Messages in this thread | | | Date | Tue, 14 Mar 2000 16:03:29 +0100 (MET) | From | Roman Zippel <> | Subject | Re: new IRQ scalability changes in 2.3.48 |
| |
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/
| |