On Wednesday 07 January 2009, Woodruff, Richard wrote: > I don't mind using a read back dependency. I don't like it but > that may be necessary in some cases for a given device. > > What I don't like is constantly hitting them and getting a broken > system. How many of these are out there? If we can remove most > of them in current software with SO then that isn't a bad tradeoff.
The same issue comes up with PCI drivers though ... and there, it's routinely accepted that critical paths in (some) drivers need to issue readbacks to flush the relevant posted writes. That's *especially* true in IRQ paths, and when DMA engines update state in shared memory. Which says to me that grumbling about strongly ordered regions is more of a developer discipline/training problem than any kind of real technical issue. Not unlike how to do locking right; or satisfy coding style guidelines; or follow correct procedures to merge patches; or synchronize between several execution contexts; or ... lots of other things that waste time when folk don't bother doing them right at first. Good drivers are not easy to do, and this is just one of the many ways that shows up. Fortunately *this* class of problem tends to be easy to address by a careful code audit. - Dave -- To unsubscribe from this list: send the line "unsubscribe linux-omap" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
