在以太网上传输IP数据报时，以太网设备并不能识别32位IP地址，而是以48位以太网地址传输以太网数据包的。因此，IP数据报在以太网上传输前需要封装为以太网帧，而以太网帧的目的地址正是通过IP数据报的目的IP地址查询得到的。因此IP地址和以太网地址之间存在着映射，通过查看ARP表就可以得到这两地址间的对应关系。地址解析协议(Address Resolution Protocol-ARP)就是用来确定这些对应关系的协议。

ARP协议的处理涉及以下文件：

include/linux/if_arp.h 定义Arp报文等结构、宏和函数原型

net/ipv4/arp.c Arp协议实现

ARP报文格式

参见tcp/ip协议学习笔记(4)ARP&RARP

定义arp报文头的结构

struct arphdr
{
	__be16		ar_hrd;		/* format of hardware address	*/
	__be16		ar_pro;		/* format of protocol address	*/
	unsigned char	ar_hln;		/* length of hardware address	*/
	unsigned char	ar_pln;		/* length of protocol address	*/
	__be16		ar_op;		/* ARP opcode (command)		*/

#if 0
	 /*
	  *	 Ethernet looks like this : This bit is variable sized however...
	  */
	unsigned char		ar_sha[ETH_ALEN];	/* sender hardware address	*/
	unsigned char		ar_sip[4];		/* sender IP address		*/
	unsigned char		ar_tha[ETH_ALEN];	/* target hardware address	*/
	unsigned char		ar_tip[4];		/* target IP address		*/
#endif

};

ARP协议并不仅仅被IPv4使用，在内核的网络模块代码中使用缩写SIP和TIP来代表发送方IP地址和目的IP地址

注册ARP报文类型

ARP报文像IP数据报一样，也是作为数据封装在以太网帧中发送的。ARP报文由arp_rcv()接收处理，ARP模块初始化时需要在协议栈中注册ARP报文的类型

/*
 *	Called once on startup.
 */

static struct packet_type arp_packet_type __read_mostly = {
	.type =	cpu_to_be16(ETH_P_ARP),
	.func =	arp_rcv,
};

ARP初始化

ARP模块的初始化是由arp_init()完成的，该函数由IPv4协议栈初始化函数inet_init()调用，首先初始化arp协议的邻居表，然后在协议栈中注册ARP协议，最后建立proc对象，注册事件通知

void __init arp_init(void)
{
	neigh_table_init(&arp_tbl);

	dev_add_pack(&arp_packet_type);
	arp_proc_init();
#ifdef CONFIG_SYSCTL
	neigh_sysctl_register(NULL, &arp_tbl.parms, NET_IPV4,
			      NET_IPV4_NEIGH, "ipv4", NULL, NULL);
#endif
	register_netdevice_notifier(&arp_netdev_notifier);
}

在ARP中，根据不同的介质，提供了多种邻居项函数指针表的实例，例如通用的arp_generic_ops，支持缓存硬件首部arp_hh_ops，不支持ARP的arp_direct_ops以及支持业余无线电设备等的arp_broken_ops。除了两个输出函数指针output和connected_output，这些邻居项函数指针表实例区别不大

static const struct neigh_ops arp_generic_ops = {
	.family =		AF_INET,
	.solicit =		arp_solicit,
	.error_report =		arp_error_report,
	.output =		neigh_resolve_output,
	.connected_output =	neigh_connected_output,
	.hh_output =		dev_queue_xmit,
	.queue_xmit =		dev_queue_xmit,
};

static const struct neigh_ops arp_hh_ops = {
	.family =		AF_INET,
	.solicit =		arp_solicit,
	.error_report =		arp_error_report,
	.output =		neigh_resolve_output,
	.connected_output =	neigh_resolve_output,
	.hh_output =		dev_queue_xmit,
	.queue_xmit =		dev_queue_xmit,
};

static const struct neigh_ops arp_direct_ops = {
	.family =		AF_INET,
	.output =		dev_queue_xmit,
	.connected_output =	dev_queue_xmit,
	.hh_output =		dev_queue_xmit,
	.queue_xmit =		dev_queue_xmit,
};

const struct neigh_ops arp_broken_ops = {
	.family =		AF_INET,
	.solicit =		arp_solicit,
	.error_report =		arp_error_report,
	.output =		neigh_compat_output,
	.connected_output =	neigh_compat_output,
	.hh_output =		dev_queue_xmit,
	.queue_xmit =		dev_queue_xmit,
};

ARP的邻居表为arp_tbl，其中与协议特性相关的字段有：地址族为AF_INET；邻居项的大小为neighbour结构+4(IPv4地址的长度)；哈希算法为arp_hash();arp初始化函数arp_constructor()；延时处理代理ARP报文的例程为parp_redo()，以及调整ARP表特性的参数。

struct neigh_table arp_tbl = {
	.family =	AF_INET,
	.entry_size =	sizeof(struct neighbour) + 4,
	.key_len =	4,
	.hash =		arp_hash,
	.constructor =	arp_constructor,
	.proxy_redo =	parp_redo,
	.id =		"arp_cache",
	.parms = {
		.tbl =			&arp_tbl,
		.base_reachable_time =	30 * HZ,
		.retrans_time =	1 * HZ,
		.gc_staletime =	60 * HZ,
		.reachable_time =		30 * HZ,
		.delay_probe_time =	5 * HZ,
		.queue_len =		3,
		.ucast_probes =	3,
		.mcast_probes =	3,
		.anycast_delay =	1 * HZ,
		.proxy_delay =		(8 * HZ) / 10,
		.proxy_qlen =		64,
		.locktime =		1 * HZ,
	},
	.gc_interval =	30 * HZ,
	.gc_thresh1 =	128,
	.gc_thresh2 =	512,
	.gc_thresh3 =	1024,
};

IPv4中邻居项的初始化

arp_constructor()是ARP的邻居初始化函数，用来创建新的neighbour结构实例，在邻居表创建函数neigh_create()中被调用。

static int arp_constructor(struct neighbour *neigh)
{
	__be32 addr = *(__be32*)neigh->primary_key;
	struct net_device *dev = neigh->dev;
	struct in_device *in_dev;
	struct neigh_parms *parms;

	rcu_read_lock();
	in_dev = __in_dev_get_rcu(dev);
	if (in_dev == NULL) {
		rcu_read_unlock();
		return -EINVAL;
	}

	neigh->type = inet_addr_type(dev_net(dev), addr);

	parms = in_dev->arp_parms;
	__neigh_parms_put(neigh->parms);
	neigh->parms = neigh_parms_clone(parms);
	rcu_read_unlock();

	if (!dev->header_ops) {
		neigh->nud_state = NUD_NOARP;
		neigh->ops = &arp_direct_ops;
		neigh->output = neigh->ops->queue_xmit;
	} else {
		/* Good devices (checked by reading texts, but only Ethernet is
		   tested)

		   ARPHRD_ETHER: (ethernet, apfddi)
		   ARPHRD_FDDI: (fddi)
		   ARPHRD_IEEE802: (tr)
		   ARPHRD_METRICOM: (strip)
		   ARPHRD_ARCNET:
		   etc. etc. etc.

		   ARPHRD_IPDDP will also work, if author repairs it.
		   I did not it, because this driver does not work even
		   in old paradigm.
		 */

#if 1
		/* So... these "amateur" devices are hopeless.
		   The only thing, that I can say now:
		   It is very sad that we need to keep ugly obsolete
		   code to make them happy.

		   They should be moved to more reasonable state, now
		   they use rebuild_header INSTEAD OF hard_start_xmit!!!
		   Besides that, they are sort of out of date
		   (a lot of redundant clones/copies, useless in 2.1),
		   I wonder why people believe that they work.
		 */
		switch (dev->type) {
		default:
			break;
		case ARPHRD_ROSE:
#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
		case ARPHRD_AX25:
#if defined(CONFIG_NETROM) || defined(CONFIG_NETROM_MODULE)
		case ARPHRD_NETROM:
#endif
			neigh->ops = &arp_broken_ops;
			neigh->output = neigh->ops->output;
			return 0;
#endif
		;}
#endif
		if (neigh->type == RTN_MULTICAST) {
			neigh->nud_state = NUD_NOARP;
			arp_mc_map(addr, neigh->ha, dev, 1);
		} else if (dev->flags&(IFF_NOARP|IFF_LOOPBACK)) {
			neigh->nud_state = NUD_NOARP;
			memcpy(neigh->ha, dev->dev_addr, dev->addr_len);
		} else if (neigh->type == RTN_BROADCAST || dev->flags&IFF_POINTOPOINT) {
			neigh->nud_state = NUD_NOARP;
			memcpy(neigh->ha, dev->broadcast, dev->addr_len);
		}

		if (dev->header_ops->cache)
			neigh->ops = &arp_hh_ops;
		else
			neigh->ops = &arp_generic_ops;

		if (neigh->nud_state&NUD_VALID)
			neigh->output = neigh->ops->connected_output;
		else
			neigh->output = neigh->ops->output;
	}
	return 0;
}

ARP的输出

arp_send()先创建一个ARP报文，如果创建成功就将其发送出。该函数的参数与arp_create()相同

/*
 *	Create and send an arp packet.
 */
void arp_send(int type, int ptype, __be32 dest_ip,
	      struct net_device *dev, __be32 src_ip,
	      const unsigned char *dest_hw, const unsigned char *src_hw,
	      const unsigned char *target_hw)
{
	struct sk_buff *skb;

	/*
	 *	No arp on this interface.
	 */

	if (dev->flags&IFF_NOARP)
		return;

	skb = arp_create(type, ptype, dest_ip, dev, src_ip,
			 dest_hw, src_hw, target_hw);
	if (skb == NULL) {
		return;
	}

	arp_xmit(skb);
}

ARP的输入

arp_rcv()用来从二层接收并处理一个ARP报文

/*
 *	Receive an arp request from the device layer.
 */

static int arp_rcv(struct sk_buff *skb, struct net_device *dev,
		   struct packet_type *pt, struct net_device *orig_dev)
{
	struct arphdr *arp;

	/* ARP header, plus 2 device addresses, plus 2 IP addresses.  */
	if (!pskb_may_pull(skb, arp_hdr_len(dev)))
		goto freeskb;

	arp = arp_hdr(skb);
	if (arp->ar_hln != dev->addr_len ||
	    dev->flags & IFF_NOARP ||
	    skb->pkt_type == PACKET_OTHERHOST ||
	    skb->pkt_type == PACKET_LOOPBACK ||
	    arp->ar_pln != 4)
		goto freeskb;

	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
		goto out_of_mem;

	memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));

	return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, skb, dev, NULL, arp_process);

freeskb:
	kfree_skb(skb);
out_of_mem:
	return 0;
}

路由表项与邻居项的绑定

在路由模块中，每当添加一条输出路由或是单播转发路由时，会尝试将该路由与该路由目的地址相对应的邻居项绑定。arp_bind_neighbour()实现了路由表项与邻居绑定的功能，在绑定过程中，如果对应的邻居项不存在，则会创建一个邻居项然后将路由项与之绑定。绑定之后，再输出报文时就能通过路由缓存找到输出函数。

ARP：地址解析协议实现学习

原文：http://blog.csdn.net/wangpeihuixyz/article/details/39449143