ip_set.h 15.9 KB
Newer Older
1
2
3
/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu>
 *                         Patrick Schaaf <bof@bof.de>
 *                         Martin Josefsson <gandalf@wlug.westbo.se>
4
 * Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
5
6
7
8
9
 *
 * 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.
 */
10
11
#ifndef _IP_SET_H
#define _IP_SET_H
12

13
14
15
16
17
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/netlink.h>
#include <linux/netfilter.h>
#include <linux/netfilter/x_tables.h>
18
#include <linux/stringify.h>
19
20
#include <linux/vmalloc.h>
#include <net/netlink.h>
21
#include <uapi/linux/netfilter/ipset/ip_set.h>
22

23
24
25
26
27
#define _IP_SET_MODULE_DESC(a, b, c)		\
	MODULE_DESCRIPTION(a " type of IP sets, revisions " b "-" c)
#define IP_SET_MODULE_DESC(a, b, c)		\
	_IP_SET_MODULE_DESC(a, __stringify(b), __stringify(c))

28
29
30
31
32
33
34
35
36
37
38
39
/* Set features */
enum ip_set_feature {
	IPSET_TYPE_IP_FLAG = 0,
	IPSET_TYPE_IP = (1 << IPSET_TYPE_IP_FLAG),
	IPSET_TYPE_PORT_FLAG = 1,
	IPSET_TYPE_PORT = (1 << IPSET_TYPE_PORT_FLAG),
	IPSET_TYPE_MAC_FLAG = 2,
	IPSET_TYPE_MAC = (1 << IPSET_TYPE_MAC_FLAG),
	IPSET_TYPE_IP2_FLAG = 3,
	IPSET_TYPE_IP2 = (1 << IPSET_TYPE_IP2_FLAG),
	IPSET_TYPE_NAME_FLAG = 4,
	IPSET_TYPE_NAME = (1 << IPSET_TYPE_NAME_FLAG),
40
41
	IPSET_TYPE_IFACE_FLAG = 5,
	IPSET_TYPE_IFACE = (1 << IPSET_TYPE_IFACE_FLAG),
42
43
44
	IPSET_TYPE_MARK_FLAG = 6,
	IPSET_TYPE_MARK = (1 << IPSET_TYPE_MARK_FLAG),
	IPSET_TYPE_NOMATCH_FLAG = 7,
45
	IPSET_TYPE_NOMATCH = (1 << IPSET_TYPE_NOMATCH_FLAG),
46
47
	/* Strictly speaking not a feature, but a flag for dumping:
	 * this settype must be dumped last */
48
	IPSET_DUMP_LAST_FLAG = 8,
49
50
51
	IPSET_DUMP_LAST = (1 << IPSET_DUMP_LAST_FLAG),
};

52
53
/* Set extensions */
enum ip_set_extension {
54
	IPSET_EXT_BIT_TIMEOUT = 0,
55
	IPSET_EXT_TIMEOUT = (1 << IPSET_EXT_BIT_TIMEOUT),
56
	IPSET_EXT_BIT_COUNTER = 1,
57
	IPSET_EXT_COUNTER = (1 << IPSET_EXT_BIT_COUNTER),
58
59
	IPSET_EXT_BIT_COMMENT = 2,
	IPSET_EXT_COMMENT = (1 << IPSET_EXT_BIT_COMMENT),
60
61
	IPSET_EXT_BIT_SKBINFO = 3,
	IPSET_EXT_SKBINFO = (1 << IPSET_EXT_BIT_SKBINFO),
62
63
64
	/* Mark set with an extension which needs to call destroy */
	IPSET_EXT_BIT_DESTROY = 7,
	IPSET_EXT_DESTROY = (1 << IPSET_EXT_BIT_DESTROY),
65
66
67
};

#define SET_WITH_TIMEOUT(s)	((s)->extensions & IPSET_EXT_TIMEOUT)
68
#define SET_WITH_COUNTER(s)	((s)->extensions & IPSET_EXT_COUNTER)
69
#define SET_WITH_COMMENT(s)	((s)->extensions & IPSET_EXT_COMMENT)
70
#define SET_WITH_SKBINFO(s)	((s)->extensions & IPSET_EXT_SKBINFO)
71
#define SET_WITH_FORCEADD(s)	((s)->flags & IPSET_CREATE_FLAG_FORCEADD)
72

73
74
75
76
/* Extension id, in size order */
enum ip_set_ext_id {
	IPSET_EXT_ID_COUNTER = 0,
	IPSET_EXT_ID_TIMEOUT,
77
	IPSET_EXT_ID_SKBINFO,
78
	IPSET_EXT_ID_COMMENT,
79
80
81
	IPSET_EXT_ID_MAX,
};

82
83
/* Extension type */
struct ip_set_ext_type {
84
85
	/* Destroy extension private data (can be NULL) */
	void (*destroy)(void *ext);
86
87
88
89
90
91
92
93
94
	enum ip_set_extension type;
	enum ipset_cadt_flags flag;
	/* Size and minimal alignment */
	u8 len;
	u8 align;
};

extern const struct ip_set_ext_type ip_set_extensions[];

95
struct ip_set_ext {
96
97
	u64 packets;
	u64 bytes;
98
	u32 timeout;
99
100
101
102
	u32 skbmark;
	u32 skbmarkmask;
	u32 skbprio;
	u16 skbqueue;
103
	char *comment;
104
105
};

106
107
108
109
110
struct ip_set_counter {
	atomic64_t bytes;
	atomic64_t packets;
};

111
112
113
114
115
struct ip_set_comment_rcu {
	struct rcu_head rcu;
	char str[0];
};

116
struct ip_set_comment {
117
	struct ip_set_comment_rcu __rcu *c;
118
};
119

120
121
122
123
124
125
126
struct ip_set_skbinfo {
	u32 skbmark;
	u32 skbmarkmask;
	u32 skbprio;
	u16 skbqueue;
};

127
struct ip_set;
128

129
#define ext_timeout(e, s)	\
130
((unsigned long *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_TIMEOUT]))
131
#define ext_counter(e, s)	\
132
((struct ip_set_counter *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COUNTER]))
133
#define ext_comment(e, s)	\
134
((struct ip_set_comment *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COMMENT]))
135
#define ext_skbinfo(e, s)	\
136
((struct ip_set_skbinfo *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_SKBINFO]))
137

138
typedef int (*ipset_adtfn)(struct ip_set *set, void *value,
139
			   const struct ip_set_ext *ext,
140
			   struct ip_set_ext *mext, u32 cmdflags);
141

142
143
144
145
146
147
/* Kernel API function options */
struct ip_set_adt_opt {
	u8 family;		/* Actual protocol family */
	u8 dim;			/* Dimension of match/target */
	u8 flags;		/* Direction and negation flags */
	u32 cmdflags;		/* Command-like flags */
148
	struct ip_set_ext ext;	/* Extensions */
149
150
};

151
152
153
154
155
156
/* Set type, variant-specific part */
struct ip_set_type_variant {
	/* Kernelspace: test/add/del entries
	 *		returns negative error code,
	 *			zero for no match/success to add/delete
	 *			positive for matching element */
157
	int (*kadt)(struct ip_set *set, const struct sk_buff *skb,
158
		    const struct xt_action_param *par,
159
		    enum ipset_adt adt, struct ip_set_adt_opt *opt);
160
161
162
163
164
165

	/* Userspace: test/add/del entries
	 *		returns negative error code,
	 *			zero for no match/success to add/delete
	 *			positive for matching element */
	int (*uadt)(struct ip_set *set, struct nlattr *tb[],
166
		    enum ipset_adt adt, u32 *lineno, u32 flags, bool retried);
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183

	/* Low level add/del/test functions */
	ipset_adtfn adt[IPSET_ADT_MAX];

	/* When adding entries and set is full, try to resize the set */
	int (*resize)(struct ip_set *set, bool retried);
	/* Destroy the set */
	void (*destroy)(struct ip_set *set);
	/* Flush the elements */
	void (*flush)(struct ip_set *set);
	/* Expire entries before listing */
	void (*expire)(struct ip_set *set);
	/* List set header data */
	int (*head)(struct ip_set *set, struct sk_buff *skb);
	/* List elements */
	int (*list)(const struct ip_set *set, struct sk_buff *skb,
		    struct netlink_callback *cb);
184
185
186
	/* Keep listing private when resizing runs parallel */
	void (*uref)(struct ip_set *set, struct netlink_callback *cb,
		     bool start);
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202

	/* Return true if "b" set is the same as "a"
	 * according to the create set parameters */
	bool (*same_set)(const struct ip_set *a, const struct ip_set *b);
};

/* The core set type structure */
struct ip_set_type {
	struct list_head list;

	/* Typename */
	char name[IPSET_MAXNAMELEN];
	/* Protocol version */
	u8 protocol;
	/* Set type dimension */
	u8 dimension;
203
204
205
206
	/*
	 * Supported family: may be NFPROTO_UNSPEC for both
	 * NFPROTO_IPV4/NFPROTO_IPV6.
	 */
207
	u8 family;
208
209
	/* Type revisions */
	u8 revision_min, revision_max;
210
211
	/* Set features to control swapping */
	u16 features;
212
213

	/* Create set */
214
215
	int (*create)(struct net *net, struct ip_set *set,
		      struct nlattr *tb[], u32 flags);
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233

	/* Attribute policies */
	const struct nla_policy create_policy[IPSET_ATTR_CREATE_MAX + 1];
	const struct nla_policy adt_policy[IPSET_ATTR_ADT_MAX + 1];

	/* Set this to THIS_MODULE if you are a module, otherwise NULL */
	struct module *me;
};

/* register and unregister set type */
extern int ip_set_type_register(struct ip_set_type *set_type);
extern void ip_set_type_unregister(struct ip_set_type *set_type);

/* A generic IP set */
struct ip_set {
	/* The name of the set */
	char name[IPSET_MAXNAMELEN];
	/* Lock protecting the set data */
234
	spinlock_t lock;
235
	/* References to the set */
236
	u32 ref;
237
238
239
240
	/* References to the set for netlink events like dump,
	 * ref can be swapped out by ip_set_swap
	 */
	u32 ref_netlink;
241
242
243
244
245
246
	/* The core set type */
	struct ip_set_type *type;
	/* The type variant doing the real job */
	const struct ip_set_type_variant *variant;
	/* The actual INET family of the set */
	u8 family;
247
248
	/* The type revision */
	u8 revision;
249
250
	/* Extensions */
	u8 extensions;
251
252
	/* Create flags */
	u8 flags;
253
254
255
256
257
258
	/* Default timeout value, if enabled */
	u32 timeout;
	/* Element data size */
	size_t dsize;
	/* Offsets to extensions in elements */
	size_t offset[IPSET_EXT_ID_MAX];
259
260
261
262
	/* The type specific data */
	void *data;
};

263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
static inline void
ip_set_ext_destroy(struct ip_set *set, void *data)
{
	/* Check that the extension is enabled for the set and
	 * call it's destroy function for its extension part in data.
	 */
	if (SET_WITH_COMMENT(set))
		ip_set_extensions[IPSET_EXT_ID_COMMENT].destroy(
			ext_comment(data, set));
}

static inline int
ip_set_put_flags(struct sk_buff *skb, struct ip_set *set)
{
	u32 cadt_flags = 0;

	if (SET_WITH_TIMEOUT(set))
		if (unlikely(nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
					   htonl(set->timeout))))
			return -EMSGSIZE;
	if (SET_WITH_COUNTER(set))
		cadt_flags |= IPSET_FLAG_WITH_COUNTERS;
	if (SET_WITH_COMMENT(set))
		cadt_flags |= IPSET_FLAG_WITH_COMMENT;
287
288
	if (SET_WITH_SKBINFO(set))
		cadt_flags |= IPSET_FLAG_WITH_SKBINFO;
289
290
	if (SET_WITH_FORCEADD(set))
		cadt_flags |= IPSET_FLAG_WITH_FORCEADD;
291
292
293
294
295
296

	if (!cadt_flags)
		return 0;
	return nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(cadt_flags));
}

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
static inline void
ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter)
{
	atomic64_add((long long)bytes, &(counter)->bytes);
}

static inline void
ip_set_add_packets(u64 packets, struct ip_set_counter *counter)
{
	atomic64_add((long long)packets, &(counter)->packets);
}

static inline u64
ip_set_get_bytes(const struct ip_set_counter *counter)
{
	return (u64)atomic64_read(&(counter)->bytes);
}

static inline u64
ip_set_get_packets(const struct ip_set_counter *counter)
{
	return (u64)atomic64_read(&(counter)->packets);
}

static inline void
ip_set_update_counter(struct ip_set_counter *counter,
		      const struct ip_set_ext *ext,
		      struct ip_set_ext *mext, u32 flags)
{
326
327
	if (ext->packets != ULLONG_MAX &&
	    !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) {
328
329
330
		ip_set_add_bytes(ext->bytes, counter);
		ip_set_add_packets(ext->packets, counter);
	}
331
332
333
334
	if (flags & IPSET_FLAG_MATCH_COUNTERS) {
		mext->packets = ip_set_get_packets(counter);
		mext->bytes = ip_set_get_bytes(counter);
	}
335
336
}

337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
static inline bool
ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter)
{
	return nla_put_net64(skb, IPSET_ATTR_BYTES,
			     cpu_to_be64(ip_set_get_bytes(counter)),
			     IPSET_ATTR_PAD) ||
	       nla_put_net64(skb, IPSET_ATTR_PACKETS,
			     cpu_to_be64(ip_set_get_packets(counter)),
			     IPSET_ATTR_PAD);
}

static inline void
ip_set_init_counter(struct ip_set_counter *counter,
		    const struct ip_set_ext *ext)
{
	if (ext->bytes != ULLONG_MAX)
		atomic64_set(&(counter)->bytes, (long long)(ext->bytes));
	if (ext->packets != ULLONG_MAX)
		atomic64_set(&(counter)->packets, (long long)(ext->packets));
}

358
359
static inline void
ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo,
360
361
		   const struct ip_set_ext *ext,
		   struct ip_set_ext *mext, u32 flags)
362
{
363
364
365
366
	mext->skbmark = skbinfo->skbmark;
	mext->skbmarkmask = skbinfo->skbmarkmask;
	mext->skbprio = skbinfo->skbprio;
	mext->skbqueue = skbinfo->skbqueue;
367
}
368

369
static inline bool
370
ip_set_put_skbinfo(struct sk_buff *skb, const struct ip_set_skbinfo *skbinfo)
371
{
372
373
374
375
	/* Send nonzero parameters only */
	return ((skbinfo->skbmark || skbinfo->skbmarkmask) &&
		nla_put_net64(skb, IPSET_ATTR_SKBMARK,
			      cpu_to_be64((u64)skbinfo->skbmark << 32 |
376
377
					  skbinfo->skbmarkmask),
			      IPSET_ATTR_PAD)) ||
378
	       (skbinfo->skbprio &&
379
		nla_put_net32(skb, IPSET_ATTR_SKBPRIO,
380
381
			      cpu_to_be32(skbinfo->skbprio))) ||
	       (skbinfo->skbqueue &&
382
		nla_put_net16(skb, IPSET_ATTR_SKBQUEUE,
383
			     cpu_to_be16(skbinfo->skbqueue)));
384
385
386
387
388
389
390
391
392
393
394
395
}

static inline void
ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo,
		    const struct ip_set_ext *ext)
{
	skbinfo->skbmark = ext->skbmark;
	skbinfo->skbmarkmask = ext->skbmarkmask;
	skbinfo->skbprio = ext->skbprio;
	skbinfo->skbqueue = ext->skbqueue;
}

396
397
/* Netlink CB args */
enum {
398
399
400
401
402
	IPSET_CB_NET = 0,	/* net namespace */
	IPSET_CB_DUMP,		/* dump single set/all sets */
	IPSET_CB_INDEX,		/* set index */
	IPSET_CB_PRIVATE,	/* set private data */
	IPSET_CB_ARG0,		/* type specific */
403
404
405
	IPSET_CB_ARG1,
};

406
/* register and unregister set references */
407
408
409
410
411
412
extern ip_set_id_t ip_set_get_byname(struct net *net,
				     const char *name, struct ip_set **set);
extern void ip_set_put_byindex(struct net *net, ip_set_id_t index);
extern const char *ip_set_name_byindex(struct net *net, ip_set_id_t index);
extern ip_set_id_t ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index);
extern void ip_set_nfnl_put(struct net *net, ip_set_id_t index);
413
414

/* API for iptables set match, and SET target */
415

416
extern int ip_set_add(ip_set_id_t id, const struct sk_buff *skb,
417
		      const struct xt_action_param *par,
418
		      struct ip_set_adt_opt *opt);
419
extern int ip_set_del(ip_set_id_t id, const struct sk_buff *skb,
420
		      const struct xt_action_param *par,
421
		      struct ip_set_adt_opt *opt);
422
extern int ip_set_test(ip_set_id_t id, const struct sk_buff *skb,
423
		       const struct xt_action_param *par,
424
		       struct ip_set_adt_opt *opt);
425
426

/* Utility functions */
427
extern void *ip_set_alloc(size_t size);
428
429
430
extern void ip_set_free(void *members);
extern int ip_set_get_ipaddr4(struct nlattr *nla,  __be32 *ipaddr);
extern int ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr);
431
extern size_t ip_set_elem_len(struct ip_set *set, struct nlattr *tb[],
432
			      size_t len, size_t align);
433
434
extern int ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[],
				 struct ip_set_ext *ext);
435
436
437
438
439
440

static inline int
ip_set_get_hostipaddr4(struct nlattr *nla, u32 *ipaddr)
{
	__be32 ip;
	int ret = ip_set_get_ipaddr4(nla, &ip);
441

442
443
444
445
446
447
448
449
450
451
452
453
454
	if (ret)
		return ret;
	*ipaddr = ntohl(ip);
	return 0;
}

/* Ignore IPSET_ERR_EXIST errors if asked to do so? */
static inline bool
ip_set_eexist(int ret, u32 flags)
{
	return ret == -IPSET_ERR_EXIST && (flags & IPSET_FLAG_EXIST);
}

455
456
/* Match elements marked with nomatch */
static inline bool
457
ip_set_enomatch(int ret, u32 flags, enum ipset_adt adt, struct ip_set *set)
458
459
{
	return adt == IPSET_TEST &&
460
461
462
	       (set->type->features & IPSET_TYPE_NOMATCH) &&
	       ((flags >> 16) & IPSET_FLAG_NOMATCH) &&
	       (ret > 0 || ret == -ENOTEMPTY);
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
/* Check the NLA_F_NET_BYTEORDER flag */
static inline bool
ip_set_attr_netorder(struct nlattr *tb[], int type)
{
	return tb[type] && (tb[type]->nla_type & NLA_F_NET_BYTEORDER);
}

static inline bool
ip_set_optattr_netorder(struct nlattr *tb[], int type)
{
	return !tb[type] || (tb[type]->nla_type & NLA_F_NET_BYTEORDER);
}

/* Useful converters */
static inline u32
ip_set_get_h32(const struct nlattr *attr)
{
	return ntohl(nla_get_be32(attr));
}

static inline u16
ip_set_get_h16(const struct nlattr *attr)
{
	return ntohs(nla_get_be16(attr));
}

#define ipset_nest_start(skb, attr) nla_nest_start(skb, attr | NLA_F_NESTED)
#define ipset_nest_end(skb, start)  nla_nest_end(skb, start)

494
495
496
497
498
499
500
static inline int nla_put_ipaddr4(struct sk_buff *skb, int type, __be32 ipaddr)
{
	struct nlattr *__nested = ipset_nest_start(skb, type);
	int ret;

	if (!__nested)
		return -EMSGSIZE;
501
	ret = nla_put_in_addr(skb, IPSET_ATTR_IPADDR_IPV4, ipaddr);
502
503
504
505
506
	if (!ret)
		ipset_nest_end(skb, __nested);
	return ret;
}

507
508
static inline int nla_put_ipaddr6(struct sk_buff *skb, int type,
				  const struct in6_addr *ipaddrptr)
509
510
511
512
513
514
{
	struct nlattr *__nested = ipset_nest_start(skb, type);
	int ret;

	if (!__nested)
		return -EMSGSIZE;
515
	ret = nla_put_in6_addr(skb, IPSET_ATTR_IPADDR_IPV6, ipaddrptr);
516
517
518
519
	if (!ret)
		ipset_nest_end(skb, __nested);
	return ret;
}
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

/* Get address from skbuff */
static inline __be32
ip4addr(const struct sk_buff *skb, bool src)
{
	return src ? ip_hdr(skb)->saddr : ip_hdr(skb)->daddr;
}

static inline void
ip4addrptr(const struct sk_buff *skb, bool src, __be32 *addr)
{
	*addr = src ? ip_hdr(skb)->saddr : ip_hdr(skb)->daddr;
}

static inline void
ip6addrptr(const struct sk_buff *skb, bool src, struct in6_addr *addr)
{
	memcpy(addr, src ? &ipv6_hdr(skb)->saddr : &ipv6_hdr(skb)->daddr,
	       sizeof(*addr));
}

/* Calculate the bytes required to store the inclusive range of a-b */
static inline int
bitmap_bytes(u32 a, u32 b)
{
	return 4 * ((((b - a + 8) / 8) + 3) / 4);
}

548
#include <linux/netfilter/ipset/ip_set_timeout.h>
549
#include <linux/netfilter/ipset/ip_set_comment.h>
550

551
int
552
ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set,
553
		      const void *e, bool active);
554

555
#define IP_SET_INIT_KEXT(skb, opt, set)			\
556
	{ .bytes = (skb)->len, .packets = 1,		\
557
	  .timeout = ip_set_adt_opt_timeout(opt, set) }
558

559
#define IP_SET_INIT_UEXT(set)				\
560
	{ .bytes = ULLONG_MAX, .packets = ULLONG_MAX,	\
561
	  .timeout = (set)->timeout }
562

563
564
565
#define IPSET_CONCAT(a, b)		a##b
#define IPSET_TOKEN(a, b)		IPSET_CONCAT(a, b)

566
#endif /*_IP_SET_H */