summaryrefslogtreecommitdiffstats
path: root/sys/netinet/ip_fw.h
blob: 97711899d37bd7a3d760ff9e1cc9c70414c41f08 (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
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
/*
 * Copyright (c) 2002 Luigi Rizzo, Universita` di Pisa
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 * $FreeBSD$
 */

#ifndef _IPFW2_H
#define _IPFW2_H
#define IPFW2  1

/*
 * The kernel representation of ipfw rules is made of a list of
 * 'instructions' (for all practical purposes equivalent to BPF
 * instructions), which specify which fields of the packet
 * (or its metadata) should be analysed.
 *
 * Each instruction is stored in a structure which begins with
 * "ipfw_insn", and can contain extra fields depending on the
 * instruction type (listed below).
 * Note that the code is written so that individual instructions
 * have a size which is a multiple of 32 bits. This means that, if
 * such structures contain pointers or other 64-bit entities,
 * (there is just one instance now) they may end up unaligned on
 * 64-bit architectures, so the must be handled with care.
 *
 * "enum ipfw_opcodes" are the opcodes supported. We can have up
 * to 256 different opcodes. When adding new opcodes, they should
 * be appended to the end of the opcode list before O_LAST_OPCODE,
 * this will prevent the ABI from being broken, otherwise users
 * will have to recompile ipfw(8) when they update the kernel.
 */

enum ipfw_opcodes {		/* arguments (4 byte each)	*/
	O_NOP,

	O_IP_SRC,		/* u32 = IP			*/
	O_IP_SRC_MASK,		/* ip = IP/mask			*/
	O_IP_SRC_ME,		/* none				*/
	O_IP_SRC_SET,		/* u32=base, arg1=len, bitmap	*/

	O_IP_DST,		/* u32 = IP			*/
	O_IP_DST_MASK,		/* ip = IP/mask			*/
	O_IP_DST_ME,		/* none				*/
	O_IP_DST_SET,		/* u32=base, arg1=len, bitmap	*/

	O_IP_SRCPORT,		/* (n)port list:mask 4 byte ea	*/
	O_IP_DSTPORT,		/* (n)port list:mask 4 byte ea	*/
	O_PROTO,		/* arg1=protocol		*/

	O_MACADDR2,		/* 2 mac addr:mask		*/
	O_MAC_TYPE,		/* same as srcport		*/

	O_LAYER2,		/* none				*/
	O_IN,			/* none				*/
	O_FRAG,			/* none				*/

	O_RECV,			/* none				*/
	O_XMIT,			/* none				*/
	O_VIA,			/* none				*/

	O_IPOPT,		/* arg1 = 2*u8 bitmap		*/
	O_IPLEN,		/* arg1 = len			*/
	O_IPID,			/* arg1 = id			*/

	O_IPTOS,		/* arg1 = id			*/
	O_IPPRECEDENCE,		/* arg1 = precedence << 5	*/
	O_IPTTL,		/* arg1 = TTL			*/

	O_IPVER,		/* arg1 = version		*/
	O_UID,			/* u32 = id			*/
	O_GID,			/* u32 = id			*/
	O_ESTAB,		/* none (tcp established)	*/
	O_TCPFLAGS,		/* arg1 = 2*u8 bitmap		*/
	O_TCPWIN,		/* arg1 = desired win		*/
	O_TCPSEQ,		/* u32 = desired seq.		*/
	O_TCPACK,		/* u32 = desired seq.		*/
	O_ICMPTYPE,		/* u32 = icmp bitmap		*/
	O_TCPOPTS,		/* arg1 = 2*u8 bitmap		*/

	O_VERREVPATH,		/* none				*/
	O_VERSRCREACH,		/* none				*/

	O_PROBE_STATE,		/* none				*/
	O_KEEP_STATE,		/* none				*/
	O_LIMIT,		/* ipfw_insn_limit		*/
	O_LIMIT_PARENT,		/* dyn_type, not an opcode.	*/

	/*
	 * These are really 'actions'.
	 */

	O_LOG,			/* ipfw_insn_log		*/
	O_PROB,			/* u32 = match probability	*/

	O_CHECK_STATE,		/* none				*/
	O_ACCEPT,		/* none				*/
	O_DENY,			/* none 			*/
	O_REJECT,		/* arg1=icmp arg (same as deny)	*/
	O_COUNT,		/* none				*/
	O_SKIPTO,		/* arg1=next rule number	*/
	O_PIPE,			/* arg1=pipe number		*/
	O_QUEUE,		/* arg1=queue number		*/
	O_DIVERT,		/* arg1=port number		*/
	O_TEE,			/* arg1=port number		*/
	O_FORWARD_IP,		/* fwd sockaddr			*/
	O_FORWARD_MAC,		/* fwd mac			*/

	/*
	 * More opcodes.
	 */
	O_IPSEC,		/* has ipsec history 		*/
	O_IP_SRC_LOOKUP,	/* arg1=table number, u32=value	*/
	O_IP_DST_LOOKUP,	/* arg1=table number, u32=value	*/
	O_ANTISPOOF,		/* none				*/
	O_JAIL,			/* u32 = id			*/
	O_ALTQ,			/* u32 = altq classif. qid	*/
	O_DIVERTED,		/* arg1=bitmap (1:loop, 2:out)	*/
	O_TCPDATALEN,		/* arg1 = tcp data len		*/

	O_LAST_OPCODE		/* not an opcode!		*/
};

/*
 * Template for instructions.
 *
 * ipfw_insn is used for all instructions which require no operands,
 * a single 16-bit value (arg1), or a couple of 8-bit values.
 *
 * For other instructions which require different/larger arguments
 * we have derived structures, ipfw_insn_*.
 *
 * The size of the instruction (in 32-bit words) is in the low
 * 6 bits of "len". The 2 remaining bits are used to implement
 * NOT and OR on individual instructions. Given a type, you can
 * compute the length to be put in "len" using F_INSN_SIZE(t)
 *
 * F_NOT	negates the match result of the instruction.
 *
 * F_OR		is used to build or blocks. By default, instructions
 *		are evaluated as part of a logical AND. An "or" block
 *		{ X or Y or Z } contains F_OR set in all but the last
 *		instruction of the block. A match will cause the code
 *		to skip past the last instruction of the block.
 *
 * NOTA BENE: in a couple of places we assume that
 *	sizeof(ipfw_insn) == sizeof(u_int32_t)
 * this needs to be fixed.
 *
 */
typedef struct	_ipfw_insn {	/* template for instructions */
	enum ipfw_opcodes	opcode:8;
	u_int8_t	len;	/* numer of 32-byte words */
#define	F_NOT		0x80
#define	F_OR		0x40
#define	F_LEN_MASK	0x3f
#define	F_LEN(cmd)	((cmd)->len & F_LEN_MASK)

	u_int16_t	arg1;
} ipfw_insn;

/*
 * The F_INSN_SIZE(type) computes the size, in 4-byte words, of
 * a given type.
 */
#define	F_INSN_SIZE(t)	((sizeof (t))/sizeof(u_int32_t))

/*
 * This is used to store an array of 16-bit entries (ports etc.)
 */
typedef struct	_ipfw_insn_u16 {
	ipfw_insn o;
	u_int16_t ports[2];	/* there may be more */
} ipfw_insn_u16;

/*
 * This is used to store an array of 32-bit entries
 * (uid, single IPv4 addresses etc.)
 */
typedef struct	_ipfw_insn_u32 {
	ipfw_insn o;
	u_int32_t d[1];	/* one or more */
} ipfw_insn_u32;

/*
 * This is used to store IP addr-mask pairs.
 */
typedef struct	_ipfw_insn_ip {
	ipfw_insn o;
	struct in_addr	addr;
	struct in_addr	mask;
} ipfw_insn_ip;

/*
 * This is used to forward to a given address (ip).
 */
typedef struct  _ipfw_insn_sa {
	ipfw_insn o;
	struct sockaddr_in sa;
} ipfw_insn_sa;

/*
 * This is used for MAC addr-mask pairs.
 */
typedef struct	_ipfw_insn_mac {
	ipfw_insn o;
	u_char addr[12];	/* dst[6] + src[6] */
	u_char mask[12];	/* dst[6] + src[6] */
} ipfw_insn_mac;

/*
 * This is used for interface match rules (recv xx, xmit xx).
 */
typedef struct	_ipfw_insn_if {
	ipfw_insn o;
	union {
		struct in_addr ip;
		int glob;
	} p;
	char name[IFNAMSIZ];
} ipfw_insn_if;

/*
 * This is used for pipe and queue actions, which need to store
 * a single pointer (which can have different size on different
 * architectures.
 * Note that, because of previous instructions, pipe_ptr might
 * be unaligned in the overall structure, so it needs to be
 * manipulated with care.
 */
typedef struct	_ipfw_insn_pipe {
	ipfw_insn	o;
	void		*pipe_ptr;	/* XXX */
} ipfw_insn_pipe;

/*
 * This is used for storing an altq queue id number.
 */
typedef struct _ipfw_insn_altq {
	ipfw_insn	o;
	u_int32_t	qid;
} ipfw_insn_altq;

/*
 * This is used for limit rules.
 */
typedef struct	_ipfw_insn_limit {
	ipfw_insn o;
	u_int8_t _pad;
	u_int8_t limit_mask;	/* combination of DYN_* below	*/
#define	DYN_SRC_ADDR	0x1
#define	DYN_SRC_PORT	0x2
#define	DYN_DST_ADDR	0x4
#define	DYN_DST_PORT	0x8

	u_int16_t conn_limit;
} ipfw_insn_limit;

/*
 * This is used for log instructions.
 */
typedef struct  _ipfw_insn_log {
        ipfw_insn o;
	u_int32_t max_log;	/* how many do we log -- 0 = all */
	u_int32_t log_left;	/* how many left to log 	*/
} ipfw_insn_log;

/*
 * Here we have the structure representing an ipfw rule.
 *
 * It starts with a general area (with link fields and counters)
 * followed by an array of one or more instructions, which the code
 * accesses as an array of 32-bit values.
 *
 * Given a rule pointer  r:
 *
 *  r->cmd		is the start of the first instruction.
 *  ACTION_PTR(r)	is the start of the first action (things to do
 *			once a rule matched).
 *
 * When assembling instruction, remember the following:
 *
 *  + if a rule has a "keep-state" (or "limit") option, then the
 *	first instruction (at r->cmd) MUST BE an O_PROBE_STATE
 *  + if a rule has a "log" option, then the first action
 *	(at ACTION_PTR(r)) MUST be O_LOG
 *  + if a rule has an "altq" option, it comes after "log"
 *
 * NOTE: we use a simple linked list of rules because we never need
 * 	to delete a rule without scanning the list. We do not use
 *	queue(3) macros for portability and readability.
 */

struct ip_fw {
	struct ip_fw	*next;		/* linked list of rules		*/
	struct ip_fw	*next_rule;	/* ptr to next [skipto] rule	*/
	/* 'next_rule' is used to pass up 'set_disable' status		*/

	u_int16_t	act_ofs;	/* offset of action in 32-bit units */
	u_int16_t	cmd_len;	/* # of 32-bit words in cmd	*/
	u_int16_t	rulenum;	/* rule number			*/
	u_int8_t	set;		/* rule set (0..31)		*/
#define	RESVD_SET	31	/* set for default and persistent rules */
	u_int8_t	_pad;		/* padding			*/

	/* These fields are present in all rules.			*/
	u_int64_t	pcnt;		/* Packet counter		*/
	u_int64_t	bcnt;		/* Byte counter			*/
	u_int32_t	timestamp;	/* tv_sec of last match		*/

	ipfw_insn	cmd[1];		/* storage for commands		*/
};

#define ACTION_PTR(rule)				\
	(ipfw_insn *)( (u_int32_t *)((rule)->cmd) + ((rule)->act_ofs) )

#define RULESIZE(rule)  (sizeof(struct ip_fw) + \
	((struct ip_fw *)(rule))->cmd_len * 4 - 4)

/*
 * This structure is used as a flow mask and a flow id for various
 * parts of the code.
 */
struct ipfw_flow_id {
	u_int32_t	dst_ip;
	u_int32_t	src_ip;
	u_int16_t	dst_port;
	u_int16_t	src_port;
	u_int8_t	proto;
	u_int8_t	flags;	/* protocol-specific flags */
};

/*
 * Dynamic ipfw rule.
 */
typedef struct _ipfw_dyn_rule ipfw_dyn_rule;

struct _ipfw_dyn_rule {
	ipfw_dyn_rule	*next;		/* linked list of rules.	*/
	struct ip_fw *rule;		/* pointer to rule		*/
	/* 'rule' is used to pass up the rule number (from the parent)	*/

	ipfw_dyn_rule *parent;		/* pointer to parent rule	*/
	u_int64_t	pcnt;		/* packet match counter		*/
	u_int64_t	bcnt;		/* byte match counter		*/
	struct ipfw_flow_id id;		/* (masked) flow id		*/
	u_int32_t	expire;		/* expire time			*/
	u_int32_t	bucket;		/* which bucket in hash table	*/
	u_int32_t	state;		/* state of this rule (typically a
					 * combination of TCP flags)
					 */
	u_int32_t	ack_fwd;	/* most recent ACKs in forward	*/
	u_int32_t	ack_rev;	/* and reverse directions (used	*/
					/* to generate keepalives)	*/
	u_int16_t	dyn_type;	/* rule type			*/
	u_int16_t	count;		/* refcount			*/
};

/*
 * Definitions for IP option names.
 */
#define	IP_FW_IPOPT_LSRR	0x01
#define	IP_FW_IPOPT_SSRR	0x02
#define	IP_FW_IPOPT_RR		0x04
#define	IP_FW_IPOPT_TS		0x08

/*
 * Definitions for TCP option names.
 */
#define	IP_FW_TCPOPT_MSS	0x01
#define	IP_FW_TCPOPT_WINDOW	0x02
#define	IP_FW_TCPOPT_SACK	0x04
#define	IP_FW_TCPOPT_TS		0x08
#define	IP_FW_TCPOPT_CC		0x10

#define	ICMP_REJECT_RST		0x100	/* fake ICMP code (send a TCP RST) */

/*
 * These are used for lookup tables.
 */
typedef struct	_ipfw_table_entry {
	in_addr_t	addr;		/* network address		*/
	u_int32_t	value;		/* value			*/
	u_int16_t	tbl;		/* table number			*/
	u_int8_t	masklen;	/* mask length			*/
} ipfw_table_entry;

typedef struct	_ipfw_table {
	u_int32_t	size;		/* size of entries in bytes	*/
	u_int32_t	cnt;		/* # of entries			*/
	u_int16_t	tbl;		/* table number			*/
	ipfw_table_entry ent[0];	/* entries			*/
} ipfw_table;

/*
 * Main firewall chains definitions and global var's definitions.
 */
#ifdef _KERNEL

#define	IP_FW_PORT_DYNT_FLAG		0x00010000
#define	IP_FW_PORT_TEE_FLAG		0x00020000
#define	IP_FW_PORT_DENY_FLAG		0x00040000
#define	IP_FW_DIVERT_LOOPBACK_FLAG	0x00080000
#define	IP_FW_DIVERT_OUTPUT_FLAG	0x00100000

/*
 * Arguments for calling ipfw_chk() and dummynet_io(). We put them
 * all into a structure because this way it is easier and more
 * efficient to pass variables around and extend the interface.
 */
struct ip_fw_args {
	struct mbuf	*m;		/* the mbuf chain		*/
	struct ifnet	*oif;		/* output interface		*/
	struct sockaddr_in *next_hop;	/* forward address		*/
	struct ip_fw	*rule;		/* matching rule		*/
	struct ether_header *eh;	/* for bridged packets		*/

	int flags;			/* for dummynet			*/

	struct ipfw_flow_id f_id;	/* grabbed from IP header	*/
	u_int32_t	retval;
	struct inpcb	*inp;
};

/*
 * Function definitions.
 */

/* Firewall hooks */
struct sockopt;
struct dn_flow_set;

int ipfw_check_in(void *, struct mbuf **, struct ifnet *, int, struct inpcb *inp);
int ipfw_check_out(void *, struct mbuf **, struct ifnet *, int, struct inpcb *inp);

int ipfw_chk(struct ip_fw_args *);

int ipfw_init(void);
void ipfw_destroy(void);

void flush_pipe_ptrs(struct dn_flow_set *match); /* used by dummynet */

typedef int ip_fw_ctl_t(struct sockopt *);
extern ip_fw_ctl_t *ip_fw_ctl_ptr;
extern int fw_one_pass;
extern int fw_enable;

/* For kernel ipfw_ether and ipfw_bridge. */
typedef	int ip_fw_chk_t(struct ip_fw_args *args);
extern	ip_fw_chk_t	*ip_fw_chk_ptr;
#define	IPFW_LOADED	(ip_fw_chk_ptr != NULL)

#endif /* _KERNEL */
#endif /* _IPFW2_H */
OpenPOWER on IntegriCloud