I wrote:
> - Use the ohci->event_lock to serialize the trigger for software-
> enforced bus resets against a large portion of the IRQ handler.
...
> Todo:
> - Test.
> - Audit *all* of ohci1394's register accesses for the need of
> serialization by spinlocks + mmiowb.
...
PS: AFAIU what I'm doing here, it affects
- bus resets triggered by local software (the bug report was also
about externally triggered bus resets),
- and potentially bus resets (even externally triggered ones) on SMP
systems with (PCI) bridges if the IRQ handler migrates to a another
CPU between two interrupt events in quick succession.
Can the latter happen in Linux or/and with -rt kernels?
--
Stefan Richter
-=====-=-=== ---= ==-=-
http://arcgraph.de/sr/
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
