Merge branch 'ICMP-error-handling-for-UDP-tunnels'

Stefano Brivio says:

====================
ICMP error handling for UDP tunnels

This series introduces ICMP error handling for UDP tunnels and
encapsulations and related selftests. We need to handle ICMP errors to
support PMTU discovery and route redirection -- this support is entirely
missing right now:

- patch 1/11 adds a socket lookup for UDP tunnels that use, by design,
  the same destination port on both endpoints -- i.e. VXLAN and GENEVE
- patches 2/11 to 7/11 are specific to VxLAN and GENEVE
- patches 8/11 and 9/11 add infrastructure for lookup of encapsulations
  where sent packets cannot be matched via receiving socket lookup, i.e.
  FoU and GUE
- patches 10/11 and 11/11 are specific to FoU and GUE

v2: changes are listed in the single patches
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 359 insertions, 18 deletions

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index a369d616b390..e2c94e47707c 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -26,6 +26,47 @@
 # - 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
@@ -72,6 +113,22 @@ 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_ipv4_vxlan4_exception	IPv4 over vxlan4: PMTU exceptions
+	pmtu_ipv6_vxlan4_exception	IPv6 over vxlan4: PMTU exceptions
+	pmtu_ipv4_vxlan6_exception	IPv4 over vxlan6: PMTU exceptions
+	pmtu_ipv6_vxlan6_exception	IPv6 over vxlan6: PMTU exceptions
+	pmtu_ipv4_geneve4_exception	IPv4 over geneve4: PMTU exceptions
+	pmtu_ipv6_geneve4_exception	IPv6 over geneve4: PMTU exceptions
+	pmtu_ipv4_geneve6_exception	IPv4 over geneve6: PMTU exceptions
+	pmtu_ipv6_geneve6_exception	IPv6 over geneve6: PMTU exceptions
+	pmtu_ipv4_fou4_exception	IPv4 over fou4: PMTU exceptions
+	pmtu_ipv6_fou4_exception	IPv6 over fou4: PMTU exceptions
+	pmtu_ipv4_fou6_exception	IPv4 over fou6: PMTU exceptions
+	pmtu_ipv6_fou6_exception	IPv6 over fou6: PMTU exceptions
+	pmtu_ipv4_gue4_exception	IPv4 over gue4: PMTU exceptions
+	pmtu_ipv6_gue4_exception	IPv6 over gue4: PMTU exceptions
+	pmtu_ipv4_gue6_exception	IPv4 over gue6: PMTU exceptions
+	pmtu_ipv6_gue6_exception	IPv6 over gue6: PMTU exceptions
 	pmtu_vti6_exception		vti6: PMTU exceptions
 	pmtu_vti4_exception		vti4: PMTU exceptions
 	pmtu_vti4_default_mtu		vti4: default MTU assignment
@@ -95,8 +152,8 @@ ns_r2="ip netns exec ${NS_R2}"
 # Addresses are:
 # - IPv4: PREFIX4.SEGMENT.ID (/24)
 # - IPv6: PREFIX6:SEGMENT::ID (/64)
-prefix4="192.168"
-prefix6="fd00"
+prefix4="10.0"
+prefix6="fc00"
 a_r1=1
 a_r2=2
 b_r1=3
@@ -129,12 +186,12 @@ 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"
+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_addr="fc00:1000::0"
 dummy6_1_addr="fc00:1001::0"
@@ -159,6 +216,89 @@ 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
+
+	${ns_a} ip fou add port 5555 ipproto ${ipproto} || return 2
+	${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
+
+	${ns_b} ip fou add port 5556 ipproto ${ipproto}
+	${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
+		${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${encap}_a
+		${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${encap}_b
+	else
+		${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${encap}_a
+		${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${encap}_b
+	fi
+
+	${ns_a} ip link set ${encap}_a up
+	${ns_b} ip link set ${encap}_b up
+
+	sleep 1
+}
+
+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
@@ -202,11 +342,57 @@ setup_vti() {
 }
 
 setup_vti4() {
-	setup_vti 4 ${veth4_a_addr} ${veth4_b_addr} ${vti4_a_addr} ${vti4_b_addr} ${vti4_mask}
+	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} ${vti6_a_addr} ${vti6_b_addr} ${vti6_mask}
+	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
+
+	${ns_a} ip link add ${type}_a type ${type} id 1 ${opts_a} remote ${b_addr} ${opts} || return 1
+	${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts}
+
+	${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a
+	${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b
+
+	${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a
+	${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b
+
+	${ns_a} ip link set ${type}_a up
+	${ns_b} ip link set ${type}_b up
+
+	sleep 1
+}
+
+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() {
@@ -465,6 +651,161 @@ 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))
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
+
+	# Check that exception was created
+	pmtu="$(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))
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
+
+	# Check that exception was created
+	pmtu="$(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 \
@@ -484,14 +825,14 @@ test_pmtu_vti4_exception() {
 
 	# 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})"
+	${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${tunnel4_b_addr} > /dev/null
+	pmtu="$(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
-	${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})"
+	${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${tunnel4_b_addr} > /dev/null
+	pmtu="$(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)))"
 }
 
@@ -506,20 +847,20 @@ test_pmtu_vti6_exception() {
 	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
+	${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${tunnel6_b_addr} > /dev/null
 
 	# Check that exception was created
-	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	pmtu="$(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}" ${vti6_b_addr})"
+	pmtu="$(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}" ${vti6_b_addr})"
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
 	check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1
 
 	return ${fail}