Re: [PATCH 3/6] locking/rwsem: Rework writer wakeup

[Peter Zijlstra <peterz@infradead.org>]

On Thu, Feb 23, 2023 at 01:26:45PM +0100, Peter Zijlstra wrote:
> +/*
> + * This function must be called with the sem->wait_lock held to prevent
> + * race conditions between checking the rwsem wait list and setting the
> + * sem->count accordingly.
> + *
> + * Implies rwsem_del_waiter() on success.
> + */
> +static void rwsem_writer_wake(struct rw_semaphore *sem,
> +			      struct rwsem_waiter *waiter,
> +			      struct wake_q_head *wake_q)
> +{
> +	struct rwsem_waiter *first = rwsem_first_waiter(sem);
> +	long count, new;
> +
> +	lockdep_assert_held(&sem->wait_lock);
> +
> +	count = atomic_long_read(&sem->count);
> +	do {
> +		bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF);
> +
> +		if (has_handoff) {
> +			/*
> +			 * Honor handoff bit and yield only when the first
> +			 * waiter is the one that set it. Otherwisee, we
> +			 * still try to acquire the rwsem.
> +			 */
> +			if (first->handoff_set && (waiter != first))
> +				return;
> +		}
> +
> +		new = count;
> +
> +		if (count & RWSEM_LOCK_MASK) {
> +			/*
> +			 * A waiter (first or not) can set the handoff bit
> +			 * if it is an RT task or wait in the wait queue
> +			 * for too long.
> +			 */
> +			if (has_handoff || (!rt_task(waiter->task) &&
> +					    !time_after(jiffies, waiter->timeout)))
> +				return;
> +
> +			new |= RWSEM_FLAG_HANDOFF;
> +		} else {
> +			new |= RWSEM_WRITER_LOCKED;
> +			new &= ~RWSEM_FLAG_HANDOFF;
> +
> +			if (list_is_singular(&sem->wait_list))
> +				new &= ~RWSEM_FLAG_WAITERS;
> +		}
> +	} while (!atomic_long_try_cmpxchg_acquire(&sem->count, &count, new));
> +
> +	/*
> +	 * We have either acquired the lock with handoff bit cleared or set
> +	 * the handoff bit. Only the first waiter can have its handoff_set
> +	 * set here to enable optimistic spinning in slowpath loop.
> +	 */
> +	if (new & RWSEM_FLAG_HANDOFF) {
> +		first->handoff_set = true;
> +		lockevent_inc(rwsem_wlock_handoff);
> +		return;
> +	}
> +
> +	/*
> +	 * Have rwsem_writer_wake() fully imply rwsem_del_waiter() on
> +	 * success.
> +	 */
> +	list_del(&waiter->list);
> +	rwsem_set_owner(sem);

At the very least this needs to be:

	atomic_long_set(&sem->owner, (long)waiter->task);

> +	rwsem_waiter_wake(waiter, wake_q);
> +}