aboutsummaryrefslogtreecommitdiffstats
path: root/include/net/ip.h
blob: 562eb653aebc2f4b6e1782eba9fe26060dc48439 (plain) (blame)
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
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
/*
 * 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/route.h>
#include <net/snmp.h>
#include <net/flow.h>
#include <net/flow_dissector.h>

struct sock;

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

#define IPSKB_FORWARDED		BIT(0)
#define IPSKB_XFRM_TUNNEL_SIZE	BIT(1)
#define IPSKB_XFRM_TRANSFORMED	BIT(2)
#define IPSKB_FRAG_COMPLETE	BIT(3)
#define IPSKB_REROUTED		BIT(4)
#define IPSKB_DOREDIRECT	BIT(5)

	u16			frag_max_size;
};

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_rcu	*opt;
	__u8			tx_flags;
	__u8			ttl;
	__s16			tos;
	char			priority;
};

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

struct ip_ra_chain {
	struct ip_ra_chain __rcu *next;
	struct sock		*sk;
	union {
		void			(*destructor)(struct sock *);
		struct sock		*saved_sk;
	};
	struct rcu_head		rcu;
};

extern struct ip_ra_chain __rcu *ip_ra_chain;

/* 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;

int igmp_mc_init(void);

/*
 *	Functions provided by ip.c
 */

int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
			  __be32 saddr, __be32 daddr,
			  struct ip_options_rcu *opt);
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
	   struct net_device *orig_dev);
int ip_local_deliver(struct sk_buff *skb);
int ip_mr_input(struct sk_buff *skb);
int ip_output(struct sock *sk, struct sk_buff *skb);
int ip_mc_output(struct sock *sk, struct sk_buff *skb);
int ip_fragment(struct sock *sk, struct sk_buff *skb,
		int (*output)(struct sock *, struct sk_buff *));
int ip_do_nat(struct sk_buff *skb);
void ip_send_check(struct iphdr *ip);
int __ip_local_out(struct sk_buff *skb);
int ip_local_out_sk(struct sock *sk, struct sk_buff *skb);
static inline int ip_local_out(struct sk_buff *skb)
{
	return ip_local_out_sk(skb->sk, skb);
}

int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
void ip_init(void);
int ip_append_data(struct sock *sk, struct flowi4 *fl4,
		   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);
int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd,
		       struct sk_buff *skb);
ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
		       int offset, size_t size, int flags);
struct sk_buff *__ip_make_skb(struct sock *sk, struct flowi4 *fl4,
			      struct sk_buff_head *queue,
			      struct inet_cork *cork);
int ip_send_skb(struct net *net, struct sk_buff *skb);
int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4);
void ip_flush_pending_frames(struct sock *sk);
struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4,
			    int getfrag(void *from, char *to, int offset,
					int len, int odd, struct sk_buff *skb),
			    void *from, int length, int transhdrlen,
			    struct ipcm_cookie *ipc, struct rtable **rtp,
			    unsigned int flags);

static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
{
	return __ip_make_skb(sk, fl4, &sk->sk_write_queue, &inet_sk(sk)->cork.base);
}

static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet)
{
	return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(inet->tos);
}

static inline __u8 get_rtconn_flags(struct ipcm_cookie* ipc, struct sock* sk)
{
	return (ipc->tos != -1) ? RT_CONN_FLAGS_TOS(sk, ipc->tos) : RT_CONN_FLAGS(sk);
}

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

void ip4_datagram_release_cb(struct sock *sk);

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;
	u8  	    tos;
}; 

#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_unicast_reply(struct sock *sk, struct sk_buff *skb,
			   const struct ip_options *sopt,
			   __be32 daddr, __be32 saddr,
			   const struct ip_reply_arg *arg,
			   unsigned int len);

#define IP_INC_STATS(net, field)	SNMP_INC_STATS64((net)->mib.ip_statistics, field)
#define IP_INC_STATS_BH(net, field)	SNMP_INC_STATS64_BH((net)->mib.ip_statistics, field)
#define IP_ADD_STATS(net, field, val)	SNMP_ADD_STATS64((net)->mib.ip_statistics, field, val)
#define IP_ADD_STATS_BH(net, field, val) SNMP_ADD_STATS64_BH((net)->mib.ip_statistics, field, val)
#define IP_UPD_PO_STATS(net, field, val) SNMP_UPD_PO_STATS64((net)->mib.ip_statistics, field, val)
#define IP_UPD_PO_STATS_BH(net, field, val) SNMP_UPD_PO_STATS64_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(net, field, adnd)	SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd)
#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)

unsigned long snmp_fold_field(void __percpu *mib, int offt);
#if BITS_PER_LONG==32
u64 snmp_fold_field64(void __percpu *mib, int offt, size_t sync_off);
#else
static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_off)
{
	return snmp_fold_field(mib, offt);
}
#endif

void inet_get_local_port_range(struct net *net, int *low, int *high);

#ifdef CONFIG_SYSCTL
static inline int inet_is_local_reserved_port(struct net *net, int port)
{
	if (!net->ipv4.sysctl_local_reserved_ports)
		return 0;
	return test_bit(port, net->ipv4.sysctl_local_reserved_ports);
}

static inline bool sysctl_dev_name_is_allowed(const char *name)
{
	return strcmp(name, "default") != 0  && strcmp(name, "all") != 0;
}

#else
static inline int inet_is_local_reserved_port(struct net *net, int port)
{
	return 0;
}
#endif

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

/* From ip_input.c */
extern int sysctl_ip_early_demux;

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

void ipfrag_init(void);

void ip_static_sysctl_init(void);

#define IP4_REPLY_MARK(net, mark) \
	((net)->ipv4.sysctl_fwmark_reflect ? (mark) : 0)

static inline bool ip_is_fragment(const struct iphdr *iph)
{
	return (iph->frag_off & htons(IP_MF | IP_OFFSET)) != 0;
}

#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)));
}

static inline bool ip_sk_accept_pmtu(const struct sock *sk)
{
	return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE &&
	       inet_sk(sk)->pmtudisc != IP_PMTUDISC_OMIT;
}

static inline bool ip_sk_use_pmtu(const struct sock *sk)
{
	return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE;
}

static inline bool ip_sk_ignore_df(const struct sock *sk)
{
	return inet_sk(sk)->pmtudisc < IP_PMTUDISC_DO ||
	       inet_sk(sk)->pmtudisc == IP_PMTUDISC_OMIT;
}

static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
						    bool forwarding)
{
	struct net *net = dev_net(dst->dev);

	if (net->ipv4.sysctl_ip_fwd_use_pmtu ||
	    dst_metric_locked(dst, RTAX_MTU) ||
	    !forwarding)
		return dst_mtu(dst);

	return min(dst->dev->mtu, IP_MAX_MTU);
}

static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb)
{
	if (!skb->sk || ip_sk_use_pmtu(skb->sk)) {
		bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;
		return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding);
	} else {
		return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU);
	}
}

u32 ip_idents_reserve(u32 hash, int segs);
void __ip_select_ident(struct net *net, struct iphdr *iph, int segs);

static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb,
					struct sock *sk, int segs)
{
	struct iphdr *iph = ip_hdr(skb);

	if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_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.
		 */
		if (sk && inet_sk(sk)->inet_daddr) {
			iph->id = htons(inet_sk(sk)->inet_id);
			inet_sk(sk)->inet_id += segs;
		} else {
			iph->id = 0;
		}
	} else {
		__ip_select_ident(net, iph, segs);
	}
}

static inline void ip_select_ident(struct net *net, struct sk_buff *skb,
				   struct sock *sk)
{
	ip_select_ident_segs(net, skb, sk, 1);
}

static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto)
{
	return csum_tcpudp_nofold(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
				  skb->len, proto, 0);
}

static inline void inet_set_txhash(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);
	struct flow_keys keys;

	keys.src = inet->inet_saddr;
	keys.dst = inet->inet_daddr;
	keys.port16[0] = inet->inet_sport;
	keys.port16[1] = inet->inet_dport;

	sk->sk_txhash = flow_hash_from_keys(&keys);
}

static inline __wsum inet_gro_compute_pseudo(struct sk_buff *skb, int proto)
{
	const struct iphdr *iph = skb_gro_network_header(skb);

	return csum_tcpudp_nofold(iph->saddr, iph->daddr,
				  skb_gro_len(skb), proto, 0);
}

/*
 *	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;
}

static inline void ip_ipgre_mc_map(__be32 naddr, const unsigned char *broadcast, char *buf)
{
	if ((broadcast[0] | broadcast[1] | broadcast[2] | broadcast[3]) != 0)
		memcpy(buf, broadcast, 4);
	else
		memcpy(buf, &naddr, sizeof(naddr));
}

#if IS_ENABLED(CONFIG_IPV6)
#include <linux/ipv6.h>
#endif

static __inline__ void inet_reset_saddr(struct sock *sk)
{
	inet_sk(sk)->inet_rcv_saddr = inet_sk(sk)->inet_saddr = 0;
#if IS_ENABLED(CONFIG_IPV6)
	if (sk->sk_family == PF_INET6) {
		struct ipv6_pinfo *np = inet6_sk(sk);

		memset(&np->saddr, 0, sizeof(np->saddr));
		memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr));
	}
#endif
}

#endif

bool 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_IN_END	= IP_DEFRAG_CONNTRACK_IN + USHRT_MAX,
	IP_DEFRAG_CONNTRACK_OUT,
	__IP_DEFRAG_CONNTRACK_OUT_END	= IP_DEFRAG_CONNTRACK_OUT + USHRT_MAX,
	IP_DEFRAG_CONNTRACK_BRIDGE_IN,
	__IP_DEFRAG_CONNTRACK_BRIDGE_IN = IP_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
	IP_DEFRAG_VS_IN,
	IP_DEFRAG_VS_OUT,
	IP_DEFRAG_VS_FWD,
	IP_DEFRAG_AF_PACKET,
	IP_DEFRAG_MACVLAN,
};

int ip_defrag(struct sk_buff *skb, u32 user);
#ifdef CONFIG_INET
struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user);
#else
static inline struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
{
	return skb;
}
#endif
int ip_frag_mem(struct net *net);

/*
 *	Functions provided by ip_forward.c
 */
 
int ip_forward(struct sk_buff *skb);
 
/*
 *	Functions provided by ip_options.c
 */
 
void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
		      __be32 daddr, struct rtable *rt, int is_frag);

int __ip_options_echo(struct ip_options *dopt, struct sk_buff *skb,
		      const struct ip_options *sopt);
static inline int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb)
{
	return __ip_options_echo(dopt, skb, &IPCB(skb)->opt);
}

void ip_options_fragment(struct sk_buff *skb);
int ip_options_compile(struct net *net, struct ip_options *opt,
		       struct sk_buff *skb);
int ip_options_get(struct net *net, struct ip_options_rcu **optp,
		   unsigned char *data, int optlen);
int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp,
			     unsigned char __user *data, int optlen);
void ip_options_undo(struct ip_options *opt);
void ip_forward_options(struct sk_buff *skb);
int ip_options_rcv_srr(struct sk_buff *skb);

/*
 *	Functions provided by ip_sockglue.c
 */

void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int offset);
int ip_cmsg_send(struct net *net, struct msghdr *msg,
		 struct ipcm_cookie *ipc, bool allow_ipv6);
int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
		  unsigned int optlen);
int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
		  int __user *optlen);
int compat_ip_setsockopt(struct sock *sk, int level, int optname,
			 char __user *optval, unsigned int optlen);
int compat_ip_getsockopt(struct sock *sk, int level, int optname,
			 char __user *optval, int __user *optlen);
int ip_ra_control(struct sock *sk, unsigned char on,
		  void (*destructor)(struct sock *));

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

static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
{
	ip_cmsg_recv_offset(msg, skb, 0);
}

bool icmp_global_allow(void);
extern int sysctl_icmp_msgs_per_sec;
extern int sysctl_icmp_msgs_burst;

#ifdef CONFIG_PROC_FS
int ip_misc_proc_init(void);
#endif

#endif	/* _IP_H */