[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20081014154217L.fujita.tomonori@lab.ntt.co.jp>
Date: Tue, 14 Oct 2008 15:50:02 +0900
From: FUJITA Tomonori <fujita.tomonori@....ntt.co.jp>
To: grundler@...isc-linux.org
Cc: fujita.tomonori@....ntt.co.jp, yinghai@...nel.org, matthew@....cx,
jbarnes@...tuousgeek.org, mingo@...e.hu, tglx@...utronix.de,
hpa@...or.com, akpm@...ux-foundation.org,
linux-kernel@...r.kernel.org, linux-pci@...r.kernel.org
Subject: Re: [PATCH] pci: print out DMA mask info
On Fri, 10 Oct 2008 16:45:08 -0600
Grant Grundler <grundler@...isc-linux.org> wrote:
> On Fri, Oct 10, 2008 at 11:40:56AM +0900, FUJITA Tomonori wrote:
> > IIRC, except for one SGI architecture, coherent_dma_mask is
> > meaningless, dma_mask is always equal to coherent_dma_mask.
>
> Not correct. Several PCI-X devices can only do 32-bit DMA to control
> data but can do 64-bit DMA for payload data. I don't have the list off
> the top of my head but that is the origin of coherent DMA mask.
Thanks. I misunderstood coherent_dma_mask. I needed to read several
old mails (posted in 2002 and 2003) in ia64 mailing list.
> > Lots of
> > IOMMU implementations ignore coherent_dma_mask and use dma_mask for
> > alloc_coherent().
>
> That sounds like a bug. And I don't think it's "lots".
Maybe it's not "lots" but seems that only IA64 and x86 non-hardware
IOMMU code (pci-nommu.c and GART) use coherent_dma_mask for
alloc_coherent.
--
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