summaryrefslogtreecommitdiffstats
path: root/net/sched/act_ct.c
blob: 1b4b3514c94f2a29b46a4c481cfc057c4e864ec8 (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
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/* -
 * net/sched/act_ct.c  Connection Tracking action
 *
 * Authors:   Paul Blakey <paulb@mellanox.com>
 *            Yossi Kuperman <yossiku@mellanox.com>
 *            Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
 */

#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/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 <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,
					      struct flow_action *action)
{
	struct nf_conn_labels *ct_labels;
	struct flow_action_entry *entry;
	enum ip_conntrack_info ctinfo;
	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 = ct->mark;
#endif
	ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED :
					     IP_CT_ESTABLISHED_REPLY;
	/* 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,
					  const 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_dir dir;
	int i, err;

	switch (tdir) {
	case FLOW_OFFLOAD_DIR_ORIGINAL:
		dir = IP_CT_DIR_ORIGINAL;
		break;
	case FLOW_OFFLOAD_DIR_REPLY:
		dir = IP_CT_DIR_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, 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 struct nf_flowtable_type flowtable_ct = {
	.action		= tcf_ct_flow_table_fill_actions,
	.owner		= THIS_MODULE,
};

static int tcf_ct_flow_table_get(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, &params->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;

	__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_params *params)
{
	struct tcf_ct_flow_table *ct_ft = params->ct_ft;

	if (refcount_dec_and_test(&params->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_table_add(struct tcf_ct_flow_table *ct_ft,
				  struct nf_conn *ct,
				  bool tcp)
{
	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;
	}

	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;

	if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY)
		return;

	switch (nf_ct_protonum(ct)) {
	case IPPROTO_TCP:
		tcp = true;
		if (ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED)
			return;
		break;
	case IPPROTO_UDP:
		break;
	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);
}

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;

	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;

	if (iph->protocol != IPPROTO_TCP &&
	    iph->protocol != IPPROTO_UDP)
		return false;

	if (iph->ttl <= 1)
		return false;

	if (!pskb_network_may_pull(skb, iph->protocol == IPPROTO_TCP ?
					thoff + sizeof(struct tcphdr) :
					thoff + sizeof(*ports)))
		return false;

	iph = ip_hdr(skb);
	if (iph->protocol == IPPROTO_TCP)
		*tcph = (void *)(skb_network_header(skb) + thoff);

	ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
	tuple->src_v4.s_addr = iph->saddr;
	tuple->dst_v4.s_addr = iph->daddr;
	tuple->src_port = ports->source;
	tuple->dst_port = ports->dest;
	tuple->l3proto = AF_INET;
	tuple->l4proto = iph->protocol;

	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;

	if (!pskb_network_may_pull(skb, sizeof(*ip6h)))
		return false;

	ip6h = ipv6_hdr(skb);

	if (ip6h->nexthdr != IPPROTO_TCP &&
	    ip6h->nexthdr != IPPROTO_UDP)
		return false;

	if (ip6h->hop_limit <= 1)
		return false;

	thoff = sizeof(*ip6h);
	if (!pskb_network_may_pull(skb, ip6h->nexthdr == IPPROTO_TCP ?
					thoff + sizeof(struct tcphdr) :
					thoff + sizeof(*ports)))
		return false;

	ip6h = ipv6_hdr(skb);
	if (ip6h->nexthdr == IPPROTO_TCP)
		*tcph = (void *)(skb_network_header(skb) + thoff);

	ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
	tuple->src_v6 = ip6h->saddr;
	tuple->dst_v6 = ip6h->daddr;
	tuple->src_port = ports->source;
	tuple->dst_port = ports->dest;
	tuple->l3proto = AF_INET6;
	tuple->l4proto = ip6h->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;
	struct flow_offload *flow;
	struct nf_conn *ct;
	u8 dir;

	/* Previously seen or loopback */
	ct = nf_ct_get(skb, &ctinfo);
	if ((ct && !nf_ct_is_template(ct)) || ctinfo == IP_CT_UNTRACKED)
		return false;

	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 (tcph && (unlikely(tcph->fin || tcph->rst))) {
		flow_offload_teardown(flow);
		return false;
	}

	ctinfo = dir == FLOW_OFFLOAD_DIR_ORIGINAL ? IP_CT_ESTABLISHED :
						    IP_CT_ESTABLISHED_REPLY;

	flow_offload_refresh(nf_ft, flow);
	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;
static unsigned int ct_net_id;

struct tc_ct_action_net {
	struct tc_action_net tn; /* Must be first */
	bool labels;
};

/* 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,
				   u16 zone_id, bool force)
{
	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)))
		return false;
	if (nf_ct_zone(ct)->id != zone_id)
		return false;

	/* Force conntrack entry direction. */
	if (force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
		if (nf_ct_is_confirmed(ct))
			nf_ct_kill(ct);

		nf_conntrack_put(&ct->ct_general);
		nf_ct_set(skb, NULL, IP_CT_UNTRACKED);

		return false;
	}

	return true;
}

/* Trim the skb to the length specified by the IP/IPv6 header,
 * removing any trailing lower-layer padding. This prepares the skb
 * for higher-layer processing that assumes skb->len excludes padding
 * (such as nf_ip_checksum). The caller needs to pull the skb to the
 * network header, and ensure ip_hdr/ipv6_hdr points to valid data.
 */
static int tcf_ct_skb_network_trim(struct sk_buff *skb, int family)
{
	unsigned int len;
	int err;

	switch (family) {
	case NFPROTO_IPV4:
		len = ntohs(ip_hdr(skb)->tot_len);
		break;
	case NFPROTO_IPV6:
		len = sizeof(struct ipv6hdr)
			+ ntohs(ipv6_hdr(skb)->payload_len);
		break;
	default:
		len = skb->len;
	}

	err = pskb_trim_rcsum(skb, len);

	return err;
}

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 qdisc_skb_cb cb;
	struct nf_conn *ct;
	int err = 0;
	bool frag;

	/* 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);
	cb = *qdisc_skb_cb(skb);

	if (family == NFPROTO_IPV4) {
		enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;

		memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
		local_bh_disable();
		err = ip_defrag(net, skb, user);
		local_bh_enable();
		if (err && err != -EINPROGRESS)
			return err;

		if (!err) {
			*defrag = true;
			cb.mru = IPCB(skb)->frag_max_size;
		}
	} else { /* NFPROTO_IPV6 */
#if IS_ENABLED(CONFIG_NF_DEFRAG_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 && err != -EINPROGRESS)
			goto out_free;

		if (!err) {
			*defrag = true;
			cb.mru = IP6CB(skb)->frag_max_size;
		}
#else
		err = -EOPNOTSUPP;
		goto out_free;
#endif
	}

	if (err != -EINPROGRESS)
		*qdisc_skb_cb(skb) = cb;
	skb_clear_hash(skb);
	skb->ignore_df = 1;
	return err;

out_free:
	kfree_skb(skb);
	return err;
}

static void tcf_ct_params_free(struct rcu_head *head)
{
	struct tcf_ct_params *params = container_of(head,
						    struct tcf_ct_params, rcu);

	tcf_ct_flow_table_put(params);

	if (params->tmpl)
		nf_conntrack_put(&params->tmpl->ct_general);
	kfree(params);
}

#if IS_ENABLED(CONFIG_NF_NAT)
/* 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 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)
{
	__be16 proto = skb_protocol(skb, true);
	int hooknum, err = NF_ACCEPT;

	/* 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 (proto == htons(ETH_P_IP) &&
		    ip_hdr(skb)->protocol == IPPROTO_ICMP) {
			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
							   hooknum))
				err = NF_DROP;
			goto out;
		} else if (IS_ENABLED(CONFIG_IPV6) && proto == 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 out;
			}
		}
		/* Non-ICMP, fall thru to initialize if needed. */
		fallthrough;
	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 out;
		}
		break;

	case IP_CT_ESTABLISHED:
	case IP_CT_ESTABLISHED_REPLY:
		break;

	default:
		err = NF_DROP;
		goto out;
	}

	err = nf_nat_packet(ct, ctinfo, hooknum, skb);
out:
	return err;
}
#endif /* CONFIG_NF_NAT */

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 | (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);
	}
#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;
	enum nf_nat_manip_type maniptype;

	if (!(ct_action & TCA_CT_ACT_NAT))
		return NF_ACCEPT;

	/* Add NAT extension if not confirmed yet. */
	if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
		return NF_DROP;   /* Can't NAT. */

	if (ctinfo != IP_CT_NEW && (ct->status & IPS_NAT_MASK) &&
	    (ctinfo != IP_CT_RELATED || 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 (ct_action & TCA_CT_ACT_NAT_SRC) {
		maniptype = NF_NAT_MANIP_SRC;
	} else if (ct_action & TCA_CT_ACT_NAT_DST) {
		maniptype = NF_NAT_MANIP_DST;
	} else {
		return NF_ACCEPT;
	}

	err = ct_nat_execute(skb, ct, ctinfo, range, maniptype);
	if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) {
		if (ct->status & IPS_SRC_NAT) {
			if (maniptype == NF_NAT_MANIP_SRC)
				maniptype = NF_NAT_MANIP_DST;
			else
				maniptype = NF_NAT_MANIP_SRC;

			err = ct_nat_execute(skb, ct, ctinfo, range,
					     maniptype);
		} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
			err = ct_nat_execute(skb, ct, ctinfo, NULL,
					     NF_NAT_MANIP_SRC);
		}
	}
	return err;
#else
	return NF_ACCEPT;
#endif
}

static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
		      struct tcf_result *res)
{
	struct net *net = dev_net(skb->dev);
	bool cached, commit, clear, force;
	enum ip_conntrack_info ctinfo;
	struct tcf_ct *c = to_ct(a);
	struct nf_conn *tmpl = NULL;
	struct nf_hook_state state;
	int nh_ofs, err, retval;
	struct tcf_ct_params *p;
	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;
	force = p->ct_action & TCA_CT_ACT_FORCE;
	tmpl = p->tmpl;

	tcf_lastuse_update(&c->tcf_tm);

	if (clear) {
		qdisc_skb_cb(skb)->post_ct = false;
		ct = nf_ct_get(skb, &ctinfo);
		if (ct) {
			nf_conntrack_put(&ct->ct_general);
			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 = tcf_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->zone, force);
	if (!cached) {
		if (tcf_ct_flow_table_lookup(p, skb, family)) {
			skip_add = true;
			goto do_nat;
		}

		/* Associate skb with specified zone. */
		if (tmpl) {
			nf_conntrack_put(skb_nfct(skb));
			nf_conntrack_get(&tmpl->ct_general);
			nf_ct_set(skb, tmpl, IP_CT_NEW);
		}

		state.hook = NF_INET_PRE_ROUTING;
		state.net = net;
		state.pf = family;
		err = nf_conntrack_in(skb, &state);
		if (err != NF_ACCEPT)
			goto out_push;
	}

do_nat:
	ct = nf_ct_get(skb, &ctinfo);
	if (!ct)
		goto out_push;
	nf_ct_deliver_cached_events(ct);

	err = tcf_ct_act_nat(skb, ct, ctinfo, p->ct_action, &p->range, commit);
	if (err != NF_ACCEPT)
		goto drop;

	if (commit) {
		tcf_ct_act_set_mark(ct, p->mark, p->mark_mask);
		tcf_ct_act_set_labels(ct, p->labels, p->labels_mask);

		/* This will take care of sending queued events
		 * even if the connection is already confirmed.
		 */
		if (nf_conntrack_confirm(skb) != NF_ACCEPT)
			goto drop;
	}

	if (!skip_add)
		tcf_ct_flow_table_process_conn(p->ct_ft, ct, ctinfo);

out_push:
	skb_push_rcsum(skb, nh_ofs);

	qdisc_skb_cb(skb)->post_ct = true;
out_clear:
	tcf_action_update_bstats(&c->common, skb);
	if (defrag)
		qdisc_skb_cb(skb)->pkt_len = skb->len;
	return retval;

drop:
	tcf_action_inc_drop_qstats(&c->common);
	return TC_ACT_SHOT;
}

static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = {
	[TCA_CT_ACTION] = { .type = NLA_U16 },
	[TCA_CT_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_ct)),
	[TCA_CT_ZONE] = { .type = NLA_U16 },
	[TCA_CT_MARK] = { .type = NLA_U32 },
	[TCA_CT_MARK_MASK] = { .type = NLA_U32 },
	[TCA_CT_LABELS] = { .type = NLA_BINARY,
			    .len = 128 / BITS_PER_BYTE },
	[TCA_CT_LABELS_MASK] = { .type = NLA_BINARY,
				 .len = 128 / BITS_PER_BYTE },
	[TCA_CT_NAT_IPV4_MIN] = { .type = NLA_U32 },
	[TCA_CT_NAT_IPV4_MAX] = { .type = NLA_U32 },
	[TCA_CT_NAT_IPV6_MIN] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
	[TCA_CT_NAT_IPV6_MAX] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
	[TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 },
	[TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 },
};

static int tcf_ct_fill_params_nat(struct tcf_ct_params *p,
				  struct tc_ct *parm,
				  struct nlattr **tb,
				  struct netlink_ext_ack *extack)
{
	struct nf_nat_range2 *range;

	if (!(p->ct_action & TCA_CT_ACT_NAT))
		return 0;

	if (!IS_ENABLED(CONFIG_NF_NAT)) {
		NL_SET_ERR_MSG_MOD(extack, "Netfilter nat isn't enabled in kernel");
		return -EOPNOTSUPP;
	}

	if (!(p->ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST)))
		return 0;

	if ((p->ct_action & TCA_CT_ACT_NAT_SRC) &&
	    (p->ct_action & TCA_CT_ACT_NAT_DST)) {
		NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time");
		return -EOPNOTSUPP;
	}

	range = &p->range;
	if (tb[TCA_CT_NAT_IPV4_MIN]) {
		struct nlattr *max_attr = tb[TCA_CT_NAT_IPV4_MAX];

		p->ipv4_range = true;
		range->flags |= NF_NAT_RANGE_MAP_IPS;
		range->min_addr.ip =
			nla_get_in_addr(tb[TCA_CT_NAT_IPV4_MIN]);

		range->max_addr.ip = max_attr ?
				     nla_get_in_addr(max_attr) :
				     range->min_addr.ip;
	} else if (tb[TCA_CT_NAT_IPV6_MIN]) {
		struct nlattr *max_attr = tb[TCA_CT_NAT_IPV6_MAX];

		p->ipv4_range = false;
		range->flags |= NF_NAT_RANGE_MAP_IPS;
		range->min_addr.in6 =
			nla_get_in6_addr(tb[TCA_CT_NAT_IPV6_MIN]);

		range->max_addr.in6 = max_attr ?
				      nla_get_in6_addr(max_attr) :
				      range->min_addr.in6;
	}

	if (tb[TCA_CT_NAT_PORT_MIN]) {
		range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
		range->min_proto.all = nla_get_be16(tb[TCA_CT_NAT_PORT_MIN]);

		range->max_proto.all = tb[TCA_CT_NAT_PORT_MAX] ?
				       nla_get_be16(tb[TCA_CT_NAT_PORT_MAX]) :
				       range->min_proto.all;
	}

	return 0;
}

static void tcf_ct_set_key_val(struct nlattr **tb,
			       void *val, int val_type,
			       void *mask, int mask_type,
			       int len)
{
	if (!tb[val_type])
		return;
	nla_memcpy(val, tb[val_type], len);

	if (!mask)
		return;

	if (mask_type == TCA_CT_UNSPEC || !tb[mask_type])
		memset(mask, 0xff, len);
	else
		nla_memcpy(mask, tb[mask_type], len);
}

static int tcf_ct_fill_params(struct net *net,
			      struct tcf_ct_params *p,
			      struct tc_ct *parm,
			      struct nlattr **tb,
			      struct netlink_ext_ack *extack)
{
	struct tc_ct_action_net *tn = net_generic(net, ct_net_id);
	struct nf_conntrack_zone zone;
	struct nf_conn *tmpl;
	int err;

	p->zone = NF_CT_DEFAULT_ZONE_ID;

	tcf_ct_set_key_val(tb,
			   &p->ct_action, TCA_CT_ACTION,
			   NULL, TCA_CT_UNSPEC,
			   sizeof(p->ct_action));

	if (p->ct_action & TCA_CT_ACT_CLEAR)
		return 0;

	err = tcf_ct_fill_params_nat(p, parm, tb, extack);
	if (err)
		return err;

	if (tb[TCA_CT_MARK]) {
		if (!IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)) {
			NL_SET_ERR_MSG_MOD(extack, "Conntrack mark isn't enabled.");
			return -EOPNOTSUPP;
		}
		tcf_ct_set_key_val(tb,
				   &p->mark, TCA_CT_MARK,
				   &p->mark_mask, TCA_CT_MARK_MASK,
				   sizeof(p->mark));
	}

	if (tb[TCA_CT_LABELS]) {
		if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) {
			NL_SET_ERR_MSG_MOD(extack, "Conntrack labels isn't enabled.");
			return -EOPNOTSUPP;
		}

		if (!tn->labels) {
			NL_SET_ERR_MSG_MOD(extack, "Failed to set connlabel length");
			return -EOPNOTSUPP;
		}
		tcf_ct_set_key_val(tb,
				   p->labels, TCA_CT_LABELS,
				   p->labels_mask, TCA_CT_LABELS_MASK,
				   sizeof(p->labels));
	}

	if (tb[TCA_CT_ZONE]) {
		if (!IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)) {
			NL_SET_ERR_MSG_MOD(extack, "Conntrack zones isn't enabled.");
			return -EOPNOTSUPP;
		}

		tcf_ct_set_key_val(tb,
				   &p->zone, TCA_CT_ZONE,
				   NULL, TCA_CT_UNSPEC,
				   sizeof(p->zone));
	}

	nf_ct_zone_init(&zone, p->zone, NF_CT_DEFAULT_ZONE_DIR, 0);
	tmpl = nf_ct_tmpl_alloc(net, &zone, GFP_KERNEL);
	if (!tmpl) {
		NL_SET_ERR_MSG_MOD(extack, "Failed to allocate conntrack template");
		return -ENOMEM;
	}
	__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
	nf_conntrack_get(&tmpl->ct_general);
	p->tmpl = tmpl;

	return 0;
}

static int tcf_ct_init(struct net *net, struct nlattr *nla,
		       struct nlattr *est, struct tc_action **a,
		       int replace, int bind, bool rtnl_held,
		       struct tcf_proto *tp, u32 flags,
		       struct netlink_ext_ack *extack)
{
	struct tc_action_net *tn = net_generic(net, ct_net_id);
	struct tcf_ct_params *params = NULL;
	struct nlattr *tb[TCA_CT_MAX + 1];
	struct tcf_chain *goto_ch = NULL;
	struct tc_ct *parm;
	struct tcf_ct *c;
	int err, res = 0;
	u32 index;

	if (!nla) {
		NL_SET_ERR_MSG_MOD(extack, "Ct requires attributes to be passed");
		return -EINVAL;
	}

	err = nla_parse_nested(tb, TCA_CT_MAX, nla, ct_policy, extack);
	if (err < 0)
		return err;

	if (!tb[TCA_CT_PARMS]) {
		NL_SET_ERR_MSG_MOD(extack, "Missing required ct parameters");
		return -EINVAL;
	}
	parm = nla_data(tb[TCA_CT_PARMS]);
	index = parm->index;
	err = tcf_idr_check_alloc(tn, &index, a, bind);
	if (err < 0)
		return err;

	if (!err) {
		err = tcf_idr_create_from_flags(tn, index, est, a,
						&act_ct_ops, bind, flags);
		if (err) {
			tcf_idr_cleanup(tn, index);
			return err;
		}
		res = ACT_P_CREATED;
	} else {
		if (bind)
			return 0;

		if (!replace) {
			tcf_idr_release(*a, bind);
			return -EEXIST;
		}
	}
	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
	if (err < 0)
		goto cleanup;

	c = to_ct(*a);

	params = kzalloc(sizeof(*params), GFP_KERNEL);
	if (unlikely(!params)) {
		err = -ENOMEM;
		goto cleanup;
	}

	err = tcf_ct_fill_params(net, params, parm, tb, extack);
	if (err)
		goto cleanup;

	err = tcf_ct_flow_table_get(params);
	if (err)
		goto cleanup;

	spin_lock_bh(&c->tcf_lock);
	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
	params = rcu_replace_pointer(c->params, params,
				     lockdep_is_held(&c->tcf_lock));
	spin_unlock_bh(&c->tcf_lock);

	if (goto_ch)
		tcf_chain_put_by_act(goto_ch);
	if (params)
		call_rcu(&params->rcu, tcf_ct_params_free);

	return res;

cleanup:
	if (goto_ch)
		tcf_chain_put_by_act(goto_ch);
	kfree(params);
	tcf_idr_release(*a, bind);
	return err;
}

static void tcf_ct_cleanup(struct tc_action *a)
{
	struct tcf_ct_params *params;
	struct tcf_ct *c = to_ct(a);

	params = rcu_dereference_protected(c->params, 1);
	if (params)
		call_rcu(&params->rcu, tcf_ct_params_free);
}

static int tcf_ct_dump_key_val(struct sk_buff *skb,
			       void *val, int val_type,
			       void *mask, int mask_type,
			       int len)
{
	int err;

	if (mask && !memchr_inv(mask, 0, len))
		return 0;

	err = nla_put(skb, val_type, len, val);
	if (err)
		return err;

	if (mask_type != TCA_CT_UNSPEC) {
		err = nla_put(skb, mask_type, len, mask);
		if (err)
			return err;
	}

	return 0;
}

static int tcf_ct_dump_nat(struct sk_buff *skb, struct tcf_ct_params *p)
{
	struct nf_nat_range2 *range = &p->range;

	if (!(p->ct_action & TCA_CT_ACT_NAT))
		return 0;

	if (!(p->ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST)))
		return 0;

	if (range->flags & NF_NAT_RANGE_MAP_IPS) {
		if (p->ipv4_range) {
			if (nla_put_in_addr(skb, TCA_CT_NAT_IPV4_MIN,
					    range->min_addr.ip))
				return -1;
			if (nla_put_in_addr(skb, TCA_CT_NAT_IPV4_MAX,
					    range->max_addr.ip))
				return -1;
		} else {
			if (nla_put_in6_addr(skb, TCA_CT_NAT_IPV6_MIN,
					     &range->min_addr.in6))
				return -1;
			if (nla_put_in6_addr(skb, TCA_CT_NAT_IPV6_MAX,
					     &range->max_addr.in6))
				return -1;
		}
	}

	if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) {
		if (nla_put_be16(skb, TCA_CT_NAT_PORT_MIN,
				 range->min_proto.all))
			return -1;
		if (nla_put_be16(skb, TCA_CT_NAT_PORT_MAX,
				 range->max_proto.all))
			return -1;
	}

	return 0;
}

static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a,
			      int bind, int ref)
{
	unsigned char *b = skb_tail_pointer(skb);
	struct tcf_ct *c = to_ct(a);
	struct tcf_ct_params *p;

	struct tc_ct opt = {
		.index   = c->tcf_index,
		.refcnt  = refcount_read(&c->tcf_refcnt) - ref,
		.bindcnt = atomic_read(&c->tcf_bindcnt) - bind,
	};
	struct tcf_t t;

	spin_lock_bh(&c->tcf_lock);
	p = rcu_dereference_protected(c->params,
				      lockdep_is_held(&c->tcf_lock));
	opt.action = c->tcf_action;

	if (tcf_ct_dump_key_val(skb,
				&p->ct_action, TCA_CT_ACTION,
				NULL, TCA_CT_UNSPEC,
				sizeof(p->ct_action)))
		goto nla_put_failure;

	if (p->ct_action & TCA_CT_ACT_CLEAR)
		goto skip_dump;

	if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) &&
	    tcf_ct_dump_key_val(skb,
				&p->mark, TCA_CT_MARK,
				&p->mark_mask, TCA_CT_MARK_MASK,
				sizeof(p->mark)))
		goto nla_put_failure;

	if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
	    tcf_ct_dump_key_val(skb,
				p->labels, TCA_CT_LABELS,
				p->labels_mask, TCA_CT_LABELS_MASK,
				sizeof(p->labels)))
		goto nla_put_failure;

	if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
	    tcf_ct_dump_key_val(skb,
				&p->zone, TCA_CT_ZONE,
				NULL, TCA_CT_UNSPEC,
				sizeof(p->zone)))
		goto nla_put_failure;

	if (tcf_ct_dump_nat(skb, p))
		goto nla_put_failure;

skip_dump:
	if (nla_put(skb, TCA_CT_PARMS, sizeof(opt), &opt))
		goto nla_put_failure;

	tcf_tm_dump(&t, &c->tcf_tm);
	if (nla_put_64bit(skb, TCA_CT_TM, sizeof(t), &t, TCA_CT_PAD))
		goto nla_put_failure;
	spin_unlock_bh(&c->tcf_lock);

	return skb->len;
nla_put_failure:
	spin_unlock_bh(&c->tcf_lock);
	nlmsg_trim(skb, b);
	return -1;
}

static int tcf_ct_walker(struct net *net, struct sk_buff *skb,
			 struct netlink_callback *cb, int type,
			 const struct tc_action_ops *ops,
			 struct netlink_ext_ack *extack)
{
	struct tc_action_net *tn = net_generic(net, ct_net_id);

	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}

static int tcf_ct_search(struct net *net, struct tc_action **a, u32 index)
{
	struct tc_action_net *tn = net_generic(net, ct_net_id);

	return tcf_idr_search(tn, a, index);
}

static void tcf_stats_update(struct tc_action *a, u64 bytes, u64 packets,
			     u64 drops, u64 lastuse, bool hw)
{
	struct tcf_ct *c = to_ct(a);

	tcf_action_update_stats(a, bytes, packets, drops, hw);
	c->tcf_tm.lastuse = max_t(u64, c->tcf_tm.lastuse, lastuse);
}

static struct tc_action_ops act_ct_ops = {
	.kind		=	"ct",
	.id		=	TCA_ID_CT,
	.owner		=	THIS_MODULE,
	.act		=	tcf_ct_act,
	.dump		=	tcf_ct_dump,
	.init		=	tcf_ct_init,
	.cleanup	=	tcf_ct_cleanup,
	.walk		=	tcf_ct_walker,
	.lookup		=	tcf_ct_search,
	.stats_update	=	tcf_stats_update,
	.size		=	sizeof(struct tcf_ct),
};

static __net_init int ct_init_net(struct net *net)
{
	unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8;
	struct tc_ct_action_net *tn = net_generic(net, ct_net_id);

	if (nf_connlabels_get(net, n_bits - 1)) {
		tn->labels = false;
		pr_err("act_ct: Failed to set connlabels length");
	} else {
		tn->labels = true;
	}

	return tc_action_net_init(net, &tn->tn, &act_ct_ops);
}

static void __net_exit ct_exit_net(struct list_head *net_list)
{
	struct net *net;

	rtnl_lock();
	list_for_each_entry(net, net_list, exit_list) {
		struct tc_ct_action_net *tn = net_generic(net, ct_net_id);

		if (tn->labels)
			nf_connlabels_put(net);
	}
	rtnl_unlock();

	tc_action_net_exit(net_list, ct_net_id);
}

static struct pernet_operations ct_net_ops = {
	.init = ct_init_net,
	.exit_batch = ct_exit_net,
	.id   = &ct_net_id,
	.size = sizeof(struct tc_ct_action_net),
};

static int __init ct_init_module(void)
{
	int err;

	act_ct_wq = alloc_ordered_workqueue("act_ct_workqueue", 0);
	if (!act_ct_wq)
		return -ENOMEM;

	err = tcf_ct_flow_tables_init();
	if (err)
		goto err_tbl_init;

	err = tcf_register_action(&act_ct_ops, &ct_net_ops);
	if (err)
		goto err_register;

	static_branch_inc(&tcf_frag_xmit_count);

	return 0;

err_register:
	tcf_ct_flow_tables_uninit();
err_tbl_init:
	destroy_workqueue(act_ct_wq);
	return err;
}

static void __exit ct_cleanup_module(void)
{
	static_branch_dec(&tcf_frag_xmit_count);
	tcf_unregister_action(&act_ct_ops, &ct_net_ops);
	tcf_ct_flow_tables_uninit();
	destroy_workqueue(act_ct_wq);
}

module_init(ct_init_module);
module_exit(ct_cleanup_module);
MODULE_AUTHOR("Paul Blakey <paulb@mellanox.com>");
MODULE_AUTHOR("Yossi Kuperman <yossiku@mellanox.com>");
MODULE_AUTHOR("Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>");
MODULE_DESCRIPTION("Connection tracking action");
MODULE_LICENSE("GPL v2");