自上而下理解内核网络(五)---网络层（IP协议）数据的接收与发送

struct iphdr {
#if defined(__LITTLE_ENDIAN_BITFIELD)
	__u8	ihl:4,
		version:4;
#elif defined (__BIG_ENDIAN_BITFIELD)
	__u8	version:4,
  		ihl:4;
#else
#error	"Please fix <asm/byteorder.h>"
#endif
	__u8	tos;
	__be16	tot_len;
	__be16	id;
	__be16	frag_off;
	__u8	ttl;
	__u8	protocol;
	__sum16	check;
	__be32	saddr;
	__be32	daddr;
	/*The options start here. */
};

static struct packet_type ip_packet_type __read_mostly = {
	.type = cpu_to_be16(ETH_P_IP),
	.func = ip_rcv,
	.list_func = ip_list_rcv,
};
static int __init inet_init(void)
{
	......
	dev_add_pack(&ip_packet_type);
	......
}

/*
 * 	Main IP Receive routine.
 */
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
	const struct iphdr *iph;
	struct net *net;
	u32 len;

	/* When the interface is in promisc. mode, drop all the crap
	 * that it receives, do not try to analyse it.
	 */
    /* 判断是其他主机的数据包，则丢弃；*/
	if (skb->pkt_type == PACKET_OTHERHOST)
		goto drop;


	net = dev_net(dev);
	__IP_UPD_PO_STATS(net, IPSTATS_MIB_IN, skb->len);

	skb = skb_share_check(skb, GFP_ATOMIC);
	if (!skb) {
		__IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS);
		goto out;
	}

	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
		goto inhdr_error;

	iph = ip_hdr(skb);

	/*
	 *	RFC1122: 3.2.1.2 MUST silently discard any IP frame that fails the checksum.
	 *
	 *	Is the datagram acceptable?
	 *
	 *	1.	Length at least the size of an ip header
	 *	2.	Version of 4
	 *	3.	Checksums correctly. [Speed optimisation for later, skip loopback checksums]
	 *	4.	Doesn't have a bogus length
	 */
	/* 检查IPv4的包头大小和版本 */
	if (iph->ihl < 5 || iph->version != 4)
		goto inhdr_error;

	BUILD_BUG_ON(IPSTATS_MIB_ECT1PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_1);
	BUILD_BUG_ON(IPSTATS_MIB_ECT0PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_0);
	BUILD_BUG_ON(IPSTATS_MIB_CEPKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_CE);
	__IP_ADD_STATS(net,
		       IPSTATS_MIB_NOECTPKTS + (iph->tos & INET_ECN_MASK),
		       max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));

	if (!pskb_may_pull(skb, iph->ihl*4))
		goto inhdr_error;

	iph = ip_hdr(skb);

	if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
		goto csum_error;

	len = ntohs(iph->tot_len);
	if (skb->len < len) {
		__IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS);
		goto drop;
	} else if (len < (iph->ihl*4))
		goto inhdr_error;

	/* Our transport medium may have padded the buffer out. Now we know it
	 * is IP we can trim to the true length of the frame.
	 * Note this now means skb->len holds ntohs(iph->tot_len).
	 */
	if (pskb_trim_rcsum(skb, len)) {
		__IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS);
		goto drop;
	}

	skb->transport_header = skb->network_header + iph->ihl*4;

	/* Remove any debris in the socket control block */
	memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
	IPCB(skb)->iif = skb->skb_iif;

	/* Must drop socket now because of tproxy. */
	skb_orphan(skb);
	/* 调用钩子函数NF_INET_PRE_ROUTING，我们这里假设没有调用，直接调用下一个函数ip_rcv_finish，真正处理数据*/
	return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
		       net, NULL, skb, dev, NULL,
		       ip_rcv_finish);

csum_error:
	__IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS);
inhdr_error:
	__IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
drop:
	kfree_skb(skb);
out:
	return NET_RX_DROP;
}

static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	const struct iphdr *iph = ip_hdr(skb);
	struct rtable *rt;
	struct net_device *dev = skb->dev;

	/* if ingress device is enslaved to an L3 master device pass the
	 * skb to its handler for processing
	 */
	skb = l3mdev_ip_rcv(skb);
	if (!skb)
		return NET_RX_SUCCESS;
	/*skb_dst()用于检查是否有与skb相关联dst对象*/
	if (net->ipv4.sysctl_ip_early_demux &&
	    !skb_dst(skb) &&
	    !skb->sk &&
	    !ip_is_fragment(iph)) {
		const struct net_protocol *ipprot;
		int protocol = iph->protocol;

		ipprot = rcu_dereference(inet_protos[protocol]);
		if (ipprot && ipprot->early_demux) {
			ipprot->early_demux(skb);
			/* must reload iph, skb->head might have changed */
			iph = ip_hdr(skb);
		}
	}

	/*
	 *	Initialise the virtual path cache for the packet. It describes
	 *	how the packet travels inside Linux networking.
	 */
	 /*如果没有与SKB关联的dst，则由ip_route_input_noref()在卤藕选择子系统中执行查找，如果查找失败，数据包被丢弃。*/
	if (!skb_valid_dst(skb)) {
		int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
					       iph->tos, dev);
		if (unlikely(err)) {
			if (err == -EXDEV)
				__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
			goto drop;
		}
	}

#ifdef CONFIG_IP_ROUTE_CLASSID
	if (unlikely(skb_dst(skb)->tclassid)) {
		struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct);
		u32 idx = skb_dst(skb)->tclassid;
		st[idx&0xFF].o_packets++;
		st[idx&0xFF].o_bytes += skb->len;
		st[(idx>>16)&0xFF].i_packets++;
		st[(idx>>16)&0xFF].i_bytes += skb->len;
	}
#endif
	/*检查IPv4报头是否包含选项，不包含时这里ihl是4*/
	if (iph->ihl > 5 && ip_rcv_options(skb))
		goto drop;

	rt = skb_rtable(skb);
	if (rt->rt_type == RTN_MULTICAST) {
		__IP_UPD_PO_STATS(net, IPSTATS_MIB_INMCAST, skb->len);
	} else if (rt->rt_type == RTN_BROADCAST) {
		__IP_UPD_PO_STATS(net, IPSTATS_MIB_INBCAST, skb->len);
	} else if (skb->pkt_type == PACKET_BROADCAST ||
		   skb->pkt_type == PACKET_MULTICAST) {
		struct in_device *in_dev = __in_dev_get_rcu(dev);

		/* RFC 1122 3.3.6:
		 *
		 *   When a host sends a datagram to a link-layer broadcast
		 *   address, the IP destination address MUST be a legal IP
		 *   broadcast or IP multicast address.
		 *
		 *   A host SHOULD silently discard a datagram that is received
		 *   via a link-layer broadcast (see Section 2.4) but does not
		 *   specify an IP multicast or broadcast destination address.
		 *
		 * This doesn't explicitly say L2 *broadcast*, but broadcast is
		 * in a way a form of multicast and the most common use case for
		 * this is 802.11 protecting against cross-station spoofing (the
		 * so-called "hole-196" attack) so do it for both.
		 */
		if (in_dev &&
		    IN_DEV_ORCONF(in_dev, DROP_UNICAST_IN_L2_MULTICAST))
			goto drop;
	}
	/*通过dst_input，调用skb_dst(skb)->input(skb)*/
	return dst_input(skb);

drop:
	kfree_skb(skb);
	return NET_RX_DROP;
}