summaryrefslogtreecommitdiffstats
path: root/sys/netinet/ip_mroute.h
blob: d4bb51748d5cccfa9c80f968051a10f02c5389c9 (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
/*
 * Copyright (c) 1989 Stephen Deering.
 * Copyright (c) 1992, 1993
 *	The Regents of the University of California.  All rights reserved.
 *
 * This code is derived from software contributed to Berkeley by
 * Stephen Deering of Stanford University.
 *
 * 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.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS 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 REGENTS 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.
 *
 *	@(#)ip_mroute.h	8.1 (Berkeley) 6/10/93
 * $FreeBSD$
 */

#ifndef _NETINET_IP_MROUTE_H_
#define _NETINET_IP_MROUTE_H_

/*
 * Definitions for IP multicast forwarding.
 *
 * Written by David Waitzman, BBN Labs, August 1988.
 * Modified by Steve Deering, Stanford, February 1989.
 * Modified by Ajit Thyagarajan, PARC, August 1993.
 * Modified by Ajit Thyagarajan, PARC, August 1994.
 * Modified by Ahmed Helmy, SGI, June 1996.
 * Modified by Pavlin Radoslavov, ICSI, October 2002.
 *
 * MROUTING Revision: 3.3.1.3
 * and PIM-SMv2 and PIM-DM support, advanced API support,
 * bandwidth metering and signaling.
 */


/*
 * Multicast Routing set/getsockopt commands.
 */
#define	MRT_INIT	100	/* initialize forwarder */
#define	MRT_DONE	101	/* shut down forwarder */
#define	MRT_ADD_VIF	102	/* create virtual interface */
#define	MRT_DEL_VIF	103	/* delete virtual interface */
#define MRT_ADD_MFC	104	/* insert forwarding cache entry */
#define MRT_DEL_MFC	105	/* delete forwarding cache entry */
#define MRT_VERSION	106	/* get kernel version number */
#define MRT_ASSERT      107     /* enable assert processing */
#define MRT_PIM		MRT_ASSERT /* enable PIM processing */
#define MRT_API_SUPPORT	109	/* supported MRT API */
#define MRT_API_CONFIG	110	/* config MRT API */
#define MRT_ADD_BW_UPCALL 111	/* create bandwidth monitor */
#define MRT_DEL_BW_UPCALL 112	/* delete bandwidth monitor */


#define GET_TIME(t)	microtime(&t)

/*
 * Types and macros for handling bitmaps with one bit per virtual interface.
 */
#define	MAXVIFS 32
typedef u_long vifbitmap_t;
typedef u_short vifi_t;		/* type of a vif index */
#define ALL_VIFS (vifi_t)-1

#define	VIFM_SET(n, m)		((m) |= (1 << (n)))
#define	VIFM_CLR(n, m)		((m) &= ~(1 << (n)))
#define	VIFM_ISSET(n, m)	((m) & (1 << (n)))
#define	VIFM_CLRALL(m)		((m) = 0x00000000)
#define	VIFM_COPY(mfrom, mto)	((mto) = (mfrom))
#define	VIFM_SAME(m1, m2)	((m1) == (m2))


/*
 * Argument structure for MRT_ADD_VIF.
 * (MRT_DEL_VIF takes a single vifi_t argument.)
 */
struct vifctl {
	vifi_t	vifc_vifi;		/* the index of the vif to be added */
	u_char	vifc_flags;		/* VIFF_ flags defined below */
	u_char	vifc_threshold;		/* min ttl required to forward on vif */
	u_int	vifc_rate_limit;	/* max rate */
	struct	in_addr vifc_lcl_addr;	/* local interface address */
	struct	in_addr vifc_rmt_addr;	/* remote address (tunnels only) */
};

#define	VIFF_TUNNEL	0x1		/* vif represents a tunnel end-point */
#define VIFF_SRCRT	0x2		/* tunnel uses IP source routing */
#define VIFF_REGISTER	0x4		/* used for PIM Register encap/decap */

/*
 * Argument structure for MRT_ADD_MFC and MRT_DEL_MFC
 * XXX if you change this, make sure to change struct mfcctl2 as well.
 */
struct mfcctl {
    struct in_addr  mfcc_origin;		/* ip origin of mcasts       */
    struct in_addr  mfcc_mcastgrp;		/* multicast group associated*/
    vifi_t	    mfcc_parent;		/* incoming vif              */
    u_char	    mfcc_ttls[MAXVIFS];		/* forwarding ttls on vifs   */
};

/*
 * The new argument structure for MRT_ADD_MFC and MRT_DEL_MFC overlays
 * and extends the old struct mfcctl.
 */
struct mfcctl2 {
	/* the mfcctl fields */
	struct in_addr	mfcc_origin;		/* ip origin of mcasts	     */
	struct in_addr	mfcc_mcastgrp;		/* multicast group associated*/
	vifi_t		mfcc_parent;		/* incoming vif		     */
	u_char		mfcc_ttls[MAXVIFS];	/* forwarding ttls on vifs   */

	/* extension fields */
	uint8_t		mfcc_flags[MAXVIFS];	/* the MRT_MFC_FLAGS_* flags */
	struct in_addr	mfcc_rp;		/* the RP address            */
};
/*
 * The advanced-API flags.
 *
 * The MRT_MFC_FLAGS_XXX API flags are also used as flags
 * for the mfcc_flags field.
 */
#define	MRT_MFC_FLAGS_DISABLE_WRONGVIF	(1 << 0) /* disable WRONGVIF signals */
#define	MRT_MFC_FLAGS_BORDER_VIF	(1 << 1) /* border vif		     */
#define MRT_MFC_RP			(1 << 8) /* enable RP address	     */
#define MRT_MFC_BW_UPCALL		(1 << 9) /* enable bw upcalls	     */
#define MRT_MFC_FLAGS_ALL		(MRT_MFC_FLAGS_DISABLE_WRONGVIF |    \
					 MRT_MFC_FLAGS_BORDER_VIF)
#define MRT_API_FLAGS_ALL		(MRT_MFC_FLAGS_ALL |		     \
					 MRT_MFC_RP |			     \
					 MRT_MFC_BW_UPCALL)

/*
 * Structure for installing or delivering an upcall if the
 * measured bandwidth is above or below a threshold.
 *
 * User programs (e.g. daemons) may have a need to know when the
 * bandwidth used by some data flow is above or below some threshold.
 * This interface allows the userland to specify the threshold (in
 * bytes and/or packets) and the measurement interval. Flows are
 * all packet with the same source and destination IP address.
 * At the moment the code is only used for multicast destinations
 * but there is nothing that prevents its use for unicast.
 *
 * The measurement interval cannot be shorter than some Tmin (currently, 3s).
 * The threshold is set in packets and/or bytes per_interval.
 *
 * Measurement works as follows:
 *
 * For >= measurements:
 * The first packet marks the start of a measurement interval.
 * During an interval we count packets and bytes, and when we
 * pass the threshold we deliver an upcall and we are done.
 * The first packet after the end of the interval resets the
 * count and restarts the measurement.
 *
 * For <= measurement:
 * We start a timer to fire at the end of the interval, and
 * then for each incoming packet we count packets and bytes.
 * When the timer fires, we compare the value with the threshold,
 * schedule an upcall if we are below, and restart the measurement
 * (reschedule timer and zero counters).
 */

struct bw_data {
	struct timeval	b_time;
	uint64_t	b_packets;
	uint64_t	b_bytes;
};

struct bw_upcall {
	struct in_addr	bu_src;			/* source address            */
	struct in_addr	bu_dst;			/* destination address       */
	uint32_t	bu_flags;		/* misc flags (see below)    */
#define BW_UPCALL_UNIT_PACKETS   (1 << 0)	/* threshold (in packets)    */
#define BW_UPCALL_UNIT_BYTES     (1 << 1)	/* threshold (in bytes)      */
#define BW_UPCALL_GEQ            (1 << 2)	/* upcall if bw >= threshold */
#define BW_UPCALL_LEQ            (1 << 3)	/* upcall if bw <= threshold */
#define BW_UPCALL_DELETE_ALL     (1 << 4)	/* delete all upcalls for s,d*/
	struct bw_data	bu_threshold;		/* the bw threshold	     */
	struct bw_data	bu_measured;		/* the measured bw	     */
};

/* max. number of upcalls to deliver together */
#define BW_UPCALLS_MAX				128
/* min. threshold time interval for bandwidth measurement */
#define BW_UPCALL_THRESHOLD_INTERVAL_MIN_SEC	3
#define BW_UPCALL_THRESHOLD_INTERVAL_MIN_USEC	0

/*
 * The kernel's multicast routing statistics.
 */
struct mrtstat {
    u_long	mrts_mfc_lookups;	/* # forw. cache hash table hits   */
    u_long	mrts_mfc_misses;	/* # forw. cache hash table misses */
    u_long	mrts_upcalls;		/* # calls to mrouted              */
    u_long	mrts_no_route;		/* no route for packet's origin    */
    u_long	mrts_bad_tunnel;	/* malformed tunnel options        */
    u_long	mrts_cant_tunnel;	/* no room for tunnel options      */
    u_long	mrts_wrong_if;		/* arrived on wrong interface	   */
    u_long	mrts_upq_ovflw;		/* upcall Q overflow		   */
    u_long	mrts_cache_cleanups;	/* # entries with no upcalls	   */
    u_long	mrts_drop_sel;		/* pkts dropped selectively        */
    u_long	mrts_q_overflow;	/* pkts dropped - Q overflow       */
    u_long	mrts_pkt2large;		/* pkts dropped - size > BKT SIZE  */
    u_long	mrts_upq_sockfull;	/* upcalls dropped - socket full */
};

/*
 * Argument structure used by mrouted to get src-grp pkt counts
 */
struct sioc_sg_req {
    struct in_addr src;
    struct in_addr grp;
    u_long pktcnt;
    u_long bytecnt;
    u_long wrong_if;
};

/*
 * Argument structure used by mrouted to get vif pkt counts
 */
struct sioc_vif_req {
    vifi_t vifi;		/* vif number				*/
    u_long icount;		/* Input packet count on vif		*/
    u_long ocount;		/* Output packet count on vif		*/
    u_long ibytes;		/* Input byte count on vif		*/
    u_long obytes;		/* Output byte count on vif		*/
};


/*
 * The kernel's virtual-interface structure.
 */
struct vif {
    u_char		v_flags;	/* VIFF_ flags defined above         */
    u_char		v_threshold;	/* min ttl required to forward on vif*/
    u_int		v_rate_limit;	/* max rate			     */
    struct tbf	       *v_tbf;		/* token bucket structure at intf.   */
    struct in_addr	v_lcl_addr;	/* local interface address           */
    struct in_addr	v_rmt_addr;	/* remote address (tunnels only)     */
    struct ifnet       *v_ifp;		/* pointer to interface              */
    u_long		v_pkt_in;	/* # pkts in on interface            */
    u_long		v_pkt_out;	/* # pkts out on interface           */
    u_long		v_bytes_in;	/* # bytes in on interface	     */
    u_long		v_bytes_out;	/* # bytes out on interface	     */
    struct route	v_route;	/* cached route if this is a tunnel */
    u_int		v_rsvp_on;	/* RSVP listening on this vif */
    struct socket      *v_rsvpd;	/* RSVP daemon socket */
};

/*
 * The kernel's multicast forwarding cache entry structure
 * (A field for the type of service (mfc_tos) is to be added
 * at a future point)
 */
struct mfc {
	struct in_addr	mfc_origin;		/* IP origin of mcasts	     */
	struct in_addr  mfc_mcastgrp;		/* multicast group associated*/
	vifi_t		mfc_parent;		/* incoming vif              */
	u_char		mfc_ttls[MAXVIFS];	/* forwarding ttls on vifs   */
	u_long		mfc_pkt_cnt;		/* pkt count for src-grp     */
	u_long		mfc_byte_cnt;		/* byte count for src-grp    */
	u_long		mfc_wrong_if;		/* wrong if for src-grp	     */
	int		mfc_expire;		/* time to clean entry up    */
	struct timeval	mfc_last_assert;	/* last time I sent an assert*/
	struct rtdetq	*mfc_stall;		/* q of packets awaiting mfc */
	struct mfc	*mfc_next;		/* next mfc entry            */
	uint8_t		mfc_flags[MAXVIFS];	/* the MRT_MFC_FLAGS_* flags */
	struct in_addr	mfc_rp;			/* the RP address	     */
	struct bw_meter	*mfc_bw_meter;		/* list of bandwidth meters  */
};

/*
 * Struct used to communicate from kernel to multicast router
 * note the convenient similarity to an IP packet
 */
struct igmpmsg {
    u_long	    unused1;
    u_long	    unused2;
    u_char	    im_msgtype;			/* what type of message	    */
#define IGMPMSG_NOCACHE		1	/* no MFC in the kernel		    */
#define IGMPMSG_WRONGVIF	2	/* packet came from wrong interface */
#define	IGMPMSG_WHOLEPKT	3	/* PIM pkt for user level encap.    */
#define	IGMPMSG_BW_UPCALL	4	/* BW monitoring upcall		    */
    u_char	    im_mbz;			/* must be zero		    */
    u_char	    im_vif;			/* vif rec'd on		    */
    u_char	    unused3;
    struct in_addr  im_src, im_dst;
};

/*
 * Argument structure used for pkt info. while upcall is made
 */
struct rtdetq {
    struct mbuf		*m;		/* A copy of the packet		    */
    struct ifnet	*ifp;		/* Interface pkt came in on	    */
    vifi_t		xmt_vif;	/* Saved copy of imo_multicast_vif  */
    struct rtdetq	*next;		/* Next in list of packets          */
};

#define MFCTBLSIZ	256
#if (MFCTBLSIZ & (MFCTBLSIZ - 1)) == 0	  /* from sys:route.h */
#define MFCHASHMOD(h)	((h) & (MFCTBLSIZ - 1))
#else
#define MFCHASHMOD(h)	((h) % MFCTBLSIZ)
#endif

#define MAX_UPQ	4		/* max. no of pkts in upcall Q */

/*
 * Token Bucket filter code
 */
#define MAX_BKT_SIZE    10000             /* 10K bytes size		*/
#define MAXQSIZE        10                /* max # of pkts in queue	*/

/*
 * the token bucket filter at each vif
 */
struct tbf
{
    struct timeval tbf_last_pkt_t; /* arr. time of last pkt	*/
    u_long tbf_n_tok;		/* no of tokens in bucket	*/
    u_long tbf_q_len;		/* length of queue at this vif	*/
    u_long tbf_max_q_len;	/* max. queue length		*/
    struct mbuf *tbf_q;		/* Packet queue			*/
    struct mbuf *tbf_t;		/* tail-insertion pointer	*/
};

/*
 * Structure for measuring the bandwidth and sending an upcall if the
 * measured bandwidth is above or below a threshold.
 */
struct bw_meter {
	struct bw_meter	*bm_mfc_next;		/* next bw meter (same mfc)  */
	struct bw_meter	*bm_time_next;		/* next bw meter (same time) */
	uint32_t	bm_time_hash;		/* the time hash value       */
	struct mfc	*bm_mfc;		/* the corresponding mfc     */
	uint32_t	bm_flags;		/* misc flags (see below)    */
#define BW_METER_UNIT_PACKETS	(1 << 0)	/* threshold (in packets)    */
#define BW_METER_UNIT_BYTES	(1 << 1)	/* threshold (in bytes)      */
#define BW_METER_GEQ		(1 << 2)	/* upcall if bw >= threshold */
#define BW_METER_LEQ		(1 << 3)	/* upcall if bw <= threshold */
#define BW_METER_USER_FLAGS	(BW_METER_UNIT_PACKETS |		\
				 BW_METER_UNIT_BYTES |			\
				 BW_METER_GEQ |				\
				 BW_METER_LEQ)

#define BW_METER_UPCALL_DELIVERED (1 << 24)	/* upcall was delivered      */

	struct bw_data	bm_threshold;		/* the upcall threshold	     */
	struct bw_data	bm_measured;		/* the measured bw	     */
	struct timeval	bm_start_time;		/* abs. time		     */
};

#ifdef _KERNEL

struct sockopt;

extern int	(*ip_mrouter_set)(struct socket *, struct sockopt *);
extern int	(*ip_mrouter_get)(struct socket *, struct sockopt *);
extern int	(*ip_mrouter_done)(void);
extern int	(*mrt_ioctl)(int, caddr_t);

#endif /* _KERNEL */

#endif /* _NETINET_IP_MROUTE_H_ */
OpenPOWER on IntegriCloud