Hi,
> oops, i missed that indeed, darn. Hm., there are not all that many such
> places though, and the value itself is cached in current->processor anyway
> (and 'current' can be cached across reschedules). I cannot see any easy
> way to avoid this bug in any 'automatic' way though. How can we prevent
> writing a 'semi-constant' to a local variable, possibly at compile-time?
At some point we should convert current->processor into a structure
anyway. On the cpus I know a current->processor->data is cheaper than a
globalarray[current->processor] (indexed addressing mode, no index*
sizeof(..)) and it's also automatically in seperate cache lines. Then we
could also add some lock to prevent rescheduling from the current cpu
while accessing current->processor.
bye, Roman
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Wed Mar 15 2000 - 21:00:28 EST