diff options
Diffstat (limited to 'tools/testing/selftests/net')
33 files changed, 2624 insertions, 154 deletions
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index f8f3e90700c0..1e6d14d2825c 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -21,6 +21,6 @@ TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls KSFT_KHDR_INSTALL := 1 include ../lib.mk -$(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma +$(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma $(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread $(OUTPUT)/tcp_inq: LDFLAGS += -lpthread diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 5821bdd98d20..e9c860d00416 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -17,8 +17,7 @@ CONFIG_VLAN_8021Q=y CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y CONFIG_NF_CONNTRACK=m -CONFIG_NF_NAT_IPV6=m -CONFIG_NF_NAT_IPV4=m +CONFIG_NF_NAT=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP6_NF_NAT=m diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 802b4af18729..1080ff55a788 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -388,6 +388,7 @@ fib_carrier_unicast_test() set -e $IP link set dev dummy0 carrier off + sleep 1 set +e echo " Carrier down" diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh index d8313d0438b7..b90dff8d3a94 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh @@ -1,7 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding" +ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn" NUM_NETIFS=4 CHECK_TC="yes" source lib.sh @@ -96,6 +96,51 @@ flooding() flood_test $swp2 $h1 $h2 } +vlan_deletion() +{ + # Test that the deletion of a VLAN on a bridge port does not affect + # the PVID VLAN + log_info "Add and delete a VLAN on bridge port $swp1" + + bridge vlan add vid 10 dev $swp1 + bridge vlan del vid 10 dev $swp1 + + ping_ipv4 + ping_ipv6 +} + +extern_learn() +{ + local mac=de:ad:be:ef:13:37 + local ageing_time + + # Test that externally learned FDB entries can roam, but not age out + RET=0 + + bridge fdb add de:ad:be:ef:13:37 dev $swp1 master extern_learn vlan 1 + + bridge fdb show brport $swp1 | grep -q de:ad:be:ef:13:37 + check_err $? "Did not find FDB entry when should" + + # Wait for 10 seconds after the ageing time to make sure the FDB entry + # was not aged out + ageing_time=$(bridge_ageing_time_get br0) + sleep $((ageing_time + 10)) + + bridge fdb show brport $swp1 | grep -q de:ad:be:ef:13:37 + check_err $? "FDB entry was aged out when should not" + + $MZ $h2 -c 1 -p 64 -a $mac -t ip -q + + bridge fdb show brport $swp2 | grep -q de:ad:be:ef:13:37 + check_err $? "FDB entry did not roam when should" + + log_test "Externally learned FDB entry - ageing & roaming" + + bridge fdb del de:ad:be:ef:13:37 dev $swp2 master vlan 1 &> /dev/null + bridge fdb del de:ad:be:ef:13:37 dev $swp1 master vlan 1 &> /dev/null +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config index 5cd2aed97958..da96eff72a8e 100644 --- a/tools/testing/selftests/net/forwarding/config +++ b/tools/testing/selftests/net/forwarding/config @@ -10,3 +10,5 @@ CONFIG_NET_CLS_FLOWER=m CONFIG_NET_SCH_INGRESS=m CONFIG_NET_ACT_GACT=m CONFIG_VETH=m +CONFIG_NAMESPACES=y +CONFIG_NET_NS=y diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh index 5ab1e5f43022..57cf8914910d 100644 --- a/tools/testing/selftests/net/forwarding/devlink_lib.sh +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -32,7 +32,7 @@ DEVLINK_VIDDID=$(lspci -s $(echo $DEVLINK_DEV | cut -d"/" -f2) \ ############################################################################## # Sanity checks -devlink -j resource show "$DEVLINK_DEV" &> /dev/null +devlink help 2>&1 | grep resource &> /dev/null if [ $? -ne 0 ]; then echo "SKIP: iproute2 too old, missing devlink resource support" exit 1 diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index e819d049d9ce..e2adb533c8fc 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -33,3 +33,6 @@ PAUSE_ON_CLEANUP=no NETIF_TYPE=veth # Whether to create virtual interfaces (veth) or not NETIF_CREATE=yes +# Timeout (in seconds) before ping exits regardless of how many packets have +# been sent or received +PING_TIMEOUT=5 diff --git a/tools/testing/selftests/net/forwarding/ipip_flat_gre.sh b/tools/testing/selftests/net/forwarding/ipip_flat_gre.sh new file mode 100755 index 000000000000..abb694397b86 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ipip_flat_gre.sh @@ -0,0 +1,63 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnel without key. +# This test uses flat topology for IP tunneling tests. See ipip_lib.sh for more +# details. + +ALL_TESTS="gre_flat4 gre_mtu_change" + +NUM_NETIFS=6 +source lib.sh +source ipip_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_flat_create gre $ol1 $ul1 + sw2_flat_create gre $ol2 $ul2 +} + +gre_flat4() +{ + RET=0 + + ping_test $h1 192.0.2.18 " gre flat" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_flat_destroy $ol2 $ul2 + sw1_flat_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ipip_flat_gre_key.sh b/tools/testing/selftests/net/forwarding/ipip_flat_gre_key.sh new file mode 100755 index 000000000000..c4f373337e48 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ipip_flat_gre_key.sh @@ -0,0 +1,63 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnel with key. +# This test uses flat topology for IP tunneling tests. See ipip_lib.sh for more +# details. + +ALL_TESTS="gre_flat4 gre_mtu_change" + +NUM_NETIFS=6 +source lib.sh +source ipip_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_flat_create gre $ol1 $ul1 key 233 + sw2_flat_create gre $ol2 $ul2 key 233 +} + +gre_flat4() +{ + RET=0 + + ping_test $h1 192.0.2.18 " gre flat with key" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_flat_destroy $ol2 $ul2 + sw1_flat_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ipip_flat_gre_keys.sh b/tools/testing/selftests/net/forwarding/ipip_flat_gre_keys.sh new file mode 100755 index 000000000000..a811130c0627 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ipip_flat_gre_keys.sh @@ -0,0 +1,63 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnel with key. +# This test uses flat topology for IP tunneling tests. See ipip_lib.sh for more +# details. + +ALL_TESTS="gre_flat4 gre_mtu_change" + +NUM_NETIFS=6 +source lib.sh +source ipip_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_flat_create gre $ol1 $ul1 ikey 111 okey 222 + sw2_flat_create gre $ol2 $ul2 ikey 222 okey 111 +} + +gre_flat4() +{ + RET=0 + + ping_test $h1 192.0.2.18 " gre flat with ikey/okey" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_flat_destroy $ol2 $ul2 + sw1_flat_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ipip_hier_gre.sh b/tools/testing/selftests/net/forwarding/ipip_hier_gre.sh new file mode 100755 index 000000000000..05c5b3cf2f78 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ipip_hier_gre.sh @@ -0,0 +1,63 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnels without key. +# This test uses hierarchical topology for IP tunneling tests. See +# ipip_lib.sh for more details. + +ALL_TESTS="gre_hier4 gre_mtu_change" + +NUM_NETIFS=6 +source lib.sh +source ipip_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_hierarchical_create gre $ol1 $ul1 + sw2_hierarchical_create gre $ol2 $ul2 +} + +gre_hier4() +{ + RET=0 + + ping_test $h1 192.0.2.18 " gre hierarchical" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_hierarchical_destroy $ol2 $ul2 + sw1_hierarchical_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ipip_hier_gre_key.sh b/tools/testing/selftests/net/forwarding/ipip_hier_gre_key.sh new file mode 100755 index 000000000000..9b105dbca32a --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ipip_hier_gre_key.sh @@ -0,0 +1,63 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnels without key. +# This test uses hierarchical topology for IP tunneling tests. See +# ipip_lib.sh for more details. + +ALL_TESTS="gre_hier4 gre_mtu_change" + +NUM_NETIFS=6 +source lib.sh +source ipip_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_hierarchical_create gre $ol1 $ul1 key 22 + sw2_hierarchical_create gre $ol2 $ul2 key 22 +} + +gre_hier4() +{ + RET=0 + + ping_test $h1 192.0.2.18 " gre hierarchical with key" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_hierarchical_destroy $ol2 $ul2 + sw1_hierarchical_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ipip_hier_gre_keys.sh b/tools/testing/selftests/net/forwarding/ipip_hier_gre_keys.sh new file mode 100755 index 000000000000..e275d25bd83a --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ipip_hier_gre_keys.sh @@ -0,0 +1,63 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnels without key. +# This test uses hierarchical topology for IP tunneling tests. See +# ipip_lib.sh for more details. + +ALL_TESTS="gre_hier4 gre_mtu_change" + +NUM_NETIFS=6 +source lib.sh +source ipip_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_hierarchical_create gre $ol1 $ul1 ikey 111 okey 222 + sw2_hierarchical_create gre $ol2 $ul2 ikey 222 okey 111 +} + +gre_hier4() +{ + RET=0 + + ping_test $h1 192.0.2.18 " gre hierarchical with ikey/okey" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_hierarchical_destroy $ol2 $ul2 + sw1_hierarchical_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ipip_lib.sh b/tools/testing/selftests/net/forwarding/ipip_lib.sh new file mode 100644 index 000000000000..30f36a57bae6 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ipip_lib.sh @@ -0,0 +1,349 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Handles creation and destruction of IP-in-IP or GRE tunnels over the given +# topology. Supports both flat and hierarchical models. +# +# Flat Model: +# Overlay and underlay share the same VRF. +# SW1 uses default VRF so tunnel has no bound dev. +# SW2 uses non-default VRF tunnel has a bound dev. +# +-------------------------+ +# | H1 | +# | $h1 + | +# | 192.0.2.1/28 | | +# +-------------------|-----+ +# | +# +-------------------|-----+ +# | SW1 | | +# | $ol1 + | +# | 192.0.2.2/28 | +# | | +# | + g1a (gre) | +# | loc=192.0.2.65 | +# | rem=192.0.2.66 --. | +# | tos=inherit | | +# | .------------------' | +# | | | +# | v | +# | + $ul1.111 (vlan) | +# | | 192.0.2.129/28 | +# | \ | +# | \_______ | +# | | | +# |VRF default + $ul1 | +# +------------|------------+ +# | +# +------------|------------+ +# | SW2 + $ul2 | +# | _______| | +# | / | +# | / | +# | + $ul2.111 (vlan) | +# | ^ 192.0.2.130/28 | +# | | | +# | | | +# | '------------------. | +# | + g2a (gre) | | +# | loc=192.0.2.66 | | +# | rem=192.0.2.65 --' | +# | tos=inherit | +# | | +# | $ol2 + | +# | 192.0.2.17/28 | | +# | VRF v$ol2 | | +# +-------------------|-----+ +# | +# +-------------------|-----+ +# | H2 | | +# | $h2 + | +# | 192.0.2.18/28 | +# +-------------------------+ +# +# Hierarchical model: +# The tunnel is bound to a device in a different VRF +# +# +---------------------------+ +# | H1 | +# | $h1 + | +# | 192.0.2.1/28 | | +# +-------------------|-------+ +# | +# +-------------------|-------+ +# | SW1 | | +# | +-----------------|-----+ | +# | | $ol1 + | | +# | | 192.0.2.2/28 | | +# | | | | +# | | + g1a (gre) | | +# | | rem=192.0.2.66 | | +# | | tos=inherit | | +# | | loc=192.0.2.65 | | +# | | ^ | | +# | | VRF v$ol1 | | | +# | +-----------|-----------+ | +# | | | +# | +-----------|-----------+ | +# | | VRF v$ul1 | | | +# | | | | | +# | | | | | +# | | v | | +# | | dummy1 + | | +# | | 192.0.2.65 | | +# | | .-------' | | +# | | | | | +# | | v | | +# | | + $ul1.111 (vlan) | | +# | | | 192.0.2.129/28 | | +# | | \ | | +# | | \_____ | | +# | | | | | +# | | + $ul1 | | +# | +----------|------------+ | +# +------------|--------------+ +# | +# +------------|--------------+ +# | SW2 | | +# | +----------|------------+ | +# | | + $ul2 | | +# | | _____| | | +# | | / | | +# | | / | | +# | | | $ul2.111 (vlan) | | +# | | + 192.0.2.130/28 | | +# | | ^ | | +# | | | | | +# | | '-------. | | +# | | dummy2 + | | +# | | 192.0.2.66 | | +# | | ^ | | +# | | | | | +# | | | | | +# | | VRF v$ul2 | | | +# | +-----------|-----------+ | +# | | | +# | +-----------|-----------+ | +# | | VRF v$ol2 | | | +# | | | | | +# | | v | | +# | | g2a (gre)+ | | +# | | loc=192.0.2.66 | | +# | | rem=192.0.2.65 | | +# | | tos=inherit | | +# | | | | +# | | $ol2 + | | +# | | 192.0.2.17/28 | | | +# | +-----------------|-----+ | +# +-------------------|-------+ +# | +# +-------------------|-------+ +# | H2 | | +# | $h2 + | +# | 192.0.2.18/28 | +# +---------------------------+ +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 + ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2 +} + +h1_destroy() +{ + ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2 + simple_if_fini $h1 192.0.2.1/28 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.18/28 + ip route add vrf v$h2 192.0.2.0/28 via 192.0.2.17 +} + +h2_destroy() +{ + ip route del vrf v$h2 192.0.2.0/28 via 192.0.2.17 + simple_if_fini $h2 192.0.2.18/28 +} + +sw1_flat_create() +{ + local type=$1; shift + local ol1=$1; shift + local ul1=$1; shift + + ip link set dev $ol1 up + __addr_add_del $ol1 add "192.0.2.2/28" + + ip link set dev $ul1 up + vlan_create $ul1 111 "" 192.0.2.129/28 + + tunnel_create g1a $type 192.0.2.65 192.0.2.66 tos inherit "$@" + ip link set dev g1a up + __addr_add_del g1a add "192.0.2.65/32" + + ip route add 192.0.2.66/32 via 192.0.2.130 + + ip route add 192.0.2.16/28 nexthop dev g1a +} + +sw1_flat_destroy() +{ + local ol1=$1; shift + local ul1=$1; shift + + ip route del 192.0.2.16/28 + + ip route del 192.0.2.66/32 via 192.0.2.130 + __simple_if_fini g1a 192.0.2.65/32 + tunnel_destroy g1a + + vlan_destroy $ul1 111 + __simple_if_fini $ul1 + __simple_if_fini $ol1 192.0.2.2/28 +} + +sw2_flat_create() +{ + local type=$1; shift + local ol2=$1; shift + local ul2=$1; shift + + simple_if_init $ol2 192.0.2.17/28 + __simple_if_init $ul2 v$ol2 + vlan_create $ul2 111 v$ol2 192.0.2.130/28 + + tunnel_create g2a $type 192.0.2.66 192.0.2.65 tos inherit dev v$ol2 \ + "$@" + __simple_if_init g2a v$ol2 192.0.2.66/32 + + ip route add vrf v$ol2 192.0.2.65/32 via 192.0.2.129 + ip route add vrf v$ol2 192.0.2.0/28 nexthop dev g2a +} + +sw2_flat_destroy() +{ + local ol2=$1; shift + local ul2=$1; shift + + ip route del vrf v$ol2 192.0.2.0/28 + + ip route del vrf v$ol2 192.0.2.65/32 via 192.0.2.129 + __simple_if_fini g2a 192.0.2.66/32 + tunnel_destroy g2a + + vlan_destroy $ul2 111 + __simple_if_fini $ul2 + simple_if_fini $ol2 192.0.2.17/28 +} + +sw1_hierarchical_create() +{ + local type=$1; shift + local ol1=$1; shift + local ul1=$1; shift + + simple_if_init $ol1 192.0.2.2/28 + simple_if_init $ul1 + ip link add name dummy1 type dummy + __simple_if_init dummy1 v$ul1 192.0.2.65/32 + + vlan_create $ul1 111 v$ul1 192.0.2.129/28 + tunnel_create g1a $type 192.0.2.65 192.0.2.66 tos inherit dev dummy1 \ + "$@" + ip link set dev g1a master v$ol1 + + ip route add vrf v$ul1 192.0.2.66/32 via 192.0.2.130 + ip route add vrf v$ol1 192.0.2.16/28 nexthop dev g1a +} + +sw1_hierarchical_destroy() +{ + local ol1=$1; shift + local ul1=$1; shift + + ip route del vrf v$ol1 192.0.2.16/28 + ip route del vrf v$ul1 192.0.2.66/32 + + tunnel_destroy g1a + vlan_destroy $ul1 111 + + __simple_if_fini dummy1 192.0.2.65/32 + ip link del dev dummy1 + + simple_if_fini $ul1 + simple_if_fini $ol1 192.0.2.2/28 +} + +sw2_hierarchical_create() +{ + local type=$1; shift + local ol2=$1; shift + local ul2=$1; shift + + simple_if_init $ol2 192.0.2.17/28 + simple_if_init $ul2 + + ip link add name dummy2 type dummy + __simple_if_init dummy2 v$ul2 192.0.2.66/32 + + vlan_create $ul2 111 v$ul2 192.0.2.130/28 + tunnel_create g2a $type 192.0.2.66 192.0.2.65 tos inherit dev dummy2 \ + "$@" + ip link set dev g2a master v$ol2 + + ip route add vrf v$ul2 192.0.2.65/32 via 192.0.2.129 + ip route add vrf v$ol2 192.0.2.0/28 nexthop dev g2a +} + +sw2_hierarchical_destroy() +{ + local ol2=$1; shift + local ul2=$1; shift + + ip route del vrf v$ol2 192.0.2.0/28 + ip route del vrf v$ul2 192.0.2.65/32 + + tunnel_destroy g2a + vlan_destroy $ul2 111 + + __simple_if_fini dummy2 192.0.2.66/32 + ip link del dev dummy2 + + simple_if_fini $ul2 + simple_if_fini $ol2 192.0.2.17/28 +} + +topo_mtu_change() +{ + local mtu=$1 + + ip link set mtu $mtu dev $h1 + ip link set mtu $mtu dev $ol1 + ip link set mtu $mtu dev g1a + ip link set mtu $mtu dev $ul1 + ip link set mtu $mtu dev $ul1.111 + ip link set mtu $mtu dev $h2 + ip link set mtu $mtu dev $ol2 + ip link set mtu $mtu dev g2a + ip link set mtu $mtu dev $ul2 + ip link set mtu $mtu dev $ul2.111 +} + +test_mtu_change() +{ + local encap=$1; shift + + RET=0 + + ping_do $h1 192.0.2.18 "-s 1800 -w 3" + check_fail $? "ping $encap should not pass with size 1800" + + RET=0 + + topo_mtu_change 2000 + ping_do $h1 192.0.2.18 "-s 1800 -w 3" + check_err $? + log_test "ping $encap packet size 1800 after MTU change" +} diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 3f248d1f5b91..9385dc971269 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -17,6 +17,7 @@ NETIF_TYPE=${NETIF_TYPE:=veth} NETIF_CREATE=${NETIF_CREATE:=yes} MCD=${MCD:=smcrouted} MC_CLI=${MC_CLI:=smcroutectl} +PING_TIMEOUT=${PING_TIMEOUT:=5} relative_path="${BASH_SOURCE%/*}" if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then @@ -211,7 +212,7 @@ log_test() return 1 fi - printf "TEST: %-60s [PASS]\n" "$test_name $opt_str" + printf "TEST: %-60s [ OK ]\n" "$test_name $opt_str" return 0 } @@ -820,7 +821,8 @@ ping_do() local vrf_name vrf_name=$(master_name_get $if_name) - ip vrf exec $vrf_name $PING $args $dip -c 10 -i 0.1 -w 2 &> /dev/null + ip vrf exec $vrf_name \ + $PING $args $dip -c 10 -i 0.1 -w $PING_TIMEOUT &> /dev/null } ping_test() @@ -840,7 +842,8 @@ ping6_do() local vrf_name vrf_name=$(master_name_get $if_name) - ip vrf exec $vrf_name $PING6 $args $dip -c 10 -i 0.1 -w 2 &> /dev/null + ip vrf exec $vrf_name \ + $PING6 $args $dip -c 10 -i 0.1 -w $PING_TIMEOUT &> /dev/null } ping6_test() diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh index 61844caf671e..28d568c48a73 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh @@ -190,6 +190,8 @@ setup_prepare() h4_create switch_create + forwarding_enable + trap_install $h3 ingress trap_install $h4 ingress } @@ -201,6 +203,8 @@ cleanup() trap_uninstall $h4 ingress trap_uninstall $h3 ingress + forwarding_restore + switch_destroy h4_destroy h3_destroy @@ -220,11 +224,15 @@ test_lag_slave() RET=0 + tc filter add dev $swp1 ingress pref 999 \ + proto 802.1q flower vlan_ethtype arp $tcflags \ + action pass mirror_install $swp1 ingress gt4 \ - "proto 802.1q flower vlan_id 333 $tcflags" + "proto 802.1q flower vlan_id 333 $tcflags" # Test connectivity through $up_dev when $down_dev is set down. ip link set dev $down_dev down + ip neigh flush dev br1 setup_wait_dev $up_dev setup_wait_dev $host_dev $ARPING -I br1 192.0.2.130 -qfc 1 @@ -240,6 +248,7 @@ test_lag_slave() ip link set dev $up_dev up ip link set dev $down_dev up mirror_uninstall $swp1 ingress + tc filter del dev $swp1 ingress pref 999 log_test "$what ($tcflags)" } diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh index 135902aa8b11..472bd023e2a5 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh @@ -79,6 +79,7 @@ test_span_gre_ttl() mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 0 ip link set dev $tundev type $type ttl 50 + sleep 2 mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10 ip link set dev $tundev type $type ttl 100 diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh b/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh index 12914f40612d..09389f3b9369 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh @@ -81,6 +81,8 @@ full_test_span_gre_dir_acl() local match_dip=$1; shift local what=$1; shift + RET=0 + mirror_install $swp1 $direction $tundev \ "protocol ip flower $tcflags dst_ip $match_dip" fail_test_span_gre_dir $tundev $direction @@ -108,8 +110,6 @@ test_ip6gretap() test_all() { - RET=0 - slow_path_trap_install $swp1 ingress slow_path_trap_install $swp1 egress diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh index 204b25f13934..c02291e9841e 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh @@ -1,11 +1,44 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# This test uses standard topology for testing gretap. See -# mirror_gre_topo_lib.sh for more details. -# # Test for "tc action mirred egress mirror" when the underlay route points at a # vlan device on top of a bridge device with vlan filtering (802.1q). +# +# +---------------------+ +---------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +-----|---------------+ +---------------|-----+ +# | | +# +-----|-------------------------------------------------------------|-----+ +# | SW o--> mirred egress mirror dev {gt4,gt6} | | +# | | | | +# | +---|-------------------------------------------------------------|---+ | +# | | + $swp1 br1 $swp2 + | | +# | | | | +# | | + $swp3 | | +# | +---|-----------------------------------------------------------------+ | +# | | | | +# | | + br1.555 | +# | | 192.0.2.130/28 | +# | | 2001:db8:2::2/64 | +# | | | +# | | + gt6 (ip6gretap) + gt4 (gretap) | +# | | : loc=2001:db8:2::1 : loc=192.0.2.129 | +# | | : rem=2001:db8:2::2 : rem=192.0.2.130 | +# | | : ttl=100 : ttl=100 | +# | | : tos=inherit : tos=inherit | +# | | : : | +# +-----|---------------------:----------------------:----------------------+ +# | : : +# +-----|---------------------:----------------------:----------------------+ +# | H3 + $h3 + h3-gt6 (ip6gretap) + h3-gt4 (gretap) | +# | | loc=2001:db8:2::2 loc=192.0.2.130 | +# | + $h3.555 rem=2001:db8:2::1 rem=192.0.2.129 | +# | 192.0.2.130/28 ttl=100 ttl=100 | +# | 2001:db8:2::2/64 tos=inherit tos=inherit | +# | | +# +-------------------------------------------------------------------------+ ALL_TESTS=" test_gretap @@ -30,6 +63,15 @@ source mirror_gre_topo_lib.sh require_command $ARPING +h3_addr_add_del() +{ + local add_del=$1; shift + local dev=$1; shift + + ip addr $add_del dev $dev 192.0.2.130/28 + ip addr $add_del dev $dev 2001:db8:2::2/64 +} + setup_prepare() { h1=${NETIFS[p1]} @@ -55,7 +97,8 @@ setup_prepare() ip route rep 192.0.2.130/32 dev br1.555 ip -6 route rep 2001:db8:2::2/128 dev br1.555 - vlan_create $h3 555 v$h3 192.0.2.130/28 2001:db8:2::2/64 + vlan_create $h3 555 v$h3 + h3_addr_add_del add $h3.555 ip link set dev $swp3 master br1 bridge vlan add dev $swp3 vid 555 @@ -68,6 +111,8 @@ cleanup() ip link set dev $swp2 nomaster ip link set dev $swp3 nomaster + + h3_addr_add_del del $h3.555 vlan_destroy $h3 555 vlan_destroy br1 555 @@ -182,13 +227,19 @@ test_span_gre_untagged_egress() quick_test_span_gre_dir $tundev ingress quick_test_span_vlan_dir $h3 555 ingress + h3_addr_add_del del $h3.555 bridge vlan add dev $swp3 vid 555 pvid untagged - sleep 1 + h3_addr_add_del add $h3 + sleep 5 + quick_test_span_gre_dir $tundev ingress fail_test_span_vlan_dir $h3 555 ingress + h3_addr_add_del del $h3 bridge vlan add dev $swp3 vid 555 - sleep 1 + h3_addr_add_del add $h3.555 + sleep 5 + quick_test_span_gre_dir $tundev ingress quick_test_span_vlan_dir $h3 555 ingress @@ -218,12 +269,25 @@ test_span_gre_fdb_roaming() mirror_install $swp1 ingress $tundev "matchall $tcflags" quick_test_span_gre_dir $tundev ingress - bridge fdb del dev $swp3 $h3mac vlan 555 master - bridge fdb add dev $swp2 $h3mac vlan 555 master - sleep 1 - fail_test_span_gre_dir $tundev ingress - - bridge fdb del dev $swp2 $h3mac vlan 555 master + while ((RET == 0)); do + bridge fdb del dev $swp3 $h3mac vlan 555 master 2>/dev/null + bridge fdb add dev $swp2 $h3mac vlan 555 master + sleep 1 + fail_test_span_gre_dir $tundev ingress + + if ! bridge fdb sh dev $swp2 vlan 555 master \ + | grep -q $h3mac; then + printf "TEST: %-60s [RETRY]\n" \ + "$what: MAC roaming ($tcflags)" + # ARP or ND probably reprimed the FDB while the test + # was running. We would get a spurious failure. + RET=0 + continue + fi + break + done + + bridge fdb del dev $swp2 $h3mac vlan 555 master 2>/dev/null # Re-prime FDB $ARPING -I br1.555 192.0.2.130 -fqc 1 sleep 1 diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh index 07991e1025c7..00797597fcf5 100644 --- a/tools/testing/selftests/net/forwarding/mirror_lib.sh +++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh @@ -29,9 +29,12 @@ mirror_test() local pref=$1; shift local expect=$1; shift + local ping_timeout=$((PING_TIMEOUT * 5)) local t0=$(tc_rule_stats_get $dev $pref) ip vrf exec $vrf_name \ - ${PING} ${sip:+-I $sip} $dip -c 10 -i 0.1 -w 2 &> /dev/null + ${PING} ${sip:+-I $sip} $dip -c 10 -i 0.5 -w $ping_timeout \ + &> /dev/null + sleep 0.5 local t1=$(tc_rule_stats_get $dev $pref) local delta=$((t1 - t0)) # Tolerate a couple stray extra packets. diff --git a/tools/testing/selftests/net/forwarding/router_broadcast.sh b/tools/testing/selftests/net/forwarding/router_broadcast.sh index 7bd2ebb6e9de..9a678ece32b4 100755 --- a/tools/testing/selftests/net/forwarding/router_broadcast.sh +++ b/tools/testing/selftests/net/forwarding/router_broadcast.sh @@ -170,7 +170,8 @@ ping_test_from() log_info "ping $dip, expected reply from $from" ip vrf exec $(master_name_get $oif) \ - $PING -I $oif $dip -c 10 -i 0.1 -w 2 -b 2>&1 | grep $from &> /dev/null + $PING -I $oif $dip -c 10 -i 0.1 -w $PING_TIMEOUT -b 2>&1 \ + | grep $from &> /dev/null check_err_fail $fail $? } diff --git a/tools/testing/selftests/net/forwarding/vxlan_asymmetric.sh b/tools/testing/selftests/net/forwarding/vxlan_asymmetric.sh new file mode 100755 index 000000000000..a0b5f57d6bd3 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/vxlan_asymmetric.sh @@ -0,0 +1,567 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +---------------------------+ +------------------------------+ +# | vrf-h1 | | vrf-h2 | +# | + $h1 | | + $h2 | +# | | 10.1.1.101/24 | | | 10.1.2.101/24 | +# | | default via 10.1.1.1 | | | default via 10.1.2.1 | +# +----|----------------------+ +----|-------------------------+ +# | | +# +----|--------------------------------------------|-------------------------+ +# | SW | | | +# | +--|--------------------------------------------|-----------------------+ | +# | | + $swp1 br1 + $swp2 | | +# | | vid 10 pvid untagged vid 20 pvid untagged | | +# | | | | +# | | + vx10 + vx20 | | +# | | local 10.0.0.1 local 10.0.0.1 | | +# | | remote 10.0.0.2 remote 10.0.0.2 | | +# | | id 1000 id 2000 | | +# | | dstport 4789 dstport 4789 | | +# | | vid 10 pvid untagged vid 20 pvid untagged | | +# | | | | +# | +-----------------------------------+-----------------------------------+ | +# | | | +# | +-----------------------------------|-----------------------------------+ | +# | | | | | +# | | +--------------------------------+--------------------------------+ | | +# | | | | | | +# | | + vlan10 vlan20 + | | +# | | | 10.1.1.11/24 10.1.2.11/24 | | | +# | | | | | | +# | | + vlan10-v (macvlan) vlan20-v (macvlan) + | | +# | | 10.1.1.1/24 10.1.2.1/24 | | +# | | 00:00:5e:00:01:01 00:00:5e:00:01:01 | | +# | | vrf-green | | +# | +-----------------------------------------------------------------------+ | +# | | +# | + $rp1 +lo | +# | | 192.0.2.1/24 10.0.0.1/32 | +# +----|----------------------------------------------------------------------+ +# | +# +----|--------------------------------------------------------+ +# | | vrf-spine | +# | + $rp2 | +# | 192.0.2.2/24 | +# | | (maybe) HW +# ============================================================================= +# | | (likely) SW +# | | +# | + v1 (veth) | +# | | 192.0.3.2/24 | +# +----|--------------------------------------------------------+ +# | +# +----|----------------------------------------------------------------------+ +# | + v2 (veth) +lo NS1 (netns) | +# | 192.0.3.1/24 10.0.0.2/32 | +# | | +# | +-----------------------------------------------------------------------+ | +# | | vrf-green | | +# | | + vlan10-v (macvlan) vlan20-v (macvlan) + | | +# | | | 10.1.1.1/24 10.1.2.1/24 | | | +# | | | 00:00:5e:00:01:01 00:00:5e:00:01:01 | | | +# | | | | | | +# | | + vlan10 vlan20 + | | +# | | | 10.1.1.12/24 10.1.2.12/24 | | | +# | | | | | | +# | | +--------------------------------+--------------------------------+ | | +# | | | | | +# | +-----------------------------------|-----------------------------------+ | +# | | | +# | +-----------------------------------+-----------------------------------+ | +# | | | | +# | | + vx10 + vx20 | | +# | | local 10.0.0.2 local 10.0.0.2 | | +# | | remote 10.0.0.1 remote 10.0.0.1 | | +# | | id 1000 id 2000 | | +# | | dstport 4789 dstport 4789 | | +# | | vid 10 pvid untagged vid 20 pvid untagged | | +# | | | | +# | | + w1 (veth) + w3 (veth) | | +# | | | vid 10 pvid untagged br1 | vid 20 pvid untagged | | +# | +--|------------------------------------------|-------------------------+ | +# | | | | +# | | | | +# | +--|----------------------+ +--|-------------------------+ | +# | | | vrf-h1 | | | vrf-h2 | | +# | | + w2 (veth) | | + w4 (veth) | | +# | | 10.1.1.102/24 | | 10.1.2.102/24 | | +# | | default via 10.1.1.1 | | default via 10.1.2.1 | | +# | +-------------------------+ +----------------------------+ | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + arp_decap + arp_suppression +" +NUM_NETIFS=6 +source lib.sh + +require_command $ARPING + +hx_create() +{ + local vrf_name=$1; shift + local if_name=$1; shift + local ip_addr=$1; shift + local gw_ip=$1; shift + + vrf_create $vrf_name + ip link set dev $if_name master $vrf_name + ip link set dev $vrf_name up + ip link set dev $if_name up + + ip address add $ip_addr/24 dev $if_name + ip neigh replace $gw_ip lladdr 00:00:5e:00:01:01 nud permanent \ + dev $if_name + ip route add default vrf $vrf_name nexthop via $gw_ip +} +export -f hx_create + +hx_destroy() +{ + local vrf_name=$1; shift + local if_name=$1; shift + local ip_addr=$1; shift + local gw_ip=$1; shift + + ip route del default vrf $vrf_name nexthop via $gw_ip + ip neigh del $gw_ip dev $if_name + ip address del $ip_addr/24 dev $if_name + + ip link set dev $if_name down + vrf_destroy $vrf_name +} + +h1_create() +{ + hx_create "vrf-h1" $h1 10.1.1.101 10.1.1.1 +} + +h1_destroy() +{ + hx_destroy "vrf-h1" $h1 10.1.1.101 10.1.1.1 +} + +h2_create() +{ + hx_create "vrf-h2" $h2 10.1.2.101 10.1.2.1 +} + +h2_destroy() +{ + hx_destroy "vrf-h2" $h2 10.1.2.101 10.1.2.1 +} + +switch_create() +{ + ip link add name br1 type bridge vlan_filtering 1 vlan_default_pvid 0 \ + mcast_snooping 0 + # Make sure the bridge uses the MAC address of the local port and not + # that of the VxLAN's device. + ip link set dev br1 address $(mac_get $swp1) + ip link set dev br1 up + + ip link set dev $rp1 up + ip address add dev $rp1 192.0.2.1/24 + ip route add 10.0.0.2/32 nexthop via 192.0.2.2 + + ip link add name vx10 type vxlan id 1000 \ + local 10.0.0.1 remote 10.0.0.2 dstport 4789 \ + nolearning noudpcsum tos inherit ttl 100 + ip link set dev vx10 up + + ip link set dev vx10 master br1 + bridge vlan add vid 10 dev vx10 pvid untagged + + ip link add name vx20 type vxlan id 2000 \ + local 10.0.0.1 remote 10.0.0.2 dstport 4789 \ + nolearning noudpcsum tos inherit ttl 100 + ip link set dev vx20 up + + ip link set dev vx20 master br1 + bridge vlan add vid 20 dev vx20 pvid untagged + + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + bridge vlan add vid 10 dev $swp1 pvid untagged + + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + bridge vlan add vid 20 dev $swp2 pvid untagged + + ip address add 10.0.0.1/32 dev lo + + # Create SVIs + vrf_create "vrf-green" + ip link set dev vrf-green up + + ip link add link br1 name vlan10 up master vrf-green type vlan id 10 + ip address add 10.1.1.11/24 dev vlan10 + ip link add link vlan10 name vlan10-v up master vrf-green \ + address 00:00:5e:00:01:01 type macvlan mode private + ip address add 10.1.1.1/24 dev vlan10-v + + ip link add link br1 name vlan20 up master vrf-green type vlan id 20 + ip address add 10.1.2.11/24 dev vlan20 + ip link add link vlan20 name vlan20-v up master vrf-green \ + address 00:00:5e:00:01:01 type macvlan mode private + ip address add 10.1.2.1/24 dev vlan20-v + + bridge vlan add vid 10 dev br1 self + bridge vlan add vid 20 dev br1 self + + bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 10 + bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 20 +} + +switch_destroy() +{ + bridge fdb del 00:00:5e:00:01:01 dev br1 self local vlan 20 + bridge fdb del 00:00:5e:00:01:01 dev br1 self local vlan 10 + + bridge vlan del vid 20 dev br1 self + bridge vlan del vid 10 dev br1 self + + ip link del dev vlan20 + + ip link del dev vlan10 + + vrf_destroy "vrf-green" + + ip address del 10.0.0.1/32 dev lo + + bridge vlan del vid 20 dev $swp2 + ip link set dev $swp2 down + ip link set dev $swp2 nomaster + + bridge vlan del vid 10 dev $swp1 + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + + bridge vlan del vid 20 dev vx20 + ip link set dev vx20 nomaster + + ip link set dev vx20 down + ip link del dev vx20 + + bridge vlan del vid 10 dev vx10 + ip link set dev vx10 nomaster + + ip link set dev vx10 down + ip link del dev vx10 + + ip route del 10.0.0.2/32 nexthop via 192.0.2.2 + ip address del dev $rp1 192.0.2.1/24 + ip link set dev $rp1 down + + ip link set dev br1 down + ip link del dev br1 +} + +spine_create() +{ + vrf_create "vrf-spine" + ip link set dev $rp2 master vrf-spine + ip link set dev v1 master vrf-spine + ip link set dev vrf-spine up + ip link set dev $rp2 up + ip link set dev v1 up + + ip address add 192.0.2.2/24 dev $rp2 + ip address add 192.0.3.2/24 dev v1 + + ip route add 10.0.0.1/32 vrf vrf-spine nexthop via 192.0.2.1 + ip route add 10.0.0.2/32 vrf vrf-spine nexthop via 192.0.3.1 +} + +spine_destroy() +{ + ip route del 10.0.0.2/32 vrf vrf-spine nexthop via 192.0.3.1 + ip route del 10.0.0.1/32 vrf vrf-spine nexthop via 192.0.2.1 + + ip address del 192.0.3.2/24 dev v1 + ip address del 192.0.2.2/24 dev $rp2 + + ip link set dev v1 down + ip link set dev $rp2 down + vrf_destroy "vrf-spine" +} + +ns_h1_create() +{ + hx_create "vrf-h1" w2 10.1.1.102 10.1.1.1 +} +export -f ns_h1_create + +ns_h2_create() +{ + hx_create "vrf-h2" w4 10.1.2.102 10.1.2.1 +} +export -f ns_h2_create + +ns_switch_create() +{ + ip link add name br1 type bridge vlan_filtering 1 vlan_default_pvid 0 \ + mcast_snooping 0 + ip link set dev br1 up + + ip link set dev v2 up + ip address add dev v2 192.0.3.1/24 + ip route add 10.0.0.1/32 nexthop via 192.0.3.2 + + ip link add name vx10 type vxlan id 1000 \ + local 10.0.0.2 remote 10.0.0.1 dstport 4789 \ + nolearning noudpcsum tos inherit ttl 100 + ip link set dev vx10 up + + ip link set dev vx10 master br1 + bridge vlan add vid 10 dev vx10 pvid untagged + + ip link add name vx20 type vxlan id 2000 \ + local 10.0.0.2 remote 10.0.0.1 dstport 4789 \ + nolearning noudpcsum tos inherit ttl 100 + ip link set dev vx20 up + + ip link set dev vx20 master br1 + bridge vlan add vid 20 dev vx20 pvid untagged + + ip link set dev w1 master br1 + ip link set dev w1 up + bridge vlan add vid 10 dev w1 pvid untagged + + ip link set dev w3 master br1 + ip link set dev w3 up + bridge vlan add vid 20 dev w3 pvid untagged + + ip address add 10.0.0.2/32 dev lo + + # Create SVIs + vrf_create "vrf-green" + ip link set dev vrf-green up + + ip link add link br1 name vlan10 up master vrf-green type vlan id 10 + ip address add 10.1.1.12/24 dev vlan10 + ip link add link vlan10 name vlan10-v up master vrf-green \ + address 00:00:5e:00:01:01 type macvlan mode private + ip address add 10.1.1.1/24 dev vlan10-v + + ip link add link br1 name vlan20 up master vrf-green type vlan id 20 + ip address add 10.1.2.12/24 dev vlan20 + ip link add link vlan20 name vlan20-v up master vrf-green \ + address 00:00:5e:00:01:01 type macvlan mode private + ip address add 10.1.2.1/24 dev vlan20-v + + bridge vlan add vid 10 dev br1 self + bridge vlan add vid 20 dev br1 self + + bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 10 + bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 20 +} +export -f ns_switch_create + +ns_init() +{ + ip link add name w1 type veth peer name w2 + ip link add name w3 type veth peer name w4 + + ip link set dev lo up + + ns_h1_create + ns_h2_create + ns_switch_create +} +export -f ns_init + +ns1_create() +{ + ip netns add ns1 + ip link set dev v2 netns ns1 + in_ns ns1 ns_init +} + +ns1_destroy() +{ + ip netns exec ns1 ip link set dev v2 netns 1 + ip netns del ns1 +} + +macs_populate() +{ + local mac1=$1; shift + local mac2=$1; shift + local ip1=$1; shift + local ip2=$1; shift + local dst=$1; shift + + bridge fdb add $mac1 dev vx10 self master extern_learn static \ + dst $dst vlan 10 + bridge fdb add $mac2 dev vx20 self master extern_learn static \ + dst $dst vlan 20 + + ip neigh add $ip1 lladdr $mac1 nud noarp dev vlan10 \ + extern_learn + ip neigh add $ip2 lladdr $mac2 nud noarp dev vlan20 \ + extern_learn +} +export -f macs_populate + +macs_initialize() +{ + local h1_ns_mac=$(in_ns ns1 mac_get w2) + local h2_ns_mac=$(in_ns ns1 mac_get w4) + local h1_mac=$(mac_get $h1) + local h2_mac=$(mac_get $h2) + + macs_populate $h1_ns_mac $h2_ns_mac 10.1.1.102 10.1.2.102 10.0.0.2 + in_ns ns1 macs_populate $h1_mac $h2_mac 10.1.1.101 10.1.2.101 10.0.0.1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + rp1=${NETIFS[p5]} + rp2=${NETIFS[p6]} + + vrf_prepare + forwarding_enable + + h1_create + h2_create + switch_create + + ip link add name v1 type veth peer name v2 + spine_create + ns1_create + + macs_initialize +} + +cleanup() +{ + pre_cleanup + + ns1_destroy + spine_destroy + ip link del dev v1 + + switch_destroy + h2_destroy + h1_destroy + + forwarding_restore + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 10.1.2.101 ": local->local vid 10->vid 20" + ping_test $h1 10.1.1.102 ": local->remote vid 10->vid 10" + ping_test $h2 10.1.2.102 ": local->remote vid 20->vid 20" + ping_test $h1 10.1.2.102 ": local->remote vid 10->vid 20" + ping_test $h2 10.1.1.102 ": local->remote vid 20->vid 10" +} + +arp_decap() +{ + # Repeat the ping tests, but without populating the neighbours. This + # makes sure we correctly decapsulate ARP packets + log_info "deleting neighbours from vlan interfaces" + + ip neigh del 10.1.1.102 dev vlan10 + ip neigh del 10.1.2.102 dev vlan20 + + ping_ipv4 + + ip neigh replace 10.1.1.102 lladdr $(in_ns ns1 mac_get w2) nud noarp \ + dev vlan10 extern_learn + ip neigh replace 10.1.2.102 lladdr $(in_ns ns1 mac_get w4) nud noarp \ + dev vlan20 extern_learn +} + +arp_suppression_compare() +{ + local expect=$1; shift + local actual=$(in_ns ns1 tc_rule_stats_get vx10 1 ingress) + + (( expect == actual )) + check_err $? "expected $expect arps got $actual" +} + +arp_suppression() +{ + ip link set dev vx10 type bridge_slave neigh_suppress on + + in_ns ns1 tc qdisc add dev vx10 clsact + in_ns ns1 tc filter add dev vx10 ingress proto arp pref 1 handle 101 \ + flower dst_mac ff:ff:ff:ff:ff:ff arp_tip 10.1.1.102 arp_op \ + request action pass + + # The neighbour is configured on the SVI and ARP suppression is on, so + # the ARP request should be suppressed + RET=0 + + $ARPING -I $h1 -fqb -c 1 -w 1 10.1.1.102 + check_err $? "arping failed" + + arp_suppression_compare 0 + + log_test "neigh_suppress: on / neigh exists: yes" + + # Delete the neighbour from the the SVI. A single ARP request should be + # received by the remote VTEP + RET=0 + + ip neigh del 10.1.1.102 dev vlan10 + + $ARPING -I $h1 -fqb -c 1 -w 1 10.1.1.102 + check_err $? "arping failed" + + arp_suppression_compare 1 + + log_test "neigh_suppress: on / neigh exists: no" + + # Turn off ARP suppression and make sure ARP is not suppressed, + # regardless of neighbour existence on the SVI + RET=0 + + ip neigh del 10.1.1.102 dev vlan10 &> /dev/null + ip link set dev vx10 type bridge_slave neigh_suppress off + + $ARPING -I $h1 -fqb -c 1 -w 1 10.1.1.102 + check_err $? "arping failed" + + arp_suppression_compare 2 + + log_test "neigh_suppress: off / neigh exists: no" + + RET=0 + + ip neigh add 10.1.1.102 lladdr $(in_ns ns1 mac_get w2) nud noarp \ + dev vlan10 extern_learn + + $ARPING -I $h1 -fqb -c 1 -w 1 10.1.1.102 + check_err $? "arping failed" + + arp_suppression_compare 3 + + log_test "neigh_suppress: off / neigh exists: yes" + + in_ns ns1 tc qdisc del dev vx10 clsact +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh index 56cef3b1c194..bb10e33690b2 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh @@ -629,7 +629,7 @@ __test_ecn_decap() RET=0 tc filter add dev $h1 ingress pref 77 prot ip \ - flower ip_tos $decapped_tos action pass + flower ip_tos $decapped_tos action drop sleep 1 vxlan_encapped_ping_test v2 v1 192.0.2.17 \ $orig_inner_tos $orig_outer_tos \ diff --git a/tools/testing/selftests/net/forwarding/vxlan_symmetric.sh b/tools/testing/selftests/net/forwarding/vxlan_symmetric.sh new file mode 100755 index 000000000000..1209031bc794 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/vxlan_symmetric.sh @@ -0,0 +1,551 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +---------------------------+ +------------------------------+ +# | vrf-h1 | | vrf-h2 | +# | + $h1 | | + $h2 | +# | | 10.1.1.101/24 | | | 10.1.2.101/24 | +# | | default via 10.1.1.1 | | | default via 10.1.2.1 | +# +----|----------------------+ +----|-------------------------+ +# | | +# +----|--------------------------------------------|-------------------------+ +# | SW | | | +# | +--|--------------------------------------------|-----------------------+ | +# | | + $swp1 br1 + $swp2 | | +# | | vid 10 pvid untagged vid 20 pvid untagged | | +# | | | | +# | | + vx10 + vx20 | | +# | | local 10.0.0.1 local 10.0.0.1 | | +# | | remote 10.0.0.2 remote 10.0.0.2 | | +# | | id 1010 id 1020 | | +# | | dstport 4789 dstport 4789 | | +# | | vid 10 pvid untagged vid 20 pvid untagged | | +# | | | | +# | | + vx4001 | | +# | | local 10.0.0.1 | | +# | | remote 10.0.0.2 | | +# | | id 104001 | | +# | | dstport 4789 | | +# | | vid 4001 pvid untagged | | +# | | | | +# | +-----------------------------------+-----------------------------------+ | +# | | | +# | +-----------------------------------|-----------------------------------+ | +# | | | | | +# | | +--------------------------------+--------------------------------+ | | +# | | | | | | | +# | | + vlan10 | vlan20 + | | +# | | | 10.1.1.11/24 | 10.1.2.11/24 | | | +# | | | | | | | +# | | + vlan10-v (macvlan) + vlan20-v (macvlan) + | | +# | | 10.1.1.1/24 vlan4001 10.1.2.1/24 | | +# | | 00:00:5e:00:01:01 00:00:5e:00:01:01 | | +# | | vrf-green | | +# | +-----------------------------------------------------------------------+ | +# | | +# | + $rp1 +lo | +# | | 192.0.2.1/24 10.0.0.1/32 | +# +----|----------------------------------------------------------------------+ +# | +# +----|--------------------------------------------------------+ +# | | vrf-spine | +# | + $rp2 | +# | 192.0.2.2/24 | +# | | (maybe) HW +# ============================================================================= +# | | (likely) SW +# | | +# | + v1 (veth) | +# | | 192.0.3.2/24 | +# +----|--------------------------------------------------------+ +# | +# +----|----------------------------------------------------------------------+ +# | + v2 (veth) +lo NS1 (netns) | +# | 192.0.3.1/24 10.0.0.2/32 | +# | | +# | +-----------------------------------------------------------------------+ | +# | | vrf-green | | +# | | + vlan10-v (macvlan) vlan20-v (macvlan) + | | +# | | | 10.1.1.1/24 10.1.2.1/24 | | | +# | | | 00:00:5e:00:01:01 00:00:5e:00:01:01 | | | +# | | | vlan4001 | | | +# | | + vlan10 + vlan20 + | | +# | | | 10.1.1.12/24 | 10.1.2.12/24 | | | +# | | | | | | | +# | | +--------------------------------+--------------------------------+ | | +# | | | | | +# | +-----------------------------------|-----------------------------------+ | +# | | | +# | +-----------------------------------+-----------------------------------+ | +# | | | | +# | | + vx10 + vx20 | | +# | | local 10.0.0.2 local 10.0.0.2 | | +# | | remote 10.0.0.1 remote 10.0.0.1 | | +# | | id 1010 id 1020 | | +# | | dstport 4789 dstport 4789 | | +# | | vid 10 pvid untagged vid 20 pvid untagged | | +# | | | | +# | | + vx4001 | | +# | | local 10.0.0.2 | | +# | | remote 10.0.0.1 | | +# | | id 104001 | | +# | | dstport 4789 | | +# | | vid 4001 pvid untagged | | +# | | | | +# | | + w1 (veth) + w3 (veth) | | +# | | | vid 10 pvid untagged br1 | vid 20 pvid untagged | | +# | +--|------------------------------------------|-------------------------+ | +# | | | | +# | | | | +# | +--|----------------------+ +--|-------------------------+ | +# | | | vrf-h1 | | | vrf-h2 | | +# | | + w2 (veth) | | + w4 (veth) | | +# | | 10.1.1.102/24 | | 10.1.2.102/24 | | +# | | default via 10.1.1.1 | | default via 10.1.2.1 | | +# | +-------------------------+ +----------------------------+ | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 +" +NUM_NETIFS=6 +source lib.sh + +hx_create() +{ + local vrf_name=$1; shift + local if_name=$1; shift + local ip_addr=$1; shift + local gw_ip=$1; shift + + vrf_create $vrf_name + ip link set dev $if_name master $vrf_name + ip link set dev $vrf_name up + ip link set dev $if_name up + + ip address add $ip_addr/24 dev $if_name + ip neigh replace $gw_ip lladdr 00:00:5e:00:01:01 nud permanent \ + dev $if_name + ip route add default vrf $vrf_name nexthop via $gw_ip +} +export -f hx_create + +hx_destroy() +{ + local vrf_name=$1; shift + local if_name=$1; shift + local ip_addr=$1; shift + local gw_ip=$1; shift + + ip route del default vrf $vrf_name nexthop via $gw_ip + ip neigh del $gw_ip dev $if_name + ip address del $ip_addr/24 dev $if_name + + ip link set dev $if_name down + vrf_destroy $vrf_name +} + +h1_create() +{ + hx_create "vrf-h1" $h1 10.1.1.101 10.1.1.1 +} + +h1_destroy() +{ + hx_destroy "vrf-h1" $h1 10.1.1.101 10.1.1.1 +} + +h2_create() +{ + hx_create "vrf-h2" $h2 10.1.2.101 10.1.2.1 +} + +h2_destroy() +{ + hx_destroy "vrf-h2" $h2 10.1.2.101 10.1.2.1 +} + +switch_create() +{ + ip link add name br1 type bridge vlan_filtering 1 vlan_default_pvid 0 \ + mcast_snooping 0 + # Make sure the bridge uses the MAC address of the local port and not + # that of the VxLAN's device. + ip link set dev br1 address $(mac_get $swp1) + ip link set dev br1 up + + ip link set dev $rp1 up + ip address add dev $rp1 192.0.2.1/24 + ip route add 10.0.0.2/32 nexthop via 192.0.2.2 + + ip link add name vx10 type vxlan id 1010 \ + local 10.0.0.1 remote 10.0.0.2 dstport 4789 \ + nolearning noudpcsum tos inherit ttl 100 + ip link set dev vx10 up + + ip link set dev vx10 master br1 + bridge vlan add vid 10 dev vx10 pvid untagged + + ip link add name vx20 type vxlan id 1020 \ + local 10.0.0.1 remote 10.0.0.2 dstport 4789 \ + nolearning noudpcsum tos inherit ttl 100 + ip link set dev vx20 up + + ip link set dev vx20 master br1 + bridge vlan add vid 20 dev vx20 pvid untagged + + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + bridge vlan add vid 10 dev $swp1 pvid untagged + + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + bridge vlan add vid 20 dev $swp2 pvid untagged + + ip link add name vx4001 type vxlan id 104001 \ + local 10.0.0.1 dstport 4789 \ + nolearning noudpcsum tos inherit ttl 100 + ip link set dev vx4001 up + + ip link set dev vx4001 master br1 + bridge vlan add vid 4001 dev vx4001 pvid untagged + + ip address add 10.0.0.1/32 dev lo + + # Create SVIs + vrf_create "vrf-green" + ip link set dev vrf-green up + + ip link add link br1 name vlan10 up master vrf-green type vlan id 10 + ip address add 10.1.1.11/24 dev vlan10 + ip link add link vlan10 name vlan10-v up master vrf-green \ + address 00:00:5e:00:01:01 type macvlan mode private + ip address add 10.1.1.1/24 dev vlan10-v + + ip link add link br1 name vlan20 up master vrf-green type vlan id 20 + ip address add 10.1.2.11/24 dev vlan20 + ip link add link vlan20 name vlan20-v up master vrf-green \ + address 00:00:5e:00:01:01 type macvlan mode private + ip address add 10.1.2.1/24 dev vlan20-v + + ip link add link br1 name vlan4001 up master vrf-green \ + type vlan id 4001 + + bridge vlan add vid 10 dev br1 self + bridge vlan add vid 20 dev br1 self + bridge vlan add vid 4001 dev br1 self + + bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 10 + bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 20 +} + +switch_destroy() +{ + bridge fdb del 00:00:5e:00:01:01 dev br1 self local vlan 20 + bridge fdb del 00:00:5e:00:01:01 dev br1 self local vlan 10 + + bridge vlan del vid 4001 dev br1 self + bridge vlan del vid 20 dev br1 self + bridge vlan del vid 10 dev br1 self + + ip link del dev vlan4001 + + ip link del dev vlan20 + + ip link del dev vlan10 + + vrf_destroy "vrf-green" + + ip address del 10.0.0.1/32 dev lo + + bridge vlan del vid 20 dev $swp2 + ip link set dev $swp2 down + ip link set dev $swp2 nomaster + + bridge vlan del vid 10 dev $swp1 + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + + bridge vlan del vid 4001 dev vx4001 + ip link set dev vx4001 nomaster + + ip link set dev vx4001 down + ip link del dev vx4001 + + bridge vlan del vid 20 dev vx20 + ip link set dev vx20 nomaster + + ip link set dev vx20 down + ip link del dev vx20 + + bridge vlan del vid 10 dev vx10 + ip link set dev vx10 nomaster + + ip link set dev vx10 down + ip link del dev vx10 + + ip route del 10.0.0.2/32 nexthop via 192.0.2.2 + ip address del dev $rp1 192.0.2.1/24 + ip link set dev $rp1 down + + ip link set dev br1 down + ip link del dev br1 +} + +spine_create() +{ + vrf_create "vrf-spine" + ip link set dev $rp2 master vrf-spine + ip link set dev v1 master vrf-spine + ip link set dev vrf-spine up + ip link set dev $rp2 up + ip link set dev v1 up + + ip address add 192.0.2.2/24 dev $rp2 + ip address add 192.0.3.2/24 dev v1 + + ip route add 10.0.0.1/32 vrf vrf-spine nexthop via 192.0.2.1 + ip route add 10.0.0.2/32 vrf vrf-spine nexthop via 192.0.3.1 +} + +spine_destroy() +{ + ip route del 10.0.0.2/32 vrf vrf-spine nexthop via 192.0.3.1 + ip route del 10.0.0.1/32 vrf vrf-spine nexthop via 192.0.2.1 + + ip address del 192.0.3.2/24 dev v1 + ip address del 192.0.2.2/24 dev $rp2 + + ip link set dev v1 down + ip link set dev $rp2 down + vrf_destroy "vrf-spine" +} + +ns_h1_create() +{ + hx_create "vrf-h1" w2 10.1.1.102 10.1.1.1 +} +export -f ns_h1_create + +ns_h2_create() +{ + hx_create "vrf-h2" w4 10.1.2.102 10.1.2.1 +} +export -f ns_h2_create + +ns_switch_create() +{ + ip link add name br1 type bridge vlan_filtering 1 vlan_default_pvid 0 \ + mcast_snooping 0 + ip link set dev br1 up + + ip link set dev v2 up + ip address add dev v2 192.0.3.1/24 + ip route add 10.0.0.1/32 nexthop via 192.0.3.2 + + ip link add name vx10 type vxlan id 1010 \ + local 10.0.0.2 remote 10.0.0.1 dstport 4789 \ + nolearning noudpcsum tos inherit ttl 100 + ip link set dev vx10 up + + ip link set dev vx10 master br1 + bridge vlan add vid 10 dev vx10 pvid untagged + + ip link add name vx20 type vxlan id 1020 \ + local 10.0.0.2 remote 10.0.0.1 dstport 4789 \ + nolearning noudpcsum tos inherit ttl 100 + ip link set dev vx20 up + + ip link set dev vx20 master br1 + bridge vlan add vid 20 dev vx20 pvid untagged + + ip link add name vx4001 type vxlan id 104001 \ + local 10.0.0.2 dstport 4789 \ + nolearning noudpcsum tos inherit ttl 100 + ip link set dev vx4001 up + + ip link set dev vx4001 master br1 + bridge vlan add vid 4001 dev vx4001 pvid untagged + + ip link set dev w1 master br1 + ip link set dev w1 up + bridge vlan add vid 10 dev w1 pvid untagged + + ip link set dev w3 master br1 + ip link set dev w3 up + bridge vlan add vid 20 dev w3 pvid untagged + + ip address add 10.0.0.2/32 dev lo + + # Create SVIs + vrf_create "vrf-green" + ip link set dev vrf-green up + + ip link add link br1 name vlan10 up master vrf-green type vlan id 10 + ip address add 10.1.1.12/24 dev vlan10 + ip link add link vlan10 name vlan10-v up master vrf-green \ + address 00:00:5e:00:01:01 type macvlan mode private + ip address add 10.1.1.1/24 dev vlan10-v + + ip link add link br1 name vlan20 up master vrf-green type vlan id 20 + ip address add 10.1.2.12/24 dev vlan20 + ip link add link vlan20 name vlan20-v up master vrf-green \ + address 00:00:5e:00:01:01 type macvlan mode private + ip address add 10.1.2.1/24 dev vlan20-v + + ip link add link br1 name vlan4001 up master vrf-green \ + type vlan id 4001 + + bridge vlan add vid 10 dev br1 self + bridge vlan add vid 20 dev br1 self + bridge vlan add vid 4001 dev br1 self + + bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 10 + bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 20 +} +export -f ns_switch_create + +ns_init() +{ + ip link add name w1 type veth peer name w2 + ip link add name w3 type veth peer name w4 + + ip link set dev lo up + + ns_h1_create + ns_h2_create + ns_switch_create +} +export -f ns_init + +ns1_create() +{ + ip netns add ns1 + ip link set dev v2 netns ns1 + in_ns ns1 ns_init +} + +ns1_destroy() +{ + ip netns exec ns1 ip link set dev v2 netns 1 + ip netns del ns1 +} + +__l2_vni_init() +{ + local mac1=$1; shift + local mac2=$1; shift + local ip1=$1; shift + local ip2=$1; shift + local dst=$1; shift + + bridge fdb add $mac1 dev vx10 self master extern_learn static \ + dst $dst vlan 10 + bridge fdb add $mac2 dev vx20 self master extern_learn static \ + dst $dst vlan 20 + + ip neigh add $ip1 lladdr $mac1 nud noarp dev vlan10 \ + extern_learn + ip neigh add $ip2 lladdr $mac2 nud noarp dev vlan20 \ + extern_learn +} +export -f __l2_vni_init + +l2_vni_init() +{ + local h1_ns_mac=$(in_ns ns1 mac_get w2) + local h2_ns_mac=$(in_ns ns1 mac_get w4) + local h1_mac=$(mac_get $h1) + local h2_mac=$(mac_get $h2) + + __l2_vni_init $h1_ns_mac $h2_ns_mac 10.1.1.102 10.1.2.102 10.0.0.2 + in_ns ns1 __l2_vni_init $h1_mac $h2_mac 10.1.1.101 10.1.2.101 10.0.0.1 +} + +__l3_vni_init() +{ + local mac=$1; shift + local vtep_ip=$1; shift + local host1_ip=$1; shift + local host2_ip=$1; shift + + bridge fdb add $mac dev vx4001 self master extern_learn static \ + dst $vtep_ip vlan 4001 + + ip neigh add $vtep_ip lladdr $mac nud noarp dev vlan4001 extern_learn + + ip route add $host1_ip/32 vrf vrf-green nexthop via $vtep_ip \ + dev vlan4001 onlink + ip route add $host2_ip/32 vrf vrf-green nexthop via $vtep_ip \ + dev vlan4001 onlink +} +export -f __l3_vni_init + +l3_vni_init() +{ + local vlan4001_ns_mac=$(in_ns ns1 mac_get vlan4001) + local vlan4001_mac=$(mac_get vlan4001) + + __l3_vni_init $vlan4001_ns_mac 10.0.0.2 10.1.1.102 10.1.2.102 + in_ns ns1 __l3_vni_init $vlan4001_mac 10.0.0.1 10.1.1.101 10.1.2.101 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + rp1=${NETIFS[p5]} + rp2=${NETIFS[p6]} + + vrf_prepare + forwarding_enable + + h1_create + h2_create + switch_create + + ip link add name v1 type veth peer name v2 + spine_create + ns1_create + + l2_vni_init + l3_vni_init +} + +cleanup() +{ + pre_cleanup + + ns1_destroy + spine_destroy + ip link del dev v1 + + switch_destroy + h2_destroy + h1_destroy + + forwarding_restore + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 10.1.2.101 ": local->local vid 10->vid 20" + ping_test $h1 10.1.1.102 ": local->remote vid 10->vid 10" + ping_test $h2 10.1.2.102 ": local->remote vid 20->vid 20" + ping_test $h1 10.1.2.102 ": local->remote vid 10->vid 20" + ping_test $h2 10.1.1.102 ": local->remote vid 20->vid 10" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c index 61ae2782388e..c0c9ecb891e1 100644 --- a/tools/testing/selftests/net/ip_defrag.c +++ b/tools/testing/selftests/net/ip_defrag.c @@ -20,6 +20,7 @@ static bool cfg_do_ipv4; static bool cfg_do_ipv6; static bool cfg_verbose; static bool cfg_overlap; +static bool cfg_permissive; static unsigned short cfg_port = 9000; const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) }; @@ -35,7 +36,7 @@ const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT; static int payload_len; static int max_frag_len; -#define MSG_LEN_MAX 60000 /* Max UDP payload length. */ +#define MSG_LEN_MAX 10000 /* Max UDP payload length. */ #define IP4_MF (1u << 13) /* IPv4 MF flag. */ #define IP6_MF (1) /* IPv6 MF flag. */ @@ -59,13 +60,14 @@ static void recv_validate_udp(int fd_udp) msg_counter++; if (cfg_overlap) { - if (ret != -1) - error(1, 0, "recv: expected timeout; got %d", - (int)ret); - if (errno != ETIMEDOUT && errno != EAGAIN) - error(1, errno, "recv: expected timeout: %d", - errno); - return; /* OK */ + if (ret == -1 && (errno == ETIMEDOUT || errno == EAGAIN)) + return; /* OK */ + if (!cfg_permissive) { + if (ret != -1) + error(1, 0, "recv: expected timeout; got %d", + (int)ret); + error(1, errno, "recv: expected timeout: %d", errno); + } } if (ret == -1) @@ -239,33 +241,80 @@ static void send_udp_frags(int fd_raw, struct sockaddr *addr, iphdr->ip_sum = 0; } + /* Occasionally test in-order fragments. */ + if (!cfg_overlap && (rand() % 100 < 15)) { + offset = 0; + while (offset < (UDP_HLEN + payload_len)) { + send_fragment(fd_raw, addr, alen, offset, ipv6); + offset += max_frag_len; + } + return; + } + + /* Occasionally test IPv4 "runs" (see net/ipv4/ip_fragment.c) */ + if (!cfg_overlap && (rand() % 100 < 20) && + (payload_len > 9 * max_frag_len)) { + offset = 6 * max_frag_len; + while (offset < (UDP_HLEN + payload_len)) { + send_fragment(fd_raw, addr, alen, offset, ipv6); + offset += max_frag_len; + } + offset = 3 * max_frag_len; + while (offset < 6 * max_frag_len) { + send_fragment(fd_raw, addr, alen, offset, ipv6); + offset += max_frag_len; + } + offset = 0; + while (offset < 3 * max_frag_len) { + send_fragment(fd_raw, addr, alen, offset, ipv6); + offset += max_frag_len; + } + return; + } + /* Odd fragments. */ offset = max_frag_len; while (offset < (UDP_HLEN + payload_len)) { send_fragment(fd_raw, addr, alen, offset, ipv6); + /* IPv4 ignores duplicates, so randomly send a duplicate. */ + if (rand() % 100 == 1) + send_fragment(fd_raw, addr, alen, offset, ipv6); offset += 2 * max_frag_len; } if (cfg_overlap) { - /* Send an extra random fragment. */ - offset = rand() % (UDP_HLEN + payload_len - 1); - /* sendto() returns EINVAL if offset + frag_len is too small. */ + /* Send an extra random fragment. + * + * Duplicates and some fragments completely inside + * previously sent fragments are dropped/ignored. So + * random offset and frag_len can result in a dropped + * fragment instead of a dropped queue/packet. Thus we + * hard-code offset and frag_len. + */ + if (max_frag_len * 4 < payload_len || max_frag_len < 16) { + /* not enough payload for random offset and frag_len. */ + offset = 8; + frag_len = UDP_HLEN + max_frag_len; + } else { + offset = rand() % (payload_len / 2); + frag_len = 2 * max_frag_len + 1 + rand() % 256; + } if (ipv6) { struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN); - frag_len = max_frag_len + rand() % 256; + /* sendto() returns EINVAL if offset + frag_len is too small. */ /* In IPv6 if !!(frag_len % 8), the fragment is dropped. */ frag_len &= ~0x7; fraghdr->ip6f_offlg = htons(offset / 8 | IP6_MF); ip6hdr->ip6_plen = htons(frag_len); frag_len += IP6_HLEN; } else { - frag_len = IP4_HLEN + UDP_HLEN + rand() % 256; + frag_len += IP4_HLEN; iphdr->ip_off = htons(offset / 8 | IP4_MF); iphdr->ip_len = htons(frag_len); } res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen); if (res < 0) - error(1, errno, "sendto overlap"); + error(1, errno, "sendto overlap: %d", frag_len); if (res != frag_len) error(1, 0, "sendto overlap: %d vs %d", (int)res, frag_len); frag_counter++; @@ -275,6 +324,9 @@ static void send_udp_frags(int fd_raw, struct sockaddr *addr, offset = 0; while (offset < (UDP_HLEN + payload_len)) { send_fragment(fd_raw, addr, alen, offset, ipv6); + /* IPv4 ignores duplicates, so randomly send a duplicate. */ + if (rand() % 100 == 1) + send_fragment(fd_raw, addr, alen, offset, ipv6); offset += 2 * max_frag_len; } } @@ -282,9 +334,13 @@ static void send_udp_frags(int fd_raw, struct sockaddr *addr, static void run_test(struct sockaddr *addr, socklen_t alen, bool ipv6) { int fd_tx_raw, fd_rx_udp; - struct timeval tv = { .tv_sec = 0, .tv_usec = 10 * 1000 }; + /* Frag queue timeout is set to one second in the calling script; + * socket timeout should be just a bit longer to avoid tests interfering + * with each other. + */ + struct timeval tv = { .tv_sec = 1, .tv_usec = 10 }; int idx; - int min_frag_len = ipv6 ? 1280 : 8; + int min_frag_len = 8; /* Initialize the payload. */ for (idx = 0; idx < MSG_LEN_MAX; ++idx) @@ -308,12 +364,32 @@ static void run_test(struct sockaddr *addr, socklen_t alen, bool ipv6) payload_len += (rand() % 4096)) { if (cfg_verbose) printf("payload_len: %d\n", payload_len); - max_frag_len = min_frag_len; - do { + + if (cfg_overlap) { + /* With overlaps, one send/receive pair below takes + * at least one second (== timeout) to run, so there + * is not enough test time to run a nested loop: + * the full overlap test takes 20-30 seconds. + */ + max_frag_len = min_frag_len + + rand() % (1500 - FRAG_HLEN - min_frag_len); send_udp_frags(fd_tx_raw, addr, alen, ipv6); recv_validate_udp(fd_rx_udp); - max_frag_len += 8 * (rand() % 8); - } while (max_frag_len < (1500 - FRAG_HLEN) && max_frag_len <= payload_len); + } else { + /* Without overlaps, each packet reassembly (== one + * send/receive pair below) takes very little time to + * run, so we can easily afford more thourough testing + * with a nested loop: the full non-overlap test takes + * less than one second). + */ + max_frag_len = min_frag_len; + do { + send_udp_frags(fd_tx_raw, addr, alen, ipv6); + recv_validate_udp(fd_rx_udp); + max_frag_len += 8 * (rand() % 8); + } while (max_frag_len < (1500 - FRAG_HLEN) && + max_frag_len <= payload_len); + } } /* Cleanup. */ @@ -356,7 +432,7 @@ static void parse_opts(int argc, char **argv) { int c; - while ((c = getopt(argc, argv, "46ov")) != -1) { + while ((c = getopt(argc, argv, "46opv")) != -1) { switch (c) { case '4': cfg_do_ipv4 = true; @@ -367,6 +443,9 @@ static void parse_opts(int argc, char **argv) case 'o': cfg_overlap = true; break; + case 'p': + cfg_permissive = true; + break; case 'v': cfg_verbose = true; break; diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh index f34672796044..15d3489ecd9c 100755 --- a/tools/testing/selftests/net/ip_defrag.sh +++ b/tools/testing/selftests/net/ip_defrag.sh @@ -11,10 +11,21 @@ readonly NETNS="ns-$(mktemp -u XXXXXX)" setup() { ip netns add "${NETNS}" ip -netns "${NETNS}" link set lo up + ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_high_thresh=9000000 >/dev/null 2>&1 ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_low_thresh=7000000 >/dev/null 2>&1 + ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_time=1 >/dev/null 2>&1 + ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_high_thresh=9000000 >/dev/null 2>&1 ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_low_thresh=7000000 >/dev/null 2>&1 + ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_time=1 >/dev/null 2>&1 + + ip netns exec "${NETNS}" sysctl -w net.netfilter.nf_conntrack_frag6_high_thresh=9000000 >/dev/null 2>&1 + ip netns exec "${NETNS}" sysctl -w net.netfilter.nf_conntrack_frag6_low_thresh=7000000 >/dev/null 2>&1 + ip netns exec "${NETNS}" sysctl -w net.netfilter.nf_conntrack_frag6_timeout=1 >/dev/null 2>&1 + + # DST cache can get full with a lot of frags, with GC not keeping up with the test. + ip netns exec "${NETNS}" sysctl -w net.ipv6.route.max_size=65536 >/dev/null 2>&1 } cleanup() { @@ -27,7 +38,6 @@ setup echo "ipv4 defrag" ip netns exec "${NETNS}" ./ip_defrag -4 - echo "ipv4 defrag with overlaps" ip netns exec "${NETNS}" ./ip_defrag -4o @@ -37,3 +47,16 @@ ip netns exec "${NETNS}" ./ip_defrag -6 echo "ipv6 defrag with overlaps" ip netns exec "${NETNS}" ./ip_defrag -6o +# insert an nf_conntrack rule so that the codepath in nf_conntrack_reasm.c taken +ip netns exec "${NETNS}" ip6tables -A INPUT -m conntrack --ctstate INVALID -j ACCEPT + +echo "ipv6 nf_conntrack defrag" +ip netns exec "${NETNS}" ./ip_defrag -6 + +echo "ipv6 nf_conntrack defrag with overlaps" +# netfilter will drop some invalid packets, so we run the test in +# permissive mode: i.e. pass the test if the packet is correctly assembled +# even if we sent an overlap +ip netns exec "${NETNS}" ./ip_defrag -6op + +echo "all tests done" diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index e2c94e47707c..912b2dc50be3 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -103,6 +103,15 @@ # and check that configured MTU is used on link creation and changes, and # that MTU is properly calculated instead when MTU is not configured from # userspace +# +# - cleanup_ipv4_exception +# Similar to pmtu_ipv4_vxlan4_exception, but explicitly generate PMTU +# exceptions on multiple CPUs and check that the veth device tear-down +# happens in a timely manner +# +# - cleanup_ipv6_exception +# Same as above, but use IPv6 transport from A to B + # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 @@ -135,7 +144,9 @@ tests=" pmtu_vti6_default_mtu vti6: default MTU assignment pmtu_vti4_link_add_mtu vti4: MTU setting on link creation pmtu_vti6_link_add_mtu vti6: MTU setting on link creation - pmtu_vti6_link_change_mtu vti6: MTU changes on link changes" + pmtu_vti6_link_change_mtu vti6: MTU changes on link changes + cleanup_ipv4_exception ipv4: cleanup of cached exceptions + cleanup_ipv6_exception ipv6: cleanup of cached exceptions" NS_A="ns-$(mktemp -u XXXXXX)" NS_B="ns-$(mktemp -u XXXXXX)" @@ -263,8 +274,6 @@ setup_fou_or_gue() { ${ns_a} ip link set ${encap}_a up ${ns_b} ip link set ${encap}_b up - - sleep 1 } setup_fou44() { @@ -302,6 +311,10 @@ setup_gue66() { 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 } @@ -337,8 +350,6 @@ setup_vti() { ${ns_a} ip link set vti${proto}_a up ${ns_b} ip link set vti${proto}_b up - - sleep 1 } setup_vti4() { @@ -375,8 +386,6 @@ setup_vxlan_or_geneve() { ${ns_a} ip link set ${type}_a up ${ns_b} ip link set ${type}_b up - - sleep 1 } setup_geneve4() { @@ -588,8 +597,8 @@ test_pmtu_ipvX() { mtu "${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 + ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst1} > /dev/null + ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -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}" ${dst1})" @@ -621,7 +630,7 @@ test_pmtu_ipvX() { # Decrease remote MTU on path via R2, get new exception mtu "${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 + ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -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 @@ -638,7 +647,7 @@ test_pmtu_ipvX() { 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 + ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -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 } @@ -687,7 +696,7 @@ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception() { 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 + ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} > /dev/null # Check that exception was created pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" @@ -767,7 +776,7 @@ test_pmtu_ipvX_over_fouY_or_gueY() { mtu "${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 + ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} > /dev/null # Check that exception was created pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" @@ -825,13 +834,13 @@ 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} ${tunnel4_b_addr} > /dev/null + ${ns_a} ping -q -M want -i 0.1 -w 1 -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)) ${tunnel4_b_addr} > /dev/null + ${ns_a} ping -q -M want -i 0.1 -w 1 -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 $((esp_payload_rfc4106 + 1)))" } @@ -847,7 +856,7 @@ test_pmtu_vti6_exception() { mtu "${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 ${tunnel6_b_addr} > /dev/null + ${ns_a} ${ping6} -q -i 0.1 -w 1 -s 60000 ${tunnel6_b_addr} > /dev/null # Check that exception was created pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" @@ -1008,6 +1017,61 @@ test_pmtu_vti6_link_change_mtu() { 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 + taskset --cpu-list ${cpu} ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${tunnel4_b_addr} > /dev/null + 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 +} + usage() { echo echo "$0 [OPTIONS] [TEST]..." diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 78fc593dfe40..b447803f3f8a 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -391,7 +391,7 @@ kci_test_encap_vxlan() vlan="test-vlan0" testns="$1" - ip netns exec "$testns" ip link add "$vxlan" type vxlan id 42 group 239.1.1.1 \ + ip -netns "$testns" link add "$vxlan" type vxlan id 42 group 239.1.1.1 \ dev "$devdummy" dstport 4789 2>/dev/null if [ $? -ne 0 ]; then echo "FAIL: can't add vxlan interface, skipping test" @@ -399,16 +399,68 @@ kci_test_encap_vxlan() fi check_err $? - ip netns exec "$testns" ip addr add 10.2.11.49/24 dev "$vxlan" + ip -netns "$testns" addr add 10.2.11.49/24 dev "$vxlan" check_err $? - ip netns exec "$testns" ip link set up dev "$vxlan" + ip -netns "$testns" link set up dev "$vxlan" check_err $? - ip netns exec "$testns" ip link add link "$vxlan" name "$vlan" type vlan id 1 + ip -netns "$testns" link add link "$vxlan" name "$vlan" type vlan id 1 check_err $? - ip netns exec "$testns" ip link del "$vxlan" + # changelink testcases + ip -netns "$testns" link set dev "$vxlan" type vxlan vni 43 2>/dev/null + check_fail $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan group ffe5::5 dev "$devdummy" 2>/dev/null + check_fail $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan ttl inherit 2>/dev/null + check_fail $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan ttl 64 + check_err $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan nolearning + check_err $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan proxy 2>/dev/null + check_fail $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan norsc 2>/dev/null + check_fail $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan l2miss 2>/dev/null + check_fail $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan l3miss 2>/dev/null + check_fail $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan external 2>/dev/null + check_fail $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan udpcsum 2>/dev/null + check_fail $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan udp6zerocsumtx 2>/dev/null + check_fail $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan udp6zerocsumrx 2>/dev/null + check_fail $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan remcsumtx 2>/dev/null + check_fail $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan remcsumrx 2>/dev/null + check_fail $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan gbp 2>/dev/null + check_fail $? + + ip -netns "$testns" link set dev "$vxlan" type vxlan gpe 2>/dev/null + check_fail $? + + ip -netns "$testns" link del "$vxlan" check_err $? if [ $ret -ne 0 ]; then @@ -430,19 +482,19 @@ kci_test_encap_fou() return $ksft_skip fi - ip netns exec "$testns" ip fou add port 7777 ipproto 47 2>/dev/null + ip -netns "$testns" fou add port 7777 ipproto 47 2>/dev/null if [ $? -ne 0 ];then echo "FAIL: can't add fou port 7777, skipping test" return 1 fi - ip netns exec "$testns" ip fou add port 8888 ipproto 4 + ip -netns "$testns" fou add port 8888 ipproto 4 check_err $? - ip netns exec "$testns" ip fou del port 9999 2>/dev/null + ip -netns "$testns" fou del port 9999 2>/dev/null check_fail $? - ip netns exec "$testns" ip fou del port 7777 + ip -netns "$testns" fou del port 7777 check_err $? if [ $ret -ne 0 ]; then @@ -465,12 +517,12 @@ kci_test_encap() return $ksft_skip fi - ip netns exec "$testns" ip link set lo up + ip -netns "$testns" link set lo up check_err $? - ip netns exec "$testns" ip link add name "$devdummy" type dummy + ip -netns "$testns" link add name "$devdummy" type dummy check_err $? - ip netns exec "$testns" ip link set "$devdummy" up + ip -netns "$testns" link set "$devdummy" up check_err $? kci_test_encap_vxlan "$testns" @@ -759,24 +811,24 @@ kci_test_gretap() fi # test native tunnel - ip netns exec "$testns" ip link add dev "$DEV_NS" type gretap seq \ + ip -netns "$testns" link add dev "$DEV_NS" type gretap seq \ key 102 local 172.16.1.100 remote 172.16.1.200 check_err $? - ip netns exec "$testns" ip addr add dev "$DEV_NS" 10.1.1.100/24 + ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24 check_err $? - ip netns exec "$testns" ip link set dev $DEV_NS up + ip -netns "$testns" link set dev $DEV_NS up check_err $? - ip netns exec "$testns" ip link del "$DEV_NS" + ip -netns "$testns" link del "$DEV_NS" check_err $? # test external mode - ip netns exec "$testns" ip link add dev "$DEV_NS" type gretap external + ip -netns "$testns" link add dev "$DEV_NS" type gretap external check_err $? - ip netns exec "$testns" ip link del "$DEV_NS" + ip -netns "$testns" link del "$DEV_NS" check_err $? if [ $ret -ne 0 ]; then @@ -809,24 +861,24 @@ kci_test_ip6gretap() fi # test native tunnel - ip netns exec "$testns" ip link add dev "$DEV_NS" type ip6gretap seq \ + ip -netns "$testns" link add dev "$DEV_NS" type ip6gretap seq \ key 102 local fc00:100::1 remote fc00:100::2 check_err $? - ip netns exec "$testns" ip addr add dev "$DEV_NS" fc00:200::1/96 + ip -netns "$testns" addr add dev "$DEV_NS" fc00:200::1/96 check_err $? - ip netns exec "$testns" ip link set dev $DEV_NS up + ip -netns "$testns" link set dev $DEV_NS up check_err $? - ip netns exec "$testns" ip link del "$DEV_NS" + ip -netns "$testns" link del "$DEV_NS" check_err $? # test external mode - ip netns exec "$testns" ip link add dev "$DEV_NS" type ip6gretap external + ip -netns "$testns" link add dev "$DEV_NS" type ip6gretap external check_err $? - ip netns exec "$testns" ip link del "$DEV_NS" + ip -netns "$testns" link del "$DEV_NS" check_err $? if [ $ret -ne 0 ]; then @@ -858,40 +910,40 @@ kci_test_erspan() fi # test native tunnel erspan v1 - ip netns exec "$testns" ip link add dev "$DEV_NS" type erspan seq \ + ip -netns "$testns" link add dev "$DEV_NS" type erspan seq \ key 102 local 172.16.1.100 remote 172.16.1.200 \ erspan_ver 1 erspan 488 check_err $? - ip netns exec "$testns" ip addr add dev "$DEV_NS" 10.1.1.100/24 + ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24 check_err $? - ip netns exec "$testns" ip link set dev $DEV_NS up + ip -netns "$testns" link set dev $DEV_NS up check_err $? - ip netns exec "$testns" ip link del "$DEV_NS" + ip -netns "$testns" link del "$DEV_NS" check_err $? # test native tunnel erspan v2 - ip netns exec "$testns" ip link add dev "$DEV_NS" type erspan seq \ + ip -netns "$testns" link add dev "$DEV_NS" type erspan seq \ key 102 local 172.16.1.100 remote 172.16.1.200 \ erspan_ver 2 erspan_dir ingress erspan_hwid 7 check_err $? - ip netns exec "$testns" ip addr add dev "$DEV_NS" 10.1.1.100/24 + ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24 check_err $? - ip netns exec "$testns" ip link set dev $DEV_NS up + ip -netns "$testns" link set dev $DEV_NS up check_err $? - ip netns exec "$testns" ip link del "$DEV_NS" + ip -netns "$testns" link del "$DEV_NS" check_err $? # test external mode - ip netns exec "$testns" ip link add dev "$DEV_NS" type erspan external + ip -netns "$testns" link add dev "$DEV_NS" type erspan external check_err $? - ip netns exec "$testns" ip link del "$DEV_NS" + ip -netns "$testns" link del "$DEV_NS" check_err $? if [ $ret -ne 0 ]; then @@ -923,41 +975,41 @@ kci_test_ip6erspan() fi # test native tunnel ip6erspan v1 - ip netns exec "$testns" ip link add dev "$DEV_NS" type ip6erspan seq \ + ip -netns "$testns" link add dev "$DEV_NS" type ip6erspan seq \ key 102 local fc00:100::1 remote fc00:100::2 \ erspan_ver 1 erspan 488 check_err $? - ip netns exec "$testns" ip addr add dev "$DEV_NS" 10.1.1.100/24 + ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24 check_err $? - ip netns exec "$testns" ip link set dev $DEV_NS up + ip -netns "$testns" link set dev $DEV_NS up check_err $? - ip netns exec "$testns" ip link del "$DEV_NS" + ip -netns "$testns" link del "$DEV_NS" check_err $? # test native tunnel ip6erspan v2 - ip netns exec "$testns" ip link add dev "$DEV_NS" type ip6erspan seq \ + ip -netns "$testns" link add dev "$DEV_NS" type ip6erspan seq \ key 102 local fc00:100::1 remote fc00:100::2 \ erspan_ver 2 erspan_dir ingress erspan_hwid 7 check_err $? - ip netns exec "$testns" ip addr add dev "$DEV_NS" 10.1.1.100/24 + ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24 check_err $? - ip netns exec "$testns" ip link set dev $DEV_NS up + ip -netns "$testns" link set dev $DEV_NS up check_err $? - ip netns exec "$testns" ip link del "$DEV_NS" + ip -netns "$testns" link del "$DEV_NS" check_err $? # test external mode - ip netns exec "$testns" ip link add dev "$DEV_NS" \ + ip -netns "$testns" link add dev "$DEV_NS" \ type ip6erspan external check_err $? - ip netns exec "$testns" ip link del "$DEV_NS" + ip -netns "$testns" link del "$DEV_NS" check_err $? if [ $ret -ne 0 ]; then diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index fac68d710f35..47ddfc154036 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -42,7 +42,7 @@ FIXTURE_SETUP(tls) len = sizeof(addr); memset(&tls12, 0, sizeof(tls12)); - tls12.info.version = TLS_1_2_VERSION; + tls12.info.version = TLS_1_3_VERSION; tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128; addr.sin_family = AF_INET; @@ -452,10 +452,12 @@ TEST_F(tls, recv_partial) memset(recv_mem, 0, sizeof(recv_mem)); EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); - EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_first), 0), -1); + EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_first), + MSG_WAITALL), -1); EXPECT_EQ(memcmp(test_str_first, recv_mem, strlen(test_str_first)), 0); memset(recv_mem, 0, sizeof(recv_mem)); - EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_second), 0), -1); + EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_second), + MSG_WAITALL), -1); EXPECT_EQ(memcmp(test_str_second, recv_mem, strlen(test_str_second)), 0); } @@ -565,10 +567,10 @@ TEST_F(tls, recv_peek_large_buf_mult_recs) len = strlen(test_str_second) + 1; EXPECT_EQ(send(self->fd, test_str_second, len, 0), len); - len = sizeof(buf); + len = strlen(test_str) + 1; memset(buf, 0, len); - EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1); - + EXPECT_NE((len = recv(self->cfd, buf, len, + MSG_PEEK | MSG_WAITALL)), -1); len = strlen(test_str) + 1; EXPECT_EQ(memcmp(test_str, buf, len), 0); } @@ -751,6 +753,20 @@ TEST_F(tls, control_msg) EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); vec.iov_base = buf; + EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL | MSG_PEEK), send_len); + + cmsg = CMSG_FIRSTHDR(&msg); + EXPECT_NE(cmsg, NULL); + EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); + EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); + record_type = *((unsigned char *)CMSG_DATA(cmsg)); + EXPECT_EQ(record_type, 100); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); + + /* Recv the message again without MSG_PEEK */ + record_type = 0; + memset(buf, 0, sizeof(buf)); + EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len); cmsg = CMSG_FIRSTHDR(&msg); EXPECT_NE(cmsg, NULL); @@ -761,4 +777,140 @@ TEST_F(tls, control_msg) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } +TEST(keysizes) { + struct tls12_crypto_info_aes_gcm_256 tls12; + struct sockaddr_in addr; + int sfd, ret, fd, cfd; + socklen_t len; + bool notls; + + notls = false; + len = sizeof(addr); + + memset(&tls12, 0, sizeof(tls12)); + tls12.info.version = TLS_1_2_VERSION; + tls12.info.cipher_type = TLS_CIPHER_AES_GCM_256; + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ret = bind(sfd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + ret = listen(sfd, 10); + ASSERT_EQ(ret, 0); + + ret = getsockname(sfd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = connect(fd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (ret != 0) { + notls = true; + printf("Failure setting TCP_ULP, testing without tls\n"); + } + + if (!notls) { + ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, + sizeof(tls12)); + EXPECT_EQ(ret, 0); + } + + cfd = accept(sfd, &addr, &len); + ASSERT_GE(cfd, 0); + + if (!notls) { + ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", + sizeof("tls")); + EXPECT_EQ(ret, 0); + + ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12, + sizeof(tls12)); + EXPECT_EQ(ret, 0); + } + + close(sfd); + close(fd); + close(cfd); +} + +TEST(tls12) { + int fd, cfd; + bool notls; + + struct tls12_crypto_info_aes_gcm_128 tls12; + struct sockaddr_in addr; + socklen_t len; + int sfd, ret; + + notls = false; + len = sizeof(addr); + + memset(&tls12, 0, sizeof(tls12)); + tls12.info.version = TLS_1_2_VERSION; + tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128; + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ret = bind(sfd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + ret = listen(sfd, 10); + ASSERT_EQ(ret, 0); + + ret = getsockname(sfd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = connect(fd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (ret != 0) { + notls = true; + printf("Failure setting TCP_ULP, testing without tls\n"); + } + + if (!notls) { + ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, + sizeof(tls12)); + ASSERT_EQ(ret, 0); + } + + cfd = accept(sfd, &addr, &len); + ASSERT_GE(cfd, 0); + + if (!notls) { + ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", + sizeof("tls")); + ASSERT_EQ(ret, 0); + + ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12, + sizeof(tls12)); + ASSERT_EQ(ret, 0); + } + + close(sfd); + + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + + send_len = strlen(test_str) + 1; + EXPECT_EQ(send(fd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); + + close(fd); + close(cfd); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index aeac53a99aeb..ac2a30be9b32 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -37,7 +37,7 @@ run_one() { cfg_veth - ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} && \ + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} && \ echo "ok" || \ echo "failed" & @@ -81,7 +81,7 @@ run_one_nat() { # will land on the 'plain' one ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 & pid=$! - ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${family} -b ${addr2%/*} ${rx_args} && \ + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} && \ echo "ok" || \ echo "failed"& @@ -99,8 +99,8 @@ run_one_2sock() { cfg_veth - ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -p 12345 & - ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} && \ + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} -p 12345 & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} && \ echo "ok" || \ echo "failed" & diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index e279051bc631..b8265ee9923f 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -17,7 +17,6 @@ #include <stdbool.h> #include <stdlib.h> #include <stdio.h> -#include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/socket.h> diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index 0c960f673324..db3d4a8b5a4c 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -45,6 +45,8 @@ static int cfg_alen = sizeof(struct sockaddr_in6); static int cfg_expected_pkt_nr; static int cfg_expected_pkt_len; static int cfg_expected_gso_size; +static int cfg_connect_timeout_ms; +static int cfg_rcv_timeout_ms; static struct sockaddr_storage cfg_bind_addr; static bool interrupted; @@ -87,7 +89,7 @@ static unsigned long gettimeofday_ms(void) return (tv.tv_sec * 1000) + (tv.tv_usec / 1000); } -static void do_poll(int fd) +static void do_poll(int fd, int timeout_ms) { struct pollfd pfd; int ret; @@ -102,8 +104,16 @@ static void do_poll(int fd) break; if (ret == -1) error(1, errno, "poll"); - if (ret == 0) - continue; + if (ret == 0) { + if (!timeout_ms) + continue; + + timeout_ms -= 10; + if (timeout_ms <= 0) { + interrupted = true; + break; + } + } if (pfd.revents != POLLIN) error(1, errno, "poll: 0x%x expected 0x%x\n", pfd.revents, POLLIN); @@ -134,7 +144,7 @@ static int do_socket(bool do_tcp) if (listen(accept_fd, 1)) error(1, errno, "listen"); - do_poll(accept_fd); + do_poll(accept_fd, cfg_connect_timeout_ms); if (interrupted) exit(0); @@ -273,7 +283,9 @@ static void do_flush_udp(int fd) static void usage(const char *filepath) { - error(1, 0, "Usage: %s [-Grtv] [-b addr] [-p port] [-l pktlen] [-n packetnr] [-S gsosize]", filepath); + error(1, 0, "Usage: %s [-C connect_timeout] [-Grtv] [-b addr] [-p port]" + " [-l pktlen] [-n packetnr] [-R rcv_timeout] [-S gsosize]", + filepath); } static void parse_opts(int argc, char **argv) @@ -282,7 +294,7 @@ static void parse_opts(int argc, char **argv) /* bind to any by default */ setup_sockaddr(PF_INET6, "::", &cfg_bind_addr); - while ((c = getopt(argc, argv, "4b:Gl:n:p:rS:tv")) != -1) { + while ((c = getopt(argc, argv, "4b:C:Gl:n:p:rR:S:tv")) != -1) { switch (c) { case '4': cfg_family = PF_INET; @@ -292,6 +304,9 @@ static void parse_opts(int argc, char **argv) case 'b': setup_sockaddr(cfg_family, optarg, &cfg_bind_addr); break; + case 'C': + cfg_connect_timeout_ms = strtoul(optarg, NULL, 0); + break; case 'G': cfg_gro_segment = true; break; @@ -307,6 +322,9 @@ static void parse_opts(int argc, char **argv) case 'r': cfg_read_all = true; break; + case 'R': + cfg_rcv_timeout_ms = strtoul(optarg, NULL, 0); + break; case 'S': cfg_expected_gso_size = strtol(optarg, NULL, 0); break; @@ -329,8 +347,9 @@ static void parse_opts(int argc, char **argv) static void do_recv(void) { + int timeout_ms = cfg_tcp ? cfg_rcv_timeout_ms : cfg_connect_timeout_ms; unsigned long tnow, treport; - int fd, loop = 0; + int fd; fd = do_socket(cfg_tcp); @@ -342,12 +361,7 @@ static void do_recv(void) treport = gettimeofday_ms() + 1000; do { - /* force termination after the second poll(); this cope both - * with sender slower than receiver and missing packet errors - */ - if (cfg_expected_pkt_nr && loop++) - interrupted = true; - do_poll(fd); + do_poll(fd, timeout_ms); if (cfg_tcp) do_flush_tcp(fd); @@ -365,6 +379,8 @@ static void do_recv(void) treport = tnow + 1000; } + timeout_ms = cfg_rcv_timeout_ms; + } while (!interrupted); if (cfg_expected_pkt_nr && (packets != cfg_expected_pkt_nr)) diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh index 8db35b99457c..71d7fdc513c1 100755 --- a/tools/testing/selftests/net/xfrm_policy.sh +++ b/tools/testing/selftests/net/xfrm_policy.sh @@ -28,6 +28,19 @@ KEY_AES=0x0123456789abcdef0123456789012345 SPI1=0x1 SPI2=0x2 +do_esp_policy() { + local ns=$1 + local me=$2 + local remote=$3 + local lnet=$4 + local rnet=$5 + + # to encrypt packets as they go out (includes forwarded packets that need encapsulation) + ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 100 action allow + # to fwd decrypted packets after esp processing: + ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 100 action allow +} + do_esp() { local ns=$1 local me=$2 @@ -40,10 +53,59 @@ do_esp() { ip -net $ns xfrm state add src $remote dst $me proto esp spi $spi_in enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $rnet dst $lnet ip -net $ns xfrm state add src $me dst $remote proto esp spi $spi_out enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $lnet dst $rnet - # to encrypt packets as they go out (includes forwarded packets that need encapsulation) - ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 100 action allow - # to fwd decrypted packets after esp processing: - ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 100 action allow + do_esp_policy $ns $me $remote $lnet $rnet +} + +# add policies with different netmasks, to make sure kernel carries +# the policies contained within new netmask over when search tree is +# re-built. +# peer netns that are supposed to be encapsulated via esp have addresses +# in the 10.0.1.0/24 and 10.0.2.0/24 subnets, respectively. +# +# Adding a policy for '10.0.1.0/23' will make it necessary to +# alter the prefix of 10.0.1.0 subnet. +# In case new prefix overlaps with existing node, the node and all +# policies it carries need to be merged with the existing one(s). +# +# Do that here. +do_overlap() +{ + local ns=$1 + + # adds new nodes to tree (neither network exists yet in policy database). + ip -net $ns xfrm policy add src 10.1.0.0/24 dst 10.0.0.0/24 dir fwd priority 200 action block + + # adds a new node in the 10.0.0.0/24 tree (dst node exists). + ip -net $ns xfrm policy add src 10.2.0.0/24 dst 10.0.0.0/24 dir fwd priority 200 action block + + # adds a 10.2.0.0/23 node, but for different dst. + ip -net $ns xfrm policy add src 10.2.0.0/23 dst 10.0.1.0/24 dir fwd priority 200 action block + + # dst now overlaps with the 10.0.1.0/24 ESP policy in fwd. + # kernel must 'promote' existing one (10.0.0.0/24) to 10.0.0.0/23. + # But 10.0.0.0/23 also includes existing 10.0.1.0/24, so that node + # also has to be merged too, including source-sorted subtrees. + # old: + # 10.0.0.0/24 (node 1 in dst tree of the bin) + # 10.1.0.0/24 (node in src tree of dst node 1) + # 10.2.0.0/24 (node in src tree of dst node 1) + # 10.0.1.0/24 (node 2 in dst tree of the bin) + # 10.0.2.0/24 (node in src tree of dst node 2) + # 10.2.0.0/24 (node in src tree of dst node 2) + # + # The next 'policy add' adds dst '10.0.0.0/23', which means + # that dst node 1 and dst node 2 have to be merged including + # the sub-tree. As no duplicates are allowed, policies in + # the two '10.0.2.0/24' are also merged. + # + # after the 'add', internal search tree should look like this: + # 10.0.0.0/23 (node in dst tree of bin) + # 10.0.2.0/24 (node in src tree of dst node) + # 10.1.0.0/24 (node in src tree of dst node) + # 10.2.0.0/24 (node in src tree of dst node) + # + # 10.0.0.0/24 and 10.0.1.0/24 nodes have been merged as 10.0.0.0/23. + ip -net $ns xfrm policy add src 10.1.0.0/24 dst 10.0.0.0/23 dir fwd priority 200 action block } do_esp_policy_get_check() { @@ -160,6 +222,41 @@ check_xfrm() { return $lret } +check_exceptions() +{ + logpostfix="$1" + local lret=0 + + # ping to .254 should be excluded from the tunnel (exception is in place). + check_xfrm 0 254 + if [ $? -ne 0 ]; then + echo "FAIL: expected ping to .254 to fail ($logpostfix)" + lret=1 + else + echo "PASS: ping to .254 bypassed ipsec tunnel ($logpostfix)" + fi + + # ping to .253 should use use ipsec due to direct policy exception. + check_xfrm 1 253 + if [ $? -ne 0 ]; then + echo "FAIL: expected ping to .253 to use ipsec tunnel ($logpostfix)" + lret=1 + else + echo "PASS: direct policy matches ($logpostfix)" + fi + + # ping to .2 should use ipsec. + check_xfrm 1 2 + if [ $? -ne 0 ]; then + echo "FAIL: expected ping to .2 to use ipsec tunnel ($logpostfix)" + lret=1 + else + echo "PASS: policy matches ($logpostfix)" + fi + + return $lret +} + #check for needed privileges if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" @@ -270,33 +367,45 @@ do_exception ns4 10.0.3.10 10.0.3.1 10.0.1.253 10.0.1.240/28 do_exception ns3 dead:3::1 dead:3::10 dead:2::fd dead:2:f0::/96 do_exception ns4 dead:3::10 dead:3::1 dead:1::fd dead:1:f0::/96 -# ping to .254 should now be excluded from the tunnel -check_xfrm 0 254 +check_exceptions "exceptions" if [ $? -ne 0 ]; then - echo "FAIL: expected ping to .254 to fail" ret=1 -else - echo "PASS: ping to .254 bypassed ipsec tunnel" fi -# ping to .253 should use use ipsec due to direct policy exception. -check_xfrm 1 253 -if [ $? -ne 0 ]; then - echo "FAIL: expected ping to .253 to use ipsec tunnel" - ret=1 -else - echo "PASS: direct policy matches" -fi +# insert block policies with adjacent/overlapping netmasks +do_overlap ns3 -# ping to .2 should use ipsec. -check_xfrm 1 2 +check_exceptions "exceptions and block policies" if [ $? -ne 0 ]; then - echo "FAIL: expected ping to .2 to use ipsec tunnel" ret=1 -else - echo "PASS: policy matches" fi +for n in ns3 ns4;do + ip -net $n xfrm policy set hthresh4 28 24 hthresh6 126 125 + sleep $((RANDOM%5)) +done + +check_exceptions "exceptions and block policies after hresh changes" + +# full flush of policy db, check everything gets freed incl. internal meta data +ip -net ns3 xfrm policy flush + +do_esp_policy ns3 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24 +do_exception ns3 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28 + +# move inexact policies to hash table +ip -net ns3 xfrm policy set hthresh4 16 16 + +sleep $((RANDOM%5)) +check_exceptions "exceptions and block policies after hthresh change in ns3" + +# restore original hthresh settings -- move policies back to tables +for n in ns3 ns4;do + ip -net $n xfrm policy set hthresh4 32 32 hthresh6 128 128 + sleep $((RANDOM%5)) +done +check_exceptions "exceptions and block policies after hresh change to normal" + for i in 1 2 3 4;do ip netns del ns$i;done exit $ret |