[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <45632B30.9090506@lwfinger.net>
Date: Tue, 21 Nov 2006 10:37:04 -0600
From: Larry Finger <Larry.Finger@...inger.net>
To: Andi Kleen <ak@...e.de>
CC: Ray Lee <ray-lk@...rabbit.org>, linux-kernel@...r.kernel.org
Subject: Re: Problem with DMA on x86_64 with 3 GB RAM
Andi Kleen wrote:
> Larry Finger <Larry.Finger@...inger.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
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists