Linux协议栈--NAT源码分析

static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
	/* Before packet filtering, change destination */
	{
		.hook		= iptable_nat_ipv4_in,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_PRE_ROUTING,
		.priority	= NF_IP_PRI_NAT_DST,
	},
	/* After packet filtering, change source */
	{
		.hook		= iptable_nat_ipv4_out,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_POST_ROUTING,
		.priority	= NF_IP_PRI_NAT_SRC,
	},
	/* Before packet filtering, change destination */
	{
		.hook		= iptable_nat_ipv4_local_fn,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_LOCAL_OUT,
		.priority	= NF_IP_PRI_NAT_DST,
	},
	/* After packet filtering, change source */
	{
		.hook		= iptable_nat_ipv4_fn,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_LOCAL_IN,
		.priority	= NF_IP_PRI_NAT_SRC,
	},
}

unsigned int
nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
	       const struct nf_hook_state *state,
	       unsigned int (*do_chain)(void *priv,
					struct sk_buff *skb,
					const struct nf_hook_state *state,
					struct nf_conn *ct))
{
	struct nf_conn *ct;
	enum ip_conntrack_info ctinfo;
	struct nf_conn_nat *nat;
	/* maniptype == SRC for postrouting. */
	enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook);

	/* 获取连接跟踪条目 */
	ct = nf_ct_get(skb, &ctinfo);
	/* Can't track?  It's not due to stress, or conntrack would
	 * have dropped it.  Hence it's the user's responsibilty to
	 * packet filter it out, or implement conntrack/NAT for that
	 * protocol. 8) --RR
	 */
	if (!ct)
		return NF_ACCEPT;

	nat = nfct_nat(ct);

	/* 根据连接跟踪的状态做相应的处理 */
	switch (ctinfo) {
	case IP_CT_RELATED:
	case IP_CT_RELATED_REPLY:
		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
							   state->hook))
				return NF_DROP;
			else
				return NF_ACCEPT;
		}
		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
	case IP_CT_NEW:
		/* Seen it before?  This can happen for loopback, retrans,
		 * or local packets.
		 */
		if (!nf_nat_initialized(ct, maniptype)) {
			unsigned int ret;
			/* 如果是一条新连接，查找Iptables策略 */
			ret = do_chain(priv, skb, state, ct);
			if (ret != NF_ACCEPT)
				return ret;

			if (nf_nat_initialized(ct, HOOK2MANIP(state->hook)))
				break;
			/* 做NAT的实际转换，并修改连接跟踪记录 */
			ret = nf_nat_alloc_null_binding(ct, state->hook);
			if (ret != NF_ACCEPT)
				return ret;
		} else {
			pr_debug("Already setup manip %s for ct %p\n",
				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
				 ct);
			if (nf_nat_oif_changed(state->hook, ctinfo, nat,
					       state->out))
				goto oif_changed;
		}
		break;

	default:
		/* ESTABLISHED */
		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
			     ctinfo == IP_CT_ESTABLISHED_REPLY);
		if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out))
			goto oif_changed;
	}
	/* 如果不是一条新连接，则在这里直接进行NAT转换 */
	return nf_nat_packet(ct, ctinfo, state->hook, skb);

oif_changed:
	nf_ct_kill_acct(ct, ctinfo, skb);
	return NF_DROP;
}

static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb,
				  unsigned int iphdroff,
				  const struct nf_nat_l4proto *l4proto,
				  const struct nf_conntrack_tuple *target,
				  enum nf_nat_manip_type maniptype)
{
	struct iphdr *iph;
	unsigned int hdroff;

	if (!skb_make_writable(skb, iphdroff + sizeof(*iph)))
		return false;

	iph = (void *)skb->data + iphdroff;
	hdroff = iphdroff + iph->ihl * 4;

	/* 调用第四层协议，更改端口号 */
	if (!l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv4, iphdroff, hdroff,
				target, maniptype))
		return false;
	iph = (void *)skb->data + iphdroff;

	/* 更改IP地址并重新计算校验值 */
	if (maniptype == NF_NAT_MANIP_SRC) {
		csum_replace4(&iph->check, iph->saddr, target->src.u3.ip);
		iph->saddr = target->src.u3.ip;
	} else {
		csum_replace4(&iph->check, iph->daddr, target->dst.u3.ip);
		iph->daddr = target->dst.u3.ip;
	}
	return true;
}