Subject: Re: ISA bounce buffer/DMA interface
To: Chris G Demetriou <Chris_G_Demetriou@BALVENIE.PDL.CS.CMU.EDU>
From: Juergen Hannken-Illjes <>
List: tech-kern
Date: 09/15/1995 14:55:02
> > Main change is the introduction of a 'sizes' array to hold the size
> > for each 'mappings' entry. The result will be an array of (phys addr, size)
> > pairs. This is a more general representation for scattered DMA segments.
> (2) as the interface was specified, the sizes of the elements were
>     implicitly defined.  the DMA map function, and friends, mapped
>     from VA -> ISA bus PA, with the assumptions that:
> 	(1) the virtual addresses were contiguous, and that,
Right, this assumption has not changed.

> 	(2) there is some correspondence between system physical
> 	    pages (or virtual pages) and ISA bus 'pages.'
Yes, this is assumed to be a one-by-one mapping of pages.

>     in other words:
> 	(1) the interface was _NOT_ meant to do sub-page-size
> 	    scatter-gather DMA; as far as i can tell, that's not
> 	    possible on any ISA implementation i've seen.  (though
> 	    the Alpha, for instance, _does_ allow one to do
> 	    scatter-gather DMA with 8k (system page size) granularity.
And here it comes. I did the implementation for an Adaptec 1542C (aha1542.c).
Like many other BUSMASTER DMA controllers this device would be able to do
byte-size scatter-gather DMA. The main reason for the 'sizes' is a more
general interface and simpler usage because there is no need to collect
the 'mappings' returned from 'isadma_map' into individual segments for
scatter-gather DMA.
Throughout the whole kernel scatter-gather is done on (addr,size) pairs.

> 	    If a given piece of hardware can do scatter-gather
> 	    DMA, then one should call the map/copy/unmap functions
> 	    multiple times (at the appropriate times!), once each
> 	    for each 'piece' of the scatter-gather DMA.
Sorry, this is impossible for BUSMASTER DMA. There is no notifaction when
one segment is done. There will be a notification when ALL scatter-gather
segments have ben transferred.

> 	(2) system pages will not be 'intertwined' on the ISA bus.
> cgd

Juergen Hannken-Illjes - - TU Braunschweig (W Germany)