summaryrefslogtreecommitdiff
path: root/net/switchdev/switchdev.c
blob: 10b819308439cb6f63edc5d4c8f75dae2f06df1b (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
/*
 * net/switchdev/switchdev.c - Switch device API
 * Copyright (c) 2014-2015 Jiri Pirko <jiri@resnulli.us>
 * Copyright (c) 2014-2015 Scott Feldman <sfeldma@gmail.com>
 *
 * 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.
 */

#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/mutex.h>
#include <linux/notifier.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/if_bridge.h>
#include <linux/list.h>
#include <linux/workqueue.h>
#include <linux/if_vlan.h>
#include <linux/rtnetlink.h>
#include <net/ip_fib.h>
#include <net/switchdev.h>

/**
 *	switchdev_trans_item_enqueue - Enqueue data item to transaction queue
 *
 *	@trans: transaction
 *	@data: pointer to data being queued
 *	@destructor: data destructor
 *	@tritem: transaction item being queued
 *
 *	Enqeueue data item to transaction queue. tritem is typically placed in
 *	cointainter pointed at by data pointer. Destructor is called on
 *	transaction abort and after successful commit phase in case
 *	the caller did not dequeue the item before.
 */
void switchdev_trans_item_enqueue(struct switchdev_trans *trans,
				  void *data, void (*destructor)(void const *),
				  struct switchdev_trans_item *tritem)
{
	tritem->data = data;
	tritem->destructor = destructor;
	list_add_tail(&tritem->list, &trans->item_list);
}
EXPORT_SYMBOL_GPL(switchdev_trans_item_enqueue);

static struct switchdev_trans_item *
__switchdev_trans_item_dequeue(struct switchdev_trans *trans)
{
	struct switchdev_trans_item *tritem;

	if (list_empty(&trans->item_list))
		return NULL;
	tritem = list_first_entry(&trans->item_list,
				  struct switchdev_trans_item, list);
	list_del(&tritem->list);
	return tritem;
}

/**
 *	switchdev_trans_item_dequeue - Dequeue data item from transaction queue
 *
 *	@trans: transaction
 */
void *switchdev_trans_item_dequeue(struct switchdev_trans *trans)
{
	struct switchdev_trans_item *tritem;

	tritem = __switchdev_trans_item_dequeue(trans);
	BUG_ON(!tritem);
	return tritem->data;
}
EXPORT_SYMBOL_GPL(switchdev_trans_item_dequeue);

static void switchdev_trans_init(struct switchdev_trans *trans)
{
	INIT_LIST_HEAD(&trans->item_list);
}

static void switchdev_trans_items_destroy(struct switchdev_trans *trans)
{
	struct switchdev_trans_item *tritem;

	while ((tritem = __switchdev_trans_item_dequeue(trans)))
		tritem->destructor(tritem->data);
}

static void switchdev_trans_items_warn_destroy(struct net_device *dev,
					       struct switchdev_trans *trans)
{
	WARN(!list_empty(&trans->item_list), "%s: transaction item queue is not empty.\n",
	     dev->name);
	switchdev_trans_items_destroy(trans);
}

static LIST_HEAD(deferred);
static DEFINE_SPINLOCK(deferred_lock);

typedef void switchdev_deferred_func_t(struct net_device *dev,
				       const void *data);

struct switchdev_deferred_item {
	struct list_head list;
	struct net_device *dev;
	switchdev_deferred_func_t *func;
	unsigned long data[0];
};

static struct switchdev_deferred_item *switchdev_deferred_dequeue(void)
{
	struct switchdev_deferred_item *dfitem;

	spin_lock_bh(&deferred_lock);
	if (list_empty(&deferred)) {
		dfitem = NULL;
		goto unlock;
	}
	dfitem = list_first_entry(&deferred,
				  struct switchdev_deferred_item, list);
	list_del(&dfitem->list);
unlock:
	spin_unlock_bh(&deferred_lock);
	return dfitem;
}

/**
 *	switchdev_deferred_process - Process ops in deferred queue
 *
 *	Called to flush the ops currently queued in deferred ops queue.
 *	rtnl_lock must be held.
 */
void switchdev_deferred_process(void)
{
	struct switchdev_deferred_item *dfitem;

	ASSERT_RTNL();

	while ((dfitem = switchdev_deferred_dequeue())) {
		dfitem->func(dfitem->dev, dfitem->data);
		dev_put(dfitem->dev);
		kfree(dfitem);
	}
}
EXPORT_SYMBOL_GPL(switchdev_deferred_process);

static void switchdev_deferred_process_work(struct work_struct *work)
{
	rtnl_lock();
	switchdev_deferred_process();
	rtnl_unlock();
}

static DECLARE_WORK(deferred_process_work, switchdev_deferred_process_work);

static int switchdev_deferred_enqueue(struct net_device *dev,
				      const void *data, size_t data_len,
				      switchdev_deferred_func_t *func)
{
	struct switchdev_deferred_item *dfitem;

	dfitem = kmalloc(sizeof(*dfitem) + data_len, GFP_ATOMIC);
	if (!dfitem)
		return -ENOMEM;
	dfitem->dev = dev;
	dfitem->func = func;
	memcpy(dfitem->data, data, data_len);
	dev_hold(dev);
	spin_lock_bh(&deferred_lock);
	list_add_tail(&dfitem->list, &deferred);
	spin_unlock_bh(&deferred_lock);
	schedule_work(&deferred_process_work);
	return 0;
}

/**
 *	switchdev_port_attr_get - Get port attribute
 *
 *	@dev: port device
 *	@attr: attribute to get
 */
int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr)
{
	const struct switchdev_ops *ops = dev->switchdev_ops;
	struct net_device *lower_dev;
	struct list_head *iter;
	struct switchdev_attr first = {
		.id = SWITCHDEV_ATTR_ID_UNDEFINED
	};
	int err = -EOPNOTSUPP;

	if (ops && ops->switchdev_port_attr_get)
		return ops->switchdev_port_attr_get(dev, attr);

	if (attr->flags & SWITCHDEV_F_NO_RECURSE)
		return err;

	/* Switch device port(s) may be stacked under
	 * bond/team/vlan dev, so recurse down to get attr on
	 * each port.  Return -ENODATA if attr values don't
	 * compare across ports.
	 */

	netdev_for_each_lower_dev(dev, lower_dev, iter) {
		err = switchdev_port_attr_get(lower_dev, attr);
		if (err)
			break;
		if (first.id == SWITCHDEV_ATTR_ID_UNDEFINED)
			first = *attr;
		else if (memcmp(&first, attr, sizeof(*attr)))
			return -ENODATA;
	}

	return err;
}
EXPORT_SYMBOL_GPL(switchdev_port_attr_get);

static int __switchdev_port_attr_set(struct net_device *dev,
				     const struct switchdev_attr *attr,
				     struct switchdev_trans *trans)
{
	const struct switchdev_ops *ops = dev->switchdev_ops;
	struct net_device *lower_dev;
	struct list_head *iter;
	int err = -EOPNOTSUPP;

	if (ops && ops->switchdev_port_attr_set) {
		err = ops->switchdev_port_attr_set(dev, attr, trans);
		goto done;
	}

	if (attr->flags & SWITCHDEV_F_NO_RECURSE)
		goto done;

	/* Switch device port(s) may be stacked under
	 * bond/team/vlan dev, so recurse down to set attr on
	 * each port.
	 */

	netdev_for_each_lower_dev(dev, lower_dev, iter) {
		err = __switchdev_port_attr_set(lower_dev, attr, trans);
		if (err)
			break;
	}

done:
	if (err == -EOPNOTSUPP && attr->flags & SWITCHDEV_F_SKIP_EOPNOTSUPP)
		err = 0;

	return err;
}

static int switchdev_port_attr_set_now(struct net_device *dev,
				       const struct switchdev_attr *attr)
{
	struct switchdev_trans trans;
	int err;

	switchdev_trans_init(&trans);

	/* Phase I: prepare for attr set. Driver/device should fail
	 * here if there are going to be issues in the commit phase,
	 * such as lack of resources or support.  The driver/device
	 * should reserve resources needed for the commit phase here,
	 * but should not commit the attr.
	 */

	trans.ph_prepare = true;
	err = __switchdev_port_attr_set(dev, attr, &trans);
	if (err) {
		/* Prepare phase failed: abort the transaction.  Any
		 * resources reserved in the prepare phase are
		 * released.
		 */

		if (err != -EOPNOTSUPP)
			switchdev_trans_items_destroy(&trans);

		return err;
	}

	/* Phase II: commit attr set.  This cannot fail as a fault
	 * of driver/device.  If it does, it's a bug in the driver/device
	 * because the driver said everythings was OK in phase I.
	 */

	trans.ph_prepare = false;
	err = __switchdev_port_attr_set(dev, attr, &trans);
	WARN(err, "%s: Commit of attribute (id=%d) failed.\n",
	     dev->name, attr->id);
	switchdev_trans_items_warn_destroy(dev, &trans);

	return err;
}

static void switchdev_port_attr_set_deferred(struct net_device *dev,
					     const void *data)
{
	const struct switchdev_attr *attr = data;
	int err;

	err = switchdev_port_attr_set_now(dev, attr);
	if (err && err != -EOPNOTSUPP)
		netdev_err(dev, "failed (err=%d) to set attribute (id=%d)\n",
			   err, attr->id);
	if (attr->complete)
		attr->complete(dev, err, attr->complete_priv);
}

static int switchdev_port_attr_set_defer(struct net_device *dev,
					 const struct switchdev_attr *attr)
{
	return switchdev_deferred_enqueue(dev, attr, sizeof(*attr),
					  switchdev_port_attr_set_deferred);
}

/**
 *	switchdev_port_attr_set - Set port attribute
 *
 *	@dev: port device
 *	@attr: attribute to set
 *
 *	Use a 2-phase prepare-commit transaction model to ensure
 *	system is not left in a partially updated state due to
 *	failure from driver/device.
 *
 *	rtnl_lock must be held and must not be in atomic section,
 *	in case SWITCHDEV_F_DEFER flag is not set.
 */
int switchdev_port_attr_set(struct net_device *dev,
			    const struct switchdev_attr *attr)
{
	if (attr->flags & SWITCHDEV_F_DEFER)
		return switchdev_port_attr_set_defer(dev, attr);
	ASSERT_RTNL();
	return switchdev_port_attr_set_now(dev, attr);
}
EXPORT_SYMBOL_GPL(switchdev_port_attr_set);

static size_t switchdev_obj_size(const struct switchdev_obj *obj)
{
	switch (obj->id) {
	case SWITCHDEV_OBJ_ID_PORT_VLAN:
		return sizeof(struct switchdev_obj_port_vlan);
	case SWITCHDEV_OBJ_ID_IPV4_FIB:
		return sizeof(struct switchdev_obj_ipv4_fib);
	case SWITCHDEV_OBJ_ID_PORT_FDB:
		return sizeof(struct switchdev_obj_port_fdb);
	case SWITCHDEV_OBJ_ID_PORT_MDB:
		return sizeof(struct switchdev_obj_port_mdb);
	default:
		BUG();
	}
	return 0;
}

static int __switchdev_port_obj_add(struct net_device *dev,
				    const struct switchdev_obj *obj,
				    struct switchdev_trans *trans)
{
	const struct switchdev_ops *ops = dev->switchdev_ops;
	struct net_device *lower_dev;
	struct list_head *iter;
	int err = -EOPNOTSUPP;

	if (ops && ops->switchdev_port_obj_add)
		return ops->switchdev_port_obj_add(dev, obj, trans);

	/* Switch device port(s) may be stacked under
	 * bond/team/vlan dev, so recurse down to add object on
	 * each port.
	 */

	netdev_for_each_lower_dev(dev, lower_dev, iter) {
		err = __switchdev_port_obj_add(lower_dev, obj, trans);
		if (err)
			break;
	}

	return err;
}

static int switchdev_port_obj_add_now(struct net_device *dev,
				      const struct switchdev_obj *obj)
{
	struct switchdev_trans trans;
	int err;

	ASSERT_RTNL();

	switchdev_trans_init(&trans);

	/* Phase I: prepare for obj add. Driver/device should fail
	 * here if there are going to be issues in the commit phase,
	 * such as lack of resources or support.  The driver/device
	 * should reserve resources needed for the commit phase here,
	 * but should not commit the obj.
	 */

	trans.ph_prepare = true;
	err = __switchdev_port_obj_add(dev, obj, &trans);
	if (err) {
		/* Prepare phase failed: abort the transaction.  Any
		 * resources reserved in the prepare phase are
		 * released.
		 */

		if (err != -EOPNOTSUPP)
			switchdev_trans_items_destroy(&trans);

		return err;
	}

	/* Phase II: commit obj add.  This cannot fail as a fault
	 * of driver/device.  If it does, it's a bug in the driver/device
	 * because the driver said everythings was OK in phase I.
	 */

	trans.ph_prepare = false;
	err = __switchdev_port_obj_add(dev, obj, &trans);
	WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id);
	switchdev_trans_items_warn_destroy(dev, &trans);

	return err;
}

static void switchdev_port_obj_add_deferred(struct net_device *dev,
					    const void *data)
{
	const struct switchdev_obj *obj = data;
	int err;

	err = switchdev_port_obj_add_now(dev, obj);
	if (err && err != -EOPNOTSUPP)
		netdev_err(dev, "failed (err=%d) to add object (id=%d)\n",
			   err, obj->id);
	if (obj->complete)
		obj->complete(dev, err, obj->complete_priv);
}

static int switchdev_port_obj_add_defer(struct net_device *dev,
					const struct switchdev_obj *obj)
{
	return switchdev_deferred_enqueue(dev, obj, switchdev_obj_size(obj),
					  switchdev_port_obj_add_deferred);
}

/**
 *	switchdev_port_obj_add - Add port object
 *
 *	@dev: port device
 *	@id: object ID
 *	@obj: object to add
 *
 *	Use a 2-phase prepare-commit transaction model to ensure
 *	system is not left in a partially updated state due to
 *	failure from driver/device.
 *
 *	rtnl_lock must be held and must not be in atomic section,
 *	in case SWITCHDEV_F_DEFER flag is not set.
 */
int switchdev_port_obj_add(struct net_device *dev,
			   const struct switchdev_obj *obj)
{
	if (obj->flags & SWITCHDEV_F_DEFER)
		return switchdev_port_obj_add_defer(dev, obj);
	ASSERT_RTNL();
	return switchdev_port_obj_add_now(dev, obj);
}
EXPORT_SYMBOL_GPL(switchdev_port_obj_add);

static int switchdev_port_obj_del_now(struct net_device *dev,
				      const struct switchdev_obj *obj)
{
	const struct switchdev_ops *ops = dev->switchdev_ops;
	struct net_device *lower_dev;
	struct list_head *iter;
	int err = -EOPNOTSUPP;

	if (ops && ops->switchdev_port_obj_del)
		return ops->switchdev_port_obj_del(dev, obj);

	/* Switch device port(s) may be stacked under
	 * bond/team/vlan dev, so recurse down to delete object on
	 * each port.
	 */

	netdev_for_each_lower_dev(dev, lower_dev, iter) {
		err = switchdev_port_obj_del_now(lower_dev, obj);
		if (err)
			break;
	}

	return err;
}

static void switchdev_port_obj_del_deferred(struct net_device *dev,
					    const void *data)
{
	const struct switchdev_obj *obj = data;
	int err;

	err = switchdev_port_obj_del_now(dev, obj);
	if (err && err != -EOPNOTSUPP)
		netdev_err(dev, "failed (err=%d) to del object (id=%d)\n",
			   err, obj->id);
	if (obj->complete)
		obj->complete(dev, err, obj->complete_priv);
}

static int switchdev_port_obj_del_defer(struct net_device *dev,
					const struct switchdev_obj *obj)
{
	return switchdev_deferred_enqueue(dev, obj, switchdev_obj_size(obj),
					  switchdev_port_obj_del_deferred);
}

/**
 *	switchdev_port_obj_del - Delete port object
 *
 *	@dev: port device
 *	@id: object ID
 *	@obj: object to delete
 *
 *	rtnl_lock must be held and must not be in atomic section,
 *	in case SWITCHDEV_F_DEFER flag is not set.
 */
int switchdev_port_obj_del(struct net_device *dev,
			   const struct switchdev_obj *obj)
{
	if (obj->flags & SWITCHDEV_F_DEFER)
		return switchdev_port_obj_del_defer(dev, obj);
	ASSERT_RTNL();
	return switchdev_port_obj_del_now(dev, obj);
}
EXPORT_SYMBOL_GPL(switchdev_port_obj_del);

/**
 *	switchdev_port_obj_dump - Dump port objects
 *
 *	@dev: port device
 *	@id: object ID
 *	@obj: object to dump
 *	@cb: function to call with a filled object
 *
 *	rtnl_lock must be held.
 */
int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj,
			    switchdev_obj_dump_cb_t *cb)
{
	const struct switchdev_ops *ops = dev->switchdev_ops;
	struct net_device *lower_dev;
	struct list_head *iter;
	int err = -EOPNOTSUPP;

	ASSERT_RTNL();

	if (ops && ops->switchdev_port_obj_dump)
		return ops->switchdev_port_obj_dump(dev, obj, cb);

	/* Switch device port(s) may be stacked under
	 * bond/team/vlan dev, so recurse down to dump objects on
	 * first port at bottom of stack.
	 */

	netdev_for_each_lower_dev(dev, lower_dev, iter) {
		err = switchdev_port_obj_dump(lower_dev, obj, cb);
		break;
	}

	return err;
}
EXPORT_SYMBOL_GPL(switchdev_port_obj_dump);

static RAW_NOTIFIER_HEAD(switchdev_notif_chain);

/**
 *	register_switchdev_notifier - Register notifier
 *	@nb: notifier_block
 *
 *	Register switch device notifier. This should be used by code
 *	which needs to monitor events happening in particular device.
 *	Return values are same as for atomic_notifier_chain_register().
 */
int register_switchdev_notifier(struct notifier_block *nb)
{
	int err;

	rtnl_lock();
	err = raw_notifier_chain_register(&switchdev_notif_chain, nb);
	rtnl_unlock();
	return err;
}
EXPORT_SYMBOL_GPL(register_switchdev_notifier);

/**
 *	unregister_switchdev_notifier - Unregister notifier
 *	@nb: notifier_block
 *
 *	Unregister switch device notifier.
 *	Return values are same as for atomic_notifier_chain_unregister().
 */
int unregister_switchdev_notifier(struct notifier_block *nb)
{
	int err;

	rtnl_lock();
	err = raw_notifier_chain_unregister(&switchdev_notif_chain, nb);
	rtnl_unlock();
	return err;
}
EXPORT_SYMBOL_GPL(unregister_switchdev_notifier);

/**
 *	call_switchdev_notifiers - Call notifiers
 *	@val: value passed unmodified to notifier function
 *	@dev: port device
 *	@info: notifier information data
 *
 *	Call all network notifier blocks. This should be called by driver
 *	when it needs to propagate hardware event.
 *	Return values are same as for atomic_notifier_call_chain().
 *	rtnl_lock must be held.
 */
int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
			     struct switchdev_notifier_info *info)
{
	int err;

	ASSERT_RTNL();

	info->dev = dev;
	err = raw_notifier_call_chain(&switchdev_notif_chain, val, info);
	return err;
}
EXPORT_SYMBOL_GPL(call_switchdev_notifiers);

struct switchdev_vlan_dump {
	struct switchdev_obj_port_vlan vlan;
	struct sk_buff *skb;
	u32 filter_mask;
	u16 flags;
	u16 begin;
	u16 end;
};

static int switchdev_port_vlan_dump_put(struct switchdev_vlan_dump *dump)
{
	struct bridge_vlan_info vinfo;

	vinfo.flags = dump->flags;

	if (dump->begin == 0 && dump->end == 0) {
		return 0;
	} else if (dump->begin == dump->end) {
		vinfo.vid = dump->begin;
		if (nla_put(dump->skb, IFLA_BRIDGE_VLAN_INFO,
			    sizeof(vinfo), &vinfo))
			return -EMSGSIZE;
	} else {
		vinfo.vid = dump->begin;
		vinfo.flags |= BRIDGE_VLAN_INFO_RANGE_BEGIN;
		if (nla_put(dump->skb, IFLA_BRIDGE_VLAN_INFO,
			    sizeof(vinfo), &vinfo))
			return -EMSGSIZE;
		vinfo.vid = dump->end;
		vinfo.flags &= ~BRIDGE_VLAN_INFO_RANGE_BEGIN;
		vinfo.flags |= BRIDGE_VLAN_INFO_RANGE_END;
		if (nla_put(dump->skb, IFLA_BRIDGE_VLAN_INFO,
			    sizeof(vinfo), &vinfo))
			return -EMSGSIZE;
	}

	return 0;
}

static int switchdev_port_vlan_dump_cb(struct switchdev_obj *obj)
{
	struct switchdev_obj_port_vlan *vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
	struct switchdev_vlan_dump *dump =
		container_of(vlan, struct switchdev_vlan_dump, vlan);
	int err = 0;

	if (vlan->vid_begin > vlan->vid_end)
		return -EINVAL;

	if (dump->filter_mask & RTEXT_FILTER_BRVLAN) {
		dump->flags = vlan->flags;
		for (dump->begin = dump->end = vlan->vid_begin;
		     dump->begin <= vlan->vid_end;
		     dump->begin++, dump->end++) {
			err = switchdev_port_vlan_dump_put(dump);
			if (err)
				return err;
		}
	} else if (dump->filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) {
		if (dump->begin > vlan->vid_begin &&
		    dump->begin >= vlan->vid_end) {
			if ((dump->begin - 1) == vlan->vid_end &&
			    dump->flags == vlan->flags) {
				/* prepend */
				dump->begin = vlan->vid_begin;
			} else {
				err = switchdev_port_vlan_dump_put(dump);
				dump->flags = vlan->flags;
				dump->begin = vlan->vid_begin;
				dump->end = vlan->vid_end;
			}
		} else if (dump->end <= vlan->vid_begin &&
		           dump->end < vlan->vid_end) {
			if ((dump->end  + 1) == vlan->vid_begin &&
			    dump->flags == vlan->flags) {
				/* append */
				dump->end = vlan->vid_end;
			} else {
				err = switchdev_port_vlan_dump_put(dump);
				dump->flags = vlan->flags;
				dump->begin = vlan->vid_begin;
				dump->end = vlan->vid_end;
			}
		} else {
			err = -EINVAL;
		}
	}

	return err;
}

static int switchdev_port_vlan_fill(struct sk_buff *skb, struct net_device *dev,
				    u32 filter_mask)
{
	struct switchdev_vlan_dump dump = {
		.vlan.obj.orig_dev = dev,
		.vlan.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
		.skb = skb,
		.filter_mask = filter_mask,
	};
	int err = 0;

	if ((filter_mask & RTEXT_FILTER_BRVLAN) ||
	    (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) {
		err = switchdev_port_obj_dump(dev, &dump.vlan.obj,
					      switchdev_port_vlan_dump_cb);
		if (err)
			goto err_out;
		if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)
			/* last one */
			err = switchdev_port_vlan_dump_put(&dump);
	}

err_out:
	return err == -EOPNOTSUPP ? 0 : err;
}

/**
 *	switchdev_port_bridge_getlink - Get bridge port attributes
 *
 *	@dev: port device
 *
 *	Called for SELF on rtnl_bridge_getlink to get bridge port
 *	attributes.
 */
int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
				  struct net_device *dev, u32 filter_mask,
				  int nlflags)
{
	struct switchdev_attr attr = {
		.orig_dev = dev,
		.id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS,
	};
	u16 mode = BRIDGE_MODE_UNDEF;
	u32 mask = BR_LEARNING | BR_LEARNING_SYNC | BR_FLOOD;
	int err;

	err = switchdev_port_attr_get(dev, &attr);
	if (err && err != -EOPNOTSUPP)
		return err;

	return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode,
				       attr.u.brport_flags, mask, nlflags,
				       filter_mask, switchdev_port_vlan_fill);
}
EXPORT_SYMBOL_GPL(switchdev_port_bridge_getlink);

static int switchdev_port_br_setflag(struct net_device *dev,
				     struct nlattr *nlattr,
				     unsigned long brport_flag)
{
	struct switchdev_attr attr = {
		.orig_dev = dev,
		.id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS,
	};
	u8 flag = nla_get_u8(nlattr);
	int err;

	err = switchdev_port_attr_get(dev, &attr);
	if (err)
		return err;

	if (flag)
		attr.u.brport_flags |= brport_flag;
	else
		attr.u.brport_flags &= ~brport_flag;

	return switchdev_port_attr_set(dev, &attr);
}

static const struct nla_policy
switchdev_port_bridge_policy[IFLA_BRPORT_MAX + 1] = {
	[IFLA_BRPORT_STATE]		= { .type = NLA_U8 },
	[IFLA_BRPORT_COST]		= { .type = NLA_U32 },
	[IFLA_BRPORT_PRIORITY]		= { .type = NLA_U16 },
	[IFLA_BRPORT_MODE]		= { .type = NLA_U8 },
	[IFLA_BRPORT_GUARD]		= { .type = NLA_U8 },
	[IFLA_BRPORT_PROTECT]		= { .type = NLA_U8 },
	[IFLA_BRPORT_FAST_LEAVE]	= { .type = NLA_U8 },
	[IFLA_BRPORT_LEARNING]		= { .type = NLA_U8 },
	[IFLA_BRPORT_LEARNING_SYNC]	= { .type = NLA_U8 },
	[IFLA_BRPORT_UNICAST_FLOOD]	= { .type = NLA_U8 },
};

static int switchdev_port_br_setlink_protinfo(struct net_device *dev,
					      struct nlattr *protinfo)
{
	struct nlattr *attr;
	int rem;
	int err;

	err = nla_validate_nested(protinfo, IFLA_BRPORT_MAX,
				  switchdev_port_bridge_policy);
	if (err)
		return err;

	nla_for_each_nested(attr, protinfo, rem) {
		switch (nla_type(attr)) {
		case IFLA_BRPORT_LEARNING:
			err = switchdev_port_br_setflag(dev, attr,
							BR_LEARNING);
			break;
		case IFLA_BRPORT_LEARNING_SYNC:
			err = switchdev_port_br_setflag(dev, attr,
							BR_LEARNING_SYNC);
			break;
		case IFLA_BRPORT_UNICAST_FLOOD:
			err = switchdev_port_br_setflag(dev, attr, BR_FLOOD);
			break;
		default:
			err = -EOPNOTSUPP;
			break;
		}
		if (err)
			return err;
	}

	return 0;
}

static int switchdev_port_br_afspec(struct net_device *dev,
				    struct nlattr *afspec,
				    int (*f)(struct net_device *dev,
					     const struct switchdev_obj *obj))
{
	struct nlattr *attr;
	struct bridge_vlan_info *vinfo;
	struct switchdev_obj_port_vlan vlan = {
		.obj.orig_dev = dev,
		.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
	};
	int rem;
	int err;

	nla_for_each_nested(attr, afspec, rem) {
		if (nla_type(attr) != IFLA_BRIDGE_VLAN_INFO)
			continue;
		if (nla_len(attr) != sizeof(struct bridge_vlan_info))
			return -EINVAL;
		vinfo = nla_data(attr);
		if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK)
			return -EINVAL;
		vlan.flags = vinfo->flags;
		if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) {
			if (vlan.vid_begin)
				return -EINVAL;
			vlan.vid_begin = vinfo->vid;
			/* don't allow range of pvids */
			if (vlan.flags & BRIDGE_VLAN_INFO_PVID)
				return -EINVAL;
		} else if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END) {
			if (!vlan.vid_begin)
				return -EINVAL;
			vlan.vid_end = vinfo->vid;
			if (vlan.vid_end <= vlan.vid_begin)
				return -EINVAL;
			err = f(dev, &vlan.obj);
			if (err)
				return err;
			vlan.vid_begin = 0;
		} else {
			if (vlan.vid_begin)
				return -EINVAL;
			vlan.vid_begin = vinfo->vid;
			vlan.vid_end = vinfo->vid;
			err = f(dev, &vlan.obj);
			if (err)
				return err;
			vlan.vid_begin = 0;
		}
	}

	return 0;
}

/**
 *	switchdev_port_bridge_setlink - Set bridge port attributes
 *
 *	@dev: port device
 *	@nlh: netlink header
 *	@flags: netlink flags
 *
 *	Called for SELF on rtnl_bridge_setlink to set bridge port
 *	attributes.
 */
int switchdev_port_bridge_setlink(struct net_device *dev,
				  struct nlmsghdr *nlh, u16 flags)
{
	struct nlattr *protinfo;
	struct nlattr *afspec;
	int err = 0;

	protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
				   IFLA_PROTINFO);
	if (protinfo) {
		err = switchdev_port_br_setlink_protinfo(dev, protinfo);
		if (err)
			return err;
	}

	afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
				 IFLA_AF_SPEC);
	if (afspec)
		err = switchdev_port_br_afspec(dev, afspec,
					       switchdev_port_obj_add);

	return err;
}
EXPORT_SYMBOL_GPL(switchdev_port_bridge_setlink);

/**
 *	switchdev_port_bridge_dellink - Set bridge port attributes
 *
 *	@dev: port device
 *	@nlh: netlink header
 *	@flags: netlink flags
 *
 *	Called for SELF on rtnl_bridge_dellink to set bridge port
 *	attributes.
 */
int switchdev_port_bridge_dellink(struct net_device *dev,
				  struct nlmsghdr *nlh, u16 flags)
{
	struct nlattr *afspec;

	afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
				 IFLA_AF_SPEC);
	if (afspec)
		return switchdev_port_br_afspec(dev, afspec,
						switchdev_port_obj_del);

	return 0;
}
EXPORT_SYMBOL_GPL(switchdev_port_bridge_dellink);

/**
 *	switchdev_port_fdb_add - Add FDB (MAC/VLAN) entry to port
 *
 *	@ndmsg: netlink hdr
 *	@nlattr: netlink attributes
 *	@dev: port device
 *	@addr: MAC address to add
 *	@vid: VLAN to add
 *
 *	Add FDB entry to switch device.
 */
int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
			   struct net_device *dev, const unsigned char *addr,
			   u16 vid, u16 nlm_flags)
{
	struct switchdev_obj_port_fdb fdb = {
		.obj.orig_dev = dev,
		.obj.id = SWITCHDEV_OBJ_ID_PORT_FDB,
		.vid = vid,
	};

	ether_addr_copy(fdb.addr, addr);
	return switchdev_port_obj_add(dev, &fdb.obj);
}
EXPORT_SYMBOL_GPL(switchdev_port_fdb_add);

/**
 *	switchdev_port_fdb_del - Delete FDB (MAC/VLAN) entry from port
 *
 *	@ndmsg: netlink hdr
 *	@nlattr: netlink attributes
 *	@dev: port device
 *	@addr: MAC address to delete
 *	@vid: VLAN to delete
 *
 *	Delete FDB entry from switch device.
 */
int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
			   struct net_device *dev, const unsigned char *addr,
			   u16 vid)
{
	struct switchdev_obj_port_fdb fdb = {
		.obj.orig_dev = dev,
		.obj.id = SWITCHDEV_OBJ_ID_PORT_FDB,
		.vid = vid,
	};

	ether_addr_copy(fdb.addr, addr);
	return switchdev_port_obj_del(dev, &fdb.obj);
}
EXPORT_SYMBOL_GPL(switchdev_port_fdb_del);

struct switchdev_fdb_dump {
	struct switchdev_obj_port_fdb fdb;
	struct net_device *dev;
	struct sk_buff *skb;
	struct netlink_callback *cb;
	int idx;
};

static int switchdev_port_fdb_dump_cb(struct switchdev_obj *obj)
{
	struct switchdev_obj_port_fdb *fdb = SWITCHDEV_OBJ_PORT_FDB(obj);
	struct switchdev_fdb_dump *dump =
		container_of(fdb, struct switchdev_fdb_dump, fdb);
	u32 portid = NETLINK_CB(dump->cb->skb).portid;
	u32 seq = dump->cb->nlh->nlmsg_seq;
	struct nlmsghdr *nlh;
	struct ndmsg *ndm;

	if (dump->idx < dump->cb->args[2])
		goto skip;

	nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH,
			sizeof(*ndm), NLM_F_MULTI);
	if (!nlh)
		return -EMSGSIZE;

	ndm = nlmsg_data(nlh);
	ndm->ndm_family  = AF_BRIDGE;
	ndm->ndm_pad1    = 0;
	ndm->ndm_pad2    = 0;
	ndm->ndm_flags   = NTF_SELF;
	ndm->ndm_type    = 0;
	ndm->ndm_ifindex = dump->dev->ifindex;
	ndm->ndm_state   = fdb->ndm_state;

	if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, fdb->addr))
		goto nla_put_failure;

	if (fdb->vid && nla_put_u16(dump->skb, NDA_VLAN, fdb->vid))
		goto nla_put_failure;

	nlmsg_end(dump->skb, nlh);

skip:
	dump->idx++;
	return 0;

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

/**
 *	switchdev_port_fdb_dump - Dump port FDB (MAC/VLAN) entries
 *
 *	@skb: netlink skb
 *	@cb: netlink callback
 *	@dev: port device
 *	@filter_dev: filter device
 *	@idx:
 *
 *	Dump FDB entries from switch device.
 */
int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
			    struct net_device *dev,
			    struct net_device *filter_dev, int *idx)
{
	struct switchdev_fdb_dump dump = {
		.fdb.obj.orig_dev = dev,
		.fdb.obj.id = SWITCHDEV_OBJ_ID_PORT_FDB,
		.dev = dev,
		.skb = skb,
		.cb = cb,
		.idx = *idx,
	};
	int err;

	err = switchdev_port_obj_dump(dev, &dump.fdb.obj,
				      switchdev_port_fdb_dump_cb);
	*idx = dump.idx;
	return err;
}
EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump);

static struct net_device *switchdev_get_lowest_dev(struct net_device *dev)
{
	const struct switchdev_ops *ops = dev->switchdev_ops;
	struct net_device *lower_dev;
	struct net_device *port_dev;
	struct list_head *iter;

	/* Recusively search down until we find a sw port dev.
	 * (A sw port dev supports switchdev_port_attr_get).
	 */

	if (ops && ops->switchdev_port_attr_get)
		return dev;

	netdev_for_each_lower_dev(dev, lower_dev, iter) {
		port_dev = switchdev_get_lowest_dev(lower_dev);
		if (port_dev)
			return port_dev;
	}

	return NULL;
}

static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi)
{
	struct switchdev_attr attr = {
		.id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
	};
	struct switchdev_attr prev_attr;
	struct net_device *dev = NULL;
	int nhsel;

	ASSERT_RTNL();

	/* For this route, all nexthop devs must be on the same switch. */

	for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
		const struct fib_nh *nh = &fi->fib_nh[nhsel];

		if (!nh->nh_dev)
			return NULL;

		dev = switchdev_get_lowest_dev(nh->nh_dev);
		if (!dev)
			return NULL;

		attr.orig_dev = dev;
		if (switchdev_port_attr_get(dev, &attr))
			return NULL;

		if (nhsel > 0 &&
		    !netdev_phys_item_id_same(&prev_attr.u.ppid, &attr.u.ppid))
				return NULL;

		prev_attr = attr;
	}

	return dev;
}

/**
 *	switchdev_fib_ipv4_add - Add/modify switch IPv4 route entry
 *
 *	@dst: route's IPv4 destination address
 *	@dst_len: destination address length (prefix length)
 *	@fi: route FIB info structure
 *	@tos: route TOS
 *	@type: route type
 *	@nlflags: netlink flags passed in (NLM_F_*)
 *	@tb_id: route table ID
 *
 *	Add/modify switch IPv4 route entry.
 */
int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
			   u8 tos, u8 type, u32 nlflags, u32 tb_id)
{
	struct switchdev_obj_ipv4_fib ipv4_fib = {
		.obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB,
		.dst = dst,
		.dst_len = dst_len,
		.fi = fi,
		.tos = tos,
		.type = type,
		.nlflags = nlflags,
		.tb_id = tb_id,
	};
	struct net_device *dev;
	int err = 0;

	/* Don't offload route if using custom ip rules or if
	 * IPv4 FIB offloading has been disabled completely.
	 */

#ifdef CONFIG_IP_MULTIPLE_TABLES
	if (fi->fib_net->ipv4.fib_has_custom_rules)
		return 0;
#endif

	if (fi->fib_net->ipv4.fib_offload_disabled)
		return 0;

	dev = switchdev_get_dev_by_nhs(fi);
	if (!dev)
		return 0;

	ipv4_fib.obj.orig_dev = dev;
	err = switchdev_port_obj_add(dev, &ipv4_fib.obj);
	if (!err)
		fi->fib_flags |= RTNH_F_OFFLOAD;

	return err == -EOPNOTSUPP ? 0 : err;
}
EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_add);

/**
 *	switchdev_fib_ipv4_del - Delete IPv4 route entry from switch
 *
 *	@dst: route's IPv4 destination address
 *	@dst_len: destination address length (prefix length)
 *	@fi: route FIB info structure
 *	@tos: route TOS
 *	@type: route type
 *	@tb_id: route table ID
 *
 *	Delete IPv4 route entry from switch device.
 */
int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
			   u8 tos, u8 type, u32 tb_id)
{
	struct switchdev_obj_ipv4_fib ipv4_fib = {
		.obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB,
		.dst = dst,
		.dst_len = dst_len,
		.fi = fi,
		.tos = tos,
		.type = type,
		.nlflags = 0,
		.tb_id = tb_id,
	};
	struct net_device *dev;
	int err = 0;

	if (!(fi->fib_flags & RTNH_F_OFFLOAD))
		return 0;

	dev = switchdev_get_dev_by_nhs(fi);
	if (!dev)
		return 0;

	ipv4_fib.obj.orig_dev = dev;
	err = switchdev_port_obj_del(dev, &ipv4_fib.obj);
	if (!err)
		fi->fib_flags &= ~RTNH_F_OFFLOAD;

	return err == -EOPNOTSUPP ? 0 : err;
}
EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_del);

/**
 *	switchdev_fib_ipv4_abort - Abort an IPv4 FIB operation
 *
 *	@fi: route FIB info structure
 */
void switchdev_fib_ipv4_abort(struct fib_info *fi)
{
	/* There was a problem installing this route to the offload
	 * device.  For now, until we come up with more refined
	 * policy handling, abruptly end IPv4 fib offloading for
	 * for entire net by flushing offload device(s) of all
	 * IPv4 routes, and mark IPv4 fib offloading broken from
	 * this point forward.
	 */

	fib_flush_external(fi->fib_net);
	fi->fib_net->ipv4.fib_offload_disabled = true;
}
EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_abort);

bool switchdev_port_same_parent_id(struct net_device *a,
				   struct net_device *b)
{
	struct switchdev_attr a_attr = {
		.orig_dev = a,
		.id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
	};
	struct switchdev_attr b_attr = {
		.orig_dev = b,
		.id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
	};

	if (switchdev_port_attr_get(a, &a_attr) ||
	    switchdev_port_attr_get(b, &b_attr))
		return false;

	return netdev_phys_item_id_same(&a_attr.u.ppid, &b_attr.u.ppid);
}
EXPORT_SYMBOL_GPL(switchdev_port_same_parent_id);