内核收包流程(5.10内核)

1 函数__netif_receive_skb_core

此函数是所有收包流程的统一入口，所以此函数非常关键

static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
				    struct packet_type **ppt_prev)
{
	struct packet_type *ptype, *pt_prev;
	rx_handler_func_t *rx_handler;
	struct sk_buff *skb = *pskb;
	struct net_device *orig_dev;
	bool deliver_exact = false;
	int ret = NET_RX_DROP;
	__be16 type;

	net_timestamp_check(!netdev_tstamp_prequeue, skb);

	trace_netif_receive_skb(skb);

	orig_dev = skb->dev;

	/* 重置skb的各协议层指针，疑问：
	1、为什么网络层无脑reset，传输层要为0才reset呢？
	2、transport_header为0时，为什么reset之后指向网络层，而不是传输层？
	3、为什么要reset mac_len，却相信mac_header一定正确？ */
	skb_reset_network_header(skb); //此时data指向网络层，所以data-head就是网络层偏移
	if (!skb_transport_header_was_set(skb))
		skb_reset_transport_header(skb);
	skb_reset_mac_len(skb);//skb->mac_header由驱动在调用eth_type_trans时设置

	pt_prev = NULL;

another_round:
	skb->skb_iif = skb->dev->ifindex;

	__this_cpu_inc(softnet_data.processed);//收包统计，可以通过/proc/net/softnet_stat查看

	/* XDP报文处理，没弄清楚使用场景 */
	if (static_branch_unlikely(&generic_xdp_needed_key)) {
		int ret2;

		preempt_disable();
		ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb);
		preempt_enable();

		if (ret2 != XDP_PASS) {
			ret = NET_RX_DROP;
			goto out;
		}
		skb_reset_mac_len(skb);
	}

	/* 如果是tag报文，则调用skb_vlan_untag剥掉tag，主要工作：
	1、skb->vlan_proto记录vlan协议类型，skb->vlan_tci记录vlan ID和优先级，skb->vlan_present置为1;
	2、skb->protocol指向报文的协议，比如IP
	3、memmove将skb修改成untag报文
	4、重置network_header、transport_header和mac_len */
	if (skb->protocol == cpu_to_be16(ETH_P_8021Q) ||
	    skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
		skb = skb_vlan_untag(skb);
		if (unlikely(!skb))
			goto out;
	}

	if (skb_skip_tc_classify(skb))
		goto skip_classify;

	if (pfmemalloc)
		goto skip_taps;

	list_for_each_entry_rcu(ptype, &ptype_all, list) {
		if (pt_prev)
			ret = deliver_skb(skb, pt_prev, orig_dev);
		pt_prev = ptype;
	}

	list_for_each_entry_rcu(ptype, &skb->dev->ptype_all, list) {
		if (pt_prev)
			ret = deliver_skb(skb, pt_prev, orig_dev);
		pt_prev = ptype;
	}

skip_taps:
#ifdef CONFIG_NET_INGRESS
	if (static_branch_unlikely(&ingress_needed_key)) {
		bool another = false;

		skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev,
					 &another);
		if (another)
			goto another_round;
		if (!skb)
			goto out;

		if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0)
			goto out;
	}
#endif
	skb_reset_redirect(skb);
skip_classify:
	if (pfmemalloc && !skb_pfmemalloc_protocol(skb))
		goto drop;

	if (skb_vlan_tag_present(skb)) {
		if (pt_prev) {
			ret = deliver_skb(skb, pt_prev, orig_dev);
			pt_prev = NULL;
		}
		if (vlan_do_receive(&skb))
			goto another_round;
		else if (unlikely(!skb))
			goto out;
	}

	rx_handler = rcu_dereference(skb->dev->rx_handler);
	if (rx_handler) {
		if (pt_prev) {
			ret = deliver_skb(skb, pt_prev, orig_dev);
			pt_prev = NULL;
		}
		switch (rx_handler(&skb)) {
		case RX_HANDLER_CONSUMED:
			ret = NET_RX_SUCCESS;
			goto out;
		case RX_HANDLER_ANOTHER:
			goto another_round;
		case RX_HANDLER_EXACT:
			deliver_exact = true;
		case RX_HANDLER_PASS:
			break;
		default:
			BUG();
		}
	}

	if (unlikely(skb_vlan_tag_present(skb)) && !netdev_uses_dsa(skb->dev)) {
check_vlan_id:
		if (skb_vlan_tag_get_id(skb)) {
			/* Vlan id is non 0 and vlan_do_receive() above couldn't
			 * find vlan device.
			 */
			skb->pkt_type = PACKET_OTHERHOST;
		} else if (skb->protocol == cpu_to_be16(ETH_P_8021Q) ||
			   skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
			/* Outer header is 802.1P with vlan 0, inner header is
			 * 802.1Q or 802.1AD and vlan_do_receive() above could
			 * not find vlan dev for vlan id 0.
			 */
			__vlan_hwaccel_clear_tag(skb);
			skb = skb_vlan_untag(skb);
			if (unlikely(!skb))
				goto out;
			if (vlan_do_receive(&skb))
				/* After stripping off 802.1P header with vlan 0
				 * vlan dev is found for inner header.
				 */
				goto another_round;
			else if (unlikely(!skb))
				goto out;
			else
				/* We have stripped outer 802.1P vlan 0 header.
				 * But could not find vlan dev.
				 * check again for vlan id to set OTHERHOST.
				 */
				goto check_vlan_id;
		}
		/* Note: we might in the future use prio bits
		 * and set skb->priority like in vlan_do_receive()
		 * For the time being, just ignore Priority Code Point
		 */
		__vlan_hwaccel_clear_tag(skb);
	}

	type = skb->protocol;

	/* deliver only exact match when indicated */
	if (likely(!deliver_exact)) {
		deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
				       &ptype_base[ntohs(type) &
						   PTYPE_HASH_MASK]);
	}

	deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
			       &orig_dev->ptype_specific);

	if (unlikely(skb->dev != orig_dev)) {
		deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
				       &skb->dev->ptype_specific);
	}

	if (pt_prev) {
		if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
			goto drop;
		*ppt_prev = pt_prev;
	} else {
drop:
		if (!deliver_exact)
			atomic_long_inc(&skb->dev->rx_dropped);
		else
			atomic_long_inc(&skb->dev->rx_nohandler);
		kfree_skb(skb);
		/* Jamal, now you will not able to escape explaining
		 * me how you were going to use this. :-)
		 */
		ret = NET_RX_DROP;
	}

out:
	/* The invariant here is that if *ppt_prev is not NULL
	 * then skb should also be non-NULL.
	 *
	 * Apparently *ppt_prev assignment above holds this invariant due to
	 * skb dereferencing near it.
	 */
	*pskb = skb;
	return ret;
}

2 函数net_rx_action

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); //合并sd->poll_list到list头部，并清空sd->poll_list
	local_irq_enable();

	for (;;) {
		struct napi_struct *n;

		if (list_empty(&list)) {
			if (!sd_has_rps_ipi_waiting(sd) && list_empty(&repoll))
				goto out;
			break;
		}

		n = list_first_entry(&list, struct napi_struct, poll_list);
		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();

	/* 下面3句就是把sd->poll_list和repoll合并之后放入sd->poll_list */
	list_splice_tail_init(&sd->poll_list, &list); //合并sd->poll_list到list尾部，并清空sd->poll_list
	list_splice_tail(&repoll, &list); // 合并repoll到list头部
	list_splice(&list, &sd->poll_list); // 合并list到sd->poll_list头部
	
	/* 如果sd->poll_list还有内容，则需要再次执行net_rx_action */
	if (!list_empty(&sd->poll_list))
		__raise_softirq_irqoff(NET_RX_SOFTIRQ);

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