diff options
Diffstat (limited to 'tools/testing/selftests/net')
36 files changed, 4136 insertions, 176 deletions
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 1a0ac3a29ec5..8cf22b3c2563 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -13,3 +13,5 @@ udpgso udpgso_bench_rx udpgso_bench_tx tcp_inq +tls +ip_defrag diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 663e11e85727..256d82d5fa87 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -5,16 +5,17 @@ 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 += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.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_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 += udpgso udpgso_bench_tx udpgso_bench_rx +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 +TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls +KSFT_KHDR_INSTALL := 1 include ../lib.mk $(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma diff --git a/tools/testing/selftests/net/fib-onlink-tests.sh b/tools/testing/selftests/net/fib-onlink-tests.sh index 3991ad1a368d..864f865eee55 100755 --- a/tools/testing/selftests/net/fib-onlink-tests.sh +++ b/tools/testing/selftests/net/fib-onlink-tests.sh @@ -167,8 +167,8 @@ setup() # add vrf table ip li add ${VRF} type vrf table ${VRF_TABLE} ip li set ${VRF} up - ip ro add table ${VRF_TABLE} unreachable default - ip -6 ro add table ${VRF_TABLE} unreachable default + ip ro add table ${VRF_TABLE} unreachable default metric 8192 + ip -6 ro add table ${VRF_TABLE} unreachable default metric 8192 # create test interfaces ip li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]} @@ -185,20 +185,20 @@ setup() for n in 1 3 5 7; do ip li set ${NETIFS[p${n}]} up ip addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} - ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} + ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad done # move peer interfaces to namespace and add addresses for n in 2 4 6 8; do ip li set ${NETIFS[p${n}]} netns ${PEER_NS} up ip -netns ${PEER_NS} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} - ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} + ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad done - set +e + ip -6 ro add default via ${V6ADDRS[p3]/::[0-9]/::64} + ip -6 ro add table ${VRF_TABLE} default via ${V6ADDRS[p7]/::[0-9]/::64} - # let DAD complete - assume default of 1 probe - sleep 1 + set +e } cleanup() diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 0f45633bd634..802b4af18729 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -9,11 +9,11 @@ ret=0 ksft_skip=4 # all tests in this script. Can be overridden with -t option -TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric" +TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics" VERBOSE=0 PAUSE_ON_FAIL=no PAUSE=no -IP="ip -netns testns" +IP="ip -netns ns1" log_test() { @@ -47,8 +47,10 @@ log_test() setup() { set -e - ip netns add testns + ip netns add ns1 $IP link set dev lo up + ip netns exec ns1 sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ns1 sysctl -qw net.ipv6.conf.all.forwarding=1 $IP link add dummy0 type dummy $IP link set dev dummy0 up @@ -61,7 +63,8 @@ setup() cleanup() { $IP link del dev dummy0 &> /dev/null - ip netns del testns + ip netns del ns1 + ip netns del ns2 &> /dev/null } get_linklocal() @@ -639,11 +642,14 @@ add_initial_route6() check_route6() { - local pfx="2001:db8:104::/64" + local pfx local expected="$1" local out local rc=0 + set -- $expected + pfx=$1 + out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//') [ "${out}" = "${expected}" ] && return 0 @@ -690,28 +696,33 @@ route_setup() [ "${VERBOSE}" = "1" ] && set -x set -e - $IP li add red up type vrf table 101 + ip netns add ns2 + ip -netns ns2 link set dev lo up + ip netns exec ns2 sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ns2 sysctl -qw net.ipv6.conf.all.forwarding=1 + $IP li add veth1 type veth peer name veth2 $IP li add veth3 type veth peer name veth4 $IP li set veth1 up $IP li set veth3 up - $IP li set veth2 vrf red up - $IP li set veth4 vrf red up - $IP li add dummy1 type dummy - $IP li set dummy1 vrf red up - - $IP -6 addr add 2001:db8:101::1/64 dev veth1 - $IP -6 addr add 2001:db8:101::2/64 dev veth2 - $IP -6 addr add 2001:db8:103::1/64 dev veth3 - $IP -6 addr add 2001:db8:103::2/64 dev veth4 - $IP -6 addr add 2001:db8:104::1/64 dev dummy1 + $IP li set veth2 netns ns2 up + $IP li set veth4 netns ns2 up + ip -netns ns2 li add dummy1 type dummy + ip -netns ns2 li set dummy1 up + $IP -6 addr add 2001:db8:101::1/64 dev veth1 nodad + $IP -6 addr add 2001:db8:103::1/64 dev veth3 nodad $IP addr add 172.16.101.1/24 dev veth1 - $IP addr add 172.16.101.2/24 dev veth2 $IP addr add 172.16.103.1/24 dev veth3 - $IP addr add 172.16.103.2/24 dev veth4 - $IP addr add 172.16.104.1/24 dev dummy1 + + ip -netns ns2 -6 addr add 2001:db8:101::2/64 dev veth2 nodad + ip -netns ns2 -6 addr add 2001:db8:103::2/64 dev veth4 nodad + ip -netns ns2 -6 addr add 2001:db8:104::1/64 dev dummy1 nodad + + ip -netns ns2 addr add 172.16.101.2/24 dev veth2 + ip -netns ns2 addr add 172.16.103.2/24 dev veth4 + ip -netns ns2 addr add 172.16.104.1/24 dev dummy1 set +ex } @@ -944,7 +955,7 @@ ipv6_addr_metric_test() log_test $rc 0 "Modify metric of address" # verify prefix route removed on down - run_cmd "ip netns exec testns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1" + run_cmd "ip netns exec ns1 sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1" run_cmd "$IP li set dev dummy2 down" rc=$? if [ $rc -eq 0 ]; then @@ -967,6 +978,77 @@ ipv6_addr_metric_test() cleanup } +ipv6_route_metrics_test() +{ + local rc + + echo + echo "IPv6 routes with metrics" + + route_setup + + # + # single path with metrics + # + run_cmd "$IP -6 ro add 2001:db8:111::/64 via 2001:db8:101::2 mtu 1400" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:111::/64 via 2001:db8:101::2 dev veth1 metric 1024 mtu 1400" + rc=$? + fi + log_test $rc 0 "Single path route with mtu metric" + + + # + # multipath via separate routes with metrics + # + run_cmd "$IP -6 ro add 2001:db8:112::/64 via 2001:db8:101::2 mtu 1400" + run_cmd "$IP -6 ro append 2001:db8:112::/64 via 2001:db8:103::2" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:112::/64 metric 1024 mtu 1400 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + rc=$? + fi + log_test $rc 0 "Multipath route via 2 single routes with mtu metric on first" + + # second route is coalesced to first to make a multipath route. + # MTU of the second path is hidden from display! + run_cmd "$IP -6 ro add 2001:db8:113::/64 via 2001:db8:101::2" + run_cmd "$IP -6 ro append 2001:db8:113::/64 via 2001:db8:103::2 mtu 1400" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:113::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + rc=$? + fi + log_test $rc 0 "Multipath route via 2 single routes with mtu metric on 2nd" + + run_cmd "$IP -6 ro del 2001:db8:113::/64 via 2001:db8:101::2" + if [ $? -eq 0 ]; then + check_route6 "2001:db8:113::/64 via 2001:db8:103::2 dev veth3 metric 1024 mtu 1400" + log_test $? 0 " MTU of second leg" + fi + + # + # multipath with metrics + # + run_cmd "$IP -6 ro add 2001:db8:115::/64 mtu 1400 nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:115::/64 metric 1024 mtu 1400 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + rc=$? + fi + log_test $rc 0 "Multipath route with mtu metric" + + $IP -6 ro add 2001:db8:104::/64 via 2001:db8:101::2 mtu 1300 + run_cmd "ip netns exec ns1 ping6 -w1 -c1 -s 1500 2001:db8:104::1" + log_test $? 0 "Using route with mtu metric" + + run_cmd "$IP -6 ro add 2001:db8:114::/64 via 2001:db8:101::2 congctl lock foo" + log_test $? 2 "Invalid metric (fails metric_convert)" + + route_cleanup +} + # add route for a prefix, flushing any existing routes first # expected to be the first step of a test add_route() @@ -1005,11 +1087,15 @@ add_initial_route() check_route() { - local pfx="172.16.104.0/24" + local pfx local expected="$1" local out local rc=0 + set -- $expected + pfx=$1 + [ "${pfx}" = "unreachable" ] && pfx=$2 + out=$($IP ro ls match ${pfx}) [ "${out}" = "${expected}" ] && return 0 @@ -1319,6 +1405,43 @@ ipv4_addr_metric_test() cleanup } +ipv4_route_metrics_test() +{ + local rc + + echo + echo "IPv4 route add / append tests" + + route_setup + + run_cmd "$IP ro add 172.16.111.0/24 via 172.16.101.2 mtu 1400" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.111.0/24 via 172.16.101.2 dev veth1 mtu 1400" + rc=$? + fi + log_test $rc 0 "Single path route with mtu metric" + + + run_cmd "$IP ro add 172.16.112.0/24 mtu 1400 nexthop via 172.16.101.2 nexthop via 172.16.103.2" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.112.0/24 mtu 1400 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + rc=$? + fi + log_test $rc 0 "Multipath route with mtu metric" + + $IP ro add 172.16.104.0/24 via 172.16.101.2 mtu 1300 + run_cmd "ip netns exec ns1 ping -w1 -c1 -s 1500 172.16.104.1" + log_test $? 0 "Using route with mtu metric" + + run_cmd "$IP ro add 172.16.111.0/24 via 172.16.101.2 congctl lock foo" + log_test $? 2 "Invalid metric (fails metric_convert)" + + route_cleanup +} + + ################################################################################ # usage @@ -1385,6 +1508,8 @@ do ipv4_route_test|ipv4_rt) ipv4_route_test;; ipv6_addr_metric) ipv6_addr_metric_test;; ipv4_addr_metric) ipv4_addr_metric_test;; + ipv6_route_metrics) ipv6_route_metrics_test;; + ipv4_route_metrics) ipv4_route_metrics_test;; help) echo "Test names: $TESTS"; exit 0;; esac diff --git a/tools/testing/selftests/net/forwarding/README b/tools/testing/selftests/net/forwarding/README index 4a0964c42860..b8a2af8fcfb7 100644 --- a/tools/testing/selftests/net/forwarding/README +++ b/tools/testing/selftests/net/forwarding/README @@ -46,6 +46,8 @@ Guidelines for Writing Tests o Where possible, reuse an existing topology for different tests instead of recreating the same topology. +o Tests that use anything but the most trivial topologies should include + an ASCII art showing the topology. o Where possible, IPv6 and IPv4 addresses shall conform to RFC 3849 and RFC 5737, respectively. o Where possible, tests shall be written so that they can be reused by diff --git a/tools/testing/selftests/net/forwarding/bridge_port_isolation.sh b/tools/testing/selftests/net/forwarding/bridge_port_isolation.sh new file mode 100755 index 000000000000..a43b4645c4de --- /dev/null +++ b/tools/testing/selftests/net/forwarding/bridge_port_isolation.sh @@ -0,0 +1,151 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS="ping_ipv4 ping_ipv6 flooding" +NUM_NETIFS=6 +CHECK_TC="yes" +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/24 2001:db8:1::2/64 +} + +h2_destroy() +{ + simple_if_fini $h2 192.0.2.2/24 2001:db8:1::2/64 +} + +h3_create() +{ + simple_if_init $h3 192.0.2.3/24 2001:db8:1::3/64 +} + +h3_destroy() +{ + simple_if_fini $h3 192.0.2.3/24 2001:db8:1::3/64 +} + +switch_create() +{ + ip link add dev br0 type bridge + + ip link set dev $swp1 master br0 + ip link set dev $swp2 master br0 + ip link set dev $swp3 master br0 + + ip link set dev $swp1 type bridge_slave isolated on + check_err $? "Can't set isolation on port $swp1" + ip link set dev $swp2 type bridge_slave isolated on + check_err $? "Can't set isolation on port $swp2" + ip link set dev $swp3 type bridge_slave isolated off + check_err $? "Can't disable isolation on port $swp3" + + ip link set dev br0 up + ip link set dev $swp1 up + ip link set dev $swp2 up + ip link set dev $swp3 up +} + +switch_destroy() +{ + ip link set dev $swp3 down + ip link set dev $swp2 down + ip link set dev $swp1 down + + ip link del dev br0 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + + h1_create + h2_create + h3_create + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + h3_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + RET=0 + ping_do $h1 192.0.2.2 + check_fail $? "Ping worked when it should not have" + + RET=0 + ping_do $h3 192.0.2.2 + check_err $? "Ping didn't work when it should have" + + log_test "Isolated port ping" +} + +ping_ipv6() +{ + RET=0 + ping6_do $h1 2001:db8:1::2 + check_fail $? "Ping6 worked when it should not have" + + RET=0 + ping6_do $h3 2001:db8:1::2 + check_err $? "Ping6 didn't work when it should have" + + log_test "Isolated port ping6" +} + +flooding() +{ + local mac=de:ad:be:ef:13:37 + local ip=192.0.2.100 + + RET=0 + flood_test_do false $mac $ip $h1 $h2 + check_err $? "Packet was flooded when it should not have been" + + RET=0 + flood_test_do true $mac $ip $h3 $h2 + check_err $? "Packet was not flooded when it should have been" + + log_test "Isolated port flooding" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh b/tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh new file mode 100755 index 000000000000..1f8ef0eff862 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh @@ -0,0 +1,69 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS="sticky" +NUM_NETIFS=4 +TEST_MAC=de:ad:be:ef:13:37 +source lib.sh + +switch_create() +{ + ip link add dev br0 type bridge + + ip link set dev $swp1 master br0 + ip link set dev $swp2 master br0 + + ip link set dev br0 up + ip link set dev $h1 up + ip link set dev $swp1 up + ip link set dev $h2 up + ip link set dev $swp2 up +} + +switch_destroy() +{ + ip link set dev $swp2 down + ip link set dev $h2 down + ip link set dev $swp1 down + ip link set dev $h1 down + + ip link del dev br0 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + h2=${NETIFS[p3]} + swp2=${NETIFS[p4]} + + switch_create +} + +cleanup() +{ + pre_cleanup + switch_destroy +} + +sticky() +{ + bridge fdb add $TEST_MAC dev $swp1 master static sticky + check_err $? "Could not add fdb entry" + bridge fdb del $TEST_MAC dev $swp1 vlan 1 master static sticky + $MZ $h2 -c 1 -a $TEST_MAC -t arp "request" -q + bridge -j fdb show br br0 brport $swp1\ + | jq -e ".[] | select(.mac == \"$TEST_MAC\")" &> /dev/null + check_err $? "Did not find FDB record when should" + + log_test "Sticky fdb entry" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh new file mode 100644 index 000000000000..5ab1e5f43022 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -0,0 +1,108 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +############################################################################## +# Source library + +relative_path="${BASH_SOURCE%/*}" +if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then + relative_path="." +fi + +source "$relative_path/lib.sh" + +############################################################################## +# Defines + +DEVLINK_DEV=$(devlink port show | grep "${NETIFS[p1]}" | \ + grep -v "${NETIFS[p1]}[0-9]" | cut -d" " -f1 | \ + rev | cut -d"/" -f2- | rev) +if [ -z "$DEVLINK_DEV" ]; then + echo "SKIP: ${NETIFS[p1]} has no devlink device registered for it" + exit 1 +fi +if [[ "$(echo $DEVLINK_DEV | grep -c pci)" -eq 0 ]]; then + echo "SKIP: devlink device's bus is not PCI" + exit 1 +fi + +DEVLINK_VIDDID=$(lspci -s $(echo $DEVLINK_DEV | cut -d"/" -f2) \ + -n | cut -d" " -f3) + +############################################################################## +# Sanity checks + +devlink -j resource show "$DEVLINK_DEV" &> /dev/null +if [ $? -ne 0 ]; then + echo "SKIP: iproute2 too old, missing devlink resource support" + exit 1 +fi + +############################################################################## +# Devlink helpers + +devlink_resource_names_to_path() +{ + local resource + local path="" + + for resource in "${@}"; do + if [ "$path" == "" ]; then + path="$resource" + else + path="${path}/$resource" + fi + done + + echo "$path" +} + +devlink_resource_get() +{ + local name=$1 + local resource_name=.[][\"$DEVLINK_DEV\"] + + resource_name="$resource_name | .[] | select (.name == \"$name\")" + + shift + for resource in "${@}"; do + resource_name="${resource_name} | .[\"resources\"][] | \ + select (.name == \"$resource\")" + done + + devlink -j resource show "$DEVLINK_DEV" | jq "$resource_name" +} + +devlink_resource_size_get() +{ + local size=$(devlink_resource_get "$@" | jq '.["size_new"]') + + if [ "$size" == "null" ]; then + devlink_resource_get "$@" | jq '.["size"]' + else + echo "$size" + fi +} + +devlink_resource_size_set() +{ + local new_size=$1 + local path + + shift + path=$(devlink_resource_names_to_path "$@") + devlink resource set "$DEVLINK_DEV" path "$path" size "$new_size" + check_err $? "Failed setting path $path to size $size" +} + +devlink_reload() +{ + local still_pending + + devlink dev reload "$DEVLINK_DEV" &> /dev/null + check_err $? "Failed reload" + + still_pending=$(devlink resource show "$DEVLINK_DEV" | \ + grep -c "size_new") + check_err $still_pending "Failed reload - There are still unset sizes" +} diff --git a/tools/testing/selftests/net/forwarding/gre_multipath.sh b/tools/testing/selftests/net/forwarding/gre_multipath.sh new file mode 100755 index 000000000000..cca2baa03fb8 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/gre_multipath.sh @@ -0,0 +1,253 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test traffic distribution when a wECMP route forwards traffic to two GRE +# tunnels. +# +# +-------------------------+ +# | H1 | +# | $h1 + | +# | 192.0.2.1/28 | | +# +-------------------|-----+ +# | +# +-------------------|------------------------+ +# | SW1 | | +# | $ol1 + | +# | 192.0.2.2/28 | +# | | +# | + g1a (gre) + g1b (gre) | +# | loc=192.0.2.65 loc=192.0.2.81 | +# | rem=192.0.2.66 --. rem=192.0.2.82 --. | +# | tos=inherit | tos=inherit | | +# | .------------------' | | +# | | .------------------' | +# | v v | +# | + $ul1.111 (vlan) + $ul1.222 (vlan) | +# | | 192.0.2.129/28 | 192.0.2.145/28 | +# | \ / | +# | \________________/ | +# | | | +# | + $ul1 | +# +------------|-------------------------------+ +# | +# +------------|-------------------------------+ +# | SW2 + $ul2 | +# | _______|________ | +# | / \ | +# | / \ | +# | + $ul2.111 (vlan) + $ul2.222 (vlan) | +# | ^ 192.0.2.130/28 ^ 192.0.2.146/28 | +# | | | | +# | | '------------------. | +# | '------------------. | | +# | + g2a (gre) | + g2b (gre) | | +# | loc=192.0.2.66 | loc=192.0.2.82 | | +# | rem=192.0.2.65 --' rem=192.0.2.81 --' | +# | tos=inherit tos=inherit | +# | | +# | $ol2 + | +# | 192.0.2.17/28 | | +# +-------------------|------------------------+ +# | +# +-------------------|-----+ +# | H2 | | +# | $h2 + | +# | 192.0.2.18/28 | +# +-------------------------+ + +ALL_TESTS=" + ping_ipv4 + multipath_ipv4 +" + +NUM_NETIFS=6 +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 + ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2 +} + +h1_destroy() +{ + ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2 + simple_if_fini $h1 192.0.2.1/28 +} + +sw1_create() +{ + simple_if_init $ol1 192.0.2.2/28 + __simple_if_init $ul1 v$ol1 + vlan_create $ul1 111 v$ol1 192.0.2.129/28 + vlan_create $ul1 222 v$ol1 192.0.2.145/28 + + tunnel_create g1a gre 192.0.2.65 192.0.2.66 tos inherit dev v$ol1 + __simple_if_init g1a v$ol1 192.0.2.65/32 + ip route add vrf v$ol1 192.0.2.66/32 via 192.0.2.130 + + tunnel_create g1b gre 192.0.2.81 192.0.2.82 tos inherit dev v$ol1 + __simple_if_init g1b v$ol1 192.0.2.81/32 + ip route add vrf v$ol1 192.0.2.82/32 via 192.0.2.146 + + ip route add vrf v$ol1 192.0.2.16/28 \ + nexthop dev g1a \ + nexthop dev g1b + + tc qdisc add dev $ul1 clsact + tc filter add dev $ul1 egress pref 111 prot ipv4 \ + flower dst_ip 192.0.2.66 action pass + tc filter add dev $ul1 egress pref 222 prot ipv4 \ + flower dst_ip 192.0.2.82 action pass +} + +sw1_destroy() +{ + tc qdisc del dev $ul1 clsact + + ip route del vrf v$ol1 192.0.2.16/28 + + ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146 + __simple_if_fini g1b 192.0.2.81/32 + tunnel_destroy g1b + + ip route del vrf v$ol1 192.0.2.66/32 via 192.0.2.130 + __simple_if_fini g1a 192.0.2.65/32 + tunnel_destroy g1a + + vlan_destroy $ul1 222 + vlan_destroy $ul1 111 + __simple_if_fini $ul1 + simple_if_fini $ol1 192.0.2.2/28 +} + +sw2_create() +{ + simple_if_init $ol2 192.0.2.17/28 + __simple_if_init $ul2 v$ol2 + vlan_create $ul2 111 v$ol2 192.0.2.130/28 + vlan_create $ul2 222 v$ol2 192.0.2.146/28 + + tunnel_create g2a gre 192.0.2.66 192.0.2.65 tos inherit dev v$ol2 + __simple_if_init g2a v$ol2 192.0.2.66/32 + ip route add vrf v$ol2 192.0.2.65/32 via 192.0.2.129 + + tunnel_create g2b gre 192.0.2.82 192.0.2.81 tos inherit dev v$ol2 + __simple_if_init g2b v$ol2 192.0.2.82/32 + ip route add vrf v$ol2 192.0.2.81/32 via 192.0.2.145 + + ip route add vrf v$ol2 192.0.2.0/28 \ + nexthop dev g2a \ + nexthop dev g2b +} + +sw2_destroy() +{ + ip route del vrf v$ol2 192.0.2.0/28 + + ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145 + __simple_if_fini g2b 192.0.2.82/32 + tunnel_destroy g2b + + ip route del vrf v$ol2 192.0.2.65/32 via 192.0.2.129 + __simple_if_fini g2a 192.0.2.66/32 + tunnel_destroy g2a + + vlan_destroy $ul2 222 + vlan_destroy $ul2 111 + __simple_if_fini $ul2 + simple_if_fini $ol2 192.0.2.17/28 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.18/28 + ip route add vrf v$h2 192.0.2.0/28 via 192.0.2.17 +} + +h2_destroy() +{ + ip route del vrf v$h2 192.0.2.0/28 via 192.0.2.17 + simple_if_fini $h2 192.0.2.18/28 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + vrf_prepare + h1_create + sw1_create + sw2_create + h2_create +} + +cleanup() +{ + pre_cleanup + + h2_destroy + sw2_destroy + sw1_destroy + h1_destroy + vrf_cleanup +} + +multipath4_test() +{ + local what=$1; shift + local weight1=$1; shift + local weight2=$1; shift + + sysctl_set net.ipv4.fib_multipath_hash_policy 1 + ip route replace vrf v$ol1 192.0.2.16/28 \ + nexthop dev g1a weight $weight1 \ + nexthop dev g1b weight $weight2 + + local t0_111=$(tc_rule_stats_get $ul1 111 egress) + local t0_222=$(tc_rule_stats_get $ul1 222 egress) + + ip vrf exec v$h1 \ + $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \ + -d 1msec -t udp "sp=1024,dp=0-32768" + + local t1_111=$(tc_rule_stats_get $ul1 111 egress) + local t1_222=$(tc_rule_stats_get $ul1 222 egress) + + local d111=$((t1_111 - t0_111)) + local d222=$((t1_222 - t0_222)) + multipath_eval "$what" $weight1 $weight2 $d111 $d222 + + ip route replace vrf v$ol1 192.0.2.16/28 \ + nexthop dev g1a \ + nexthop dev g1b + sysctl_restore net.ipv4.fib_multipath_hash_policy +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.18 +} + +multipath_ipv4() +{ + log_info "Running IPv4 multipath tests" + multipath4_test "ECMP" 1 1 + multipath4_test "Weighted MP 2:1" 2 1 + multipath4_test "Weighted MP 11:45" 11 45 +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 7b18a53aa556..85d253546684 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -8,14 +8,21 @@ PING=${PING:=ping} PING6=${PING6:=ping6} MZ=${MZ:=mausezahn} +ARPING=${ARPING:=arping} +TEAMD=${TEAMD:=teamd} WAIT_TIME=${WAIT_TIME:=5} PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} PAUSE_ON_CLEANUP=${PAUSE_ON_CLEANUP:=no} NETIF_TYPE=${NETIF_TYPE:=veth} NETIF_CREATE=${NETIF_CREATE:=yes} -if [[ -f forwarding.config ]]; then - source forwarding.config +relative_path="${BASH_SOURCE%/*}" +if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then + relative_path="." +fi + +if [[ -f $relative_path/forwarding.config ]]; then + source "$relative_path/forwarding.config" fi ############################################################################## @@ -28,7 +35,10 @@ check_tc_version() echo "SKIP: iproute2 too old; tc is missing JSON support" exit 1 fi +} +check_tc_shblock_support() +{ tc filter help 2>&1 | grep block &> /dev/null if [[ $? -ne 0 ]]; then echo "SKIP: iproute2 too old; tc is missing shared block support" @@ -36,6 +46,15 @@ check_tc_version() fi } +check_tc_chain_support() +{ + tc help 2>&1|grep chain &> /dev/null + if [[ $? -ne 0 ]]; then + echo "SKIP: iproute2 too old; tc is missing chain support" + exit 1 + fi +} + if [[ "$(id -u)" -ne 0 ]]; then echo "SKIP: need root privileges" exit 0 @@ -45,15 +64,18 @@ if [[ "$CHECK_TC" = "yes" ]]; then check_tc_version fi -if [[ ! -x "$(command -v jq)" ]]; then - echo "SKIP: jq not installed" - exit 1 -fi +require_command() +{ + local cmd=$1; shift -if [[ ! -x "$(command -v $MZ)" ]]; then - echo "SKIP: $MZ not installed" - exit 1 -fi + if [[ ! -x "$(command -v "$cmd")" ]]; then + echo "SKIP: $cmd not installed" + exit 1 + fi +} + +require_command jq +require_command $MZ if [[ ! -v NUM_NETIFS ]]; then echo "SKIP: importer does not define \"NUM_NETIFS\"" @@ -151,6 +173,19 @@ check_fail() fi } +check_err_fail() +{ + local should_fail=$1; shift + local err=$1; shift + local what=$1; shift + + if ((should_fail)); then + check_fail $err "$what succeeded, but should have failed" + else + check_err $err "$what failed" + fi +} + log_test() { local test_name=$1 @@ -185,24 +220,54 @@ log_info() echo "INFO: $msg" } +setup_wait_dev() +{ + local dev=$1; shift + + while true; do + ip link show dev $dev up \ + | grep 'state UP' &> /dev/null + if [[ $? -ne 0 ]]; then + sleep 1 + else + break + fi + done +} + setup_wait() { - for i in $(eval echo {1..$NUM_NETIFS}); do - while true; do - ip link show dev ${NETIFS[p$i]} up \ - | grep 'state UP' &> /dev/null - if [[ $? -ne 0 ]]; then - sleep 1 - else - break - fi - done + local num_netifs=${1:-$NUM_NETIFS} + + for ((i = 1; i <= num_netifs; ++i)); do + setup_wait_dev ${NETIFS[p$i]} done # Make sure links are ready. sleep $WAIT_TIME } +lldpad_app_wait_set() +{ + local dev=$1; shift + + while lldptool -t -i $dev -V APP -c app | grep -Eq "pending|unknown"; do + echo "$dev: waiting for lldpad to push pending APP updates" + sleep 5 + done +} + +lldpad_app_wait_del() +{ + # Give lldpad a chance to push down the changes. If the device is downed + # too soon, the updates will be left pending. However, they will have + # been struck off the lldpad's DB already, so we won't be able to tell + # they are pending. Then on next test iteration this would cause + # weirdness as newly-added APP rules conflict with the old ones, + # sometimes getting stuck in an "unknown" state. + sleep 5 +} + pre_cleanup() { if [ "${PAUSE_ON_CLEANUP}" = "yes" ]; then @@ -287,6 +352,29 @@ __addr_add_del() done } +__simple_if_init() +{ + local if_name=$1; shift + local vrf_name=$1; shift + local addrs=("${@}") + + ip link set dev $if_name master $vrf_name + ip link set dev $if_name up + + __addr_add_del $if_name add "${addrs[@]}" +} + +__simple_if_fini() +{ + local if_name=$1; shift + local addrs=("${@}") + + __addr_add_del $if_name del "${addrs[@]}" + + ip link set dev $if_name down + ip link set dev $if_name nomaster +} + simple_if_init() { local if_name=$1 @@ -298,11 +386,8 @@ simple_if_init() array=("${@}") vrf_create $vrf_name - ip link set dev $if_name master $vrf_name ip link set dev $vrf_name up - ip link set dev $if_name up - - __addr_add_del $if_name add "${array[@]}" + __simple_if_init $if_name $vrf_name "${array[@]}" } simple_if_fini() @@ -315,9 +400,7 @@ simple_if_fini() vrf_name=v$if_name array=("${@}") - __addr_add_del $if_name del "${array[@]}" - - ip link set dev $if_name down + __simple_if_fini $if_name "${array[@]}" vrf_destroy $vrf_name } @@ -365,6 +448,28 @@ vlan_destroy() ip link del dev $name } +team_create() +{ + local if_name=$1; shift + local mode=$1; shift + + require_command $TEAMD + $TEAMD -t $if_name -d -c '{"runner": {"name": "'$mode'"}}' + for slave in "$@"; do + ip link set dev $slave down + ip link set dev $slave master $if_name + ip link set dev $slave up + done + ip link set dev $if_name up +} + +team_destroy() +{ + local if_name=$1; shift + + $TEAMD -t $if_name -k +} + master_name_get() { local if_name=$1 @@ -383,9 +488,18 @@ tc_rule_stats_get() { local dev=$1; shift local pref=$1; shift + local dir=$1; shift - tc -j -s filter show dev $dev ingress pref $pref | - jq '.[1].options.actions[].stats.packets' + tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \ + | jq '.[1].options.actions[].stats.packets' +} + +ethtool_stats_get() +{ + local dev=$1; shift + local stat=$1; shift + + ethtool -S $dev | grep "^ *$stat:" | head -n 1 | cut -d: -f2 } mac_get() @@ -435,9 +549,28 @@ forwarding_restore() sysctl_restore net.ipv4.conf.all.forwarding } +declare -A MTU_ORIG +mtu_set() +{ + local dev=$1; shift + local mtu=$1; shift + + MTU_ORIG["$dev"]=$(ip -j link show dev $dev | jq -e '.[].mtu') + ip link set dev $dev mtu $mtu +} + +mtu_restore() +{ + local dev=$1; shift + + ip link set dev $dev mtu ${MTU_ORIG["$dev"]} +} + tc_offload_check() { - for i in $(eval echo {1..$NUM_NETIFS}); do + local num_netifs=${1:-$NUM_NETIFS} + + for ((i = 1; i <= num_netifs; ++i)); do ethtool -k ${NETIFS[p$i]} \ | grep "hw-tc-offload: on" &> /dev/null if [[ $? -ne 0 ]]; then @@ -453,9 +586,15 @@ trap_install() local dev=$1; shift local direction=$1; shift - # For slow-path testing, we need to install a trap to get to - # slow path the packets that would otherwise be switched in HW. - tc filter add dev $dev $direction pref 1 flower skip_sw action trap + # Some devices may not support or need in-hardware trapping of traffic + # (e.g. the veth pairs that this library creates for non-existent + # loopbacks). Use continue instead, so that there is a filter in there + # (some tests check counters), and so that other filters are still + # processed. + tc filter add dev $dev $direction pref 1 \ + flower skip_sw action trap 2>/dev/null \ + || tc filter add dev $dev $direction pref 1 \ + flower action continue } trap_uninstall() @@ -463,11 +602,13 @@ trap_uninstall() local dev=$1; shift local direction=$1; shift - tc filter del dev $dev $direction pref 1 flower skip_sw + tc filter del dev $dev $direction pref 1 flower } slow_path_trap_install() { + # For slow-path testing, we need to install a trap to get to + # slow path the packets that would otherwise be switched in HW. if [ "${tcflags/skip_hw}" != "$tcflags" ]; then trap_install "$@" fi @@ -537,6 +678,48 @@ vlan_capture_uninstall() __vlan_capture_add_del del 100 "$@" } +__dscp_capture_add_del() +{ + local add_del=$1; shift + local dev=$1; shift + local base=$1; shift + local dscp; + + for prio in {0..7}; do + dscp=$((base + prio)) + __icmp_capture_add_del $add_del $((dscp + 100)) "" $dev \ + "skip_hw ip_tos $((dscp << 2))" + done +} + +dscp_capture_install() +{ + local dev=$1; shift + local base=$1; shift + + __dscp_capture_add_del add $dev $base +} + +dscp_capture_uninstall() +{ + local dev=$1; shift + local base=$1; shift + + __dscp_capture_add_del del $dev $base +} + +dscp_fetch_stats() +{ + local dev=$1; shift + local base=$1; shift + + for prio in {0..7}; do + local dscp=$((base + prio)) + local t=$(tc_rule_stats_get $dev $((dscp + 100))) + echo "[$dscp]=$t " + done +} + matchall_sink_create() { local dev=$1; shift @@ -557,33 +740,86 @@ tests_run() done } +multipath_eval() +{ + local desc="$1" + local weight_rp12=$2 + local weight_rp13=$3 + local packets_rp12=$4 + local packets_rp13=$5 + local weights_ratio packets_ratio diff + + RET=0 + + if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then + weights_ratio=$(echo "scale=2; $weight_rp12 / $weight_rp13" \ + | bc -l) + else + weights_ratio=$(echo "scale=2; $weight_rp13 / $weight_rp12" \ + | bc -l) + fi + + if [[ "$packets_rp12" -eq "0" || "$packets_rp13" -eq "0" ]]; then + check_err 1 "Packet difference is 0" + log_test "Multipath" + log_info "Expected ratio $weights_ratio" + return + fi + + if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then + packets_ratio=$(echo "scale=2; $packets_rp12 / $packets_rp13" \ + | bc -l) + else + packets_ratio=$(echo "scale=2; $packets_rp13 / $packets_rp12" \ + | bc -l) + fi + + diff=$(echo $weights_ratio - $packets_ratio | bc -l) + diff=${diff#-} + + test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0 + check_err $? "Too large discrepancy between expected and measured ratios" + log_test "$desc" + log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio" +} + ############################################################################## # Tests -ping_test() +ping_do() { local if_name=$1 local dip=$2 local vrf_name - RET=0 - vrf_name=$(master_name_get $if_name) ip vrf exec $vrf_name $PING $dip -c 10 -i 0.1 -w 2 &> /dev/null +} + +ping_test() +{ + RET=0 + + ping_do $1 $2 check_err $? log_test "ping" } -ping6_test() +ping6_do() { local if_name=$1 local dip=$2 local vrf_name - RET=0 - vrf_name=$(master_name_get $if_name) ip vrf exec $vrf_name $PING6 $dip -c 10 -i 0.1 -w 2 &> /dev/null +} + +ping6_test() +{ + RET=0 + + ping6_do $1 $2 check_err $? log_test "ping6" } diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh new file mode 100755 index 000000000000..c5095da7f6bf --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh @@ -0,0 +1,132 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test for "tc action mirred egress mirror" when the underlay route points at a +# bridge device without vlan filtering (802.1d). +# +# This test uses standard topology for testing mirror-to-gretap. See +# mirror_gre_topo_lib.sh for more details. The full topology is as follows: +# +# +---------------------+ +---------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +-----|---------------+ +---------------|-----+ +# | | +# +-----|-------------------------------------------------------------|-----+ +# | SW o---> mirror | | +# | +---|-------------------------------------------------------------|---+ | +# | | + $swp1 + br1 (802.1q bridge) $swp2 + | | +# | +---------------------------------------------------------------------+ | +# | | +# | +---------------------------------------------------------------------+ | +# | | + br2 (802.1d bridge) | | +# | | 192.0.2.129/28 | | +# | | + $swp3 2001:db8:2::1/64 | | +# | +---|-----------------------------------------------------------------+ | +# | | ^ ^ | +# | | + gt6 (ip6gretap) | + gt4 (gretap) | | +# | | : loc=2001:db8:2::1 | : loc=192.0.2.129 | | +# | | : rem=2001:db8:2::2 -+ : rem=192.0.2.130 -+ | +# | | : ttl=100 : ttl=100 | +# | | : tos=inherit : tos=inherit | +# +-----|---------------------:----------------------:----------------------+ +# | : : +# +-----|---------------------:----------------------:----------------------+ +# | H3 + $h3 + h3-gt6(ip6gretap) + h3-gt4 (gretap) | +# | 192.0.2.130/28 loc=2001:db8:2::2 loc=192.0.2.130 | +# | 2001:db8:2::2/64 rem=2001:db8:2::1 rem=192.0.2.129 | +# | ttl=100 ttl=100 | +# | tos=inherit tos=inherit | +# +-------------------------------------------------------------------------+ + +ALL_TESTS=" + test_gretap + test_ip6gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + ip link add name br2 type bridge vlan_filtering 0 + ip link set dev br2 up + + ip link set dev $swp3 master br2 + ip route add 192.0.2.130/32 dev br2 + ip -6 route add 2001:db8:2::2/128 dev br2 + + ip address add dev br2 192.0.2.129/28 + ip address add dev br2 2001:db8:2::1/64 + + ip address add dev $h3 192.0.2.130/28 + ip address add dev $h3 2001:db8:2::2/64 +} + +cleanup() +{ + pre_cleanup + + ip address del dev $h3 2001:db8:2::2/64 + ip address del dev $h3 192.0.2.130/28 + ip link del dev br2 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_gretap() +{ + full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap" + full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap" +} + +test_ip6gretap() +{ + full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap" + full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh index 3bb4c2ba7b14..197e769c2ed1 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh @@ -74,12 +74,14 @@ test_vlan_match() test_gretap() { - test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap" + test_vlan_match gt4 'skip_hw vlan_id 555 vlan_ethtype ip' \ + "mirror to gretap" } test_ip6gretap() { - test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap" + test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ip' \ + "mirror to ip6gretap" } test_gretap_stp() diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh new file mode 100755 index 000000000000..a3402cd8d5b6 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh @@ -0,0 +1,126 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test for "tc action mirred egress mirror" when the underlay route points at a +# bridge device with vlan filtering (802.1q). +# +# This test uses standard topology for testing mirror-to-gretap. See +# mirror_gre_topo_lib.sh for more details. The full topology is as follows: +# +# +---------------------+ +---------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +-----|---------------+ +---------------|-----+ +# | | +# +-----|---------------------------------------------------------------|-----+ +# | SW o---> mirror | | +# | +---|---------------------------------------------------------------|---+ | +# | | + $swp1 + br1 (802.1q bridge) $swp2 + | | +# | | 192.0.2.129/28 | | +# | | + $swp3 2001:db8:2::1/64 | | +# | | | vid555 vid555[pvid,untagged] | | +# | +---|-------------------------------------------------------------------+ | +# | | ^ ^ | +# | | + gt6 (ip6gretap) | + gt4 (gretap) | | +# | | : loc=2001:db8:2::1 | : loc=192.0.2.129 | | +# | | : rem=2001:db8:2::2 -+ : rem=192.0.2.130 -+ | +# | | : ttl=100 : ttl=100 | +# | | : tos=inherit : tos=inherit | +# +-----|---------------------:------------------------:----------------------+ +# | : : +# +-----|---------------------:------------------------:----------------------+ +# | H3 + $h3 + h3-gt6(ip6gretap) + h3-gt4 (gretap) | +# | | loc=2001:db8:2::2 loc=192.0.2.130 | +# | + $h3.555 rem=2001:db8:2::1 rem=192.0.2.129 | +# | 192.0.2.130/28 ttl=100 ttl=100 | +# | 2001:db8:2::2/64 tos=inherit tos=inherit | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + test_gretap + test_ip6gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + ip link set dev $swp3 master br1 + bridge vlan add dev br1 vid 555 pvid untagged self + ip address add dev br1 192.0.2.129/28 + ip address add dev br1 2001:db8:2::1/64 + + ip -4 route add 192.0.2.130/32 dev br1 + ip -6 route add 2001:db8:2::2/128 dev br1 + + vlan_create $h3 555 v$h3 192.0.2.130/28 2001:db8:2::2/64 + bridge vlan add dev $swp3 vid 555 +} + +cleanup() +{ + pre_cleanup + + ip link set dev $swp3 nomaster + vlan_destroy $h3 555 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_gretap() +{ + full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap" + full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap" +} + +test_ip6gretap() +{ + full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap" + full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap" +} + +tests() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +tests + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + tests +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh new file mode 100755 index 000000000000..61844caf671e --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh @@ -0,0 +1,283 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test for "tc action mirred egress mirror" when the underlay route points at a +# bridge device with vlan filtering (802.1q), and the egress device is a team +# device. +# +# +----------------------+ +----------------------+ +# | H1 | | H2 | +# | + $h1.333 | | $h1.555 + | +# | | 192.0.2.1/28 | | 192.0.2.18/28 | | +# +-----|----------------+ +----------------|-----+ +# | $h1 | +# +--------------------------------+------------------------------+ +# | +# +--------------------------------------|------------------------------------+ +# | SW o---> mirror | +# | | | +# | +--------------------------------+------------------------------+ | +# | | $swp1 | | +# | + $swp1.333 $swp1.555 + | +# | 192.0.2.2/28 192.0.2.17/28 | +# | | +# | +-----------------------------------------------------------------------+ | +# | | BR1 (802.1q) | | +# | | + lag (team) 192.0.2.129/28 | | +# | | / \ 2001:db8:2::1/64 | | +# | +---/---\---------------------------------------------------------------+ | +# | / \ ^ | +# | | \ + gt4 (gretap) | | +# | | \ loc=192.0.2.129 | | +# | | \ rem=192.0.2.130 -+ | +# | | \ ttl=100 | +# | | \ tos=inherit | +# | | \ | +# | | \_________________________________ | +# | | \ | +# | + $swp3 + $swp4 | +# +---|------------------------------------------------|----------------------+ +# | | +# +---|----------------------+ +---|----------------------+ +# | + $h3 H3 | | + $h4 H4 | +# | 192.0.2.130/28 | | 192.0.2.130/28 | +# | 2001:db8:2::2/64 | | 2001:db8:2::2/64 | +# +--------------------------+ +--------------------------+ + +ALL_TESTS=" + test_mirror_gretap_first + test_mirror_gretap_second +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh + +require_command $ARPING + +vlan_host_create() +{ + local if_name=$1; shift + local vid=$1; shift + local vrf_name=$1; shift + local ips=("${@}") + + vrf_create $vrf_name + ip link set dev $vrf_name up + vlan_create $if_name $vid $vrf_name "${ips[@]}" +} + +vlan_host_destroy() +{ + local if_name=$1; shift + local vid=$1; shift + local vrf_name=$1; shift + + vlan_destroy $if_name $vid + ip link set dev $vrf_name down + vrf_destroy $vrf_name +} + +h1_create() +{ + vlan_host_create $h1 333 vrf-h1 192.0.2.1/28 + ip -4 route add 192.0.2.16/28 vrf vrf-h1 nexthop via 192.0.2.2 +} + +h1_destroy() +{ + ip -4 route del 192.0.2.16/28 vrf vrf-h1 + vlan_host_destroy $h1 333 vrf-h1 +} + +h2_create() +{ + vlan_host_create $h1 555 vrf-h2 192.0.2.18/28 + ip -4 route add 192.0.2.0/28 vrf vrf-h2 nexthop via 192.0.2.17 +} + +h2_destroy() +{ + ip -4 route del 192.0.2.0/28 vrf vrf-h2 + vlan_host_destroy $h1 555 vrf-h2 +} + +h3_create() +{ + simple_if_init $h3 192.0.2.130/28 + tc qdisc add dev $h3 clsact +} + +h3_destroy() +{ + tc qdisc del dev $h3 clsact + simple_if_fini $h3 192.0.2.130/28 +} + +h4_create() +{ + simple_if_init $h4 192.0.2.130/28 + tc qdisc add dev $h4 clsact +} + +h4_destroy() +{ + tc qdisc del dev $h4 clsact + simple_if_fini $h4 192.0.2.130/28 +} + +switch_create() +{ + ip link set dev $swp1 up + tc qdisc add dev $swp1 clsact + vlan_create $swp1 333 "" 192.0.2.2/28 + vlan_create $swp1 555 "" 192.0.2.17/28 + + tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \ + ttl 100 tos inherit + + ip link set dev $swp3 up + ip link set dev $swp4 up + + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 up + __addr_add_del br1 add 192.0.2.129/32 + ip -4 route add 192.0.2.130/32 dev br1 + + team_create lag loadbalance $swp3 $swp4 + ip link set dev lag master br1 +} + +switch_destroy() +{ + ip link set dev lag nomaster + team_destroy lag + + ip -4 route del 192.0.2.130/32 dev br1 + __addr_add_del br1 del 192.0.2.129/32 + ip link set dev br1 down + ip link del dev br1 + + ip link set dev $swp4 down + ip link set dev $swp3 down + + tunnel_destroy gt4 + + vlan_destroy $swp1 555 + vlan_destroy $swp1 333 + tc qdisc del dev $swp1 clsact + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp3=${NETIFS[p3]} + h3=${NETIFS[p4]} + + swp4=${NETIFS[p5]} + h4=${NETIFS[p6]} + + vrf_prepare + + ip link set dev $h1 up + h1_create + h2_create + h3_create + h4_create + switch_create + + trap_install $h3 ingress + trap_install $h4 ingress +} + +cleanup() +{ + pre_cleanup + + trap_uninstall $h4 ingress + trap_uninstall $h3 ingress + + switch_destroy + h4_destroy + h3_destroy + h2_destroy + h1_destroy + ip link set dev $h1 down + + vrf_cleanup +} + +test_lag_slave() +{ + local host_dev=$1; shift + local up_dev=$1; shift + local down_dev=$1; shift + local what=$1; shift + + RET=0 + + mirror_install $swp1 ingress gt4 \ + "proto 802.1q flower vlan_id 333 $tcflags" + + # Test connectivity through $up_dev when $down_dev is set down. + ip link set dev $down_dev down + setup_wait_dev $up_dev + setup_wait_dev $host_dev + $ARPING -I br1 192.0.2.130 -qfc 1 + sleep 2 + mirror_test vrf-h1 192.0.2.1 192.0.2.18 $host_dev 1 10 + + # Test lack of connectivity when both slaves are down. + ip link set dev $up_dev down + sleep 2 + mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h3 1 0 + mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h4 1 0 + + ip link set dev $up_dev up + ip link set dev $down_dev up + mirror_uninstall $swp1 ingress + + log_test "$what ($tcflags)" +} + +test_mirror_gretap_first() +{ + test_lag_slave $h3 $swp3 $swp4 "mirror to gretap: LAG first slave" +} + +test_mirror_gretap_second() +{ + test_lag_slave $h4 $swp4 $swp3 "mirror to gretap: LAG second slave" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh index aa29d46186a8..135902aa8b11 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh @@ -122,15 +122,8 @@ test_span_gre_egress_up() # After setting the device up, wait for neighbor to get resolved so that # we can expect mirroring to work. ip link set dev $swp3 up - while true; do - ip neigh sh dev $swp3 $remote_ip nud reachable | - grep -q ^ - if [[ $? -ne 0 ]]; then - sleep 1 - else - break - fi - done + setup_wait_dev $swp3 + ping -c 1 -I $swp3 $remote_ip &>/dev/null quick_test_span_gre_dir $tundev ingress mirror_uninstall $swp1 ingress diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh new file mode 100755 index 000000000000..9edf4cb104a8 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh @@ -0,0 +1,285 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test for "tc action mirred egress mirror" when the underlay route points at a +# team device. +# +# +----------------------+ +----------------------+ +# | H1 | | H2 | +# | + $h1.333 | | $h1.555 + | +# | | 192.0.2.1/28 | | 192.0.2.18/28 | | +# +----|-----------------+ +----------------|-----+ +# | $h1 | +# +---------------------------------+------------------------------+ +# | +# +--------------------------------------|------------------------------------+ +# | SW o---> mirror | +# | | | +# | +----------------------------------+------------------------------+ | +# | | $swp1 | | +# | + $swp1.333 $swp1.555 + | +# | 192.0.2.2/28 192.0.2.17/28 | +# | | +# | | +# | + gt4 (gretap) ,-> + lag1 (team) | +# | loc=192.0.2.129 | | 192.0.2.129/28 | +# | rem=192.0.2.130 --' | | +# | ttl=100 | | +# | tos=inherit | | +# | _____________________|______________________ | +# | / \ | +# | / \ | +# | + $swp3 + $swp4 | +# +---|------------------------------------------------|----------------------+ +# | | +# +---|------------------------------------------------|----------------------+ +# | + $h3 + $h4 H3 | +# | \ / | +# | \____________________________________________/ | +# | | | +# | + lag2 (team) | +# | 192.0.2.130/28 | +# | | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + test_mirror_gretap_first + test_mirror_gretap_second +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh + +require_command $ARPING + +vlan_host_create() +{ + local if_name=$1; shift + local vid=$1; shift + local vrf_name=$1; shift + local ips=("${@}") + + vrf_create $vrf_name + ip link set dev $vrf_name up + vlan_create $if_name $vid $vrf_name "${ips[@]}" +} + +vlan_host_destroy() +{ + local if_name=$1; shift + local vid=$1; shift + local vrf_name=$1; shift + + vlan_destroy $if_name $vid + ip link set dev $vrf_name down + vrf_destroy $vrf_name +} + +h1_create() +{ + vlan_host_create $h1 333 vrf-h1 192.0.2.1/28 + ip -4 route add 192.0.2.16/28 vrf vrf-h1 nexthop via 192.0.2.2 +} + +h1_destroy() +{ + ip -4 route del 192.0.2.16/28 vrf vrf-h1 + vlan_host_destroy $h1 333 vrf-h1 +} + +h2_create() +{ + vlan_host_create $h1 555 vrf-h2 192.0.2.18/28 + ip -4 route add 192.0.2.0/28 vrf vrf-h2 nexthop via 192.0.2.17 +} + +h2_destroy() +{ + ip -4 route del 192.0.2.0/28 vrf vrf-h2 + vlan_host_destroy $h1 555 vrf-h2 +} + +h3_create_team() +{ + team_create lag2 lacp $h3 $h4 + __simple_if_init lag2 vrf-h3 192.0.2.130/32 + ip -4 route add vrf vrf-h3 192.0.2.129/32 dev lag2 +} + +h3_destroy_team() +{ + ip -4 route del vrf vrf-h3 192.0.2.129/32 dev lag2 + __simple_if_fini lag2 192.0.2.130/32 + team_destroy lag2 + + ip link set dev $h3 down + ip link set dev $h4 down +} + +h3_create() +{ + vrf_create vrf-h3 + ip link set dev vrf-h3 up + tc qdisc add dev $h3 clsact + tc qdisc add dev $h4 clsact + h3_create_team +} + +h3_destroy() +{ + h3_destroy_team + tc qdisc del dev $h4 clsact + tc qdisc del dev $h3 clsact + ip link set dev vrf-h3 down + vrf_destroy vrf-h3 +} + +switch_create() +{ + ip link set dev $swp1 up + tc qdisc add dev $swp1 clsact + vlan_create $swp1 333 "" 192.0.2.2/28 + vlan_create $swp1 555 "" 192.0.2.17/28 + + tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \ + ttl 100 tos inherit + + ip link set dev $swp3 up + ip link set dev $swp4 up + team_create lag1 lacp $swp3 $swp4 + __addr_add_del lag1 add 192.0.2.129/32 + ip -4 route add 192.0.2.130/32 dev lag1 +} + +switch_destroy() +{ + ip -4 route del 192.0.2.130/32 dev lag1 + __addr_add_del lag1 del 192.0.2.129/32 + team_destroy lag1 + + ip link set dev $swp4 down + ip link set dev $swp3 down + + tunnel_destroy gt4 + + vlan_destroy $swp1 555 + vlan_destroy $swp1 333 + tc qdisc del dev $swp1 clsact + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp3=${NETIFS[p3]} + h3=${NETIFS[p4]} + + swp4=${NETIFS[p5]} + h4=${NETIFS[p6]} + + vrf_prepare + + ip link set dev $h1 up + h1_create + h2_create + h3_create + switch_create + + trap_install $h3 ingress + trap_install $h4 ingress +} + +cleanup() +{ + pre_cleanup + + trap_uninstall $h4 ingress + trap_uninstall $h3 ingress + + switch_destroy + h3_destroy + h2_destroy + h1_destroy + ip link set dev $h1 down + + vrf_cleanup +} + +test_lag_slave() +{ + local up_dev=$1; shift + local down_dev=$1; shift + local what=$1; shift + + RET=0 + + mirror_install $swp1 ingress gt4 \ + "proto 802.1q flower vlan_id 333 $tcflags" + + # Move $down_dev away from the team. That will prompt change in + # txability of the connected device, without changing its upness. The + # driver should notice the txability change and move the traffic to the + # other slave. + ip link set dev $down_dev nomaster + sleep 2 + mirror_test vrf-h1 192.0.2.1 192.0.2.18 $up_dev 1 10 + + # Test lack of connectivity when neither slave is txable. + ip link set dev $up_dev nomaster + sleep 2 + mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h3 1 0 + mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h4 1 0 + mirror_uninstall $swp1 ingress + + # Recreate H3's team device, because mlxsw, which this test is + # predominantly mean to test, requires a bottom-up construction and + # doesn't allow enslavement to a device that already has an upper. + h3_destroy_team + h3_create_team + # Wait for ${h,swp}{3,4}. + setup_wait + + log_test "$what ($tcflags)" +} + +test_mirror_gretap_first() +{ + test_lag_slave $h3 $h4 "mirror to gretap: LAG first slave" +} + +test_mirror_gretap_second() +{ + test_lag_slave $h4 $h3 "mirror to gretap: LAG second slave" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh index 619b469365be..fac486178ef7 100644 --- a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -source mirror_lib.sh +source "$relative_path/mirror_lib.sh" quick_test_span_gre_dir_ips() { @@ -62,7 +62,7 @@ full_test_span_gre_dir_vlan_ips() "$backward_type" "$ip1" "$ip2" tc filter add dev $h3 ingress pref 77 prot 802.1q \ - flower $vlan_match ip_proto 0x2f \ + flower $vlan_match \ action pass mirror_test v$h1 $ip1 $ip2 $h3 77 10 tc filter del dev $h3 ingress pref 77 diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh index 8fa681eb90e7..6f9ef1820e93 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh @@ -35,6 +35,8 @@ setup_prepare() vrf_prepare mirror_gre_topo_create + sysctl_set net.ipv4.conf.v$h3.rp_filter 0 + ip address add dev $swp3 192.0.2.161/28 ip address add dev $h3 192.0.2.162/28 ip address add dev gt4 192.0.2.129/32 @@ -61,6 +63,8 @@ cleanup() ip address del dev $h3 192.0.2.162/28 ip address del dev $swp3 192.0.2.161/28 + sysctl_restore net.ipv4.conf.v$h3.rp_filter 0 + mirror_gre_topo_destroy vrf_cleanup diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh index 253419564708..39c03e2867f4 100644 --- a/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh @@ -33,7 +33,7 @@ # | | # +-------------------------------------------------------------------------+ -source mirror_topo_lib.sh +source "$relative_path/mirror_topo_lib.sh" mirror_gre_topo_h3_create() { diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh index 5dbc7a08f4bd..204b25f13934 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh @@ -28,6 +28,8 @@ source mirror_lib.sh source mirror_gre_lib.sh source mirror_gre_topo_lib.sh +require_command $ARPING + setup_prepare() { h1=${NETIFS[p1]} @@ -39,6 +41,12 @@ setup_prepare() swp3=${NETIFS[p5]} h3=${NETIFS[p6]} + # gt4's remote address is at $h3.555, not $h3. Thus the packets arriving + # directly to $h3 for test_gretap_untagged_egress() are rejected by + # rp_filter and the test spuriously fails. + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf.$h3.rp_filter 0 + vrf_prepare mirror_gre_topo_create @@ -65,6 +73,9 @@ cleanup() mirror_gre_topo_destroy vrf_cleanup + + sysctl_restore net.ipv4.conf.$h3.rp_filter + sysctl_restore net.ipv4.conf.all.rp_filter } test_vlan_match() @@ -79,12 +90,14 @@ test_vlan_match() test_gretap() { - test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap" + test_vlan_match gt4 'skip_hw vlan_id 555 vlan_ethtype ip' \ + "mirror to gretap" } test_ip6gretap() { - test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap" + test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ip' \ + "mirror to ip6gretap" } test_span_gre_forbidden_cpu() @@ -138,7 +151,7 @@ test_span_gre_forbidden_egress() bridge vlan add dev $swp3 vid 555 # Re-prime FDB - arping -I br1.555 192.0.2.130 -fqc 1 + $ARPING -I br1.555 192.0.2.130 -fqc 1 sleep 1 quick_test_span_gre_dir $tundev ingress @@ -212,7 +225,7 @@ test_span_gre_fdb_roaming() bridge fdb del dev $swp2 $h3mac vlan 555 master # Re-prime FDB - arping -I br1.555 192.0.2.130 -fqc 1 + $ARPING -I br1.555 192.0.2.130 -fqc 1 sleep 1 quick_test_span_gre_dir $tundev ingress diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh index d36dc26c6c51..07991e1025c7 100644 --- a/tools/testing/selftests/net/forwarding/mirror_lib.sh +++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh @@ -105,7 +105,7 @@ do_test_span_vlan_dir_ips() # Install the capture as skip_hw to avoid double-counting of packets. # The traffic is meant for local box anyway, so will be trapped to # kernel. - vlan_capture_install $dev "skip_hw vlan_id $vid" + vlan_capture_install $dev "skip_hw vlan_id $vid vlan_ethtype ip" mirror_test v$h1 $ip1 $ip2 $dev 100 $expect mirror_test v$h2 $ip2 $ip1 $dev 100 $expect vlan_capture_uninstall $dev diff --git a/tools/testing/selftests/net/forwarding/router_bridge.sh b/tools/testing/selftests/net/forwarding/router_bridge.sh new file mode 100755 index 000000000000..ebc596a272f7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_bridge.sh @@ -0,0 +1,113 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 +" +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 + ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2 + ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del 2001:db8:2::/64 vrf v$h1 + ip -4 route del 192.0.2.128/28 vrf v$h1 + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64 + ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129 + ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1 +} + +h2_destroy() +{ + ip -6 route del 2001:db8:1::/64 vrf v$h2 + ip -4 route del 192.0.2.0/28 vrf v$h2 + simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64 +} + +router_create() +{ + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 up + + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + __addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64 + + ip link set dev $swp2 up + __addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64 +} + +router_destroy() +{ + __addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64 + ip link set dev $swp2 down + + __addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64 + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + router_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.130 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh new file mode 100755 index 000000000000..fef88eb4b873 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh @@ -0,0 +1,132 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + vlan +" +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 + vlan_create $h1 555 v$h1 192.0.2.1/28 2001:db8:1::1/64 + ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2 + ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del 2001:db8:2::/64 vrf v$h1 + ip -4 route del 192.0.2.128/28 vrf v$h1 + vlan_destroy $h1 555 + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64 + ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129 + ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1 +} + +h2_destroy() +{ + ip -6 route del 2001:db8:1::/64 vrf v$h2 + ip -4 route del 192.0.2.0/28 vrf v$h2 + simple_if_fini $h2 192.0.2.130/28 +} + +router_create() +{ + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 up + + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + + bridge vlan add dev br1 vid 555 self pvid untagged + bridge vlan add dev $swp1 vid 555 + + __addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64 + + ip link set dev $swp2 up + __addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64 +} + +router_destroy() +{ + __addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64 + ip link set dev $swp2 down + + __addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64 + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + router_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +vlan() +{ + RET=0 + + bridge vlan add dev br1 vid 333 self + check_err $? "Can't add a non-PVID VLAN" + bridge vlan del dev br1 vid 333 self + check_err $? "Can't remove a non-PVID VLAN" + + log_test "vlan" +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.130 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_broadcast.sh b/tools/testing/selftests/net/forwarding/router_broadcast.sh new file mode 100755 index 000000000000..7bd2ebb6e9de --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_broadcast.sh @@ -0,0 +1,233 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS="ping_ipv4" +NUM_NETIFS=6 +source lib.sh + +h1_create() +{ + vrf_create "vrf-h1" + ip link set dev $h1 master vrf-h1 + + ip link set dev vrf-h1 up + ip link set dev $h1 up + + ip address add 192.0.2.2/24 dev $h1 + + ip route add 198.51.100.0/24 vrf vrf-h1 nexthop via 192.0.2.1 + ip route add 198.51.200.0/24 vrf vrf-h1 nexthop via 192.0.2.1 +} + +h1_destroy() +{ + ip route del 198.51.200.0/24 vrf vrf-h1 + ip route del 198.51.100.0/24 vrf vrf-h1 + + ip address del 192.0.2.2/24 dev $h1 + + ip link set dev $h1 down + vrf_destroy "vrf-h1" +} + +h2_create() +{ + vrf_create "vrf-h2" + ip link set dev $h2 master vrf-h2 + + ip link set dev vrf-h2 up + ip link set dev $h2 up + + ip address add 198.51.100.2/24 dev $h2 + + ip route add 192.0.2.0/24 vrf vrf-h2 nexthop via 198.51.100.1 + ip route add 198.51.200.0/24 vrf vrf-h2 nexthop via 198.51.100.1 +} + +h2_destroy() +{ + ip route del 198.51.200.0/24 vrf vrf-h2 + ip route del 192.0.2.0/24 vrf vrf-h2 + + ip address del 198.51.100.2/24 dev $h2 + + ip link set dev $h2 down + vrf_destroy "vrf-h2" +} + +h3_create() +{ + vrf_create "vrf-h3" + ip link set dev $h3 master vrf-h3 + + ip link set dev vrf-h3 up + ip link set dev $h3 up + + ip address add 198.51.200.2/24 dev $h3 + + ip route add 192.0.2.0/24 vrf vrf-h3 nexthop via 198.51.200.1 + ip route add 198.51.100.0/24 vrf vrf-h3 nexthop via 198.51.200.1 +} + +h3_destroy() +{ + ip route del 198.51.100.0/24 vrf vrf-h3 + ip route del 192.0.2.0/24 vrf vrf-h3 + + ip address del 198.51.200.2/24 dev $h3 + + ip link set dev $h3 down + vrf_destroy "vrf-h3" +} + +router_create() +{ + ip link set dev $rp1 up + ip link set dev $rp2 up + ip link set dev $rp3 up + + ip address add 192.0.2.1/24 dev $rp1 + + ip address add 198.51.100.1/24 dev $rp2 + ip address add 198.51.200.1/24 dev $rp3 +} + +router_destroy() +{ + ip address del 198.51.200.1/24 dev $rp3 + ip address del 198.51.100.1/24 dev $rp2 + + ip address del 192.0.2.1/24 dev $rp1 + + ip link set dev $rp3 down + ip link set dev $rp2 down + ip link set dev $rp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rp1=${NETIFS[p2]} + + rp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + rp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + + h1_create + h2_create + h3_create + + router_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h3_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +bc_forwarding_disable() +{ + sysctl_set net.ipv4.conf.all.bc_forwarding 0 + sysctl_set net.ipv4.conf.$rp1.bc_forwarding 0 +} + +bc_forwarding_enable() +{ + sysctl_set net.ipv4.conf.all.bc_forwarding 1 + sysctl_set net.ipv4.conf.$rp1.bc_forwarding 1 +} + +bc_forwarding_restore() +{ + sysctl_restore net.ipv4.conf.$rp1.bc_forwarding + sysctl_restore net.ipv4.conf.all.bc_forwarding +} + +ping_test_from() +{ + local oif=$1 + local dip=$2 + local from=$3 + local fail=${4:-0} + + RET=0 + + log_info "ping $dip, expected reply from $from" + ip vrf exec $(master_name_get $oif) \ + $PING -I $oif $dip -c 10 -i 0.1 -w 2 -b 2>&1 | grep $from &> /dev/null + check_err_fail $fail $? +} + +ping_ipv4() +{ + sysctl_set net.ipv4.icmp_echo_ignore_broadcasts 0 + + bc_forwarding_disable + log_info "bc_forwarding disabled on r1 =>" + ping_test_from $h1 198.51.100.255 192.0.2.1 + log_test "h1 -> net2: reply from r1 (not forwarding)" + ping_test_from $h1 198.51.200.255 192.0.2.1 + log_test "h1 -> net3: reply from r1 (not forwarding)" + ping_test_from $h1 192.0.2.255 192.0.2.1 + log_test "h1 -> net1: reply from r1 (not dropping)" + ping_test_from $h1 255.255.255.255 192.0.2.1 + log_test "h1 -> 255.255.255.255: reply from r1 (not forwarding)" + + ping_test_from $h2 192.0.2.255 198.51.100.1 + log_test "h2 -> net1: reply from r1 (not forwarding)" + ping_test_from $h2 198.51.200.255 198.51.100.1 + log_test "h2 -> net3: reply from r1 (not forwarding)" + ping_test_from $h2 198.51.100.255 198.51.100.1 + log_test "h2 -> net2: reply from r1 (not dropping)" + ping_test_from $h2 255.255.255.255 198.51.100.1 + log_test "h2 -> 255.255.255.255: reply from r1 (not forwarding)" + bc_forwarding_restore + + bc_forwarding_enable + log_info "bc_forwarding enabled on r1 =>" + ping_test_from $h1 198.51.100.255 198.51.100.2 + log_test "h1 -> net2: reply from h2 (forwarding)" + ping_test_from $h1 198.51.200.255 198.51.200.2 + log_test "h1 -> net3: reply from h3 (forwarding)" + ping_test_from $h1 192.0.2.255 192.0.2.1 1 + log_test "h1 -> net1: no reply (dropping)" + ping_test_from $h1 255.255.255.255 192.0.2.1 + log_test "h1 -> 255.255.255.255: reply from r1 (not forwarding)" + + ping_test_from $h2 192.0.2.255 192.0.2.2 + log_test "h2 -> net1: reply from h1 (forwarding)" + ping_test_from $h2 198.51.200.255 198.51.200.2 + log_test "h2 -> net3: reply from h3 (forwarding)" + ping_test_from $h2 198.51.100.255 198.51.100.1 1 + log_test "h2 -> net2: no reply (dropping)" + ping_test_from $h2 255.255.255.255 198.51.100.1 + log_test "h2 -> 255.255.255.255: reply from r1 (not forwarding)" + bc_forwarding_restore + + sysctl_restore net.ipv4.icmp_echo_ignore_broadcasts +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh index 8b6d0fb6d604..79a209927962 100755 --- a/tools/testing/selftests/net/forwarding/router_multipath.sh +++ b/tools/testing/selftests/net/forwarding/router_multipath.sh @@ -159,45 +159,6 @@ router2_destroy() vrf_destroy "vrf-r2" } -multipath_eval() -{ - local desc="$1" - local weight_rp12=$2 - local weight_rp13=$3 - local packets_rp12=$4 - local packets_rp13=$5 - local weights_ratio packets_ratio diff - - RET=0 - - if [[ "$packets_rp12" -eq "0" || "$packets_rp13" -eq "0" ]]; then - check_err 1 "Packet difference is 0" - log_test "Multipath" - log_info "Expected ratio $weights_ratio" - return - fi - - if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then - weights_ratio=$(echo "scale=2; $weight_rp12 / $weight_rp13" \ - | bc -l) - packets_ratio=$(echo "scale=2; $packets_rp12 / $packets_rp13" \ - | bc -l) - else - weights_ratio=$(echo "scale=2; $weight_rp13 / $weight_rp12" | \ - bc -l) - packets_ratio=$(echo "scale=2; $packets_rp13 / $packets_rp12" | \ - bc -l) - fi - - diff=$(echo $weights_ratio - $packets_ratio | bc -l) - diff=${diff#-} - - test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0 - check_err $? "Too large discrepancy between expected and measured ratios" - log_test "$desc" - log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio" -} - multipath4_test() { local desc="$1" diff --git a/tools/testing/selftests/net/forwarding/tc_chains.sh b/tools/testing/selftests/net/forwarding/tc_chains.sh index d2c783e94df3..2934fb5ed2a2 100755 --- a/tools/testing/selftests/net/forwarding/tc_chains.sh +++ b/tools/testing/selftests/net/forwarding/tc_chains.sh @@ -1,7 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -ALL_TESTS="unreachable_chain_test gact_goto_chain_test" +ALL_TESTS="unreachable_chain_test gact_goto_chain_test create_destroy_chain \ + template_filter_fits" NUM_NETIFS=2 source tc_common.sh source lib.sh @@ -80,6 +81,87 @@ gact_goto_chain_test() log_test "gact goto chain ($tcflags)" } +create_destroy_chain() +{ + RET=0 + + tc chain add dev $h2 ingress + check_err $? "Failed to create default chain" + + output="$(tc -j chain get dev $h2 ingress)" + check_err $? "Failed to get default chain" + + echo $output | jq -e ".[] | select(.chain == 0)" &> /dev/null + check_err $? "Unexpected output for default chain" + + tc chain add dev $h2 ingress chain 1 + check_err $? "Failed to create chain 1" + + output="$(tc -j chain get dev $h2 ingress chain 1)" + check_err $? "Failed to get chain 1" + + echo $output | jq -e ".[] | select(.chain == 1)" &> /dev/null + check_err $? "Unexpected output for chain 1" + + output="$(tc -j chain show dev $h2 ingress)" + check_err $? "Failed to dump chains" + + echo $output | jq -e ".[] | select(.chain == 0)" &> /dev/null + check_err $? "Can't find default chain in dump" + + echo $output | jq -e ".[] | select(.chain == 1)" &> /dev/null + check_err $? "Can't find chain 1 in dump" + + tc chain del dev $h2 ingress + check_err $? "Failed to destroy default chain" + + tc chain del dev $h2 ingress chain 1 + check_err $? "Failed to destroy chain 1" + + log_test "create destroy chain" +} + +template_filter_fits() +{ + RET=0 + + tc chain add dev $h2 ingress protocol ip \ + flower dst_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF &> /dev/null + tc chain add dev $h2 ingress chain 1 protocol ip \ + flower src_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF &> /dev/null + + tc filter add dev $h2 ingress protocol ip pref 1 handle 1101 \ + flower dst_mac $h2mac action drop + check_err $? "Failed to insert filter which fits template" + + tc filter add dev $h2 ingress protocol ip pref 1 handle 1102 \ + flower src_mac $h2mac action drop &> /dev/null + check_fail $? "Incorrectly succeded to insert filter which does not template" + + tc filter add dev $h2 ingress chain 1 protocol ip pref 1 handle 1101 \ + flower src_mac $h2mac action drop + check_err $? "Failed to insert filter which fits template" + + tc filter add dev $h2 ingress chain 1 protocol ip pref 1 handle 1102 \ + flower dst_mac $h2mac action drop &> /dev/null + check_fail $? "Incorrectly succeded to insert filter which does not template" + + tc filter del dev $h2 ingress chain 1 protocol ip pref 1 handle 1102 \ + flower &> /dev/null + tc filter del dev $h2 ingress chain 1 protocol ip pref 1 handle 1101 \ + flower &> /dev/null + + tc filter del dev $h2 ingress protocol ip pref 1 handle 1102 \ + flower &> /dev/null + tc filter del dev $h2 ingress protocol ip pref 1 handle 1101 \ + flower &> /dev/null + + tc chain del dev $h2 ingress chain 1 + tc chain del dev $h2 ingress + + log_test "template filter fits" +} + setup_prepare() { h1=${NETIFS[p1]} @@ -103,6 +185,8 @@ cleanup() vrf_cleanup } +check_tc_chain_support + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/tc_shblocks.sh b/tools/testing/selftests/net/forwarding/tc_shblocks.sh index b5b917203815..9826a446e2c0 100755 --- a/tools/testing/selftests/net/forwarding/tc_shblocks.sh +++ b/tools/testing/selftests/net/forwarding/tc_shblocks.sh @@ -105,6 +105,8 @@ cleanup() ip link set $swp2 address $swp2origmac } +check_tc_shblock_support + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/ip6_gre_headroom.sh b/tools/testing/selftests/net/ip6_gre_headroom.sh new file mode 100755 index 000000000000..5b41e8bb6e2d --- /dev/null +++ b/tools/testing/selftests/net/ip6_gre_headroom.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test that enough headroom is reserved for the first packet passing through an +# IPv6 GRE-like netdevice. + +setup_prepare() +{ + ip link add h1 type veth peer name swp1 + ip link add h3 type veth peer name swp3 + + ip link set dev h1 up + ip address add 192.0.2.1/28 dev h1 + + ip link add dev vh3 type vrf table 20 + ip link set dev h3 master vh3 + ip link set dev vh3 up + ip link set dev h3 up + + ip link set dev swp3 up + ip address add dev swp3 2001:db8:2::1/64 + ip address add dev swp3 2001:db8:2::3/64 + + ip link set dev swp1 up + tc qdisc add dev swp1 clsact + + ip link add name er6 type ip6erspan \ + local 2001:db8:2::1 remote 2001:db8:2::2 oseq okey 123 + ip link set dev er6 up + + ip link add name gt6 type ip6gretap \ + local 2001:db8:2::3 remote 2001:db8:2::4 + ip link set dev gt6 up + + sleep 1 +} + +cleanup() +{ + ip link del dev gt6 + ip link del dev er6 + ip link del dev swp1 + ip link del dev swp3 + ip link del dev vh3 +} + +test_headroom() +{ + local type=$1; shift + local tundev=$1; shift + + tc filter add dev swp1 ingress pref 1000 matchall skip_hw \ + action mirred egress mirror dev $tundev + ping -I h1 192.0.2.2 -c 1 -w 2 &> /dev/null + tc filter del dev swp1 ingress pref 1000 + + # If it doesn't panic, it passes. + printf "TEST: %-60s [PASS]\n" "$type headroom" +} + +trap cleanup EXIT + +setup_prepare +test_headroom ip6gretap gt6 +test_headroom ip6erspan er6 diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c new file mode 100644 index 000000000000..61ae2782388e --- /dev/null +++ b/tools/testing/selftests/net/ip_defrag.c @@ -0,0 +1,393 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <errno.h> +#include <error.h> +#include <linux/in.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/udp.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> + +static bool cfg_do_ipv4; +static bool cfg_do_ipv6; +static bool cfg_verbose; +static bool cfg_overlap; +static unsigned short cfg_port = 9000; + +const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) }; +const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT; + +#define IP4_HLEN (sizeof(struct iphdr)) +#define IP6_HLEN (sizeof(struct ip6_hdr)) +#define UDP_HLEN (sizeof(struct udphdr)) + +/* IPv6 fragment header lenth. */ +#define FRAG_HLEN 8 + +static int payload_len; +static int max_frag_len; + +#define MSG_LEN_MAX 60000 /* Max UDP payload length. */ + +#define IP4_MF (1u << 13) /* IPv4 MF flag. */ +#define IP6_MF (1) /* IPv6 MF flag. */ + +#define CSUM_MANGLED_0 (0xffff) + +static uint8_t udp_payload[MSG_LEN_MAX]; +static uint8_t ip_frame[IP_MAXPACKET]; +static uint32_t ip_id = 0xabcd; +static int msg_counter; +static int frag_counter; +static unsigned int seed; + +/* Receive a UDP packet. Validate it matches udp_payload. */ +static void recv_validate_udp(int fd_udp) +{ + ssize_t ret; + static uint8_t recv_buff[MSG_LEN_MAX]; + + ret = recv(fd_udp, recv_buff, payload_len, 0); + msg_counter++; + + if (cfg_overlap) { + if (ret != -1) + error(1, 0, "recv: expected timeout; got %d", + (int)ret); + if (errno != ETIMEDOUT && errno != EAGAIN) + error(1, errno, "recv: expected timeout: %d", + errno); + return; /* OK */ + } + + if (ret == -1) + error(1, errno, "recv: payload_len = %d max_frag_len = %d", + payload_len, max_frag_len); + if (ret != payload_len) + error(1, 0, "recv: wrong size: %d vs %d", (int)ret, payload_len); + if (memcmp(udp_payload, recv_buff, payload_len)) + error(1, 0, "recv: wrong data"); +} + +static uint32_t raw_checksum(uint8_t *buf, int len, uint32_t sum) +{ + int i; + + for (i = 0; i < (len & ~1U); i += 2) { + sum += (u_int16_t)ntohs(*((u_int16_t *)(buf + i))); + if (sum > 0xffff) + sum -= 0xffff; + } + + if (i < len) { + sum += buf[i] << 8; + if (sum > 0xffff) + sum -= 0xffff; + } + + return sum; +} + +static uint16_t udp_checksum(struct ip *iphdr, struct udphdr *udphdr) +{ + uint32_t sum = 0; + uint16_t res; + + sum = raw_checksum((uint8_t *)&iphdr->ip_src, 2 * sizeof(iphdr->ip_src), + IPPROTO_UDP + (uint32_t)(UDP_HLEN + payload_len)); + sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum); + sum = raw_checksum((uint8_t *)udp_payload, payload_len, sum); + res = 0xffff & ~sum; + if (res) + return htons(res); + else + return CSUM_MANGLED_0; +} + +static uint16_t udp6_checksum(struct ip6_hdr *iphdr, struct udphdr *udphdr) +{ + uint32_t sum = 0; + uint16_t res; + + sum = raw_checksum((uint8_t *)&iphdr->ip6_src, 2 * sizeof(iphdr->ip6_src), + IPPROTO_UDP); + sum = raw_checksum((uint8_t *)&udphdr->len, sizeof(udphdr->len), sum); + sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum); + sum = raw_checksum((uint8_t *)udp_payload, payload_len, sum); + res = 0xffff & ~sum; + if (res) + return htons(res); + else + return CSUM_MANGLED_0; +} + +static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen, + int offset, bool ipv6) +{ + int frag_len; + int res; + int payload_offset = offset > 0 ? offset - UDP_HLEN : 0; + uint8_t *frag_start = ipv6 ? ip_frame + IP6_HLEN + FRAG_HLEN : + ip_frame + IP4_HLEN; + + if (offset == 0) { + struct udphdr udphdr; + udphdr.source = htons(cfg_port + 1); + udphdr.dest = htons(cfg_port); + udphdr.len = htons(UDP_HLEN + payload_len); + udphdr.check = 0; + if (ipv6) + udphdr.check = udp6_checksum((struct ip6_hdr *)ip_frame, &udphdr); + else + udphdr.check = udp_checksum((struct ip *)ip_frame, &udphdr); + memcpy(frag_start, &udphdr, UDP_HLEN); + } + + if (ipv6) { + struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame; + struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN); + if (payload_len - payload_offset <= max_frag_len && offset > 0) { + /* This is the last fragment. */ + frag_len = FRAG_HLEN + payload_len - payload_offset; + fraghdr->ip6f_offlg = htons(offset); + } else { + frag_len = FRAG_HLEN + max_frag_len; + fraghdr->ip6f_offlg = htons(offset | IP6_MF); + } + ip6hdr->ip6_plen = htons(frag_len); + if (offset == 0) + memcpy(frag_start + UDP_HLEN, udp_payload, + frag_len - FRAG_HLEN - UDP_HLEN); + else + memcpy(frag_start, udp_payload + payload_offset, + frag_len - FRAG_HLEN); + frag_len += IP6_HLEN; + } else { + struct ip *iphdr = (struct ip *)ip_frame; + if (payload_len - payload_offset <= max_frag_len && offset > 0) { + /* This is the last fragment. */ + frag_len = IP4_HLEN + payload_len - payload_offset; + iphdr->ip_off = htons(offset / 8); + } else { + frag_len = IP4_HLEN + max_frag_len; + iphdr->ip_off = htons(offset / 8 | IP4_MF); + } + iphdr->ip_len = htons(frag_len); + if (offset == 0) + memcpy(frag_start + UDP_HLEN, udp_payload, + frag_len - IP4_HLEN - UDP_HLEN); + else + memcpy(frag_start, udp_payload + payload_offset, + frag_len - IP4_HLEN); + } + + res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen); + if (res < 0) + error(1, errno, "send_fragment"); + if (res != frag_len) + error(1, 0, "send_fragment: %d vs %d", res, frag_len); + + frag_counter++; +} + +static void send_udp_frags(int fd_raw, struct sockaddr *addr, + socklen_t alen, bool ipv6) +{ + struct ip *iphdr = (struct ip *)ip_frame; + struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame; + int res; + int offset; + int frag_len; + + /* Send the UDP datagram using raw IP fragments: the 0th fragment + * has the UDP header; other fragments are pieces of udp_payload + * split in chunks of frag_len size. + * + * Odd fragments (1st, 3rd, 5th, etc.) are sent out first, then + * even fragments (0th, 2nd, etc.) are sent out. + */ + if (ipv6) { + struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN); + ((struct sockaddr_in6 *)addr)->sin6_port = 0; + memset(ip6hdr, 0, sizeof(*ip6hdr)); + ip6hdr->ip6_flow = htonl(6<<28); /* Version. */ + ip6hdr->ip6_nxt = IPPROTO_FRAGMENT; + ip6hdr->ip6_hops = 255; + ip6hdr->ip6_src = addr6; + ip6hdr->ip6_dst = addr6; + fraghdr->ip6f_nxt = IPPROTO_UDP; + fraghdr->ip6f_reserved = 0; + fraghdr->ip6f_ident = htonl(ip_id++); + } else { + memset(iphdr, 0, sizeof(*iphdr)); + iphdr->ip_hl = 5; + iphdr->ip_v = 4; + iphdr->ip_tos = 0; + iphdr->ip_id = htons(ip_id++); + iphdr->ip_ttl = 0x40; + iphdr->ip_p = IPPROTO_UDP; + iphdr->ip_src.s_addr = htonl(INADDR_LOOPBACK); + iphdr->ip_dst = addr4; + iphdr->ip_sum = 0; + } + + /* Odd fragments. */ + offset = max_frag_len; + while (offset < (UDP_HLEN + payload_len)) { + send_fragment(fd_raw, addr, alen, offset, ipv6); + offset += 2 * max_frag_len; + } + + if (cfg_overlap) { + /* Send an extra random fragment. */ + offset = rand() % (UDP_HLEN + payload_len - 1); + /* sendto() returns EINVAL if offset + frag_len is too small. */ + if (ipv6) { + struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN); + frag_len = max_frag_len + rand() % 256; + /* In IPv6 if !!(frag_len % 8), the fragment is dropped. */ + frag_len &= ~0x7; + fraghdr->ip6f_offlg = htons(offset / 8 | IP6_MF); + ip6hdr->ip6_plen = htons(frag_len); + frag_len += IP6_HLEN; + } else { + frag_len = IP4_HLEN + UDP_HLEN + rand() % 256; + iphdr->ip_off = htons(offset / 8 | IP4_MF); + iphdr->ip_len = htons(frag_len); + } + res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen); + if (res < 0) + error(1, errno, "sendto overlap"); + if (res != frag_len) + error(1, 0, "sendto overlap: %d vs %d", (int)res, frag_len); + frag_counter++; + } + + /* Event fragments. */ + offset = 0; + while (offset < (UDP_HLEN + payload_len)) { + send_fragment(fd_raw, addr, alen, offset, ipv6); + offset += 2 * max_frag_len; + } +} + +static void run_test(struct sockaddr *addr, socklen_t alen, bool ipv6) +{ + int fd_tx_raw, fd_rx_udp; + struct timeval tv = { .tv_sec = 0, .tv_usec = 10 * 1000 }; + int idx; + int min_frag_len = ipv6 ? 1280 : 8; + + /* Initialize the payload. */ + for (idx = 0; idx < MSG_LEN_MAX; ++idx) + udp_payload[idx] = idx % 256; + + /* Open sockets. */ + fd_tx_raw = socket(addr->sa_family, SOCK_RAW, IPPROTO_RAW); + if (fd_tx_raw == -1) + error(1, errno, "socket tx_raw"); + + fd_rx_udp = socket(addr->sa_family, SOCK_DGRAM, 0); + if (fd_rx_udp == -1) + error(1, errno, "socket rx_udp"); + if (bind(fd_rx_udp, addr, alen)) + error(1, errno, "bind"); + /* Fail fast. */ + if (setsockopt(fd_rx_udp, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv))) + error(1, errno, "setsockopt rcv timeout"); + + for (payload_len = min_frag_len; payload_len < MSG_LEN_MAX; + payload_len += (rand() % 4096)) { + if (cfg_verbose) + printf("payload_len: %d\n", payload_len); + max_frag_len = min_frag_len; + do { + send_udp_frags(fd_tx_raw, addr, alen, ipv6); + recv_validate_udp(fd_rx_udp); + max_frag_len += 8 * (rand() % 8); + } while (max_frag_len < (1500 - FRAG_HLEN) && max_frag_len <= payload_len); + } + + /* Cleanup. */ + if (close(fd_tx_raw)) + error(1, errno, "close tx_raw"); + if (close(fd_rx_udp)) + error(1, errno, "close rx_udp"); + + if (cfg_verbose) + printf("processed %d messages, %d fragments\n", + msg_counter, frag_counter); + + fprintf(stderr, "PASS\n"); +} + + +static void run_test_v4(void) +{ + struct sockaddr_in addr = {0}; + + addr.sin_family = AF_INET; + addr.sin_port = htons(cfg_port); + addr.sin_addr = addr4; + + run_test((void *)&addr, sizeof(addr), false /* !ipv6 */); +} + +static void run_test_v6(void) +{ + struct sockaddr_in6 addr = {0}; + + addr.sin6_family = AF_INET6; + addr.sin6_port = htons(cfg_port); + addr.sin6_addr = addr6; + + run_test((void *)&addr, sizeof(addr), true /* ipv6 */); +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "46ov")) != -1) { + switch (c) { + case '4': + cfg_do_ipv4 = true; + break; + case '6': + cfg_do_ipv6 = true; + break; + case 'o': + cfg_overlap = true; + break; + case 'v': + cfg_verbose = true; + break; + default: + error(1, 0, "%s: parse error", argv[0]); + } + } +} + +int main(int argc, char **argv) +{ + parse_opts(argc, argv); + seed = time(NULL); + srand(seed); + /* Print the seed to track/reproduce potential failures. */ + printf("seed = %d\n", seed); + + if (cfg_do_ipv4) + run_test_v4(); + if (cfg_do_ipv6) + run_test_v6(); + + return 0; +} diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh new file mode 100755 index 000000000000..f34672796044 --- /dev/null +++ b/tools/testing/selftests/net/ip_defrag.sh @@ -0,0 +1,39 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Run a couple of IP defragmentation tests. + +set +x +set -e + +readonly NETNS="ns-$(mktemp -u XXXXXX)" + +setup() { + ip netns add "${NETNS}" + ip -netns "${NETNS}" link set lo up + ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_high_thresh=9000000 >/dev/null 2>&1 + ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_low_thresh=7000000 >/dev/null 2>&1 + ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_high_thresh=9000000 >/dev/null 2>&1 + ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_low_thresh=7000000 >/dev/null 2>&1 +} + +cleanup() { + ip netns del "${NETNS}" +} + +trap cleanup EXIT +setup + +echo "ipv4 defrag" +ip netns exec "${NETNS}" ./ip_defrag -4 + + +echo "ipv4 defrag with overlaps" +ip netns exec "${NETNS}" ./ip_defrag -4o + +echo "ipv6 defrag" +ip netns exec "${NETNS}" ./ip_defrag -6 + +echo "ipv6 defrag with overlaps" +ip netns exec "${NETNS}" ./ip_defrag -6o + diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index f8cc38afffa2..a369d616b390 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -6,6 +6,26 @@ # # Tests currently implemented: # +# - pmtu_ipv4 +# Set up two namespaces, A and B, with two paths between them over routers +# R1 and R2 (also implemented with namespaces), with different MTUs: +# +# segment a_r1 segment b_r1 a_r1: 2000 +# .--------------R1--------------. a_r2: 1500 +# A B a_r3: 2000 +# '--------------R2--------------' a_r4: 1400 +# segment a_r2 segment b_r2 +# +# Check that PMTU exceptions with the correct PMTU are created. Then +# decrease and increase the MTU of the local link for one of the paths, +# A to R1, checking that route exception PMTU changes accordingly over +# this path. Also check that locked exceptions are created when an ICMP +# message advertising a PMTU smaller than net.ipv4.route.min_pmtu is +# received +# +# - pmtu_ipv6 +# Same as pmtu_ipv4, except for locked PMTU tests, using IPv6 +# # - pmtu_vti4_exception # Set up vti tunnel on top of veth, with xfrm states and policies, in two # namespaces with matching endpoints. Check that route exception is not @@ -46,7 +66,12 @@ # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +# Some systems don't have a ping6 binary anymore +which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) + tests=" + pmtu_ipv4_exception ipv4: PMTU exceptions + pmtu_ipv6_exception ipv6: PMTU exceptions pmtu_vti6_exception vti6: PMTU exceptions pmtu_vti4_exception vti4: PMTU exceptions pmtu_vti4_default_mtu vti4: default MTU assignment @@ -57,8 +82,45 @@ tests=" NS_A="ns-$(mktemp -u XXXXXX)" NS_B="ns-$(mktemp -u XXXXXX)" +NS_R1="ns-$(mktemp -u XXXXXX)" +NS_R2="ns-$(mktemp -u XXXXXX)" ns_a="ip netns exec ${NS_A}" ns_b="ip netns exec ${NS_B}" +ns_r1="ip netns exec ${NS_R1}" +ns_r2="ip netns exec ${NS_R2}" + +# Addressing and routing for tests with routers: four network segments, with +# index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an +# identifier ID, which is 1 for hosts (A and B), 2 for routers (R1 and R2). +# Addresses are: +# - IPv4: PREFIX4.SEGMENT.ID (/24) +# - IPv6: PREFIX6:SEGMENT::ID (/64) +prefix4="192.168" +prefix6="fd00" +a_r1=1 +a_r2=2 +b_r1=3 +b_r2=4 +# ns peer segment +routing_addrs=" + A R1 ${a_r1} + A R2 ${a_r2} + B R1 ${b_r1} + B R2 ${b_r2} +" +# Traffic from A to B goes through R1 by default, and through R2, if destined to +# B's address on the b_r2 segment. +# Traffic from B to A goes through R1. +# ns destination gateway +routes=" + A default ${prefix4}.${a_r1}.2 + A ${prefix4}.${b_r2}.1 ${prefix4}.${a_r2}.2 + B default ${prefix4}.${b_r1}.2 + + A default ${prefix6}:${a_r1}::2 + A ${prefix6}:${b_r2}::1 ${prefix6}:${a_r2}::2 + B default ${prefix6}:${b_r1}::2 +" veth4_a_addr="192.168.1.1" veth4_b_addr="192.168.1.2" @@ -80,6 +142,7 @@ dummy6_mask="64" cleanup_done=1 err_buf= +tcpdump_pids= err() { err_buf="${err_buf}${1} @@ -91,9 +154,15 @@ err_flush() { err_buf= } +# Find the auto-generated name for this namespace +nsname() { + eval echo \$NS_$1 +} + setup_namespaces() { - ip netns add ${NS_A} || return 1 - ip netns add ${NS_B} + for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do + ip netns add ${n} || return 1 + done } setup_veth() { @@ -164,6 +233,49 @@ setup_xfrm6() { setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} } +setup_routing() { + for i in ${NS_R1} ${NS_R2}; do + ip netns exec ${i} sysctl -q net/ipv4/ip_forward=1 + ip netns exec ${i} sysctl -q net/ipv6/conf/all/forwarding=1 + done + + for i in ${routing_addrs}; do + [ "${ns}" = "" ] && ns="${i}" && continue + [ "${peer}" = "" ] && peer="${i}" && continue + [ "${segment}" = "" ] && segment="${i}" + + ns_name="$(nsname ${ns})" + peer_name="$(nsname ${peer})" + if="veth_${ns}-${peer}" + ifpeer="veth_${peer}-${ns}" + + # Create veth links + ip link add ${if} up netns ${ns_name} type veth peer name ${ifpeer} netns ${peer_name} || return 1 + ip -n ${peer_name} link set dev ${ifpeer} up + + # Add addresses + ip -n ${ns_name} addr add ${prefix4}.${segment}.1/24 dev ${if} + ip -n ${ns_name} addr add ${prefix6}:${segment}::1/64 dev ${if} + + ip -n ${peer_name} addr add ${prefix4}.${segment}.2/24 dev ${ifpeer} + ip -n ${peer_name} addr add ${prefix6}:${segment}::2/64 dev ${ifpeer} + + ns=""; peer=""; segment="" + done + + for i in ${routes}; do + [ "${ns}" = "" ] && ns="${i}" && continue + [ "${addr}" = "" ] && addr="${i}" && continue + [ "${gw}" = "" ] && gw="${i}" + + ns_name="$(nsname ${ns})" + + ip -n ${ns_name} route add ${addr} via ${gw} + + ns=""; addr=""; gw="" + done +} + setup() { [ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip @@ -173,10 +285,28 @@ setup() { done } +trace() { + [ $tracing -eq 0 ] && return + + for arg do + [ "${ns_cmd}" = "" ] && ns_cmd="${arg}" && continue + ${ns_cmd} tcpdump -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null & + tcpdump_pids="${tcpdump_pids} $!" + ns_cmd= + done + sleep 1 +} + cleanup() { + for pid in ${tcpdump_pids}; do + kill ${pid} + done + tcpdump_pids= + [ ${cleanup_done} -eq 1 ] && return - ip netns del ${NS_A} 2 > /dev/null - ip netns del ${NS_B} 2 > /dev/null + for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do + ip netns del ${n} 2> /dev/null + done cleanup_done=1 } @@ -193,7 +323,9 @@ mtu_parse() { next=0 for i in ${input}; do + [ ${next} -eq 1 -a "${i}" = "lock" ] && next=2 && continue [ ${next} -eq 1 ] && echo "${i}" && return + [ ${next} -eq 2 ] && echo "lock ${i}" && return [ "${i}" = "mtu" ] && next=1 done } @@ -226,8 +358,117 @@ route_get_dst_pmtu_from_exception() { mtu_parse "$(route_get_dst_exception "${ns_cmd}" ${dst})" } +check_pmtu_value() { + expected="${1}" + value="${2}" + event="${3}" + + [ "${expected}" = "any" ] && [ -n "${value}" ] && return 0 + [ "${value}" = "${expected}" ] && return 0 + [ -z "${value}" ] && err " PMTU exception wasn't created after ${event}" && return 1 + [ -z "${expected}" ] && err " PMTU exception shouldn't exist after ${event}" && return 1 + err " found PMTU exception with incorrect MTU ${value}, expected ${expected}, after ${event}" + return 1 +} + +test_pmtu_ipvX() { + family=${1} + + setup namespaces routing || return 2 + trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \ + "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \ + "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2 + + if [ ${family} -eq 4 ]; then + ping=ping + dst1="${prefix4}.${b_r1}.1" + dst2="${prefix4}.${b_r2}.1" + else + ping=${ping6} + dst1="${prefix6}:${b_r1}::1" + dst2="${prefix6}:${b_r2}::1" + fi + + # Set up initial MTU values + mtu "${ns_a}" veth_A-R1 2000 + mtu "${ns_r1}" veth_R1-A 2000 + mtu "${ns_r1}" veth_R1-B 1400 + mtu "${ns_b}" veth_B-R1 1400 + + mtu "${ns_a}" veth_A-R2 2000 + mtu "${ns_r2}" veth_R2-A 2000 + mtu "${ns_r2}" veth_R2-B 1500 + mtu "${ns_b}" veth_B-R2 1500 + + # Create route exceptions + ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst1} > /dev/null + ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst2} > /dev/null + + # Check that exceptions have been created with the correct PMTU + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})" + check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1 + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})" + check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1 + + # Decrease local MTU below PMTU, check for PMTU decrease in route exception + mtu "${ns_a}" veth_A-R1 1300 + mtu "${ns_r1}" veth_R1-A 1300 + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})" + check_pmtu_value "1300" "${pmtu_1}" "decreasing local MTU" || return 1 + # Second exception shouldn't be modified + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})" + check_pmtu_value "1500" "${pmtu_2}" "changing local MTU on a link not on this path" || return 1 + + # Increase MTU, check for PMTU increase in route exception + mtu "${ns_a}" veth_A-R1 1700 + mtu "${ns_r1}" veth_R1-A 1700 + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})" + check_pmtu_value "1700" "${pmtu_1}" "increasing local MTU" || return 1 + # Second exception shouldn't be modified + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})" + check_pmtu_value "1500" "${pmtu_2}" "changing local MTU on a link not on this path" || return 1 + + # Skip PMTU locking tests for IPv6 + [ $family -eq 6 ] && return 0 + + # Decrease remote MTU on path via R2, get new exception + mtu "${ns_r2}" veth_R2-B 400 + mtu "${ns_b}" veth_B-R2 400 + ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})" + check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1 + + # Decrease local MTU below PMTU + mtu "${ns_a}" veth_A-R2 500 + mtu "${ns_r2}" veth_R2-A 500 + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})" + check_pmtu_value "500" "${pmtu_2}" "decreasing local MTU" || return 1 + + # Increase local MTU + mtu "${ns_a}" veth_A-R2 1500 + mtu "${ns_r2}" veth_R2-A 1500 + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})" + check_pmtu_value "1500" "${pmtu_2}" "increasing local MTU" || return 1 + + # Get new exception + ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})" + check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1 +} + +test_pmtu_ipv4_exception() { + test_pmtu_ipvX 4 +} + +test_pmtu_ipv6_exception() { + test_pmtu_ipvX 6 +} + test_pmtu_vti4_exception() { setup namespaces veth vti4 xfrm4 || return 2 + trace "${ns_a}" veth_a "${ns_b}" veth_b \ + "${ns_a}" vti4_a "${ns_b}" vti4_b veth_mtu=1500 vti_mtu=$((veth_mtu - 20)) @@ -245,28 +486,19 @@ test_pmtu_vti4_exception() { # exception is created ${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${vti4_b_addr} > /dev/null pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})" - if [ "${pmtu}" != "" ]; then - err " unexpected exception created with PMTU ${pmtu} for IP payload length ${esp_payload_rfc4106}" - return 1 - fi + check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1 # Now exceed link layer MTU by one byte, check that exception is created + # with the right PMTU value ${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${vti4_b_addr} > /dev/null pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})" - if [ "${pmtu}" = "" ]; then - err " exception not created for IP payload length $((esp_payload_rfc4106 + 1))" - return 1 - fi - - # ...with the right PMTU value - if [ ${pmtu} -ne ${esp_payload_rfc4106} ]; then - err " wrong PMTU ${pmtu} in exception, expected: ${esp_payload_rfc4106}" - return 1 - fi + check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))" } test_pmtu_vti6_exception() { setup namespaces veth vti6 xfrm6 || return 2 + trace "${ns_a}" veth_a "${ns_b}" veth_b \ + "${ns_a}" vti6_a "${ns_b}" vti6_b fail=0 # Create route exception by exceeding link layer MTU @@ -274,28 +506,21 @@ test_pmtu_vti6_exception() { mtu "${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 ${vti6_b_addr} > /dev/null # Check that exception was created - if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" = "" ]; then - err " tunnel exceeding link layer MTU didn't create route exception" - return 1 - fi + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" + check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1 # Decrease tunnel MTU, check for PMTU decrease in route exception mtu "${ns_a}" vti6_a 3000 - - if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 3000 ]; then - err " decreasing tunnel MTU didn't decrease route exception PMTU" - fail=1 - fi + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" + check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1 # Increase tunnel MTU, check for PMTU increase in route exception mtu "${ns_a}" vti6_a 9000 - if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 9000 ]; then - err " increasing tunnel MTU didn't increase route exception PMTU" - fail=1 - fi + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" + check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1 return ${fail} } @@ -334,7 +559,7 @@ test_pmtu_vti4_link_add_mtu() { fail=0 min=68 - max=$((65528 - 20)) + max=$((65535 - 20)) # Check invalid values first for v in $((min - 1)) $((max + 1)); do ${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10 2>/dev/null @@ -442,15 +667,56 @@ test_pmtu_vti6_link_change_mtu() { return ${fail} } -trap cleanup EXIT +usage() { + echo + echo "$0 [OPTIONS] [TEST]..." + echo "If no TEST argument is given, all tests will be run." + echo + echo "Options" + echo " --trace: capture traffic to TEST_INTERFACE.pcap" + echo + echo "Available tests${tests}" + exit 1 +} exitcode=0 desc=0 IFS=" " + +tracing=0 +for arg do + if [ "${arg}" != "${arg#--*}" ]; then + opt="${arg#--}" + if [ "${opt}" = "trace" ]; then + if which tcpdump > /dev/null 2>&1; then + tracing=1 + else + echo "=== tcpdump not available, tracing disabled" + fi + else + usage + fi + else + # Check first that all requested tests are available before + # running any + command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; } + fi +done + +trap cleanup EXIT + for t in ${tests}; do [ $desc -eq 0 ] && name="${t}" && desc=1 && continue || desc=0 + run_this=1 + for arg do + [ "${arg}" != "${arg#--*}" ] && continue + [ "${arg}" = "${name}" ] && run_this=1 && break + run_this=0 + done + [ $run_this -eq 0 ] && continue + ( unset IFS eval test_${name} diff --git a/tools/testing/selftests/net/reuseport_bpf.c b/tools/testing/selftests/net/reuseport_bpf.c index cad14cd0ea92..b5277106df1f 100644 --- a/tools/testing/selftests/net/reuseport_bpf.c +++ b/tools/testing/selftests/net/reuseport_bpf.c @@ -437,14 +437,19 @@ void enable_fastopen(void) } } -static struct rlimit rlim_old, rlim_new; +static struct rlimit rlim_old; static __attribute__((constructor)) void main_ctor(void) { getrlimit(RLIMIT_MEMLOCK, &rlim_old); - rlim_new.rlim_cur = rlim_old.rlim_cur + (1UL << 20); - rlim_new.rlim_max = rlim_old.rlim_max + (1UL << 20); - setrlimit(RLIMIT_MEMLOCK, &rlim_new); + + if (rlim_old.rlim_cur != RLIM_INFINITY) { + struct rlimit rlim_new; + + rlim_new.rlim_cur = rlim_old.rlim_cur + (1UL << 20); + rlim_new.rlim_max = rlim_old.rlim_max + (1UL << 20); + setrlimit(RLIMIT_MEMLOCK, &rlim_new); + } } static __attribute__((destructor)) void main_dtor(void) diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 0d7a44fa30af..e101af52d1d6 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # # This test is for checking rtnetlink callpaths, and get as much coverage as possible. # @@ -525,18 +525,21 @@ kci_test_macsec() #------------------------------------------------------------------- kci_test_ipsec() { - srcip="14.0.0.52" - dstip="14.0.0.70" + ret=0 algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128" + srcip=192.168.123.1 + dstip=192.168.123.2 + spi=7 + + ip addr add $srcip dev $devdummy # flush to be sure there's nothing configured ip x s flush ; ip x p flush check_err $? # start the monitor in the background - tmpfile=`mktemp ipsectestXXX` - ip x m > $tmpfile & - mpid=$! + tmpfile=`mktemp /var/run/ipsectestXXX` + mpid=`(ip x m > $tmpfile & echo $!) 2>/dev/null` sleep 0.2 ipsecid="proto esp src $srcip dst $dstip spi 0x07" @@ -599,6 +602,7 @@ kci_test_ipsec() check_err $? ip x p flush check_err $? + ip addr del $srcip/32 dev $devdummy if [ $ret -ne 0 ]; then echo "FAIL: ipsec" @@ -607,6 +611,119 @@ kci_test_ipsec() echo "PASS: ipsec" } +#------------------------------------------------------------------- +# Example commands +# ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \ +# spi 0x07 mode transport reqid 0x07 replay-window 32 \ +# aead 'rfc4106(gcm(aes))' 1234567890123456dcba 128 \ +# sel src 14.0.0.52/24 dst 14.0.0.70/24 +# offload dev sim1 dir out +# ip x p add dir out src 14.0.0.52/24 dst 14.0.0.70/24 \ +# tmpl proto esp src 14.0.0.52 dst 14.0.0.70 \ +# spi 0x07 mode transport reqid 0x07 +# +#------------------------------------------------------------------- +kci_test_ipsec_offload() +{ + ret=0 + algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128" + srcip=192.168.123.3 + dstip=192.168.123.4 + dev=simx1 + sysfsd=/sys/kernel/debug/netdevsim/$dev + sysfsf=$sysfsd/ipsec + + # setup netdevsim since dummydev doesn't have offload support + modprobe netdevsim + check_err $? + if [ $ret -ne 0 ]; then + echo "FAIL: ipsec_offload can't load netdevsim" + return 1 + fi + + ip link add $dev type netdevsim + ip addr add $srcip dev $dev + ip link set $dev up + if [ ! -d $sysfsd ] ; then + echo "FAIL: ipsec_offload can't create device $dev" + return 1 + fi + if [ ! -f $sysfsf ] ; then + echo "FAIL: ipsec_offload netdevsim doesn't support IPsec offload" + return 1 + fi + + # flush to be sure there's nothing configured + ip x s flush ; ip x p flush + + # create offloaded SAs, both in and out + ip x p add dir out src $srcip/24 dst $dstip/24 \ + tmpl proto esp src $srcip dst $dstip spi 9 \ + mode transport reqid 42 + check_err $? + ip x p add dir out src $dstip/24 dst $srcip/24 \ + tmpl proto esp src $dstip dst $srcip spi 9 \ + mode transport reqid 42 + check_err $? + + ip x s add proto esp src $srcip dst $dstip spi 9 \ + mode transport reqid 42 $algo sel src $srcip/24 dst $dstip/24 \ + offload dev $dev dir out + check_err $? + ip x s add proto esp src $dstip dst $srcip spi 9 \ + mode transport reqid 42 $algo sel src $dstip/24 dst $srcip/24 \ + offload dev $dev dir in + check_err $? + if [ $ret -ne 0 ]; then + echo "FAIL: ipsec_offload can't create SA" + return 1 + fi + + # does offload show up in ip output + lines=`ip x s list | grep -c "crypto offload parameters: dev $dev dir"` + if [ $lines -ne 2 ] ; then + echo "FAIL: ipsec_offload SA offload missing from list output" + check_err 1 + fi + + # use ping to exercise the Tx path + ping -I $dev -c 3 -W 1 -i 0 $dstip >/dev/null + + # does driver have correct offload info + diff $sysfsf - << EOF +SA count=2 tx=3 +sa[0] tx ipaddr=0x00000000 00000000 00000000 00000000 +sa[0] spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1 +sa[0] key=0x34333231 38373635 32313039 36353433 +sa[1] rx ipaddr=0x00000000 00000000 00000000 037ba8c0 +sa[1] spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1 +sa[1] key=0x34333231 38373635 32313039 36353433 +EOF + if [ $? -ne 0 ] ; then + echo "FAIL: ipsec_offload incorrect driver data" + check_err 1 + fi + + # does offload get removed from driver + ip x s flush + ip x p flush + lines=`grep -c "SA count=0" $sysfsf` + if [ $lines -ne 1 ] ; then + echo "FAIL: ipsec_offload SA not removed from driver" + check_err 1 + fi + + # clean up any leftovers + ip link del $dev + rmmod netdevsim + + if [ $ret -ne 0 ]; then + echo "FAIL: ipsec_offload" + return 1 + fi + echo "PASS: ipsec_offload" +} + kci_test_gretap() { testns="testns" @@ -861,6 +978,7 @@ kci_test_rtnl() kci_test_encap kci_test_macsec kci_test_ipsec + kci_test_ipsec_offload kci_del_dummy } diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 77f762780199..e8c5dff448eb 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -402,7 +402,7 @@ int main(int argc, char *argv[]) exit(1); } - fd = socket(AF_INET6, SOCK_STREAM, 0); + fd = socket(cfg_family, SOCK_STREAM, 0); if (fd == -1) { perror("socket"); exit(1); diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c new file mode 100644 index 000000000000..fac68d710f35 --- /dev/null +++ b/tools/testing/selftests/net/tls.c @@ -0,0 +1,764 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <errno.h> +#include <error.h> +#include <fcntl.h> +#include <poll.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + +#include <linux/tls.h> +#include <linux/tcp.h> +#include <linux/socket.h> + +#include <sys/types.h> +#include <sys/sendfile.h> +#include <sys/socket.h> +#include <sys/stat.h> + +#include "../kselftest_harness.h" + +#define TLS_PAYLOAD_MAX_LEN 16384 +#define SOL_TLS 282 + +FIXTURE(tls) +{ + int fd, cfd; + bool notls; +}; + +FIXTURE_SETUP(tls) +{ + struct tls12_crypto_info_aes_gcm_128 tls12; + struct sockaddr_in addr; + socklen_t len; + int sfd, ret; + + self->notls = false; + len = sizeof(addr); + + memset(&tls12, 0, sizeof(tls12)); + tls12.info.version = TLS_1_2_VERSION; + tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128; + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + self->fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ret = bind(sfd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + ret = listen(sfd, 10); + ASSERT_EQ(ret, 0); + + ret = getsockname(sfd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = connect(self->fd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (ret != 0) { + self->notls = true; + printf("Failure setting TCP_ULP, testing without tls\n"); + } + + if (!self->notls) { + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, + sizeof(tls12)); + ASSERT_EQ(ret, 0); + } + + self->cfd = accept(sfd, &addr, &len); + ASSERT_GE(self->cfd, 0); + + if (!self->notls) { + ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", + sizeof("tls")); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, + sizeof(tls12)); + ASSERT_EQ(ret, 0); + } + + close(sfd); +} + +FIXTURE_TEARDOWN(tls) +{ + close(self->fd); + close(self->cfd); +} + +TEST_F(tls, sendfile) +{ + int filefd = open("/proc/self/exe", O_RDONLY); + struct stat st; + + EXPECT_GE(filefd, 0); + fstat(filefd, &st); + EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0); +} + +TEST_F(tls, send_then_sendfile) +{ + int filefd = open("/proc/self/exe", O_RDONLY); + char const *test_str = "test_send"; + int to_send = strlen(test_str) + 1; + char recv_buf[10]; + struct stat st; + char *buf; + + EXPECT_GE(filefd, 0); + fstat(filefd, &st); + buf = (char *)malloc(st.st_size); + + EXPECT_EQ(send(self->fd, test_str, to_send, 0), to_send); + EXPECT_EQ(recv(self->cfd, recv_buf, to_send, MSG_WAITALL), to_send); + EXPECT_EQ(memcmp(test_str, recv_buf, to_send), 0); + + EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0); + EXPECT_EQ(recv(self->cfd, buf, st.st_size, MSG_WAITALL), st.st_size); +} + +TEST_F(tls, recv_max) +{ + unsigned int send_len = TLS_PAYLOAD_MAX_LEN; + char recv_mem[TLS_PAYLOAD_MAX_LEN]; + char buf[TLS_PAYLOAD_MAX_LEN]; + + EXPECT_GE(send(self->fd, buf, send_len, 0), 0); + EXPECT_NE(recv(self->cfd, recv_mem, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, recv_mem, send_len), 0); +} + +TEST_F(tls, recv_small) +{ + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + + send_len = strlen(test_str) + 1; + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); +} + +TEST_F(tls, msg_more) +{ + char const *test_str = "test_read"; + int send_len = 10; + char buf[10 * 2]; + + EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1); + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_WAITALL), + send_len * 2); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); +} + +TEST_F(tls, sendmsg_single) +{ + struct msghdr msg; + + char const *test_str = "test_sendmsg"; + size_t send_len = 13; + struct iovec vec; + char buf[13]; + + vec.iov_base = (char *)test_str; + vec.iov_len = send_len; + memset(&msg, 0, sizeof(struct msghdr)); + msg.msg_iov = &vec; + msg.msg_iovlen = 1; + EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); +} + +TEST_F(tls, sendmsg_large) +{ + void *mem = malloc(16384); + size_t send_len = 16384; + size_t sends = 128; + struct msghdr msg; + size_t recvs = 0; + size_t sent = 0; + + memset(&msg, 0, sizeof(struct msghdr)); + while (sent++ < sends) { + struct iovec vec = { (void *)mem, send_len }; + + msg.msg_iov = &vec; + msg.msg_iovlen = 1; + EXPECT_EQ(sendmsg(self->cfd, &msg, 0), send_len); + } + + while (recvs++ < sends) + EXPECT_NE(recv(self->fd, mem, send_len, 0), -1); + + free(mem); +} + +TEST_F(tls, sendmsg_multiple) +{ + char const *test_str = "test_sendmsg_multiple"; + struct iovec vec[5]; + char *test_strs[5]; + struct msghdr msg; + int total_len = 0; + int len_cmp = 0; + int iov_len = 5; + char *buf; + int i; + + memset(&msg, 0, sizeof(struct msghdr)); + for (i = 0; i < iov_len; i++) { + test_strs[i] = (char *)malloc(strlen(test_str) + 1); + snprintf(test_strs[i], strlen(test_str) + 1, "%s", test_str); + vec[i].iov_base = (void *)test_strs[i]; + vec[i].iov_len = strlen(test_strs[i]) + 1; + total_len += vec[i].iov_len; + } + msg.msg_iov = vec; + msg.msg_iovlen = iov_len; + + EXPECT_EQ(sendmsg(self->cfd, &msg, 0), total_len); + buf = malloc(total_len); + EXPECT_NE(recv(self->fd, buf, total_len, 0), -1); + for (i = 0; i < iov_len; i++) { + EXPECT_EQ(memcmp(test_strs[i], buf + len_cmp, + strlen(test_strs[i])), + 0); + len_cmp += strlen(buf + len_cmp) + 1; + } + for (i = 0; i < iov_len; i++) + free(test_strs[i]); + free(buf); +} + +TEST_F(tls, sendmsg_multiple_stress) +{ + char const *test_str = "abcdefghijklmno"; + struct iovec vec[1024]; + char *test_strs[1024]; + int iov_len = 1024; + int total_len = 0; + char buf[1 << 14]; + struct msghdr msg; + int len_cmp = 0; + int i; + + memset(&msg, 0, sizeof(struct msghdr)); + for (i = 0; i < iov_len; i++) { + test_strs[i] = (char *)malloc(strlen(test_str) + 1); + snprintf(test_strs[i], strlen(test_str) + 1, "%s", test_str); + vec[i].iov_base = (void *)test_strs[i]; + vec[i].iov_len = strlen(test_strs[i]) + 1; + total_len += vec[i].iov_len; + } + msg.msg_iov = vec; + msg.msg_iovlen = iov_len; + + EXPECT_EQ(sendmsg(self->fd, &msg, 0), total_len); + EXPECT_NE(recv(self->cfd, buf, total_len, 0), -1); + + for (i = 0; i < iov_len; i++) + len_cmp += strlen(buf + len_cmp) + 1; + + for (i = 0; i < iov_len; i++) + free(test_strs[i]); +} + +TEST_F(tls, splice_from_pipe) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_GE(write(p[1], mem_send, send_len), 0); + EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), 0); + EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + +TEST_F(tls, splice_from_pipe2) +{ + int send_len = 16000; + char mem_send[16000]; + char mem_recv[16000]; + int p2[2]; + int p[2]; + + ASSERT_GE(pipe(p), 0); + ASSERT_GE(pipe(p2), 0); + EXPECT_GE(write(p[1], mem_send, 8000), 0); + EXPECT_GE(splice(p[0], NULL, self->fd, NULL, 8000, 0), 0); + EXPECT_GE(write(p2[1], mem_send + 8000, 8000), 0); + EXPECT_GE(splice(p2[0], NULL, self->fd, NULL, 8000, 0), 0); + EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + +TEST_F(tls, send_and_splice) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + char const *test_str = "test_read"; + int send_len2 = 10; + char buf[10]; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(send(self->fd, test_str, send_len2, 0), send_len2); + EXPECT_EQ(recv(self->cfd, buf, send_len2, MSG_WAITALL), send_len2); + EXPECT_EQ(memcmp(test_str, buf, send_len2), 0); + + EXPECT_GE(write(p[1], mem_send, send_len), send_len); + EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), send_len); + + EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + +TEST_F(tls, splice_to_pipe) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_GE(send(self->fd, mem_send, send_len, 0), 0); + EXPECT_GE(splice(self->cfd, NULL, p[1], NULL, send_len, 0), 0); + EXPECT_GE(read(p[0], mem_recv, send_len), 0); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + +TEST_F(tls, recvmsg_single) +{ + char const *test_str = "test_recvmsg_single"; + int send_len = strlen(test_str) + 1; + char buf[20]; + struct msghdr hdr; + struct iovec vec; + + memset(&hdr, 0, sizeof(hdr)); + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + vec.iov_base = (char *)buf; + vec.iov_len = send_len; + hdr.msg_iovlen = 1; + hdr.msg_iov = &vec; + EXPECT_NE(recvmsg(self->cfd, &hdr, 0), -1); + EXPECT_EQ(memcmp(test_str, buf, send_len), 0); +} + +TEST_F(tls, recvmsg_single_max) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char send_mem[TLS_PAYLOAD_MAX_LEN]; + char recv_mem[TLS_PAYLOAD_MAX_LEN]; + struct iovec vec; + struct msghdr hdr; + + EXPECT_EQ(send(self->fd, send_mem, send_len, 0), send_len); + vec.iov_base = (char *)recv_mem; + vec.iov_len = TLS_PAYLOAD_MAX_LEN; + + hdr.msg_iovlen = 1; + hdr.msg_iov = &vec; + EXPECT_NE(recvmsg(self->cfd, &hdr, 0), -1); + EXPECT_EQ(memcmp(send_mem, recv_mem, send_len), 0); +} + +TEST_F(tls, recvmsg_multiple) +{ + unsigned int msg_iovlen = 1024; + unsigned int len_compared = 0; + struct iovec vec[1024]; + char *iov_base[1024]; + unsigned int iov_len = 16; + int send_len = 1 << 14; + char buf[1 << 14]; + struct msghdr hdr; + int i; + + EXPECT_EQ(send(self->fd, buf, send_len, 0), send_len); + for (i = 0; i < msg_iovlen; i++) { + iov_base[i] = (char *)malloc(iov_len); + vec[i].iov_base = iov_base[i]; + vec[i].iov_len = iov_len; + } + + hdr.msg_iovlen = msg_iovlen; + hdr.msg_iov = vec; + EXPECT_NE(recvmsg(self->cfd, &hdr, 0), -1); + for (i = 0; i < msg_iovlen; i++) + len_compared += iov_len; + + for (i = 0; i < msg_iovlen; i++) + free(iov_base[i]); +} + +TEST_F(tls, single_send_multiple_recv) +{ + unsigned int total_len = TLS_PAYLOAD_MAX_LEN * 2; + unsigned int send_len = TLS_PAYLOAD_MAX_LEN; + char send_mem[TLS_PAYLOAD_MAX_LEN * 2]; + char recv_mem[TLS_PAYLOAD_MAX_LEN * 2]; + + EXPECT_GE(send(self->fd, send_mem, total_len, 0), 0); + memset(recv_mem, 0, total_len); + + EXPECT_NE(recv(self->cfd, recv_mem, send_len, 0), -1); + EXPECT_NE(recv(self->cfd, recv_mem + send_len, send_len, 0), -1); + EXPECT_EQ(memcmp(send_mem, recv_mem, total_len), 0); +} + +TEST_F(tls, multiple_send_single_recv) +{ + unsigned int total_len = 2 * 10; + unsigned int send_len = 10; + char recv_mem[2 * 10]; + char send_mem[10]; + + EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0); + EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0); + memset(recv_mem, 0, total_len); + EXPECT_EQ(recv(self->cfd, recv_mem, total_len, MSG_WAITALL), total_len); + + EXPECT_EQ(memcmp(send_mem, recv_mem, send_len), 0); + EXPECT_EQ(memcmp(send_mem, recv_mem + send_len, send_len), 0); +} + +TEST_F(tls, recv_partial) +{ + char const *test_str = "test_read_partial"; + char const *test_str_first = "test_read"; + char const *test_str_second = "_partial"; + int send_len = strlen(test_str) + 1; + char recv_mem[18]; + + memset(recv_mem, 0, sizeof(recv_mem)); + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_first), 0), -1); + EXPECT_EQ(memcmp(test_str_first, recv_mem, strlen(test_str_first)), 0); + memset(recv_mem, 0, sizeof(recv_mem)); + EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_second), 0), -1); + EXPECT_EQ(memcmp(test_str_second, recv_mem, strlen(test_str_second)), + 0); +} + +TEST_F(tls, recv_nonblock) +{ + char buf[4096]; + bool err; + + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_DONTWAIT), -1); + err = (errno == EAGAIN || errno == EWOULDBLOCK); + EXPECT_EQ(err, true); +} + +TEST_F(tls, recv_peek) +{ + char const *test_str = "test_read_peek"; + int send_len = strlen(test_str) + 1; + char buf[15]; + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(self->cfd, buf, send_len, MSG_PEEK), -1); + EXPECT_EQ(memcmp(test_str, buf, send_len), 0); + memset(buf, 0, sizeof(buf)); + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(test_str, buf, send_len), 0); +} + +TEST_F(tls, recv_peek_multiple) +{ + char const *test_str = "test_read_peek"; + int send_len = strlen(test_str) + 1; + unsigned int num_peeks = 100; + char buf[15]; + int i; + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + for (i = 0; i < num_peeks; i++) { + EXPECT_NE(recv(self->cfd, buf, send_len, MSG_PEEK), -1); + EXPECT_EQ(memcmp(test_str, buf, send_len), 0); + memset(buf, 0, sizeof(buf)); + } + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(test_str, buf, send_len), 0); +} + +TEST_F(tls, recv_peek_multiple_records) +{ + char const *test_str = "test_read_peek_mult_recs"; + char const *test_str_first = "test_read_peek"; + char const *test_str_second = "_mult_recs"; + int len; + char buf[64]; + + len = strlen(test_str_first); + EXPECT_EQ(send(self->fd, test_str_first, len, 0), len); + + len = strlen(test_str_second) + 1; + EXPECT_EQ(send(self->fd, test_str_second, len, 0), len); + + len = strlen(test_str_first); + memset(buf, 0, len); + EXPECT_EQ(recv(self->cfd, buf, len, MSG_PEEK | MSG_WAITALL), len); + + /* MSG_PEEK can only peek into the current record. */ + len = strlen(test_str_first); + EXPECT_EQ(memcmp(test_str_first, buf, len), 0); + + len = strlen(test_str) + 1; + memset(buf, 0, len); + EXPECT_EQ(recv(self->cfd, buf, len, MSG_WAITALL), len); + + /* Non-MSG_PEEK will advance strparser (and therefore record) + * however. + */ + len = strlen(test_str) + 1; + EXPECT_EQ(memcmp(test_str, buf, len), 0); + + /* MSG_MORE will hold current record open, so later MSG_PEEK + * will see everything. + */ + len = strlen(test_str_first); + EXPECT_EQ(send(self->fd, test_str_first, len, MSG_MORE), len); + + len = strlen(test_str_second) + 1; + EXPECT_EQ(send(self->fd, test_str_second, len, 0), len); + + len = strlen(test_str) + 1; + memset(buf, 0, len); + EXPECT_EQ(recv(self->cfd, buf, len, MSG_PEEK | MSG_WAITALL), len); + + len = strlen(test_str) + 1; + EXPECT_EQ(memcmp(test_str, buf, len), 0); +} + +TEST_F(tls, recv_peek_large_buf_mult_recs) +{ + char const *test_str = "test_read_peek_mult_recs"; + char const *test_str_first = "test_read_peek"; + char const *test_str_second = "_mult_recs"; + int len; + char buf[64]; + + len = strlen(test_str_first); + EXPECT_EQ(send(self->fd, test_str_first, len, 0), len); + + len = strlen(test_str_second) + 1; + EXPECT_EQ(send(self->fd, test_str_second, len, 0), len); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1); + + len = strlen(test_str) + 1; + EXPECT_EQ(memcmp(test_str, buf, len), 0); +} + + +TEST_F(tls, pollin) +{ + char const *test_str = "test_poll"; + struct pollfd fd = { 0, 0, 0 }; + char buf[10]; + int send_len = 10; + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + fd.fd = self->cfd; + fd.events = POLLIN; + + EXPECT_EQ(poll(&fd, 1, 20), 1); + EXPECT_EQ(fd.revents & POLLIN, 1); + EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len); + /* Test timing out */ + EXPECT_EQ(poll(&fd, 1, 20), 0); +} + +TEST_F(tls, poll_wait) +{ + char const *test_str = "test_poll_wait"; + int send_len = strlen(test_str) + 1; + struct pollfd fd = { 0, 0, 0 }; + char recv_mem[15]; + + fd.fd = self->cfd; + fd.events = POLLIN; + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + /* Set timeout to inf. secs */ + EXPECT_EQ(poll(&fd, 1, -1), 1); + EXPECT_EQ(fd.revents & POLLIN, 1); + EXPECT_EQ(recv(self->cfd, recv_mem, send_len, MSG_WAITALL), send_len); +} + +TEST_F(tls, blocking) +{ + size_t data = 100000; + int res = fork(); + + EXPECT_NE(res, -1); + + if (res) { + /* parent */ + size_t left = data; + char buf[16384]; + int status; + int pid2; + + while (left) { + int res = send(self->fd, buf, + left > 16384 ? 16384 : left, 0); + + EXPECT_GE(res, 0); + left -= res; + } + + pid2 = wait(&status); + EXPECT_EQ(status, 0); + EXPECT_EQ(res, pid2); + } else { + /* child */ + size_t left = data; + char buf[16384]; + + while (left) { + int res = recv(self->cfd, buf, + left > 16384 ? 16384 : left, 0); + + EXPECT_GE(res, 0); + left -= res; + } + } +} + +TEST_F(tls, nonblocking) +{ + size_t data = 100000; + int sendbuf = 100; + int flags; + int res; + + flags = fcntl(self->fd, F_GETFL, 0); + fcntl(self->fd, F_SETFL, flags | O_NONBLOCK); + fcntl(self->cfd, F_SETFL, flags | O_NONBLOCK); + + /* Ensure nonblocking behavior by imposing a small send + * buffer. + */ + EXPECT_EQ(setsockopt(self->fd, SOL_SOCKET, SO_SNDBUF, + &sendbuf, sizeof(sendbuf)), 0); + + res = fork(); + EXPECT_NE(res, -1); + + if (res) { + /* parent */ + bool eagain = false; + size_t left = data; + char buf[16384]; + int status; + int pid2; + + while (left) { + int res = send(self->fd, buf, + left > 16384 ? 16384 : left, 0); + + if (res == -1 && errno == EAGAIN) { + eagain = true; + usleep(10000); + continue; + } + EXPECT_GE(res, 0); + left -= res; + } + + EXPECT_TRUE(eagain); + pid2 = wait(&status); + + EXPECT_EQ(status, 0); + EXPECT_EQ(res, pid2); + } else { + /* child */ + bool eagain = false; + size_t left = data; + char buf[16384]; + + while (left) { + int res = recv(self->cfd, buf, + left > 16384 ? 16384 : left, 0); + + if (res == -1 && errno == EAGAIN) { + eagain = true; + usleep(10000); + continue; + } + EXPECT_GE(res, 0); + left -= res; + } + EXPECT_TRUE(eagain); + } +} + +TEST_F(tls, control_msg) +{ + if (self->notls) + return; + + char cbuf[CMSG_SPACE(sizeof(char))]; + char const *test_str = "test_read"; + int cmsg_len = sizeof(char); + char record_type = 100; + struct cmsghdr *cmsg; + struct msghdr msg; + int send_len = 10; + struct iovec vec; + char buf[10]; + + vec.iov_base = (char *)test_str; + vec.iov_len = 10; + memset(&msg, 0, sizeof(struct msghdr)); + msg.msg_iov = &vec; + msg.msg_iovlen = 1; + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_TLS; + /* test sending non-record types. */ + cmsg->cmsg_type = TLS_SET_RECORD_TYPE; + cmsg->cmsg_len = CMSG_LEN(cmsg_len); + *CMSG_DATA(cmsg) = record_type; + msg.msg_controllen = cmsg->cmsg_len; + + EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len); + /* Should fail because we didn't provide a control message */ + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); + + vec.iov_base = buf; + EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len); + cmsg = CMSG_FIRSTHDR(&msg); + EXPECT_NE(cmsg, NULL); + EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); + EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); + record_type = *((unsigned char *)CMSG_DATA(cmsg)); + EXPECT_EQ(record_type, 100); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh index 850767befa47..99e537ab5ad9 100755 --- a/tools/testing/selftests/net/udpgso_bench.sh +++ b/tools/testing/selftests/net/udpgso_bench.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # # Run a series of udpgso benchmarks |
