On Mon, 2010-02-15 at 15:06 +1100, Anton Blanchard wrote: > > Yeah that was my primary concern. Right now these things fail 100%, so > no one is relying on it. The worry is if people start writing their own > crazy low level system call + locking stubs that might work most of the > time (if we remove the stwcx in syscall exit).
Worse than that. It will look like it works, but it won't really since the dangling reservation matches a completely unrelated lwarx done by the kernel and not the original userspace one, so the stwcx. might succeed despite the fact that the original value -was- changed. So it's really a matter of documentation I suppose but we have to be careful as I've learned with time that there is nothing too silly for userspace to do :-) > Good point, I hadn't thought of signals and I agree we'd need to clear the > reservation in the sigreturn path. Right. As I said, I'm pretty sure it will happen as a side effect of other things but I'd rather pay the small price of having an explicit blurb to do it in sigreturn regardless. Cheers, Ben. _______________________________________________ Linuxppc-dev mailing list [email protected] https://lists.ozlabs.org/listinfo/linuxppc-dev
