summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/net/pmtu.sh
blob: 6c38a7637744e576428fec89b449023e095155c0 (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
#!/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_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

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

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

tests="
	pmtu_vti6_exception		vti6: PMTU exceptions
	pmtu_vti4_exception		vti4: PMTU exceptions
	pmtu_vti4_default_mtu		vti4: default MTU assignment
	pmtu_vti6_default_mtu		vti6: default MTU assignment
	pmtu_vti4_link_add_mtu		vti4: MTU setting on link creation
	pmtu_vti6_link_add_mtu		vti6: MTU setting on link creation
	pmtu_vti6_link_change_mtu	vti6: MTU changes on link changes"

NS_A="ns-$(mktemp -u XXXXXX)"
NS_B="ns-$(mktemp -u XXXXXX)"
ns_a="ip netns exec ${NS_A}"
ns_b="ip netns exec ${NS_B}"

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"

vti4_a_addr="192.168.2.1"
vti4_b_addr="192.168.2.2"
vti4_mask="24"
vti6_a_addr="fd00:2::a"
vti6_b_addr="fd00:2::b"
vti6_mask="64"

dummy6_0_addr="fc00:1000::0"
dummy6_1_addr="fc00:1001::0"
dummy6_mask="64"

cleanup_done=1
err_buf=

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

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

setup_namespaces() {
	ip netns add ${NS_A} || return 1
	ip netns add ${NS_B}
}

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

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

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

	${ns_a} ip link set veth_a up
	${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"

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

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

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

	sleep 1
}

setup_vti4() {
	setup_vti 4 ${veth4_a_addr} ${veth4_b_addr} ${vti4_a_addr} ${vti4_b_addr} ${vti4_mask}
}

setup_vti6() {
	setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${vti6_a_addr} ${vti6_b_addr} ${vti6_mask}
}

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

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

	${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
	${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
	${ns_b} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel
	${ns_b} ip -${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() {
	[ "$(id -u)" -ne 0 ] && echo "  need to run as root" && return $ksft_skip

	cleanup_done=0
	for arg do
		eval setup_${arg} || { echo "  ${arg} not supported"; return 1; }
	done
}

cleanup() {
	[ ${cleanup_done} -eq 1 ] && return
	ip netns del ${NS_A} 2> /dev/null
	ip netns del ${NS_B} 2> /dev/null
	cleanup_done=1
}

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
		[ ${next} -eq 1 ] && echo "${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_vti4_exception() {
	setup namespaces veth vti4 xfrm4 || return 2

	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
	${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${vti4_b_addr} > /dev/null
	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
	check_pmtu_value "" "${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
	${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${vti4_b_addr} > /dev/null
	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
	check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
}

test_pmtu_vti6_exception() {
	setup namespaces veth vti6 xfrm6 || return 2
	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
	${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null

	# Check that exception was created
	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
	check_pmtu_value any "${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}" ${vti6_b_addr})"
	check_pmtu_value "3000" "${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}" ${vti6_b_addr})"
	check_pmtu_value "9000" "${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

	${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
	${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
		${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10 2>/dev/null
		# 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
		${ns_a} ip link del vti4_a
	done

	# Now check valid values
	for v in ${min} 1300 ${max}; do
		${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)"
		${ns_a} ip link del vti4_a
		if [ "${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

	${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
	${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
		${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10 2>/dev/null
		# 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
		${ns_a} ip link del vti6_a
	done

	# Now check valid values
	for v in 68 1280 1300 $((65535 - 40)); do
		${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)"
		${ns_a} ip link del vti6_a
		if [ "${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

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

	${ns_a} ip addr add ${dummy6_0_addr}/${dummy6_mask} dev dummy0
	${ns_a} ip addr add ${dummy6_1_addr}/${dummy6_mask} dev dummy1

	fail=0

	# Create vti6 interface bound to device, passing MTU, check it
	${ns_a} ip link add vti6_a mtu 1300 type vti6 remote ${dummy6_0_addr} local ${dummy6_0_addr}
	mtu="$(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
	${ns_a} ip link set vti6_a type vti6 remote ${dummy6_1_addr} local ${dummy6_1_addr}
	mtu="$(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
	${ns_a} ip link set vti6_a mtu 1280 type vti6 remote ${dummy6_0_addr} local ${dummy6_0_addr}
	mtu="$(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}
}

trap cleanup EXIT

exitcode=0
desc=0
IFS="	
"
for t in ${tests}; do
	[ $desc -eq 0 ] && name="${t}" && desc=1 && continue || desc=0

	(
		unset IFS
		eval test_${name}
		ret=$?
		cleanup

		if [ $ret -eq 0 ]; then
			printf "TEST: %-60s  [ OK ]\n" "${t}"
		elif [ $ret -eq 1 ]; then
			printf "TEST: %-60s  [FAIL]\n" "${t}"
			err_flush
			exit 1
		elif [ $ret -eq 2 ]; then
			printf "TEST: %-60s  [SKIP]\n" "${t}"
			err_flush
		fi
	)
	[ $? -ne 0 ] && exitcode=1
done

exit ${exitcode}