summaryrefslogtreecommitdiffstats
path: root/net/sched/cls_api.c
blob: d29e79d98a69e7ca94384ed64520df8f4f3bff83 (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
/*
 * 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/err.h>
#include <linux/slab.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);

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();

	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);

/* 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, u32 parent, struct Qdisc *q,
					  struct tcf_chain *chain)
{
	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 {
			err = -ENOENT;
		}
		goto errout;
#endif
	}
	tp->classify = tp->ops->classify;
	tp->protocol = protocol;
	tp->prio = prio;
	tp->classid = parent;
	tp->q = q;
	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)
{
	tp->ops->destroy(tp);
	module_put(tp->ops->owner);
	kfree_rcu(tp, rcu);
}

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;
	list_add_tail(&chain->list, &block->chain_list);
	chain->block = block;
	chain->index = chain_index;
	chain->refcnt = 1;
	return chain;
}

static void tcf_chain_flush(struct tcf_chain *chain)
{
	struct tcf_proto *tp;

	if (chain->p_filter_chain)
		RCU_INIT_POINTER(*chain->p_filter_chain, NULL);
	while ((tp = rtnl_dereference(chain->filter_chain)) != NULL) {
		RCU_INIT_POINTER(chain->filter_chain, tp->next);
		tcf_chain_put(chain);
		tcf_proto_destroy(tp);
	}
}

static void tcf_chain_destroy(struct tcf_chain *chain)
{
	list_del(&chain->list);
	kfree(chain);
}

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 void
tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain,
			       struct tcf_proto __rcu **p_filter_chain)
{
	chain->p_filter_chain = p_filter_chain;
}

int tcf_block_get(struct tcf_block **p_block,
		  struct tcf_proto __rcu **p_filter_chain)
{
	struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL);
	struct tcf_chain *chain;
	int err;

	if (!block)
		return -ENOMEM;
	INIT_LIST_HEAD(&block->chain_list);
	/* Create chain 0 by default, it has to be always present. */
	chain = tcf_chain_create(block, 0);
	if (!chain) {
		err = -ENOMEM;
		goto err_chain_create;
	}
	tcf_chain_filter_chain_ptr_set(chain, p_filter_chain);
	*p_block = block;
	return 0;

err_chain_create:
	kfree(block);
	return err;
}
EXPORT_SYMBOL(tcf_block_get);

void tcf_block_put(struct tcf_block *block)
{
	struct tcf_chain *chain, *tmp;

	if (!block)
		return;

	/* XXX: Standalone actions are not allowed to jump to any chain, and
	 * bound actions should be all removed after flushing. However,
	 * filters are destroyed in RCU callbacks, we have to flush and wait
	 * for them inside the loop, otherwise we race with RCU callbacks on
	 * this list.
	 */
	list_for_each_entry_safe(chain, tmp, &block->chain_list, list) {
		tcf_chain_flush(chain);
		rcu_barrier();
	}

	list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
		tcf_chain_put(chain);
	kfree(block);
}
EXPORT_SYMBOL(tcf_block_put);

/* 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("%s: reclassify loop, rule prio %u, protocol %02x\n",
				       tp->q->ops->id, 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->p_filter_chain &&
	    *chain_info->pprev == chain->filter_chain)
		rcu_assign_pointer(*chain->p_filter_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 (chain->p_filter_chain && tp == chain->filter_chain)
		RCU_INIT_POINTER(*chain->p_filter_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, 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;
	tcm->tcm_ifindex = qdisc_dev(tp->q)->ifindex;
	tcm->tcm_parent = tp->classid;
	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,
			  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, 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,
			      void *fh, bool unicast, bool *last)
{
	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, fh, portid, n->nlmsg_seq,
			  n->nlmsg_flags, RTM_DELTFILTER) <= 0) {
		kfree_skb(skb);
		return -EINVAL;
	}

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

	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 void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
				 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, 0, event, false);
}

/* Add/change/delete/get a filter node */

static int tc_ctl_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 net_device *dev;
	struct Qdisc  *q;
	struct tcf_chain_info chain_info;
	struct tcf_chain *chain = NULL;
	struct tcf_block *block;
	struct tcf_proto *tp;
	const struct Qdisc_class_ops *cops;
	unsigned long cl;
	void *fh;
	int err;
	int tp_created;

	if ((n->nlmsg_type != RTM_GETTFILTER) &&
	    !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) {
		switch (n->nlmsg_type) {
		case RTM_DELTFILTER:
			if (protocol || t->tcm_handle || tca[TCA_KIND])
				return -ENOENT;
			break;
		case RTM_NEWTFILTER:
			/* 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;
				break;
			}
			/* fall-through */
		default:
			return -ENOENT;
		}
	}

	/* Find head of filter chain. */

	/* Find link */
	dev = __dev_get_by_index(net, t->tcm_ifindex);
	if (dev == NULL)
		return -ENODEV;

	/* Find qdisc */
	if (!parent) {
		q = dev->qdisc;
		parent = q->handle;
	} else {
		q = qdisc_lookup(dev, TC_H_MAJ(t->tcm_parent));
		if (q == NULL)
			return -EINVAL;
	}

	/* Is it classful? */
	cops = q->ops->cl_ops;
	if (!cops)
		return -EINVAL;

	if (!cops->tcf_block)
		return -EOPNOTSUPP;

	/* Do we search for filter, attached to class? */
	if (TC_H_MIN(parent)) {
		cl = cops->find(q, parent);
		if (cl == 0)
			return -ENOENT;
	}

	/* And the last stroke */
	block = cops->tcf_block(q, cl);
	if (!block) {
		err = -EINVAL;
		goto errout;
	}

	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
	if (chain_index > TC_ACT_EXT_VAL_MASK) {
		err = -EINVAL;
		goto errout;
	}
	chain = tcf_chain_get(block, chain_index,
			      n->nlmsg_type == RTM_NEWTFILTER);
	if (!chain) {
		err = n->nlmsg_type == RTM_NEWTFILTER ? -ENOMEM : -EINVAL;
		goto errout;
	}

	if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) {
		tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER);
		tcf_chain_flush(chain);
		err = 0;
		goto errout;
	}

	tp = tcf_chain_tp_find(chain, &chain_info, protocol,
			       prio, prio_allocate);
	if (IS_ERR(tp)) {
		err = PTR_ERR(tp);
		goto errout;
	}

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

		if (tca[TCA_KIND] == NULL || !protocol) {
			err = -EINVAL;
			goto errout;
		}

		if (n->nlmsg_type != RTM_NEWTFILTER ||
		    !(n->nlmsg_flags & NLM_F_CREATE)) {
			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, parent, q, chain);
		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)) {
		err = -EINVAL;
		goto errout;
	}

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

	if (!fh) {
		if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) {
			tcf_chain_tp_remove(chain, &chain_info, tp);
			tfilter_notify(net, skb, n, tp, fh,
				       RTM_DELTFILTER, false);
			tcf_proto_destroy(tp);
			err = 0;
			goto errout;
		}

		if (n->nlmsg_type != RTM_NEWTFILTER ||
		    !(n->nlmsg_flags & NLM_F_CREATE)) {
			err = -ENOENT;
			goto errout;
		}
	} else {
		bool last;

		switch (n->nlmsg_type) {
		case RTM_NEWTFILTER:
			if (n->nlmsg_flags & NLM_F_EXCL) {
				if (tp_created)
					tcf_proto_destroy(tp);
				err = -EEXIST;
				goto errout;
			}
			break;
		case RTM_DELTFILTER:
			err = tfilter_del_notify(net, skb, n, tp, fh, false,
						 &last);
			if (err)
				goto errout;
			if (last) {
				tcf_chain_tp_remove(chain, &chain_info, tp);
				tcf_proto_destroy(tp);
			}
			goto errout;
		case RTM_GETTFILTER:
			err = tfilter_notify(net, skb, n, tp, fh,
					     RTM_NEWTFILTER, true);
			goto errout;
		default:
			err = -EINVAL;
			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);
	if (err == 0) {
		if (tp_created)
			tcf_chain_tp_insert(chain, &chain_info, tp);
		tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER, false);
	} else {
		if (tp_created)
			tcf_proto_destroy(tp);
	}

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

struct tcf_dump_args {
	struct tcf_walker w;
	struct sk_buff *skb;
	struct netlink_callback *cb;
};

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, 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 sk_buff *skb,
			   struct netlink_callback *cb,
			   long index_start, long *p_index)
{
	struct net *net = sock_net(skb->sk);
	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, 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.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 net_device *dev;
	struct Qdisc *q;
	struct tcf_block *block;
	struct tcf_chain *chain;
	struct tcmsg *tcm = nlmsg_data(cb->nlh);
	unsigned long cl = 0;
	const struct Qdisc_class_ops *cops;
	long index_start;
	long index;
	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;

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

	if (!tcm->tcm_parent)
		q = dev->qdisc;
	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);
	if (!block)
		goto out;

	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, skb, cb, index_start, &index))
			break;
	}

	cb->args[0] = index;

out:
	return skb->len;
}

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

	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)
{
#ifdef CONFIG_NET_CLS_ACT
	{
		struct tc_action *act;

		if (exts->police && tb[exts->police]) {
			act = tcf_action_init_1(net, tp, tb[exts->police],
						rate_tlv, "police", ovr,
						TCA_ACT_BIND);
			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);
			if (err)
				return err;
			list_for_each_entry(act, &actions, list)
				exts->actions[i++] = act;
			exts->nr_actions = i;
		}
	}
#else
	if ((exts->action && tb[exts->action]) ||
	    (exts->police && tb[exts->police]))
		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);

int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts,
		     struct net_device **hw_dev)
{
#ifdef CONFIG_NET_CLS_ACT
	const struct tc_action *a;
	LIST_HEAD(actions);

	if (!tcf_exts_has_actions(exts))
		return -EINVAL;

	tcf_exts_to_list(exts, &actions);
	list_for_each_entry(a, &actions, list) {
		if (a->ops->get_dev) {
			a->ops->get_dev(a, dev_net(dev), hw_dev);
			break;
		}
	}
	if (*hw_dev)
		return 0;
#endif
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(tcf_exts_get_dev);

static int __init tc_filter_init(void)
{
	rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, 0);
	rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL, 0);
	rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_ctl_tfilter,
		      tc_dump_tfilter, 0);

	return 0;
}

subsys_initcall(tc_filter_init);