summaryrefslogtreecommitdiff
path: root/net/core/net_namespace.c
blob: 711b161505ac1afcc2aa2dd5d07b33b5a2f1ac89 (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
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/workqueue.h>
#include <linux/rtnetlink.h>
#include <linux/cache.h>
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/delay.h>
#include <linux/sched.h>
#include <linux/idr.h>
#include <linux/rculist.h>
#include <linux/nsproxy.h>
#include <linux/fs.h>
#include <linux/proc_ns.h>
#include <linux/file.h>
#include <linux/export.h>
#include <linux/user_namespace.h>
#include <linux/net_namespace.h>
#include <linux/sched/task.h>
#include <linux/uidgid.h>

#include <net/sock.h>
#include <net/netlink.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>

/*
 *	Our network namespace constructor/destructor lists
 */

static LIST_HEAD(pernet_list);
static struct list_head *first_device = &pernet_list;

LIST_HEAD(net_namespace_list);
EXPORT_SYMBOL_GPL(net_namespace_list);

/* Protects net_namespace_list. Nests iside rtnl_lock() */
DECLARE_RWSEM(net_rwsem);
EXPORT_SYMBOL_GPL(net_rwsem);

struct net init_net = {
	.count		= REFCOUNT_INIT(1),
	.dev_base_head	= LIST_HEAD_INIT(init_net.dev_base_head),
};
EXPORT_SYMBOL(init_net);

static bool init_net_initialized;
/*
 * pernet_ops_rwsem: protects: pernet_list, net_generic_ids,
 * init_net_initialized and first_device pointer.
 * This is internal net namespace object. Please, don't use it
 * outside.
 */
DECLARE_RWSEM(pernet_ops_rwsem);
EXPORT_SYMBOL_GPL(pernet_ops_rwsem);

#define MIN_PERNET_OPS_ID	\
	((sizeof(struct net_generic) + sizeof(void *) - 1) / sizeof(void *))

#define INITIAL_NET_GEN_PTRS	13 /* +1 for len +2 for rcu_head */

static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS;

static struct net_generic *net_alloc_generic(void)
{
	struct net_generic *ng;
	unsigned int generic_size = offsetof(struct net_generic, ptr[max_gen_ptrs]);

	ng = kzalloc(generic_size, GFP_KERNEL);
	if (ng)
		ng->s.len = max_gen_ptrs;

	return ng;
}

static int net_assign_generic(struct net *net, unsigned int id, void *data)
{
	struct net_generic *ng, *old_ng;

	BUG_ON(id < MIN_PERNET_OPS_ID);

	old_ng = rcu_dereference_protected(net->gen,
					   lockdep_is_held(&pernet_ops_rwsem));
	if (old_ng->s.len > id) {
		old_ng->ptr[id] = data;
		return 0;
	}

	ng = net_alloc_generic();
	if (ng == NULL)
		return -ENOMEM;

	/*
	 * Some synchronisation notes:
	 *
	 * The net_generic explores the net->gen array inside rcu
	 * read section. Besides once set the net->gen->ptr[x]
	 * pointer never changes (see rules in netns/generic.h).
	 *
	 * That said, we simply duplicate this array and schedule
	 * the old copy for kfree after a grace period.
	 */

	memcpy(&ng->ptr[MIN_PERNET_OPS_ID], &old_ng->ptr[MIN_PERNET_OPS_ID],
	       (old_ng->s.len - MIN_PERNET_OPS_ID) * sizeof(void *));
	ng->ptr[id] = data;

	rcu_assign_pointer(net->gen, ng);
	kfree_rcu(old_ng, s.rcu);
	return 0;
}

static int ops_init(const struct pernet_operations *ops, struct net *net)
{
	int err = -ENOMEM;
	void *data = NULL;

	if (ops->id && ops->size) {
		data = kzalloc(ops->size, GFP_KERNEL);
		if (!data)
			goto out;

		err = net_assign_generic(net, *ops->id, data);
		if (err)
			goto cleanup;
	}
	err = 0;
	if (ops->init)
		err = ops->init(net);
	if (!err)
		return 0;

cleanup:
	kfree(data);

out:
	return err;
}

static void ops_free(const struct pernet_operations *ops, struct net *net)
{
	if (ops->id && ops->size) {
		kfree(net_generic(net, *ops->id));
	}
}

static void ops_exit_list(const struct pernet_operations *ops,
			  struct list_head *net_exit_list)
{
	struct net *net;
	if (ops->exit) {
		list_for_each_entry(net, net_exit_list, exit_list)
			ops->exit(net);
	}
	if (ops->exit_batch)
		ops->exit_batch(net_exit_list);
}

static void ops_free_list(const struct pernet_operations *ops,
			  struct list_head *net_exit_list)
{
	struct net *net;
	if (ops->size && ops->id) {
		list_for_each_entry(net, net_exit_list, exit_list)
			ops_free(ops, net);
	}
}

/* should be called with nsid_lock held */
static int alloc_netid(struct net *net, struct net *peer, int reqid)
{
	int min = 0, max = 0;

	if (reqid >= 0) {
		min = reqid;
		max = reqid + 1;
	}

	return idr_alloc(&net->netns_ids, peer, min, max, GFP_ATOMIC);
}

/* This function is used by idr_for_each(). If net is equal to peer, the
 * function returns the id so that idr_for_each() stops. Because we cannot
 * returns the id 0 (idr_for_each() will not stop), we return the magic value
 * NET_ID_ZERO (-1) for it.
 */
#define NET_ID_ZERO -1
static int net_eq_idr(int id, void *net, void *peer)
{
	if (net_eq(net, peer))
		return id ? : NET_ID_ZERO;
	return 0;
}

/* Should be called with nsid_lock held. If a new id is assigned, the bool alloc
 * is set to true, thus the caller knows that the new id must be notified via
 * rtnl.
 */
static int __peernet2id_alloc(struct net *net, struct net *peer, bool *alloc)
{
	int id = idr_for_each(&net->netns_ids, net_eq_idr, peer);
	bool alloc_it = *alloc;

	*alloc = false;

	/* Magic value for id 0. */
	if (id == NET_ID_ZERO)
		return 0;
	if (id > 0)
		return id;

	if (alloc_it) {
		id = alloc_netid(net, peer, -1);
		*alloc = true;
		return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED;
	}

	return NETNSA_NSID_NOT_ASSIGNED;
}

/* should be called with nsid_lock held */
static int __peernet2id(struct net *net, struct net *peer)
{
	bool no = false;

	return __peernet2id_alloc(net, peer, &no);
}

static void rtnl_net_notifyid(struct net *net, int cmd, int id);
/* This function returns the id of a peer netns. If no id is assigned, one will
 * be allocated and returned.
 */
int peernet2id_alloc(struct net *net, struct net *peer)
{
	bool alloc = false, alive = false;
	int id;

	if (refcount_read(&net->count) == 0)
		return NETNSA_NSID_NOT_ASSIGNED;
	spin_lock_bh(&net->nsid_lock);
	/*
	 * When peer is obtained from RCU lists, we may race with
	 * its cleanup. Check whether it's alive, and this guarantees
	 * we never hash a peer back to net->netns_ids, after it has
	 * just been idr_remove()'d from there in cleanup_net().
	 */
	if (maybe_get_net(peer))
		alive = alloc = true;
	id = __peernet2id_alloc(net, peer, &alloc);
	spin_unlock_bh(&net->nsid_lock);
	if (alloc && id >= 0)
		rtnl_net_notifyid(net, RTM_NEWNSID, id);
	if (alive)
		put_net(peer);
	return id;
}
EXPORT_SYMBOL_GPL(peernet2id_alloc);

/* This function returns, if assigned, the id of a peer netns. */
int peernet2id(struct net *net, struct net *peer)
{
	int id;

	spin_lock_bh(&net->nsid_lock);
	id = __peernet2id(net, peer);
	spin_unlock_bh(&net->nsid_lock);
	return id;
}
EXPORT_SYMBOL(peernet2id);

/* This function returns true is the peer netns has an id assigned into the
 * current netns.
 */
bool peernet_has_id(struct net *net, struct net *peer)
{
	return peernet2id(net, peer) >= 0;
}

struct net *get_net_ns_by_id(struct net *net, int id)
{
	struct net *peer;

	if (id < 0)
		return NULL;

	rcu_read_lock();
	peer = idr_find(&net->netns_ids, id);
	if (peer)
		peer = maybe_get_net(peer);
	rcu_read_unlock();

	return peer;
}

/*
 * setup_net runs the initializers for the network namespace object.
 */
static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
{
	/* Must be called with pernet_ops_rwsem held */
	const struct pernet_operations *ops, *saved_ops;
	int error = 0;
	LIST_HEAD(net_exit_list);

	refcount_set(&net->count, 1);
	refcount_set(&net->passive, 1);
	get_random_bytes(&net->hash_mix, sizeof(u32));
	net->dev_base_seq = 1;
	net->user_ns = user_ns;
	idr_init(&net->netns_ids);
	spin_lock_init(&net->nsid_lock);
	mutex_init(&net->ipv4.ra_mutex);

	list_for_each_entry(ops, &pernet_list, list) {
		error = ops_init(ops, net);
		if (error < 0)
			goto out_undo;
	}
	down_write(&net_rwsem);
	list_add_tail_rcu(&net->list, &net_namespace_list);
	up_write(&net_rwsem);
out:
	return error;

out_undo:
	/* Walk through the list backwards calling the exit functions
	 * for the pernet modules whose init functions did not fail.
	 */
	list_add(&net->exit_list, &net_exit_list);
	saved_ops = ops;
	list_for_each_entry_continue_reverse(ops, &pernet_list, list)
		ops_exit_list(ops, &net_exit_list);

	ops = saved_ops;
	list_for_each_entry_continue_reverse(ops, &pernet_list, list)
		ops_free_list(ops, &net_exit_list);

	rcu_barrier();
	goto out;
}

static int __net_init net_defaults_init_net(struct net *net)
{
	net->core.sysctl_somaxconn = SOMAXCONN;
	return 0;
}

static struct pernet_operations net_defaults_ops = {
	.init = net_defaults_init_net,
};

static __init int net_defaults_init(void)
{
	if (register_pernet_subsys(&net_defaults_ops))
		panic("Cannot initialize net default settings");

	return 0;
}

core_initcall(net_defaults_init);

#ifdef CONFIG_NET_NS
static struct ucounts *inc_net_namespaces(struct user_namespace *ns)
{
	return inc_ucount(ns, current_euid(), UCOUNT_NET_NAMESPACES);
}

static void dec_net_namespaces(struct ucounts *ucounts)
{
	dec_ucount(ucounts, UCOUNT_NET_NAMESPACES);
}

static struct kmem_cache *net_cachep __ro_after_init;
static struct workqueue_struct *netns_wq;

static struct net *net_alloc(void)
{
	struct net *net = NULL;
	struct net_generic *ng;

	ng = net_alloc_generic();
	if (!ng)
		goto out;

	net = kmem_cache_zalloc(net_cachep, GFP_KERNEL);
	if (!net)
		goto out_free;

	rcu_assign_pointer(net->gen, ng);
out:
	return net;

out_free:
	kfree(ng);
	goto out;
}

static void net_free(struct net *net)
{
	kfree(rcu_access_pointer(net->gen));
	kmem_cache_free(net_cachep, net);
}

void net_drop_ns(void *p)
{
	struct net *ns = p;
	if (ns && refcount_dec_and_test(&ns->passive))
		net_free(ns);
}

struct net *copy_net_ns(unsigned long flags,
			struct user_namespace *user_ns, struct net *old_net)
{
	struct ucounts *ucounts;
	struct net *net;
	int rv;

	if (!(flags & CLONE_NEWNET))
		return get_net(old_net);

	ucounts = inc_net_namespaces(user_ns);
	if (!ucounts)
		return ERR_PTR(-ENOSPC);

	net = net_alloc();
	if (!net) {
		rv = -ENOMEM;
		goto dec_ucounts;
	}
	refcount_set(&net->passive, 1);
	net->ucounts = ucounts;
	get_user_ns(user_ns);

	rv = down_read_killable(&pernet_ops_rwsem);
	if (rv < 0)
		goto put_userns;

	rv = setup_net(net, user_ns);

	up_read(&pernet_ops_rwsem);

	if (rv < 0) {
put_userns:
		put_user_ns(user_ns);
		net_drop_ns(net);
dec_ucounts:
		dec_net_namespaces(ucounts);
		return ERR_PTR(rv);
	}
	return net;
}

/**
 * net_ns_get_ownership - get sysfs ownership data for @net
 * @net: network namespace in question (can be NULL)
 * @uid: kernel user ID for sysfs objects
 * @gid: kernel group ID for sysfs objects
 *
 * Returns the uid/gid pair of root in the user namespace associated with the
 * given network namespace.
 */
void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid)
{
	if (net) {
		kuid_t ns_root_uid = make_kuid(net->user_ns, 0);
		kgid_t ns_root_gid = make_kgid(net->user_ns, 0);

		if (uid_valid(ns_root_uid))
			*uid = ns_root_uid;

		if (gid_valid(ns_root_gid))
			*gid = ns_root_gid;
	} else {
		*uid = GLOBAL_ROOT_UID;
		*gid = GLOBAL_ROOT_GID;
	}
}
EXPORT_SYMBOL_GPL(net_ns_get_ownership);

static void unhash_nsid(struct net *net, struct net *last)
{
	struct net *tmp;
	/* This function is only called from cleanup_net() work,
	 * and this work is the only process, that may delete
	 * a net from net_namespace_list. So, when the below
	 * is executing, the list may only grow. Thus, we do not
	 * use for_each_net_rcu() or net_rwsem.
	 */
	for_each_net(tmp) {
		int id;

		spin_lock_bh(&tmp->nsid_lock);
		id = __peernet2id(tmp, net);
		if (id >= 0)
			idr_remove(&tmp->netns_ids, id);
		spin_unlock_bh(&tmp->nsid_lock);
		if (id >= 0)
			rtnl_net_notifyid(tmp, RTM_DELNSID, id);
		if (tmp == last)
			break;
	}
	spin_lock_bh(&net->nsid_lock);
	idr_destroy(&net->netns_ids);
	spin_unlock_bh(&net->nsid_lock);
}

static LLIST_HEAD(cleanup_list);

static void cleanup_net(struct work_struct *work)
{
	const struct pernet_operations *ops;
	struct net *net, *tmp, *last;
	struct llist_node *net_kill_list;
	LIST_HEAD(net_exit_list);

	/* Atomically snapshot the list of namespaces to cleanup */
	net_kill_list = llist_del_all(&cleanup_list);

	down_read(&pernet_ops_rwsem);

	/* Don't let anyone else find us. */
	down_write(&net_rwsem);
	llist_for_each_entry(net, net_kill_list, cleanup_list)
		list_del_rcu(&net->list);
	/* Cache last net. After we unlock rtnl, no one new net
	 * added to net_namespace_list can assign nsid pointer
	 * to a net from net_kill_list (see peernet2id_alloc()).
	 * So, we skip them in unhash_nsid().
	 *
	 * Note, that unhash_nsid() does not delete nsid links
	 * between net_kill_list's nets, as they've already
	 * deleted from net_namespace_list. But, this would be
	 * useless anyway, as netns_ids are destroyed there.
	 */
	last = list_last_entry(&net_namespace_list, struct net, list);
	up_write(&net_rwsem);

	llist_for_each_entry(net, net_kill_list, cleanup_list) {
		unhash_nsid(net, last);
		list_add_tail(&net->exit_list, &net_exit_list);
	}

	/*
	 * Another CPU might be rcu-iterating the list, wait for it.
	 * This needs to be before calling the exit() notifiers, so
	 * the rcu_barrier() below isn't sufficient alone.
	 */
	synchronize_rcu();

	/* Run all of the network namespace exit methods */
	list_for_each_entry_reverse(ops, &pernet_list, list)
		ops_exit_list(ops, &net_exit_list);

	/* Free the net generic variables */
	list_for_each_entry_reverse(ops, &pernet_list, list)
		ops_free_list(ops, &net_exit_list);

	up_read(&pernet_ops_rwsem);

	/* Ensure there are no outstanding rcu callbacks using this
	 * network namespace.
	 */
	rcu_barrier();

	/* Finally it is safe to free my network namespace structure */
	list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) {
		list_del_init(&net->exit_list);
		dec_net_namespaces(net->ucounts);
		put_user_ns(net->user_ns);
		net_drop_ns(net);
	}
}

/**
 * net_ns_barrier - wait until concurrent net_cleanup_work is done
 *
 * cleanup_net runs from work queue and will first remove namespaces
 * from the global list, then run net exit functions.
 *
 * Call this in module exit path to make sure that all netns
 * ->exit ops have been invoked before the function is removed.
 */
void net_ns_barrier(void)
{
	down_write(&pernet_ops_rwsem);
	up_write(&pernet_ops_rwsem);
}
EXPORT_SYMBOL(net_ns_barrier);

static DECLARE_WORK(net_cleanup_work, cleanup_net);

void __put_net(struct net *net)
{
	/* Cleanup the network namespace in process context */
	if (llist_add(&net->cleanup_list, &cleanup_list))
		queue_work(netns_wq, &net_cleanup_work);
}
EXPORT_SYMBOL_GPL(__put_net);

struct net *get_net_ns_by_fd(int fd)
{
	struct file *file;
	struct ns_common *ns;
	struct net *net;

	file = proc_ns_fget(fd);
	if (IS_ERR(file))
		return ERR_CAST(file);

	ns = get_proc_ns(file_inode(file));
	if (ns->ops == &netns_operations)
		net = get_net(container_of(ns, struct net, ns));
	else
		net = ERR_PTR(-EINVAL);

	fput(file);
	return net;
}

#else
struct net *get_net_ns_by_fd(int fd)
{
	return ERR_PTR(-EINVAL);
}
#endif
EXPORT_SYMBOL_GPL(get_net_ns_by_fd);

struct net *get_net_ns_by_pid(pid_t pid)
{
	struct task_struct *tsk;
	struct net *net;

	/* Lookup the network namespace */
	net = ERR_PTR(-ESRCH);
	rcu_read_lock();
	tsk = find_task_by_vpid(pid);
	if (tsk) {
		struct nsproxy *nsproxy;
		task_lock(tsk);
		nsproxy = tsk->nsproxy;
		if (nsproxy)
			net = get_net(nsproxy->net_ns);
		task_unlock(tsk);
	}
	rcu_read_unlock();
	return net;
}
EXPORT_SYMBOL_GPL(get_net_ns_by_pid);

static __net_init int net_ns_net_init(struct net *net)
{
#ifdef CONFIG_NET_NS
	net->ns.ops = &netns_operations;
#endif
	return ns_alloc_inum(&net->ns);
}

static __net_exit void net_ns_net_exit(struct net *net)
{
	ns_free_inum(&net->ns);
}

static struct pernet_operations __net_initdata net_ns_ops = {
	.init = net_ns_net_init,
	.exit = net_ns_net_exit,
};

static const struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = {
	[NETNSA_NONE]		= { .type = NLA_UNSPEC },
	[NETNSA_NSID]		= { .type = NLA_S32 },
	[NETNSA_PID]		= { .type = NLA_U32 },
	[NETNSA_FD]		= { .type = NLA_U32 },
	[NETNSA_TARGET_NSID]	= { .type = NLA_S32 },
};

static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
			  struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct nlattr *tb[NETNSA_MAX + 1];
	struct nlattr *nla;
	struct net *peer;
	int nsid, err;

	err = nlmsg_parse_deprecated(nlh, sizeof(struct rtgenmsg), tb,
				     NETNSA_MAX, rtnl_net_policy, extack);
	if (err < 0)
		return err;
	if (!tb[NETNSA_NSID]) {
		NL_SET_ERR_MSG(extack, "nsid is missing");
		return -EINVAL;
	}
	nsid = nla_get_s32(tb[NETNSA_NSID]);

	if (tb[NETNSA_PID]) {
		peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID]));
		nla = tb[NETNSA_PID];
	} else if (tb[NETNSA_FD]) {
		peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD]));
		nla = tb[NETNSA_FD];
	} else {
		NL_SET_ERR_MSG(extack, "Peer netns reference is missing");
		return -EINVAL;
	}
	if (IS_ERR(peer)) {
		NL_SET_BAD_ATTR(extack, nla);
		NL_SET_ERR_MSG(extack, "Peer netns reference is invalid");
		return PTR_ERR(peer);
	}

	spin_lock_bh(&net->nsid_lock);
	if (__peernet2id(net, peer) >= 0) {
		spin_unlock_bh(&net->nsid_lock);
		err = -EEXIST;
		NL_SET_BAD_ATTR(extack, nla);
		NL_SET_ERR_MSG(extack,
			       "Peer netns already has a nsid assigned");
		goto out;
	}

	err = alloc_netid(net, peer, nsid);
	spin_unlock_bh(&net->nsid_lock);
	if (err >= 0) {
		rtnl_net_notifyid(net, RTM_NEWNSID, err);
		err = 0;
	} else if (err == -ENOSPC && nsid >= 0) {
		err = -EEXIST;
		NL_SET_BAD_ATTR(extack, tb[NETNSA_NSID]);
		NL_SET_ERR_MSG(extack, "The specified nsid is already used");
	}
out:
	put_net(peer);
	return err;
}

static int rtnl_net_get_size(void)
{
	return NLMSG_ALIGN(sizeof(struct rtgenmsg))
	       + nla_total_size(sizeof(s32)) /* NETNSA_NSID */
	       + nla_total_size(sizeof(s32)) /* NETNSA_CURRENT_NSID */
	       ;
}

struct net_fill_args {
	u32 portid;
	u32 seq;
	int flags;
	int cmd;
	int nsid;
	bool add_ref;
	int ref_nsid;
};

static int rtnl_net_fill(struct sk_buff *skb, struct net_fill_args *args)
{
	struct nlmsghdr *nlh;
	struct rtgenmsg *rth;

	nlh = nlmsg_put(skb, args->portid, args->seq, args->cmd, sizeof(*rth),
			args->flags);
	if (!nlh)
		return -EMSGSIZE;

	rth = nlmsg_data(nlh);
	rth->rtgen_family = AF_UNSPEC;

	if (nla_put_s32(skb, NETNSA_NSID, args->nsid))
		goto nla_put_failure;

	if (args->add_ref &&
	    nla_put_s32(skb, NETNSA_CURRENT_NSID, args->ref_nsid))
		goto nla_put_failure;

	nlmsg_end(skb, nlh);
	return 0;

nla_put_failure:
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
}

static int rtnl_net_valid_getid_req(struct sk_buff *skb,
				    const struct nlmsghdr *nlh,
				    struct nlattr **tb,
				    struct netlink_ext_ack *extack)
{
	int i, err;

	if (!netlink_strict_get_check(skb))
		return nlmsg_parse_deprecated(nlh, sizeof(struct rtgenmsg),
					      tb, NETNSA_MAX, rtnl_net_policy,
					      extack);

	err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct rtgenmsg), tb,
					    NETNSA_MAX, rtnl_net_policy,
					    extack);
	if (err)
		return err;

	for (i = 0; i <= NETNSA_MAX; i++) {
		if (!tb[i])
			continue;

		switch (i) {
		case NETNSA_PID:
		case NETNSA_FD:
		case NETNSA_NSID:
		case NETNSA_TARGET_NSID:
			break;
		default:
			NL_SET_ERR_MSG(extack, "Unsupported attribute in peer netns getid request");
			return -EINVAL;
		}
	}

	return 0;
}

static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
			  struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct nlattr *tb[NETNSA_MAX + 1];
	struct net_fill_args fillargs = {
		.portid = NETLINK_CB(skb).portid,
		.seq = nlh->nlmsg_seq,
		.cmd = RTM_NEWNSID,
	};
	struct net *peer, *target = net;
	struct nlattr *nla;
	struct sk_buff *msg;
	int err;

	err = rtnl_net_valid_getid_req(skb, nlh, tb, extack);
	if (err < 0)
		return err;
	if (tb[NETNSA_PID]) {
		peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID]));
		nla = tb[NETNSA_PID];
	} else if (tb[NETNSA_FD]) {
		peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD]));
		nla = tb[NETNSA_FD];
	} else if (tb[NETNSA_NSID]) {
		peer = get_net_ns_by_id(net, nla_get_s32(tb[NETNSA_NSID]));
		if (!peer)
			peer = ERR_PTR(-ENOENT);
		nla = tb[NETNSA_NSID];
	} else {
		NL_SET_ERR_MSG(extack, "Peer netns reference is missing");
		return -EINVAL;
	}

	if (IS_ERR(peer)) {
		NL_SET_BAD_ATTR(extack, nla);
		NL_SET_ERR_MSG(extack, "Peer netns reference is invalid");
		return PTR_ERR(peer);
	}

	if (tb[NETNSA_TARGET_NSID]) {
		int id = nla_get_s32(tb[NETNSA_TARGET_NSID]);

		target = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, id);
		if (IS_ERR(target)) {
			NL_SET_BAD_ATTR(extack, tb[NETNSA_TARGET_NSID]);
			NL_SET_ERR_MSG(extack,
				       "Target netns reference is invalid");
			err = PTR_ERR(target);
			goto out;
		}
		fillargs.add_ref = true;
		fillargs.ref_nsid = peernet2id(net, peer);
	}

	msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL);
	if (!msg) {
		err = -ENOMEM;
		goto out;
	}

	fillargs.nsid = peernet2id(target, peer);
	err = rtnl_net_fill(msg, &fillargs);
	if (err < 0)
		goto err_out;

	err = rtnl_unicast(msg, net, NETLINK_CB(skb).portid);
	goto out;

err_out:
	nlmsg_free(msg);
out:
	if (fillargs.add_ref)
		put_net(target);
	put_net(peer);
	return err;
}

struct rtnl_net_dump_cb {
	struct net *tgt_net;
	struct net *ref_net;
	struct sk_buff *skb;
	struct net_fill_args fillargs;
	int idx;
	int s_idx;
};

static int rtnl_net_dumpid_one(int id, void *peer, void *data)
{
	struct rtnl_net_dump_cb *net_cb = (struct rtnl_net_dump_cb *)data;
	int ret;

	if (net_cb->idx < net_cb->s_idx)
		goto cont;

	net_cb->fillargs.nsid = id;
	if (net_cb->fillargs.add_ref)
		net_cb->fillargs.ref_nsid = __peernet2id(net_cb->ref_net, peer);
	ret = rtnl_net_fill(net_cb->skb, &net_cb->fillargs);
	if (ret < 0)
		return ret;

cont:
	net_cb->idx++;
	return 0;
}

static int rtnl_valid_dump_net_req(const struct nlmsghdr *nlh, struct sock *sk,
				   struct rtnl_net_dump_cb *net_cb,
				   struct netlink_callback *cb)
{
	struct netlink_ext_ack *extack = cb->extack;
	struct nlattr *tb[NETNSA_MAX + 1];
	int err, i;

	err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct rtgenmsg), tb,
					    NETNSA_MAX, rtnl_net_policy,
					    extack);
	if (err < 0)
		return err;

	for (i = 0; i <= NETNSA_MAX; i++) {
		if (!tb[i])
			continue;

		if (i == NETNSA_TARGET_NSID) {
			struct net *net;

			net = rtnl_get_net_ns_capable(sk, nla_get_s32(tb[i]));
			if (IS_ERR(net)) {
				NL_SET_BAD_ATTR(extack, tb[i]);
				NL_SET_ERR_MSG(extack,
					       "Invalid target network namespace id");
				return PTR_ERR(net);
			}
			net_cb->fillargs.add_ref = true;
			net_cb->ref_net = net_cb->tgt_net;
			net_cb->tgt_net = net;
		} else {
			NL_SET_BAD_ATTR(extack, tb[i]);
			NL_SET_ERR_MSG(extack,
				       "Unsupported attribute in dump request");
			return -EINVAL;
		}
	}

	return 0;
}

static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct rtnl_net_dump_cb net_cb = {
		.tgt_net = sock_net(skb->sk),
		.skb = skb,
		.fillargs = {
			.portid = NETLINK_CB(cb->skb).portid,
			.seq = cb->nlh->nlmsg_seq,
			.flags = NLM_F_MULTI,
			.cmd = RTM_NEWNSID,
		},
		.idx = 0,
		.s_idx = cb->args[0],
	};
	int err = 0;

	if (cb->strict_check) {
		err = rtnl_valid_dump_net_req(cb->nlh, skb->sk, &net_cb, cb);
		if (err < 0)
			goto end;
	}

	spin_lock_bh(&net_cb.tgt_net->nsid_lock);
	if (net_cb.fillargs.add_ref &&
	    !net_eq(net_cb.ref_net, net_cb.tgt_net) &&
	    !spin_trylock_bh(&net_cb.ref_net->nsid_lock)) {
		spin_unlock_bh(&net_cb.tgt_net->nsid_lock);
		err = -EAGAIN;
		goto end;
	}
	idr_for_each(&net_cb.tgt_net->netns_ids, rtnl_net_dumpid_one, &net_cb);
	if (net_cb.fillargs.add_ref &&
	    !net_eq(net_cb.ref_net, net_cb.tgt_net))
		spin_unlock_bh(&net_cb.ref_net->nsid_lock);
	spin_unlock_bh(&net_cb.tgt_net->nsid_lock);

	cb->args[0] = net_cb.idx;
end:
	if (net_cb.fillargs.add_ref)
		put_net(net_cb.tgt_net);
	return err < 0 ? err : skb->len;
}

static void rtnl_net_notifyid(struct net *net, int cmd, int id)
{
	struct net_fill_args fillargs = {
		.cmd = cmd,
		.nsid = id,
	};
	struct sk_buff *msg;
	int err = -ENOMEM;

	msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL);
	if (!msg)
		goto out;

	err = rtnl_net_fill(msg, &fillargs);
	if (err < 0)
		goto err_out;

	rtnl_notify(msg, net, 0, RTNLGRP_NSID, NULL, 0);
	return;

err_out:
	nlmsg_free(msg);
out:
	rtnl_set_sk_err(net, RTNLGRP_NSID, err);
}

static int __init net_ns_init(void)
{
	struct net_generic *ng;

#ifdef CONFIG_NET_NS
	net_cachep = kmem_cache_create("net_namespace", sizeof(struct net),
					SMP_CACHE_BYTES,
					SLAB_PANIC|SLAB_ACCOUNT, NULL);

	/* Create workqueue for cleanup */
	netns_wq = create_singlethread_workqueue("netns");
	if (!netns_wq)
		panic("Could not create netns workq");
#endif

	ng = net_alloc_generic();
	if (!ng)
		panic("Could not allocate generic netns");

	rcu_assign_pointer(init_net.gen, ng);

	down_write(&pernet_ops_rwsem);
	if (setup_net(&init_net, &init_user_ns))
		panic("Could not setup the initial network namespace");

	init_net_initialized = true;
	up_write(&pernet_ops_rwsem);

	if (register_pernet_subsys(&net_ns_ops))
		panic("Could not register network namespace subsystems");

	rtnl_register(PF_UNSPEC, RTM_NEWNSID, rtnl_net_newid, NULL,
		      RTNL_FLAG_DOIT_UNLOCKED);
	rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, rtnl_net_dumpid,
		      RTNL_FLAG_DOIT_UNLOCKED);

	return 0;
}

pure_initcall(net_ns_init);

#ifdef CONFIG_NET_NS
static int __register_pernet_operations(struct list_head *list,
					struct pernet_operations *ops)
{
	struct net *net;
	int error;
	LIST_HEAD(net_exit_list);

	list_add_tail(&ops->list, list);
	if (ops->init || (ops->id && ops->size)) {
		/* We held write locked pernet_ops_rwsem, and parallel
		 * setup_net() and cleanup_net() are not possible.
		 */
		for_each_net(net) {
			error = ops_init(ops, net);
			if (error)
				goto out_undo;
			list_add_tail(&net->exit_list, &net_exit_list);
		}
	}
	return 0;

out_undo:
	/* If I have an error cleanup all namespaces I initialized */
	list_del(&ops->list);
	ops_exit_list(ops, &net_exit_list);
	ops_free_list(ops, &net_exit_list);
	return error;
}

static void __unregister_pernet_operations(struct pernet_operations *ops)
{
	struct net *net;
	LIST_HEAD(net_exit_list);

	list_del(&ops->list);
	/* See comment in __register_pernet_operations() */
	for_each_net(net)
		list_add_tail(&net->exit_list, &net_exit_list);
	ops_exit_list(ops, &net_exit_list);
	ops_free_list(ops, &net_exit_list);
}

#else

static int __register_pernet_operations(struct list_head *list,
					struct pernet_operations *ops)
{
	if (!init_net_initialized) {
		list_add_tail(&ops->list, list);
		return 0;
	}

	return ops_init(ops, &init_net);
}

static void __unregister_pernet_operations(struct pernet_operations *ops)
{
	if (!init_net_initialized) {
		list_del(&ops->list);
	} else {
		LIST_HEAD(net_exit_list);
		list_add(&init_net.exit_list, &net_exit_list);
		ops_exit_list(ops, &net_exit_list);
		ops_free_list(ops, &net_exit_list);
	}
}

#endif /* CONFIG_NET_NS */

static DEFINE_IDA(net_generic_ids);

static int register_pernet_operations(struct list_head *list,
				      struct pernet_operations *ops)
{
	int error;

	if (ops->id) {
		error = ida_alloc_min(&net_generic_ids, MIN_PERNET_OPS_ID,
				GFP_KERNEL);
		if (error < 0)
			return error;
		*ops->id = error;
		max_gen_ptrs = max(max_gen_ptrs, *ops->id + 1);
	}
	error = __register_pernet_operations(list, ops);
	if (error) {
		rcu_barrier();
		if (ops->id)
			ida_free(&net_generic_ids, *ops->id);
	}

	return error;
}

static void unregister_pernet_operations(struct pernet_operations *ops)
{
	__unregister_pernet_operations(ops);
	rcu_barrier();
	if (ops->id)
		ida_free(&net_generic_ids, *ops->id);
}

/**
 *      register_pernet_subsys - register a network namespace subsystem
 *	@ops:  pernet operations structure for the subsystem
 *
 *	Register a subsystem which has init and exit functions
 *	that are called when network namespaces are created and
 *	destroyed respectively.
 *
 *	When registered all network namespace init functions are
 *	called for every existing network namespace.  Allowing kernel
 *	modules to have a race free view of the set of network namespaces.
 *
 *	When a new network namespace is created all of the init
 *	methods are called in the order in which they were registered.
 *
 *	When a network namespace is destroyed all of the exit methods
 *	are called in the reverse of the order with which they were
 *	registered.
 */
int register_pernet_subsys(struct pernet_operations *ops)
{
	int error;
	down_write(&pernet_ops_rwsem);
	error =  register_pernet_operations(first_device, ops);
	up_write(&pernet_ops_rwsem);
	return error;
}
EXPORT_SYMBOL_GPL(register_pernet_subsys);

/**
 *      unregister_pernet_subsys - unregister a network namespace subsystem
 *	@ops: pernet operations structure to manipulate
 *
 *	Remove the pernet operations structure from the list to be
 *	used when network namespaces are created or destroyed.  In
 *	addition run the exit method for all existing network
 *	namespaces.
 */
void unregister_pernet_subsys(struct pernet_operations *ops)
{
	down_write(&pernet_ops_rwsem);
	unregister_pernet_operations(ops);
	up_write(&pernet_ops_rwsem);
}
EXPORT_SYMBOL_GPL(unregister_pernet_subsys);

/**
 *      register_pernet_device - register a network namespace device
 *	@ops:  pernet operations structure for the subsystem
 *
 *	Register a device which has init and exit functions
 *	that are called when network namespaces are created and
 *	destroyed respectively.
 *
 *	When registered all network namespace init functions are
 *	called for every existing network namespace.  Allowing kernel
 *	modules to have a race free view of the set of network namespaces.
 *
 *	When a new network namespace is created all of the init
 *	methods are called in the order in which they were registered.
 *
 *	When a network namespace is destroyed all of the exit methods
 *	are called in the reverse of the order with which they were
 *	registered.
 */
int register_pernet_device(struct pernet_operations *ops)
{
	int error;
	down_write(&pernet_ops_rwsem);
	error = register_pernet_operations(&pernet_list, ops);
	if (!error && (first_device == &pernet_list))
		first_device = &ops->list;
	up_write(&pernet_ops_rwsem);
	return error;
}
EXPORT_SYMBOL_GPL(register_pernet_device);

/**
 *      unregister_pernet_device - unregister a network namespace netdevice
 *	@ops: pernet operations structure to manipulate
 *
 *	Remove the pernet operations structure from the list to be
 *	used when network namespaces are created or destroyed.  In
 *	addition run the exit method for all existing network
 *	namespaces.
 */
void unregister_pernet_device(struct pernet_operations *ops)
{
	down_write(&pernet_ops_rwsem);
	if (&ops->list == first_device)
		first_device = first_device->next;
	unregister_pernet_operations(ops);
	up_write(&pernet_ops_rwsem);
}
EXPORT_SYMBOL_GPL(unregister_pernet_device);

#ifdef CONFIG_NET_NS
static struct ns_common *netns_get(struct task_struct *task)
{
	struct net *net = NULL;
	struct nsproxy *nsproxy;

	task_lock(task);
	nsproxy = task->nsproxy;
	if (nsproxy)
		net = get_net(nsproxy->net_ns);
	task_unlock(task);

	return net ? &net->ns : NULL;
}

static inline struct net *to_net_ns(struct ns_common *ns)
{
	return container_of(ns, struct net, ns);
}

static void netns_put(struct ns_common *ns)
{
	put_net(to_net_ns(ns));
}

static int netns_install(struct nsproxy *nsproxy, struct ns_common *ns)
{
	struct net *net = to_net_ns(ns);

	if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) ||
	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
		return -EPERM;

	put_net(nsproxy->net_ns);
	nsproxy->net_ns = get_net(net);
	return 0;
}

static struct user_namespace *netns_owner(struct ns_common *ns)
{
	return to_net_ns(ns)->user_ns;
}

const struct proc_ns_operations netns_operations = {
	.name		= "net",
	.type		= CLONE_NEWNET,
	.get		= netns_get,
	.put		= netns_put,
	.install	= netns_install,
	.owner		= netns_owner,
};
#endif