>  Noriyuki Soda <soda@sra.co.jp> wrote:
> 
>  > About bus_dmamap_callback_t, I think that reducing bounce memory size
>  > is certainly good thing. But it is pain if we must use callback in all
>  > cases.  (Think about hardware_scb in ahc driver.)
 

Yes, I found this to be problematic when I did the FreeBSD/CAM
version of the ISP driver. Personally, I don't see it as being
that difficult to take a flag in the alloc case that says
"alloc now or return failure", but I'll leave that up to Justin
to decide (I coped).