summaryrefslogtreecommitdiff
path: root/include/net/ip.h
blob: 5b26a0bd178ecc031d357786f519bfdacde0f8eb (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Definitions for the IP module.
 *
 * Version:	@(#)ip.h	1.0.2	05/07/93
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Alan Cox, <gw4pts@gw4pts.ampr.org>
 *
 * Changes:
 *		Mike McLagan    :       Routing by source
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 */
#ifndef _IP_H
#define _IP_H

#include <linux/types.h>
#include <linux/ip.h>
#include <linux/in.h>
#include <linux/skbuff.h>

#include <net/inet_sock.h>
#include <net/snmp.h>
#include <net/flow.h>

struct sock;

struct inet_skb_parm
{
	struct ip_options	opt;		/* Compiled IP options		*/
	unsigned char		flags;

#define IPSKB_FORWARDED		1
#define IPSKB_XFRM_TUNNEL_SIZE	2
#define IPSKB_XFRM_TRANSFORMED	4
#define IPSKB_FRAG_COMPLETE	8
#define IPSKB_REROUTED		16
};

static inline unsigned int ip_hdrlen(const struct sk_buff *skb)
{
	return ip_hdr(skb)->ihl * 4;
}

struct ipcm_cookie
{
	__be32			addr;
	int			oif;
	struct ip_options	*opt;
	union skb_shared_tx	shtx;
};

#define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))

struct ip_ra_chain
{
	struct ip_ra_chain	*next;
	struct sock		*sk;
	void			(*destructor)(struct sock *);
};

extern struct ip_ra_chain *ip_ra_chain;
extern rwlock_t ip_ra_lock;

/* IP flags. */
#define IP_CE		0x8000		/* Flag: "Congestion"		*/
#define IP_DF		0x4000		/* Flag: "Don't Fragment"	*/
#define IP_MF		0x2000		/* Flag: "More Fragments"	*/
#define IP_OFFSET	0x1FFF		/* "Fragment Offset" part	*/

#define IP_FRAG_TIME	(30 * HZ)		/* fragment lifetime	*/

struct msghdr;
struct net_device;
struct packet_type;
struct rtable;
struct sockaddr;

extern int		igmp_mc_proc_init(void);

/*
 *	Functions provided by ip.c
 */

extern int		ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
					      __be32 saddr, __be32 daddr,
					      struct ip_options *opt);
extern int		ip_rcv(struct sk_buff *skb, struct net_device *dev,
			       struct packet_type *pt, struct net_device *orig_dev);
extern int		ip_local_deliver(struct sk_buff *skb);
extern int		ip_mr_input(struct sk_buff *skb);
extern int		ip_output(struct sk_buff *skb);
extern int		ip_mc_output(struct sk_buff *skb);
extern int		ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
extern int		ip_do_nat(struct sk_buff *skb);
extern void		ip_send_check(struct iphdr *ip);
extern int		__ip_local_out(struct sk_buff *skb);
extern int		ip_local_out(struct sk_buff *skb);
extern int		ip_queue_xmit(struct sk_buff *skb, int ipfragok);
extern void		ip_init(void);
extern int		ip_append_data(struct sock *sk,
				       int getfrag(void *from, char *to, int offset, int len,
						   int odd, struct sk_buff *skb),
				void *from, int len, int protolen,
				struct ipcm_cookie *ipc,
				struct rtable **rt,
				unsigned int flags);
extern int		ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb);
extern ssize_t		ip_append_page(struct sock *sk, struct page *page,
				int offset, size_t size, int flags);
extern int		ip_push_pending_frames(struct sock *sk);
extern void		ip_flush_pending_frames(struct sock *sk);

/* datagram.c */
extern int		ip4_datagram_connect(struct sock *sk, 
					     struct sockaddr *uaddr, int addr_len);

/*
 *	Map a multicast IP onto multicast MAC for type Token Ring.
 *      This conforms to RFC1469 Option 2 Multicasting i.e.
 *      using a functional address to transmit / receive 
 *      multicast packets.
 */

static inline void ip_tr_mc_map(__be32 addr, char *buf)
{
	buf[0]=0xC0;
	buf[1]=0x00;
	buf[2]=0x00;
	buf[3]=0x04;
	buf[4]=0x00;
	buf[5]=0x00;
}

struct ip_reply_arg {
	struct kvec iov[1];   
	int	    flags;
	__wsum 	    csum;
	int	    csumoffset; /* u16 offset of csum in iov[0].iov_base */
				/* -1 if not needed */ 
	int	    bound_dev_if;
}; 

#define IP_REPLY_ARG_NOSRCCHECK 1

static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg)
{
	return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0;
}

void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *arg,
		   unsigned int len); 

struct ipv4_config
{
	int	log_martians;
	int	no_pmtu_disc;
};

extern struct ipv4_config ipv4_config;
#define IP_INC_STATS(net, field)	SNMP_INC_STATS((net)->mib.ip_statistics, field)
#define IP_INC_STATS_BH(net, field)	SNMP_INC_STATS_BH((net)->mib.ip_statistics, field)
#define IP_ADD_STATS(net, field, val)	SNMP_ADD_STATS((net)->mib.ip_statistics, field, val)
#define IP_ADD_STATS_BH(net, field, val) SNMP_ADD_STATS_BH((net)->mib.ip_statistics, field, val)
#define IP_UPD_PO_STATS(net, field, val) SNMP_UPD_PO_STATS((net)->mib.ip_statistics, field, val)
#define IP_UPD_PO_STATS_BH(net, field, val) SNMP_UPD_PO_STATS_BH((net)->mib.ip_statistics, field, val)
#define NET_INC_STATS(net, field)	SNMP_INC_STATS((net)->mib.net_statistics, field)
#define NET_INC_STATS_BH(net, field)	SNMP_INC_STATS_BH((net)->mib.net_statistics, field)
#define NET_INC_STATS_USER(net, field) 	SNMP_INC_STATS_USER((net)->mib.net_statistics, field)
#define NET_ADD_STATS_BH(net, field, adnd) SNMP_ADD_STATS_BH((net)->mib.net_statistics, field, adnd)
#define NET_ADD_STATS_USER(net, field, adnd) SNMP_ADD_STATS_USER((net)->mib.net_statistics, field, adnd)

extern unsigned long snmp_fold_field(void *mib[], int offt);
extern int snmp_mib_init(void *ptr[2], size_t mibsize);
extern void snmp_mib_free(void *ptr[2]);

extern struct local_ports {
	seqlock_t	lock;
	int		range[2];
} sysctl_local_ports;
extern void inet_get_local_port_range(int *low, int *high);

extern int sysctl_ip_default_ttl;
extern int sysctl_ip_nonlocal_bind;

extern struct ctl_path net_core_path[];
extern struct ctl_path net_ipv4_ctl_path[];

/* From inetpeer.c */
extern int inet_peer_threshold;
extern int inet_peer_minttl;
extern int inet_peer_maxttl;
extern int inet_peer_gc_mintime;
extern int inet_peer_gc_maxtime;

/* From ip_output.c */
extern int sysctl_ip_dynaddr;

extern void ipfrag_init(void);

extern void ip_static_sysctl_init(void);

#ifdef CONFIG_INET
#include <net/dst.h>

/* The function in 2.2 was invalid, producing wrong result for
 * check=0xFEFF. It was noticed by Arthur Skawina _year_ ago. --ANK(000625) */
static inline
int ip_decrease_ttl(struct iphdr *iph)
{
	u32 check = (__force u32)iph->check;
	check += (__force u32)htons(0x0100);
	iph->check = (__force __sum16)(check + (check>=0xFFFF));
	return --iph->ttl;
}

static inline
int ip_dont_fragment(struct sock *sk, struct dst_entry *dst)
{
	return (inet_sk(sk)->pmtudisc == IP_PMTUDISC_DO ||
		(inet_sk(sk)->pmtudisc == IP_PMTUDISC_WANT &&
		 !(dst_metric_locked(dst, RTAX_MTU))));
}

extern void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more);

static inline void ip_select_ident(struct iphdr *iph, struct dst_entry *dst, struct sock *sk)
{
	if (iph->frag_off & htons(IP_DF)) {
		/* This is only to work around buggy Windows95/2000
		 * VJ compression implementations.  If the ID field
		 * does not change, they drop every other packet in
		 * a TCP stream using header compression.
		 */
		iph->id = (sk && inet_sk(sk)->daddr) ?
					htons(inet_sk(sk)->id++) : 0;
	} else
		__ip_select_ident(iph, dst, 0);
}

static inline void ip_select_ident_more(struct iphdr *iph, struct dst_entry *dst, struct sock *sk, int more)
{
	if (iph->frag_off & htons(IP_DF)) {
		if (sk && inet_sk(sk)->daddr) {
			iph->id = htons(inet_sk(sk)->id);
			inet_sk(sk)->id += 1 + more;
		} else
			iph->id = 0;
	} else
		__ip_select_ident(iph, dst, more);
}

/*
 *	Map a multicast IP onto multicast MAC for type ethernet.
 */

static inline void ip_eth_mc_map(__be32 naddr, char *buf)
{
	__u32 addr=ntohl(naddr);
	buf[0]=0x01;
	buf[1]=0x00;
	buf[2]=0x5e;
	buf[5]=addr&0xFF;
	addr>>=8;
	buf[4]=addr&0xFF;
	addr>>=8;
	buf[3]=addr&0x7F;
}

/*
 *	Map a multicast IP onto multicast MAC for type IP-over-InfiniBand.
 *	Leave P_Key as 0 to be filled in by driver.
 */

static inline void ip_ib_mc_map(__be32 naddr, const unsigned char *broadcast, char *buf)
{
	__u32 addr;
	unsigned char scope = broadcast[5] & 0xF;

	buf[0]  = 0;		/* Reserved */
	buf[1]  = 0xff;		/* Multicast QPN */
	buf[2]  = 0xff;
	buf[3]  = 0xff;
	addr    = ntohl(naddr);
	buf[4]  = 0xff;
	buf[5]  = 0x10 | scope;	/* scope from broadcast address */
	buf[6]  = 0x40;		/* IPv4 signature */
	buf[7]  = 0x1b;
	buf[8]  = broadcast[8];		/* P_Key */
	buf[9]  = broadcast[9];
	buf[10] = 0;
	buf[11] = 0;
	buf[12] = 0;
	buf[13] = 0;
	buf[14] = 0;
	buf[15] = 0;
	buf[19] = addr & 0xff;
	addr  >>= 8;
	buf[18] = addr & 0xff;
	addr  >>= 8;
	buf[17] = addr & 0xff;
	addr  >>= 8;
	buf[16] = addr & 0x0f;
}

#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
#include <linux/ipv6.h>
#endif

static __inline__ void inet_reset_saddr(struct sock *sk)
{
	inet_sk(sk)->rcv_saddr = inet_sk(sk)->saddr = 0;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
	if (sk->sk_family == PF_INET6) {
		struct ipv6_pinfo *np = inet6_sk(sk);

		memset(&np->saddr, 0, sizeof(np->saddr));
		memset(&np->rcv_saddr, 0, sizeof(np->rcv_saddr));
	}
#endif
}

#endif

extern int	ip_call_ra_chain(struct sk_buff *skb);

/*
 *	Functions provided by ip_fragment.c
 */

enum ip_defrag_users
{
	IP_DEFRAG_LOCAL_DELIVER,
	IP_DEFRAG_CALL_RA_CHAIN,
	IP_DEFRAG_CONNTRACK_IN,
	IP_DEFRAG_CONNTRACK_OUT,
	IP_DEFRAG_VS_IN,
	IP_DEFRAG_VS_OUT,
	IP_DEFRAG_VS_FWD
};

int ip_defrag(struct sk_buff *skb, u32 user);
int ip_frag_mem(struct net *net);
int ip_frag_nqueues(struct net *net);

/*
 *	Functions provided by ip_forward.c
 */
 
extern int ip_forward(struct sk_buff *skb);
 
/*
 *	Functions provided by ip_options.c
 */
 
extern void ip_options_build(struct sk_buff *skb, struct ip_options *opt, __be32 daddr, struct rtable *rt, int is_frag);
extern int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb);
extern void ip_options_fragment(struct sk_buff *skb);
extern int ip_options_compile(struct net *net,
			      struct ip_options *opt, struct sk_buff *skb);
extern int ip_options_get(struct net *net, struct ip_options **optp,
			  unsigned char *data, int optlen);
extern int ip_options_get_from_user(struct net *net, struct ip_options **optp,
				    unsigned char __user *data, int optlen);
extern void ip_options_undo(struct ip_options * opt);
extern void ip_forward_options(struct sk_buff *skb);
extern int ip_options_rcv_srr(struct sk_buff *skb);

/*
 *	Functions provided by ip_sockglue.c
 */

extern void	ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb);
extern int	ip_cmsg_send(struct net *net,
			     struct msghdr *msg, struct ipcm_cookie *ipc);
extern int	ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen);
extern int	ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen);
extern int	compat_ip_setsockopt(struct sock *sk, int level,
			int optname, char __user *optval, int optlen);
extern int	compat_ip_getsockopt(struct sock *sk, int level,
			int optname, char __user *optval, int __user *optlen);
extern int	ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *));

extern int 	ip_recv_error(struct sock *sk, struct msghdr *msg, int len);
extern void	ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, 
			      __be16 port, u32 info, u8 *payload);
extern void	ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
			       u32 info);

/* sysctl helpers - any sysctl which holds a value that ends up being
 * fed into the routing cache should use these handlers.
 */
int ipv4_doint_and_flush(ctl_table *ctl, int write,
			 void __user *buffer,
			 size_t *lenp, loff_t *ppos);
int ipv4_doint_and_flush_strategy(ctl_table *table,
				  void __user *oldval, size_t __user *oldlenp,
				  void __user *newval, size_t newlen);
#ifdef CONFIG_PROC_FS
extern int ip_misc_proc_init(void);
#endif

#endif	/* _IP_H */