diff options
Diffstat (limited to 'tools')
19 files changed, 3319 insertions, 26 deletions
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index b001c602414b..b45a8f77ee24 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -32,6 +32,7 @@ TARGETS += memory-hotplug TARGETS += mount TARGETS += mqueue TARGETS += net +TARGETS += net/mptcp TARGETS += netfilter TARGETS += networking/timestamping TARGETS += nsfs diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh index a5937069ac16..faa51012cdac 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh @@ -1,29 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -humanize() -{ - local speed=$1; shift - - for unit in bps Kbps Mbps Gbps; do - if (($(echo "$speed < 1024" | bc))); then - break - fi - - speed=$(echo "scale=1; $speed / 1024" | bc) - done - - echo "$speed${unit}" -} - -rate() -{ - local t0=$1; shift - local t1=$1; shift - local interval=$1; shift - - echo $((8 * (t1 - t0) / interval)) -} - check_rate() { local rate=$1; shift diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh new file mode 100755 index 000000000000..c6ce0b448bf3 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source qos_lib.sh +bail_on_lldpad + +lib_dir=$(dirname $0)/../../../net/forwarding +TCFLAGS=skip_sw +source $lib_dir/sch_tbf_ets.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh new file mode 100755 index 000000000000..8d245f331619 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source qos_lib.sh +bail_on_lldpad + +lib_dir=$(dirname $0)/../../../net/forwarding +TCFLAGS=skip_sw +source $lib_dir/sch_tbf_prio.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh new file mode 100755 index 000000000000..013886061f15 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source qos_lib.sh +bail_on_lldpad + +lib_dir=$(dirname $0)/../../../net/forwarding +TCFLAGS=skip_sw +source $lib_dir/sch_tbf_root.sh diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 8dc5fac98cbc..2f5da414aaa7 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -248,6 +248,24 @@ busywait() done } +until_counter_is() +{ + local value=$1; shift + local current=$("$@") + + echo $((current)) + ((current >= value)) +} + +busywait_for_counter() +{ + local timeout=$1; shift + local delta=$1; shift + + local base=$("$@") + busywait "$timeout" until_counter_is $((base + delta)) "$@" +} + setup_wait_dev() { local dev=$1; shift @@ -575,9 +593,10 @@ tc_rule_stats_get() local dev=$1; shift local pref=$1; shift local dir=$1; shift + local selector=${1:-.packets}; shift tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \ - | jq '.[1].options.actions[].stats.packets' + | jq ".[1].options.actions[].stats$selector" } ethtool_stats_get() @@ -588,6 +607,30 @@ ethtool_stats_get() ethtool -S $dev | grep "^ *$stat:" | head -n 1 | cut -d: -f2 } +humanize() +{ + local speed=$1; shift + + for unit in bps Kbps Mbps Gbps; do + if (($(echo "$speed < 1024" | bc))); then + break + fi + + speed=$(echo "scale=1; $speed / 1024" | bc) + done + + echo "$speed${unit}" +} + +rate() +{ + local t0=$1; shift + local t1=$1; shift + local interval=$1; shift + + echo $((8 * (t1 - t0) / interval)) +} + mac_get() { local if_name=$1 diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_core.sh b/tools/testing/selftests/net/forwarding/sch_tbf_core.sh new file mode 100644 index 000000000000..d1f26cb7cd73 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_tbf_core.sh @@ -0,0 +1,233 @@ +# SPDX-License-Identifier: GPL-2.0 + +# This test sends a stream of traffic from H1 through a switch, to H2. On the +# egress port from the switch ($swp2), a shaper is installed. The test verifies +# that the rates on the port match the configured shaper. +# +# In order to test per-class shaping, $swp2 actually contains TBF under PRIO or +# ETS, with two different configurations. Traffic is prioritized using 802.1p. +# +# +-------------------------------------------+ +# | H1 | +# | + $h1.10 $h1.11 + | +# | | 192.0.2.1/28 192.0.2.17/28 | | +# | | | | +# | \______________ _____________/ | +# | \ / | +# | + $h1 | +# +---------------------|---------------------+ +# | +# +---------------------|---------------------+ +# | SW + $swp1 | +# | _______________/ \_______________ | +# | / \ | +# | +-|--------------+ +--------------|-+ | +# | | + $swp1.10 | | $swp1.11 + | | +# | | | | | | +# | | BR10 | | BR11 | | +# | | | | | | +# | | + $swp2.10 | | $swp2.11 + | | +# | +-|--------------+ +--------------|-+ | +# | \_______________ ______________/ | +# | \ / | +# | + $swp2 | +# +---------------------|---------------------+ +# | +# +---------------------|---------------------+ +# | H2 + $h2 | +# | ______________/ \______________ | +# | / \ | +# | | | | +# | + $h2.10 $h2.11 + | +# | 192.0.2.2/28 192.0.2.18/28 | +# +-------------------------------------------+ + +NUM_NETIFS=4 +CHECK_TC="yes" +source $lib_dir/lib.sh + +ipaddr() +{ + local host=$1; shift + local vlan=$1; shift + + echo 192.0.2.$((16 * (vlan - 10) + host)) +} + +host_create() +{ + local dev=$1; shift + local host=$1; shift + + simple_if_init $dev + mtu_set $dev 10000 + + vlan_create $dev 10 v$dev $(ipaddr $host 10)/28 + ip link set dev $dev.10 type vlan egress 0:0 + + vlan_create $dev 11 v$dev $(ipaddr $host 11)/28 + ip link set dev $dev.11 type vlan egress 0:1 +} + +host_destroy() +{ + local dev=$1; shift + + vlan_destroy $dev 11 + vlan_destroy $dev 10 + mtu_restore $dev + simple_if_fini $dev +} + +h1_create() +{ + host_create $h1 1 +} + +h1_destroy() +{ + host_destroy $h1 +} + +h2_create() +{ + host_create $h2 2 + + tc qdisc add dev $h2 clsact + tc filter add dev $h2 ingress pref 1010 prot 802.1q \ + flower $TCFLAGS vlan_id 10 action pass + tc filter add dev $h2 ingress pref 1011 prot 802.1q \ + flower $TCFLAGS vlan_id 11 action pass +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + host_destroy $h2 +} + +switch_create() +{ + local intf + local vlan + + ip link add dev br10 type bridge + ip link add dev br11 type bridge + + for intf in $swp1 $swp2; do + ip link set dev $intf up + mtu_set $intf 10000 + + for vlan in 10 11; do + vlan_create $intf $vlan + ip link set dev $intf.$vlan master br$vlan + ip link set dev $intf.$vlan up + done + done + + for vlan in 10 11; do + ip link set dev $swp1.$vlan type vlan ingress 0:0 1:1 + done + + ip link set dev br10 up + ip link set dev br11 up +} + +switch_destroy() +{ + local intf + local vlan + + # A test may have been interrupted mid-run, with Qdisc installed. Delete + # it here. + tc qdisc del dev $swp2 root 2>/dev/null + + ip link set dev br11 down + ip link set dev br10 down + + for intf in $swp2 $swp1; do + for vlan in 11 10; do + ip link set dev $intf.$vlan down + ip link set dev $intf.$vlan nomaster + vlan_destroy $intf $vlan + done + + mtu_restore $intf + ip link set dev $intf down + done + + ip link del dev br11 + ip link del dev br10 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + swp4=${NETIFS[p7]} + swp5=${NETIFS[p8]} + + h2_mac=$(mac_get $h2) + + vrf_prepare + + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1.10 $(ipaddr 2 10) " vlan 10" + ping_test $h1.11 $(ipaddr 2 11) " vlan 11" +} + +tbf_get_counter() +{ + local vlan=$1; shift + + tc_rule_stats_get $h2 10$vlan ingress .bytes +} + +do_tbf_test() +{ + local vlan=$1; shift + local mbit=$1; shift + + start_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 2 $vlan) $h2_mac + sleep 5 # Wait for the burst to dwindle + + local t2=$(busywait_for_counter 1000 +1 tbf_get_counter $vlan) + sleep 10 + local t3=$(tbf_get_counter $vlan) + stop_traffic + + RET=0 + + # Note: TBF uses 10^6 Mbits, not 2^20 ones. + local er=$((mbit * 1000 * 1000)) + local nr=$(rate $t2 $t3 10) + local nr_pct=$((100 * (nr - er) / er)) + ((-5 <= nr_pct && nr_pct <= 5)) + check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-5%." + + log_test "TC $((vlan - 10)): TBF rate ${mbit}Mbit" +} diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_ets.sh b/tools/testing/selftests/net/forwarding/sch_tbf_ets.sh new file mode 100755 index 000000000000..84fb6cab88e4 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_tbf_ets.sh @@ -0,0 +1,6 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +QDISC="ets strict" +: ${lib_dir:=.} +source $lib_dir/sch_tbf_etsprio.sh diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh new file mode 100644 index 000000000000..8bd85da1905a --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh @@ -0,0 +1,39 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + ping_ipv4 + tbf_test +" +source $lib_dir/sch_tbf_core.sh + +tbf_test_one() +{ + local bs=$1; shift + + tc qdisc replace dev $swp2 parent 10:3 handle 103: tbf \ + rate 400Mbit burst $bs limit 1M + tc qdisc replace dev $swp2 parent 10:2 handle 102: tbf \ + rate 800Mbit burst $bs limit 1M + + do_tbf_test 10 400 $bs + do_tbf_test 11 800 $bs +} + +tbf_test() +{ + # This test is used for both ETS and PRIO. Even though we only need two + # bands, PRIO demands a minimum of three. + tc qdisc add dev $swp2 root handle 10: $QDISC 3 priomap 2 1 0 + tbf_test_one 128K + tc qdisc del dev $swp2 root +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_prio.sh b/tools/testing/selftests/net/forwarding/sch_tbf_prio.sh new file mode 100755 index 000000000000..9c8cb1cb9ba4 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_tbf_prio.sh @@ -0,0 +1,6 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +QDISC="prio bands" +: ${lib_dir:=.} +source $lib_dir/sch_tbf_etsprio.sh diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_root.sh b/tools/testing/selftests/net/forwarding/sch_tbf_root.sh new file mode 100755 index 000000000000..72aa21ba88c7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_tbf_root.sh @@ -0,0 +1,33 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + ping_ipv4 + tbf_test +" +: ${lib_dir:=.} +source $lib_dir/sch_tbf_core.sh + +tbf_test_one() +{ + local bs=$1; shift + + tc qdisc replace dev $swp2 root handle 108: tbf \ + rate 400Mbit burst $bs limit 1M + do_tbf_test 10 400 $bs +} + +tbf_test() +{ + tbf_test_one 128K + tc qdisc del dev $swp2 root +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore new file mode 100644 index 000000000000..d72f07642738 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/.gitignore @@ -0,0 +1,2 @@ +mptcp_connect +*.pcap diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile new file mode 100644 index 000000000000..93de52016dde --- /dev/null +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0 + +top_srcdir = ../../../../.. + +CFLAGS = -Wall -Wl,--no-as-needed -O2 -g + +TEST_PROGS := mptcp_connect.sh + +TEST_GEN_FILES = mptcp_connect + +EXTRA_CLEAN := *.pcap + +include ../../lib.mk diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config new file mode 100644 index 000000000000..2499824d9e1c --- /dev/null +++ b/tools/testing/selftests/net/mptcp/config @@ -0,0 +1,4 @@ +CONFIG_MPTCP=y +CONFIG_MPTCP_IPV6=y +CONFIG_VETH=y +CONFIG_NET_SCH_NETEM=m diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c new file mode 100644 index 000000000000..a3dccd816ae4 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -0,0 +1,832 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <errno.h> +#include <limits.h> +#include <fcntl.h> +#include <string.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <strings.h> +#include <unistd.h> + +#include <sys/poll.h> +#include <sys/sendfile.h> +#include <sys/stat.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <sys/mman.h> + +#include <netdb.h> +#include <netinet/in.h> + +#include <linux/tcp.h> + +extern int optind; + +#ifndef IPPROTO_MPTCP +#define IPPROTO_MPTCP 262 +#endif +#ifndef TCP_ULP +#define TCP_ULP 31 +#endif + +static bool listen_mode; +static int poll_timeout; + +enum cfg_mode { + CFG_MODE_POLL, + CFG_MODE_MMAP, + CFG_MODE_SENDFILE, +}; + +static enum cfg_mode cfg_mode = CFG_MODE_POLL; +static const char *cfg_host; +static const char *cfg_port = "12000"; +static int cfg_sock_proto = IPPROTO_MPTCP; +static bool tcpulp_audit; +static int pf = AF_INET; +static int cfg_sndbuf; + +static void die_usage(void) +{ + fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] -m mode]" + "[ -l ] [ -t timeout ] connect_address\n"); + exit(1); +} + +static const char *getxinfo_strerr(int err) +{ + if (err == EAI_SYSTEM) + return strerror(errno); + + return gai_strerror(err); +} + +static void xgetnameinfo(const struct sockaddr *addr, socklen_t addrlen, + char *host, socklen_t hostlen, + char *serv, socklen_t servlen) +{ + int flags = NI_NUMERICHOST | NI_NUMERICSERV; + int err = getnameinfo(addr, addrlen, host, hostlen, serv, servlen, + flags); + + if (err) { + const char *errstr = getxinfo_strerr(err); + + fprintf(stderr, "Fatal: getnameinfo: %s\n", errstr); + exit(1); + } +} + +static void xgetaddrinfo(const char *node, const char *service, + const struct addrinfo *hints, + struct addrinfo **res) +{ + int err = getaddrinfo(node, service, hints, res); + + if (err) { + const char *errstr = getxinfo_strerr(err); + + fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n", + node ? node : "", service ? service : "", errstr); + exit(1); + } +} + +static void set_sndbuf(int fd, unsigned int size) +{ + int err; + + err = setsockopt(fd, SOL_SOCKET, SO_SNDBUF, &size, sizeof(size)); + if (err) { + perror("set SO_SNDBUF"); + exit(1); + } +} + +static int sock_listen_mptcp(const char * const listenaddr, + const char * const port) +{ + int sock; + struct addrinfo hints = { + .ai_protocol = IPPROTO_TCP, + .ai_socktype = SOCK_STREAM, + .ai_flags = AI_PASSIVE | AI_NUMERICHOST + }; + + hints.ai_family = pf; + + struct addrinfo *a, *addr; + int one = 1; + + xgetaddrinfo(listenaddr, port, &hints, &addr); + hints.ai_family = pf; + + for (a = addr; a; a = a->ai_next) { + sock = socket(a->ai_family, a->ai_socktype, cfg_sock_proto); + if (sock < 0) + continue; + + if (-1 == setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &one, + sizeof(one))) + perror("setsockopt"); + + if (bind(sock, a->ai_addr, a->ai_addrlen) == 0) + break; /* success */ + + perror("bind"); + close(sock); + sock = -1; + } + + freeaddrinfo(addr); + + if (sock < 0) { + fprintf(stderr, "Could not create listen socket\n"); + return sock; + } + + if (listen(sock, 20)) { + perror("listen"); + close(sock); + return -1; + } + + return sock; +} + +static bool sock_test_tcpulp(const char * const remoteaddr, + const char * const port) +{ + struct addrinfo hints = { + .ai_protocol = IPPROTO_TCP, + .ai_socktype = SOCK_STREAM, + }; + struct addrinfo *a, *addr; + int sock = -1, ret = 0; + bool test_pass = false; + + hints.ai_family = AF_INET; + + xgetaddrinfo(remoteaddr, port, &hints, &addr); + for (a = addr; a; a = a->ai_next) { + sock = socket(a->ai_family, a->ai_socktype, IPPROTO_TCP); + if (sock < 0) { + perror("socket"); + continue; + } + ret = setsockopt(sock, IPPROTO_TCP, TCP_ULP, "mptcp", + sizeof("mptcp")); + if (ret == -1 && errno == EOPNOTSUPP) + test_pass = true; + close(sock); + + if (test_pass) + break; + if (!ret) + fprintf(stderr, + "setsockopt(TCP_ULP) returned 0\n"); + else + perror("setsockopt(TCP_ULP)"); + } + return test_pass; +} + +static int sock_connect_mptcp(const char * const remoteaddr, + const char * const port, int proto) +{ + struct addrinfo hints = { + .ai_protocol = IPPROTO_TCP, + .ai_socktype = SOCK_STREAM, + }; + struct addrinfo *a, *addr; + int sock = -1; + + hints.ai_family = pf; + + xgetaddrinfo(remoteaddr, port, &hints, &addr); + for (a = addr; a; a = a->ai_next) { + sock = socket(a->ai_family, a->ai_socktype, proto); + if (sock < 0) { + perror("socket"); + continue; + } + + if (connect(sock, a->ai_addr, a->ai_addrlen) == 0) + break; /* success */ + + perror("connect()"); + close(sock); + sock = -1; + } + + freeaddrinfo(addr); + return sock; +} + +static size_t do_rnd_write(const int fd, char *buf, const size_t len) +{ + unsigned int do_w; + ssize_t bw; + + do_w = rand() & 0xffff; + if (do_w == 0 || do_w > len) + do_w = len; + + bw = write(fd, buf, do_w); + if (bw < 0) + perror("write"); + + return bw; +} + +static size_t do_write(const int fd, char *buf, const size_t len) +{ + size_t offset = 0; + + while (offset < len) { + size_t written; + ssize_t bw; + + bw = write(fd, buf + offset, len - offset); + if (bw < 0) { + perror("write"); + return 0; + } + + written = (size_t)bw; + offset += written; + } + + return offset; +} + +static ssize_t do_rnd_read(const int fd, char *buf, const size_t len) +{ + size_t cap = rand(); + + cap &= 0xffff; + + if (cap == 0) + cap = 1; + else if (cap > len) + cap = len; + + return read(fd, buf, cap); +} + +static void set_nonblock(int fd) +{ + int flags = fcntl(fd, F_GETFL); + + if (flags == -1) + return; + + fcntl(fd, F_SETFL, flags | O_NONBLOCK); +} + +static int copyfd_io_poll(int infd, int peerfd, int outfd) +{ + struct pollfd fds = { + .fd = peerfd, + .events = POLLIN | POLLOUT, + }; + unsigned int woff = 0, wlen = 0; + char wbuf[8192]; + + set_nonblock(peerfd); + + for (;;) { + char rbuf[8192]; + ssize_t len; + + if (fds.events == 0) + break; + + switch (poll(&fds, 1, poll_timeout)) { + case -1: + if (errno == EINTR) + continue; + perror("poll"); + return 1; + case 0: + fprintf(stderr, "%s: poll timed out (events: " + "POLLIN %u, POLLOUT %u)\n", __func__, + fds.events & POLLIN, fds.events & POLLOUT); + return 2; + } + + if (fds.revents & POLLIN) { + len = do_rnd_read(peerfd, rbuf, sizeof(rbuf)); + if (len == 0) { + /* no more data to receive: + * peer has closed its write side + */ + fds.events &= ~POLLIN; + + if ((fds.events & POLLOUT) == 0) + /* and nothing more to send */ + break; + + /* Else, still have data to transmit */ + } else if (len < 0) { + perror("read"); + return 3; + } + + do_write(outfd, rbuf, len); + } + + if (fds.revents & POLLOUT) { + if (wlen == 0) { + woff = 0; + wlen = read(infd, wbuf, sizeof(wbuf)); + } + + if (wlen > 0) { + ssize_t bw; + + bw = do_rnd_write(peerfd, wbuf + woff, wlen); + if (bw < 0) + return 111; + + woff += bw; + wlen -= bw; + } else if (wlen == 0) { + /* We have no more data to send. */ + fds.events &= ~POLLOUT; + + if ((fds.events & POLLIN) == 0) + /* ... and peer also closed already */ + break; + + /* ... but we still receive. + * Close our write side. + */ + shutdown(peerfd, SHUT_WR); + } else { + if (errno == EINTR) + continue; + perror("read"); + return 4; + } + } + + if (fds.revents & (POLLERR | POLLNVAL)) { + fprintf(stderr, "Unexpected revents: " + "POLLERR/POLLNVAL(%x)\n", fds.revents); + return 5; + } + } + + close(peerfd); + return 0; +} + +static int do_recvfile(int infd, int outfd) +{ + ssize_t r; + + do { + char buf[16384]; + + r = do_rnd_read(infd, buf, sizeof(buf)); + if (r > 0) { + if (write(outfd, buf, r) != r) + break; + } else if (r < 0) { + perror("read"); + } + } while (r > 0); + + return (int)r; +} + +static int do_mmap(int infd, int outfd, unsigned int size) +{ + char *inbuf = mmap(NULL, size, PROT_READ, MAP_SHARED, infd, 0); + ssize_t ret = 0, off = 0; + size_t rem; + + if (inbuf == MAP_FAILED) { + perror("mmap"); + return 1; + } + + rem = size; + + while (rem > 0) { + ret = write(outfd, inbuf + off, rem); + + if (ret < 0) { + perror("write"); + break; + } + + off += ret; + rem -= ret; + } + + munmap(inbuf, size); + return rem; +} + +static int get_infd_size(int fd) +{ + struct stat sb; + ssize_t count; + int err; + + err = fstat(fd, &sb); + if (err < 0) { + perror("fstat"); + return -1; + } + + if ((sb.st_mode & S_IFMT) != S_IFREG) { + fprintf(stderr, "%s: stdin is not a regular file\n", __func__); + return -2; + } + + count = sb.st_size; + if (count > INT_MAX) { + fprintf(stderr, "File too large: %zu\n", count); + return -3; + } + + return (int)count; +} + +static int do_sendfile(int infd, int outfd, unsigned int count) +{ + while (count > 0) { + ssize_t r; + + r = sendfile(outfd, infd, NULL, count); + if (r < 0) { + perror("sendfile"); + return 3; + } + + count -= r; + } + + return 0; +} + +static int copyfd_io_mmap(int infd, int peerfd, int outfd, + unsigned int size) +{ + int err; + + if (listen_mode) { + err = do_recvfile(peerfd, outfd); + if (err) + return err; + + err = do_mmap(infd, peerfd, size); + } else { + err = do_mmap(infd, peerfd, size); + if (err) + return err; + + shutdown(peerfd, SHUT_WR); + + err = do_recvfile(peerfd, outfd); + } + + return err; +} + +static int copyfd_io_sendfile(int infd, int peerfd, int outfd, + unsigned int size) +{ + int err; + + if (listen_mode) { + err = do_recvfile(peerfd, outfd); + if (err) + return err; + + err = do_sendfile(infd, peerfd, size); + } else { + err = do_sendfile(infd, peerfd, size); + if (err) + return err; + err = do_recvfile(peerfd, outfd); + } + + return err; +} + +static int copyfd_io(int infd, int peerfd, int outfd) +{ + int file_size; + + switch (cfg_mode) { + case CFG_MODE_POLL: + return copyfd_io_poll(infd, peerfd, outfd); + case CFG_MODE_MMAP: + file_size = get_infd_size(infd); + if (file_size < 0) + return file_size; + return copyfd_io_mmap(infd, peerfd, outfd, file_size); + case CFG_MODE_SENDFILE: + file_size = get_infd_size(infd); + if (file_size < 0) + return file_size; + return copyfd_io_sendfile(infd, peerfd, outfd, file_size); + } + + fprintf(stderr, "Invalid mode %d\n", cfg_mode); + + die_usage(); + return 1; +} + +static void check_sockaddr(int pf, struct sockaddr_storage *ss, + socklen_t salen) +{ + struct sockaddr_in6 *sin6; + struct sockaddr_in *sin; + socklen_t wanted_size = 0; + + switch (pf) { + case AF_INET: + wanted_size = sizeof(*sin); + sin = (void *)ss; + if (!sin->sin_port) + fprintf(stderr, "accept: something wrong: ip connection from port 0"); + break; + case AF_INET6: + wanted_size = sizeof(*sin6); + sin6 = (void *)ss; + if (!sin6->sin6_port) + fprintf(stderr, "accept: something wrong: ipv6 connection from port 0"); + break; + default: + fprintf(stderr, "accept: Unknown pf %d, salen %u\n", pf, salen); + return; + } + + if (salen != wanted_size) + fprintf(stderr, "accept: size mismatch, got %d expected %d\n", + (int)salen, wanted_size); + + if (ss->ss_family != pf) + fprintf(stderr, "accept: pf mismatch, expect %d, ss_family is %d\n", + (int)ss->ss_family, pf); +} + +static void check_getpeername(int fd, struct sockaddr_storage *ss, socklen_t salen) +{ + struct sockaddr_storage peerss; + socklen_t peersalen = sizeof(peerss); + + if (getpeername(fd, (struct sockaddr *)&peerss, &peersalen) < 0) { + perror("getpeername"); + return; + } + + if (peersalen != salen) { + fprintf(stderr, "%s: %d vs %d\n", __func__, peersalen, salen); + return; + } + + if (memcmp(ss, &peerss, peersalen)) { + char a[INET6_ADDRSTRLEN]; + char b[INET6_ADDRSTRLEN]; + char c[INET6_ADDRSTRLEN]; + char d[INET6_ADDRSTRLEN]; + + xgetnameinfo((struct sockaddr *)ss, salen, + a, sizeof(a), b, sizeof(b)); + + xgetnameinfo((struct sockaddr *)&peerss, peersalen, + c, sizeof(c), d, sizeof(d)); + + fprintf(stderr, "%s: memcmp failure: accept %s vs peername %s, %s vs %s salen %d vs %d\n", + __func__, a, c, b, d, peersalen, salen); + } +} + +static void check_getpeername_connect(int fd) +{ + struct sockaddr_storage ss; + socklen_t salen = sizeof(ss); + char a[INET6_ADDRSTRLEN]; + char b[INET6_ADDRSTRLEN]; + + if (getpeername(fd, (struct sockaddr *)&ss, &salen) < 0) { + perror("getpeername"); + return; + } + + xgetnameinfo((struct sockaddr *)&ss, salen, + a, sizeof(a), b, sizeof(b)); + + if (strcmp(cfg_host, a) || strcmp(cfg_port, b)) + fprintf(stderr, "%s: %s vs %s, %s vs %s\n", __func__, + cfg_host, a, cfg_port, b); +} + +int main_loop_s(int listensock) +{ + struct sockaddr_storage ss; + struct pollfd polls; + socklen_t salen; + int remotesock; + + polls.fd = listensock; + polls.events = POLLIN; + + switch (poll(&polls, 1, poll_timeout)) { + case -1: + perror("poll"); + return 1; + case 0: + fprintf(stderr, "%s: timed out\n", __func__); + close(listensock); + return 2; + } + + salen = sizeof(ss); + remotesock = accept(listensock, (struct sockaddr *)&ss, &salen); + if (remotesock >= 0) { + check_sockaddr(pf, &ss, salen); + check_getpeername(remotesock, &ss, salen); + + return copyfd_io(0, remotesock, 1); + } + + perror("accept"); + + return 1; +} + +static void init_rng(void) +{ + int fd = open("/dev/urandom", O_RDONLY); + unsigned int foo; + + if (fd > 0) { + int ret = read(fd, &foo, sizeof(foo)); + + if (ret < 0) + srand(fd + foo); + close(fd); + } + + srand(foo); +} + +int main_loop(void) +{ + int fd; + + /* listener is ready. */ + fd = sock_connect_mptcp(cfg_host, cfg_port, cfg_sock_proto); + if (fd < 0) + return 2; + + check_getpeername_connect(fd); + + if (cfg_sndbuf) + set_sndbuf(fd, cfg_sndbuf); + + return copyfd_io(0, fd, 1); +} + +int parse_proto(const char *proto) +{ + if (!strcasecmp(proto, "MPTCP")) + return IPPROTO_MPTCP; + if (!strcasecmp(proto, "TCP")) + return IPPROTO_TCP; + + fprintf(stderr, "Unknown protocol: %s\n.", proto); + die_usage(); + + /* silence compiler warning */ + return 0; +} + +int parse_mode(const char *mode) +{ + if (!strcasecmp(mode, "poll")) + return CFG_MODE_POLL; + if (!strcasecmp(mode, "mmap")) + return CFG_MODE_MMAP; + if (!strcasecmp(mode, "sendfile")) + return CFG_MODE_SENDFILE; + + fprintf(stderr, "Unknown test mode: %s\n", mode); + fprintf(stderr, "Supported modes are:\n"); + fprintf(stderr, "\t\t\"poll\" - interleaved read/write using poll()\n"); + fprintf(stderr, "\t\t\"mmap\" - send entire input file (mmap+write), then read response (-l will read input first)\n"); + fprintf(stderr, "\t\t\"sendfile\" - send entire input file (sendfile), then read response (-l will read input first)\n"); + + die_usage(); + + /* silence compiler warning */ + return 0; +} + +int parse_sndbuf(const char *size) +{ + unsigned long s; + + errno = 0; + + s = strtoul(size, NULL, 0); + + if (errno) { + fprintf(stderr, "Invalid sndbuf size %s (%s)\n", + size, strerror(errno)); + die_usage(); + } + + if (s > INT_MAX) { + fprintf(stderr, "Invalid sndbuf size %s (%s)\n", + size, strerror(ERANGE)); + die_usage(); + } + + cfg_sndbuf = s; + + return 0; +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "6lp:s:hut:m:b:")) != -1) { + switch (c) { + case 'l': + listen_mode = true; + break; + case 'p': + cfg_port = optarg; + break; + case 's': + cfg_sock_proto = parse_proto(optarg); + break; + case 'h': + die_usage(); + break; + case 'u': + tcpulp_audit = true; + break; + case '6': + pf = AF_INET6; + break; + case 't': + poll_timeout = atoi(optarg) * 1000; + if (poll_timeout <= 0) + poll_timeout = -1; + break; + case 'm': + cfg_mode = parse_mode(optarg); + break; + case 'b': + cfg_sndbuf = parse_sndbuf(optarg); + break; + } + } + + if (optind + 1 != argc) + die_usage(); + cfg_host = argv[optind]; + + if (strchr(cfg_host, ':')) + pf = AF_INET6; +} + +int main(int argc, char *argv[]) +{ + init_rng(); + + parse_opts(argc, argv); + + if (tcpulp_audit) + return sock_test_tcpulp(cfg_host, cfg_port) ? 0 : 1; + + if (listen_mode) { + int fd = sock_listen_mptcp(cfg_host, cfg_port); + + if (fd < 0) + return 1; + + if (cfg_sndbuf) + set_sndbuf(fd, cfg_sndbuf); + + return main_loop_s(fd); + } + + return main_loop(); +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh new file mode 100755 index 000000000000..d573a0feb98d --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -0,0 +1,595 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +time_start=$(date +%s) + +optstring="b:d:e:l:r:h4cm:" +ret=0 +sin="" +sout="" +cin="" +cout="" +ksft_skip=4 +capture=false +timeout=30 +ipv6=true +ethtool_random_on=true +tc_delay="$((RANDOM%400))" +tc_loss=$((RANDOM%101)) +tc_reorder="" +testmode="" +sndbuf=0 +options_log=true + +if [ $tc_loss -eq 100 ];then + tc_loss=1% +elif [ $tc_loss -ge 10 ]; then + tc_loss=0.$tc_loss% +elif [ $tc_loss -ge 1 ]; then + tc_loss=0.0$tc_loss% +else + tc_loss="" +fi + +usage() { + echo "Usage: $0 [ -a ]" + echo -e "\t-d: tc/netem delay in milliseconds, e.g. \"-d 10\" (default random)" + echo -e "\t-l: tc/netem loss percentage, e.g. \"-l 0.02\" (default random)" + echo -e "\t-r: tc/netem reorder mode, e.g. \"-r 25% 50% gap 5\", use "-r 0" to disable reordering (default random)" + echo -e "\t-e: ethtool features to disable, e.g.: \"-e tso -e gso\" (default: randomly disable any of tso/gso/gro)" + echo -e "\t-4: IPv4 only: disable IPv6 tests (default: test both IPv4 and IPv6)" + echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)" + echo -e "\t-b: set sndbuf value (default: use kernel default)" + echo -e "\t-m: test mode (poll, sendfile; default: poll)" +} + +while getopts "$optstring" option;do + case "$option" in + "h") + usage $0 + exit 0 + ;; + "d") + if [ $OPTARG -ge 0 ];then + tc_delay="$OPTARG" + else + echo "-d requires numeric argument, got \"$OPTARG\"" 1>&2 + exit 1 + fi + ;; + "e") + ethtool_args="$ethtool_args $OPTARG off" + ethtool_random_on=false + ;; + "l") + tc_loss="$OPTARG" + ;; + "r") + tc_reorder="$OPTARG" + ;; + "4") + ipv6=false + ;; + "c") + capture=true + ;; + "b") + if [ $OPTARG -ge 0 ];then + sndbuf="$OPTARG" + else + echo "-s requires numeric argument, got \"$OPTARG\"" 1>&2 + exit 1 + fi + ;; + "m") + testmode="$OPTARG" + ;; + "?") + usage $0 + exit 1 + ;; + esac +done + +sec=$(date +%s) +rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) +ns1="ns1-$rndh" +ns2="ns2-$rndh" +ns3="ns3-$rndh" +ns4="ns4-$rndh" + +TEST_COUNT=0 + +cleanup() +{ + rm -f "$cin" "$cout" + rm -f "$sin" "$sout" + rm -f "$capout" + + local netns + for netns in "$ns1" "$ns2" "$ns3" "$ns4";do + ip netns del $netns + done +} + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +sin=$(mktemp) +sout=$(mktemp) +cin=$(mktemp) +cout=$(mktemp) +capout=$(mktemp) +trap cleanup EXIT + +for i in "$ns1" "$ns2" "$ns3" "$ns4";do + ip netns add $i || exit $ksft_skip + ip -net $i link set lo up +done + +# "$ns1" ns2 ns3 ns4 +# ns1eth2 ns2eth1 ns2eth3 ns3eth2 ns3eth4 ns4eth3 +# - drop 1% -> reorder 25% +# <- TSO off - + +ip link add ns1eth2 netns "$ns1" type veth peer name ns2eth1 netns "$ns2" +ip link add ns2eth3 netns "$ns2" type veth peer name ns3eth2 netns "$ns3" +ip link add ns3eth4 netns "$ns3" type veth peer name ns4eth3 netns "$ns4" + +ip -net "$ns1" addr add 10.0.1.1/24 dev ns1eth2 +ip -net "$ns1" addr add dead:beef:1::1/64 dev ns1eth2 nodad + +ip -net "$ns1" link set ns1eth2 up +ip -net "$ns1" route add default via 10.0.1.2 +ip -net "$ns1" route add default via dead:beef:1::2 + +ip -net "$ns2" addr add 10.0.1.2/24 dev ns2eth1 +ip -net "$ns2" addr add dead:beef:1::2/64 dev ns2eth1 nodad +ip -net "$ns2" link set ns2eth1 up + +ip -net "$ns2" addr add 10.0.2.1/24 dev ns2eth3 +ip -net "$ns2" addr add dead:beef:2::1/64 dev ns2eth3 nodad +ip -net "$ns2" link set ns2eth3 up +ip -net "$ns2" route add default via 10.0.2.2 +ip -net "$ns2" route add default via dead:beef:2::2 +ip netns exec "$ns2" sysctl -q net.ipv4.ip_forward=1 +ip netns exec "$ns2" sysctl -q net.ipv6.conf.all.forwarding=1 + +ip -net "$ns3" addr add 10.0.2.2/24 dev ns3eth2 +ip -net "$ns3" addr add dead:beef:2::2/64 dev ns3eth2 nodad +ip -net "$ns3" link set ns3eth2 up + +ip -net "$ns3" addr add 10.0.3.2/24 dev ns3eth4 +ip -net "$ns3" addr add dead:beef:3::2/64 dev ns3eth4 nodad +ip -net "$ns3" link set ns3eth4 up +ip -net "$ns3" route add default via 10.0.2.1 +ip -net "$ns3" route add default via dead:beef:2::1 +ip netns exec "$ns3" sysctl -q net.ipv4.ip_forward=1 +ip netns exec "$ns3" sysctl -q net.ipv6.conf.all.forwarding=1 + +ip -net "$ns4" addr add 10.0.3.1/24 dev ns4eth3 +ip -net "$ns4" addr add dead:beef:3::1/64 dev ns4eth3 nodad +ip -net "$ns4" link set ns4eth3 up +ip -net "$ns4" route add default via 10.0.3.2 +ip -net "$ns4" route add default via dead:beef:3::2 + +set_ethtool_flags() { + local ns="$1" + local dev="$2" + local flags="$3" + + ip netns exec $ns ethtool -K $dev $flags 2>/dev/null + [ $? -eq 0 ] && echo "INFO: set $ns dev $dev: ethtool -K $flags" +} + +set_random_ethtool_flags() { + local flags="" + local r=$RANDOM + + local pick1=$((r & 1)) + local pick2=$((r & 2)) + local pick3=$((r & 4)) + + [ $pick1 -ne 0 ] && flags="tso off" + [ $pick2 -ne 0 ] && flags="$flags gso off" + [ $pick3 -ne 0 ] && flags="$flags gro off" + + [ -z "$flags" ] && return + + set_ethtool_flags "$1" "$2" "$flags" +} + +if $ethtool_random_on;then + set_random_ethtool_flags "$ns3" ns3eth2 + set_random_ethtool_flags "$ns4" ns4eth3 +else + set_ethtool_flags "$ns3" ns3eth2 "$ethtool_args" + set_ethtool_flags "$ns4" ns4eth3 "$ethtool_args" +fi + +print_file_err() +{ + ls -l "$1" 1>&2 + echo "Trailing bytes are: " + tail -c 27 "$1" +} + +check_transfer() +{ + local in=$1 + local out=$2 + local what=$3 + + cmp "$in" "$out" > /dev/null 2>&1 + if [ $? -ne 0 ] ;then + echo "[ FAIL ] $what does not match (in, out):" + print_file_err "$in" + print_file_err "$out" + + return 1 + fi + + return 0 +} + +check_mptcp_disabled() +{ + local disabled_ns + disabled_ns="ns_disabled-$sech-$(mktemp -u XXXXXX)" + ip netns add ${disabled_ns} || exit $ksft_skip + + # net.mptcp.enabled should be enabled by default + if [ "$(ip netns exec ${disabled_ns} sysctl net.mptcp.enabled | awk '{ print $3 }')" -ne 1 ]; then + echo -e "net.mptcp.enabled sysctl is not 1 by default\t\t[ FAIL ]" + ret=1 + return 1 + fi + ip netns exec ${disabled_ns} sysctl -q net.mptcp.enabled=0 + + local err=0 + LANG=C ip netns exec ${disabled_ns} ./mptcp_connect -t $timeout -p 10000 -s MPTCP 127.0.0.1 < "$cin" 2>&1 | \ + grep -q "^socket: Protocol not available$" && err=1 + ip netns delete ${disabled_ns} + + if [ ${err} -eq 0 ]; then + echo -e "New MPTCP socket cannot be blocked via sysctl\t\t[ FAIL ]" + ret=1 + return 1 + fi + + echo -e "New MPTCP socket can be blocked via sysctl\t\t[ OK ]" + return 0 +} + +check_mptcp_ulp_setsockopt() +{ + local t retval + t="ns_ulp-$sech-$(mktemp -u XXXXXX)" + + ip netns add ${t} || exit $ksft_skip + if ! ip netns exec ${t} ./mptcp_connect -u -p 10000 -s TCP 127.0.0.1 2>&1; then + printf "setsockopt(..., TCP_ULP, \"mptcp\", ...) allowed\t[ FAIL ]\n" + retval=1 + ret=$retval + else + printf "setsockopt(..., TCP_ULP, \"mptcp\", ...) blocked\t[ OK ]\n" + retval=0 + fi + ip netns del ${t} + return $retval +} + +# $1: IP address +is_v6() +{ + [ -z "${1##*:*}" ] +} + +do_ping() +{ + local listener_ns="$1" + local connector_ns="$2" + local connect_addr="$3" + local ping_args="-q -c 1" + + if is_v6 "${connect_addr}"; then + $ipv6 || return 0 + ping_args="${ping_args} -6" + fi + + ip netns exec ${connector_ns} ping ${ping_args} $connect_addr >/dev/null + if [ $? -ne 0 ] ; then + echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2 + ret=1 + + return 1 + fi + + return 0 +} + +# $1: ns, $2: port +wait_local_port_listen() +{ + local listener_ns="${1}" + local port="${2}" + + local port_hex i + + port_hex="$(printf "%04X" "${port}")" + for i in $(seq 10); do + ip netns exec "${listener_ns}" cat /proc/net/tcp* | \ + awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" && + break + sleep 0.1 + done +} + +do_transfer() +{ + local listener_ns="$1" + local connector_ns="$2" + local cl_proto="$3" + local srv_proto="$4" + local connect_addr="$5" + local local_addr="$6" + local extra_args="" + + local port + port=$((10000+$TEST_COUNT)) + TEST_COUNT=$((TEST_COUNT+1)) + + if [ "$sndbuf" -gt 0 ]; then + extra_args="$extra_args -b $sndbuf" + fi + + if [ -n "$testmode" ]; then + extra_args="$extra_args -m $testmode" + fi + + if [ -n "$extra_args" ] && $options_log; then + options_log=false + echo "INFO: extra options: $extra_args" + fi + + :> "$cout" + :> "$sout" + :> "$capout" + + local addr_port + addr_port=$(printf "%s:%d" ${connect_addr} ${port}) + printf "%.3s %-5s -> %.3s (%-20s) %-5s\t" ${connector_ns} ${cl_proto} ${listener_ns} ${addr_port} ${srv_proto} + + if $capture; then + local capuser + if [ -z $SUDO_USER ] ; then + capuser="" + else + capuser="-Z $SUDO_USER" + fi + + local capfile="${listener_ns}-${connector_ns}-${cl_proto}-${srv_proto}-${connect_addr}.pcap" + + ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 & + local cappid=$! + + sleep 1 + fi + + ip netns exec ${listener_ns} ./mptcp_connect -t $timeout -l -p $port -s ${srv_proto} $extra_args $local_addr < "$sin" > "$sout" & + local spid=$! + + wait_local_port_listen "${listener_ns}" "${port}" + + local start + start=$(date +%s%3N) + ip netns exec ${connector_ns} ./mptcp_connect -t $timeout -p $port -s ${cl_proto} $extra_args $connect_addr < "$cin" > "$cout" & + local cpid=$! + + wait $cpid + local retc=$? + wait $spid + local rets=$? + + local stop + stop=$(date +%s%3N) + + if $capture; then + sleep 1 + kill $cappid + fi + + local duration + duration=$((stop-start)) + duration=$(printf "(duration %05sms)" $duration) + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + echo "$duration [ FAIL ] client exit code $retc, server $rets" 1>&2 + echo "\nnetns ${listener_ns} socket stat for $port:" 1>&2 + ip netns exec ${listener_ns} ss -nita 1>&2 -o "sport = :$port" + echo "\nnetns ${connector_ns} socket stat for $port:" 1>&2 + ip netns exec ${connector_ns} ss -nita 1>&2 -o "dport = :$port" + + cat "$capout" + return 1 + fi + + check_transfer $sin $cout "file received by client" + retc=$? + check_transfer $cin $sout "file received by server" + rets=$? + + if [ $retc -eq 0 ] && [ $rets -eq 0 ];then + echo "$duration [ OK ]" + cat "$capout" + return 0 + fi + + cat "$capout" + return 1 +} + +make_file() +{ + local name=$1 + local who=$2 + + local SIZE TSIZE + SIZE=$((RANDOM % (1024 * 8))) + TSIZE=$((SIZE * 1024)) + + dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null + + SIZE=$((RANDOM % 1024)) + SIZE=$((SIZE + 128)) + TSIZE=$((TSIZE + SIZE)) + dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$SIZE 2> /dev/null + echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" + + echo "Created $name (size $TSIZE) containing data sent by $who" +} + +run_tests_lo() +{ + local listener_ns="$1" + local connector_ns="$2" + local connect_addr="$3" + local loopback="$4" + local lret=0 + + # skip if test programs are running inside same netns for subsequent runs. + if [ $loopback -eq 0 ] && [ ${listener_ns} = ${connector_ns} ]; then + return 0 + fi + + # skip if we don't want v6 + if ! $ipv6 && is_v6 "${connect_addr}"; then + return 0 + fi + + local local_addr + if is_v6 "${connect_addr}"; then + local_addr="::" + else + local_addr="0.0.0.0" + fi + + do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${local_addr} + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + + # don't bother testing fallback tcp except for loopback case. + if [ ${listener_ns} != ${connector_ns} ]; then + return 0 + fi + + do_transfer ${listener_ns} ${connector_ns} MPTCP TCP ${connect_addr} ${local_addr} + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + + do_transfer ${listener_ns} ${connector_ns} TCP MPTCP ${connect_addr} ${local_addr} + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + + return 0 +} + +run_tests() +{ + run_tests_lo $1 $2 $3 0 +} + +make_file "$cin" "client" +make_file "$sin" "server" + +check_mptcp_disabled + +check_mptcp_ulp_setsockopt + +echo "INFO: validating network environment with pings" +for sender in "$ns1" "$ns2" "$ns3" "$ns4";do + do_ping "$ns1" $sender 10.0.1.1 + do_ping "$ns1" $sender dead:beef:1::1 + + do_ping "$ns2" $sender 10.0.1.2 + do_ping "$ns2" $sender dead:beef:1::2 + do_ping "$ns2" $sender 10.0.2.1 + do_ping "$ns2" $sender dead:beef:2::1 + + do_ping "$ns3" $sender 10.0.2.2 + do_ping "$ns3" $sender dead:beef:2::2 + do_ping "$ns3" $sender 10.0.3.2 + do_ping "$ns3" $sender dead:beef:3::2 + + do_ping "$ns4" $sender 10.0.3.1 + do_ping "$ns4" $sender dead:beef:3::1 +done + +[ -n "$tc_loss" ] && tc -net "$ns2" qdisc add dev ns2eth3 root netem loss random $tc_loss +echo -n "INFO: Using loss of $tc_loss " +test "$tc_delay" -gt 0 && echo -n "delay $tc_delay ms " + +if [ -z "${tc_reorder}" ]; then + reorder1=$((RANDOM%10)) + reorder1=$((100 - reorder1)) + reorder2=$((RANDOM%100)) + + if [ $tc_delay -gt 0 ] && [ $reorder1 -lt 100 ] && [ $reorder2 -gt 0 ]; then + tc_reorder="reorder ${reorder1}% ${reorder2}%" + echo -n "$tc_reorder " + fi +elif [ "$tc_reorder" = "0" ];then + tc_reorder="" +elif [ "$tc_delay" -gt 0 ];then + # reordering requires some delay + tc_reorder="reorder $tc_reorder" + echo -n "$tc_reorder " +fi + +echo "on ns3eth4" + +tc -net "$ns3" qdisc add dev ns3eth4 root netem delay ${tc_delay}ms $tc_reorder + +for sender in $ns1 $ns2 $ns3 $ns4;do + run_tests_lo "$ns1" "$sender" 10.0.1.1 1 + if [ $ret -ne 0 ] ;then + echo "FAIL: Could not even run loopback test" 1>&2 + exit $ret + fi + run_tests_lo "$ns1" $sender dead:beef:1::1 1 + if [ $ret -ne 0 ] ;then + echo "FAIL: Could not even run loopback v6 test" 2>&1 + exit $ret + fi + + run_tests "$ns2" $sender 10.0.1.2 + run_tests "$ns2" $sender dead:beef:1::2 + run_tests "$ns2" $sender 10.0.2.1 + run_tests "$ns2" $sender dead:beef:2::1 + + run_tests "$ns3" $sender 10.0.2.2 + run_tests "$ns3" $sender dead:beef:2::2 + run_tests "$ns3" $sender 10.0.3.2 + run_tests "$ns3" $sender dead:beef:3::2 + + run_tests "$ns4" $sender 10.0.3.1 + run_tests "$ns4" $sender dead:beef:3::1 +done + +time_end=$(date +%s) +time_run=$((time_end-time_start)) + +echo "Time: ${time_run} seconds" + +exit $ret diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings new file mode 100644 index 000000000000..026384c189c9 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/settings @@ -0,0 +1 @@ +timeout=450 diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index de1032b5ddea..08194aa44006 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -2,6 +2,7 @@ # Makefile for netfilter selftests TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \ - conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh + conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ + nft_concat_range.sh include ../lib.mk diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh new file mode 100755 index 000000000000..aca21dde102a --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_concat_range.sh @@ -0,0 +1,1481 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# nft_concat_range.sh - Tests for sets with concatenation of ranged fields +# +# Copyright (c) 2019 Red Hat GmbH +# +# Author: Stefano Brivio <sbrivio@redhat.com> +# +# shellcheck disable=SC2154,SC2034,SC2016,SC2030,SC2031 +# ^ Configuration and templates sourced with eval, counters reused in subshells + +KSELFTEST_SKIP=4 + +# Available test groups: +# - correctness: check that packets match given entries, and only those +# - concurrency: attempt races between insertion, deletion and lookup +# - timeout: check that packets match entries until they expire +# - performance: estimate matching rate, compare with rbtree and hash baselines +TESTS="correctness concurrency timeout" +[ "${quicktest}" != "1" ] && TESTS="${TESTS} performance" + +# Set types, defined by TYPE_ variables below +TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto + net_port_net net_mac net_mac_icmp net6_mac_icmp net6_port_net6_port + net_port_mac_proto_net" + +# List of possible paths to pktgen script from kernel tree for performance tests +PKTGEN_SCRIPT_PATHS=" + ../../../samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh + pktgen/pktgen_bench_xmit_mode_netif_receive.sh" + +# Definition of set types: +# display display text for test report +# type_spec nftables set type specifier +# chain_spec nftables type specifier for rules mapping to set +# dst call sequence of format_*() functions for destination fields +# src call sequence of format_*() functions for source fields +# start initial integer used to generate addresses and ports +# count count of entries to generate and match +# src_delta number summed to destination generator for source fields +# tools list of tools for correctness and timeout tests, any can be used +# proto L4 protocol of test packets +# +# race_repeat race attempts per thread, 0 disables concurrency test for type +# flood_tools list of tools for concurrency tests, any can be used +# flood_proto L4 protocol of test packets for concurrency tests +# flood_spec nftables type specifier for concurrency tests +# +# perf_duration duration of single pktgen injection test +# perf_spec nftables type specifier for performance tests +# perf_dst format_*() functions for destination fields in performance test +# perf_src format_*() functions for source fields in performance test +# perf_entries number of set entries for performance test +# perf_proto L3 protocol of test packets +TYPE_net_port=" +display net,port +type_spec ipv4_addr . inet_service +chain_spec ip daddr . udp dport +dst addr4 port +src +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto udp +flood_spec ip daddr . udp dport + +perf_duration 5 +perf_spec ip daddr . udp dport +perf_dst addr4 port +perf_src +perf_entries 1000 +perf_proto ipv4 +" + +TYPE_port_net=" +display port,net +type_spec inet_service . ipv4_addr +chain_spec udp dport . ip daddr +dst port addr4 +src +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto udp +flood_spec udp dport . ip daddr + +perf_duration 5 +perf_spec udp dport . ip daddr +perf_dst port addr4 +perf_src +perf_entries 100 +perf_proto ipv4 +" + +TYPE_net6_port=" +display net6,port +type_spec ipv6_addr . inet_service +chain_spec ip6 daddr . udp dport +dst addr6 port +src +start 10 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp6 + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto tcp6 +flood_spec ip6 daddr . udp dport + +perf_duration 5 +perf_spec ip6 daddr . udp dport +perf_dst addr6 port +perf_src +perf_entries 1000 +perf_proto ipv6 +" + +TYPE_port_proto=" +display port,proto +type_spec inet_service . inet_proto +chain_spec udp dport . meta l4proto +dst port proto +src +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 5 +perf_spec udp dport . meta l4proto +perf_dst port proto +perf_src +perf_entries 30000 +perf_proto ipv4 +" + +TYPE_net6_port_mac=" +display net6,port,mac +type_spec ipv6_addr . inet_service . ether_addr +chain_spec ip6 daddr . udp dport . ether saddr +dst addr6 port +src mac +start 10 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp6 + +race_repeat 0 + +perf_duration 5 +perf_spec ip6 daddr . udp dport . ether daddr +perf_dst addr6 port mac +perf_src +perf_entries 10 +perf_proto ipv6 +" + +TYPE_net6_port_mac_proto=" +display net6,port,mac,proto +type_spec ipv6_addr . inet_service . ether_addr . inet_proto +chain_spec ip6 daddr . udp dport . ether saddr . meta l4proto +dst addr6 port +src mac proto +start 10 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp6 + +race_repeat 0 + +perf_duration 5 +perf_spec ip6 daddr . udp dport . ether daddr . meta l4proto +perf_dst addr6 port mac proto +perf_src +perf_entries 1000 +perf_proto ipv6 +" + +TYPE_net_port_net=" +display net,port,net +type_spec ipv4_addr . inet_service . ipv4_addr +chain_spec ip daddr . udp dport . ip saddr +dst addr4 port +src addr4 +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto tcp +flood_spec ip daddr . udp dport . ip saddr + +perf_duration 0 +" + +TYPE_net6_port_net6_port=" +display net6,port,net6,port +type_spec ipv6_addr . inet_service . ipv6_addr . inet_service +chain_spec ip6 daddr . udp dport . ip6 saddr . udp sport +dst addr6 port +src addr6 port +start 10 +count 5 +src_delta 2000 +tools sendip nc +proto udp6 + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto tcp6 +flood_spec ip6 daddr . tcp dport . ip6 saddr . tcp sport + +perf_duration 0 +" + +TYPE_net_port_mac_proto_net=" +display net,port,mac,proto,net +type_spec ipv4_addr . inet_service . ether_addr . inet_proto . ipv4_addr +chain_spec ip daddr . udp dport . ether saddr . meta l4proto . ip saddr +dst addr4 port +src mac proto addr4 +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 0 +" + +TYPE_net_mac=" +display net,mac +type_spec ipv4_addr . ether_addr +chain_spec ip daddr . ether saddr +dst addr4 +src mac +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 5 +perf_spec ip daddr . ether daddr +perf_dst addr4 mac +perf_src +perf_entries 1000 +perf_proto ipv4 +" + +TYPE_net_mac_icmp=" +display net,mac - ICMP +type_spec ipv4_addr . ether_addr +chain_spec ip daddr . ether saddr +dst addr4 +src mac +start 1 +count 5 +src_delta 2000 +tools ping +proto icmp + +race_repeat 0 + +perf_duration 0 +" + +TYPE_net6_mac_icmp=" +display net6,mac - ICMPv6 +type_spec ipv6_addr . ether_addr +chain_spec ip6 daddr . ether saddr +dst addr6 +src mac +start 10 +count 50 +src_delta 2000 +tools ping +proto icmp6 + +race_repeat 0 + +perf_duration 0 +" + +TYPE_net_port_proto_net=" +display net,port,proto,net +type_spec ipv4_addr . inet_service . inet_proto . ipv4_addr +chain_spec ip daddr . udp dport . meta l4proto . ip saddr +dst addr4 port proto +src addr4 +start 1 +count 5 +src_delta 2000 +tools sendip nc +proto udp + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto tcp +flood_spec ip daddr . tcp dport . meta l4proto . ip saddr + +perf_duration 0 +" + +# Set template for all tests, types and rules are filled in depending on test +set_template=' +flush ruleset + +table inet filter { + counter test { + packets 0 bytes 0 + } + + set test { + type ${type_spec} + flags interval,timeout + } + + chain input { + type filter hook prerouting priority 0; policy accept; + ${chain_spec} @test counter name \"test\" + } +} + +table netdev perf { + counter test { + packets 0 bytes 0 + } + + counter match { + packets 0 bytes 0 + } + + set test { + type ${type_spec} + flags interval + } + + set norange { + type ${type_spec} + } + + set noconcat { + type ${type_spec%% *} + flags interval + } + + chain test { + type filter hook ingress device veth_a priority 0; + } +} +' + +err_buf= +info_buf= + +# Append string to error buffer +err() { + err_buf="${err_buf}${1} +" +} + +# Append string to information buffer +info() { + info_buf="${info_buf}${1} +" +} + +# Flush error buffer to stdout +err_flush() { + printf "%s" "${err_buf}" + err_buf= +} + +# Flush information buffer to stdout +info_flush() { + printf "%s" "${info_buf}" + info_buf= +} + +# Setup veth pair: this namespace receives traffic, B generates it +setup_veth() { + ip netns add B + ip link add veth_a type veth peer name veth_b || return 1 + + ip link set veth_a up + ip link set veth_b netns B + + ip -n B link set veth_b up + + ip addr add dev veth_a 10.0.0.1 + ip route add default dev veth_a + + ip -6 addr add fe80::1/64 dev veth_a nodad + ip -6 addr add 2001:db8::1/64 dev veth_a nodad + ip -6 route add default dev veth_a + + ip -n B route add default dev veth_b + + ip -6 -n B addr add fe80::2/64 dev veth_b nodad + ip -6 -n B addr add 2001:db8::2/64 dev veth_b nodad + ip -6 -n B route add default dev veth_b + + B() { + ip netns exec B "$@" >/dev/null 2>&1 + } + + sleep 2 +} + +# Fill in set template and initialise set +setup_set() { + eval "echo \"${set_template}\"" | nft -f - +} + +# Check that at least one of the needed tools is available +check_tools() { + __tools= + for tool in ${tools}; do + if [ "${tool}" = "nc" ] && [ "${proto}" = "udp6" ] && \ + ! nc -u -w0 1.1.1.1 1 2>/dev/null; then + # Some GNU netcat builds might not support IPv6 + __tools="${__tools} netcat-openbsd" + continue + fi + __tools="${__tools} ${tool}" + + command -v "${tool}" >/dev/null && return 0 + done + err "need one of:${__tools}, skipping" && return 1 +} + +# Set up function to send ICMP packets +setup_send_icmp() { + send_icmp() { + B ping -c1 -W1 "${dst_addr4}" >/dev/null 2>&1 + } +} + +# Set up function to send ICMPv6 packets +setup_send_icmp6() { + if command -v ping6 >/dev/null; then + send_icmp6() { + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + B ping6 -q -c1 -W1 "${dst_addr6}" + } + else + send_icmp6() { + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + B ping -q -6 -c1 -W1 "${dst_addr6}" + } + fi +} + +# Set up function to send single UDP packets on IPv4 +setup_send_udp() { + if command -v sendip >/dev/null; then + send_udp() { + [ -n "${src_port}" ] && src_port="-us ${src_port}" + [ -n "${dst_port}" ] && dst_port="-ud ${dst_port}" + [ -n "${src_addr4}" ] && src_addr4="-is ${src_addr4}" + + # shellcheck disable=SC2086 # sendip needs split options + B sendip -p ipv4 -p udp ${src_addr4} ${src_port} \ + ${dst_port} "${dst_addr4}" + + src_port= + dst_port= + src_addr4= + } + elif command -v nc >/dev/null; then + if nc -u -w0 1.1.1.1 1 2>/dev/null; then + # OpenBSD netcat + nc_opt="-w0" + else + # GNU netcat + nc_opt="-q0" + fi + + send_udp() { + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}" dev veth_b + __src_addr4="-s ${src_addr4}" + fi + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + [ -n "${src_port}" ] && src_port="-p ${src_port}" + + echo "" | B nc -u "${nc_opt}" "${__src_addr4}" \ + "${src_port}" "${dst_addr4}" "${dst_port}" + + src_addr4= + src_port= + } + elif [ -z "$(bash -c 'type -p')" ]; then + send_udp() { + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + B ip route add default dev veth_b + fi + + B bash -c "echo > /dev/udp/${dst_addr4}/${dst_port}" + + if [ -n "${src_addr4}" ]; then + B ip addr del "${src_addr4}/16" dev veth_b + fi + src_addr4= + } + else + return 1 + fi +} + +# Set up function to send single UDP packets on IPv6 +setup_send_udp6() { + if command -v sendip >/dev/null; then + send_udp6() { + [ -n "${src_port}" ] && src_port="-us ${src_port}" + [ -n "${dst_port}" ] && dst_port="-ud ${dst_port}" + if [ -n "${src_addr6}" ]; then + src_addr6="-6s ${src_addr6}" + else + src_addr6="-6s 2001:db8::2" + fi + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + B sendip -p ipv6 -p udp ${src_addr6} ${src_port} \ + ${dst_port} "${dst_addr6}" + + src_port= + dst_port= + src_addr6= + } + elif command -v nc >/dev/null && nc -u -w0 1.1.1.1 1 2>/dev/null; then + # GNU netcat might not work with IPv6, try next tool + send_udp6() { + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + if [ -n "${src_addr6}" ]; then + B ip addr add "${src_addr6}" dev veth_b nodad + else + src_addr6="2001:db8::2" + fi + [ -n "${src_port}" ] && src_port="-p ${src_port}" + + # shellcheck disable=SC2086 # this needs split options + echo "" | B nc -u w0 "-s${src_addr6}" ${src_port} \ + ${dst_addr6} ${dst_port} + + src_addr6= + src_port= + } + elif [ -z "$(bash -c 'type -p')" ]; then + send_udp6() { + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + B ip addr add "${src_addr6}" dev veth_b nodad + B bash -c "echo > /dev/udp/${dst_addr6}/${dst_port}" + ip -6 addr del "${dst_addr6}" dev veth_a 2>/dev/null + } + else + return 1 + fi +} + +# Set up function to send TCP traffic on IPv4 +setup_flood_tcp() { + if command -v iperf3 >/dev/null; then + flood_tcp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + src_addr4="-B ${src_addr4}" + else + B ip addr add dev veth_b 10.0.0.2 + src_addr4="-B 10.0.0.2" + fi + if [ -n "${src_port}" ]; then + src_port="--cport ${src_port}" + fi + B ip route add default dev veth_b 2>/dev/null + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf3 -s -DB "${dst_addr4}" ${dst_port} >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf3 -c "${dst_addr4}" ${dst_port} ${src_port} \ + ${src_addr4} -l16 -t 1000 + + src_addr4= + src_port= + dst_port= + } + elif command -v iperf >/dev/null; then + flood_tcp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + src_addr4="-B ${src_addr4}" + else + B ip addr add dev veth_b 10.0.0.2 2>/dev/null + src_addr4="-B 10.0.0.2" + fi + if [ -n "${src_port}" ]; then + src_addr4="${src_addr4}:${src_port}" + fi + B ip route add default dev veth_b + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf -s -DB "${dst_addr4}" ${dst_port} >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf -c "${dst_addr4}" ${dst_port} ${src_addr4} \ + -l20 -t 1000 + + src_addr4= + src_port= + dst_port= + } + elif command -v netperf >/dev/null; then + flood_tcp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + else + B ip addr add dev veth_b 10.0.0.2 + src_addr4="10.0.0.2" + fi + if [ -n "${src_port}" ]; then + dst_port="${dst_port},${src_port}" + fi + B ip route add default dev veth_b + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + netserver -4 ${dst_port} -L "${dst_addr4}" \ + >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B netperf -4 -H "${dst_addr4}" ${dst_port} \ + -L "${src_addr4}" -l 1000 -t TCP_STREAM + + src_addr4= + src_port= + dst_port= + } + else + return 1 + fi +} + +# Set up function to send TCP traffic on IPv6 +setup_flood_tcp6() { + if command -v iperf3 >/dev/null; then + flood_tcp6() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr6}" ]; then + B ip addr add "${src_addr6}" dev veth_b nodad + src_addr6="-B ${src_addr6}" + else + src_addr6="-B 2001:db8::2" + fi + if [ -n "${src_port}" ]; then + src_port="--cport ${src_port}" + fi + B ip route add default dev veth_b + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf3 -s -DB "${dst_addr6}" ${dst_port} >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf3 -c "${dst_addr6}" ${dst_port} \ + ${src_port} ${src_addr6} -l16 -t 1000 + + src_addr6= + src_port= + dst_port= + } + elif command -v iperf >/dev/null; then + flood_tcp6() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr6}" ]; then + B ip addr add "${src_addr6}" dev veth_b nodad + src_addr6="-B ${src_addr6}" + else + src_addr6="-B 2001:db8::2" + fi + if [ -n "${src_port}" ]; then + src_addr6="${src_addr6}:${src_port}" + fi + B ip route add default dev veth_b + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf -s -VDB "${dst_addr6}" ${dst_port} >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf -c "${dst_addr6}" -V ${dst_port} \ + ${src_addr6} -l1 -t 1000 + + src_addr6= + src_port= + dst_port= + } + elif command -v netperf >/dev/null; then + flood_tcp6() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr6}" ]; then + B ip addr add "${src_addr6}" dev veth_b nodad + else + src_addr6="2001:db8::2" + fi + if [ -n "${src_port}" ]; then + dst_port="${dst_port},${src_port}" + fi + B ip route add default dev veth_b + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + netserver -6 ${dst_port} -L "${dst_addr6}" \ + >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B netperf -6 -H "${dst_addr6}" ${dst_port} \ + -L "${src_addr6}" -l 1000 -t TCP_STREAM + + src_addr6= + src_port= + dst_port= + } + else + return 1 + fi +} + +# Set up function to send UDP traffic on IPv4 +setup_flood_udp() { + if command -v iperf3 >/dev/null; then + flood_udp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + src_addr4="-B ${src_addr4}" + else + B ip addr add dev veth_b 10.0.0.2 2>/dev/null + src_addr4="-B 10.0.0.2" + fi + if [ -n "${src_port}" ]; then + src_port="--cport ${src_port}" + fi + B ip route add default dev veth_b + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf3 -s -DB "${dst_addr4}" ${dst_port} + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf3 -u -c "${dst_addr4}" -Z -b 100M -l16 -t1000 \ + ${dst_port} ${src_port} ${src_addr4} + + src_addr4= + src_port= + dst_port= + } + elif command -v iperf >/dev/null; then + flood_udp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + src_addr4="-B ${src_addr4}" + else + B ip addr add dev veth_b 10.0.0.2 + src_addr4="-B 10.0.0.2" + fi + if [ -n "${src_port}" ]; then + src_addr4="${src_addr4}:${src_port}" + fi + B ip route add default dev veth_b + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf -u -sDB "${dst_addr4}" ${dst_port} >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf -u -c "${dst_addr4}" -b 100M -l1 -t1000 \ + ${dst_port} ${src_addr4} + + src_addr4= + src_port= + dst_port= + } + elif command -v netperf >/dev/null; then + flood_udp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + else + B ip addr add dev veth_b 10.0.0.2 + src_addr4="10.0.0.2" + fi + if [ -n "${src_port}" ]; then + dst_port="${dst_port},${src_port}" + fi + B ip route add default dev veth_b + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + netserver -4 ${dst_port} -L "${dst_addr4}" \ + >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B netperf -4 -H "${dst_addr4}" ${dst_port} \ + -L "${src_addr4}" -l 1000 -t UDP_STREAM + + src_addr4= + src_port= + dst_port= + } + else + return 1 + fi +} + +# Find pktgen script and set up function to start pktgen injection +setup_perf() { + for pktgen_script_path in ${PKTGEN_SCRIPT_PATHS} __notfound; do + command -v "${pktgen_script_path}" >/dev/null && break + done + [ "${pktgen_script_path}" = "__notfound" ] && return 1 + + perf_ipv4() { + ${pktgen_script_path} -s80 \ + -i veth_a -d "${dst_addr4}" -p "${dst_port}" \ + -m "${dst_mac}" \ + -t $(($(nproc) / 5 + 1)) -b10000 -n0 2>/dev/null & + perf_pid=$! + } + perf_ipv6() { + IP6=6 ${pktgen_script_path} -s100 \ + -i veth_a -d "${dst_addr6}" -p "${dst_port}" \ + -m "${dst_mac}" \ + -t $(($(nproc) / 5 + 1)) -b10000 -n0 2>/dev/null & + perf_pid=$! + } +} + +# Clean up before each test +cleanup() { + nft reset counter inet filter test >/dev/null 2>&1 + nft flush ruleset >/dev/null 2>&1 + ip link del dummy0 2>/dev/null + ip route del default 2>/dev/null + ip -6 route del default 2>/dev/null + ip netns del B 2>/dev/null + ip link del veth_a 2>/dev/null + timeout= + killall iperf3 2>/dev/null + killall iperf 2>/dev/null + killall netperf 2>/dev/null + killall netserver 2>/dev/null + rm -f ${tmp} + sleep 2 +} + +# Entry point for setup functions +setup() { + if [ "$(id -u)" -ne 0 ]; then + echo " need to run as root" + exit ${KSELFTEST_SKIP} + fi + + cleanup + check_tools || return 1 + for arg do + if ! eval setup_"${arg}"; then + err " ${arg} not supported" + return 1 + fi + done +} + +# Format integer into IPv4 address, summing 10.0.0.5 (arbitrary) to it +format_addr4() { + a=$((${1} + 16777216 * 10 + 5)) + printf "%i.%i.%i.%i" \ + "$((a / 16777216))" "$((a % 16777216 / 65536))" \ + "$((a % 65536 / 256))" "$((a % 256))" +} + +# Format integer into IPv6 address, summing 2001:db8:: to it +format_addr6() { + printf "2001:db8::%04x:%04x" "$((${1} / 65536))" "$((${1} % 65536))" +} + +# Format integer into EUI-48 address, summing 00:01:00:00:00:00 to it +format_mac() { + printf "00:01:%02x:%02x:%02x:%02x" \ + "$((${1} / 16777216))" "$((${1} % 16777216 / 65536))" \ + "$((${1} % 65536 / 256))" "$((${1} % 256))" +} + +# Format integer into port, avoid 0 port +format_port() { + printf "%i" "$((${1} % 65534 + 1))" +} + +# Drop suffixed '6' from L4 protocol, if any +format_proto() { + printf "%s" "${proto}" | tr -d 6 +} + +# Format destination and source fields into nft concatenated type +format() { + __start= + __end= + __expr="{ " + + for f in ${dst}; do + [ "${__expr}" != "{ " ] && __expr="${__expr} . " + + __start="$(eval format_"${f}" "${start}")" + __end="$(eval format_"${f}" "${end}")" + + if [ "${f}" = "proto" ]; then + __expr="${__expr}${__start}" + else + __expr="${__expr}${__start}-${__end}" + fi + done + for f in ${src}; do + __expr="${__expr} . " + __start="$(eval format_"${f}" "${srcstart}")" + __end="$(eval format_"${f}" "${srcend}")" + + if [ "${f}" = "proto" ]; then + __expr="${__expr}${__start}" + else + __expr="${__expr}${__start}-${__end}" + fi + done + + if [ -n "${timeout}" ]; then + echo "${__expr} timeout ${timeout}s }" + else + echo "${__expr} }" + fi +} + +# Format destination and source fields into nft type, start element only +format_norange() { + __expr="{ " + + for f in ${dst}; do + [ "${__expr}" != "{ " ] && __expr="${__expr} . " + + __expr="${__expr}$(eval format_"${f}" "${start}")" + done + for f in ${src}; do + __expr="${__expr} . $(eval format_"${f}" "${start}")" + done + + echo "${__expr} }" +} + +# Format first destination field into nft type +format_noconcat() { + for f in ${dst}; do + __start="$(eval format_"${f}" "${start}")" + __end="$(eval format_"${f}" "${end}")" + + if [ "${f}" = "proto" ]; then + echo "{ ${__start} }" + else + echo "{ ${__start}-${__end} }" + fi + return + done +} + +# Add single entry to 'test' set in 'inet filter' table +add() { + if ! nft add element inet filter test "${1}"; then + err "Failed to add ${1} given ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi +} + +# Format and output entries for sets in 'netdev perf' table +add_perf() { + if [ "${1}" = "test" ]; then + echo "add element netdev perf test $(format)" + elif [ "${1}" = "norange" ]; then + echo "add element netdev perf norange $(format_norange)" + elif [ "${1}" = "noconcat" ]; then + echo "add element netdev perf noconcat $(format_noconcat)" + fi +} + +# Add single entry to 'norange' set in 'netdev perf' table +add_perf_norange() { + if ! nft add element netdev perf norange "${1}"; then + err "Failed to add ${1} given ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi +} + +# Add single entry to 'noconcat' set in 'netdev perf' table +add_perf_noconcat() { + if ! nft add element netdev perf noconcat "${1}"; then + err "Failed to add ${1} given ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi +} + +# Delete single entry from set +del() { + if ! nft delete element inet filter test "${1}"; then + err "Failed to delete ${1} given ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi +} + +# Return packet count from 'test' counter in 'inet filter' table +count_packets() { + found=0 + for token in $(nft list counter inet filter test); do + [ ${found} -eq 1 ] && echo "${token}" && return + [ "${token}" = "packets" ] && found=1 + done +} + +# Return packet count from 'test' counter in 'netdev perf' table +count_perf_packets() { + found=0 + for token in $(nft list counter netdev perf test); do + [ ${found} -eq 1 ] && echo "${token}" && return + [ "${token}" = "packets" ] && found=1 + done +} + +# Set MAC addresses, send traffic according to specifier +flood() { + ip link set veth_a address "$(format_mac "${1}")" + ip -n B link set veth_b address "$(format_mac "${2}")" + + for f in ${dst}; do + eval dst_"$f"=\$\(format_\$f "${1}"\) + done + for f in ${src}; do + eval src_"$f"=\$\(format_\$f "${2}"\) + done + eval flood_\$proto +} + +# Set MAC addresses, start pktgen injection +perf() { + dst_mac="$(format_mac "${1}")" + ip link set veth_a address "${dst_mac}" + + for f in ${dst}; do + eval dst_"$f"=\$\(format_\$f "${1}"\) + done + for f in ${src}; do + eval src_"$f"=\$\(format_\$f "${2}"\) + done + eval perf_\$perf_proto +} + +# Set MAC addresses, send single packet, check that it matches, reset counter +send_match() { + ip link set veth_a address "$(format_mac "${1}")" + ip -n B link set veth_b address "$(format_mac "${2}")" + + for f in ${dst}; do + eval dst_"$f"=\$\(format_\$f "${1}"\) + done + for f in ${src}; do + eval src_"$f"=\$\(format_\$f "${2}"\) + done + eval send_\$proto + if [ "$(count_packets)" != "1" ]; then + err "${proto} packet to:" + err " $(for f in ${dst}; do + eval format_\$f "${1}"; printf ' '; done)" + err "from:" + err " $(for f in ${src}; do + eval format_\$f "${2}"; printf ' '; done)" + err "should have matched ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi + nft reset counter inet filter test >/dev/null +} + +# Set MAC addresses, send single packet, check that it doesn't match +send_nomatch() { + ip link set veth_a address "$(format_mac "${1}")" + ip -n B link set veth_b address "$(format_mac "${2}")" + + for f in ${dst}; do + eval dst_"$f"=\$\(format_\$f "${1}"\) + done + for f in ${src}; do + eval src_"$f"=\$\(format_\$f "${2}"\) + done + eval send_\$proto + if [ "$(count_packets)" != "0" ]; then + err "${proto} packet to:" + err " $(for f in ${dst}; do + eval format_\$f "${1}"; printf ' '; done)" + err "from:" + err " $(for f in ${src}; do + eval format_\$f "${2}"; printf ' '; done)" + err "should not have matched ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi +} + +# Correctness test template: +# - add ranged element, check that packets match it +# - check that packets outside range don't match it +# - remove some elements, check that packets don't match anymore +test_correctness() { + setup veth send_"${proto}" set || return ${KSELFTEST_SKIP} + + range_size=1 + for i in $(seq "${start}" $((start + count))); do + end=$((start + range_size)) + + # Avoid negative or zero-sized port ranges + if [ $((end / 65534)) -gt $((start / 65534)) ]; then + start=${end} + end=$((end + 1)) + fi + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" || return 1 + for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do + send_match "${j}" $((j + src_delta)) || return 1 + done + send_nomatch $((end + 1)) $((end + 1 + src_delta)) || return 1 + + # Delete elements now and then + if [ $((i % 3)) -eq 0 ]; then + del "$(format)" || return 1 + for j in $(seq ${start} \ + $((range_size / 2 + 1)) ${end}); do + send_nomatch "${j}" $((j + src_delta)) \ + || return 1 + done + fi + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done +} + +# Concurrency test template: +# - add all the elements +# - start a thread for each physical thread that: +# - adds all the elements +# - flushes the set +# - adds all the elements +# - flushes the entire ruleset +# - adds the set back +# - adds all the elements +# - delete all the elements +test_concurrency() { + proto=${flood_proto} + tools=${flood_tools} + chain_spec=${flood_spec} + setup veth flood_"${proto}" set || return ${KSELFTEST_SKIP} + + range_size=1 + cstart=${start} + flood_pids= + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" || return 1 + + flood "${i}" $((i + src_delta)) & flood_pids="${flood_pids} $!" + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + sleep 10 + + pids= + for c in $(seq 1 "$(nproc)"); do ( + for r in $(seq 1 "${race_repeat}"); do + range_size=1 + + # $start needs to be local to this subshell + # shellcheck disable=SC2030 + start=${cstart} + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" 2>/dev/null + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + nft flush inet filter test 2>/dev/null + + range_size=1 + start=${cstart} + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" 2>/dev/null + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + nft flush ruleset + setup set 2>/dev/null + + range_size=1 + start=${cstart} + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" 2>/dev/null + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + range_size=1 + start=${cstart} + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + del "$(format)" 2>/dev/null + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + done + ) & pids="${pids} $!" + done + + # shellcheck disable=SC2046,SC2086 # word splitting wanted here + wait $(for pid in ${pids}; do echo ${pid}; done) + # shellcheck disable=SC2046,SC2086 + kill $(for pid in ${flood_pids}; do echo ${pid}; done) 2>/dev/null + # shellcheck disable=SC2046,SC2086 + wait $(for pid in ${flood_pids}; do echo ${pid}; done) 2>/dev/null + + return 0 +} + +# Timeout test template: +# - add all the elements with 3s timeout while checking that packets match +# - wait 3s after the last insertion, check that packets don't match any entry +test_timeout() { + setup veth send_"${proto}" set || return ${KSELFTEST_SKIP} + + timeout=3 + range_size=1 + for i in $(seq "${start}" $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" || return 1 + + for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do + send_match "${j}" $((j + src_delta)) || return 1 + done + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + sleep 3 + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do + send_nomatch "${j}" $((j + src_delta)) || return 1 + done + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done +} + +# Performance test template: +# - add concatenated ranged entries +# - add non-ranged concatenated entries (for hash set matching rate baseline) +# - add ranged entries with first field only (for rbhash baseline) +# - start pktgen injection directly on device rx path of this namespace +# - measure drop only rate, hash and rbtree baselines, then matching rate +test_performance() { + chain_spec=${perf_spec} + dst="${perf_dst}" + src="${perf_src}" + setup veth perf set || return ${KSELFTEST_SKIP} + + first=${start} + range_size=1 + for set in test norange noconcat; do + start=${first} + for i in $(seq ${start} $((start + perf_entries))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + if [ $((end / 65534)) -gt $((start / 65534)) ]; then + start=${end} + end=$((end + 1)) + elif [ ${start} -eq ${end} ]; then + end=$((start + 1)) + fi + + add_perf ${set} + + start=$((end + range_size)) + done > "${tmp}" + nft -f "${tmp}" + done + + perf $((end - 1)) ${srcstart} + + sleep 2 + + nft add rule netdev perf test counter name \"test\" drop + nft reset counter netdev perf test >/dev/null 2>&1 + sleep "${perf_duration}" + pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))" + info " baseline (drop from netdev hook): ${pps}pps" + handle="$(nft -a list chain netdev perf test | grep counter)" + handle="${handle##* }" + nft delete rule netdev perf test handle "${handle}" + + nft add rule "netdev perf test ${chain_spec} @norange \ + counter name \"test\" drop" + nft reset counter netdev perf test >/dev/null 2>&1 + sleep "${perf_duration}" + pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))" + info " baseline hash (non-ranged entries): ${pps}pps" + handle="$(nft -a list chain netdev perf test | grep counter)" + handle="${handle##* }" + nft delete rule netdev perf test handle "${handle}" + + nft add rule "netdev perf test ${chain_spec%%. *} @noconcat \ + counter name \"test\" drop" + nft reset counter netdev perf test >/dev/null 2>&1 + sleep "${perf_duration}" + pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))" + info " baseline rbtree (match on first field only): ${pps}pps" + handle="$(nft -a list chain netdev perf test | grep counter)" + handle="${handle##* }" + nft delete rule netdev perf test handle "${handle}" + + nft add rule "netdev perf test ${chain_spec} @test \ + counter name \"test\" drop" + nft reset counter netdev perf test >/dev/null 2>&1 + sleep "${perf_duration}" + pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))" + p5="$(printf %5s "${perf_entries}")" + info " set with ${p5} full, ranged entries: ${pps}pps" + kill "${perf_pid}" +} + +# Run everything in a separate network namespace +[ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; } +tmp="$(mktemp)" +trap cleanup EXIT + +# Entry point for test runs +passed=0 +for name in ${TESTS}; do + printf "TEST: %s\n" "${name}" + for type in ${TYPES}; do + eval desc=\$TYPE_"${type}" + IFS=' +' + for __line in ${desc}; do + # shellcheck disable=SC2086 + eval ${__line%% *}=\"${__line##* }\"; + done + IFS=' +' + + if [ "${name}" = "concurrency" ] && \ + [ "${race_repeat}" = "0" ]; then + continue + fi + if [ "${name}" = "performance" ] && \ + [ "${perf_duration}" = "0" ]; then + continue + fi + + printf " %-60s " "${display}" + eval test_"${name}" + ret=$? + + if [ $ret -eq 0 ]; then + printf "[ OK ]\n" + info_flush + passed=$((passed + 1)) + elif [ $ret -eq 1 ]; then + printf "[FAIL]\n" + err_flush + exit 1 + elif [ $ret -eq ${KSELFTEST_SKIP} ]; then + printf "[SKIP]\n" + err_flush + fi + done +done + +[ ${passed} -eq 0 ] && exit ${KSELFTEST_SKIP} |