Messages in this thread | | | Date | Sat, 30 Apr 2005 15:13:14 +1000 | From | Paul Mackerras <> | Subject | Re: [RFC] unify semaphore implementations |
| |
I wrote:
> The only fast path that needs atomic_dec_if_positive is down_trylock. > You can use atomic_dec for down_trylock instead; the only downside to > that is that if somebody was holding the semaphore but nobody was > waiting, the holder will take the slow path when it does the up.
Better still, on machines without ll/sc we can do down_trylock as:
return atomic_read(&sem->count) <= 0 || atomic_add_negative(-1, &sem->count);
Then we will only take the slow path unnecessarily on up() if another cpu decrements the count between the test and the atomic_add_negative, which should be very rare. Doing the test will also avoid doing the atomic op if the semaphore is already held.
Paul. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |