Re: sem_lock() vs qspinlocks

[Peter Zijlstra <peterz@infradead.org>]

On Thu, May 19, 2016 at 10:39:26PM -0700, Davidlohr Bueso wrote:

> However, this is semantically different to
> what was previously done with ticket locks in that spin_unlock_wait() will always observe
> all waiters by adding itself to the tail.


static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
{
	__ticket_t head = READ_ONCE(lock->tickets.head);

	for (;;) {
		struct __raw_tickets tmp = READ_ONCE(lock->tickets);
		/*
		 * We need to check "unlocked" in a loop, tmp.head == head
		 * can be false positive because of overflow.
		 */
		if (__tickets_equal(tmp.head, tmp.tail) ||
				!__tickets_equal(tmp.head, head))
			break;

		cpu_relax();
	}
}


I'm not seeing that (although I think I agreed yesterday on IRC). Note
how we observe the head and then loop until either the lock is unlocked
(head == tail) or simply head isn't what it used to be.

And head is the lock holder end of the queue; see arch_spin_unlock()
incrementing it.

So the ticket lock too should only wait for the current lock holder to
go away, not any longer.