Re: [patch 05/15] Generic Mutex Subsystem, mutex-core.patch

[Steven Rostedt]

On Mon, 2005-12-19 at 02:37 +0100, Ingo Molnar wrote:
> +/*
> + * We can speed up the lock-acquire, if the architecture
> + * supports cmpxchg and if there's no debugging state
> + * to be set up (!DEBUG_MUTEXESS).
> + *
> + * trick: we can use cmpxchg on the release side too, if bit
> + * 0 of lock->owner is set if there is at least a single pending

I think you mean lock->count and not lock->owner (you're getting your
patches mixed up ;)


> + * task in the wait_list. This way the release atomic-fastpath
> + * can be a mirror image of the acquire path:
> + */
> +#if defined(__HAVE_ARCH_CMPXCHG) && !defined(CONFIG_DEBUG_MUTEXESS)
> +# define MUTEX_LOCKLESS_FASTPATH
> +#endif
> +

-- Steve


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/