-
Notifications
You must be signed in to change notification settings - Fork 3k
/
Copy pathif.c
5237 lines (4577 loc) · 118 KB
/
if.c
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
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*-
* SPDX-License-Identifier: BSD-3-Clause
*
* Copyright (c) 2010 Bjoern A. Zeeb <[email protected]>
* Copyright (c) 1980, 1986, 1993
* The Regents of the University of California. All rights reserved.
*
* 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.
* 3. 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.
*/
#include "opt_bpf.h"
#include "opt_inet6.h"
#include "opt_inet.h"
#include "opt_ddb.h"
#include <sys/param.h>
#include <sys/capsicum.h>
#include <sys/conf.h>
#include <sys/eventhandler.h>
#include <sys/malloc.h>
#include <sys/domainset.h>
#include <sys/sbuf.h>
#include <sys/bus.h>
#include <sys/epoch.h>
#include <sys/mbuf.h>
#include <sys/systm.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/protosw.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/refcount.h>
#include <sys/module.h>
#include <sys/nv.h>
#include <sys/rwlock.h>
#include <sys/sockio.h>
#include <sys/syslog.h>
#include <sys/sysctl.h>
#include <sys/sysent.h>
#include <sys/taskqueue.h>
#include <sys/domain.h>
#include <sys/jail.h>
#include <sys/priv.h>
#ifdef DDB
#include <ddb/ddb.h>
#endif
#include <machine/stdarg.h>
#include <vm/uma.h>
#include <net/bpf.h>
#include <net/ethernet.h>
#include <net/if.h>
#include <net/if_arp.h>
#include <net/if_clone.h>
#include <net/if_dl.h>
#include <net/if_strings.h>
#include <net/if_types.h>
#include <net/if_var.h>
#include <net/if_media.h>
#include <net/if_mib.h>
#include <net/if_private.h>
#include <net/if_vlan_var.h>
#include <net/radix.h>
#include <net/route.h>
#include <net/route/route_ctl.h>
#include <net/vnet.h>
#if defined(INET) || defined(INET6)
#include <net/ethernet.h>
#include <netinet/in.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
#include <netinet/ip_carp.h>
#ifdef INET
#include <net/debugnet.h>
#include <netinet/if_ether.h>
#endif /* INET */
#ifdef INET6
#include <netinet6/in6_var.h>
#include <netinet6/in6_ifattach.h>
#endif /* INET6 */
#endif /* INET || INET6 */
#include <security/mac/mac_framework.h>
/*
* Consumers of struct ifreq such as tcpdump assume no pad between ifr_name
* and ifr_ifru when it is used in SIOCGIFCONF.
*/
_Static_assert(sizeof(((struct ifreq *)0)->ifr_name) ==
offsetof(struct ifreq, ifr_ifru), "gap between ifr_name and ifr_ifru");
__read_mostly epoch_t net_epoch_preempt;
#ifdef COMPAT_FREEBSD32
#include <sys/mount.h>
#include <compat/freebsd32/freebsd32.h>
struct ifreq_buffer32 {
uint32_t length; /* (size_t) */
uint32_t buffer; /* (void *) */
};
/*
* Interface request structure used for socket
* ioctl's. All interface ioctl's must have parameter
* definitions which begin with ifr_name. The
* remainder may be interface specific.
*/
struct ifreq32 {
char ifr_name[IFNAMSIZ]; /* if name, e.g. "en0" */
union {
struct sockaddr ifru_addr;
struct sockaddr ifru_dstaddr;
struct sockaddr ifru_broadaddr;
struct ifreq_buffer32 ifru_buffer;
short ifru_flags[2];
short ifru_index;
int ifru_jid;
int ifru_metric;
int ifru_mtu;
int ifru_phys;
int ifru_media;
uint32_t ifru_data;
int ifru_cap[2];
u_int ifru_fib;
u_char ifru_vlan_pcp;
} ifr_ifru;
};
CTASSERT(sizeof(struct ifreq) == sizeof(struct ifreq32));
CTASSERT(__offsetof(struct ifreq, ifr_ifru) ==
__offsetof(struct ifreq32, ifr_ifru));
struct ifconf32 {
int32_t ifc_len;
union {
uint32_t ifcu_buf;
uint32_t ifcu_req;
} ifc_ifcu;
};
#define SIOCGIFCONF32 _IOWR('i', 36, struct ifconf32)
struct ifdrv32 {
char ifd_name[IFNAMSIZ];
uint32_t ifd_cmd;
uint32_t ifd_len;
uint32_t ifd_data;
};
#define SIOCSDRVSPEC32 _IOC_NEWTYPE(SIOCSDRVSPEC, struct ifdrv32)
#define SIOCGDRVSPEC32 _IOC_NEWTYPE(SIOCGDRVSPEC, struct ifdrv32)
struct ifgroupreq32 {
char ifgr_name[IFNAMSIZ];
u_int ifgr_len;
union {
char ifgru_group[IFNAMSIZ];
uint32_t ifgru_groups;
} ifgr_ifgru;
};
#define SIOCAIFGROUP32 _IOC_NEWTYPE(SIOCAIFGROUP, struct ifgroupreq32)
#define SIOCGIFGROUP32 _IOC_NEWTYPE(SIOCGIFGROUP, struct ifgroupreq32)
#define SIOCDIFGROUP32 _IOC_NEWTYPE(SIOCDIFGROUP, struct ifgroupreq32)
#define SIOCGIFGMEMB32 _IOC_NEWTYPE(SIOCGIFGMEMB, struct ifgroupreq32)
struct ifmediareq32 {
char ifm_name[IFNAMSIZ];
int ifm_current;
int ifm_mask;
int ifm_status;
int ifm_active;
int ifm_count;
uint32_t ifm_ulist; /* (int *) */
};
#define SIOCGIFMEDIA32 _IOC_NEWTYPE(SIOCGIFMEDIA, struct ifmediareq32)
#define SIOCGIFXMEDIA32 _IOC_NEWTYPE(SIOCGIFXMEDIA, struct ifmediareq32)
#endif /* COMPAT_FREEBSD32 */
union ifreq_union {
struct ifreq ifr;
#ifdef COMPAT_FREEBSD32
struct ifreq32 ifr32;
#endif
};
SYSCTL_NODE(_net, PF_LINK, link, CTLFLAG_RW | CTLFLAG_MPSAFE, 0,
"Link layers");
SYSCTL_NODE(_net_link, 0, generic, CTLFLAG_RW | CTLFLAG_MPSAFE, 0,
"Generic link-management");
SYSCTL_INT(_net_link, OID_AUTO, ifqmaxlen, CTLFLAG_RDTUN,
&ifqmaxlen, 0, "max send queue size");
/* Log link state change events */
static int log_link_state_change = 1;
SYSCTL_INT(_net_link, OID_AUTO, log_link_state_change, CTLFLAG_RW,
&log_link_state_change, 0,
"log interface link state change events");
/* Log promiscuous mode change events */
static int log_promisc_mode_change = 1;
SYSCTL_INT(_net_link, OID_AUTO, log_promisc_mode_change, CTLFLAG_RDTUN,
&log_promisc_mode_change, 1,
"log promiscuous mode change events");
/* Interface description */
static unsigned int ifdescr_maxlen = 1024;
SYSCTL_UINT(_net, OID_AUTO, ifdescr_maxlen, CTLFLAG_RW,
&ifdescr_maxlen, 0,
"administrative maximum length for interface description");
static MALLOC_DEFINE(M_IFDESCR, "ifdescr", "ifnet descriptions");
/* global sx for non-critical path ifdescr */
static struct sx ifdescr_sx;
SX_SYSINIT(ifdescr_sx, &ifdescr_sx, "ifnet descr");
void (*ng_ether_link_state_p)(struct ifnet *ifp, int state);
void (*lagg_linkstate_p)(struct ifnet *ifp, int state);
/* These are external hooks for CARP. */
void (*carp_linkstate_p)(struct ifnet *ifp);
void (*carp_demote_adj_p)(int, char *);
int (*carp_master_p)(struct ifaddr *);
#if defined(INET) || defined(INET6)
int (*carp_forus_p)(struct ifnet *ifp, u_char *dhost);
int (*carp_output_p)(struct ifnet *ifp, struct mbuf *m,
const struct sockaddr *sa);
int (*carp_ioctl_p)(struct ifreq *, u_long, struct thread *);
int (*carp_attach_p)(struct ifaddr *, int);
void (*carp_detach_p)(struct ifaddr *, bool);
#endif
#ifdef INET
int (*carp_iamatch_p)(struct ifaddr *, uint8_t **);
#endif
#ifdef INET6
struct ifaddr *(*carp_iamatch6_p)(struct ifnet *ifp, struct in6_addr *taddr6);
caddr_t (*carp_macmatch6_p)(struct ifnet *ifp, struct mbuf *m,
const struct in6_addr *taddr);
#endif
struct mbuf *(*tbr_dequeue_ptr)(struct ifaltq *, int) = NULL;
/*
* XXX: Style; these should be sorted alphabetically, and unprototyped
* static functions should be prototyped. Currently they are sorted by
* declaration order.
*/
static void if_attachdomain(void *);
static void if_attachdomain1(struct ifnet *);
static int ifconf(u_long, caddr_t);
static void if_input_default(struct ifnet *, struct mbuf *);
static int if_requestencap_default(struct ifnet *, struct if_encap_req *);
static int if_setflag(struct ifnet *, int, int, int *, int);
static int if_transmit_default(struct ifnet *ifp, struct mbuf *m);
static void if_unroute(struct ifnet *, int flag, int fam);
static int if_delmulti_locked(struct ifnet *, struct ifmultiaddr *, int);
static void do_link_state_change(void *, int);
static int if_getgroup(struct ifgroupreq *, struct ifnet *);
static int if_getgroupmembers(struct ifgroupreq *);
static void if_delgroups(struct ifnet *);
static void if_attach_internal(struct ifnet *, bool);
static void if_detach_internal(struct ifnet *, bool);
static void if_siocaddmulti(void *, int);
static void if_link_ifnet(struct ifnet *);
static bool if_unlink_ifnet(struct ifnet *, bool);
#ifdef VIMAGE
static void if_vmove(struct ifnet *, struct vnet *);
#endif
#ifdef INET6
/*
* XXX: declare here to avoid to include many inet6 related files..
* should be more generalized?
*/
extern void nd6_setmtu(struct ifnet *);
#endif
/* ipsec helper hooks */
VNET_DEFINE(struct hhook_head *, ipsec_hhh_in[HHOOK_IPSEC_COUNT]);
VNET_DEFINE(struct hhook_head *, ipsec_hhh_out[HHOOK_IPSEC_COUNT]);
int ifqmaxlen = IFQ_MAXLEN;
VNET_DEFINE(struct ifnethead, ifnet); /* depend on static init XXX */
VNET_DEFINE(struct ifgrouphead, ifg_head);
/* Table of ifnet by index. */
static int if_index;
static int if_indexlim = 8;
static struct ifindex_entry {
struct ifnet *ife_ifnet;
uint16_t ife_gencnt;
} *ifindex_table;
SYSCTL_NODE(_net_link_generic, IFMIB_SYSTEM, system,
CTLFLAG_RW | CTLFLAG_MPSAFE, 0,
"Variables global to all interfaces");
static int
sysctl_ifcount(SYSCTL_HANDLER_ARGS)
{
int rv = 0;
IFNET_RLOCK();
for (int i = 1; i <= if_index; i++)
if (ifindex_table[i].ife_ifnet != NULL &&
ifindex_table[i].ife_ifnet->if_vnet == curvnet)
rv = i;
IFNET_RUNLOCK();
return (sysctl_handle_int(oidp, &rv, 0, req));
}
SYSCTL_PROC(_net_link_generic_system, IFMIB_IFCOUNT, ifcount,
CTLTYPE_INT | CTLFLAG_VNET | CTLFLAG_RD, NULL, 0, sysctl_ifcount, "I",
"Maximum known interface index");
/*
* The global network interface list (V_ifnet) and related state (such as
* if_index, if_indexlim, and ifindex_table) are protected by an sxlock.
* This may be acquired to stabilise the list, or we may rely on NET_EPOCH.
*/
struct sx ifnet_sxlock;
SX_SYSINIT_FLAGS(ifnet_sx, &ifnet_sxlock, "ifnet_sx", SX_RECURSE);
struct sx ifnet_detach_sxlock;
SX_SYSINIT_FLAGS(ifnet_detach, &ifnet_detach_sxlock, "ifnet_detach_sx",
SX_RECURSE);
#ifdef VIMAGE
#define VNET_IS_SHUTTING_DOWN(_vnet) \
((_vnet)->vnet_shutdown && (_vnet)->vnet_state < SI_SUB_VNET_DONE)
#endif
static if_com_alloc_t *if_com_alloc[256];
static if_com_free_t *if_com_free[256];
static MALLOC_DEFINE(M_IFNET, "ifnet", "interface internals");
MALLOC_DEFINE(M_IFADDR, "ifaddr", "interface address");
MALLOC_DEFINE(M_IFMADDR, "ether_multi", "link-level multicast address");
struct ifnet *
ifnet_byindex(u_int idx)
{
struct ifnet *ifp;
NET_EPOCH_ASSERT();
if (__predict_false(idx > if_index))
return (NULL);
ifp = ck_pr_load_ptr(&ifindex_table[idx].ife_ifnet);
if (curvnet != NULL && ifp != NULL && ifp->if_vnet != curvnet)
ifp = NULL;
return (ifp);
}
struct ifnet *
ifnet_byindex_ref(u_int idx)
{
struct ifnet *ifp;
ifp = ifnet_byindex(idx);
if (ifp == NULL || (ifp->if_flags & IFF_DYING))
return (NULL);
if (!if_try_ref(ifp))
return (NULL);
return (ifp);
}
struct ifnet *
ifnet_byindexgen(uint16_t idx, uint16_t gen)
{
struct ifnet *ifp;
NET_EPOCH_ASSERT();
if (__predict_false(idx > if_index))
return (NULL);
ifp = ck_pr_load_ptr(&ifindex_table[idx].ife_ifnet);
if (ifindex_table[idx].ife_gencnt == gen)
return (ifp);
else
return (NULL);
}
/*
* Network interface utility routines.
*
* Routines with ifa_ifwith* names take sockaddr *'s as
* parameters.
*/
static void
if_init_idxtable(void *arg __unused)
{
ifindex_table = malloc(if_indexlim * sizeof(*ifindex_table),
M_IFNET, M_WAITOK | M_ZERO);
}
SYSINIT(if_init, SI_SUB_INIT_IF, SI_ORDER_SECOND, if_init_idxtable, NULL);
static void
vnet_if_init(const void *unused __unused)
{
CK_STAILQ_INIT(&V_ifnet);
CK_STAILQ_INIT(&V_ifg_head);
}
VNET_SYSINIT(vnet_if_init, SI_SUB_INIT_IF, SI_ORDER_SECOND, vnet_if_init,
NULL);
static void
if_link_ifnet(struct ifnet *ifp)
{
IFNET_WLOCK();
CK_STAILQ_INSERT_TAIL(&V_ifnet, ifp, if_link);
#ifdef VIMAGE
curvnet->vnet_ifcnt++;
#endif
IFNET_WUNLOCK();
}
static bool
if_unlink_ifnet(struct ifnet *ifp, bool vmove)
{
struct ifnet *iter;
int found = 0;
IFNET_WLOCK();
CK_STAILQ_FOREACH(iter, &V_ifnet, if_link)
if (iter == ifp) {
CK_STAILQ_REMOVE(&V_ifnet, ifp, ifnet, if_link);
if (!vmove)
ifp->if_flags |= IFF_DYING;
found = 1;
break;
}
#ifdef VIMAGE
curvnet->vnet_ifcnt--;
#endif
IFNET_WUNLOCK();
return (found);
}
#ifdef VIMAGE
static void
vnet_if_return(const void *unused __unused)
{
struct ifnet *ifp, *nifp;
struct ifnet **pending;
int found __diagused;
int i;
i = 0;
/*
* We need to protect our access to the V_ifnet tailq. Ordinarily we'd
* enter NET_EPOCH, but that's not possible, because if_vmove() calls
* if_detach_internal(), which waits for NET_EPOCH callbacks to
* complete. We can't do that from within NET_EPOCH.
*
* However, we can also use the IFNET_xLOCK, which is the V_ifnet
* read/write lock. We cannot hold the lock as we call if_vmove()
* though, as that presents LOR w.r.t ifnet_sx, in_multi_sx and iflib
* ctx lock.
*/
IFNET_WLOCK();
pending = malloc(sizeof(struct ifnet *) * curvnet->vnet_ifcnt,
M_IFNET, M_WAITOK | M_ZERO);
/* Return all inherited interfaces to their parent vnets. */
CK_STAILQ_FOREACH_SAFE(ifp, &V_ifnet, if_link, nifp) {
if (ifp->if_home_vnet != ifp->if_vnet) {
found = if_unlink_ifnet(ifp, true);
MPASS(found);
pending[i++] = ifp;
}
}
IFNET_WUNLOCK();
for (int j = 0; j < i; j++) {
sx_xlock(&ifnet_detach_sxlock);
if_vmove(pending[j], pending[j]->if_home_vnet);
sx_xunlock(&ifnet_detach_sxlock);
}
free(pending, M_IFNET);
}
VNET_SYSUNINIT(vnet_if_return, SI_SUB_VNET_DONE, SI_ORDER_ANY,
vnet_if_return, NULL);
#endif
/*
* Allocate a struct ifnet and an index for an interface. A layer 2
* common structure will also be allocated if an allocation routine is
* registered for the passed type.
*/
static struct ifnet *
if_alloc_domain(u_char type, int numa_domain)
{
struct ifnet *ifp;
u_short idx;
KASSERT(numa_domain <= IF_NODOM, ("numa_domain too large"));
if (numa_domain == IF_NODOM)
ifp = malloc(sizeof(struct ifnet), M_IFNET,
M_WAITOK | M_ZERO);
else
ifp = malloc_domainset(sizeof(struct ifnet), M_IFNET,
DOMAINSET_PREF(numa_domain), M_WAITOK | M_ZERO);
ifp->if_type = type;
ifp->if_alloctype = type;
ifp->if_numa_domain = numa_domain;
#ifdef VIMAGE
ifp->if_vnet = curvnet;
#endif
if (if_com_alloc[type] != NULL) {
ifp->if_l2com = if_com_alloc[type](type, ifp);
KASSERT(ifp->if_l2com, ("%s: if_com_alloc[%u] failed", __func__,
type));
}
IF_ADDR_LOCK_INIT(ifp);
TASK_INIT(&ifp->if_linktask, 0, do_link_state_change, ifp);
TASK_INIT(&ifp->if_addmultitask, 0, if_siocaddmulti, ifp);
ifp->if_afdata_initialized = 0;
IF_AFDATA_LOCK_INIT(ifp);
CK_STAILQ_INIT(&ifp->if_addrhead);
CK_STAILQ_INIT(&ifp->if_multiaddrs);
CK_STAILQ_INIT(&ifp->if_groups);
#ifdef MAC
mac_ifnet_init(ifp);
#endif
ifq_init(&ifp->if_snd, ifp);
refcount_init(&ifp->if_refcount, 1); /* Index reference. */
for (int i = 0; i < IFCOUNTERS; i++)
ifp->if_counters[i] = counter_u64_alloc(M_WAITOK);
ifp->if_get_counter = if_get_counter_default;
ifp->if_pcp = IFNET_PCP_NONE;
/* Allocate an ifindex array entry. */
IFNET_WLOCK();
/*
* Try to find an empty slot below if_index. If we fail, take the
* next slot.
*/
for (idx = 1; idx <= if_index; idx++) {
if (ifindex_table[idx].ife_ifnet == NULL)
break;
}
/* Catch if_index overflow. */
if (idx >= if_indexlim) {
struct ifindex_entry *new, *old;
int newlim;
newlim = if_indexlim * 2;
new = malloc(newlim * sizeof(*new), M_IFNET, M_WAITOK | M_ZERO);
memcpy(new, ifindex_table, if_indexlim * sizeof(*new));
old = ifindex_table;
ck_pr_store_ptr(&ifindex_table, new);
if_indexlim = newlim;
NET_EPOCH_WAIT();
free(old, M_IFNET);
}
if (idx > if_index)
if_index = idx;
ifp->if_index = idx;
ifp->if_idxgen = ifindex_table[idx].ife_gencnt;
ck_pr_store_ptr(&ifindex_table[idx].ife_ifnet, ifp);
IFNET_WUNLOCK();
return (ifp);
}
struct ifnet *
if_alloc_dev(u_char type, device_t dev)
{
int numa_domain;
if (dev == NULL || bus_get_domain(dev, &numa_domain) != 0)
return (if_alloc_domain(type, IF_NODOM));
return (if_alloc_domain(type, numa_domain));
}
struct ifnet *
if_alloc(u_char type)
{
return (if_alloc_domain(type, IF_NODOM));
}
/*
* Do the actual work of freeing a struct ifnet, and layer 2 common
* structure. This call is made when the network epoch guarantees
* us that nobody holds a pointer to the interface.
*/
static void
if_free_deferred(epoch_context_t ctx)
{
struct ifnet *ifp = __containerof(ctx, struct ifnet, if_epoch_ctx);
KASSERT((ifp->if_flags & IFF_DYING),
("%s: interface not dying", __func__));
if (if_com_free[ifp->if_alloctype] != NULL)
if_com_free[ifp->if_alloctype](ifp->if_l2com,
ifp->if_alloctype);
#ifdef MAC
mac_ifnet_destroy(ifp);
#endif /* MAC */
IF_AFDATA_DESTROY(ifp);
IF_ADDR_LOCK_DESTROY(ifp);
ifq_delete(&ifp->if_snd);
for (int i = 0; i < IFCOUNTERS; i++)
counter_u64_free(ifp->if_counters[i]);
if_freedescr(ifp->if_description);
free(ifp->if_hw_addr, M_IFADDR);
free(ifp, M_IFNET);
}
/*
* Deregister an interface and free the associated storage.
*/
void
if_free(struct ifnet *ifp)
{
ifp->if_flags |= IFF_DYING; /* XXX: Locking */
/*
* XXXGL: An interface index is really an alias to ifp pointer.
* Why would we clear the alias now, and not in the deferred
* context? Indeed there is nothing wrong with some network
* thread obtaining ifp via ifnet_byindex() inside the network
* epoch and then dereferencing ifp while we perform if_free(),
* and after if_free() finished, too.
*
* This early index freeing was important back when ifindex was
* virtualized and interface would outlive the vnet.
*/
IFNET_WLOCK();
MPASS(ifindex_table[ifp->if_index].ife_ifnet == ifp);
ck_pr_store_ptr(&ifindex_table[ifp->if_index].ife_ifnet, NULL);
ifindex_table[ifp->if_index].ife_gencnt++;
while (if_index > 0 && ifindex_table[if_index].ife_ifnet == NULL)
if_index--;
IFNET_WUNLOCK();
if (refcount_release(&ifp->if_refcount))
NET_EPOCH_CALL(if_free_deferred, &ifp->if_epoch_ctx);
}
/*
* Interfaces to keep an ifnet type-stable despite the possibility of the
* driver calling if_free(). If there are additional references, we defer
* freeing the underlying data structure.
*/
void
if_ref(struct ifnet *ifp)
{
u_int old __diagused;
/* We don't assert the ifnet list lock here, but arguably should. */
old = refcount_acquire(&ifp->if_refcount);
KASSERT(old > 0, ("%s: ifp %p has 0 refs", __func__, ifp));
}
bool
if_try_ref(struct ifnet *ifp)
{
NET_EPOCH_ASSERT();
return (refcount_acquire_if_not_zero(&ifp->if_refcount));
}
void
if_rele(struct ifnet *ifp)
{
if (!refcount_release(&ifp->if_refcount))
return;
NET_EPOCH_CALL(if_free_deferred, &ifp->if_epoch_ctx);
}
void
ifq_init(struct ifaltq *ifq, struct ifnet *ifp)
{
mtx_init(&ifq->ifq_mtx, ifp->if_xname, "if send queue", MTX_DEF);
if (ifq->ifq_maxlen == 0)
ifq->ifq_maxlen = ifqmaxlen;
ifq->altq_type = 0;
ifq->altq_disc = NULL;
ifq->altq_flags &= ALTQF_CANTCHANGE;
ifq->altq_tbr = NULL;
ifq->altq_ifp = ifp;
}
void
ifq_delete(struct ifaltq *ifq)
{
mtx_destroy(&ifq->ifq_mtx);
}
/*
* Perform generic interface initialization tasks and attach the interface
* to the list of "active" interfaces. If vmove flag is set on entry
* to if_attach_internal(), perform only a limited subset of initialization
* tasks, given that we are moving from one vnet to another an ifnet which
* has already been fully initialized.
*
* Note that if_detach_internal() removes group membership unconditionally
* even when vmove flag is set, and if_attach_internal() adds only IFG_ALL.
* Thus, when if_vmove() is applied to a cloned interface, group membership
* is lost while a cloned one always joins a group whose name is
* ifc->ifc_name. To recover this after if_detach_internal() and
* if_attach_internal(), the cloner should be specified to
* if_attach_internal() via ifc. If it is non-NULL, if_attach_internal()
* attempts to join a group whose name is ifc->ifc_name.
*
* XXX:
* - The decision to return void and thus require this function to
* succeed is questionable.
* - We should probably do more sanity checking. For instance we don't
* do anything to insure if_xname is unique or non-empty.
*/
void
if_attach(struct ifnet *ifp)
{
if_attach_internal(ifp, false);
}
/*
* Compute the least common TSO limit.
*/
void
if_hw_tsomax_common(if_t ifp, struct ifnet_hw_tsomax *pmax)
{
/*
* 1) If there is no limit currently, take the limit from
* the network adapter.
*
* 2) If the network adapter has a limit below the current
* limit, apply it.
*/
if (pmax->tsomaxbytes == 0 || (ifp->if_hw_tsomax != 0 &&
ifp->if_hw_tsomax < pmax->tsomaxbytes)) {
pmax->tsomaxbytes = ifp->if_hw_tsomax;
}
if (pmax->tsomaxsegcount == 0 || (ifp->if_hw_tsomaxsegcount != 0 &&
ifp->if_hw_tsomaxsegcount < pmax->tsomaxsegcount)) {
pmax->tsomaxsegcount = ifp->if_hw_tsomaxsegcount;
}
if (pmax->tsomaxsegsize == 0 || (ifp->if_hw_tsomaxsegsize != 0 &&
ifp->if_hw_tsomaxsegsize < pmax->tsomaxsegsize)) {
pmax->tsomaxsegsize = ifp->if_hw_tsomaxsegsize;
}
}
/*
* Update TSO limit of a network adapter.
*
* Returns zero if no change. Else non-zero.
*/
int
if_hw_tsomax_update(if_t ifp, struct ifnet_hw_tsomax *pmax)
{
int retval = 0;
if (ifp->if_hw_tsomax != pmax->tsomaxbytes) {
ifp->if_hw_tsomax = pmax->tsomaxbytes;
retval++;
}
if (ifp->if_hw_tsomaxsegsize != pmax->tsomaxsegsize) {
ifp->if_hw_tsomaxsegsize = pmax->tsomaxsegsize;
retval++;
}
if (ifp->if_hw_tsomaxsegcount != pmax->tsomaxsegcount) {
ifp->if_hw_tsomaxsegcount = pmax->tsomaxsegcount;
retval++;
}
return (retval);
}
static void
if_attach_internal(struct ifnet *ifp, bool vmove)
{
unsigned socksize, ifasize;
int namelen, masklen;
struct sockaddr_dl *sdl;
struct ifaddr *ifa;
MPASS(ifindex_table[ifp->if_index].ife_ifnet == ifp);
#ifdef VIMAGE
CURVNET_ASSERT_SET();
ifp->if_vnet = curvnet;
if (ifp->if_home_vnet == NULL)
ifp->if_home_vnet = curvnet;
#endif
if_addgroup(ifp, IFG_ALL);
#ifdef VIMAGE
/* Restore group membership for cloned interface. */
if (vmove)
if_clone_restoregroup(ifp);
#endif
getmicrotime(&ifp->if_lastchange);
ifp->if_epoch = time_uptime;
KASSERT((ifp->if_transmit == NULL && ifp->if_qflush == NULL) ||
(ifp->if_transmit != NULL && ifp->if_qflush != NULL),
("transmit and qflush must both either be set or both be NULL"));
if (ifp->if_transmit == NULL) {
ifp->if_transmit = if_transmit_default;
ifp->if_qflush = if_qflush;
}
if (ifp->if_input == NULL)
ifp->if_input = if_input_default;
if (ifp->if_requestencap == NULL)
ifp->if_requestencap = if_requestencap_default;
if (!vmove) {
#ifdef MAC
mac_ifnet_create(ifp);
#endif
/*
* Create a Link Level name for this device.
*/
namelen = strlen(ifp->if_xname);
/*
* Always save enough space for any possiable name so we
* can do a rename in place later.
*/
masklen = offsetof(struct sockaddr_dl, sdl_data[0]) + IFNAMSIZ;
socksize = masklen + ifp->if_addrlen;
if (socksize < sizeof(*sdl))
socksize = sizeof(*sdl);
socksize = roundup2(socksize, sizeof(long));
ifasize = sizeof(*ifa) + 2 * socksize;
ifa = ifa_alloc(ifasize, M_WAITOK);
sdl = (struct sockaddr_dl *)(ifa + 1);
sdl->sdl_len = socksize;
sdl->sdl_family = AF_LINK;
bcopy(ifp->if_xname, sdl->sdl_data, namelen);
sdl->sdl_nlen = namelen;
sdl->sdl_index = ifp->if_index;
sdl->sdl_type = ifp->if_type;
ifp->if_addr = ifa;
ifa->ifa_ifp = ifp;
ifa->ifa_addr = (struct sockaddr *)sdl;
sdl = (struct sockaddr_dl *)(socksize + (caddr_t)sdl);
ifa->ifa_netmask = (struct sockaddr *)sdl;
sdl->sdl_len = masklen;
while (namelen != 0)
sdl->sdl_data[--namelen] = 0xff;
CK_STAILQ_INSERT_HEAD(&ifp->if_addrhead, ifa, ifa_link);
/* Reliably crash if used uninitialized. */
ifp->if_broadcastaddr = NULL;
if (ifp->if_type == IFT_ETHER) {
ifp->if_hw_addr = malloc(ifp->if_addrlen, M_IFADDR,
M_WAITOK | M_ZERO);
}
#if defined(INET) || defined(INET6)
/* Use defaults for TSO, if nothing is set */
if (ifp->if_hw_tsomax == 0 &&
ifp->if_hw_tsomaxsegcount == 0 &&
ifp->if_hw_tsomaxsegsize == 0) {
/*
* The TSO defaults needs to be such that an
* NFS mbuf list of 35 mbufs totalling just
* below 64K works and that a chain of mbufs
* can be defragged into at most 32 segments:
*/
ifp->if_hw_tsomax = min(IP_MAXPACKET, (32 * MCLBYTES) -
(ETHER_HDR_LEN + ETHER_VLAN_ENCAP_LEN));
ifp->if_hw_tsomaxsegcount = 35;
ifp->if_hw_tsomaxsegsize = 2048; /* 2K */
/* XXX some drivers set IFCAP_TSO after ethernet attach */
if (ifp->if_capabilities & IFCAP_TSO) {
if_printf(ifp, "Using defaults for TSO: %u/%u/%u\n",
ifp->if_hw_tsomax,
ifp->if_hw_tsomaxsegcount,
ifp->if_hw_tsomaxsegsize);
}
}
#endif
}
#ifdef VIMAGE
else {
/*
* Update the interface index in the link layer address
* of the interface.
*/
for (ifa = ifp->if_addr; ifa != NULL;
ifa = CK_STAILQ_NEXT(ifa, ifa_link)) {
if (ifa->ifa_addr->sa_family == AF_LINK) {
sdl = (struct sockaddr_dl *)ifa->ifa_addr;
sdl->sdl_index = ifp->if_index;
}
}
}
#endif
if_link_ifnet(ifp);
if (domain_init_status >= 2)
if_attachdomain1(ifp);
EVENTHANDLER_INVOKE(ifnet_arrival_event, ifp);
if (IS_DEFAULT_VNET(curvnet))
devctl_notify("IFNET", ifp->if_xname, "ATTACH", NULL);
}
static void
if_epochalloc(void *dummy __unused)
{
net_epoch_preempt = epoch_alloc("Net preemptible", EPOCH_PREEMPT);
}
SYSINIT(ifepochalloc, SI_SUB_EPOCH, SI_ORDER_ANY, if_epochalloc, NULL);
static void
if_attachdomain(void *dummy)
{
struct ifnet *ifp;
CK_STAILQ_FOREACH(ifp, &V_ifnet, if_link)
if_attachdomain1(ifp);
}
SYSINIT(domainifattach, SI_SUB_PROTO_IFATTACHDOMAIN, SI_ORDER_SECOND,
if_attachdomain, NULL);
static void
if_attachdomain1(struct ifnet *ifp)
{
struct domain *dp;
/*
* Since dp->dom_ifattach calls malloc() with M_WAITOK, we
* cannot lock ifp->if_afdata initialization, entirely.
*/
IF_AFDATA_LOCK(ifp);
if (ifp->if_afdata_initialized >= domain_init_status) {
IF_AFDATA_UNLOCK(ifp);
log(LOG_WARNING, "%s called more than once on %s\n",
__func__, ifp->if_xname);
return;
}
ifp->if_afdata_initialized = domain_init_status;
IF_AFDATA_UNLOCK(ifp);
/* address family dependent data region */
bzero(ifp->if_afdata, sizeof(ifp->if_afdata));
SLIST_FOREACH(dp, &domains, dom_next) {