> p.s.: "Red Herring"? I'd believe this except it's repeatable. If it
> were an asynchronous fault, I'd expect random death. This has died
> in the same place before, I believe.

"same place a few times" i'd still believe is a red herring.
(especially if "very nearby place" also.)

It could be that you're coming through a pretty standard code path
which starts up a DMA from an interrupt handler and then exits.  If
the device is deterministic (i.e. has a relatively fixed time between
command issue and start of DMA), i could believe seeing the same
address more than once...


Oh, that reminds me:

is there any real locking on the extent/dma mapping code?  i haven't
looked to hard, but i don't see anything right off...  who's to keep
multiple requests (e.g. from a non-interrupt context and an interrupt
context) from losing?

I don't recall seeing anything like this in the docs, and it's not
clear that it 'works' to have the driver do the locking...


> Well, "watch this space"- I'm
> reluctant to do too much remotely- but if I do and wedge the 8200,
> I guess it'll be time come and work on it more.

Heh.


chris