linux-kernel - Re: more iommu sg merging fallout

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, 19 Feb 2008 19:57:58 +0900
From:	FUJITA Tomonori <fujita.tomonori@....ntt.co.jp>
To:	davem@...emloft.net
Cc:	tomof@....org, fujita.tomonori@....ntt.co.jp,
	jens.axboe@...cle.com, linux-kernel@...r.kernel.org
Subject: Re: more iommu sg merging fallout

On Sun, 17 Feb 2008 23:41:42 -0800 (PST)
David Miller <davem@...emloft.net> wrote:

> From: FUJITA Tomonori <tomof@....org>
> Date: Sat, 16 Feb 2008 15:03:43 +0900
> 
> > [PATCH] sparc64: make IOMMU code respect the segment boundary limits
> > 
> > Signed-off-by: FUJITA Tomonori <fujita.tomonori@....ntt.co.jp>
> 
> Looks good, but I think it will break sound for some ALI chips.
> 
> Please see arch/sparc64/kernel/pci.c:ali_sound_dma_hack()
> and it's caller pci_dma_supported().

Could you explain the problem a little more?

The shift argument is only used as an offset when iommu-helper decides
whether a memory area (index plus npages) spanning LLD's segment
boudnary size or not.

For example, if a device's segment boudary size is 64K, the helper see
the following value is larger than 64K or not:

((the offset + index of the IOMMU table) ((64K / 8K) - 1) + npages
--
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/