Date: Fri, 13 Sep 2002 15:39:16 -0400
From: Adam Kropelin <akropel1@rochester.rr.com>
To: linux-kernel@vger.kernel.org
Subject: Streaming DMA mapping question
Message-ID: <20020913193916.GA5004@www.kroptech.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
User-Agent: Mutt/1.3.28i
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1140
Lines: 30

I'm working on revamping the DMA mapping of a driver and have been reading
Documentation/DMA-Mapping.txt and becoming one with it. On i386 I notice the
following discrepency:

According to the docs, you should either unmap or sync your DMA buffer before
touching it from the host. The i386 implementation of pci_unmap is empty --no
problem; there must not be any unmap work to do on this arch. But the 
implementation of pci_dma_sync does contain a flush_write_buffers() call. This
makes me think that perhaps if I'm going to modify the buffer before I submit it
back to the controller I need to do:

/* so I can read it; not necessary on i386 */
pci_dma_sync_single(...);

fiddle_with_buffer(...);

/* so adapter sees my changes; this is necessary on i386 */
pci_dma_sync_single(...);

Otherwise I don't see why it is safe to touch the buffer after pci_unmap.

Someone lend me a clue?

--Adam
 
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/