分析完了xt_TPROXY.c源代码：
首先，这是tproxy向netfilter注册的一个target，该target能够在不对数据包修改的情况下，将数据包代理到本地套接字上；
他的关键点在于通过获得数据包的目的端口和目的地址，而非本地监听套接字的bind地址，再通nf_tproxy_get_sock_v4函数，获得监听套接字，最后把skb->sock = sk；
他的优势在于不对数据包进行任何改变（NAT），就可以重定向数据包。
代码注释如下
/*
* Transparent proxy support for Linux/iptables
*
* Copyright (c) 2006-2007 BalaBit IT Ltd.
* Author: Balazs Scheidler, Krisztian Kovacs
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
*/
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
#include
#include
#include
#include
#endif
#include
#include
static inline __be32
tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
{
struct in_device *indev;
__be32 laddr;
if (user_laddr)
return user_laddr;
laddr = 0;
rcu_read_lock();
indev = __in_dev_get_rcu(skb->dev);
for_primary_ifa(indev) {
laddr = ifa->ifa_local;
break;
} endfor_ifa(indev);
rcu_read_unlock();
return laddr ? laddr : daddr;
}
/*
iptables -t mangle -A PREROUTING -p tcp --dport 80 -j TPROXY --tproxy-mark 0x1/0x1 --on-port 50080
参数说明：
laddr 为代理服务器的本地监听套接字的本地ip
lport 为代理服务器的本地监听套接字的本地port，50080
mark_value 为mark值
*/
static unsigned int
tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport, u_int32_t mark_mask, u_int32_t mark_value)
{
const struct iphdr *iph = ip_hdr(skb);
struct udphdr _hdr, *hp;
struct sock *sk;
hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr);//获得传输头
if (hp == NULL) {
pr_debug("TPROXY: packet is too short to contain a transport header, dropping\n");
return NF_DROP;
}
//根据数据包的内容，向tcp已建立的队列查找skb属于的struct sock
//如果客户端与代理服务器已经建立连接，该数据包属于的sock将存在
/* check if there's an ongoing connection on the packet
* addresses, this happens if the redirect already happened
* and the current packet belongs to an already established
* connection */
sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol,
iph->saddr, iph->daddr,
hp->source, hp->dest,
skb->dev, NFT_LOOKUP_ESTABLISHED);
/* udp has no TCP_TIME_WAIT state, so we never enter here */
if (sk && sk->sk_state == TCP_TIME_WAIT) {
struct tcphdr _hdr, *hp;
hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr);
if (hp == NULL)
return NF_DROP;
if (hp->syn && !hp->rst && !hp->ack && !hp->fin) {
struct sock *sk2;
/* Hm.. we got a SYN to a TIME_WAIT socket, let's see if
* there's a listener on the redirected port
*/
sk2 = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol,
iph->saddr, tproxy_laddr4(skb, laddr, iph->daddr),
hp->source, lport ? lport : hp->dest,
skb->dev, NFT_LOOKUP_LISTENER);
if (sk2) {
/* yeah, there's one, let's kill the TIME_WAIT
* socket and redirect to the listener
*/
inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
inet_twsk_put(inet_twsk(sk));
sk = sk2;
}
}
} else if (!sk) {
//如果不存在sk，说明是客户端向代理服务器发出tcp syn的数据包
//此时，通过该函数，将该数据包的skb与代理服务器的本地监听套接字建立联系，即skb->sock = sock
//tproxy_laddr4(skb, laddr, iph->daddr) 根据tproxy target的传入参数struct xt_tproxy_target_info_v0，找到当前代理服务器端已经建立的监听socket
/* no there's no established connection, check if
* there's a listener on the redirected addr/port */
sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol,
iph->saddr, tproxy_laddr4(skb, laddr, iph->daddr),
hp->source, lport ? lport : hp->dest,
skb->dev, NFT_LOOKUP_LISTENER);
}
/* NOTE: assign_sock consumes our sk reference */
if (sk && nf_tproxy_assign_sock(skb, sk)) {
//运行至此，说明客户端已经与服务器端建立了三次握手，即sk存在
//则通过nf_tproxy_assign_sock函数，将当前数据包的skb与代理服务器的监听socket建立联系，即skb->sock = sk
//最后，将数据包打上比较，待策略路由转发到loobackshang
/* This should be in a separate target, but we don't do multiple
targets on the same rule yet */
skb->mark = (skb->mark & ~mark_mask) ^ mark_value;
pr_debug("TPROXY: redirecting: proto %u %08x:%u -> %08x:%u, mark: %x\n",
iph->protocol, ntohl(iph->daddr), ntohs(hp->dest),
ntohl(laddr), ntohs(lport), skb->mark);
return NF_ACCEPT;
}
pr_debug("TPROXY: no socket, dropping: proto %u %08x:%u -> %08x:%u, mark: %x\n",
iph->protocol, ntohl(iph->daddr), ntohs(hp->dest),
ntohl(laddr), ntohs(lport), skb->mark);
return NF_DROP;
}
static unsigned int
tproxy_tg4_v0(struct sk_buff *skb, const struct xt_target_param *par)
{
const struct xt_tproxy_target_info_v0 *tgi = par->targinfo;
return tproxy_tg4(skb, tgi->laddr, tgi->lport, tgi->mark_mask, tgi->mark_value);
}
//tproxy具体的target函数
static unsigned int
tproxy_tg4_v1(struct sk_buff *skb, const struct xt_target_param *par)
{
const struct xt_tproxy_target_info_v1 *tgi = par->targinfo;//获得参数
return tproxy_tg4(skb, tgi->laddr.ip, tgi->lport, tgi->mark_mask, tgi->mark_value);//根据传入的参数，将所有流量代理到本地监听套接字上
}
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
static inline const struct in6_addr *
tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr, const struct in6_addr *daddr)
{
struct inet6_dev *indev;
struct inet6_ifaddr *ifa;
struct in6_addr *laddr;
if (!ipv6_addr_any(user_laddr))
return user_laddr;
laddr = NULL;
rcu_read_lock();
indev = __in6_dev_get(skb->dev);
if (indev && (ifa = indev->addr_list)) {
laddr = &ifa->addr;
}
rcu_read_unlock();
return laddr ? laddr : daddr;
}
static unsigned int
tproxy_tg6_v1(struct sk_buff *skb, const struct xt_target_param *par)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
const struct xt_tproxy_target_info_v1 *tgi = par->targinfo;
struct udphdr _hdr, *hp;
struct sock *sk;
int thoff;
int tproto;
tproto = ipv6_find_hdr(skb, &thoff, -1, NULL);
if (tproto < 0) {
pr_debug("TPROXY: Unable to find transport header in IPv6 packet, dropping\n");
return NF_DROP;
}
hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr);
if (hp == NULL) {
pr_debug("TPROXY: Unable to grab transport header contents in IPv6 packet, dropping\n");
return NF_DROP;
}
/* check if there's an ongoing connection on the packet
* addresses, this happens if the redirect already happened
* and the current packet belongs to an already established
* connection */
sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto,
&iph->saddr, &iph->daddr,
hp->source, hp->dest,
par->in, NFT_LOOKUP_ESTABLISHED);
/* udp has no TCP_TIME_WAIT state, so we never enter here */
if (sk && sk->sk_state == TCP_TIME_WAIT) {
struct tcphdr _hdr, *hp;
hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr);
if (hp == NULL) {
pr_debug("TPROXY: Unable to grab TCP transport header contents in IPv6 packet, dropping\n");
return NF_DROP;
}
if (hp->syn && !hp->rst && !hp->ack && !hp->fin) {
struct sock *sk2;
/* Hm.. we got a SYN to a TIME_WAIT socket, let's see if
* there's a listener on the redirected port
*/
sk2 = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto,
&iph->saddr, tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr),
hp->source, tgi->lport ? tgi->lport : hp->dest,
par->in, NFT_LOOKUP_LISTENER);
if (sk2) {
/* yeah, there's one, let's kill the TIME_WAIT
* socket and redirect to the listener
*/
inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
inet_twsk_put(inet_twsk(sk));
sk = sk2;
}
}
} else if (!sk) {
/* no there's no established connection, check if
* there's a listener on the redirected addr/port */
sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto,
&iph->saddr, tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr),
hp->source, tgi->lport ? tgi->lport : hp->dest,
par->in, NFT_LOOKUP_LISTENER);
}
/* NOTE: assign_sock consumes our sk reference */
if (sk && nf_tproxy_assign_sock(skb, sk)) {
/* This should be in a separate target, but we don't do multiple
targets on the same rule yet */
skb->mark = (skb->mark & ~tgi->mark_mask) ^ tgi->mark_value;
pr_debug("TPROXY: redirecting: proto %u %pI6:%u -> %pI6:%u, mark: %x\n",
tproto, &iph->saddr, ntohs(hp->dest),
&tgi->laddr.in6, ntohs(tgi->lport), skb->mark);
return NF_ACCEPT;
}
pr_debug("TPROXY: no socket, dropping: proto %u %pI6:%u -> %pI6:%u, mark: %x\n",
tproto, &iph->saddr, ntohs(hp->dest),
&tgi->laddr.in6, ntohs(tgi->lport), skb->mark);
return NF_DROP;
}
#endif
static bool tproxy_tg4_check(const struct xt_tgchk_param *par)
{
const struct ipt_ip *i = par->entryinfo;
if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP)
&& !(i->invflags & IPT_INV_PROTO))
return true;
pr_info("xt_TPROXY: Can be used only in combination with "
"either -p tcp or -p udp\n");
return false;
}
static bool tproxy_tg6_check(const struct xt_tgchk_param *par)
{
const struct ip6t_ip6 *i = par->entryinfo;
if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP)
&& !(i->flags & IP6T_INV_PROTO))
return true;
pr_info("xt_TPROXY: Can be used only in combination with "
"either -p tcp or -p udp\n");
return false;
}
static struct xt_target tproxy_tg_reg[] __read_mostly = {
{
.name = "TPROXY",
.family = NFPROTO_IPV4,
.table = "mangle",
.target = tproxy_tg4_v0,//tproxy的target执行钩子
.revision = 0,
.targetsize = sizeof(struct xt_tproxy_target_info_v0),//struct xt_tproxy_target_info_v0 为向target钩子函数传入的参数
.checkentry = tproxy_tg4_check,
.hooks = 1 << NF_INET_PRE_ROUTING,//钩子点
.me = THIS_MODULE,
},
{
.name = "TPROXY",
.family = NFPROTO_IPV4,
.table = "mangle",
.target = tproxy_tg4_v1,
.revision = 1,
.targetsize = sizeof(struct xt_tproxy_target_info_v1),
.checkentry = tproxy_tg4_check,
.hooks = 1 << NF_INET_PRE_ROUTING,
.me = THIS_MODULE,
},
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
{
.name = "TPROXY",
.family = NFPROTO_IPV6,
.table = "mangle",
.target = tproxy_tg6_v1,
.revision = 1,
.targetsize = sizeof(struct xt_tproxy_target_info_v1),
.checkentry = tproxy_tg6_check,
.hooks = 1 << NF_INET_PRE_ROUTING,
.me = THIS_MODULE,
},
#endif
};
//tproxy target初始化，向iptables中target注册
static int __init tproxy_tg_init(void)
{
//tproxy是需要先对数据包进行重组的
nf_defrag_ipv4_enable();
nf_defrag_ipv6_enable();
return xt_register_targets(tproxy_tg_reg, ARRAY_SIZE(tproxy_tg_reg));
}
static void __exit tproxy_tg_exit(void)
{
xt_unregister_targets(tproxy_tg_reg, ARRAY_SIZE(tproxy_tg_reg));
}
module_init(tproxy_tg_init);
module_exit(tproxy_tg_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Krisztian Kovacs");
MODULE_DESCRIPTION("Netfilter transparent proxy (TPROXY) target module.");
MODULE_ALIAS("ipt_TPROXY");
MODULE_ALIAS("ip6t_TPROXY");
