-
Notifications
You must be signed in to change notification settings - Fork 34
/
ip_output.c
1320 lines (1215 loc) · 33.5 KB
/
ip_output.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
/*-
* Copyright (c) 1982, 1986, 1988, 1990, 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.
* 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_output.c 8.3 (Berkeley) 1/21/94
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_ipfw.h"
#include "opt_ipsec.h"
#include "opt_route.h"
#include "opt_mbuf_stress_test.h"
#include "opt_mpath.h"
#include "opt_sctp.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sysctl.h>
#include <sys/ucred.h>
#include <net/if.h>
#include <net/if_llatbl.h>
#include <net/netisr.h>
#include <net/pfil.h>
#include <net/route.h>
#include <net/flowtable.h>
#ifdef RADIX_MPATH
#include <net/radix_mpath.h>
#endif
#include <net/vnet.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/in_pcb.h>
#include <netinet/in_var.h>
#include <netinet/ip_var.h>
#include <netinet/ip_options.h>
#ifdef SCTP
#include <netinet/sctp.h>
#include <netinet/sctp_crc32.h>
#endif
#ifdef IPSEC
#include <netinet/ip_ipsec.h>
#include <netipsec/ipsec.h>
#endif /* IPSEC*/
#include <machine/in_cksum.h>
#include <security/mac/mac_framework.h>
VNET_DEFINE(u_short, ip_id);
#ifdef MBUF_STRESS_TEST
static int mbuf_frag_size = 0;
SYSCTL_INT(_net_inet_ip, OID_AUTO, mbuf_frag_size, CTLFLAG_RW,
&mbuf_frag_size, 0, "Fragment outgoing mbufs to this size");
#endif
static void ip_mloopback
(struct ifnet *, struct mbuf *, struct sockaddr_in *, int);
extern int in_mcast_loop;
extern struct protosw inetsw[];
/*
* IP output. The packet in mbuf chain m contains a skeletal IP
* header (with len, off, ttl, proto, tos, src, dst).
* The mbuf chain containing the packet will be freed.
* The mbuf opt, if present, will not be freed.
* If route ro is present and has ro_rt initialized, route lookup would be
* skipped and ro->ro_rt would be used. If ro is present but ro->ro_rt is NULL,
* then result of route lookup is stored in ro->ro_rt.
*
* In the IP forwarding case, the packet will arrive with options already
* inserted, so must have a NULL opt pointer.
*/
int
ip_output(struct mbuf *m, struct mbuf *opt, struct route *ro, int flags,
struct ip_moptions *imo, struct inpcb *inp)
{
struct ip *ip;
struct ifnet *ifp = NULL; /* keep compiler happy */
struct mbuf *m0;
int hlen = sizeof (struct ip);
int mtu;
int n; /* scratchpad */
int error = 0;
struct sockaddr_in *dst;
struct in_ifaddr *ia;
int isbroadcast;
uint16_t ip_len, ip_off;
struct route iproute;
struct rtentry *rte; /* cache for ro->ro_rt */
struct in_addr odst;
struct m_tag *fwd_tag = NULL;
#ifdef IPSEC
int no_route_but_check_spd = 0;
#endif
M_ASSERTPKTHDR(m);
if (inp != NULL) {
INP_LOCK_ASSERT(inp);
M_SETFIB(m, inp->inp_inc.inc_fibnum);
if (inp->inp_flags & (INP_HW_FLOWID|INP_SW_FLOWID)) {
m->m_pkthdr.flowid = inp->inp_flowid;
m->m_flags |= M_FLOWID;
}
}
if (ro == NULL) {
ro = &iproute;
bzero(ro, sizeof (*ro));
}
#ifdef FLOWTABLE
if (ro->ro_rt == NULL) {
struct flentry *fle;
/*
* The flow table returns route entries valid for up to 30
* seconds; we rely on the remainder of ip_output() taking no
* longer than that long for the stability of ro_rt. The
* flow ID assignment must have happened before this point.
*/
fle = flowtable_lookup_mbuf(V_ip_ft, m, AF_INET);
if (fle != NULL)
flow_to_route(fle, ro);
}
#endif
if (opt) {
int len = 0;
m = ip_insertoptions(m, opt, &len);
if (len != 0)
hlen = len; /* ip->ip_hl is updated above */
}
ip = mtod(m, struct ip *);
ip_len = ntohs(ip->ip_len);
ip_off = ntohs(ip->ip_off);
/*
* Fill in IP header. If we are not allowing fragmentation,
* then the ip_id field is meaningless, but we don't set it
* to zero. Doing so causes various problems when devices along
* the path (routers, load balancers, firewalls, etc.) illegally
* disable DF on our packet. Note that a 16-bit counter
* will wrap around in less than 10 seconds at 100 Mbit/s on a
* medium with MTU 1500. See Steven M. Bellovin, "A Technique
* for Counting NATted Hosts", Proc. IMW'02, available at
* <http://www.cs.columbia.edu/~smb/papers/fnat.pdf>.
*/
if ((flags & (IP_FORWARDING|IP_RAWOUTPUT)) == 0) {
ip->ip_v = IPVERSION;
ip->ip_hl = hlen >> 2;
ip->ip_id = ip_newid();
IPSTAT_INC(ips_localout);
} else {
/* Header already set, fetch hlen from there */
hlen = ip->ip_hl << 2;
}
dst = (struct sockaddr_in *)&ro->ro_dst;
again:
ia = NULL;
/*
* If there is a cached route,
* check that it is to the same destination
* and is still up. If not, free it and try again.
* The address family should also be checked in case of sharing the
* cache with IPv6.
*/
rte = ro->ro_rt;
if (rte && ((rte->rt_flags & RTF_UP) == 0 ||
rte->rt_ifp == NULL ||
!RT_LINK_IS_UP(rte->rt_ifp) ||
dst->sin_family != AF_INET ||
dst->sin_addr.s_addr != ip->ip_dst.s_addr)) {
RO_RTFREE(ro);
ro->ro_lle = NULL;
rte = NULL;
}
if (rte == NULL && fwd_tag == NULL) {
bzero(dst, sizeof(*dst));
dst->sin_family = AF_INET;
dst->sin_len = sizeof(*dst);
dst->sin_addr = ip->ip_dst;
}
/*
* If routing to interface only, short circuit routing lookup.
* The use of an all-ones broadcast address implies this; an
* interface is specified by the broadcast address of an interface,
* or the destination address of a ptp interface.
*/
if (flags & IP_SENDONES) {
if ((ia = ifatoia(ifa_ifwithbroadaddr(sintosa(dst)))) == NULL &&
(ia = ifatoia(ifa_ifwithdstaddr(sintosa(dst)))) == NULL) {
IPSTAT_INC(ips_noroute);
error = ENETUNREACH;
goto bad;
}
ip->ip_dst.s_addr = INADDR_BROADCAST;
dst->sin_addr = ip->ip_dst;
ifp = ia->ia_ifp;
ip->ip_ttl = 1;
isbroadcast = 1;
} else if (flags & IP_ROUTETOIF) {
if ((ia = ifatoia(ifa_ifwithdstaddr(sintosa(dst)))) == NULL &&
(ia = ifatoia(ifa_ifwithnet(sintosa(dst), 0))) == NULL) {
IPSTAT_INC(ips_noroute);
error = ENETUNREACH;
goto bad;
}
ifp = ia->ia_ifp;
ip->ip_ttl = 1;
isbroadcast = in_broadcast(dst->sin_addr, ifp);
} else if (IN_MULTICAST(ntohl(ip->ip_dst.s_addr)) &&
imo != NULL && imo->imo_multicast_ifp != NULL) {
/*
* Bypass the normal routing lookup for multicast
* packets if the interface is specified.
*/
ifp = imo->imo_multicast_ifp;
IFP_TO_IA(ifp, ia);
isbroadcast = 0; /* fool gcc */
} else {
/*
* We want to do any cloning requested by the link layer,
* as this is probably required in all cases for correct
* operation (as it is for ARP).
*/
if (rte == NULL) {
#ifdef RADIX_MPATH
rtalloc_mpath_fib(ro,
ntohl(ip->ip_src.s_addr ^ ip->ip_dst.s_addr),
inp ? inp->inp_inc.inc_fibnum : M_GETFIB(m));
#else
in_rtalloc_ign(ro, 0,
inp ? inp->inp_inc.inc_fibnum : M_GETFIB(m));
#endif
rte = ro->ro_rt;
}
if (rte == NULL ||
rte->rt_ifp == NULL ||
!RT_LINK_IS_UP(rte->rt_ifp)) {
#ifdef IPSEC
/*
* There is no route for this packet, but it is
* possible that a matching SPD entry exists.
*/
no_route_but_check_spd = 1;
mtu = 0; /* Silence GCC warning. */
goto sendit;
#endif
IPSTAT_INC(ips_noroute);
error = EHOSTUNREACH;
goto bad;
}
ia = ifatoia(rte->rt_ifa);
ifa_ref(&ia->ia_ifa);
ifp = rte->rt_ifp;
rte->rt_rmx.rmx_pksent++;
if (rte->rt_flags & RTF_GATEWAY)
dst = (struct sockaddr_in *)rte->rt_gateway;
if (rte->rt_flags & RTF_HOST)
isbroadcast = (rte->rt_flags & RTF_BROADCAST);
else
isbroadcast = in_broadcast(dst->sin_addr, ifp);
}
/*
* Calculate MTU. If we have a route that is up, use that,
* otherwise use the interface's MTU.
*/
if (rte != NULL && (rte->rt_flags & (RTF_UP|RTF_HOST))) {
/*
* This case can happen if the user changed the MTU
* of an interface after enabling IP on it. Because
* most netifs don't keep track of routes pointing to
* them, there is no way for one to update all its
* routes when the MTU is changed.
*/
if (rte->rt_rmx.rmx_mtu > ifp->if_mtu)
rte->rt_rmx.rmx_mtu = ifp->if_mtu;
mtu = rte->rt_rmx.rmx_mtu;
} else {
mtu = ifp->if_mtu;
}
/* Catch a possible divide by zero later. */
KASSERT(mtu > 0, ("%s: mtu %d <= 0, rte=%p (rt_flags=0x%08x) ifp=%p",
__func__, mtu, rte, (rte != NULL) ? rte->rt_flags : 0, ifp));
if (IN_MULTICAST(ntohl(ip->ip_dst.s_addr))) {
m->m_flags |= M_MCAST;
/*
* IP destination address is multicast. Make sure "dst"
* still points to the address in "ro". (It may have been
* changed to point to a gateway address, above.)
*/
dst = (struct sockaddr_in *)&ro->ro_dst;
/*
* See if the caller provided any multicast options
*/
if (imo != NULL) {
ip->ip_ttl = imo->imo_multicast_ttl;
if (imo->imo_multicast_vif != -1)
ip->ip_src.s_addr =
ip_mcast_src ?
ip_mcast_src(imo->imo_multicast_vif) :
INADDR_ANY;
} else
ip->ip_ttl = IP_DEFAULT_MULTICAST_TTL;
/*
* Confirm that the outgoing interface supports multicast.
*/
if ((imo == NULL) || (imo->imo_multicast_vif == -1)) {
if ((ifp->if_flags & IFF_MULTICAST) == 0) {
IPSTAT_INC(ips_noroute);
error = ENETUNREACH;
goto bad;
}
}
/*
* If source address not specified yet, use address
* of outgoing interface.
*/
if (ip->ip_src.s_addr == INADDR_ANY) {
/* Interface may have no addresses. */
if (ia != NULL)
ip->ip_src = IA_SIN(ia)->sin_addr;
}
if ((imo == NULL && in_mcast_loop) ||
(imo && imo->imo_multicast_loop)) {
/*
* Loop back multicast datagram if not expressly
* forbidden to do so, even if we are not a member
* of the group; ip_input() will filter it later,
* thus deferring a hash lookup and mutex acquisition
* at the expense of a cheap copy using m_copym().
*/
ip_mloopback(ifp, m, dst, hlen);
} else {
/*
* If we are acting as a multicast router, perform
* multicast forwarding as if the packet had just
* arrived on the interface to which we are about
* to send. The multicast forwarding function
* recursively calls this function, using the
* IP_FORWARDING flag to prevent infinite recursion.
*
* Multicasts that are looped back by ip_mloopback(),
* above, will be forwarded by the ip_input() routine,
* if necessary.
*/
if (V_ip_mrouter && (flags & IP_FORWARDING) == 0) {
/*
* If rsvp daemon is not running, do not
* set ip_moptions. This ensures that the packet
* is multicast and not just sent down one link
* as prescribed by rsvpd.
*/
if (!V_rsvp_on)
imo = NULL;
if (ip_mforward &&
ip_mforward(ip, ifp, m, imo) != 0) {
m_freem(m);
goto done;
}
}
}
/*
* Multicasts with a time-to-live of zero may be looped-
* back, above, but must not be transmitted on a network.
* Also, multicasts addressed to the loopback interface
* are not sent -- the above call to ip_mloopback() will
* loop back a copy. ip_input() will drop the copy if
* this host does not belong to the destination group on
* the loopback interface.
*/
if (ip->ip_ttl == 0 || ifp->if_flags & IFF_LOOPBACK) {
m_freem(m);
goto done;
}
goto sendit;
}
/*
* If the source address is not specified yet, use the address
* of the outoing interface.
*/
if (ip->ip_src.s_addr == INADDR_ANY) {
/* Interface may have no addresses. */
if (ia != NULL) {
ip->ip_src = IA_SIN(ia)->sin_addr;
}
}
/*
* Verify that we have any chance at all of being able to queue the
* packet or packet fragments, unless ALTQ is enabled on the given
* interface in which case packetdrop should be done by queueing.
*/
n = ip_len / mtu + 1; /* how many fragments ? */
if (
#ifdef ALTQ
(!ALTQ_IS_ENABLED(&ifp->if_snd)) &&
#endif /* ALTQ */
(ifp->if_snd.ifq_len + n) >= ifp->if_snd.ifq_maxlen ) {
error = ENOBUFS;
IPSTAT_INC(ips_odropped);
ifp->if_snd.ifq_drops += n;
goto bad;
}
/*
* Look for broadcast address and
* verify user is allowed to send
* such a packet.
*/
if (isbroadcast) {
if ((ifp->if_flags & IFF_BROADCAST) == 0) {
error = EADDRNOTAVAIL;
goto bad;
}
if ((flags & IP_ALLOWBROADCAST) == 0) {
error = EACCES;
goto bad;
}
/* don't allow broadcast messages to be fragmented */
if (ip_len > mtu) {
error = EMSGSIZE;
goto bad;
}
m->m_flags |= M_BCAST;
} else {
m->m_flags &= ~M_BCAST;
}
sendit:
#ifdef IPSEC
switch(ip_ipsec_output(&m, inp, &flags, &error)) {
case 1:
goto bad;
case -1:
goto done;
case 0:
default:
break; /* Continue with packet processing. */
}
/*
* Check if there was a route for this packet; return error if not.
*/
if (no_route_but_check_spd) {
IPSTAT_INC(ips_noroute);
error = EHOSTUNREACH;
goto bad;
}
/* Update variables that are affected by ipsec4_output(). */
ip = mtod(m, struct ip *);
hlen = ip->ip_hl << 2;
#endif /* IPSEC */
/* Jump over all PFIL processing if hooks are not active. */
if (!PFIL_HOOKED(&V_inet_pfil_hook))
goto passout;
/* Run through list of hooks for output packets. */
odst.s_addr = ip->ip_dst.s_addr;
error = pfil_run_hooks(&V_inet_pfil_hook, &m, ifp, PFIL_OUT, inp);
if (error != 0 || m == NULL)
goto done;
ip = mtod(m, struct ip *);
/* See if destination IP address was changed by packet filter. */
if (odst.s_addr != ip->ip_dst.s_addr) {
m->m_flags |= M_SKIP_FIREWALL;
/* If destination is now ourself drop to ip_input(). */
if (in_localip(ip->ip_dst)) {
m->m_flags |= M_FASTFWD_OURS;
if (m->m_pkthdr.rcvif == NULL)
m->m_pkthdr.rcvif = V_loif;
if (m->m_pkthdr.csum_flags & CSUM_DELAY_DATA) {
m->m_pkthdr.csum_flags |=
CSUM_DATA_VALID | CSUM_PSEUDO_HDR;
m->m_pkthdr.csum_data = 0xffff;
}
m->m_pkthdr.csum_flags |=
CSUM_IP_CHECKED | CSUM_IP_VALID;
#ifdef SCTP
if (m->m_pkthdr.csum_flags & CSUM_SCTP)
m->m_pkthdr.csum_flags |= CSUM_SCTP_VALID;
#endif
error = netisr_queue(NETISR_IP, m);
goto done;
} else {
if (ia != NULL)
ifa_free(&ia->ia_ifa);
goto again; /* Redo the routing table lookup. */
}
}
/* See if local, if yes, send it to netisr with IP_FASTFWD_OURS. */
if (m->m_flags & M_FASTFWD_OURS) {
if (m->m_pkthdr.rcvif == NULL)
m->m_pkthdr.rcvif = V_loif;
if (m->m_pkthdr.csum_flags & CSUM_DELAY_DATA) {
m->m_pkthdr.csum_flags |=
CSUM_DATA_VALID | CSUM_PSEUDO_HDR;
m->m_pkthdr.csum_data = 0xffff;
}
#ifdef SCTP
if (m->m_pkthdr.csum_flags & CSUM_SCTP)
m->m_pkthdr.csum_flags |= CSUM_SCTP_VALID;
#endif
m->m_pkthdr.csum_flags |=
CSUM_IP_CHECKED | CSUM_IP_VALID;
error = netisr_queue(NETISR_IP, m);
goto done;
}
/* Or forward to some other address? */
if ((m->m_flags & M_IP_NEXTHOP) &&
(fwd_tag = m_tag_find(m, PACKET_TAG_IPFORWARD, NULL)) != NULL) {
dst = (struct sockaddr_in *)&ro->ro_dst;
bcopy((fwd_tag+1), dst, sizeof(struct sockaddr_in));
m->m_flags |= M_SKIP_FIREWALL;
m->m_flags &= ~M_IP_NEXTHOP;
m_tag_delete(m, fwd_tag);
if (ia != NULL)
ifa_free(&ia->ia_ifa);
goto again;
}
passout:
/* 127/8 must not appear on wire - RFC1122. */
if ((ntohl(ip->ip_dst.s_addr) >> IN_CLASSA_NSHIFT) == IN_LOOPBACKNET ||
(ntohl(ip->ip_src.s_addr) >> IN_CLASSA_NSHIFT) == IN_LOOPBACKNET) {
if ((ifp->if_flags & IFF_LOOPBACK) == 0) {
IPSTAT_INC(ips_badaddr);
error = EADDRNOTAVAIL;
goto bad;
}
}
m->m_pkthdr.csum_flags |= CSUM_IP;
if (m->m_pkthdr.csum_flags & CSUM_DELAY_DATA & ~ifp->if_hwassist) {
in_delayed_cksum(m);
m->m_pkthdr.csum_flags &= ~CSUM_DELAY_DATA;
}
#ifdef SCTP
if (m->m_pkthdr.csum_flags & CSUM_SCTP & ~ifp->if_hwassist) {
sctp_delayed_cksum(m, (uint32_t)(ip->ip_hl << 2));
m->m_pkthdr.csum_flags &= ~CSUM_SCTP;
}
#endif
/*
* If small enough for interface, or the interface will take
* care of the fragmentation for us, we can just send directly.
*/
if (ip_len <= mtu ||
(m->m_pkthdr.csum_flags & ifp->if_hwassist & CSUM_TSO) != 0 ||
((ip_off & IP_DF) == 0 && (ifp->if_hwassist & CSUM_FRAGMENT))) {
ip->ip_sum = 0;
if (m->m_pkthdr.csum_flags & CSUM_IP & ~ifp->if_hwassist) {
ip->ip_sum = in_cksum(m, hlen);
m->m_pkthdr.csum_flags &= ~CSUM_IP;
}
/*
* Record statistics for this interface address.
* With CSUM_TSO the byte/packet count will be slightly
* incorrect because we count the IP+TCP headers only
* once instead of for every generated packet.
*/
if (!(flags & IP_FORWARDING) && ia) {
if (m->m_pkthdr.csum_flags & CSUM_TSO)
ia->ia_ifa.if_opackets +=
m->m_pkthdr.len / m->m_pkthdr.tso_segsz;
else
ia->ia_ifa.if_opackets++;
ia->ia_ifa.if_obytes += m->m_pkthdr.len;
}
#ifdef MBUF_STRESS_TEST
if (mbuf_frag_size && m->m_pkthdr.len > mbuf_frag_size)
m = m_fragment(m, M_NOWAIT, mbuf_frag_size);
#endif
/*
* Reset layer specific mbuf flags
* to avoid confusing lower layers.
*/
m->m_flags &= ~(M_PROTOFLAGS);
error = (*ifp->if_output)(ifp, m,
(struct sockaddr *)dst, ro);
goto done;
}
/* Balk when DF bit is set or the interface didn't support TSO. */
if ((ip_off & IP_DF) || (m->m_pkthdr.csum_flags & CSUM_TSO)) {
error = EMSGSIZE;
IPSTAT_INC(ips_cantfrag);
goto bad;
}
/*
* Too large for interface; fragment if possible. If successful,
* on return, m will point to a list of packets to be sent.
*/
error = ip_fragment(ip, &m, mtu, ifp->if_hwassist);
if (error)
goto bad;
for (; m; m = m0) {
m0 = m->m_nextpkt;
m->m_nextpkt = 0;
if (error == 0) {
/* Record statistics for this interface address. */
if (ia != NULL) {
ia->ia_ifa.if_opackets++;
ia->ia_ifa.if_obytes += m->m_pkthdr.len;
}
/*
* Reset layer specific mbuf flags
* to avoid confusing upper layers.
*/
m->m_flags &= ~(M_PROTOFLAGS);
error = (*ifp->if_output)(ifp, m,
(struct sockaddr *)dst, ro);
} else
m_freem(m);
}
if (error == 0)
IPSTAT_INC(ips_fragmented);
done:
if (ro == &iproute)
RO_RTFREE(ro);
if (ia != NULL)
ifa_free(&ia->ia_ifa);
return (error);
bad:
m_freem(m);
goto done;
}
/*
* Create a chain of fragments which fit the given mtu. m_frag points to the
* mbuf to be fragmented; on return it points to the chain with the fragments.
* Return 0 if no error. If error, m_frag may contain a partially built
* chain of fragments that should be freed by the caller.
*
* if_hwassist_flags is the hw offload capabilities (see if_data.ifi_hwassist)
*/
int
ip_fragment(struct ip *ip, struct mbuf **m_frag, int mtu,
u_long if_hwassist_flags)
{
int error = 0;
int hlen = ip->ip_hl << 2;
int len = (mtu - hlen) & ~7; /* size of payload in each fragment */
int off;
struct mbuf *m0 = *m_frag; /* the original packet */
int firstlen;
struct mbuf **mnext;
int nfrags;
uint16_t ip_len, ip_off;
ip_len = ntohs(ip->ip_len);
ip_off = ntohs(ip->ip_off);
if (ip_off & IP_DF) { /* Fragmentation not allowed */
IPSTAT_INC(ips_cantfrag);
return EMSGSIZE;
}
/*
* Must be able to put at least 8 bytes per fragment.
*/
if (len < 8)
return EMSGSIZE;
/*
* If the interface will not calculate checksums on
* fragmented packets, then do it here.
*/
if (m0->m_pkthdr.csum_flags & CSUM_DELAY_DATA) {
in_delayed_cksum(m0);
m0->m_pkthdr.csum_flags &= ~CSUM_DELAY_DATA;
}
#ifdef SCTP
if (m0->m_pkthdr.csum_flags & CSUM_SCTP) {
sctp_delayed_cksum(m0, hlen);
m0->m_pkthdr.csum_flags &= ~CSUM_SCTP;
}
#endif
if (len > PAGE_SIZE) {
/*
* Fragment large datagrams such that each segment
* contains a multiple of PAGE_SIZE amount of data,
* plus headers. This enables a receiver to perform
* page-flipping zero-copy optimizations.
*
* XXX When does this help given that sender and receiver
* could have different page sizes, and also mtu could
* be less than the receiver's page size ?
*/
int newlen;
struct mbuf *m;
for (m = m0, off = 0; m && (off+m->m_len) <= mtu; m = m->m_next)
off += m->m_len;
/*
* firstlen (off - hlen) must be aligned on an
* 8-byte boundary
*/
if (off < hlen)
goto smart_frag_failure;
off = ((off - hlen) & ~7) + hlen;
newlen = (~PAGE_MASK) & mtu;
if ((newlen + sizeof (struct ip)) > mtu) {
/* we failed, go back the default */
smart_frag_failure:
newlen = len;
off = hlen + len;
}
len = newlen;
} else {
off = hlen + len;
}
firstlen = off - hlen;
mnext = &m0->m_nextpkt; /* pointer to next packet */
/*
* Loop through length of segment after first fragment,
* make new header and copy data of each part and link onto chain.
* Here, m0 is the original packet, m is the fragment being created.
* The fragments are linked off the m_nextpkt of the original
* packet, which after processing serves as the first fragment.
*/
for (nfrags = 1; off < ip_len; off += len, nfrags++) {
struct ip *mhip; /* ip header on the fragment */
struct mbuf *m;
int mhlen = sizeof (struct ip);
MGETHDR(m, M_NOWAIT, MT_DATA);
if (m == NULL) {
error = ENOBUFS;
IPSTAT_INC(ips_odropped);
goto done;
}
m->m_flags |= (m0->m_flags & M_MCAST) | M_FRAG;
/*
* In the first mbuf, leave room for the link header, then
* copy the original IP header including options. The payload
* goes into an additional mbuf chain returned by m_copym().
*/
m->m_data += max_linkhdr;
mhip = mtod(m, struct ip *);
*mhip = *ip;
if (hlen > sizeof (struct ip)) {
mhlen = ip_optcopy(ip, mhip) + sizeof (struct ip);
mhip->ip_v = IPVERSION;
mhip->ip_hl = mhlen >> 2;
}
m->m_len = mhlen;
/* XXX do we need to add ip_off below ? */
mhip->ip_off = ((off - hlen) >> 3) + ip_off;
if (off + len >= ip_len) { /* last fragment */
len = ip_len - off;
m->m_flags |= M_LASTFRAG;
} else
mhip->ip_off |= IP_MF;
mhip->ip_len = htons((u_short)(len + mhlen));
m->m_next = m_copym(m0, off, len, M_NOWAIT);
if (m->m_next == NULL) { /* copy failed */
m_free(m);
error = ENOBUFS; /* ??? */
IPSTAT_INC(ips_odropped);
goto done;
}
m->m_pkthdr.len = mhlen + len;
m->m_pkthdr.rcvif = NULL;
#ifdef MAC
mac_netinet_fragment(m0, m);
#endif
m->m_pkthdr.csum_flags = m0->m_pkthdr.csum_flags;
mhip->ip_off = htons(mhip->ip_off);
mhip->ip_sum = 0;
if (m->m_pkthdr.csum_flags & CSUM_IP & ~if_hwassist_flags) {
mhip->ip_sum = in_cksum(m, mhlen);
m->m_pkthdr.csum_flags &= ~CSUM_IP;
}
*mnext = m;
mnext = &m->m_nextpkt;
}
IPSTAT_ADD(ips_ofragments, nfrags);
/* set first marker for fragment chain */
m0->m_flags |= M_FIRSTFRAG | M_FRAG;
m0->m_pkthdr.csum_data = nfrags;
/*
* Update first fragment by trimming what's been copied out
* and updating header.
*/
m_adj(m0, hlen + firstlen - ip_len);
m0->m_pkthdr.len = hlen + firstlen;
ip->ip_len = htons((u_short)m0->m_pkthdr.len);
ip->ip_off = htons(ip_off | IP_MF);
ip->ip_sum = 0;
if (m0->m_pkthdr.csum_flags & CSUM_IP & ~if_hwassist_flags) {
ip->ip_sum = in_cksum(m0, hlen);
m0->m_pkthdr.csum_flags &= ~CSUM_IP;
}
done:
*m_frag = m0;
return error;
}
void
in_delayed_cksum(struct mbuf *m)
{
struct ip *ip;
uint16_t csum, offset, ip_len;
ip = mtod(m, struct ip *);
offset = ip->ip_hl << 2 ;
ip_len = ntohs(ip->ip_len);
csum = in_cksum_skip(m, ip_len, offset);
if (m->m_pkthdr.csum_flags & CSUM_UDP && csum == 0)
csum = 0xffff;
offset += m->m_pkthdr.csum_data; /* checksum offset */
if (offset + sizeof(u_short) > m->m_len) {
printf("delayed m_pullup, m->len: %d off: %d p: %d\n",
m->m_len, offset, ip->ip_p);
/*
* XXX
* this shouldn't happen, but if it does, the
* correct behavior may be to insert the checksum
* in the appropriate next mbuf in the chain.
*/
return;
}
*(u_short *)(m->m_data + offset) = csum;
}
/*
* IP socket option processing.
*/
int
ip_ctloutput(struct socket *so, struct sockopt *sopt)
{
struct inpcb *inp = sotoinpcb(so);
int error, optval;
error = optval = 0;
if (sopt->sopt_level != IPPROTO_IP) {
error = EINVAL;
if (sopt->sopt_level == SOL_SOCKET &&
sopt->sopt_dir == SOPT_SET) {
switch (sopt->sopt_name) {
case SO_REUSEADDR:
INP_WLOCK(inp);
if (IN_MULTICAST(ntohl(inp->inp_laddr.s_addr))) {
if ((so->so_options &
(SO_REUSEADDR | SO_REUSEPORT)) != 0)
inp->inp_flags2 |= INP_REUSEPORT;
else
inp->inp_flags2 &= ~INP_REUSEPORT;
}
INP_WUNLOCK(inp);
error = 0;
break;
case SO_REUSEPORT:
INP_WLOCK(inp);
if ((so->so_options & SO_REUSEPORT) != 0)
inp->inp_flags2 |= INP_REUSEPORT;
else
inp->inp_flags2 &= ~INP_REUSEPORT;
INP_WUNLOCK(inp);
error = 0;
break;
case SO_SETFIB:
INP_WLOCK(inp);
inp->inp_inc.inc_fibnum = so->so_fibnum;
INP_WUNLOCK(inp);
error = 0;
break;
default:
break;
}
}
return (error);
}
switch (sopt->sopt_dir) {
case SOPT_SET:
switch (sopt->sopt_name) {
case IP_OPTIONS:
#ifdef notyet
case IP_RETOPTS:
#endif
{
struct mbuf *m;
if (sopt->sopt_valsize > MLEN) {
error = EMSGSIZE;
break;
}
MGET(m, sopt->sopt_td ? M_WAITOK : M_NOWAIT, MT_DATA);
if (m == NULL) {
error = ENOBUFS;
break;
}
m->m_len = sopt->sopt_valsize;
error = sooptcopyin(sopt, mtod(m, char *), m->m_len,
m->m_len);
if (error) {
m_free(m);
break;
}
INP_WLOCK(inp);
error = ip_pcbopts(inp, sopt->sopt_name, m);
INP_WUNLOCK(inp);
return (error);
}
case IP_BINDANY:
if (sopt->sopt_td != NULL) {
error = priv_check(sopt->sopt_td,
PRIV_NETINET_BINDANY);
if (error)
break;
}
/* FALLTHROUGH */
case IP_TOS:
case IP_TTL:
case IP_MINTTL:
case IP_RECVOPTS:
case IP_RECVRETOPTS:
case IP_RECVDSTADDR:
case IP_RECVTTL:
case IP_RECVIF:
case IP_FAITH:
case IP_ONESBCAST:
case IP_DONTFRAG:
case IP_RECVTOS:
error = sooptcopyin(sopt, &optval, sizeof optval,
sizeof optval);
if (error)
break;
switch (sopt->sopt_name) {
case IP_TOS:
inp->inp_ip_tos = optval;
break;