Re: [PATCH 14/31] sched_ext: Implement BPF extensible scheduler class

[Barret Rhoden]

hi -

On 11/30/22 03:22, Tejun Heo wrote:
[...]
> +static bool consume_dispatch_q(struct rq *rq, struct rq_flags *rf,
> +			       struct scx_dispatch_q *dsq)
> +{
> +	struct scx_rq *scx_rq = &rq->scx;
> +	struct task_struct *p;
> +	struct rq *task_rq;
> +	bool moved = false;
> +retry:
> +	if (list_empty(&dsq->fifo))
> +		return false;
> +
> +	raw_spin_lock(&dsq->lock);
> +	list_for_each_entry(p, &dsq->fifo, scx.dsq_node) {
> +		task_rq = task_rq(p);
> +		if (rq == task_rq)
> +			goto this_rq;
> +		if (likely(rq->online) && !is_migration_disabled(p) &&
> +		    cpumask_test_cpu(cpu_of(rq), p->cpus_ptr))
> +			goto remote_rq;
> +	}
> +	raw_spin_unlock(&dsq->lock);
> +	return false;
> +
> +this_rq:
> +	/* @dsq is locked and @p is on this rq */
> +	WARN_ON_ONCE(p->scx.holding_cpu >= 0);
> +	list_move_tail(&p->scx.dsq_node, &scx_rq->local_dsq.fifo);
> +	dsq->nr--;
> +	scx_rq->local_dsq.nr++;
> +	p->scx.dsq = &scx_rq->local_dsq;
> +	raw_spin_unlock(&dsq->lock);
> +	return true;
> +
> +remote_rq:
> +#ifdef CONFIG_SMP
> +	/*
> +	 * @dsq is locked and @p is on a remote rq. @p is currently protected by
> +	 * @dsq->lock. We want to pull @p to @rq but may deadlock if we grab
> +	 * @task_rq while holding @dsq and @rq locks. As dequeue can't drop the
> +	 * rq lock or fail, do a little dancing from our side. See
> +	 * move_task_to_local_dsq().
> +	 */
> +	WARN_ON_ONCE(p->scx.holding_cpu >= 0);
> +	list_del_init(&p->scx.dsq_node);
> +	dsq->nr--;
> +	p->scx.holding_cpu = raw_smp_processor_id();
> +	raw_spin_unlock(&dsq->lock);
> +
> +	rq_unpin_lock(rq, rf);
> +	double_lock_balance(rq, task_rq);
> +	rq_repin_lock(rq, rf);
> +
> +	moved = move_task_to_local_dsq(rq, p);

you might be able to avoid the double_lock_balance() by using 
move_queued_task(), which internally hands off the old rq lock and 
returns with the new rq lock.

the pattern for consume_dispatch_q() would be something like:

- kfunc from bpf, with this_rq lock held
- notice p isn't on this_rq, goto remote_rq:
- do sched_ext accounting, like the this_rq->dsq->nr--
- unlock this_rq
- p_rq = task_rq_lock(p)
- double_check p->rq didn't change to this_rq during that unlock
- new_rq = move_queued_task(p_rq, rf, p, new_cpu)
- do sched_ext accounting like new_rq->dsq->nr++
- unlock new_rq
- relock the original this_rq
- return to bpf

you still end up grabbing both locks, but just not at the same time.

plus, task_rq_lock() takes the guesswork out of whether you're getting 
p's rq lock or not.  it looks like you're using the holding_cpu to 
handle the race where p moves cpus after you read task_rq(p) but before 
you lock that task_rq.  maybe you can drop the whole concept of the 
holding_cpu?

thanks,
barret


> +
> +	double_unlock_balance(rq, task_rq);
> +#endif /* CONFIG_SMP */
> +	if (likely(moved))
> +		return true;
> +	goto retry;
> +}