Merge branch 'more-pmtu-selftests'

Sabrina Dubroca says:

====================
selftests: add more PMTU tests

The current selftests for PMTU cover VTI tunnels, but there's nothing
about the generation and handling of PMTU exceptions by intermediate
routers. This series adds and improves existing helpers, then adds
IPv4 and IPv6 selftests with a setup involving an intermediate router.

Joint work with Stefano Brivio.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

tools/testing/selftests/net/pmtu.sh

@@ -6,6 +6,26 @@
 #
 # 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--------------.	a_r2: 1500
+#	A                               B	a_r3: 2000
+#	'--------------R2--------------'	a_r4: 1400
+#	  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_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
@@ -50,6 +70,8 @@ ksft_skip=4
 which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
 
 tests="
+	pmtu_ipv4_exception		ipv4: PMTU exceptions
+	pmtu_ipv6_exception		ipv6: PMTU exceptions
 	pmtu_vti6_exception		vti6: PMTU exceptions
 	pmtu_vti4_exception		vti4: PMTU exceptions
 	pmtu_vti4_default_mtu		vti4: default MTU assignment
@@ -60,8 +82,45 @@ tests="
 
 NS_A="ns-$(mktemp -u XXXXXX)"
 NS_B="ns-$(mktemp -u XXXXXX)"
+NS_R1="ns-$(mktemp -u XXXXXX)"
+NS_R2="ns-$(mktemp -u XXXXXX)"
 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="192.168"
+prefix6="fd00"
+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
+"
 
 veth4_a_addr="192.168.1.1"
 veth4_b_addr="192.168.1.2"
@@ -94,9 +153,15 @@ err_flush() {
 	err_buf=
 }
 
+# Find the auto-generated name for this namespace
+nsname() {
+	eval echo \$NS_$1
+}
+
 setup_namespaces() {
-	ip netns add ${NS_A} || return 1
-	ip netns add ${NS_B}
+	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
+		ip netns add ${n} || return 1
+	done
 }
 
 setup_veth() {
@@ -167,6 +232,49 @@ setup_xfrm6() {
 	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr}
 }
 
+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
+
+	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 ${gw}
+
+		ns=""; addr=""; gw=""
+	done
+}
+
 setup() {
 	[ "$(id -u)" -ne 0 ] && echo "  need to run as root" && return $ksft_skip
 
@@ -178,8 +286,9 @@ setup() {
 
 cleanup() {
 	[ ${cleanup_done} -eq 1 ] && return
-	ip netns del ${NS_A} 2> /dev/null
-	ip netns del ${NS_B} 2> /dev/null
+	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
+		ip netns del ${n} 2> /dev/null
+	done
 	cleanup_done=1
 }
 
@@ -196,7 +305,9 @@ mtu_parse() {
 
 	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
 }
@@ -229,6 +340,109 @@ route_get_dst_pmtu_from_exception() {
 	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
+
+	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
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst1} > /dev/null
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst2} > /dev/null
+
+	# Check that exceptions have been created with the correct PMTU
+	pmtu_1="$(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
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null
+	pmtu_2="$(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
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null
+	pmtu_2="$(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_vti4_exception() {
 	setup namespaces veth vti4 xfrm4 || return 2
 
@@ -248,24 +462,13 @@ test_pmtu_vti4_exception() {
 	# 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}" ${vti4_b_addr})"
-	if [ "${pmtu}" != "" ]; then
-		err "  unexpected exception created with PMTU ${pmtu} for IP payload length ${esp_payload_rfc4106}"
-		return 1
-	fi
+	check_pmtu_value "" "${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}" ${vti4_b_addr})"
-	if [ "${pmtu}" = "" ]; then
-		err "  exception not created for IP payload length $((esp_payload_rfc4106 + 1))"
-		return 1
-	fi
-
-	# ...with the right PMTU value
-	if [ ${pmtu} -ne ${esp_payload_rfc4106} ]; then
-		err "  wrong PMTU ${pmtu} in exception, expected: ${esp_payload_rfc4106}"
-		return 1
-	fi
+	check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
 }
 
 test_pmtu_vti6_exception() {
@@ -280,25 +483,18 @@ test_pmtu_vti6_exception() {
 	${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null
 
 	# Check that exception was created
-	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" = "" ]; then
-		err "  tunnel exceeding link layer MTU didn't create route exception"
-		return 1
-	fi
+	pmtu="$(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 "${ns_a}" vti6_a 3000
-
-	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 3000 ]; then
-		err "  decreasing tunnel MTU didn't decrease route exception PMTU"
-		fail=1
-	fi
+	pmtu="$(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 "${ns_a}" vti6_a 9000
-	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 9000 ]; then
-		err "  increasing tunnel MTU didn't increase route exception PMTU"
-		fail=1
-	fi
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1
 
 	return ${fail}
 }