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]

Date:	Tue, 21 Nov 2006 10:34:56 -0600
From:	Larry Finger <Larry.Finger@...inger.net>
To:	Alan <alan@...rguk.ukuu.org.uk>
CC:	Ray Lee <ray-lk@...rabbit.org>, LKML <linux-kernel@...r.kernel.org>
Subject: Re: Problem with DMA on x86_64 with 3 GB RAM

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
-
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/