forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathcls_api.c
2577 lines (2211 loc) · 62.7 KB
/
cls_api.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* 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, <[email protected]>
*
* Changes:
*
* Eduardo J. Blanco <[email protected]> :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 <linux/rhashtable.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1];
/* 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;
}
static const struct tcf_proto_ops *
tcf_proto_lookup_ops(const char *kind, struct netlink_ext_ack *extack)
{
const struct tcf_proto_ops *ops;
ops = __tcf_proto_lookup_ops(kind);
if (ops)
return ops;
#ifdef CONFIG_MODULES
rtnl_unlock();
request_module("cls_%s", kind);
rtnl_lock();
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 (ops) {
module_put(ops->owner);
return ERR_PTR(-EAGAIN);
}
#endif
NL_SET_ERR_MSG(extack, "TC classifier not found");
return ERR_PTR(-ENOENT);
}
/* 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);
tp->ops = tcf_proto_lookup_ops(kind, extack);
if (IS_ERR(tp->ops)) {
err = PTR_ERR(tp->ops);
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;
list_add_tail(&chain->list, &block->chain_list);
chain->block = block;
chain->index = chain_index;
chain->refcnt = 1;
if (!chain->index)
block->chain0.chain = chain;
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_chain0_head_change(struct tcf_chain *chain,
struct tcf_proto *tp_head)
{
struct tcf_filter_chain_list_item *item;
struct tcf_block *block = chain->block;
if (chain->index)
return;
list_for_each_entry(item, &block->chain0.filter_chain_list, list)
tcf_chain_head_change_item(item, tp_head);
}
static void tcf_chain_destroy(struct tcf_chain *chain)
{
struct tcf_block *block = chain->block;
list_del(&chain->list);
if (!chain->index)
block->chain0.chain = NULL;
kfree(chain);
if (list_empty(&block->chain_list) && !refcount_read(&block->refcnt))
kfree_rcu(block, rcu);
}
static void tcf_chain_hold(struct tcf_chain *chain)
{
++chain->refcnt;
}
static bool tcf_chain_held_by_acts_only(struct tcf_chain *chain)
{
/* In case all the references are action references, this
* chain should not be shown to the user.
*/
return chain->refcnt == chain->action_refcnt;
}
static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block,
u32 chain_index)
{
struct tcf_chain *chain;
list_for_each_entry(chain, &block->chain_list, list) {
if (chain->index == chain_index)
return chain;
}
return NULL;
}
static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
u32 seq, u16 flags, int event, bool unicast);
static struct tcf_chain *__tcf_chain_get(struct tcf_block *block,
u32 chain_index, bool create,
bool by_act)
{
struct tcf_chain *chain = tcf_chain_lookup(block, chain_index);
if (chain) {
tcf_chain_hold(chain);
} else {
if (!create)
return NULL;
chain = tcf_chain_create(block, chain_index);
if (!chain)
return NULL;
}
if (by_act)
++chain->action_refcnt;
/* Send notification only in case we got the first
* non-action reference. Until then, the chain acts only as
* a placeholder for actions pointing to it and user ought
* not know about them.
*/
if (chain->refcnt - chain->action_refcnt == 1 && !by_act)
tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL,
RTM_NEWCHAIN, false);
return chain;
}
static struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
bool create)
{
return __tcf_chain_get(block, chain_index, create, false);
}
struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index)
{
return __tcf_chain_get(block, chain_index, true, true);
}
EXPORT_SYMBOL(tcf_chain_get_by_act);
static void tc_chain_tmplt_del(struct tcf_chain *chain);
static void __tcf_chain_put(struct tcf_chain *chain, bool by_act)
{
if (by_act)
chain->action_refcnt--;
chain->refcnt--;
/* The last dropped non-action reference will trigger notification. */
if (chain->refcnt - chain->action_refcnt == 0 && !by_act)
tc_chain_notify(chain, NULL, 0, 0, RTM_DELCHAIN, false);
if (chain->refcnt == 0) {
tc_chain_tmplt_del(chain);
tcf_chain_destroy(chain);
}
}
static void tcf_chain_put(struct tcf_chain *chain)
{
__tcf_chain_put(chain, false);
}
void tcf_chain_put_by_act(struct tcf_chain *chain)
{
__tcf_chain_put(chain, true);
}
EXPORT_SYMBOL(tcf_chain_put_by_act);
static void tcf_chain_put_explicitly_created(struct tcf_chain *chain)
{
if (chain->explicitly_created)
tcf_chain_put(chain);
}
static void tcf_chain_flush(struct tcf_chain *chain)
{
struct tcf_proto *tp = rtnl_dereference(chain->filter_chain);
tcf_chain0_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 struct tcf_block *tc_dev_ingress_block(struct net_device *dev)
{
const struct Qdisc_class_ops *cops;
struct Qdisc *qdisc;
if (!dev_ingress_queue(dev))
return NULL;
qdisc = dev_ingress_queue(dev)->qdisc_sleeping;
if (!qdisc)
return NULL;
cops = qdisc->ops->cl_ops;
if (!cops)
return NULL;
if (!cops->tcf_block)
return NULL;
return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL);
}
static struct rhashtable indr_setup_block_ht;
struct tc_indr_block_dev {
struct rhash_head ht_node;
struct net_device *dev;
unsigned int refcnt;
struct list_head cb_list;
struct tcf_block *block;
};
struct tc_indr_block_cb {
struct list_head list;
void *cb_priv;
tc_indr_block_bind_cb_t *cb;
void *cb_ident;
};
static const struct rhashtable_params tc_indr_setup_block_ht_params = {
.key_offset = offsetof(struct tc_indr_block_dev, dev),
.head_offset = offsetof(struct tc_indr_block_dev, ht_node),
.key_len = sizeof(struct net_device *),
};
static struct tc_indr_block_dev *
tc_indr_block_dev_lookup(struct net_device *dev)
{
return rhashtable_lookup_fast(&indr_setup_block_ht, &dev,
tc_indr_setup_block_ht_params);
}
static struct tc_indr_block_dev *tc_indr_block_dev_get(struct net_device *dev)
{
struct tc_indr_block_dev *indr_dev;
indr_dev = tc_indr_block_dev_lookup(dev);
if (indr_dev)
goto inc_ref;
indr_dev = kzalloc(sizeof(*indr_dev), GFP_KERNEL);
if (!indr_dev)
return NULL;
INIT_LIST_HEAD(&indr_dev->cb_list);
indr_dev->dev = dev;
indr_dev->block = tc_dev_ingress_block(dev);
if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node,
tc_indr_setup_block_ht_params)) {
kfree(indr_dev);
return NULL;
}
inc_ref:
indr_dev->refcnt++;
return indr_dev;
}
static void tc_indr_block_dev_put(struct tc_indr_block_dev *indr_dev)
{
if (--indr_dev->refcnt)
return;
rhashtable_remove_fast(&indr_setup_block_ht, &indr_dev->ht_node,
tc_indr_setup_block_ht_params);
kfree(indr_dev);
}
static struct tc_indr_block_cb *
tc_indr_block_cb_lookup(struct tc_indr_block_dev *indr_dev,
tc_indr_block_bind_cb_t *cb, void *cb_ident)
{
struct tc_indr_block_cb *indr_block_cb;
list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list)
if (indr_block_cb->cb == cb &&
indr_block_cb->cb_ident == cb_ident)
return indr_block_cb;
return NULL;
}
static struct tc_indr_block_cb *
tc_indr_block_cb_add(struct tc_indr_block_dev *indr_dev, void *cb_priv,
tc_indr_block_bind_cb_t *cb, void *cb_ident)
{
struct tc_indr_block_cb *indr_block_cb;
indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident);
if (indr_block_cb)
return ERR_PTR(-EEXIST);
indr_block_cb = kzalloc(sizeof(*indr_block_cb), GFP_KERNEL);
if (!indr_block_cb)
return ERR_PTR(-ENOMEM);
indr_block_cb->cb_priv = cb_priv;
indr_block_cb->cb = cb;
indr_block_cb->cb_ident = cb_ident;
list_add(&indr_block_cb->list, &indr_dev->cb_list);
return indr_block_cb;
}
static void tc_indr_block_cb_del(struct tc_indr_block_cb *indr_block_cb)
{
list_del(&indr_block_cb->list);
kfree(indr_block_cb);
}
static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev,
struct tc_indr_block_cb *indr_block_cb,
enum tc_block_command command)
{
struct tc_block_offload bo = {
.command = command,
.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS,
.block = indr_dev->block,
};
if (!indr_dev->block)
return;
indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK,
&bo);
}
int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
tc_indr_block_bind_cb_t *cb, void *cb_ident)
{
struct tc_indr_block_cb *indr_block_cb;
struct tc_indr_block_dev *indr_dev;
int err;
indr_dev = tc_indr_block_dev_get(dev);
if (!indr_dev)
return -ENOMEM;
indr_block_cb = tc_indr_block_cb_add(indr_dev, cb_priv, cb, cb_ident);
err = PTR_ERR_OR_ZERO(indr_block_cb);
if (err)
goto err_dev_put;
tc_indr_block_ing_cmd(indr_dev, indr_block_cb, TC_BLOCK_BIND);
return 0;
err_dev_put:
tc_indr_block_dev_put(indr_dev);
return err;
}
EXPORT_SYMBOL_GPL(__tc_indr_block_cb_register);
int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
tc_indr_block_bind_cb_t *cb, void *cb_ident)
{
int err;
rtnl_lock();
err = __tc_indr_block_cb_register(dev, cb_priv, cb, cb_ident);
rtnl_unlock();
return err;
}
EXPORT_SYMBOL_GPL(tc_indr_block_cb_register);
void __tc_indr_block_cb_unregister(struct net_device *dev,
tc_indr_block_bind_cb_t *cb, void *cb_ident)
{
struct tc_indr_block_cb *indr_block_cb;
struct tc_indr_block_dev *indr_dev;
indr_dev = tc_indr_block_dev_lookup(dev);
if (!indr_dev)
return;
indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident);
if (!indr_block_cb)
return;
/* Send unbind message if required to free any block cbs. */
tc_indr_block_ing_cmd(indr_dev, indr_block_cb, TC_BLOCK_UNBIND);
tc_indr_block_cb_del(indr_block_cb);
tc_indr_block_dev_put(indr_dev);
}
EXPORT_SYMBOL_GPL(__tc_indr_block_cb_unregister);
void tc_indr_block_cb_unregister(struct net_device *dev,
tc_indr_block_bind_cb_t *cb, void *cb_ident)
{
rtnl_lock();
__tc_indr_block_cb_unregister(dev, cb, cb_ident);
rtnl_unlock();
}
EXPORT_SYMBOL_GPL(tc_indr_block_cb_unregister);
static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev,
struct tcf_block_ext_info *ei,
enum tc_block_command command,
struct netlink_ext_ack *extack)
{
struct tc_indr_block_cb *indr_block_cb;
struct tc_indr_block_dev *indr_dev;
struct tc_block_offload bo = {
.command = command,
.binder_type = ei->binder_type,
.block = block,
.extack = extack,
};
indr_dev = tc_indr_block_dev_lookup(dev);
if (!indr_dev)
return;
indr_dev->block = command == TC_BLOCK_BIND ? block : NULL;
list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list)
indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK,
&bo);
}
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 netlink_ext_ack *extack)
{
struct tc_block_offload bo = {};
bo.command = command;
bo.binder_type = ei->binder_type;
bo.block = block;
bo.extack = extack;
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 netlink_ext_ack *extack)
{
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)) {
NL_SET_ERR_MSG(extack, "Bind to offloaded block failed as dev has offload disabled");
return -EOPNOTSUPP;
}
err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND, extack);
if (err == -EOPNOTSUPP)
goto no_offload_dev_inc;
if (err)
return err;
tc_indr_block_call(block, dev, ei, TC_BLOCK_BIND, extack);
return 0;
no_offload_dev_inc:
if (tcf_block_offload_in_use(block))
return -EOPNOTSUPP;
block->nooffloaddevcnt++;
tc_indr_block_call(block, dev, ei, TC_BLOCK_BIND, extack);
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;
tc_indr_block_call(block, dev, ei, TC_BLOCK_UNBIND, NULL);
if (!dev->netdev_ops->ndo_setup_tc)
goto no_offload_dev_dec;
err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND, NULL);
if (err == -EOPNOTSUPP)
goto no_offload_dev_dec;
return;
no_offload_dev_dec:
WARN_ON(block->nooffloaddevcnt-- == 0);
}
static int
tcf_chain0_head_change_cb_add(struct tcf_block *block,
struct tcf_block_ext_info *ei,
struct netlink_ext_ack *extack)
{
struct tcf_chain *chain0 = block->chain0.chain;
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 (chain0 && chain0->filter_chain)
tcf_chain_head_change_item(item, chain0->filter_chain);
list_add(&item->list, &block->chain0.filter_chain_list);
return 0;
}
static void
tcf_chain0_head_change_cb_del(struct tcf_block *block,
struct tcf_block_ext_info *ei)
{
struct tcf_chain *chain0 = block->chain0.chain;
struct tcf_filter_chain_list_item *item;
list_for_each_entry(item, &block->chain0.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)) {
if (chain0)
tcf_chain_head_change_item(item, NULL);
list_del(&item->list);
kfree(item);
return;
}
}
WARN_ON(1);
}
struct tcf_net {
spinlock_t idr_lock; /* Protects idr */
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);
int err;
idr_preload(GFP_KERNEL);
spin_lock(&tn->idr_lock);
err = idr_alloc_u32(&tn->idr, block, &block->index, block->index,
GFP_NOWAIT);
spin_unlock(&tn->idr_lock);
idr_preload_end();
return err;
}
static void tcf_block_remove(struct tcf_block *block, struct net *net)
{
struct tcf_net *tn = net_generic(net, tcf_net_id);
spin_lock(&tn->idr_lock);
idr_remove(&tn->idr, block->index);
spin_unlock(&tn->idr_lock);
}
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;
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);
INIT_LIST_HEAD(&block->chain0.filter_chain_list);
refcount_set(&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;
}
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);
}
static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index)
{
struct tcf_block *block;
rcu_read_lock();
block = tcf_block_lookup(net, block_index);
if (block && !refcount_inc_not_zero(&block->refcnt))
block = NULL;
rcu_read_unlock();
return block;
}
static void tcf_block_flush_all_chains(struct tcf_block *block)
{
struct tcf_chain *chain;
/* 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);
}
static void tcf_block_put_all_chains(struct tcf_block *block)
{
struct tcf_chain *chain, *tmp;
/* At this point, all the chains should have refcnt >= 1. */
list_for_each_entry_safe(chain, tmp, &block->chain_list, list) {
tcf_chain_put_explicitly_created(chain);
tcf_chain_put(chain);
}
}
static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q,
struct tcf_block_ext_info *ei)
{
if (refcount_dec_and_test(&block->refcnt)) {
/* Flushing/putting all chains will cause the block to be
* deallocated when last chain is freed. However, if chain_list
* is empty, block has to be manually deallocated. After block
* reference counter reached 0, it is no longer possible to
* increment it or add new chains to block.
*/
bool free_block = list_empty(&block->chain_list);
if (tcf_block_shared(block))
tcf_block_remove(block, block->net);
if (!free_block)
tcf_block_flush_all_chains(block);
if (q)
tcf_block_offload_unbind(block, q, ei);
if (free_block)
kfree_rcu(block, rcu);
else
tcf_block_put_all_chains(block);
} else if (q) {
tcf_block_offload_unbind(block, q, ei);
}
}
static void tcf_block_refcnt_put(struct tcf_block *block)
{
__tcf_block_put(block, NULL, NULL);
}
/* 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;
int err = 0;
if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
block = tcf_block_refcnt_get(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;
rcu_read_lock();
/* Find link */
dev = dev_get_by_index_rcu(net, ifindex);
if (!dev) {
rcu_read_unlock();
return ERR_PTR(-ENODEV);
}
/* Find qdisc */
if (!*parent) {
*q = dev->qdisc;
*parent = (*q)->handle;
} else {
*q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent));
if (!*q) {
NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
err = -EINVAL;
goto errout_rcu;
}
}
*q = qdisc_refcount_inc_nz(*q);
if (!*q) {
NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
err = -EINVAL;
goto errout_rcu;
}
/* Is it classful? */
cops = (*q)->ops->cl_ops;
if (!cops) {
NL_SET_ERR_MSG(extack, "Qdisc not classful");
err = -EINVAL;
goto errout_rcu;
}
if (!cops->tcf_block) {
NL_SET_ERR_MSG(extack, "Class doesn't support blocks");
err = -EOPNOTSUPP;
goto errout_rcu;
}
/* At this point we know that qdisc is not noop_qdisc,
* which means that qdisc holds a reference to net_device
* and we hold a reference to qdisc, so it is safe to release
* rcu read lock.
*/
rcu_read_unlock();
/* 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");
err = -ENOENT;
goto errout_qdisc;
}
}
/* And the last stroke */
block = cops->tcf_block(*q, *cl, extack);
if (!block) {
err = -EINVAL;
goto errout_qdisc;
}
if (tcf_block_shared(block)) {
NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters");
err = -EOPNOTSUPP;
goto errout_qdisc;
}
/* Always take reference to block in order to support execution
* of rules update path of cls API without rtnl lock. Caller
* must release block when it is finished using it. 'if' block
* of this conditional obtain reference to block by calling
* tcf_block_refcnt_get().
*/
refcount_inc(&block->refcnt);
}
return block;
errout_rcu:
rcu_read_unlock();
errout_qdisc:
if (*q) {
qdisc_put(*q);
*q = NULL;
}
return ERR_PTR(err);
}
static void tcf_block_release(struct Qdisc *q, struct tcf_block *block)
{
if (!IS_ERR_OR_NULL(block))
tcf_block_refcnt_put(block);
if (q)
qdisc_put(q);
}
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));
}