标签：linux stateless nat stateful nat iptables netfilter
关于Linux上如何配置NAT的资料已经不少，可谓铺天盖地！本文与此无关。本文提供一种iptables之外的方式。/*
*
* 用法：
* 对目标地址为1.2.1.2的数据包做目标地址转换，目标转为192.168.1.8
* echo +1.2.1.2 192.168.1.8 dst >/proc/net/static_nat
* 上述命令会同时添加一条反向的SNAT映射
*
* 请解释：
* echo +192.168.184.250 192.168.184.154 src >/proc/net/static_nat
*
*/
#include <linux/module.h>
#include <linux/skbuff.h>
#include <net/ip.h>
#include <net/netfilter/nf_conntrack.h>
#define DIRMASK 0x11
#define BUCKETS 1024
#define NAT_OPT_DEL 0x01
#define NAT_OPT_FIND 0x04
#define NAT_OPT_ACCT_BIT 0x02
enum nat_dir {
DIR_SNAT,
DIR_DNAT,
DIR_NUM
};
/*
* 记录统计信息
*/
struct nat_account {
u32 nat_packets;
u32 nat_bytes;
};
struct static_nat_entry {
__be32 addr[DIR_NUM];
enum nat_dir type;
struct nat_account acct[DIR_NUM];
struct hlist_node node[DIR_NUM];
};
static DEFINE_SPINLOCK(nat_lock);
/* 保存SNAT映射 */
struct hlist_head *src_list;
/* 保存DNAT映射 */
struct hlist_head *dst_list;
/*
* 用一个IP地址(对于PREROUTING是daddr，对于POSTROUTING是saddr)作为key来获取value。
*/
static __be32 get_address_from_map(struct sk_buff *skb, unsigned int dir, __be32 addr_key, unsigned int opt)
{
__be32 ret = 0, cmp_key, ret_value;
u32 hash;
struct hlist_head *list;
struct hlist_node *iter, *tmp;
struct static_nat_entry *ent;
hash = jhash_1word(addr_key, 1);
hash = hash%BUCKETS;
spin_lock(&nat_lock);
if (dir == DIR_DNAT) {
list = &dst_list[hash];
} else if (dir == DIR_SNAT) {
list = &src_list[hash];
} else {
spin_unlock(&nat_lock);
goto out;
}
hlist_for_each_safe(iter, tmp, list) {
ent = hlist_entry(iter, struct static_nat_entry, node[dir]);
/* 注意反转 */
cmp_key = (ent->type == dir) ?
ent->addr[0]:ent->addr[1];
ret_value = (ent->type == dir) ?
ent->addr[1]:ent->addr[0];
if (addr_key == cmp_key) {
ret = ret_value;
if (opt == NAT_OPT_DEL) {
if (dir == ent->type) {
hlist_del(&ent->node[0]);
hlist_del(&ent->node[1]);
kfree(ent);
} else {
ret = 0;
}
}
if (opt & NAT_OPT_ACCT_BIT) {
ent->acct[dir].nat_packets ++;
ent->acct[dir].nat_bytes += skb == NULL?1:skb->len;
}
break;
}
}
spin_unlock(&nat_lock);
out:
return ret;
}
/*
* 更新第四层的校验码信息
*/
static void nat4_update_l4(struct sk_buff *skb, __be32 oldip, __be32 newip)
{
struct iphdr *iph = ip_hdr(skb);
void *transport_hdr = (void *)iph + ip_hdrlen(skb);
struct tcphdr *tcph;
struct udphdr *udph;
bool cond;
switch (iph->protocol) {
case IPPROTO_TCP:
tcph = transport_hdr;
inet_proto_csum_replace4(&tcph->check, skb, oldip, newip, true);
break;
case IPPROTO_UDP:
case IPPROTO_UDPLITE:
udph = transport_hdr;
cond = udph->check != 0;
cond |= skb->ip_summed == CHECKSUM_PARTIAL;
if (cond) {
inet_proto_csum_replace4(&udph->check, skb, oldip, newip, true);
if (udph->check == 0) {
udph->check = CSUM_MANGLED_0;
}
}
break;
}
}
/*
* 在POSTROUTING上执行源地址转换：
* 1.正向源地址转换；
* 2.目标地址转换的逆向源地址转换
*/
static unsigned int ipv4_nat_out(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
unsigned int ret = NF_ACCEPT;
__be32 to_trans = 0;
struct iphdr *hdr = ip_hdr(skb);
to_trans = get_address_from_map(skb, DIR_SNAT, hdr->saddr, NAT_OPT_FIND|NAT_OPT_ACCT_BIT);
if (!to_trans) {
goto out;
}
if (hdr->saddr == to_trans) {
goto out;
}
/* 执行SNAT */
csum_replace4(&hdr->check, hdr->saddr, to_trans);
nat4_update_l4(skb, hdr->saddr, to_trans);
hdr->saddr = to_trans;
out:
return ret;
}
/*
* 在PREROUTING上执行目标地址转换：
* 1.正向目标地址转换；
* 2.源地址转换的逆向目标地址转换
*/
static unsigned int ipv4_nat_in(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
unsigned int ret = NF_ACCEPT;
__be32 to_trans = 0;
struct iphdr *hdr = ip_hdr(skb);
if (skb->nfct && skb->nfct != &nf_conntrack_untracked.ct_general) {
goto out;
}
to_trans = get_address_from_map(skb, DIR_DNAT, hdr->daddr, NAT_OPT_FIND|NAT_OPT_ACCT_BIT);
if (!to_trans) {
goto out;
}
if (hdr->daddr == to_trans) {
goto out;
}
/* 执行DNAT */
csum_replace4(&hdr->check, hdr->daddr, to_trans);
nat4_update_l4(skb, hdr->daddr, to_trans);
hdr->daddr = to_trans;
/*
* 设置一个notrack 防止其被track以及nat.
* 这是绝对合适的，因为既然是static的stateless NAT
* 我们就不希望它被状态左右
**/
/*
* 其实，并不是主要避开基于conntrack的NAT就可以了，因为
* conntrack本身就不容你对两个方向的tuple进行随意修改
*/
if (!skb->nfct) {
skb->nfct = &nf_conntrack_untracked.ct_general;
skb->nfctinfo = IP_CT_NEW;
nf_conntrack_get(skb->nfct);
}
out:
return ret;
}
static struct nf_hook_ops ipv4_nat_ops[] __read_mostly = {
{
.hook = ipv4_nat_in,
.owner = THIS_MODULE,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_PRE_ROUTING,
.priority = NF_IP_PRI_CONNTRACK-1,
},
{
.hook = ipv4_nat_out,
.owner = THIS_MODULE,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_POST_ROUTING,
.priority = NF_IP_PRI_CONNTRACK+1,
},
};
static char *parse_addr(const char *input, __be32 *from, __be32 *to)
{
char *p1, *p2;
size_t length = strlen(input);
if (!(p1 = memchr(input, ‘ ‘, length))) {
return NULL;
}
if (!(p2 = memchr(p1 + 1, ‘ ‘, length - (p1 + 1 - input)))) {
return NULL;
}
if (!(in4_pton(input, p1 - input, (u8 *)from, ‘ ‘, NULL))
|| !(in4_pton(p1 + 1, p2 - p1 - 1, (u8 *)to, ‘ ‘, NULL))) {
return NULL;
}
return ++p2;
}
static ssize_t static_nat_config_write(struct file *file, const char *buffer, size_t count, loff_t *unused)
{
int ret = 0;
size_t length = count;
__be32 from, to;
u32 normal, reverse;
char *buf = NULL;
char *p;
struct static_nat_entry *ent;
if (length) {
char *pp = (char *)(buffer + (length - 1));
for (; (*pp < (char)32) || (*pp > (char)126); pp--) {
if (length <= 0) {
ret = -EINVAL;
goto out;
}
length--;
}
} else {
goto out;
}
buf = kzalloc((length + 1), GFP_ATOMIC);
if (!buf) {
ret = -ENOMEM;
goto out;
}
memcpy(buf, buffer, length);
if (!(p = parse_addr(buf + 1, &from, &to))) {
ret = -EINVAL;
goto out;
}
if (‘+‘ == *buf) {
ent = (struct static_nat_entry *)kzalloc(sizeof(struct static_nat_entry), GFP_KERNEL);
if (!ent) {
ret = -EFAULT;
goto out;
}
/* 计算原始项的hash桶位置 */
normal = jhash_1word(from, 1);
normal = normal%BUCKETS;
/* 计算反转位置的hash桶位置 */
reverse = jhash_1word(to, 1);
reverse = reverse%BUCKETS;
/*
* 设置key/value对
* 注意，反转类型的hnode其key/value也要反转
*/
ent->addr[0] = from;
ent->addr[1] = to;
/* 初始化链表节点 */
INIT_HLIST_NODE(&ent->node[DIR_SNAT]);
INIT_HLIST_NODE(&ent->node[DIR_DNAT]);
if (strstr(p, "src")) { /* 添加SNAT项，自动生成DNAT项 */
/* 首先判断是否已经存在了 */
if (get_address_from_map(NULL, DIR_SNAT, from, NAT_OPT_FIND) ||
get_address_from_map(NULL, DIR_SNAT, to, NAT_OPT_FIND)) {
ret = -EEXIST;
kfree(ent);
goto out;
}
/* 这是这个entry的type，用来区分生成的两条配置项 */
ent->type = DIR_SNAT;
/* 落实到链表 */
spin_lock(&nat_lock);
hlist_add_head(&ent->node[DIR_SNAT], &src_list[normal]);
hlist_add_head(&ent->node[DIR_DNAT], &dst_list[reverse]);
spin_unlock(&nat_lock);
} else if(strstr(p, "dst")) { /* 添加DNAT项，自动生成SNAT项 */
/* 首先判断是否已经存在了 */
if (get_address_from_map(NULL, DIR_DNAT, from, NAT_OPT_FIND) ||
get_address_from_map(NULL, DIR_DNAT, to, NAT_OPT_FIND)){
ret = -EEXIST;
kfree(ent);
goto out;
}
/* 这是这个entry的type，用来区分生成的两条配置项 */
ent->type = DIR_DNAT;
/* 落实到链表 */
spin_lock(&nat_lock);
hlist_add_head(&ent->node[DIR_DNAT], &dst_list[normal]);
hlist_add_head(&ent->node[DIR_SNAT], &src_list[reverse]);
spin_unlock(&nat_lock);
} else {
ret = -EFAULT;
kfree(ent);
goto out;
}
} else if (‘-‘ ==*buf) {
u32 r1;
if (strstr(p, "src")) {
r1 = get_address_from_map(NULL, DIR_SNAT, from, NAT_OPT_DEL);
if (r1 == 0) {
ret = -ENOENT;
goto out;
}
} else if(strstr(p, "dst")) {
r1 = get_address_from_map(NULL, DIR_DNAT, from, NAT_OPT_DEL);
if (r1 == 0) {
ret = -ENOENT;
goto out;
}
} else {
}
} else {
ret = -EINVAL;
goto out;
}
ret = count;
out:
kfree(buf);
return ret;
}
static ssize_t static_nat_config_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
int len = 0;
static int done = 0;
int i;
char from[15], to[15];
char *kbuf_to_avoid_user_space_memory_page_fault = NULL;
/* 每一行的最大长度 */
#define MAX_LINE_CHARS 128
if (done) {
done = 0;
goto out;
}
/*
* 分配一块内核内存，为了避免直接操作用户内存而引发页面调度，
* 页面调度会导致睡眠切换，而我们操作的内容处在自旋锁的保护
* 下，所以不能切换！
*/
/*
* 问题：
* 我这里仅仅分配count大小的内存，是因为这个版本不支持多次读，
* 只能一次读完。也许我应该学学seq read的方法。
*/
kbuf_to_avoid_user_space_memory_page_fault = kzalloc(count, GFP_KERNEL);
if (!kbuf_to_avoid_user_space_memory_page_fault) {
len = -ENOMEM;
done = 1;
goto out;
}
spin_lock(&nat_lock);
len += sprintf(kbuf_to_avoid_user_space_memory_page_fault + len, "Source trans table:\n");
if (len + MAX_LINE_CHARS > count) {
goto copy_now;
}
for (i = 0; i < BUCKETS; i++) {
struct hlist_node *iter, *tmp;
struct static_nat_entry *ent;
hlist_for_each_safe(iter, tmp, &src_list[i]) {
ent = hlist_entry(iter, struct static_nat_entry, node[DIR_SNAT]);
sprintf(from, "%pI4", (ent->type == DIR_SNAT)? &ent->addr[0]:&ent->addr[1]);
sprintf(to, "%pI4", (ent->type == DIR_SNAT)? &ent->addr[1]:&ent->addr[0]);
len += sprintf(kbuf_to_avoid_user_space_memory_page_fault + len, "From:%-15s To:%-15s [%s] [Bytes:%u Packet:%u]\n",
from,
to,
(ent->type == DIR_SNAT)?"STATIC":"AUTO",
ent->acct[DIR_SNAT].nat_bytes,
ent->acct[DIR_SNAT].nat_packets);
if (len + MAX_LINE_CHARS > count) {
goto copy_now;
}
}
}
len += sprintf(kbuf_to_avoid_user_space_memory_page_fault + len, "\nDestination trans table:\n");
if (len + MAX_LINE_CHARS > count) {
goto copy_now;
}
for (i = 0; i < BUCKETS; i++) {
struct hlist_node *iter, *tmp;
struct static_nat_entry *ent;
hlist_for_each_safe(iter, tmp, &dst_list[i]) {
ent = hlist_entry(iter, struct static_nat_entry, node[DIR_DNAT]);
sprintf(from, "%pI4", (ent->type == DIR_DNAT)? &ent->addr[0]:&ent->addr[1]);
sprintf(to, "%pI4", (ent->type == DIR_DNAT)? &ent->addr[1]:&ent->addr[0]);
len += sprintf(kbuf_to_avoid_user_space_memory_page_fault + len, "From:%-15s To:%-15s [%s] [Bytes:%u Packet:%u]\n",
from,
to,
(ent->type == DIR_DNAT)?"STATIC":"AUTO",
ent->acct[DIR_DNAT].nat_bytes,
ent->acct[DIR_DNAT].nat_packets);
if (len + MAX_LINE_CHARS > count) {
goto copy_now;
}
}
}
copy_now:
spin_unlock(&nat_lock);
done = 1;
/* 这里已经解除自旋锁 */
if (copy_to_user(buf, kbuf_to_avoid_user_space_memory_page_fault, len)) {
len = EFAULT;
goto out;
}
out:
if (kbuf_to_avoid_user_space_memory_page_fault) {
kfree(kbuf_to_avoid_user_space_memory_page_fault);
}
return len;
}
static const struct file_operations static_nat_file_ops = {
.owner = THIS_MODULE,
.read = static_nat_config_read,
.write = static_nat_config_write,
};
static int __init nf_static_nat_init(void)
{
int ret = 0;
int i;
src_list = kzalloc(sizeof(struct hlist_head) * BUCKETS, GFP_KERNEL);
if (!src_list) {
ret = -ENOMEM;
goto out;
}
dst_list = kzalloc(sizeof(struct hlist_head) * BUCKETS, GFP_KERNEL);
if (!dst_list) {
ret = -ENOMEM;
goto out;
}
ret = nf_register_hooks(ipv4_nat_ops, ARRAY_SIZE(ipv4_nat_ops));
if (ret < 0) {
printk("nf_nat_ipv4: can‘t register hooks.\n");
goto out;
}
if (!proc_create("static_nat", 0644, init_net.proc_net, &static_nat_file_ops)) {
ret = -ENOMEM;
goto out;
}
for (i = 0; i < BUCKETS; i++) {
INIT_HLIST_HEAD(&src_list[i]);
INIT_HLIST_HEAD(&dst_list[i]);
}
return ret;
out:
if (src_list) {
kfree(src_list);
}
if (dst_list) {
kfree(dst_list);
}
return ret;
}
static void __exit nf_static_nat_fini(void)
{
int i;
remove_proc_entry("static_nat", init_net.proc_net);
nf_unregister_hooks(ipv4_nat_ops, ARRAY_SIZE(ipv4_nat_ops));
spin_lock(&nat_lock);
for (i = 0; i < BUCKETS; i++) {
struct hlist_node *iter, *tmp;
struct static_nat_entry *ent;
hlist_for_each_safe(iter, tmp, &src_list[i]) {
ent = hlist_entry(iter, struct static_nat_entry, node[0]);
hlist_del(&ent->node[DIR_SNAT]);
hlist_del(&ent->node[DIR_DNAT]);
kfree(ent);
}
}
spin_unlock(&nat_lock);
if (src_list) {
kfree(src_list);
}
if (dst_list) {
kfree(dst_list);
}
}
module_init(nf_static_nat_init);
module_exit(nf_static_nat_fini);
MODULE_DESCRIPTION("STATIC two-way NAT");
MODULE_AUTHOR("marywangran@126.com");
MODULE_LICENSE("GPL");
Makefile：
obj-m += nf_rawnat.o all: make -C /lib/modules/`uname -r`/build SUBDIRS=`pwd` modules clean: rm -rf *.ko *.o .tmp_versions .*.mod.o .*.o.cmd *.mod.c .*.ko.cmd Module.symvers modules.order
在Linux上实现一个可用的stateless双向静态NAT模块
标签：linux stateless nat stateful nat iptables netfilter
原文地址：http://blog.csdn.net/dog250/article/details/42046867
