ip_nat_helper.c

一个2.4.21版本的嵌入式linux内核

/* ip_nat_mangle.c - generic support functions for NAT helpers 
 *
 * (C) 2000-2002 by Harald Welte <[e-mail]>
 *
 * distributed under the terms of GNU GPL
 *
 * 	14 Jan 2002 Harald Welte <[e-mail]>:
 *		- add support for SACK adjustment 
 *	14 Mar 2002 Harald Welte <[e-mail]>:
 *		- merge SACK support into newnat API
 *	16 Aug 2002 Brian J. Murrell <[e-mail]>:
 *		- make ip_nat_resize_packet more generic (TCP and UDP)
 *		- add ip_nat_mangle_udp_packet
 */
#include <linux/version.h>
#include <linux/config.h>
#include <linux/module.h>
#include <linux/kmod.h>
#include <linux/types.h>
#include <linux/timer.h>
#include <linux/skbuff.h>
#include <linux/netfilter_ipv4.h>
#include <linux/brlock.h>
#include <net/checksum.h>
#include <net/icmp.h>
#include <net/ip.h>
#include <net/tcp.h>
#include <net/udp.h>

#define ASSERT_READ_LOCK(x) MUST_BE_READ_LOCKED(&ip_nat_lock)
#define ASSERT_WRITE_LOCK(x) MUST_BE_WRITE_LOCKED(&ip_nat_lock)

#include <linux/netfilter_ipv4/ip_conntrack.h>
#include <linux/netfilter_ipv4/ip_conntrack_helper.h>
#include <linux/netfilter_ipv4/ip_nat.h>
#include <linux/netfilter_ipv4/ip_nat_protocol.h>
#include <linux/netfilter_ipv4/ip_nat_core.h>
#include <linux/netfilter_ipv4/ip_nat_helper.h>
#include <linux/netfilter_ipv4/listhelp.h>

#if 0
#define DEBUGP printk
#define DUMP_OFFSET(x)	printk("offset_before=%d, offset_after=%d, correction_pos=%u\n", x->offset_before, x->offset_after, x->correction_pos);
#else
#define DEBUGP(format, args...)
#define DUMP_OFFSET(x)
#endif

DECLARE_LOCK(ip_nat_seqofs_lock);
			 
static inline int 
ip_nat_resize_packet(struct sk_buff **skb,
		     struct ip_conntrack *ct, 
		     enum ip_conntrack_info ctinfo,
		     int new_size)
{
	struct iphdr *iph;
	int dir;
	struct ip_nat_seq *this_way, *other_way;

	DEBUGP("ip_nat_resize_packet: old_size = %u, new_size = %u\n",
		(*skb)->len, new_size);

	dir = CTINFO2DIR(ctinfo);

	this_way = &ct->nat.info.seq[dir];
	other_way = &ct->nat.info.seq[!dir];

	if (new_size > (*skb)->len + skb_tailroom(*skb)) {
		struct sk_buff *newskb;
		newskb = skb_copy_expand(*skb, skb_headroom(*skb),
					 new_size - (*skb)->len,
					 GFP_ATOMIC);

		if (!newskb) {
			printk("ip_nat_resize_packet: oom\n");
			return 0;
		} else {
			kfree_skb(*skb);
			*skb = newskb;
		}
	}

	iph = (*skb)->nh.iph;
	if (iph->protocol == IPPROTO_TCP) {
		struct tcphdr *tcph = (void *)iph + iph->ihl*4;
		void *data = (void *)tcph + tcph->doff*4;

		DEBUGP("ip_nat_resize_packet: Seq_offset before: ");
		DUMP_OFFSET(this_way);

		LOCK_BH(&ip_nat_seqofs_lock);

		/* SYN adjust. If it's uninitialized, of this is after last 
		 * correction, record it: we don't handle more than one 
		 * adjustment in the window, but do deal with common case of a 
		 * retransmit */
		if (this_way->offset_before == this_way->offset_after
		    || before(this_way->correction_pos, ntohl(tcph->seq))) {
			this_way->correction_pos = ntohl(tcph->seq);
			this_way->offset_before = this_way->offset_after;
			this_way->offset_after = (int32_t)
				this_way->offset_before + new_size -
				(*skb)->len;
		}

		UNLOCK_BH(&ip_nat_seqofs_lock);

		DEBUGP("ip_nat_resize_packet: Seq_offset after: ");
		DUMP_OFFSET(this_way);
	}
	
	return 1;
}


/* Generic function for mangling variable-length address changes inside
 * NATed TCP connections (like the PORT XXX,XXX,XXX,XXX,XXX,XXX
 * command in FTP).
 *
 * Takes care about all the nasty sequence number changes, checksumming,
 * skb enlargement, ...
 *
 * */
int 
ip_nat_mangle_tcp_packet(struct sk_buff **skb,
			 struct ip_conntrack *ct,
			 enum ip_conntrack_info ctinfo,
			 unsigned int match_offset,
			 unsigned int match_len,
			 char *rep_buffer,
			 unsigned int rep_len)
{
	struct iphdr *iph = (*skb)->nh.iph;
	struct tcphdr *tcph;
	unsigned char *data;
	u_int32_t tcplen, newlen, newtcplen;

	tcplen = (*skb)->len - iph->ihl*4;
	newtcplen = tcplen - match_len + rep_len;
	newlen = iph->ihl*4 + newtcplen;

	if (newlen > 65535) {
		if (net_ratelimit())
			printk("ip_nat_mangle_tcp_packet: nat'ed packet "
				"exceeds maximum packet size\n");
		return 0;
	}

	if ((*skb)->len != newlen) {
		if (!ip_nat_resize_packet(skb, ct, ctinfo, newlen)) {
			printk("resize_packet failed!!\n");
			return 0;
		}
	}

	/* Alexey says: if a hook changes _data_ ... it can break
	   original packet sitting in tcp queue and this is fatal */
	if (skb_cloned(*skb)) {
		struct sk_buff *nskb = skb_copy(*skb, GFP_ATOMIC);
		if (!nskb) {
			if (net_ratelimit())
				printk("Out of memory cloning TCP packet\n");
			return 0;
		}
		/* Rest of kernel will get very unhappy if we pass it
		   a suddenly-orphaned skbuff */
		if ((*skb)->sk)
			skb_set_owner_w(nskb, (*skb)->sk);
		kfree_skb(*skb);
		*skb = nskb;
	}

	/* skb may be copied !! */
	iph = (*skb)->nh.iph;
	tcph = (void *)iph + iph->ihl*4;
	data = (void *)tcph + tcph->doff*4;

	if (rep_len != match_len)
		/* move post-replacement */
		memmove(data + match_offset + rep_len,
			data + match_offset + match_len,
			(*skb)->tail - (data + match_offset + match_len));

	/* insert data from buffer */
	memcpy(data + match_offset, rep_buffer, rep_len);

	/* update skb info */
	if (newlen > (*skb)->len) {
		DEBUGP("ip_nat_mangle_tcp_packet: Extending packet by "
			"%u to %u bytes\n", newlen - (*skb)->len, newlen);
		skb_put(*skb, newlen - (*skb)->len);
	} else {
		DEBUGP("ip_nat_mangle_tcp_packet: Shrinking packet from "
			"%u to %u bytes\n", (*skb)->len, newlen);
		skb_trim(*skb, newlen);
	}

	/* fix checksum information */

	iph->tot_len = htons(newlen);
	(*skb)->csum = csum_partial((char *)tcph + tcph->doff*4,
				    newtcplen - tcph->doff*4, 0);

	tcph->check = 0;
	tcph->check = tcp_v4_check(tcph, newtcplen, iph->saddr, iph->daddr,
				   csum_partial((char *)tcph, tcph->doff*4,
					   (*skb)->csum));
	ip_send_check(iph);

	return 1;
}
			
/* Generic function for mangling variable-length address changes inside
 * NATed UDP connections (like the CONNECT DATA XXXXX MESG XXXXX INDEX XXXXX
 * command in the Amanda protocol)
 *
 * Takes care about all the nasty sequence number changes, checksumming,
 * skb enlargement, ...
 *
 * XXX - This function could be merged with ip_nat_mangle_tcp_packet which
 *       should be fairly easy to do.
 */
int 
ip_nat_mangle_udp_packet(struct sk_buff **skb,
			 struct ip_conntrack *ct,
			 enum ip_conntrack_info ctinfo,
			 unsigned int match_offset,
			 unsigned int match_len,
			 char *rep_buffer,
			 unsigned int rep_len)
{
	struct iphdr *iph = (*skb)->nh.iph;
	struct udphdr *udph = (void *)iph + iph->ihl * 4;
	unsigned char *data;
	u_int32_t udplen, newlen, newudplen;

	udplen = (*skb)->len - iph->ihl*4;
	newudplen = udplen - match_len + rep_len;
	newlen = iph->ihl*4 + newudplen;

	if (newlen > 65535) {
		if (net_ratelimit())
			printk("ip_nat_mangle_udp_packet: nat'ed packet "
				"exceeds maximum packet size\n");
		return 0;
	}

	if ((*skb)->len != newlen) {
		if (!ip_nat_resize_packet(skb, ct, ctinfo, newlen)) {
			printk("resize_packet failed!!\n");
			return 0;
		}
	}

	/* Alexey says: if a hook changes _data_ ... it can break
	   original packet sitting in tcp queue and this is fatal */
	if (skb_cloned(*skb)) {
		struct sk_buff *nskb = skb_copy(*skb, GFP_ATOMIC);
		if (!nskb) {
			if (net_ratelimit())
				printk("Out of memory cloning TCP packet\n");
			return 0;
		}
		/* Rest of kernel will get very unhappy if we pass it
		   a suddenly-orphaned skbuff */
		if ((*skb)->sk)
			skb_set_owner_w(nskb, (*skb)->sk);
		kfree_skb(*skb);
		*skb = nskb;
	}

	/* skb may be copied !! */
	iph = (*skb)->nh.iph;
	udph = (void *)iph + iph->ihl*4;
	data = (void *)udph + sizeof(struct udphdr);

	if (rep_len != match_len)
		/* move post-replacement */
		memmove(data + match_offset + rep_len,
			data + match_offset + match_len,
			(*skb)->tail - (data + match_offset + match_len));

	/* insert data from buffer */
	memcpy(data + match_offset, rep_buffer, rep_len);

	/* update skb info */
	if (newlen > (*skb)->len) {
		DEBUGP("ip_nat_mangle_udp_packet: Extending packet by "
			"%u to %u bytes\n", newlen - (*skb)->len, newlen);