linux-kernel - Re: Problem with DMA on x86

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <p73psbhay8n.fsf@bingen.suse.de>
Date:	21 Nov 2006 11:30:00 +0100
From:	Andi Kleen <ak@...e.de>
To:	Larry Finger <Larry.Finger@...inger.net>
Cc:	Ray Lee <ray-lk@...rabbit.org>, linux-kernel@...r.kernel.org
Subject: Re: Problem with DMA on x86_64 with 3 GB RAM

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.

-Andi
-
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/