linux-kernel - Re: [PATCH 0/7] x86 dma_*

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: <20080812164914.GC4342@8bytes.org>
Date:	Tue, 12 Aug 2008 18:49:14 +0200
From:	Joerg Roedel <joro@...tes.org>
To:	Muli Ben-Yehuda <muli@...ibm.com>
Cc:	Joerg Roedel <joerg.roedel@....com>, mingo@...hat.com,
	tglx@...utronix.de, hpa@...or.com, linux-kernel@...r.kernel.org,
	iommu@...ts.linux-foundation.org, andi@...stfloor.org
Subject: Re: [PATCH 0/7] x86 dma_*_coherent rework patchset

On Tue, Aug 12, 2008 at 07:06:58PM +0300, Muli Ben-Yehuda wrote:
> [added Andi to CC]
> 
> On Tue, Aug 12, 2008 at 05:24:10PM +0200, Joerg Roedel wrote:
> > Hi,
> > 
> > this patchset reworks the dma_*_coherent functions in the DMA layer
> > for the x86 architecture. The patch series extends the existing DMA
> > backends with missing *coherent callbacks and simplifies the generic
> > function to basically only call the registered backend. This allows
> > future optimizations in hardware specific IOMMU implementations.
> > The code ist tested on AMD64 with AMD IOMMU and GART as well as on
> > my old 486 box. It is not yet tested on a Calgary IOMMU system.
> 
> Now it is---appears to work fine on a Calgary system.
> 
> In general the patchset looks good and is definitely a step in the
> right direction. I am a bit concerned about the contortions that the
> generic dma_alloc_coherent went through before calling the ops
> version---have you verified they are no longer needed?

Most of the logic in the old dma_alloc_coherent function is moved to the
specific IOMMU implementations now. The old function tried to handle all
cases, hardware IOMMU, GART and NOMMU in one function which made it a
bit hard to read. This logic is split up and moved to the specific DMA
backends now.

Joerg

--
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/