From: Larry Finger <Larry.Finger@lwfinger.net>
To: Andi Kleen <ak@suse.de>
Cc: Ray Lee <ray-lk@madrabbit.org>, linux-kernel@vger.kernel.org
Subject: Re: Problem with DMA on x86_64 with 3 GB RAM
Date: Tue, 21 Nov 2006 10:37:04 -0600 [thread overview]
Message-ID: <45632B30.9090506@lwfinger.net> (raw)
In-Reply-To: <p73psbhay8n.fsf@bingen.suse.de>
Andi Kleen wrote:
> Larry Finger <Larry.Finger@lwfinger.net> writes:
>
>> I am trying to debug a bcm43xx DMA problem on an x86_64 system with 3
>> GB RAM. Depending on the particular chip and its implementation, dma
>> transfers may use 64-, 32-, or 30-bit addressing, with the problem
>> interface using 30-bit addressing. From test prints, the correct mask
>> (0x3FFFFFFF) is supplied to pci_set_dma_mask and
>> pci_set_consistent_dma_mask. Neither call returns an error. In
>> addition, several x86_64 systems with more than 1 GB RAM have worked
>> with the current code.
>
> 30bit DMA has be bounced through GFP_DMA. The driver needs special
> code for this. You can look at the b44 driver for a working reference.
>
> The pci_dma_* interfaces on x86-64 only support masks >= 0xffffffff,
> anything smaller has to be handled manually.
Thanks for the info. I obviously get to devote some effort to seeing how the b44 code handles the
same problem.
Shouldn't this problem be mentioned somewhere in the documentation, or did I miss something?
Larry
next prev parent reply other threads:[~2006-11-21 16:37 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
2006-11-21 10:30 ` Andi Kleen
2006-11-21 16:37 ` Larry Finger [this message]
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=45632B30.9090506@lwfinger.net \
--to=larry.finger@lwfinger.net \
--cc=ak@suse.de \
--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