NAPI 流程

napi 流程记录

1、初始化一个napi_struct 结构。此时 NAPI的状态为 NAPI_STATE_SCHED状态。。

void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
		    int (*poll)(struct napi_struct *, int), int weight)
{
	INIT_LIST_HEAD(&napi->poll_list);
	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
	napi->timer.function = napi_watchdog;
	init_gro_hash(napi);
	napi->skb = NULL;
	INIT_LIST_HEAD(&napi->rx_list);
	napi->rx_count = 0;
	napi->poll = poll;
	if (weight > NAPI_POLL_WEIGHT)
		netdev_err_once(dev, "%s() called with weight %d\n", __func__,
				weight);
	napi->weight = weight;
	list_add(&napi->dev_list, &dev->napi_list);
	napi->dev = dev;
#ifdef CONFIG_NETPOLL
	napi->poll_owner = -1;
#endif
	set_bit(NAPI_STATE_SCHED, &napi->state);//初始化为NAPI_STATE_SCHED状态
	napi_hash_add(napi);
}

2、使能一个napi_struct, napi_enable. 此时NAPI的状态全被清除

static inline void napi_enable(struct napi_struct *n)
{
	BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
	smp_mb__before_atomic();
	clear_bit(NAPI_STATE_SCHED, &n->state);
	clear_bit(NAPI_STATE_NPSVC, &n->state);
}

3、网卡硬件中断产生， 执行中断处理函数，并调用
bool napi_schedule_prep(struct napi_struct *n);和 napi_schedule。
napi_schedule_prep 检测NAPI状态是否是NAPI_STATE_SCHED或NAPI_STATE_DISABLE状态，是的话就返回，不是则设置NAPI 为NAPI_STATE_SCHED状态，然后执行napi_schedule，将NAPI挂到队列里面，触发一个软件中断。

//网卡接收中断处理函数
irqreturn xxx_intr (int irq, xxx *data)
{
    if (likely(napi_schedule_prep(&data->napi_rx))) {
        __napi_schedule(&data->napi_rx);
    } else {
        //clear irq
    }
return IRQ_HANDLED;
}
void __napi_schedule(struct napi_struct *n)
{
	unsigned long flags;

	local_irq_save(flags);
	____napi_schedule(this_cpu_ptr(&softnet_data), n);
	local_irq_restore(flags);
}
static inline void ____napi_schedule(struct softnet_data *sd,
				     struct napi_struct *napi)
{
    //将NAPI加入软件中断的poll_list链表里面
	list_add_tail(&napi->poll_list, &sd->poll_list); 
	//发出一个软件中断
	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
}

4、处理软件中断， 此时状态仍为 NAPI_STATE_SCHED状态

static __latent_entropy void net_rx_action(struct softirq_action *h)
{
	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
	unsigned long time_limit = jiffies +
		usecs_to_jiffies(netdev_budget_usecs);
	int budget = netdev_budget;
	LIST_HEAD(list);
	LIST_HEAD(repoll);

	local_irq_disable();
	list_splice_init(&sd->poll_list, &list);
	local_irq_enable();

	for (;;) { //轮训NAPI 队列
		struct napi_struct *n;

		if (list_empty(&list)) {
			if (!sd_has_rps_ipi_waiting(sd) && list_empty(&repoll))
				goto out;
			break;
		}
         //取出一个NAPI 
		n = list_first_entry(&list, struct napi_struct, poll_list);
		//执行poll操作
		budget -= napi_poll(n, &repoll);

		/* If softirq window is exhausted then punt.
		 * Allow this to run for 2 jiffies since which will allow
		 * an average latency of 1.5/HZ.
		 */
		if (unlikely(budget <= 0 ||
			     time_after_eq(jiffies, time_limit))) {
			sd->time_squeeze++;
			break;
		}
	}

	local_irq_disable();

	list_splice_tail_init(&sd->poll_list, &list);
	list_splice_tail(&repoll, &list);
	list_splice(&list, &sd->poll_list);
	if (!list_empty(&sd->poll_list))
		__raise_softirq_irqoff(NET_RX_SOFTIRQ);

	net_rps_action_and_irq_enable(sd);
out:
	__kfree_skb_flush();
}

//将NAPI节点从队列里面删除，再执行驱动自己注册的收包回调
static int napi_poll(struct napi_struct *n, struct list_head *repoll)
{
	void *have;
	int work, weight;

    //先从队列里面删除
	list_del_init(&n->poll_list);

	have = netpoll_poll_lock(n);

	weight = n->weight;

	/* This NAPI_STATE_SCHED test is for avoiding a race
	 * with netpoll's poll_napi().  Only the entity which
	 * obtains the lock and sees NAPI_STATE_SCHED set will
	 * actually make the ->poll() call.  Therefore we avoid
	 * accidentally calling ->poll() when NAPI is not scheduled.
	 */
	work = 0;
	if (test_bit(NAPI_STATE_SCHED, &n->state)) {
		work = n->poll(n, weight);//调用我们驱动里面注册的回调
		trace_napi_poll(n, work, weight);
	}

	WARN_ON_ONCE(work > weight);

	if (likely(work < weight))
		goto out_unlock;

	/* Drivers must not modify the NAPI state if they
	 * consume the entire weight.  In such cases this code
	 * still "owns" the NAPI instance and therefore can
	 * move the instance around on the list at-will.
	 */
	if (unlikely(napi_disable_pending(n))) {
		napi_complete(n);
		goto out_unlock;
	}

	if (n->gro_bitmask) {
		/* flush too old packets
		 * If HZ < 1000, flush all packets.
		 */
		napi_gro_flush(n, HZ >= 1000);
	}

	gro_normal_list(n);

	/* Some drivers may have called napi_schedule
	 * prior to exhausting their budget.
	 */
	if (unlikely(!list_empty(&n->poll_list))) {
		pr_warn_once("%s: Budget exhausted after napi rescheduled\n",
			     n->dev ? n->dev->name : "backlog");
		goto out_unlock;
	}

	list_add_tail(&n->poll_list, repoll);

out_unlock:
	netpoll_poll_unlock(have);

	return work;
}

4、执行驱动收报回调，最后掉用napi_complete,将NAPI NAPIF_STATE_SCHED 状态清除.

bool napi_complete(struct napi_struct *n, int work_done)
{
	unsigned long flags, val, new;

	/*
	 * 1) Don't let napi dequeue from the cpu poll list
	 *    just in case its running on a different cpu.
	 * 2) If we are busy polling, do nothing here, we have
	 *    the guarantee we will be called later.
	 */
	if (unlikely(n->state & (NAPIF_STATE_NPSVC |
				 NAPIF_STATE_IN_BUSY_POLL)))
		return false;

	if (n->gro_bitmask) {
		unsigned long timeout = 0;

		if (work_done)
			timeout = n->dev->gro_flush_timeout;

		/* When the NAPI instance uses a timeout and keeps postponing
		 * it, we need to bound somehow the time packets are kept in
		 * the GRO layer
		 */
		napi_gro_flush(n, !!timeout);
		if (timeout)
			hrtimer_start(&n->timer, ns_to_ktime(timeout),
				      HRTIMER_MODE_REL_PINNED);
	}

	gro_normal_list(n);

	if (unlikely(!list_empty(&n->poll_list))) {
		/* If n->poll_list is not empty, we need to mask irqs */
		local_irq_save(flags);
		list_del_init(&n->poll_list);
		local_irq_restore(flags);
	}

	do {
		val = READ_ONCE(n->state);

		WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));

		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED);

		/* If STATE_MISSED was set, leave STATE_SCHED set,
		 * because we will call napi->poll() one more time.
		 * This C code was suggested by Alexander Duyck to help gcc.
		 */
		new |= (val & NAPIF_STATE_MISSED) / NAPIF_STATE_MISSED *
						    NAPIF_STATE_SCHED;
	} while (cmpxchg(&n->state, val, new) != val);

	if (unlikely(val & NAPIF_STATE_MISSED)) {
		__napi_schedule(n);
		return false;
	}

	return true;
}