forked from openvswitch/ovs
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathconntrack.c
2287 lines (1975 loc) · 59.9 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 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#include <linux/kconfig.h>
#include <linux/version.h>
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#include <linux/module.h>
#include <linux/openvswitch.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/sctp.h>
#include <linux/static_key.h>
#include <net/ip.h>
#include <net/genetlink.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_count.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_labels.h>
#include <net/netfilter/nf_conntrack_seqadj.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#ifdef CONFIG_NF_NAT_NEEDED
#include <linux/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_l3proto.h>
#endif
#include "datapath.h"
#include "conntrack.h"
#include "flow.h"
#include "flow_netlink.h"
#include "gso.h"
#ifndef HAVE_NF_NAT_RANGE2
#define nf_nat_range2 nf_nat_range
#endif
struct ovs_ct_len_tbl {
int maxlen;
int minlen;
};
/* Metadata mark for masked write to conntrack mark */
struct md_mark {
u32 value;
u32 mask;
};
/* Metadata label for masked write to conntrack label. */
struct md_labels {
struct ovs_key_ct_labels value;
struct ovs_key_ct_labels mask;
};
enum ovs_ct_nat {
OVS_CT_NAT = 1 << 0, /* NAT for committed connections only. */
OVS_CT_SRC_NAT = 1 << 1, /* Source NAT for NEW connections. */
OVS_CT_DST_NAT = 1 << 2, /* Destination NAT for NEW connections. */
};
/* Conntrack action context for execution. */
struct ovs_conntrack_info {
struct nf_conntrack_helper *helper;
struct nf_conntrack_zone zone;
struct nf_conn *ct;
u8 commit : 1;
u8 nat : 3; /* enum ovs_ct_nat */
u8 random_fully_compat : 1; /* bool */
u8 force : 1;
u8 have_eventmask : 1;
u16 family;
u32 eventmask; /* Mask of 1 << IPCT_*. */
struct md_mark mark;
struct md_labels labels;
#ifdef CONFIG_NF_NAT_NEEDED
struct nf_nat_range2 range; /* Only present for SRC NAT and DST NAT. */
#endif
};
#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
#define OVS_CT_LIMIT_UNLIMITED 0
#define OVS_CT_LIMIT_DEFAULT OVS_CT_LIMIT_UNLIMITED
#define CT_LIMIT_HASH_BUCKETS 512
static DEFINE_STATIC_KEY_FALSE(ovs_ct_limit_enabled);
struct ovs_ct_limit {
/* Elements in ovs_ct_limit_info->limits hash table */
struct hlist_node hlist_node;
struct rcu_head rcu;
u16 zone;
u32 limit;
};
struct ovs_ct_limit_info {
u32 default_limit;
struct hlist_head *limits;
struct nf_conncount_data *data;
};
static const struct nla_policy ct_limit_policy[OVS_CT_LIMIT_ATTR_MAX + 1] = {
[OVS_CT_LIMIT_ATTR_ZONE_LIMIT] = { .type = NLA_NESTED, },
};
#endif
static bool labels_nonzero(const struct ovs_key_ct_labels *labels);
static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info);
static u16 key_to_nfproto(const struct sw_flow_key *key)
{
switch (ntohs(key->eth.type)) {
case ETH_P_IP:
return NFPROTO_IPV4;
case ETH_P_IPV6:
return NFPROTO_IPV6;
default:
return NFPROTO_UNSPEC;
}
}
/* Map SKB connection state into the values used by flow definition. */
static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo)
{
u8 ct_state = OVS_CS_F_TRACKED;
switch (ctinfo) {
case IP_CT_ESTABLISHED_REPLY:
case IP_CT_RELATED_REPLY:
ct_state |= OVS_CS_F_REPLY_DIR;
break;
default:
break;
}
switch (ctinfo) {
case IP_CT_ESTABLISHED:
case IP_CT_ESTABLISHED_REPLY:
ct_state |= OVS_CS_F_ESTABLISHED;
break;
case IP_CT_RELATED:
case IP_CT_RELATED_REPLY:
ct_state |= OVS_CS_F_RELATED;
break;
case IP_CT_NEW:
ct_state |= OVS_CS_F_NEW;
break;
default:
break;
}
return ct_state;
}
static u32 ovs_ct_get_mark(const struct nf_conn *ct)
{
#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
return ct ? ct->mark : 0;
#else
return 0;
#endif
}
/* Guard against conntrack labels max size shrinking below 128 bits. */
#if NF_CT_LABELS_MAX_SIZE < 16
#error NF_CT_LABELS_MAX_SIZE must be at least 16 bytes
#endif
static void ovs_ct_get_labels(const struct nf_conn *ct,
struct ovs_key_ct_labels *labels)
{
struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL;
if (cl)
memcpy(labels, cl->bits, OVS_CT_LABELS_LEN);
else
memset(labels, 0, OVS_CT_LABELS_LEN);
}
static void __ovs_ct_update_key_orig_tp(struct sw_flow_key *key,
const struct nf_conntrack_tuple *orig,
u8 icmp_proto)
{
key->ct_orig_proto = orig->dst.protonum;
if (orig->dst.protonum == icmp_proto) {
key->ct.orig_tp.src = htons(orig->dst.u.icmp.type);
key->ct.orig_tp.dst = htons(orig->dst.u.icmp.code);
} else {
key->ct.orig_tp.src = orig->src.u.all;
key->ct.orig_tp.dst = orig->dst.u.all;
}
}
static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state,
const struct nf_conntrack_zone *zone,
const struct nf_conn *ct)
{
key->ct_state = state;
key->ct_zone = zone->id;
key->ct.mark = ovs_ct_get_mark(ct);
ovs_ct_get_labels(ct, &key->ct.labels);
if (ct) {
const struct nf_conntrack_tuple *orig;
/* Use the master if we have one. */
if (ct->master)
ct = ct->master;
orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
/* IP version must match with the master connection. */
if (key->eth.type == htons(ETH_P_IP) &&
nf_ct_l3num(ct) == NFPROTO_IPV4) {
key->ipv4.ct_orig.src = orig->src.u3.ip;
key->ipv4.ct_orig.dst = orig->dst.u3.ip;
__ovs_ct_update_key_orig_tp(key, orig, IPPROTO_ICMP);
return;
} else if (key->eth.type == htons(ETH_P_IPV6) &&
!sw_flow_key_is_nd(key) &&
nf_ct_l3num(ct) == NFPROTO_IPV6) {
key->ipv6.ct_orig.src = orig->src.u3.in6;
key->ipv6.ct_orig.dst = orig->dst.u3.in6;
__ovs_ct_update_key_orig_tp(key, orig, NEXTHDR_ICMP);
return;
}
}
/* Clear 'ct_orig_proto' to mark the non-existence of conntrack
* original direction key fields.
*/
key->ct_orig_proto = 0;
}
/* Update 'key' based on skb->_nfct. If 'post_ct' is true, then OVS has
* previously sent the packet to conntrack via the ct action. If
* 'keep_nat_flags' is true, the existing NAT flags retained, else they are
* initialized from the connection status.
*/
static void ovs_ct_update_key(const struct sk_buff *skb,
const struct ovs_conntrack_info *info,
struct sw_flow_key *key, bool post_ct,
bool keep_nat_flags)
{
const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt;
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
u8 state = 0;
ct = nf_ct_get(skb, &ctinfo);
if (ct) {
state = ovs_ct_get_state(ctinfo);
/* All unconfirmed entries are NEW connections. */
if (!nf_ct_is_confirmed(ct))
state |= OVS_CS_F_NEW;
/* OVS persists the related flag for the duration of the
* connection.
*/
if (ct->master)
state |= OVS_CS_F_RELATED;
if (keep_nat_flags) {
state |= key->ct_state & OVS_CS_F_NAT_MASK;
} else {
if (ct->status & IPS_SRC_NAT)
state |= OVS_CS_F_SRC_NAT;
if (ct->status & IPS_DST_NAT)
state |= OVS_CS_F_DST_NAT;
}
zone = nf_ct_zone(ct);
} else if (post_ct) {
state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID;
if (info)
zone = &info->zone;
}
__ovs_ct_update_key(key, state, zone, ct);
}
/* This is called to initialize CT key fields possibly coming in from the local
* stack.
*/
void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key)
{
ovs_ct_update_key(skb, NULL, key, false, false);
}
#define IN6_ADDR_INITIALIZER(ADDR) \
{ (ADDR).s6_addr32[0], (ADDR).s6_addr32[1], \
(ADDR).s6_addr32[2], (ADDR).s6_addr32[3] }
int ovs_ct_put_key(const struct sw_flow_key *swkey,
const struct sw_flow_key *output, struct sk_buff *skb)
{
if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, output->ct_state))
return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
nla_put_u16(skb, OVS_KEY_ATTR_CT_ZONE, output->ct_zone))
return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) &&
nla_put_u32(skb, OVS_KEY_ATTR_CT_MARK, output->ct.mark))
return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(output->ct.labels),
&output->ct.labels))
return -EMSGSIZE;
if (swkey->ct_orig_proto) {
if (swkey->eth.type == htons(ETH_P_IP)) {
struct ovs_key_ct_tuple_ipv4 orig = {
output->ipv4.ct_orig.src,
output->ipv4.ct_orig.dst,
output->ct.orig_tp.src,
output->ct.orig_tp.dst,
output->ct_orig_proto,
};
if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,
sizeof(orig), &orig))
return -EMSGSIZE;
} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
struct ovs_key_ct_tuple_ipv6 orig = {
IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.src),
IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.dst),
output->ct.orig_tp.src,
output->ct.orig_tp.dst,
output->ct_orig_proto,
};
if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,
sizeof(orig), &orig))
return -EMSGSIZE;
}
}
return 0;
}
static int ovs_ct_set_mark(struct nf_conn *ct, struct sw_flow_key *key,
u32 ct_mark, u32 mask)
{
#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
u32 new_mark;
new_mark = ct_mark | (ct->mark & ~(mask));
if (ct->mark != new_mark) {
ct->mark = new_mark;
if (nf_ct_is_confirmed(ct))
nf_conntrack_event_cache(IPCT_MARK, ct);
key->ct.mark = new_mark;
}
return 0;
#else
return -ENOTSUPP;
#endif
}
static struct nf_conn_labels *ovs_ct_get_conn_labels(struct nf_conn *ct)
{
struct nf_conn_labels *cl;
cl = nf_ct_labels_find(ct);
if (!cl) {
nf_ct_labels_ext_add(ct);
cl = nf_ct_labels_find(ct);
}
return cl;
}
/* Initialize labels for a new, yet to be committed conntrack entry. Note that
* since the new connection is not yet confirmed, and thus no-one else has
* access to it's labels, we simply write them over.
*/
static int ovs_ct_init_labels(struct nf_conn *ct, struct sw_flow_key *key,
const struct ovs_key_ct_labels *labels,
const struct ovs_key_ct_labels *mask)
{
struct nf_conn_labels *cl, *master_cl;
bool have_mask = labels_nonzero(mask);
/* Inherit master's labels to the related connection? */
master_cl = ct->master ? nf_ct_labels_find(ct->master) : NULL;
if (!master_cl && !have_mask)
return 0; /* Nothing to do. */
cl = ovs_ct_get_conn_labels(ct);
if (!cl)
return -ENOSPC;
/* Inherit the master's labels, if any. Must use memcpy for backport
* as struct assignment only copies the length field in older
* kernels.
*/
if (master_cl)
memcpy(cl->bits, master_cl->bits, OVS_CT_LABELS_LEN);
if (have_mask) {
u32 *dst = (u32 *)cl->bits;
int i;
for (i = 0; i < OVS_CT_LABELS_LEN_32; i++)
dst[i] = (dst[i] & ~mask->ct_labels_32[i]) |
(labels->ct_labels_32[i]
& mask->ct_labels_32[i]);
}
/* Labels are included in the IPCTNL_MSG_CT_NEW event only if the
* IPCT_LABEL bit is set in the event cache.
*/
nf_conntrack_event_cache(IPCT_LABEL, ct);
memcpy(&key->ct.labels, cl->bits, OVS_CT_LABELS_LEN);
return 0;
}
static int ovs_ct_set_labels(struct nf_conn *ct, struct sw_flow_key *key,
const struct ovs_key_ct_labels *labels,
const struct ovs_key_ct_labels *mask)
{
struct nf_conn_labels *cl;
int err;
cl = ovs_ct_get_conn_labels(ct);
if (!cl)
return -ENOSPC;
err = nf_connlabels_replace(ct, labels->ct_labels_32,
mask->ct_labels_32,
OVS_CT_LABELS_LEN_32);
if (err)
return err;
memcpy(&key->ct.labels, cl->bits, OVS_CT_LABELS_LEN);
return 0;
}
/* 'skb' should already be pulled to nh_ofs. */
static int ovs_ct_helper(struct sk_buff *skb, u16 proto)
{
const struct nf_conntrack_helper *helper;
const struct nf_conn_help *help;
enum ip_conntrack_info ctinfo;
unsigned int protoff;
struct nf_conn *ct;
u8 nexthdr;
int err;
#if LINUX_VERSION_CODE < KERNEL_VERSION(4,6,0)
bool dst_set = false;
struct rtable rt = { .rt_flags = 0 };
#endif
ct = nf_ct_get(skb, &ctinfo);
if (!ct || ctinfo == IP_CT_RELATED_REPLY)
return NF_ACCEPT;
help = nfct_help(ct);
if (!help)
return NF_ACCEPT;
helper = rcu_dereference(help->helper);
if (!helper)
return NF_ACCEPT;
switch (proto) {
case NFPROTO_IPV4:
protoff = ip_hdrlen(skb);
break;
case NFPROTO_IPV6: {
__be16 frag_off;
int ofs;
nexthdr = ipv6_hdr(skb)->nexthdr;
ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
&frag_off);
if (ofs < 0 || (frag_off & htons(~0x7)) != 0) {
pr_debug("proto header not found\n");
return NF_ACCEPT;
}
protoff = ofs;
break;
}
default:
WARN_ONCE(1, "helper invoked on non-IP family!");
return NF_DROP;
}
#if LINUX_VERSION_CODE < KERNEL_VERSION(4,6,0)
/* Linux 4.5 and older depend on skb_dst being set when recalculating
* checksums after NAT helper has mangled TCP or UDP packet payload.
* skb_dst is cast to a rtable struct and the flags examined.
* Forcing these flags to have RTCF_LOCAL not set ensures checksum mod
* is carried out in the same way as kernel versions > 4.5
*/
if (ct->status & IPS_NAT_MASK && skb->ip_summed != CHECKSUM_PARTIAL
&& !skb_dst(skb)) {
dst_set = true;
skb_dst_set(skb, &rt.dst);
}
#endif
err = helper->help(skb, protoff, ct, ctinfo);
if (err != NF_ACCEPT)
return err;
#if LINUX_VERSION_CODE < KERNEL_VERSION(4,6,0)
if (dst_set)
skb_dst_set(skb, NULL);
#endif
/* Adjust seqs after helper. This is needed due to some helpers (e.g.,
* FTP with NAT) adusting the TCP payload size when mangling IP
* addresses and/or port numbers in the text-based control connection.
*/
if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
!nf_ct_seq_adjust(skb, ct, ctinfo, protoff))
return NF_DROP;
return NF_ACCEPT;
}
/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero
* value if 'skb' is freed.
*/
static int handle_fragments(struct net *net, struct sw_flow_key *key,
u16 zone, struct sk_buff *skb)
{
struct ovs_gso_cb ovs_cb = *OVS_GSO_CB(skb);
int err;
if (key->eth.type == htons(ETH_P_IP)) {
enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
err = ip_defrag(net, skb, user);
if (err)
return err;
ovs_cb.dp_cb.mru = IPCB(skb)->frag_max_size;
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
} else if (key->eth.type == htons(ETH_P_IPV6)) {
enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
err = nf_ct_frag6_gather(net, skb, user);
if (err) {
if (err != -EINPROGRESS)
kfree_skb(skb);
return err;
}
key->ip.proto = ipv6_hdr(skb)->nexthdr;
ovs_cb.dp_cb.mru = IP6CB(skb)->frag_max_size;
#endif /* IP frag support */
} else {
kfree_skb(skb);
return -EPFNOSUPPORT;
}
key->ip.frag = OVS_FRAG_TYPE_NONE;
skb_clear_hash(skb);
skb->ignore_df = 1;
*OVS_GSO_CB(skb) = ovs_cb;
return 0;
}
static struct nf_conntrack_expect *
ovs_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone,
u16 proto, const struct sk_buff *skb)
{
struct nf_conntrack_tuple tuple;
struct nf_conntrack_expect *exp;
if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, net, &tuple))
return NULL;
exp = __nf_ct_expect_find(net, zone, &tuple);
if (exp) {
struct nf_conntrack_tuple_hash *h;
/* Delete existing conntrack entry, if it clashes with the
* expectation. This can happen since conntrack ALGs do not
* check for clashes between (new) expectations and existing
* conntrack entries. nf_conntrack_in() will check the
* expectations only if a conntrack entry can not be found,
* which can lead to OVS finding the expectation (here) in the
* init direction, but which will not be removed by the
* nf_conntrack_in() call, if a matching conntrack entry is
* found instead. In this case all init direction packets
* would be reported as new related packets, while reply
* direction packets would be reported as un-related
* established packets.
*/
h = nf_conntrack_find_get(net, zone, &tuple);
if (h) {
struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
nf_ct_delete(ct, 0, 0);
nf_conntrack_put(&ct->ct_general);
}
}
return exp;
}
/* This replicates logic from nf_conntrack_core.c that is not exported. */
static enum ip_conntrack_info
ovs_ct_get_info(const struct nf_conntrack_tuple_hash *h)
{
const struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
return IP_CT_ESTABLISHED_REPLY;
/* Once we've had two way comms, always ESTABLISHED. */
if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status))
return IP_CT_ESTABLISHED;
if (test_bit(IPS_EXPECTED_BIT, &ct->status))
return IP_CT_RELATED;
return IP_CT_NEW;
}
/* Find an existing connection which this packet belongs to without
* re-attributing statistics or modifying the connection state. This allows an
* skb->_nfct lost due to an upcall to be recovered during actions execution.
*
* Must be called with rcu_read_lock.
*
* On success, populates skb->_nfct and returns the connection. Returns NULL
* if there is no existing entry.
*/
static struct nf_conn *
ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone,
u8 l3num, struct sk_buff *skb, bool natted)
{
const struct nf_conntrack_l3proto *l3proto;
const struct nf_conntrack_l4proto *l4proto;
struct nf_conntrack_tuple tuple;
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
unsigned int dataoff;
u8 protonum;
l3proto = __nf_ct_l3proto_find(l3num);
if (l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff,
&protonum) <= 0) {
pr_debug("ovs_ct_find_existing: Can't get protonum\n");
return NULL;
}
l4proto = __nf_ct_l4proto_find(l3num, protonum);
if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num,
protonum, net, &tuple, l3proto, l4proto)) {
pr_debug("ovs_ct_find_existing: Can't get tuple\n");
return NULL;
}
/* Must invert the tuple if skb has been transformed by NAT. */
if (natted) {
struct nf_conntrack_tuple inverse;
if (!nf_ct_invert_tuple(&inverse, &tuple, l3proto, l4proto)) {
pr_debug("ovs_ct_find_existing: Inversion failed!\n");
return NULL;
}
tuple = inverse;
}
/* look for tuple match */
h = nf_conntrack_find_get(net, zone, &tuple);
if (!h)
return NULL; /* Not found. */
ct = nf_ct_tuplehash_to_ctrack(h);
/* Inverted packet tuple matches the reverse direction conntrack tuple,
* select the other tuplehash to get the right 'ctinfo' bits for this
* packet.
*/
if (natted)
h = &ct->tuplehash[!h->tuple.dst.dir];
nf_ct_set(skb, ct, ovs_ct_get_info(h));
return ct;
}
static
struct nf_conn *ovs_ct_executed(struct net *net,
const struct sw_flow_key *key,
const struct ovs_conntrack_info *info,
struct sk_buff *skb,
bool *ct_executed)
{
struct nf_conn *ct = NULL;
/* If no ct, check if we have evidence that an existing conntrack entry
* might be found for this skb. This happens when we lose a skb->_nfct
* due to an upcall, or if the direction is being forced. If the
* connection was not confirmed, it is not cached and needs to be run
* through conntrack again.
*/
*ct_executed = (key->ct_state & OVS_CS_F_TRACKED) &&
!(key->ct_state & OVS_CS_F_INVALID) &&
(key->ct_zone == info->zone.id);
if (*ct_executed || (!key->ct_state && info->force)) {
ct = ovs_ct_find_existing(net, &info->zone, info->family, skb,
!!(key->ct_state &
OVS_CS_F_NAT_MASK));
}
return ct;
}
/* Determine whether skb->_nfct is equal to the result of conntrack lookup. */
static bool skb_nfct_cached(struct net *net,
const struct sw_flow_key *key,
const struct ovs_conntrack_info *info,
struct sk_buff *skb)
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
bool ct_executed = true;
ct = nf_ct_get(skb, &ctinfo);
if (!ct)
ct = ovs_ct_executed(net, key, info, skb, &ct_executed);
if (ct)
nf_ct_get(skb, &ctinfo);
else
return false;
if (!net_eq(net, read_pnet(&ct->ct_net)))
return false;
if (!nf_ct_zone_equal_any(info->ct, nf_ct_zone(ct)))
return false;
if (info->helper) {
struct nf_conn_help *help;
help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER);
if (help && rcu_access_pointer(help->helper) != info->helper)
return false;
}
/* Force conntrack entry direction to the current packet? */
if (info->force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
/* Delete the conntrack entry if confirmed, else just release
* the reference.
*/
if (nf_ct_is_confirmed(ct))
nf_ct_delete(ct, 0, 0);
nf_conntrack_put(&ct->ct_general);
nf_ct_set(skb, NULL, 0);
return false;
}
return ct_executed;
}
#ifdef CONFIG_NF_NAT_NEEDED
/* Modelled after nf_nat_ipv[46]_fn().
* range is only used for new, uninitialized NAT state.
* Returns either NF_ACCEPT or NF_DROP.
*/
static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype)
{
int hooknum, nh_off, err = NF_ACCEPT;
nh_off = skb_network_offset(skb);
skb_pull_rcsum(skb, nh_off);
/* See HOOK2MANIP(). */
if (maniptype == NF_NAT_MANIP_SRC)
hooknum = NF_INET_LOCAL_IN; /* Source NAT */
else
hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED_REPLY:
if (IS_ENABLED(CONFIG_NF_NAT_IPV4) &&
skb->protocol == htons(ETH_P_IP) &&
ip_hdr(skb)->protocol == IPPROTO_ICMP) {
if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
hooknum))
err = NF_DROP;
goto push;
} else if (IS_ENABLED(CONFIG_NF_NAT_IPV6) &&
skb->protocol == htons(ETH_P_IPV6)) {
__be16 frag_off;
u8 nexthdr = ipv6_hdr(skb)->nexthdr;
int hdrlen = ipv6_skip_exthdr(skb,
sizeof(struct ipv6hdr),
&nexthdr, &frag_off);
if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
if (!nf_nat_icmpv6_reply_translation(skb, ct,
ctinfo,
hooknum,
hdrlen))
err = NF_DROP;
goto push;
}
}
/* Non-ICMP, fall thru to initialize if needed. */
case IP_CT_NEW:
/* Seen it before? This can happen for loopback, retrans,
* or local packets.
*/
if (!nf_nat_initialized(ct, maniptype)) {
/* Initialize according to the NAT action. */
err = (range && range->flags & NF_NAT_RANGE_MAP_IPS)
/* Action is set up to establish a new
* mapping.
*/
? nf_nat_setup_info(ct, range, maniptype)
: nf_nat_alloc_null_binding(ct, hooknum);
if (err != NF_ACCEPT)
goto push;
}
break;
case IP_CT_ESTABLISHED:
case IP_CT_ESTABLISHED_REPLY:
break;
default:
err = NF_DROP;
goto push;
}
err = nf_nat_packet(ct, ctinfo, hooknum, skb);
push:
skb_push(skb, nh_off);
skb_postpush_rcsum(skb, skb->data, nh_off);
return err;
}
static void ovs_nat_update_key(struct sw_flow_key *key,
const struct sk_buff *skb,
enum nf_nat_manip_type maniptype)
{
if (maniptype == NF_NAT_MANIP_SRC) {
__be16 src;
key->ct_state |= OVS_CS_F_SRC_NAT;
if (key->eth.type == htons(ETH_P_IP))
key->ipv4.addr.src = ip_hdr(skb)->saddr;
else if (key->eth.type == htons(ETH_P_IPV6))
memcpy(&key->ipv6.addr.src, &ipv6_hdr(skb)->saddr,
sizeof(key->ipv6.addr.src));
else
return;
if (key->ip.proto == IPPROTO_UDP)
src = udp_hdr(skb)->source;
else if (key->ip.proto == IPPROTO_TCP)
src = tcp_hdr(skb)->source;
else if (key->ip.proto == IPPROTO_SCTP)
src = sctp_hdr(skb)->source;
else
return;
key->tp.src = src;
} else {
__be16 dst;
key->ct_state |= OVS_CS_F_DST_NAT;
if (key->eth.type == htons(ETH_P_IP))
key->ipv4.addr.dst = ip_hdr(skb)->daddr;
else if (key->eth.type == htons(ETH_P_IPV6))
memcpy(&key->ipv6.addr.dst, &ipv6_hdr(skb)->daddr,
sizeof(key->ipv6.addr.dst));
else
return;
if (key->ip.proto == IPPROTO_UDP)
dst = udp_hdr(skb)->dest;
else if (key->ip.proto == IPPROTO_TCP)
dst = tcp_hdr(skb)->dest;
else if (key->ip.proto == IPPROTO_SCTP)
dst = sctp_hdr(skb)->dest;
else
return;
key->tp.dst = dst;
}
}
/* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
const struct ovs_conntrack_info *info,
struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo)
{
enum nf_nat_manip_type maniptype;
int err;
#ifdef HAVE_NF_CT_IS_UNTRACKED
if (nf_ct_is_untracked(ct)) {
/* A NAT action may only be performed on tracked packets. */
return NF_ACCEPT;
}
#endif /* HAVE_NF_CT_IS_UNTRACKED */
/* Add NAT extension if not confirmed yet. */
if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
return NF_ACCEPT; /* Can't NAT. */
/* Determine NAT type.
* Check if the NAT type can be deduced from the tracked connection.
* Make sure new expected connections (IP_CT_RELATED) are NATted only
* when committing.
*/
if (info->nat & OVS_CT_NAT && ctinfo != IP_CT_NEW &&
ct->status & IPS_NAT_MASK &&
(ctinfo != IP_CT_RELATED || info->commit)) {
/* NAT an established or related connection like before. */
if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY)
/* This is the REPLY direction for a connection
* for which NAT was applied in the forward
* direction. Do the reverse NAT.
*/
maniptype = ct->status & IPS_SRC_NAT
? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC;
else
maniptype = ct->status & IPS_SRC_NAT
? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST;
} else if (info->nat & OVS_CT_SRC_NAT) {
maniptype = NF_NAT_MANIP_SRC;
} else if (info->nat & OVS_CT_DST_NAT) {
maniptype = NF_NAT_MANIP_DST;
} else {
return NF_ACCEPT; /* Connection is not NATed. */
}
err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype);
/* Mark NAT done if successful and update the flow key. */
if (err == NF_ACCEPT)
ovs_nat_update_key(key, skb, maniptype);
return err;
}
#else /* !CONFIG_NF_NAT_NEEDED */
static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
const struct ovs_conntrack_info *info,
struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo)
{
return NF_ACCEPT;
}
#endif
/* Pass 'skb' through conntrack in 'net', using zone configured in 'info', if
* not done already. Update key with new CT state after passing the packet
* through conntrack.
* Note that if the packet is deemed invalid by conntrack, skb->_nfct will be
* set to NULL and 0 will be returned.
*/
static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
const struct ovs_conntrack_info *info,
struct sk_buff *skb)
{
/* If we are recirculating packets to match on conntrack fields and
* committing with a separate conntrack action, then we don't need to
* actually run the packet through conntrack twice unless it's for a
* different zone.
*/
bool cached = skb_nfct_cached(net, key, info, skb);
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
if (!cached) {
struct nf_conn *tmpl = info->ct;
int err;
/* Associate skb with specified zone. */
if (tmpl) {
if (skb_nfct(skb))
nf_conntrack_put(skb_nfct(skb));
nf_conntrack_get(&tmpl->ct_general);
nf_ct_set(skb, tmpl, IP_CT_NEW);
}