Re: [RFC][PATCH v2 5/5] mutex: Give spinners a chance tospin_on_owner if need_resched() triggered while queued

[Jason Low]

On Mon, 2014-02-03 at 20:25 +0100, Peter Zijlstra wrote:

> +void m_spin_unlock(struct m_spinlock **lock)
> +{
> +	struct m_spinlock *node = this_cpu_ptr(&m_node);
> +	struct m_spinlock *next;
> +
> +	if (likely(cmpxchg(lock, node, NULL) == node))
> +		return;

At this current point, (node->next != NULL) is a likely scenario.
Perhaps we can also add the following code here:

	next = xchg(&node->next, NULL);
	if (next) {
		ACCESS_ONCE(next->locked) = 1;
		return;
	}

> +	next = m_spin_wait_next(lock, node, NULL);
> +	if (next)
> +		ACCESS_ONCE(next->locked) = 1;
> +}


--
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/