summaryrefslogtreecommitdiffstats
path: root/sys/netinet/ip_fastfwd.c
blob: 78e46dda39a757fbba9ed0463b28f722bf452122 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
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
/*
 * Copyright (c) 2003 Andre Oppermann, Internet Business Solutions AG
 * 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. The name of the author may not be used to endorse or promote
 *    products derived from this software without specific prior written
 *    permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 * $FreeBSD$
 */

/*
 * ip_fastforward gets its speed from processing the forwarded packet to
 * completion (if_output on the other side) without any queues or netisr's.
 * The receiving interface DMAs the packet into memory, the upper half of
 * driver calls ip_fastforward, we do our routing table lookup and directly
 * send it off to the outgoing interface which DMAs the packet to the
 * network card. The only part of the packet we touch with the CPU is the
 * IP header (unless there are complex firewall rules touching other parts
 * of the packet, but that is up to you). We are essentially limited by bus
 * bandwidth and how fast the network card/driver can set up receives and
 * transmits.
 *
 * We handle basic errors, ip header errors, checksum errors,
 * destination unreachable, fragmentation and fragmentation needed and
 * report them via icmp to the sender.
 *
 * Else if something is not pure IPv4 unicast forwarding we fall back to
 * the normal ip_input processing path. We should only be called from
 * interfaces connected to the outside world.
 *
 * Firewalling is fully supported including divert, ipfw fwd and ipfilter
 * ipnat and address rewrite.
 *
 * IPSEC is not supported if this host is a tunnel broker. IPSEC is
 * supported for connections to/from local host.
 *
 * We try to do the least expensive (in CPU ops) checks and operations
 * first to catch junk with as little overhead as possible.
 * 
 * We take full advantage of hardware support for ip checksum and
 * fragmentation offloading.
 *
 * We don't do ICMP redirect in the fast forwarding path. I have had my own
 * cases where two core routers with Zebra routing suite would send millions
 * ICMP redirects to connected hosts if the router to dest was not the default
 * gateway. In one case it was filling the routing table of a host with close
 * 300'000 cloned redirect entries until it ran out of kernel memory. However
 * the networking code proved very robust and it didn't crash or went ill
 * otherwise.
 */

/*
 * Many thanks to Matt Thomas of NetBSD for basic structure of ip_flow.c which
 * is being followed here.
 */

#include "opt_ipfw.h"
#include "opt_ipdn.h"
#include "opt_ipdivert.h"
#include "opt_ipfilter.h"
#include "opt_ipstealth.h"
#include "opt_pfil_hooks.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/sysctl.h>

#include <net/pfil.h>
#include <net/if.h>
#include <net/if_types.h>
#include <net/if_var.h>
#include <net/if_dl.h>
#include <net/route.h>

#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
#include <netinet/ip_var.h>
#include <netinet/ip_icmp.h>

#include <machine/in_cksum.h>

#include <netinet/ip_fw.h>
#include <netinet/ip_divert.h>
#include <netinet/ip_dummynet.h>

static int ipfastforward_active = 0;
SYSCTL_INT(_net_inet_ip, OID_AUTO, fastforwarding, CTLFLAG_RW,
    &ipfastforward_active, 0, "Enable fast IP forwarding");

static struct sockaddr_in *
ip_findroute(struct route *ro, struct in_addr dest, struct mbuf *m)
{
	struct sockaddr_in *dst;
	struct rtentry *rt;

	/*
	 * Find route to destination.
	 */
	bzero(ro, sizeof(*ro));
	dst = (struct sockaddr_in *)&ro->ro_dst;
	dst->sin_family = AF_INET;
	dst->sin_len = sizeof(*dst);
	dst->sin_addr.s_addr = dest.s_addr;
	rtalloc_ign(ro, RTF_CLONING);

	/*
	 * Route there and interface still up?
	 */
	rt = ro->ro_rt;
	if (rt && (rt->rt_flags & RTF_UP) &&
	    (rt->rt_ifp->if_flags & IFF_UP) &&
	    (rt->rt_ifp->if_flags & IFF_RUNNING)) {
		if (rt->rt_flags & RTF_GATEWAY)
			dst = (struct sockaddr_in *)rt->rt_gateway;
	} else {
		ipstat.ips_noroute++;
		ipstat.ips_cantforward++;
		if (rt)
			RTFREE(rt);
		icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_HOST, 0, NULL);
		return NULL;
	}
	return dst;
}

/*
 * Try to forward a packet based on the destination address.
 * This is a fast path optimized for the plain forwarding case.
 * If the packet is handled (and consumed) here then we return 1;
 * otherwise 0 is returned and the packet should be delivered
 * to ip_input for full processing.
 */
int
ip_fastforward(struct mbuf *m)
{
	struct ip *ip;
	struct mbuf *m0 = NULL;
#ifdef IPDIVERT
	struct ip *tip;
	struct mbuf *clone = NULL;
#endif
	struct route ro;
	struct sockaddr_in *dst = NULL;
	struct in_ifaddr *ia = NULL;
	struct ifaddr *ifa = NULL;
	struct ifnet *ifp;
	struct ip_fw_args args;
	struct in_addr odest, dest;
	u_short sum, ip_len;
	int error = 0;
	int hlen, ipfw, mtu;

	/*
	 * Are we active and forwarding packets?
	 */
	if (!ipfastforward_active || !ipforwarding)
		return 0;

	M_ASSERTVALID(m);
	M_ASSERTPKTHDR(m);

	ro.ro_rt = NULL;

	/*
	 * Step 1: check for packet drop conditions (and sanity checks)
	 */

	/*
	 * Is entire packet big enough?
	 */
	if (m->m_pkthdr.len < sizeof(struct ip)) {
		ipstat.ips_tooshort++;
		goto drop;
	}

	/*
	 * Is first mbuf large enough for ip header and is header present?
	 */
	if (m->m_len < sizeof (struct ip) &&
	   (m = m_pullup(m, sizeof (struct ip))) == 0) {
		ipstat.ips_toosmall++;
		goto drop;
	}

	ip = mtod(m, struct ip *);

	/*
	 * Is it IPv4?
	 */
	if (ip->ip_v != IPVERSION) {
		ipstat.ips_badvers++;
		goto drop;
	}

	/*
	 * Is IP header length correct and is it in first mbuf?
	 */
	hlen = ip->ip_hl << 2;
	if (hlen < sizeof(struct ip)) {	/* minimum header length */
		ipstat.ips_badlen++;
		goto drop;
	}
	if (hlen > m->m_len) {
		if ((m = m_pullup(m, hlen)) == 0) {
			ipstat.ips_badhlen++;
			goto drop;
		}
		ip = mtod(m, struct ip *);
	}

	/*
	 * Checksum correct?
	 */
	if (m->m_pkthdr.csum_flags & CSUM_IP_CHECKED)
		sum = !(m->m_pkthdr.csum_flags & CSUM_IP_VALID);
	else {
		if (hlen == sizeof(struct ip))
			sum = in_cksum_hdr(ip);
		else
			sum = in_cksum(m, hlen);
	}
	if (sum) {
		ipstat.ips_badsum++;
		goto drop;
	}
	m->m_pkthdr.csum_flags |= (CSUM_IP_CHECKED | CSUM_IP_VALID);

	ip_len = ntohs(ip->ip_len);

	/*
	 * Is IP length longer than packet we have got?
	 */
	if (m->m_pkthdr.len < ip_len) {
		ipstat.ips_tooshort++;
		goto drop;
	}

	/*
	 * Is packet longer than IP header tells us? If yes, truncate packet.
	 */
	if (m->m_pkthdr.len > ip_len) {
		if (m->m_len == m->m_pkthdr.len) {
			m->m_len = ip_len;
			m->m_pkthdr.len = ip_len;
		} else
			m_adj(m, ip_len - m->m_pkthdr.len);
	}

	/*
	 * Is packet from or to 127/8?
	 */
	if ((ntohl(ip->ip_dst.s_addr) >> IN_CLASSA_NSHIFT) == IN_LOOPBACKNET ||
	    (ntohl(ip->ip_src.s_addr) >> IN_CLASSA_NSHIFT) == IN_LOOPBACKNET) {
		ipstat.ips_badaddr++;
		goto drop;
	}

#ifdef ALTQ
	/*
	 * Is packet dropped by traffic conditioner?
	 */
	if (altq_input != NULL && (*altq_input)(m, AF_INET) == 0)
		return 1;
#endif

	/*
	 * Step 2: fallback conditions to normal ip_input path processing
	 */

	/*
	 * Only IP packets without options
	 */
	if (ip->ip_hl != (sizeof(struct ip) >> 2)) {
		if (ip_doopts == 1)
			return 0;
		else if (ip_doopts == 2) {
			icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_FILTER_PROHIB,
				0, NULL);
			return 1;
		}
		/* else ignore IP options and continue */
	}

	/*
	 * Only unicast IP, not from loopback, no L2 or IP broadcast,
	 * no multicast, no INADDR_ANY
	 *
	 * XXX: Probably some of these checks could be direct drop
	 * conditions.  However it is not clear whether there are some
	 * hacks or obscure behaviours which make it neccessary to
	 * let ip_input handle it.  We play safe here and let ip_input
	 * deal with it until it is proven that we can directly drop it.
	 */
	if ((m->m_pkthdr.rcvif->if_flags & IFF_LOOPBACK) ||
	    ntohl(ip->ip_src.s_addr) == (u_long)INADDR_BROADCAST ||
	    ntohl(ip->ip_dst.s_addr) == (u_long)INADDR_BROADCAST ||
	    IN_MULTICAST(ntohl(ip->ip_src.s_addr)) ||
	    IN_MULTICAST(ntohl(ip->ip_dst.s_addr)) ||
	    ip->ip_dst.s_addr == INADDR_ANY )
		return 0;

	/*
	 * Is it for a local address on this host?
	 */
	if (in_localip(ip->ip_dst))
		return 0;

	/*
	 * Or is it for a local IP broadcast address on this host?
	 */
	if ((m->m_flags & M_BCAST) &&
	    (m->m_pkthdr.rcvif->if_flags & IFF_BROADCAST)) {
	        TAILQ_FOREACH(ifa, &m->m_pkthdr.rcvif->if_addrhead, ifa_link) {
			if (ifa->ifa_addr->sa_family != AF_INET)
				continue;
			ia = ifatoia(ifa);
			if (ia->ia_netbroadcast.s_addr == ip->ip_dst.s_addr)
				return 0;
			if (satosin(&ia->ia_broadaddr)->sin_addr.s_addr ==
			    ip->ip_dst.s_addr)
				return 0;
		}
	}
	ipstat.ips_total++;

	/*
	 * Step 3: incoming packet firewall processing
	 */

	/*
	 * Convert to host representation
	 */
	ip->ip_len = ntohs(ip->ip_len);
	ip->ip_off = ntohs(ip->ip_off);

	odest.s_addr = dest.s_addr = ip->ip_dst.s_addr;
#ifdef PFIL_HOOKS
	/*
	 * Run through list of ipfilter hooks for input packets
	 */
	if (pfil_run_hooks(&inet_pfil_hook, &m, m->m_pkthdr.rcvif, PFIL_IN) ||
	    m == NULL)
		return 1;

	M_ASSERTVALID(m);
	M_ASSERTPKTHDR(m);

	ip = mtod(m, struct ip *);	/* m may have changed by pfil hook */
	dest.s_addr = ip->ip_dst.s_addr;
#endif

	/*
	 * Run through ipfw for input packets
	 */
	if (fw_enable && IPFW_LOADED) {
		bzero(&args, sizeof(args));
		args.m = m;

		ipfw = ip_fw_chk_ptr(&args);
		m = args.m;

		M_ASSERTVALID(m);
		M_ASSERTPKTHDR(m);

		/*
		 * Packet denied, drop it
		 */
		if ((ipfw & IP_FW_PORT_DENY_FLAG) || m == NULL)
			goto drop;
		/*
		 * Send packet to the appropriate pipe
		 */
		if (DUMMYNET_LOADED && (ipfw & IP_FW_PORT_DYNT_FLAG) != 0) {
			ip_dn_io_ptr(m, ipfw & 0xffff, DN_TO_IP_IN, &args);
			return 1;
		}
#ifdef IPDIVERT
		/*
		 * Divert packet
		 */
		if (ipfw != 0 && (ipfw & IP_FW_PORT_DYNT_FLAG) == 0) {
			/*
			 * See if this is a fragment
			 */
			if (ip->ip_off & (IP_MF | IP_OFFMASK))
				goto droptoours;
			/*
			 * Tee packet
			 */
			if ((ipfw & IP_FW_PORT_TEE_FLAG) != 0)
				clone = divert_clone(m);
			else
				clone = m;
			if (clone == NULL)
				goto passin;

			/*
			 * Delayed checksums are not compatible
			 */
			if (m->m_pkthdr.csum_flags & CSUM_DELAY_DATA) {
				in_delayed_cksum(m);
				m->m_pkthdr.csum_flags &= ~CSUM_DELAY_DATA;
			}
			/*
			 * Restore packet header fields to original values
			 */
			tip = mtod(m, struct ip *);
			tip->ip_len = htons(tip->ip_len);
			tip->ip_off = htons(tip->ip_off);
			/*
			 * Deliver packet to divert input routine
			 */
			divert_packet(m, 0);
			/*
			 * If this was not tee, we are done
			 */
			m = clone;
			if ((ipfw & IP_FW_PORT_TEE_FLAG) == 0)
				return 1;
			/* Continue if it was tee */
			goto passin;
		}
#endif
		if (ipfw == 0 && args.next_hop != NULL) {
			dest.s_addr = args.next_hop->sin_addr.s_addr;
			goto passin;
		}
		/*
		 * Let through or not?
		 */
		if (ipfw != 0)
			goto drop;
	}
passin:
	ip = mtod(m, struct ip *);	/* if m changed during fw processing */

	/*
	 * Destination address changed?
	 */
	if (odest.s_addr != dest.s_addr) {
		/*
		 * Is it now for a local address on this host?
		 */
		if (in_localip(dest))
			goto forwardlocal;
		/*
		 * Go on with new destination address
		 */
	}

	/*
	 * Step 4: decrement TTL and look up route
	 */

	/*
	 * Check TTL
	 */
#ifdef IPSTEALTH
	if (!ipstealth) {
#endif
	if (ip->ip_ttl <= IPTTLDEC) {
		icmp_error(m, ICMP_TIMXCEED, ICMP_TIMXCEED_INTRANS, 0, NULL);
		return 1;
	}

	/*
	 * Decrement the TTL and incrementally change the checksum.
	 * Don't bother doing this with hw checksum offloading.
	 */
	ip->ip_ttl -= IPTTLDEC;
	if (ip->ip_sum >= (u_int16_t) ~htons(IPTTLDEC << 8))
		ip->ip_sum -= ~htons(IPTTLDEC << 8);
	else
		ip->ip_sum += htons(IPTTLDEC << 8);
#ifdef IPSTEALTH
	}
#endif

	/*
	 * Find route to destination.
	 */
	if ((dst = ip_findroute(&ro, dest, m)) == NULL)
		return 1;	/* icmp unreach already sent */
	ifp = ro.ro_rt->rt_ifp;

	/*
	 * Step 5: outgoing firewall packet processing
	 */

#ifdef PFIL_HOOKS
	/*
	 * Run through list of hooks for output packets.
	 */
	if (pfil_run_hooks(&inet_pfil_hook, &m, ifp, PFIL_OUT) || m == NULL) {
		goto consumed;
	}

	M_ASSERTVALID(m);
	M_ASSERTPKTHDR(m);

	ip = mtod(m, struct ip *);
	dest.s_addr = ip->ip_dst.s_addr;
#endif
	if (fw_enable && IPFW_LOADED && !args.next_hop) {
		bzero(&args, sizeof(args));
		args.m = m;
		args.oif = ifp;

		ipfw = ip_fw_chk_ptr(&args);
		m = args.m;

		M_ASSERTVALID(m);
		M_ASSERTPKTHDR(m);

		if ((ipfw & IP_FW_PORT_DENY_FLAG) || m == NULL)
			goto drop;

		if (DUMMYNET_LOADED && (ipfw & IP_FW_PORT_DYNT_FLAG) != 0) {
			/*
			 * XXX note: if the ifp or rt entry are deleted
			 * while a pkt is in dummynet, we are in trouble!
			 */
			args.ro = &ro;		/* dummynet does not save it */
			args.dst = dst;

			ip_dn_io_ptr(m, ipfw & 0xffff, DN_TO_IP_OUT, &args);
			goto consumed;
		}
#ifdef IPDIVERT
		if (ipfw != 0 && (ipfw & IP_FW_PORT_DYNT_FLAG) == 0) {
			/*
			 * See if this is a fragment
			 */
			if (ip->ip_off & (IP_MF | IP_OFFMASK))
				goto droptoours;
			/*
			 * Tee packet
			 */
			if ((ipfw & IP_FW_PORT_TEE_FLAG) != 0)
				clone = divert_clone(m);
			else
				clone = m;
			if (clone == NULL)
				goto passout;

			/*
			 * Delayed checksums are not compatible with divert
			 */
			if (m->m_pkthdr.csum_flags & CSUM_DELAY_DATA) {
				in_delayed_cksum(m);
				m->m_pkthdr.csum_flags &= ~CSUM_DELAY_DATA;
			}
			/*
			 * Restore packet header fields to original values
			 */
			tip = mtod(m, struct ip *);
			tip->ip_len = htons(tip->ip_len);
			tip->ip_off = htons(tip->ip_off);
			/*
			 * Deliver packet to divert input routine
			 */
			divert_packet(m, 0);
			/*
			 * If this was not tee, we are done
			 */
			m = clone;
			if ((ipfw & IP_FW_PORT_TEE_FLAG) == 0) {
				goto consumed;
			}
			/* Continue if it was tee */
			goto passout;
		}
#endif
		if (ipfw == 0 && args.next_hop != NULL) {
			dest.s_addr = args.next_hop->sin_addr.s_addr;
			goto passout;
		}
		/*
		 * Let through or not?
		 */
		if (ipfw != 0)
			goto drop;
	}
passout:
	ip = mtod(m, struct ip *);

	/*
	 * Destination address changed?
	 */
	if (odest.s_addr != dest.s_addr) {
		/*
		 * Is it now for a local address on this host?
		 */
		if (in_localip(dest)) {
forwardlocal:
			if (args.next_hop) {
				struct m_tag *mtag = m_tag_get(
				    PACKET_TAG_IPFORWARD,
				    sizeof(struct sockaddr_in *),
				    M_NOWAIT);
				if (mtag == NULL) {
					goto drop;
				}
				*(struct sockaddr_in **)(mtag+1) =
				    args.next_hop;
				m_tag_prepend(m, mtag);
			}
#ifdef IPDIVERT
droptoours:	/* Used for DIVERT */
#endif
			/* for ip_input */
			m->m_flags |= M_FASTFWD_OURS;

			/* ip still points to the real packet */
			ip->ip_len = htons(ip->ip_len);
			ip->ip_off = htons(ip->ip_off);

			/*
			 * Return packet for processing by ip_input
			 */
			if (ro.ro_rt)
				RTFREE(ro.ro_rt);
			return 0;
		}
		/*
		 * Redo route lookup with new destination address
		 */
		RTFREE(ro.ro_rt);
		if ((dst = ip_findroute(&ro, dest, m)) == NULL)
			return 1;	/* icmp unreach already sent */
		ifp = ro.ro_rt->rt_ifp;
	}

	/*
	 * Step 6: send off the packet
	 */

	/*
	 * Check if route is dampned (when ARP is unable to resolve)
	 */
	if ((ro.ro_rt->rt_flags & RTF_REJECT) &&
	    ro.ro_rt->rt_rmx.rmx_expire >= time_second) {
		icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_HOST, 0, NULL);
		goto consumed;
	}

#ifndef ALTQ
	/*
	 * Check if there is enough space in the interface queue
	 */
	if ((ifp->if_snd.ifq_len + ip->ip_len / ifp->if_mtu + 1) >=
	    ifp->if_snd.ifq_maxlen) {
		ipstat.ips_odropped++;
		/* would send source quench here but that is depreciated */
		goto drop;
	}
#endif

	/*
	 * Check if media link state of interface is not down
	 */
	if (ifp->if_link_state == LINK_STATE_DOWN) {
		icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_HOST, 0, NULL);
		goto consumed;
	}

	/*
	 * Check if packet fits MTU or if hardware will fragement for us
	 */
	if (ro.ro_rt->rt_rmx.rmx_mtu)
		mtu = min(ro.ro_rt->rt_rmx.rmx_mtu, ifp->if_mtu);
	else
		mtu = ifp->if_mtu;

	if (ip->ip_len <= mtu ||
	    (ifp->if_hwassist & CSUM_FRAGMENT && (ip->ip_off & IP_DF) == 0)) {
		/*
		 * Restore packet header fields to original values
		 */
		ip->ip_len = htons(ip->ip_len);
		ip->ip_off = htons(ip->ip_off);
		/*
		 * Send off the packet via outgoing interface
		 */
		error = (*ifp->if_output)(ifp, m,
				(struct sockaddr *)dst, ro.ro_rt);
	} else {
		/*
		 * Handle EMSGSIZE with icmp reply needfrag for TCP MTU discovery
		 */
		if (ip->ip_off & IP_DF) {
			ipstat.ips_cantfrag++;
			icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_NEEDFRAG,
				0, ifp);
			goto consumed;
		} else {
			/*
			 * We have to fragement the packet
			 */
			m->m_pkthdr.csum_flags |= CSUM_IP;
			/*
			 * ip_fragment expects ip_len and ip_off in host byte
			 * order but returns all packets in network byte order
			 */
			if (ip_fragment(ip, &m, mtu, ifp->if_hwassist,
					(~ifp->if_hwassist & CSUM_DELAY_IP))) {
				goto drop;
			}
			KASSERT(m != NULL, ("null mbuf and no error"));
			/*
			 * Send off the fragments via outgoing interface
			 */
			error = 0;
			do {
				m0 = m->m_nextpkt;
				m->m_nextpkt = NULL;

				error = (*ifp->if_output)(ifp, m,
					(struct sockaddr *)dst, ro.ro_rt);
				if (error)
					break;
			} while ((m = m0) != NULL);
			if (error) {
				/* Reclaim remaining fragments */
				for (; m; m = m0) {
					m0 = m->m_nextpkt;
					m->m_nextpkt = NULL;
					m_freem(m);
				}
			} else
				ipstat.ips_fragmented++;
		}
	}

	if (error != 0)
		ipstat.ips_odropped++;
	else {
		ro.ro_rt->rt_rmx.rmx_pksent++;
		ipstat.ips_forward++;
		ipstat.ips_fastforward++;
	}
consumed:
	RTFREE(ro.ro_rt);
	return 1;
drop:
	if (m)
		m_freem(m);
	if (ro.ro_rt)
		RTFREE(ro.ro_rt);
	return 1;
}
OpenPOWER on IntegriCloud