summaryrefslogtreecommitdiffstats
path: root/drivers/net/netdevsim/fib.c
blob: a1f91ff8ec5688e7c3bf3274a47a8f8304992a76 (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
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
/*
 * Copyright (c) 2018 Cumulus Networks. All rights reserved.
 * Copyright (c) 2018 David Ahern <dsa@cumulusnetworks.com>
 *
 * This software is licensed under the GNU General License Version 2,
 * June 1991 as shown in the file COPYING in the top-level directory of this
 * source tree.
 *
 * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
 * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
 * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
 * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE
 * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME
 * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
 */

#include <linux/bitmap.h>
#include <linux/in6.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/rhashtable.h>
#include <linux/spinlock_types.h>
#include <linux/types.h>
#include <net/fib_notifier.h>
#include <net/inet_dscp.h>
#include <net/ip_fib.h>
#include <net/ip6_fib.h>
#include <net/fib_rules.h>
#include <net/net_namespace.h>
#include <net/nexthop.h>
#include <linux/debugfs.h>

#include "netdevsim.h"

struct nsim_fib_entry {
	u64 max;
	atomic64_t num;
};

struct nsim_per_fib_data {
	struct nsim_fib_entry fib;
	struct nsim_fib_entry rules;
};

struct nsim_fib_data {
	struct notifier_block fib_nb;
	struct nsim_per_fib_data ipv4;
	struct nsim_per_fib_data ipv6;
	struct nsim_fib_entry nexthops;
	struct rhashtable fib_rt_ht;
	struct list_head fib_rt_list;
	struct mutex fib_lock; /* Protects FIB HT and list */
	struct notifier_block nexthop_nb;
	struct rhashtable nexthop_ht;
	struct devlink *devlink;
	struct work_struct fib_event_work;
	struct work_struct fib_flush_work;
	struct list_head fib_event_queue;
	spinlock_t fib_event_queue_lock; /* Protects fib event queue list */
	struct mutex nh_lock; /* Protects NH HT */
	struct dentry *ddir;
	bool fail_route_offload;
	bool fail_res_nexthop_group_replace;
	bool fail_nexthop_bucket_replace;
	bool fail_route_delete;
};

struct nsim_fib_rt_key {
	unsigned char addr[sizeof(struct in6_addr)];
	unsigned char prefix_len;
	int family;
	u32 tb_id;
};

struct nsim_fib_rt {
	struct nsim_fib_rt_key key;
	struct rhash_head ht_node;
	struct list_head list;	/* Member of fib_rt_list */
};

struct nsim_fib4_rt {
	struct nsim_fib_rt common;
	struct fib_info *fi;
	dscp_t dscp;
	u8 type;
};

struct nsim_fib6_rt {
	struct nsim_fib_rt common;
	struct list_head nh_list;
	unsigned int nhs;
};

struct nsim_fib6_rt_nh {
	struct list_head list;	/* Member of nh_list */
	struct fib6_info *rt;
};

struct nsim_fib6_event {
	struct fib6_info **rt_arr;
	unsigned int nrt6;
};

struct nsim_fib_event {
	struct list_head list; /* node in fib queue */
	union {
		struct fib_entry_notifier_info fen_info;
		struct nsim_fib6_event fib6_event;
	};
	struct nsim_fib_data *data;
	unsigned long event;
	int family;
};

static const struct rhashtable_params nsim_fib_rt_ht_params = {
	.key_offset = offsetof(struct nsim_fib_rt, key),
	.head_offset = offsetof(struct nsim_fib_rt, ht_node),
	.key_len = sizeof(struct nsim_fib_rt_key),
	.automatic_shrinking = true,
};

struct nsim_nexthop {
	struct rhash_head ht_node;
	u64 occ;
	u32 id;
	bool is_resilient;
};

static const struct rhashtable_params nsim_nexthop_ht_params = {
	.key_offset = offsetof(struct nsim_nexthop, id),
	.head_offset = offsetof(struct nsim_nexthop, ht_node),
	.key_len = sizeof(u32),
	.automatic_shrinking = true,
};

u64 nsim_fib_get_val(struct nsim_fib_data *fib_data,
		     enum nsim_resource_id res_id, bool max)
{
	struct nsim_fib_entry *entry;

	switch (res_id) {
	case NSIM_RESOURCE_IPV4_FIB:
		entry = &fib_data->ipv4.fib;
		break;
	case NSIM_RESOURCE_IPV4_FIB_RULES:
		entry = &fib_data->ipv4.rules;
		break;
	case NSIM_RESOURCE_IPV6_FIB:
		entry = &fib_data->ipv6.fib;
		break;
	case NSIM_RESOURCE_IPV6_FIB_RULES:
		entry = &fib_data->ipv6.rules;
		break;
	case NSIM_RESOURCE_NEXTHOPS:
		entry = &fib_data->nexthops;
		break;
	default:
		return 0;
	}

	return max ? entry->max : atomic64_read(&entry->num);
}

static void nsim_fib_set_max(struct nsim_fib_data *fib_data,
			     enum nsim_resource_id res_id, u64 val)
{
	struct nsim_fib_entry *entry;

	switch (res_id) {
	case NSIM_RESOURCE_IPV4_FIB:
		entry = &fib_data->ipv4.fib;
		break;
	case NSIM_RESOURCE_IPV4_FIB_RULES:
		entry = &fib_data->ipv4.rules;
		break;
	case NSIM_RESOURCE_IPV6_FIB:
		entry = &fib_data->ipv6.fib;
		break;
	case NSIM_RESOURCE_IPV6_FIB_RULES:
		entry = &fib_data->ipv6.rules;
		break;
	case NSIM_RESOURCE_NEXTHOPS:
		entry = &fib_data->nexthops;
		break;
	default:
		WARN_ON(1);
		return;
	}
	entry->max = val;
}

static int nsim_fib_rule_account(struct nsim_fib_entry *entry, bool add,
				 struct netlink_ext_ack *extack)
{
	int err = 0;

	if (add) {
		if (!atomic64_add_unless(&entry->num, 1, entry->max)) {
			err = -ENOSPC;
			NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib rule entries");
		}
	} else {
		atomic64_dec_if_positive(&entry->num);
	}

	return err;
}

static int nsim_fib_rule_event(struct nsim_fib_data *data,
			       struct fib_notifier_info *info, bool add)
{
	struct netlink_ext_ack *extack = info->extack;
	int err = 0;

	switch (info->family) {
	case AF_INET:
		err = nsim_fib_rule_account(&data->ipv4.rules, add, extack);
		break;
	case AF_INET6:
		err = nsim_fib_rule_account(&data->ipv6.rules, add, extack);
		break;
	}

	return err;
}

static int nsim_fib_account(struct nsim_fib_entry *entry, bool add)
{
	int err = 0;

	if (add) {
		if (!atomic64_add_unless(&entry->num, 1, entry->max))
			err = -ENOSPC;
	} else {
		atomic64_dec_if_positive(&entry->num);
	}

	return err;
}

static void nsim_fib_rt_init(struct nsim_fib_data *data,
			     struct nsim_fib_rt *fib_rt, const void *addr,
			     size_t addr_len, unsigned int prefix_len,
			     int family, u32 tb_id)
{
	memcpy(fib_rt->key.addr, addr, addr_len);
	fib_rt->key.prefix_len = prefix_len;
	fib_rt->key.family = family;
	fib_rt->key.tb_id = tb_id;
	list_add(&fib_rt->list, &data->fib_rt_list);
}

static void nsim_fib_rt_fini(struct nsim_fib_rt *fib_rt)
{
	list_del(&fib_rt->list);
}

static struct nsim_fib_rt *nsim_fib_rt_lookup(struct rhashtable *fib_rt_ht,
					      const void *addr, size_t addr_len,
					      unsigned int prefix_len,
					      int family, u32 tb_id)
{
	struct nsim_fib_rt_key key;

	memset(&key, 0, sizeof(key));
	memcpy(key.addr, addr, addr_len);
	key.prefix_len = prefix_len;
	key.family = family;
	key.tb_id = tb_id;

	return rhashtable_lookup_fast(fib_rt_ht, &key, nsim_fib_rt_ht_params);
}

static struct nsim_fib4_rt *
nsim_fib4_rt_create(struct nsim_fib_data *data,
		    struct fib_entry_notifier_info *fen_info)
{
	struct nsim_fib4_rt *fib4_rt;

	fib4_rt = kzalloc(sizeof(*fib4_rt), GFP_KERNEL);
	if (!fib4_rt)
		return NULL;

	nsim_fib_rt_init(data, &fib4_rt->common, &fen_info->dst, sizeof(u32),
			 fen_info->dst_len, AF_INET, fen_info->tb_id);

	fib4_rt->fi = fen_info->fi;
	fib_info_hold(fib4_rt->fi);
	fib4_rt->dscp = fen_info->dscp;
	fib4_rt->type = fen_info->type;

	return fib4_rt;
}

static void nsim_fib4_rt_destroy(struct nsim_fib4_rt *fib4_rt)
{
	fib_info_put(fib4_rt->fi);
	nsim_fib_rt_fini(&fib4_rt->common);
	kfree(fib4_rt);
}

static struct nsim_fib4_rt *
nsim_fib4_rt_lookup(struct rhashtable *fib_rt_ht,
		    const struct fib_entry_notifier_info *fen_info)
{
	struct nsim_fib_rt *fib_rt;

	fib_rt = nsim_fib_rt_lookup(fib_rt_ht, &fen_info->dst, sizeof(u32),
				    fen_info->dst_len, AF_INET,
				    fen_info->tb_id);
	if (!fib_rt)
		return NULL;

	return container_of(fib_rt, struct nsim_fib4_rt, common);
}

static void
nsim_fib4_rt_offload_failed_flag_set(struct net *net,
				     struct fib_entry_notifier_info *fen_info)
{
	u32 *p_dst = (u32 *)&fen_info->dst;
	struct fib_rt_info fri;

	fri.fi = fen_info->fi;
	fri.tb_id = fen_info->tb_id;
	fri.dst = cpu_to_be32(*p_dst);
	fri.dst_len = fen_info->dst_len;
	fri.dscp = fen_info->dscp;
	fri.type = fen_info->type;
	fri.offload = false;
	fri.trap = false;
	fri.offload_failed = true;
	fib_alias_hw_flags_set(net, &fri);
}

static void nsim_fib4_rt_hw_flags_set(struct net *net,
				      const struct nsim_fib4_rt *fib4_rt,
				      bool trap)
{
	u32 *p_dst = (u32 *) fib4_rt->common.key.addr;
	int dst_len = fib4_rt->common.key.prefix_len;
	struct fib_rt_info fri;

	fri.fi = fib4_rt->fi;
	fri.tb_id = fib4_rt->common.key.tb_id;
	fri.dst = cpu_to_be32(*p_dst);
	fri.dst_len = dst_len;
	fri.dscp = fib4_rt->dscp;
	fri.type = fib4_rt->type;
	fri.offload = false;
	fri.trap = trap;
	fri.offload_failed = false;
	fib_alias_hw_flags_set(net, &fri);
}

static int nsim_fib4_rt_add(struct nsim_fib_data *data,
			    struct nsim_fib4_rt *fib4_rt)
{
	struct net *net = devlink_net(data->devlink);
	int err;

	err = rhashtable_insert_fast(&data->fib_rt_ht,
				     &fib4_rt->common.ht_node,
				     nsim_fib_rt_ht_params);
	if (err)
		goto err_fib_dismiss;

	/* Simulate hardware programming latency. */
	msleep(1);
	nsim_fib4_rt_hw_flags_set(net, fib4_rt, true);

	return 0;

err_fib_dismiss:
	/* Drop the accounting that was increased from the notification
	 * context when FIB_EVENT_ENTRY_REPLACE was triggered.
	 */
	nsim_fib_account(&data->ipv4.fib, false);
	return err;
}

static int nsim_fib4_rt_replace(struct nsim_fib_data *data,
				struct nsim_fib4_rt *fib4_rt,
				struct nsim_fib4_rt *fib4_rt_old)
{
	struct net *net = devlink_net(data->devlink);
	int err;

	/* We are replacing a route, so need to remove the accounting which
	 * was increased when FIB_EVENT_ENTRY_REPLACE was triggered.
	 */
	err = nsim_fib_account(&data->ipv4.fib, false);
	if (err)
		return err;
	err = rhashtable_replace_fast(&data->fib_rt_ht,
				      &fib4_rt_old->common.ht_node,
				      &fib4_rt->common.ht_node,
				      nsim_fib_rt_ht_params);
	if (err)
		return err;

	msleep(1);
	nsim_fib4_rt_hw_flags_set(net, fib4_rt, true);

	nsim_fib4_rt_hw_flags_set(net, fib4_rt_old, false);
	nsim_fib4_rt_destroy(fib4_rt_old);

	return 0;
}

static int nsim_fib4_rt_insert(struct nsim_fib_data *data,
			       struct fib_entry_notifier_info *fen_info)
{
	struct nsim_fib4_rt *fib4_rt, *fib4_rt_old;
	int err;

	if (data->fail_route_offload) {
		/* For testing purposes, user set debugfs fail_route_offload
		 * value to true. Simulate hardware programming latency and then
		 * fail.
		 */
		msleep(1);
		return -EINVAL;
	}

	fib4_rt = nsim_fib4_rt_create(data, fen_info);
	if (!fib4_rt)
		return -ENOMEM;

	fib4_rt_old = nsim_fib4_rt_lookup(&data->fib_rt_ht, fen_info);
	if (!fib4_rt_old)
		err = nsim_fib4_rt_add(data, fib4_rt);
	else
		err = nsim_fib4_rt_replace(data, fib4_rt, fib4_rt_old);

	if (err)
		nsim_fib4_rt_destroy(fib4_rt);

	return err;
}

static void nsim_fib4_rt_remove(struct nsim_fib_data *data,
				const struct fib_entry_notifier_info *fen_info)
{
	struct nsim_fib4_rt *fib4_rt;

	fib4_rt = nsim_fib4_rt_lookup(&data->fib_rt_ht, fen_info);
	if (!fib4_rt)
		return;

	rhashtable_remove_fast(&data->fib_rt_ht, &fib4_rt->common.ht_node,
			       nsim_fib_rt_ht_params);
	nsim_fib4_rt_destroy(fib4_rt);
}

static int nsim_fib4_event(struct nsim_fib_data *data,
			   struct fib_entry_notifier_info *fen_info,
			   unsigned long event)
{
	int err = 0;

	switch (event) {
	case FIB_EVENT_ENTRY_REPLACE:
		err = nsim_fib4_rt_insert(data, fen_info);
		if (err) {
			struct net *net = devlink_net(data->devlink);

			nsim_fib4_rt_offload_failed_flag_set(net, fen_info);
		}
		break;
	case FIB_EVENT_ENTRY_DEL:
		nsim_fib4_rt_remove(data, fen_info);
		break;
	default:
		break;
	}

	return err;
}

static struct nsim_fib6_rt_nh *
nsim_fib6_rt_nh_find(const struct nsim_fib6_rt *fib6_rt,
		     const struct fib6_info *rt)
{
	struct nsim_fib6_rt_nh *fib6_rt_nh;

	list_for_each_entry(fib6_rt_nh, &fib6_rt->nh_list, list) {
		if (fib6_rt_nh->rt == rt)
			return fib6_rt_nh;
	}

	return NULL;
}

static int nsim_fib6_rt_nh_add(struct nsim_fib6_rt *fib6_rt,
			       struct fib6_info *rt)
{
	struct nsim_fib6_rt_nh *fib6_rt_nh;

	fib6_rt_nh = kzalloc(sizeof(*fib6_rt_nh), GFP_KERNEL);
	if (!fib6_rt_nh)
		return -ENOMEM;

	fib6_info_hold(rt);
	fib6_rt_nh->rt = rt;
	list_add_tail(&fib6_rt_nh->list, &fib6_rt->nh_list);
	fib6_rt->nhs++;

	return 0;
}

#if IS_ENABLED(CONFIG_IPV6)
static void nsim_rt6_release(struct fib6_info *rt)
{
	fib6_info_release(rt);
}
#else
static void nsim_rt6_release(struct fib6_info *rt)
{
}
#endif

static void nsim_fib6_rt_nh_del(struct nsim_fib6_rt *fib6_rt,
				const struct fib6_info *rt)
{
	struct nsim_fib6_rt_nh *fib6_rt_nh;

	fib6_rt_nh = nsim_fib6_rt_nh_find(fib6_rt, rt);
	if (!fib6_rt_nh)
		return;

	fib6_rt->nhs--;
	list_del(&fib6_rt_nh->list);
	nsim_rt6_release(fib6_rt_nh->rt);
	kfree(fib6_rt_nh);
}

static struct nsim_fib6_rt *
nsim_fib6_rt_create(struct nsim_fib_data *data,
		    struct fib6_info **rt_arr, unsigned int nrt6)
{
	struct fib6_info *rt = rt_arr[0];
	struct nsim_fib6_rt *fib6_rt;
	int i = 0;
	int err;

	fib6_rt = kzalloc(sizeof(*fib6_rt), GFP_KERNEL);
	if (!fib6_rt)
		return ERR_PTR(-ENOMEM);

	nsim_fib_rt_init(data, &fib6_rt->common, &rt->fib6_dst.addr,
			 sizeof(rt->fib6_dst.addr), rt->fib6_dst.plen, AF_INET6,
			 rt->fib6_table->tb6_id);

	/* We consider a multipath IPv6 route as one entry, but it can be made
	 * up from several fib6_info structs (one for each nexthop), so we
	 * add them all to the same list under the entry.
	 */
	INIT_LIST_HEAD(&fib6_rt->nh_list);

	for (i = 0; i < nrt6; i++) {
		err = nsim_fib6_rt_nh_add(fib6_rt, rt_arr[i]);
		if (err)
			goto err_fib6_rt_nh_del;
	}

	return fib6_rt;

err_fib6_rt_nh_del:
	for (i--; i >= 0; i--) {
		nsim_fib6_rt_nh_del(fib6_rt, rt_arr[i]);
	}
	nsim_fib_rt_fini(&fib6_rt->common);
	kfree(fib6_rt);
	return ERR_PTR(err);
}

static void nsim_fib6_rt_destroy(struct nsim_fib6_rt *fib6_rt)
{
	struct nsim_fib6_rt_nh *iter, *tmp;

	list_for_each_entry_safe(iter, tmp, &fib6_rt->nh_list, list)
		nsim_fib6_rt_nh_del(fib6_rt, iter->rt);
	WARN_ON_ONCE(!list_empty(&fib6_rt->nh_list));
	nsim_fib_rt_fini(&fib6_rt->common);
	kfree(fib6_rt);
}

static struct nsim_fib6_rt *
nsim_fib6_rt_lookup(struct rhashtable *fib_rt_ht, const struct fib6_info *rt)
{
	struct nsim_fib_rt *fib_rt;

	fib_rt = nsim_fib_rt_lookup(fib_rt_ht, &rt->fib6_dst.addr,
				    sizeof(rt->fib6_dst.addr),
				    rt->fib6_dst.plen, AF_INET6,
				    rt->fib6_table->tb6_id);
	if (!fib_rt)
		return NULL;

	return container_of(fib_rt, struct nsim_fib6_rt, common);
}

static int nsim_fib6_rt_append(struct nsim_fib_data *data,
			       struct nsim_fib6_event *fib6_event)
{
	struct fib6_info *rt = fib6_event->rt_arr[0];
	struct nsim_fib6_rt *fib6_rt;
	int i, err;

	if (data->fail_route_offload) {
		/* For testing purposes, user set debugfs fail_route_offload
		 * value to true. Simulate hardware programming latency and then
		 * fail.
		 */
		msleep(1);
		return -EINVAL;
	}

	fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt);
	if (!fib6_rt)
		return -EINVAL;

	for (i = 0; i < fib6_event->nrt6; i++) {
		err = nsim_fib6_rt_nh_add(fib6_rt, fib6_event->rt_arr[i]);
		if (err)
			goto err_fib6_rt_nh_del;

		WRITE_ONCE(fib6_event->rt_arr[i]->trap, true);
	}

	return 0;

err_fib6_rt_nh_del:
	for (i--; i >= 0; i--) {
		WRITE_ONCE(fib6_event->rt_arr[i]->trap, false);
		nsim_fib6_rt_nh_del(fib6_rt, fib6_event->rt_arr[i]);
	}
	return err;
}

#if IS_ENABLED(CONFIG_IPV6)
static void nsim_fib6_rt_offload_failed_flag_set(struct nsim_fib_data *data,
						 struct fib6_info **rt_arr,
						 unsigned int nrt6)

{
	struct net *net = devlink_net(data->devlink);
	int i;

	for (i = 0; i < nrt6; i++)
		fib6_info_hw_flags_set(net, rt_arr[i], false, false, true);
}
#else
static void nsim_fib6_rt_offload_failed_flag_set(struct nsim_fib_data *data,
						 struct fib6_info **rt_arr,
						 unsigned int nrt6)
{
}
#endif

#if IS_ENABLED(CONFIG_IPV6)
static void nsim_fib6_rt_hw_flags_set(struct nsim_fib_data *data,
				      const struct nsim_fib6_rt *fib6_rt,
				      bool trap)
{
	struct net *net = devlink_net(data->devlink);
	struct nsim_fib6_rt_nh *fib6_rt_nh;

	list_for_each_entry(fib6_rt_nh, &fib6_rt->nh_list, list)
		fib6_info_hw_flags_set(net, fib6_rt_nh->rt, false, trap, false);
}
#else
static void nsim_fib6_rt_hw_flags_set(struct nsim_fib_data *data,
				      const struct nsim_fib6_rt *fib6_rt,
				      bool trap)
{
}
#endif

static int nsim_fib6_rt_add(struct nsim_fib_data *data,
			    struct nsim_fib6_rt *fib6_rt)
{
	int err;

	err = rhashtable_insert_fast(&data->fib_rt_ht,
				     &fib6_rt->common.ht_node,
				     nsim_fib_rt_ht_params);

	if (err)
		goto err_fib_dismiss;

	msleep(1);
	nsim_fib6_rt_hw_flags_set(data, fib6_rt, true);

	return 0;

err_fib_dismiss:
	/* Drop the accounting that was increased from the notification
	 * context when FIB_EVENT_ENTRY_REPLACE was triggered.
	 */
	nsim_fib_account(&data->ipv6.fib, false);
	return err;
}

static int nsim_fib6_rt_replace(struct nsim_fib_data *data,
				struct nsim_fib6_rt *fib6_rt,
				struct nsim_fib6_rt *fib6_rt_old)
{
	int err;

	/* We are replacing a route, so need to remove the accounting which
	 * was increased when FIB_EVENT_ENTRY_REPLACE was triggered.
	 */
	err = nsim_fib_account(&data->ipv6.fib, false);
	if (err)
		return err;

	err = rhashtable_replace_fast(&data->fib_rt_ht,
				      &fib6_rt_old->common.ht_node,
				      &fib6_rt->common.ht_node,
				      nsim_fib_rt_ht_params);

	if (err)
		return err;

	msleep(1);
	nsim_fib6_rt_hw_flags_set(data, fib6_rt, true);

	nsim_fib6_rt_hw_flags_set(data, fib6_rt_old, false);
	nsim_fib6_rt_destroy(fib6_rt_old);

	return 0;
}

static int nsim_fib6_rt_insert(struct nsim_fib_data *data,
			       struct nsim_fib6_event *fib6_event)
{
	struct fib6_info *rt = fib6_event->rt_arr[0];
	struct nsim_fib6_rt *fib6_rt, *fib6_rt_old;
	int err;

	if (data->fail_route_offload) {
		/* For testing purposes, user set debugfs fail_route_offload
		 * value to true. Simulate hardware programming latency and then
		 * fail.
		 */
		msleep(1);
		return -EINVAL;
	}

	fib6_rt = nsim_fib6_rt_create(data, fib6_event->rt_arr,
				      fib6_event->nrt6);
	if (IS_ERR(fib6_rt))
		return PTR_ERR(fib6_rt);

	fib6_rt_old = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt);
	if (!fib6_rt_old)
		err = nsim_fib6_rt_add(data, fib6_rt);
	else
		err = nsim_fib6_rt_replace(data, fib6_rt, fib6_rt_old);

	if (err)
		nsim_fib6_rt_destroy(fib6_rt);

	return err;
}

static void nsim_fib6_rt_remove(struct nsim_fib_data *data,
				struct nsim_fib6_event *fib6_event)
{
	struct fib6_info *rt = fib6_event->rt_arr[0];
	struct nsim_fib6_rt *fib6_rt;
	int i;

	/* Multipath routes are first added to the FIB trie and only then
	 * notified. If we vetoed the addition, we will get a delete
	 * notification for a route we do not have. Therefore, do not warn if
	 * route was not found.
	 */
	fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt);
	if (!fib6_rt)
		return;

	/* If not all the nexthops are deleted, then only reduce the nexthop
	 * group.
	 */
	if (fib6_event->nrt6 != fib6_rt->nhs) {
		for (i = 0; i < fib6_event->nrt6; i++)
			nsim_fib6_rt_nh_del(fib6_rt, fib6_event->rt_arr[i]);
		return;
	}

	rhashtable_remove_fast(&data->fib_rt_ht, &fib6_rt->common.ht_node,
			       nsim_fib_rt_ht_params);
	nsim_fib6_rt_destroy(fib6_rt);
}

static int nsim_fib6_event_init(struct nsim_fib6_event *fib6_event,
				struct fib6_entry_notifier_info *fen6_info)
{
	struct fib6_info *rt = fen6_info->rt;
	struct fib6_info **rt_arr;
	struct fib6_info *iter;
	unsigned int nrt6;
	int i = 0;

	nrt6 = fen6_info->nsiblings + 1;

	rt_arr = kcalloc(nrt6, sizeof(struct fib6_info *), GFP_ATOMIC);
	if (!rt_arr)
		return -ENOMEM;

	fib6_event->rt_arr = rt_arr;
	fib6_event->nrt6 = nrt6;

	rt_arr[0] = rt;
	fib6_info_hold(rt);

	if (!fen6_info->nsiblings)
		return 0;

	list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) {
		if (i == fen6_info->nsiblings)
			break;

		rt_arr[i + 1] = iter;
		fib6_info_hold(iter);
		i++;
	}
	WARN_ON_ONCE(i != fen6_info->nsiblings);

	return 0;
}

static void nsim_fib6_event_fini(struct nsim_fib6_event *fib6_event)
{
	int i;

	for (i = 0; i < fib6_event->nrt6; i++)
		nsim_rt6_release(fib6_event->rt_arr[i]);
	kfree(fib6_event->rt_arr);
}

static int nsim_fib6_event(struct nsim_fib_data *data,
			   struct nsim_fib6_event *fib6_event,
			   unsigned long event)
{
	int err;

	if (fib6_event->rt_arr[0]->fib6_src.plen)
		return 0;

	switch (event) {
	case FIB_EVENT_ENTRY_REPLACE:
		err = nsim_fib6_rt_insert(data, fib6_event);
		if (err)
			goto err_rt_offload_failed_flag_set;
		break;
	case FIB_EVENT_ENTRY_APPEND:
		err = nsim_fib6_rt_append(data, fib6_event);
		if (err)
			goto err_rt_offload_failed_flag_set;
		break;
	case FIB_EVENT_ENTRY_DEL:
		nsim_fib6_rt_remove(data, fib6_event);
		break;
	default:
		break;
	}

	return 0;

err_rt_offload_failed_flag_set:
	nsim_fib6_rt_offload_failed_flag_set(data, fib6_event->rt_arr,
					     fib6_event->nrt6);
	return err;
}

static void nsim_fib_event(struct nsim_fib_event *fib_event)
{
	switch (fib_event->family) {
	case AF_INET:
		nsim_fib4_event(fib_event->data, &fib_event->fen_info,
				fib_event->event);
		fib_info_put(fib_event->fen_info.fi);
		break;
	case AF_INET6:
		nsim_fib6_event(fib_event->data, &fib_event->fib6_event,
				fib_event->event);
		nsim_fib6_event_fini(&fib_event->fib6_event);
		break;
	}
}

static int nsim_fib4_prepare_event(struct fib_notifier_info *info,
				   struct nsim_fib_event *fib_event,
				   unsigned long event)
{
	struct nsim_fib_data *data = fib_event->data;
	struct fib_entry_notifier_info *fen_info;
	struct netlink_ext_ack *extack;
	int err = 0;

	fen_info = container_of(info, struct fib_entry_notifier_info,
				info);
	fib_event->fen_info = *fen_info;
	extack = info->extack;

	switch (event) {
	case FIB_EVENT_ENTRY_REPLACE:
		err = nsim_fib_account(&data->ipv4.fib, true);
		if (err) {
			NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib entries");
			return err;
		}
		break;
	case FIB_EVENT_ENTRY_DEL:
		if (data->fail_route_delete) {
			NL_SET_ERR_MSG_MOD(extack, "Failed to process route deletion");
			return -EINVAL;
		}
		nsim_fib_account(&data->ipv4.fib, false);
		break;
	}

	/* Take reference on fib_info to prevent it from being
	 * freed while event is queued. Release it afterwards.
	 */
	fib_info_hold(fib_event->fen_info.fi);

	return 0;
}

static int nsim_fib6_prepare_event(struct fib_notifier_info *info,
				   struct nsim_fib_event *fib_event,
				   unsigned long event)
{
	struct nsim_fib_data *data = fib_event->data;
	struct fib6_entry_notifier_info *fen6_info;
	struct netlink_ext_ack *extack;
	int err = 0;

	fen6_info = container_of(info, struct fib6_entry_notifier_info,
				 info);

	err = nsim_fib6_event_init(&fib_event->fib6_event, fen6_info);
	if (err)
		return err;

	extack = info->extack;
	switch (event) {
	case FIB_EVENT_ENTRY_REPLACE:
		err = nsim_fib_account(&data->ipv6.fib, true);
		if (err) {
			NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib entries");
			goto err_fib6_event_fini;
		}
		break;
	case FIB_EVENT_ENTRY_DEL:
		if (data->fail_route_delete) {
			err = -EINVAL;
			NL_SET_ERR_MSG_MOD(extack, "Failed to process route deletion");
			goto err_fib6_event_fini;
		}
		nsim_fib_account(&data->ipv6.fib, false);
		break;
	}

	return 0;

err_fib6_event_fini:
	nsim_fib6_event_fini(&fib_event->fib6_event);
	return err;
}

static int nsim_fib_event_schedule_work(struct nsim_fib_data *data,
					struct fib_notifier_info *info,
					unsigned long event)
{
	struct nsim_fib_event *fib_event;
	int err;

	if (info->family != AF_INET && info->family != AF_INET6)
		/* netdevsim does not support 'RTNL_FAMILY_IP6MR' and
		 * 'RTNL_FAMILY_IPMR' and should ignore them.
		 */
		return NOTIFY_DONE;

	fib_event = kzalloc(sizeof(*fib_event), GFP_ATOMIC);
	if (!fib_event)
		goto err_fib_event_alloc;

	fib_event->data = data;
	fib_event->event = event;
	fib_event->family = info->family;

	switch (info->family) {
	case AF_INET:
		err = nsim_fib4_prepare_event(info, fib_event, event);
		break;
	case AF_INET6:
		err = nsim_fib6_prepare_event(info, fib_event, event);
		break;
	}

	if (err)
		goto err_fib_prepare_event;

	/* Enqueue the event and trigger the work */
	spin_lock_bh(&data->fib_event_queue_lock);
	list_add_tail(&fib_event->list, &data->fib_event_queue);
	spin_unlock_bh(&data->fib_event_queue_lock);
	schedule_work(&data->fib_event_work);

	return NOTIFY_DONE;

err_fib_prepare_event:
	kfree(fib_event);
err_fib_event_alloc:
	if (event == FIB_EVENT_ENTRY_DEL)
		schedule_work(&data->fib_flush_work);
	return NOTIFY_BAD;
}

static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event,
			     void *ptr)
{
	struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data,
						  fib_nb);
	struct fib_notifier_info *info = ptr;
	int err;

	switch (event) {
	case FIB_EVENT_RULE_ADD:
	case FIB_EVENT_RULE_DEL:
		err = nsim_fib_rule_event(data, info,
					  event == FIB_EVENT_RULE_ADD);
		return notifier_from_errno(err);
	case FIB_EVENT_ENTRY_REPLACE:
	case FIB_EVENT_ENTRY_APPEND:
	case FIB_EVENT_ENTRY_DEL:
		return nsim_fib_event_schedule_work(data, info, event);
	}

	return NOTIFY_DONE;
}

static void nsim_fib4_rt_free(struct nsim_fib_rt *fib_rt,
			      struct nsim_fib_data *data)
{
	struct devlink *devlink = data->devlink;
	struct nsim_fib4_rt *fib4_rt;

	fib4_rt = container_of(fib_rt, struct nsim_fib4_rt, common);
	nsim_fib4_rt_hw_flags_set(devlink_net(devlink), fib4_rt, false);
	nsim_fib_account(&data->ipv4.fib, false);
	nsim_fib4_rt_destroy(fib4_rt);
}

static void nsim_fib6_rt_free(struct nsim_fib_rt *fib_rt,
			      struct nsim_fib_data *data)
{
	struct nsim_fib6_rt *fib6_rt;

	fib6_rt = container_of(fib_rt, struct nsim_fib6_rt, common);
	nsim_fib6_rt_hw_flags_set(data, fib6_rt, false);
	nsim_fib_account(&data->ipv6.fib, false);
	nsim_fib6_rt_destroy(fib6_rt);
}

static void nsim_fib_rt_free(void *ptr, void *arg)
{
	struct nsim_fib_rt *fib_rt = ptr;
	struct nsim_fib_data *data = arg;

	switch (fib_rt->key.family) {
	case AF_INET:
		nsim_fib4_rt_free(fib_rt, data);
		break;
	case AF_INET6:
		nsim_fib6_rt_free(fib_rt, data);
		break;
	default:
		WARN_ON_ONCE(1);
	}
}

/* inconsistent dump, trying again */
static void nsim_fib_dump_inconsistent(struct notifier_block *nb)
{
	struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data,
						  fib_nb);
	struct nsim_fib_rt *fib_rt, *fib_rt_tmp;

	/* Flush the work to make sure there is no race with notifications. */
	flush_work(&data->fib_event_work);

	/* The notifier block is still not registered, so we do not need to
	 * take any locks here.
	 */
	list_for_each_entry_safe(fib_rt, fib_rt_tmp, &data->fib_rt_list, list) {
		rhashtable_remove_fast(&data->fib_rt_ht, &fib_rt->ht_node,
				       nsim_fib_rt_ht_params);
		nsim_fib_rt_free(fib_rt, data);
	}

	atomic64_set(&data->ipv4.rules.num, 0ULL);
	atomic64_set(&data->ipv6.rules.num, 0ULL);
}

static struct nsim_nexthop *nsim_nexthop_create(struct nsim_fib_data *data,
						struct nh_notifier_info *info)
{
	struct nsim_nexthop *nexthop;
	u64 occ = 0;
	int i;

	nexthop = kzalloc(sizeof(*nexthop), GFP_KERNEL);
	if (!nexthop)
		return ERR_PTR(-ENOMEM);

	nexthop->id = info->id;

	/* Determine the number of nexthop entries the new nexthop will
	 * occupy.
	 */

	switch (info->type) {
	case NH_NOTIFIER_INFO_TYPE_SINGLE:
		occ = 1;
		break;
	case NH_NOTIFIER_INFO_TYPE_GRP:
		for (i = 0; i < info->nh_grp->num_nh; i++)
			occ += info->nh_grp->nh_entries[i].weight;
		break;
	case NH_NOTIFIER_INFO_TYPE_RES_TABLE:
		occ = info->nh_res_table->num_nh_buckets;
		nexthop->is_resilient = true;
		break;
	default:
		NL_SET_ERR_MSG_MOD(info->extack, "Unsupported nexthop type");
		kfree(nexthop);
		return ERR_PTR(-EOPNOTSUPP);
	}

	nexthop->occ = occ;
	return nexthop;
}

static void nsim_nexthop_destroy(struct nsim_nexthop *nexthop)
{
	kfree(nexthop);
}

static int nsim_nexthop_account(struct nsim_fib_data *data, u64 occ,
				bool add, struct netlink_ext_ack *extack)
{
	int i, err = 0;

	if (add) {
		for (i = 0; i < occ; i++)
			if (!atomic64_add_unless(&data->nexthops.num, 1,
						 data->nexthops.max)) {
				err = -ENOSPC;
				NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported nexthops");
				goto err_num_decrease;
			}
	} else {
		if (WARN_ON(occ > atomic64_read(&data->nexthops.num)))
			return -EINVAL;
		atomic64_sub(occ, &data->nexthops.num);
	}

	return err;

err_num_decrease:
	atomic64_sub(i, &data->nexthops.num);
	return err;

}

static void nsim_nexthop_hw_flags_set(struct net *net,
				      const struct nsim_nexthop *nexthop,
				      bool trap)
{
	int i;

	nexthop_set_hw_flags(net, nexthop->id, false, trap);

	if (!nexthop->is_resilient)
		return;

	for (i = 0; i < nexthop->occ; i++)
		nexthop_bucket_set_hw_flags(net, nexthop->id, i, false, trap);
}

static int nsim_nexthop_add(struct nsim_fib_data *data,
			    struct nsim_nexthop *nexthop,
			    struct netlink_ext_ack *extack)
{
	struct net *net = devlink_net(data->devlink);
	int err;

	err = nsim_nexthop_account(data, nexthop->occ, true, extack);
	if (err)
		return err;

	err = rhashtable_insert_fast(&data->nexthop_ht, &nexthop->ht_node,
				     nsim_nexthop_ht_params);
	if (err) {
		NL_SET_ERR_MSG_MOD(extack, "Failed to insert nexthop");
		goto err_nexthop_dismiss;
	}

	nsim_nexthop_hw_flags_set(net, nexthop, true);

	return 0;

err_nexthop_dismiss:
	nsim_nexthop_account(data, nexthop->occ, false, extack);
	return err;
}

static int nsim_nexthop_replace(struct nsim_fib_data *data,
				struct nsim_nexthop *nexthop,
				struct nsim_nexthop *nexthop_old,
				struct netlink_ext_ack *extack)
{
	struct net *net = devlink_net(data->devlink);
	int err;

	err = nsim_nexthop_account(data, nexthop->occ, true, extack);
	if (err)
		return err;

	err = rhashtable_replace_fast(&data->nexthop_ht,
				      &nexthop_old->ht_node, &nexthop->ht_node,
				      nsim_nexthop_ht_params);
	if (err) {
		NL_SET_ERR_MSG_MOD(extack, "Failed to replace nexthop");
		goto err_nexthop_dismiss;
	}

	nsim_nexthop_hw_flags_set(net, nexthop, true);
	nsim_nexthop_account(data, nexthop_old->occ, false, extack);
	nsim_nexthop_destroy(nexthop_old);

	return 0;

err_nexthop_dismiss:
	nsim_nexthop_account(data, nexthop->occ, false, extack);
	return err;
}

static int nsim_nexthop_insert(struct nsim_fib_data *data,
			       struct nh_notifier_info *info)
{
	struct nsim_nexthop *nexthop, *nexthop_old;
	int err;

	nexthop = nsim_nexthop_create(data, info);
	if (IS_ERR(nexthop))
		return PTR_ERR(nexthop);

	nexthop_old = rhashtable_lookup_fast(&data->nexthop_ht, &info->id,
					     nsim_nexthop_ht_params);
	if (!nexthop_old)
		err = nsim_nexthop_add(data, nexthop, info->extack);
	else
		err = nsim_nexthop_replace(data, nexthop, nexthop_old,
					   info->extack);

	if (err)
		nsim_nexthop_destroy(nexthop);

	return err;
}

static void nsim_nexthop_remove(struct nsim_fib_data *data,
				struct nh_notifier_info *info)
{
	struct nsim_nexthop *nexthop;

	nexthop = rhashtable_lookup_fast(&data->nexthop_ht, &info->id,
					 nsim_nexthop_ht_params);
	if (!nexthop)
		return;

	rhashtable_remove_fast(&data->nexthop_ht, &nexthop->ht_node,
			       nsim_nexthop_ht_params);
	nsim_nexthop_account(data, nexthop->occ, false, info->extack);
	nsim_nexthop_destroy(nexthop);
}

static int nsim_nexthop_res_table_pre_replace(struct nsim_fib_data *data,
					      struct nh_notifier_info *info)
{
	if (data->fail_res_nexthop_group_replace) {
		NL_SET_ERR_MSG_MOD(info->extack, "Failed to replace a resilient nexthop group");
		return -EINVAL;
	}

	return 0;
}

static int nsim_nexthop_bucket_replace(struct nsim_fib_data *data,
				       struct nh_notifier_info *info)
{
	if (data->fail_nexthop_bucket_replace) {
		NL_SET_ERR_MSG_MOD(info->extack, "Failed to replace nexthop bucket");
		return -EINVAL;
	}

	nexthop_bucket_set_hw_flags(info->net, info->id,
				    info->nh_res_bucket->bucket_index,
				    false, true);

	return 0;
}

static int nsim_nexthop_event_nb(struct notifier_block *nb, unsigned long event,
				 void *ptr)
{
	struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data,
						  nexthop_nb);
	struct nh_notifier_info *info = ptr;
	int err = 0;

	mutex_lock(&data->nh_lock);
	switch (event) {
	case NEXTHOP_EVENT_REPLACE:
		err = nsim_nexthop_insert(data, info);
		break;
	case NEXTHOP_EVENT_DEL:
		nsim_nexthop_remove(data, info);
		break;
	case NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE:
		err = nsim_nexthop_res_table_pre_replace(data, info);
		break;
	case NEXTHOP_EVENT_BUCKET_REPLACE:
		err = nsim_nexthop_bucket_replace(data, info);
		break;
	default:
		break;
	}

	mutex_unlock(&data->nh_lock);
	return notifier_from_errno(err);
}

static void nsim_nexthop_free(void *ptr, void *arg)
{
	struct nsim_nexthop *nexthop = ptr;
	struct nsim_fib_data *data = arg;
	struct net *net;

	net = devlink_net(data->devlink);
	nsim_nexthop_hw_flags_set(net, nexthop, false);
	nsim_nexthop_account(data, nexthop->occ, false, NULL);
	nsim_nexthop_destroy(nexthop);
}

static ssize_t nsim_nexthop_bucket_activity_write(struct file *file,
						  const char __user *user_buf,
						  size_t size, loff_t *ppos)
{
	struct nsim_fib_data *data = file->private_data;
	struct net *net = devlink_net(data->devlink);
	struct nsim_nexthop *nexthop;
	unsigned long *activity;
	loff_t pos = *ppos;
	u16 bucket_index;
	char buf[128];
	int err = 0;
	u32 nhid;

	if (pos != 0)
		return -EINVAL;
	if (size > sizeof(buf))
		return -EINVAL;
	if (copy_from_user(buf, user_buf, size))
		return -EFAULT;
	if (sscanf(buf, "%u %hu", &nhid, &bucket_index) != 2)
		return -EINVAL;

	rtnl_lock();

	nexthop = rhashtable_lookup_fast(&data->nexthop_ht, &nhid,
					 nsim_nexthop_ht_params);
	if (!nexthop || !nexthop->is_resilient ||
	    bucket_index >= nexthop->occ) {
		err = -EINVAL;
		goto out;
	}

	activity = bitmap_zalloc(nexthop->occ, GFP_KERNEL);
	if (!activity) {
		err = -ENOMEM;
		goto out;
	}

	bitmap_set(activity, bucket_index, 1);
	nexthop_res_grp_activity_update(net, nhid, nexthop->occ, activity);
	bitmap_free(activity);

out:
	rtnl_unlock();

	*ppos = size;
	return err ?: size;
}

static const struct file_operations nsim_nexthop_bucket_activity_fops = {
	.open = simple_open,
	.write = nsim_nexthop_bucket_activity_write,
	.llseek = no_llseek,
	.owner = THIS_MODULE,
};

static u64 nsim_fib_ipv4_resource_occ_get(void *priv)
{
	struct nsim_fib_data *data = priv;

	return nsim_fib_get_val(data, NSIM_RESOURCE_IPV4_FIB, false);
}

static u64 nsim_fib_ipv4_rules_res_occ_get(void *priv)
{
	struct nsim_fib_data *data = priv;

	return nsim_fib_get_val(data, NSIM_RESOURCE_IPV4_FIB_RULES, false);
}

static u64 nsim_fib_ipv6_resource_occ_get(void *priv)
{
	struct nsim_fib_data *data = priv;

	return nsim_fib_get_val(data, NSIM_RESOURCE_IPV6_FIB, false);
}

static u64 nsim_fib_ipv6_rules_res_occ_get(void *priv)
{
	struct nsim_fib_data *data = priv;

	return nsim_fib_get_val(data, NSIM_RESOURCE_IPV6_FIB_RULES, false);
}

static u64 nsim_fib_nexthops_res_occ_get(void *priv)
{
	struct nsim_fib_data *data = priv;

	return nsim_fib_get_val(data, NSIM_RESOURCE_NEXTHOPS, false);
}

static void nsim_fib_set_max_all(struct nsim_fib_data *data,
				 struct devlink *devlink)
{
	static const enum nsim_resource_id res_ids[] = {
		NSIM_RESOURCE_IPV4_FIB, NSIM_RESOURCE_IPV4_FIB_RULES,
		NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES,
		NSIM_RESOURCE_NEXTHOPS,
	};
	int i;

	for (i = 0; i < ARRAY_SIZE(res_ids); i++) {
		int err;
		u64 val;

		err = devl_resource_size_get(devlink, res_ids[i], &val);
		if (err)
			val = (u64) -1;
		nsim_fib_set_max(data, res_ids[i], val);
	}
}

static void nsim_fib_event_work(struct work_struct *work)
{
	struct nsim_fib_data *data = container_of(work, struct nsim_fib_data,
						  fib_event_work);
	struct nsim_fib_event *fib_event, *next_fib_event;

	LIST_HEAD(fib_event_queue);

	spin_lock_bh(&data->fib_event_queue_lock);
	list_splice_init(&data->fib_event_queue, &fib_event_queue);
	spin_unlock_bh(&data->fib_event_queue_lock);

	mutex_lock(&data->fib_lock);
	list_for_each_entry_safe(fib_event, next_fib_event, &fib_event_queue,
				 list) {
		nsim_fib_event(fib_event);
		list_del(&fib_event->list);
		kfree(fib_event);
		cond_resched();
	}
	mutex_unlock(&data->fib_lock);
}

static void nsim_fib_flush_work(struct work_struct *work)
{
	struct nsim_fib_data *data = container_of(work, struct nsim_fib_data,
						  fib_flush_work);
	struct nsim_fib_rt *fib_rt, *fib_rt_tmp;

	/* Process pending work. */
	flush_work(&data->fib_event_work);

	mutex_lock(&data->fib_lock);
	list_for_each_entry_safe(fib_rt, fib_rt_tmp, &data->fib_rt_list, list) {
		rhashtable_remove_fast(&data->fib_rt_ht, &fib_rt->ht_node,
				       nsim_fib_rt_ht_params);
		nsim_fib_rt_free(fib_rt, data);
	}
	mutex_unlock(&data->fib_lock);
}

static int
nsim_fib_debugfs_init(struct nsim_fib_data *data, struct nsim_dev *nsim_dev)
{
	data->ddir = debugfs_create_dir("fib", nsim_dev->ddir);
	if (IS_ERR(data->ddir))
		return PTR_ERR(data->ddir);

	data->fail_route_offload = false;
	debugfs_create_bool("fail_route_offload", 0600, data->ddir,
			    &data->fail_route_offload);

	data->fail_res_nexthop_group_replace = false;
	debugfs_create_bool("fail_res_nexthop_group_replace", 0600, data->ddir,
			    &data->fail_res_nexthop_group_replace);

	data->fail_nexthop_bucket_replace = false;
	debugfs_create_bool("fail_nexthop_bucket_replace", 0600, data->ddir,
			    &data->fail_nexthop_bucket_replace);

	debugfs_create_file("nexthop_bucket_activity", 0200, data->ddir,
			    data, &nsim_nexthop_bucket_activity_fops);

	data->fail_route_delete = false;
	debugfs_create_bool("fail_route_delete", 0600, data->ddir,
			    &data->fail_route_delete);
	return 0;
}

static void nsim_fib_debugfs_exit(struct nsim_fib_data *data)
{
	debugfs_remove_recursive(data->ddir);
}

struct nsim_fib_data *nsim_fib_create(struct devlink *devlink,
				      struct netlink_ext_ack *extack)
{
	struct nsim_fib_data *data;
	struct nsim_dev *nsim_dev;
	int err;

	data = kzalloc(sizeof(*data), GFP_KERNEL);
	if (!data)
		return ERR_PTR(-ENOMEM);
	data->devlink = devlink;

	nsim_dev = devlink_priv(devlink);
	err = nsim_fib_debugfs_init(data, nsim_dev);
	if (err)
		goto err_data_free;

	mutex_init(&data->nh_lock);
	err = rhashtable_init(&data->nexthop_ht, &nsim_nexthop_ht_params);
	if (err)
		goto err_debugfs_exit;

	mutex_init(&data->fib_lock);
	INIT_LIST_HEAD(&data->fib_rt_list);
	err = rhashtable_init(&data->fib_rt_ht, &nsim_fib_rt_ht_params);
	if (err)
		goto err_rhashtable_nexthop_destroy;

	INIT_WORK(&data->fib_event_work, nsim_fib_event_work);
	INIT_WORK(&data->fib_flush_work, nsim_fib_flush_work);
	INIT_LIST_HEAD(&data->fib_event_queue);
	spin_lock_init(&data->fib_event_queue_lock);

	nsim_fib_set_max_all(data, devlink);

	data->nexthop_nb.notifier_call = nsim_nexthop_event_nb;
	err = register_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb,
					extack);
	if (err) {
		pr_err("Failed to register nexthop notifier\n");
		goto err_rhashtable_fib_destroy;
	}

	data->fib_nb.notifier_call = nsim_fib_event_nb;
	err = register_fib_notifier(devlink_net(devlink), &data->fib_nb,
				    nsim_fib_dump_inconsistent, extack);
	if (err) {
		pr_err("Failed to register fib notifier\n");
		goto err_nexthop_nb_unregister;
	}

	devl_resource_occ_get_register(devlink,
				       NSIM_RESOURCE_IPV4_FIB,
				       nsim_fib_ipv4_resource_occ_get,
				       data);
	devl_resource_occ_get_register(devlink,
				       NSIM_RESOURCE_IPV4_FIB_RULES,
				       nsim_fib_ipv4_rules_res_occ_get,
				       data);
	devl_resource_occ_get_register(devlink,
				       NSIM_RESOURCE_IPV6_FIB,
				       nsim_fib_ipv6_resource_occ_get,
				       data);
	devl_resource_occ_get_register(devlink,
				       NSIM_RESOURCE_IPV6_FIB_RULES,
				       nsim_fib_ipv6_rules_res_occ_get,
				       data);
	devl_resource_occ_get_register(devlink,
				       NSIM_RESOURCE_NEXTHOPS,
				       nsim_fib_nexthops_res_occ_get,
				       data);
	return data;

err_nexthop_nb_unregister:
	unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb);
err_rhashtable_fib_destroy:
	cancel_work_sync(&data->fib_flush_work);
	flush_work(&data->fib_event_work);
	rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free,
				    data);
err_rhashtable_nexthop_destroy:
	rhashtable_free_and_destroy(&data->nexthop_ht, nsim_nexthop_free,
				    data);
	mutex_destroy(&data->fib_lock);
err_debugfs_exit:
	mutex_destroy(&data->nh_lock);
	nsim_fib_debugfs_exit(data);
err_data_free:
	kfree(data);
	return ERR_PTR(err);
}

void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *data)
{
	devl_resource_occ_get_unregister(devlink,
					 NSIM_RESOURCE_NEXTHOPS);
	devl_resource_occ_get_unregister(devlink,
					 NSIM_RESOURCE_IPV6_FIB_RULES);
	devl_resource_occ_get_unregister(devlink,
					 NSIM_RESOURCE_IPV6_FIB);
	devl_resource_occ_get_unregister(devlink,
					 NSIM_RESOURCE_IPV4_FIB_RULES);
	devl_resource_occ_get_unregister(devlink,
					 NSIM_RESOURCE_IPV4_FIB);
	unregister_fib_notifier(devlink_net(devlink), &data->fib_nb);
	unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb);
	cancel_work_sync(&data->fib_flush_work);
	flush_work(&data->fib_event_work);
	rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free,
				    data);
	rhashtable_free_and_destroy(&data->nexthop_ht, nsim_nexthop_free,
				    data);
	WARN_ON_ONCE(!list_empty(&data->fib_event_queue));
	WARN_ON_ONCE(!list_empty(&data->fib_rt_list));
	mutex_destroy(&data->fib_lock);
	mutex_destroy(&data->nh_lock);
	nsim_fib_debugfs_exit(data);
	kfree(data);
}