diff options
Diffstat (limited to 'tools/testing/selftests/net/mptcp')
| -rw-r--r-- | tools/testing/selftests/net/mptcp/.gitignore | 6 | ||||
| -rw-r--r-- | tools/testing/selftests/net/mptcp/Makefile | 16 | ||||
| -rw-r--r-- | tools/testing/selftests/net/mptcp/config | 31 | ||||
| -rwxr-xr-x | tools/testing/selftests/net/mptcp/diag.sh | 241 | ||||
| -rw-r--r-- | tools/testing/selftests/net/mptcp/mptcp_connect.c | 1415 | ||||
| -rwxr-xr-x | tools/testing/selftests/net/mptcp/mptcp_connect.sh | 934 | ||||
| -rw-r--r-- | tools/testing/selftests/net/mptcp/mptcp_inq.c | 599 | ||||
| -rwxr-xr-x | tools/testing/selftests/net/mptcp/mptcp_join.sh | 3327 | ||||
| -rw-r--r-- | tools/testing/selftests/net/mptcp/mptcp_lib.sh | 104 | ||||
| -rw-r--r-- | tools/testing/selftests/net/mptcp/mptcp_sockopt.c | 752 | ||||
| -rwxr-xr-x | tools/testing/selftests/net/mptcp/mptcp_sockopt.sh | 367 | ||||
| -rwxr-xr-x | tools/testing/selftests/net/mptcp/pm_netlink.sh | 196 | ||||
| -rw-r--r-- | tools/testing/selftests/net/mptcp/pm_nl_ctl.c | 1505 | ||||
| -rw-r--r-- | tools/testing/selftests/net/mptcp/settings | 1 | ||||
| -rwxr-xr-x | tools/testing/selftests/net/mptcp/simult_flows.sh | 310 | ||||
| -rwxr-xr-x | tools/testing/selftests/net/mptcp/userspace_pm.sh | 886 |
16 files changed, 10690 insertions, 0 deletions
diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore new file mode 100644 index 000000000..49daae73c --- /dev/null +++ b/tools/testing/selftests/net/mptcp/.gitignore @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0-only +mptcp_connect +mptcp_inq +mptcp_sockopt +pm_nl_ctl +*.pcap diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile new file mode 100644 index 000000000..7b936a926 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -0,0 +1,16 @@ +# SPDX-License-Identifier: GPL-2.0 + +top_srcdir = ../../../../.. + +CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) + +TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ + simult_flows.sh mptcp_sockopt.sh userspace_pm.sh + +TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq + +TEST_FILES := mptcp_lib.sh settings + +EXTRA_CLEAN := *.pcap + +include ../../lib.mk diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config new file mode 100644 index 000000000..e317c2e44 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/config @@ -0,0 +1,31 @@ +CONFIG_KALLSYMS=y +CONFIG_MPTCP=y +CONFIG_IPV6=y +CONFIG_MPTCP_IPV6=y +CONFIG_INET_DIAG=m +CONFIG_INET_MPTCP_DIAG=m +CONFIG_VETH=y +CONFIG_NET_SCH_NETEM=m +CONFIG_SYN_COOKIES=y +CONFIG_NETFILTER=y +CONFIG_NETFILTER_ADVANCED=y +CONFIG_NETFILTER_NETLINK=m +CONFIG_NF_TABLES=m +CONFIG_NFT_COMPAT=m +CONFIG_NETFILTER_XTABLES=m +CONFIG_NETFILTER_XT_MATCH_BPF=m +CONFIG_NETFILTER_XT_MATCH_LENGTH=m +CONFIG_NETFILTER_XT_MATCH_STATISTIC=m +CONFIG_NETFILTER_XT_TARGET_MARK=m +CONFIG_NF_TABLES_INET=y +CONFIG_NFT_TPROXY=m +CONFIG_NFT_SOCKET=m +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_NET_ACT_CSUM=m +CONFIG_NET_ACT_PEDIT=m +CONFIG_NET_CLS_ACT=y +CONFIG_NET_CLS_FW=m +CONFIG_NET_SCH_INGRESS=m diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh new file mode 100755 index 000000000..400cf1ce9 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -0,0 +1,241 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(dirname "${0}")/mptcp_lib.sh" + +rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) +ns="ns1-$rndh" +ksft_skip=4 +test_cnt=1 +timeout_poll=100 +timeout_test=$((timeout_poll * 2 + 1)) +ret=0 + +flush_pids() +{ + # mptcp_connect in join mode will sleep a bit before completing, + # give it some time + sleep 1.1 + + ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGUSR1 &>/dev/null +} + +cleanup() +{ + ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGKILL &>/dev/null + + ip netns del $ns +} + +mptcp_lib_check_mptcp + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi +ss -h | grep -q MPTCP +if [ $? -ne 0 ];then + echo "SKIP: ss tool does not support MPTCP" + exit $ksft_skip +fi + +__chk_nr() +{ + local command="$1" + local expected=$2 + local msg="$3" + local skip="${4:-SKIP}" + local nr + + nr=$(eval $command) + + printf "%-50s" "$msg" + if [ $nr != $expected ]; then + if [ $nr = "$skip" ] && ! mptcp_lib_expect_all_features; then + echo "[ skip ] Feature probably not supported" + else + echo "[ fail ] expected $expected found $nr" + ret=$test_cnt + fi + else + echo "[ ok ]" + fi + test_cnt=$((test_cnt+1)) +} + +__chk_msk_nr() +{ + local condition=$1 + shift 1 + + __chk_nr "ss -inmHMN $ns | $condition" "$@" +} + +chk_msk_nr() +{ + __chk_msk_nr "grep -c token:" "$@" +} + +wait_msk_nr() +{ + local condition="grep -c token:" + local expected=$1 + local timeout=20 + local msg nr + local max=0 + local i=0 + + shift 1 + msg=$* + + while [ $i -lt $timeout ]; do + nr=$(ss -inmHMN $ns | $condition) + [ $nr == $expected ] && break; + [ $nr -gt $max ] && max=$nr + i=$((i + 1)) + sleep 1 + done + + printf "%-50s" "$msg" + if [ $i -ge $timeout ]; then + echo "[ fail ] timeout while expecting $expected max $max last $nr" + ret=$test_cnt + elif [ $nr != $expected ]; then + echo "[ fail ] expected $expected found $nr" + ret=$test_cnt + else + echo "[ ok ]" + fi + test_cnt=$((test_cnt+1)) +} + +chk_msk_fallback_nr() +{ + __chk_msk_nr "grep -c fallback" "$@" +} + +chk_msk_remote_key_nr() +{ + __chk_msk_nr "grep -c remote_key" "$@" +} + +__chk_listen() +{ + local filter="$1" + local expected=$2 + local msg="$3" + + __chk_nr "ss -N $ns -Ml '$filter' | grep -c LISTEN" "$expected" "$msg" 0 +} + +chk_msk_listen() +{ + lport=$1 + + # destination port search should always return empty list + __chk_listen "dport $lport" 0 "listen match for dport $lport" + + # should return 'our' mptcp listen socket + __chk_listen "sport $lport" 1 "listen match for sport $lport" + + __chk_listen "src inet:0.0.0.0:$lport" 1 "listen match for saddr and sport" + + __chk_listen "" 1 "all listen sockets" + + nr=$(ss -Ml $filter | wc -l) +} + +# $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 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" && + break + sleep 0.1 + done +} + +wait_connected() +{ + local listener_ns="${1}" + local port="${2}" + + local port_hex i + + port_hex="$(printf "%04X" "${port}")" + for i in $(seq 10); do + ip netns exec ${listener_ns} grep -q " 0100007F:${port_hex} " /proc/net/tcp && break + sleep 0.1 + done +} + +trap cleanup EXIT +ip netns add $ns +ip -n $ns link set dev lo up + +echo "a" | \ + timeout ${timeout_test} \ + ip netns exec $ns \ + ./mptcp_connect -p 10000 -l -t ${timeout_poll} -w 20 \ + 0.0.0.0 >/dev/null & +wait_local_port_listen $ns 10000 +chk_msk_nr 0 "no msk on netns creation" +chk_msk_listen 10000 + +echo "b" | \ + timeout ${timeout_test} \ + ip netns exec $ns \ + ./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} -w 20 \ + 127.0.0.1 >/dev/null & +wait_connected $ns 10000 +chk_msk_nr 2 "after MPC handshake " +chk_msk_remote_key_nr 2 "....chk remote_key" +chk_msk_fallback_nr 0 "....chk no fallback" +flush_pids + + +echo "a" | \ + timeout ${timeout_test} \ + ip netns exec $ns \ + ./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} -w 20 \ + 0.0.0.0 >/dev/null & +wait_local_port_listen $ns 10001 +echo "b" | \ + timeout ${timeout_test} \ + ip netns exec $ns \ + ./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} -w 20 \ + 127.0.0.1 >/dev/null & +wait_connected $ns 10001 +chk_msk_fallback_nr 1 "check fallback" +flush_pids + +NR_CLIENTS=100 +for I in `seq 1 $NR_CLIENTS`; do + echo "a" | \ + timeout ${timeout_test} \ + ip netns exec $ns \ + ./mptcp_connect -p $((I+10001)) -l -w 20 \ + -t ${timeout_poll} 0.0.0.0 >/dev/null & +done +wait_local_port_listen $ns $((NR_CLIENTS + 10001)) + +for I in `seq 1 $NR_CLIENTS`; do + echo "b" | \ + timeout ${timeout_test} \ + ip netns exec $ns \ + ./mptcp_connect -p $((I+10001)) -w 20 \ + -t ${timeout_poll} 127.0.0.1 >/dev/null & +done + +wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present" +flush_pids + +exit $ret 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 000000000..e6b514cb7 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -0,0 +1,1415 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <errno.h> +#include <limits.h> +#include <fcntl.h> +#include <string.h> +#include <stdarg.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <strings.h> +#include <signal.h> +#include <unistd.h> +#include <time.h> + +#include <sys/ioctl.h> +#include <sys/poll.h> +#include <sys/random.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> +#include <linux/time_types.h> +#include <linux/sockios.h> + +extern int optind; + +#ifndef IPPROTO_MPTCP +#define IPPROTO_MPTCP 262 +#endif +#ifndef TCP_ULP +#define TCP_ULP 31 +#endif + +static int poll_timeout = 10 * 1000; +static bool listen_mode; +static bool quit; + +enum cfg_mode { + CFG_MODE_POLL, + CFG_MODE_MMAP, + CFG_MODE_SENDFILE, +}; + +enum cfg_peek { + CFG_NONE_PEEK, + CFG_WITH_PEEK, + CFG_AFTER_PEEK, +}; + +static enum cfg_mode cfg_mode = CFG_MODE_POLL; +static enum cfg_peek cfg_peek = CFG_NONE_PEEK; +static const char *cfg_host; +static const char *cfg_port = "12000"; +static int cfg_sock_proto = IPPROTO_MPTCP; +static int pf = AF_INET; +static int cfg_sndbuf; +static int cfg_rcvbuf; +static bool cfg_join; +static bool cfg_remove; +static unsigned int cfg_time; +static unsigned int cfg_do_w; +static int cfg_wait; +static uint32_t cfg_mark; +static char *cfg_input; +static int cfg_repeat = 1; +static int cfg_truncate; +static int cfg_rcv_trunc; + +struct cfg_cmsg_types { + unsigned int cmsg_enabled:1; + unsigned int timestampns:1; + unsigned int tcp_inq:1; +}; + +struct cfg_sockopt_types { + unsigned int transparent:1; +}; + +struct tcp_inq_state { + unsigned int last; + bool expect_eof; +}; + +static struct tcp_inq_state tcp_inq; + +static struct cfg_cmsg_types cfg_cmsg_types; +static struct cfg_sockopt_types cfg_sockopt_types; + +static void die_usage(void) +{ + fprintf(stderr, "Usage: mptcp_connect [-6] [-c cmsg] [-f offset] [-i file] [-I num] [-j] [-l] " + "[-m mode] [-M mark] [-o option] [-p port] [-P mode] [-r num] [-R num] " + "[-s MPTCP|TCP] [-S num] [-t num] [-T num] [-w sec] connect_address\n"); + fprintf(stderr, "\t-6 use ipv6\n"); + fprintf(stderr, "\t-c cmsg -- test cmsg type <cmsg>\n"); + fprintf(stderr, "\t-f offset -- stop the I/O after receiving and sending the specified amount " + "of bytes. If there are unread bytes in the receive queue, that will cause a MPTCP " + "fastclose at close/shutdown. If offset is negative, expect the peer to close before " + "all the local data as been sent, thus toleration errors on write and EPIPE signals\n"); + fprintf(stderr, "\t-i file -- read the data to send from the given file instead of stdin"); + fprintf(stderr, "\t-I num -- repeat the transfer 'num' times. In listen mode accepts num " + "incoming connections, in client mode, disconnect and reconnect to the server\n"); + fprintf(stderr, "\t-j -- add additional sleep at connection start and tear down " + "-- for MPJ tests\n"); + fprintf(stderr, "\t-l -- listens mode, accepts incoming connection\n"); + fprintf(stderr, "\t-m [poll|mmap|sendfile] -- use poll(default)/mmap+write/sendfile\n"); + fprintf(stderr, "\t-M mark -- set socket packet mark\n"); + fprintf(stderr, "\t-o option -- test sockopt <option>\n"); + fprintf(stderr, "\t-p num -- use port num\n"); + fprintf(stderr, + "\t-P [saveWithPeek|saveAfterPeek] -- save data with/after MSG_PEEK form tcp socket\n"); + fprintf(stderr, "\t-r num -- enable slow mode, limiting each write to num bytes " + "-- for remove addr tests\n"); + fprintf(stderr, "\t-R num -- set SO_RCVBUF to num\n"); + fprintf(stderr, "\t-s [MPTCP|TCP] -- use mptcp(default) or tcp sockets\n"); + fprintf(stderr, "\t-S num -- set SO_SNDBUF to num\n"); + fprintf(stderr, "\t-t num -- set poll timeout to num\n"); + fprintf(stderr, "\t-T num -- set expected runtime to num ms\n"); + fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n"); + exit(1); +} + +static void xerror(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + exit(1); +} + +static void handle_signal(int nr) +{ + quit = true; +} + +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_rcvbuf(int fd, unsigned int size) +{ + int err; + + err = setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &size, sizeof(size)); + if (err) { + perror("set SO_RCVBUF"); + 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 void set_mark(int fd, uint32_t mark) +{ + int err; + + err = setsockopt(fd, SOL_SOCKET, SO_MARK, &mark, sizeof(mark)); + if (err) { + perror("set SO_MARK"); + exit(1); + } +} + +static void set_transparent(int fd, int pf) +{ + int one = 1; + + switch (pf) { + case AF_INET: + if (-1 == setsockopt(fd, SOL_IP, IP_TRANSPARENT, &one, sizeof(one))) + perror("IP_TRANSPARENT"); + break; + case AF_INET6: + if (-1 == setsockopt(fd, IPPROTO_IPV6, IPV6_TRANSPARENT, &one, sizeof(one))) + perror("IPV6_TRANSPARENT"); + break; + } +} + +static int do_ulp_so(int sock, const char *name) +{ + return setsockopt(sock, IPPROTO_TCP, TCP_ULP, name, strlen(name)); +} + +#define X(m) xerror("%s:%u: %s: failed for proto %d at line %u", __FILE__, __LINE__, (m), proto, line) +static void sock_test_tcpulp(int sock, int proto, unsigned int line) +{ + socklen_t buflen = 8; + char buf[8] = ""; + int ret = getsockopt(sock, IPPROTO_TCP, TCP_ULP, buf, &buflen); + + if (ret != 0) + X("getsockopt"); + + if (buflen > 0) { + if (strcmp(buf, "mptcp") != 0) + xerror("unexpected ULP '%s' for proto %d at line %u", buf, proto, line); + ret = do_ulp_so(sock, "tls"); + if (ret == 0) + X("setsockopt"); + } else if (proto == IPPROTO_MPTCP) { + ret = do_ulp_so(sock, "tls"); + if (ret != -1) + X("setsockopt"); + } + + ret = do_ulp_so(sock, "mptcp"); + if (ret != -1) + X("setsockopt"); + +#undef X +} + +#define SOCK_TEST_TCPULP(s, p) sock_test_tcpulp((s), (p), __LINE__) + +static int sock_listen_mptcp(const char * const listenaddr, + const char * const port) +{ + int sock = -1; + 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; + + SOCK_TEST_TCPULP(sock, cfg_sock_proto); + + if (-1 == setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &one, + sizeof(one))) + perror("setsockopt"); + + if (cfg_sockopt_types.transparent) + set_transparent(sock, pf); + + 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; + } + + SOCK_TEST_TCPULP(sock, cfg_sock_proto); + + if (listen(sock, 20)) { + perror("listen"); + close(sock); + return -1; + } + + SOCK_TEST_TCPULP(sock, cfg_sock_proto); + + return sock; +} + +static int sock_connect_mptcp(const char * const remoteaddr, + const char * const port, int proto, + struct addrinfo **peer) +{ + 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; + } + + SOCK_TEST_TCPULP(sock, proto); + + if (cfg_mark) + set_mark(sock, cfg_mark); + + if (connect(sock, a->ai_addr, a->ai_addrlen) == 0) { + *peer = a; + break; /* success */ + } + + perror("connect()"); + close(sock); + sock = -1; + } + + freeaddrinfo(addr); + if (sock != -1) + SOCK_TEST_TCPULP(sock, proto); + return sock; +} + +static size_t do_rnd_write(const int fd, char *buf, const size_t len) +{ + static bool first = true; + unsigned int do_w; + ssize_t bw; + + do_w = rand() & 0xffff; + if (do_w == 0 || do_w > len) + do_w = len; + + if (cfg_join && first && do_w > 100) + do_w = 100; + + if (cfg_remove && do_w > cfg_do_w) + do_w = cfg_do_w; + + bw = write(fd, buf, do_w); + if (bw < 0) + return bw; + + /* let the join handshake complete, before going on */ + if (cfg_join && first) { + usleep(200000); + first = false; + } + + if (cfg_remove) + usleep(200000); + + 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 void process_cmsg(struct msghdr *msgh) +{ + struct __kernel_timespec ts; + bool inq_found = false; + bool ts_found = false; + unsigned int inq = 0; + struct cmsghdr *cmsg; + + for (cmsg = CMSG_FIRSTHDR(msgh); cmsg ; cmsg = CMSG_NXTHDR(msgh, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type == SO_TIMESTAMPNS_NEW) { + memcpy(&ts, CMSG_DATA(cmsg), sizeof(ts)); + ts_found = true; + continue; + } + if (cmsg->cmsg_level == IPPROTO_TCP && cmsg->cmsg_type == TCP_CM_INQ) { + memcpy(&inq, CMSG_DATA(cmsg), sizeof(inq)); + inq_found = true; + continue; + } + + } + + if (cfg_cmsg_types.timestampns) { + if (!ts_found) + xerror("TIMESTAMPNS not present\n"); + } + + if (cfg_cmsg_types.tcp_inq) { + if (!inq_found) + xerror("TCP_INQ not present\n"); + + if (inq > 1024) + xerror("tcp_inq %u is larger than one kbyte\n", inq); + tcp_inq.last = inq; + } +} + +static ssize_t do_recvmsg_cmsg(const int fd, char *buf, const size_t len) +{ + char msg_buf[8192]; + struct iovec iov = { + .iov_base = buf, + .iov_len = len, + }; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_control = msg_buf, + .msg_controllen = sizeof(msg_buf), + }; + int flags = 0; + unsigned int last_hint = tcp_inq.last; + int ret = recvmsg(fd, &msg, flags); + + if (ret <= 0) { + if (ret == 0 && tcp_inq.expect_eof) + return ret; + + if (ret == 0 && cfg_cmsg_types.tcp_inq) + if (last_hint != 1 && last_hint != 0) + xerror("EOF but last tcp_inq hint was %u\n", last_hint); + + return ret; + } + + if (tcp_inq.expect_eof) + xerror("expected EOF, last_hint %u, now %u\n", + last_hint, tcp_inq.last); + + if (msg.msg_controllen && !cfg_cmsg_types.cmsg_enabled) + xerror("got %lu bytes of cmsg data, expected 0\n", + (unsigned long)msg.msg_controllen); + + if (msg.msg_controllen == 0 && cfg_cmsg_types.cmsg_enabled) + xerror("%s\n", "got no cmsg data"); + + if (msg.msg_controllen) + process_cmsg(&msg); + + if (cfg_cmsg_types.tcp_inq) { + if ((size_t)ret < len && last_hint > (unsigned int)ret) { + if (ret + 1 != (int)last_hint) { + int next = read(fd, msg_buf, sizeof(msg_buf)); + + xerror("read %u of %u, last_hint was %u tcp_inq hint now %u next_read returned %d/%m\n", + ret, (unsigned int)len, last_hint, tcp_inq.last, next); + } else { + tcp_inq.expect_eof = true; + } + } + } + + return ret; +} + +static ssize_t do_rnd_read(const int fd, char *buf, const size_t len) +{ + int ret = 0; + char tmp[16384]; + size_t cap = rand(); + + cap &= 0xffff; + + if (cap == 0) + cap = 1; + else if (cap > len) + cap = len; + + if (cfg_peek == CFG_WITH_PEEK) { + ret = recv(fd, buf, cap, MSG_PEEK); + ret = (ret < 0) ? ret : read(fd, tmp, ret); + } else if (cfg_peek == CFG_AFTER_PEEK) { + ret = recv(fd, buf, cap, MSG_PEEK); + ret = (ret < 0) ? ret : read(fd, buf, cap); + } else if (cfg_cmsg_types.cmsg_enabled) { + ret = do_recvmsg_cmsg(fd, buf, cap); + } else { + ret = read(fd, buf, cap); + } + + return ret; +} + +static void set_nonblock(int fd, bool nonblock) +{ + int flags = fcntl(fd, F_GETFL); + + if (flags == -1) + return; + + if (nonblock) + fcntl(fd, F_SETFL, flags | O_NONBLOCK); + else + fcntl(fd, F_SETFL, flags & ~O_NONBLOCK); +} + +static void shut_wr(int fd) +{ + /* Close our write side, ev. give some time + * for address notification and/or checking + * the current status + */ + if (cfg_wait) + usleep(cfg_wait); + + shutdown(fd, SHUT_WR); +} + +static int copyfd_io_poll(int infd, int peerfd, int outfd, bool *in_closed_after_out) +{ + struct pollfd fds = { + .fd = peerfd, + .events = POLLIN | POLLOUT, + }; + unsigned int woff = 0, wlen = 0, total_wlen = 0, total_rlen = 0; + char wbuf[8192]; + + set_nonblock(peerfd, true); + + 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) { + ssize_t rb = sizeof(rbuf); + + /* limit the total amount of read data to the trunc value*/ + if (cfg_truncate > 0) { + if (rb + total_rlen > cfg_truncate) + rb = cfg_truncate - total_rlen; + len = read(peerfd, rbuf, rb); + } else { + 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) { + *in_closed_after_out = true; + /* and nothing more to send */ + break; + } + + /* Else, still have data to transmit */ + } else if (len < 0) { + if (cfg_rcv_trunc) + return 0; + perror("read"); + return 3; + } + + total_rlen += len; + 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; + + /* limit the total amount of written data to the trunc value */ + if (cfg_truncate > 0 && wlen + total_wlen > cfg_truncate) + wlen = cfg_truncate - total_wlen; + + bw = do_rnd_write(peerfd, wbuf + woff, wlen); + if (bw < 0) { + if (cfg_rcv_trunc) + return 0; + perror("write"); + return 111; + } + + woff += bw; + wlen -= bw; + total_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; + + shut_wr(peerfd); + } else { + if (errno == EINTR) + continue; + perror("read"); + return 4; + } + } + + if (fds.revents & (POLLERR | POLLNVAL)) { + if (cfg_rcv_trunc) + return 0; + fprintf(stderr, "Unexpected revents: " + "POLLERR/POLLNVAL(%x)\n", fds.revents); + return 5; + } + + if (cfg_truncate > 0 && total_wlen >= cfg_truncate && + total_rlen >= cfg_truncate) + break; + } + + /* leave some time for late join/announce */ + if (cfg_remove) + usleep(cfg_wait); + + 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, bool *in_closed_after_out) +{ + 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; + + shut_wr(peerfd); + + err = do_recvfile(peerfd, outfd); + *in_closed_after_out = true; + } + + return err; +} + +static int copyfd_io_sendfile(int infd, int peerfd, int outfd, + unsigned int size, bool *in_closed_after_out) +{ + 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; + + shut_wr(peerfd); + + err = do_recvfile(peerfd, outfd); + *in_closed_after_out = true; + } + + return err; +} + +static int copyfd_io(int infd, int peerfd, int outfd, bool close_peerfd) +{ + bool in_closed_after_out = false; + struct timespec start, end; + int file_size; + int ret; + + if (cfg_time && (clock_gettime(CLOCK_MONOTONIC, &start) < 0)) + xerror("can not fetch start time %d", errno); + + switch (cfg_mode) { + case CFG_MODE_POLL: + ret = copyfd_io_poll(infd, peerfd, outfd, &in_closed_after_out); + break; + + case CFG_MODE_MMAP: + file_size = get_infd_size(infd); + if (file_size < 0) + return file_size; + ret = copyfd_io_mmap(infd, peerfd, outfd, file_size, &in_closed_after_out); + break; + + case CFG_MODE_SENDFILE: + file_size = get_infd_size(infd); + if (file_size < 0) + return file_size; + ret = copyfd_io_sendfile(infd, peerfd, outfd, file_size, &in_closed_after_out); + break; + + default: + fprintf(stderr, "Invalid mode %d\n", cfg_mode); + + die_usage(); + return 1; + } + + if (ret) + return ret; + + if (close_peerfd) + close(peerfd); + + if (cfg_time) { + unsigned int delta_ms; + + if (clock_gettime(CLOCK_MONOTONIC, &end) < 0) + xerror("can not fetch end time %d", errno); + delta_ms = (end.tv_sec - start.tv_sec) * 1000 + (end.tv_nsec - start.tv_nsec) / 1000000; + if (delta_ms > cfg_time) { + xerror("transfer slower than expected! runtime %d ms, expected %d ms", + delta_ms, cfg_time); + } + + /* show the runtime only if this end shutdown(wr) before receiving the EOF, + * (that is, if this end got the longer runtime) + */ + if (in_closed_after_out) + fprintf(stderr, "%d", delta_ms); + } + + return 0; +} + +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); +} + +static void maybe_close(int fd) +{ + unsigned int r = rand(); + + if (!(cfg_join || cfg_remove || cfg_repeat > 1) && (r & 1)) + close(fd); +} + +int main_loop_s(int listensock) +{ + struct sockaddr_storage ss; + struct pollfd polls; + socklen_t salen; + int remotesock; + int fd = 0; + +again: + 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) { + maybe_close(listensock); + check_sockaddr(pf, &ss, salen); + check_getpeername(remotesock, &ss, salen); + + if (cfg_input) { + fd = open(cfg_input, O_RDONLY); + if (fd < 0) + xerror("can't open %s: %d", cfg_input, errno); + } + + SOCK_TEST_TCPULP(remotesock, 0); + + copyfd_io(fd, remotesock, 1, true); + } else { + perror("accept"); + return 1; + } + + if (--cfg_repeat > 0) { + if (cfg_input) + close(fd); + goto again; + } + + return 0; +} + +static void init_rng(void) +{ + unsigned int foo; + + if (getrandom(&foo, sizeof(foo), 0) == -1) { + perror("getrandom"); + exit(1); + } + + srand(foo); +} + +static void xsetsockopt(int fd, int level, int optname, const void *optval, socklen_t optlen) +{ + int err; + + err = setsockopt(fd, level, optname, optval, optlen); + if (err) { + perror("setsockopt"); + exit(1); + } +} + +static void apply_cmsg_types(int fd, const struct cfg_cmsg_types *cmsg) +{ + static const unsigned int on = 1; + + if (cmsg->timestampns) + xsetsockopt(fd, SOL_SOCKET, SO_TIMESTAMPNS_NEW, &on, sizeof(on)); + if (cmsg->tcp_inq) + xsetsockopt(fd, IPPROTO_TCP, TCP_INQ, &on, sizeof(on)); +} + +static void parse_cmsg_types(const char *type) +{ + char *next = strchr(type, ','); + unsigned int len = 0; + + cfg_cmsg_types.cmsg_enabled = 1; + + if (next) { + parse_cmsg_types(next + 1); + len = next - type; + } else { + len = strlen(type); + } + + if (strncmp(type, "TIMESTAMPNS", len) == 0) { + cfg_cmsg_types.timestampns = 1; + return; + } + + if (strncmp(type, "TCPINQ", len) == 0) { + cfg_cmsg_types.tcp_inq = 1; + return; + } + + fprintf(stderr, "Unrecognized cmsg option %s\n", type); + exit(1); +} + +static void parse_setsock_options(const char *name) +{ + char *next = strchr(name, ','); + unsigned int len = 0; + + if (next) { + parse_setsock_options(next + 1); + len = next - name; + } else { + len = strlen(name); + } + + if (strncmp(name, "TRANSPARENT", len) == 0) { + cfg_sockopt_types.transparent = 1; + return; + } + + fprintf(stderr, "Unrecognized setsockopt option %s\n", name); + exit(1); +} + +void xdisconnect(int fd, int addrlen) +{ + struct sockaddr_storage empty; + int msec_sleep = 10; + int queued = 1; + int i; + + shutdown(fd, SHUT_WR); + + /* while until the pending data is completely flushed, the later + * disconnect will bypass/ignore/drop any pending data. + */ + for (i = 0; ; i += msec_sleep) { + if (ioctl(fd, SIOCOUTQ, &queued) < 0) + xerror("can't query out socket queue: %d", errno); + + if (!queued) + break; + + if (i > poll_timeout) + xerror("timeout while waiting for spool to complete"); + usleep(msec_sleep * 1000); + } + + memset(&empty, 0, sizeof(empty)); + empty.ss_family = AF_UNSPEC; + if (connect(fd, (struct sockaddr *)&empty, addrlen) < 0) + xerror("can't disconnect: %d", errno); +} + +int main_loop(void) +{ + int fd, ret, fd_in = 0; + struct addrinfo *peer; + + /* listener is ready. */ + fd = sock_connect_mptcp(cfg_host, cfg_port, cfg_sock_proto, &peer); + if (fd < 0) + return 2; + +again: + check_getpeername_connect(fd); + + SOCK_TEST_TCPULP(fd, cfg_sock_proto); + + if (cfg_rcvbuf) + set_rcvbuf(fd, cfg_rcvbuf); + if (cfg_sndbuf) + set_sndbuf(fd, cfg_sndbuf); + if (cfg_cmsg_types.cmsg_enabled) + apply_cmsg_types(fd, &cfg_cmsg_types); + + if (cfg_input) { + fd_in = open(cfg_input, O_RDONLY); + if (fd < 0) + xerror("can't open %s:%d", cfg_input, errno); + } + + /* close the client socket open only if we are not going to reconnect */ + ret = copyfd_io(fd_in, fd, 1, 0); + if (ret) + return ret; + + if (cfg_truncate > 0) { + xdisconnect(fd, peer->ai_addrlen); + } else if (--cfg_repeat > 0) { + xdisconnect(fd, peer->ai_addrlen); + + /* the socket could be unblocking at this point, we need the + * connect to be blocking + */ + set_nonblock(fd, false); + if (connect(fd, peer->ai_addr, peer->ai_addrlen)) + xerror("can't reconnect: %d", errno); + if (cfg_input) + close(fd_in); + goto again; + } else { + close(fd); + } + + return 0; +} + +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_peek(const char *mode) +{ + if (!strcasecmp(mode, "saveWithPeek")) + return CFG_WITH_PEEK; + if (!strcasecmp(mode, "saveAfterPeek")) + return CFG_AFTER_PEEK; + + fprintf(stderr, "Unknown: %s\n", mode); + fprintf(stderr, "Supported MSG_PEEK mode are:\n"); + fprintf(stderr, + "\t\t\"saveWithPeek\" - recv data with flags 'MSG_PEEK' and save the peek data into file\n"); + fprintf(stderr, + "\t\t\"saveAfterPeek\" - read and save data into file after recv with flags 'MSG_PEEK'\n"); + + die_usage(); + + /* silence compiler warning */ + return 0; +} + +static int parse_int(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(); + } + + return (int)s; +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "6c:f:hi:I:jlm:M:o:p:P:r:R:s:S:t:T:w:")) != -1) { + switch (c) { + case 'f': + cfg_truncate = atoi(optarg); + + /* when receiving a fastclose, ignore PIPE signals and + * all the I/O errors later in the code + */ + if (cfg_truncate < 0) { + cfg_rcv_trunc = true; + signal(SIGPIPE, handle_signal); + } + break; + case 'j': + cfg_join = true; + cfg_mode = CFG_MODE_POLL; + break; + case 'r': + cfg_remove = true; + cfg_mode = CFG_MODE_POLL; + cfg_wait = 400000; + cfg_do_w = atoi(optarg); + if (cfg_do_w <= 0) + cfg_do_w = 50; + break; + case 'i': + cfg_input = optarg; + break; + case 'I': + cfg_repeat = atoi(optarg); + break; + 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 '6': + pf = AF_INET6; + break; + case 't': + poll_timeout = atoi(optarg) * 1000; + if (poll_timeout <= 0) + poll_timeout = -1; + break; + case 'T': + cfg_time = atoi(optarg); + break; + case 'm': + cfg_mode = parse_mode(optarg); + break; + case 'S': + cfg_sndbuf = parse_int(optarg); + break; + case 'R': + cfg_rcvbuf = parse_int(optarg); + break; + case 'w': + cfg_wait = atoi(optarg)*1000000; + break; + case 'M': + cfg_mark = strtol(optarg, NULL, 0); + break; + case 'P': + cfg_peek = parse_peek(optarg); + break; + case 'c': + parse_cmsg_types(optarg); + break; + case 'o': + parse_setsock_options(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(); + + signal(SIGUSR1, handle_signal); + parse_opts(argc, argv); + + if (listen_mode) { + int fd = sock_listen_mptcp(cfg_host, cfg_port); + + if (fd < 0) + return 1; + + if (cfg_rcvbuf) + set_rcvbuf(fd, cfg_rcvbuf); + if (cfg_sndbuf) + set_sndbuf(fd, cfg_sndbuf); + if (cfg_mark) + set_mark(fd, cfg_mark); + if (cfg_cmsg_types.cmsg_enabled) + apply_cmsg_types(fd, &cfg_cmsg_types); + + 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 000000000..18c9b00ca --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -0,0 +1,934 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(dirname "${0}")/mptcp_lib.sh" + +time_start=$(date +%s) + +optstring="S:R:d:e:l:r:h4cm:f:tC" +ret=0 +sin="" +sout="" +cin_disconnect="" +cin="" +cout="" +ksft_skip=4 +capture=false +timeout_poll=30 +timeout_test=$((timeout_poll * 2 + 1)) +ipv6=true +ethtool_random_on=true +tc_delay="$((RANDOM%50))" +tc_loss=$((RANDOM%101)) +testmode="" +sndbuf=0 +rcvbuf=0 +options_log=true +do_tcp=0 +checksum=false +filesize=0 +connect_per_transfer=1 + +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: $0 [ -a ]" + echo -e "\t-d: tc/netem delay in milliseconds, e.g. \"-d 10\" (default random)" + echo -e "\t-l: tc/netem loss percentage, e.g. \"-l 0.02\" (default random)" + echo -e "\t-r: tc/netem reorder mode, e.g. \"-r 25% 50% gap 5\", use "-r 0" to disable reordering (default random)" + echo -e "\t-e: ethtool features to disable, e.g.: \"-e tso -e gso\" (default: randomly disable any of tso/gso/gro)" + echo -e "\t-4: IPv4 only: disable IPv6 tests (default: test both IPv4 and IPv6)" + echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)" + echo -e "\t-f: size of file to transfer in bytes (default random)" + echo -e "\t-S: set sndbuf value (default: use kernel default)" + echo -e "\t-R: set rcvbuf value (default: use kernel default)" + echo -e "\t-m: test mode (poll, sendfile; default: poll)" + echo -e "\t-t: also run tests with TCP (use twice to non-fallback tcp)" + echo -e "\t-C: enable the MPTCP data checksum" +} + +while getopts "$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 + ;; + "S") + if [ $OPTARG -ge 0 ];then + sndbuf="$OPTARG" + else + echo "-S requires numeric argument, got \"$OPTARG\"" 1>&2 + exit 1 + fi + ;; + "R") + if [ $OPTARG -ge 0 ];then + rcvbuf="$OPTARG" + else + echo "-R requires numeric argument, got \"$OPTARG\"" 1>&2 + exit 1 + fi + ;; + "m") + testmode="$OPTARG" + ;; + "f") + filesize="$OPTARG" + ;; + "t") + do_tcp=$((do_tcp+1)) + ;; + "C") + checksum=true + ;; + "?") + 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 "$cin_disconnect" "$cout_disconnect" + rm -f "$cin" "$cout" + rm -f "$sin" "$sout" + rm -f "$capout" + + local netns + for netns in "$ns1" "$ns2" "$ns3" "$ns4";do + ip netns del $netns + rm -f /tmp/$netns.{nstat,out} + done +} + +mptcp_lib_check_mptcp +mptcp_lib_check_kallsyms + +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) +cin_disconnect="$cin".disconnect +cout_disconnect="$cout".disconnect +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 + +if $checksum; then + for i in "$ns1" "$ns2" "$ns3" "$ns4";do + ip netns exec $i sysctl -q net.mptcp.checksum_enabled=1 + done +fi + +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 + LC_ALL=C ip netns exec ${disabled_ns} ./mptcp_connect -p 10000 -s MPTCP 127.0.0.1 < "$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 +} + +# $1: IP address +is_v6() +{ + [ -z "${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, $2: MIB counter +get_mib_counter() +{ + local listener_ns="${1}" + local mib="${2}" + + # strip the header + ip netns exec "${listener_ns}" \ + nstat -z -a "${mib}" | \ + tail -n+2 | \ + while read a count c rest; do + echo $count + done +} + +# $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="$7" + + local port + port=$((10000+$TEST_COUNT)) + TEST_COUNT=$((TEST_COUNT+1)) + + if [ "$rcvbuf" -gt 0 ]; then + extra_args="$extra_args -R $rcvbuf" + fi + + if [ "$sndbuf" -gt 0 ]; then + extra_args="$extra_args -S $sndbuf" + fi + + if [ -n "$testmode" ]; then + extra_args="$extra_args -m $testmode" + fi + + if [ -n "$extra_args" ] && $options_log; then + echo "INFO: extra options: $extra_args" + fi + options_log=false + + :> "$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 $SUDO_USER" + fi + + local capfile="${rndh}-${connector_ns:0:3}-${listener_ns:0:3}-${cl_proto}-${srv_proto}-${connect_addr}-${port}" + local capopt="-i any -s 65535 -B 32768 ${capuser}" + + ip netns exec ${listener_ns} tcpdump ${capopt} -w "${capfile}-listener.pcap" >> "${capout}" 2>&1 & + local cappid_listener=$! + + ip netns exec ${connector_ns} tcpdump ${capopt} -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 & + local cappid_connector=$! + + sleep 1 + fi + + NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ + nstat -n + if [ ${listener_ns} != ${connector_ns} ]; then + NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ + nstat -n + fi + + local stat_synrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + local stat_ackrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + local stat_cookietx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent") + local stat_cookierx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") + local stat_csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") + local stat_csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr") + + timeout ${timeout_test} \ + ip netns exec ${listener_ns} \ + ./mptcp_connect -t ${timeout_poll} -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) + timeout ${timeout_test} \ + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -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_listener} + kill ${cappid_connector} + fi + + NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ + nstat | grep Tcp > /tmp/${listener_ns}.out + if [ ${listener_ns} != ${connector_ns} ]; then + NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ + nstat | grep Tcp > /tmp/${connector_ns}.out + fi + + local duration + duration=$((stop-start)) + printf "(duration %05sms) " "${duration}" + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + echo "[ FAIL ] client exit code $retc, server $rets" 1>&2 + echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2 + ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port" + cat /tmp/${listener_ns}.out + echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2 + ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port" + [ ${listener_ns} != ${connector_ns} ] && cat /tmp/${connector_ns}.out + + echo + cat "$capout" + return 1 + fi + + check_transfer $sin $cout "file received by client" + retc=$? + check_transfer $cin $sout "file received by server" + rets=$? + + local stat_synrx_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + local stat_ackrx_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + local stat_cookietx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent") + local stat_cookierx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") + local stat_ooo_now=$(get_mib_counter "${listener_ns}" "TcpExtTCPOFOQueue") + + expect_synrx=$((stat_synrx_last_l)) + expect_ackrx=$((stat_ackrx_last_l)) + + cookies=$(ip netns exec ${listener_ns} sysctl net.ipv4.tcp_syncookies) + cookies=${cookies##*=} + + if [ ${cl_proto} = "MPTCP" ] && [ ${srv_proto} = "MPTCP" ]; then + expect_synrx=$((stat_synrx_last_l+$connect_per_transfer)) + expect_ackrx=$((stat_ackrx_last_l+$connect_per_transfer)) + fi + + if [ ${stat_synrx_now_l} -lt ${expect_synrx} ]; then + printf "[ FAIL ] lower MPC SYN rx (%d) than expected (%d)\n" \ + "${stat_synrx_now_l}" "${expect_synrx}" 1>&2 + retc=1 + fi + if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} -a ${stat_ooo_now} -eq 0 ]; then + if [ ${stat_ooo_now} -eq 0 ]; then + printf "[ FAIL ] lower MPC ACK rx (%d) than expected (%d)\n" \ + "${stat_ackrx_now_l}" "${expect_ackrx}" 1>&2 + rets=1 + else + printf "[ Note ] fallback due to TCP OoO" + fi + fi + + if $checksum; then + local csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") + local csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr") + + local csum_err_s_nr=$((csum_err_s - stat_csum_err_s)) + if [ $csum_err_s_nr -gt 0 ]; then + printf "[ FAIL ]\nserver got $csum_err_s_nr data checksum error[s]" + rets=1 + fi + + local csum_err_c_nr=$((csum_err_c - stat_csum_err_c)) + if [ $csum_err_c_nr -gt 0 ]; then + printf "[ FAIL ]\nclient got $csum_err_c_nr data checksum error[s]" + retc=1 + fi + fi + + if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then + printf "[ OK ]" + fi + + if [ $cookies -eq 2 ];then + if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then + printf " WARN: CookieSent: did not advance" + fi + if [ $stat_cookierx_last -ge $stat_cookierx_now ] ;then + printf " WARN: CookieRecv: did not advance" + fi + else + if [ $stat_cookietx_last -ne $stat_cookietx_now ] ;then + printf " WARN: CookieSent: changed" + fi + if [ $stat_cookierx_last -ne $stat_cookierx_now ] ;then + printf " WARN: CookieRecv: changed" + fi + fi + + if [ ${stat_synrx_now_l} -gt ${expect_synrx} ]; then + printf " WARN: SYNRX: expect %d, got %d (probably retransmissions)" \ + "${expect_synrx}" "${stat_synrx_now_l}" + fi + if [ ${stat_ackrx_now_l} -gt ${expect_ackrx} ]; then + printf " WARN: ACKRX: expect %d, got %d (probably retransmissions)" \ + "${expect_ackrx}" "${stat_ackrx_now_l}" + fi + + echo + cat "$capout" + [ $retc -eq 0 ] && [ $rets -eq 0 ] +} + +make_file() +{ + local name=$1 + local who=$2 + local SIZE=$filesize + local ksize + local rem + + if [ $SIZE -eq 0 ]; then + local MAXSIZE=$((1024 * 1024 * 8)) + local MINSIZE=$((1024 * 256)) + + SIZE=$(((RANDOM * RANDOM + MINSIZE) % MAXSIZE)) + fi + + ksize=$((SIZE / 1024)) + rem=$((SIZE - (ksize * 1024))) + + dd if=/dev/urandom of="$name" bs=1024 count=$ksize 2> /dev/null + dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$rem 2> /dev/null + echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" + + echo "Created $name (size $(du -b "$name")) containing data sent by $who" +} + +run_tests_lo() +{ + local listener_ns="$1" + local connector_ns="$2" + local connect_addr="$3" + local loopback="$4" + local extra_args="$5" + 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} ${local_addr} "${extra_args}" + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + + if [ $do_tcp -eq 0 ]; then + # don't bother testing fallback tcp except for loopback case. + if [ ${listener_ns} != ${connector_ns} ]; then + return 0 + fi + fi + + do_transfer ${listener_ns} ${connector_ns} MPTCP TCP \ + ${connect_addr} ${local_addr} "${extra_args}" + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + + do_transfer ${listener_ns} ${connector_ns} TCP MPTCP \ + ${connect_addr} ${local_addr} "${extra_args}" + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + + if [ $do_tcp -gt 1 ] ;then + do_transfer ${listener_ns} ${connector_ns} TCP TCP \ + ${connect_addr} ${local_addr} "${extra_args}" + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + fi + + return 0 +} + +run_tests() +{ + run_tests_lo $1 $2 $3 0 +} + +run_test_transparent() +{ + local connect_addr="$1" + local msg="$2" + + local connector_ns="$ns1" + local listener_ns="$ns2" + local lret=0 + local r6flag="" + + # skip if we don't want v6 + if ! $ipv6 && is_v6 "${connect_addr}"; then + return 0 + fi + + # IP(V6)_TRANSPARENT has been added after TOS support which came with + # the required infrastructure in MPTCP sockopt code. To support TOS, the + # following function has been exported (T). Not great but better than + # checking for a specific kernel version. + if ! mptcp_lib_kallsyms_has "T __ip_sock_set_tos$"; then + echo "INFO: ${msg} not supported by the kernel: SKIP" + return + fi + +ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF" +flush ruleset +table inet mangle { + chain divert { + type filter hook prerouting priority -150; + + meta l4proto tcp socket transparent 1 meta mark set 1 accept + tcp dport 20000 tproxy to :20000 meta mark set 1 accept + } +} +EOF + if [ $? -ne 0 ]; then + echo "SKIP: $msg, could not load nft ruleset" + mptcp_lib_fail_if_expected_feature "nft rules" + return + fi + + local local_addr + if is_v6 "${connect_addr}"; then + local_addr="::" + r6flag="-6" + else + local_addr="0.0.0.0" + fi + + ip -net "$listener_ns" $r6flag rule add fwmark 1 lookup 100 + if [ $? -ne 0 ]; then + ip netns exec "$listener_ns" nft flush ruleset + echo "SKIP: $msg, ip $r6flag rule failed" + mptcp_lib_fail_if_expected_feature "ip rule" + return + fi + + ip -net "$listener_ns" route add local $local_addr/0 dev lo table 100 + if [ $? -ne 0 ]; then + ip netns exec "$listener_ns" nft flush ruleset + ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100 + echo "SKIP: $msg, ip route add local $local_addr failed" + mptcp_lib_fail_if_expected_feature "ip route" + return + fi + + echo "INFO: test $msg" + + TEST_COUNT=10000 + local extra_args="-o TRANSPARENT" + do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP \ + ${connect_addr} ${local_addr} "${extra_args}" + lret=$? + + ip netns exec "$listener_ns" nft flush ruleset + ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100 + ip -net "$listener_ns" route del local $local_addr/0 dev lo table 100 + + if [ $lret -ne 0 ]; then + echo "FAIL: $msg, mptcp connection error" 1>&2 + ret=$lret + return 1 + fi + + echo "PASS: $msg" + return 0 +} + +run_tests_peekmode() +{ + local peekmode="$1" + + echo "INFO: with peek mode: ${peekmode}" + run_tests_lo "$ns1" "$ns1" 10.0.1.1 1 "-P ${peekmode}" + run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-P ${peekmode}" +} + +run_tests_disconnect() +{ + local peekmode="$1" + local old_cin=$cin + local old_sin=$sin + + if ! mptcp_lib_kallsyms_has "mptcp_pm_data_reset$"; then + echo "INFO: Full disconnect not supported: SKIP" + return + fi + + cat $cin $cin $cin > "$cin".disconnect + + # force do_transfer to cope with the multiple tranmissions + sin="$cin.disconnect" + sin_disconnect=$old_sin + cin="$cin.disconnect" + cin_disconnect="$old_cin" + connect_per_transfer=3 + + echo "INFO: disconnect" + run_tests_lo "$ns1" "$ns1" 10.0.1.1 1 "-I 3 -i $old_cin" + run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-I 3 -i $old_cin" + + # restore previous status + sin=$old_sin + sin_disconnect="$cout".disconnect + cin=$old_cin + cin_disconnect="$cin".disconnect + connect_per_transfer=1 +} + +display_time() +{ + time_end=$(date +%s) + time_run=$((time_end-time_start)) + + echo "Time: ${time_run} seconds" +} + +stop_if_error() +{ + local msg="$1" + + if [ ${ret} -ne 0 ]; then + echo "FAIL: ${msg}" 1>&2 + display_time + exit ${ret} + fi +} + +make_file "$cin" "client" +make_file "$sin" "server" + +check_mptcp_disabled + +stop_if_error "The kernel configuration is not valid for MPTCP" + +echo "INFO: validating network environment with pings" +for sender in "$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" $sender dead:beef:3::1 +done + +stop_if_error "Could not even run ping tests" + +[ -n "$tc_loss" ] && tc -net "$ns2" qdisc add dev ns2eth3 root netem loss random $tc_loss delay ${tc_delay}ms +echo -n "INFO: Using loss of $tc_loss " +test "$tc_delay" -gt 0 && echo -n "delay $tc_delay ms " + +reorder_delay=$(($tc_delay / 4)) + +if [ -z "${tc_reorder}" ]; then + reorder1=$((RANDOM%10)) + reorder1=$((100 - reorder1)) + reorder2=$((RANDOM%100)) + + if [ $reorder_delay -gt 0 ] && [ $reorder1 -lt 100 ] && [ $reorder2 -gt 0 ]; then + tc_reorder="reorder ${reorder1}% ${reorder2}%" + echo -n "$tc_reorder with delay ${reorder_delay}ms " + fi +elif [ "$tc_reorder" = "0" ];then + tc_reorder="" +elif [ "$reorder_delay" -gt 0 ];then + # reordering requires some delay + tc_reorder="reorder $tc_reorder" + echo -n "$tc_reorder with delay ${reorder_delay}ms " +fi + +echo "on ns3eth4" + +tc -net "$ns3" qdisc add dev ns3eth4 root netem delay ${reorder_delay}ms $tc_reorder + +run_tests_lo "$ns1" "$ns1" 10.0.1.1 1 +stop_if_error "Could not even run loopback test" + +run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 +stop_if_error "Could not even run loopback v6 test" + +for sender in $ns1 $ns2 $ns3 $ns4;do + # ns1<->ns2 is not subject to reordering/tc delays. Use it to test + # mptcp syncookie support. + if [ $sender = $ns1 ]; then + ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2 + else + ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=1 + fi + + run_tests "$ns1" $sender 10.0.1.1 + run_tests "$ns1" $sender dead:beef:1::1 + + run_tests "$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 + + stop_if_error "Tests with $sender as a sender have failed" +done + +run_tests_peekmode "saveWithPeek" +run_tests_peekmode "saveAfterPeek" +stop_if_error "Tests with peek mode have failed" + +# connect to ns4 ip address, ns2 should intercept/proxy +run_test_transparent 10.0.3.1 "tproxy ipv4" +run_test_transparent dead:beef:3::1 "tproxy ipv6" +stop_if_error "Tests with tproxy have failed" + +run_tests_disconnect + +display_time +exit $ret diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c new file mode 100644 index 000000000..218aac467 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c @@ -0,0 +1,599 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <assert.h> +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <string.h> +#include <stdarg.h> +#include <stdbool.h> +#include <stdint.h> +#include <inttypes.h> +#include <stdio.h> +#include <stdlib.h> +#include <strings.h> +#include <unistd.h> +#include <time.h> + +#include <sys/ioctl.h> +#include <sys/random.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <sys/wait.h> + +#include <netdb.h> +#include <netinet/in.h> + +#include <linux/tcp.h> +#include <linux/sockios.h> + +#ifndef IPPROTO_MPTCP +#define IPPROTO_MPTCP 262 +#endif +#ifndef SOL_MPTCP +#define SOL_MPTCP 284 +#endif + +static int pf = AF_INET; +static int proto_tx = IPPROTO_MPTCP; +static int proto_rx = IPPROTO_MPTCP; + +static void die_perror(const char *msg) +{ + perror(msg); + exit(1); +} + +static void die_usage(int r) +{ + fprintf(stderr, "Usage: mptcp_inq [-6] [ -t tcp|mptcp ] [ -r tcp|mptcp]\n"); + exit(r); +} + +static void xerror(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + fputc('\n', stderr); + exit(1); +} + +static const char *getxinfo_strerr(int err) +{ + if (err == EAI_SYSTEM) + return strerror(errno); + + return gai_strerror(err); +} + +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 int sock_listen_mptcp(const char * const listenaddr, + const char * const port) +{ + int sock = -1; + 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, proto_rx); + 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) + xerror("could not create listen socket"); + + if (listen(sock, 20)) + die_perror("listen"); + + return sock; +} + +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) + continue; + + if (connect(sock, a->ai_addr, a->ai_addrlen) == 0) + break; /* success */ + + die_perror("connect"); + } + + if (sock < 0) + xerror("could not create connect socket"); + + freeaddrinfo(addr); + return sock; +} + +static int protostr_to_num(const char *s) +{ + if (strcasecmp(s, "tcp") == 0) + return IPPROTO_TCP; + if (strcasecmp(s, "mptcp") == 0) + return IPPROTO_MPTCP; + + die_usage(1); + return 0; +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "h6t:r:")) != -1) { + switch (c) { + case 'h': + die_usage(0); + break; + case '6': + pf = AF_INET6; + break; + case 't': + proto_tx = protostr_to_num(optarg); + break; + case 'r': + proto_rx = protostr_to_num(optarg); + break; + default: + die_usage(1); + break; + } + } +} + +/* wait up to timeout milliseconds */ +static void wait_for_ack(int fd, int timeout, size_t total) +{ + int i; + + for (i = 0; i < timeout; i++) { + int nsd, ret, queued = -1; + struct timespec req; + + ret = ioctl(fd, TIOCOUTQ, &queued); + if (ret < 0) + die_perror("TIOCOUTQ"); + + ret = ioctl(fd, SIOCOUTQNSD, &nsd); + if (ret < 0) + die_perror("SIOCOUTQNSD"); + + if ((size_t)queued > total) + xerror("TIOCOUTQ %u, but only %zu expected\n", queued, total); + assert(nsd <= queued); + + if (queued == 0) + return; + + /* wait for peer to ack rx of all data */ + req.tv_sec = 0; + req.tv_nsec = 1 * 1000 * 1000ul; /* 1ms */ + nanosleep(&req, NULL); + } + + xerror("still tx data queued after %u ms\n", timeout); +} + +static void connect_one_server(int fd, int unixfd) +{ + size_t len, i, total, sent; + char buf[4096], buf2[4096]; + ssize_t ret; + + len = rand() % (sizeof(buf) - 1); + + if (len < 128) + len = 128; + + for (i = 0; i < len ; i++) { + buf[i] = rand() % 26; + buf[i] += 'A'; + } + + buf[i] = '\n'; + + /* un-block server */ + ret = read(unixfd, buf2, 4); + assert(ret == 4); + + assert(strncmp(buf2, "xmit", 4) == 0); + + ret = write(unixfd, &len, sizeof(len)); + assert(ret == (ssize_t)sizeof(len)); + + ret = write(fd, buf, len); + if (ret < 0) + die_perror("write"); + + if (ret != (ssize_t)len) + xerror("short write"); + + ret = read(unixfd, buf2, 4); + assert(strncmp(buf2, "huge", 4) == 0); + + total = rand() % (16 * 1024 * 1024); + total += (1 * 1024 * 1024); + sent = total; + + ret = write(unixfd, &total, sizeof(total)); + assert(ret == (ssize_t)sizeof(total)); + + wait_for_ack(fd, 5000, len); + + while (total > 0) { + if (total > sizeof(buf)) + len = sizeof(buf); + else + len = total; + + ret = write(fd, buf, len); + if (ret < 0) + die_perror("write"); + total -= ret; + + /* we don't have to care about buf content, only + * number of total bytes sent + */ + } + + ret = read(unixfd, buf2, 4); + assert(ret == 4); + assert(strncmp(buf2, "shut", 4) == 0); + + wait_for_ack(fd, 5000, sent); + + ret = write(fd, buf, 1); + assert(ret == 1); + close(fd); + ret = write(unixfd, "closed", 6); + assert(ret == 6); + + close(unixfd); +} + +static void get_tcp_inq(struct msghdr *msgh, unsigned int *inqv) +{ + struct cmsghdr *cmsg; + + for (cmsg = CMSG_FIRSTHDR(msgh); cmsg ; cmsg = CMSG_NXTHDR(msgh, cmsg)) { + if (cmsg->cmsg_level == IPPROTO_TCP && cmsg->cmsg_type == TCP_CM_INQ) { + memcpy(inqv, CMSG_DATA(cmsg), sizeof(*inqv)); + return; + } + } + + xerror("could not find TCP_CM_INQ cmsg type"); +} + +static void process_one_client(int fd, int unixfd) +{ + unsigned int tcp_inq; + size_t expect_len; + char msg_buf[4096]; + char buf[4096]; + char tmp[16]; + struct iovec iov = { + .iov_base = buf, + .iov_len = 1, + }; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_control = msg_buf, + .msg_controllen = sizeof(msg_buf), + }; + ssize_t ret, tot; + + ret = write(unixfd, "xmit", 4); + assert(ret == 4); + + ret = read(unixfd, &expect_len, sizeof(expect_len)); + assert(ret == (ssize_t)sizeof(expect_len)); + + if (expect_len > sizeof(buf)) + xerror("expect len %zu exceeds buffer size", expect_len); + + for (;;) { + struct timespec req; + unsigned int queued; + + ret = ioctl(fd, FIONREAD, &queued); + if (ret < 0) + die_perror("FIONREAD"); + if (queued > expect_len) + xerror("FIONREAD returned %u, but only %zu expected\n", + queued, expect_len); + if (queued == expect_len) + break; + + req.tv_sec = 0; + req.tv_nsec = 1000 * 1000ul; + nanosleep(&req, NULL); + } + + /* read one byte, expect cmsg to return expected - 1 */ + ret = recvmsg(fd, &msg, 0); + if (ret < 0) + die_perror("recvmsg"); + + if (msg.msg_controllen == 0) + xerror("msg_controllen is 0"); + + get_tcp_inq(&msg, &tcp_inq); + + assert((size_t)tcp_inq == (expect_len - 1)); + + iov.iov_len = sizeof(buf); + ret = recvmsg(fd, &msg, 0); + if (ret < 0) + die_perror("recvmsg"); + + /* should have gotten exact remainder of all pending data */ + assert(ret == (ssize_t)tcp_inq); + + /* should be 0, all drained */ + get_tcp_inq(&msg, &tcp_inq); + assert(tcp_inq == 0); + + /* request a large swath of data. */ + ret = write(unixfd, "huge", 4); + assert(ret == 4); + + ret = read(unixfd, &expect_len, sizeof(expect_len)); + assert(ret == (ssize_t)sizeof(expect_len)); + + /* peer should send us a few mb of data */ + if (expect_len <= sizeof(buf)) + xerror("expect len %zu too small\n", expect_len); + + tot = 0; + do { + iov.iov_len = sizeof(buf); + ret = recvmsg(fd, &msg, 0); + if (ret < 0) + die_perror("recvmsg"); + + tot += ret; + + get_tcp_inq(&msg, &tcp_inq); + + if (tcp_inq > expect_len - tot) + xerror("inq %d, remaining %d total_len %d\n", + tcp_inq, expect_len - tot, (int)expect_len); + + assert(tcp_inq <= expect_len - tot); + } while ((size_t)tot < expect_len); + + ret = write(unixfd, "shut", 4); + assert(ret == 4); + + /* wait for hangup. Should have received one more byte of data. */ + ret = read(unixfd, tmp, sizeof(tmp)); + assert(ret == 6); + assert(strncmp(tmp, "closed", 6) == 0); + + sleep(1); + + iov.iov_len = 1; + ret = recvmsg(fd, &msg, 0); + if (ret < 0) + die_perror("recvmsg"); + assert(ret == 1); + + get_tcp_inq(&msg, &tcp_inq); + + /* tcp_inq should be 1 due to received fin. */ + assert(tcp_inq == 1); + + iov.iov_len = 1; + ret = recvmsg(fd, &msg, 0); + if (ret < 0) + die_perror("recvmsg"); + + /* expect EOF */ + assert(ret == 0); + get_tcp_inq(&msg, &tcp_inq); + assert(tcp_inq == 1); + + close(fd); +} + +static int xaccept(int s) +{ + int fd = accept(s, NULL, 0); + + if (fd < 0) + die_perror("accept"); + + return fd; +} + +static int server(int unixfd) +{ + int fd = -1, r, on = 1; + + switch (pf) { + case AF_INET: + fd = sock_listen_mptcp("127.0.0.1", "15432"); + break; + case AF_INET6: + fd = sock_listen_mptcp("::1", "15432"); + break; + default: + xerror("Unknown pf %d\n", pf); + break; + } + + r = write(unixfd, "conn", 4); + assert(r == 4); + + alarm(15); + r = xaccept(fd); + + if (-1 == setsockopt(r, IPPROTO_TCP, TCP_INQ, &on, sizeof(on))) + die_perror("setsockopt"); + + process_one_client(r, unixfd); + + return 0; +} + +static int client(int unixfd) +{ + int fd = -1; + + alarm(15); + + switch (pf) { + case AF_INET: + fd = sock_connect_mptcp("127.0.0.1", "15432", proto_tx); + break; + case AF_INET6: + fd = sock_connect_mptcp("::1", "15432", proto_tx); + break; + default: + xerror("Unknown pf %d\n", pf); + } + + connect_one_server(fd, unixfd); + + return 0; +} + +static void init_rng(void) +{ + unsigned int foo; + + if (getrandom(&foo, sizeof(foo), 0) == -1) { + perror("getrandom"); + exit(1); + } + + srand(foo); +} + +static pid_t xfork(void) +{ + pid_t p = fork(); + + if (p < 0) + die_perror("fork"); + else if (p == 0) + init_rng(); + + return p; +} + +static int rcheck(int wstatus, const char *what) +{ + if (WIFEXITED(wstatus)) { + if (WEXITSTATUS(wstatus) == 0) + return 0; + fprintf(stderr, "%s exited, status=%d\n", what, WEXITSTATUS(wstatus)); + return WEXITSTATUS(wstatus); + } else if (WIFSIGNALED(wstatus)) { + xerror("%s killed by signal %d\n", what, WTERMSIG(wstatus)); + } else if (WIFSTOPPED(wstatus)) { + xerror("%s stopped by signal %d\n", what, WSTOPSIG(wstatus)); + } + + return 111; +} + +int main(int argc, char *argv[]) +{ + int e1, e2, wstatus; + pid_t s, c, ret; + int unixfds[2]; + + parse_opts(argc, argv); + + e1 = socketpair(AF_UNIX, SOCK_DGRAM, 0, unixfds); + if (e1 < 0) + die_perror("pipe"); + + s = xfork(); + if (s == 0) + return server(unixfds[1]); + + close(unixfds[1]); + + /* wait until server bound a socket */ + e1 = read(unixfds[0], &e1, 4); + assert(e1 == 4); + + c = xfork(); + if (c == 0) + return client(unixfds[0]); + + close(unixfds[0]); + + ret = waitpid(s, &wstatus, 0); + if (ret == -1) + die_perror("waitpid"); + e1 = rcheck(wstatus, "server"); + ret = waitpid(c, &wstatus, 0); + if (ret == -1) + die_perror("waitpid"); + e2 = rcheck(wstatus, "client"); + + return e1 ? e1 : e2; +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh new file mode 100755 index 000000000..2107579e2 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -0,0 +1,3327 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it, especially because there were too many before having +# address all other issues detected by shellcheck. +#shellcheck disable=SC2086 + +. "$(dirname "${0}")/mptcp_lib.sh" + +# ShellCheck incorrectly believes that most of the code here is unreachable +# because it's invoked by variable name, see how the "tests" array is used +#shellcheck disable=SC2317 + +ret=0 +sin="" +sinfail="" +sout="" +cin="" +cinfail="" +cinsent="" +tmpfile="" +cout="" +capout="" +ns1="" +ns2="" +ksft_skip=4 +iptables="iptables" +ip6tables="ip6tables" +timeout_poll=30 +timeout_test=$((timeout_poll * 2 + 1)) +capture=0 +checksum=0 +ip_mptcp=0 +check_invert=0 +validate_checksum=0 +init=0 + +declare -A all_tests +declare -a only_tests_ids +declare -a only_tests_names +declare -A failed_tests +TEST_COUNT=0 +TEST_NAME="" +nr_blank=40 + +export FAILING_LINKS="" + +# generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) || +# (ip6 && (ip6[74] & 0xf0) == 0x30)'" +CBPF_MPTCP_SUBOPTION_ADD_ADDR="14, + 48 0 0 0, + 84 0 0 240, + 21 0 3 64, + 48 0 0 54, + 84 0 0 240, + 21 6 7 48, + 48 0 0 0, + 84 0 0 240, + 21 0 4 96, + 48 0 0 74, + 84 0 0 240, + 21 0 1 48, + 6 0 0 65535, + 6 0 0 0" + +init_partial() +{ + capout=$(mktemp) + + local rndh + rndh=$(mktemp -u XXXXXX) + + ns1="ns1-$rndh" + ns2="ns2-$rndh" + + local netns + for netns in "$ns1" "$ns2"; do + ip netns add $netns || exit $ksft_skip + ip -net $netns link set lo up + ip netns exec $netns sysctl -q net.mptcp.enabled=1 + ip netns exec $netns sysctl -q net.mptcp.pm_type=0 2>/dev/null || true + ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0 + ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0 + if [ $checksum -eq 1 ]; then + ip netns exec $netns sysctl -q net.mptcp.checksum_enabled=1 + fi + done + + check_invert=0 + validate_checksum=$checksum + FAILING_LINKS="" + + # ns1 ns2 + # ns1eth1 ns2eth1 + # ns1eth2 ns2eth2 + # ns1eth3 ns2eth3 + # ns1eth4 ns2eth4 + + local i + for i in $(seq 1 4); do + ip link add ns1eth$i netns "$ns1" type veth peer name ns2eth$i netns "$ns2" + ip -net "$ns1" addr add 10.0.$i.1/24 dev ns1eth$i + ip -net "$ns1" addr add dead:beef:$i::1/64 dev ns1eth$i nodad + ip -net "$ns1" link set ns1eth$i up + + ip -net "$ns2" addr add 10.0.$i.2/24 dev ns2eth$i + ip -net "$ns2" addr add dead:beef:$i::2/64 dev ns2eth$i nodad + ip -net "$ns2" link set ns2eth$i up + + # let $ns2 reach any $ns1 address from any interface + ip -net "$ns2" route add default via 10.0.$i.1 dev ns2eth$i metric 10$i + ip -net "$ns2" route add default via dead:beef:$i::1 dev ns2eth$i metric 10$i + done +} + +init_shapers() +{ + local i + for i in $(seq 1 4); do + tc -n $ns1 qdisc add dev ns1eth$i root netem rate 20mbit delay 1 + tc -n $ns2 qdisc add dev ns2eth$i root netem rate 20mbit delay 1 + done +} + +cleanup_partial() +{ + rm -f "$capout" + + local netns + for netns in "$ns1" "$ns2"; do + ip netns del $netns + rm -f /tmp/$netns.{nstat,out} + done +} + +check_tools() +{ + mptcp_lib_check_mptcp + mptcp_lib_check_kallsyms + + if ! ip -Version &> /dev/null; then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip + fi + + # Use the legacy version if available to support old kernel versions + if iptables-legacy -V &> /dev/null; then + iptables="iptables-legacy" + ip6tables="ip6tables-legacy" + elif ! iptables -V &> /dev/null; then + echo "SKIP: Could not run all tests without iptables tool" + exit $ksft_skip + elif ! ip6tables -V &> /dev/null; then + echo "SKIP: Could not run all tests without ip6tables tool" + exit $ksft_skip + fi +} + +init() { + init=1 + + check_tools + + sin=$(mktemp) + sout=$(mktemp) + cin=$(mktemp) + cinsent=$(mktemp) + cout=$(mktemp) + + trap cleanup EXIT + + make_file "$cin" "client" 1 + make_file "$sin" "server" 1 +} + +cleanup() +{ + rm -f "$cin" "$cout" "$sinfail" + rm -f "$sin" "$sout" "$cinsent" "$cinfail" + rm -f "$tmpfile" + cleanup_partial +} + +# $1: msg +print_title() +{ + printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${1}" +} + +# [ $1: fail msg ] +mark_as_skipped() +{ + local msg="${1:-"Feature not supported"}" + + mptcp_lib_fail_if_expected_feature "${msg}" + + print_title "[ skip ] ${msg}" + printf "\n" +} + +# $@: condition +continue_if() +{ + if ! "${@}"; then + mark_as_skipped + return 1 + fi +} + +skip_test() +{ + if [ "${#only_tests_ids[@]}" -eq 0 ] && [ "${#only_tests_names[@]}" -eq 0 ]; then + return 1 + fi + + local i + for i in "${only_tests_ids[@]}"; do + if [ "${TEST_COUNT}" -eq "${i}" ]; then + return 1 + fi + done + for i in "${only_tests_names[@]}"; do + if [ "${TEST_NAME}" = "${i}" ]; then + return 1 + fi + done + + return 0 +} + +# $1: test name +reset() +{ + TEST_NAME="${1}" + + TEST_COUNT=$((TEST_COUNT+1)) + + if skip_test; then + return 1 + fi + + if [ "${init}" != "1" ]; then + init + else + cleanup_partial + fi + + init_partial + + return 0 +} + +# $1: test name ; $2: counter to check +reset_check_counter() +{ + reset "${1}" || return 1 + + local counter="${2}" + + if ! nstat -asz "${counter}" | grep -wq "${counter}"; then + mark_as_skipped "counter '${counter}' is not available" + return 1 + fi +} + +# $1: test name +reset_with_cookies() +{ + reset "${1}" || return 1 + + local netns + for netns in "$ns1" "$ns2"; do + ip netns exec $netns sysctl -q net.ipv4.tcp_syncookies=2 + done +} + +# $1: test name +reset_with_add_addr_timeout() +{ + local ip="${2:-4}" + local tables + + reset "${1}" || return 1 + + tables="${iptables}" + if [ $ip -eq 6 ]; then + tables="${ip6tables}" + fi + + ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 + + if ! ip netns exec $ns2 $tables -A OUTPUT -p tcp \ + -m tcp --tcp-option 30 \ + -m bpf --bytecode \ + "$CBPF_MPTCP_SUBOPTION_ADD_ADDR" \ + -j DROP; then + mark_as_skipped "unable to set the 'add addr' rule" + return 1 + fi +} + +# $1: test name +reset_with_checksum() +{ + local ns1_enable=$1 + local ns2_enable=$2 + + reset "checksum test ${1} ${2}" || return 1 + + ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=$ns1_enable + ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=$ns2_enable + + validate_checksum=1 +} + +reset_with_allow_join_id0() +{ + local ns1_enable=$2 + local ns2_enable=$3 + + reset "${1}" || return 1 + + ip netns exec $ns1 sysctl -q net.mptcp.allow_join_initial_addr_port=$ns1_enable + ip netns exec $ns2 sysctl -q net.mptcp.allow_join_initial_addr_port=$ns2_enable +} + +# Modify TCP payload without corrupting the TCP packet +# +# This rule inverts a 8-bit word at byte offset 148 for the 2nd TCP ACK packets +# carrying enough data. +# Once it is done, the TCP Checksum field is updated so the packet is still +# considered as valid at the TCP level. +# Because the MPTCP checksum, covering the TCP options and data, has not been +# updated, the modification will be detected and an MP_FAIL will be emitted: +# what we want to validate here without corrupting "random" MPTCP options. +# +# To avoid having tc producing this pr_info() message for each TCP ACK packets +# not carrying enough data: +# +# tc action pedit offset 162 out of bounds +# +# Netfilter is used to mark packets with enough data. +setup_fail_rules() +{ + check_invert=1 + validate_checksum=1 + local i="$1" + local ip="${2:-4}" + local tables + + tables="${iptables}" + if [ $ip -eq 6 ]; then + tables="${ip6tables}" + fi + + ip netns exec $ns2 $tables \ + -t mangle \ + -A OUTPUT \ + -o ns2eth$i \ + -p tcp \ + -m length --length 150:9999 \ + -m statistic --mode nth --packet 1 --every 99999 \ + -j MARK --set-mark 42 || return ${ksft_skip} + + tc -n $ns2 qdisc add dev ns2eth$i clsact || return ${ksft_skip} + tc -n $ns2 filter add dev ns2eth$i egress \ + protocol ip prio 1000 \ + handle 42 fw \ + action pedit munge offset 148 u8 invert \ + pipe csum tcp \ + index 100 || return ${ksft_skip} +} + +reset_with_fail() +{ + reset_check_counter "${1}" "MPTcpExtInfiniteMapTx" || return 1 + shift + + ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=1 + ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=1 + + local rc=0 + setup_fail_rules "${@}" || rc=$? + + if [ ${rc} -eq ${ksft_skip} ]; then + mark_as_skipped "unable to set the 'fail' rules" + return 1 + fi +} + +reset_with_tcp_filter() +{ + reset "${1}" || return 1 + shift + + local ns="${!1}" + local src="${2}" + local target="${3}" + + if ! ip netns exec "${ns}" ${iptables} \ + -A INPUT \ + -s "${src}" \ + -p tcp \ + -j "${target}"; then + mark_as_skipped "unable to set the filter rules" + return 1 + fi +} + +fail_test() +{ + ret=1 + failed_tests[${TEST_COUNT}]="${TEST_NAME}" +} + +get_failed_tests_ids() +{ + # sorted + local i + for i in "${!failed_tests[@]}"; do + echo "${i}" + done | sort -n +} + +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 + local bytes=$4 + local i a b + + local line + if [ -n "$bytes" ]; then + local out_size + # when truncating we must check the size explicitly + out_size=$(wc -c $out | awk '{print $1}') + if [ $out_size -ne $bytes ]; then + echo "[ FAIL ] $what output file has wrong size ($out_size, $bytes)" + fail_test + return 1 + fi + + # note: BusyBox's "cmp" command doesn't support --bytes + tmpfile=$(mktemp) + head --bytes="$bytes" "$in" > "$tmpfile" + mv "$tmpfile" "$in" + head --bytes="$bytes" "$out" > "$tmpfile" + mv "$tmpfile" "$out" + tmpfile="" + fi + cmp -l "$in" "$out" | while read -r i a b; do + local sum=$((0${a} + 0${b})) + if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then + echo "[ FAIL ] $what does not match (in, out):" + print_file_err "$in" + print_file_err "$out" + fail_test + + return 1 + else + echo "$what has inverted byte at ${i}" + fi + done + + return 0 +} + +do_ping() +{ + local listener_ns="$1" + local connector_ns="$2" + local connect_addr="$3" + + if ! ip netns exec ${connector_ns} ping -q -c 1 $connect_addr >/dev/null; then + echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2 + fail_test + fi +} + +link_failure() +{ + local ns="$1" + + if [ -z "$FAILING_LINKS" ]; then + l=$((RANDOM%4)) + FAILING_LINKS=$((l+1)) + fi + + local l + for l in $FAILING_LINKS; do + local veth="ns1eth$l" + ip -net "$ns" link set "$veth" down + done +} + +# $1: IP address +is_v6() +{ + [ -z "${1##*:*}" ] +} + +# $1: ns, $2: port +wait_local_port_listen() +{ + local listener_ns="${1}" + local port="${2}" + + local port_hex + port_hex="$(printf "%04X" "${port}")" + + local i + 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 +} + +# $1: ns ; $2: counter +get_counter() +{ + local ns="${1}" + local counter="${2}" + local count + + count=$(ip netns exec ${ns} nstat -asz "${counter}" | awk 'NR==1 {next} {print $2}') + if [ -z "${count}" ]; then + mptcp_lib_fail_if_expected_feature "${counter} counter" + return 1 + fi + + echo "${count}" +} + +rm_addr_count() +{ + get_counter "${1}" "MPTcpExtRmAddr" +} + +# $1: ns, $2: old rm_addr counter in $ns +wait_rm_addr() +{ + local ns="${1}" + local old_cnt="${2}" + local cnt + + local i + for i in $(seq 10); do + cnt=$(rm_addr_count ${ns}) + [ "$cnt" = "${old_cnt}" ] || break + sleep 0.1 + done +} + +wait_mpj() +{ + local ns="${1}" + local cnt old_cnt + + old_cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") + + local i + for i in $(seq 10); do + cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") + [ "$cnt" = "${old_cnt}" ] || break + sleep 0.1 + done +} + +kill_wait() +{ + kill $1 > /dev/null 2>&1 + wait $1 2>/dev/null +} + +kill_tests_wait() +{ + #shellcheck disable=SC2046 + kill -SIGUSR1 $(ip netns pids $ns2) $(ip netns pids $ns1) + wait +} + +pm_nl_set_limits() +{ + local ns=$1 + local addrs=$2 + local subflows=$3 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp limits set add_addr_accepted $addrs subflows $subflows + else + ip netns exec $ns ./pm_nl_ctl limits $addrs $subflows + fi +} + +pm_nl_add_endpoint() +{ + local ns=$1 + local addr=$2 + local flags _flags + local port _port + local dev _dev + local id _id + local nr=2 + + local p + for p in "${@}" + do + if [ $p = "flags" ]; then + eval _flags=\$"$nr" + [ -n "$_flags" ]; flags="flags $_flags" + fi + if [ $p = "dev" ]; then + eval _dev=\$"$nr" + [ -n "$_dev" ]; dev="dev $_dev" + fi + if [ $p = "id" ]; then + eval _id=\$"$nr" + [ -n "$_id" ]; id="id $_id" + fi + if [ $p = "port" ]; then + eval _port=\$"$nr" + [ -n "$_port" ]; port="port $_port" + fi + + nr=$((nr + 1)) + done + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint add $addr ${_flags//","/" "} $dev $id $port + else + ip netns exec $ns ./pm_nl_ctl add $addr $flags $dev $id $port + fi +} + +pm_nl_del_endpoint() +{ + local ns=$1 + local id=$2 + local addr=$3 + + if [ $ip_mptcp -eq 1 ]; then + [ $id -ne 0 ] && addr='' + ip -n $ns mptcp endpoint delete id $id $addr + else + ip netns exec $ns ./pm_nl_ctl del $id $addr + fi +} + +pm_nl_flush_endpoint() +{ + local ns=$1 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint flush + else + ip netns exec $ns ./pm_nl_ctl flush + fi +} + +pm_nl_show_endpoints() +{ + local ns=$1 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint show + else + ip netns exec $ns ./pm_nl_ctl dump + fi +} + +pm_nl_change_endpoint() +{ + local ns=$1 + local id=$2 + local flags=$3 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint change id $id ${flags//","/" "} + else + ip netns exec $ns ./pm_nl_ctl set id $id flags $flags + fi +} + +pm_nl_check_endpoint() +{ + local line expected_line + local need_title=$1 + local msg="$2" + local ns=$3 + local addr=$4 + local _flags="" + local flags + local _port + local port + local dev + local _id + local id + + if [ "${need_title}" = 1 ]; then + printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}" + else + printf "%-${nr_blank}s %s" " " "${msg}" + fi + + shift 4 + while [ -n "$1" ]; do + if [ $1 = "flags" ]; then + _flags=$2 + [ -n "$_flags" ]; flags="flags $_flags" + shift + elif [ $1 = "dev" ]; then + [ -n "$2" ]; dev="dev $1" + shift + elif [ $1 = "id" ]; then + _id=$2 + [ -n "$_id" ]; id="id $_id" + shift + elif [ $1 = "port" ]; then + _port=$2 + [ -n "$_port" ]; port=" port $_port" + shift + fi + + shift + done + + if [ -z "$id" ]; then + echo "[skip] bad test - missing endpoint id" + return + fi + + if [ $ip_mptcp -eq 1 ]; then + # get line and trim trailing whitespace + line=$(ip -n $ns mptcp endpoint show $id) + line="${line% }" + # the dump order is: address id flags port dev + [ -n "$addr" ] && expected_line="$addr" + expected_line="$expected_line $id" + [ -n "$_flags" ] && expected_line="$expected_line ${_flags//","/" "}" + [ -n "$dev" ] && expected_line="$expected_line $dev" + [ -n "$port" ] && expected_line="$expected_line $port" + else + line=$(ip netns exec $ns ./pm_nl_ctl get $_id) + # the dump order is: id flags dev address port + expected_line="$id" + [ -n "$flags" ] && expected_line="$expected_line $flags" + [ -n "$dev" ] && expected_line="$expected_line $dev" + [ -n "$addr" ] && expected_line="$expected_line $addr" + [ -n "$_port" ] && expected_line="$expected_line $_port" + fi + if [ "$line" = "$expected_line" ]; then + echo "[ ok ]" + else + echo "[fail] expected '$expected_line' found '$line'" + fail_test + fi +} + +do_transfer() +{ + local listener_ns="$1" + local connector_ns="$2" + local cl_proto="$3" + local srv_proto="$4" + local connect_addr="$5" + local test_link_fail="$6" + local addr_nr_ns1="$7" + local addr_nr_ns2="$8" + local speed="$9" + local sflags="${10}" + + local port=$((10000 + TEST_COUNT - 1)) + local cappid + local userspace_pm=0 + local evts_ns1 + local evts_ns1_pid + local evts_ns2 + local evts_ns2_pid + + :> "$cout" + :> "$sout" + :> "$capout" + + if [ $capture -eq 1 ]; then + local capuser + if [ -z $SUDO_USER ] ; then + capuser="" + else + capuser="-Z $SUDO_USER" + fi + + capfile=$(printf "mp_join-%02u-%s.pcap" "$TEST_COUNT" "${listener_ns}") + + echo "Capturing traffic for test $TEST_COUNT into $capfile" + ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 & + cappid=$! + + sleep 1 + fi + + NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ + nstat -n + NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ + nstat -n + + local extra_args + if [ $speed = "fast" ]; then + extra_args="-j" + elif [ $speed = "slow" ]; then + extra_args="-r 50" + elif [[ $speed = "speed_"* ]]; then + extra_args="-r ${speed:6}" + fi + + if [[ "${addr_nr_ns1}" = "userspace_"* ]]; then + userspace_pm=1 + addr_nr_ns1=${addr_nr_ns1:10} + fi + + local flags="subflow" + local extra_cl_args="" + local extra_srv_args="" + local trunc_size="" + if [[ "${addr_nr_ns2}" = "fastclose_"* ]]; then + if [ ${test_link_fail} -le 1 ]; then + echo "fastclose tests need test_link_fail argument" + fail_test + return 1 + fi + + # disconnect + trunc_size=${test_link_fail} + local side=${addr_nr_ns2:10} + + if [ ${side} = "client" ]; then + extra_cl_args="-f ${test_link_fail}" + extra_srv_args="-f -1" + elif [ ${side} = "server" ]; then + extra_srv_args="-f ${test_link_fail}" + extra_cl_args="-f -1" + else + echo "wrong/unknown fastclose spec ${side}" + fail_test + return 1 + fi + addr_nr_ns2=0 + elif [[ "${addr_nr_ns2}" = "userspace_"* ]]; then + userspace_pm=1 + addr_nr_ns2=${addr_nr_ns2:10} + elif [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then + flags="${flags},fullmesh" + addr_nr_ns2=${addr_nr_ns2:9} + fi + + if [ $userspace_pm -eq 1 ]; then + evts_ns1=$(mktemp) + evts_ns2=$(mktemp) + :> "$evts_ns1" + :> "$evts_ns2" + ip netns exec ${listener_ns} ./pm_nl_ctl events >> "$evts_ns1" 2>&1 & + evts_ns1_pid=$! + ip netns exec ${connector_ns} ./pm_nl_ctl events >> "$evts_ns2" 2>&1 & + evts_ns2_pid=$! + fi + + local local_addr + if is_v6 "${connect_addr}"; then + local_addr="::" + else + local_addr="0.0.0.0" + fi + + extra_srv_args="$extra_args $extra_srv_args" + if [ "$test_link_fail" -gt 1 ];then + timeout ${timeout_test} \ + ip netns exec ${listener_ns} \ + ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ + $extra_srv_args ${local_addr} < "$sinfail" > "$sout" & + else + timeout ${timeout_test} \ + ip netns exec ${listener_ns} \ + ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ + $extra_srv_args ${local_addr} < "$sin" > "$sout" & + fi + local spid=$! + + wait_local_port_listen "${listener_ns}" "${port}" + + extra_cl_args="$extra_args $extra_cl_args" + if [ "$test_link_fail" -eq 0 ];then + timeout ${timeout_test} \ + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr < "$cin" > "$cout" & + elif [ "$test_link_fail" -eq 1 ] || [ "$test_link_fail" -eq 2 ];then + ( cat "$cinfail" ; sleep 2; link_failure $listener_ns ; cat "$cinfail" ) | \ + tee "$cinsent" | \ + timeout ${timeout_test} \ + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr > "$cout" & + else + tee "$cinsent" < "$cinfail" | \ + timeout ${timeout_test} \ + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr > "$cout" & + fi + local cpid=$! + + # let the mptcp subflow be established in background before + # do endpoint manipulation + if [ $addr_nr_ns1 != "0" ] || [ $addr_nr_ns2 != "0" ]; then + sleep 1 + fi + + if [ $addr_nr_ns1 -gt 0 ]; then + local counter=2 + local add_nr_ns1=${addr_nr_ns1} + local id=10 + local tk + while [ $add_nr_ns1 -gt 0 ]; do + local addr + if is_v6 "${connect_addr}"; then + addr="dead:beef:$counter::1" + else + addr="10.0.$counter.1" + fi + if [ $userspace_pm -eq 0 ]; then + pm_nl_add_endpoint $ns1 $addr flags signal + else + tk=$(sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns1") + ip netns exec ${listener_ns} ./pm_nl_ctl ann $addr token $tk id $id + sleep 1 + sp=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + da=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(daddr[46]:\)\([0-9a-f:.]*\).*$/\2/p;q') + echo "$da" | grep -q ":" && addr="::ffff:$addr" + dp=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q') + ip netns exec ${listener_ns} ./pm_nl_ctl rem token $tk id $id + ip netns exec ${listener_ns} ./pm_nl_ctl dsf lip "$addr" \ + lport $sp rip $da rport $dp token $tk + fi + + counter=$((counter + 1)) + add_nr_ns1=$((add_nr_ns1 - 1)) + id=$((id + 1)) + done + elif [ $addr_nr_ns1 -lt 0 ]; then + local rm_nr_ns1=$((-addr_nr_ns1)) + if [ $rm_nr_ns1 -lt 8 ]; then + local counter=0 + local line + pm_nl_show_endpoints ${listener_ns} | while read -r line; do + # shellcheck disable=SC2206 # we do want to split per word + local arr=($line) + local nr=0 + + local i + for i in "${arr[@]}"; do + if [ $i = "id" ]; then + if [ $counter -eq $rm_nr_ns1 ]; then + break + fi + id=${arr[$nr+1]} + rm_addr=$(rm_addr_count ${connector_ns}) + pm_nl_del_endpoint ${listener_ns} $id + wait_rm_addr ${connector_ns} ${rm_addr} + counter=$((counter + 1)) + fi + nr=$((nr + 1)) + done + done + elif [ $rm_nr_ns1 -eq 8 ]; then + pm_nl_flush_endpoint ${listener_ns} + elif [ $rm_nr_ns1 -eq 9 ]; then + pm_nl_del_endpoint ${listener_ns} 0 ${connect_addr} + fi + fi + + # if newly added endpoints must be deleted, give the background msk + # some time to created them + [ $addr_nr_ns1 -gt 0 ] && [ $addr_nr_ns2 -lt 0 ] && sleep 1 + + if [ $addr_nr_ns2 -gt 0 ]; then + local add_nr_ns2=${addr_nr_ns2} + local counter=3 + local id=20 + local tk da dp sp + while [ $add_nr_ns2 -gt 0 ]; do + local addr + if is_v6 "${connect_addr}"; then + addr="dead:beef:$counter::2" + else + addr="10.0.$counter.2" + fi + if [ $userspace_pm -eq 0 ]; then + pm_nl_add_endpoint $ns2 $addr flags $flags + else + tk=$(sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") + da=$(sed -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evts_ns2") + dp=$(sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") + ip netns exec ${connector_ns} ./pm_nl_ctl csf lip $addr lid $id \ + rip $da rport $dp token $tk + sleep 1 + sp=$(grep "type:10" "$evts_ns2" | + sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + ip netns exec ${connector_ns} ./pm_nl_ctl rem token $tk id $id + ip netns exec ${connector_ns} ./pm_nl_ctl dsf lip $addr lport $sp \ + rip $da rport $dp token $tk + fi + counter=$((counter + 1)) + add_nr_ns2=$((add_nr_ns2 - 1)) + id=$((id + 1)) + done + elif [ $addr_nr_ns2 -lt 0 ]; then + local rm_nr_ns2=$((-addr_nr_ns2)) + if [ $rm_nr_ns2 -lt 8 ]; then + local counter=0 + local line + pm_nl_show_endpoints ${connector_ns} | while read -r line; do + # shellcheck disable=SC2206 # we do want to split per word + local arr=($line) + local nr=0 + + local i + for i in "${arr[@]}"; do + if [ $i = "id" ]; then + if [ $counter -eq $rm_nr_ns2 ]; then + break + fi + local id rm_addr + # rm_addr are serialized, allow the previous one to + # complete + id=${arr[$nr+1]} + rm_addr=$(rm_addr_count ${listener_ns}) + pm_nl_del_endpoint ${connector_ns} $id + wait_rm_addr ${listener_ns} ${rm_addr} + counter=$((counter + 1)) + fi + nr=$((nr + 1)) + done + done + elif [ $rm_nr_ns2 -eq 8 ]; then + pm_nl_flush_endpoint ${connector_ns} + elif [ $rm_nr_ns2 -eq 9 ]; then + local addr + if is_v6 "${connect_addr}"; then + addr="dead:beef:1::2" + else + addr="10.0.1.2" + fi + pm_nl_del_endpoint ${connector_ns} 0 $addr + fi + fi + + if [ -n "${sflags}" ]; then + sleep 1 + + local netns + for netns in "$ns1" "$ns2"; do + local line + pm_nl_show_endpoints $netns | while read -r line; do + # shellcheck disable=SC2206 # we do want to split per word + local arr=($line) + local nr=0 + local id + + local i + for i in "${arr[@]}"; do + if [ $i = "id" ]; then + id=${arr[$nr+1]} + fi + nr=$((nr + 1)) + done + pm_nl_change_endpoint $netns $id $sflags + done + done + fi + + wait $cpid + local retc=$? + wait $spid + local rets=$? + + if [ $capture -eq 1 ]; then + sleep 1 + kill $cappid + fi + + if [ $userspace_pm -eq 1 ]; then + kill_wait $evts_ns1_pid + kill_wait $evts_ns2_pid + rm -rf $evts_ns1 $evts_ns2 + fi + + NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ + nstat | grep Tcp > /tmp/${listener_ns}.out + NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ + nstat | grep Tcp > /tmp/${connector_ns}.out + + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + echo " client exit code $retc, server $rets" 1>&2 + echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2 + ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port" + cat /tmp/${listener_ns}.out + echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2 + ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port" + cat /tmp/${connector_ns}.out + + cat "$capout" + fail_test + return 1 + fi + + if [ "$test_link_fail" -gt 1 ];then + check_transfer $sinfail $cout "file received by client" $trunc_size + else + check_transfer $sin $cout "file received by client" $trunc_size + fi + retc=$? + if [ "$test_link_fail" -eq 0 ];then + check_transfer $cin $sout "file received by server" $trunc_size + else + check_transfer $cinsent $sout "file received by server" $trunc_size + fi + rets=$? + + if [ $retc -eq 0 ] && [ $rets -eq 0 ];then + cat "$capout" + return 0 + fi + + cat "$capout" + return 1 +} + +make_file() +{ + local name=$1 + local who=$2 + local size=$3 + + dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null + echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" + + echo "Created $name (size $size KB) containing data sent by $who" +} + +run_tests() +{ + local listener_ns="$1" + local connector_ns="$2" + local connect_addr="$3" + local test_linkfail="${4:-0}" + local addr_nr_ns1="${5:-0}" + local addr_nr_ns2="${6:-0}" + local speed="${7:-fast}" + local sflags="${8:-""}" + + local size + + # The values above 2 are reused to make test files + # with the given sizes (KB) + if [ "$test_linkfail" -gt 2 ]; then + size=$test_linkfail + + if [ -z "$cinfail" ]; then + cinfail=$(mktemp) + fi + make_file "$cinfail" "client" $size + # create the input file for the failure test when + # the first failure test run + elif [ "$test_linkfail" -ne 0 ] && [ -z "$cinfail" ]; then + # the client file must be considerably larger + # of the maximum expected cwin value, or the + # link utilization will be not predicable + size=$((RANDOM%2)) + size=$((size+1)) + size=$((size*8192)) + size=$((size + ( RANDOM % 8192) )) + + cinfail=$(mktemp) + make_file "$cinfail" "client" $size + fi + + if [ "$test_linkfail" -gt 2 ]; then + size=$test_linkfail + + if [ -z "$sinfail" ]; then + sinfail=$(mktemp) + fi + make_file "$sinfail" "server" $size + elif [ "$test_linkfail" -eq 2 ] && [ -z "$sinfail" ]; then + size=$((RANDOM%16)) + size=$((size+1)) + size=$((size*2048)) + + sinfail=$(mktemp) + make_file "$sinfail" "server" $size + fi + + do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \ + ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${sflags} +} + +dump_stats() +{ + echo Server ns stats + ip netns exec $ns1 nstat -as | grep Tcp + echo Client ns stats + ip netns exec $ns2 nstat -as | grep Tcp +} + +chk_csum_nr() +{ + local csum_ns1=${1:-0} + local csum_ns2=${2:-0} + local count + local dump_stats + local extra_msg="" + local allow_multi_errors_ns1=0 + local allow_multi_errors_ns2=0 + + if [[ "${csum_ns1}" = "+"* ]]; then + allow_multi_errors_ns1=1 + csum_ns1=${csum_ns1:1} + fi + if [[ "${csum_ns2}" = "+"* ]]; then + allow_multi_errors_ns2=1 + csum_ns2=${csum_ns2:1} + fi + + printf "%-${nr_blank}s %s" " " "sum" + count=$(get_counter ${ns1} "MPTcpExtDataCsumErr") + if [ "$count" != "$csum_ns1" ]; then + extra_msg="$extra_msg ns1=$count" + fi + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } || + { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then + echo "[fail] got $count data checksum error[s] expected $csum_ns1" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + echo -n " - csum " + count=$(get_counter ${ns2} "MPTcpExtDataCsumErr") + if [ "$count" != "$csum_ns2" ]; then + extra_msg="$extra_msg ns2=$count" + fi + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } || + { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then + echo "[fail] got $count data checksum error[s] expected $csum_ns2" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + [ "${dump_stats}" = 1 ] && dump_stats + + echo "$extra_msg" +} + +chk_fail_nr() +{ + local fail_tx=$1 + local fail_rx=$2 + local ns_invert=${3:-""} + local count + local dump_stats + local ns_tx=$ns1 + local ns_rx=$ns2 + local extra_msg="" + local allow_tx_lost=0 + local allow_rx_lost=0 + + if [[ $ns_invert = "invert" ]]; then + ns_tx=$ns2 + ns_rx=$ns1 + extra_msg=" invert" + fi + + if [[ "${fail_tx}" = "-"* ]]; then + allow_tx_lost=1 + fail_tx=${fail_tx:1} + fi + if [[ "${fail_rx}" = "-"* ]]; then + allow_rx_lost=1 + fail_rx=${fail_rx:1} + fi + + printf "%-${nr_blank}s %s" " " "ftx" + count=$(get_counter ${ns_tx} "MPTcpExtMPFailTx") + if [ "$count" != "$fail_tx" ]; then + extra_msg="$extra_msg,tx=$count" + fi + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } || + { [ "$count" -gt "$fail_tx" ] && [ $allow_tx_lost -eq 1 ]; }; then + echo "[fail] got $count MP_FAIL[s] TX expected $fail_tx" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - failrx" + count=$(get_counter ${ns_rx} "MPTcpExtMPFailRx") + if [ "$count" != "$fail_rx" ]; then + extra_msg="$extra_msg,rx=$count" + fi + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } || + { [ "$count" -gt "$fail_rx" ] && [ $allow_rx_lost -eq 1 ]; }; then + echo "[fail] got $count MP_FAIL[s] RX expected $fail_rx" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + [ "${dump_stats}" = 1 ] && dump_stats + + echo "$extra_msg" +} + +chk_fclose_nr() +{ + local fclose_tx=$1 + local fclose_rx=$2 + local ns_invert=$3 + local count + local dump_stats + local ns_tx=$ns2 + local ns_rx=$ns1 + local extra_msg=" " + + if [[ $ns_invert = "invert" ]]; then + ns_tx=$ns1 + ns_rx=$ns2 + extra_msg=${extra_msg}"invert" + fi + + printf "%-${nr_blank}s %s" " " "ctx" + count=$(get_counter ${ns_tx} "MPTcpExtMPFastcloseTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$fclose_tx" ]; then + extra_msg="$extra_msg,tx=$count" + echo "[fail] got $count MP_FASTCLOSE[s] TX expected $fclose_tx" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - fclzrx" + count=$(get_counter ${ns_rx} "MPTcpExtMPFastcloseRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$fclose_rx" ]; then + extra_msg="$extra_msg,rx=$count" + echo "[fail] got $count MP_FASTCLOSE[s] RX expected $fclose_rx" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + [ "${dump_stats}" = 1 ] && dump_stats + + echo "$extra_msg" +} + +chk_rst_nr() +{ + local rst_tx=$1 + local rst_rx=$2 + local ns_invert=${3:-""} + local count + local dump_stats + local ns_tx=$ns1 + local ns_rx=$ns2 + local extra_msg="" + + if [[ $ns_invert = "invert" ]]; then + ns_tx=$ns2 + ns_rx=$ns1 + extra_msg=" invert" + fi + + printf "%-${nr_blank}s %s" " " "rtx" + count=$(get_counter ${ns_tx} "MPTcpExtMPRstTx") + if [ -z "$count" ]; then + echo -n "[skip]" + # accept more rst than expected except if we don't expect any + elif { [ $rst_tx -ne 0 ] && [ $count -lt $rst_tx ]; } || + { [ $rst_tx -eq 0 ] && [ $count -ne 0 ]; }; then + echo "[fail] got $count MP_RST[s] TX expected $rst_tx" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - rstrx " + count=$(get_counter ${ns_rx} "MPTcpExtMPRstRx") + if [ -z "$count" ]; then + echo -n "[skip]" + # accept more rst than expected except if we don't expect any + elif { [ $rst_rx -ne 0 ] && [ $count -lt $rst_rx ]; } || + { [ $rst_rx -eq 0 ] && [ $count -ne 0 ]; }; then + echo "[fail] got $count MP_RST[s] RX expected $rst_rx" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + [ "${dump_stats}" = 1 ] && dump_stats + + echo "$extra_msg" +} + +chk_infi_nr() +{ + local infi_tx=$1 + local infi_rx=$2 + local count + local dump_stats + + printf "%-${nr_blank}s %s" " " "itx" + count=$(get_counter ${ns2} "MPTcpExtInfiniteMapTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$infi_tx" ]; then + echo "[fail] got $count infinite map[s] TX expected $infi_tx" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - infirx" + count=$(get_counter ${ns1} "MPTcpExtInfiniteMapRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$infi_rx" ]; then + echo "[fail] got $count infinite map[s] RX expected $infi_rx" + fail_test + dump_stats=1 + else + echo "[ ok ]" + fi + + [ "${dump_stats}" = 1 ] && dump_stats +} + +chk_join_nr() +{ + local syn_nr=$1 + local syn_ack_nr=$2 + local ack_nr=$3 + local csum_ns1=${4:-0} + local csum_ns2=${5:-0} + local fail_nr=${6:-0} + local rst_nr=${7:-0} + local infi_nr=${8:-0} + local corrupted_pkts=${9:-0} + local count + local dump_stats + local with_cookie + local title="${TEST_NAME}" + + if [ "${corrupted_pkts}" -gt 0 ]; then + title+=": ${corrupted_pkts} corrupted pkts" + fi + + printf "%03u %-36s %s" "${TEST_COUNT}" "${title}" "syn" + count=$(get_counter ${ns1} "MPTcpExtMPJoinSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_nr" ]; then + echo "[fail] got $count JOIN[s] syn expected $syn_nr" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - synack" + with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies) + count=$(get_counter ${ns2} "MPTcpExtMPJoinSynAckRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_ack_nr" ]; then + # simult connections exceeding the limit with cookie enabled could go up to + # synack validation as the conn limit can be enforced reliably only after + # the subflow creation + if [ "$with_cookie" = 2 ] && [ "$count" -gt "$syn_ack_nr" ] && [ "$count" -le "$syn_nr" ]; then + echo -n "[ ok ]" + else + echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr" + fail_test + dump_stats=1 + fi + else + echo -n "[ ok ]" + fi + + echo -n " - ack" + count=$(get_counter ${ns1} "MPTcpExtMPJoinAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$ack_nr" ]; then + echo "[fail] got $count JOIN[s] ack expected $ack_nr" + fail_test + dump_stats=1 + else + echo "[ ok ]" + fi + [ "${dump_stats}" = 1 ] && dump_stats + if [ $validate_checksum -eq 1 ]; then + chk_csum_nr $csum_ns1 $csum_ns2 + chk_fail_nr $fail_nr $fail_nr + chk_rst_nr $rst_nr $rst_nr + chk_infi_nr $infi_nr $infi_nr + fi +} + +# a negative value for 'stale_max' means no upper bound: +# for bidirectional transfer, if one peer sleep for a while +# - as these tests do - we can have a quite high number of +# stale/recover conversions, proportional to +# sleep duration/ MPTCP-level RTX interval. +chk_stale_nr() +{ + local ns=$1 + local stale_min=$2 + local stale_max=$3 + local stale_delta=$4 + local dump_stats + local stale_nr + local recover_nr + + printf "%-${nr_blank}s %-18s" " " "stale" + + stale_nr=$(get_counter ${ns} "MPTcpExtSubflowStale") + recover_nr=$(get_counter ${ns} "MPTcpExtSubflowRecover") + if [ -z "$stale_nr" ] || [ -z "$recover_nr" ]; then + echo "[skip]" + elif [ $stale_nr -lt $stale_min ] || + { [ $stale_max -gt 0 ] && [ $stale_nr -gt $stale_max ]; } || + [ $((stale_nr - recover_nr)) -ne $stale_delta ]; then + echo "[fail] got $stale_nr stale[s] $recover_nr recover[s], " \ + " expected stale in range [$stale_min..$stale_max]," \ + " stale-recover delta $stale_delta " + fail_test + dump_stats=1 + else + echo "[ ok ]" + fi + + if [ "${dump_stats}" = 1 ]; then + echo $ns stats + ip netns exec $ns ip -s link show + ip netns exec $ns nstat -as | grep MPTcp + fi +} + +chk_add_nr() +{ + local add_nr=$1 + local echo_nr=$2 + local port_nr=${3:-0} + local syn_nr=${4:-$port_nr} + local syn_ack_nr=${5:-$port_nr} + local ack_nr=${6:-$port_nr} + local mis_syn_nr=${7:-0} + local mis_ack_nr=${8:-0} + local count + local dump_stats + local timeout + + timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) + + printf "%-${nr_blank}s %s" " " "add" + count=$(get_counter ${ns2} "MPTcpExtAddAddr") + if [ -z "$count" ]; then + echo -n "[skip]" + # if the test configured a short timeout tolerate greater then expected + # add addrs options, due to retransmissions + elif [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then + echo "[fail] got $count ADD_ADDR[s] expected $add_nr" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - echo " + count=$(get_counter ${ns1} "MPTcpExtEchoAdd") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$echo_nr" ]; then + echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + if [ $port_nr -gt 0 ]; then + echo -n " - pt " + count=$(get_counter ${ns2} "MPTcpExtPortAdd") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$port_nr" ]; then + echo "[fail] got $count ADD_ADDR[s] with a port-number expected $port_nr" + fail_test + dump_stats=1 + else + echo "[ ok ]" + fi + + printf "%-${nr_blank}s %s" " " "syn" + count=$(get_counter ${ns1} "MPTcpExtMPJoinPortSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_nr" ]; then + echo "[fail] got $count JOIN[s] syn with a different \ + port-number expected $syn_nr" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - synack" + count=$(get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_ack_nr" ]; then + echo "[fail] got $count JOIN[s] synack with a different \ + port-number expected $syn_ack_nr" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - ack" + count=$(get_counter ${ns1} "MPTcpExtMPJoinPortAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$ack_nr" ]; then + echo "[fail] got $count JOIN[s] ack with a different \ + port-number expected $ack_nr" + fail_test + dump_stats=1 + else + echo "[ ok ]" + fi + + printf "%-${nr_blank}s %s" " " "syn" + count=$(get_counter ${ns1} "MPTcpExtMismatchPortSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$mis_syn_nr" ]; then + echo "[fail] got $count JOIN[s] syn with a mismatched \ + port-number expected $mis_syn_nr" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - ack " + count=$(get_counter ${ns1} "MPTcpExtMismatchPortAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$mis_ack_nr" ]; then + echo "[fail] got $count JOIN[s] ack with a mismatched \ + port-number expected $mis_ack_nr" + fail_test + dump_stats=1 + else + echo "[ ok ]" + fi + else + echo "" + fi + + [ "${dump_stats}" = 1 ] && dump_stats +} + +chk_rm_nr() +{ + local rm_addr_nr=$1 + local rm_subflow_nr=$2 + local invert + local simult + local count + local dump_stats + local addr_ns=$ns1 + local subflow_ns=$ns2 + local extra_msg="" + + shift 2 + while [ -n "$1" ]; do + [ "$1" = "invert" ] && invert=true + [ "$1" = "simult" ] && simult=true + shift + done + + if [ -z $invert ]; then + addr_ns=$ns1 + subflow_ns=$ns2 + elif [ $invert = "true" ]; then + addr_ns=$ns2 + subflow_ns=$ns1 + extra_msg=" invert" + fi + + printf "%-${nr_blank}s %s" " " "rm " + count=$(get_counter ${addr_ns} "MPTcpExtRmAddr") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$rm_addr_nr" ]; then + echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - rmsf " + count=$(get_counter ${subflow_ns} "MPTcpExtRmSubflow") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ -n "$simult" ]; then + local cnt suffix + + cnt=$(get_counter ${addr_ns} "MPTcpExtRmSubflow") + + # in case of simult flush, the subflow removal count on each side is + # unreliable + count=$((count + cnt)) + [ "$count" != "$rm_subflow_nr" ] && suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]" + if [ $count -ge "$rm_subflow_nr" ] && \ + [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then + echo -n "[ ok ] $suffix" + else + echo "[fail] got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]" + fail_test + dump_stats=1 + fi + elif [ "$count" != "$rm_subflow_nr" ]; then + echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + [ "${dump_stats}" = 1 ] && dump_stats + + echo "$extra_msg" +} + +chk_prio_nr() +{ + local mp_prio_nr_tx=$1 + local mp_prio_nr_rx=$2 + local count + local dump_stats + + printf "%-${nr_blank}s %s" " " "ptx" + count=$(get_counter ${ns1} "MPTcpExtMPPrioTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$mp_prio_nr_tx" ]; then + echo "[fail] got $count MP_PRIO[s] TX expected $mp_prio_nr_tx" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - prx " + count=$(get_counter ${ns1} "MPTcpExtMPPrioRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$mp_prio_nr_rx" ]; then + echo "[fail] got $count MP_PRIO[s] RX expected $mp_prio_nr_rx" + fail_test + dump_stats=1 + else + echo "[ ok ]" + fi + + [ "${dump_stats}" = 1 ] && dump_stats +} + +chk_subflow_nr() +{ + local need_title="$1" + local msg="$2" + local subflow_nr=$3 + local cnt1 + local cnt2 + local dump_stats + + if [ -n "${need_title}" ]; then + printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}" + else + printf "%-${nr_blank}s %s" " " "${msg}" + fi + + cnt1=$(ss -N $ns1 -tOni | grep -c token) + cnt2=$(ss -N $ns2 -tOni | grep -c token) + if [ "$cnt1" != "$subflow_nr" ] || [ "$cnt2" != "$subflow_nr" ]; then + echo "[fail] got $cnt1:$cnt2 subflows expected $subflow_nr" + fail_test + dump_stats=1 + else + echo "[ ok ]" + fi + + if [ "${dump_stats}" = 1 ]; then + ss -N $ns1 -tOni + ss -N $ns1 -tOni | grep token + ip -n $ns1 mptcp endpoint + dump_stats + fi +} + +chk_link_usage() +{ + local ns=$1 + local link=$2 + local out=$3 + local expected_rate=$4 + + local tx_link tx_total + tx_link=$(ip netns exec $ns cat /sys/class/net/$link/statistics/tx_bytes) + tx_total=$(stat --format=%s $out) + local tx_rate=$((tx_link * 100 / tx_total)) + local tolerance=5 + + printf "%-${nr_blank}s %-18s" " " "link usage" + if [ $tx_rate -lt $((expected_rate - tolerance)) ] || \ + [ $tx_rate -gt $((expected_rate + tolerance)) ]; then + echo "[fail] got $tx_rate% usage, expected $expected_rate%" + fail_test + else + echo "[ ok ]" + fi +} + +wait_attempt_fail() +{ + local timeout_ms=$((timeout_poll * 1000)) + local time=0 + local ns=$1 + + while [ $time -lt $timeout_ms ]; do + local cnt + + cnt=$(get_counter ${ns} "TcpAttemptFails") + + [ "$cnt" = 1 ] && return 1 + time=$((time + 100)) + sleep 0.1 + done + return 1 +} + +set_userspace_pm() +{ + local ns=$1 + + ip netns exec $ns sysctl -q net.mptcp.pm_type=1 +} + +subflows_tests() +{ + if reset "no JOIN"; then + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi + + # subflow limited by client + if reset "single subflow, limited by client"; then + pm_nl_set_limits $ns1 0 0 + pm_nl_set_limits $ns2 0 0 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi + + # subflow limited by server + if reset "single subflow, limited by server"; then + pm_nl_set_limits $ns1 0 0 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 0 + fi + + # subflow + if reset "single subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi + + # multiple subflows + if reset "multiple subflows"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + fi + + # multiple subflows limited by server + if reset "multiple subflows, limited by server"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 1 + fi + + # single subflow, dev + if reset "single subflow, dev"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow dev ns2eth3 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi +} + +subflows_error_tests() +{ + # If a single subflow is configured, and matches the MPC src + # address, no additional subflow should be created + if reset "no MPC reuse with single endpoint"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 0 0 0 + fi + + # multiple subflows, with subflow creation error + if reset_with_tcp_filter "multi subflows, with failing subflow" ns1 10.0.3.2 REJECT && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 1 1 1 + fi + + # multiple subflows, with subflow timeout on MPJ + if reset_with_tcp_filter "multi subflows, with subflow timeout" ns1 10.0.3.2 DROP && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 1 1 1 + fi + + # multiple subflows, check that the endpoint corresponding to + # closed subflow (due to reset) is not reused if additional + # subflows are added later + if reset_with_tcp_filter "multi subflows, fair usage on close" ns1 10.0.3.2 REJECT && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & + + # mpj subflow will be in TW after the reset + wait_attempt_fail $ns2 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + wait + + # additional subflow could be created only if the PM select + # the later endpoint, skipping the already used one + chk_join_nr 1 1 1 + fi +} + +signal_address_tests() +{ + # add_address, unused + if reset "unused signal address"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + chk_add_nr 1 1 + fi + + # accept and use add_addr + if reset "signal address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi + + # accept and use add_addr with an additional subflow + # note: signal address in server ns and local addresses in client ns must + # belong to different subnets or one of the listed local address could be + # used for 'add_addr' subflow + if reset "subflow and signal"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + fi + + # accept and use add_addr with additional subflows + if reset "multiple subflows and signal"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + fi + + # signal addresses + if reset "signal addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 3 3 3 + chk_add_nr 3 3 + fi + + # signal invalid addresses + if reset "signal invalid addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 3 3 + fi + + # signal addresses race test + if reset "signal addresses race test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_set_limits $ns2 4 4 + pm_nl_add_endpoint $ns1 10.0.1.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_add_endpoint $ns2 10.0.1.2 flags signal + pm_nl_add_endpoint $ns2 10.0.2.2 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags signal + pm_nl_add_endpoint $ns2 10.0.4.2 flags signal + + # the peer could possibly miss some addr notification, allow retransmission + ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + + # It is not directly linked to the commit introducing this + # symbol but for the parent one which is linked anyway. + if ! mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then + chk_join_nr 3 3 2 + chk_add_nr 4 4 + else + chk_join_nr 3 3 3 + # the server will not signal the address terminating + # the MPC subflow + chk_add_nr 3 3 + fi + fi +} + +link_failure_tests() +{ + # accept and use add_addr with additional subflows and link loss + if reset "multiple flows, signal, link failure"; then + # without any b/w limit each veth could spool the packets and get + # them acked at xmit time, so that the corresponding subflow will + # have almost always no outstanding pkts, the scheduler will pick + # always the first subflow and we will have hard time testing + # active backup and link switch-over. + # Let's set some arbitrary (low) virtual link limits. + init_shapers + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow + run_tests $ns1 $ns2 10.0.1.1 1 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_stale_nr $ns2 1 5 1 + fi + + # accept and use add_addr with additional subflows and link loss + # for bidirectional transfer + if reset "multi flows, signal, bidi, link fail"; then + init_shapers + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow + run_tests $ns1 $ns2 10.0.1.1 2 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_stale_nr $ns2 1 -1 1 + fi + + # 2 subflows plus 1 backup subflow with a lossy link, backup + # will never be used + if reset "backup subflow unused, link failure"; then + init_shapers + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup + FAILING_LINKS="1" \ + run_tests $ns1 $ns2 10.0.1.1 1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_link_usage $ns2 ns2eth3 $cinsent 0 + fi + + # 2 lossy links after half transfer, backup will get half of + # the traffic + if reset "backup flow used, multi links fail"; then + init_shapers + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup + FAILING_LINKS="1 2" \ + run_tests $ns1 $ns2 10.0.1.1 1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_stale_nr $ns2 2 4 2 + chk_link_usage $ns2 ns2eth3 $cinsent 50 + fi + + # use a backup subflow with the first subflow on a lossy link + # for bidirectional transfer + if reset "backup flow used, bidi, link failure"; then + init_shapers + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup + FAILING_LINKS="1 2" \ + run_tests $ns1 $ns2 10.0.1.1 2 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_stale_nr $ns2 1 -1 2 + chk_link_usage $ns2 ns2eth3 $cinsent 50 + fi +} + +add_addr_timeout_tests() +{ + # add_addr timeout + if reset_with_add_addr_timeout "signal address, ADD_ADDR timeout"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 1 1 1 + chk_add_nr 4 0 + fi + + # add_addr timeout IPv6 + if reset_with_add_addr_timeout "signal address, ADD_ADDR6 timeout" 6; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 1 1 1 + chk_add_nr 4 0 + fi + + # signal addresses timeout + if reset_with_add_addr_timeout "signal addresses, ADD_ADDR timeout"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 speed_10 + chk_join_nr 2 2 2 + chk_add_nr 8 0 + fi + + # signal invalid addresses timeout + if reset_with_add_addr_timeout "invalid address, ADD_ADDR timeout"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 speed_10 + chk_join_nr 1 1 1 + chk_add_nr 8 0 + fi +} + +remove_tests() +{ + # single subflow, remove + if reset "remove single subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow + chk_join_nr 1 1 1 + chk_rm_nr 1 1 + chk_rst_nr 0 0 + fi + + # multiple subflows, remove + if reset "remove multiple subflows"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 -2 slow + chk_join_nr 2 2 2 + chk_rm_nr 2 2 + chk_rst_nr 0 0 + fi + + # single address, remove + if reset "remove single address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_rm_nr 1 1 invert + chk_rst_nr 0 0 + fi + + # subflow and signal, remove + if reset "remove subflow and signal"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_rm_nr 1 1 + chk_rst_nr 0 0 + fi + + # subflows and signal, remove + if reset "remove subflows and signal"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 speed_10 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_rm_nr 2 2 + chk_rst_nr 0 0 + fi + + # addresses remove + if reset "remove addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -3 0 speed_10 + chk_join_nr 3 3 3 + chk_add_nr 3 3 + chk_rm_nr 3 3 invert + chk_rst_nr 0 0 + fi + + # invalid addresses remove + if reset "remove invalid addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -3 0 speed_10 + chk_join_nr 1 1 1 + chk_add_nr 3 3 + chk_rm_nr 3 1 invert + chk_rst_nr 0 0 + fi + + # subflows and signal, flush + if reset "flush subflows and signal"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_rm_nr 1 3 invert simult + chk_rst_nr 0 0 + fi + + # subflows flush + if reset "flush subflows"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_set_limits $ns2 3 3 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow id 150 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + chk_join_nr 3 3 3 + + if mptcp_lib_kversion_ge 5.18; then + chk_rm_nr 0 3 simult + else + chk_rm_nr 3 3 + fi + chk_rst_nr 0 0 + fi + + # addresses flush + if reset "flush addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + chk_join_nr 3 3 3 + chk_add_nr 3 3 + chk_rm_nr 3 3 invert simult + chk_rst_nr 0 0 + fi + + # invalid addresses flush + if reset "flush invalid addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -8 0 slow + chk_join_nr 1 1 1 + chk_add_nr 3 3 + chk_rm_nr 3 1 invert + chk_rst_nr 0 0 + fi + + # remove id 0 subflow + if reset "remove id 0 subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 -9 slow + chk_join_nr 1 1 1 + chk_rm_nr 1 1 + chk_rst_nr 0 0 + fi + + # remove id 0 address + if reset "remove id 0 address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 -9 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_rm_nr 1 1 invert + chk_rst_nr 0 0 invert + fi +} + +add_tests() +{ + # add single subflow + if reset "add single subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow + chk_join_nr 1 1 1 + fi + + # add signal address + if reset "add signal address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi + + # add multiple subflows + if reset "add multiple subflows"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow + chk_join_nr 2 2 2 + fi + + # add multiple subflows IPv6 + if reset "add multiple subflows IPv6"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + run_tests $ns1 $ns2 dead:beef:1::1 0 0 2 slow + chk_join_nr 2 2 2 + fi + + # add multiple addresses IPv6 + if reset "add multiple addresses IPv6"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 dead:beef:1::1 0 2 0 slow + chk_join_nr 2 2 2 + chk_add_nr 2 2 + fi +} + +ipv6_tests() +{ + # subflow IPv6 + if reset "single subflow IPv6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 1 1 1 + fi + + # add_address, unused IPv6 + if reset "unused signal address IPv6"; then + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 0 0 0 + chk_add_nr 1 1 + fi + + # signal address IPv6 + if reset "single address IPv6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi + + # single address IPv6, remove + if reset "remove single address IPv6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 dead:beef:1::1 0 -1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_rm_nr 1 1 invert + fi + + # subflow and signal IPv6, remove + if reset "remove subflow and signal IPv6"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow + run_tests $ns1 $ns2 dead:beef:1::1 0 -1 -1 slow + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_rm_nr 1 1 + fi +} + +v4mapped_tests() +{ + # subflow IPv4-mapped to IPv4-mapped + if reset "single subflow IPv4-mapped"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 "::ffff:10.0.3.2" flags subflow + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + fi + + # signal address IPv4-mapped with IPv4-mapped sk + if reset "signal address IPv4-mapped"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 "::ffff:10.0.2.1" flags signal + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi + + # subflow v4-map-v6 + if reset "single subflow v4-map-v6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + fi + + # signal address v4-map-v6 + if reset "signal address v4-map-v6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi + + # subflow v6-map-v4 + if reset "single subflow v6-map-v4"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 "::ffff:10.0.3.2" flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi + + # signal address v6-map-v4 + if reset "signal address v6-map-v4"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 "::ffff:10.0.2.1" flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi + + # no subflow IPv6 to v4 address + if reset "no JOIN with diff families v4-v6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:2::2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi + + # no subflow IPv6 to v4 address even if v6 has a valid v4 at the end + if reset "no JOIN with diff families v4-v6-2"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:2::10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi + + # no subflow IPv4 to v6 address, no need to slow down too then + if reset "no JOIN with diff families v6-v4"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 dead:beef:1::1 + chk_join_nr 0 0 0 + fi +} + +backup_tests() +{ + # single subflow, backup + if reset "single subflow, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup + chk_join_nr 1 1 1 + chk_prio_nr 0 1 + fi + + # single address, backup + if reset "single address, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_prio_nr 1 1 + fi + + # single address with port, backup + if reset "single address with port, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_prio_nr 1 1 + fi + + if reset "mpc backup" && + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then + pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 0 0 0 + chk_prio_nr 0 1 + fi + + if reset "mpc backup both sides" && + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then + pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup + pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 0 0 0 + chk_prio_nr 1 1 + fi + + if reset "mpc switch to backup" && + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then + pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + chk_join_nr 0 0 0 + chk_prio_nr 0 1 + fi + + if reset "mpc switch to backup both sides" && + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then + pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow + pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + chk_join_nr 0 0 0 + chk_prio_nr 1 1 + fi +} + +add_addr_ports_tests() +{ + # signal address with port + if reset "signal address with port"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 1 + fi + + # subflow and signal with port + if reset "subflow and signal with port"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 1 + fi + + # single address with port, remove + if reset "remove single address with port"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 1 + chk_rm_nr 1 1 invert + fi + + # subflow and signal with port, remove + if reset "remove subflow and signal with port"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow + chk_join_nr 2 2 2 + chk_add_nr 1 1 1 + chk_rm_nr 1 1 + fi + + # subflows and signal with port, flush + if reset "flush subflows and signal with port"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -8 -2 slow + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_rm_nr 1 3 invert simult + fi + + # multiple addresses with port + if reset "multiple addresses with port"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal port 10100 + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 2 2 2 + fi + + # multiple addresses with ports + if reset "multiple addresses with ports"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal port 10101 + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 2 2 2 + fi +} + +syncookies_tests() +{ + # single subflow, syncookies + if reset_with_cookies "single subflow with syn cookies"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi + + # multiple subflows with syn cookies + if reset_with_cookies "multiple subflows with syn cookies"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + fi + + # multiple subflows limited by server + if reset_with_cookies "subflows limited by server w cookies"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 1 1 + fi + + # test signal address with cookies + if reset_with_cookies "signal address with syn cookies"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi + + # test cookie with subflow and signal + if reset_with_cookies "subflow and signal w cookies"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + fi + + # accept and use add_addr with additional subflows + if reset_with_cookies "subflows and signal w. cookies"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + fi +} + +checksum_tests() +{ + # checksum test 0 0 + if reset_with_checksum 0 0; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi + + # checksum test 1 1 + if reset_with_checksum 1 1; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi + + # checksum test 0 1 + if reset_with_checksum 0 1; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi + + # checksum test 1 0 + if reset_with_checksum 1 0; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi +} + +deny_join_id0_tests() +{ + # subflow allow join id0 ns1 + if reset_with_allow_join_id0 "single subflow allow join id0 ns1" 1 0; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi + + # subflow allow join id0 ns2 + if reset_with_allow_join_id0 "single subflow allow join id0 ns2" 0 1; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi + + # signal address allow join id0 ns1 + # ADD_ADDRs are not affected by allow_join_id0 value. + if reset_with_allow_join_id0 "signal address allow join id0 ns1" 1 0; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi + + # signal address allow join id0 ns2 + # ADD_ADDRs are not affected by allow_join_id0 value. + if reset_with_allow_join_id0 "signal address allow join id0 ns2" 0 1; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi + + # subflow and address allow join id0 ns1 + if reset_with_allow_join_id0 "subflow and address allow join id0 1" 1 0; then + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + fi + + # subflow and address allow join id0 ns2 + if reset_with_allow_join_id0 "subflow and address allow join id0 2" 0 1; then + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi +} + +fullmesh_tests() +{ + # fullmesh 1 + # 2 fullmesh addrs in ns2, added before the connection, + # 1 non-fullmesh addr in ns1, added during the connection. + if reset "fullmesh test 2x1"; then + pm_nl_set_limits $ns1 0 4 + pm_nl_set_limits $ns2 1 4 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,fullmesh + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,fullmesh + run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow + chk_join_nr 4 4 4 + chk_add_nr 1 1 + fi + + # fullmesh 2 + # 1 non-fullmesh addr in ns1, added before the connection, + # 1 fullmesh addr in ns2, added during the connection. + if reset "fullmesh test 1x1"; then + pm_nl_set_limits $ns1 1 3 + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow + chk_join_nr 3 3 3 + chk_add_nr 1 1 + fi + + # fullmesh 3 + # 1 non-fullmesh addr in ns1, added before the connection, + # 2 fullmesh addrs in ns2, added during the connection. + if reset "fullmesh test 1x2"; then + pm_nl_set_limits $ns1 2 5 + pm_nl_set_limits $ns2 1 5 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow + chk_join_nr 5 5 5 + chk_add_nr 1 1 + fi + + # fullmesh 4 + # 1 non-fullmesh addr in ns1, added before the connection, + # 2 fullmesh addrs in ns2, added during the connection, + # limit max_subflows to 4. + if reset "fullmesh test 1x2, limited"; then + pm_nl_set_limits $ns1 2 4 + pm_nl_set_limits $ns2 1 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow + chk_join_nr 4 4 4 + chk_add_nr 1 1 + fi + + # set fullmesh flag + if reset "set fullmesh flag test" && + continue_if mptcp_lib_kversion_ge 5.18; then + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow fullmesh + chk_join_nr 2 2 2 + chk_rm_nr 0 1 + fi + + # set nofullmesh flag + if reset "set nofullmesh flag test" && + continue_if mptcp_lib_kversion_ge 5.18; then + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow,fullmesh + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow nofullmesh + chk_join_nr 2 2 2 + chk_rm_nr 0 1 + fi + + # set backup,fullmesh flags + if reset "set backup,fullmesh flags test" && + continue_if mptcp_lib_kversion_ge 5.18; then + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow backup,fullmesh + chk_join_nr 2 2 2 + chk_prio_nr 0 1 + chk_rm_nr 0 1 + fi + + # set nobackup,nofullmesh flags + if reset "set nobackup,nofullmesh flags test" && + continue_if mptcp_lib_kversion_ge 5.18; then + pm_nl_set_limits $ns1 4 4 + pm_nl_set_limits $ns2 4 4 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup,fullmesh + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup,nofullmesh + chk_join_nr 2 2 2 + chk_prio_nr 0 1 + chk_rm_nr 0 1 + fi +} + +fastclose_tests() +{ + if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then + run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_client + chk_join_nr 0 0 0 + chk_fclose_nr 1 1 + chk_rst_nr 1 1 invert + fi + + if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then + run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_server + chk_join_nr 0 0 0 0 0 0 1 + chk_fclose_nr 1 1 invert + chk_rst_nr 1 1 + fi +} + +pedit_action_pkts() +{ + tc -n $ns2 -j -s action show action pedit index 100 | \ + grep "packets" | \ + sed 's/.*"packets":\([0-9]\+\),.*/\1/' +} + +fail_tests() +{ + # single subflow + if reset_with_fail "Infinite map" 1; then + run_tests $ns1 $ns2 10.0.1.1 128 + chk_join_nr 0 0 0 +1 +0 1 0 1 "$(pedit_action_pkts)" + chk_fail_nr 1 -1 invert + fi + + # multiple subflows + if reset_with_fail "MP_FAIL MP_RST" 2; then + tc -n $ns2 qdisc add dev ns2eth1 root netem rate 1mbit delay 5 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 1024 + chk_join_nr 1 1 1 1 0 1 1 0 "$(pedit_action_pkts)" + fi +} + +userspace_tests() +{ + # userspace pm type prevents add_addr + if reset "userspace pm type prevents add_addr" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + set_userspace_pm $ns1 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + chk_add_nr 0 0 + fi + + # userspace pm type does not echo add_addr without daemon + if reset "userspace pm no echo w/o daemon" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + set_userspace_pm $ns2 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + chk_add_nr 1 0 + fi + + # userspace pm type rejects join + if reset "userspace pm type rejects join" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + set_userspace_pm $ns1 + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 0 + fi + + # userspace pm type does not send join + if reset "userspace pm type does not send join" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + set_userspace_pm $ns2 + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi + + # userspace pm type prevents mp_prio + if reset "userspace pm type prevents mp_prio" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + set_userspace_pm $ns1 + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + chk_join_nr 1 1 0 + chk_prio_nr 0 0 + fi + + # userspace pm type prevents rm_addr + if reset "userspace pm type prevents rm_addr" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + set_userspace_pm $ns1 + set_userspace_pm $ns2 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow + chk_join_nr 0 0 0 + chk_rm_nr 0 0 + fi + + # userspace pm add & remove address + if reset "userspace pm add & remove address" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + set_userspace_pm $ns1 + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 userspace_1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_rm_nr 1 1 invert + fi + + # userspace pm create destroy subflow + if reset "userspace pm create destroy subflow" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + set_userspace_pm $ns2 + pm_nl_set_limits $ns1 0 1 + run_tests $ns1 $ns2 10.0.1.1 0 0 userspace_1 slow + chk_join_nr 1 1 1 + chk_rm_nr 1 1 + fi +} + +endpoint_tests() +{ + # subflow_rebuild_header is needed to support the implicit flag + # userspace pm type prevents add_addr + if reset "implicit EP" && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow 2>/dev/null & + + wait_mpj $ns1 + pm_nl_check_endpoint 1 "creation" \ + $ns2 10.0.2.2 id 1 flags implicit + + pm_nl_add_endpoint $ns2 10.0.2.2 id 33 + pm_nl_check_endpoint 0 "ID change is prevented" \ + $ns2 10.0.2.2 id 1 flags implicit + + pm_nl_add_endpoint $ns2 10.0.2.2 flags signal + pm_nl_check_endpoint 0 "modif is allowed" \ + $ns2 10.0.2.2 id 1 flags signal + kill_tests_wait + fi + + if reset "delete and re-add" && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 4 0 0 speed_20 2>/dev/null & + + wait_mpj $ns2 + pm_nl_del_endpoint $ns2 2 10.0.2.2 + sleep 0.5 + chk_subflow_nr needtitle "after delete" 1 + + pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow + wait_mpj $ns2 + chk_subflow_nr "" "after re-add" 2 + kill_tests_wait + fi +} + +# [$1: error message] +usage() +{ + if [ -n "${1}" ]; then + echo "${1}" + ret=1 + fi + + echo "mptcp_join usage:" + + local key + for key in "${!all_tests[@]}"; do + echo " -${key} ${all_tests[${key}]}" + done + + echo " -c capture pcap files" + echo " -C enable data checksum" + echo " -i use ip mptcp" + echo " -h help" + + echo "[test ids|names]" + + exit ${ret} +} + + +# Use a "simple" array to force an specific order we cannot have with an associative one +all_tests_sorted=( + f@subflows_tests + e@subflows_error_tests + s@signal_address_tests + l@link_failure_tests + t@add_addr_timeout_tests + r@remove_tests + a@add_tests + 6@ipv6_tests + 4@v4mapped_tests + b@backup_tests + p@add_addr_ports_tests + k@syncookies_tests + S@checksum_tests + d@deny_join_id0_tests + m@fullmesh_tests + z@fastclose_tests + F@fail_tests + u@userspace_tests + I@endpoint_tests +) + +all_tests_args="" +all_tests_names=() +for subtests in "${all_tests_sorted[@]}"; do + key="${subtests%@*}" + value="${subtests#*@}" + + all_tests_args+="${key}" + all_tests_names+=("${value}") + all_tests[${key}]="${value}" +done + +tests=() +while getopts "${all_tests_args}cCih" opt; do + case $opt in + ["${all_tests_args}"]) + tests+=("${all_tests[${opt}]}") + ;; + c) + capture=1 + ;; + C) + checksum=1 + ;; + i) + ip_mptcp=1 + ;; + h) + usage + ;; + *) + usage "Unknown option: -${opt}" + ;; + esac +done + +shift $((OPTIND - 1)) + +for arg in "${@}"; do + if [[ "${arg}" =~ ^[0-9]+$ ]]; then + only_tests_ids+=("${arg}") + else + only_tests_names+=("${arg}") + fi +done + +if [ ${#tests[@]} -eq 0 ]; then + tests=("${all_tests_names[@]}") +fi + +for subtests in "${tests[@]}"; do + "${subtests}" +done + +if [ ${ret} -ne 0 ]; then + echo + echo "${#failed_tests[@]} failure(s) has(ve) been detected:" + for i in $(get_failed_tests_ids); do + echo -e "\t- ${i}: ${failed_tests[${i}]}" + done + echo +fi + +exit $ret diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh new file mode 100644 index 000000000..f32045b23 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -0,0 +1,104 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 + +readonly KSFT_FAIL=1 +readonly KSFT_SKIP=4 + +# SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all +# features using the last version of the kernel and the selftests to make sure +# a test is not being skipped by mistake. +mptcp_lib_expect_all_features() { + [ "${SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES:-}" = "1" ] +} + +# $1: msg +mptcp_lib_fail_if_expected_feature() { + if mptcp_lib_expect_all_features; then + echo "ERROR: missing feature: ${*}" + exit ${KSFT_FAIL} + fi + + return 1 +} + +# $1: file +mptcp_lib_has_file() { + local f="${1}" + + if [ -f "${f}" ]; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${f} file not found" +} + +mptcp_lib_check_mptcp() { + if ! mptcp_lib_has_file "/proc/sys/net/mptcp/enabled"; then + echo "SKIP: MPTCP support is not available" + exit ${KSFT_SKIP} + fi +} + +mptcp_lib_check_kallsyms() { + if ! mptcp_lib_has_file "/proc/kallsyms"; then + echo "SKIP: CONFIG_KALLSYMS is missing" + exit ${KSFT_SKIP} + fi +} + +# Internal: use mptcp_lib_kallsyms_has() instead +__mptcp_lib_kallsyms_has() { + local sym="${1}" + + mptcp_lib_check_kallsyms + + grep -q " ${sym}" /proc/kallsyms +} + +# $1: part of a symbol to look at, add '$' at the end for full name +mptcp_lib_kallsyms_has() { + local sym="${1}" + + if __mptcp_lib_kallsyms_has "${sym}"; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${sym} symbol not found" +} + +# $1: part of a symbol to look at, add '$' at the end for full name +mptcp_lib_kallsyms_doesnt_have() { + local sym="${1}" + + if ! __mptcp_lib_kallsyms_has "${sym}"; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${sym} symbol has been found" +} + +# !!!AVOID USING THIS!!! +# Features might not land in the expected version and features can be backported +# +# $1: kernel version, e.g. 6.3 +mptcp_lib_kversion_ge() { + local exp_maj="${1%.*}" + local exp_min="${1#*.}" + local v maj min + + # If the kernel has backported features, set this env var to 1: + if [ "${SELFTESTS_MPTCP_LIB_NO_KVERSION_CHECK:-}" = "1" ]; then + return 0 + fi + + v=$(uname -r | cut -d'.' -f1,2) + maj=${v%.*} + min=${v#*.} + + if [ "${maj}" -gt "${exp_maj}" ] || + { [ "${maj}" -eq "${exp_maj}" ] && [ "${min}" -ge "${exp_min}" ]; }; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "kernel version ${1} lower than ${v}" +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c new file mode 100644 index 000000000..b35148edb --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -0,0 +1,752 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <assert.h> +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <string.h> +#include <stdarg.h> +#include <stdbool.h> +#include <stdint.h> +#include <inttypes.h> +#include <stdio.h> +#include <stdlib.h> +#include <strings.h> +#include <time.h> +#include <unistd.h> + +#include <sys/socket.h> +#include <sys/types.h> +#include <sys/wait.h> + +#include <netdb.h> +#include <netinet/in.h> + +#include <linux/tcp.h> + +static int pf = AF_INET; + +#ifndef IPPROTO_MPTCP +#define IPPROTO_MPTCP 262 +#endif +#ifndef SOL_MPTCP +#define SOL_MPTCP 284 +#endif + +#ifndef MPTCP_INFO +struct mptcp_info { + __u8 mptcpi_subflows; + __u8 mptcpi_add_addr_signal; + __u8 mptcpi_add_addr_accepted; + __u8 mptcpi_subflows_max; + __u8 mptcpi_add_addr_signal_max; + __u8 mptcpi_add_addr_accepted_max; + __u32 mptcpi_flags; + __u32 mptcpi_token; + __u64 mptcpi_write_seq; + __u64 mptcpi_snd_una; + __u64 mptcpi_rcv_nxt; + __u8 mptcpi_local_addr_used; + __u8 mptcpi_local_addr_max; + __u8 mptcpi_csum_enabled; +}; + +struct mptcp_subflow_data { + __u32 size_subflow_data; /* size of this structure in userspace */ + __u32 num_subflows; /* must be 0, set by kernel */ + __u32 size_kernel; /* must be 0, set by kernel */ + __u32 size_user; /* size of one element in data[] */ +} __attribute__((aligned(8))); + +struct mptcp_subflow_addrs { + union { + __kernel_sa_family_t sa_family; + struct sockaddr sa_local; + struct sockaddr_in sin_local; + struct sockaddr_in6 sin6_local; + struct __kernel_sockaddr_storage ss_local; + }; + union { + struct sockaddr sa_remote; + struct sockaddr_in sin_remote; + struct sockaddr_in6 sin6_remote; + struct __kernel_sockaddr_storage ss_remote; + }; +}; + +#define MPTCP_INFO 1 +#define MPTCP_TCPINFO 2 +#define MPTCP_SUBFLOW_ADDRS 3 +#endif + +struct so_state { + struct mptcp_info mi; + uint64_t mptcpi_rcv_delta; + uint64_t tcpi_rcv_delta; +}; + +#ifndef MIN +#define MIN(a, b) ((a) < (b) ? (a) : (b)) +#endif + +static void die_perror(const char *msg) +{ + perror(msg); + exit(1); +} + +static void die_usage(int r) +{ + fprintf(stderr, "Usage: mptcp_sockopt [-6]\n"); + exit(r); +} + +static void xerror(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + fputc('\n', stderr); + exit(1); +} + +static const char *getxinfo_strerr(int err) +{ + if (err == EAI_SYSTEM) + return strerror(errno); + + return gai_strerror(err); +} + +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 int sock_listen_mptcp(const char * const listenaddr, + const char * const port) +{ + int sock = -1; + 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, IPPROTO_MPTCP); + 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) + xerror("could not create listen socket"); + + if (listen(sock, 20)) + die_perror("listen"); + + return sock; +} + +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) + continue; + + if (connect(sock, a->ai_addr, a->ai_addrlen) == 0) + break; /* success */ + + die_perror("connect"); + } + + if (sock < 0) + xerror("could not create connect socket"); + + freeaddrinfo(addr); + return sock; +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "h6")) != -1) { + switch (c) { + case 'h': + die_usage(0); + break; + case '6': + pf = AF_INET6; + break; + default: + die_usage(1); + break; + } + } +} + +static void do_getsockopt_bogus_sf_data(int fd, int optname) +{ + struct mptcp_subflow_data good_data; + struct bogus_data { + struct mptcp_subflow_data d; + char buf[2]; + } bd; + socklen_t olen, _olen; + int ret; + + memset(&bd, 0, sizeof(bd)); + memset(&good_data, 0, sizeof(good_data)); + + olen = sizeof(good_data); + good_data.size_subflow_data = olen; + + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret < 0); /* 0 size_subflow_data */ + assert(olen == sizeof(good_data)); + + bd.d = good_data; + + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret == 0); + assert(olen == sizeof(good_data)); + assert(bd.d.num_subflows == 1); + assert(bd.d.size_kernel > 0); + assert(bd.d.size_user == 0); + + bd.d = good_data; + _olen = rand() % olen; + olen = _olen; + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret < 0); /* bogus olen */ + assert(olen == _olen); /* must be unchanged */ + + bd.d = good_data; + olen = sizeof(good_data); + bd.d.size_kernel = 1; + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret < 0); /* size_kernel not 0 */ + + bd.d = good_data; + olen = sizeof(good_data); + bd.d.num_subflows = 1; + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret < 0); /* num_subflows not 0 */ + + /* forward compat check: larger struct mptcp_subflow_data on 'old' kernel */ + bd.d = good_data; + olen = sizeof(bd); + bd.d.size_subflow_data = sizeof(bd); + + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret == 0); + + /* olen must be truncated to real data size filled by kernel: */ + assert(olen == sizeof(good_data)); + + assert(bd.d.size_subflow_data == sizeof(bd)); + + bd.d = good_data; + bd.d.size_subflow_data += 1; + bd.d.size_user = 1; + olen = bd.d.size_subflow_data + 1; + _olen = olen; + + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &_olen); + assert(ret == 0); + + /* no truncation, kernel should have filled 1 byte of optname payload in buf[1]: */ + assert(olen == _olen); + + assert(bd.d.size_subflow_data == sizeof(good_data) + 1); + assert(bd.buf[0] == 0); +} + +static void do_getsockopt_mptcp_info(struct so_state *s, int fd, size_t w) +{ + struct mptcp_info i; + socklen_t olen; + int ret; + + olen = sizeof(i); + ret = getsockopt(fd, SOL_MPTCP, MPTCP_INFO, &i, &olen); + + if (ret < 0) + die_perror("getsockopt MPTCP_INFO"); + + assert(olen == sizeof(i)); + + if (s->mi.mptcpi_write_seq == 0) + s->mi = i; + + assert(s->mi.mptcpi_write_seq + w == i.mptcpi_write_seq); + + s->mptcpi_rcv_delta = i.mptcpi_rcv_nxt - s->mi.mptcpi_rcv_nxt; +} + +static void do_getsockopt_tcp_info(struct so_state *s, int fd, size_t r, size_t w) +{ + struct my_tcp_info { + struct mptcp_subflow_data d; + struct tcp_info ti[2]; + } ti; + int ret, tries = 5; + socklen_t olen; + + do { + memset(&ti, 0, sizeof(ti)); + + ti.d.size_subflow_data = sizeof(struct mptcp_subflow_data); + ti.d.size_user = sizeof(struct tcp_info); + olen = sizeof(ti); + + ret = getsockopt(fd, SOL_MPTCP, MPTCP_TCPINFO, &ti, &olen); + if (ret < 0) + xerror("getsockopt MPTCP_TCPINFO (tries %d, %m)"); + + assert(olen <= sizeof(ti)); + assert(ti.d.size_kernel > 0); + assert(ti.d.size_user == + MIN(ti.d.size_kernel, sizeof(struct tcp_info))); + assert(ti.d.num_subflows == 1); + + assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data)); + olen -= sizeof(struct mptcp_subflow_data); + assert(olen == ti.d.size_user); + + if (ti.ti[0].tcpi_bytes_sent == w && + ti.ti[0].tcpi_bytes_received == r) + goto done; + + if (r == 0 && ti.ti[0].tcpi_bytes_sent == w && + ti.ti[0].tcpi_bytes_received) { + s->tcpi_rcv_delta = ti.ti[0].tcpi_bytes_received; + goto done; + } + + /* wait and repeat, might be that tx is still ongoing */ + sleep(1); + } while (tries-- > 0); + + xerror("tcpi_bytes_sent %" PRIu64 ", want %zu. tcpi_bytes_received %" PRIu64 ", want %zu", + ti.ti[0].tcpi_bytes_sent, w, ti.ti[0].tcpi_bytes_received, r); + +done: + do_getsockopt_bogus_sf_data(fd, MPTCP_TCPINFO); +} + +static void do_getsockopt_subflow_addrs(int fd) +{ + struct sockaddr_storage remote, local; + socklen_t olen, rlen, llen; + int ret; + struct my_addrs { + struct mptcp_subflow_data d; + struct mptcp_subflow_addrs addr[2]; + } addrs; + + memset(&addrs, 0, sizeof(addrs)); + memset(&local, 0, sizeof(local)); + memset(&remote, 0, sizeof(remote)); + + addrs.d.size_subflow_data = sizeof(struct mptcp_subflow_data); + addrs.d.size_user = sizeof(struct mptcp_subflow_addrs); + olen = sizeof(addrs); + + ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, &addrs, &olen); + if (ret < 0) + die_perror("getsockopt MPTCP_SUBFLOW_ADDRS"); + + assert(olen <= sizeof(addrs)); + assert(addrs.d.size_kernel > 0); + assert(addrs.d.size_user == + MIN(addrs.d.size_kernel, sizeof(struct mptcp_subflow_addrs))); + assert(addrs.d.num_subflows == 1); + + assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data)); + olen -= sizeof(struct mptcp_subflow_data); + assert(olen == addrs.d.size_user); + + llen = sizeof(local); + ret = getsockname(fd, (struct sockaddr *)&local, &llen); + if (ret < 0) + die_perror("getsockname"); + rlen = sizeof(remote); + ret = getpeername(fd, (struct sockaddr *)&remote, &rlen); + if (ret < 0) + die_perror("getpeername"); + + assert(rlen > 0); + assert(rlen == llen); + + assert(remote.ss_family == local.ss_family); + + assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) == 0); + assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) == 0); + + memset(&addrs, 0, sizeof(addrs)); + + addrs.d.size_subflow_data = sizeof(struct mptcp_subflow_data); + addrs.d.size_user = sizeof(sa_family_t); + olen = sizeof(addrs.d) + sizeof(sa_family_t); + + ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, &addrs, &olen); + assert(ret == 0); + assert(olen == sizeof(addrs.d) + sizeof(sa_family_t)); + + assert(addrs.addr[0].sa_family == pf); + assert(addrs.addr[0].sa_family == local.ss_family); + + assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) != 0); + assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) != 0); + + do_getsockopt_bogus_sf_data(fd, MPTCP_SUBFLOW_ADDRS); +} + +static void do_getsockopts(struct so_state *s, int fd, size_t r, size_t w) +{ + do_getsockopt_mptcp_info(s, fd, w); + + do_getsockopt_tcp_info(s, fd, r, w); + + do_getsockopt_subflow_addrs(fd); +} + +static void connect_one_server(int fd, int pipefd) +{ + char buf[4096], buf2[4096]; + size_t len, i, total; + struct so_state s; + bool eof = false; + ssize_t ret; + + memset(&s, 0, sizeof(s)); + + len = rand() % (sizeof(buf) - 1); + + if (len < 128) + len = 128; + + for (i = 0; i < len ; i++) { + buf[i] = rand() % 26; + buf[i] += 'A'; + } + + buf[i] = '\n'; + + do_getsockopts(&s, fd, 0, 0); + + /* un-block server */ + ret = read(pipefd, buf2, 4); + assert(ret == 4); + close(pipefd); + + assert(strncmp(buf2, "xmit", 4) == 0); + + ret = write(fd, buf, len); + if (ret < 0) + die_perror("write"); + + if (ret != (ssize_t)len) + xerror("short write"); + + total = 0; + do { + ret = read(fd, buf2 + total, sizeof(buf2) - total); + if (ret < 0) + die_perror("read"); + if (ret == 0) { + eof = true; + break; + } + + total += ret; + } while (total < len); + + if (total != len) + xerror("total %lu, len %lu eof %d\n", total, len, eof); + + if (memcmp(buf, buf2, len)) + xerror("data corruption"); + + if (s.tcpi_rcv_delta) + assert(s.tcpi_rcv_delta <= total); + + do_getsockopts(&s, fd, ret, ret); + + if (eof) + total += 1; /* sequence advances due to FIN */ + + assert(s.mptcpi_rcv_delta == (uint64_t)total); + close(fd); +} + +static void process_one_client(int fd, int pipefd) +{ + ssize_t ret, ret2, ret3; + struct so_state s; + char buf[4096]; + + memset(&s, 0, sizeof(s)); + do_getsockopts(&s, fd, 0, 0); + + ret = write(pipefd, "xmit", 4); + assert(ret == 4); + + ret = read(fd, buf, sizeof(buf)); + if (ret < 0) + die_perror("read"); + + assert(s.mptcpi_rcv_delta <= (uint64_t)ret); + + if (s.tcpi_rcv_delta) + assert(s.tcpi_rcv_delta == (uint64_t)ret); + + ret2 = write(fd, buf, ret); + if (ret2 < 0) + die_perror("write"); + + /* wait for hangup */ + ret3 = read(fd, buf, 1); + if (ret3 != 0) + xerror("expected EOF, got %lu", ret3); + + do_getsockopts(&s, fd, ret, ret2); + if (s.mptcpi_rcv_delta != (uint64_t)ret + 1) + xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64, s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - ret); + close(fd); +} + +static int xaccept(int s) +{ + int fd = accept(s, NULL, 0); + + if (fd < 0) + die_perror("accept"); + + return fd; +} + +static int server(int pipefd) +{ + int fd = -1, r; + + switch (pf) { + case AF_INET: + fd = sock_listen_mptcp("127.0.0.1", "15432"); + break; + case AF_INET6: + fd = sock_listen_mptcp("::1", "15432"); + break; + default: + xerror("Unknown pf %d\n", pf); + break; + } + + r = write(pipefd, "conn", 4); + assert(r == 4); + + alarm(15); + r = xaccept(fd); + + process_one_client(r, pipefd); + + return 0; +} + +static void test_ip_tos_sockopt(int fd) +{ + uint8_t tos_in, tos_out; + socklen_t s; + int r; + + tos_in = rand() & 0xfc; + r = setsockopt(fd, SOL_IP, IP_TOS, &tos_in, sizeof(tos_out)); + if (r != 0) + die_perror("setsockopt IP_TOS"); + + tos_out = 0; + s = sizeof(tos_out); + r = getsockopt(fd, SOL_IP, IP_TOS, &tos_out, &s); + if (r != 0) + die_perror("getsockopt IP_TOS"); + + if (tos_in != tos_out) + xerror("tos %x != %x socklen_t %d\n", tos_in, tos_out, s); + + if (s != 1) + xerror("tos should be 1 byte"); + + s = 0; + r = getsockopt(fd, SOL_IP, IP_TOS, &tos_out, &s); + if (r != 0) + die_perror("getsockopt IP_TOS 0"); + if (s != 0) + xerror("expect socklen_t == 0"); + + s = -1; + r = getsockopt(fd, SOL_IP, IP_TOS, &tos_out, &s); + if (r != -1 && errno != EINVAL) + die_perror("getsockopt IP_TOS did not indicate -EINVAL"); + if (s != -1) + xerror("expect socklen_t == -1"); +} + +static int client(int pipefd) +{ + int fd = -1; + + alarm(15); + + switch (pf) { + case AF_INET: + fd = sock_connect_mptcp("127.0.0.1", "15432", IPPROTO_MPTCP); + break; + case AF_INET6: + fd = sock_connect_mptcp("::1", "15432", IPPROTO_MPTCP); + break; + default: + xerror("Unknown pf %d\n", pf); + } + + test_ip_tos_sockopt(fd); + + connect_one_server(fd, pipefd); + + return 0; +} + +static pid_t xfork(void) +{ + pid_t p = fork(); + + if (p < 0) + die_perror("fork"); + + return p; +} + +static int rcheck(int wstatus, const char *what) +{ + if (WIFEXITED(wstatus)) { + if (WEXITSTATUS(wstatus) == 0) + return 0; + fprintf(stderr, "%s exited, status=%d\n", what, WEXITSTATUS(wstatus)); + return WEXITSTATUS(wstatus); + } else if (WIFSIGNALED(wstatus)) { + xerror("%s killed by signal %d\n", what, WTERMSIG(wstatus)); + } else if (WIFSTOPPED(wstatus)) { + xerror("%s stopped by signal %d\n", what, WSTOPSIG(wstatus)); + } + + return 111; +} + +static void init_rng(void) +{ + int fd = open("/dev/urandom", O_RDONLY); + + if (fd >= 0) { + unsigned int foo; + ssize_t ret; + + /* can't fail */ + ret = read(fd, &foo, sizeof(foo)); + assert(ret == sizeof(foo)); + + close(fd); + srand(foo); + } else { + srand(time(NULL)); + } +} + +int main(int argc, char *argv[]) +{ + int e1, e2, wstatus; + pid_t s, c, ret; + int pipefds[2]; + + parse_opts(argc, argv); + + init_rng(); + + e1 = pipe(pipefds); + if (e1 < 0) + die_perror("pipe"); + + s = xfork(); + if (s == 0) + return server(pipefds[1]); + + close(pipefds[1]); + + /* wait until server bound a socket */ + e1 = read(pipefds[0], &e1, 4); + assert(e1 == 4); + + c = xfork(); + if (c == 0) + return client(pipefds[0]); + + close(pipefds[0]); + + ret = waitpid(s, &wstatus, 0); + if (ret == -1) + die_perror("waitpid"); + e1 = rcheck(wstatus, "server"); + ret = waitpid(c, &wstatus, 0); + if (ret == -1) + die_perror("waitpid"); + e2 = rcheck(wstatus, "client"); + + return e1 ? e1 : e2; +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh new file mode 100755 index 000000000..114c4ce71 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -0,0 +1,367 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(dirname "${0}")/mptcp_lib.sh" + +ret=0 +sin="" +sout="" +cin="" +cout="" +ksft_skip=4 +timeout_poll=30 +timeout_test=$((timeout_poll * 2 + 1)) +mptcp_connect="" +do_all_tests=1 +iptables="iptables" +ip6tables="ip6tables" + +add_mark_rules() +{ + local ns=$1 + local m=$2 + + for t in ${iptables} ${ip6tables}; do + # just to debug: check we have multiple subflows connection requests + ip netns exec $ns $t -A OUTPUT -p tcp --syn -m mark --mark $m -j ACCEPT + + # RST packets might be handled by a internal dummy socket + ip netns exec $ns $t -A OUTPUT -p tcp --tcp-flags RST RST -m mark --mark 0 -j ACCEPT + + ip netns exec $ns $t -A OUTPUT -p tcp -m mark --mark $m -j ACCEPT + ip netns exec $ns $t -A OUTPUT -p tcp -m mark --mark 0 -j DROP + done +} + +init() +{ + rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) + + ns1="ns1-$rndh" + ns2="ns2-$rndh" + ns_sbox="ns_sbox-$rndh" + + for netns in "$ns1" "$ns2" "$ns_sbox";do + ip netns add $netns || exit $ksft_skip + ip -net $netns link set lo up + ip netns exec $netns sysctl -q net.mptcp.enabled=1 + ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0 + ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0 + done + + for i in `seq 1 4`; do + ip link add ns1eth$i netns "$ns1" type veth peer name ns2eth$i netns "$ns2" + ip -net "$ns1" addr add 10.0.$i.1/24 dev ns1eth$i + ip -net "$ns1" addr add dead:beef:$i::1/64 dev ns1eth$i nodad + ip -net "$ns1" link set ns1eth$i up + + ip -net "$ns2" addr add 10.0.$i.2/24 dev ns2eth$i + ip -net "$ns2" addr add dead:beef:$i::2/64 dev ns2eth$i nodad + ip -net "$ns2" link set ns2eth$i up + + # let $ns2 reach any $ns1 address from any interface + ip -net "$ns2" route add default via 10.0.$i.1 dev ns2eth$i metric 10$i + + ip netns exec $ns1 ./pm_nl_ctl add 10.0.$i.1 flags signal + ip netns exec $ns1 ./pm_nl_ctl add dead:beef:$i::1 flags signal + + ip netns exec $ns2 ./pm_nl_ctl add 10.0.$i.2 flags signal + ip netns exec $ns2 ./pm_nl_ctl add dead:beef:$i::2 flags signal + done + + ip netns exec $ns1 ./pm_nl_ctl limits 8 8 + ip netns exec $ns2 ./pm_nl_ctl limits 8 8 + + add_mark_rules $ns1 1 + add_mark_rules $ns2 2 +} + +cleanup() +{ + for netns in "$ns1" "$ns2" "$ns_sbox"; do + ip netns del $netns + done + rm -f "$cin" "$cout" + rm -f "$sin" "$sout" +} + +mptcp_lib_check_mptcp +mptcp_lib_check_kallsyms + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +# Use the legacy version if available to support old kernel versions +if iptables-legacy -V &> /dev/null; then + iptables="iptables-legacy" + ip6tables="ip6tables-legacy" +elif ! iptables -V &> /dev/null; then + echo "SKIP: Could not run all tests without iptables tool" + exit $ksft_skip +elif ! ip6tables -V &> /dev/null; then + echo "SKIP: Could not run all tests without ip6tables tool" + exit $ksft_skip +fi + +check_mark() +{ + local ns=$1 + local af=$2 + + tables=${iptables} + + if [ $af -eq 6 ];then + tables=${ip6tables} + fi + + counters=$(ip netns exec $ns $tables -v -L OUTPUT | grep DROP) + values=${counters%DROP*} + + for v in $values; do + if [ $v -ne 0 ]; then + echo "FAIL: got $tables $values in ns $ns , not 0 - not all expected packets marked" 1>&2 + ret=1 + return 1 + fi + done + + return 0 +} + +print_file_err() +{ + ls -l "$1" 1>&2 + echo "Trailing bytes are: " + tail -c 27 "$1" +} + +check_transfer() +{ + in=$1 + out=$2 + 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" + ret=1 + + return 1 + fi + + return 0 +} + +# $1: IP address +is_v6() +{ + [ -z "${1##*:*}" ] +} + +do_transfer() +{ + listener_ns="$1" + connector_ns="$2" + cl_proto="$3" + srv_proto="$4" + connect_addr="$5" + + port=12001 + + :> "$cout" + :> "$sout" + + mptcp_connect="./mptcp_connect -r 20" + + local local_addr + if is_v6 "${connect_addr}"; then + local_addr="::" + else + local_addr="0.0.0.0" + fi + + cmsg="TIMESTAMPNS" + if mptcp_lib_kallsyms_has "mptcp_ioctl$"; then + cmsg+=",TCPINQ" + fi + + timeout ${timeout_test} \ + ip netns exec ${listener_ns} \ + $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ + ${local_addr} < "$sin" > "$sout" & + spid=$! + + sleep 1 + + timeout ${timeout_test} \ + ip netns exec ${connector_ns} \ + $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c "${cmsg}" \ + $connect_addr < "$cin" > "$cout" & + + cpid=$! + + wait $cpid + retc=$? + wait $spid + rets=$? + + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + echo " client exit code $retc, server $rets" 1>&2 + echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2 + ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port" + + echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2 + ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port" + + ret=1 + return 1 + fi + + if [ $local_addr = "::" ];then + check_mark $listener_ns 6 || retc=1 + check_mark $connector_ns 6 || retc=1 + else + check_mark $listener_ns 4 || retc=1 + check_mark $connector_ns 4 || retc=1 + fi + + check_transfer $cin $sout "file received by server" + + rets=$? + + if [ $retc -eq 0 ] && [ $rets -eq 0 ];then + return 0 + fi + + return 1 +} + +make_file() +{ + name=$1 + who=$2 + size=$3 + + dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null + echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" + + echo "Created $name (size $size KB) containing data sent by $who" +} + +do_mptcp_sockopt_tests() +{ + local lret=0 + + if ! mptcp_lib_kallsyms_has "mptcp_diag_fill_info$"; then + echo "INFO: MPTCP sockopt not supported: SKIP" + return + fi + + ip netns exec "$ns_sbox" ./mptcp_sockopt + lret=$? + + if [ $lret -ne 0 ]; then + echo "FAIL: SOL_MPTCP getsockopt" 1>&2 + ret=$lret + return + fi + + ip netns exec "$ns_sbox" ./mptcp_sockopt -6 + lret=$? + + if [ $lret -ne 0 ]; then + echo "FAIL: SOL_MPTCP getsockopt (ipv6)" 1>&2 + ret=$lret + return + fi +} + +run_tests() +{ + listener_ns="$1" + connector_ns="$2" + connect_addr="$3" + local lret=0 + + do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} + + lret=$? + + if [ $lret -ne 0 ]; then + ret=$lret + return + fi +} + +do_tcpinq_test() +{ + ip netns exec "$ns1" ./mptcp_inq "$@" + lret=$? + if [ $lret -ne 0 ];then + ret=$lret + echo "FAIL: mptcp_inq $@" 1>&2 + return $lret + fi + + echo "PASS: TCP_INQ cmsg/ioctl $@" + return $lret +} + +do_tcpinq_tests() +{ + local lret=0 + + ip netns exec "$ns1" ${iptables} -F + ip netns exec "$ns1" ${ip6tables} -F + + if ! mptcp_lib_kallsyms_has "mptcp_ioctl$"; then + echo "INFO: TCP_INQ not supported: SKIP" + return + fi + + for args in "-t tcp" "-r tcp"; do + do_tcpinq_test $args + lret=$? + if [ $lret -ne 0 ] ; then + return $lret + fi + do_tcpinq_test -6 $args + lret=$? + if [ $lret -ne 0 ] ; then + return $lret + fi + done + + do_tcpinq_test -r tcp -t tcp + + return $? +} + +sin=$(mktemp) +sout=$(mktemp) +cin=$(mktemp) +cout=$(mktemp) +init +make_file "$cin" "client" 1 +make_file "$sin" "server" 1 +trap cleanup EXIT + +run_tests $ns1 $ns2 10.0.1.1 +run_tests $ns1 $ns2 dead:beef:1::1 + +if [ $ret -eq 0 ];then + echo "PASS: all packets had packet mark set" +fi + +do_mptcp_sockopt_tests +if [ $ret -eq 0 ];then + echo "PASS: SOL_MPTCP getsockopt has expected information" +fi + +do_tcpinq_tests +exit $ret diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh new file mode 100755 index 000000000..d02e0d63a --- /dev/null +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -0,0 +1,196 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(dirname "${0}")/mptcp_lib.sh" + +ksft_skip=4 +ret=0 + +usage() { + echo "Usage: $0 [ -h ]" +} + + +while getopts "$optstring" option;do + case "$option" in + "h") + usage $0 + exit 0 + ;; + "?") + usage $0 + exit 1 + ;; + esac +done + +sec=$(date +%s) +rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) +ns1="ns1-$rndh" +err=$(mktemp) +ret=0 + +cleanup() +{ + rm -f $err + ip netns del $ns1 +} + +mptcp_lib_check_mptcp + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +trap cleanup EXIT + +ip netns add $ns1 || exit $ksft_skip +ip -net $ns1 link set lo up +ip netns exec $ns1 sysctl -q net.mptcp.enabled=1 + +check() +{ + local cmd="$1" + local expected="$2" + local msg="$3" + local out=`$cmd 2>$err` + local cmd_ret=$? + + printf "%-50s %s" "$msg" + if [ $cmd_ret -ne 0 ]; then + echo "[FAIL] command execution '$cmd' stderr " + cat $err + ret=1 + elif [ "$out" = "$expected" ]; then + echo "[ OK ]" + else + echo -n "[FAIL] " + echo "expected '$expected' got '$out'" + ret=1 + fi +} + +check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "defaults addr list" + +default_limits="$(ip netns exec $ns1 ./pm_nl_ctl limits)" +if mptcp_lib_expect_all_features; then + check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 +subflows 2" "defaults limits" +fi + +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.2 flags subflow dev lo +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.3 flags signal,backup +check "ip netns exec $ns1 ./pm_nl_ctl get 1" "id 1 flags 10.0.1.1" "simple add/get addr" + +check "ip netns exec $ns1 ./pm_nl_ctl dump" \ +"id 1 flags 10.0.1.1 +id 2 flags subflow dev lo 10.0.1.2 +id 3 flags signal,backup 10.0.1.3" "dump addrs" + +ip netns exec $ns1 ./pm_nl_ctl del 2 +check "ip netns exec $ns1 ./pm_nl_ctl get 2" "" "simple del addr" +check "ip netns exec $ns1 ./pm_nl_ctl dump" \ +"id 1 flags 10.0.1.1 +id 3 flags signal,backup 10.0.1.3" "dump addrs after del" + +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.3 +check "ip netns exec $ns1 ./pm_nl_ctl get 4" "" "duplicate addr" + +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.4 flags signal +check "ip netns exec $ns1 ./pm_nl_ctl get 4" "id 4 flags signal 10.0.1.4" "id addr increment" + +for i in `seq 5 9`; do + ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.$i flags signal >/dev/null 2>&1 +done +check "ip netns exec $ns1 ./pm_nl_ctl get 9" "id 9 flags signal 10.0.1.9" "hard addr limit" +check "ip netns exec $ns1 ./pm_nl_ctl get 10" "" "above hard addr limit" + +ip netns exec $ns1 ./pm_nl_ctl del 9 +for i in `seq 10 255`; do + ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.9 id $i + ip netns exec $ns1 ./pm_nl_ctl del $i +done +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags 10.0.1.1 +id 3 flags signal,backup 10.0.1.3 +id 4 flags signal 10.0.1.4 +id 5 flags signal 10.0.1.5 +id 6 flags signal 10.0.1.6 +id 7 flags signal 10.0.1.7 +id 8 flags signal 10.0.1.8" "id limit" + +ip netns exec $ns1 ./pm_nl_ctl flush +check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "flush addrs" + +ip netns exec $ns1 ./pm_nl_ctl limits 9 1 +check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "rcv addrs above hard limit" + +ip netns exec $ns1 ./pm_nl_ctl limits 1 9 +check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "subflows above hard limit" + +ip netns exec $ns1 ./pm_nl_ctl limits 8 8 +check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 8 +subflows 8" "set limits" + +ip netns exec $ns1 ./pm_nl_ctl flush +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.2 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.3 id 100 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.4 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.5 id 254 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.6 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.7 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.8 +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags 10.0.1.1 +id 2 flags 10.0.1.2 +id 3 flags 10.0.1.7 +id 4 flags 10.0.1.8 +id 100 flags 10.0.1.3 +id 101 flags 10.0.1.4 +id 254 flags 10.0.1.5 +id 255 flags 10.0.1.6" "set ids" + +ip netns exec $ns1 ./pm_nl_ctl flush +ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.1 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.2 id 254 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.3 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.4 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.5 id 253 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.6 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.7 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.8 +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags 10.0.0.1 +id 2 flags 10.0.0.4 +id 3 flags 10.0.0.6 +id 4 flags 10.0.0.7 +id 5 flags 10.0.0.8 +id 253 flags 10.0.0.5 +id 254 flags 10.0.0.2 +id 255 flags 10.0.0.3" "wrap-around ids" + +ip netns exec $ns1 ./pm_nl_ctl flush +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 flags subflow +ip netns exec $ns1 ./pm_nl_ctl set 10.0.1.1 flags backup +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow,backup 10.0.1.1" "set flags (backup)" +ip netns exec $ns1 ./pm_nl_ctl set 10.0.1.1 flags nobackup +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow 10.0.1.1" " (nobackup)" + +# fullmesh support has been added later +ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh +if ip netns exec $ns1 ./pm_nl_ctl dump | grep -q "fullmesh" || + mptcp_lib_expect_all_features; then + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow,fullmesh 10.0.1.1" " (fullmesh)" + ip netns exec $ns1 ./pm_nl_ctl set id 1 flags nofullmesh + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow 10.0.1.1" " (nofullmesh)" + ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow,backup,fullmesh 10.0.1.1" " (backup,fullmesh)" +fi + +exit $ret diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c new file mode 100644 index 000000000..1887bd61b --- /dev/null +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -0,0 +1,1505 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <errno.h> +#include <error.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <limits.h> + +#include <sys/socket.h> +#include <sys/types.h> + +#include <arpa/inet.h> +#include <net/if.h> + +#include <linux/rtnetlink.h> +#include <linux/genetlink.h> + +#include "linux/mptcp.h" + +#ifndef MPTCP_PM_NAME +#define MPTCP_PM_NAME "mptcp_pm" +#endif +#ifndef MPTCP_PM_EVENTS +#define MPTCP_PM_EVENTS "mptcp_pm_events" +#endif +#ifndef IPPROTO_MPTCP +#define IPPROTO_MPTCP 262 +#endif + +static void syntax(char *argv[]) +{ + fprintf(stderr, "%s add|ann|rem|csf|dsf|get|set|del|flush|dump|events|listen|accept [<args>]\n", argv[0]); + fprintf(stderr, "\tadd [flags signal|subflow|backup|fullmesh] [id <nr>] [dev <name>] <ip>\n"); + fprintf(stderr, "\tann <local-ip> id <local-id> token <token> [port <local-port>] [dev <name>]\n"); + fprintf(stderr, "\trem id <local-id> token <token>\n"); + fprintf(stderr, "\tcsf lip <local-ip> lid <local-id> rip <remote-ip> rport <remote-port> token <token>\n"); + fprintf(stderr, "\tdsf lip <local-ip> lport <local-port> rip <remote-ip> rport <remote-port> token <token>\n"); + fprintf(stderr, "\tdel <id> [<ip>]\n"); + fprintf(stderr, "\tget <id>\n"); + fprintf(stderr, "\tset [<ip>] [id <nr>] flags [no]backup|[no]fullmesh [port <nr>] [token <token>] [rip <ip>] [rport <port>]\n"); + fprintf(stderr, "\tflush\n"); + fprintf(stderr, "\tdump\n"); + fprintf(stderr, "\tlimits [<rcv addr max> <subflow max>]\n"); + fprintf(stderr, "\tevents\n"); + fprintf(stderr, "\tlisten <local-ip> <local-port>\n"); + exit(0); +} + +static int init_genl_req(char *data, int family, int cmd, int version) +{ + struct nlmsghdr *nh = (void *)data; + struct genlmsghdr *gh; + int off = 0; + + nh->nlmsg_type = family; + nh->nlmsg_flags = NLM_F_REQUEST; + nh->nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN); + off += NLMSG_ALIGN(sizeof(*nh)); + + gh = (void *)(data + off); + gh->cmd = cmd; + gh->version = version; + off += NLMSG_ALIGN(sizeof(*gh)); + return off; +} + +static void nl_error(struct nlmsghdr *nh) +{ + struct nlmsgerr *err = (struct nlmsgerr *)NLMSG_DATA(nh); + int len = nh->nlmsg_len - sizeof(*nh); + uint32_t off; + + if (len < sizeof(struct nlmsgerr)) + error(1, 0, "netlink error message truncated %d min %ld", len, + sizeof(struct nlmsgerr)); + + if (!err->error) { + /* check messages from kernel */ + struct rtattr *attrs = (struct rtattr *)NLMSG_DATA(nh); + + while (RTA_OK(attrs, len)) { + if (attrs->rta_type == NLMSGERR_ATTR_MSG) + fprintf(stderr, "netlink ext ack msg: %s\n", + (char *)RTA_DATA(attrs)); + if (attrs->rta_type == NLMSGERR_ATTR_OFFS) { + memcpy(&off, RTA_DATA(attrs), 4); + fprintf(stderr, "netlink err off %d\n", + (int)off); + } + attrs = RTA_NEXT(attrs, len); + } + } else { + fprintf(stderr, "netlink error %d", err->error); + } +} + +static int capture_events(int fd, int event_group) +{ + u_int8_t buffer[NLMSG_ALIGN(sizeof(struct nlmsghdr)) + + NLMSG_ALIGN(sizeof(struct genlmsghdr)) + 1024]; + struct genlmsghdr *ghdr; + struct rtattr *attrs; + struct nlmsghdr *nh; + int ret = 0; + int res_len; + int msg_len; + fd_set rfds; + + if (setsockopt(fd, SOL_NETLINK, NETLINK_ADD_MEMBERSHIP, + &event_group, sizeof(event_group)) < 0) + error(1, errno, "could not join the " MPTCP_PM_EVENTS " mcast group"); + + do { + FD_ZERO(&rfds); + FD_SET(fd, &rfds); + res_len = NLMSG_ALIGN(sizeof(struct nlmsghdr)) + + NLMSG_ALIGN(sizeof(struct genlmsghdr)) + 1024; + + ret = select(FD_SETSIZE, &rfds, NULL, NULL, NULL); + + if (ret < 0) + error(1, ret, "error in select() on NL socket"); + + res_len = recv(fd, buffer, res_len, 0); + if (res_len < 0) + error(1, res_len, "error on recv() from NL socket"); + + nh = (struct nlmsghdr *)buffer; + + for (; NLMSG_OK(nh, res_len); nh = NLMSG_NEXT(nh, res_len)) { + if (nh->nlmsg_type == NLMSG_ERROR) + error(1, NLMSG_ERROR, "received invalid NL message"); + + ghdr = (struct genlmsghdr *)NLMSG_DATA(nh); + + if (ghdr->cmd == 0) + continue; + + fprintf(stderr, "type:%d", ghdr->cmd); + + msg_len = nh->nlmsg_len - NLMSG_LENGTH(GENL_HDRLEN); + + attrs = (struct rtattr *) ((char *) ghdr + GENL_HDRLEN); + while (RTA_OK(attrs, msg_len)) { + if (attrs->rta_type == MPTCP_ATTR_TOKEN) + fprintf(stderr, ",token:%u", *(__u32 *)RTA_DATA(attrs)); + else if (attrs->rta_type == MPTCP_ATTR_FAMILY) + fprintf(stderr, ",family:%u", *(__u16 *)RTA_DATA(attrs)); + else if (attrs->rta_type == MPTCP_ATTR_LOC_ID) + fprintf(stderr, ",loc_id:%u", *(__u8 *)RTA_DATA(attrs)); + else if (attrs->rta_type == MPTCP_ATTR_REM_ID) + fprintf(stderr, ",rem_id:%u", *(__u8 *)RTA_DATA(attrs)); + else if (attrs->rta_type == MPTCP_ATTR_SADDR4) { + u_int32_t saddr4 = ntohl(*(__u32 *)RTA_DATA(attrs)); + + fprintf(stderr, ",saddr4:%u.%u.%u.%u", saddr4 >> 24, + (saddr4 >> 16) & 0xFF, (saddr4 >> 8) & 0xFF, + (saddr4 & 0xFF)); + } else if (attrs->rta_type == MPTCP_ATTR_SADDR6) { + char buf[INET6_ADDRSTRLEN]; + + if (inet_ntop(AF_INET6, RTA_DATA(attrs), buf, + sizeof(buf)) != NULL) + fprintf(stderr, ",saddr6:%s", buf); + } else if (attrs->rta_type == MPTCP_ATTR_DADDR4) { + u_int32_t daddr4 = ntohl(*(__u32 *)RTA_DATA(attrs)); + + fprintf(stderr, ",daddr4:%u.%u.%u.%u", daddr4 >> 24, + (daddr4 >> 16) & 0xFF, (daddr4 >> 8) & 0xFF, + (daddr4 & 0xFF)); + } else if (attrs->rta_type == MPTCP_ATTR_DADDR6) { + char buf[INET6_ADDRSTRLEN]; + + if (inet_ntop(AF_INET6, RTA_DATA(attrs), buf, + sizeof(buf)) != NULL) + fprintf(stderr, ",daddr6:%s", buf); + } else if (attrs->rta_type == MPTCP_ATTR_SPORT) + fprintf(stderr, ",sport:%u", + ntohs(*(__u16 *)RTA_DATA(attrs))); + else if (attrs->rta_type == MPTCP_ATTR_DPORT) + fprintf(stderr, ",dport:%u", + ntohs(*(__u16 *)RTA_DATA(attrs))); + else if (attrs->rta_type == MPTCP_ATTR_BACKUP) + fprintf(stderr, ",backup:%u", *(__u8 *)RTA_DATA(attrs)); + else if (attrs->rta_type == MPTCP_ATTR_ERROR) + fprintf(stderr, ",error:%u", *(__u8 *)RTA_DATA(attrs)); + else if (attrs->rta_type == MPTCP_ATTR_SERVER_SIDE) + fprintf(stderr, ",server_side:%u", *(__u8 *)RTA_DATA(attrs)); + + attrs = RTA_NEXT(attrs, msg_len); + } + } + fprintf(stderr, "\n"); + } while (1); + + return 0; +} + +/* do a netlink command and, if max > 0, fetch the reply */ +static int do_nl_req(int fd, struct nlmsghdr *nh, int len, int max) +{ + struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK }; + socklen_t addr_len; + void *data = nh; + int rem, ret; + int err = 0; + + nh->nlmsg_len = len; + ret = sendto(fd, data, len, 0, (void *)&nladdr, sizeof(nladdr)); + if (ret != len) + error(1, errno, "send netlink: %uB != %uB\n", ret, len); + if (max == 0) + return 0; + + addr_len = sizeof(nladdr); + rem = ret = recvfrom(fd, data, max, 0, (void *)&nladdr, &addr_len); + if (ret < 0) + error(1, errno, "recv netlink: %uB\n", ret); + + /* Beware: the NLMSG_NEXT macro updates the 'rem' argument */ + for (; NLMSG_OK(nh, rem); nh = NLMSG_NEXT(nh, rem)) { + if (nh->nlmsg_type == NLMSG_ERROR) { + nl_error(nh); + err = 1; + } + } + if (err) + error(1, 0, "bailing out due to netlink error[s]"); + return ret; +} + +static int genl_parse_getfamily(struct nlmsghdr *nlh, int *pm_family, + int *events_mcast_grp) +{ + struct genlmsghdr *ghdr = NLMSG_DATA(nlh); + int len = nlh->nlmsg_len; + struct rtattr *attrs; + struct rtattr *grps; + struct rtattr *grp; + int got_events_grp; + int got_family; + int grps_len; + int grp_len; + + if (nlh->nlmsg_type != GENL_ID_CTRL) + error(1, errno, "Not a controller message, len=%d type=0x%x\n", + nlh->nlmsg_len, nlh->nlmsg_type); + + len -= NLMSG_LENGTH(GENL_HDRLEN); + + if (len < 0) + error(1, errno, "wrong controller message len %d\n", len); + + if (ghdr->cmd != CTRL_CMD_NEWFAMILY) + error(1, errno, "Unknown controller command %d\n", ghdr->cmd); + + attrs = (struct rtattr *) ((char *) ghdr + GENL_HDRLEN); + got_family = 0; + got_events_grp = 0; + + while (RTA_OK(attrs, len)) { + if (attrs->rta_type == CTRL_ATTR_FAMILY_ID) { + *pm_family = *(__u16 *)RTA_DATA(attrs); + got_family = 1; + } else if (attrs->rta_type == CTRL_ATTR_MCAST_GROUPS) { + grps = RTA_DATA(attrs); + grps_len = RTA_PAYLOAD(attrs); + + while (RTA_OK(grps, grps_len)) { + grp = RTA_DATA(grps); + grp_len = RTA_PAYLOAD(grps); + got_events_grp = 0; + + while (RTA_OK(grp, grp_len)) { + if (grp->rta_type == CTRL_ATTR_MCAST_GRP_ID) + *events_mcast_grp = *(__u32 *)RTA_DATA(grp); + else if (grp->rta_type == CTRL_ATTR_MCAST_GRP_NAME && + !strcmp(RTA_DATA(grp), MPTCP_PM_EVENTS)) + got_events_grp = 1; + + grp = RTA_NEXT(grp, grp_len); + } + + if (got_events_grp) + break; + + grps = RTA_NEXT(grps, grps_len); + } + } + + if (got_family && got_events_grp) + return 0; + + attrs = RTA_NEXT(attrs, len); + } + + error(1, errno, "can't find CTRL_ATTR_FAMILY_ID attr"); + return -1; +} + +static int resolve_mptcp_pm_netlink(int fd, int *pm_family, int *events_mcast_grp) +{ + char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) + + NLMSG_ALIGN(sizeof(struct genlmsghdr)) + + 1024]; + struct nlmsghdr *nh; + struct rtattr *rta; + int namelen; + int off = 0; + + memset(data, 0, sizeof(data)); + nh = (void *)data; + off = init_genl_req(data, GENL_ID_CTRL, CTRL_CMD_GETFAMILY, 0); + + rta = (void *)(data + off); + namelen = strlen(MPTCP_PM_NAME) + 1; + rta->rta_type = CTRL_ATTR_FAMILY_NAME; + rta->rta_len = RTA_LENGTH(namelen); + memcpy(RTA_DATA(rta), MPTCP_PM_NAME, namelen); + off += NLMSG_ALIGN(rta->rta_len); + + do_nl_req(fd, nh, off, sizeof(data)); + return genl_parse_getfamily((void *)data, pm_family, events_mcast_grp); +} + +int dsf(int fd, int pm_family, int argc, char *argv[]) +{ + char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) + + NLMSG_ALIGN(sizeof(struct genlmsghdr)) + + 1024]; + struct rtattr *rta, *addr; + u_int16_t family, port; + struct nlmsghdr *nh; + u_int32_t token; + int addr_start; + int off = 0; + int arg; + + const char *params[5]; + + memset(params, 0, 5 * sizeof(const char *)); + + memset(data, 0, sizeof(data)); + nh = (void *)data; + off = init_genl_req(data, pm_family, MPTCP_PM_CMD_SUBFLOW_DESTROY, + MPTCP_PM_VER); + + if (argc < 12) + syntax(argv); + + /* Params recorded in this order: + * <local-ip>, <local-port>, <remote-ip>, <remote-port>, <token> + */ + for (arg = 2; arg < argc; arg++) { + if (!strcmp(argv[arg], "lip")) { + if (++arg >= argc) + error(1, 0, " missing local IP"); + + params[0] = argv[arg]; + } else if (!strcmp(argv[arg], "lport")) { + if (++arg >= argc) + error(1, 0, " missing local port"); + + params[1] = argv[arg]; + } else if (!strcmp(argv[arg], "rip")) { + if (++arg >= argc) + error(1, 0, " missing remote IP"); + + params[2] = argv[arg]; + } else if (!strcmp(argv[arg], "rport")) { + if (++arg >= argc) + error(1, 0, " missing remote port"); + + params[3] = argv[arg]; + } else if (!strcmp(argv[arg], "token")) { + if (++arg >= argc) + error(1, 0, " missing token"); + + params[4] = argv[arg]; + } else + error(1, 0, "unknown keyword %s", argv[arg]); + } + + for (arg = 0; arg < 4; arg = arg + 2) { + /* addr header */ + addr_start = off; + addr = (void *)(data + off); + addr->rta_type = NLA_F_NESTED | + ((arg == 0) ? MPTCP_PM_ATTR_ADDR : MPTCP_PM_ATTR_ADDR_REMOTE); + addr->rta_len = RTA_LENGTH(0); + off += NLMSG_ALIGN(addr->rta_len); + + /* addr data */ + rta = (void *)(data + off); + if (inet_pton(AF_INET, params[arg], RTA_DATA(rta))) { + family = AF_INET; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4; + rta->rta_len = RTA_LENGTH(4); + } else if (inet_pton(AF_INET6, params[arg], RTA_DATA(rta))) { + family = AF_INET6; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6; + rta->rta_len = RTA_LENGTH(16); + } else + error(1, errno, "can't parse ip %s", params[arg]); + off += NLMSG_ALIGN(rta->rta_len); + + /* family */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &family, 2); + off += NLMSG_ALIGN(rta->rta_len); + + /* port */ + port = atoi(params[arg + 1]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_PORT; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &port, 2); + off += NLMSG_ALIGN(rta->rta_len); + + addr->rta_len = off - addr_start; + } + + /* token */ + token = strtoul(params[4], NULL, 10); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ATTR_TOKEN; + rta->rta_len = RTA_LENGTH(4); + memcpy(RTA_DATA(rta), &token, 4); + off += NLMSG_ALIGN(rta->rta_len); + + do_nl_req(fd, nh, off, 0); + + return 0; +} + +int csf(int fd, int pm_family, int argc, char *argv[]) +{ + char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) + + NLMSG_ALIGN(sizeof(struct genlmsghdr)) + + 1024]; + const char *params[5]; + struct nlmsghdr *nh; + struct rtattr *addr; + struct rtattr *rta; + u_int16_t family; + u_int32_t token; + u_int16_t port; + int addr_start; + u_int8_t id; + int off = 0; + int arg; + + memset(params, 0, 5 * sizeof(const char *)); + + memset(data, 0, sizeof(data)); + nh = (void *)data; + off = init_genl_req(data, pm_family, MPTCP_PM_CMD_SUBFLOW_CREATE, + MPTCP_PM_VER); + + if (argc < 12) + syntax(argv); + + /* Params recorded in this order: + * <local-ip>, <local-id>, <remote-ip>, <remote-port>, <token> + */ + for (arg = 2; arg < argc; arg++) { + if (!strcmp(argv[arg], "lip")) { + if (++arg >= argc) + error(1, 0, " missing local IP"); + + params[0] = argv[arg]; + } else if (!strcmp(argv[arg], "lid")) { + if (++arg >= argc) + error(1, 0, " missing local id"); + + params[1] = argv[arg]; + } else if (!strcmp(argv[arg], "rip")) { + if (++arg >= argc) + error(1, 0, " missing remote ip"); + + params[2] = argv[arg]; + } else if (!strcmp(argv[arg], "rport")) { + if (++arg >= argc) + error(1, 0, " missing remote port"); + + params[3] = argv[arg]; + } else if (!strcmp(argv[arg], "token")) { + if (++arg >= argc) + error(1, 0, " missing token"); + + params[4] = argv[arg]; + } else + error(1, 0, "unknown param %s", argv[arg]); + } + + for (arg = 0; arg < 4; arg = arg + 2) { + /* addr header */ + addr_start = off; + addr = (void *)(data + off); + addr->rta_type = NLA_F_NESTED | + ((arg == 0) ? MPTCP_PM_ATTR_ADDR : MPTCP_PM_ATTR_ADDR_REMOTE); + addr->rta_len = RTA_LENGTH(0); + off += NLMSG_ALIGN(addr->rta_len); + + /* addr data */ + rta = (void *)(data + off); + if (inet_pton(AF_INET, params[arg], RTA_DATA(rta))) { + family = AF_INET; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4; + rta->rta_len = RTA_LENGTH(4); + } else if (inet_pton(AF_INET6, params[arg], RTA_DATA(rta))) { + family = AF_INET6; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6; + rta->rta_len = RTA_LENGTH(16); + } else + error(1, errno, "can't parse ip %s", params[arg]); + off += NLMSG_ALIGN(rta->rta_len); + + /* family */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &family, 2); + off += NLMSG_ALIGN(rta->rta_len); + + if (arg == 2) { + /* port */ + port = atoi(params[arg + 1]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_PORT; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &port, 2); + off += NLMSG_ALIGN(rta->rta_len); + } + + if (arg == 0) { + /* id */ + id = atoi(params[arg + 1]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_ID; + rta->rta_len = RTA_LENGTH(1); + memcpy(RTA_DATA(rta), &id, 1); + off += NLMSG_ALIGN(rta->rta_len); + } + + addr->rta_len = off - addr_start; + } + + /* token */ + token = strtoul(params[4], NULL, 10); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ATTR_TOKEN; + rta->rta_len = RTA_LENGTH(4); + memcpy(RTA_DATA(rta), &token, 4); + off += NLMSG_ALIGN(rta->rta_len); + + do_nl_req(fd, nh, off, 0); + + return 0; +} + +int remove_addr(int fd, int pm_family, int argc, char *argv[]) +{ + char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) + + NLMSG_ALIGN(sizeof(struct genlmsghdr)) + + 1024]; + struct nlmsghdr *nh; + struct rtattr *rta; + u_int32_t token; + u_int8_t id; + int off = 0; + int arg; + + memset(data, 0, sizeof(data)); + nh = (void *)data; + off = init_genl_req(data, pm_family, MPTCP_PM_CMD_REMOVE, + MPTCP_PM_VER); + + if (argc < 6) + syntax(argv); + + for (arg = 2; arg < argc; arg++) { + if (!strcmp(argv[arg], "id")) { + if (++arg >= argc) + error(1, 0, " missing id value"); + + id = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ATTR_LOC_ID; + rta->rta_len = RTA_LENGTH(1); + memcpy(RTA_DATA(rta), &id, 1); + off += NLMSG_ALIGN(rta->rta_len); + } else if (!strcmp(argv[arg], "token")) { + if (++arg >= argc) + error(1, 0, " missing token value"); + + token = strtoul(argv[arg], NULL, 10); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ATTR_TOKEN; + rta->rta_len = RTA_LENGTH(4); + memcpy(RTA_DATA(rta), &token, 4); + off += NLMSG_ALIGN(rta->rta_len); + } else + error(1, 0, "unknown keyword %s", argv[arg]); + } + + do_nl_req(fd, nh, off, 0); + return 0; +} + +int announce_addr(int fd, int pm_family, int argc, char *argv[]) +{ + char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) + + NLMSG_ALIGN(sizeof(struct genlmsghdr)) + + 1024]; + u_int32_t flags = MPTCP_PM_ADDR_FLAG_SIGNAL; + u_int32_t token = UINT_MAX; + struct rtattr *rta, *addr; + u_int32_t id = UINT_MAX; + struct nlmsghdr *nh; + u_int16_t family; + int addr_start; + int off = 0; + int arg; + + memset(data, 0, sizeof(data)); + nh = (void *)data; + off = init_genl_req(data, pm_family, MPTCP_PM_CMD_ANNOUNCE, + MPTCP_PM_VER); + + if (argc < 7) + syntax(argv); + + /* local-ip header */ + addr_start = off; + addr = (void *)(data + off); + addr->rta_type = NLA_F_NESTED | MPTCP_PM_ATTR_ADDR; + addr->rta_len = RTA_LENGTH(0); + off += NLMSG_ALIGN(addr->rta_len); + + /* local-ip data */ + /* record addr type */ + rta = (void *)(data + off); + if (inet_pton(AF_INET, argv[2], RTA_DATA(rta))) { + family = AF_INET; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4; + rta->rta_len = RTA_LENGTH(4); + } else if (inet_pton(AF_INET6, argv[2], RTA_DATA(rta))) { + family = AF_INET6; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6; + rta->rta_len = RTA_LENGTH(16); + } else + error(1, errno, "can't parse ip %s", argv[2]); + off += NLMSG_ALIGN(rta->rta_len); + + /* addr family */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &family, 2); + off += NLMSG_ALIGN(rta->rta_len); + + for (arg = 3; arg < argc; arg++) { + if (!strcmp(argv[arg], "id")) { + /* local-id */ + if (++arg >= argc) + error(1, 0, " missing id value"); + + id = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_ID; + rta->rta_len = RTA_LENGTH(1); + memcpy(RTA_DATA(rta), &id, 1); + off += NLMSG_ALIGN(rta->rta_len); + } else if (!strcmp(argv[arg], "dev")) { + /* for the if_index */ + int32_t ifindex; + + if (++arg >= argc) + error(1, 0, " missing dev name"); + + ifindex = if_nametoindex(argv[arg]); + if (!ifindex) + error(1, errno, "unknown device %s", argv[arg]); + + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_IF_IDX; + rta->rta_len = RTA_LENGTH(4); + memcpy(RTA_DATA(rta), &ifindex, 4); + off += NLMSG_ALIGN(rta->rta_len); + } else if (!strcmp(argv[arg], "port")) { + /* local-port (optional) */ + u_int16_t port; + + if (++arg >= argc) + error(1, 0, " missing port value"); + + port = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_PORT; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &port, 2); + off += NLMSG_ALIGN(rta->rta_len); + } else if (!strcmp(argv[arg], "token")) { + /* MPTCP connection token */ + if (++arg >= argc) + error(1, 0, " missing token value"); + + token = strtoul(argv[arg], NULL, 10); + } else + error(1, 0, "unknown keyword %s", argv[arg]); + } + + /* addr flags */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_FLAGS; + rta->rta_len = RTA_LENGTH(4); + memcpy(RTA_DATA(rta), &flags, 4); + off += NLMSG_ALIGN(rta->rta_len); + + addr->rta_len = off - addr_start; + + if (id == UINT_MAX || token == UINT_MAX) + error(1, 0, " missing mandatory inputs"); + + /* token */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ATTR_TOKEN; + rta->rta_len = RTA_LENGTH(4); + memcpy(RTA_DATA(rta), &token, 4); + off += NLMSG_ALIGN(rta->rta_len); + + do_nl_req(fd, nh, off, 0); + + return 0; +} + +int add_addr(int fd, int pm_family, int argc, char *argv[]) +{ + char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) + + NLMSG_ALIGN(sizeof(struct genlmsghdr)) + + 1024]; + struct rtattr *rta, *nest; + struct nlmsghdr *nh; + u_int32_t flags = 0; + u_int16_t family; + int nest_start; + u_int8_t id; + int off = 0; + int arg; + + memset(data, 0, sizeof(data)); + nh = (void *)data; + off = init_genl_req(data, pm_family, MPTCP_PM_CMD_ADD_ADDR, + MPTCP_PM_VER); + + if (argc < 3) + syntax(argv); + + nest_start = off; + nest = (void *)(data + off); + nest->rta_type = NLA_F_NESTED | MPTCP_PM_ATTR_ADDR; + nest->rta_len = RTA_LENGTH(0); + off += NLMSG_ALIGN(nest->rta_len); + + /* addr data */ + rta = (void *)(data + off); + if (inet_pton(AF_INET, argv[2], RTA_DATA(rta))) { + family = AF_INET; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4; + rta->rta_len = RTA_LENGTH(4); + } else if (inet_pton(AF_INET6, argv[2], RTA_DATA(rta))) { + family = AF_INET6; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6; + rta->rta_len = RTA_LENGTH(16); + } else + error(1, errno, "can't parse ip %s", argv[2]); + off += NLMSG_ALIGN(rta->rta_len); + + /* family */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &family, 2); + off += NLMSG_ALIGN(rta->rta_len); + + for (arg = 3; arg < argc; arg++) { + if (!strcmp(argv[arg], "flags")) { + char *tok, *str; + + /* flags */ + if (++arg >= argc) + error(1, 0, " missing flags value"); + + /* do not support flag list yet */ + for (str = argv[arg]; (tok = strtok(str, ",")); + str = NULL) { + if (!strcmp(tok, "subflow")) + flags |= MPTCP_PM_ADDR_FLAG_SUBFLOW; + else if (!strcmp(tok, "signal")) + flags |= MPTCP_PM_ADDR_FLAG_SIGNAL; + else if (!strcmp(tok, "backup")) + flags |= MPTCP_PM_ADDR_FLAG_BACKUP; + else if (!strcmp(tok, "fullmesh")) + flags |= MPTCP_PM_ADDR_FLAG_FULLMESH; + else + error(1, errno, + "unknown flag %s", argv[arg]); + } + + if (flags & MPTCP_PM_ADDR_FLAG_SIGNAL && + flags & MPTCP_PM_ADDR_FLAG_FULLMESH) { + error(1, errno, "error flag fullmesh"); + } + + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_FLAGS; + rta->rta_len = RTA_LENGTH(4); + memcpy(RTA_DATA(rta), &flags, 4); + off += NLMSG_ALIGN(rta->rta_len); + } else if (!strcmp(argv[arg], "id")) { + if (++arg >= argc) + error(1, 0, " missing id value"); + + id = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_ID; + rta->rta_len = RTA_LENGTH(1); + memcpy(RTA_DATA(rta), &id, 1); + off += NLMSG_ALIGN(rta->rta_len); + } else if (!strcmp(argv[arg], "dev")) { + int32_t ifindex; + + if (++arg >= argc) + error(1, 0, " missing dev name"); + + ifindex = if_nametoindex(argv[arg]); + if (!ifindex) + error(1, errno, "unknown device %s", argv[arg]); + + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_IF_IDX; + rta->rta_len = RTA_LENGTH(4); + memcpy(RTA_DATA(rta), &ifindex, 4); + off += NLMSG_ALIGN(rta->rta_len); + } else if (!strcmp(argv[arg], "port")) { + u_int16_t port; + + if (++arg >= argc) + error(1, 0, " missing port value"); + if (!(flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) + error(1, 0, " flags must be signal when using port"); + + port = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_PORT; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &port, 2); + off += NLMSG_ALIGN(rta->rta_len); + } else + error(1, 0, "unknown keyword %s", argv[arg]); + } + nest->rta_len = off - nest_start; + + do_nl_req(fd, nh, off, 0); + return 0; +} + +int del_addr(int fd, int pm_family, int argc, char *argv[]) +{ + char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) + + NLMSG_ALIGN(sizeof(struct genlmsghdr)) + + 1024]; + struct rtattr *rta, *nest; + struct nlmsghdr *nh; + u_int16_t family; + int nest_start; + u_int8_t id; + int off = 0; + + memset(data, 0, sizeof(data)); + nh = (void *)data; + off = init_genl_req(data, pm_family, MPTCP_PM_CMD_DEL_ADDR, + MPTCP_PM_VER); + + /* the only argument is the address id (nonzero) */ + if (argc != 3 && argc != 4) + syntax(argv); + + id = atoi(argv[2]); + /* zero id with the IP address */ + if (!id && argc != 4) + syntax(argv); + + nest_start = off; + nest = (void *)(data + off); + nest->rta_type = NLA_F_NESTED | MPTCP_PM_ATTR_ADDR; + nest->rta_len = RTA_LENGTH(0); + off += NLMSG_ALIGN(nest->rta_len); + + /* build a dummy addr with only the ID set */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_ID; + rta->rta_len = RTA_LENGTH(1); + memcpy(RTA_DATA(rta), &id, 1); + off += NLMSG_ALIGN(rta->rta_len); + + if (!id) { + /* addr data */ + rta = (void *)(data + off); + if (inet_pton(AF_INET, argv[3], RTA_DATA(rta))) { + family = AF_INET; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4; + rta->rta_len = RTA_LENGTH(4); + } else if (inet_pton(AF_INET6, argv[3], RTA_DATA(rta))) { + family = AF_INET6; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6; + rta->rta_len = RTA_LENGTH(16); + } else { + error(1, errno, "can't parse ip %s", argv[3]); + } + off += NLMSG_ALIGN(rta->rta_len); + + /* family */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &family, 2); + off += NLMSG_ALIGN(rta->rta_len); + } + nest->rta_len = off - nest_start; + + do_nl_req(fd, nh, off, 0); + return 0; +} + +static void print_addr(struct rtattr *attrs, int len) +{ + uint16_t family = 0; + uint16_t port = 0; + char str[1024]; + uint32_t flags; + uint8_t id; + + while (RTA_OK(attrs, len)) { + if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_FAMILY) + memcpy(&family, RTA_DATA(attrs), 2); + if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_PORT) + memcpy(&port, RTA_DATA(attrs), 2); + if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_ADDR4) { + if (family != AF_INET) + error(1, errno, "wrong IP (v4) for family %d", + family); + inet_ntop(AF_INET, RTA_DATA(attrs), str, sizeof(str)); + printf("%s", str); + if (port) + printf(" %d", port); + } + if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_ADDR6) { + if (family != AF_INET6) + error(1, errno, "wrong IP (v6) for family %d", + family); + inet_ntop(AF_INET6, RTA_DATA(attrs), str, sizeof(str)); + printf("%s", str); + if (port) + printf(" %d", port); + } + if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_ID) { + memcpy(&id, RTA_DATA(attrs), 1); + printf("id %d ", id); + } + if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_FLAGS) { + memcpy(&flags, RTA_DATA(attrs), 4); + + printf("flags "); + if (flags & MPTCP_PM_ADDR_FLAG_SIGNAL) { + printf("signal"); + flags &= ~MPTCP_PM_ADDR_FLAG_SIGNAL; + if (flags) + printf(","); + } + + if (flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { + printf("subflow"); + flags &= ~MPTCP_PM_ADDR_FLAG_SUBFLOW; + if (flags) + printf(","); + } + + if (flags & MPTCP_PM_ADDR_FLAG_BACKUP) { + printf("backup"); + flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP; + if (flags) + printf(","); + } + + if (flags & MPTCP_PM_ADDR_FLAG_FULLMESH) { + printf("fullmesh"); + flags &= ~MPTCP_PM_ADDR_FLAG_FULLMESH; + if (flags) + printf(","); + } + + if (flags & MPTCP_PM_ADDR_FLAG_IMPLICIT) { + printf("implicit"); + flags &= ~MPTCP_PM_ADDR_FLAG_IMPLICIT; + if (flags) + printf(","); + } + + /* bump unknown flags, if any */ + if (flags) + printf("0x%x", flags); + printf(" "); + } + if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_IF_IDX) { + char name[IF_NAMESIZE], *ret; + int32_t ifindex; + + memcpy(&ifindex, RTA_DATA(attrs), 4); + ret = if_indextoname(ifindex, name); + if (ret) + printf("dev %s ", ret); + else + printf("dev unknown/%d", ifindex); + } + + attrs = RTA_NEXT(attrs, len); + } + printf("\n"); +} + +static void print_addrs(struct nlmsghdr *nh, int pm_family, int total_len) +{ + struct rtattr *attrs; + + for (; NLMSG_OK(nh, total_len); nh = NLMSG_NEXT(nh, total_len)) { + int len = nh->nlmsg_len; + + if (nh->nlmsg_type == NLMSG_DONE) + break; + if (nh->nlmsg_type == NLMSG_ERROR) + nl_error(nh); + if (nh->nlmsg_type != pm_family) + continue; + + len -= NLMSG_LENGTH(GENL_HDRLEN); + attrs = (struct rtattr *) ((char *) NLMSG_DATA(nh) + + GENL_HDRLEN); + while (RTA_OK(attrs, len)) { + if (attrs->rta_type == + (MPTCP_PM_ATTR_ADDR | NLA_F_NESTED)) + print_addr((void *)RTA_DATA(attrs), + attrs->rta_len); + attrs = RTA_NEXT(attrs, len); + } + } +} + +int get_addr(int fd, int pm_family, int argc, char *argv[]) +{ + char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) + + NLMSG_ALIGN(sizeof(struct genlmsghdr)) + + 1024]; + struct rtattr *rta, *nest; + struct nlmsghdr *nh; + int nest_start; + u_int8_t id; + int off = 0; + + memset(data, 0, sizeof(data)); + nh = (void *)data; + off = init_genl_req(data, pm_family, MPTCP_PM_CMD_GET_ADDR, + MPTCP_PM_VER); + + /* the only argument is the address id */ + if (argc != 3) + syntax(argv); + + id = atoi(argv[2]); + + nest_start = off; + nest = (void *)(data + off); + nest->rta_type = NLA_F_NESTED | MPTCP_PM_ATTR_ADDR; + nest->rta_len = RTA_LENGTH(0); + off += NLMSG_ALIGN(nest->rta_len); + + /* build a dummy addr with only the ID set */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_ID; + rta->rta_len = RTA_LENGTH(1); + memcpy(RTA_DATA(rta), &id, 1); + off += NLMSG_ALIGN(rta->rta_len); + nest->rta_len = off - nest_start; + + print_addrs(nh, pm_family, do_nl_req(fd, nh, off, sizeof(data))); + return 0; +} + +int dump_addrs(int fd, int pm_family, int argc, char *argv[]) +{ + char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) + + NLMSG_ALIGN(sizeof(struct genlmsghdr)) + + 1024]; + pid_t pid = getpid(); + struct nlmsghdr *nh; + int off = 0; + + memset(data, 0, sizeof(data)); + nh = (void *)data; + off = init_genl_req(data, pm_family, MPTCP_PM_CMD_GET_ADDR, + MPTCP_PM_VER); + nh->nlmsg_flags |= NLM_F_DUMP; + nh->nlmsg_seq = 1; + nh->nlmsg_pid = pid; + nh->nlmsg_len = off; + + print_addrs(nh, pm_family, do_nl_req(fd, nh, off, sizeof(data))); + return 0; +} + +int flush_addrs(int fd, int pm_family, int argc, char *argv[]) +{ + char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) + + NLMSG_ALIGN(sizeof(struct genlmsghdr)) + + 1024]; + struct nlmsghdr *nh; + int off = 0; + + memset(data, 0, sizeof(data)); + nh = (void *)data; + off = init_genl_req(data, pm_family, MPTCP_PM_CMD_FLUSH_ADDRS, + MPTCP_PM_VER); + + do_nl_req(fd, nh, off, 0); + return 0; +} + +static void print_limits(struct nlmsghdr *nh, int pm_family, int total_len) +{ + struct rtattr *attrs; + uint32_t max; + + for (; NLMSG_OK(nh, total_len); nh = NLMSG_NEXT(nh, total_len)) { + int len = nh->nlmsg_len; + + if (nh->nlmsg_type == NLMSG_DONE) + break; + if (nh->nlmsg_type == NLMSG_ERROR) + nl_error(nh); + if (nh->nlmsg_type != pm_family) + continue; + + len -= NLMSG_LENGTH(GENL_HDRLEN); + attrs = (struct rtattr *) ((char *) NLMSG_DATA(nh) + + GENL_HDRLEN); + while (RTA_OK(attrs, len)) { + int type = attrs->rta_type; + + if (type != MPTCP_PM_ATTR_RCV_ADD_ADDRS && + type != MPTCP_PM_ATTR_SUBFLOWS) + goto next; + + memcpy(&max, RTA_DATA(attrs), 4); + printf("%s %u\n", type == MPTCP_PM_ATTR_SUBFLOWS ? + "subflows" : "accept", max); + +next: + attrs = RTA_NEXT(attrs, len); + } + } +} + +int get_set_limits(int fd, int pm_family, int argc, char *argv[]) +{ + char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) + + NLMSG_ALIGN(sizeof(struct genlmsghdr)) + + 1024]; + uint32_t rcv_addr = 0, subflows = 0; + int cmd, len = sizeof(data); + struct nlmsghdr *nh; + int off = 0; + + /* limit */ + if (argc == 4) { + rcv_addr = atoi(argv[2]); + subflows = atoi(argv[3]); + cmd = MPTCP_PM_CMD_SET_LIMITS; + } else { + cmd = MPTCP_PM_CMD_GET_LIMITS; + } + + memset(data, 0, sizeof(data)); + nh = (void *)data; + off = init_genl_req(data, pm_family, cmd, MPTCP_PM_VER); + + /* limit */ + if (cmd == MPTCP_PM_CMD_SET_LIMITS) { + struct rtattr *rta = (void *)(data + off); + + rta->rta_type = MPTCP_PM_ATTR_RCV_ADD_ADDRS; + rta->rta_len = RTA_LENGTH(4); + memcpy(RTA_DATA(rta), &rcv_addr, 4); + off += NLMSG_ALIGN(rta->rta_len); + + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ATTR_SUBFLOWS; + rta->rta_len = RTA_LENGTH(4); + memcpy(RTA_DATA(rta), &subflows, 4); + off += NLMSG_ALIGN(rta->rta_len); + + /* do not expect a reply */ + len = 0; + } + + len = do_nl_req(fd, nh, off, len); + if (cmd == MPTCP_PM_CMD_GET_LIMITS) + print_limits(nh, pm_family, len); + return 0; +} + +int add_listener(int argc, char *argv[]) +{ + struct sockaddr_storage addr; + struct sockaddr_in6 *a6; + struct sockaddr_in *a4; + u_int16_t family; + int enable = 1; + int sock; + int err; + + if (argc < 4) + syntax(argv); + + memset(&addr, 0, sizeof(struct sockaddr_storage)); + a4 = (struct sockaddr_in *)&addr; + a6 = (struct sockaddr_in6 *)&addr; + + if (inet_pton(AF_INET, argv[2], &a4->sin_addr)) { + family = AF_INET; + a4->sin_family = family; + a4->sin_port = htons(atoi(argv[3])); + } else if (inet_pton(AF_INET6, argv[2], &a6->sin6_addr)) { + family = AF_INET6; + a6->sin6_family = family; + a6->sin6_port = htons(atoi(argv[3])); + } else + error(1, errno, "can't parse ip %s", argv[2]); + + sock = socket(family, SOCK_STREAM, IPPROTO_MPTCP); + if (sock < 0) + error(1, errno, "can't create listener sock\n"); + + if (setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &enable, sizeof(enable))) { + close(sock); + error(1, errno, "can't set SO_REUSEADDR on listener sock\n"); + } + + err = bind(sock, (struct sockaddr *)&addr, + ((family == AF_INET) ? sizeof(struct sockaddr_in) : + sizeof(struct sockaddr_in6))); + + if (err == 0 && listen(sock, 30) == 0) + pause(); + + close(sock); + return 0; +} + +int set_flags(int fd, int pm_family, int argc, char *argv[]) +{ + char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) + + NLMSG_ALIGN(sizeof(struct genlmsghdr)) + + 1024]; + struct rtattr *rta, *nest; + struct nlmsghdr *nh; + u_int32_t flags = 0; + u_int32_t token = 0; + u_int16_t rport = 0; + u_int16_t family; + void *rip = NULL; + int nest_start; + int use_id = 0; + u_int8_t id; + int off = 0; + int arg = 2; + + memset(data, 0, sizeof(data)); + nh = (void *)data; + off = init_genl_req(data, pm_family, MPTCP_PM_CMD_SET_FLAGS, + MPTCP_PM_VER); + + if (argc < 3) + syntax(argv); + + nest_start = off; + nest = (void *)(data + off); + nest->rta_type = NLA_F_NESTED | MPTCP_PM_ATTR_ADDR; + nest->rta_len = RTA_LENGTH(0); + off += NLMSG_ALIGN(nest->rta_len); + + if (!strcmp(argv[arg], "id")) { + if (++arg >= argc) + error(1, 0, " missing id value"); + + use_id = 1; + id = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_ID; + rta->rta_len = RTA_LENGTH(1); + memcpy(RTA_DATA(rta), &id, 1); + off += NLMSG_ALIGN(rta->rta_len); + } else { + /* addr data */ + rta = (void *)(data + off); + if (inet_pton(AF_INET, argv[arg], RTA_DATA(rta))) { + family = AF_INET; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4; + rta->rta_len = RTA_LENGTH(4); + } else if (inet_pton(AF_INET6, argv[arg], RTA_DATA(rta))) { + family = AF_INET6; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6; + rta->rta_len = RTA_LENGTH(16); + } else { + error(1, errno, "can't parse ip %s", argv[arg]); + } + off += NLMSG_ALIGN(rta->rta_len); + + /* family */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &family, 2); + off += NLMSG_ALIGN(rta->rta_len); + } + + if (++arg >= argc) + error(1, 0, " missing flags keyword"); + + for (; arg < argc; arg++) { + if (!strcmp(argv[arg], "token")) { + if (++arg >= argc) + error(1, 0, " missing token value"); + + /* token */ + token = strtoul(argv[arg], NULL, 10); + } else if (!strcmp(argv[arg], "flags")) { + char *tok, *str; + + /* flags */ + if (++arg >= argc) + error(1, 0, " missing flags value"); + + for (str = argv[arg]; (tok = strtok(str, ",")); + str = NULL) { + if (!strcmp(tok, "backup")) + flags |= MPTCP_PM_ADDR_FLAG_BACKUP; + else if (!strcmp(tok, "fullmesh")) + flags |= MPTCP_PM_ADDR_FLAG_FULLMESH; + else if (strcmp(tok, "nobackup") && + strcmp(tok, "nofullmesh")) + error(1, errno, + "unknown flag %s", argv[arg]); + } + + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_FLAGS; + rta->rta_len = RTA_LENGTH(4); + memcpy(RTA_DATA(rta), &flags, 4); + off += NLMSG_ALIGN(rta->rta_len); + } else if (!strcmp(argv[arg], "port")) { + u_int16_t port; + + if (use_id) + error(1, 0, " port can't be used with id"); + + if (++arg >= argc) + error(1, 0, " missing port value"); + + port = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_PORT; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &port, 2); + off += NLMSG_ALIGN(rta->rta_len); + } else if (!strcmp(argv[arg], "rport")) { + if (++arg >= argc) + error(1, 0, " missing remote port"); + + rport = atoi(argv[arg]); + } else if (!strcmp(argv[arg], "rip")) { + if (++arg >= argc) + error(1, 0, " missing remote ip"); + + rip = argv[arg]; + } else { + error(1, 0, "unknown keyword %s", argv[arg]); + } + } + nest->rta_len = off - nest_start; + + /* token */ + if (token) { + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ATTR_TOKEN; + rta->rta_len = RTA_LENGTH(4); + memcpy(RTA_DATA(rta), &token, 4); + off += NLMSG_ALIGN(rta->rta_len); + } + + /* remote addr/port */ + if (rip) { + nest_start = off; + nest = (void *)(data + off); + nest->rta_type = NLA_F_NESTED | MPTCP_PM_ATTR_ADDR_REMOTE; + nest->rta_len = RTA_LENGTH(0); + off += NLMSG_ALIGN(nest->rta_len); + + /* addr data */ + rta = (void *)(data + off); + if (inet_pton(AF_INET, rip, RTA_DATA(rta))) { + family = AF_INET; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4; + rta->rta_len = RTA_LENGTH(4); + } else if (inet_pton(AF_INET6, rip, RTA_DATA(rta))) { + family = AF_INET6; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6; + rta->rta_len = RTA_LENGTH(16); + } else { + error(1, errno, "can't parse ip %s", (char *)rip); + } + off += NLMSG_ALIGN(rta->rta_len); + + /* family */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &family, 2); + off += NLMSG_ALIGN(rta->rta_len); + + if (rport) { + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_PORT; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &rport, 2); + off += NLMSG_ALIGN(rta->rta_len); + } + + nest->rta_len = off - nest_start; + } + + do_nl_req(fd, nh, off, 0); + return 0; +} + +int main(int argc, char *argv[]) +{ + int events_mcast_grp; + int pm_family; + int fd; + + if (argc < 2) + syntax(argv); + + fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC); + if (fd == -1) + error(1, errno, "socket netlink"); + + resolve_mptcp_pm_netlink(fd, &pm_family, &events_mcast_grp); + + if (!strcmp(argv[1], "add")) + return add_addr(fd, pm_family, argc, argv); + else if (!strcmp(argv[1], "ann")) + return announce_addr(fd, pm_family, argc, argv); + else if (!strcmp(argv[1], "rem")) + return remove_addr(fd, pm_family, argc, argv); + else if (!strcmp(argv[1], "csf")) + return csf(fd, pm_family, argc, argv); + else if (!strcmp(argv[1], "dsf")) + return dsf(fd, pm_family, argc, argv); + else if (!strcmp(argv[1], "del")) + return del_addr(fd, pm_family, argc, argv); + else if (!strcmp(argv[1], "flush")) + return flush_addrs(fd, pm_family, argc, argv); + else if (!strcmp(argv[1], "get")) + return get_addr(fd, pm_family, argc, argv); + else if (!strcmp(argv[1], "dump")) + return dump_addrs(fd, pm_family, argc, argv); + else if (!strcmp(argv[1], "limits")) + return get_set_limits(fd, pm_family, argc, argv); + else if (!strcmp(argv[1], "set")) + return set_flags(fd, pm_family, argc, argv); + else if (!strcmp(argv[1], "events")) + return capture_events(fd, events_mcast_grp); + else if (!strcmp(argv[1], "listen")) + return add_listener(argc, argv); + + fprintf(stderr, "unknown sub-command: %s", argv[1]); + syntax(argv); + return 0; +} diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings new file mode 100644 index 000000000..79b65bdf0 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/settings @@ -0,0 +1 @@ +timeout=1200 diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh new file mode 100755 index 000000000..4a417f9d5 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -0,0 +1,310 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(dirname "${0}")/mptcp_lib.sh" + +rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) +ns1="ns1-$rndh" +ns2="ns2-$rndh" +ns3="ns3-$rndh" +capture=false +ksft_skip=4 +timeout_poll=30 +timeout_test=$((timeout_poll * 2 + 1)) +test_cnt=1 +ret=0 +bail=0 +slack=50 + +usage() { + echo "Usage: $0 [ -b ] [ -c ] [ -d ]" + echo -e "\t-b: bail out after first error, otherwise runs al testcases" + echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)" + echo -e "\t-d: debug this script" +} + +cleanup() +{ + rm -f "$cout" "$sout" + rm -f "$large" "$small" + rm -f "$capout" + + local netns + for netns in "$ns1" "$ns2" "$ns3";do + ip netns del $netns + done +} + +mptcp_lib_check_mptcp + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +# "$ns1" ns2 ns3 +# ns1eth1 ns2eth1 ns2eth3 ns3eth1 +# netem +# ns1eth2 ns2eth2 +# netem + +setup() +{ + large=$(mktemp) + small=$(mktemp) + sout=$(mktemp) + cout=$(mktemp) + capout=$(mktemp) + size=$((2 * 2048 * 4096)) + + dd if=/dev/zero of=$small bs=4096 count=20 >/dev/null 2>&1 + dd if=/dev/zero of=$large bs=4096 count=$((size / 4096)) >/dev/null 2>&1 + + trap cleanup EXIT + + for i in "$ns1" "$ns2" "$ns3";do + ip netns add $i || exit $ksft_skip + ip -net $i link set lo up + ip netns exec $i sysctl -q net.ipv4.conf.all.rp_filter=0 + ip netns exec $i sysctl -q net.ipv4.conf.default.rp_filter=0 + done + + ip link add ns1eth1 netns "$ns1" type veth peer name ns2eth1 netns "$ns2" + ip link add ns1eth2 netns "$ns1" type veth peer name ns2eth2 netns "$ns2" + ip link add ns2eth3 netns "$ns2" type veth peer name ns3eth1 netns "$ns3" + + ip -net "$ns1" addr add 10.0.1.1/24 dev ns1eth1 + ip -net "$ns1" addr add dead:beef:1::1/64 dev ns1eth1 nodad + ip -net "$ns1" link set ns1eth1 up mtu 1500 + ip -net "$ns1" route add default via 10.0.1.2 + ip -net "$ns1" route add default via dead:beef:1::2 + + ip -net "$ns1" addr add 10.0.2.1/24 dev ns1eth2 + ip -net "$ns1" addr add dead:beef:2::1/64 dev ns1eth2 nodad + ip -net "$ns1" link set ns1eth2 up mtu 1500 + ip -net "$ns1" route add default via 10.0.2.2 metric 101 + ip -net "$ns1" route add default via dead:beef:2::2 metric 101 + + ip netns exec "$ns1" ./pm_nl_ctl limits 1 1 + ip netns exec "$ns1" ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags subflow + + ip -net "$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 mtu 1500 + + ip -net "$ns2" addr add 10.0.2.2/24 dev ns2eth2 + ip -net "$ns2" addr add dead:beef:2::2/64 dev ns2eth2 nodad + ip -net "$ns2" link set ns2eth2 up mtu 1500 + + ip -net "$ns2" addr add 10.0.3.2/24 dev ns2eth3 + ip -net "$ns2" addr add dead:beef:3::2/64 dev ns2eth3 nodad + ip -net "$ns2" link set ns2eth3 up mtu 1500 + 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 "$ns3" addr add 10.0.3.3/24 dev ns3eth1 + ip -net "$ns3" addr add dead:beef:3::3/64 dev ns3eth1 nodad + ip -net "$ns3" link set ns3eth1 up mtu 1500 + ip -net "$ns3" route add default via 10.0.3.2 + ip -net "$ns3" route add default via dead:beef:3::2 + + ip netns exec "$ns3" ./pm_nl_ctl limits 1 1 + + # debug build can slow down measurably the test program + # we use quite tight time limit on the run-time, to ensure + # maximum B/W usage. + # Use kmemleak/lockdep/kasan/prove_locking presence as a rough + # estimate for this being a debug kernel and increase the + # maximum run-time accordingly. Observed run times for CI builds + # running selftests, including kbuild, were used to determine the + # amount of time to add. + grep -q ' kmemleak_init$\| lockdep_init$\| kasan_init$\| prove_locking$' /proc/kallsyms && slack=$((slack+550)) +} + +# $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 cin=$1 + local sin=$2 + local max_time=$3 + local port + port=$((10000+$test_cnt)) + test_cnt=$((test_cnt+1)) + + :> "$cout" + :> "$sout" + :> "$capout" + + local addr_port + addr_port=$(printf "%s:%d" ${connect_addr} ${port}) + + if $capture; then + local capuser + if [ -z $SUDO_USER ] ; then + capuser="" + else + capuser="-Z $SUDO_USER" + fi + + local capfile="${rndh}-${port}" + local capopt="-i any -s 65535 -B 32768 ${capuser}" + + ip netns exec ${ns3} tcpdump ${capopt} -w "${capfile}-listener.pcap" >> "${capout}" 2>&1 & + local cappid_listener=$! + + ip netns exec ${ns1} tcpdump ${capopt} -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 & + local cappid_connector=$! + + sleep 1 + fi + + timeout ${timeout_test} \ + ip netns exec ${ns3} \ + ./mptcp_connect -jt ${timeout_poll} -l -p $port -T $time \ + 0.0.0.0 < "$sin" > "$sout" & + local spid=$! + + wait_local_port_listen "${ns3}" "${port}" + + timeout ${timeout_test} \ + ip netns exec ${ns1} \ + ./mptcp_connect -jt ${timeout_poll} -p $port -T $time \ + 10.0.3.3 < "$cin" > "$cout" & + local cpid=$! + + wait $cpid + local retc=$? + wait $spid + local rets=$? + + if $capture; then + sleep 1 + kill ${cappid_listener} + kill ${cappid_connector} + fi + + cmp $sin $cout > /dev/null 2>&1 + local cmps=$? + cmp $cin $sout > /dev/null 2>&1 + local cmpc=$? + + printf "%-16s" " max $max_time " + if [ $retc -eq 0 ] && [ $rets -eq 0 ] && \ + [ $cmpc -eq 0 ] && [ $cmps -eq 0 ]; then + echo "[ OK ]" + cat "$capout" + return 0 + fi + + echo " [ fail ]" + echo "client exit code $retc, server $rets" 1>&2 + echo -e "\nnetns ${ns3} socket stat for $port:" 1>&2 + ip netns exec ${ns3} ss -nita 1>&2 -o "sport = :$port" + echo -e "\nnetns ${ns1} socket stat for $port:" 1>&2 + ip netns exec ${ns1} ss -nita 1>&2 -o "dport = :$port" + ls -l $sin $cout + ls -l $cin $sout + + cat "$capout" + return 1 +} + +run_test() +{ + local rate1=$1 + local rate2=$2 + local delay1=$3 + local delay2=$4 + local lret + local dev + shift 4 + local msg=$* + + [ $delay1 -gt 0 ] && delay1="delay $delay1" || delay1="" + [ $delay2 -gt 0 ] && delay2="delay $delay2" || delay2="" + + for dev in ns1eth1 ns1eth2; do + tc -n $ns1 qdisc del dev $dev root >/dev/null 2>&1 + done + for dev in ns2eth1 ns2eth2; do + tc -n $ns2 qdisc del dev $dev root >/dev/null 2>&1 + done + tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 + tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 + tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 + tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 + + # time is measured in ms, account for transfer size, aggregated link speed + # and header overhead (10%) + # ms byte -> bit 10% mbit -> kbit -> bit 10% + local time=$((1000 * size * 8 * 10 / ((rate1 + rate2) * 1000 * 1000 * 9) )) + + # mptcp_connect will do some sleeps to allow the mp_join handshake + # completion (see mptcp_connect): 200ms on each side, add some slack + time=$((time + 400 + slack)) + + printf "%-60s" "$msg" + do_transfer $small $large $time + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + [ $bail -eq 0 ] || exit $ret + fi + + printf "%-60s" "$msg - reverse direction" + do_transfer $large $small $time + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + [ $bail -eq 0 ] || exit $ret + fi +} + +while getopts "bcdh" option;do + case "$option" in + "h") + usage $0 + exit 0 + ;; + "b") + bail=1 + ;; + "c") + capture=true + ;; + "d") + set -x + ;; + "?") + usage $0 + exit 1 + ;; + esac +done + +setup +run_test 10 10 0 0 "balanced bwidth" +run_test 10 10 1 50 "balanced bwidth with unbalanced delay" + +# we still need some additional infrastructure to pass the following test-cases +run_test 30 10 0 0 "unbalanced bwidth" +run_test 30 10 1 50 "unbalanced bwidth with unbalanced delay" +run_test 30 10 50 1 "unbalanced bwidth with opposed, unbalanced delay" +exit $ret diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh new file mode 100755 index 000000000..cb6c28d40 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -0,0 +1,886 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(dirname "${0}")/mptcp_lib.sh" + +mptcp_lib_check_mptcp + +if ! mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + echo "userspace pm tests are not supported by the kernel: SKIP" + exit ${KSFT_SKIP} +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Cannot not run test without ip tool" + exit ${KSFT_SKIP} +fi + +ANNOUNCED=6 # MPTCP_EVENT_ANNOUNCED +REMOVED=7 # MPTCP_EVENT_REMOVED +SUB_ESTABLISHED=10 # MPTCP_EVENT_SUB_ESTABLISHED +SUB_CLOSED=11 # MPTCP_EVENT_SUB_CLOSED + +AF_INET=2 +AF_INET6=10 + +evts_pid=0 +client4_pid=0 +server4_pid=0 +client6_pid=0 +server6_pid=0 +client4_token="" +server4_token="" +client6_token="" +server6_token="" +client4_port=0; +client6_port=0; +app4_port=50002 +new4_port=50003 +app6_port=50004 +client_addr_id=${RANDOM:0:2} +server_addr_id=${RANDOM:0:2} + +sec=$(date +%s) +rndh=$(stdbuf -o0 -e0 printf %x "$sec")-$(mktemp -u XXXXXX) +ns1="ns1-$rndh" +ns2="ns2-$rndh" + +kill_wait() +{ + kill $1 > /dev/null 2>&1 + wait $1 2>/dev/null +} + +cleanup() +{ + echo "cleanup" + + rm -rf $file + + # Terminate the MPTCP connection and related processes + if [ $client4_pid -ne 0 ]; then + kill -SIGUSR1 $client4_pid > /dev/null 2>&1 + fi + if [ $server4_pid -ne 0 ]; then + kill_wait $server4_pid + fi + if [ $client6_pid -ne 0 ]; then + kill -SIGUSR1 $client6_pid > /dev/null 2>&1 + fi + if [ $server6_pid -ne 0 ]; then + kill_wait $server6_pid + fi + if [ $evts_pid -ne 0 ]; then + kill_wait $evts_pid + fi + local netns + for netns in "$ns1" "$ns2" ;do + ip netns del "$netns" + done +} + +trap cleanup EXIT + +# Create and configure network namespaces for testing +for i in "$ns1" "$ns2" ;do + ip netns add "$i" || exit 1 + ip -net "$i" link set lo up + ip netns exec "$i" sysctl -q net.mptcp.enabled=1 + ip netns exec "$i" sysctl -q net.mptcp.pm_type=1 +done + +# "$ns1" ns2 +# ns1eth2 ns2eth1 + +ip link add ns1eth2 netns "$ns1" type veth peer name ns2eth1 netns "$ns2" + +# Add IPv4/v6 addresses to the namespaces +ip -net "$ns1" addr add 10.0.1.1/24 dev ns1eth2 +ip -net "$ns1" addr add 10.0.2.1/24 dev ns1eth2 +ip -net "$ns1" addr add dead:beef:1::1/64 dev ns1eth2 nodad +ip -net "$ns1" addr add dead:beef:2::1/64 dev ns1eth2 nodad +ip -net "$ns1" link set ns1eth2 up + +ip -net "$ns2" addr add 10.0.1.2/24 dev ns2eth1 +ip -net "$ns2" addr add 10.0.2.2/24 dev ns2eth1 +ip -net "$ns2" addr add dead:beef:1::2/64 dev ns2eth1 nodad +ip -net "$ns2" addr add dead:beef:2::2/64 dev ns2eth1 nodad +ip -net "$ns2" link set ns2eth1 up + +stdbuf -o0 -e0 printf "Created network namespaces ns1, ns2 \t\t\t[OK]\n" + +make_file() +{ + # Store a chunk of data in a file to transmit over an MPTCP connection + local name=$1 + local ksize=1 + + dd if=/dev/urandom of="$name" bs=2 count=$ksize 2> /dev/null + echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" +} + +make_connection() +{ + local file + file=$(mktemp) + make_file "$file" "client" + + local is_v6=$1 + local app_port=$app4_port + local connect_addr="10.0.1.1" + local listen_addr="0.0.0.0" + if [ "$is_v6" = "v6" ] + then + connect_addr="dead:beef:1::1" + listen_addr="::" + app_port=$app6_port + else + is_v6="v4" + fi + + # Capture netlink events over the two network namespaces running + # the MPTCP client and server + local client_evts + client_evts=$(mktemp) + :>"$client_evts" + ip netns exec "$ns2" ./pm_nl_ctl events >> "$client_evts" 2>&1 & + local client_evts_pid=$! + local server_evts + server_evts=$(mktemp) + :>"$server_evts" + ip netns exec "$ns1" ./pm_nl_ctl events >> "$server_evts" 2>&1 & + local server_evts_pid=$! + sleep 0.5 + + # Run the server + ip netns exec "$ns1" \ + ./mptcp_connect -s MPTCP -w 300 -p $app_port -l $listen_addr > /dev/null 2>&1 & + local server_pid=$! + sleep 0.5 + + # Run the client, transfer $file and stay connected to the server + # to conduct tests + ip netns exec "$ns2" \ + ./mptcp_connect -s MPTCP -w 300 -m sendfile -p $app_port $connect_addr\ + 2>&1 > /dev/null < "$file" & + local client_pid=$! + sleep 1 + + # Capture client/server attributes from MPTCP connection netlink events + kill_wait $client_evts_pid + + local client_token + local client_port + local client_serverside + local server_token + local server_serverside + + client_token=$(sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts") + client_port=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts") + client_serverside=$(sed --unbuffered -n 's/.*\(server_side:\)\([[:digit:]]*\).*$/\2/p;q'\ + "$client_evts") + kill_wait $server_evts_pid + server_token=$(sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts") + server_serverside=$(sed --unbuffered -n 's/.*\(server_side:\)\([[:digit:]]*\).*$/\2/p;q'\ + "$server_evts") + rm -f "$client_evts" "$server_evts" "$file" + + if [ "$client_token" != "" ] && [ "$server_token" != "" ] && [ "$client_serverside" = 0 ] && + [ "$server_serverside" = 1 ] + then + stdbuf -o0 -e0 printf "Established IP%s MPTCP Connection ns2 => ns1 \t\t[OK]\n" $is_v6 + else + exit 1 + fi + + if [ "$is_v6" = "v6" ] + then + client6_token=$client_token + server6_token=$server_token + client6_port=$client_port + client6_pid=$client_pid + server6_pid=$server_pid + else + client4_token=$client_token + server4_token=$server_token + client4_port=$client_port + client4_pid=$client_pid + server4_pid=$server_pid + fi +} + +verify_announce_event() +{ + local evt=$1 + local e_type=$2 + local e_token=$3 + local e_addr=$4 + local e_id=$5 + local e_dport=$6 + local e_af=$7 + local type + local token + local addr + local dport + local id + + type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + token=$(sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + if [ "$e_af" = "v6" ] + then + addr=$(sed --unbuffered -n 's/.*\(daddr6:\)\([0-9a-f:.]*\).*$/\2/p;q' "$evt") + else + addr=$(sed --unbuffered -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evt") + fi + dport=$(sed --unbuffered -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + id=$(sed --unbuffered -n 's/.*\(rem_id:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + if [ "$type" = "$e_type" ] && [ "$token" = "$e_token" ] && + [ "$addr" = "$e_addr" ] && [ "$dport" = "$e_dport" ] && + [ "$id" = "$e_id" ] + then + stdbuf -o0 -e0 printf "[OK]\n" + return 0 + fi + stdbuf -o0 -e0 printf "[FAIL]\n" + exit 1 +} + +test_announce() +{ + local evts + evts=$(mktemp) + # Capture events on the network namespace running the server + :>"$evts" + ip netns exec "$ns1" ./pm_nl_ctl events >> "$evts" 2>&1 & + evts_pid=$! + sleep 0.5 + + # ADD_ADDR using an invalid token should result in no action + local invalid_token=$(( client4_token - 1)) + ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token $invalid_token id\ + $client_addr_id dev ns2eth1 > /dev/null 2>&1 + + local type + type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$evts") + stdbuf -o0 -e0 printf "ADD_ADDR 10.0.2.2 (ns2) => ns1, invalid token \t\t" + if [ "$type" = "" ] + then + stdbuf -o0 -e0 printf "[OK]\n" + else + stdbuf -o0 -e0 printf "[FAIL]\n" + exit 1 + fi + + # ADD_ADDR from the client to server machine reusing the subflow port + :>"$evts" + ip netns exec "$ns2"\ + ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id $client_addr_id dev\ + ns2eth1 > /dev/null 2>&1 + stdbuf -o0 -e0 printf "ADD_ADDR id:%d 10.0.2.2 (ns2) => ns1, reuse port \t\t" $client_addr_id + sleep 0.5 + verify_announce_event "$evts" "$ANNOUNCED" "$server4_token" "10.0.2.2" "$client_addr_id"\ + "$client4_port" + + # ADD_ADDR6 from the client to server machine reusing the subflow port + :>"$evts" + ip netns exec "$ns2" ./pm_nl_ctl ann\ + dead:beef:2::2 token "$client6_token" id $client_addr_id dev ns2eth1 > /dev/null 2>&1 + stdbuf -o0 -e0 printf "ADD_ADDR6 id:%d dead:beef:2::2 (ns2) => ns1, reuse port\t\t" $client_addr_id + sleep 0.5 + verify_announce_event "$evts" "$ANNOUNCED" "$server6_token" "dead:beef:2::2"\ + "$client_addr_id" "$client6_port" "v6" + + # ADD_ADDR from the client to server machine using a new port + :>"$evts" + client_addr_id=$((client_addr_id+1)) + ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\ + $client_addr_id dev ns2eth1 port $new4_port > /dev/null 2>&1 + stdbuf -o0 -e0 printf "ADD_ADDR id:%d 10.0.2.2 (ns2) => ns1, new port \t\t\t" $client_addr_id + sleep 0.5 + verify_announce_event "$evts" "$ANNOUNCED" "$server4_token" "10.0.2.2"\ + "$client_addr_id" "$new4_port" + + kill_wait $evts_pid + + # Capture events on the network namespace running the client + :>"$evts" + ip netns exec "$ns2" ./pm_nl_ctl events >> "$evts" 2>&1 & + evts_pid=$! + sleep 0.5 + + # ADD_ADDR from the server to client machine reusing the subflow port + ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\ + $server_addr_id dev ns1eth2 > /dev/null 2>&1 + stdbuf -o0 -e0 printf "ADD_ADDR id:%d 10.0.2.1 (ns1) => ns2, reuse port \t\t" $server_addr_id + sleep 0.5 + verify_announce_event "$evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\ + "$server_addr_id" "$app4_port" + + # ADD_ADDR6 from the server to client machine reusing the subflow port + :>"$evts" + ip netns exec "$ns1" ./pm_nl_ctl ann dead:beef:2::1 token "$server6_token" id\ + $server_addr_id dev ns1eth2 > /dev/null 2>&1 + stdbuf -o0 -e0 printf "ADD_ADDR6 id:%d dead:beef:2::1 (ns1) => ns2, reuse port\t\t" $server_addr_id + sleep 0.5 + verify_announce_event "$evts" "$ANNOUNCED" "$client6_token" "dead:beef:2::1"\ + "$server_addr_id" "$app6_port" "v6" + + # ADD_ADDR from the server to client machine using a new port + :>"$evts" + server_addr_id=$((server_addr_id+1)) + ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\ + $server_addr_id dev ns1eth2 port $new4_port > /dev/null 2>&1 + stdbuf -o0 -e0 printf "ADD_ADDR id:%d 10.0.2.1 (ns1) => ns2, new port \t\t\t" $server_addr_id + sleep 0.5 + verify_announce_event "$evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\ + "$server_addr_id" "$new4_port" + + kill_wait $evts_pid + rm -f "$evts" +} + +verify_remove_event() +{ + local evt=$1 + local e_type=$2 + local e_token=$3 + local e_id=$4 + local type + local token + local id + + type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + token=$(sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + id=$(sed --unbuffered -n 's/.*\(rem_id:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + if [ "$type" = "$e_type" ] && [ "$token" = "$e_token" ] && + [ "$id" = "$e_id" ] + then + stdbuf -o0 -e0 printf "[OK]\n" + return 0 + fi + stdbuf -o0 -e0 printf "[FAIL]\n" + exit 1 +} + +test_remove() +{ + local evts + evts=$(mktemp) + + # Capture events on the network namespace running the server + :>"$evts" + ip netns exec "$ns1" ./pm_nl_ctl events >> "$evts" 2>&1 & + evts_pid=$! + sleep 0.5 + + # RM_ADDR using an invalid token should result in no action + local invalid_token=$(( client4_token - 1 )) + ip netns exec "$ns2" ./pm_nl_ctl rem token $invalid_token id\ + $client_addr_id > /dev/null 2>&1 + stdbuf -o0 -e0 printf "RM_ADDR id:%d ns2 => ns1, invalid token \t"\ + $client_addr_id + local type + type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$evts") + if [ "$type" = "" ] + then + stdbuf -o0 -e0 printf "[OK]\n" + else + stdbuf -o0 -e0 printf "[FAIL]\n" + exit 1 + fi + + # RM_ADDR using an invalid addr id should result in no action + local invalid_id=$(( client_addr_id + 1 )) + ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ + $invalid_id > /dev/null 2>&1 + stdbuf -o0 -e0 printf "RM_ADDR id:%d ns2 => ns1, invalid id \t"\ + $invalid_id + type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$evts") + if [ "$type" = "" ] + then + stdbuf -o0 -e0 printf "[OK]\n" + else + stdbuf -o0 -e0 printf "[FAIL]\n" + exit 1 + fi + + # RM_ADDR from the client to server machine + :>"$evts" + ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ + $client_addr_id > /dev/null 2>&1 + stdbuf -o0 -e0 printf "RM_ADDR id:%d ns2 => ns1 \t"\ + $client_addr_id + sleep 0.5 + verify_remove_event "$evts" "$REMOVED" "$server4_token" "$client_addr_id" + + # RM_ADDR from the client to server machine + :>"$evts" + client_addr_id=$(( client_addr_id - 1 )) + ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ + $client_addr_id > /dev/null 2>&1 + stdbuf -o0 -e0 printf "RM_ADDR id:%d ns2 => ns1 \t"\ + $client_addr_id + sleep 0.5 + verify_remove_event "$evts" "$REMOVED" "$server4_token" "$client_addr_id" + + # RM_ADDR6 from the client to server machine + :>"$evts" + ip netns exec "$ns2" ./pm_nl_ctl rem token "$client6_token" id\ + $client_addr_id > /dev/null 2>&1 + stdbuf -o0 -e0 printf "RM_ADDR6 id:%d ns2 => ns1 \t"\ + $client_addr_id + sleep 0.5 + verify_remove_event "$evts" "$REMOVED" "$server6_token" "$client_addr_id" + + kill_wait $evts_pid + + # Capture events on the network namespace running the client + :>"$evts" + ip netns exec "$ns2" ./pm_nl_ctl events >> "$evts" 2>&1 & + evts_pid=$! + sleep 0.5 + + # RM_ADDR from the server to client machine + ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\ + $server_addr_id > /dev/null 2>&1 + stdbuf -o0 -e0 printf "RM_ADDR id:%d ns1 => ns2 \t"\ + $server_addr_id + sleep 0.5 + verify_remove_event "$evts" "$REMOVED" "$client4_token" "$server_addr_id" + + # RM_ADDR from the server to client machine + :>"$evts" + server_addr_id=$(( server_addr_id - 1 )) + ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\ + $server_addr_id > /dev/null 2>&1 + stdbuf -o0 -e0 printf "RM_ADDR id:%d ns1 => ns2 \t" $server_addr_id + sleep 0.5 + verify_remove_event "$evts" "$REMOVED" "$client4_token" "$server_addr_id" + + # RM_ADDR6 from the server to client machine + :>"$evts" + ip netns exec "$ns1" ./pm_nl_ctl rem token "$server6_token" id\ + $server_addr_id > /dev/null 2>&1 + stdbuf -o0 -e0 printf "RM_ADDR6 id:%d ns1 => ns2 \t" $server_addr_id + sleep 0.5 + verify_remove_event "$evts" "$REMOVED" "$client6_token" "$server_addr_id" + + kill_wait $evts_pid + rm -f "$evts" +} + +verify_subflow_events() +{ + local evt=$1 + local e_type=$2 + local e_token=$3 + local e_family=$4 + local e_saddr=$5 + local e_daddr=$6 + local e_dport=$7 + local e_locid=$8 + local e_remid=$9 + shift 2 + local e_from=$8 + local e_to=$9 + local type + local token + local family + local saddr + local daddr + local dport + local locid + local remid + + if [ "$e_type" = "$SUB_ESTABLISHED" ] + then + if [ "$e_family" = "$AF_INET6" ] + then + stdbuf -o0 -e0 printf "CREATE_SUBFLOW6 %s (%s) => %s (%s) "\ + "$e_saddr" "$e_from" "$e_daddr" "$e_to" + else + stdbuf -o0 -e0 printf "CREATE_SUBFLOW %s (%s) => %s (%s) \t"\ + "$e_saddr" "$e_from" "$e_daddr" "$e_to" + fi + else + if [ "$e_family" = "$AF_INET6" ] + then + stdbuf -o0 -e0 printf "DESTROY_SUBFLOW6 %s (%s) => %s (%s) "\ + "$e_saddr" "$e_from" "$e_daddr" "$e_to" + else + stdbuf -o0 -e0 printf "DESTROY_SUBFLOW %s (%s) => %s (%s) \t"\ + "$e_saddr" "$e_from" "$e_daddr" "$e_to" + fi + fi + + type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + token=$(sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + family=$(sed --unbuffered -n 's/.*\(family:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + dport=$(sed --unbuffered -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + locid=$(sed --unbuffered -n 's/.*\(loc_id:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + remid=$(sed --unbuffered -n 's/.*\(rem_id:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + if [ "$family" = "$AF_INET6" ] + then + saddr=$(sed --unbuffered -n 's/.*\(saddr6:\)\([0-9a-f:.]*\).*$/\2/p;q' "$evt") + daddr=$(sed --unbuffered -n 's/.*\(daddr6:\)\([0-9a-f:.]*\).*$/\2/p;q' "$evt") + else + saddr=$(sed --unbuffered -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q' "$evt") + daddr=$(sed --unbuffered -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evt") + fi + + if [ "$type" = "$e_type" ] && [ "$token" = "$e_token" ] && + [ "$daddr" = "$e_daddr" ] && [ "$e_dport" = "$dport" ] && + [ "$family" = "$e_family" ] && [ "$saddr" = "$e_saddr" ] && + [ "$e_locid" = "$locid" ] && [ "$e_remid" = "$remid" ] + then + stdbuf -o0 -e0 printf "[OK]\n" + return 0 + fi + stdbuf -o0 -e0 printf "[FAIL]\n" + exit 1 +} + +test_subflows() +{ + local evts + evts=$(mktemp) + # Capture events on the network namespace running the server + :>"$evts" + ip netns exec "$ns1" ./pm_nl_ctl events >> "$evts" 2>&1 & + evts_pid=$! + sleep 0.5 + + # Attempt to add a listener at 10.0.2.2:<subflow-port> + ip netns exec "$ns2" ./pm_nl_ctl listen 10.0.2.2\ + "$client4_port" > /dev/null 2>&1 & + local listener_pid=$! + + # ADD_ADDR from client to server machine reusing the subflow port + ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\ + $client_addr_id > /dev/null 2>&1 + sleep 0.5 + + # CREATE_SUBFLOW from server to client machine + :>"$evts" + ip netns exec "$ns1" ./pm_nl_ctl csf lip 10.0.2.1 lid 23 rip 10.0.2.2\ + rport "$client4_port" token "$server4_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$evts" "$SUB_ESTABLISHED" "$server4_token" "$AF_INET" "10.0.2.1"\ + "10.0.2.2" "$client4_port" "23" "$client_addr_id" "ns1" "ns2" + + # Delete the listener from the client ns, if one was created + kill_wait $listener_pid + + local sport + sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts") + + # DESTROY_SUBFLOW from server to client machine + :>"$evts" + ip netns exec "$ns1" ./pm_nl_ctl dsf lip 10.0.2.1 lport "$sport" rip 10.0.2.2 rport\ + "$client4_port" token "$server4_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$evts" "$SUB_CLOSED" "$server4_token" "$AF_INET" "10.0.2.1"\ + "10.0.2.2" "$client4_port" "23" "$client_addr_id" "ns1" "ns2" + + # RM_ADDR from client to server machine + ip netns exec "$ns2" ./pm_nl_ctl rem id $client_addr_id token\ + "$client4_token" > /dev/null 2>&1 + sleep 0.5 + + # Attempt to add a listener at dead:beef:2::2:<subflow-port> + ip netns exec "$ns2" ./pm_nl_ctl listen dead:beef:2::2\ + "$client6_port" > /dev/null 2>&1 & + listener_pid=$! + + # ADD_ADDR6 from client to server machine reusing the subflow port + :>"$evts" + ip netns exec "$ns2" ./pm_nl_ctl ann dead:beef:2::2 token "$client6_token" id\ + $client_addr_id > /dev/null 2>&1 + sleep 0.5 + + # CREATE_SUBFLOW6 from server to client machine + :>"$evts" + ip netns exec "$ns1" ./pm_nl_ctl csf lip dead:beef:2::1 lid 23 rip\ + dead:beef:2::2 rport "$client6_port" token "$server6_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$evts" "$SUB_ESTABLISHED" "$server6_token" "$AF_INET6"\ + "dead:beef:2::1" "dead:beef:2::2" "$client6_port" "23"\ + "$client_addr_id" "ns1" "ns2" + + # Delete the listener from the client ns, if one was created + kill_wait $listener_pid + + sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts") + + # DESTROY_SUBFLOW6 from server to client machine + :>"$evts" + ip netns exec "$ns1" ./pm_nl_ctl dsf lip dead:beef:2::1 lport "$sport" rip\ + dead:beef:2::2 rport "$client6_port" token "$server6_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$evts" "$SUB_CLOSED" "$server6_token" "$AF_INET6"\ + "dead:beef:2::1" "dead:beef:2::2" "$client6_port" "23"\ + "$client_addr_id" "ns1" "ns2" + + # RM_ADDR from client to server machine + ip netns exec "$ns2" ./pm_nl_ctl rem id $client_addr_id token\ + "$client6_token" > /dev/null 2>&1 + sleep 0.5 + + # Attempt to add a listener at 10.0.2.2:<new-port> + ip netns exec "$ns2" ./pm_nl_ctl listen 10.0.2.2\ + $new4_port > /dev/null 2>&1 & + listener_pid=$! + + # ADD_ADDR from client to server machine using a new port + :>"$evts" + ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\ + $client_addr_id port $new4_port > /dev/null 2>&1 + sleep 0.5 + + # CREATE_SUBFLOW from server to client machine + :>"$evts" + ip netns exec "$ns1" ./pm_nl_ctl csf lip 10.0.2.1 lid 23 rip 10.0.2.2 rport\ + $new4_port token "$server4_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$evts" "$SUB_ESTABLISHED" "$server4_token" "$AF_INET"\ + "10.0.2.1" "10.0.2.2" "$new4_port" "23"\ + "$client_addr_id" "ns1" "ns2" + + # Delete the listener from the client ns, if one was created + kill_wait $listener_pid + + sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts") + + # DESTROY_SUBFLOW from server to client machine + :>"$evts" + ip netns exec "$ns1" ./pm_nl_ctl dsf lip 10.0.2.1 lport "$sport" rip 10.0.2.2 rport\ + $new4_port token "$server4_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$evts" "$SUB_CLOSED" "$server4_token" "$AF_INET" "10.0.2.1"\ + "10.0.2.2" "$new4_port" "23" "$client_addr_id" "ns1" "ns2" + + # RM_ADDR from client to server machine + ip netns exec "$ns2" ./pm_nl_ctl rem id $client_addr_id token\ + "$client4_token" > /dev/null 2>&1 + + kill_wait $evts_pid + + # Capture events on the network namespace running the client + :>"$evts" + ip netns exec "$ns2" ./pm_nl_ctl events >> "$evts" 2>&1 & + evts_pid=$! + sleep 0.5 + + # Attempt to add a listener at 10.0.2.1:<subflow-port> + ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\ + $app4_port > /dev/null 2>&1 & + listener_pid=$! + + # ADD_ADDR from server to client machine reusing the subflow port + ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\ + $server_addr_id > /dev/null 2>&1 + sleep 0.5 + + # CREATE_SUBFLOW from client to server machine + :>"$evts" + ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\ + $app4_port token "$client4_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$evts" "$SUB_ESTABLISHED" "$client4_token" "$AF_INET" "10.0.2.2"\ + "10.0.2.1" "$app4_port" "23" "$server_addr_id" "ns2" "ns1" + + # Delete the listener from the server ns, if one was created + kill_wait $listener_pid + + sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts") + + # DESTROY_SUBFLOW from client to server machine + :>"$evts" + ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\ + $app4_port token "$client4_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$evts" "$SUB_CLOSED" "$client4_token" "$AF_INET" "10.0.2.2"\ + "10.0.2.1" "$app4_port" "23" "$server_addr_id" "ns2" "ns1" + + # RM_ADDR from server to client machine + ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\ + "$server4_token" > /dev/null 2>&1 + sleep 0.5 + + # Attempt to add a listener at dead:beef:2::1:<subflow-port> + ip netns exec "$ns1" ./pm_nl_ctl listen dead:beef:2::1\ + $app6_port > /dev/null 2>&1 & + listener_pid=$! + + # ADD_ADDR6 from server to client machine reusing the subflow port + :>"$evts" + ip netns exec "$ns1" ./pm_nl_ctl ann dead:beef:2::1 token "$server6_token" id\ + $server_addr_id > /dev/null 2>&1 + sleep 0.5 + + # CREATE_SUBFLOW6 from client to server machine + :>"$evts" + ip netns exec "$ns2" ./pm_nl_ctl csf lip dead:beef:2::2 lid 23 rip\ + dead:beef:2::1 rport $app6_port token "$client6_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$evts" "$SUB_ESTABLISHED" "$client6_token"\ + "$AF_INET6" "dead:beef:2::2"\ + "dead:beef:2::1" "$app6_port" "23"\ + "$server_addr_id" "ns2" "ns1" + + # Delete the listener from the server ns, if one was created + kill_wait $listener_pid + + sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts") + + # DESTROY_SUBFLOW6 from client to server machine + :>"$evts" + ip netns exec "$ns2" ./pm_nl_ctl dsf lip dead:beef:2::2 lport "$sport" rip\ + dead:beef:2::1 rport $app6_port token "$client6_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$evts" "$SUB_CLOSED" "$client6_token" "$AF_INET6" "dead:beef:2::2"\ + "dead:beef:2::1" "$app6_port" "23" "$server_addr_id" "ns2" "ns1" + + # RM_ADDR6 from server to client machine + ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\ + "$server6_token" > /dev/null 2>&1 + sleep 0.5 + + # Attempt to add a listener at 10.0.2.1:<new-port> + ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\ + $new4_port > /dev/null 2>&1 & + listener_pid=$! + + # ADD_ADDR from server to client machine using a new port + :>"$evts" + ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\ + $server_addr_id port $new4_port > /dev/null 2>&1 + sleep 0.5 + + # CREATE_SUBFLOW from client to server machine + :>"$evts" + ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\ + $new4_port token "$client4_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$evts" "$SUB_ESTABLISHED" "$client4_token" "$AF_INET"\ + "10.0.2.2" "10.0.2.1" "$new4_port" "23" "$server_addr_id" "ns2" "ns1" + + # Delete the listener from the server ns, if one was created + kill_wait $listener_pid + + sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts") + + # DESTROY_SUBFLOW from client to server machine + :>"$evts" + ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\ + $new4_port token "$client4_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$evts" "$SUB_CLOSED" "$client4_token" "$AF_INET" "10.0.2.2"\ + "10.0.2.1" "$new4_port" "23" "$server_addr_id" "ns2" "ns1" + + # RM_ADDR from server to client machine + ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\ + "$server4_token" > /dev/null 2>&1 + + kill_wait $evts_pid + rm -f "$evts" +} + +test_subflows_v4_v6_mix() +{ + local client_evts + client_evts=$(mktemp) + # Capture events on the network namespace running the client + :>"$client_evts" + ip netns exec "$ns2" ./pm_nl_ctl events >> "$client_evts" 2>&1 & + evts_pid=$! + sleep 0.5 + + # Attempt to add a listener at 10.0.2.1:<subflow-port> + ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\ + $app6_port > /dev/null 2>&1 & + local listener_pid=$! + + # ADD_ADDR4 from server to client machine reusing the subflow port on + # the established v6 connection + :>"$client_evts" + ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server6_token" id\ + $server_addr_id dev ns1eth2 > /dev/null 2>&1 + stdbuf -o0 -e0 printf "ADD_ADDR4 id:%d 10.0.2.1 (ns1) => ns2, reuse port\t\t" $server_addr_id + sleep 0.5 + verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "10.0.2.1"\ + "$server_addr_id" "$app6_port" + + # CREATE_SUBFLOW from client to server machine + :>"$client_evts" + ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\ + $app6_port token "$client6_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$client_evts" "$SUB_ESTABLISHED" "$client6_token"\ + "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\ + "$server_addr_id" "ns2" "ns1" + + # Delete the listener from the server ns, if one was created + kill_wait $listener_pid + + sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts") + + # DESTROY_SUBFLOW from client to server machine + :>"$client_evts" + ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\ + $app6_port token "$client6_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$client_evts" "$SUB_CLOSED" "$client6_token" \ + "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\ + "$server_addr_id" "ns2" "ns1" + + # RM_ADDR from server to client machine + ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\ + "$server6_token" > /dev/null 2>&1 + sleep 0.5 + + kill_wait $evts_pid + rm -f "$client_evts" +} + +test_prio() +{ + local count + + # Send MP_PRIO signal from client to server machine + ip netns exec "$ns2" ./pm_nl_ctl set 10.0.1.2 port "$client4_port" flags backup token "$client4_token" rip 10.0.1.1 rport "$app4_port" + sleep 0.5 + + # Check TX + stdbuf -o0 -e0 printf "MP_PRIO TX \t" + count=$(ip netns exec "$ns2" nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') + [ -z "$count" ] && count=0 + if [ $count != 1 ]; then + stdbuf -o0 -e0 printf "[FAIL]\n" + exit 1 + else + stdbuf -o0 -e0 printf "[OK]\n" + fi + + # Check RX + stdbuf -o0 -e0 printf "MP_PRIO RX \t" + count=$(ip netns exec "$ns1" nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}') + [ -z "$count" ] && count=0 + if [ $count != 1 ]; then + stdbuf -o0 -e0 printf "[FAIL]\n" + exit 1 + else + stdbuf -o0 -e0 printf "[OK]\n" + fi +} + +make_connection +make_connection "v6" +test_announce +test_remove +test_subflows +test_subflows_v4_v6_mix +test_prio + +exit 0 |