Re: [RFC PATCH 3/3] sched: Implement shared wakequeue in CFS

[Peter Zijlstra]

On Tue, Jun 13, 2023 at 12:20:04AM -0500, David Vernet wrote:
> +struct swqueue {
> +	struct list_head list;
> +	spinlock_t lock;
> +} ____cacheline_aligned;
> +
>  #ifdef CONFIG_SMP
> +static struct swqueue *rq_swqueue(struct rq *rq)
> +{
> +	return rq->cfs.swqueue;
> +}
> +
> +static struct task_struct *swqueue_pull_task(struct swqueue *swqueue)
> +{
> +	unsigned long flags;
> +
> +	struct task_struct *p;
> +
> +	spin_lock_irqsave(&swqueue->lock, flags);
> +	p = list_first_entry_or_null(&swqueue->list, struct task_struct,
> +				     swqueue_node);
> +	if (p)
> +		list_del_init(&p->swqueue_node);
> +	spin_unlock_irqrestore(&swqueue->lock, flags);
> +
> +	return p;
> +}
> +
> +static void swqueue_enqueue(struct rq *rq, struct task_struct *p, int enq_flags)
> +{
> +	unsigned long flags;
> +	struct swqueue *swqueue;
> +	bool task_migrated = enq_flags & ENQUEUE_MIGRATED;
> +	bool task_wakeup = enq_flags & ENQUEUE_WAKEUP;
> +
> +	/*
> +	 * Only enqueue the task in the shared wakequeue if:
> +	 *
> +	 * - SWQUEUE is enabled
> +	 * - The task is on the wakeup path
> +	 * - The task wasn't purposefully migrated to the current rq by
> +	 *   select_task_rq()
> +	 * - The task isn't pinned to a specific CPU
> +	 */
> +	if (!task_wakeup || task_migrated || p->nr_cpus_allowed == 1)
> +		return;
> +
> +	swqueue = rq_swqueue(rq);
> +	spin_lock_irqsave(&swqueue->lock, flags);
> +	list_add_tail(&p->swqueue_node, &swqueue->list);
> +	spin_unlock_irqrestore(&swqueue->lock, flags);
> +}
> +
>  static int swqueue_pick_next_task(struct rq *rq, struct rq_flags *rf)
>  {
> -	return 0;
> +	struct swqueue *swqueue;
> +	struct task_struct *p = NULL;
> +	struct rq *src_rq;
> +	struct rq_flags src_rf;
> +	int ret;
> +
> +	swqueue = rq_swqueue(rq);
> +	if (!list_empty(&swqueue->list))
> +		p = swqueue_pull_task(swqueue);
> +
> +	if (!p)
> +		return 0;
> +
> +	rq_unpin_lock(rq, rf);
> +	raw_spin_rq_unlock(rq);
> +
> +	src_rq = task_rq_lock(p, &src_rf);
> +
> +	if (task_on_rq_queued(p) && !task_on_cpu(rq, p))
> +		src_rq = migrate_task_to(src_rq, &src_rf, p, cpu_of(rq));
> +
> +	if (src_rq->cpu != rq->cpu)
> +		ret = 1;
> +	else
> +		ret = -1;
> +
> +	task_rq_unlock(src_rq, p, &src_rf);
> +
> +	raw_spin_rq_lock(rq);
> +	rq_repin_lock(rq, rf);
> +
> +	return ret;
>  }
>  
>  static void swqueue_remove_task(struct task_struct *p)
> -{}
> +{
> +	unsigned long flags;
> +	struct swqueue *swqueue;
> +
> +	if (!list_empty(&p->swqueue_node)) {
> +		swqueue = rq_swqueue(task_rq(p));
> +		spin_lock_irqsave(&swqueue->lock, flags);
> +		list_del_init(&p->swqueue_node);
> +		spin_unlock_irqrestore(&swqueue->lock, flags);
> +	}
> +}
>  
>  /*
>   * For asym packing, by default the lower numbered CPU has higher priority.

*sigh*... pretty much all, if not all of this is called with rq->lock
held. So why the irqsave and big fat fail for using spinlock :-(