I'm no miata wizard either, but the following might help folks:

Hal Murray <murray@pa.dec.com> writes:
> The PCI-PCI bridge breaks transfers at page boundaries so that prevents 
> the bug.

Actually, it breaks them up on "cache line boundaries" if i recall,
and those will always be small (relative to the page size) powers of
two, so it has the effect of making sure things are broken at page
boundaries (as well as a lot of other places), at a performance cost.


> I think only the 2 64 bit slots are not behind the bridge. 
> 
> I think the firmware knows that some cards don't provoke the problem.  
> If it finds anything else in either of the two 64 bit slots, it complains.
>
> I think there is some command to disable that complaint.  I don't 
> know if that's wise with your card.

Search for "set_pci_device_override" on mail-index.netbsd.org.
That should probably help.  (Note that I don't think i've ever
personally used a miata, so i can't say that i've done this myself.)



chris
-- 
Chris Demetriou - cgd@netbsd.org - http://www.netbsd.org/People/Pages/cgd.html
Disclaimer: Not speaking for NetBSD, just expressing my own opinion.