forked from openvswitch/ovs
-
Notifications
You must be signed in to change notification settings - Fork 0
/
conntrack.c
3299 lines (2918 loc) · 111 KB
/
conntrack.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) 2015, 2016, 2017 Nicira, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at:
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#include <config.h>
#include <ctype.h>
#include <errno.h>
#include <sys/types.h>
#include <netinet/in.h>
#include <netinet/icmp6.h>
#include <string.h>
#include "bitmap.h"
#include "conntrack.h"
#include "conntrack-private.h"
#include "coverage.h"
#include "csum.h"
#include "ct-dpif.h"
#include "dp-packet.h"
#include "flow.h"
#include "netdev.h"
#include "odp-netlink.h"
#include "openvswitch/hmap.h"
#include "openvswitch/vlog.h"
#include "ovs-rcu.h"
#include "ovs-thread.h"
#include "openvswitch/poll-loop.h"
#include "random.h"
#include "timeval.h"
VLOG_DEFINE_THIS_MODULE(conntrack);
COVERAGE_DEFINE(conntrack_full);
COVERAGE_DEFINE(conntrack_long_cleanup);
struct conn_lookup_ctx {
struct conn_key key;
struct conn *conn;
uint32_t hash;
bool reply;
bool icmp_related;
};
enum ftp_ctl_pkt {
/* Control packets with address and/or port specifiers. */
CT_FTP_CTL_INTEREST,
/* Control packets without address and/or port specifiers. */
CT_FTP_CTL_OTHER,
CT_FTP_CTL_INVALID,
};
enum ct_alg_mode {
CT_FTP_MODE_ACTIVE,
CT_FTP_MODE_PASSIVE,
CT_TFTP_MODE,
};
enum ct_alg_ctl_type {
CT_ALG_CTL_NONE,
CT_ALG_CTL_FTP,
CT_ALG_CTL_TFTP,
/* SIP is not enabled through Openflow and presently only used as
* an example of an alg that allows a wildcard src ip. */
CT_ALG_CTL_SIP,
};
static bool conn_key_extract(struct conntrack *, struct dp_packet *,
ovs_be16 dl_type, struct conn_lookup_ctx *,
uint16_t zone);
static uint32_t conn_key_hash(const struct conn_key *, uint32_t basis);
static void conn_key_reverse(struct conn_key *);
static void conn_key_lookup(struct conntrack_bucket *ctb,
struct conn_lookup_ctx *ctx,
long long now);
static bool valid_new(struct dp_packet *pkt, struct conn_key *);
static struct conn *new_conn(struct conntrack_bucket *, struct dp_packet *pkt,
struct conn_key *, long long now);
static void delete_conn(struct conn *);
static enum ct_update_res conn_update(struct conn *,
struct conntrack_bucket *ctb,
struct dp_packet *, bool reply,
long long now);
static bool conn_expired(struct conn *, long long now);
static void set_mark(struct dp_packet *, struct conn *,
uint32_t val, uint32_t mask);
static void set_label(struct dp_packet *, struct conn *,
const struct ovs_key_ct_labels *val,
const struct ovs_key_ct_labels *mask);
static void *clean_thread_main(void *f_);
static struct nat_conn_key_node *
nat_conn_keys_lookup(struct hmap *nat_conn_keys,
const struct conn_key *key,
uint32_t basis);
static bool
nat_conn_keys_insert(struct hmap *nat_conn_keys,
const struct conn *nat_conn,
uint32_t hash_basis);
static void
nat_conn_keys_remove(struct hmap *nat_conn_keys,
const struct conn_key *key,
uint32_t basis);
static bool
nat_select_range_tuple(struct conntrack *ct, const struct conn *conn,
struct conn *nat_conn);
static uint8_t
reverse_icmp_type(uint8_t type);
static uint8_t
reverse_icmp6_type(uint8_t type);
static inline bool
extract_l3_ipv4(struct conn_key *key, const void *data, size_t size,
const char **new_data, bool validate_checksum);
static inline bool
extract_l3_ipv6(struct conn_key *key, const void *data, size_t size,
const char **new_data);
static struct alg_exp_node *
expectation_lookup(struct hmap *alg_expectations, const struct conn_key *key,
uint32_t basis, bool src_ip_wc);
static int
repl_ftp_v4_addr(struct dp_packet *pkt, ovs_be32 v4_addr_rep,
char *ftp_data_v4_start,
size_t addr_offset_from_ftp_data_start);
static enum ftp_ctl_pkt
process_ftp_ctl_v4(struct conntrack *ct,
struct dp_packet *pkt,
const struct conn *conn_for_expectation,
ovs_be32 *v4_addr_rep,
char **ftp_data_v4_start,
size_t *addr_offset_from_ftp_data_start);
static enum ftp_ctl_pkt
detect_ftp_ctl_type(const struct conn_lookup_ctx *ctx,
struct dp_packet *pkt);
static void
expectation_clean(struct conntrack *ct, const struct conn_key *master_key,
uint32_t basis);
static struct ct_l4_proto *l4_protos[] = {
[IPPROTO_TCP] = &ct_proto_tcp,
[IPPROTO_UDP] = &ct_proto_other,
[IPPROTO_ICMP] = &ct_proto_icmp4,
[IPPROTO_ICMPV6] = &ct_proto_icmp6,
};
static void
handle_ftp_ctl(struct conntrack *ct, const struct conn_lookup_ctx *ctx,
struct dp_packet *pkt,
const struct conn *conn_for_expectation,
long long now, enum ftp_ctl_pkt ftp_ctl, bool nat);
static void
handle_tftp_ctl(struct conntrack *ct,
const struct conn_lookup_ctx *ctx OVS_UNUSED,
struct dp_packet *pkt,
const struct conn *conn_for_expectation,
long long now OVS_UNUSED,
enum ftp_ctl_pkt ftp_ctl OVS_UNUSED, bool nat OVS_UNUSED);
typedef void (*alg_helper)(struct conntrack *ct,
const struct conn_lookup_ctx *ctx,
struct dp_packet *pkt,
const struct conn *conn_for_expectation,
long long now, enum ftp_ctl_pkt ftp_ctl,
bool nat);
static alg_helper alg_helpers[] = {
[CT_ALG_CTL_NONE] = NULL,
[CT_ALG_CTL_FTP] = handle_ftp_ctl,
[CT_ALG_CTL_TFTP] = handle_tftp_ctl,
};
long long ct_timeout_val[] = {
#define CT_TIMEOUT(NAME, VAL) [CT_TM_##NAME] = VAL,
CT_TIMEOUTS
#undef CT_TIMEOUT
};
/* The maximum TCP or UDP port number. */
#define CT_MAX_L4_PORT 65535
/* String buffer used for parsing FTP string messages.
* This is sized about twice what is needed to leave some
* margin of error. */
#define LARGEST_FTP_MSG_OF_INTEREST 128
/* FTP port string used in active mode. */
#define FTP_PORT_CMD "PORT"
/* FTP pasv string used in passive mode. */
#define FTP_PASV_REPLY_CODE "227"
/* Maximum decimal digits for port in FTP command.
* The port is represented as two 3 digit numbers with the
* high part a multiple of 256. */
#define MAX_FTP_PORT_DGTS 3
/* FTP extension EPRT string used for active mode. */
#define FTP_EPRT_CMD "EPRT"
/* FTP extension EPSV string used for passive mode. */
#define FTP_EPSV_REPLY "EXTENDED PASSIVE"
/* Maximum decimal digits for port in FTP extended command. */
#define MAX_EXT_FTP_PORT_DGTS 5
/* FTP extended command code for IPv6. */
#define FTP_AF_V6 '2'
/* Used to indicate a wildcard L4 source port number for ALGs.
* This is used for port numbers that we cannot predict in
* expectations. */
#define ALG_WC_SRC_PORT 0
/* If the total number of connections goes above this value, no new connections
* are accepted; this is for CT_CONN_TYPE_DEFAULT connections. */
#define DEFAULT_N_CONN_LIMIT 3000000
/* Does a member by member comparison of two conn_keys; this
* function must be kept in sync with struct conn_key; returns 0
* if the keys are equal or 1 if the keys are not equal. */
static int
conn_key_cmp(const struct conn_key *key1, const struct conn_key *key2)
{
if (!memcmp(&key1->src.addr, &key2->src.addr, sizeof key1->src.addr) &&
!memcmp(&key1->dst.addr, &key2->dst.addr, sizeof key1->dst.addr) &&
(key1->src.icmp_id == key2->src.icmp_id) &&
(key1->src.icmp_type == key2->src.icmp_type) &&
(key1->src.icmp_code == key2->src.icmp_code) &&
(key1->dst.icmp_id == key2->dst.icmp_id) &&
(key1->dst.icmp_type == key2->dst.icmp_type) &&
(key1->dst.icmp_code == key2->dst.icmp_code) &&
(key1->dl_type == key2->dl_type) &&
(key1->zone == key2->zone) &&
(key1->nw_proto == key2->nw_proto)) {
return 0;
}
return 1;
}
static void
ct_print_conn_info(const struct conn *c, const char *log_msg,
enum vlog_level vll, bool force, bool rl_on)
{
#define CT_VLOG(RL_ON, LEVEL, ...) \
do { \
if (RL_ON) { \
static struct vlog_rate_limit rl_ = VLOG_RATE_LIMIT_INIT(5, 5); \
vlog_rate_limit(&this_module, LEVEL, &rl_, __VA_ARGS__); \
} else { \
vlog(&this_module, LEVEL, __VA_ARGS__); \
} \
} while (0)
if (OVS_UNLIKELY(force || vlog_is_enabled(&this_module, vll))) {
if (c->key.dl_type == htons(ETH_TYPE_IP)) {
CT_VLOG(rl_on, vll, "%s: src ip "IP_FMT" dst ip "IP_FMT" rev src "
"ip "IP_FMT" rev dst ip "IP_FMT" src/dst ports "
"%"PRIu16"/%"PRIu16" rev src/dst ports "
"%"PRIu16"/%"PRIu16" zone/rev zone "
"%"PRIu16"/%"PRIu16" nw_proto/rev nw_proto "
"%"PRIu8"/%"PRIu8, log_msg,
IP_ARGS(c->key.src.addr.ipv4_aligned),
IP_ARGS(c->key.dst.addr.ipv4_aligned),
IP_ARGS(c->rev_key.src.addr.ipv4_aligned),
IP_ARGS(c->rev_key.dst.addr.ipv4_aligned),
ntohs(c->key.src.port), ntohs(c->key.dst.port),
ntohs(c->rev_key.src.port), ntohs(c->rev_key.dst.port),
c->key.zone, c->rev_key.zone, c->key.nw_proto,
c->rev_key.nw_proto);
} else {
char ip6_s[INET6_ADDRSTRLEN];
inet_ntop(AF_INET6, &c->key.src.addr.ipv6, ip6_s, sizeof ip6_s);
char ip6_d[INET6_ADDRSTRLEN];
inet_ntop(AF_INET6, &c->key.dst.addr.ipv6, ip6_d, sizeof ip6_d);
char ip6_rs[INET6_ADDRSTRLEN];
inet_ntop(AF_INET6, &c->rev_key.src.addr.ipv6, ip6_rs,
sizeof ip6_rs);
char ip6_rd[INET6_ADDRSTRLEN];
inet_ntop(AF_INET6, &c->rev_key.dst.addr.ipv6, ip6_rd,
sizeof ip6_rd);
CT_VLOG(rl_on, vll, "%s: src ip %s dst ip %s rev src ip %s"
" rev dst ip %s src/dst ports %"PRIu16"/%"PRIu16
" rev src/dst ports %"PRIu16"/%"PRIu16" zone/rev zone "
"%"PRIu16"/%"PRIu16" nw_proto/rev nw_proto "
"%"PRIu8"/%"PRIu8, log_msg, ip6_s, ip6_d, ip6_rs,
ip6_rd, ntohs(c->key.src.port), ntohs(c->key.dst.port),
ntohs(c->rev_key.src.port), ntohs(c->rev_key.dst.port),
c->key.zone, c->rev_key.zone, c->key.nw_proto,
c->rev_key.nw_proto);
}
}
}
/* Initializes the connection tracker 'ct'. The caller is responsible for
* calling 'conntrack_destroy()', when the instance is not needed anymore */
void
conntrack_init(struct conntrack *ct)
{
long long now = time_msec();
ct_rwlock_init(&ct->resources_lock);
ct_rwlock_wrlock(&ct->resources_lock);
hmap_init(&ct->nat_conn_keys);
hmap_init(&ct->alg_expectations);
hindex_init(&ct->alg_expectation_refs);
ovs_list_init(&ct->alg_exp_list);
ct_rwlock_unlock(&ct->resources_lock);
for (unsigned i = 0; i < CONNTRACK_BUCKETS; i++) {
struct conntrack_bucket *ctb = &ct->buckets[i];
ct_lock_init(&ctb->lock);
ct_lock_lock(&ctb->lock);
hmap_init(&ctb->connections);
for (unsigned j = 0; j < ARRAY_SIZE(ctb->exp_lists); j++) {
ovs_list_init(&ctb->exp_lists[j]);
}
ct_lock_unlock(&ctb->lock);
ovs_mutex_init(&ctb->cleanup_mutex);
ovs_mutex_lock(&ctb->cleanup_mutex);
ctb->next_cleanup = now + CT_TM_MIN;
ovs_mutex_unlock(&ctb->cleanup_mutex);
}
ct->hash_basis = random_uint32();
atomic_count_init(&ct->n_conn, 0);
atomic_init(&ct->n_conn_limit, DEFAULT_N_CONN_LIMIT);
latch_init(&ct->clean_thread_exit);
ct->clean_thread = ovs_thread_create("ct_clean", clean_thread_main, ct);
}
/* Destroys the connection tracker 'ct' and frees all the allocated memory. */
void
conntrack_destroy(struct conntrack *ct)
{
latch_set(&ct->clean_thread_exit);
pthread_join(ct->clean_thread, NULL);
latch_destroy(&ct->clean_thread_exit);
for (unsigned i = 0; i < CONNTRACK_BUCKETS; i++) {
struct conntrack_bucket *ctb = &ct->buckets[i];
struct conn *conn;
ovs_mutex_destroy(&ctb->cleanup_mutex);
ct_lock_lock(&ctb->lock);
HMAP_FOR_EACH_POP (conn, node, &ctb->connections) {
if (conn->conn_type == CT_CONN_TYPE_DEFAULT) {
atomic_count_dec(&ct->n_conn);
}
delete_conn(conn);
}
hmap_destroy(&ctb->connections);
ct_lock_unlock(&ctb->lock);
ct_lock_destroy(&ctb->lock);
}
ct_rwlock_wrlock(&ct->resources_lock);
struct nat_conn_key_node *nat_conn_key_node;
HMAP_FOR_EACH_POP (nat_conn_key_node, node, &ct->nat_conn_keys) {
free(nat_conn_key_node);
}
hmap_destroy(&ct->nat_conn_keys);
struct alg_exp_node *alg_exp_node;
HMAP_FOR_EACH_POP (alg_exp_node, node, &ct->alg_expectations) {
free(alg_exp_node);
}
ovs_list_poison(&ct->alg_exp_list);
hmap_destroy(&ct->alg_expectations);
hindex_destroy(&ct->alg_expectation_refs);
ct_rwlock_unlock(&ct->resources_lock);
ct_rwlock_destroy(&ct->resources_lock);
}
static unsigned hash_to_bucket(uint32_t hash)
{
/* Extracts the most significant bits in hash. The least significant bits
* are already used internally by the hmap implementation. */
BUILD_ASSERT(CONNTRACK_BUCKETS_SHIFT < 32 && CONNTRACK_BUCKETS_SHIFT >= 1);
return (hash >> (32 - CONNTRACK_BUCKETS_SHIFT)) % CONNTRACK_BUCKETS;
}
static void
write_ct_md(struct dp_packet *pkt, uint16_t zone, const struct conn *conn,
const struct conn_key *key, const struct alg_exp_node *alg_exp)
{
pkt->md.ct_state |= CS_TRACKED;
pkt->md.ct_zone = zone;
pkt->md.ct_mark = conn ? conn->mark : 0;
pkt->md.ct_label = conn ? conn->label : OVS_U128_ZERO;
/* Use the original direction tuple if we have it. */
if (conn) {
if (conn->alg_related) {
key = &conn->master_key;
} else {
key = &conn->key;
}
} else if (alg_exp) {
pkt->md.ct_mark = alg_exp->master_mark;
pkt->md.ct_label = alg_exp->master_label;
key = &alg_exp->master_key;
}
pkt->md.ct_orig_tuple_ipv6 = false;
if (key) {
if (key->dl_type == htons(ETH_TYPE_IP)) {
pkt->md.ct_orig_tuple.ipv4 = (struct ovs_key_ct_tuple_ipv4) {
key->src.addr.ipv4_aligned,
key->dst.addr.ipv4_aligned,
key->nw_proto != IPPROTO_ICMP
? key->src.port : htons(key->src.icmp_type),
key->nw_proto != IPPROTO_ICMP
? key->dst.port : htons(key->src.icmp_code),
key->nw_proto,
};
} else {
pkt->md.ct_orig_tuple_ipv6 = true;
pkt->md.ct_orig_tuple.ipv6 = (struct ovs_key_ct_tuple_ipv6) {
key->src.addr.ipv6_aligned,
key->dst.addr.ipv6_aligned,
key->nw_proto != IPPROTO_ICMPV6
? key->src.port : htons(key->src.icmp_type),
key->nw_proto != IPPROTO_ICMPV6
? key->dst.port : htons(key->src.icmp_code),
key->nw_proto,
};
}
} else {
memset(&pkt->md.ct_orig_tuple, 0, sizeof pkt->md.ct_orig_tuple);
}
}
static uint8_t
get_ip_proto(const struct dp_packet *pkt)
{
uint8_t ip_proto;
struct eth_header *l2 = dp_packet_eth(pkt);
if (l2->eth_type == htons(ETH_TYPE_IPV6)) {
struct ovs_16aligned_ip6_hdr *nh6 = dp_packet_l3(pkt);
ip_proto = nh6->ip6_ctlun.ip6_un1.ip6_un1_nxt;
} else {
struct ip_header *l3_hdr = dp_packet_l3(pkt);
ip_proto = l3_hdr->ip_proto;
}
return ip_proto;
}
static bool
is_ftp_ctl(const enum ct_alg_ctl_type ct_alg_ctl)
{
return ct_alg_ctl == CT_ALG_CTL_FTP;
}
static enum ct_alg_ctl_type
get_alg_ctl_type(const struct dp_packet *pkt, ovs_be16 tp_src, ovs_be16 tp_dst,
const char *helper)
{
/* CT_IPPORT_FTP/TFTP is used because IPPORT_FTP/TFTP in not defined
* in OSX, at least in in.h. Since these values will never change, remove
* the external dependency. */
enum { CT_IPPORT_FTP = 21 };
enum { CT_IPPORT_TFTP = 69 };
uint8_t ip_proto = get_ip_proto(pkt);
struct udp_header *uh = dp_packet_l4(pkt);
struct tcp_header *th = dp_packet_l4(pkt);
ovs_be16 ftp_src_port = htons(CT_IPPORT_FTP);
ovs_be16 ftp_dst_port = htons(CT_IPPORT_FTP);
ovs_be16 tftp_dst_port = htons(CT_IPPORT_TFTP);
if (OVS_UNLIKELY(tp_dst)) {
if (helper && !strncmp(helper, "ftp", strlen("ftp"))) {
ftp_dst_port = tp_dst;
} else if (helper && !strncmp(helper, "tftp", strlen("tftp"))) {
tftp_dst_port = tp_dst;
}
} else if (OVS_UNLIKELY(tp_src)) {
if (helper && !strncmp(helper, "ftp", strlen("ftp"))) {
ftp_src_port = tp_src;
}
}
if (ip_proto == IPPROTO_UDP && uh->udp_dst == tftp_dst_port) {
return CT_ALG_CTL_TFTP;
} else if (ip_proto == IPPROTO_TCP &&
(th->tcp_src == ftp_src_port || th->tcp_dst == ftp_dst_port)) {
return CT_ALG_CTL_FTP;
}
return CT_ALG_CTL_NONE;
}
static bool
alg_src_ip_wc(enum ct_alg_ctl_type alg_ctl_type)
{
if (alg_ctl_type == CT_ALG_CTL_SIP) {
return true;
}
return false;
}
static void
handle_alg_ctl(struct conntrack *ct, const struct conn_lookup_ctx *ctx,
struct dp_packet *pkt, enum ct_alg_ctl_type ct_alg_ctl,
const struct conn *conn, long long now, bool nat,
const struct conn *conn_for_expectation)
{
/* ALG control packet handling with expectation creation. */
if (OVS_UNLIKELY(alg_helpers[ct_alg_ctl] && conn && conn->alg)) {
alg_helpers[ct_alg_ctl](ct, ctx, pkt, conn_for_expectation, now,
CT_FTP_CTL_INTEREST, nat);
}
}
static void
pat_packet(struct dp_packet *pkt, const struct conn *conn)
{
if (conn->nat_info->nat_action & NAT_ACTION_SRC) {
if (conn->key.nw_proto == IPPROTO_TCP) {
struct tcp_header *th = dp_packet_l4(pkt);
packet_set_tcp_port(pkt, conn->rev_key.dst.port, th->tcp_dst);
} else if (conn->key.nw_proto == IPPROTO_UDP) {
struct udp_header *uh = dp_packet_l4(pkt);
packet_set_udp_port(pkt, conn->rev_key.dst.port, uh->udp_dst);
}
} else if (conn->nat_info->nat_action & NAT_ACTION_DST) {
if (conn->key.nw_proto == IPPROTO_TCP) {
struct tcp_header *th = dp_packet_l4(pkt);
packet_set_tcp_port(pkt, th->tcp_src, conn->rev_key.src.port);
} else if (conn->key.nw_proto == IPPROTO_UDP) {
struct udp_header *uh = dp_packet_l4(pkt);
packet_set_udp_port(pkt, uh->udp_src, conn->rev_key.src.port);
}
}
}
static void
nat_packet(struct dp_packet *pkt, const struct conn *conn, bool related)
{
if (conn->nat_info->nat_action & NAT_ACTION_SRC) {
pkt->md.ct_state |= CS_SRC_NAT;
if (conn->key.dl_type == htons(ETH_TYPE_IP)) {
struct ip_header *nh = dp_packet_l3(pkt);
packet_set_ipv4_addr(pkt, &nh->ip_src,
conn->rev_key.dst.addr.ipv4_aligned);
} else {
struct ovs_16aligned_ip6_hdr *nh6 = dp_packet_l3(pkt);
packet_set_ipv6_addr(pkt, conn->key.nw_proto,
nh6->ip6_src.be32,
&conn->rev_key.dst.addr.ipv6_aligned,
true);
}
if (!related) {
pat_packet(pkt, conn);
}
} else if (conn->nat_info->nat_action & NAT_ACTION_DST) {
pkt->md.ct_state |= CS_DST_NAT;
if (conn->key.dl_type == htons(ETH_TYPE_IP)) {
struct ip_header *nh = dp_packet_l3(pkt);
packet_set_ipv4_addr(pkt, &nh->ip_dst,
conn->rev_key.src.addr.ipv4_aligned);
} else {
struct ovs_16aligned_ip6_hdr *nh6 = dp_packet_l3(pkt);
packet_set_ipv6_addr(pkt, conn->key.nw_proto,
nh6->ip6_dst.be32,
&conn->rev_key.src.addr.ipv6_aligned,
true);
}
if (!related) {
pat_packet(pkt, conn);
}
}
}
static void
un_pat_packet(struct dp_packet *pkt, const struct conn *conn)
{
if (conn->nat_info->nat_action & NAT_ACTION_SRC) {
if (conn->key.nw_proto == IPPROTO_TCP) {
struct tcp_header *th = dp_packet_l4(pkt);
packet_set_tcp_port(pkt, th->tcp_src, conn->key.src.port);
} else if (conn->key.nw_proto == IPPROTO_UDP) {
struct udp_header *uh = dp_packet_l4(pkt);
packet_set_udp_port(pkt, uh->udp_src, conn->key.src.port);
}
} else if (conn->nat_info->nat_action & NAT_ACTION_DST) {
if (conn->key.nw_proto == IPPROTO_TCP) {
struct tcp_header *th = dp_packet_l4(pkt);
packet_set_tcp_port(pkt, conn->key.dst.port, th->tcp_dst);
} else if (conn->key.nw_proto == IPPROTO_UDP) {
struct udp_header *uh = dp_packet_l4(pkt);
packet_set_udp_port(pkt, conn->key.dst.port, uh->udp_dst);
}
}
}
static void
reverse_pat_packet(struct dp_packet *pkt, const struct conn *conn)
{
if (conn->nat_info->nat_action & NAT_ACTION_SRC) {
if (conn->key.nw_proto == IPPROTO_TCP) {
struct tcp_header *th_in = dp_packet_l4(pkt);
packet_set_tcp_port(pkt, conn->key.src.port,
th_in->tcp_dst);
} else if (conn->key.nw_proto == IPPROTO_UDP) {
struct udp_header *uh_in = dp_packet_l4(pkt);
packet_set_udp_port(pkt, conn->key.src.port,
uh_in->udp_dst);
}
} else if (conn->nat_info->nat_action & NAT_ACTION_DST) {
if (conn->key.nw_proto == IPPROTO_TCP) {
struct tcp_header *th_in = dp_packet_l4(pkt);
packet_set_tcp_port(pkt, th_in->tcp_src,
conn->key.dst.port);
} else if (conn->key.nw_proto == IPPROTO_UDP) {
struct udp_header *uh_in = dp_packet_l4(pkt);
packet_set_udp_port(pkt, uh_in->udp_src,
conn->key.dst.port);
}
}
}
static void
reverse_nat_packet(struct dp_packet *pkt, const struct conn *conn)
{
char *tail = dp_packet_tail(pkt);
char pad = dp_packet_l2_pad_size(pkt);
struct conn_key inner_key;
const char *inner_l4 = NULL;
uint16_t orig_l3_ofs = pkt->l3_ofs;
uint16_t orig_l4_ofs = pkt->l4_ofs;
if (conn->key.dl_type == htons(ETH_TYPE_IP)) {
struct ip_header *nh = dp_packet_l3(pkt);
struct icmp_header *icmp = dp_packet_l4(pkt);
struct ip_header *inner_l3 = (struct ip_header *) (icmp + 1);
extract_l3_ipv4(&inner_key, inner_l3, tail - ((char *)inner_l3) - pad,
&inner_l4, false);
pkt->l3_ofs += (char *) inner_l3 - (char *) nh;
pkt->l4_ofs += inner_l4 - (char *) icmp;
if (conn->nat_info->nat_action & NAT_ACTION_SRC) {
packet_set_ipv4_addr(pkt, &inner_l3->ip_src,
conn->key.src.addr.ipv4_aligned);
} else if (conn->nat_info->nat_action & NAT_ACTION_DST) {
packet_set_ipv4_addr(pkt, &inner_l3->ip_dst,
conn->key.dst.addr.ipv4_aligned);
}
reverse_pat_packet(pkt, conn);
icmp->icmp_csum = 0;
icmp->icmp_csum = csum(icmp, tail - (char *) icmp - pad);
} else {
struct ovs_16aligned_ip6_hdr *nh6 = dp_packet_l3(pkt);
struct icmp6_error_header *icmp6 = dp_packet_l4(pkt);
struct ovs_16aligned_ip6_hdr *inner_l3_6 =
(struct ovs_16aligned_ip6_hdr *) (icmp6 + 1);
extract_l3_ipv6(&inner_key, inner_l3_6,
tail - ((char *)inner_l3_6) - pad,
&inner_l4);
pkt->l3_ofs += (char *) inner_l3_6 - (char *) nh6;
pkt->l4_ofs += inner_l4 - (char *) icmp6;
if (conn->nat_info->nat_action & NAT_ACTION_SRC) {
packet_set_ipv6_addr(pkt, conn->key.nw_proto,
inner_l3_6->ip6_src.be32,
&conn->key.src.addr.ipv6_aligned,
true);
} else if (conn->nat_info->nat_action & NAT_ACTION_DST) {
packet_set_ipv6_addr(pkt, conn->key.nw_proto,
inner_l3_6->ip6_dst.be32,
&conn->key.dst.addr.ipv6_aligned,
true);
}
reverse_pat_packet(pkt, conn);
uint32_t icmp6_csum = packet_csum_pseudoheader6(nh6);
icmp6->icmp6_base.icmp6_cksum = 0;
icmp6->icmp6_base.icmp6_cksum = csum_finish(
csum_continue(icmp6_csum, icmp6, tail - (char *) icmp6 - pad));
}
pkt->l3_ofs = orig_l3_ofs;
pkt->l4_ofs = orig_l4_ofs;
}
static void
un_nat_packet(struct dp_packet *pkt, const struct conn *conn,
bool related)
{
if (conn->nat_info->nat_action & NAT_ACTION_SRC) {
pkt->md.ct_state |= CS_DST_NAT;
if (conn->key.dl_type == htons(ETH_TYPE_IP)) {
struct ip_header *nh = dp_packet_l3(pkt);
packet_set_ipv4_addr(pkt, &nh->ip_dst,
conn->key.src.addr.ipv4_aligned);
} else {
struct ovs_16aligned_ip6_hdr *nh6 = dp_packet_l3(pkt);
packet_set_ipv6_addr(pkt, conn->key.nw_proto,
nh6->ip6_dst.be32,
&conn->key.src.addr.ipv6_aligned, true);
}
if (OVS_UNLIKELY(related)) {
reverse_nat_packet(pkt, conn);
} else {
un_pat_packet(pkt, conn);
}
} else if (conn->nat_info->nat_action & NAT_ACTION_DST) {
pkt->md.ct_state |= CS_SRC_NAT;
if (conn->key.dl_type == htons(ETH_TYPE_IP)) {
struct ip_header *nh = dp_packet_l3(pkt);
packet_set_ipv4_addr(pkt, &nh->ip_src,
conn->key.dst.addr.ipv4_aligned);
} else {
struct ovs_16aligned_ip6_hdr *nh6 = dp_packet_l3(pkt);
packet_set_ipv6_addr(pkt, conn->key.nw_proto,
nh6->ip6_src.be32,
&conn->key.dst.addr.ipv6_aligned, true);
}
if (OVS_UNLIKELY(related)) {
reverse_nat_packet(pkt, conn);
} else {
un_pat_packet(pkt, conn);
}
}
}
/* Typical usage of this helper is in non per-packet code;
* this is because the bucket lock needs to be held for lookup
* and a hash would have already been needed. Hence, this function
* is just intended for code clarity. */
static struct conn *
conn_lookup(struct conntrack *ct, const struct conn_key *key, long long now)
{
struct conn_lookup_ctx ctx;
ctx.conn = NULL;
ctx.key = *key;
ctx.hash = conn_key_hash(key, ct->hash_basis);
unsigned bucket = hash_to_bucket(ctx.hash);
conn_key_lookup(&ct->buckets[bucket], &ctx, now);
return ctx.conn;
}
static void
conn_seq_skew_set(struct conntrack *ct, const struct conn_key *key,
long long now, int seq_skew, bool seq_skew_dir)
{
unsigned bucket = hash_to_bucket(conn_key_hash(key, ct->hash_basis));
ct_lock_lock(&ct->buckets[bucket].lock);
struct conn *conn = conn_lookup(ct, key, now);
if (conn && seq_skew) {
conn->seq_skew = seq_skew;
conn->seq_skew_dir = seq_skew_dir;
}
ct_lock_unlock(&ct->buckets[bucket].lock);
}
static void
nat_clean(struct conntrack *ct, struct conn *conn,
struct conntrack_bucket *ctb)
OVS_REQUIRES(ctb->lock)
{
ct_rwlock_wrlock(&ct->resources_lock);
nat_conn_keys_remove(&ct->nat_conn_keys, &conn->rev_key, ct->hash_basis);
ct_rwlock_unlock(&ct->resources_lock);
ct_lock_unlock(&ctb->lock);
unsigned bucket_rev_conn =
hash_to_bucket(conn_key_hash(&conn->rev_key, ct->hash_basis));
ct_lock_lock(&ct->buckets[bucket_rev_conn].lock);
ct_rwlock_wrlock(&ct->resources_lock);
long long now = time_msec();
struct conn *rev_conn = conn_lookup(ct, &conn->rev_key, now);
struct nat_conn_key_node *nat_conn_key_node =
nat_conn_keys_lookup(&ct->nat_conn_keys, &conn->rev_key,
ct->hash_basis);
/* In the unlikely event, rev conn was recreated, then skip
* rev_conn cleanup. */
if (rev_conn && (!nat_conn_key_node ||
conn_key_cmp(&nat_conn_key_node->value,
&rev_conn->rev_key))) {
hmap_remove(&ct->buckets[bucket_rev_conn].connections,
&rev_conn->node);
free(rev_conn);
}
delete_conn(conn);
ct_rwlock_unlock(&ct->resources_lock);
ct_lock_unlock(&ct->buckets[bucket_rev_conn].lock);
ct_lock_lock(&ctb->lock);
}
static void
conn_clean(struct conntrack *ct, struct conn *conn,
struct conntrack_bucket *ctb)
OVS_REQUIRES(ctb->lock)
{
if (conn->alg) {
expectation_clean(ct, &conn->key, ct->hash_basis);
}
ovs_list_remove(&conn->exp_node);
hmap_remove(&ctb->connections, &conn->node);
atomic_count_dec(&ct->n_conn);
if (conn->nat_info) {
nat_clean(ct, conn, ctb);
} else {
delete_conn(conn);
}
}
static bool
ct_verify_helper(const char *helper, enum ct_alg_ctl_type ct_alg_ctl)
{
if (ct_alg_ctl == CT_ALG_CTL_NONE) {
return true;
} else if (helper) {
if ((ct_alg_ctl == CT_ALG_CTL_FTP) &&
!strncmp(helper, "ftp", strlen("ftp"))) {
return true;
} else if ((ct_alg_ctl == CT_ALG_CTL_TFTP) &&
!strncmp(helper, "tftp", strlen("tftp"))) {
return true;
} else {
return false;
}
} else {
return false;
}
}
/* This function is called with the bucket lock held. */
static struct conn *
conn_not_found(struct conntrack *ct, struct dp_packet *pkt,
struct conn_lookup_ctx *ctx, bool commit, long long now,
const struct nat_action_info_t *nat_action_info,
struct conn *conn_for_un_nat_copy,
const char *helper,
const struct alg_exp_node *alg_exp,
enum ct_alg_ctl_type ct_alg_ctl)
{
struct conn *nc = NULL;
if (!valid_new(pkt, &ctx->key)) {
pkt->md.ct_state = CS_INVALID;
return nc;
}
pkt->md.ct_state = CS_NEW;
if (alg_exp) {
pkt->md.ct_state |= CS_RELATED;
}
if (commit) {
unsigned int n_conn_limit;
atomic_read_relaxed(&ct->n_conn_limit, &n_conn_limit);
if (atomic_count_get(&ct->n_conn) >= n_conn_limit) {
COVERAGE_INC(conntrack_full);
return nc;
}
unsigned bucket = hash_to_bucket(ctx->hash);
nc = new_conn(&ct->buckets[bucket], pkt, &ctx->key, now);
ctx->conn = nc;
nc->rev_key = nc->key;
conn_key_reverse(&nc->rev_key);
if (ct_verify_helper(helper, ct_alg_ctl)) {
nc->alg = nullable_xstrdup(helper);
}
if (alg_exp) {
nc->alg_related = true;
nc->mark = alg_exp->master_mark;
nc->label = alg_exp->master_label;
nc->master_key = alg_exp->master_key;
}
if (nat_action_info) {
nc->nat_info = xmemdup(nat_action_info, sizeof *nc->nat_info);
if (alg_exp) {
if (alg_exp->nat_rpl_dst) {
nc->rev_key.dst.addr = alg_exp->alg_nat_repl_addr;
nc->nat_info->nat_action = NAT_ACTION_SRC;
} else {
nc->rev_key.src.addr = alg_exp->alg_nat_repl_addr;
nc->nat_info->nat_action = NAT_ACTION_DST;
}
*conn_for_un_nat_copy = *nc;
ct_rwlock_wrlock(&ct->resources_lock);
bool new_insert = nat_conn_keys_insert(&ct->nat_conn_keys,
conn_for_un_nat_copy,
ct->hash_basis);
ct_rwlock_unlock(&ct->resources_lock);
if (!new_insert) {
char *log_msg = xasprintf("Pre-existing alg "
"nat_conn_key");
ct_print_conn_info(conn_for_un_nat_copy, log_msg, VLL_INFO,
true, false);
free(log_msg);
}
} else {
*conn_for_un_nat_copy = *nc;
ct_rwlock_wrlock(&ct->resources_lock);
bool nat_res = nat_select_range_tuple(ct, nc,
conn_for_un_nat_copy);
if (!nat_res) {
goto nat_res_exhaustion;
}
/* Update nc with nat adjustments made to
* conn_for_un_nat_copy by nat_select_range_tuple(). */
*nc = *conn_for_un_nat_copy;
ct_rwlock_unlock(&ct->resources_lock);
}
conn_for_un_nat_copy->conn_type = CT_CONN_TYPE_UN_NAT;
conn_for_un_nat_copy->nat_info = NULL;
conn_for_un_nat_copy->alg = NULL;
nat_packet(pkt, nc, ctx->icmp_related);
}
hmap_insert(&ct->buckets[bucket].connections, &nc->node, ctx->hash);
atomic_count_inc(&ct->n_conn);
}
return nc;
/* This would be a user error or a DOS attack.
* A user error is prevented by allocating enough
* combinations of NAT addresses when combined with
* ephemeral ports. A DOS attack should be protected
* against with firewall rules or a separate firewall.
* Also using zone partitioning can limit DoS impact. */
nat_res_exhaustion:
ovs_list_remove(&nc->exp_node);
delete_conn(nc);
/* conn_for_un_nat_copy is a local variable in process_one; this
* memset() serves to document that conn_for_un_nat_copy is from
* this point on unused. */
memset(conn_for_un_nat_copy, 0, sizeof *conn_for_un_nat_copy);
ct_rwlock_unlock(&ct->resources_lock);
static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(5, 5);
VLOG_WARN_RL(&rl, "Unable to NAT due to tuple space exhaustion - "
"if DoS attack, use firewalling and/or zone partitioning.");
return NULL;
}
static bool
conn_update_state(struct conntrack *ct, struct dp_packet *pkt,
struct conn_lookup_ctx *ctx, struct conn **conn,
long long now, unsigned bucket)
OVS_REQUIRES(ct->buckets[bucket].lock)
{
bool create_new_conn = false;
if (ctx->icmp_related) {
pkt->md.ct_state |= CS_RELATED;
if (ctx->reply) {
pkt->md.ct_state |= CS_REPLY_DIR;
}
} else {
if ((*conn)->alg_related) {
pkt->md.ct_state |= CS_RELATED;
}
enum ct_update_res res = conn_update(*conn, &ct->buckets[bucket],
pkt, ctx->reply, now);
switch (res) {
case CT_UPDATE_VALID:
pkt->md.ct_state |= CS_ESTABLISHED;
pkt->md.ct_state &= ~CS_NEW;
if (ctx->reply) {
pkt->md.ct_state |= CS_REPLY_DIR;
}
break;
case CT_UPDATE_INVALID:
pkt->md.ct_state = CS_INVALID;
break;
case CT_UPDATE_NEW:
conn_clean(ct, *conn, &ct->buckets[bucket]);
create_new_conn = true;
break;
default:
OVS_NOT_REACHED();