I hope the OpenBSD folks are monitoring this exchange. The exact same
topic (even wrt the same h/w) came up on one of their mailing lists
recently.

On Tue, 11 Feb 2003, Jason R Thorpe wrote:

> On Tue, Feb 11, 2003 at 12:35:01PM -0500, Stephan Uphoff wrote:
>
>  > The i82257 driver ignores this problem and just illegally calls
>  > bus_dmamap_sync with
>  > BUS_DMASYNC_POSTXXXX flags with full knowledge that the DMA might not have
>  > completed.
>  > ( When it finds out that the DMA did not complete it just calls bus_dmamap_sync
>  > again with BUS_DMASYNC_PREXXXX op flags)
>
> This is not illegal... this is an acceptable/intended use of the interface
> (I should know -- I designed the interface and wrote the code that you're
> citing :-)
>
> --
>         -- Jason R. Thorpe <thorpej@wasabisystems.com>
>