diff options
Diffstat (limited to 'tools/testing/selftests/net')
24 files changed, 3828 insertions, 54 deletions
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 8cf22b3c2563..6f81130605d7 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -3,6 +3,7 @@ socket psock_fanout psock_snd psock_tpacket +reuseport_addr_any reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa @@ -14,4 +15,5 @@ udpgso_bench_rx udpgso_bench_tx tcp_inq tls +txring_overwrite ip_defrag diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 923570a9708a..f8f3e90700c0 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -4,14 +4,16 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ -TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh +TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \ + rtnetlink.sh xfrm_policy.sh TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh +TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh TEST_PROGS += test_vxlan_fdb_changelink.sh TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket -TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy -TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd +TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any +TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index cd3a2f1545b5..5821bdd98d20 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -14,3 +14,17 @@ CONFIG_IPV6_VTI=y CONFIG_DUMMY=y CONFIG_BRIDGE=y 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_IP6_NF_IPTABLES=m +CONFIG_IP_NF_IPTABLES=m +CONFIG_IP6_NF_NAT=m +CONFIG_IP_NF_NAT=m +CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_IPV6=y +CONFIG_NF_TABLES_IPV4=y +CONFIG_NFT_CHAIN_NAT_IPV6=m +CONFIG_NFT_CHAIN_NAT_IPV4=m diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 85d253546684..3f248d1f5b91 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -15,6 +15,8 @@ PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} PAUSE_ON_CLEANUP=${PAUSE_ON_CLEANUP:=no} NETIF_TYPE=${NETIF_TYPE:=veth} NETIF_CREATE=${NETIF_CREATE:=yes} +MCD=${MCD:=smcrouted} +MC_CLI=${MC_CLI:=smcroutectl} relative_path="${BASH_SOURCE%/*}" if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then @@ -104,7 +106,7 @@ create_netif_veth() { local i - for i in $(eval echo {1..$NUM_NETIFS}); do + for ((i = 1; i <= NUM_NETIFS; ++i)); do local j=$((i+1)) ip link show dev ${NETIFS[p$i]} &> /dev/null @@ -135,7 +137,7 @@ if [[ "$NETIF_CREATE" = "yes" ]]; then create_netif fi -for i in $(eval echo {1..$NUM_NETIFS}); do +for ((i = 1; i <= NUM_NETIFS; ++i)); do ip link show dev ${NETIFS[p$i]} &> /dev/null if [[ $? -ne 0 ]]; then echo "SKIP: could not find all required interfaces" @@ -477,11 +479,24 @@ master_name_get() ip -j link show dev $if_name | jq -r '.[]["master"]' } +link_stats_get() +{ + local if_name=$1; shift + local dir=$1; shift + local stat=$1; shift + + ip -j -s link show dev $if_name \ + | jq '.[]["stats64"]["'$dir'"]["'$stat'"]' +} + link_stats_tx_packets_get() { - local if_name=$1 + link_stats_get $1 tx packets +} - ip -j -s link show dev $if_name | jq '.[]["stats64"]["tx"]["packets"]' +link_stats_rx_errors_get() +{ + link_stats_get $1 rx errors } tc_rule_stats_get() @@ -783,6 +798,17 @@ multipath_eval() log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio" } +in_ns() +{ + local name=$1; shift + + ip netns exec $name bash <<-EOF + NUM_NETIFS=0 + source lib.sh + $(for a in "$@"; do printf "%q${IFS:0:1}" "$a"; done) + EOF +} + ############################################################################## # Tests @@ -790,10 +816,11 @@ ping_do() { local if_name=$1 local dip=$2 + local args=$3 local vrf_name vrf_name=$(master_name_get $if_name) - ip vrf exec $vrf_name $PING $dip -c 10 -i 0.1 -w 2 &> /dev/null + ip vrf exec $vrf_name $PING $args $dip -c 10 -i 0.1 -w 2 &> /dev/null } ping_test() @@ -802,17 +829,18 @@ ping_test() ping_do $1 $2 check_err $? - log_test "ping" + log_test "ping$3" } ping6_do() { local if_name=$1 local dip=$2 + local args=$3 local vrf_name vrf_name=$(master_name_get $if_name) - ip vrf exec $vrf_name $PING6 $dip -c 10 -i 0.1 -w 2 &> /dev/null + ip vrf exec $vrf_name $PING6 $args $dip -c 10 -i 0.1 -w 2 &> /dev/null } ping6_test() @@ -821,7 +849,7 @@ ping6_test() ping6_do $1 $2 check_err $? - log_test "ping6" + log_test "ping6$3" } learning_test() diff --git a/tools/testing/selftests/net/forwarding/router_multicast.sh b/tools/testing/selftests/net/forwarding/router_multicast.sh new file mode 100755 index 000000000000..109e6d785169 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_multicast.sh @@ -0,0 +1,311 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +------------------+ +# | H1 (v$h1) | +# | 2001:db8:1::2/64 | +# | 198.51.100.2/28 | +# | $h1 + | +# +-------------|----+ +# | +# +-------------|-------------------------------+ +# | SW1 | | +# | $rp1 + | +# | 198.51.100.1/28 | +# | 2001:db8:1::1/64 | +# | | +# | 2001:db8:2::1/64 2001:db8:3::1/64 | +# | 198.51.100.17/28 198.51.100.33/28 | +# | $rp2 + $rp3 + | +# +--------------|--------------------------|---+ +# | | +# | | +# +--------------|---+ +--------------|---+ +# | H2 (v$h2) | | | H3 (v$h3) | | +# | $h2 + | | $h3 + | +# | 198.51.100.18/28 | | 198.51.100.34/28 | +# | 2001:db8:2::2/64 | | 2001:db8:3::2/64 | +# +------------------+ +------------------+ +# + +ALL_TESTS="mcast_v4 mcast_v6" +NUM_NETIFS=6 +source lib.sh +source tc_common.sh + +require_command $MCD +require_command $MC_CLI +table_name=selftests + +h1_create() +{ + simple_if_init $h1 198.51.100.2/28 2001:db8:1::2/64 + + ip route add 198.51.100.16/28 vrf v$h1 nexthop via 198.51.100.1 + ip route add 198.51.100.32/28 vrf v$h1 nexthop via 198.51.100.1 + + ip route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::1 + ip route add 2001:db8:3::/64 vrf v$h1 nexthop via 2001:db8:1::1 +} + +h1_destroy() +{ + ip route del 2001:db8:3::/64 vrf v$h1 + ip route del 2001:db8:2::/64 vrf v$h1 + + ip route del 198.51.100.32/28 vrf v$h1 + ip route del 198.51.100.16/28 vrf v$h1 + + simple_if_fini $h1 198.51.100.2/28 2001:db8:1::2/64 +} + +h2_create() +{ + simple_if_init $h2 198.51.100.18/28 2001:db8:2::2/64 + + ip route add 198.51.100.0/28 vrf v$h2 nexthop via 198.51.100.17 + ip route add 198.51.100.32/28 vrf v$h2 nexthop via 198.51.100.17 + + ip route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1 + ip route add 2001:db8:3::/64 vrf v$h2 nexthop via 2001:db8:2::1 + + tc qdisc add dev $h2 ingress +} + +h2_destroy() +{ + tc qdisc del dev $h2 ingress + + ip route del 2001:db8:3::/64 vrf v$h2 + ip route del 2001:db8:1::/64 vrf v$h2 + + ip route del 198.51.100.32/28 vrf v$h2 + ip route del 198.51.100.0/28 vrf v$h2 + + simple_if_fini $h2 198.51.100.18/28 2001:db8:2::2/64 +} + +h3_create() +{ + simple_if_init $h3 198.51.100.34/28 2001:db8:3::2/64 + + ip route add 198.51.100.0/28 vrf v$h3 nexthop via 198.51.100.33 + ip route add 198.51.100.16/28 vrf v$h3 nexthop via 198.51.100.33 + + ip route add 2001:db8:1::/64 vrf v$h3 nexthop via 2001:db8:3::1 + ip route add 2001:db8:2::/64 vrf v$h3 nexthop via 2001:db8:3::1 + + tc qdisc add dev $h3 ingress +} + +h3_destroy() +{ + tc qdisc del dev $h3 ingress + + ip route del 2001:db8:2::/64 vrf v$h3 + ip route del 2001:db8:1::/64 vrf v$h3 + + ip route del 198.51.100.16/28 vrf v$h3 + ip route del 198.51.100.0/28 vrf v$h3 + + simple_if_fini $h3 198.51.100.34/28 2001:db8:3::2/64 +} + +router_create() +{ + ip link set dev $rp1 up + ip link set dev $rp2 up + ip link set dev $rp3 up + + ip address add 198.51.100.1/28 dev $rp1 + ip address add 198.51.100.17/28 dev $rp2 + ip address add 198.51.100.33/28 dev $rp3 + + ip address add 2001:db8:1::1/64 dev $rp1 + ip address add 2001:db8:2::1/64 dev $rp2 + ip address add 2001:db8:3::1/64 dev $rp3 +} + +router_destroy() +{ + ip address del 2001:db8:3::1/64 dev $rp3 + ip address del 2001:db8:2::1/64 dev $rp2 + ip address del 2001:db8:1::1/64 dev $rp1 + + ip address del 198.51.100.33/28 dev $rp3 + ip address del 198.51.100.17/28 dev $rp2 + ip address del 198.51.100.1/28 dev $rp1 + + ip link set dev $rp3 down + ip link set dev $rp2 down + ip link set dev $rp1 down +} + +start_mcd() +{ + SMCROUTEDIR="$(mktemp -d)" + + for ((i = 1; i <= $NUM_NETIFS; ++i)); do + echo "phyint ${NETIFS[p$i]} enable" >> \ + $SMCROUTEDIR/$table_name.conf + done + + $MCD -N -I $table_name -f $SMCROUTEDIR/$table_name.conf \ + -P $SMCROUTEDIR/$table_name.pid +} + +kill_mcd() +{ + pkill $MCD + rm -rf $SMCROUTEDIR +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rp1=${NETIFS[p2]} + + rp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + rp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + start_mcd + + vrf_prepare + + h1_create + h2_create + h3_create + + router_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h3_destroy + h2_destroy + h1_destroy + + vrf_cleanup + + kill_mcd +} + +create_mcast_sg() +{ + local if_name=$1; shift + local s_addr=$1; shift + local mcast=$1; shift + local dest_ifs=${@} + + $MC_CLI -I $table_name add $if_name $s_addr $mcast $dest_ifs +} + +delete_mcast_sg() +{ + local if_name=$1; shift + local s_addr=$1; shift + local mcast=$1; shift + local dest_ifs=${@} + + $MC_CLI -I $table_name remove $if_name $s_addr $mcast $dest_ifs +} + +mcast_v4() +{ + # Add two interfaces to an MC group, send a packet to the MC group and + # verify packets are received on both. Then delete the route and verify + # packets are no longer received. + + RET=0 + + tc filter add dev $h2 ingress protocol ip pref 1 handle 122 flower \ + dst_ip 225.1.2.3 action drop + tc filter add dev $h3 ingress protocol ip pref 1 handle 133 flower \ + dst_ip 225.1.2.3 action drop + + create_mcast_sg $rp1 198.51.100.2 225.1.2.3 $rp2 $rp3 + + # Send frames with the corresponding L2 destination address. + $MZ $h1 -c 5 -p 128 -t udp -a 00:11:22:33:44:55 -b 01:00:5e:01:02:03 \ + -A 198.51.100.2 -B 225.1.2.3 -q + + tc_check_packets "dev $h2 ingress" 122 5 + check_err $? "Multicast not received on first host" + tc_check_packets "dev $h3 ingress" 133 5 + check_err $? "Multicast not received on second host" + + delete_mcast_sg $rp1 198.51.100.2 225.1.2.3 $rp2 $rp3 + + $MZ $h1 -c 5 -p 128 -t udp -a 00:11:22:33:44:55 -b 01:00:5e:01:02:03 \ + -A 198.51.100.2 -B 225.1.2.3 -q + + tc_check_packets "dev $h2 ingress" 122 5 + check_err $? "Multicast received on host although deleted" + tc_check_packets "dev $h3 ingress" 133 5 + check_err $? "Multicast received on second host although deleted" + + tc filter del dev $h3 ingress protocol ip pref 1 handle 133 flower + tc filter del dev $h2 ingress protocol ip pref 1 handle 122 flower + + log_test "mcast IPv4" +} + +mcast_v6() +{ + # Add two interfaces to an MC group, send a packet to the MC group and + # verify packets are received on both. Then delete the route and verify + # packets are no longer received. + + RET=0 + + tc filter add dev $h2 ingress protocol ipv6 pref 1 handle 122 flower \ + dst_ip ff0e::3 action drop + tc filter add dev $h3 ingress protocol ipv6 pref 1 handle 133 flower \ + dst_ip ff0e::3 action drop + + create_mcast_sg $rp1 2001:db8:1::2 ff0e::3 $rp2 $rp3 + + # Send frames with the corresponding L2 destination address. + $MZ $h1 -6 -c 5 -p 128 -t udp -a 00:11:22:33:44:55 \ + -b 33:33:00:00:00:03 -A 2001:db8:1::2 -B ff0e::3 -q + + tc_check_packets "dev $h2 ingress" 122 5 + check_err $? "Multicast not received on first host" + tc_check_packets "dev $h3 ingress" 133 5 + check_err $? "Multicast not received on second host" + + delete_mcast_sg $rp1 2001:db8:1::2 ff0e::3 $rp2 $rp3 + + $MZ $h1 -6 -c 5 -p 128 -t udp -a 00:11:22:33:44:55 \ + -b 33:33:00:00:00:03 -A 2001:db8:1::2 -B ff0e::3 -q + + tc_check_packets "dev $h2 ingress" 122 5 + check_err $? "Multicast received on first host although deleted" + tc_check_packets "dev $h3 ingress" 133 5 + check_err $? "Multicast received on second host although deleted" + + tc filter del dev $h3 ingress protocol ipv6 pref 1 handle 133 flower + tc filter del dev $h2 ingress protocol ipv6 pref 1 handle 122 flower + + log_test "mcast IPv6" +} + +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 new file mode 100755 index 000000000000..56cef3b1c194 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh @@ -0,0 +1,786 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +--------------------+ +----------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1 | | + $h2 | +# | | 192.0.2.1/28 | | | 192.0.2.2/28 | +# +----|---------------+ +--|-------------------+ +# | | +# +----|--------------------------------------------------|-------------------+ +# | SW | | | +# | +--|--------------------------------------------------|-----------------+ | +# | | + $swp1 BR1 (802.1d) + $swp2 | | +# | | | | +# | | + vx1 (vxlan) | | +# | | local 192.0.2.17 | | +# | | remote 192.0.2.34 192.0.2.50 | | +# | | id 1000 dstport $VXPORT | | +# | +-----------------------------------------------------------------------+ | +# | | +# | 192.0.2.32/28 via 192.0.2.18 | +# | 192.0.2.48/28 via 192.0.2.18 | +# | | +# | + $rp1 | +# | | 192.0.2.17/28 | +# +----|----------------------------------------------------------------------+ +# | +# +----|--------------------------------------------------------+ +# | | VRP2 (vrf) | +# | + $rp2 | +# | 192.0.2.18/28 | +# | | (maybe) HW +# ============================================================================= +# | | (likely) SW +# | + v1 (veth) + v3 (veth) | +# | | 192.0.2.33/28 | 192.0.2.49/28 | +# +----|---------------------------------------|----------------+ +# | | +# +----|------------------------------+ +----|------------------------------+ +# | + v2 (veth) NS1 (netns) | | + v4 (veth) NS2 (netns) | +# | 192.0.2.34/28 | | 192.0.2.50/28 | +# | | | | +# | 192.0.2.16/28 via 192.0.2.33 | | 192.0.2.16/28 via 192.0.2.49 | +# | 192.0.2.50/32 via 192.0.2.33 | | 192.0.2.34/32 via 192.0.2.49 | +# | | | | +# | +-------------------------------+ | | +-------------------------------+ | +# | | BR2 (802.1d) | | | | BR2 (802.1d) | | +# | | + vx2 (vxlan) | | | | + vx2 (vxlan) | | +# | | local 192.0.2.34 | | | | local 192.0.2.50 | | +# | | remote 192.0.2.17 | | | | remote 192.0.2.17 | | +# | | remote 192.0.2.50 | | | | remote 192.0.2.34 | | +# | | id 1000 dstport $VXPORT | | | | id 1000 dstport $VXPORT | | +# | | | | | | | | +# | | + w1 (veth) | | | | + w1 (veth) | | +# | +--|----------------------------+ | | +--|----------------------------+ | +# | | | | | | +# | +--|----------------------------+ | | +--|----------------------------+ | +# | | | VW2 (vrf) | | | | | VW2 (vrf) | | +# | | + w2 (veth) | | | | + w2 (veth) | | +# | | 192.0.2.3/28 | | | | 192.0.2.4/28 | | +# | +-------------------------------+ | | +-------------------------------+ | +# +-----------------------------------+ +-----------------------------------+ + +: ${VXPORT:=4789} +export VXPORT + +: ${ALL_TESTS:=" + ping_ipv4 + test_flood + test_unicast + test_ttl + test_tos + test_ecn_encap + test_ecn_decap + reapply_config + ping_ipv4 + test_flood + test_unicast + test_learning + "} + +NUM_NETIFS=6 +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 + tc qdisc add dev $h1 clsact +} + +h1_destroy() +{ + tc qdisc del dev $h1 clsact + simple_if_fini $h1 192.0.2.1/28 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 + tc qdisc add dev $h2 clsact +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + simple_if_fini $h2 192.0.2.2/28 +} + +rp1_set_addr() +{ + ip address add dev $rp1 192.0.2.17/28 + + ip route add 192.0.2.32/28 nexthop via 192.0.2.18 + ip route add 192.0.2.48/28 nexthop via 192.0.2.18 +} + +rp1_unset_addr() +{ + ip route del 192.0.2.48/28 nexthop via 192.0.2.18 + ip route del 192.0.2.32/28 nexthop via 192.0.2.18 + + ip address del dev $rp1 192.0.2.17/28 +} + +switch_create() +{ + ip link add name br1 type bridge vlan_filtering 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 $rp1 up + rp1_set_addr + + ip link add name vx1 type vxlan id 1000 \ + local 192.0.2.17 dstport "$VXPORT" \ + nolearning noudpcsum tos inherit ttl 100 + ip link set dev vx1 up + + ip link set dev vx1 master br1 + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self + bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self +} + +switch_destroy() +{ + rp1_unset_addr + ip link set dev $rp1 down + + bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self + bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self + + ip link set dev vx1 nomaster + ip link set dev vx1 down + ip link del dev vx1 + + ip link set dev $swp2 down + ip link set dev $swp2 nomaster + + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + + ip link set dev br1 down + ip link del dev br1 +} + +vrp2_create() +{ + simple_if_init $rp2 192.0.2.18/28 + __simple_if_init v1 v$rp2 192.0.2.33/28 + __simple_if_init v3 v$rp2 192.0.2.49/28 + tc qdisc add dev v1 clsact +} + +vrp2_destroy() +{ + tc qdisc del dev v1 clsact + __simple_if_fini v3 192.0.2.49/28 + __simple_if_fini v1 192.0.2.33/28 + simple_if_fini $rp2 192.0.2.18/28 +} + +ns_init_common() +{ + local in_if=$1; shift + local in_addr=$1; shift + local other_in_addr=$1; shift + local nh_addr=$1; shift + local host_addr=$1; shift + + ip link set dev $in_if up + ip address add dev $in_if $in_addr/28 + tc qdisc add dev $in_if clsact + + ip link add name br2 type bridge vlan_filtering 0 + ip link set dev br2 up + + ip link add name w1 type veth peer name w2 + + ip link set dev w1 master br2 + ip link set dev w1 up + + ip link add name vx2 type vxlan id 1000 local $in_addr dstport "$VXPORT" + ip link set dev vx2 up + bridge fdb append dev vx2 00:00:00:00:00:00 dst 192.0.2.17 self + bridge fdb append dev vx2 00:00:00:00:00:00 dst $other_in_addr self + + ip link set dev vx2 master br2 + tc qdisc add dev vx2 clsact + + simple_if_init w2 $host_addr/28 + + ip route add 192.0.2.16/28 nexthop via $nh_addr + ip route add $other_in_addr/32 nexthop via $nh_addr +} +export -f ns_init_common + +ns1_create() +{ + ip netns add ns1 + ip link set dev v2 netns ns1 + in_ns ns1 \ + ns_init_common v2 192.0.2.34 192.0.2.50 192.0.2.33 192.0.2.3 +} + +ns1_destroy() +{ + ip netns exec ns1 ip link set dev v2 netns 1 + ip netns del ns1 +} + +ns2_create() +{ + ip netns add ns2 + ip link set dev v4 netns ns2 + in_ns ns2 \ + ns_init_common v4 192.0.2.50 192.0.2.34 192.0.2.49 192.0.2.4 +} + +ns2_destroy() +{ + ip netns exec ns2 ip link set dev v4 netns 1 + ip netns del ns2 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + rp1=${NETIFS[p5]} + rp2=${NETIFS[p6]} + + vrf_prepare + forwarding_enable + + h1_create + h2_create + switch_create + + ip link add name v1 type veth peer name v2 + ip link add name v3 type veth peer name v4 + vrp2_create + ns1_create + ns2_create + + r1_mac=$(in_ns ns1 mac_get w2) + r2_mac=$(in_ns ns2 mac_get w2) + h2_mac=$(mac_get $h2) +} + +cleanup() +{ + pre_cleanup + + ns2_destroy + ns1_destroy + vrp2_destroy + ip link del dev v3 + ip link del dev v1 + + switch_destroy + h2_destroy + h1_destroy + + forwarding_restore + vrf_cleanup +} + +# For the first round of tests, vx1 is the first device to get attached to the +# bridge, and that at the point that the local IP is already configured. Try the +# other scenario of attaching the device to an already-offloaded bridge, and +# only then attach the local IP. +reapply_config() +{ + echo "Reapplying configuration" + + bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self + bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self + rp1_unset_addr + ip link set dev vx1 nomaster + sleep 5 + + ip link set dev vx1 master br1 + bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self + bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self + sleep 1 + rp1_set_addr + sleep 5 +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.2 ": local->local" + ping_test $h1 192.0.2.3 ": local->remote 1" + ping_test $h1 192.0.2.4 ": local->remote 2" +} + +maybe_in_ns() +{ + echo ${1:+in_ns} $1 +} + +__flood_counter_add_del() +{ + local add_del=$1; shift + local dev=$1; shift + local ns=$1; shift + + # Putting the ICMP capture both to HW and to SW will end up + # double-counting the packets that are trapped to slow path, such as for + # the unicast test. Adding either skip_hw or skip_sw fixes this problem, + # but with skip_hw, the flooded packets are not counted at all, because + # those are dropped due to MAC address mismatch; and skip_sw is a no-go + # for veth-based topologies. + # + # So try to install with skip_sw and fall back to skip_sw if that fails. + + $(maybe_in_ns $ns) __icmp_capture_add_del \ + $add_del 100 "" $dev skip_sw 2>/dev/null || \ + $(maybe_in_ns $ns) __icmp_capture_add_del \ + $add_del 100 "" $dev skip_hw +} + +flood_counter_install() +{ + __flood_counter_add_del add "$@" +} + +flood_counter_uninstall() +{ + __flood_counter_add_del del "$@" +} + +flood_fetch_stat() +{ + local dev=$1; shift + local ns=$1; shift + + $(maybe_in_ns $ns) tc_rule_stats_get $dev 100 ingress +} + +flood_fetch_stats() +{ + local counters=("${@}") + local counter + + for counter in "${counters[@]}"; do + flood_fetch_stat $counter + done +} + +vxlan_flood_test() +{ + local mac=$1; shift + local dst=$1; shift + local -a expects=("${@}") + + local -a counters=($h2 "vx2 ns1" "vx2 ns2") + local counter + local key + + for counter in "${counters[@]}"; do + flood_counter_install $counter + done + + local -a t0s=($(flood_fetch_stats "${counters[@]}")) + $MZ $h1 -c 10 -d 100msec -p 64 -b $mac -B $dst -t icmp -q + sleep 1 + local -a t1s=($(flood_fetch_stats "${counters[@]}")) + + for key in ${!t0s[@]}; do + local delta=$((t1s[$key] - t0s[$key])) + local expect=${expects[$key]} + + ((expect == delta)) + check_err $? "${counters[$key]}: Expected to capture $expect packets, got $delta." + done + + for counter in "${counters[@]}"; do + flood_counter_uninstall $counter + done +} + +__test_flood() +{ + local mac=$1; shift + local dst=$1; shift + local what=$1; shift + + RET=0 + + vxlan_flood_test $mac $dst 10 10 10 + + log_test "VXLAN: $what" +} + +test_flood() +{ + __test_flood de:ad:be:ef:13:37 192.0.2.100 "flood" +} + +vxlan_fdb_add_del() +{ + local add_del=$1; shift + local mac=$1; shift + local dev=$1; shift + local dst=$1; shift + + bridge fdb $add_del dev $dev $mac self static permanent \ + ${dst:+dst} $dst 2>/dev/null + bridge fdb $add_del dev $dev $mac master static 2>/dev/null +} + +__test_unicast() +{ + local mac=$1; shift + local dst=$1; shift + local hit_idx=$1; shift + local what=$1; shift + + RET=0 + + local -a expects=(0 0 0) + expects[$hit_idx]=10 + + vxlan_flood_test $mac $dst "${expects[@]}" + + log_test "VXLAN: $what" +} + +test_unicast() +{ + local -a targets=("$h2_mac $h2" + "$r1_mac vx1 192.0.2.34" + "$r2_mac vx1 192.0.2.50") + local target + + for target in "${targets[@]}"; do + vxlan_fdb_add_del add $target + done + + __test_unicast $h2_mac 192.0.2.2 0 "local MAC unicast" + __test_unicast $r1_mac 192.0.2.3 1 "remote MAC 1 unicast" + __test_unicast $r2_mac 192.0.2.4 2 "remote MAC 2 unicast" + + for target in "${targets[@]}"; do + vxlan_fdb_add_del del $target + done +} + +vxlan_ping_test() +{ + local ping_dev=$1; shift + local ping_dip=$1; shift + local ping_args=$1; shift + local capture_dev=$1; shift + local capture_dir=$1; shift + local capture_pref=$1; shift + local expect=$1; shift + + local t0=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir) + ping_do $ping_dev $ping_dip "$ping_args" + local t1=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir) + local delta=$((t1 - t0)) + + # Tolerate a couple stray extra packets. + ((expect <= delta && delta <= expect + 2)) + check_err $? "$capture_dev: Expected to capture $expect packets, got $delta." +} + +test_ttl() +{ + RET=0 + + tc filter add dev v1 egress pref 77 prot ip \ + flower ip_ttl 99 action pass + vxlan_ping_test $h1 192.0.2.3 "" v1 egress 77 10 + tc filter del dev v1 egress pref 77 prot ip + + log_test "VXLAN: envelope TTL" +} + +test_tos() +{ + RET=0 + + tc filter add dev v1 egress pref 77 prot ip \ + flower ip_tos 0x40 action pass + vxlan_ping_test $h1 192.0.2.3 "-Q 0x40" v1 egress 77 10 + vxlan_ping_test $h1 192.0.2.3 "-Q 0x30" v1 egress 77 0 + tc filter del dev v1 egress pref 77 prot ip + + log_test "VXLAN: envelope TOS inheritance" +} + +__test_ecn_encap() +{ + local q=$1; shift + local tos=$1; shift + + RET=0 + + tc filter add dev v1 egress pref 77 prot ip \ + flower ip_tos $tos action pass + sleep 1 + vxlan_ping_test $h1 192.0.2.3 "-Q $q" v1 egress 77 10 + tc filter del dev v1 egress pref 77 prot ip + + log_test "VXLAN: ECN encap: $q->$tos" +} + +test_ecn_encap() +{ + # In accordance with INET_ECN_encapsulate() + __test_ecn_encap 0x00 0x00 + __test_ecn_encap 0x01 0x01 + __test_ecn_encap 0x02 0x02 + __test_ecn_encap 0x03 0x02 +} + +vxlan_encapped_ping_do() +{ + local count=$1; shift + local dev=$1; shift + local next_hop_mac=$1; shift + local dest_ip=$1; shift + local dest_mac=$1; shift + local inner_tos=$1; shift + local outer_tos=$1; shift + + $MZ $dev -c $count -d 100msec -q \ + -b $next_hop_mac -B $dest_ip \ + -t udp tos=$outer_tos,sp=23456,dp=$VXPORT,p=$(: + )"08:"$( : VXLAN flags + )"00:00:00:"$( : VXLAN reserved + )"00:03:e8:"$( : VXLAN VNI + )"00:"$( : VXLAN reserved + )"$dest_mac:"$( : ETH daddr + )"$(mac_get w2):"$( : ETH saddr + )"08:00:"$( : ETH type + )"45:"$( : IP version + IHL + )"$inner_tos:"$( : IP TOS + )"00:54:"$( : IP total length + )"99:83:"$( : IP identification + )"40:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"01:"$( : IP proto + )"00:00:"$( : IP header csum + )"c0:00:02:03:"$( : IP saddr: 192.0.2.3 + )"c0:00:02:01:"$( : IP daddr: 192.0.2.1 + )"08:"$( : ICMP type + )"00:"$( : ICMP code + )"8b:f2:"$( : ICMP csum + )"1f:6a:"$( : ICMP request identifier + )"00:01:"$( : ICMP request sequence number + )"4f:ff:c5:5b:00:00:00:00:"$( : ICMP payload + )"6d:74:0b:00:00:00:00:00:"$( : + )"10:11:12:13:14:15:16:17:"$( : + )"18:19:1a:1b:1c:1d:1e:1f:"$( : + )"20:21:22:23:24:25:26:27:"$( : + )"28:29:2a:2b:2c:2d:2e:2f:"$( : + )"30:31:32:33:34:35:36:37" +} +export -f vxlan_encapped_ping_do + +vxlan_encapped_ping_test() +{ + local ping_dev=$1; shift + local nh_dev=$1; shift + local ping_dip=$1; shift + local inner_tos=$1; shift + local outer_tos=$1; shift + local stat_get=$1; shift + local expect=$1; shift + + local t0=$($stat_get) + + in_ns ns1 \ + vxlan_encapped_ping_do 10 $ping_dev $(mac_get $nh_dev) \ + $ping_dip $(mac_get $h1) \ + $inner_tos $outer_tos + + local t1=$($stat_get) + local delta=$((t1 - t0)) + + # Tolerate a couple stray extra packets. + ((expect <= delta && delta <= expect + 2)) + check_err $? "Expected to capture $expect packets, got $delta." +} +export -f vxlan_encapped_ping_test + +__test_ecn_decap() +{ + local orig_inner_tos=$1; shift + local orig_outer_tos=$1; shift + local decapped_tos=$1; shift + + RET=0 + + tc filter add dev $h1 ingress pref 77 prot ip \ + flower ip_tos $decapped_tos action pass + sleep 1 + vxlan_encapped_ping_test v2 v1 192.0.2.17 \ + $orig_inner_tos $orig_outer_tos \ + "tc_rule_stats_get $h1 77 ingress" 10 + tc filter del dev $h1 ingress pref 77 + + log_test "VXLAN: ECN decap: $orig_outer_tos/$orig_inner_tos->$decapped_tos" +} + +test_ecn_decap_error() +{ + local orig_inner_tos=00 + local orig_outer_tos=03 + + RET=0 + + vxlan_encapped_ping_test v2 v1 192.0.2.17 \ + $orig_inner_tos $orig_outer_tos \ + "link_stats_rx_errors_get vx1" 10 + + log_test "VXLAN: ECN decap: $orig_outer_tos/$orig_inner_tos->error" +} + +test_ecn_decap() +{ + # In accordance with INET_ECN_decapsulate() + __test_ecn_decap 00 00 0x00 + __test_ecn_decap 01 01 0x01 + __test_ecn_decap 02 01 0x02 + __test_ecn_decap 01 03 0x03 + __test_ecn_decap 02 03 0x03 + test_ecn_decap_error +} + +test_learning() +{ + local mac=de:ad:be:ef:13:37 + local dst=192.0.2.100 + + # Enable learning on the VxLAN device and set ageing time to 10 seconds + ip link set dev br1 type bridge ageing_time 1000 + ip link set dev vx1 type vxlan ageing 10 + ip link set dev vx1 type vxlan learning + reapply_config + + # Check that flooding works + RET=0 + + vxlan_flood_test $mac $dst 10 10 10 + + log_test "VXLAN: flood before learning" + + # Send a packet with source mac set to $mac from host w2 and check that + # a corresponding entry is created in VxLAN device vx1 + RET=0 + + in_ns ns1 $MZ w2 -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff -B $dst \ + -t icmp -q + sleep 1 + + bridge fdb show brport vx1 | grep $mac | grep -q self + check_err $? + bridge fdb show brport vx1 | grep $mac | grep -q -v self + check_err $? + + log_test "VXLAN: show learned FDB entry" + + # Repeat first test and check that packets only reach host w2 in ns1 + RET=0 + + vxlan_flood_test $mac $dst 0 10 0 + + log_test "VXLAN: learned FDB entry" + + # Delete the learned FDB entry from the VxLAN and bridge devices and + # check that packets are flooded + RET=0 + + bridge fdb del dev vx1 $mac master self + sleep 1 + + vxlan_flood_test $mac $dst 10 10 10 + + log_test "VXLAN: deletion of learned FDB entry" + + # Re-learn the first FDB entry and check that it is correctly aged-out + RET=0 + + in_ns ns1 $MZ w2 -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff -B $dst \ + -t icmp -q + sleep 1 + + bridge fdb show brport vx1 | grep $mac | grep -q self + check_err $? + bridge fdb show brport vx1 | grep $mac | grep -q -v self + check_err $? + + vxlan_flood_test $mac $dst 0 10 0 + + sleep 20 + + bridge fdb show brport vx1 | grep $mac | grep -q self + check_fail $? + bridge fdb show brport vx1 | grep $mac | grep -q -v self + check_fail $? + + vxlan_flood_test $mac $dst 10 10 10 + + log_test "VXLAN: Ageing of learned FDB entry" + + # Toggle learning on the bridge port and check that the bridge's FDB + # is populated only when it should + RET=0 + + ip link set dev vx1 type bridge_slave learning off + + in_ns ns1 $MZ w2 -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff -B $dst \ + -t icmp -q + sleep 1 + + bridge fdb show brport vx1 | grep $mac | grep -q -v self + check_fail $? + + ip link set dev vx1 type bridge_slave learning on + + in_ns ns1 $MZ w2 -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff -B $dst \ + -t icmp -q + sleep 1 + + bridge fdb show brport vx1 | grep $mac | grep -q -v self + check_err $? + + log_test "VXLAN: learning toggling on bridge port" + + # Restore previous settings + ip link set dev vx1 type vxlan nolearning + ip link set dev vx1 type vxlan ageing 300 + ip link set dev br1 type bridge ageing_time 30000 + reapply_config +} + +test_all() +{ + echo "Running tests with UDP port $VXPORT" + tests_run +} + +trap cleanup EXIT + +setup_prepare +setup_wait +test_all + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh new file mode 100755 index 000000000000..3bf3da69195f --- /dev/null +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh @@ -0,0 +1,10 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# A wrapper to run VXLAN tests with an unusual port number. + +VXPORT=8472 +ALL_TESTS=" + ping_ipv4 +" +source vxlan_bridge_1d.sh diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh new file mode 100755 index 000000000000..a5789721ba92 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh @@ -0,0 +1,860 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-----------------------+ +------------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1.10 | | + $h2.10 | +# | | 192.0.2.1/28 | | | 192.0.2.2/28 | +# | | | | | | +# | | + $h1.20 | | | + $h2.20 | +# | \ | 198.51.100.1/24 | | \ | 198.51.100.2/24 | +# | \| | | \| | +# | + $h1 | | + $h2 | +# +----|------------------+ +----|-------------------+ +# | | +# +----|--------------------------------------------------|-------------------+ +# | SW | | | +# | +--|--------------------------------------------------|-----------------+ | +# | | + $swp1 BR1 (802.1q) + $swp2 | | +# | | vid 10 vid 10 | | +# | | vid 20 vid 20 | | +# | | | | +# | | + vx10 (vxlan) + vx20 (vxlan) | | +# | | local 192.0.2.17 local 192.0.2.17 | | +# | | remote 192.0.2.34 192.0.2.50 remote 192.0.2.34 192.0.2.50 | | +# | | id 1000 dstport $VXPORT id 2000 dstport $VXPORT | | +# | | vid 10 pvid untagged vid 20 pvid untagged | | +# | +-----------------------------------------------------------------------+ | +# | | +# | 192.0.2.32/28 via 192.0.2.18 | +# | 192.0.2.48/28 via 192.0.2.18 | +# | | +# | + $rp1 | +# | | 192.0.2.17/28 | +# +----|----------------------------------------------------------------------+ +# | +# +----|--------------------------------------------------------+ +# | | VRP2 (vrf) | +# | + $rp2 | +# | 192.0.2.18/28 | +# | | (maybe) HW +# ============================================================================= +# | | (likely) SW +# | + v1 (veth) + v3 (veth) | +# | | 192.0.2.33/28 | 192.0.2.49/28 | +# +----|---------------------------------------|----------------+ +# | | +# +----|------------------------------+ +----|------------------------------+ +# | + v2 (veth) NS1 (netns) | | + v4 (veth) NS2 (netns) | +# | 192.0.2.34/28 | | 192.0.2.50/28 | +# | | | | +# | 192.0.2.16/28 via 192.0.2.33 | | 192.0.2.16/28 via 192.0.2.49 | +# | 192.0.2.50/32 via 192.0.2.33 | | 192.0.2.34/32 via 192.0.2.49 | +# | | | | +# | +-------------------------------+ | | +-------------------------------+ | +# | | BR2 (802.1q) | | | | BR2 (802.1q) | | +# | | + vx10 (vxlan) | | | | + vx10 (vxlan) | | +# | | local 192.0.2.34 | | | | local 192.0.2.50 | | +# | | remote 192.0.2.17 | | | | remote 192.0.2.17 | | +# | | remote 192.0.2.50 | | | | remote 192.0.2.34 | | +# | | id 1000 dstport $VXPORT | | | | id 1000 dstport $VXPORT | | +# | | vid 10 pvid untagged | | | | vid 10 pvid untagged | | +# | | | | | | | | +# | | + vx20 (vxlan) | | | | + vx20 (vxlan) | | +# | | local 192.0.2.34 | | | | local 192.0.2.50 | | +# | | remote 192.0.2.17 | | | | remote 192.0.2.17 | | +# | | remote 192.0.2.50 | | | | remote 192.0.2.34 | | +# | | id 2000 dstport $VXPORT | | | | id 2000 dstport $VXPORT | | +# | | vid 20 pvid untagged | | | | vid 20 pvid untagged | | +# | | | | | | | | +# | | + w1 (veth) | | | | + w1 (veth) | | +# | | | vid 10 | | | | | vid 10 | | +# | | | vid 20 | | | | | vid 20 | | +# | +--|----------------------------+ | | +--|----------------------------+ | +# | | | | | | +# | +--|----------------------------+ | | +--|----------------------------+ | +# | | + w2 (veth) VW2 (vrf) | | | | + w2 (veth) VW2 (vrf) | | +# | | |\ | | | | |\ | | +# | | | + w2.10 | | | | | + w2.10 | | +# | | | 192.0.2.3/28 | | | | | 192.0.2.4/28 | | +# | | | | | | | | | | +# | | + w2.20 | | | | + w2.20 | | +# | | 198.51.100.3/24 | | | | 198.51.100.4/24 | | +# | +-------------------------------+ | | +-------------------------------+ | +# +-----------------------------------+ +-----------------------------------+ + +: ${VXPORT:=4789} +export VXPORT + +: ${ALL_TESTS:=" + ping_ipv4 + test_flood + test_unicast + reapply_config + ping_ipv4 + test_flood + test_unicast + test_learning + test_pvid + "} + +NUM_NETIFS=6 +source lib.sh + +h1_create() +{ + simple_if_init $h1 + tc qdisc add dev $h1 clsact + vlan_create $h1 10 v$h1 192.0.2.1/28 + vlan_create $h1 20 v$h1 198.51.100.1/24 +} + +h1_destroy() +{ + vlan_destroy $h1 20 + vlan_destroy $h1 10 + tc qdisc del dev $h1 clsact + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 + tc qdisc add dev $h2 clsact + vlan_create $h2 10 v$h2 192.0.2.2/28 + vlan_create $h2 20 v$h2 198.51.100.2/24 +} + +h2_destroy() +{ + vlan_destroy $h2 20 + vlan_destroy $h2 10 + tc qdisc del dev $h2 clsact + simple_if_fini $h2 +} + +rp1_set_addr() +{ + ip address add dev $rp1 192.0.2.17/28 + + ip route add 192.0.2.32/28 nexthop via 192.0.2.18 + ip route add 192.0.2.48/28 nexthop via 192.0.2.18 +} + +rp1_unset_addr() +{ + ip route del 192.0.2.48/28 nexthop via 192.0.2.18 + ip route del 192.0.2.32/28 nexthop via 192.0.2.18 + + ip address del dev $rp1 192.0.2.17/28 +} + +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 $rp1 up + rp1_set_addr + + ip link add name vx10 type vxlan id 1000 \ + local 192.0.2.17 dstport "$VXPORT" \ + 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 192.0.2.17 dstport "$VXPORT" \ + 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 + bridge vlan add vid 20 dev $swp1 + + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + bridge vlan add vid 10 dev $swp2 + bridge vlan add vid 20 dev $swp2 + + bridge fdb append dev vx10 00:00:00:00:00:00 dst 192.0.2.34 self + bridge fdb append dev vx10 00:00:00:00:00:00 dst 192.0.2.50 self + + bridge fdb append dev vx20 00:00:00:00:00:00 dst 192.0.2.34 self + bridge fdb append dev vx20 00:00:00:00:00:00 dst 192.0.2.50 self +} + +switch_destroy() +{ + bridge fdb del dev vx20 00:00:00:00:00:00 dst 192.0.2.50 self + bridge fdb del dev vx20 00:00:00:00:00:00 dst 192.0.2.34 self + + bridge fdb del dev vx10 00:00:00:00:00:00 dst 192.0.2.50 self + bridge fdb del dev vx10 00:00:00:00:00:00 dst 192.0.2.34 self + + bridge vlan del vid 20 dev $swp2 + bridge vlan del vid 10 dev $swp2 + ip link set dev $swp2 down + ip link set dev $swp2 nomaster + + bridge vlan del vid 20 dev $swp1 + 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 + + rp1_unset_addr + ip link set dev $rp1 down + + ip link set dev br1 down + ip link del dev br1 +} + +vrp2_create() +{ + simple_if_init $rp2 192.0.2.18/28 + __simple_if_init v1 v$rp2 192.0.2.33/28 + __simple_if_init v3 v$rp2 192.0.2.49/28 + tc qdisc add dev v1 clsact +} + +vrp2_destroy() +{ + tc qdisc del dev v1 clsact + __simple_if_fini v3 192.0.2.49/28 + __simple_if_fini v1 192.0.2.33/28 + simple_if_fini $rp2 192.0.2.18/28 +} + +ns_init_common() +{ + local in_if=$1; shift + local in_addr=$1; shift + local other_in_addr=$1; shift + local nh_addr=$1; shift + local host_addr1=$1; shift + local host_addr2=$1; shift + + ip link set dev $in_if up + ip address add dev $in_if $in_addr/28 + tc qdisc add dev $in_if clsact + + ip link add name br2 type bridge vlan_filtering 1 vlan_default_pvid 0 + ip link set dev br2 up + + ip link add name w1 type veth peer name w2 + + ip link set dev w1 master br2 + ip link set dev w1 up + + bridge vlan add vid 10 dev w1 + bridge vlan add vid 20 dev w1 + + ip link add name vx10 type vxlan id 1000 local $in_addr \ + dstport "$VXPORT" + ip link set dev vx10 up + bridge fdb append dev vx10 00:00:00:00:00:00 dst 192.0.2.17 self + bridge fdb append dev vx10 00:00:00:00:00:00 dst $other_in_addr self + + ip link set dev vx10 master br2 + tc qdisc add dev vx10 clsact + + bridge vlan add vid 10 dev vx10 pvid untagged + + ip link add name vx20 type vxlan id 2000 local $in_addr \ + dstport "$VXPORT" + ip link set dev vx20 up + bridge fdb append dev vx20 00:00:00:00:00:00 dst 192.0.2.17 self + bridge fdb append dev vx20 00:00:00:00:00:00 dst $other_in_addr self + + ip link set dev vx20 master br2 + tc qdisc add dev vx20 clsact + + bridge vlan add vid 20 dev vx20 pvid untagged + + simple_if_init w2 + vlan_create w2 10 vw2 $host_addr1/28 + vlan_create w2 20 vw2 $host_addr2/24 + + ip route add 192.0.2.16/28 nexthop via $nh_addr + ip route add $other_in_addr/32 nexthop via $nh_addr +} +export -f ns_init_common + +ns1_create() +{ + ip netns add ns1 + ip link set dev v2 netns ns1 + in_ns ns1 \ + ns_init_common v2 192.0.2.34 192.0.2.50 192.0.2.33 192.0.2.3 \ + 198.51.100.3 +} + +ns1_destroy() +{ + ip netns exec ns1 ip link set dev v2 netns 1 + ip netns del ns1 +} + +ns2_create() +{ + ip netns add ns2 + ip link set dev v4 netns ns2 + in_ns ns2 \ + ns_init_common v4 192.0.2.50 192.0.2.34 192.0.2.49 192.0.2.4 \ + 198.51.100.4 +} + +ns2_destroy() +{ + ip netns exec ns2 ip link set dev v4 netns 1 + ip netns del ns2 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + rp1=${NETIFS[p5]} + rp2=${NETIFS[p6]} + + vrf_prepare + forwarding_enable + + h1_create + h2_create + switch_create + + ip link add name v1 type veth peer name v2 + ip link add name v3 type veth peer name v4 + vrp2_create + ns1_create + ns2_create + + r1_mac=$(in_ns ns1 mac_get w2) + r2_mac=$(in_ns ns2 mac_get w2) + h2_mac=$(mac_get $h2) +} + +cleanup() +{ + pre_cleanup + + ns2_destroy + ns1_destroy + vrp2_destroy + ip link del dev v3 + ip link del dev v1 + + switch_destroy + h2_destroy + h1_destroy + + forwarding_restore + vrf_cleanup +} + +# For the first round of tests, vx10 and vx20 were the first devices to get +# attached to the bridge, and that at the point that the local IP is already +# configured. Try the other scenario of attaching these devices to a bridge +# that already has local ports members, and only then assign the local IP. +reapply_config() +{ + log_info "Reapplying configuration" + + bridge fdb del dev vx20 00:00:00:00:00:00 dst 192.0.2.50 self + bridge fdb del dev vx20 00:00:00:00:00:00 dst 192.0.2.34 self + + bridge fdb del dev vx10 00:00:00:00:00:00 dst 192.0.2.50 self + bridge fdb del dev vx10 00:00:00:00:00:00 dst 192.0.2.34 self + + ip link set dev vx20 nomaster + ip link set dev vx10 nomaster + + rp1_unset_addr + sleep 5 + + ip link set dev vx10 master br1 + bridge vlan add vid 10 dev vx10 pvid untagged + + ip link set dev vx20 master br1 + bridge vlan add vid 20 dev vx20 pvid untagged + + bridge fdb append dev vx10 00:00:00:00:00:00 dst 192.0.2.34 self + bridge fdb append dev vx10 00:00:00:00:00:00 dst 192.0.2.50 self + + bridge fdb append dev vx20 00:00:00:00:00:00 dst 192.0.2.34 self + bridge fdb append dev vx20 00:00:00:00:00:00 dst 192.0.2.50 self + + rp1_set_addr + sleep 5 +} + +ping_ipv4() +{ + ping_test $h1.10 192.0.2.2 ": local->local vid 10" + ping_test $h1.20 198.51.100.2 ": local->local vid 20" + ping_test $h1.10 192.0.2.3 ": local->remote 1 vid 10" + ping_test $h1.10 192.0.2.4 ": local->remote 2 vid 10" + ping_test $h1.20 198.51.100.3 ": local->remote 1 vid 20" + ping_test $h1.20 198.51.100.4 ": local->remote 2 vid 20" +} + +maybe_in_ns() +{ + echo ${1:+in_ns} $1 +} + +__flood_counter_add_del() +{ + local add_del=$1; shift + local dev=$1; shift + local ns=$1; shift + + # Putting the ICMP capture both to HW and to SW will end up + # double-counting the packets that are trapped to slow path, such as for + # the unicast test. Adding either skip_hw or skip_sw fixes this problem, + # but with skip_hw, the flooded packets are not counted at all, because + # those are dropped due to MAC address mismatch; and skip_sw is a no-go + # for veth-based topologies. + # + # So try to install with skip_sw and fall back to skip_sw if that fails. + + $(maybe_in_ns $ns) __icmp_capture_add_del \ + $add_del 100 "" $dev skip_sw 2>/dev/null || \ + $(maybe_in_ns $ns) __icmp_capture_add_del \ + $add_del 100 "" $dev skip_hw +} + +flood_counter_install() +{ + __flood_counter_add_del add "$@" +} + +flood_counter_uninstall() +{ + __flood_counter_add_del del "$@" +} + +flood_fetch_stat() +{ + local dev=$1; shift + local ns=$1; shift + + $(maybe_in_ns $ns) tc_rule_stats_get $dev 100 ingress +} + +flood_fetch_stats() +{ + local counters=("${@}") + local counter + + for counter in "${counters[@]}"; do + flood_fetch_stat $counter + done +} + +vxlan_flood_test() +{ + local mac=$1; shift + local dst=$1; shift + local vid=$1; shift + local -a expects=("${@}") + + local -a counters=($h2 "vx10 ns1" "vx20 ns1" "vx10 ns2" "vx20 ns2") + local counter + local key + + # Packets reach the local host tagged whereas they reach the VxLAN + # devices untagged. In order to be able to use the same filter for + # all counters, make sure the packets also reach the local host + # untagged + bridge vlan add vid $vid dev $swp2 untagged + for counter in "${counters[@]}"; do + flood_counter_install $counter + done + + local -a t0s=($(flood_fetch_stats "${counters[@]}")) + $MZ $h1 -Q $vid -c 10 -d 100msec -p 64 -b $mac -B $dst -t icmp -q + sleep 1 + local -a t1s=($(flood_fetch_stats "${counters[@]}")) + + for key in ${!t0s[@]}; do + local delta=$((t1s[$key] - t0s[$key])) + local expect=${expects[$key]} + + ((expect == delta)) + check_err $? "${counters[$key]}: Expected to capture $expect packets, got $delta." + done + + for counter in "${counters[@]}"; do + flood_counter_uninstall $counter + done + bridge vlan add vid $vid dev $swp2 +} + +__test_flood() +{ + local mac=$1; shift + local dst=$1; shift + local vid=$1; shift + local what=$1; shift + local -a expects=("${@}") + + RET=0 + + vxlan_flood_test $mac $dst $vid "${expects[@]}" + + log_test "VXLAN: $what" +} + +test_flood() +{ + __test_flood de:ad:be:ef:13:37 192.0.2.100 10 "flood vlan 10" \ + 10 10 0 10 0 + __test_flood ca:fe:be:ef:13:37 198.51.100.100 20 "flood vlan 20" \ + 10 0 10 0 10 +} + +vxlan_fdb_add_del() +{ + local add_del=$1; shift + local vid=$1; shift + local mac=$1; shift + local dev=$1; shift + local dst=$1; shift + + bridge fdb $add_del dev $dev $mac self static permanent \ + ${dst:+dst} $dst 2>/dev/null + bridge fdb $add_del dev $dev $mac master static vlan $vid 2>/dev/null +} + +__test_unicast() +{ + local mac=$1; shift + local dst=$1; shift + local hit_idx=$1; shift + local vid=$1; shift + local what=$1; shift + + RET=0 + + local -a expects=(0 0 0 0 0) + expects[$hit_idx]=10 + + vxlan_flood_test $mac $dst $vid "${expects[@]}" + + log_test "VXLAN: $what" +} + +test_unicast() +{ + local -a targets=("$h2_mac $h2" + "$r1_mac vx10 192.0.2.34" + "$r2_mac vx10 192.0.2.50") + local target + + log_info "unicast vlan 10" + + for target in "${targets[@]}"; do + vxlan_fdb_add_del add 10 $target + done + + __test_unicast $h2_mac 192.0.2.2 0 10 "local MAC unicast" + __test_unicast $r1_mac 192.0.2.3 1 10 "remote MAC 1 unicast" + __test_unicast $r2_mac 192.0.2.4 3 10 "remote MAC 2 unicast" + + for target in "${targets[@]}"; do + vxlan_fdb_add_del del 10 $target + done + + log_info "unicast vlan 20" + + targets=("$h2_mac $h2" "$r1_mac vx20 192.0.2.34" \ + "$r2_mac vx20 192.0.2.50") + + for target in "${targets[@]}"; do + vxlan_fdb_add_del add 20 $target + done + + __test_unicast $h2_mac 198.51.100.2 0 20 "local MAC unicast" + __test_unicast $r1_mac 198.51.100.3 2 20 "remote MAC 1 unicast" + __test_unicast $r2_mac 198.51.100.4 4 20 "remote MAC 2 unicast" + + for target in "${targets[@]}"; do + vxlan_fdb_add_del del 20 $target + done +} + +test_pvid() +{ + local -a expects=(0 0 0 0 0) + local mac=de:ad:be:ef:13:37 + local dst=192.0.2.100 + local vid=10 + + # Check that flooding works + RET=0 + + expects[0]=10; expects[1]=10; expects[3]=10 + vxlan_flood_test $mac $dst $vid "${expects[@]}" + + log_test "VXLAN: flood before pvid off" + + # Toggle PVID off and test that flood to remote hosts does not work + RET=0 + + bridge vlan add vid 10 dev vx10 + + expects[0]=10; expects[1]=0; expects[3]=0 + vxlan_flood_test $mac $dst $vid "${expects[@]}" + + log_test "VXLAN: flood after pvid off" + + # Toggle PVID on and test that flood to remote hosts does work + RET=0 + + bridge vlan add vid 10 dev vx10 pvid untagged + + expects[0]=10; expects[1]=10; expects[3]=10 + vxlan_flood_test $mac $dst $vid "${expects[@]}" + + log_test "VXLAN: flood after pvid on" + + # Add a new VLAN and test that it does not affect flooding + RET=0 + + bridge vlan add vid 30 dev vx10 + + expects[0]=10; expects[1]=10; expects[3]=10 + vxlan_flood_test $mac $dst $vid "${expects[@]}" + + bridge vlan del vid 30 dev vx10 + + log_test "VXLAN: flood after vlan add" + + # Remove currently mapped VLAN and test that flood to remote hosts does + # not work + RET=0 + + bridge vlan del vid 10 dev vx10 + + expects[0]=10; expects[1]=0; expects[3]=0 + vxlan_flood_test $mac $dst $vid "${expects[@]}" + + log_test "VXLAN: flood after vlan delete" + + # Re-add the VLAN and test that flood to remote hosts does work + RET=0 + + bridge vlan add vid 10 dev vx10 pvid untagged + + expects[0]=10; expects[1]=10; expects[3]=10 + vxlan_flood_test $mac $dst $vid "${expects[@]}" + + log_test "VXLAN: flood after vlan re-add" +} + +vxlan_ping_test() +{ + local ping_dev=$1; shift + local ping_dip=$1; shift + local ping_args=$1; shift + local capture_dev=$1; shift + local capture_dir=$1; shift + local capture_pref=$1; shift + local expect=$1; shift + + local t0=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir) + ping_do $ping_dev $ping_dip "$ping_args" + local t1=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir) + local delta=$((t1 - t0)) + + # Tolerate a couple stray extra packets. + ((expect <= delta && delta <= expect + 2)) + check_err $? "$capture_dev: Expected to capture $expect packets, got $delta." +} + +__test_learning() +{ + local -a expects=(0 0 0 0 0) + local mac=$1; shift + local dst=$1; shift + local vid=$1; shift + local idx1=$1; shift + local idx2=$1; shift + local vx=vx$vid + + # Check that flooding works + RET=0 + + expects[0]=10; expects[$idx1]=10; expects[$idx2]=10 + vxlan_flood_test $mac $dst $vid "${expects[@]}" + + log_test "VXLAN: flood before learning" + + # Send a packet with source mac set to $mac from host w2 and check that + # a corresponding entry is created in the VxLAN device + RET=0 + + in_ns ns1 $MZ w2 -Q $vid -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff \ + -B $dst -t icmp -q + sleep 1 + + bridge fdb show brport $vx | grep $mac | grep -q self + check_err $? + bridge fdb show brport $vx | grep $mac | grep "vlan $vid" \ + | grep -q -v self + check_err $? + + log_test "VXLAN: show learned FDB entry" + + # Repeat first test and check that packets only reach host w2 in ns1 + RET=0 + + expects[0]=0; expects[$idx1]=10; expects[$idx2]=0 + vxlan_flood_test $mac $dst $vid "${expects[@]}" + + log_test "VXLAN: learned FDB entry" + + # Delete the learned FDB entry from the VxLAN and bridge devices and + # check that packets are flooded + RET=0 + + bridge fdb del dev $vx $mac master self vlan $vid + sleep 1 + + expects[0]=10; expects[$idx1]=10; expects[$idx2]=10 + vxlan_flood_test $mac $dst $vid "${expects[@]}" + + log_test "VXLAN: deletion of learned FDB entry" + + # Re-learn the first FDB entry and check that it is correctly aged-out + RET=0 + + in_ns ns1 $MZ w2 -Q $vid -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff \ + -B $dst -t icmp -q + sleep 1 + + bridge fdb show brport $vx | grep $mac | grep -q self + check_err $? + bridge fdb show brport $vx | grep $mac | grep "vlan $vid" \ + | grep -q -v self + check_err $? + + expects[0]=0; expects[$idx1]=10; expects[$idx2]=0 + vxlan_flood_test $mac $dst $vid "${expects[@]}" + + sleep 20 + + bridge fdb show brport $vx | grep $mac | grep -q self + check_fail $? + bridge fdb show brport $vx | grep $mac | grep "vlan $vid" \ + | grep -q -v self + check_fail $? + + expects[0]=10; expects[$idx1]=10; expects[$idx2]=10 + vxlan_flood_test $mac $dst $vid "${expects[@]}" + + log_test "VXLAN: Ageing of learned FDB entry" + + # Toggle learning on the bridge port and check that the bridge's FDB + # is populated only when it should + RET=0 + + ip link set dev $vx type bridge_slave learning off + + in_ns ns1 $MZ w2 -Q $vid -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff \ + -B $dst -t icmp -q + sleep 1 + + bridge fdb show brport $vx | grep $mac | grep "vlan $vid" \ + | grep -q -v self + check_fail $? + + ip link set dev $vx type bridge_slave learning on + + in_ns ns1 $MZ w2 -Q $vid -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff \ + -B $dst -t icmp -q + sleep 1 + + bridge fdb show brport $vx | grep $mac | grep "vlan $vid" \ + | grep -q -v self + check_err $? + + log_test "VXLAN: learning toggling on bridge port" +} + +test_learning() +{ + local mac=de:ad:be:ef:13:37 + local dst=192.0.2.100 + local vid=10 + + # Enable learning on the VxLAN devices and set ageing time to 10 seconds + ip link set dev br1 type bridge ageing_time 1000 + ip link set dev vx10 type vxlan ageing 10 + ip link set dev vx10 type vxlan learning + ip link set dev vx20 type vxlan ageing 10 + ip link set dev vx20 type vxlan learning + reapply_config + + log_info "learning vlan 10" + + __test_learning $mac $dst $vid 1 3 + + log_info "learning vlan 20" + + mac=ca:fe:be:ef:13:37 + dst=198.51.100.100 + vid=20 + + __test_learning $mac $dst $vid 2 4 + + # Restore previous settings + ip link set dev vx20 type vxlan nolearning + ip link set dev vx20 type vxlan ageing 300 + ip link set dev vx10 type vxlan nolearning + ip link set dev vx10 type vxlan ageing 300 + ip link set dev br1 type bridge ageing_time 30000 + reapply_config +} + +test_all() +{ + log_info "Running tests with UDP port $VXPORT" + tests_run +} + +trap cleanup EXIT + +setup_prepare +setup_wait +test_all + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_port_8472.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_port_8472.sh new file mode 100755 index 000000000000..b1b2d1a3164f --- /dev/null +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_port_8472.sh @@ -0,0 +1,10 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# A wrapper to run VXLAN tests with an unusual port number. + +VXPORT=8472 +ALL_TESTS=" + ping_ipv4 +" +source vxlan_bridge_1q.sh diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index 406cc70c571d..4b02933cab8a 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -651,12 +651,13 @@ static void do_flush_datagram(int fd, int type) static void do_rx(int domain, int type, int protocol) { + const int cfg_receiver_wait_ms = 400; uint64_t tstop; int fd; fd = do_setup_rx(domain, type, protocol); - tstop = gettimeofday_ms() + cfg_runtime_ms; + tstop = gettimeofday_ms() + cfg_runtime_ms + cfg_receiver_wait_ms; do { if (type == SOCK_STREAM) do_flush_tcp(fd); diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh index c43c6debda06..825ffec85cea 100755 --- a/tools/testing/selftests/net/msg_zerocopy.sh +++ b/tools/testing/selftests/net/msg_zerocopy.sh @@ -25,6 +25,8 @@ readonly path_sysctl_mem="net.core.optmem_max" if [[ "$#" -eq "0" ]]; then $0 4 tcp -t 1 $0 6 tcp -t 1 + $0 4 udp -t 1 + $0 6 udp -t 1 echo "OK. All tests passed" exit 0 fi diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index a369d616b390..e2c94e47707c 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -26,6 +26,47 @@ # - pmtu_ipv6 # Same as pmtu_ipv4, except for locked PMTU tests, using IPv6 # +# - pmtu_ipv4_vxlan4_exception +# Set up the same network topology as pmtu_ipv4, create a VXLAN tunnel +# over IPv4 between A and B, routed via R1. On the link between R1 and B, +# set a MTU lower than the VXLAN MTU and the MTU on the link between A and +# R1. Send IPv4 packets, exceeding the MTU between R1 and B, over VXLAN +# from A to B and check that the PMTU exception is created with the right +# value on A +# +# - pmtu_ipv6_vxlan4_exception +# Same as pmtu_ipv4_vxlan4_exception, but send IPv6 packets from A to B +# +# - pmtu_ipv4_vxlan6_exception +# Same as pmtu_ipv4_vxlan4_exception, but use IPv6 transport from A to B +# +# - pmtu_ipv6_vxlan6_exception +# Same as pmtu_ipv4_vxlan6_exception, but send IPv6 packets from A to B +# +# - pmtu_ipv4_geneve4_exception +# Same as pmtu_ipv4_vxlan4_exception, but using a GENEVE tunnel instead of +# VXLAN +# +# - pmtu_ipv6_geneve4_exception +# Same as pmtu_ipv6_vxlan4_exception, but using a GENEVE tunnel instead of +# VXLAN +# +# - pmtu_ipv4_geneve6_exception +# Same as pmtu_ipv4_vxlan6_exception, but using a GENEVE tunnel instead of +# VXLAN +# +# - pmtu_ipv6_geneve6_exception +# Same as pmtu_ipv6_vxlan6_exception, but using a GENEVE tunnel instead of +# VXLAN +# +# - pmtu_ipv{4,6}_fou{4,6}_exception +# Same as pmtu_ipv4_vxlan4, but using a direct IPv4/IPv6 encapsulation +# (FoU) over IPv4/IPv6, instead of VXLAN +# +# - pmtu_ipv{4,6}_fou{4,6}_exception +# Same as pmtu_ipv4_vxlan4, but using a generic UDP IPv4/IPv6 +# encapsulation (GUE) over IPv4/IPv6, instead of VXLAN +# # - pmtu_vti4_exception # Set up vti tunnel on top of veth, with xfrm states and policies, in two # namespaces with matching endpoints. Check that route exception is not @@ -72,6 +113,22 @@ which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) tests=" pmtu_ipv4_exception ipv4: PMTU exceptions pmtu_ipv6_exception ipv6: PMTU exceptions + pmtu_ipv4_vxlan4_exception IPv4 over vxlan4: PMTU exceptions + pmtu_ipv6_vxlan4_exception IPv6 over vxlan4: PMTU exceptions + pmtu_ipv4_vxlan6_exception IPv4 over vxlan6: PMTU exceptions + pmtu_ipv6_vxlan6_exception IPv6 over vxlan6: PMTU exceptions + pmtu_ipv4_geneve4_exception IPv4 over geneve4: PMTU exceptions + pmtu_ipv6_geneve4_exception IPv6 over geneve4: PMTU exceptions + pmtu_ipv4_geneve6_exception IPv4 over geneve6: PMTU exceptions + pmtu_ipv6_geneve6_exception IPv6 over geneve6: PMTU exceptions + pmtu_ipv4_fou4_exception IPv4 over fou4: PMTU exceptions + pmtu_ipv6_fou4_exception IPv6 over fou4: PMTU exceptions + pmtu_ipv4_fou6_exception IPv4 over fou6: PMTU exceptions + pmtu_ipv6_fou6_exception IPv6 over fou6: PMTU exceptions + pmtu_ipv4_gue4_exception IPv4 over gue4: PMTU exceptions + pmtu_ipv6_gue4_exception IPv6 over gue4: PMTU exceptions + pmtu_ipv4_gue6_exception IPv4 over gue6: PMTU exceptions + pmtu_ipv6_gue6_exception IPv6 over gue6: PMTU exceptions pmtu_vti6_exception vti6: PMTU exceptions pmtu_vti4_exception vti4: PMTU exceptions pmtu_vti4_default_mtu vti4: default MTU assignment @@ -95,8 +152,8 @@ ns_r2="ip netns exec ${NS_R2}" # Addresses are: # - IPv4: PREFIX4.SEGMENT.ID (/24) # - IPv6: PREFIX6:SEGMENT::ID (/64) -prefix4="192.168" -prefix6="fd00" +prefix4="10.0" +prefix6="fc00" a_r1=1 a_r2=2 b_r1=3 @@ -129,12 +186,12 @@ veth6_a_addr="fd00:1::a" veth6_b_addr="fd00:1::b" veth6_mask="64" -vti4_a_addr="192.168.2.1" -vti4_b_addr="192.168.2.2" -vti4_mask="24" -vti6_a_addr="fd00:2::a" -vti6_b_addr="fd00:2::b" -vti6_mask="64" +tunnel4_a_addr="192.168.2.1" +tunnel4_b_addr="192.168.2.2" +tunnel4_mask="24" +tunnel6_a_addr="fd00:2::a" +tunnel6_b_addr="fd00:2::b" +tunnel6_mask="64" dummy6_0_addr="fc00:1000::0" dummy6_1_addr="fc00:1001::0" @@ -159,6 +216,89 @@ nsname() { eval echo \$NS_$1 } +setup_fou_or_gue() { + outer="${1}" + inner="${2}" + encap="${3}" + + if [ "${outer}" = "4" ]; then + modprobe fou || return 2 + a_addr="${prefix4}.${a_r1}.1" + b_addr="${prefix4}.${b_r1}.1" + if [ "${inner}" = "4" ]; then + type="ipip" + ipproto="4" + else + type="sit" + ipproto="41" + fi + else + modprobe fou6 || return 2 + a_addr="${prefix6}:${a_r1}::1" + b_addr="${prefix6}:${b_r1}::1" + if [ "${inner}" = "4" ]; then + type="ip6tnl" + mode="mode ipip6" + ipproto="4 -6" + else + type="ip6tnl" + mode="mode ip6ip6" + ipproto="41 -6" + fi + fi + + ${ns_a} ip fou add port 5555 ipproto ${ipproto} || return 2 + ${ns_a} ip link add ${encap}_a type ${type} ${mode} local ${a_addr} remote ${b_addr} encap ${encap} encap-sport auto encap-dport 5556 || return 2 + + ${ns_b} ip fou add port 5556 ipproto ${ipproto} + ${ns_b} ip link add ${encap}_b type ${type} ${mode} local ${b_addr} remote ${a_addr} encap ${encap} encap-sport auto encap-dport 5555 + + if [ "${inner}" = "4" ]; then + ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${encap}_a + ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${encap}_b + else + ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${encap}_a + ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${encap}_b + fi + + ${ns_a} ip link set ${encap}_a up + ${ns_b} ip link set ${encap}_b up + + sleep 1 +} + +setup_fou44() { + setup_fou_or_gue 4 4 fou +} + +setup_fou46() { + setup_fou_or_gue 4 6 fou +} + +setup_fou64() { + setup_fou_or_gue 6 4 fou +} + +setup_fou66() { + setup_fou_or_gue 6 6 fou +} + +setup_gue44() { + setup_fou_or_gue 4 4 gue +} + +setup_gue46() { + setup_fou_or_gue 4 6 gue +} + +setup_gue64() { + setup_fou_or_gue 6 4 gue +} + +setup_gue66() { + setup_fou_or_gue 6 6 gue +} + setup_namespaces() { for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do ip netns add ${n} || return 1 @@ -202,11 +342,57 @@ setup_vti() { } setup_vti4() { - setup_vti 4 ${veth4_a_addr} ${veth4_b_addr} ${vti4_a_addr} ${vti4_b_addr} ${vti4_mask} + setup_vti 4 ${veth4_a_addr} ${veth4_b_addr} ${tunnel4_a_addr} ${tunnel4_b_addr} ${tunnel4_mask} } setup_vti6() { - setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${vti6_a_addr} ${vti6_b_addr} ${vti6_mask} + setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask} +} + +setup_vxlan_or_geneve() { + type="${1}" + a_addr="${2}" + b_addr="${3}" + opts="${4}" + + if [ "${type}" = "vxlan" ]; then + opts="${opts} ttl 64 dstport 4789" + opts_a="local ${a_addr}" + opts_b="local ${b_addr}" + else + opts_a="" + opts_b="" + fi + + ${ns_a} ip link add ${type}_a type ${type} id 1 ${opts_a} remote ${b_addr} ${opts} || return 1 + ${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts} + + ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a + ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b + + ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a + ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b + + ${ns_a} ip link set ${type}_a up + ${ns_b} ip link set ${type}_b up + + sleep 1 +} + +setup_geneve4() { + setup_vxlan_or_geneve geneve ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "df set" +} + +setup_vxlan4() { + setup_vxlan_or_geneve vxlan ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "df set" +} + +setup_geneve6() { + setup_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 +} + +setup_vxlan6() { + setup_vxlan_or_geneve vxlan ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 } setup_xfrm() { @@ -465,6 +651,161 @@ test_pmtu_ipv6_exception() { test_pmtu_ipvX 6 } +test_pmtu_ipvX_over_vxlanY_or_geneveY_exception() { + type=${1} + family=${2} + outer_family=${3} + ll_mtu=4000 + + if [ ${outer_family} -eq 4 ]; then + setup namespaces routing ${type}4 || return 2 + # IPv4 header UDP header VXLAN/GENEVE header Ethernet header + exp_mtu=$((${ll_mtu} - 20 - 8 - 8 - 14)) + else + setup namespaces routing ${type}6 || return 2 + # IPv6 header UDP header VXLAN/GENEVE header Ethernet header + exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - 14)) + fi + + trace "${ns_a}" ${type}_a "${ns_b}" ${type}_b \ + "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B + + if [ ${family} -eq 4 ]; then + ping=ping + dst=${tunnel4_b_addr} + else + ping=${ping6} + dst=${tunnel6_b_addr} + fi + + # Create route exception by exceeding link layer MTU + mtu "${ns_a}" veth_A-R1 $((${ll_mtu} + 1000)) + mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000)) + mtu "${ns_b}" veth_B-R1 ${ll_mtu} + mtu "${ns_r1}" veth_R1-B ${ll_mtu} + + mtu "${ns_a}" ${type}_a $((${ll_mtu} + 1000)) + mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000)) + ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null + + # Check that exception was created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on ${type} interface" +} + +test_pmtu_ipv4_vxlan4_exception() { + test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan 4 4 +} + +test_pmtu_ipv6_vxlan4_exception() { + test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan 6 4 +} + +test_pmtu_ipv4_geneve4_exception() { + test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 4 4 +} + +test_pmtu_ipv6_geneve4_exception() { + test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 6 4 +} + +test_pmtu_ipv4_vxlan6_exception() { + test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan 4 6 +} + +test_pmtu_ipv6_vxlan6_exception() { + test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan 6 6 +} + +test_pmtu_ipv4_geneve6_exception() { + test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 4 6 +} + +test_pmtu_ipv6_geneve6_exception() { + test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 6 6 +} + +test_pmtu_ipvX_over_fouY_or_gueY() { + inner_family=${1} + outer_family=${2} + encap=${3} + ll_mtu=4000 + + setup namespaces routing ${encap}${outer_family}${inner_family} || return 2 + trace "${ns_a}" ${encap}_a "${ns_b}" ${encap}_b \ + "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B + + if [ ${inner_family} -eq 4 ]; then + ping=ping + dst=${tunnel4_b_addr} + else + ping=${ping6} + dst=${tunnel6_b_addr} + fi + + if [ "${encap}" = "gue" ]; then + encap_overhead=4 + else + encap_overhead=0 + fi + + if [ ${outer_family} -eq 4 ]; then + # IPv4 header UDP header + exp_mtu=$((${ll_mtu} - 20 - 8 - ${encap_overhead})) + else + # IPv6 header Option 4 UDP header + exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - ${encap_overhead})) + fi + + # Create route exception by exceeding link layer MTU + mtu "${ns_a}" veth_A-R1 $((${ll_mtu} + 1000)) + mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000)) + mtu "${ns_b}" veth_B-R1 ${ll_mtu} + mtu "${ns_r1}" veth_R1-B ${ll_mtu} + + mtu "${ns_a}" ${encap}_a $((${ll_mtu} + 1000)) + mtu "${ns_b}" ${encap}_b $((${ll_mtu} + 1000)) + ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null + + # Check that exception was created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on ${encap} interface" +} + +test_pmtu_ipv4_fou4_exception() { + test_pmtu_ipvX_over_fouY_or_gueY 4 4 fou +} + +test_pmtu_ipv6_fou4_exception() { + test_pmtu_ipvX_over_fouY_or_gueY 6 4 fou +} + +test_pmtu_ipv4_fou6_exception() { + test_pmtu_ipvX_over_fouY_or_gueY 4 6 fou +} + +test_pmtu_ipv6_fou6_exception() { + test_pmtu_ipvX_over_fouY_or_gueY 6 6 fou +} + +test_pmtu_ipv4_gue4_exception() { + test_pmtu_ipvX_over_fouY_or_gueY 4 4 gue +} + +test_pmtu_ipv6_gue4_exception() { + test_pmtu_ipvX_over_fouY_or_gueY 6 4 gue +} + +test_pmtu_ipv4_gue6_exception() { + test_pmtu_ipvX_over_fouY_or_gueY 4 6 gue +} + +test_pmtu_ipv6_gue6_exception() { + test_pmtu_ipvX_over_fouY_or_gueY 6 6 gue +} + test_pmtu_vti4_exception() { setup namespaces veth vti4 xfrm4 || return 2 trace "${ns_a}" veth_a "${ns_b}" veth_b \ @@ -484,14 +825,14 @@ test_pmtu_vti4_exception() { # Send DF packet without exceeding link layer MTU, check that no # exception is created - ${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${vti4_b_addr} > /dev/null - pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})" + ${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${tunnel4_b_addr} > /dev/null + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})" check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1 # Now exceed link layer MTU by one byte, check that exception is created # with the right PMTU value - ${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${vti4_b_addr} > /dev/null - pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})" + ${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${tunnel4_b_addr} > /dev/null + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})" check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))" } @@ -506,20 +847,20 @@ test_pmtu_vti6_exception() { mtu "${ns_b}" veth_b 4000 mtu "${ns_a}" vti6_a 5000 mtu "${ns_b}" vti6_b 5000 - ${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null + ${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${tunnel6_b_addr} > /dev/null # Check that exception was created - pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1 # Decrease tunnel MTU, check for PMTU decrease in route exception mtu "${ns_a}" vti6_a 3000 - pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1 # Increase tunnel MTU, check for PMTU increase in route exception mtu "${ns_a}" vti6_a 9000 - pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1 return ${fail} diff --git a/tools/testing/selftests/net/reuseport_addr_any.c b/tools/testing/selftests/net/reuseport_addr_any.c new file mode 100644 index 000000000000..6f54d425dba9 --- /dev/null +++ b/tools/testing/selftests/net/reuseport_addr_any.c @@ -0,0 +1,264 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Test that sockets listening on a specific address are preferred + * over sockets listening on addr_any. + */ + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <errno.h> +#include <error.h> +#include <linux/dccp.h> +#include <linux/in.h> +#include <linux/unistd.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/epoll.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <unistd.h> + +static const char *IP4_ADDR = "127.0.0.1"; +static const char *IP6_ADDR = "::1"; +static const char *IP4_MAPPED6 = "::ffff:127.0.0.1"; + +static const int PORT = 8888; + +static void build_rcv_fd(int family, int proto, int *rcv_fds, int count, + const char *addr_str) +{ + struct sockaddr_in addr4 = {0}; + struct sockaddr_in6 addr6 = {0}; + struct sockaddr *addr; + int opt, i, sz; + + memset(&addr, 0, sizeof(addr)); + + switch (family) { + case AF_INET: + addr4.sin_family = family; + if (!addr_str) + addr4.sin_addr.s_addr = htonl(INADDR_ANY); + else if (!inet_pton(family, addr_str, &addr4.sin_addr.s_addr)) + error(1, errno, "inet_pton failed: %s", addr_str); + addr4.sin_port = htons(PORT); + sz = sizeof(addr4); + addr = (struct sockaddr *)&addr4; + break; + case AF_INET6: + addr6.sin6_family = AF_INET6; + if (!addr_str) + addr6.sin6_addr = in6addr_any; + else if (!inet_pton(family, addr_str, &addr6.sin6_addr)) + error(1, errno, "inet_pton failed: %s", addr_str); + addr6.sin6_port = htons(PORT); + sz = sizeof(addr6); + addr = (struct sockaddr *)&addr6; + break; + default: + error(1, 0, "Unsupported family %d", family); + } + + for (i = 0; i < count; ++i) { + rcv_fds[i] = socket(family, proto, 0); + if (rcv_fds[i] < 0) + error(1, errno, "failed to create receive socket"); + + opt = 1; + if (setsockopt(rcv_fds[i], SOL_SOCKET, SO_REUSEPORT, &opt, + sizeof(opt))) + error(1, errno, "failed to set SO_REUSEPORT"); + + if (bind(rcv_fds[i], addr, sz)) + error(1, errno, "failed to bind receive socket"); + + if (proto == SOCK_STREAM && listen(rcv_fds[i], 10)) + error(1, errno, "tcp: failed to listen on receive port"); + else if (proto == SOCK_DCCP) { + if (setsockopt(rcv_fds[i], SOL_DCCP, + DCCP_SOCKOPT_SERVICE, + &(int) {htonl(42)}, sizeof(int))) + error(1, errno, "failed to setsockopt"); + + if (listen(rcv_fds[i], 10)) + error(1, errno, "dccp: failed to listen on receive port"); + } + } +} + +static int connect_and_send(int family, int proto) +{ + struct sockaddr_in saddr4 = {0}; + struct sockaddr_in daddr4 = {0}; + struct sockaddr_in6 saddr6 = {0}; + struct sockaddr_in6 daddr6 = {0}; + struct sockaddr *saddr, *daddr; + int fd, sz; + + switch (family) { + case AF_INET: + saddr4.sin_family = AF_INET; + saddr4.sin_addr.s_addr = htonl(INADDR_ANY); + saddr4.sin_port = 0; + + daddr4.sin_family = AF_INET; + if (!inet_pton(family, IP4_ADDR, &daddr4.sin_addr.s_addr)) + error(1, errno, "inet_pton failed: %s", IP4_ADDR); + daddr4.sin_port = htons(PORT); + + sz = sizeof(saddr4); + saddr = (struct sockaddr *)&saddr4; + daddr = (struct sockaddr *)&daddr4; + break; + case AF_INET6: + saddr6.sin6_family = AF_INET6; + saddr6.sin6_addr = in6addr_any; + + daddr6.sin6_family = AF_INET6; + if (!inet_pton(family, IP6_ADDR, &daddr6.sin6_addr)) + error(1, errno, "inet_pton failed: %s", IP6_ADDR); + daddr6.sin6_port = htons(PORT); + + sz = sizeof(saddr6); + saddr = (struct sockaddr *)&saddr6; + daddr = (struct sockaddr *)&daddr6; + break; + default: + error(1, 0, "Unsupported family %d", family); + } + + fd = socket(family, proto, 0); + if (fd < 0) + error(1, errno, "failed to create send socket"); + + if (proto == SOCK_DCCP && + setsockopt(fd, SOL_DCCP, DCCP_SOCKOPT_SERVICE, + &(int){htonl(42)}, sizeof(int))) + error(1, errno, "failed to setsockopt"); + + if (bind(fd, saddr, sz)) + error(1, errno, "failed to bind send socket"); + + if (connect(fd, daddr, sz)) + error(1, errno, "failed to connect send socket"); + + if (send(fd, "a", 1, 0) < 0) + error(1, errno, "failed to send message"); + + return fd; +} + +static int receive_once(int epfd, int proto) +{ + struct epoll_event ev; + int i, fd; + char buf[8]; + + i = epoll_wait(epfd, &ev, 1, 3); + if (i < 0) + error(1, errno, "epoll_wait failed"); + + if (proto == SOCK_STREAM || proto == SOCK_DCCP) { + fd = accept(ev.data.fd, NULL, NULL); + if (fd < 0) + error(1, errno, "failed to accept"); + i = recv(fd, buf, sizeof(buf), 0); + close(fd); + } else { + i = recv(ev.data.fd, buf, sizeof(buf), 0); + } + + if (i < 0) + error(1, errno, "failed to recv"); + + return ev.data.fd; +} + +static void test(int *rcv_fds, int count, int family, int proto, int fd) +{ + struct epoll_event ev; + int epfd, i, send_fd, recv_fd; + + epfd = epoll_create(1); + if (epfd < 0) + error(1, errno, "failed to create epoll"); + + ev.events = EPOLLIN; + for (i = 0; i < count; ++i) { + ev.data.fd = rcv_fds[i]; + if (epoll_ctl(epfd, EPOLL_CTL_ADD, rcv_fds[i], &ev)) + error(1, errno, "failed to register sock epoll"); + } + + send_fd = connect_and_send(family, proto); + + recv_fd = receive_once(epfd, proto); + if (recv_fd != fd) + error(1, 0, "received on an unexpected socket"); + + close(send_fd); + close(epfd); +} + + +static void run_one_test(int fam_send, int fam_rcv, int proto, + const char *addr_str) +{ + /* Below we test that a socket listening on a specific address + * is always selected in preference over a socket listening + * on addr_any. Bugs where this is not the case often result + * in sockets created first or last to get picked. So below + * we make sure that there are always addr_any sockets created + * before and after a specific socket is created. + */ + int rcv_fds[10], i; + + build_rcv_fd(AF_INET, proto, rcv_fds, 2, NULL); + build_rcv_fd(AF_INET6, proto, rcv_fds + 2, 2, NULL); + build_rcv_fd(fam_rcv, proto, rcv_fds + 4, 1, addr_str); + build_rcv_fd(AF_INET, proto, rcv_fds + 5, 2, NULL); + build_rcv_fd(AF_INET6, proto, rcv_fds + 7, 2, NULL); + test(rcv_fds, 9, fam_send, proto, rcv_fds[4]); + for (i = 0; i < 9; ++i) + close(rcv_fds[i]); + fprintf(stderr, "pass\n"); +} + +static void test_proto(int proto, const char *proto_str) +{ + if (proto == SOCK_DCCP) { + int test_fd; + + test_fd = socket(AF_INET, proto, 0); + if (test_fd < 0) { + if (errno == ESOCKTNOSUPPORT) { + fprintf(stderr, "DCCP not supported: skipping DCCP tests\n"); + return; + } else + error(1, errno, "failed to create a DCCP socket"); + } + close(test_fd); + } + + fprintf(stderr, "%s IPv4 ... ", proto_str); + run_one_test(AF_INET, AF_INET, proto, IP4_ADDR); + + fprintf(stderr, "%s IPv6 ... ", proto_str); + run_one_test(AF_INET6, AF_INET6, proto, IP6_ADDR); + + fprintf(stderr, "%s IPv4 mapped to IPv6 ... ", proto_str); + run_one_test(AF_INET, AF_INET6, proto, IP4_MAPPED6); +} + +int main(void) +{ + test_proto(SOCK_DGRAM, "UDP"); + test_proto(SOCK_STREAM, "TCP"); + test_proto(SOCK_DCCP, "DCCP"); + + fprintf(stderr, "SUCCESS\n"); + return 0; +} diff --git a/tools/testing/selftests/net/reuseport_addr_any.sh b/tools/testing/selftests/net/reuseport_addr_any.sh new file mode 100755 index 000000000000..104592f62ad4 --- /dev/null +++ b/tools/testing/selftests/net/reuseport_addr_any.sh @@ -0,0 +1,4 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +./in_netns.sh ./reuseport_addr_any diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index e101af52d1d6..c5cbea9b317d 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -955,6 +955,111 @@ kci_test_ip6erspan() ip netns del "$testns" } +kci_test_fdb_get() +{ + IP="ip -netns testns" + BRIDGE="bridge -netns testns" + brdev="test-br0" + vxlandev="vxlan10" + test_mac=de:ad:be:ef:13:37 + localip="10.0.2.2" + dstip="10.0.2.3" + ret=0 + + bridge fdb help 2>&1 |grep -q 'bridge fdb get' + if [ $? -ne 0 ];then + echo "SKIP: fdb get tests: iproute2 too old" + return $ksft_skip + fi + + ip netns add testns + if [ $? -ne 0 ]; then + echo "SKIP fdb get tests: cannot add net namespace $testns" + return $ksft_skip + fi + + $IP link add "$vxlandev" type vxlan id 10 local $localip \ + dstport 4789 2>/dev/null + check_err $? + $IP link add name "$brdev" type bridge &>/dev/null + check_err $? + $IP link set dev "$vxlandev" master "$brdev" &>/dev/null + check_err $? + $BRIDGE fdb add $test_mac dev "$vxlandev" master &>/dev/null + check_err $? + $BRIDGE fdb add $test_mac dev "$vxlandev" dst $dstip self &>/dev/null + check_err $? + + $BRIDGE fdb get $test_mac brport "$vxlandev" 2>/dev/null | grep -q "dev $vxlandev master $brdev" + check_err $? + $BRIDGE fdb get $test_mac br "$brdev" 2>/dev/null | grep -q "dev $vxlandev master $brdev" + check_err $? + $BRIDGE fdb get $test_mac dev "$vxlandev" self 2>/dev/null | grep -q "dev $vxlandev dst $dstip" + check_err $? + + ip netns del testns &>/dev/null + + if [ $ret -ne 0 ]; then + echo "FAIL: bridge fdb get" + return 1 + fi + + echo "PASS: bridge fdb get" +} + +kci_test_neigh_get() +{ + dstmac=de:ad:be:ef:13:37 + dstip=10.0.2.4 + dstip6=dead::2 + ret=0 + + ip neigh help 2>&1 |grep -q 'ip neigh get' + if [ $? -ne 0 ];then + echo "SKIP: fdb get tests: iproute2 too old" + return $ksft_skip + fi + + # ipv4 + ip neigh add $dstip lladdr $dstmac dev "$devdummy" > /dev/null + check_err $? + ip neigh get $dstip dev "$devdummy" 2> /dev/null | grep -q "$dstmac" + check_err $? + ip neigh del $dstip lladdr $dstmac dev "$devdummy" > /dev/null + check_err $? + + # ipv4 proxy + ip neigh add proxy $dstip dev "$devdummy" > /dev/null + check_err $? + ip neigh get proxy $dstip dev "$devdummy" 2>/dev/null | grep -q "$dstip" + check_err $? + ip neigh del proxy $dstip dev "$devdummy" > /dev/null + check_err $? + + # ipv6 + ip neigh add $dstip6 lladdr $dstmac dev "$devdummy" > /dev/null + check_err $? + ip neigh get $dstip6 dev "$devdummy" 2> /dev/null | grep -q "$dstmac" + check_err $? + ip neigh del $dstip6 lladdr $dstmac dev "$devdummy" > /dev/null + check_err $? + + # ipv6 proxy + ip neigh add proxy $dstip6 dev "$devdummy" > /dev/null + check_err $? + ip neigh get proxy $dstip6 dev "$devdummy" 2>/dev/null | grep -q "$dstip6" + check_err $? + ip neigh del proxy $dstip6 dev "$devdummy" > /dev/null + check_err $? + + if [ $ret -ne 0 ];then + echo "FAIL: neigh get" + return 1 + fi + + echo "PASS: neigh get" +} + kci_test_rtnl() { kci_add_dummy @@ -979,6 +1084,8 @@ kci_test_rtnl() kci_test_macsec kci_test_ipsec kci_test_ipsec_offload + kci_test_fdb_get + kci_test_neigh_get kci_del_dummy } diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests index bea079edc278..2dc95fda7ef7 100755 --- a/tools/testing/selftests/net/run_afpackettests +++ b/tools/testing/selftests/net/run_afpackettests @@ -25,3 +25,13 @@ if [ $? -ne 0 ]; then else echo "[PASS]" fi + +echo "--------------------" +echo "running txring_overwrite test" +echo "--------------------" +./in_netns.sh ./txring_overwrite +if [ $? -ne 0 ]; then + echo "[FAIL]" +else + echo "[PASS]" +fi diff --git a/tools/testing/selftests/net/test_vxlan_under_vrf.sh b/tools/testing/selftests/net/test_vxlan_under_vrf.sh new file mode 100755 index 000000000000..09f9ed92cbe4 --- /dev/null +++ b/tools/testing/selftests/net/test_vxlan_under_vrf.sh @@ -0,0 +1,129 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test is for checking VXLAN underlay in a non-default VRF. +# +# It simulates two hypervisors running a VM each using four network namespaces: +# two for the HVs, two for the VMs. +# A small VXLAN tunnel is made between the two hypervisors to have the two vms +# in the same virtual L2: +# +# +-------------------+ +-------------------+ +# | | | | +# | vm-1 netns | | vm-2 netns | +# | | | | +# | +-------------+ | | +-------------+ | +# | | veth-hv | | | | veth-hv | | +# | | 10.0.0.1/24 | | | | 10.0.0.2/24 | | +# | +-------------+ | | +-------------+ | +# | . | | . | +# +-------------------+ +-------------------+ +# . . +# . . +# . . +# +-----------------------------------+ +------------------------------------+ +# | . | | . | +# | +----------+ | | +----------+ | +# | | veth-tap | | | | veth-tap | | +# | +----+-----+ | | +----+-----+ | +# | | | | | | +# | +--+--+ +--------------+ | | +--------------+ +--+--+ | +# | | br0 | | vrf-underlay | | | | vrf-underlay | | br0 | | +# | +--+--+ +-------+------+ | | +------+-------+ +--+--+ | +# | | | | | | | | +# | +---+----+ +-------+-------+ | | +-------+-------+ +---+----+ | +# | | vxlan0 |....| veth0 |.|...|.| veth0 |....| vxlan0 | | +# | +--------+ | 172.16.0.1/24 | | | | 172.16.0.2/24 | +--------+ | +# | +---------------+ | | +---------------+ | +# | | | | +# | hv-1 netns | | hv-2 netns | +# | | | | +# +-----------------------------------+ +------------------------------------+ +# +# This tests both the connectivity between vm-1 and vm-2, and that the underlay +# can be moved in and out of the vrf by unsetting and setting veth0's master. + +set -e + +cleanup() { + ip link del veth-hv-1 2>/dev/null || true + ip link del veth-tap 2>/dev/null || true + + for ns in hv-1 hv-2 vm-1 vm-2; do + ip netns del $ns || true + done +} + +# Clean start +cleanup &> /dev/null + +[[ $1 == "clean" ]] && exit 0 + +trap cleanup EXIT + +# Setup "Hypervisors" simulated with netns +ip link add veth-hv-1 type veth peer name veth-hv-2 +setup-hv-networking() { + hv=$1 + + ip netns add hv-$hv + ip link set veth-hv-$hv netns hv-$hv + ip -netns hv-$hv link set veth-hv-$hv name veth0 + + ip -netns hv-$hv link add vrf-underlay type vrf table 1 + ip -netns hv-$hv link set vrf-underlay up + ip -netns hv-$hv addr add 172.16.0.$hv/24 dev veth0 + ip -netns hv-$hv link set veth0 up + + ip -netns hv-$hv link add br0 type bridge + ip -netns hv-$hv link set br0 up + + ip -netns hv-$hv link add vxlan0 type vxlan id 10 local 172.16.0.$hv dev veth0 dstport 4789 + ip -netns hv-$hv link set vxlan0 master br0 + ip -netns hv-$hv link set vxlan0 up +} +setup-hv-networking 1 +setup-hv-networking 2 + +# Check connectivity between HVs by pinging hv-2 from hv-1 +echo -n "Checking HV connectivity " +ip netns exec hv-1 ping -c 1 -W 1 172.16.0.2 &> /dev/null || (echo "[FAIL]"; false) +echo "[ OK ]" + +# Setups a "VM" simulated by a netns an a veth pair +setup-vm() { + id=$1 + + ip netns add vm-$id + ip link add veth-tap type veth peer name veth-hv + + ip link set veth-tap netns hv-$id + ip -netns hv-$id link set veth-tap master br0 + ip -netns hv-$id link set veth-tap up + + ip link set veth-hv netns vm-$id + ip -netns vm-$id addr add 10.0.0.$id/24 dev veth-hv + ip -netns vm-$id link set veth-hv up +} +setup-vm 1 +setup-vm 2 + +# Setup VTEP routes to make ARP work +bridge -netns hv-1 fdb add 00:00:00:00:00:00 dev vxlan0 dst 172.16.0.2 self permanent +bridge -netns hv-2 fdb add 00:00:00:00:00:00 dev vxlan0 dst 172.16.0.1 self permanent + +echo -n "Check VM connectivity through VXLAN (underlay in the default VRF) " +ip netns exec vm-1 ping -c 1 -W 1 10.0.0.2 &> /dev/null || (echo "[FAIL]"; false) +echo "[ OK ]" + +# Move the underlay to a non-default VRF +ip -netns hv-1 link set veth0 vrf vrf-underlay +ip -netns hv-1 link set veth0 down +ip -netns hv-1 link set veth0 up +ip -netns hv-2 link set veth0 vrf vrf-underlay +ip -netns hv-2 link set veth0 down +ip -netns hv-2 link set veth0 up + +echo -n "Check VM connectivity through VXLAN (underlay in a VRF) " +ip netns exec vm-1 ping -c 1 -W 1 10.0.0.2 &> /dev/null || (echo "[FAIL]"; false) +echo "[ OK ]" diff --git a/tools/testing/selftests/net/txring_overwrite.c b/tools/testing/selftests/net/txring_overwrite.c new file mode 100644 index 000000000000..fd8b1c663c39 --- /dev/null +++ b/tools/testing/selftests/net/txring_overwrite.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Verify that consecutive sends over packet tx_ring are mirrored + * with their original content intact. + */ + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <assert.h> +#include <error.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/filter.h> +#include <linux/if_packet.h> +#include <net/ethernet.h> +#include <net/if.h> +#include <netinet/in.h> +#include <netinet/ip.h> +#include <netinet/udp.h> +#include <poll.h> +#include <pthread.h> +#include <sched.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/socket.h> +#include <sys/time.h> +#include <sys/types.h> +#include <sys/utsname.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +const int eth_off = TPACKET_HDRLEN - sizeof(struct sockaddr_ll); +const int cfg_frame_size = 1000; + +static void build_packet(void *buffer, size_t blen, char payload_char) +{ + struct udphdr *udph; + struct ethhdr *eth; + struct iphdr *iph; + size_t off = 0; + + memset(buffer, 0, blen); + + eth = buffer; + eth->h_proto = htons(ETH_P_IP); + + off += sizeof(*eth); + iph = buffer + off; + iph->ttl = 8; + iph->ihl = 5; + iph->version = 4; + iph->saddr = htonl(INADDR_LOOPBACK); + iph->daddr = htonl(INADDR_LOOPBACK + 1); + iph->protocol = IPPROTO_UDP; + iph->tot_len = htons(blen - off); + iph->check = 0; + + off += sizeof(*iph); + udph = buffer + off; + udph->dest = htons(8000); + udph->source = htons(8001); + udph->len = htons(blen - off); + udph->check = 0; + + off += sizeof(*udph); + memset(buffer + off, payload_char, blen - off); +} + +static int setup_rx(void) +{ + int fdr; + + fdr = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_IP)); + if (fdr == -1) + error(1, errno, "socket r"); + + return fdr; +} + +static int setup_tx(char **ring) +{ + struct sockaddr_ll laddr = {}; + struct tpacket_req req = {}; + int fdt; + + fdt = socket(PF_PACKET, SOCK_RAW, 0); + if (fdt == -1) + error(1, errno, "socket t"); + + laddr.sll_family = AF_PACKET; + laddr.sll_protocol = htons(0); + laddr.sll_ifindex = if_nametoindex("lo"); + if (!laddr.sll_ifindex) + error(1, errno, "if_nametoindex"); + + if (bind(fdt, (void *)&laddr, sizeof(laddr))) + error(1, errno, "bind fdt"); + + req.tp_block_size = getpagesize(); + req.tp_block_nr = 1; + req.tp_frame_size = getpagesize(); + req.tp_frame_nr = 1; + + if (setsockopt(fdt, SOL_PACKET, PACKET_TX_RING, + (void *)&req, sizeof(req))) + error(1, errno, "setsockopt ring"); + + *ring = mmap(0, req.tp_block_size * req.tp_block_nr, + PROT_READ | PROT_WRITE, MAP_SHARED, fdt, 0); + if (!*ring) + error(1, errno, "mmap"); + + return fdt; +} + +static void send_pkt(int fdt, void *slot, char payload_char) +{ + struct tpacket_hdr *header = slot; + int ret; + + while (header->tp_status != TP_STATUS_AVAILABLE) + usleep(1000); + + build_packet(slot + eth_off, cfg_frame_size, payload_char); + + header->tp_len = cfg_frame_size; + header->tp_status = TP_STATUS_SEND_REQUEST; + + ret = sendto(fdt, NULL, 0, 0, NULL, 0); + if (ret == -1) + error(1, errno, "kick tx"); +} + +static int read_verify_pkt(int fdr, char payload_char) +{ + char buf[100]; + int ret; + + ret = read(fdr, buf, sizeof(buf)); + if (ret != sizeof(buf)) + error(1, errno, "read"); + + if (buf[60] != payload_char) { + printf("wrong pattern: 0x%x != 0x%x\n", buf[60], payload_char); + return 1; + } + + printf("read: %c (0x%x)\n", buf[60], buf[60]); + return 0; +} + +int main(int argc, char **argv) +{ + const char payload_patterns[] = "ab"; + char *ring; + int fdr, fdt, ret = 0; + + fdr = setup_rx(); + fdt = setup_tx(&ring); + + send_pkt(fdt, ring, payload_patterns[0]); + send_pkt(fdt, ring, payload_patterns[1]); + + ret |= read_verify_pkt(fdr, payload_patterns[0]); + ret |= read_verify_pkt(fdr, payload_patterns[1]); + + if (close(fdt)) + error(1, errno, "close t"); + if (close(fdr)) + error(1, errno, "close r"); + + return ret; +} diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh new file mode 100755 index 000000000000..aeac53a99aeb --- /dev/null +++ b/tools/testing/selftests/net/udpgro.sh @@ -0,0 +1,182 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Run a series of udpgro functional tests. + +readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" + +cleanup() { + local -r jobs="$(jobs -p)" + local -r ns="$(ip netns list|grep $PEER_NS)" + + [ -n "${jobs}" ] && kill -1 ${jobs} 2>/dev/null + [ -n "$ns" ] && ip netns del $ns 2>/dev/null +} +trap cleanup EXIT + +cfg_veth() { + ip netns add "${PEER_NS}" + ip -netns "${PEER_NS}" link set lo up + ip link add type veth + ip link set dev veth0 up + ip addr add dev veth0 192.168.1.2/24 + ip addr add dev veth0 2001:db8::2/64 nodad + + ip link set dev veth1 netns "${PEER_NS}" + ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24 + ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad + ip -netns "${PEER_NS}" link set dev veth1 up + ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy +} + +run_one() { + # use 'rx' as separator between sender args and receiver args + local -r all="$@" + local -r tx_args=${all%rx*} + local -r rx_args=${all#*rx} + + cfg_veth + + ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} && \ + echo "ok" || \ + echo "failed" & + + # Hack: let bg programs complete the startup + sleep 0.1 + ./udpgso_bench_tx ${tx_args} + wait $(jobs -p) +} + +run_test() { + local -r args=$@ + + printf " %-40s" "$1" + ./in_netns.sh $0 __subprocess $2 rx -G -r $3 +} + +run_one_nat() { + # use 'rx' as separator between sender args and receiver args + local addr1 addr2 pid family="" ipt_cmd=ip6tables + local -r all="$@" + local -r tx_args=${all%rx*} + local -r rx_args=${all#*rx} + + if [[ ${tx_args} = *-4* ]]; then + ipt_cmd=iptables + family=-4 + addr1=192.168.1.1 + addr2=192.168.1.3/24 + else + addr1=2001:db8::1 + addr2="2001:db8::3/64 nodad" + fi + + cfg_veth + ip -netns "${PEER_NS}" addr add dev veth1 ${addr2} + + # fool the GRO engine changing the destination address ... + ip netns exec "${PEER_NS}" $ipt_cmd -t nat -I PREROUTING -d ${addr1} -j DNAT --to-destination ${addr2%/*} + + # ... so that GRO will match the UDP_GRO enabled socket, but packets + # will land on the 'plain' one + ip netns exec "${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} && \ + echo "ok" || \ + echo "failed"& + + sleep 0.1 + ./udpgso_bench_tx ${tx_args} + kill -INT $pid + wait $(jobs -p) +} + +run_one_2sock() { + # use 'rx' as separator between sender args and receiver args + local -r all="$@" + local -r tx_args=${all%rx*} + local -r rx_args=${all#*rx} + + cfg_veth + + ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -p 12345 & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} && \ + echo "ok" || \ + echo "failed" & + + # Hack: let bg programs complete the startup + sleep 0.1 + ./udpgso_bench_tx ${tx_args} -p 12345 + sleep 0.1 + # first UDP GSO socket should be closed at this point + ./udpgso_bench_tx ${tx_args} + wait $(jobs -p) +} + +run_nat_test() { + local -r args=$@ + + printf " %-40s" "$1" + ./in_netns.sh $0 __subprocess_nat $2 rx -r $3 +} + +run_2sock_test() { + local -r args=$@ + + printf " %-40s" "$1" + ./in_netns.sh $0 __subprocess_2sock $2 rx -G -r $3 +} + +run_all() { + local -r core_args="-l 4" + local -r ipv4_args="${core_args} -4 -D 192.168.1.1" + local -r ipv6_args="${core_args} -6 -D 2001:db8::1" + + echo "ipv4" + run_test "no GRO" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400" + + # explicitly check we are not receiving UDP_SEGMENT cmsg (-S -1) + # when GRO does not take place + run_test "no GRO chk cmsg" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400 -S -1" + + # the GSO packets are aggregated because: + # * veth schedule napi after each xmit + # * segmentation happens in BH context, veth napi poll is delayed after + # the transmission of the last segment + run_test "GRO" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720" + run_test "GRO chk cmsg" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472" + run_test "GRO with custom segment size" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720" + run_test "GRO with custom segment size cmsg" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720 -S 500" + + run_nat_test "bad GRO lookup" "${ipv4_args} -M 1 -s 14720 -S 0" "-n 10 -l 1472" + run_2sock_test "multiple GRO socks" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472" + + echo "ipv6" + run_test "no GRO" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400" + run_test "no GRO chk cmsg" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400 -S -1" + run_test "GRO" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520" + run_test "GRO chk cmsg" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520 -S 1452" + run_test "GRO with custom segment size" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520" + run_test "GRO with custom segment size cmsg" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520 -S 500" + + run_nat_test "bad GRO lookup" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 10 -l 1452" + run_2sock_test "multiple GRO socks" "${ipv6_args} -M 1 -s 14520 -S 0 " "-n 1 -l 14520 -S 1452" +} + +if [ ! -f ../bpf/xdp_dummy.o ]; then + echo "Missing xdp_dummy helper. Build bpf selftest first" + exit -1 +fi + +if [[ $# -eq 0 ]]; then + run_all +elif [[ $1 == "__subprocess" ]]; then + shift + run_one $@ +elif [[ $1 == "__subprocess_nat" ]]; then + shift + run_one_nat $@ +elif [[ $1 == "__subprocess_2sock" ]]; then + shift + run_one_2sock $@ +fi diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh new file mode 100755 index 000000000000..820bc50f6b68 --- /dev/null +++ b/tools/testing/selftests/net/udpgro_bench.sh @@ -0,0 +1,95 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Run a series of udpgro benchmarks + +readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" + +cleanup() { + local -r jobs="$(jobs -p)" + local -r ns="$(ip netns list|grep $PEER_NS)" + + [ -n "${jobs}" ] && kill -INT ${jobs} 2>/dev/null + [ -n "$ns" ] && ip netns del $ns 2>/dev/null +} +trap cleanup EXIT + +run_one() { + # use 'rx' as separator between sender args and receiver args + local -r all="$@" + local -r tx_args=${all%rx*} + local rx_args=${all#*rx} + + [[ "${tx_args}" == *"-4"* ]] && rx_args="${rx_args} -4" + + ip netns add "${PEER_NS}" + ip -netns "${PEER_NS}" link set lo up + ip link add type veth + ip link set dev veth0 up + ip addr add dev veth0 192.168.1.2/24 + ip addr add dev veth0 2001:db8::2/64 nodad + + ip link set dev veth1 netns "${PEER_NS}" + ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24 + ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad + ip -netns "${PEER_NS}" link set dev veth1 up + + ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy + ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -t ${rx_args} -r & + + # Hack: let bg programs complete the startup + sleep 0.1 + ./udpgso_bench_tx ${tx_args} +} + +run_in_netns() { + local -r args=$@ + + ./in_netns.sh $0 __subprocess ${args} +} + +run_udp() { + local -r args=$@ + + echo "udp gso - over veth touching data" + run_in_netns ${args} -S 0 rx + + echo "udp gso and gro - over veth touching data" + run_in_netns ${args} -S 0 rx -G +} + +run_tcp() { + local -r args=$@ + + echo "tcp - over veth touching data" + run_in_netns ${args} -t rx +} + +run_all() { + local -r core_args="-l 4" + local -r ipv4_args="${core_args} -4 -D 192.168.1.1" + local -r ipv6_args="${core_args} -6 -D 2001:db8::1" + + echo "ipv4" + run_tcp "${ipv4_args}" + run_udp "${ipv4_args}" + + echo "ipv6" + run_tcp "${ipv4_args}" + run_udp "${ipv6_args}" +} + +if [ ! -f ../bpf/xdp_dummy.o ]; then + echo "Missing xdp_dummy helper. Build bpf selftest first" + exit -1 +fi + +if [[ $# -eq 0 ]]; then + run_all +elif [[ $1 == "__subprocess" ]]; then + shift + run_one $@ +else + run_in_netns $@ +fi diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh index 99e537ab5ad9..5670a9ffd8eb 100755 --- a/tools/testing/selftests/net/udpgso_bench.sh +++ b/tools/testing/selftests/net/udpgso_bench.sh @@ -34,7 +34,10 @@ run_udp() { run_in_netns ${args} echo "udp gso" - run_in_netns ${args} -S + run_in_netns ${args} -S 0 + + echo "udp gso zerocopy" + run_in_netns ${args} -S 0 -z } run_tcp() { diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index 727cf67a3f75..0c960f673324 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -31,9 +31,21 @@ #include <sys/wait.h> #include <unistd.h> +#ifndef UDP_GRO +#define UDP_GRO 104 +#endif + static int cfg_port = 8000; static bool cfg_tcp; static bool cfg_verify; +static bool cfg_read_all; +static bool cfg_gro_segment; +static int cfg_family = PF_INET6; +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 struct sockaddr_storage cfg_bind_addr; static bool interrupted; static unsigned long packets, bytes; @@ -44,6 +56,29 @@ static void sigint_handler(int signum) interrupted = true; } +static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr) +{ + struct sockaddr_in6 *addr6 = (void *) sockaddr; + struct sockaddr_in *addr4 = (void *) sockaddr; + + switch (domain) { + case PF_INET: + addr4->sin_family = AF_INET; + addr4->sin_port = htons(cfg_port); + if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1) + error(1, 0, "ipv4 parse error: %s", str_addr); + break; + case PF_INET6: + addr6->sin6_family = AF_INET6; + addr6->sin6_port = htons(cfg_port); + if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1) + error(1, 0, "ipv6 parse error: %s", str_addr); + break; + default: + error(1, 0, "illegal domain"); + } +} + static unsigned long gettimeofday_ms(void) { struct timeval tv; @@ -63,6 +98,8 @@ static void do_poll(int fd) do { ret = poll(&pfd, 1, 10); + if (interrupted) + break; if (ret == -1) error(1, errno, "poll"); if (ret == 0) @@ -70,15 +107,14 @@ static void do_poll(int fd) if (pfd.revents != POLLIN) error(1, errno, "poll: 0x%x expected 0x%x\n", pfd.revents, POLLIN); - } while (!ret && !interrupted); + } while (!ret); } static int do_socket(bool do_tcp) { - struct sockaddr_in6 addr = {0}; int fd, val; - fd = socket(PF_INET6, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0); + fd = socket(cfg_family, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0); if (fd == -1) error(1, errno, "socket"); @@ -89,10 +125,7 @@ static int do_socket(bool do_tcp) if (setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &val, sizeof(val))) error(1, errno, "setsockopt reuseport"); - addr.sin6_family = PF_INET6; - addr.sin6_port = htons(cfg_port); - addr.sin6_addr = in6addr_any; - if (bind(fd, (void *) &addr, sizeof(addr))) + if (bind(fd, (void *)&cfg_bind_addr, cfg_alen)) error(1, errno, "bind"); if (do_tcp) { @@ -102,6 +135,8 @@ static int do_socket(bool do_tcp) error(1, errno, "listen"); do_poll(accept_fd); + if (interrupted) + exit(0); fd = accept(accept_fd, NULL, NULL); if (fd == -1) @@ -164,51 +199,123 @@ static void do_verify_udp(const char *data, int len) } } +static int recv_msg(int fd, char *buf, int len, int *gso_size) +{ + char control[CMSG_SPACE(sizeof(uint16_t))] = {0}; + struct msghdr msg = {0}; + struct iovec iov = {0}; + struct cmsghdr *cmsg; + uint16_t *gsosizeptr; + int ret; + + iov.iov_base = buf; + iov.iov_len = len; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + *gso_size = -1; + ret = recvmsg(fd, &msg, MSG_TRUNC | MSG_DONTWAIT); + if (ret != -1) { + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL; + cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_level == SOL_UDP + && cmsg->cmsg_type == UDP_GRO) { + gsosizeptr = (uint16_t *) CMSG_DATA(cmsg); + *gso_size = *gsosizeptr; + break; + } + } + } + return ret; +} + /* Flush all outstanding datagrams. Verify first few bytes of each. */ static void do_flush_udp(int fd) { - static char rbuf[ETH_DATA_LEN]; - int ret, len, budget = 256; + static char rbuf[ETH_MAX_MTU]; + int ret, len, gso_size, budget = 256; - len = cfg_verify ? sizeof(rbuf) : 0; + len = cfg_read_all ? sizeof(rbuf) : 0; while (budget--) { /* MSG_TRUNC will make return value full datagram length */ - ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT); + if (!cfg_expected_gso_size) + ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT); + else + ret = recv_msg(fd, rbuf, len, &gso_size); if (ret == -1 && errno == EAGAIN) - return; + break; if (ret == -1) error(1, errno, "recv"); - if (len) { + if (cfg_expected_pkt_len && ret != cfg_expected_pkt_len) + error(1, 0, "recv: bad packet len, got %d," + " expected %d\n", ret, cfg_expected_pkt_len); + if (len && cfg_verify) { if (ret == 0) error(1, errno, "recv: 0 byte datagram\n"); do_verify_udp(rbuf, ret); } + if (cfg_expected_gso_size && cfg_expected_gso_size != gso_size) + error(1, 0, "recv: bad gso size, got %d, expected %d " + "(-1 == no gso cmsg))\n", gso_size, + cfg_expected_gso_size); packets++; bytes += ret; + if (cfg_expected_pkt_nr && packets >= cfg_expected_pkt_nr) + break; } } static void usage(const char *filepath) { - error(1, 0, "Usage: %s [-tv] [-p port]", filepath); + error(1, 0, "Usage: %s [-Grtv] [-b addr] [-p port] [-l pktlen] [-n packetnr] [-S gsosize]", filepath); } static void parse_opts(int argc, char **argv) { int c; - while ((c = getopt(argc, argv, "ptv")) != -1) { + /* bind to any by default */ + setup_sockaddr(PF_INET6, "::", &cfg_bind_addr); + while ((c = getopt(argc, argv, "4b:Gl:n:p:rS:tv")) != -1) { switch (c) { + case '4': + cfg_family = PF_INET; + cfg_alen = sizeof(struct sockaddr_in); + setup_sockaddr(PF_INET, "0.0.0.0", &cfg_bind_addr); + break; + case 'b': + setup_sockaddr(cfg_family, optarg, &cfg_bind_addr); + break; + case 'G': + cfg_gro_segment = true; + break; + case 'l': + cfg_expected_pkt_len = strtoul(optarg, NULL, 0); + break; + case 'n': + cfg_expected_pkt_nr = strtoul(optarg, NULL, 0); + break; case 'p': - cfg_port = htons(strtoul(optarg, NULL, 0)); + cfg_port = strtoul(optarg, NULL, 0); + break; + case 'r': + cfg_read_all = true; + break; + case 'S': + cfg_expected_gso_size = strtol(optarg, NULL, 0); break; case 't': cfg_tcp = true; break; case 'v': cfg_verify = true; + cfg_read_all = true; break; } } @@ -223,12 +330,23 @@ static void parse_opts(int argc, char **argv) static void do_recv(void) { unsigned long tnow, treport; - int fd; + int fd, loop = 0; fd = do_socket(cfg_tcp); + if (cfg_gro_segment && !cfg_tcp) { + int val = 1; + if (setsockopt(fd, IPPROTO_UDP, UDP_GRO, &val, sizeof(val))) + error(1, errno, "setsockopt UDP_GRO"); + } + 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); if (cfg_tcp) @@ -249,6 +367,10 @@ static void do_recv(void) } while (!interrupted); + if (cfg_expected_pkt_nr && (packets != cfg_expected_pkt_nr)) + error(1, 0, "wrong packet number! got %ld, expected %d\n", + packets, cfg_expected_pkt_nr); + if (close(fd)) error(1, errno, "close"); } diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c index e821564053cf..4074538b5df5 100644 --- a/tools/testing/selftests/net/udpgso_bench_tx.c +++ b/tools/testing/selftests/net/udpgso_bench_tx.c @@ -52,6 +52,8 @@ static bool cfg_segment; static bool cfg_sendmmsg; static bool cfg_tcp; static bool cfg_zerocopy; +static int cfg_msg_nr; +static uint16_t cfg_gso_size; static socklen_t cfg_alen; static struct sockaddr_storage cfg_dst_addr; @@ -205,14 +207,14 @@ static void send_udp_segment_cmsg(struct cmsghdr *cm) cm->cmsg_level = SOL_UDP; cm->cmsg_type = UDP_SEGMENT; - cm->cmsg_len = CMSG_LEN(sizeof(cfg_mss)); + cm->cmsg_len = CMSG_LEN(sizeof(cfg_gso_size)); valp = (void *)CMSG_DATA(cm); - *valp = cfg_mss; + *valp = cfg_gso_size; } static int send_udp_segment(int fd, char *data) { - char control[CMSG_SPACE(sizeof(cfg_mss))] = {0}; + char control[CMSG_SPACE(sizeof(cfg_gso_size))] = {0}; struct msghdr msg = {0}; struct iovec iov = {0}; int ret; @@ -241,7 +243,7 @@ static int send_udp_segment(int fd, char *data) static void usage(const char *filepath) { - error(1, 0, "Usage: %s [-46cmStuz] [-C cpu] [-D dst ip] [-l secs] [-p port] [-s sendsize]", + error(1, 0, "Usage: %s [-46cmtuz] [-C cpu] [-D dst ip] [-l secs] [-m messagenr] [-p port] [-s sendsize] [-S gsosize]", filepath); } @@ -250,7 +252,7 @@ static void parse_opts(int argc, char **argv) int max_len, hdrlen; int c; - while ((c = getopt(argc, argv, "46cC:D:l:mp:s:Stuz")) != -1) { + while ((c = getopt(argc, argv, "46cC:D:l:mM:p:s:S:tuz")) != -1) { switch (c) { case '4': if (cfg_family != PF_UNSPEC) @@ -279,6 +281,9 @@ static void parse_opts(int argc, char **argv) case 'm': cfg_sendmmsg = true; break; + case 'M': + cfg_msg_nr = strtoul(optarg, NULL, 10); + break; case 'p': cfg_port = strtoul(optarg, NULL, 0); break; @@ -286,6 +291,7 @@ static void parse_opts(int argc, char **argv) cfg_payload_len = strtoul(optarg, NULL, 0); break; case 'S': + cfg_gso_size = strtoul(optarg, NULL, 0); cfg_segment = true; break; case 't': @@ -317,6 +323,8 @@ static void parse_opts(int argc, char **argv) cfg_mss = ETH_DATA_LEN - hdrlen; max_len = ETH_MAX_MTU - hdrlen; + if (!cfg_gso_size) + cfg_gso_size = cfg_mss; if (cfg_payload_len > max_len) error(1, 0, "payload length %u exceeds max %u", @@ -392,10 +400,12 @@ int main(int argc, char **argv) else num_sends += send_udp(fd, buf[i]); num_msgs++; - if (cfg_zerocopy && ((num_msgs & 0xF) == 0)) flush_zerocopy(fd); + if (cfg_msg_nr && num_msgs >= cfg_msg_nr) + break; + tnow = gettimeofday_ms(); if (tnow > treport) { fprintf(stderr, diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh new file mode 100755 index 000000000000..8db35b99457c --- /dev/null +++ b/tools/testing/selftests/net/xfrm_policy.sh @@ -0,0 +1,302 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Check xfrm policy resolution. Topology: +# +# 1.2 1.1 3.1 3.10 2.1 2.2 +# eth1 eth1 veth0 veth0 eth1 eth1 +# ns1 ---- ns3 ----- ns4 ---- ns2 +# +# ns3 and ns4 are connected via ipsec tunnel. +# pings from ns1 to ns2 (and vice versa) are supposed to work like this: +# ns1: ping 10.0.2.2: passes via ipsec tunnel. +# ns2: ping 10.0.1.2: passes via ipsec tunnel. + +# ns1: ping 10.0.1.253: passes via ipsec tunnel (direct policy) +# ns2: ping 10.0.2.253: passes via ipsec tunnel (direct policy) +# +# ns1: ping 10.0.2.254: does NOT pass via ipsec tunnel (exception) +# ns2: ping 10.0.1.254: does NOT pass via ipsec tunnel (exception) + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 +policy_checks_ok=1 + +KEY_SHA=0xdeadbeef1234567890abcdefabcdefabcdefabcd +KEY_AES=0x0123456789abcdef0123456789012345 +SPI1=0x1 +SPI2=0x2 + +do_esp() { + local ns=$1 + local me=$2 + local remote=$3 + local lnet=$4 + local rnet=$5 + local spi_out=$6 + local spi_in=$7 + + 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_get_check() { + local ns=$1 + local lnet=$2 + local rnet=$3 + + ip -net $ns xfrm policy get src $lnet dst $rnet dir out > /dev/null + if [ $? -ne 0 ] && [ $policy_checks_ok -eq 1 ] ;then + policy_checks_ok=0 + echo "FAIL: ip -net $ns xfrm policy get src $lnet dst $rnet dir out" + ret=1 + fi + + ip -net $ns xfrm policy get src $rnet dst $lnet dir fwd > /dev/null + if [ $? -ne 0 ] && [ $policy_checks_ok -eq 1 ] ;then + policy_checks_ok=0 + echo "FAIL: ip -net $ns xfrm policy get src $rnet dst $lnet dir fwd" + ret=1 + fi +} + +do_exception() { + local ns=$1 + local me=$2 + local remote=$3 + local encryptip=$4 + local plain=$5 + + # network $plain passes without tunnel + ip -net $ns xfrm policy add dst $plain dir out priority 10 action allow + + # direct policy for $encryptip, use tunnel, higher prio takes precedence + ip -net $ns xfrm policy add dst $encryptip dir out tmpl src $me dst $remote proto esp mode tunnel priority 1 action allow +} + +# policies that are not supposed to match any packets generated in this test. +do_dummies4() { + local ns=$1 + + for i in $(seq 10 16);do + # dummy policy with wildcard src/dst. + echo netns exec $ns ip xfrm policy add src 0.0.0.0/0 dst 10.$i.99.0/30 dir out action block + echo netns exec $ns ip xfrm policy add src 10.$i.99.0/30 dst 0.0.0.0/0 dir out action block + for j in $(seq 32 64);do + echo netns exec $ns ip xfrm policy add src 10.$i.1.0/30 dst 10.$i.$j.0/30 dir out action block + # silly, as it encompasses the one above too, but its allowed: + echo netns exec $ns ip xfrm policy add src 10.$i.1.0/29 dst 10.$i.$j.0/29 dir out action block + # and yet again, even more broad one. + echo netns exec $ns ip xfrm policy add src 10.$i.1.0/24 dst 10.$i.$j.0/24 dir out action block + echo netns exec $ns ip xfrm policy add src 10.$i.$j.0/24 dst 10.$i.1.0/24 dir fwd action block + done + done | ip -batch /dev/stdin +} + +do_dummies6() { + local ns=$1 + + for i in $(seq 10 16);do + for j in $(seq 32 64);do + echo netns exec $ns ip xfrm policy add src dead:$i::/64 dst dead:$i:$j::/64 dir out action block + echo netns exec $ns ip xfrm policy add src dead:$i:$j::/64 dst dead:$i::/24 dir fwd action block + done + done | ip -batch /dev/stdin +} + +check_ipt_policy_count() +{ + ns=$1 + + ip netns exec $ns iptables-save -c |grep policy | ( read c rest + ip netns exec $ns iptables -Z + if [ x"$c" = x'[0:0]' ]; then + exit 0 + elif [ x"$c" = x ]; then + echo "ERROR: No counters" + ret=1 + exit 111 + else + exit 1 + fi + ) +} + +check_xfrm() { + # 0: iptables -m policy rule count == 0 + # 1: iptables -m policy rule count != 0 + rval=$1 + ip=$2 + lret=0 + + ip netns exec ns1 ping -q -c 1 10.0.2.$ip > /dev/null + + check_ipt_policy_count ns3 + if [ $? -ne $rval ] ; then + lret=1 + fi + check_ipt_policy_count ns4 + if [ $? -ne $rval ] ; then + lret=1 + fi + + ip netns exec ns2 ping -q -c 1 10.0.1.$ip > /dev/null + + check_ipt_policy_count ns3 + if [ $? -ne $rval ] ; then + lret=1 + fi + check_ipt_policy_count ns4 + if [ $? -ne $rval ] ; then + lret=1 + fi + + return $lret +} + +#check for needed privileges +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip +fi + +ip -Version 2>/dev/null >/dev/null +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without the ip tool" + exit $ksft_skip +fi + +# needed to check if policy lookup got valid ipsec result +iptables --version 2>/dev/null >/dev/null +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without iptables tool" + exit $ksft_skip +fi + +for i in 1 2 3 4; do + ip netns add ns$i + ip -net ns$i link set lo up +done + +DEV=veth0 +ip link add $DEV netns ns1 type veth peer name eth1 netns ns3 +ip link add $DEV netns ns2 type veth peer name eth1 netns ns4 + +ip link add $DEV netns ns3 type veth peer name veth0 netns ns4 + +DEV=veth0 +for i in 1 2; do + ip -net ns$i link set $DEV up + ip -net ns$i addr add 10.0.$i.2/24 dev $DEV + ip -net ns$i addr add dead:$i::2/64 dev $DEV + + ip -net ns$i addr add 10.0.$i.253 dev $DEV + ip -net ns$i addr add 10.0.$i.254 dev $DEV + ip -net ns$i addr add dead:$i::fd dev $DEV + ip -net ns$i addr add dead:$i::fe dev $DEV +done + +for i in 3 4; do +ip -net ns$i link set eth1 up +ip -net ns$i link set veth0 up +done + +ip -net ns1 route add default via 10.0.1.1 +ip -net ns2 route add default via 10.0.2.1 + +ip -net ns3 addr add 10.0.1.1/24 dev eth1 +ip -net ns3 addr add 10.0.3.1/24 dev veth0 +ip -net ns3 addr add 2001:1::1/64 dev eth1 +ip -net ns3 addr add 2001:3::1/64 dev veth0 + +ip -net ns3 route add default via 10.0.3.10 + +ip -net ns4 addr add 10.0.2.1/24 dev eth1 +ip -net ns4 addr add 10.0.3.10/24 dev veth0 +ip -net ns4 addr add 2001:2::1/64 dev eth1 +ip -net ns4 addr add 2001:3::10/64 dev veth0 +ip -net ns4 route add default via 10.0.3.1 + +for j in 4 6; do + for i in 3 4;do + ip netns exec ns$i sysctl net.ipv$j.conf.eth1.forwarding=1 > /dev/null + ip netns exec ns$i sysctl net.ipv$j.conf.veth0.forwarding=1 > /dev/null + done +done + +# abuse iptables rule counter to check if ping matches a policy +ip netns exec ns3 iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec +ip netns exec ns4 iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec +if [ $? -ne 0 ];then + echo "SKIP: Could not insert iptables rule" + for i in 1 2 3 4;do ip netns del ns$i;done + exit $ksft_skip +fi + +# localip remoteip localnet remotenet +do_esp ns3 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2 +do_esp ns3 dead:3::1 dead:3::10 dead:1::/64 dead:2::/64 $SPI1 $SPI2 +do_esp ns4 10.0.3.10 10.0.3.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1 +do_esp ns4 dead:3::10 dead:3::1 dead:2::/64 dead:1::/64 $SPI2 $SPI1 + +do_dummies4 ns3 +do_dummies6 ns4 + +do_esp_policy_get_check ns3 10.0.1.0/24 10.0.2.0/24 +do_esp_policy_get_check ns4 10.0.2.0/24 10.0.1.0/24 +do_esp_policy_get_check ns3 dead:1::/64 dead:2::/64 +do_esp_policy_get_check ns4 dead:2::/64 dead:1::/64 + +# ping to .254 should use ipsec, exception is not installed. +check_xfrm 1 254 +if [ $? -ne 0 ]; then + echo "FAIL: expected ping to .254 to use ipsec tunnel" + ret=1 +else + echo "PASS: policy before exception matches" +fi + +# installs exceptions +# localip remoteip encryptdst plaindst +do_exception ns3 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28 +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 +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 + +# ping to .2 should use ipsec. +check_xfrm 1 2 +if [ $? -ne 0 ]; then + echo "FAIL: expected ping to .2 to use ipsec tunnel" + ret=1 +else + echo "PASS: policy matches" +fi + +for i in 1 2 3 4;do ip netns del ns$i;done + +exit $ret |