On Mon, 28 Aug 2000, Andrea Arcangeli wrote:
> Returning to your patch you're introducing an SMP race in the wait
> event interface. We enforced that wake_up had to provide an implicit
> memory barrier to avoid adding an explicit memory barrier in the
> middle of things like UnlockPage. [...]
yep, these are the cases i'm worried about as well. I thought that in all
cases where we use a waitqueue we do have some other synchronized object
as well (which administers the event/object we are waiting for) so in 99%
of the cases we dont rely on the synchronization of the wake_up() itself.
Isnt UnlockPage() atomic already (and a read/write barrier) to keep the
bits themselves consistent?
we have a number of other places that rely on clear_bit() being atomic -
if this isnt true anymore on Alpha then we could make it nonatomic on x86
as well - this would be a great micro-optimization eg. in the ext2fs code
[and other places]. We attempted this in early 2.3 but it was an obviously
broken thing.
Ingo
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Thu Aug 31 2000 - 21:00:21 EST