summaryrefslogtreecommitdiffstats
path: root/net/sched/cls_api.c
blob: cdc3c87c53e62d4db4bb18fa5f59d7889b9866cb (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
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
/*
 * net/sched/cls_api.c	Packet classifier API.
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 *
 * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
 *
 * Changes:
 *
 * Eduardo J. Blanco <ejbs@netlabs.com.uy> :990222: kmod support
 *
 */

#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/slab.h>
#include <linux/idr.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>

/* The list of all installed classifier types */
static LIST_HEAD(tcf_proto_base);

/* Protects list of registered TC modules. It is pure SMP lock. */
static DEFINE_RWLOCK(cls_mod_lock);

/* Find classifier type by string name */

static const struct tcf_proto_ops *tcf_proto_lookup_ops(const char *kind)
{
	const struct tcf_proto_ops *t, *res = NULL;

	if (kind) {
		read_lock(&cls_mod_lock);
		list_for_each_entry(t, &tcf_proto_base, head) {
			if (strcmp(kind, t->kind) == 0) {
				if (try_module_get(t->owner))
					res = t;
				break;
			}
		}
		read_unlock(&cls_mod_lock);
	}
	return res;
}

/* Register(unregister) new classifier type */

int register_tcf_proto_ops(struct tcf_proto_ops *ops)
{
	struct tcf_proto_ops *t;
	int rc = -EEXIST;

	write_lock(&cls_mod_lock);
	list_for_each_entry(t, &tcf_proto_base, head)
		if (!strcmp(ops->kind, t->kind))
			goto out;

	list_add_tail(&ops->head, &tcf_proto_base);
	rc = 0;
out:
	write_unlock(&cls_mod_lock);
	return rc;
}
EXPORT_SYMBOL(register_tcf_proto_ops);

static struct workqueue_struct *tc_filter_wq;

int unregister_tcf_proto_ops(struct tcf_proto_ops *ops)
{
	struct tcf_proto_ops *t;
	int rc = -ENOENT;

	/* Wait for outstanding call_rcu()s, if any, from a
	 * tcf_proto_ops's destroy() handler.
	 */
	rcu_barrier();
	flush_workqueue(tc_filter_wq);

	write_lock(&cls_mod_lock);
	list_for_each_entry(t, &tcf_proto_base, head) {
		if (t == ops) {
			list_del(&t->head);
			rc = 0;
			break;
		}
	}
	write_unlock(&cls_mod_lock);
	return rc;
}
EXPORT_SYMBOL(unregister_tcf_proto_ops);

bool tcf_queue_work(struct rcu_work *rwork, work_func_t func)
{
	INIT_RCU_WORK(rwork, func);
	return queue_rcu_work(tc_filter_wq, rwork);
}
EXPORT_SYMBOL(tcf_queue_work);

/* Select new prio value from the range, managed by kernel. */

static inline u32 tcf_auto_prio(struct tcf_proto *tp)
{
	u32 first = TC_H_MAKE(0xC0000000U, 0U);

	if (tp)
		first = tp->prio - 1;

	return TC_H_MAJ(first);
}

static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol,
					  u32 prio, struct tcf_chain *chain,
					  struct netlink_ext_ack *extack)
{
	struct tcf_proto *tp;
	int err;

	tp = kzalloc(sizeof(*tp), GFP_KERNEL);
	if (!tp)
		return ERR_PTR(-ENOBUFS);

	err = -ENOENT;
	tp->ops = tcf_proto_lookup_ops(kind);
	if (!tp->ops) {
#ifdef CONFIG_MODULES
		rtnl_unlock();
		request_module("cls_%s", kind);
		rtnl_lock();
		tp->ops = tcf_proto_lookup_ops(kind);
		/* We dropped the RTNL semaphore in order to perform
		 * the module load. So, even if we succeeded in loading
		 * the module we have to replay the request. We indicate
		 * this using -EAGAIN.
		 */
		if (tp->ops) {
			module_put(tp->ops->owner);
			err = -EAGAIN;
		} else {
			NL_SET_ERR_MSG(extack, "TC classifier not found");
			err = -ENOENT;
		}
#endif
		goto errout;
	}
	tp->classify = tp->ops->classify;
	tp->protocol = protocol;
	tp->prio = prio;
	tp->chain = chain;

	err = tp->ops->init(tp);
	if (err) {
		module_put(tp->ops->owner);
		goto errout;
	}
	return tp;

errout:
	kfree(tp);
	return ERR_PTR(err);
}

static void tcf_proto_destroy(struct tcf_proto *tp,
			      struct netlink_ext_ack *extack)
{
	tp->ops->destroy(tp, extack);
	module_put(tp->ops->owner);
	kfree_rcu(tp, rcu);
}

struct tcf_filter_chain_list_item {
	struct list_head list;
	tcf_chain_head_change_t *chain_head_change;
	void *chain_head_change_priv;
};

static struct tcf_chain *tcf_chain_create(struct tcf_block *block,
					  u32 chain_index)
{
	struct tcf_chain *chain;

	chain = kzalloc(sizeof(*chain), GFP_KERNEL);
	if (!chain)
		return NULL;
	INIT_LIST_HEAD(&chain->filter_chain_list);
	list_add_tail(&chain->list, &block->chain_list);
	chain->block = block;
	chain->index = chain_index;
	chain->refcnt = 1;
	return chain;
}

static void tcf_chain_head_change_item(struct tcf_filter_chain_list_item *item,
				       struct tcf_proto *tp_head)
{
	if (item->chain_head_change)
		item->chain_head_change(tp_head, item->chain_head_change_priv);
}
static void tcf_chain_head_change(struct tcf_chain *chain,
				  struct tcf_proto *tp_head)
{
	struct tcf_filter_chain_list_item *item;

	list_for_each_entry(item, &chain->filter_chain_list, list)
		tcf_chain_head_change_item(item, tp_head);
}

static void tcf_chain_flush(struct tcf_chain *chain)
{
	struct tcf_proto *tp = rtnl_dereference(chain->filter_chain);

	tcf_chain_head_change(chain, NULL);
	while (tp) {
		RCU_INIT_POINTER(chain->filter_chain, tp->next);
		tcf_proto_destroy(tp, NULL);
		tp = rtnl_dereference(chain->filter_chain);
		tcf_chain_put(chain);
	}
}

static void tcf_chain_destroy(struct tcf_chain *chain)
{
	struct tcf_block *block = chain->block;

	list_del(&chain->list);
	kfree(chain);
	if (list_empty(&block->chain_list))
		kfree(block);
}

static void tcf_chain_hold(struct tcf_chain *chain)
{
	++chain->refcnt;
}

struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
				bool create)
{
	struct tcf_chain *chain;

	list_for_each_entry(chain, &block->chain_list, list) {
		if (chain->index == chain_index) {
			tcf_chain_hold(chain);
			return chain;
		}
	}

	return create ? tcf_chain_create(block, chain_index) : NULL;
}
EXPORT_SYMBOL(tcf_chain_get);

void tcf_chain_put(struct tcf_chain *chain)
{
	if (--chain->refcnt == 0)
		tcf_chain_destroy(chain);
}
EXPORT_SYMBOL(tcf_chain_put);

static bool tcf_block_offload_in_use(struct tcf_block *block)
{
	return block->offloadcnt;
}

static int tcf_block_offload_cmd(struct tcf_block *block,
				 struct net_device *dev,
				 struct tcf_block_ext_info *ei,
				 enum tc_block_command command)
{
	struct tc_block_offload bo = {};

	bo.command = command;
	bo.binder_type = ei->binder_type;
	bo.block = block;
	return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
}

static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
				  struct tcf_block_ext_info *ei)
{
	struct net_device *dev = q->dev_queue->dev;
	int err;

	if (!dev->netdev_ops->ndo_setup_tc)
		goto no_offload_dev_inc;

	/* If tc offload feature is disabled and the block we try to bind
	 * to already has some offloaded filters, forbid to bind.
	 */
	if (!tc_can_offload(dev) && tcf_block_offload_in_use(block))
		return -EOPNOTSUPP;

	err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND);
	if (err == -EOPNOTSUPP)
		goto no_offload_dev_inc;
	return err;

no_offload_dev_inc:
	if (tcf_block_offload_in_use(block))
		return -EOPNOTSUPP;
	block->nooffloaddevcnt++;
	return 0;
}

static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q,
				     struct tcf_block_ext_info *ei)
{
	struct net_device *dev = q->dev_queue->dev;
	int err;

	if (!dev->netdev_ops->ndo_setup_tc)
		goto no_offload_dev_dec;
	err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND);
	if (err == -EOPNOTSUPP)
		goto no_offload_dev_dec;
	return;

no_offload_dev_dec:
	WARN_ON(block->nooffloaddevcnt-- == 0);
}

static int
tcf_chain_head_change_cb_add(struct tcf_chain *chain,
			     struct tcf_block_ext_info *ei,
			     struct netlink_ext_ack *extack)
{
	struct tcf_filter_chain_list_item *item;

	item = kmalloc(sizeof(*item), GFP_KERNEL);
	if (!item) {
		NL_SET_ERR_MSG(extack, "Memory allocation for head change callback item failed");
		return -ENOMEM;
	}
	item->chain_head_change = ei->chain_head_change;
	item->chain_head_change_priv = ei->chain_head_change_priv;
	if (chain->filter_chain)
		tcf_chain_head_change_item(item, chain->filter_chain);
	list_add(&item->list, &chain->filter_chain_list);
	return 0;
}

static void
tcf_chain_head_change_cb_del(struct tcf_chain *chain,
			     struct tcf_block_ext_info *ei)
{
	struct tcf_filter_chain_list_item *item;

	list_for_each_entry(item, &chain->filter_chain_list, list) {
		if ((!ei->chain_head_change && !ei->chain_head_change_priv) ||
		    (item->chain_head_change == ei->chain_head_change &&
		     item->chain_head_change_priv == ei->chain_head_change_priv)) {
			tcf_chain_head_change_item(item, NULL);
			list_del(&item->list);
			kfree(item);
			return;
		}
	}
	WARN_ON(1);
}

struct tcf_net {
	struct idr idr;
};

static unsigned int tcf_net_id;

static int tcf_block_insert(struct tcf_block *block, struct net *net,
			    struct netlink_ext_ack *extack)
{
	struct tcf_net *tn = net_generic(net, tcf_net_id);

	return idr_alloc_u32(&tn->idr, block, &block->index, block->index,
			     GFP_KERNEL);
}

static void tcf_block_remove(struct tcf_block *block, struct net *net)
{
	struct tcf_net *tn = net_generic(net, tcf_net_id);

	idr_remove(&tn->idr, block->index);
}

static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
					  u32 block_index,
					  struct netlink_ext_ack *extack)
{
	struct tcf_block *block;
	struct tcf_chain *chain;
	int err;

	block = kzalloc(sizeof(*block), GFP_KERNEL);
	if (!block) {
		NL_SET_ERR_MSG(extack, "Memory allocation for block failed");
		return ERR_PTR(-ENOMEM);
	}
	INIT_LIST_HEAD(&block->chain_list);
	INIT_LIST_HEAD(&block->cb_list);
	INIT_LIST_HEAD(&block->owner_list);

	/* Create chain 0 by default, it has to be always present. */
	chain = tcf_chain_create(block, 0);
	if (!chain) {
		NL_SET_ERR_MSG(extack, "Failed to create new tcf chain");
		err = -ENOMEM;
		goto err_chain_create;
	}
	block->refcnt = 1;
	block->net = net;
	block->index = block_index;

	/* Don't store q pointer for blocks which are shared */
	if (!tcf_block_shared(block))
		block->q = q;
	return block;

err_chain_create:
	kfree(block);
	return ERR_PTR(err);
}

static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index)
{
	struct tcf_net *tn = net_generic(net, tcf_net_id);

	return idr_find(&tn->idr, block_index);
}

/* Find tcf block.
 * Set q, parent, cl when appropriate.
 */

static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
					u32 *parent, unsigned long *cl,
					int ifindex, u32 block_index,
					struct netlink_ext_ack *extack)
{
	struct tcf_block *block;

	if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
		block = tcf_block_lookup(net, block_index);
		if (!block) {
			NL_SET_ERR_MSG(extack, "Block of given index was not found");
			return ERR_PTR(-EINVAL);
		}
	} else {
		const struct Qdisc_class_ops *cops;
		struct net_device *dev;

		/* Find link */
		dev = __dev_get_by_index(net, ifindex);
		if (!dev)
			return ERR_PTR(-ENODEV);

		/* Find qdisc */
		if (!*parent) {
			*q = dev->qdisc;
			*parent = (*q)->handle;
		} else {
			*q = qdisc_lookup(dev, TC_H_MAJ(*parent));
			if (!*q) {
				NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
				return ERR_PTR(-EINVAL);
			}
		}

		/* Is it classful? */
		cops = (*q)->ops->cl_ops;
		if (!cops) {
			NL_SET_ERR_MSG(extack, "Qdisc not classful");
			return ERR_PTR(-EINVAL);
		}

		if (!cops->tcf_block) {
			NL_SET_ERR_MSG(extack, "Class doesn't support blocks");
			return ERR_PTR(-EOPNOTSUPP);
		}

		/* Do we search for filter, attached to class? */
		if (TC_H_MIN(*parent)) {
			*cl = cops->find(*q, *parent);
			if (*cl == 0) {
				NL_SET_ERR_MSG(extack, "Specified class doesn't exist");
				return ERR_PTR(-ENOENT);
			}
		}

		/* And the last stroke */
		block = cops->tcf_block(*q, *cl, extack);
		if (!block)
			return ERR_PTR(-EINVAL);
		if (tcf_block_shared(block)) {
			NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters");
			return ERR_PTR(-EOPNOTSUPP);
		}
	}

	return block;
}

static struct tcf_chain *tcf_block_chain_zero(struct tcf_block *block)
{
	return list_first_entry(&block->chain_list, struct tcf_chain, list);
}

struct tcf_block_owner_item {
	struct list_head list;
	struct Qdisc *q;
	enum tcf_block_binder_type binder_type;
};

static void
tcf_block_owner_netif_keep_dst(struct tcf_block *block,
			       struct Qdisc *q,
			       enum tcf_block_binder_type binder_type)
{
	if (block->keep_dst &&
	    binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS &&
	    binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
		netif_keep_dst(qdisc_dev(q));
}

void tcf_block_netif_keep_dst(struct tcf_block *block)
{
	struct tcf_block_owner_item *item;

	block->keep_dst = true;
	list_for_each_entry(item, &block->owner_list, list)
		tcf_block_owner_netif_keep_dst(block, item->q,
					       item->binder_type);
}
EXPORT_SYMBOL(tcf_block_netif_keep_dst);

static int tcf_block_owner_add(struct tcf_block *block,
			       struct Qdisc *q,
			       enum tcf_block_binder_type binder_type)
{
	struct tcf_block_owner_item *item;

	item = kmalloc(sizeof(*item), GFP_KERNEL);
	if (!item)
		return -ENOMEM;
	item->q = q;
	item->binder_type = binder_type;
	list_add(&item->list, &block->owner_list);
	return 0;
}

static void tcf_block_owner_del(struct tcf_block *block,
				struct Qdisc *q,
				enum tcf_block_binder_type binder_type)
{
	struct tcf_block_owner_item *item;

	list_for_each_entry(item, &block->owner_list, list) {
		if (item->q == q && item->binder_type == binder_type) {
			list_del(&item->list);
			kfree(item);
			return;
		}
	}
	WARN_ON(1);
}

int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
		      struct tcf_block_ext_info *ei,
		      struct netlink_ext_ack *extack)
{
	struct net *net = qdisc_net(q);
	struct tcf_block *block = NULL;
	bool created = false;
	int err;

	if (ei->block_index) {
		/* block_index not 0 means the shared block is requested */
		block = tcf_block_lookup(net, ei->block_index);
		if (block)
			block->refcnt++;
	}

	if (!block) {
		block = tcf_block_create(net, q, ei->block_index, extack);
		if (IS_ERR(block))
			return PTR_ERR(block);
		created = true;
		if (tcf_block_shared(block)) {
			err = tcf_block_insert(block, net, extack);
			if (err)
				goto err_block_insert;
		}
	}

	err = tcf_block_owner_add(block, q, ei->binder_type);
	if (err)
		goto err_block_owner_add;

	tcf_block_owner_netif_keep_dst(block, q, ei->binder_type);

	err = tcf_chain_head_change_cb_add(tcf_block_chain_zero(block),
					   ei, extack);
	if (err)
		goto err_chain_head_change_cb_add;

	err = tcf_block_offload_bind(block, q, ei);
	if (err)
		goto err_block_offload_bind;

	*p_block = block;
	return 0;

err_block_offload_bind:
	tcf_chain_head_change_cb_del(tcf_block_chain_zero(block), ei);
err_chain_head_change_cb_add:
	tcf_block_owner_del(block, q, ei->binder_type);
err_block_owner_add:
	if (created) {
		if (tcf_block_shared(block))
			tcf_block_remove(block, net);
err_block_insert:
		kfree(tcf_block_chain_zero(block));
		kfree(block);
	} else {
		block->refcnt--;
	}
	return err;
}
EXPORT_SYMBOL(tcf_block_get_ext);

static void tcf_chain_head_change_dflt(struct tcf_proto *tp_head, void *priv)
{
	struct tcf_proto __rcu **p_filter_chain = priv;

	rcu_assign_pointer(*p_filter_chain, tp_head);
}

int tcf_block_get(struct tcf_block **p_block,
		  struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
		  struct netlink_ext_ack *extack)
{
	struct tcf_block_ext_info ei = {
		.chain_head_change = tcf_chain_head_change_dflt,
		.chain_head_change_priv = p_filter_chain,
	};

	WARN_ON(!p_filter_chain);
	return tcf_block_get_ext(p_block, q, &ei, extack);
}
EXPORT_SYMBOL(tcf_block_get);

/* XXX: Standalone actions are not allowed to jump to any chain, and bound
 * actions should be all removed after flushing.
 */
void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
		       struct tcf_block_ext_info *ei)
{
	struct tcf_chain *chain, *tmp;

	if (!block)
		return;
	tcf_chain_head_change_cb_del(tcf_block_chain_zero(block), ei);
	tcf_block_owner_del(block, q, ei->binder_type);

	if (--block->refcnt == 0) {
		if (tcf_block_shared(block))
			tcf_block_remove(block, block->net);

		/* Hold a refcnt for all chains, so that they don't disappear
		 * while we are iterating.
		 */
		list_for_each_entry(chain, &block->chain_list, list)
			tcf_chain_hold(chain);

		list_for_each_entry(chain, &block->chain_list, list)
			tcf_chain_flush(chain);
	}

	tcf_block_offload_unbind(block, q, ei);

	if (block->refcnt == 0) {
		/* At this point, all the chains should have refcnt >= 1. */
		list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
			tcf_chain_put(chain);

		/* Finally, put chain 0 and allow block to be freed. */
		tcf_chain_put(tcf_block_chain_zero(block));
	}
}
EXPORT_SYMBOL(tcf_block_put_ext);

void tcf_block_put(struct tcf_block *block)
{
	struct tcf_block_ext_info ei = {0, };

	if (!block)
		return;
	tcf_block_put_ext(block, block->q, &ei);
}

EXPORT_SYMBOL(tcf_block_put);

struct tcf_block_cb {
	struct list_head list;
	tc_setup_cb_t *cb;
	void *cb_ident;
	void *cb_priv;
	unsigned int refcnt;
};

void *tcf_block_cb_priv(struct tcf_block_cb *block_cb)
{
	return block_cb->cb_priv;
}
EXPORT_SYMBOL(tcf_block_cb_priv);

struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
					 tc_setup_cb_t *cb, void *cb_ident)
{	struct tcf_block_cb *block_cb;

	list_for_each_entry(block_cb, &block->cb_list, list)
		if (block_cb->cb == cb && block_cb->cb_ident == cb_ident)
			return block_cb;
	return NULL;
}
EXPORT_SYMBOL(tcf_block_cb_lookup);

void tcf_block_cb_incref(struct tcf_block_cb *block_cb)
{
	block_cb->refcnt++;
}
EXPORT_SYMBOL(tcf_block_cb_incref);

unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb)
{
	return --block_cb->refcnt;
}
EXPORT_SYMBOL(tcf_block_cb_decref);

struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
					     tc_setup_cb_t *cb, void *cb_ident,
					     void *cb_priv)
{
	struct tcf_block_cb *block_cb;

	/* At this point, playback of previous block cb calls is not supported,
	 * so forbid to register to block which already has some offloaded
	 * filters present.
	 */
	if (tcf_block_offload_in_use(block))
		return ERR_PTR(-EOPNOTSUPP);

	block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL);
	if (!block_cb)
		return ERR_PTR(-ENOMEM);
	block_cb->cb = cb;
	block_cb->cb_ident = cb_ident;
	block_cb->cb_priv = cb_priv;
	list_add(&block_cb->list, &block->cb_list);
	return block_cb;
}
EXPORT_SYMBOL(__tcf_block_cb_register);

int tcf_block_cb_register(struct tcf_block *block,
			  tc_setup_cb_t *cb, void *cb_ident,
			  void *cb_priv)
{
	struct tcf_block_cb *block_cb;

	block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv);
	return IS_ERR(block_cb) ? PTR_ERR(block_cb) : 0;
}
EXPORT_SYMBOL(tcf_block_cb_register);

void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb)
{
	list_del(&block_cb->list);
	kfree(block_cb);
}
EXPORT_SYMBOL(__tcf_block_cb_unregister);

void tcf_block_cb_unregister(struct tcf_block *block,
			     tc_setup_cb_t *cb, void *cb_ident)
{
	struct tcf_block_cb *block_cb;

	block_cb = tcf_block_cb_lookup(block, cb, cb_ident);
	if (!block_cb)
		return;
	__tcf_block_cb_unregister(block_cb);
}
EXPORT_SYMBOL(tcf_block_cb_unregister);

static int tcf_block_cb_call(struct tcf_block *block, enum tc_setup_type type,
			     void *type_data, bool err_stop)
{
	struct tcf_block_cb *block_cb;
	int ok_count = 0;
	int err;

	/* Make sure all netdevs sharing this block are offload-capable. */
	if (block->nooffloaddevcnt && err_stop)
		return -EOPNOTSUPP;

	list_for_each_entry(block_cb, &block->cb_list, list) {
		err = block_cb->cb(type, type_data, block_cb->cb_priv);
		if (err) {
			if (err_stop)
				return err;
		} else {
			ok_count++;
		}
	}
	return ok_count;
}

/* Main classifier routine: scans classifier chain attached
 * to this qdisc, (optionally) tests for protocol and asks
 * specific classifiers.
 */
int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
		 struct tcf_result *res, bool compat_mode)
{
	__be16 protocol = tc_skb_protocol(skb);
#ifdef CONFIG_NET_CLS_ACT
	const int max_reclassify_loop = 4;
	const struct tcf_proto *orig_tp = tp;
	const struct tcf_proto *first_tp;
	int limit = 0;

reclassify:
#endif
	for (; tp; tp = rcu_dereference_bh(tp->next)) {
		int err;

		if (tp->protocol != protocol &&
		    tp->protocol != htons(ETH_P_ALL))
			continue;

		err = tp->classify(skb, tp, res);
#ifdef CONFIG_NET_CLS_ACT
		if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) {
			first_tp = orig_tp;
			goto reset;
		} else if (unlikely(TC_ACT_EXT_CMP(err, TC_ACT_GOTO_CHAIN))) {
			first_tp = res->goto_tp;
			goto reset;
		}
#endif
		if (err >= 0)
			return err;
	}

	return TC_ACT_UNSPEC; /* signal: continue lookup */
#ifdef CONFIG_NET_CLS_ACT
reset:
	if (unlikely(limit++ >= max_reclassify_loop)) {
		net_notice_ratelimited("%u: reclassify loop, rule prio %u, protocol %02x\n",
				       tp->chain->block->index,
				       tp->prio & 0xffff,
				       ntohs(tp->protocol));
		return TC_ACT_SHOT;
	}

	tp = first_tp;
	protocol = tc_skb_protocol(skb);
	goto reclassify;
#endif
}
EXPORT_SYMBOL(tcf_classify);

struct tcf_chain_info {
	struct tcf_proto __rcu **pprev;
	struct tcf_proto __rcu *next;
};

static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain_info *chain_info)
{
	return rtnl_dereference(*chain_info->pprev);
}

static void tcf_chain_tp_insert(struct tcf_chain *chain,
				struct tcf_chain_info *chain_info,
				struct tcf_proto *tp)
{
	if (*chain_info->pprev == chain->filter_chain)
		tcf_chain_head_change(chain, tp);
	RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info));
	rcu_assign_pointer(*chain_info->pprev, tp);
	tcf_chain_hold(chain);
}

static void tcf_chain_tp_remove(struct tcf_chain *chain,
				struct tcf_chain_info *chain_info,
				struct tcf_proto *tp)
{
	struct tcf_proto *next = rtnl_dereference(chain_info->next);

	if (tp == chain->filter_chain)
		tcf_chain_head_change(chain, next);
	RCU_INIT_POINTER(*chain_info->pprev, next);
	tcf_chain_put(chain);
}

static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain,
					   struct tcf_chain_info *chain_info,
					   u32 protocol, u32 prio,
					   bool prio_allocate)
{
	struct tcf_proto **pprev;
	struct tcf_proto *tp;

	/* Check the chain for existence of proto-tcf with this priority */
	for (pprev = &chain->filter_chain;
	     (tp = rtnl_dereference(*pprev)); pprev = &tp->next) {
		if (tp->prio >= prio) {
			if (tp->prio == prio) {
				if (prio_allocate ||
				    (tp->protocol != protocol && protocol))
					return ERR_PTR(-EINVAL);
			} else {
				tp = NULL;
			}
			break;
		}
	}
	chain_info->pprev = pprev;
	chain_info->next = tp ? tp->next : NULL;
	return tp;
}

static int tcf_fill_node(struct net *net, struct sk_buff *skb,
			 struct tcf_proto *tp, struct tcf_block *block,
			 struct Qdisc *q, u32 parent, void *fh,
			 u32 portid, u32 seq, u16 flags, int event)
{
	struct tcmsg *tcm;
	struct nlmsghdr  *nlh;
	unsigned char *b = skb_tail_pointer(skb);

	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
	if (!nlh)
		goto out_nlmsg_trim;
	tcm = nlmsg_data(nlh);
	tcm->tcm_family = AF_UNSPEC;
	tcm->tcm__pad1 = 0;
	tcm->tcm__pad2 = 0;
	if (q) {
		tcm->tcm_ifindex = qdisc_dev(q)->ifindex;
		tcm->tcm_parent = parent;
	} else {
		tcm->tcm_ifindex = TCM_IFINDEX_MAGIC_BLOCK;
		tcm->tcm_block_index = block->index;
	}
	tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol);
	if (nla_put_string(skb, TCA_KIND, tp->ops->kind))
		goto nla_put_failure;
	if (nla_put_u32(skb, TCA_CHAIN, tp->chain->index))
		goto nla_put_failure;
	if (!fh) {
		tcm->tcm_handle = 0;
	} else {
		if (tp->ops->dump && tp->ops->dump(net, tp, fh, skb, tcm) < 0)
			goto nla_put_failure;
	}
	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
	return skb->len;

out_nlmsg_trim:
nla_put_failure:
	nlmsg_trim(skb, b);
	return -1;
}

static int tfilter_notify(struct net *net, struct sk_buff *oskb,
			  struct nlmsghdr *n, struct tcf_proto *tp,
			  struct tcf_block *block, struct Qdisc *q,
			  u32 parent, void *fh, int event, bool unicast)
{
	struct sk_buff *skb;
	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;

	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
	if (!skb)
		return -ENOBUFS;

	if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
			  n->nlmsg_seq, n->nlmsg_flags, event) <= 0) {
		kfree_skb(skb);
		return -EINVAL;
	}

	if (unicast)
		return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT);

	return rtnetlink_send(skb, net, portid, RTNLGRP_TC,
			      n->nlmsg_flags & NLM_F_ECHO);
}

static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
			      struct nlmsghdr *n, struct tcf_proto *tp,
			      struct tcf_block *block, struct Qdisc *q,
			      u32 parent, void *fh, bool unicast, bool *last,
			      struct netlink_ext_ack *extack)
{
	struct sk_buff *skb;
	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
	int err;

	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
	if (!skb)
		return -ENOBUFS;

	if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
			  n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER) <= 0) {
		NL_SET_ERR_MSG(extack, "Failed to build del event notification");
		kfree_skb(skb);
		return -EINVAL;
	}

	err = tp->ops->delete(tp, fh, last, extack);
	if (err) {
		kfree_skb(skb);
		return err;
	}

	if (unicast)
		return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT);

	err = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
			     n->nlmsg_flags & NLM_F_ECHO);
	if (err < 0)
		NL_SET_ERR_MSG(extack, "Failed to send filter delete notification");
	return err;
}

static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
				 struct tcf_block *block, struct Qdisc *q,
				 u32 parent, struct nlmsghdr *n,
				 struct tcf_chain *chain, int event)
{
	struct tcf_proto *tp;

	for (tp = rtnl_dereference(chain->filter_chain);
	     tp; tp = rtnl_dereference(tp->next))
		tfilter_notify(net, oskb, n, tp, block,
			       q, parent, 0, event, false);
}

static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
			  struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct nlattr *tca[TCA_MAX + 1];
	struct tcmsg *t;
	u32 protocol;
	u32 prio;
	bool prio_allocate;
	u32 parent;
	u32 chain_index;
	struct Qdisc *q = NULL;
	struct tcf_chain_info chain_info;
	struct tcf_chain *chain = NULL;
	struct tcf_block *block;
	struct tcf_proto *tp;
	unsigned long cl;
	void *fh;
	int err;
	int tp_created;

	if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
		return -EPERM;

replay:
	tp_created = 0;

	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
	if (err < 0)
		return err;

	t = nlmsg_data(n);
	protocol = TC_H_MIN(t->tcm_info);
	prio = TC_H_MAJ(t->tcm_info);
	prio_allocate = false;
	parent = t->tcm_parent;
	cl = 0;

	if (prio == 0) {
		/* If no priority is provided by the user,
		 * we allocate one.
		 */
		if (n->nlmsg_flags & NLM_F_CREATE) {
			prio = TC_H_MAKE(0x80000000U, 0U);
			prio_allocate = true;
		} else {
			NL_SET_ERR_MSG(extack, "Invalid filter command with priority of zero");
			return -ENOENT;
		}
	}

	/* Find head of filter chain. */

	block = tcf_block_find(net, &q, &parent, &cl,
			       t->tcm_ifindex, t->tcm_block_index, extack);
	if (IS_ERR(block)) {
		err = PTR_ERR(block);
		goto errout;
	}

	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
	if (chain_index > TC_ACT_EXT_VAL_MASK) {
		NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
		err = -EINVAL;
		goto errout;
	}
	chain = tcf_chain_get(block, chain_index, true);
	if (!chain) {
		NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
		err = -ENOMEM;
		goto errout;
	}

	tp = tcf_chain_tp_find(chain, &chain_info, protocol,
			       prio, prio_allocate);
	if (IS_ERR(tp)) {
		NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
		err = PTR_ERR(tp);
		goto errout;
	}

	if (tp == NULL) {
		/* Proto-tcf does not exist, create new one */

		if (tca[TCA_KIND] == NULL || !protocol) {
			NL_SET_ERR_MSG(extack, "Filter kind and protocol must be specified");
			err = -EINVAL;
			goto errout;
		}

		if (!(n->nlmsg_flags & NLM_F_CREATE)) {
			NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter");
			err = -ENOENT;
			goto errout;
		}

		if (prio_allocate)
			prio = tcf_auto_prio(tcf_chain_tp_prev(&chain_info));

		tp = tcf_proto_create(nla_data(tca[TCA_KIND]),
				      protocol, prio, chain, extack);
		if (IS_ERR(tp)) {
			err = PTR_ERR(tp);
			goto errout;
		}
		tp_created = 1;
	} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
		NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
		err = -EINVAL;
		goto errout;
	}

	fh = tp->ops->get(tp, t->tcm_handle);

	if (!fh) {
		if (!(n->nlmsg_flags & NLM_F_CREATE)) {
			NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter");
			err = -ENOENT;
			goto errout;
		}
	} else if (n->nlmsg_flags & NLM_F_EXCL) {
		NL_SET_ERR_MSG(extack, "Filter already exists");
		err = -EEXIST;
		goto errout;
	}

	err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
			      n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE,
			      extack);
	if (err == 0) {
		if (tp_created)
			tcf_chain_tp_insert(chain, &chain_info, tp);
		tfilter_notify(net, skb, n, tp, block, q, parent, fh,
			       RTM_NEWTFILTER, false);
	} else {
		if (tp_created)
			tcf_proto_destroy(tp, NULL);
	}

errout:
	if (chain)
		tcf_chain_put(chain);
	if (err == -EAGAIN)
		/* Replay the request. */
		goto replay;
	return err;
}

static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
			  struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct nlattr *tca[TCA_MAX + 1];
	struct tcmsg *t;
	u32 protocol;
	u32 prio;
	u32 parent;
	u32 chain_index;
	struct Qdisc *q = NULL;
	struct tcf_chain_info chain_info;
	struct tcf_chain *chain = NULL;
	struct tcf_block *block;
	struct tcf_proto *tp = NULL;
	unsigned long cl = 0;
	void *fh = NULL;
	int err;

	if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
		return -EPERM;

	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
	if (err < 0)
		return err;

	t = nlmsg_data(n);
	protocol = TC_H_MIN(t->tcm_info);
	prio = TC_H_MAJ(t->tcm_info);
	parent = t->tcm_parent;

	if (prio == 0 && (protocol || t->tcm_handle || tca[TCA_KIND])) {
		NL_SET_ERR_MSG(extack, "Cannot flush filters with protocol, handle or kind set");
		return -ENOENT;
	}

	/* Find head of filter chain. */

	block = tcf_block_find(net, &q, &parent, &cl,
			       t->tcm_ifindex, t->tcm_block_index, extack);
	if (IS_ERR(block)) {
		err = PTR_ERR(block);
		goto errout;
	}

	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
	if (chain_index > TC_ACT_EXT_VAL_MASK) {
		NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
		err = -EINVAL;
		goto errout;
	}
	chain = tcf_chain_get(block, chain_index, false);
	if (!chain) {
		NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
		err = -EINVAL;
		goto errout;
	}

	if (prio == 0) {
		tfilter_notify_chain(net, skb, block, q, parent, n,
				     chain, RTM_DELTFILTER);
		tcf_chain_flush(chain);
		err = 0;
		goto errout;
	}

	tp = tcf_chain_tp_find(chain, &chain_info, protocol,
			       prio, false);
	if (!tp || IS_ERR(tp)) {
		NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
		err = tp ? PTR_ERR(tp) : -ENOENT;
		goto errout;
	} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
		NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
		err = -EINVAL;
		goto errout;
	}

	fh = tp->ops->get(tp, t->tcm_handle);

	if (!fh) {
		if (t->tcm_handle == 0) {
			tcf_chain_tp_remove(chain, &chain_info, tp);
			tfilter_notify(net, skb, n, tp, block, q, parent, fh,
				       RTM_DELTFILTER, false);
			tcf_proto_destroy(tp, extack);
			err = 0;
		} else {
			NL_SET_ERR_MSG(extack, "Specified filter handle not found");
			err = -ENOENT;
		}
	} else {
		bool last;

		err = tfilter_del_notify(net, skb, n, tp, block,
					 q, parent, fh, false, &last,
					 extack);
		if (err)
			goto errout;
		if (last) {
			tcf_chain_tp_remove(chain, &chain_info, tp);
			tcf_proto_destroy(tp, extack);
		}
	}

errout:
	if (chain)
		tcf_chain_put(chain);
	return err;
}

static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
			  struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct nlattr *tca[TCA_MAX + 1];
	struct tcmsg *t;
	u32 protocol;
	u32 prio;
	u32 parent;
	u32 chain_index;
	struct Qdisc *q = NULL;
	struct tcf_chain_info chain_info;
	struct tcf_chain *chain = NULL;
	struct tcf_block *block;
	struct tcf_proto *tp = NULL;
	unsigned long cl = 0;
	void *fh = NULL;
	int err;

	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
	if (err < 0)
		return err;

	t = nlmsg_data(n);
	protocol = TC_H_MIN(t->tcm_info);
	prio = TC_H_MAJ(t->tcm_info);
	parent = t->tcm_parent;

	if (prio == 0) {
		NL_SET_ERR_MSG(extack, "Invalid filter command with priority of zero");
		return -ENOENT;
	}

	/* Find head of filter chain. */

	block = tcf_block_find(net, &q, &parent, &cl,
			       t->tcm_ifindex, t->tcm_block_index, extack);
	if (IS_ERR(block)) {
		err = PTR_ERR(block);
		goto errout;
	}

	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
	if (chain_index > TC_ACT_EXT_VAL_MASK) {
		NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
		err = -EINVAL;
		goto errout;
	}
	chain = tcf_chain_get(block, chain_index, false);
	if (!chain) {
		NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
		err = -EINVAL;
		goto errout;
	}

	tp = tcf_chain_tp_find(chain, &chain_info, protocol,
			       prio, false);
	if (!tp || IS_ERR(tp)) {
		NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
		err = tp ? PTR_ERR(tp) : -ENOENT;
		goto errout;
	} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
		NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
		err = -EINVAL;
		goto errout;
	}

	fh = tp->ops->get(tp, t->tcm_handle);

	if (!fh) {
		NL_SET_ERR_MSG(extack, "Specified filter handle not found");
		err = -ENOENT;
	} else {
		err = tfilter_notify(net, skb, n, tp, block, q, parent,
				     fh, RTM_NEWTFILTER, true);
		if (err < 0)
			NL_SET_ERR_MSG(extack, "Failed to send filter notify message");
	}

errout:
	if (chain)
		tcf_chain_put(chain);
	return err;
}

struct tcf_dump_args {
	struct tcf_walker w;
	struct sk_buff *skb;
	struct netlink_callback *cb;
	struct tcf_block *block;
	struct Qdisc *q;
	u32 parent;
};

static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
{
	struct tcf_dump_args *a = (void *)arg;
	struct net *net = sock_net(a->skb->sk);

	return tcf_fill_node(net, a->skb, tp, a->block, a->q, a->parent,
			     n, NETLINK_CB(a->cb->skb).portid,
			     a->cb->nlh->nlmsg_seq, NLM_F_MULTI,
			     RTM_NEWTFILTER);
}

static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
			   struct sk_buff *skb, struct netlink_callback *cb,
			   long index_start, long *p_index)
{
	struct net *net = sock_net(skb->sk);
	struct tcf_block *block = chain->block;
	struct tcmsg *tcm = nlmsg_data(cb->nlh);
	struct tcf_dump_args arg;
	struct tcf_proto *tp;

	for (tp = rtnl_dereference(chain->filter_chain);
	     tp; tp = rtnl_dereference(tp->next), (*p_index)++) {
		if (*p_index < index_start)
			continue;
		if (TC_H_MAJ(tcm->tcm_info) &&
		    TC_H_MAJ(tcm->tcm_info) != tp->prio)
			continue;
		if (TC_H_MIN(tcm->tcm_info) &&
		    TC_H_MIN(tcm->tcm_info) != tp->protocol)
			continue;
		if (*p_index > index_start)
			memset(&cb->args[1], 0,
			       sizeof(cb->args) - sizeof(cb->args[0]));
		if (cb->args[1] == 0) {
			if (tcf_fill_node(net, skb, tp, block, q, parent, 0,
					  NETLINK_CB(cb->skb).portid,
					  cb->nlh->nlmsg_seq, NLM_F_MULTI,
					  RTM_NEWTFILTER) <= 0)
				return false;

			cb->args[1] = 1;
		}
		if (!tp->ops->walk)
			continue;
		arg.w.fn = tcf_node_dump;
		arg.skb = skb;
		arg.cb = cb;
		arg.block = block;
		arg.q = q;
		arg.parent = parent;
		arg.w.stop = 0;
		arg.w.skip = cb->args[1] - 1;
		arg.w.count = 0;
		tp->ops->walk(tp, &arg.w);
		cb->args[1] = arg.w.count + 1;
		if (arg.w.stop)
			return false;
	}
	return true;
}

/* called with RTNL */
static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct net *net = sock_net(skb->sk);
	struct nlattr *tca[TCA_MAX + 1];
	struct Qdisc *q = NULL;
	struct tcf_block *block;
	struct tcf_chain *chain;
	struct tcmsg *tcm = nlmsg_data(cb->nlh);
	long index_start;
	long index;
	u32 parent;
	int err;

	if (nlmsg_len(cb->nlh) < sizeof(*tcm))
		return skb->len;

	err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL);
	if (err)
		return err;

	if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
		block = tcf_block_lookup(net, tcm->tcm_block_index);
		if (!block)
			goto out;
		/* If we work with block index, q is NULL and parent value
		 * will never be used in the following code. The check
		 * in tcf_fill_node prevents it. However, compiler does not
		 * see that far, so set parent to zero to silence the warning
		 * about parent being uninitialized.
		 */
		parent = 0;
	} else {
		const struct Qdisc_class_ops *cops;
		struct net_device *dev;
		unsigned long cl = 0;

		dev = __dev_get_by_index(net, tcm->tcm_ifindex);
		if (!dev)
			return skb->len;

		parent = tcm->tcm_parent;
		if (!parent) {
			q = dev->qdisc;
			parent = q->handle;
		} else {
			q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
		}
		if (!q)
			goto out;
		cops = q->ops->cl_ops;
		if (!cops)
			goto out;
		if (!cops->tcf_block)
			goto out;
		if (TC_H_MIN(tcm->tcm_parent)) {
			cl = cops->find(q, tcm->tcm_parent);
			if (cl == 0)
				goto out;
		}
		block = cops->tcf_block(q, cl, NULL);
		if (!block)
			goto out;
		if (tcf_block_shared(block))
			q = NULL;
	}

	index_start = cb->args[0];
	index = 0;

	list_for_each_entry(chain, &block->chain_list, list) {
		if (tca[TCA_CHAIN] &&
		    nla_get_u32(tca[TCA_CHAIN]) != chain->index)
			continue;
		if (!tcf_chain_dump(chain, q, parent, skb, cb,
				    index_start, &index)) {
			err = -EMSGSIZE;
			break;
		}
	}

	cb->args[0] = index;

out:
	/* If we did no progress, the error (EMSGSIZE) is real */
	if (skb->len == 0 && err)
		return err;
	return skb->len;
}

void tcf_exts_destroy(struct tcf_exts *exts)
{
#ifdef CONFIG_NET_CLS_ACT
	LIST_HEAD(actions);

	ASSERT_RTNL();
	tcf_exts_to_list(exts, &actions);
	tcf_action_destroy(&actions, TCA_ACT_UNBIND);
	kfree(exts->actions);
	exts->nr_actions = 0;
#endif
}
EXPORT_SYMBOL(tcf_exts_destroy);

int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
		      struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr,
		      struct netlink_ext_ack *extack)
{
#ifdef CONFIG_NET_CLS_ACT
	{
		struct tc_action *act;
		size_t attr_size = 0;

		if (exts->police && tb[exts->police]) {
			act = tcf_action_init_1(net, tp, tb[exts->police],
						rate_tlv, "police", ovr,
						TCA_ACT_BIND, extack);
			if (IS_ERR(act))
				return PTR_ERR(act);

			act->type = exts->type = TCA_OLD_COMPAT;
			exts->actions[0] = act;
			exts->nr_actions = 1;
		} else if (exts->action && tb[exts->action]) {
			LIST_HEAD(actions);
			int err, i = 0;

			err = tcf_action_init(net, tp, tb[exts->action],
					      rate_tlv, NULL, ovr, TCA_ACT_BIND,
					      &actions, &attr_size, extack);
			if (err)
				return err;
			list_for_each_entry(act, &actions, list)
				exts->actions[i++] = act;
			exts->nr_actions = i;
		}
		exts->net = net;
	}
#else
	if ((exts->action && tb[exts->action]) ||
	    (exts->police && tb[exts->police])) {
		NL_SET_ERR_MSG(extack, "Classifier actions are not supported per compile options (CONFIG_NET_CLS_ACT)");
		return -EOPNOTSUPP;
	}
#endif

	return 0;
}
EXPORT_SYMBOL(tcf_exts_validate);

void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src)
{
#ifdef CONFIG_NET_CLS_ACT
	struct tcf_exts old = *dst;

	*dst = *src;
	tcf_exts_destroy(&old);
#endif
}
EXPORT_SYMBOL(tcf_exts_change);

#ifdef CONFIG_NET_CLS_ACT
static struct tc_action *tcf_exts_first_act(struct tcf_exts *exts)
{
	if (exts->nr_actions == 0)
		return NULL;
	else
		return exts->actions[0];
}
#endif

int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts)
{
#ifdef CONFIG_NET_CLS_ACT
	struct nlattr *nest;

	if (exts->action && tcf_exts_has_actions(exts)) {
		/*
		 * again for backward compatible mode - we want
		 * to work with both old and new modes of entering
		 * tc data even if iproute2  was newer - jhs
		 */
		if (exts->type != TCA_OLD_COMPAT) {
			LIST_HEAD(actions);

			nest = nla_nest_start(skb, exts->action);
			if (nest == NULL)
				goto nla_put_failure;

			tcf_exts_to_list(exts, &actions);
			if (tcf_action_dump(skb, &actions, 0, 0) < 0)
				goto nla_put_failure;
			nla_nest_end(skb, nest);
		} else if (exts->police) {
			struct tc_action *act = tcf_exts_first_act(exts);
			nest = nla_nest_start(skb, exts->police);
			if (nest == NULL || !act)
				goto nla_put_failure;
			if (tcf_action_dump_old(skb, act, 0, 0) < 0)
				goto nla_put_failure;
			nla_nest_end(skb, nest);
		}
	}
	return 0;

nla_put_failure:
	nla_nest_cancel(skb, nest);
	return -1;
#else
	return 0;
#endif
}
EXPORT_SYMBOL(tcf_exts_dump);


int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts)
{
#ifdef CONFIG_NET_CLS_ACT
	struct tc_action *a = tcf_exts_first_act(exts);
	if (a != NULL && tcf_action_copy_stats(skb, a, 1) < 0)
		return -1;
#endif
	return 0;
}
EXPORT_SYMBOL(tcf_exts_dump_stats);

static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts,
				       enum tc_setup_type type,
				       void *type_data, bool err_stop)
{
	int ok_count = 0;
#ifdef CONFIG_NET_CLS_ACT
	const struct tc_action *a;
	struct net_device *dev;
	int i, ret;

	if (!tcf_exts_has_actions(exts))
		return 0;

	for (i = 0; i < exts->nr_actions; i++) {
		a = exts->actions[i];
		if (!a->ops->get_dev)
			continue;
		dev = a->ops->get_dev(a);
		if (!dev)
			continue;
		ret = tc_setup_cb_egdev_call(dev, type, type_data, err_stop);
		if (ret < 0)
			return ret;
		ok_count += ret;
	}
#endif
	return ok_count;
}

int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts,
		     enum tc_setup_type type, void *type_data, bool err_stop)
{
	int ok_count;
	int ret;

	ret = tcf_block_cb_call(block, type, type_data, err_stop);
	if (ret < 0)
		return ret;
	ok_count = ret;

	if (!exts || ok_count)
		return ok_count;
	ret = tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop);
	if (ret < 0)
		return ret;
	ok_count += ret;

	return ok_count;
}
EXPORT_SYMBOL(tc_setup_cb_call);

static __net_init int tcf_net_init(struct net *net)
{
	struct tcf_net *tn = net_generic(net, tcf_net_id);

	idr_init(&tn->idr);
	return 0;
}

static void __net_exit tcf_net_exit(struct net *net)
{
	struct tcf_net *tn = net_generic(net, tcf_net_id);

	idr_destroy(&tn->idr);
}

static struct pernet_operations tcf_net_ops = {
	.init = tcf_net_init,
	.exit = tcf_net_exit,
	.id   = &tcf_net_id,
	.size = sizeof(struct tcf_net),
};

static int __init tc_filter_init(void)
{
	int err;

	tc_filter_wq = alloc_ordered_workqueue("tc_filter_workqueue", 0);
	if (!tc_filter_wq)
		return -ENOMEM;

	err = register_pernet_subsys(&tcf_net_ops);
	if (err)
		goto err_register_pernet_subsys;

	rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, 0);
	rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, 0);
	rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter,
		      tc_dump_tfilter, 0);

	return 0;

err_register_pernet_subsys:
	destroy_workqueue(tc_filter_wq);
	return err;
}

subsys_initcall(tc_filter_init);