summaryrefslogtreecommitdiffstats
path: root/tools/testing/selftests/net/pmtu.sh
blob: 71a62e7e35b1c1bdfd78b8c43d14a2547d01c951 (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
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
#
# Check that route PMTU values match expectations, and that initial device MTU
# values are assigned correctly
#
# Tests currently implemented:
#
# - pmtu_ipv4
#	Set up two namespaces, A and B, with two paths between them over routers
#	R1 and R2 (also implemented with namespaces), with different MTUs:
#
#	  segment a_r1    segment b_r1		a_r1: 2000
#	.--------------R1--------------.	b_r1: 1400
#	A                               B	a_r2: 2000
#	'--------------R2--------------'	b_r2: 1500
#	  segment a_r2    segment b_r2
#
#	Check that PMTU exceptions with the correct PMTU are created. Then
#	decrease and increase the MTU of the local link for one of the paths,
#	A to R1, checking that route exception PMTU changes accordingly over
#	this path. Also check that locked exceptions are created when an ICMP
#	message advertising a PMTU smaller than net.ipv4.route.min_pmtu is
#	received
#
# - pmtu_ipv6
#	Same as pmtu_ipv4, except for locked PMTU tests, using IPv6
#
# - pmtu_ipv4_vxlan4_exception
#	Set up the same network topology as pmtu_ipv4, create a VXLAN tunnel
#	over IPv4 between A and B, routed via R1. On the link between R1 and B,
#	set a MTU lower than the VXLAN MTU and the MTU on the link between A and
#	R1. Send IPv4 packets, exceeding the MTU between R1 and B, over VXLAN
#	from A to B and check that the PMTU exception is created with the right
#	value on A
#
# - pmtu_ipv6_vxlan4_exception
#	Same as pmtu_ipv4_vxlan4_exception, but send IPv6 packets from A to B
#
# - pmtu_ipv4_vxlan6_exception
#	Same as pmtu_ipv4_vxlan4_exception, but use IPv6 transport from A to B
#
# - pmtu_ipv6_vxlan6_exception
#	Same as pmtu_ipv4_vxlan6_exception, but send IPv6 packets from A to B
#
# - pmtu_ipv4_geneve4_exception
#	Same as pmtu_ipv4_vxlan4_exception, but using a GENEVE tunnel instead of
#	VXLAN
#
# - pmtu_ipv6_geneve4_exception
#	Same as pmtu_ipv6_vxlan4_exception, but using a GENEVE tunnel instead of
#	VXLAN
#
# - pmtu_ipv4_geneve6_exception
#	Same as pmtu_ipv4_vxlan6_exception, but using a GENEVE tunnel instead of
#	VXLAN
#
# - pmtu_ipv6_geneve6_exception
#	Same as pmtu_ipv6_vxlan6_exception, but using a GENEVE tunnel instead of
#	VXLAN
#
# - pmtu_ipv{4,6}_fou{4,6}_exception
#	Same as pmtu_ipv4_vxlan4, but using a direct IPv4/IPv6 encapsulation
#	(FoU) over IPv4/IPv6, instead of VXLAN
#
# - pmtu_ipv{4,6}_fou{4,6}_exception
#	Same as pmtu_ipv4_vxlan4, but using a generic UDP IPv4/IPv6
#	encapsulation (GUE) over IPv4/IPv6, instead of VXLAN
#
# - pmtu_vti4_exception
#	Set up vti tunnel on top of veth, with xfrm states and policies, in two
#	namespaces with matching endpoints. Check that route exception is not
#	created if link layer MTU is not exceeded, then exceed it and check that
#	exception is created with the expected PMTU. The approach described
#	below for IPv6 doesn't apply here, because, on IPv4, administrative MTU
#	changes alone won't affect PMTU
#
# - pmtu_vti6_exception
#	Set up vti6 tunnel on top of veth, with xfrm states and policies, in two
#	namespaces with matching endpoints. Check that route exception is
#	created by exceeding link layer MTU with ping to other endpoint. Then
#	decrease and increase MTU of tunnel, checking that route exception PMTU
#	changes accordingly
#
# - pmtu_vti4_default_mtu
#	Set up vti4 tunnel on top of veth, in two namespaces with matching
#	endpoints. Check that MTU assigned to vti interface is the MTU of the
#	lower layer (veth) minus additional lower layer headers (zero, for veth)
#	minus IPv4 header length
#
# - pmtu_vti6_default_mtu
#	Same as above, for IPv6
#
# - pmtu_vti4_link_add_mtu
#	Set up vti4 interface passing MTU value at link creation, check MTU is
#	configured, and that link is not created with invalid MTU values
#
# - pmtu_vti6_link_add_mtu
#	Same as above, for IPv6
#
# - pmtu_vti6_link_change_mtu
#	Set up two dummy interfaces with different MTUs, create a vti6 tunnel
#	and check that configured MTU is used on link creation and changes, and
#	that MTU is properly calculated instead when MTU is not configured from
#	userspace
#
# - cleanup_ipv4_exception
#	Similar to pmtu_ipv4_vxlan4_exception, but explicitly generate PMTU
#	exceptions on multiple CPUs and check that the veth device tear-down
# 	happens in a timely manner
#
# - cleanup_ipv6_exception
#	Same as above, but use IPv6 transport from A to B
#
# - list_flush_ipv4_exception
#	Using the same topology as in pmtu_ipv4, create exceptions, and check
#	they are shown when listing exception caches, gone after flushing them
#
# - list_flush_ipv6_exception
#	Using the same topology as in pmtu_ipv6, create exceptions, and check
#	they are shown when listing exception caches, gone after flushing them


# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4

PAUSE_ON_FAIL=no
VERBOSE=0
TRACING=0

# Some systems don't have a ping6 binary anymore
which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)

#               Name                          Description                  re-run with nh
tests="
	pmtu_ipv4_exception		ipv4: PMTU exceptions			1
	pmtu_ipv6_exception		ipv6: PMTU exceptions			1
	pmtu_ipv4_vxlan4_exception	IPv4 over vxlan4: PMTU exceptions	1
	pmtu_ipv6_vxlan4_exception	IPv6 over vxlan4: PMTU exceptions	1
	pmtu_ipv4_vxlan6_exception	IPv4 over vxlan6: PMTU exceptions	1
	pmtu_ipv6_vxlan6_exception	IPv6 over vxlan6: PMTU exceptions	1
	pmtu_ipv4_geneve4_exception	IPv4 over geneve4: PMTU exceptions	1
	pmtu_ipv6_geneve4_exception	IPv6 over geneve4: PMTU exceptions	1
	pmtu_ipv4_geneve6_exception	IPv4 over geneve6: PMTU exceptions	1
	pmtu_ipv6_geneve6_exception	IPv6 over geneve6: PMTU exceptions	1
	pmtu_ipv4_fou4_exception	IPv4 over fou4: PMTU exceptions		1
	pmtu_ipv6_fou4_exception	IPv6 over fou4: PMTU exceptions		1
	pmtu_ipv4_fou6_exception	IPv4 over fou6: PMTU exceptions		1
	pmtu_ipv6_fou6_exception	IPv6 over fou6: PMTU exceptions		1
	pmtu_ipv4_gue4_exception	IPv4 over gue4: PMTU exceptions		1
	pmtu_ipv6_gue4_exception	IPv6 over gue4: PMTU exceptions		1
	pmtu_ipv4_gue6_exception	IPv4 over gue6: PMTU exceptions		1
	pmtu_ipv6_gue6_exception	IPv6 over gue6: PMTU exceptions		1
	pmtu_vti6_exception		vti6: PMTU exceptions			0
	pmtu_vti4_exception		vti4: PMTU exceptions			0
	pmtu_vti4_default_mtu		vti4: default MTU assignment		0
	pmtu_vti6_default_mtu		vti6: default MTU assignment		0
	pmtu_vti4_link_add_mtu		vti4: MTU setting on link creation	0
	pmtu_vti6_link_add_mtu		vti6: MTU setting on link creation	0
	pmtu_vti6_link_change_mtu	vti6: MTU changes on link changes	0
	cleanup_ipv4_exception		ipv4: cleanup of cached exceptions	1
	cleanup_ipv6_exception		ipv6: cleanup of cached exceptions	1
	list_flush_ipv4_exception	ipv4: list and flush cached exceptions	1
	list_flush_ipv6_exception	ipv6: list and flush cached exceptions	1"

NS_A="ns-A"
NS_B="ns-B"
NS_R1="ns-R1"
NS_R2="ns-R2"
ns_a="ip netns exec ${NS_A}"
ns_b="ip netns exec ${NS_B}"
ns_r1="ip netns exec ${NS_R1}"
ns_r2="ip netns exec ${NS_R2}"

# Addressing and routing for tests with routers: four network segments, with
# index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an
# identifier ID, which is 1 for hosts (A and B), 2 for routers (R1 and R2).
# Addresses are:
# - IPv4: PREFIX4.SEGMENT.ID (/24)
# - IPv6: PREFIX6:SEGMENT::ID (/64)
prefix4="10.0"
prefix6="fc00"
a_r1=1
a_r2=2
b_r1=3
b_r2=4
#	ns	peer	segment
routing_addrs="
	A	R1	${a_r1}
	A	R2	${a_r2}
	B	R1	${b_r1}
	B	R2	${b_r2}
"
# Traffic from A to B goes through R1 by default, and through R2, if destined to
# B's address on the b_r2 segment.
# Traffic from B to A goes through R1.
#	ns	destination		gateway
routes="
	A	default			${prefix4}.${a_r1}.2
	A	${prefix4}.${b_r2}.1	${prefix4}.${a_r2}.2
	B	default			${prefix4}.${b_r1}.2

	A	default			${prefix6}:${a_r1}::2
	A	${prefix6}:${b_r2}::1	${prefix6}:${a_r2}::2
	B	default			${prefix6}:${b_r1}::2
"

USE_NH="no"
#	ns	family	nh id	   destination		gateway
nexthops="
	A	4	41	${prefix4}.${a_r1}.2	veth_A-R1
	A	4	42	${prefix4}.${a_r2}.2	veth_A-R2
	B	4	41	${prefix4}.${b_r1}.2	veth_B-R1

	A	6	61	${prefix6}:${a_r1}::2	veth_A-R1
	A	6	62	${prefix6}:${a_r2}::2	veth_A-R2
	B	6	61	${prefix6}:${b_r1}::2	veth_B-R1
"

# nexthop id correlates to id in nexthops config above
#	ns    family	prefix			nh id
routes_nh="
	A	4	default			41
	A	4	${prefix4}.${b_r2}.1	42
	B	4	default			41

	A	6	default			61
	A	6	${prefix6}:${b_r2}::1	62
	B	6	default			61
"

veth4_a_addr="192.168.1.1"
veth4_b_addr="192.168.1.2"
veth4_mask="24"
veth6_a_addr="fd00:1::a"
veth6_b_addr="fd00:1::b"
veth6_mask="64"

tunnel4_a_addr="192.168.2.1"
tunnel4_b_addr="192.168.2.2"
tunnel4_mask="24"
tunnel6_a_addr="fd00:2::a"
tunnel6_b_addr="fd00:2::b"
tunnel6_mask="64"

dummy6_0_prefix="fc00:1000::"
dummy6_1_prefix="fc00:1001::"
dummy6_mask="64"

err_buf=
tcpdump_pids=

err() {
	err_buf="${err_buf}${1}
"
}

err_flush() {
	echo -n "${err_buf}"
	err_buf=
}

run_cmd() {
	cmd="$*"

	if [ "$VERBOSE" = "1" ]; then
		printf "    COMMAND: $cmd\n"
	fi

	out="$($cmd 2>&1)"
	rc=$?
	if [ "$VERBOSE" = "1" -a -n "$out" ]; then
		echo "    $out"
		echo
	fi

	return $rc
}

# Find the auto-generated name for this namespace
nsname() {
	eval echo \$NS_$1
}

setup_fou_or_gue() {
	outer="${1}"
	inner="${2}"
	encap="${3}"

	if [ "${outer}" = "4" ]; then
		modprobe fou || return 2
		a_addr="${prefix4}.${a_r1}.1"
		b_addr="${prefix4}.${b_r1}.1"
		if [ "${inner}" = "4" ]; then
			type="ipip"
			ipproto="4"
		else
			type="sit"
			ipproto="41"
		fi
	else
		modprobe fou6 || return 2
		a_addr="${prefix6}:${a_r1}::1"
		b_addr="${prefix6}:${b_r1}::1"
		if [ "${inner}" = "4" ]; then
			type="ip6tnl"
			mode="mode ipip6"
			ipproto="4 -6"
		else
			type="ip6tnl"
			mode="mode ip6ip6"
			ipproto="41 -6"
		fi
	fi

	run_cmd ${ns_a} ip fou add port 5555 ipproto ${ipproto} || return 2
	run_cmd ${ns_a} ip link add ${encap}_a type ${type} ${mode} local ${a_addr} remote ${b_addr} encap ${encap} encap-sport auto encap-dport 5556 || return 2

	run_cmd ${ns_b} ip fou add port 5556 ipproto ${ipproto}
	run_cmd ${ns_b} ip link add ${encap}_b type ${type} ${mode} local ${b_addr} remote ${a_addr} encap ${encap} encap-sport auto encap-dport 5555

	if [ "${inner}" = "4" ]; then
		run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${encap}_a
		run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${encap}_b
	else
		run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${encap}_a
		run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${encap}_b
	fi

	run_cmd ${ns_a} ip link set ${encap}_a up
	run_cmd ${ns_b} ip link set ${encap}_b up
}

setup_fou44() {
	setup_fou_or_gue 4 4 fou
}

setup_fou46() {
	setup_fou_or_gue 4 6 fou
}

setup_fou64() {
	setup_fou_or_gue 6 4 fou
}

setup_fou66() {
	setup_fou_or_gue 6 6 fou
}

setup_gue44() {
	setup_fou_or_gue 4 4 gue
}

setup_gue46() {
	setup_fou_or_gue 4 6 gue
}

setup_gue64() {
	setup_fou_or_gue 6 4 gue
}

setup_gue66() {
	setup_fou_or_gue 6 6 gue
}

setup_namespaces() {
	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
		ip netns add ${n} || return 1

		# Disable DAD, so that we don't have to wait to use the
		# configured IPv6 addresses
		ip netns exec ${n} sysctl -q net/ipv6/conf/default/accept_dad=0
	done
}

setup_veth() {
	run_cmd ${ns_a} ip link add veth_a type veth peer name veth_b || return 1
	run_cmd ${ns_a} ip link set veth_b netns ${NS_B}

	run_cmd ${ns_a} ip addr add ${veth4_a_addr}/${veth4_mask} dev veth_a
	run_cmd ${ns_b} ip addr add ${veth4_b_addr}/${veth4_mask} dev veth_b

	run_cmd ${ns_a} ip addr add ${veth6_a_addr}/${veth6_mask} dev veth_a
	run_cmd ${ns_b} ip addr add ${veth6_b_addr}/${veth6_mask} dev veth_b

	run_cmd ${ns_a} ip link set veth_a up
	run_cmd ${ns_b} ip link set veth_b up
}

setup_vti() {
	proto=${1}
	veth_a_addr="${2}"
	veth_b_addr="${3}"
	vti_a_addr="${4}"
	vti_b_addr="${5}"
	vti_mask=${6}

	[ ${proto} -eq 6 ] && vti_type="vti6" || vti_type="vti"

	run_cmd ${ns_a} ip link add vti${proto}_a type ${vti_type} local ${veth_a_addr} remote ${veth_b_addr} key 10 || return 1
	run_cmd ${ns_b} ip link add vti${proto}_b type ${vti_type} local ${veth_b_addr} remote ${veth_a_addr} key 10

	run_cmd ${ns_a} ip addr add ${vti_a_addr}/${vti_mask} dev vti${proto}_a
	run_cmd ${ns_b} ip addr add ${vti_b_addr}/${vti_mask} dev vti${proto}_b

	run_cmd ${ns_a} ip link set vti${proto}_a up
	run_cmd ${ns_b} ip link set vti${proto}_b up
}

setup_vti4() {
	setup_vti 4 ${veth4_a_addr} ${veth4_b_addr} ${tunnel4_a_addr} ${tunnel4_b_addr} ${tunnel4_mask}
}

setup_vti6() {
	setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
}

setup_vxlan_or_geneve() {
	type="${1}"
	a_addr="${2}"
	b_addr="${3}"
	opts="${4}"

	if [ "${type}" = "vxlan" ]; then
		opts="${opts} ttl 64 dstport 4789"
		opts_a="local ${a_addr}"
		opts_b="local ${b_addr}"
	else
		opts_a=""
		opts_b=""
	fi

	run_cmd ${ns_a} ip link add ${type}_a type ${type} id 1 ${opts_a} remote ${b_addr} ${opts} || return 1
	run_cmd ${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts}

	run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a
	run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b

	run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a
	run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b

	run_cmd ${ns_a} ip link set ${type}_a up
	run_cmd ${ns_b} ip link set ${type}_b up
}

setup_geneve4() {
	setup_vxlan_or_geneve geneve ${prefix4}.${a_r1}.1  ${prefix4}.${b_r1}.1  "df set"
}

setup_vxlan4() {
	setup_vxlan_or_geneve vxlan  ${prefix4}.${a_r1}.1  ${prefix4}.${b_r1}.1  "df set"
}

setup_geneve6() {
	setup_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1
}

setup_vxlan6() {
	setup_vxlan_or_geneve vxlan  ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1
}

setup_xfrm() {
	proto=${1}
	veth_a_addr="${2}"
	veth_b_addr="${3}"

	run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel || return 1
	run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
	run_cmd ${ns_a} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
	run_cmd ${ns_a} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel

	run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
	run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
	run_cmd ${ns_b} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel
	run_cmd ${ns_b} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
}

setup_xfrm4() {
	setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr}
}

setup_xfrm6() {
	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr}
}

setup_routing_old() {
	for i in ${routes}; do
		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
		[ "${addr}" = "" ]	&& addr="${i}"		&& continue
		[ "${gw}" = "" ]	&& gw="${i}"

		ns_name="$(nsname ${ns})"

		ip -n ${ns_name} route add ${addr} via ${gw}

		ns=""; addr=""; gw=""
	done
}

setup_routing_new() {
	for i in ${nexthops}; do
		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
		[ "${fam}" = "" ]	&& fam="${i}"		&& continue
		[ "${nhid}" = "" ]	&& nhid="${i}"		&& continue
		[ "${gw}" = "" ]	&& gw="${i}"		&& continue
		[ "${dev}" = "" ]	&& dev="${i}"

		ns_name="$(nsname ${ns})"

		ip -n ${ns_name} -${fam} nexthop add id ${nhid} via ${gw} dev ${dev}

		ns=""; fam=""; nhid=""; gw=""; dev=""

	done

	for i in ${routes_nh}; do
		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
		[ "${fam}" = "" ]	&& fam="${i}"		&& continue
		[ "${addr}" = "" ]	&& addr="${i}"		&& continue
		[ "${nhid}" = "" ]	&& nhid="${i}"

		ns_name="$(nsname ${ns})"

		ip -n ${ns_name} -${fam} route add ${addr} nhid ${nhid}

		ns=""; fam=""; addr=""; nhid=""
	done
}

setup_routing() {
	for i in ${NS_R1} ${NS_R2}; do
		ip netns exec ${i} sysctl -q net/ipv4/ip_forward=1
		ip netns exec ${i} sysctl -q net/ipv6/conf/all/forwarding=1
	done

	for i in ${routing_addrs}; do
		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
		[ "${peer}" = "" ]	&& peer="${i}"		&& continue
		[ "${segment}" = "" ]	&& segment="${i}"

		ns_name="$(nsname ${ns})"
		peer_name="$(nsname ${peer})"
		if="veth_${ns}-${peer}"
		ifpeer="veth_${peer}-${ns}"

		# Create veth links
		ip link add ${if} up netns ${ns_name} type veth peer name ${ifpeer} netns ${peer_name} || return 1
		ip -n ${peer_name} link set dev ${ifpeer} up

		# Add addresses
		ip -n ${ns_name}   addr add ${prefix4}.${segment}.1/24  dev ${if}
		ip -n ${ns_name}   addr add ${prefix6}:${segment}::1/64 dev ${if}

		ip -n ${peer_name} addr add ${prefix4}.${segment}.2/24  dev ${ifpeer}
		ip -n ${peer_name} addr add ${prefix6}:${segment}::2/64 dev ${ifpeer}

		ns=""; peer=""; segment=""
	done

	if [ "$USE_NH" = "yes" ]; then
		setup_routing_new
	else
		setup_routing_old
	fi

	return 0
}

setup() {
	[ "$(id -u)" -ne 0 ] && echo "  need to run as root" && return $ksft_skip

	cleanup
	for arg do
		eval setup_${arg} || { echo "  ${arg} not supported"; return 1; }
	done
}

trace() {
	[ $TRACING -eq 0 ] && return

	for arg do
		[ "${ns_cmd}" = "" ] && ns_cmd="${arg}" && continue
		${ns_cmd} tcpdump -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null &
		tcpdump_pids="${tcpdump_pids} $!"
		ns_cmd=
	done
	sleep 1
}

cleanup() {
	for pid in ${tcpdump_pids}; do
		kill ${pid}
	done
	tcpdump_pids=

	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
		ip netns del ${n} 2> /dev/null
	done
}

mtu() {
	ns_cmd="${1}"
	dev="${2}"
	mtu="${3}"

	${ns_cmd} ip link set dev ${dev} mtu ${mtu}
}

mtu_parse() {
	input="${1}"

	next=0
	for i in ${input}; do
		[ ${next} -eq 1 -a "${i}" = "lock" ] && next=2 && continue
		[ ${next} -eq 1 ] && echo "${i}" && return
		[ ${next} -eq 2 ] && echo "lock ${i}" && return
		[ "${i}" = "mtu" ] && next=1
	done
}

link_get() {
	ns_cmd="${1}"
	name="${2}"

	${ns_cmd} ip link show dev "${name}"
}

link_get_mtu() {
	ns_cmd="${1}"
	name="${2}"

	mtu_parse "$(link_get "${ns_cmd}" ${name})"
}

route_get_dst_exception() {
	ns_cmd="${1}"
	dst="${2}"

	${ns_cmd} ip route get "${dst}"
}

route_get_dst_pmtu_from_exception() {
	ns_cmd="${1}"
	dst="${2}"

	mtu_parse "$(route_get_dst_exception "${ns_cmd}" ${dst})"
}

check_pmtu_value() {
	expected="${1}"
	value="${2}"
	event="${3}"

	[ "${expected}" = "any" ] && [ -n "${value}" ] && return 0
	[ "${value}" = "${expected}" ] && return 0
	[ -z "${value}" ] &&    err "  PMTU exception wasn't created after ${event}" && return 1
	[ -z "${expected}" ] && err "  PMTU exception shouldn't exist after ${event}" && return 1
	err "  found PMTU exception with incorrect MTU ${value}, expected ${expected}, after ${event}"
	return 1
}

test_pmtu_ipvX() {
	family=${1}

	setup namespaces routing || return 2
	trace "${ns_a}"  veth_A-R1    "${ns_r1}" veth_R1-A \
	      "${ns_r1}" veth_R1-B    "${ns_b}"  veth_B-R1 \
	      "${ns_a}"  veth_A-R2    "${ns_r2}" veth_R2-A \
	      "${ns_r2}" veth_R2-B    "${ns_b}"  veth_B-R2

	if [ ${family} -eq 4 ]; then
		ping=ping
		dst1="${prefix4}.${b_r1}.1"
		dst2="${prefix4}.${b_r2}.1"
	else
		ping=${ping6}
		dst1="${prefix6}:${b_r1}::1"
		dst2="${prefix6}:${b_r2}::1"
	fi

	# Set up initial MTU values
	mtu "${ns_a}"  veth_A-R1 2000
	mtu "${ns_r1}" veth_R1-A 2000
	mtu "${ns_r1}" veth_R1-B 1400
	mtu "${ns_b}"  veth_B-R1 1400

	mtu "${ns_a}"  veth_A-R2 2000
	mtu "${ns_r2}" veth_R2-A 2000
	mtu "${ns_r2}" veth_R2-B 1500
	mtu "${ns_b}"  veth_B-R2 1500

	# Create route exceptions
	run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst1}
	run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst2}

	# Check that exceptions have been created with the correct PMTU
	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
	check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1
	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
	check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1

	# Decrease local MTU below PMTU, check for PMTU decrease in route exception
	mtu "${ns_a}"  veth_A-R1 1300
	mtu "${ns_r1}" veth_R1-A 1300
	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
	check_pmtu_value "1300" "${pmtu_1}" "decreasing local MTU" || return 1
	# Second exception shouldn't be modified
	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
	check_pmtu_value "1500" "${pmtu_2}" "changing local MTU on a link not on this path" || return 1

	# Increase MTU, check for PMTU increase in route exception
	mtu "${ns_a}"  veth_A-R1 1700
	mtu "${ns_r1}" veth_R1-A 1700
	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
	check_pmtu_value "1700" "${pmtu_1}" "increasing local MTU" || return 1
	# Second exception shouldn't be modified
	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
	check_pmtu_value "1500" "${pmtu_2}" "changing local MTU on a link not on this path" || return 1

	# Skip PMTU locking tests for IPv6
	[ $family -eq 6 ] && return 0

	# Decrease remote MTU on path via R2, get new exception
	mtu "${ns_r2}" veth_R2-B 400
	mtu "${ns_b}"  veth_B-R2 400
	run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1400 ${dst2}
	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
	check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1

	# Decrease local MTU below PMTU
	mtu "${ns_a}"  veth_A-R2 500
	mtu "${ns_r2}" veth_R2-A 500
	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
	check_pmtu_value "500" "${pmtu_2}" "decreasing local MTU" || return 1

	# Increase local MTU
	mtu "${ns_a}"  veth_A-R2 1500
	mtu "${ns_r2}" veth_R2-A 1500
	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
	check_pmtu_value "1500" "${pmtu_2}" "increasing local MTU" || return 1

	# Get new exception
	run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1400 ${dst2}
	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
	check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1
}

test_pmtu_ipv4_exception() {
	test_pmtu_ipvX 4
}

test_pmtu_ipv6_exception() {
	test_pmtu_ipvX 6
}

test_pmtu_ipvX_over_vxlanY_or_geneveY_exception() {
	type=${1}
	family=${2}
	outer_family=${3}
	ll_mtu=4000

	if [ ${outer_family} -eq 4 ]; then
		setup namespaces routing ${type}4 || return 2
		#                      IPv4 header   UDP header   VXLAN/GENEVE header   Ethernet header
		exp_mtu=$((${ll_mtu} - 20          - 8          - 8                   - 14))
	else
		setup namespaces routing ${type}6 || return 2
		#                      IPv6 header   UDP header   VXLAN/GENEVE header   Ethernet header
		exp_mtu=$((${ll_mtu} - 40          - 8          - 8                   - 14))
	fi

	trace "${ns_a}" ${type}_a    "${ns_b}"  ${type}_b \
	      "${ns_a}" veth_A-R1    "${ns_r1}" veth_R1-A \
	      "${ns_b}" veth_B-R1    "${ns_r1}" veth_R1-B

	if [ ${family} -eq 4 ]; then
		ping=ping
		dst=${tunnel4_b_addr}
	else
		ping=${ping6}
		dst=${tunnel6_b_addr}
	fi

	# Create route exception by exceeding link layer MTU
	mtu "${ns_a}"  veth_A-R1 $((${ll_mtu} + 1000))
	mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000))
	mtu "${ns_b}"  veth_B-R1 ${ll_mtu}
	mtu "${ns_r1}" veth_R1-B ${ll_mtu}

	mtu "${ns_a}" ${type}_a $((${ll_mtu} + 1000))
	mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000))
	run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst}

	# Check that exception was created
	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
	check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on ${type} interface"
}

test_pmtu_ipv4_vxlan4_exception() {
	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan  4 4
}

test_pmtu_ipv6_vxlan4_exception() {
	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan  6 4
}

test_pmtu_ipv4_geneve4_exception() {
	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 4 4
}

test_pmtu_ipv6_geneve4_exception() {
	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 6 4
}

test_pmtu_ipv4_vxlan6_exception() {
	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan  4 6
}

test_pmtu_ipv6_vxlan6_exception() {
	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan  6 6
}

test_pmtu_ipv4_geneve6_exception() {
	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 4 6
}

test_pmtu_ipv6_geneve6_exception() {
	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 6 6
}

test_pmtu_ipvX_over_fouY_or_gueY() {
	inner_family=${1}
	outer_family=${2}
	encap=${3}
	ll_mtu=4000

	setup namespaces routing ${encap}${outer_family}${inner_family} || return 2
	trace "${ns_a}" ${encap}_a   "${ns_b}"  ${encap}_b \
	      "${ns_a}" veth_A-R1    "${ns_r1}" veth_R1-A \
	      "${ns_b}" veth_B-R1    "${ns_r1}" veth_R1-B

	if [ ${inner_family} -eq 4 ]; then
		ping=ping
		dst=${tunnel4_b_addr}
	else
		ping=${ping6}
		dst=${tunnel6_b_addr}
	fi

	if [ "${encap}" = "gue" ]; then
		encap_overhead=4
	else
		encap_overhead=0
	fi

	if [ ${outer_family} -eq 4 ]; then
		#                      IPv4 header   UDP header
		exp_mtu=$((${ll_mtu} - 20          - 8         - ${encap_overhead}))
	else
		#                      IPv6 header   Option 4   UDP header
		exp_mtu=$((${ll_mtu} - 40          - 8        - 8       - ${encap_overhead}))
	fi

	# Create route exception by exceeding link layer MTU
	mtu "${ns_a}"  veth_A-R1 $((${ll_mtu} + 1000))
	mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000))
	mtu "${ns_b}"  veth_B-R1 ${ll_mtu}
	mtu "${ns_r1}" veth_R1-B ${ll_mtu}

	mtu "${ns_a}" ${encap}_a $((${ll_mtu} + 1000))
	mtu "${ns_b}" ${encap}_b $((${ll_mtu} + 1000))
	run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst}

	# Check that exception was created
	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
	check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on ${encap} interface"
}

test_pmtu_ipv4_fou4_exception() {
	test_pmtu_ipvX_over_fouY_or_gueY 4 4 fou
}

test_pmtu_ipv6_fou4_exception() {
	test_pmtu_ipvX_over_fouY_or_gueY 6 4 fou
}

test_pmtu_ipv4_fou6_exception() {
	test_pmtu_ipvX_over_fouY_or_gueY 4 6 fou
}

test_pmtu_ipv6_fou6_exception() {
	test_pmtu_ipvX_over_fouY_or_gueY 6 6 fou
}

test_pmtu_ipv4_gue4_exception() {
	test_pmtu_ipvX_over_fouY_or_gueY 4 4 gue
}

test_pmtu_ipv6_gue4_exception() {
	test_pmtu_ipvX_over_fouY_or_gueY 6 4 gue
}

test_pmtu_ipv4_gue6_exception() {
	test_pmtu_ipvX_over_fouY_or_gueY 4 6 gue
}

test_pmtu_ipv6_gue6_exception() {
	test_pmtu_ipvX_over_fouY_or_gueY 6 6 gue
}

test_pmtu_vti4_exception() {
	setup namespaces veth vti4 xfrm4 || return 2
	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
	      "${ns_a}" vti4_a    "${ns_b}" vti4_b

	veth_mtu=1500
	vti_mtu=$((veth_mtu - 20))

	#                                SPI   SN   IV  ICV   pad length   next header
	esp_payload_rfc4106=$((vti_mtu - 4   - 4  - 8 - 16  - 1          - 1))
	ping_payload=$((esp_payload_rfc4106 - 28))

	mtu "${ns_a}" veth_a ${veth_mtu}
	mtu "${ns_b}" veth_b ${veth_mtu}
	mtu "${ns_a}" vti4_a ${vti_mtu}
	mtu "${ns_b}" vti4_b ${vti_mtu}

	# Send DF packet without exceeding link layer MTU, check that no
	# exception is created
	run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr}
	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
	check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1

	# Now exceed link layer MTU by one byte, check that exception is created
	# with the right PMTU value
	run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload + 1)) ${tunnel4_b_addr}
	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
	check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
}

test_pmtu_vti6_exception() {
	setup namespaces veth vti6 xfrm6 || return 2
	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
	      "${ns_a}" vti6_a    "${ns_b}" vti6_b
	fail=0

	# Create route exception by exceeding link layer MTU
	mtu "${ns_a}" veth_a 4000
	mtu "${ns_b}" veth_b 4000
	mtu "${ns_a}" vti6_a 5000
	mtu "${ns_b}" vti6_b 5000
	run_cmd ${ns_a} ${ping6} -q -i 0.1 -w 1 -s 60000 ${tunnel6_b_addr}

	# Check that exception was created
	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
	check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1

	# Decrease tunnel MTU, check for PMTU decrease in route exception
	mtu "${ns_a}" vti6_a 3000
	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
	check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1

	# Increase tunnel MTU, check for PMTU increase in route exception
	mtu "${ns_a}" vti6_a 9000
	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
	check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1

	return ${fail}
}

test_pmtu_vti4_default_mtu() {
	setup namespaces veth vti4 || return 2

	# Check that MTU of vti device is MTU of veth minus IPv4 header length
	veth_mtu="$(link_get_mtu "${ns_a}" veth_a)"
	vti4_mtu="$(link_get_mtu "${ns_a}" vti4_a)"
	if [ $((veth_mtu - vti4_mtu)) -ne 20 ]; then
		err "  vti MTU ${vti4_mtu} is not veth MTU ${veth_mtu} minus IPv4 header length"
		return 1
	fi
}

test_pmtu_vti6_default_mtu() {
	setup namespaces veth vti6 || return 2

	# Check that MTU of vti device is MTU of veth minus IPv6 header length
	veth_mtu="$(link_get_mtu "${ns_a}" veth_a)"
	vti6_mtu="$(link_get_mtu "${ns_a}" vti6_a)"
	if [ $((veth_mtu - vti6_mtu)) -ne 40 ]; then
		err "  vti MTU ${vti6_mtu} is not veth MTU ${veth_mtu} minus IPv6 header length"
		return 1
	fi
}

test_pmtu_vti4_link_add_mtu() {
	setup namespaces || return 2

	run_cmd ${ns_a} ip link add vti4_a type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10
	[ $? -ne 0 ] && err "  vti not supported" && return 2
	run_cmd ${ns_a} ip link del vti4_a

	fail=0

	min=68
	max=$((65535 - 20))
	# Check invalid values first
	for v in $((min - 1)) $((max + 1)); do
		run_cmd ${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10
		# This can fail, or MTU can be adjusted to a proper value
		[ $? -ne 0 ] && continue
		mtu="$(link_get_mtu "${ns_a}" vti4_a)"
		if [ ${mtu} -lt ${min} -o ${mtu} -gt ${max} ]; then
			err "  vti tunnel created with invalid MTU ${mtu}"
			fail=1
		fi
		run_cmd ${ns_a} ip link del vti4_a
	done

	# Now check valid values
	for v in ${min} 1300 ${max}; do
		run_cmd ${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10
		mtu="$(link_get_mtu "${ns_a}" vti4_a)"
		run_cmd ${ns_a} ip link del vti4_a
		if [ "${mtu}" != "${v}" ]; then
			err "  vti MTU ${mtu} doesn't match configured value ${v}"
			fail=1
		fi
	done

	return ${fail}
}

test_pmtu_vti6_link_add_mtu() {
	setup namespaces || return 2

	run_cmd ${ns_a} ip link add vti6_a type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10
	[ $? -ne 0 ] && err "  vti6 not supported" && return 2
	run_cmd ${ns_a} ip link del vti6_a

	fail=0

	min=68			# vti6 can carry IPv4 packets too
	max=$((65535 - 40))
	# Check invalid values first
	for v in $((min - 1)) $((max + 1)); do
		run_cmd ${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10
		# This can fail, or MTU can be adjusted to a proper value
		[ $? -ne 0 ] && continue
		mtu="$(link_get_mtu "${ns_a}" vti6_a)"
		if [ ${mtu} -lt ${min} -o ${mtu} -gt ${max} ]; then
			err "  vti6 tunnel created with invalid MTU ${v}"
			fail=1
		fi
		run_cmd ${ns_a} ip link del vti6_a
	done

	# Now check valid values
	for v in 68 1280 1300 $((65535 - 40)); do
		run_cmd ${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10
		mtu="$(link_get_mtu "${ns_a}" vti6_a)"
		run_cmd ${ns_a} ip link del vti6_a
		if [ "${mtu}" != "${v}" ]; then
			err "  vti6 MTU ${mtu} doesn't match configured value ${v}"
			fail=1
		fi
	done

	return ${fail}
}

test_pmtu_vti6_link_change_mtu() {
	setup namespaces || return 2

	run_cmd ${ns_a} ip link add dummy0 mtu 1500 type dummy
	[ $? -ne 0 ] && err "  dummy not supported" && return 2
	run_cmd ${ns_a} ip link add dummy1 mtu 3000 type dummy
	run_cmd ${ns_a} ip link set dummy0 up
	run_cmd ${ns_a} ip link set dummy1 up

	run_cmd ${ns_a} ip addr add ${dummy6_0_prefix}1/${dummy6_mask} dev dummy0
	run_cmd ${ns_a} ip addr add ${dummy6_1_prefix}1/${dummy6_mask} dev dummy1

	fail=0

	# Create vti6 interface bound to device, passing MTU, check it
	run_cmd ${ns_a} ip link add vti6_a mtu 1300 type vti6 remote ${dummy6_0_prefix}2 local ${dummy6_0_prefix}1
	mtu="$(link_get_mtu "${ns_a}" vti6_a)"
	if [ ${mtu} -ne 1300 ]; then
		err "  vti6 MTU ${mtu} doesn't match configured value 1300"
		fail=1
	fi

	# Move to another device with different MTU, without passing MTU, check
	# MTU is adjusted
	run_cmd ${ns_a} ip link set vti6_a type vti6 remote ${dummy6_1_prefix}2 local ${dummy6_1_prefix}1
	mtu="$(link_get_mtu "${ns_a}" vti6_a)"
	if [ ${mtu} -ne $((3000 - 40)) ]; then
		err "  vti MTU ${mtu} is not dummy MTU 3000 minus IPv6 header length"
		fail=1
	fi

	# Move it back, passing MTU, check MTU is not overridden
	run_cmd ${ns_a} ip link set vti6_a mtu 1280 type vti6 remote ${dummy6_0_prefix}2 local ${dummy6_0_prefix}1
	mtu="$(link_get_mtu "${ns_a}" vti6_a)"
	if [ ${mtu} -ne 1280 ]; then
		err "  vti6 MTU ${mtu} doesn't match configured value 1280"
		fail=1
	fi

	return ${fail}
}

check_command() {
	cmd=${1}

	if ! which ${cmd} > /dev/null 2>&1; then
		err "  missing required command: '${cmd}'"
		return 1
	fi
	return 0
}

test_cleanup_vxlanX_exception() {
	outer="${1}"
	encap="vxlan"
	ll_mtu=4000

	check_command taskset || return 2
	cpu_list=$(grep -m 2 processor /proc/cpuinfo | cut -d ' ' -f 2)

	setup namespaces routing ${encap}${outer} || return 2
	trace "${ns_a}" ${encap}_a   "${ns_b}"  ${encap}_b \
	      "${ns_a}" veth_A-R1    "${ns_r1}" veth_R1-A \
	      "${ns_b}" veth_B-R1    "${ns_r1}" veth_R1-B

	# Create route exception by exceeding link layer MTU
	mtu "${ns_a}"  veth_A-R1 $((${ll_mtu} + 1000))
	mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000))
	mtu "${ns_b}"  veth_B-R1 ${ll_mtu}
	mtu "${ns_r1}" veth_R1-B ${ll_mtu}

	mtu "${ns_a}" ${encap}_a $((${ll_mtu} + 1000))
	mtu "${ns_b}" ${encap}_b $((${ll_mtu} + 1000))

	# Fill exception cache for multiple CPUs (2)
	# we can always use inner IPv4 for that
	for cpu in ${cpu_list}; do
		run_cmd taskset --cpu-list ${cpu} ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${tunnel4_b_addr}
	done

	${ns_a} ip link del dev veth_A-R1 &
	iplink_pid=$!
	sleep 1
	if [ "$(cat /proc/${iplink_pid}/cmdline 2>/dev/null | tr -d '\0')" = "iplinkdeldevveth_A-R1" ]; then
		err "  can't delete veth device in a timely manner, PMTU dst likely leaked"
		return 1
	fi
}

test_cleanup_ipv6_exception() {
	test_cleanup_vxlanX_exception 6
}

test_cleanup_ipv4_exception() {
	test_cleanup_vxlanX_exception 4
}

run_test() {
	(
	tname="$1"
	tdesc="$2"

	unset IFS

	if [ "$VERBOSE" = "1" ]; then
		printf "\n##########################################################################\n\n"
	fi

	eval test_${tname}
	ret=$?

	if [ $ret -eq 0 ]; then
		printf "TEST: %-60s  [ OK ]\n" "${tdesc}"
	elif [ $ret -eq 1 ]; then
		printf "TEST: %-60s  [FAIL]\n" "${tdesc}"
		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
			echo
			echo "Pausing. Hit enter to continue"
			read a
		fi
		err_flush
		exit 1
	elif [ $ret -eq 2 ]; then
		printf "TEST: %-60s  [SKIP]\n" "${tdesc}"
		err_flush
	fi

	return $ret
	)
	ret=$?
	[ $ret -ne 0 ] && exitcode=1

	return $ret
}

run_test_nh() {
	tname="$1"
	tdesc="$2"

	USE_NH=yes
	run_test "${tname}" "${tdesc} - nexthop objects"
	USE_NH=no
}

test_list_flush_ipv4_exception() {
	setup namespaces routing || return 2
	trace "${ns_a}"  veth_A-R1    "${ns_r1}" veth_R1-A \
	      "${ns_r1}" veth_R1-B    "${ns_b}"  veth_B-R1 \
	      "${ns_a}"  veth_A-R2    "${ns_r2}" veth_R2-A \
	      "${ns_r2}" veth_R2-B    "${ns_b}"  veth_B-R2

	dst_prefix1="${prefix4}.${b_r1}."
	dst2="${prefix4}.${b_r2}.1"

	# Set up initial MTU values
	mtu "${ns_a}"  veth_A-R1 2000
	mtu "${ns_r1}" veth_R1-A 2000
	mtu "${ns_r1}" veth_R1-B 1500
	mtu "${ns_b}"  veth_B-R1 1500

	mtu "${ns_a}"  veth_A-R2 2000
	mtu "${ns_r2}" veth_R2-A 2000
	mtu "${ns_r2}" veth_R2-B 1500
	mtu "${ns_b}"  veth_B-R2 1500

	fail=0

	# Add 100 addresses for veth endpoint on B reached by default A route
	for i in $(seq 100 199); do
		run_cmd ${ns_b} ip addr add "${dst_prefix1}${i}" dev veth_B-R1
	done

	# Create 100 cached route exceptions for path via R1, one via R2. Note
	# that with IPv4 we need to actually cause a route lookup that matches
	# the exception caused by ICMP, in order to actually have a cached
	# route, so we need to ping each destination twice
	for i in $(seq 100 199); do
		run_cmd ${ns_a} ping -q -M want -i 0.1 -c 2 -s 1800 "${dst_prefix1}${i}"
	done
	run_cmd ${ns_a} ping -q -M want -i 0.1 -c 2 -s 1800 "${dst2}"

	if [ "$(${ns_a} ip -oneline route list cache | wc -l)" -ne 101 ]; then
		err "  can't list cached exceptions"
		fail=1
	fi

	run_cmd ${ns_a} ip route flush cache
	pmtu1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst_prefix}1)"
	pmtu2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst_prefix}2)"
	if [ -n "${pmtu1}" ] || [ -n "${pmtu2}" ] || \
	   [ -n "$(${ns_a} ip route list cache)" ]; then
		err "  can't flush cached exceptions"
		fail=1
	fi

	return ${fail}
}

test_list_flush_ipv6_exception() {
	setup namespaces routing || return 2
	trace "${ns_a}"  veth_A-R1    "${ns_r1}" veth_R1-A \
	      "${ns_r1}" veth_R1-B    "${ns_b}"  veth_B-R1 \
	      "${ns_a}"  veth_A-R2    "${ns_r2}" veth_R2-A \
	      "${ns_r2}" veth_R2-B    "${ns_b}"  veth_B-R2

	dst_prefix1="${prefix6}:${b_r1}::"
	dst2="${prefix6}:${b_r2}::1"

	# Set up initial MTU values
	mtu "${ns_a}"  veth_A-R1 2000
	mtu "${ns_r1}" veth_R1-A 2000
	mtu "${ns_r1}" veth_R1-B 1500
	mtu "${ns_b}"  veth_B-R1 1500

	mtu "${ns_a}"  veth_A-R2 2000
	mtu "${ns_r2}" veth_R2-A 2000
	mtu "${ns_r2}" veth_R2-B 1500
	mtu "${ns_b}"  veth_B-R2 1500

	fail=0

	# Add 100 addresses for veth endpoint on B reached by default A route
	for i in $(seq 100 199); do
		run_cmd ${ns_b} ip addr add "${dst_prefix1}${i}" dev veth_B-R1
	done

	# Create 100 cached route exceptions for path via R1, one via R2
	for i in $(seq 100 199); do
		run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s 1800 "${dst_prefix1}${i}"
	done
	run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s 1800 "${dst2}"
	if [ "$(${ns_a} ip -oneline -6 route list cache | wc -l)" -ne 101 ]; then
		err "  can't list cached exceptions"
		fail=1
	fi

	run_cmd ${ns_a} ip -6 route flush cache
	pmtu1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst_prefix1}100")"
	pmtu2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
	if [ -n "${pmtu1}" ] || [ -n "${pmtu2}" ] || \
	   [ -n "$(${ns_a} ip -6 route list cache)" ]; then
		err "  can't flush cached exceptions"
		fail=1
	fi

	return ${fail}
}

usage() {
	echo
	echo "$0 [OPTIONS] [TEST]..."
	echo "If no TEST argument is given, all tests will be run."
	echo
	echo "Options"
	echo "  --trace: capture traffic to TEST_INTERFACE.pcap"
	echo
	echo "Available tests${tests}"
	exit 1
}

################################################################################
#
exitcode=0
desc=0

while getopts :ptv o
do
	case $o in
	p) PAUSE_ON_FAIL=yes;;
	v) VERBOSE=1;;
	t) if which tcpdump > /dev/null 2>&1; then
		TRACING=1
	   else
		echo "=== tcpdump not available, tracing disabled"
	   fi
	   ;;
	*) usage;;
	esac
done
shift $(($OPTIND-1))

IFS="	
"

for arg do
	# Check first that all requested tests are available before running any
	command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; }
done

trap cleanup EXIT

# start clean
cleanup

HAVE_NH=no
ip nexthop ls >/dev/null 2>&1
[ $? -eq 0 ] && HAVE_NH=yes

name=""
desc=""
rerun_nh=0
for t in ${tests}; do
	[ "${name}" = "" ]	&& name="${t}"	&& continue
	[ "${desc}" = "" ]	&& desc="${t}"	&& continue

	if [ "${HAVE_NH}" = "yes" ]; then
		rerun_nh="${t}"
	fi

	run_this=1
	for arg do
		[ "${arg}" != "${arg#--*}" ] && continue
		[ "${arg}" = "${name}" ] && run_this=1 && break
		run_this=0
	done
	if [ $run_this -eq 1 ]; then
		run_test "${name}" "${desc}"
		# if test was skipped no need to retry with nexthop objects
		[ $? -eq 2 ] && rerun_nh=0

		if [ "${rerun_nh}" = "1" ]; then
			run_test_nh "${name}" "${desc}"
		fi
	fi
	name=""
	desc=""
	rerun_nh=0
done

exit ${exitcode}