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
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
|
#ifndef __LINUX_RTNETLINK_H
#define __LINUX_RTNETLINK_H
#ifdef __KERNEL__
#include <linux/config.h>
#endif
#include <linux/netlink.h>
#define RTNL_DEBUG 1
/****
* Routing/neighbour discovery messages.
****/
/* Types of messages */
#define RTM_BASE 0x10
#define RTM_NEWLINK (RTM_BASE+0)
#define RTM_DELLINK (RTM_BASE+1)
#define RTM_GETLINK (RTM_BASE+2)
#define RTM_NEWADDR (RTM_BASE+4)
#define RTM_DELADDR (RTM_BASE+5)
#define RTM_GETADDR (RTM_BASE+6)
#define RTM_NEWROUTE (RTM_BASE+8)
#define RTM_DELROUTE (RTM_BASE+9)
#define RTM_GETROUTE (RTM_BASE+10)
#define RTM_NEWNEIGH (RTM_BASE+12)
#define RTM_DELNEIGH (RTM_BASE+13)
#define RTM_GETNEIGH (RTM_BASE+14)
#define RTM_NEWRULE (RTM_BASE+16)
#define RTM_DELRULE (RTM_BASE+17)
#define RTM_GETRULE (RTM_BASE+18)
#define RTM_NEWQDISC (RTM_BASE+20)
#define RTM_DELQDISC (RTM_BASE+21)
#define RTM_GETQDISC (RTM_BASE+22)
#define RTM_NEWTCLASS (RTM_BASE+24)
#define RTM_DELTCLASS (RTM_BASE+25)
#define RTM_GETTCLASS (RTM_BASE+26)
#define RTM_NEWTFILTER (RTM_BASE+28)
#define RTM_DELTFILTER (RTM_BASE+29)
#define RTM_GETTFILTER (RTM_BASE+30)
#define RTM_MAX (RTM_BASE+31)
/*
Generic structure for encapsulation optional route information.
It is reminiscent of sockaddr, but with sa_family replaced
with attribute type.
*/
struct rtattr
{
unsigned short rta_len;
unsigned short rta_type;
};
/* Macros to handle rtattributes */
#define RTA_ALIGNTO 4
#define RTA_ALIGN(len) ( ((len)+RTA_ALIGNTO-1) & ~(RTA_ALIGNTO-1) )
#define RTA_OK(rta,len) ((len) > 0 && (rta)->rta_len >= sizeof(struct rtattr) && \
(rta)->rta_len <= (len))
#define RTA_NEXT(rta,attrlen) ((attrlen) -= RTA_ALIGN((rta)->rta_len), \
(struct rtattr*)(((char*)(rta)) + RTA_ALIGN((rta)->rta_len)))
#define RTA_LENGTH(len) (RTA_ALIGN(sizeof(struct rtattr)) + (len))
#define RTA_SPACE(len) RTA_ALIGN(RTA_LENGTH(len))
#define RTA_DATA(rta) ((void*)(((char*)(rta)) + RTA_LENGTH(0)))
#define RTA_PAYLOAD(rta) ((int)((rta)->rta_len) - RTA_LENGTH(0))
/******************************************************************************
* Definitions used in routing table administation.
****/
struct rtmsg
{
unsigned char rtm_family;
unsigned char rtm_dst_len;
unsigned char rtm_src_len;
unsigned char rtm_tos;
unsigned char rtm_table; /* Routing table id */
unsigned char rtm_protocol; /* Routing protocol; see below */
unsigned char rtm_scope; /* See below */
unsigned char rtm_type; /* See below */
unsigned rtm_flags;
};
/* rtm_type */
enum
{
RTN_UNSPEC,
RTN_UNICAST, /* Gateway or direct route */
RTN_LOCAL, /* Accept locally */
RTN_BROADCAST, /* Accept locally as broadcast,
send as broadcast */
RTN_ANYCAST, /* Accept locally as broadcast,
but send as unicast */
RTN_MULTICAST, /* Multicast route */
RTN_BLACKHOLE, /* Drop */
RTN_UNREACHABLE, /* Destination is unreachable */
RTN_PROHIBIT, /* Administratively prohibited */
RTN_THROW, /* Not in this table */
RTN_NAT, /* Translate this address */
RTN_XRESOLVE, /* Use external resolver */
};
#define RTN_MAX RTN_XRESOLVE
/* rtm_protocol */
#define RTPROT_UNSPEC 0
#define RTPROT_REDIRECT 1 /* Route installed by ICMP redirects;
not used by current IPv4 */
#define RTPROT_KERNEL 2 /* Route installed by kernel */
#define RTPROT_BOOT 3 /* Route installed during boot */
#define RTPROT_STATIC 4 /* Route installed by administrator */
/* Values of protocol >= RTPROT_STATIC are not interpreted by kernel;
they just passed from user and back as is.
It will be used by hypothetical multiple routing daemons.
Note that protocol values should be standardized in order to
avoid conflicts.
*/
#define RTPROT_GATED 8 /* Apparently, GateD */
#define RTPROT_RA 9 /* RDISC/ND router advertisments */
#define RTPROT_MRT 10 /* Merit MRT */
#define RTPROT_ZEBRA 11 /* Zebra */
#define RTPROT_BIRD 12 /* BIRD */
/* rtm_scope
Really it is not scope, but sort of distance to the destination.
NOWHERE are reserved for not existing destinations, HOST is our
local addresses, LINK are destinations, located on directly attached
link and UNIVERSE is everywhere in the Universe.
Intermediate values are also possible f.e. interior routes
could be assigned a value between UNIVERSE and LINK.
*/
enum rt_scope_t
{
RT_SCOPE_UNIVERSE=0,
/* User defined values */
RT_SCOPE_SITE=200,
RT_SCOPE_LINK=253,
RT_SCOPE_HOST=254,
RT_SCOPE_NOWHERE=255
};
/* rtm_flags */
#define RTM_F_NOTIFY 0x100 /* Notify user of route change */
#define RTM_F_CLONED 0x200 /* This route is cloned */
#define RTM_F_EQUALIZE 0x400 /* Multipath equalizer: NI */
/* Reserved table identifiers */
enum rt_class_t
{
RT_TABLE_UNSPEC=0,
/* User defined values */
RT_TABLE_DEFAULT=253,
RT_TABLE_MAIN=254,
RT_TABLE_LOCAL=255
};
#define RT_TABLE_MAX RT_TABLE_LOCAL
/* Routing message attributes */
enum rtattr_type_t
{
RTA_UNSPEC,
RTA_DST,
RTA_SRC,
RTA_IIF,
RTA_OIF,
RTA_GATEWAY,
RTA_PRIORITY,
RTA_PREFSRC,
RTA_METRICS,
RTA_MULTIPATH,
RTA_PROTOINFO,
RTA_FLOW,
RTA_CACHEINFO
};
#define RTA_MAX RTA_CACHEINFO
#define RTM_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct rtmsg))))
#define RTM_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct rtmsg))
/* RTM_MULTIPATH --- array of struct rtnexthop.
*
* "struct rtnexthop" describres all necessary nexthop information,
* i.e. parameters of path to a destination via this nextop.
*
* At the moment it is impossible to set different prefsrc, mtu, window
* and rtt for different paths from multipath.
*/
struct rtnexthop
{
unsigned short rtnh_len;
unsigned char rtnh_flags;
unsigned char rtnh_hops;
int rtnh_ifindex;
};
/* rtnh_flags */
#define RTNH_F_DEAD 1 /* Nexthop is dead (used by multipath) */
#define RTNH_F_PERVASIVE 2 /* Do recursive gateway lookup */
#define RTNH_F_ONLINK 4 /* Gateway is forced on link */
/* Macros to handle hexthops */
#define RTNH_ALIGNTO 4
#define RTNH_ALIGN(len) ( ((len)+RTNH_ALIGNTO-1) & ~(RTNH_ALIGNTO-1) )
#define RTNH_OK(rtnh,len) ((rtnh)->rtnh_len >= sizeof(struct rtnexthop) && \
((int)(rtnh)->rtnh_len) <= (len))
#define RTNH_NEXT(rtnh) ((struct rtnexthop*)(((char*)(rtnh)) + RTNH_ALIGN((rtnh)->rtnh_len)))
#define RTNH_LENGTH(len) (RTNH_ALIGN(sizeof(struct rtnexthop)) + (len))
#define RTNH_SPACE(len) RTNH_ALIGN(RTNH_LENGTH(len))
#define RTNH_DATA(rtnh) ((struct rtattr*)(((char*)(rtnh)) + RTNH_LENGTH(0)))
/* RTM_CACHEINFO */
struct rta_cacheinfo
{
__u32 rta_clntref;
__u32 rta_lastuse;
__s32 rta_expires;
__u32 rta_error;
__u32 rta_used;
};
/* RTM_METRICS --- array of struct rtattr with types of RTAX_* */
enum
{
RTAX_UNSPEC,
RTAX_LOCK,
RTAX_MTU,
RTAX_WINDOW,
RTAX_RTT,
RTAX_HOPS,
RTAX_SSTHRESH,
RTAX_CWND,
};
#define RTAX_MAX RTAX_CWND
/*********************************************************
* Interface address.
****/
struct ifaddrmsg
{
unsigned char ifa_family;
unsigned char ifa_prefixlen; /* The prefix length */
unsigned char ifa_flags; /* Flags */
unsigned char ifa_scope; /* See above */
int ifa_index; /* Link index */
};
enum
{
IFA_UNSPEC,
IFA_ADDRESS,
IFA_LOCAL,
IFA_LABEL,
IFA_BROADCAST,
IFA_ANYCAST,
IFA_CACHEINFO
};
#define IFA_MAX IFA_CACHEINFO
/* ifa_flags */
#define IFA_F_SECONDARY 0x01
#define IFA_F_DEPRECATED 0x20
#define IFA_F_TENTATIVE 0x40
#define IFA_F_PERMANENT 0x80
struct ifa_cacheinfo
{
__s32 ifa_prefered;
__s32 ifa_valid;
};
#define IFA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifaddrmsg))))
#define IFA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifaddrmsg))
/*
Important comment:
IFA_ADDRESS is prefix address, rather than local interface address.
It makes no difference for normally configured broadcast interfaces,
but for point-to-point IFA_ADDRESS is DESTINATION address,
local address is supplied in IFA_LOCAL attribute.
*/
/**************************************************************
* Neighbour discovery.
****/
struct ndmsg
{
unsigned char ndm_family;
unsigned char ndm_pad1;
unsigned short ndm_pad2;
int ndm_ifindex; /* Link index */
__u16 ndm_state;
__u8 ndm_flags;
__u8 ndm_type;
};
enum
{
NDA_UNSPEC,
NDA_DST,
NDA_LLADDR,
NDA_CACHEINFO
};
#define NDA_MAX NDA_CACHEINFO
#define NDA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ndmsg))))
#define NDA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ndmsg))
/*
* Neighbor Cache Entry Flags
*/
#define NTF_PROXY 0x08 /* == ATF_PUBL */
#define NTF_ROUTER 0x80
/*
* Neighbor Cache Entry States.
*/
#define NUD_INCOMPLETE 0x01
#define NUD_REACHABLE 0x02
#define NUD_STALE 0x04
#define NUD_DELAY 0x08
#define NUD_PROBE 0x10
#define NUD_FAILED 0x20
/* Dummy states */
#define NUD_NOARP 0x40
#define NUD_PERMANENT 0x80
#define NUD_NONE 0x00
struct nda_cacheinfo
{
__u32 ndm_confirmed;
__u32 ndm_used;
__u32 ndm_updated;
__u32 ndm_refcnt;
};
/****
* General form of address family dependent message.
****/
struct rtgenmsg
{
unsigned char rtgen_family;
};
/*****************************************************************
* Link layer specific messages.
****/
/* struct ifinfomsg
* passes link level specific information, not dependent
* on network protocol.
*/
struct ifinfomsg
{
unsigned char ifi_family;
unsigned char __ifi_pad;
unsigned short ifi_type; /* ARPHRD_* */
int ifi_index; /* Link index */
unsigned ifi_flags; /* IFF_* flags */
unsigned ifi_change; /* IFF_* change mask */
};
enum
{
IFLA_UNSPEC,
IFLA_ADDRESS,
IFLA_BROADCAST,
IFLA_IFNAME,
IFLA_MTU,
IFLA_LINK,
IFLA_QDISC,
IFLA_STATS
};
#define IFLA_MAX IFLA_STATS
#define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg))
/* ifi_flags.
IFF_* flags.
The only change is:
IFF_LOOPBACK, IFF_BROADCAST and IFF_POINTOPOINT are
more not changeable by user. They describe link media
characteristics and set by device driver.
Comments:
- Combination IFF_BROADCAST|IFF_POINTOPOINT is invalid
- If neiher of these three flags are set;
the interface is NBMA.
- IFF_MULTICAST does not mean anything special:
multicasts can be used on all not-NBMA links.
IFF_MULTICAST means that this media uses special encapsulation
for multicast frames. Apparently, all IFF_POINTOPOINT and
IFF_BROADCAST devices are able to use multicasts too.
*/
/* ifi_link.
For usual devices it is equal ifi_index.
If it is a "virtual interface" (f.e. tunnel), ifi_link
can point to real physical interface (f.e. for bandwidth calculations),
or maybe 0, what means, that real media is unknown (usual
for IPIP tunnels, when route to endpoint is allowed to change)
*/
/*****************************************************************
* Traffic control messages.
****/
struct tcmsg
{
unsigned char tcm_family;
unsigned char tcm__pad1;
unsigned short tcm__pad2;
int tcm_ifindex;
__u32 tcm_handle;
__u32 tcm_parent;
__u32 tcm_info;
};
enum
{
TCA_UNSPEC,
TCA_KIND,
TCA_OPTIONS,
TCA_STATS,
TCA_XSTATS,
TCA_RATE,
};
#define TCA_MAX TCA_RATE
#define TCA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcmsg))))
#define TCA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcmsg))
/* SUMMARY: maximal rtattr understood by kernel */
#define RTATTR_MAX RTA_MAX
/* RTnetlink multicast groups */
#define RTMGRP_LINK 1
#define RTMGRP_NOTIFY 2
#define RTMGRP_NEIGH 4
#define RTMGRP_TC 8
#define RTMGRP_IPV4_IFADDR 0x10
#define RTMGRP_IPV4_MROUTE 0x20
#define RTMGRP_IPV4_ROUTE 0x40
#define RTMGRP_IPV6_IFADDR 0x100
#define RTMGRP_IPV6_MROUTE 0x200
#define RTMGRP_IPV6_ROUTE 0x400
/* End of information exported to user level */
#ifdef __KERNEL__
extern atomic_t rtnl_rlockct;
extern struct wait_queue *rtnl_wait;
extern __inline__ int rtattr_strcmp(struct rtattr *rta, char *str)
{
int len = strlen(str) + 1;
return len > rta->rta_len || memcmp(RTA_DATA(rta), str, len);
}
extern int rtattr_parse(struct rtattr *tb[], int maxattr, struct rtattr *rta, int len);
#ifdef CONFIG_RTNETLINK
extern struct sock *rtnl;
struct rtnetlink_link
{
int (*doit)(struct sk_buff *, struct nlmsghdr*, void *attr);
int (*dumpit)(struct sk_buff *, struct netlink_callback *cb);
};
extern struct rtnetlink_link * rtnetlink_links[NPROTO];
extern int rtnetlink_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb);
extern int rtnetlink_send(struct sk_buff *skb, u32 pid, u32 group, int echo);
extern void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data);
#define RTA_PUT(skb, attrtype, attrlen, data) \
({ if (skb_tailroom(skb) < (int)RTA_SPACE(attrlen)) goto rtattr_failure; \
__rta_fill(skb, attrtype, attrlen, data); })
extern unsigned long rtnl_wlockct;
/* NOTE: these locks are not interrupt safe, are not SMP safe,
* they are even not atomic. 8)8)8) ... and it is not a bug.
* Really, if these locks will be programmed correctly,
* all the addressing/routing machine would become SMP safe,
* but is absolutely useless at the moment, because all the kernel
* is not reenterable in any case. --ANK
*
* Well, atomic_* and set_bit provide the only thing here:
* gcc is confused not to overoptimize them, that's all.
* I remember as gcc splitted ++ operation, but cannot reproduce
* it with gcc-2.7.*. --ANK
*
* One more note: rwlock facility should be written and put
* to a kernel wide location: f.e. current implementation of semaphores
* (especially, for x86) looks like a wonder. It would be good
* to have something similar for rwlock. Recursive lock could be also
* useful thing. --ANK
*/
extern __inline__ int rtnl_shlock_nowait(void)
{
atomic_inc(&rtnl_rlockct);
if (test_bit(0, &rtnl_wlockct)) {
atomic_dec(&rtnl_rlockct);
return -EAGAIN;
}
return 0;
}
extern __inline__ void rtnl_shlock(void)
{
while (rtnl_shlock_nowait())
sleep_on(&rtnl_wait);
}
/* Check for possibility to PROMOTE shared lock to exclusive.
Shared lock must be already grabbed with rtnl_shlock*().
*/
extern __inline__ int rtnl_exlock_nowait(void)
{
if (atomic_read(&rtnl_rlockct) > 1)
return -EAGAIN;
if (test_and_set_bit(0, &rtnl_wlockct))
return -EAGAIN;
return 0;
}
extern __inline__ void rtnl_exlock(void)
{
while (rtnl_exlock_nowait())
sleep_on(&rtnl_wait);
}
#if 0
extern __inline__ void rtnl_shunlock(void)
{
atomic_dec(&rtnl_rlockct);
if (atomic_read(&rtnl_rlockct) <= 1) {
wake_up(&rtnl_wait);
if (rtnl && rtnl->receive_queue.qlen)
rtnl->data_ready(rtnl, 0);
}
}
#else
/* The problem: inline requires to include <net/sock.h> and, hence,
almost all of net includes :-(
*/
#define rtnl_shunlock() ({ \
atomic_dec(&rtnl_rlockct); \
if (atomic_read(&rtnl_rlockct) <= 1) { \
wake_up(&rtnl_wait); \
if (rtnl && rtnl->receive_queue.qlen) \
rtnl->data_ready(rtnl, 0); \
} \
})
#endif
/* Release exclusive lock. Note, that we do not wake up rtnetlink socket,
* it will be done later after releasing shared lock.
*/
extern __inline__ void rtnl_exunlock(void)
{
clear_bit(0, &rtnl_wlockct);
wake_up(&rtnl_wait);
}
#else
extern __inline__ void rtnl_shlock(void)
{
#ifndef _HURD_
while (atomic_read(&rtnl_rlockct))
sleep_on(&rtnl_wait);
atomic_inc(&rtnl_rlockct);
#endif
}
extern __inline__ void rtnl_shunlock(void)
{
#ifndef _HURD_
if (atomic_dec_and_test(&rtnl_rlockct))
wake_up(&rtnl_wait);
#endif
}
extern __inline__ void rtnl_exlock(void)
{
}
extern __inline__ void rtnl_exunlock(void)
{
}
#endif
extern void rtnl_lock(void);
extern void rtnl_unlock(void);
extern void rtnetlink_init(void);
#endif /* __KERNEL__ */
#endif /* __LINUX_RTNETLINK_H */
|