forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathact_api.c
2257 lines (1909 loc) · 52.7 KB
/
act_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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* net/sched/act_api.c Packet action API.
*
* Author: Jamal Hadi Salim
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/err.h>
#include <linux/module.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/sch_generic.h>
#include <net/pkt_cls.h>
#include <net/tc_act/tc_pedit.h>
#include <net/act_api.h>
#include <net/netlink.h>
#include <net/flow_offload.h>
#include <net/tc_wrapper.h>
#ifdef CONFIG_INET
DEFINE_STATIC_KEY_FALSE(tcf_frag_xmit_count);
EXPORT_SYMBOL_GPL(tcf_frag_xmit_count);
#endif
int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb))
{
#ifdef CONFIG_INET
if (static_branch_unlikely(&tcf_frag_xmit_count))
return sch_frag_xmit_hook(skb, xmit);
#endif
return xmit(skb);
}
EXPORT_SYMBOL_GPL(tcf_dev_queue_xmit);
static void tcf_action_goto_chain_exec(const struct tc_action *a,
struct tcf_result *res)
{
const struct tcf_chain *chain = rcu_dereference_bh(a->goto_chain);
res->goto_tp = rcu_dereference_bh(chain->filter_chain);
}
static void tcf_free_cookie_rcu(struct rcu_head *p)
{
struct tc_cookie *cookie = container_of(p, struct tc_cookie, rcu);
kfree(cookie->data);
kfree(cookie);
}
static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie,
struct tc_cookie *new_cookie)
{
struct tc_cookie *old;
old = xchg((__force struct tc_cookie **)old_cookie, new_cookie);
if (old)
call_rcu(&old->rcu, tcf_free_cookie_rcu);
}
int tcf_action_check_ctrlact(int action, struct tcf_proto *tp,
struct tcf_chain **newchain,
struct netlink_ext_ack *extack)
{
int opcode = TC_ACT_EXT_OPCODE(action), ret = -EINVAL;
u32 chain_index;
if (!opcode)
ret = action > TC_ACT_VALUE_MAX ? -EINVAL : 0;
else if (opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC)
ret = 0;
if (ret) {
NL_SET_ERR_MSG(extack, "invalid control action");
goto end;
}
if (TC_ACT_EXT_CMP(action, TC_ACT_GOTO_CHAIN)) {
chain_index = action & TC_ACT_EXT_VAL_MASK;
if (!tp || !newchain) {
ret = -EINVAL;
NL_SET_ERR_MSG(extack,
"can't goto NULL proto/chain");
goto end;
}
*newchain = tcf_chain_get_by_act(tp->chain->block, chain_index);
if (!*newchain) {
ret = -ENOMEM;
NL_SET_ERR_MSG(extack,
"can't allocate goto_chain");
}
}
end:
return ret;
}
EXPORT_SYMBOL(tcf_action_check_ctrlact);
struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action,
struct tcf_chain *goto_chain)
{
a->tcfa_action = action;
goto_chain = rcu_replace_pointer(a->goto_chain, goto_chain, 1);
return goto_chain;
}
EXPORT_SYMBOL(tcf_action_set_ctrlact);
/* XXX: For standalone actions, we don't need a RCU grace period either, because
* actions are always connected to filters and filters are already destroyed in
* RCU callbacks, so after a RCU grace period actions are already disconnected
* from filters. Readers later can not find us.
*/
static void free_tcf(struct tc_action *p)
{
struct tcf_chain *chain = rcu_dereference_protected(p->goto_chain, 1);
free_percpu(p->cpu_bstats);
free_percpu(p->cpu_bstats_hw);
free_percpu(p->cpu_qstats);
tcf_set_action_cookie(&p->user_cookie, NULL);
if (chain)
tcf_chain_put_by_act(chain);
kfree(p);
}
static void offload_action_hw_count_set(struct tc_action *act,
u32 hw_count)
{
act->in_hw_count = hw_count;
}
static void offload_action_hw_count_inc(struct tc_action *act,
u32 hw_count)
{
act->in_hw_count += hw_count;
}
static void offload_action_hw_count_dec(struct tc_action *act,
u32 hw_count)
{
act->in_hw_count = act->in_hw_count > hw_count ?
act->in_hw_count - hw_count : 0;
}
static unsigned int tcf_offload_act_num_actions_single(struct tc_action *act)
{
if (is_tcf_pedit(act))
return tcf_pedit_nkeys(act);
else
return 1;
}
static bool tc_act_skip_hw(u32 flags)
{
return (flags & TCA_ACT_FLAGS_SKIP_HW) ? true : false;
}
static bool tc_act_skip_sw(u32 flags)
{
return (flags & TCA_ACT_FLAGS_SKIP_SW) ? true : false;
}
/* SKIP_HW and SKIP_SW are mutually exclusive flags. */
static bool tc_act_flags_valid(u32 flags)
{
flags &= TCA_ACT_FLAGS_SKIP_HW | TCA_ACT_FLAGS_SKIP_SW;
return flags ^ (TCA_ACT_FLAGS_SKIP_HW | TCA_ACT_FLAGS_SKIP_SW);
}
static int offload_action_init(struct flow_offload_action *fl_action,
struct tc_action *act,
enum offload_act_command cmd,
struct netlink_ext_ack *extack)
{
int err;
fl_action->extack = extack;
fl_action->command = cmd;
fl_action->index = act->tcfa_index;
fl_action->cookie = (unsigned long)act;
if (act->ops->offload_act_setup) {
spin_lock_bh(&act->tcfa_lock);
err = act->ops->offload_act_setup(act, fl_action, NULL,
false, extack);
spin_unlock_bh(&act->tcfa_lock);
return err;
}
return -EOPNOTSUPP;
}
static int tcf_action_offload_cmd_ex(struct flow_offload_action *fl_act,
u32 *hw_count)
{
int err;
err = flow_indr_dev_setup_offload(NULL, NULL, TC_SETUP_ACT,
fl_act, NULL, NULL);
if (err < 0)
return err;
if (hw_count)
*hw_count = err;
return 0;
}
static int tcf_action_offload_cmd_cb_ex(struct flow_offload_action *fl_act,
u32 *hw_count,
flow_indr_block_bind_cb_t *cb,
void *cb_priv)
{
int err;
err = cb(NULL, NULL, cb_priv, TC_SETUP_ACT, NULL, fl_act, NULL);
if (err < 0)
return err;
if (hw_count)
*hw_count = 1;
return 0;
}
static int tcf_action_offload_cmd(struct flow_offload_action *fl_act,
u32 *hw_count,
flow_indr_block_bind_cb_t *cb,
void *cb_priv)
{
return cb ? tcf_action_offload_cmd_cb_ex(fl_act, hw_count,
cb, cb_priv) :
tcf_action_offload_cmd_ex(fl_act, hw_count);
}
static int tcf_action_offload_add_ex(struct tc_action *action,
struct netlink_ext_ack *extack,
flow_indr_block_bind_cb_t *cb,
void *cb_priv)
{
bool skip_sw = tc_act_skip_sw(action->tcfa_flags);
struct tc_action *actions[TCA_ACT_MAX_PRIO] = {
[0] = action,
};
struct flow_offload_action *fl_action;
u32 in_hw_count = 0;
int num, err = 0;
if (tc_act_skip_hw(action->tcfa_flags))
return 0;
num = tcf_offload_act_num_actions_single(action);
fl_action = offload_action_alloc(num);
if (!fl_action)
return -ENOMEM;
err = offload_action_init(fl_action, action, FLOW_ACT_REPLACE, extack);
if (err)
goto fl_err;
err = tc_setup_action(&fl_action->action, actions, 0, extack);
if (err) {
NL_SET_ERR_MSG_MOD(extack,
"Failed to setup tc actions for offload");
goto fl_err;
}
err = tcf_action_offload_cmd(fl_action, &in_hw_count, cb, cb_priv);
if (!err)
cb ? offload_action_hw_count_inc(action, in_hw_count) :
offload_action_hw_count_set(action, in_hw_count);
if (skip_sw && !tc_act_in_hw(action))
err = -EINVAL;
tc_cleanup_offload_action(&fl_action->action);
fl_err:
kfree(fl_action);
return err;
}
/* offload the tc action after it is inserted */
static int tcf_action_offload_add(struct tc_action *action,
struct netlink_ext_ack *extack)
{
return tcf_action_offload_add_ex(action, extack, NULL, NULL);
}
int tcf_action_update_hw_stats(struct tc_action *action)
{
struct flow_offload_action fl_act = {};
int err;
err = offload_action_init(&fl_act, action, FLOW_ACT_STATS, NULL);
if (err)
return err;
err = tcf_action_offload_cmd(&fl_act, NULL, NULL, NULL);
if (!err) {
preempt_disable();
tcf_action_stats_update(action, fl_act.stats.bytes,
fl_act.stats.pkts,
fl_act.stats.drops,
fl_act.stats.lastused,
true);
preempt_enable();
action->used_hw_stats = fl_act.stats.used_hw_stats;
action->used_hw_stats_valid = true;
} else {
return -EOPNOTSUPP;
}
return 0;
}
EXPORT_SYMBOL(tcf_action_update_hw_stats);
static int tcf_action_offload_del_ex(struct tc_action *action,
flow_indr_block_bind_cb_t *cb,
void *cb_priv)
{
struct flow_offload_action fl_act = {};
u32 in_hw_count = 0;
int err = 0;
if (!tc_act_in_hw(action))
return 0;
err = offload_action_init(&fl_act, action, FLOW_ACT_DESTROY, NULL);
if (err)
return err;
err = tcf_action_offload_cmd(&fl_act, &in_hw_count, cb, cb_priv);
if (err < 0)
return err;
if (!cb && action->in_hw_count != in_hw_count)
return -EINVAL;
/* do not need to update hw state when deleting action */
if (cb && in_hw_count)
offload_action_hw_count_dec(action, in_hw_count);
return 0;
}
static int tcf_action_offload_del(struct tc_action *action)
{
return tcf_action_offload_del_ex(action, NULL, NULL);
}
static void tcf_action_cleanup(struct tc_action *p)
{
tcf_action_offload_del(p);
if (p->ops->cleanup)
p->ops->cleanup(p);
gen_kill_estimator(&p->tcfa_rate_est);
free_tcf(p);
}
static int __tcf_action_put(struct tc_action *p, bool bind)
{
struct tcf_idrinfo *idrinfo = p->idrinfo;
if (refcount_dec_and_mutex_lock(&p->tcfa_refcnt, &idrinfo->lock)) {
if (bind)
atomic_dec(&p->tcfa_bindcnt);
idr_remove(&idrinfo->action_idr, p->tcfa_index);
mutex_unlock(&idrinfo->lock);
tcf_action_cleanup(p);
return 1;
}
if (bind)
atomic_dec(&p->tcfa_bindcnt);
return 0;
}
static int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
{
int ret = 0;
/* Release with strict==1 and bind==0 is only called through act API
* interface (classifiers always bind). Only case when action with
* positive reference count and zero bind count can exist is when it was
* also created with act API (unbinding last classifier will destroy the
* action if it was created by classifier). So only case when bind count
* can be changed after initial check is when unbound action is
* destroyed by act API while classifier binds to action with same id
* concurrently. This result either creation of new action(same behavior
* as before), or reusing existing action if concurrent process
* increments reference count before action is deleted. Both scenarios
* are acceptable.
*/
if (p) {
if (!bind && strict && atomic_read(&p->tcfa_bindcnt) > 0)
return -EPERM;
if (__tcf_action_put(p, bind))
ret = ACT_P_DELETED;
}
return ret;
}
int tcf_idr_release(struct tc_action *a, bool bind)
{
const struct tc_action_ops *ops = a->ops;
int ret;
ret = __tcf_idr_release(a, bind, false);
if (ret == ACT_P_DELETED)
module_put(ops->owner);
return ret;
}
EXPORT_SYMBOL(tcf_idr_release);
static size_t tcf_action_shared_attrs_size(const struct tc_action *act)
{
struct tc_cookie *user_cookie;
u32 cookie_len = 0;
rcu_read_lock();
user_cookie = rcu_dereference(act->user_cookie);
if (user_cookie)
cookie_len = nla_total_size(user_cookie->len);
rcu_read_unlock();
return nla_total_size(0) /* action number nested */
+ nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */
+ cookie_len /* TCA_ACT_COOKIE */
+ nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_HW_STATS */
+ nla_total_size(0) /* TCA_ACT_STATS nested */
+ nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */
/* TCA_STATS_BASIC */
+ nla_total_size_64bit(sizeof(struct gnet_stats_basic))
/* TCA_STATS_PKT64 */
+ nla_total_size_64bit(sizeof(u64))
/* TCA_STATS_QUEUE */
+ nla_total_size_64bit(sizeof(struct gnet_stats_queue))
+ nla_total_size(0) /* TCA_ACT_OPTIONS nested */
+ nla_total_size(sizeof(struct tcf_t)); /* TCA_GACT_TM */
}
static size_t tcf_action_full_attrs_size(size_t sz)
{
return NLMSG_HDRLEN /* struct nlmsghdr */
+ sizeof(struct tcamsg)
+ nla_total_size(0) /* TCA_ACT_TAB nested */
+ sz;
}
static size_t tcf_action_fill_size(const struct tc_action *act)
{
size_t sz = tcf_action_shared_attrs_size(act);
if (act->ops->get_fill_size)
return act->ops->get_fill_size(act) + sz;
return sz;
}
static int
tcf_action_dump_terse(struct sk_buff *skb, struct tc_action *a, bool from_act)
{
unsigned char *b = skb_tail_pointer(skb);
struct tc_cookie *cookie;
if (nla_put_string(skb, TCA_ACT_KIND, a->ops->kind))
goto nla_put_failure;
if (tcf_action_copy_stats(skb, a, 0))
goto nla_put_failure;
if (from_act && nla_put_u32(skb, TCA_ACT_INDEX, a->tcfa_index))
goto nla_put_failure;
rcu_read_lock();
cookie = rcu_dereference(a->user_cookie);
if (cookie) {
if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) {
rcu_read_unlock();
goto nla_put_failure;
}
}
rcu_read_unlock();
return 0;
nla_put_failure:
nlmsg_trim(skb, b);
return -1;
}
static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
struct netlink_callback *cb)
{
int err = 0, index = -1, s_i = 0, n_i = 0;
u32 act_flags = cb->args[2];
unsigned long jiffy_since = cb->args[3];
struct nlattr *nest;
struct idr *idr = &idrinfo->action_idr;
struct tc_action *p;
unsigned long id = 1;
unsigned long tmp;
mutex_lock(&idrinfo->lock);
s_i = cb->args[0];
idr_for_each_entry_ul(idr, p, tmp, id) {
index++;
if (index < s_i)
continue;
if (IS_ERR(p))
continue;
if (jiffy_since &&
time_after(jiffy_since,
(unsigned long)p->tcfa_tm.lastuse))
continue;
tcf_action_update_hw_stats(p);
nest = nla_nest_start_noflag(skb, n_i);
if (!nest) {
index--;
goto nla_put_failure;
}
err = (act_flags & TCA_ACT_FLAG_TERSE_DUMP) ?
tcf_action_dump_terse(skb, p, true) :
tcf_action_dump_1(skb, p, 0, 0);
if (err < 0) {
index--;
nlmsg_trim(skb, nest);
goto done;
}
nla_nest_end(skb, nest);
n_i++;
if (!(act_flags & TCA_ACT_FLAG_LARGE_DUMP_ON) &&
n_i >= TCA_ACT_MAX_PRIO)
goto done;
}
done:
if (index >= 0)
cb->args[0] = index + 1;
mutex_unlock(&idrinfo->lock);
if (n_i) {
if (act_flags & TCA_ACT_FLAG_LARGE_DUMP_ON)
cb->args[1] = n_i;
}
return n_i;
nla_put_failure:
nla_nest_cancel(skb, nest);
goto done;
}
static int tcf_idr_release_unsafe(struct tc_action *p)
{
if (atomic_read(&p->tcfa_bindcnt) > 0)
return -EPERM;
if (refcount_dec_and_test(&p->tcfa_refcnt)) {
idr_remove(&p->idrinfo->action_idr, p->tcfa_index);
tcf_action_cleanup(p);
return ACT_P_DELETED;
}
return 0;
}
static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
const struct tc_action_ops *ops,
struct netlink_ext_ack *extack)
{
struct nlattr *nest;
int n_i = 0;
int ret = -EINVAL;
struct idr *idr = &idrinfo->action_idr;
struct tc_action *p;
unsigned long id = 1;
unsigned long tmp;
nest = nla_nest_start_noflag(skb, 0);
if (nest == NULL)
goto nla_put_failure;
if (nla_put_string(skb, TCA_ACT_KIND, ops->kind))
goto nla_put_failure;
ret = 0;
mutex_lock(&idrinfo->lock);
idr_for_each_entry_ul(idr, p, tmp, id) {
if (IS_ERR(p))
continue;
ret = tcf_idr_release_unsafe(p);
if (ret == ACT_P_DELETED)
module_put(ops->owner);
else if (ret < 0)
break;
n_i++;
}
mutex_unlock(&idrinfo->lock);
if (ret < 0) {
if (n_i)
NL_SET_ERR_MSG(extack, "Unable to flush all TC actions");
else
goto nla_put_failure;
}
ret = nla_put_u32(skb, TCA_FCNT, n_i);
if (ret)
goto nla_put_failure;
nla_nest_end(skb, nest);
return n_i;
nla_put_failure:
nla_nest_cancel(skb, nest);
return ret;
}
int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
struct netlink_callback *cb, int type,
const struct tc_action_ops *ops,
struct netlink_ext_ack *extack)
{
struct tcf_idrinfo *idrinfo = tn->idrinfo;
if (type == RTM_DELACTION) {
return tcf_del_walker(idrinfo, skb, ops, extack);
} else if (type == RTM_GETACTION) {
return tcf_dump_walker(idrinfo, skb, cb);
} else {
WARN(1, "tcf_generic_walker: unknown command %d\n", type);
NL_SET_ERR_MSG(extack, "tcf_generic_walker: unknown command");
return -EINVAL;
}
}
EXPORT_SYMBOL(tcf_generic_walker);
int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index)
{
struct tcf_idrinfo *idrinfo = tn->idrinfo;
struct tc_action *p;
mutex_lock(&idrinfo->lock);
p = idr_find(&idrinfo->action_idr, index);
if (IS_ERR(p))
p = NULL;
else if (p)
refcount_inc(&p->tcfa_refcnt);
mutex_unlock(&idrinfo->lock);
if (p) {
*a = p;
return true;
}
return false;
}
EXPORT_SYMBOL(tcf_idr_search);
static int __tcf_generic_walker(struct net *net, struct sk_buff *skb,
struct netlink_callback *cb, int type,
const struct tc_action_ops *ops,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, ops->net_id);
if (unlikely(ops->walk))
return ops->walk(net, skb, cb, type, ops, extack);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
static int __tcf_idr_search(struct net *net,
const struct tc_action_ops *ops,
struct tc_action **a, u32 index)
{
struct tc_action_net *tn = net_generic(net, ops->net_id);
if (unlikely(ops->lookup))
return ops->lookup(net, a, index);
return tcf_idr_search(tn, a, index);
}
static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index)
{
struct tc_action *p;
int ret = 0;
mutex_lock(&idrinfo->lock);
p = idr_find(&idrinfo->action_idr, index);
if (!p) {
mutex_unlock(&idrinfo->lock);
return -ENOENT;
}
if (!atomic_read(&p->tcfa_bindcnt)) {
if (refcount_dec_and_test(&p->tcfa_refcnt)) {
struct module *owner = p->ops->owner;
WARN_ON(p != idr_remove(&idrinfo->action_idr,
p->tcfa_index));
mutex_unlock(&idrinfo->lock);
tcf_action_cleanup(p);
module_put(owner);
return 0;
}
ret = 0;
} else {
ret = -EPERM;
}
mutex_unlock(&idrinfo->lock);
return ret;
}
int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
struct tc_action **a, const struct tc_action_ops *ops,
int bind, bool cpustats, u32 flags)
{
struct tc_action *p = kzalloc(ops->size, GFP_KERNEL);
struct tcf_idrinfo *idrinfo = tn->idrinfo;
int err = -ENOMEM;
if (unlikely(!p))
return -ENOMEM;
refcount_set(&p->tcfa_refcnt, 1);
if (bind)
atomic_set(&p->tcfa_bindcnt, 1);
if (cpustats) {
p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync);
if (!p->cpu_bstats)
goto err1;
p->cpu_bstats_hw = netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync);
if (!p->cpu_bstats_hw)
goto err2;
p->cpu_qstats = alloc_percpu(struct gnet_stats_queue);
if (!p->cpu_qstats)
goto err3;
}
gnet_stats_basic_sync_init(&p->tcfa_bstats);
gnet_stats_basic_sync_init(&p->tcfa_bstats_hw);
spin_lock_init(&p->tcfa_lock);
p->tcfa_index = index;
p->tcfa_tm.install = jiffies;
p->tcfa_tm.lastuse = jiffies;
p->tcfa_tm.firstuse = 0;
p->tcfa_flags = flags;
if (est) {
err = gen_new_estimator(&p->tcfa_bstats, p->cpu_bstats,
&p->tcfa_rate_est,
&p->tcfa_lock, false, est);
if (err)
goto err4;
}
p->idrinfo = idrinfo;
__module_get(ops->owner);
p->ops = ops;
*a = p;
return 0;
err4:
free_percpu(p->cpu_qstats);
err3:
free_percpu(p->cpu_bstats_hw);
err2:
free_percpu(p->cpu_bstats);
err1:
kfree(p);
return err;
}
EXPORT_SYMBOL(tcf_idr_create);
int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index,
struct nlattr *est, struct tc_action **a,
const struct tc_action_ops *ops, int bind,
u32 flags)
{
/* Set cpustats according to actions flags. */
return tcf_idr_create(tn, index, est, a, ops, bind,
!(flags & TCA_ACT_FLAGS_NO_PERCPU_STATS), flags);
}
EXPORT_SYMBOL(tcf_idr_create_from_flags);
/* Cleanup idr index that was allocated but not initialized. */
void tcf_idr_cleanup(struct tc_action_net *tn, u32 index)
{
struct tcf_idrinfo *idrinfo = tn->idrinfo;
mutex_lock(&idrinfo->lock);
/* Remove ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */
WARN_ON(!IS_ERR(idr_remove(&idrinfo->action_idr, index)));
mutex_unlock(&idrinfo->lock);
}
EXPORT_SYMBOL(tcf_idr_cleanup);
/* Check if action with specified index exists. If actions is found, increments
* its reference and bind counters, and return 1. Otherwise insert temporary
* error pointer (to prevent concurrent users from inserting actions with same
* index) and return 0.
*
* May return -EAGAIN for binding actions in case of a parallel add/delete on
* the requested index.
*/
int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
struct tc_action **a, int bind)
{
struct tcf_idrinfo *idrinfo = tn->idrinfo;
struct tc_action *p;
int ret;
u32 max;
if (*index) {
again:
rcu_read_lock();
p = idr_find(&idrinfo->action_idr, *index);
if (IS_ERR(p)) {
/* This means that another process allocated
* index but did not assign the pointer yet.
*/
rcu_read_unlock();
goto again;
}
if (!p) {
/* Empty slot, try to allocate it */
max = *index;
rcu_read_unlock();
goto new;
}
if (!refcount_inc_not_zero(&p->tcfa_refcnt)) {
/* Action was deleted in parallel */
rcu_read_unlock();
return -EAGAIN;
}
if (bind)
atomic_inc(&p->tcfa_bindcnt);
*a = p;
rcu_read_unlock();
return 1;
} else {
/* Find a slot */
*index = 1;
max = UINT_MAX;
}
new:
*a = NULL;
mutex_lock(&idrinfo->lock);
ret = idr_alloc_u32(&idrinfo->action_idr, ERR_PTR(-EBUSY), index, max,
GFP_KERNEL);
mutex_unlock(&idrinfo->lock);
/* N binds raced for action allocation,
* retry for all the ones that failed.
*/
if (ret == -ENOSPC && *index == max)
ret = -EAGAIN;
return ret;
}
EXPORT_SYMBOL(tcf_idr_check_alloc);
void tcf_idrinfo_destroy(const struct tc_action_ops *ops,
struct tcf_idrinfo *idrinfo)
{
struct idr *idr = &idrinfo->action_idr;
struct tc_action *p;
int ret;
unsigned long id = 1;
unsigned long tmp;
idr_for_each_entry_ul(idr, p, tmp, id) {
ret = __tcf_idr_release(p, false, true);
if (ret == ACT_P_DELETED)
module_put(ops->owner);
else if (ret < 0)
return;
}
idr_destroy(&idrinfo->action_idr);
}
EXPORT_SYMBOL(tcf_idrinfo_destroy);
static LIST_HEAD(act_base);
static DEFINE_RWLOCK(act_mod_lock);
/* since act ops id is stored in pernet subsystem list,
* then there is no way to walk through only all the action
* subsystem, so we keep tc action pernet ops id for
* reoffload to walk through.
*/
static LIST_HEAD(act_pernet_id_list);
static DEFINE_MUTEX(act_id_mutex);
struct tc_act_pernet_id {
struct list_head list;
unsigned int id;
};
static int tcf_pernet_add_id_list(unsigned int id)
{
struct tc_act_pernet_id *id_ptr;
int ret = 0;
mutex_lock(&act_id_mutex);
list_for_each_entry(id_ptr, &act_pernet_id_list, list) {
if (id_ptr->id == id) {
ret = -EEXIST;
goto err_out;
}
}
id_ptr = kzalloc(sizeof(*id_ptr), GFP_KERNEL);
if (!id_ptr) {
ret = -ENOMEM;
goto err_out;
}
id_ptr->id = id;
list_add_tail(&id_ptr->list, &act_pernet_id_list);
err_out:
mutex_unlock(&act_id_mutex);
return ret;
}
static void tcf_pernet_del_id_list(unsigned int id)
{
struct tc_act_pernet_id *id_ptr;
mutex_lock(&act_id_mutex);
list_for_each_entry(id_ptr, &act_pernet_id_list, list) {
if (id_ptr->id == id) {
list_del(&id_ptr->list);
kfree(id_ptr);
break;
}
}
mutex_unlock(&act_id_mutex);
}
int tcf_register_action(struct tc_action_ops *act,
struct pernet_operations *ops)
{
struct tc_action_ops *a;
int ret;
if (!act->act || !act->dump || !act->init)
return -EINVAL;
/* We have to register pernet ops before making the action ops visible,
* otherwise tcf_action_init_1() could get a partially initialized
* netns.
*/
ret = register_pernet_subsys(ops);
if (ret)
return ret;
if (ops->id) {
ret = tcf_pernet_add_id_list(*ops->id);
if (ret)
goto err_id;
}
write_lock(&act_mod_lock);
list_for_each_entry(a, &act_base, head) {
if (act->id == a->id || (strcmp(act->kind, a->kind) == 0)) {
ret = -EEXIST;
goto err_out;
}
}
list_add_tail(&act->head, &act_base);
write_unlock(&act_mod_lock);
return 0;
err_out: