12  4:06           ` ieee80211 sleeping in invalid context Ray Lee
2006-12-12  9:14             ` Michael Buesch
2006-12-12 17:51               ` Ray Lee
2006-12-12 18:31                 ` Larry Finger
2006-11-19  6:15         ` Problem with DMA on x86_64 with 3 GB RAM Larry Finger
2006-11-21  4:38           ` Ray Lee
2006-11-21 11:28             ` Alan
2006-11-21 16:34               ` Larry Finger [this message]
2006-11-21 10:30           ` Andi Kleen
2006-11-21 16:37             ` Larry Finger
2006-11-21 16:46               ` Andi Kleen
2006-11-21 18:27                 ` Alan
2006-11-21 18:31                   ` Andi Kleen
2006-11-21 20:04                     ` Alan

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=45632AB0.60507@lwfinger.net \
    --to=larry.finger@lwfinger.net \
    --cc=alan@lxorguk.ukuu.org.uk \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ray-lk@madrabbit.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