forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
act_ct.c
1642 lines (1378 loc) · 40 KB
/
act_ct.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/* -
* net/sched/act_ct.c Connection Tracking action
*
* Authors: Paul Blakey <[email protected]>
* Yossi Kuperman <[email protected]>
* Marcelo Ricardo Leitner <[email protected]>
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/pkt_cls.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/rhashtable.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <net/act_api.h>
#include <net/ip.h>
#include <net/ipv6_frag.h>
#include <uapi/linux/tc_act/tc_ct.h>
#include <net/tc_act/tc_ct.h>
#include <net/tc_wrapper.h>
#include <net/netfilter/nf_flow_table.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_acct.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include <net/netfilter/nf_conntrack_act_ct.h>
#include <net/netfilter/nf_conntrack_seqadj.h>
#include <uapi/linux/netfilter/nf_nat.h>
static struct workqueue_struct *act_ct_wq;
static struct rhashtable zones_ht;
static DEFINE_MUTEX(zones_mutex);
struct tcf_ct_flow_table {
struct rhash_head node; /* In zones tables */
struct rcu_work rwork;
struct nf_flowtable nf_ft;
refcount_t ref;
u16 zone;
bool dying;
};
static const struct rhashtable_params zones_params = {
.head_offset = offsetof(struct tcf_ct_flow_table, node),
.key_offset = offsetof(struct tcf_ct_flow_table, zone),
.key_len = sizeof_field(struct tcf_ct_flow_table, zone),
.automatic_shrinking = true,
};
static struct flow_action_entry *
tcf_ct_flow_table_flow_action_get_next(struct flow_action *flow_action)
{
int i = flow_action->num_entries++;
return &flow_action->entries[i];
}
static void tcf_ct_add_mangle_action(struct flow_action *action,
enum flow_action_mangle_base htype,
u32 offset,
u32 mask,
u32 val)
{
struct flow_action_entry *entry;
entry = tcf_ct_flow_table_flow_action_get_next(action);
entry->id = FLOW_ACTION_MANGLE;
entry->mangle.htype = htype;
entry->mangle.mask = ~mask;
entry->mangle.offset = offset;
entry->mangle.val = val;
}
/* The following nat helper functions check if the inverted reverse tuple
* (target) is different then the current dir tuple - meaning nat for ports
* and/or ip is needed, and add the relevant mangle actions.
*/
static void
tcf_ct_flow_table_add_action_nat_ipv4(const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple target,
struct flow_action *action)
{
if (memcmp(&target.src.u3, &tuple->src.u3, sizeof(target.src.u3)))
tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP4,
offsetof(struct iphdr, saddr),
0xFFFFFFFF,
be32_to_cpu(target.src.u3.ip));
if (memcmp(&target.dst.u3, &tuple->dst.u3, sizeof(target.dst.u3)))
tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP4,
offsetof(struct iphdr, daddr),
0xFFFFFFFF,
be32_to_cpu(target.dst.u3.ip));
}
static void
tcf_ct_add_ipv6_addr_mangle_action(struct flow_action *action,
union nf_inet_addr *addr,
u32 offset)
{
int i;
for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i++)
tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP6,
i * sizeof(u32) + offset,
0xFFFFFFFF, be32_to_cpu(addr->ip6[i]));
}
static void
tcf_ct_flow_table_add_action_nat_ipv6(const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple target,
struct flow_action *action)
{
if (memcmp(&target.src.u3, &tuple->src.u3, sizeof(target.src.u3)))
tcf_ct_add_ipv6_addr_mangle_action(action, &target.src.u3,
offsetof(struct ipv6hdr,
saddr));
if (memcmp(&target.dst.u3, &tuple->dst.u3, sizeof(target.dst.u3)))
tcf_ct_add_ipv6_addr_mangle_action(action, &target.dst.u3,
offsetof(struct ipv6hdr,
daddr));
}
static void
tcf_ct_flow_table_add_action_nat_tcp(const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple target,
struct flow_action *action)
{
__be16 target_src = target.src.u.tcp.port;
__be16 target_dst = target.dst.u.tcp.port;
if (target_src != tuple->src.u.tcp.port)
tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP,
offsetof(struct tcphdr, source),
0xFFFF, be16_to_cpu(target_src));
if (target_dst != tuple->dst.u.tcp.port)
tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP,
offsetof(struct tcphdr, dest),
0xFFFF, be16_to_cpu(target_dst));
}
static void
tcf_ct_flow_table_add_action_nat_udp(const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple target,
struct flow_action *action)
{
__be16 target_src = target.src.u.udp.port;
__be16 target_dst = target.dst.u.udp.port;
if (target_src != tuple->src.u.udp.port)
tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP,
offsetof(struct udphdr, source),
0xFFFF, be16_to_cpu(target_src));
if (target_dst != tuple->dst.u.udp.port)
tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP,
offsetof(struct udphdr, dest),
0xFFFF, be16_to_cpu(target_dst));
}
static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct,
enum ip_conntrack_dir dir,
enum ip_conntrack_info ctinfo,
struct flow_action *action)
{
struct nf_conn_labels *ct_labels;
struct flow_action_entry *entry;
u32 *act_ct_labels;
entry = tcf_ct_flow_table_flow_action_get_next(action);
entry->id = FLOW_ACTION_CT_METADATA;
#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
entry->ct_metadata.mark = READ_ONCE(ct->mark);
#endif
/* aligns with the CT reference on the SKB nf_ct_set */
entry->ct_metadata.cookie = (unsigned long)ct | ctinfo;
entry->ct_metadata.orig_dir = dir == IP_CT_DIR_ORIGINAL;
act_ct_labels = entry->ct_metadata.labels;
ct_labels = nf_ct_labels_find(ct);
if (ct_labels)
memcpy(act_ct_labels, ct_labels->bits, NF_CT_LABELS_MAX_SIZE);
else
memset(act_ct_labels, 0, NF_CT_LABELS_MAX_SIZE);
}
static int tcf_ct_flow_table_add_action_nat(struct net *net,
struct nf_conn *ct,
enum ip_conntrack_dir dir,
struct flow_action *action)
{
const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
struct nf_conntrack_tuple target;
if (!(ct->status & IPS_NAT_MASK))
return 0;
nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple);
switch (tuple->src.l3num) {
case NFPROTO_IPV4:
tcf_ct_flow_table_add_action_nat_ipv4(tuple, target,
action);
break;
case NFPROTO_IPV6:
tcf_ct_flow_table_add_action_nat_ipv6(tuple, target,
action);
break;
default:
return -EOPNOTSUPP;
}
switch (nf_ct_protonum(ct)) {
case IPPROTO_TCP:
tcf_ct_flow_table_add_action_nat_tcp(tuple, target, action);
break;
case IPPROTO_UDP:
tcf_ct_flow_table_add_action_nat_udp(tuple, target, action);
break;
default:
return -EOPNOTSUPP;
}
return 0;
}
static int tcf_ct_flow_table_fill_actions(struct net *net,
struct flow_offload *flow,
enum flow_offload_tuple_dir tdir,
struct nf_flow_rule *flow_rule)
{
struct flow_action *action = &flow_rule->rule->action;
int num_entries = action->num_entries;
struct nf_conn *ct = flow->ct;
enum ip_conntrack_info ctinfo;
enum ip_conntrack_dir dir;
int i, err;
switch (tdir) {
case FLOW_OFFLOAD_DIR_ORIGINAL:
dir = IP_CT_DIR_ORIGINAL;
ctinfo = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ?
IP_CT_ESTABLISHED : IP_CT_NEW;
if (ctinfo == IP_CT_ESTABLISHED)
set_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags);
break;
case FLOW_OFFLOAD_DIR_REPLY:
dir = IP_CT_DIR_REPLY;
ctinfo = IP_CT_ESTABLISHED_REPLY;
break;
default:
return -EOPNOTSUPP;
}
err = tcf_ct_flow_table_add_action_nat(net, ct, dir, action);
if (err)
goto err_nat;
tcf_ct_flow_table_add_action_meta(ct, dir, ctinfo, action);
return 0;
err_nat:
/* Clear filled actions */
for (i = num_entries; i < action->num_entries; i++)
memset(&action->entries[i], 0, sizeof(action->entries[i]));
action->num_entries = num_entries;
return err;
}
static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow)
{
return test_bit(IPS_SEEN_REPLY_BIT, &flow->ct->status) &&
test_bit(IPS_HW_OFFLOAD_BIT, &flow->ct->status) &&
!test_bit(NF_FLOW_HW_PENDING, &flow->flags) &&
!test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags);
}
static struct nf_flowtable_type flowtable_ct = {
.gc = tcf_ct_flow_is_outdated,
.action = tcf_ct_flow_table_fill_actions,
.owner = THIS_MODULE,
};
static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params)
{
struct tcf_ct_flow_table *ct_ft;
int err = -ENOMEM;
mutex_lock(&zones_mutex);
ct_ft = rhashtable_lookup_fast(&zones_ht, ¶ms->zone, zones_params);
if (ct_ft && refcount_inc_not_zero(&ct_ft->ref))
goto out_unlock;
ct_ft = kzalloc(sizeof(*ct_ft), GFP_KERNEL);
if (!ct_ft)
goto err_alloc;
refcount_set(&ct_ft->ref, 1);
ct_ft->zone = params->zone;
err = rhashtable_insert_fast(&zones_ht, &ct_ft->node, zones_params);
if (err)
goto err_insert;
ct_ft->nf_ft.type = &flowtable_ct;
ct_ft->nf_ft.flags |= NF_FLOWTABLE_HW_OFFLOAD |
NF_FLOWTABLE_COUNTER;
err = nf_flow_table_init(&ct_ft->nf_ft);
if (err)
goto err_init;
write_pnet(&ct_ft->nf_ft.net, net);
__module_get(THIS_MODULE);
out_unlock:
params->ct_ft = ct_ft;
params->nf_ft = &ct_ft->nf_ft;
mutex_unlock(&zones_mutex);
return 0;
err_init:
rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params);
err_insert:
kfree(ct_ft);
err_alloc:
mutex_unlock(&zones_mutex);
return err;
}
static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
{
struct flow_block_cb *block_cb, *tmp_cb;
struct tcf_ct_flow_table *ct_ft;
struct flow_block *block;
ct_ft = container_of(to_rcu_work(work), struct tcf_ct_flow_table,
rwork);
nf_flow_table_free(&ct_ft->nf_ft);
/* Remove any remaining callbacks before cleanup */
block = &ct_ft->nf_ft.flow_block;
down_write(&ct_ft->nf_ft.flow_block_lock);
list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) {
list_del(&block_cb->list);
flow_block_cb_free(block_cb);
}
up_write(&ct_ft->nf_ft.flow_block_lock);
kfree(ct_ft);
module_put(THIS_MODULE);
}
static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft)
{
if (refcount_dec_and_test(&ct_ft->ref)) {
rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params);
INIT_RCU_WORK(&ct_ft->rwork, tcf_ct_flow_table_cleanup_work);
queue_rcu_work(act_ct_wq, &ct_ft->rwork);
}
}
static void tcf_ct_flow_tc_ifidx(struct flow_offload *entry,
struct nf_conn_act_ct_ext *act_ct_ext, u8 dir)
{
entry->tuplehash[dir].tuple.xmit_type = FLOW_OFFLOAD_XMIT_TC;
entry->tuplehash[dir].tuple.tc.iifidx = act_ct_ext->ifindex[dir];
}
static void tcf_ct_flow_ct_ext_ifidx_update(struct flow_offload *entry)
{
struct nf_conn_act_ct_ext *act_ct_ext;
act_ct_ext = nf_conn_act_ct_ext_find(entry->ct);
if (act_ct_ext) {
tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL);
tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY);
}
}
static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft,
struct nf_conn *ct,
bool tcp, bool bidirectional)
{
struct nf_conn_act_ct_ext *act_ct_ext;
struct flow_offload *entry;
int err;
if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status))
return;
entry = flow_offload_alloc(ct);
if (!entry) {
WARN_ON_ONCE(1);
goto err_alloc;
}
if (tcp) {
ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
}
if (bidirectional)
__set_bit(NF_FLOW_HW_BIDIRECTIONAL, &entry->flags);
act_ct_ext = nf_conn_act_ct_ext_find(ct);
if (act_ct_ext) {
tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL);
tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY);
}
err = flow_offload_add(&ct_ft->nf_ft, entry);
if (err)
goto err_add;
return;
err_add:
flow_offload_free(entry);
err_alloc:
clear_bit(IPS_OFFLOAD_BIT, &ct->status);
}
static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo)
{
bool tcp = false, bidirectional = true;
switch (nf_ct_protonum(ct)) {
case IPPROTO_TCP:
if ((ctinfo != IP_CT_ESTABLISHED &&
ctinfo != IP_CT_ESTABLISHED_REPLY) ||
!test_bit(IPS_ASSURED_BIT, &ct->status) ||
ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED)
return;
tcp = true;
break;
case IPPROTO_UDP:
if (!nf_ct_is_confirmed(ct))
return;
if (!test_bit(IPS_ASSURED_BIT, &ct->status))
bidirectional = false;
break;
#ifdef CONFIG_NF_CT_PROTO_GRE
case IPPROTO_GRE: {
struct nf_conntrack_tuple *tuple;
if ((ctinfo != IP_CT_ESTABLISHED &&
ctinfo != IP_CT_ESTABLISHED_REPLY) ||
!test_bit(IPS_ASSURED_BIT, &ct->status) ||
ct->status & IPS_NAT_MASK)
return;
tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
/* No support for GRE v1 */
if (tuple->src.u.gre.key || tuple->dst.u.gre.key)
return;
break;
}
#endif
default:
return;
}
if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) ||
ct->status & IPS_SEQ_ADJUST)
return;
tcf_ct_flow_table_add(ct_ft, ct, tcp, bidirectional);
}
static bool
tcf_ct_flow_table_fill_tuple_ipv4(struct sk_buff *skb,
struct flow_offload_tuple *tuple,
struct tcphdr **tcph)
{
struct flow_ports *ports;
unsigned int thoff;
struct iphdr *iph;
size_t hdrsize;
u8 ipproto;
if (!pskb_network_may_pull(skb, sizeof(*iph)))
return false;
iph = ip_hdr(skb);
thoff = iph->ihl * 4;
if (ip_is_fragment(iph) ||
unlikely(thoff != sizeof(struct iphdr)))
return false;
ipproto = iph->protocol;
switch (ipproto) {
case IPPROTO_TCP:
hdrsize = sizeof(struct tcphdr);
break;
case IPPROTO_UDP:
hdrsize = sizeof(*ports);
break;
#ifdef CONFIG_NF_CT_PROTO_GRE
case IPPROTO_GRE:
hdrsize = sizeof(struct gre_base_hdr);
break;
#endif
default:
return false;
}
if (iph->ttl <= 1)
return false;
if (!pskb_network_may_pull(skb, thoff + hdrsize))
return false;
switch (ipproto) {
case IPPROTO_TCP:
*tcph = (void *)(skb_network_header(skb) + thoff);
fallthrough;
case IPPROTO_UDP:
ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
tuple->src_port = ports->source;
tuple->dst_port = ports->dest;
break;
case IPPROTO_GRE: {
struct gre_base_hdr *greh;
greh = (struct gre_base_hdr *)(skb_network_header(skb) + thoff);
if ((greh->flags & GRE_VERSION) != GRE_VERSION_0)
return false;
break;
}
}
iph = ip_hdr(skb);
tuple->src_v4.s_addr = iph->saddr;
tuple->dst_v4.s_addr = iph->daddr;
tuple->l3proto = AF_INET;
tuple->l4proto = ipproto;
return true;
}
static bool
tcf_ct_flow_table_fill_tuple_ipv6(struct sk_buff *skb,
struct flow_offload_tuple *tuple,
struct tcphdr **tcph)
{
struct flow_ports *ports;
struct ipv6hdr *ip6h;
unsigned int thoff;
size_t hdrsize;
u8 nexthdr;
if (!pskb_network_may_pull(skb, sizeof(*ip6h)))
return false;
ip6h = ipv6_hdr(skb);
thoff = sizeof(*ip6h);
nexthdr = ip6h->nexthdr;
switch (nexthdr) {
case IPPROTO_TCP:
hdrsize = sizeof(struct tcphdr);
break;
case IPPROTO_UDP:
hdrsize = sizeof(*ports);
break;
#ifdef CONFIG_NF_CT_PROTO_GRE
case IPPROTO_GRE:
hdrsize = sizeof(struct gre_base_hdr);
break;
#endif
default:
return false;
}
if (ip6h->hop_limit <= 1)
return false;
if (!pskb_network_may_pull(skb, thoff + hdrsize))
return false;
switch (nexthdr) {
case IPPROTO_TCP:
*tcph = (void *)(skb_network_header(skb) + thoff);
fallthrough;
case IPPROTO_UDP:
ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
tuple->src_port = ports->source;
tuple->dst_port = ports->dest;
break;
case IPPROTO_GRE: {
struct gre_base_hdr *greh;
greh = (struct gre_base_hdr *)(skb_network_header(skb) + thoff);
if ((greh->flags & GRE_VERSION) != GRE_VERSION_0)
return false;
break;
}
}
ip6h = ipv6_hdr(skb);
tuple->src_v6 = ip6h->saddr;
tuple->dst_v6 = ip6h->daddr;
tuple->l3proto = AF_INET6;
tuple->l4proto = nexthdr;
return true;
}
static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p,
struct sk_buff *skb,
u8 family)
{
struct nf_flowtable *nf_ft = &p->ct_ft->nf_ft;
struct flow_offload_tuple_rhash *tuplehash;
struct flow_offload_tuple tuple = {};
enum ip_conntrack_info ctinfo;
struct tcphdr *tcph = NULL;
bool force_refresh = false;
struct flow_offload *flow;
struct nf_conn *ct;
u8 dir;
switch (family) {
case NFPROTO_IPV4:
if (!tcf_ct_flow_table_fill_tuple_ipv4(skb, &tuple, &tcph))
return false;
break;
case NFPROTO_IPV6:
if (!tcf_ct_flow_table_fill_tuple_ipv6(skb, &tuple, &tcph))
return false;
break;
default:
return false;
}
tuplehash = flow_offload_lookup(nf_ft, &tuple);
if (!tuplehash)
return false;
dir = tuplehash->tuple.dir;
flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
ct = flow->ct;
if (dir == FLOW_OFFLOAD_DIR_REPLY &&
!test_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags)) {
/* Only offload reply direction after connection became
* assured.
*/
if (test_bit(IPS_ASSURED_BIT, &ct->status))
set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags);
else if (test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags))
/* If flow_table flow has already been updated to the
* established state, then don't refresh.
*/
return false;
force_refresh = true;
}
if (tcph && (unlikely(tcph->fin || tcph->rst))) {
flow_offload_teardown(flow);
return false;
}
if (dir == FLOW_OFFLOAD_DIR_ORIGINAL)
ctinfo = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ?
IP_CT_ESTABLISHED : IP_CT_NEW;
else
ctinfo = IP_CT_ESTABLISHED_REPLY;
nf_conn_act_ct_ext_fill(skb, ct, ctinfo);
tcf_ct_flow_ct_ext_ifidx_update(flow);
flow_offload_refresh(nf_ft, flow, force_refresh);
if (!test_bit(IPS_ASSURED_BIT, &ct->status)) {
/* Process this flow in SW to allow promoting to ASSURED */
return false;
}
nf_conntrack_get(&ct->ct_general);
nf_ct_set(skb, ct, ctinfo);
if (nf_ft->flags & NF_FLOWTABLE_COUNTER)
nf_ct_acct_update(ct, dir, skb->len);
return true;
}
static int tcf_ct_flow_tables_init(void)
{
return rhashtable_init(&zones_ht, &zones_params);
}
static void tcf_ct_flow_tables_uninit(void)
{
rhashtable_destroy(&zones_ht);
}
static struct tc_action_ops act_ct_ops;
struct tc_ct_action_net {
struct tc_action_net tn; /* Must be first */
};
/* Determine whether skb->_nfct is equal to the result of conntrack lookup. */
static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb,
struct tcf_ct_params *p)
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
ct = nf_ct_get(skb, &ctinfo);
if (!ct)
return false;
if (!net_eq(net, read_pnet(&ct->ct_net)))
goto drop_ct;
if (nf_ct_zone(ct)->id != p->zone)
goto drop_ct;
if (p->helper) {
struct nf_conn_help *help;
help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER);
if (help && rcu_access_pointer(help->helper) != p->helper)
goto drop_ct;
}
/* Force conntrack entry direction. */
if ((p->ct_action & TCA_CT_ACT_FORCE) &&
CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
if (nf_ct_is_confirmed(ct))
nf_ct_kill(ct);
goto drop_ct;
}
return true;
drop_ct:
nf_ct_put(ct);
nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
return false;
}
static u8 tcf_ct_skb_nf_family(struct sk_buff *skb)
{
u8 family = NFPROTO_UNSPEC;
switch (skb_protocol(skb, true)) {
case htons(ETH_P_IP):
family = NFPROTO_IPV4;
break;
case htons(ETH_P_IPV6):
family = NFPROTO_IPV6;
break;
default:
break;
}
return family;
}
static int tcf_ct_ipv4_is_fragment(struct sk_buff *skb, bool *frag)
{
unsigned int len;
len = skb_network_offset(skb) + sizeof(struct iphdr);
if (unlikely(skb->len < len))
return -EINVAL;
if (unlikely(!pskb_may_pull(skb, len)))
return -ENOMEM;
*frag = ip_is_fragment(ip_hdr(skb));
return 0;
}
static int tcf_ct_ipv6_is_fragment(struct sk_buff *skb, bool *frag)
{
unsigned int flags = 0, len, payload_ofs = 0;
unsigned short frag_off;
int nexthdr;
len = skb_network_offset(skb) + sizeof(struct ipv6hdr);
if (unlikely(skb->len < len))
return -EINVAL;
if (unlikely(!pskb_may_pull(skb, len)))
return -ENOMEM;
nexthdr = ipv6_find_hdr(skb, &payload_ofs, -1, &frag_off, &flags);
if (unlikely(nexthdr < 0))
return -EPROTO;
*frag = flags & IP6_FH_F_FRAG;
return 0;
}
static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
u8 family, u16 zone, bool *defrag)
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
int err = 0;
bool frag;
u8 proto;
u16 mru;
/* Previously seen (loopback)? Ignore. */
ct = nf_ct_get(skb, &ctinfo);
if ((ct && !nf_ct_is_template(ct)) || ctinfo == IP_CT_UNTRACKED)
return 0;
if (family == NFPROTO_IPV4)
err = tcf_ct_ipv4_is_fragment(skb, &frag);
else
err = tcf_ct_ipv6_is_fragment(skb, &frag);
if (err || !frag)
return err;
skb_get(skb);
err = nf_ct_handle_fragments(net, skb, zone, family, &proto, &mru);
if (err)
return err;
*defrag = true;
tc_skb_cb(skb)->mru = mru;
return 0;
}
static void tcf_ct_params_free(struct tcf_ct_params *params)
{
if (params->helper) {
#if IS_ENABLED(CONFIG_NF_NAT)
if (params->ct_action & TCA_CT_ACT_NAT)
nf_nat_helper_put(params->helper);
#endif
nf_conntrack_helper_put(params->helper);
}
if (params->ct_ft)
tcf_ct_flow_table_put(params->ct_ft);
if (params->tmpl) {
if (params->put_labels)
nf_connlabels_put(nf_ct_net(params->tmpl));
nf_ct_put(params->tmpl);
}
kfree(params);
}
static void tcf_ct_params_free_rcu(struct rcu_head *head)
{
struct tcf_ct_params *params;
params = container_of(head, struct tcf_ct_params, rcu);
tcf_ct_params_free(params);
}
static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask)
{
#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
u32 new_mark;
if (!mask)
return;
new_mark = mark | (READ_ONCE(ct->mark) & ~(mask));
if (READ_ONCE(ct->mark) != new_mark) {
WRITE_ONCE(ct->mark, new_mark);
if (nf_ct_is_confirmed(ct))
nf_conntrack_event_cache(IPCT_MARK, ct);
}
#endif
}
static void tcf_ct_act_set_labels(struct nf_conn *ct,
u32 *labels,
u32 *labels_m)
{
#if IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)
size_t labels_sz = sizeof_field(struct tcf_ct_params, labels);
if (!memchr_inv(labels_m, 0, labels_sz))
return;
nf_connlabels_replace(ct, labels, labels_m, 4);
#endif
}
static int tcf_ct_act_nat(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
int ct_action,
struct nf_nat_range2 *range,
bool commit)
{
#if IS_ENABLED(CONFIG_NF_NAT)
int err, action = 0;
if (!(ct_action & TCA_CT_ACT_NAT))
return NF_ACCEPT;
if (ct_action & TCA_CT_ACT_NAT_SRC)
action |= BIT(NF_NAT_MANIP_SRC);
if (ct_action & TCA_CT_ACT_NAT_DST)
action |= BIT(NF_NAT_MANIP_DST);
err = nf_ct_nat(skb, ct, ctinfo, &action, range, commit);
if (action & BIT(NF_NAT_MANIP_SRC))
tc_skb_cb(skb)->post_ct_snat = 1;
if (action & BIT(NF_NAT_MANIP_DST))
tc_skb_cb(skb)->post_ct_dnat = 1;
return err;
#else
return NF_ACCEPT;
#endif
}
TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct net *net = dev_net(skb->dev);
enum ip_conntrack_info ctinfo;
struct tcf_ct *c = to_ct(a);
struct nf_conn *tmpl = NULL;
struct nf_hook_state state;
bool cached, commit, clear;
int nh_ofs, err, retval;
struct tcf_ct_params *p;
bool add_helper = false;
bool skip_add = false;
bool defrag = false;
struct nf_conn *ct;
u8 family;
p = rcu_dereference_bh(c->params);
retval = READ_ONCE(c->tcf_action);
commit = p->ct_action & TCA_CT_ACT_COMMIT;
clear = p->ct_action & TCA_CT_ACT_CLEAR;
tmpl = p->tmpl;
tcf_lastuse_update(&c->tcf_tm);
tcf_action_update_bstats(&c->common, skb);
if (clear) {
tc_skb_cb(skb)->post_ct = false;
ct = nf_ct_get(skb, &ctinfo);
if (ct) {
nf_ct_put(ct);
nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
}
goto out_clear;
}
family = tcf_ct_skb_nf_family(skb);
if (family == NFPROTO_UNSPEC)
goto drop;
/* The conntrack module expects to be working at L3.
* We also try to pull the IPv4/6 header to linear area
*/
nh_ofs = skb_network_offset(skb);
skb_pull_rcsum(skb, nh_ofs);
err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag);
if (err == -EINPROGRESS) {
retval = TC_ACT_STOLEN;
goto out_clear;
}
if (err)
goto drop;
err = nf_ct_skb_network_trim(skb, family);
if (err)
goto drop;
/* If we are recirculating packets to match on ct fields and
* committing with a separate ct action, then we don't need to
* actually run the packet through conntrack twice unless it's for a
* different zone.
*/
cached = tcf_ct_skb_nfct_cached(net, skb, p);
if (!cached) {
if (tcf_ct_flow_table_lookup(p, skb, family)) {
skip_add = true;
goto do_nat;