diff options
Diffstat (limited to 'tools/testing/selftests/net')
32 files changed, 4826 insertions, 83 deletions
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 79c9eb0034d5..492b273743b4 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -25,6 +25,9 @@ TEST_PROGS += bareudp.sh TEST_PROGS += unicast_extensions.sh TEST_PROGS += udpgro_fwd.sh TEST_PROGS += veth.sh +TEST_PROGS += ioam6.sh +TEST_PROGS += gro.sh +TEST_PROGS += gre_gso.sh TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any @@ -36,8 +39,11 @@ TEST_GEN_FILES += fin_ack_lat TEST_GEN_FILES += reuseaddr_ports_exhausted TEST_GEN_FILES += hwtstamp_config rxtimestamp timestamping txtimestamp TEST_GEN_FILES += ipsec +TEST_GEN_FILES += ioam6_parser +TEST_GEN_FILES += gro TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls +TEST_GEN_FILES += toeplitz TEST_FILES := settings diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile new file mode 100644 index 000000000000..cfc7f4f97fd1 --- /dev/null +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -0,0 +1,5 @@ +##TEST_GEN_FILES := test_unix_oob +TEST_PROGS := test_unix_oob +include ../../lib.mk + +all: $(TEST_PROGS) diff --git a/tools/testing/selftests/net/af_unix/test_unix_oob.c b/tools/testing/selftests/net/af_unix/test_unix_oob.c new file mode 100644 index 000000000000..0f3e3763f4f8 --- /dev/null +++ b/tools/testing/selftests/net/af_unix/test_unix_oob.c @@ -0,0 +1,437 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include <stdio.h> +#include <stdlib.h> +#include <sys/socket.h> +#include <arpa/inet.h> +#include <unistd.h> +#include <string.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <errno.h> +#include <netinet/tcp.h> +#include <sys/un.h> +#include <sys/signal.h> +#include <sys/poll.h> + +static int pipefd[2]; +static int signal_recvd; +static pid_t producer_id; +static char sock_name[32]; + +static void sig_hand(int sn, siginfo_t *si, void *p) +{ + signal_recvd = sn; +} + +static int set_sig_handler(int signal) +{ + struct sigaction sa; + + sa.sa_sigaction = sig_hand; + sigemptyset(&sa.sa_mask); + sa.sa_flags = SA_SIGINFO | SA_RESTART; + + return sigaction(signal, &sa, NULL); +} + +static void set_filemode(int fd, int set) +{ + int flags = fcntl(fd, F_GETFL, 0); + + if (set) + flags &= ~O_NONBLOCK; + else + flags |= O_NONBLOCK; + fcntl(fd, F_SETFL, flags); +} + +static void signal_producer(int fd) +{ + char cmd; + + cmd = 'S'; + write(fd, &cmd, sizeof(cmd)); +} + +static void wait_for_signal(int fd) +{ + char buf[5]; + + read(fd, buf, 5); +} + +static void die(int status) +{ + fflush(NULL); + unlink(sock_name); + kill(producer_id, SIGTERM); + exit(status); +} + +int is_sioctatmark(int fd) +{ + int ans = -1; + + if (ioctl(fd, SIOCATMARK, &ans, sizeof(ans)) < 0) { +#ifdef DEBUG + perror("SIOCATMARK Failed"); +#endif + } + return ans; +} + +void read_oob(int fd, char *c) +{ + + *c = ' '; + if (recv(fd, c, sizeof(*c), MSG_OOB) < 0) { +#ifdef DEBUG + perror("Reading MSG_OOB Failed"); +#endif + } +} + +int read_data(int pfd, char *buf, int size) +{ + int len = 0; + + memset(buf, size, '0'); + len = read(pfd, buf, size); +#ifdef DEBUG + if (len < 0) + perror("read failed"); +#endif + return len; +} + +static void wait_for_data(int pfd, int event) +{ + struct pollfd pfds[1]; + + pfds[0].fd = pfd; + pfds[0].events = event; + poll(pfds, 1, -1); +} + +void producer(struct sockaddr_un *consumer_addr) +{ + int cfd; + char buf[64]; + int i; + + memset(buf, 'x', sizeof(buf)); + cfd = socket(AF_UNIX, SOCK_STREAM, 0); + + wait_for_signal(pipefd[0]); + if (connect(cfd, (struct sockaddr *)consumer_addr, + sizeof(struct sockaddr)) != 0) { + perror("Connect failed"); + kill(0, SIGTERM); + exit(1); + } + + for (i = 0; i < 2; i++) { + /* Test 1: Test for SIGURG and OOB */ + wait_for_signal(pipefd[0]); + memset(buf, 'x', sizeof(buf)); + buf[63] = '@'; + send(cfd, buf, sizeof(buf), MSG_OOB); + + wait_for_signal(pipefd[0]); + + /* Test 2: Test for OOB being overwitten */ + memset(buf, 'x', sizeof(buf)); + buf[63] = '%'; + send(cfd, buf, sizeof(buf), MSG_OOB); + + memset(buf, 'x', sizeof(buf)); + buf[63] = '#'; + send(cfd, buf, sizeof(buf), MSG_OOB); + + wait_for_signal(pipefd[0]); + + /* Test 3: Test for SIOCATMARK */ + memset(buf, 'x', sizeof(buf)); + buf[63] = '@'; + send(cfd, buf, sizeof(buf), MSG_OOB); + + memset(buf, 'x', sizeof(buf)); + buf[63] = '%'; + send(cfd, buf, sizeof(buf), MSG_OOB); + + memset(buf, 'x', sizeof(buf)); + send(cfd, buf, sizeof(buf), 0); + + wait_for_signal(pipefd[0]); + + /* Test 4: Test for 1byte OOB msg */ + memset(buf, 'x', sizeof(buf)); + buf[0] = '@'; + send(cfd, buf, 1, MSG_OOB); + } +} + +int +main(int argc, char **argv) +{ + int lfd, pfd; + struct sockaddr_un consumer_addr, paddr; + socklen_t len = sizeof(consumer_addr); + char buf[1024]; + int on = 0; + char oob; + int flags; + int atmark; + char *tmp_file; + + lfd = socket(AF_UNIX, SOCK_STREAM, 0); + memset(&consumer_addr, 0, sizeof(consumer_addr)); + consumer_addr.sun_family = AF_UNIX; + sprintf(sock_name, "unix_oob_%d", getpid()); + unlink(sock_name); + strcpy(consumer_addr.sun_path, sock_name); + + if ((bind(lfd, (struct sockaddr *)&consumer_addr, + sizeof(consumer_addr))) != 0) { + perror("socket bind failed"); + exit(1); + } + + pipe(pipefd); + + listen(lfd, 1); + + producer_id = fork(); + if (producer_id == 0) { + producer(&consumer_addr); + exit(0); + } + + set_sig_handler(SIGURG); + signal_producer(pipefd[1]); + + pfd = accept(lfd, (struct sockaddr *) &paddr, &len); + fcntl(pfd, F_SETOWN, getpid()); + + signal_recvd = 0; + signal_producer(pipefd[1]); + + /* Test 1: + * veriyf that SIGURG is + * delivered and 63 bytes are + * read and oob is '@' + */ + wait_for_data(pfd, POLLIN | POLLPRI); + read_oob(pfd, &oob); + len = read_data(pfd, buf, 1024); + if (!signal_recvd || len != 63 || oob != '@') { + fprintf(stderr, "Test 1 failed sigurg %d len %d %c\n", + signal_recvd, len, oob); + die(1); + } + + signal_recvd = 0; + signal_producer(pipefd[1]); + + /* Test 2: + * Verify that the first OOB is over written by + * the 2nd one and the first OOB is returned as + * part of the read, and sigurg is received. + */ + wait_for_data(pfd, POLLIN | POLLPRI); + len = 0; + while (len < 70) + len = recv(pfd, buf, 1024, MSG_PEEK); + len = read_data(pfd, buf, 1024); + read_oob(pfd, &oob); + if (!signal_recvd || len != 127 || oob != '#') { + fprintf(stderr, "Test 2 failed, sigurg %d len %d OOB %c\n", + signal_recvd, len, oob); + die(1); + } + + signal_recvd = 0; + signal_producer(pipefd[1]); + + /* Test 3: + * verify that 2nd oob over writes + * the first one and read breaks at + * oob boundary returning 127 bytes + * and sigurg is received and atmark + * is set. + * oob is '%' and second read returns + * 64 bytes. + */ + len = 0; + wait_for_data(pfd, POLLIN | POLLPRI); + while (len < 150) + len = recv(pfd, buf, 1024, MSG_PEEK); + len = read_data(pfd, buf, 1024); + atmark = is_sioctatmark(pfd); + read_oob(pfd, &oob); + + if (!signal_recvd || len != 127 || oob != '%' || atmark != 1) { + fprintf(stderr, "Test 3 failed, sigurg %d len %d OOB %c ", + "atmark %d\n", signal_recvd, len, oob, atmark); + die(1); + } + + signal_recvd = 0; + + len = read_data(pfd, buf, 1024); + if (len != 64) { + fprintf(stderr, "Test 3.1 failed, sigurg %d len %d OOB %c\n", + signal_recvd, len, oob); + die(1); + } + + signal_recvd = 0; + signal_producer(pipefd[1]); + + /* Test 4: + * verify that a single byte + * oob message is delivered. + * set non blocking mode and + * check proper error is + * returned and sigurg is + * received and correct + * oob is read. + */ + + set_filemode(pfd, 0); + + wait_for_data(pfd, POLLIN | POLLPRI); + len = read_data(pfd, buf, 1024); + if ((len == -1) && (errno == 11)) + len = 0; + + read_oob(pfd, &oob); + + if (!signal_recvd || len != 0 || oob != '@') { + fprintf(stderr, "Test 4 failed, sigurg %d len %d OOB %c\n", + signal_recvd, len, oob); + die(1); + } + + set_filemode(pfd, 1); + + /* Inline Testing */ + + on = 1; + if (setsockopt(pfd, SOL_SOCKET, SO_OOBINLINE, &on, sizeof(on))) { + perror("SO_OOBINLINE"); + die(1); + } + + signal_recvd = 0; + signal_producer(pipefd[1]); + + /* Test 1 -- Inline: + * Check that SIGURG is + * delivered and 63 bytes are + * read and oob is '@' + */ + + wait_for_data(pfd, POLLIN | POLLPRI); + len = read_data(pfd, buf, 1024); + + if (!signal_recvd || len != 63) { + fprintf(stderr, "Test 1 Inline failed, sigurg %d len %d\n", + signal_recvd, len); + die(1); + } + + len = read_data(pfd, buf, 1024); + + if (len != 1) { + fprintf(stderr, + "Test 1.1 Inline failed, sigurg %d len %d oob %c\n", + signal_recvd, len, oob); + die(1); + } + + signal_recvd = 0; + signal_producer(pipefd[1]); + + /* Test 2 -- Inline: + * Verify that the first OOB is over written by + * the 2nd one and read breaks correctly on + * 2nd OOB boundary with the first OOB returned as + * part of the read, and sigurg is delivered and + * siocatmark returns true. + * next read returns one byte, the oob byte + * and siocatmark returns false. + */ + len = 0; + wait_for_data(pfd, POLLIN | POLLPRI); + while (len < 70) + len = recv(pfd, buf, 1024, MSG_PEEK); + len = read_data(pfd, buf, 1024); + atmark = is_sioctatmark(pfd); + if (len != 127 || atmark != 1 || !signal_recvd) { + fprintf(stderr, "Test 2 Inline failed, len %d atmark %d\n", + len, atmark); + die(1); + } + + len = read_data(pfd, buf, 1024); + atmark = is_sioctatmark(pfd); + if (len != 1 || buf[0] != '#' || atmark == 1) { + fprintf(stderr, "Test 2.1 Inline failed, len %d data %c atmark %d\n", + len, buf[0], atmark); + die(1); + } + + signal_recvd = 0; + signal_producer(pipefd[1]); + + /* Test 3 -- Inline: + * verify that 2nd oob over writes + * the first one and read breaks at + * oob boundary returning 127 bytes + * and sigurg is received and siocatmark + * is true after the read. + * subsequent read returns 65 bytes + * because of oob which should be '%'. + */ + len = 0; + wait_for_data(pfd, POLLIN | POLLPRI); + while (len < 126) + len = recv(pfd, buf, 1024, MSG_PEEK); + len = read_data(pfd, buf, 1024); + atmark = is_sioctatmark(pfd); + if (!signal_recvd || len != 127 || !atmark) { + fprintf(stderr, + "Test 3 Inline failed, sigurg %d len %d data %c\n", + signal_recvd, len, buf[0]); + die(1); + } + + len = read_data(pfd, buf, 1024); + atmark = is_sioctatmark(pfd); + if (len != 65 || buf[0] != '%' || atmark != 0) { + fprintf(stderr, + "Test 3.1 Inline failed, len %d oob %c atmark %d\n", + len, buf[0], atmark); + die(1); + } + + signal_recvd = 0; + signal_producer(pipefd[1]); + + /* Test 4 -- Inline: + * verify that a single + * byte oob message is delivered + * and read returns one byte, the oob + * byte and sigurg is received + */ + wait_for_data(pfd, POLLIN | POLLPRI); + len = read_data(pfd, buf, 1024); + if (!signal_recvd || len != 1 || buf[0] != '@') { + fprintf(stderr, + "Test 4 Inline failed, signal %d len %d data %c\n", + signal_recvd, len, buf[0]); + die(1); + } + die(0); +} diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 6f905b53904f..21b646d10b88 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -42,3 +42,4 @@ CONFIG_NET_CLS_FLOWER=m CONFIG_NET_ACT_TUNNEL_KEY=m CONFIG_NET_ACT_MIRRED=m CONFIG_BAREUDP=m +CONFIG_IPV6_IOAM6_LWTUNNEL=y diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index a8ad92850e63..13350cd5c8ac 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -37,6 +37,9 @@ # # server / client nomenclature relative to ns-A +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + VERBOSE=0 NSA_DEV=eth1 @@ -3879,6 +3882,32 @@ use_case_ping_lla_multi() log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV2}, ping out ns-C" } +# Perform IPv{4,6} SNAT on ns-A, and verify TCP connection is successfully +# established with ns-B. +use_case_snat_on_vrf() +{ + setup "yes" + + local port="12345" + + run_cmd iptables -t nat -A POSTROUTING -p tcp -m tcp --dport ${port} -j SNAT --to-source ${NSA_LO_IP} -o ${VRF} + run_cmd ip6tables -t nat -A POSTROUTING -p tcp -m tcp --dport ${port} -j SNAT --to-source ${NSA_LO_IP6} -o ${VRF} + + run_cmd_nsb nettest -s -l ${NSB_IP} -p ${port} & + sleep 1 + run_cmd nettest -d ${VRF} -r ${NSB_IP} -p ${port} + log_test $? 0 "IPv4 TCP connection over VRF with SNAT" + + run_cmd_nsb nettest -6 -s -l ${NSB_IP6} -p ${port} & + sleep 1 + run_cmd nettest -6 -d ${VRF} -r ${NSB_IP6} -p ${port} + log_test $? 0 "IPv6 TCP connection over VRF with SNAT" + + # Cleanup + run_cmd iptables -t nat -D POSTROUTING -p tcp -m tcp --dport ${port} -j SNAT --to-source ${NSA_LO_IP} -o ${VRF} + run_cmd ip6tables -t nat -D POSTROUTING -p tcp -m tcp --dport ${port} -j SNAT --to-source ${NSA_LO_IP6} -o ${VRF} +} + use_cases() { log_section "Use cases" @@ -3886,6 +3915,8 @@ use_cases() use_case_br log_subsection "Ping LLA with multiple interfaces" use_case_ping_lla_multi + log_subsection "SNAT on VRF" + use_case_snat_on_vrf } ################################################################################ @@ -3946,7 +3977,7 @@ fi which nettest >/dev/null if [ $? -ne 0 ]; then echo "'nettest' command not found; skipping tests" - exit 0 + exit $ksft_skip fi declare -i nfail=0 diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index a93e6b690e06..43ea8407a82e 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -3,6 +3,9 @@ # This test is for checking IPv4 and IPv6 FIB rules API +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + ret=0 PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} @@ -238,12 +241,12 @@ run_fibrule_tests() if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" - exit 0 + exit $ksft_skip fi if [ ! -x "$(command -v ip)" ]; then echo "SKIP: Could not run test without ip tool" - exit 0 + exit $ksft_skip fi # start clean diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh index 13d3d4428a32..2c14a86adaaa 100644 --- a/tools/testing/selftests/net/forwarding/devlink_lib.sh +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -1,6 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + ############################################################################## # Defines @@ -9,11 +12,11 @@ if [[ ! -v DEVLINK_DEV ]]; then | jq -r '.port | keys[]' | cut -d/ -f-2) if [ -z "$DEVLINK_DEV" ]; then echo "SKIP: ${NETIFS[p1]} has no devlink device registered for it" - exit 1 + exit $ksft_skip fi if [[ "$(echo $DEVLINK_DEV | grep -c pci)" -eq 0 ]]; then echo "SKIP: devlink device's bus is not PCI" - exit 1 + exit $ksft_skip fi DEVLINK_VIDDID=$(lspci -s $(echo $DEVLINK_DEV | cut -d"/" -f2) \ @@ -22,7 +25,7 @@ elif [[ ! -z "$DEVLINK_DEV" ]]; then devlink dev show $DEVLINK_DEV &> /dev/null if [ $? -ne 0 ]; then echo "SKIP: devlink device \"$DEVLINK_DEV\" not found" - exit 1 + exit $ksft_skip fi fi @@ -32,19 +35,19 @@ fi devlink help 2>&1 | grep resource &> /dev/null if [ $? -ne 0 ]; then echo "SKIP: iproute2 too old, missing devlink resource support" - exit 1 + exit $ksft_skip fi devlink help 2>&1 | grep trap &> /dev/null if [ $? -ne 0 ]; then echo "SKIP: iproute2 too old, missing devlink trap support" - exit 1 + exit $ksft_skip fi devlink dev help 2>&1 | grep info &> /dev/null if [ $? -ne 0 ]; then echo "SKIP: iproute2 too old, missing devlink dev info support" - exit 1 + exit $ksft_skip fi ############################################################################## diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 42e28c983d41..e7fc5c35b569 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -4,6 +4,9 @@ ############################################################################## # Defines +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + # Can be overridden by the configuration file. PING=${PING:=ping} PING6=${PING6:=ping6} @@ -38,7 +41,7 @@ check_tc_version() tc -j &> /dev/null if [[ $? -ne 0 ]]; then echo "SKIP: iproute2 too old; tc is missing JSON support" - exit 1 + exit $ksft_skip fi } @@ -51,7 +54,7 @@ check_tc_mpls_support() matchall action pipe &> /dev/null if [[ $? -ne 0 ]]; then echo "SKIP: iproute2 too old; tc is missing MPLS support" - return 1 + return $ksft_skip fi tc filter del dev $dev ingress protocol mpls_uc pref 1 handle 1 \ matchall @@ -69,7 +72,7 @@ check_tc_mpls_lse_stats() if [[ $? -ne 0 ]]; then echo "SKIP: iproute2 too old; tc-flower is missing extended MPLS support" - return 1 + return $ksft_skip fi tc -j filter show dev $dev ingress protocol mpls_uc | jq . &> /dev/null @@ -79,7 +82,7 @@ check_tc_mpls_lse_stats() if [[ $ret -ne 0 ]]; then echo "SKIP: iproute2 too old; tc-flower produces invalid json output for extended MPLS filters" - return 1 + return $ksft_skip fi } @@ -88,7 +91,7 @@ check_tc_shblock_support() tc filter help 2>&1 | grep block &> /dev/null if [[ $? -ne 0 ]]; then echo "SKIP: iproute2 too old; tc is missing shared block support" - exit 1 + exit $ksft_skip fi } @@ -97,7 +100,7 @@ check_tc_chain_support() tc help 2>&1|grep chain &> /dev/null if [[ $? -ne 0 ]]; then echo "SKIP: iproute2 too old; tc is missing chain support" - exit 1 + exit $ksft_skip fi } @@ -106,7 +109,7 @@ check_tc_action_hw_stats_support() tc actions help 2>&1 | grep -q hw_stats if [[ $? -ne 0 ]]; then echo "SKIP: iproute2 too old; tc is missing action hw_stats support" - exit 1 + exit $ksft_skip fi } @@ -115,13 +118,13 @@ check_ethtool_lanes_support() ethtool --help 2>&1| grep lanes &> /dev/null if [[ $? -ne 0 ]]; then echo "SKIP: ethtool too old; it is missing lanes support" - exit 1 + exit $ksft_skip fi } if [[ "$(id -u)" -ne 0 ]]; then echo "SKIP: need root privileges" - exit 0 + exit $ksft_skip fi if [[ "$CHECK_TC" = "yes" ]]; then @@ -134,7 +137,7 @@ require_command() if [[ ! -x "$(command -v "$cmd")" ]]; then echo "SKIP: $cmd not installed" - exit 1 + exit $ksft_skip fi } @@ -143,7 +146,7 @@ require_command $MZ if [[ ! -v NUM_NETIFS ]]; then echo "SKIP: importer does not define \"NUM_NETIFS\"" - exit 1 + exit $ksft_skip fi ############################################################################## @@ -203,7 +206,7 @@ for ((i = 1; i <= NUM_NETIFS; ++i)); do ip link show dev ${NETIFS[p$i]} &> /dev/null if [[ $? -ne 0 ]]; then echo "SKIP: could not find all required interfaces" - exit 1 + exit $ksft_skip fi done diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh index 76efb1f8375e..a0d612e04990 100755 --- a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh @@ -411,7 +411,7 @@ ping_ipv6() ip nexthop ls >/dev/null 2>&1 if [ $? -ne 0 ]; then echo "Nexthop objects not supported; skipping tests" - exit 0 + exit $ksft_skip fi trap cleanup EXIT diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh index 4898dd4118f1..cb08ffe2356a 100755 --- a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh @@ -386,7 +386,7 @@ ping_ipv6() ip nexthop ls >/dev/null 2>&1 if [ $? -ne 0 ]; then echo "Nexthop objects not supported; skipping tests" - exit 0 + exit $ksft_skip fi trap cleanup EXIT diff --git a/tools/testing/selftests/net/gre_gso.sh b/tools/testing/selftests/net/gre_gso.sh new file mode 100755 index 000000000000..facbb0c80443 --- /dev/null +++ b/tools/testing/selftests/net/gre_gso.sh @@ -0,0 +1,236 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test is for checking GRE GSO. + +ret=0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +# all tests in this script. Can be overridden with -t option +TESTS="gre_gso" + +VERBOSE=0 +PAUSE_ON_FAIL=no +PAUSE=no +IP="ip -netns ns1" +NS_EXEC="ip netns exec ns1" +TMPFILE=`mktemp` +PID= + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf " TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) + else + ret=1 + nfail=$((nfail+1)) + printf " TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi + + if [ "${PAUSE}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi +} + +setup() +{ + set -e + ip netns add ns1 + ip netns set ns1 auto + $IP link set dev lo up + + ip link add veth0 type veth peer name veth1 + ip link set veth0 up + ip link set veth1 netns ns1 + $IP link set veth1 name veth0 + $IP link set veth0 up + + dd if=/dev/urandom of=$TMPFILE bs=1024 count=2048 &>/dev/null + set +e +} + +cleanup() +{ + rm -rf $TMPFILE + [ -n "$PID" ] && kill $PID + ip link del dev gre1 &> /dev/null + ip link del dev veth0 &> /dev/null + ip netns del ns1 +} + +get_linklocal() +{ + local dev=$1 + local ns=$2 + local addr + + [ -n "$ns" ] && ns="-netns $ns" + + addr=$(ip -6 -br $ns addr show dev ${dev} | \ + awk '{ + for (i = 3; i <= NF; ++i) { + if ($i ~ /^fe80/) + print $i + } + }' + ) + addr=${addr/\/*} + + [ -z "$addr" ] && return 1 + + echo $addr + + return 0 +} + +gre_create_tun() +{ + local a1=$1 + local a2=$2 + local mode + + [[ $a1 =~ ^[0-9.]*$ ]] && mode=gre || mode=ip6gre + + ip tunnel add gre1 mode $mode local $a1 remote $a2 dev veth0 + ip link set gre1 up + $IP tunnel add gre1 mode $mode local $a2 remote $a1 dev veth0 + $IP link set gre1 up +} + +gre_gst_test_checks() +{ + local name=$1 + local addr=$2 + + $NS_EXEC nc -kl $port >/dev/null & + PID=$! + while ! $NS_EXEC ss -ltn | grep -q $port; do ((i++)); sleep 0.01; done + + cat $TMPFILE | timeout 1 nc $addr $port + log_test $? 0 "$name - copy file w/ TSO" + + ethtool -K veth0 tso off + + cat $TMPFILE | timeout 1 nc $addr $port + log_test $? 0 "$name - copy file w/ GSO" + + ethtool -K veth0 tso on + + kill $PID + PID= +} + +gre6_gso_test() +{ + local port=7777 + + setup + + a1=$(get_linklocal veth0) + a2=$(get_linklocal veth0 ns1) + + gre_create_tun $a1 $a2 + + ip addr add 172.16.2.1/24 dev gre1 + $IP addr add 172.16.2.2/24 dev gre1 + + ip -6 addr add 2001:db8:1::1/64 dev gre1 nodad + $IP -6 addr add 2001:db8:1::2/64 dev gre1 nodad + + sleep 2 + + gre_gst_test_checks GREv6/v4 172.16.2.2 + gre_gst_test_checks GREv6/v6 2001:db8:1::2 + + cleanup +} + +gre_gso_test() +{ + gre6_gso_test +} + +################################################################################ +# usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -t <test> Test(s) to run (default: all) + (options: $TESTS) + -p Pause on fail + -P Pause after each test before cleanup + -v verbose mode (show commands and output) +EOF +} + +################################################################################ +# main + +while getopts :t:pPhv o +do + case $o in + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + P) PAUSE=yes;; + v) VERBOSE=$(($VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +PEER_CMD="ip netns exec ${PEER_NS}" + +# make sure we don't pause twice +[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip; +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +if [ ! -x "$(command -v nc)" ]; then + echo "SKIP: Could not run test without nc tool" + exit $ksft_skip +fi + +# start clean +cleanup &> /dev/null + +for t in $TESTS +do + case $t in + gre_gso) gre_gso_test;; + + help) echo "Test names: $TESTS"; exit 0;; + esac +done + +if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} +fi + +exit $ret diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c new file mode 100644 index 000000000000..cf37ce86b0fd --- /dev/null +++ b/tools/testing/selftests/net/gro.c @@ -0,0 +1,1095 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This testsuite provides conformance testing for GRO coalescing. + * + * Test cases: + * 1.data + * Data packets of the same size and same header setup with correct + * sequence numbers coalesce. The one exception being the last data + * packet coalesced: it can be smaller than the rest and coalesced + * as long as it is in the same flow. + * 2.ack + * Pure ACK does not coalesce. + * 3.flags + * Specific test cases: no packets with PSH, SYN, URG, RST set will + * be coalesced. + * 4.tcp + * Packets with incorrect checksum, non-consecutive seqno and + * different TCP header options shouldn't coalesce. Nit: given that + * some extension headers have paddings, such as timestamp, headers + * that are padding differently would not be coalesced. + * 5.ip: + * Packets with different (ECN, TTL, TOS) header, ip options or + * ip fragments (ipv6) shouldn't coalesce. + * 6.large: + * Packets larger than GRO_MAX_SIZE packets shouldn't coalesce. + * + * MSS is defined as 4096 - header because if it is too small + * (i.e. 1500 MTU - header), it will result in many packets, + * increasing the "large" test case's flakiness. This is because + * due to time sensitivity in the coalescing window, the receiver + * may not coalesce all of the packets. + * + * Note the timing issue applies to all of the test cases, so some + * flakiness is to be expected. + * + */ + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <errno.h> +#include <error.h> +#include <getopt.h> +#include <linux/filter.h> +#include <linux/if_packet.h> +#include <linux/ipv6.h> +#include <net/ethernet.h> +#include <net/if.h> +#include <netinet/in.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/tcp.h> +#include <stdbool.h> +#include <stddef.h> +#include <stdio.h> +#include <stdarg.h> +#include <string.h> +#include <unistd.h> + +#define DPORT 8000 +#define SPORT 1500 +#define PAYLOAD_LEN 100 +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) +#define NUM_PACKETS 4 +#define START_SEQ 100 +#define START_ACK 100 +#define SIP6 "fdaa::2" +#define DIP6 "fdaa::1" +#define SIP4 "192.168.1.200" +#define DIP4 "192.168.1.100" +#define ETH_P_NONE 0 +#define TOTAL_HDR_LEN (ETH_HLEN + sizeof(struct ipv6hdr) + sizeof(struct tcphdr)) +#define MSS (4096 - sizeof(struct tcphdr) - sizeof(struct ipv6hdr)) +#define MAX_PAYLOAD (IP_MAXPACKET - sizeof(struct tcphdr) - sizeof(struct ipv6hdr)) +#define NUM_LARGE_PKT (MAX_PAYLOAD / MSS) +#define MAX_HDR_LEN (ETH_HLEN + sizeof(struct ipv6hdr) + sizeof(struct tcphdr)) + +static int proto = -1; +static uint8_t src_mac[ETH_ALEN], dst_mac[ETH_ALEN]; +static char *testname = "data"; +static char *ifname = "eth0"; +static char *smac = "aa:00:00:00:00:02"; +static char *dmac = "aa:00:00:00:00:01"; +static bool verbose; +static bool tx_socket = true; +static int tcp_offset = -1; +static int total_hdr_len = -1; +static int ethhdr_proto = -1; + +static void vlog(const char *fmt, ...) +{ + va_list args; + + if (verbose) { + va_start(args, fmt); + vfprintf(stderr, fmt, args); + va_end(args); + } +} + +static void setup_sock_filter(int fd) +{ + const int dport_off = tcp_offset + offsetof(struct tcphdr, dest); + const int ethproto_off = offsetof(struct ethhdr, h_proto); + int optlen = 0; + int ipproto_off; + int next_off; + + if (proto == PF_INET) + next_off = offsetof(struct iphdr, protocol); + else + next_off = offsetof(struct ipv6hdr, nexthdr); + ipproto_off = ETH_HLEN + next_off; + + if (strcmp(testname, "ip") == 0) { + if (proto == PF_INET) + optlen = sizeof(struct ip_timestamp); + else + optlen = sizeof(struct ip6_frag); + } + + struct sock_filter filter[] = { + BPF_STMT(BPF_LD + BPF_H + BPF_ABS, ethproto_off), + BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, ntohs(ethhdr_proto), 0, 7), + BPF_STMT(BPF_LD + BPF_B + BPF_ABS, ipproto_off), + BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, IPPROTO_TCP, 0, 5), + BPF_STMT(BPF_LD + BPF_H + BPF_ABS, dport_off), + BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, DPORT, 2, 0), + BPF_STMT(BPF_LD + BPF_H + BPF_ABS, dport_off + optlen), + BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, DPORT, 0, 1), + BPF_STMT(BPF_RET + BPF_K, 0xFFFFFFFF), + BPF_STMT(BPF_RET + BPF_K, 0), + }; + + struct sock_fprog bpf = { + .len = ARRAY_SIZE(filter), + .filter = filter, + }; + + if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &bpf, sizeof(bpf)) < 0) + error(1, errno, "error setting filter"); +} + +static uint32_t checksum_nofold(void *data, size_t len, uint32_t sum) +{ + uint16_t *words = data; + int i; + + for (i = 0; i < len / 2; i++) + sum += words[i]; + if (len & 1) + sum += ((char *)data)[len - 1]; + return sum; +} + +static uint16_t checksum_fold(void *data, size_t len, uint32_t sum) +{ + sum = checksum_nofold(data, len, sum); + while (sum > 0xFFFF) + sum = (sum & 0xFFFF) + (sum >> 16); + return ~sum; +} + +static uint16_t tcp_checksum(void *buf, int payload_len) +{ + struct pseudo_header6 { + struct in6_addr saddr; + struct in6_addr daddr; + uint16_t protocol; + uint16_t payload_len; + } ph6; + struct pseudo_header4 { + struct in_addr saddr; + struct in_addr daddr; + uint16_t protocol; + uint16_t payload_len; + } ph4; + uint32_t sum = 0; + + if (proto == PF_INET6) { + if (inet_pton(AF_INET6, SIP6, &ph6.saddr) != 1) + error(1, errno, "inet_pton6 source ip pseudo"); + if (inet_pton(AF_INET6, DIP6, &ph6.daddr) != 1) + error(1, errno, "inet_pton6 dest ip pseudo"); + ph6.protocol = htons(IPPROTO_TCP); + ph6.payload_len = htons(sizeof(struct tcphdr) + payload_len); + + sum = checksum_nofold(&ph6, sizeof(ph6), 0); + } else if (proto == PF_INET) { + if (inet_pton(AF_INET, SIP4, &ph4.saddr) != 1) + error(1, errno, "inet_pton source ip pseudo"); + if (inet_pton(AF_INET, DIP4, &ph4.daddr) != 1) + error(1, errno, "inet_pton dest ip pseudo"); + ph4.protocol = htons(IPPROTO_TCP); + ph4.payload_len = htons(sizeof(struct tcphdr) + payload_len); + + sum = checksum_nofold(&ph4, sizeof(ph4), 0); + } + + return checksum_fold(buf, sizeof(struct tcphdr) + payload_len, sum); +} + +static void read_MAC(uint8_t *mac_addr, char *mac) +{ + if (sscanf(mac, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx", + &mac_addr[0], &mac_addr[1], &mac_addr[2], + &mac_addr[3], &mac_addr[4], &mac_addr[5]) != 6) + error(1, 0, "sscanf"); +} + +static void fill_datalinklayer(void *buf) +{ + struct ethhdr *eth = buf; + + memcpy(eth->h_dest, dst_mac, ETH_ALEN); + memcpy(eth->h_source, src_mac, ETH_ALEN); + eth->h_proto = ethhdr_proto; +} + +static void fill_networklayer(void *buf, int payload_len) +{ + struct ipv6hdr *ip6h = buf; + struct iphdr *iph = buf; + + if (proto == PF_INET6) { + memset(ip6h, 0, sizeof(*ip6h)); + + ip6h->version = 6; + ip6h->payload_len = htons(sizeof(struct tcphdr) + payload_len); + ip6h->nexthdr = IPPROTO_TCP; + ip6h->hop_limit = 8; + if (inet_pton(AF_INET6, SIP6, &ip6h->saddr) != 1) + error(1, errno, "inet_pton source ip6"); + if (inet_pton(AF_INET6, DIP6, &ip6h->daddr) != 1) + error(1, errno, "inet_pton dest ip6"); + } else if (proto == PF_INET) { + memset(iph, 0, sizeof(*iph)); + + iph->version = 4; + iph->ihl = 5; + iph->ttl = 8; + iph->protocol = IPPROTO_TCP; + iph->tot_len = htons(sizeof(struct tcphdr) + + payload_len + sizeof(struct iphdr)); + iph->frag_off = htons(0x4000); /* DF = 1, MF = 0 */ + if (inet_pton(AF_INET, SIP4, &iph->saddr) != 1) + error(1, errno, "inet_pton source ip"); + if (inet_pton(AF_INET, DIP4, &iph->daddr) != 1) + error(1, errno, "inet_pton dest ip"); + iph->check = checksum_fold(buf, sizeof(struct iphdr), 0); + } +} + +static void fill_transportlayer(void *buf, int seq_offset, int ack_offset, + int payload_len, int fin) +{ + struct tcphdr *tcph = buf; + + memset(tcph, 0, sizeof(*tcph)); + + tcph->source = htons(SPORT); + tcph->dest = htons(DPORT); + tcph->seq = ntohl(START_SEQ + seq_offset); + tcph->ack_seq = ntohl(START_ACK + ack_offset); + tcph->ack = 1; + tcph->fin = fin; + tcph->doff = 5; + tcph->window = htons(TCP_MAXWIN); + tcph->urg_ptr = 0; + tcph->check = tcp_checksum(tcph, payload_len); +} + +static void write_packet(int fd, char *buf, int len, struct sockaddr_ll *daddr) +{ + int ret = -1; + + ret = sendto(fd, buf, len, 0, (struct sockaddr *)daddr, sizeof(*daddr)); + if (ret == -1) + error(1, errno, "sendto failure"); + if (ret != len) + error(1, errno, "sendto wrong length"); +} + +static void create_packet(void *buf, int seq_offset, int ack_offset, + int payload_len, int fin) +{ + memset(buf, 0, total_hdr_len); + memset(buf + total_hdr_len, 'a', payload_len); + fill_transportlayer(buf + tcp_offset, seq_offset, ack_offset, + payload_len, fin); + fill_networklayer(buf + ETH_HLEN, payload_len); + fill_datalinklayer(buf); +} + +/* send one extra flag, not first and not last pkt */ +static void send_flags(int fd, struct sockaddr_ll *daddr, int psh, int syn, + int rst, int urg) +{ + static char flag_buf[MAX_HDR_LEN + PAYLOAD_LEN]; + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + int payload_len, pkt_size, flag, i; + struct tcphdr *tcph; + + payload_len = PAYLOAD_LEN * psh; + pkt_size = total_hdr_len + payload_len; + flag = NUM_PACKETS / 2; + + create_packet(flag_buf, flag * payload_len, 0, payload_len, 0); + + tcph = (struct tcphdr *)(flag_buf + tcp_offset); + tcph->psh = psh; + tcph->syn = syn; + tcph->rst = rst; + tcph->urg = urg; + tcph->check = 0; + tcph->check = tcp_checksum(tcph, payload_len); + + for (i = 0; i < NUM_PACKETS + 1; i++) { + if (i == flag) { + write_packet(fd, flag_buf, pkt_size, daddr); + continue; + } + create_packet(buf, i * PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, total_hdr_len + PAYLOAD_LEN, daddr); + } +} + +/* Test for data of same length, smaller than previous + * and of different lengths + */ +static void send_data_pkts(int fd, struct sockaddr_ll *daddr, + int payload_len1, int payload_len2) +{ + static char buf[ETH_HLEN + IP_MAXPACKET]; + + create_packet(buf, 0, 0, payload_len1, 0); + write_packet(fd, buf, total_hdr_len + payload_len1, daddr); + create_packet(buf, payload_len1, 0, payload_len2, 0); + write_packet(fd, buf, total_hdr_len + payload_len2, daddr); +} + +/* If incoming segments make tracked segment length exceed + * legal IP datagram length, do not coalesce + */ +static void send_large(int fd, struct sockaddr_ll *daddr, int remainder) +{ + static char pkts[NUM_LARGE_PKT][TOTAL_HDR_LEN + MSS]; + static char last[TOTAL_HDR_LEN + MSS]; + static char new_seg[TOTAL_HDR_LEN + MSS]; + int i; + + for (i = 0; i < NUM_LARGE_PKT; i++) + create_packet(pkts[i], i * MSS, 0, MSS, 0); + create_packet(last, NUM_LARGE_PKT * MSS, 0, remainder, 0); + create_packet(new_seg, (NUM_LARGE_PKT + 1) * MSS, 0, remainder, 0); + + for (i = 0; i < NUM_LARGE_PKT; i++) + write_packet(fd, pkts[i], total_hdr_len + MSS, daddr); + write_packet(fd, last, total_hdr_len + remainder, daddr); + write_packet(fd, new_seg, total_hdr_len + remainder, daddr); +} + +/* Pure acks and dup acks don't coalesce */ +static void send_ack(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN]; + + create_packet(buf, 0, 0, 0, 0); + write_packet(fd, buf, total_hdr_len, daddr); + write_packet(fd, buf, total_hdr_len, daddr); + create_packet(buf, 0, 1, 0, 0); + write_packet(fd, buf, total_hdr_len, daddr); +} + +static void recompute_packet(char *buf, char *no_ext, int extlen) +{ + struct tcphdr *tcphdr = (struct tcphdr *)(buf + tcp_offset); + struct ipv6hdr *ip6h = (struct ipv6hdr *)(buf + ETH_HLEN); + struct iphdr *iph = (struct iphdr *)(buf + ETH_HLEN); + + memmove(buf, no_ext, total_hdr_len); + memmove(buf + total_hdr_len + extlen, + no_ext + total_hdr_len, PAYLOAD_LEN); + + tcphdr->doff = tcphdr->doff + (extlen / 4); + tcphdr->check = 0; + tcphdr->check = tcp_checksum(tcphdr, PAYLOAD_LEN + extlen); + if (proto == PF_INET) { + iph->tot_len = htons(ntohs(iph->tot_len) + extlen); + iph->check = 0; + iph->check = checksum_fold(iph, sizeof(struct iphdr), 0); + } else { + ip6h->payload_len = htons(ntohs(ip6h->payload_len) + extlen); + } +} + +static void tcp_write_options(char *buf, int kind, int ts) +{ + struct tcp_option_ts { + uint8_t kind; + uint8_t len; + uint32_t tsval; + uint32_t tsecr; + } *opt_ts = (void *)buf; + struct tcp_option_window { + uint8_t kind; + uint8_t len; + uint8_t shift; + } *opt_window = (void *)buf; + + switch (kind) { + case TCPOPT_NOP: + buf[0] = TCPOPT_NOP; + break; + case TCPOPT_WINDOW: + memset(opt_window, 0, sizeof(struct tcp_option_window)); + opt_window->kind = TCPOPT_WINDOW; + opt_window->len = TCPOLEN_WINDOW; + opt_window->shift = 0; + break; + case TCPOPT_TIMESTAMP: + memset(opt_ts, 0, sizeof(struct tcp_option_ts)); + opt_ts->kind = TCPOPT_TIMESTAMP; + opt_ts->len = TCPOLEN_TIMESTAMP; + opt_ts->tsval = ts; + opt_ts->tsecr = 0; + break; + default: + error(1, 0, "unimplemented TCP option"); + break; + } +} + +/* TCP with options is always a permutation of {TS, NOP, NOP}. + * Implement different orders to verify coalescing stops. + */ +static void add_standard_tcp_options(char *buf, char *no_ext, int ts, int order) +{ + switch (order) { + case 0: + tcp_write_options(buf + total_hdr_len, TCPOPT_NOP, 0); + tcp_write_options(buf + total_hdr_len + 1, TCPOPT_NOP, 0); + tcp_write_options(buf + total_hdr_len + 2 /* two NOP opts */, + TCPOPT_TIMESTAMP, ts); + break; + case 1: + tcp_write_options(buf + total_hdr_len, TCPOPT_NOP, 0); + tcp_write_options(buf + total_hdr_len + 1, + TCPOPT_TIMESTAMP, ts); + tcp_write_options(buf + total_hdr_len + 1 + TCPOLEN_TIMESTAMP, + TCPOPT_NOP, 0); + break; + case 2: + tcp_write_options(buf + total_hdr_len, TCPOPT_TIMESTAMP, ts); + tcp_write_options(buf + total_hdr_len + TCPOLEN_TIMESTAMP + 1, + TCPOPT_NOP, 0); + tcp_write_options(buf + total_hdr_len + TCPOLEN_TIMESTAMP + 2, + TCPOPT_NOP, 0); + break; + default: + error(1, 0, "unknown order"); + break; + } + recompute_packet(buf, no_ext, TCPOLEN_TSTAMP_APPA); +} + +/* Packets with invalid checksum don't coalesce. */ +static void send_changed_checksum(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + struct tcphdr *tcph = (struct tcphdr *)(buf + tcp_offset); + int pkt_size = total_hdr_len + PAYLOAD_LEN; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + tcph->check = tcph->check - 1; + write_packet(fd, buf, pkt_size, daddr); +} + + /* Packets with non-consecutive sequence number don't coalesce.*/ +static void send_changed_seq(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + struct tcphdr *tcph = (struct tcphdr *)(buf + tcp_offset); + int pkt_size = total_hdr_len + PAYLOAD_LEN; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + tcph->seq = ntohl(htonl(tcph->seq) + 1); + tcph->check = 0; + tcph->check = tcp_checksum(tcph, PAYLOAD_LEN); + write_packet(fd, buf, pkt_size, daddr); +} + + /* Packet with different timestamp option or different timestamps + * don't coalesce. + */ +static void send_changed_ts(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + static char extpkt[sizeof(buf) + TCPOLEN_TSTAMP_APPA]; + int pkt_size = total_hdr_len + PAYLOAD_LEN + TCPOLEN_TSTAMP_APPA; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + add_standard_tcp_options(extpkt, buf, 0, 0); + write_packet(fd, extpkt, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + add_standard_tcp_options(extpkt, buf, 0, 0); + write_packet(fd, extpkt, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0); + add_standard_tcp_options(extpkt, buf, 100, 0); + write_packet(fd, extpkt, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN * 3, 0, PAYLOAD_LEN, 0); + add_standard_tcp_options(extpkt, buf, 100, 1); + write_packet(fd, extpkt, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN * 4, 0, PAYLOAD_LEN, 0); + add_standard_tcp_options(extpkt, buf, 100, 2); + write_packet(fd, extpkt, pkt_size, daddr); +} + +/* Packet with different tcp options don't coalesce. */ +static void send_diff_opt(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + static char extpkt1[sizeof(buf) + TCPOLEN_TSTAMP_APPA]; + static char extpkt2[sizeof(buf) + TCPOLEN_MAXSEG]; + int extpkt1_size = total_hdr_len + PAYLOAD_LEN + TCPOLEN_TSTAMP_APPA; + int extpkt2_size = total_hdr_len + PAYLOAD_LEN + TCPOLEN_MAXSEG; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + add_standard_tcp_options(extpkt1, buf, 0, 0); + write_packet(fd, extpkt1, extpkt1_size, daddr); + + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + add_standard_tcp_options(extpkt1, buf, 0, 0); + write_packet(fd, extpkt1, extpkt1_size, daddr); + + create_packet(buf, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0); + tcp_write_options(extpkt2 + MAX_HDR_LEN, TCPOPT_NOP, 0); + tcp_write_options(extpkt2 + MAX_HDR_LEN + 1, TCPOPT_WINDOW, 0); + recompute_packet(extpkt2, buf, TCPOLEN_WINDOW + 1); + write_packet(fd, extpkt2, extpkt2_size, daddr); +} + +static void add_ipv4_ts_option(void *buf, void *optpkt) +{ + struct ip_timestamp *ts = (struct ip_timestamp *)(optpkt + tcp_offset); + int optlen = sizeof(struct ip_timestamp); + struct iphdr *iph; + + if (optlen % 4) + error(1, 0, "ipv4 timestamp length is not a multiple of 4B"); + + ts->ipt_code = IPOPT_TS; + ts->ipt_len = optlen; + ts->ipt_ptr = 5; + ts->ipt_flg = IPOPT_TS_TSONLY; + + memcpy(optpkt, buf, tcp_offset); + memcpy(optpkt + tcp_offset + optlen, buf + tcp_offset, + sizeof(struct tcphdr) + PAYLOAD_LEN); + + iph = (struct iphdr *)(optpkt + ETH_HLEN); + iph->ihl = 5 + (optlen / 4); + iph->tot_len = htons(ntohs(iph->tot_len) + optlen); + iph->check = 0; + iph->check = checksum_fold(iph, sizeof(struct iphdr) + optlen, 0); +} + +/* IPv4 options shouldn't coalesce */ +static void send_ip_options(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + static char optpkt[sizeof(buf) + sizeof(struct ip_timestamp)]; + int optlen = sizeof(struct ip_timestamp); + int pkt_size = total_hdr_len + PAYLOAD_LEN + optlen; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, total_hdr_len + PAYLOAD_LEN, daddr); + + create_packet(buf, PAYLOAD_LEN * 1, 0, PAYLOAD_LEN, 0); + add_ipv4_ts_option(buf, optpkt); + write_packet(fd, optpkt, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, total_hdr_len + PAYLOAD_LEN, daddr); +} + +/* IPv4 fragments shouldn't coalesce */ +static void send_fragment4(int fd, struct sockaddr_ll *daddr) +{ + static char buf[IP_MAXPACKET]; + struct iphdr *iph = (struct iphdr *)(buf + ETH_HLEN); + int pkt_size = total_hdr_len + PAYLOAD_LEN; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, pkt_size, daddr); + + /* Once fragmented, packet would retain the total_len. + * Tcp header is prepared as if rest of data is in follow-up frags, + * but follow up frags aren't actually sent. + */ + memset(buf + total_hdr_len, 'a', PAYLOAD_LEN * 2); + fill_transportlayer(buf + tcp_offset, PAYLOAD_LEN, 0, PAYLOAD_LEN * 2, 0); + fill_networklayer(buf + ETH_HLEN, PAYLOAD_LEN); + fill_datalinklayer(buf); + + iph->frag_off = htons(0x6000); // DF = 1, MF = 1 + iph->check = 0; + iph->check = checksum_fold(iph, sizeof(struct iphdr), 0); + write_packet(fd, buf, pkt_size, daddr); +} + +/* IPv4 packets with different ttl don't coalesce.*/ +static void send_changed_ttl(int fd, struct sockaddr_ll *daddr) +{ + int pkt_size = total_hdr_len + PAYLOAD_LEN; + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + struct iphdr *iph = (struct iphdr *)(buf + ETH_HLEN); + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + iph->ttl = 7; + iph->check = 0; + iph->check = checksum_fold(iph, sizeof(struct iphdr), 0); + write_packet(fd, buf, pkt_size, daddr); +} + +/* Packets with different tos don't coalesce.*/ +static void send_changed_tos(int fd, struct sockaddr_ll *daddr) +{ + int pkt_size = total_hdr_len + PAYLOAD_LEN; + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + struct iphdr *iph = (struct iphdr *)(buf + ETH_HLEN); + struct ipv6hdr *ip6h = (struct ipv6hdr *)(buf + ETH_HLEN); + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + if (proto == PF_INET) { + iph->tos = 1; + iph->check = 0; + iph->check = checksum_fold(iph, sizeof(struct iphdr), 0); + } else if (proto == PF_INET6) { + ip6h->priority = 0xf; + } + write_packet(fd, buf, pkt_size, daddr); +} + +/* Packets with different ECN don't coalesce.*/ +static void send_changed_ECN(int fd, struct sockaddr_ll *daddr) +{ + int pkt_size = total_hdr_len + PAYLOAD_LEN; + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + struct iphdr *iph = (struct iphdr *)(buf + ETH_HLEN); + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + if (proto == PF_INET) { + buf[ETH_HLEN + 1] ^= 0x2; // ECN set to 10 + iph->check = 0; + iph->check = checksum_fold(iph, sizeof(struct iphdr), 0); + } else { + buf[ETH_HLEN + 1] ^= 0x20; // ECN set to 10 + } + write_packet(fd, buf, pkt_size, daddr); +} + +/* IPv6 fragments and packets with extensions don't coalesce.*/ +static void send_fragment6(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + static char extpkt[MAX_HDR_LEN + PAYLOAD_LEN + + sizeof(struct ip6_frag)]; + struct ipv6hdr *ip6h = (struct ipv6hdr *)(buf + ETH_HLEN); + struct ip6_frag *frag = (void *)(extpkt + tcp_offset); + int extlen = sizeof(struct ip6_frag); + int bufpkt_len = total_hdr_len + PAYLOAD_LEN; + int extpkt_len = bufpkt_len + extlen; + int i; + + for (i = 0; i < 2; i++) { + create_packet(buf, PAYLOAD_LEN * i, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, bufpkt_len, daddr); + } + + create_packet(buf, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0); + memset(extpkt, 0, extpkt_len); + + ip6h->nexthdr = IPPROTO_FRAGMENT; + ip6h->payload_len = htons(ntohs(ip6h->payload_len) + extlen); + frag->ip6f_nxt = IPPROTO_TCP; + + memcpy(extpkt, buf, tcp_offset); + memcpy(extpkt + tcp_offset + extlen, buf + tcp_offset, + sizeof(struct tcphdr) + PAYLOAD_LEN); + write_packet(fd, extpkt, extpkt_len, daddr); + + create_packet(buf, PAYLOAD_LEN * 3, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, bufpkt_len, daddr); +} + +static void bind_packetsocket(int fd) +{ + struct sockaddr_ll daddr = {}; + + daddr.sll_family = AF_PACKET; + daddr.sll_protocol = ethhdr_proto; + daddr.sll_ifindex = if_nametoindex(ifname); + if (daddr.sll_ifindex == 0) + error(1, errno, "if_nametoindex"); + + if (bind(fd, (void *)&daddr, sizeof(daddr)) < 0) + error(1, errno, "could not bind socket"); +} + +static void set_timeout(int fd) +{ + struct timeval timeout; + + timeout.tv_sec = 120; + timeout.tv_usec = 0; + if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, (char *)&timeout, + sizeof(timeout)) < 0) + error(1, errno, "cannot set timeout, setsockopt failed"); +} + +static void check_recv_pkts(int fd, int *correct_payload, + int correct_num_pkts) +{ + static char buffer[IP_MAXPACKET + ETH_HLEN + 1]; + struct iphdr *iph = (struct iphdr *)(buffer + ETH_HLEN); + struct ipv6hdr *ip6h = (struct ipv6hdr *)(buffer + ETH_HLEN); + struct tcphdr *tcph; + bool bad_packet = false; + int tcp_ext_len = 0; + int ip_ext_len = 0; + int pkt_size = -1; + int data_len = 0; + int num_pkt = 0; + int i; + + vlog("Expected {"); + for (i = 0; i < correct_num_pkts; i++) + vlog("%d ", correct_payload[i]); + vlog("}, Total %d packets\nReceived {", correct_num_pkts); + + while (1) { + pkt_size = recv(fd, buffer, IP_MAXPACKET + ETH_HLEN + 1, 0); + if (pkt_size < 0) + error(1, errno, "could not receive"); + + if (iph->version == 4) + ip_ext_len = (iph->ihl - 5) * 4; + else if (ip6h->version == 6 && ip6h->nexthdr != IPPROTO_TCP) + ip_ext_len = sizeof(struct ip6_frag); + + tcph = (struct tcphdr *)(buffer + tcp_offset + ip_ext_len); + + if (tcph->fin) + break; + + tcp_ext_len = (tcph->doff - 5) * 4; + data_len = pkt_size - total_hdr_len - tcp_ext_len - ip_ext_len; + /* Min ethernet frame payload is 46(ETH_ZLEN - ETH_HLEN) by RFC 802.3. + * Ipv4/tcp packets without at least 6 bytes of data will be padded. + * Packet sockets are protocol agnostic, and will not trim the padding. + */ + if (pkt_size == ETH_ZLEN && iph->version == 4) { + data_len = ntohs(iph->tot_len) + - sizeof(struct tcphdr) - sizeof(struct iphdr); + } + vlog("%d ", data_len); + if (data_len != correct_payload[num_pkt]) { + vlog("[!=%d]", correct_payload[num_pkt]); + bad_packet = true; + } + num_pkt++; + } + vlog("}, Total %d packets.\n", num_pkt); + if (num_pkt != correct_num_pkts) + error(1, 0, "incorrect number of packets"); + if (bad_packet) + error(1, 0, "incorrect packet geometry"); + + printf("Test succeeded\n\n"); +} + +static void gro_sender(void) +{ + static char fin_pkt[MAX_HDR_LEN]; + struct sockaddr_ll daddr = {}; + int txfd = -1; + + txfd = socket(PF_PACKET, SOCK_RAW, IPPROTO_RAW); + if (txfd < 0) + error(1, errno, "socket creation"); + + memset(&daddr, 0, sizeof(daddr)); + daddr.sll_ifindex = if_nametoindex(ifname); + if (daddr.sll_ifindex == 0) + error(1, errno, "if_nametoindex"); + daddr.sll_family = AF_PACKET; + memcpy(daddr.sll_addr, dst_mac, ETH_ALEN); + daddr.sll_halen = ETH_ALEN; + create_packet(fin_pkt, PAYLOAD_LEN * 2, 0, 0, 1); + + if (strcmp(testname, "data") == 0) { + send_data_pkts(txfd, &daddr, PAYLOAD_LEN, PAYLOAD_LEN); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + send_data_pkts(txfd, &daddr, PAYLOAD_LEN, PAYLOAD_LEN / 2); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + send_data_pkts(txfd, &daddr, PAYLOAD_LEN / 2, PAYLOAD_LEN); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ack") == 0) { + send_ack(txfd, &daddr); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "flags") == 0) { + send_flags(txfd, &daddr, 1, 0, 0, 0); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + send_flags(txfd, &daddr, 0, 1, 0, 0); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + send_flags(txfd, &daddr, 0, 0, 1, 0); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + send_flags(txfd, &daddr, 0, 0, 0, 1); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "tcp") == 0) { + send_changed_checksum(txfd, &daddr); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + send_changed_seq(txfd, &daddr); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + send_changed_ts(txfd, &daddr); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + send_diff_opt(txfd, &daddr); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip") == 0) { + send_changed_ECN(txfd, &daddr); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + send_changed_tos(txfd, &daddr); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + if (proto == PF_INET) { + /* Modified packets may be received out of order. + * Sleep function added to enforce test boundaries + * so that fin pkts are not received prior to other pkts. + */ + sleep(1); + send_changed_ttl(txfd, &daddr); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + sleep(1); + send_ip_options(txfd, &daddr); + sleep(1); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + sleep(1); + send_fragment4(txfd, &daddr); + sleep(1); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (proto == PF_INET6) { + send_fragment6(txfd, &daddr); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } + } else if (strcmp(testname, "large") == 0) { + /* 20 is the difference between min iphdr size + * and min ipv6hdr size. Like MAX_HDR_SIZE, + * MAX_PAYLOAD is defined with the larger header of the two. + */ + int offset = proto == PF_INET ? 20 : 0; + int remainder = (MAX_PAYLOAD + offset) % MSS; + + send_large(txfd, &daddr, remainder); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + send_large(txfd, &daddr, remainder + 1); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else { + error(1, 0, "Unknown testcase"); + } + + if (close(txfd)) + error(1, errno, "socket close"); +} + +static void gro_receiver(void) +{ + static int correct_payload[NUM_PACKETS]; + int rxfd = -1; + + rxfd = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_NONE)); + if (rxfd < 0) + error(1, 0, "socket creation"); + setup_sock_filter(rxfd); + set_timeout(rxfd); + bind_packetsocket(rxfd); + + memset(correct_payload, 0, sizeof(correct_payload)); + + if (strcmp(testname, "data") == 0) { + printf("pure data packet of same size: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 1); + + printf("large data packets followed by a smaller one: "); + correct_payload[0] = PAYLOAD_LEN * 1.5; + check_recv_pkts(rxfd, correct_payload, 1); + + printf("small data packets followed by a larger one: "); + correct_payload[0] = PAYLOAD_LEN / 2; + correct_payload[1] = PAYLOAD_LEN; + check_recv_pkts(rxfd, correct_payload, 2); + } else if (strcmp(testname, "ack") == 0) { + printf("duplicate ack and pure ack: "); + check_recv_pkts(rxfd, correct_payload, 3); + } else if (strcmp(testname, "flags") == 0) { + correct_payload[0] = PAYLOAD_LEN * 3; + correct_payload[1] = PAYLOAD_LEN * 2; + + printf("psh flag ends coalescing: "); + check_recv_pkts(rxfd, correct_payload, 2); + + correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = 0; + correct_payload[2] = PAYLOAD_LEN * 2; + printf("syn flag ends coalescing: "); + check_recv_pkts(rxfd, correct_payload, 3); + + printf("rst flag ends coalescing: "); + check_recv_pkts(rxfd, correct_payload, 3); + + printf("urg flag ends coalescing: "); + check_recv_pkts(rxfd, correct_payload, 3); + } else if (strcmp(testname, "tcp") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; + correct_payload[2] = PAYLOAD_LEN; + correct_payload[3] = PAYLOAD_LEN; + + printf("changed checksum does not coalesce: "); + check_recv_pkts(rxfd, correct_payload, 2); + + printf("Wrong Seq number doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 2); + + printf("Different timestamp doesn't coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 4); + + printf("Different options doesn't coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 2); + } else if (strcmp(testname, "ip") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; + + printf("different ECN doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 2); + + printf("different tos doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 2); + + if (proto == PF_INET) { + printf("different ttl doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 2); + + printf("ip options doesn't coalesce: "); + correct_payload[2] = PAYLOAD_LEN; + check_recv_pkts(rxfd, correct_payload, 3); + + printf("fragmented ip4 doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 2); + } else if (proto == PF_INET6) { + /* GRO doesn't check for ipv6 hop limit when flushing. + * Hence no corresponding test to the ipv4 case. + */ + printf("fragmented ip6 doesn't coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 2); + } + } else if (strcmp(testname, "large") == 0) { + int offset = proto == PF_INET ? 20 : 0; + int remainder = (MAX_PAYLOAD + offset) % MSS; + + correct_payload[0] = (MAX_PAYLOAD + offset); + correct_payload[1] = remainder; + printf("Shouldn't coalesce if exceed IP max pkt size: "); + check_recv_pkts(rxfd, correct_payload, 2); + + /* last segment sent individually, doesn't start new segment */ + correct_payload[0] = correct_payload[0] - remainder; + correct_payload[1] = remainder + 1; + correct_payload[2] = remainder + 1; + check_recv_pkts(rxfd, correct_payload, 3); + } else { + error(1, 0, "Test case error, should never trigger"); + } + + if (close(rxfd)) + error(1, 0, "socket close"); +} + +static void parse_args(int argc, char **argv) +{ + static const struct option opts[] = { + { "dmac", required_argument, NULL, 'D' }, + { "iface", required_argument, NULL, 'i' }, + { "ipv4", no_argument, NULL, '4' }, + { "ipv6", no_argument, NULL, '6' }, + { "rx", no_argument, NULL, 'r' }, + { "smac", required_argument, NULL, 'S' }, + { "test", required_argument, NULL, 't' }, + { "verbose", no_argument, NULL, 'v' }, + { 0, 0, 0, 0 } + }; + int c; + + while ((c = getopt_long(argc, argv, "46D:i:rS:t:v", opts, NULL)) != -1) { + switch (c) { + case '4': + proto = PF_INET; + ethhdr_proto = htons(ETH_P_IP); + break; + case '6': + proto = PF_INET6; + ethhdr_proto = htons(ETH_P_IPV6); + break; + case 'D': + dmac = optarg; + break; + case 'i': + ifname = optarg; + break; + case 'r': + tx_socket = false; + break; + case 'S': + smac = optarg; + break; + case 't': + testname = optarg; + break; + case 'v': + verbose = true; + break; + default: + error(1, 0, "%s invalid option %c\n", __func__, c); + break; + } + } +} + +int main(int argc, char **argv) +{ + parse_args(argc, argv); + + if (proto == PF_INET) { + tcp_offset = ETH_HLEN + sizeof(struct iphdr); + total_hdr_len = tcp_offset + sizeof(struct tcphdr); + } else if (proto == PF_INET6) { + tcp_offset = ETH_HLEN + sizeof(struct ipv6hdr); + total_hdr_len = MAX_HDR_LEN; + } else { + error(1, 0, "Protocol family is not ipv4 or ipv6"); + } + + read_MAC(src_mac, smac); + read_MAC(dst_mac, dmac); + + if (tx_socket) + gro_sender(); + else + gro_receiver(); + return 0; +} diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh new file mode 100755 index 000000000000..342ad27f631b --- /dev/null +++ b/tools/testing/selftests/net/gro.sh @@ -0,0 +1,99 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +readonly SERVER_MAC="aa:00:00:00:00:02" +readonly CLIENT_MAC="aa:00:00:00:00:01" +readonly TESTS=("data" "ack" "flags" "tcp" "ip" "large") +readonly PROTOS=("ipv4" "ipv6") +dev="" +test="all" +proto="ipv4" + +run_test() { + local server_pid=0 + local exit_code=0 + local protocol=$1 + local test=$2 + local ARGS=( "--${protocol}" "--dmac" "${SERVER_MAC}" \ + "--smac" "${CLIENT_MAC}" "--test" "${test}" "--verbose" ) + + setup_ns + # Each test is run 3 times to deflake, because given the receive timing, + # not all packets that should coalesce will be considered in the same flow + # on every try. + for tries in {1..3}; do + # Actual test starts here + ip netns exec server_ns ./gro "${ARGS[@]}" "--rx" "--iface" "server" \ + 1>>log.txt & + server_pid=$! + sleep 0.5 # to allow for socket init + ip netns exec client_ns ./gro "${ARGS[@]}" "--iface" "client" \ + 1>>log.txt + wait "${server_pid}" + exit_code=$? + if [[ "${exit_code}" -eq 0 ]]; then + break; + fi + done + cleanup_ns + echo ${exit_code} +} + +run_all_tests() { + local failed_tests=() + for proto in "${PROTOS[@]}"; do + for test in "${TESTS[@]}"; do + echo "running test ${proto} ${test}" >&2 + exit_code=$(run_test $proto $test) + if [[ "${exit_code}" -ne 0 ]]; then + failed_tests+=("${proto}_${test}") + fi; + done; + done + if [[ ${#failed_tests[@]} -ne 0 ]]; then + echo "failed tests: ${failed_tests[*]}. \ + Please see log.txt for more logs" + exit 1 + else + echo "All Tests Succeeded!" + fi; +} + +usage() { + echo "Usage: $0 \ + [-i <DEV>] \ + [-t data|ack|flags|tcp|ip|large] \ + [-p <ipv4|ipv6>]" 1>&2; + exit 1; +} + +while getopts "i:t:p:" opt; do + case "${opt}" in + i) + dev="${OPTARG}" + ;; + t) + test="${OPTARG}" + ;; + p) + proto="${OPTARG}" + ;; + *) + usage + ;; + esac +done + +if [ -n "$dev" ]; then + source setup_loopback.sh +else + source setup_veth.sh +fi + +setup +trap cleanup EXIT +if [[ "${test}" == "all" ]]; then + run_all_tests +else + run_test "${proto}" "${test}" +fi; diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh new file mode 100755 index 000000000000..3caf72bb9c6a --- /dev/null +++ b/tools/testing/selftests/net/ioam6.sh @@ -0,0 +1,652 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Author: Justin Iurman <justin.iurman@uliege.be> +# +# This script evaluates the IOAM insertion for IPv6 by checking the IOAM data +# consistency directly inside packets on the receiver side. Tests are divided +# into three categories: OUTPUT (evaluates the IOAM processing by the sender), +# INPUT (evaluates the IOAM processing by the receiver) and GLOBAL (evaluates +# wider use cases that do not fall into the other two categories). Both OUTPUT +# and INPUT tests only use a two-node topology (alpha and beta), while GLOBAL +# tests use the entire three-node topology (alpha, beta, gamma). Each test is +# documented inside its own handler in the code below. +# +# An IOAM domain is configured from Alpha to Gamma but not on the reverse path. +# When either Beta or Gamma is the destination (depending on the test category), +# Alpha adds an IOAM option (Pre-allocated Trace) inside a Hop-by-hop. +# +# +# +-------------------+ +-------------------+ +# | | | | +# | Alpha netns | | Gamma netns | +# | | | | +# | +-------------+ | | +-------------+ | +# | | veth0 | | | | veth0 | | +# | | db01::2/64 | | | | db02::2/64 | | +# | +-------------+ | | +-------------+ | +# | . | | . | +# +-------------------+ +-------------------+ +# . . +# . . +# . . +# +----------------------------------------------------+ +# | . . | +# | +-------------+ +-------------+ | +# | | veth0 | | veth1 | | +# | | db01::1/64 | ................ | db02::1/64 | | +# | +-------------+ +-------------+ | +# | | +# | Beta netns | +# | | +# +----------------------------------------------------+ +# +# +# +# ============================================================= +# | Alpha - IOAM configuration | +# +===========================================================+ +# | Node ID | 1 | +# +-----------------------------------------------------------+ +# | Node Wide ID | 11111111 | +# +-----------------------------------------------------------+ +# | Ingress ID | 0xffff (default value) | +# +-----------------------------------------------------------+ +# | Ingress Wide ID | 0xffffffff (default value) | +# +-----------------------------------------------------------+ +# | Egress ID | 101 | +# +-----------------------------------------------------------+ +# | Egress Wide ID | 101101 | +# +-----------------------------------------------------------+ +# | Namespace Data | 0xdeadbee0 | +# +-----------------------------------------------------------+ +# | Namespace Wide Data | 0xcafec0caf00dc0de | +# +-----------------------------------------------------------+ +# | Schema ID | 777 | +# +-----------------------------------------------------------+ +# | Schema Data | something that will be 4n-aligned | +# +-----------------------------------------------------------+ +# +# +# ============================================================= +# | Beta - IOAM configuration | +# +===========================================================+ +# | Node ID | 2 | +# +-----------------------------------------------------------+ +# | Node Wide ID | 22222222 | +# +-----------------------------------------------------------+ +# | Ingress ID | 201 | +# +-----------------------------------------------------------+ +# | Ingress Wide ID | 201201 | +# +-----------------------------------------------------------+ +# | Egress ID | 202 | +# +-----------------------------------------------------------+ +# | Egress Wide ID | 202202 | +# +-----------------------------------------------------------+ +# | Namespace Data | 0xdeadbee1 | +# +-----------------------------------------------------------+ +# | Namespace Wide Data | 0xcafec0caf11dc0de | +# +-----------------------------------------------------------+ +# | Schema ID | 666 | +# +-----------------------------------------------------------+ +# | Schema Data | Hello there -Obi | +# +-----------------------------------------------------------+ +# +# +# ============================================================= +# | Gamma - IOAM configuration | +# +===========================================================+ +# | Node ID | 3 | +# +-----------------------------------------------------------+ +# | Node Wide ID | 33333333 | +# +-----------------------------------------------------------+ +# | Ingress ID | 301 | +# +-----------------------------------------------------------+ +# | Ingress Wide ID | 301301 | +# +-----------------------------------------------------------+ +# | Egress ID | 0xffff (default value) | +# +-----------------------------------------------------------+ +# | Egress Wide ID | 0xffffffff (default value) | +# +-----------------------------------------------------------+ +# | Namespace Data | 0xdeadbee2 | +# +-----------------------------------------------------------+ +# | Namespace Wide Data | 0xcafec0caf22dc0de | +# +-----------------------------------------------------------+ +# | Schema ID | 0xffffff (= None) | +# +-----------------------------------------------------------+ +# | Schema Data | | +# +-----------------------------------------------------------+ + + +################################################################################ +# # +# WARNING: Be careful if you modify the block below - it MUST be kept # +# synchronized with configurations inside ioam6_parser.c and always # +# reflect the same. # +# # +################################################################################ + +ALPHA=( + 1 # ID + 11111111 # Wide ID + 0xffff # Ingress ID + 0xffffffff # Ingress Wide ID + 101 # Egress ID + 101101 # Egress Wide ID + 0xdeadbee0 # Namespace Data + 0xcafec0caf00dc0de # Namespace Wide Data + 777 # Schema ID (0xffffff = None) + "something that will be 4n-aligned" # Schema Data +) + +BETA=( + 2 + 22222222 + 201 + 201201 + 202 + 202202 + 0xdeadbee1 + 0xcafec0caf11dc0de + 666 + "Hello there -Obi" +) + +GAMMA=( + 3 + 33333333 + 301 + 301301 + 0xffff + 0xffffffff + 0xdeadbee2 + 0xcafec0caf22dc0de + 0xffffff + "" +) + +TESTS_OUTPUT=" + out_undef_ns + out_no_room + out_bits + out_full_supp_trace +" + +TESTS_INPUT=" + in_undef_ns + in_no_room + in_oflag + in_bits + in_full_supp_trace +" + +TESTS_GLOBAL=" + fwd_full_supp_trace +" + + +################################################################################ +# # +# LIBRARY # +# # +################################################################################ + +check_kernel_compatibility() +{ + ip netns add ioam-tmp-node + ip link add name veth0 netns ioam-tmp-node type veth \ + peer name veth1 netns ioam-tmp-node + + ip -netns ioam-tmp-node link set veth0 up + ip -netns ioam-tmp-node link set veth1 up + + ip -netns ioam-tmp-node ioam namespace add 0 &>/dev/null + ns_ad=$? + + ip -netns ioam-tmp-node ioam namespace show | grep -q "namespace 0" + ns_sh=$? + + if [[ $ns_ad != 0 || $ns_sh != 0 ]] + then + echo "SKIP: kernel version probably too old, missing ioam support" + ip link del veth0 2>/dev/null || true + ip netns del ioam-tmp-node || true + exit 1 + fi + + ip -netns ioam-tmp-node route add db02::/64 encap ioam6 trace prealloc \ + type 0x800000 ns 0 size 4 dev veth0 &>/dev/null + tr_ad=$? + + ip -netns ioam-tmp-node -6 route | grep -q "encap ioam6 trace" + tr_sh=$? + + if [[ $tr_ad != 0 || $tr_sh != 0 ]] + then + echo "SKIP: cannot attach an ioam trace to a route, did you compile" \ + "without CONFIG_IPV6_IOAM6_LWTUNNEL?" + ip link del veth0 2>/dev/null || true + ip netns del ioam-tmp-node || true + exit 1 + fi + + ip link del veth0 2>/dev/null || true + ip netns del ioam-tmp-node || true +} + +cleanup() +{ + ip link del ioam-veth-alpha 2>/dev/null || true + ip link del ioam-veth-gamma 2>/dev/null || true + + ip netns del ioam-node-alpha || true + ip netns del ioam-node-beta || true + ip netns del ioam-node-gamma || true +} + +setup() +{ + ip netns add ioam-node-alpha + ip netns add ioam-node-beta + ip netns add ioam-node-gamma + + ip link add name ioam-veth-alpha netns ioam-node-alpha type veth \ + peer name ioam-veth-betaL netns ioam-node-beta + ip link add name ioam-veth-betaR netns ioam-node-beta type veth \ + peer name ioam-veth-gamma netns ioam-node-gamma + + ip -netns ioam-node-alpha link set ioam-veth-alpha name veth0 + ip -netns ioam-node-beta link set ioam-veth-betaL name veth0 + ip -netns ioam-node-beta link set ioam-veth-betaR name veth1 + ip -netns ioam-node-gamma link set ioam-veth-gamma name veth0 + + ip -netns ioam-node-alpha addr add db01::2/64 dev veth0 + ip -netns ioam-node-alpha link set veth0 up + ip -netns ioam-node-alpha link set lo up + ip -netns ioam-node-alpha route add db02::/64 via db01::1 dev veth0 + ip -netns ioam-node-alpha route del db01::/64 + ip -netns ioam-node-alpha route add db01::/64 dev veth0 + + ip -netns ioam-node-beta addr add db01::1/64 dev veth0 + ip -netns ioam-node-beta addr add db02::1/64 dev veth1 + ip -netns ioam-node-beta link set veth0 up + ip -netns ioam-node-beta link set veth1 up + ip -netns ioam-node-beta link set lo up + + ip -netns ioam-node-gamma addr add db02::2/64 dev veth0 + ip -netns ioam-node-gamma link set veth0 up + ip -netns ioam-node-gamma link set lo up + ip -netns ioam-node-gamma route add db01::/64 via db02::1 dev veth0 + + # - IOAM config - + ip netns exec ioam-node-alpha sysctl -wq net.ipv6.ioam6_id=${ALPHA[0]} + ip netns exec ioam-node-alpha sysctl -wq net.ipv6.ioam6_id_wide=${ALPHA[1]} + ip netns exec ioam-node-alpha sysctl -wq net.ipv6.conf.veth0.ioam6_id=${ALPHA[4]} + ip netns exec ioam-node-alpha sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${ALPHA[5]} + ip -netns ioam-node-alpha ioam namespace add 123 data ${ALPHA[6]} wide ${ALPHA[7]} + ip -netns ioam-node-alpha ioam schema add ${ALPHA[8]} "${ALPHA[9]}" + ip -netns ioam-node-alpha ioam namespace set 123 schema ${ALPHA[8]} + + ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.all.forwarding=1 + ip netns exec ioam-node-beta sysctl -wq net.ipv6.ioam6_id=${BETA[0]} + ip netns exec ioam-node-beta sysctl -wq net.ipv6.ioam6_id_wide=${BETA[1]} + ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1 + ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_id=${BETA[2]} + ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${BETA[3]} + ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth1.ioam6_id=${BETA[4]} + ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth1.ioam6_id_wide=${BETA[5]} + ip -netns ioam-node-beta ioam namespace add 123 data ${BETA[6]} wide ${BETA[7]} + ip -netns ioam-node-beta ioam schema add ${BETA[8]} "${BETA[9]}" + ip -netns ioam-node-beta ioam namespace set 123 schema ${BETA[8]} + + ip netns exec ioam-node-gamma sysctl -wq net.ipv6.ioam6_id=${GAMMA[0]} + ip netns exec ioam-node-gamma sysctl -wq net.ipv6.ioam6_id_wide=${GAMMA[1]} + ip netns exec ioam-node-gamma sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1 + ip netns exec ioam-node-gamma sysctl -wq net.ipv6.conf.veth0.ioam6_id=${GAMMA[2]} + ip netns exec ioam-node-gamma sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${GAMMA[3]} + ip -netns ioam-node-gamma ioam namespace add 123 data ${GAMMA[6]} wide ${GAMMA[7]} + + sleep 1 + + ip netns exec ioam-node-alpha ping6 -c 5 -W 1 db02::2 &>/dev/null + if [ $? != 0 ] + then + echo "Setup FAILED" + cleanup &>/dev/null + exit 0 + fi +} + +log_test_passed() +{ + local desc=$1 + printf "TEST: %-60s [ OK ]\n" "${desc}" +} + +log_test_failed() +{ + local desc=$1 + printf "TEST: %-60s [FAIL]\n" "${desc}" +} + +run_test() +{ + local name=$1 + local desc=$2 + local node_src=$3 + local node_dst=$4 + local ip6_src=$5 + local ip6_dst=$6 + local if_dst=$7 + local trace_type=$8 + local ioam_ns=$9 + + ip netns exec $node_dst ./ioam6_parser $if_dst $name $ip6_src $ip6_dst \ + $trace_type $ioam_ns & + local spid=$! + sleep 0.1 + + ip netns exec $node_src ping6 -t 64 -c 1 -W 1 $ip6_dst &>/dev/null + if [ $? != 0 ] + then + log_test_failed "${desc}" + kill -2 $spid &>/dev/null + else + wait $spid + [ $? = 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}" + fi +} + +run() +{ + echo + echo "OUTPUT tests" + printf "%0.s-" {1..74} + echo + + # set OUTPUT settings + ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=0 + + for t in $TESTS_OUTPUT + do + $t + done + + # clean OUTPUT settings + ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1 + ip -netns ioam-node-alpha route change db01::/64 dev veth0 + + + echo + echo "INPUT tests" + printf "%0.s-" {1..74} + echo + + # set INPUT settings + ip -netns ioam-node-alpha ioam namespace del 123 + + for t in $TESTS_INPUT + do + $t + done + + # clean INPUT settings + ip -netns ioam-node-alpha ioam namespace add 123 \ + data ${ALPHA[6]} wide ${ALPHA[7]} + ip -netns ioam-node-alpha ioam namespace set 123 schema ${ALPHA[8]} + ip -netns ioam-node-alpha route change db01::/64 dev veth0 + + + echo + echo "GLOBAL tests" + printf "%0.s-" {1..74} + echo + + for t in $TESTS_GLOBAL + do + $t + done +} + +bit2type=( + 0x800000 0x400000 0x200000 0x100000 0x080000 0x040000 0x020000 0x010000 + 0x008000 0x004000 0x002000 0x001000 0x000800 0x000400 0x000200 0x000100 + 0x000080 0x000040 0x000020 0x000010 0x000008 0x000004 0x000002 +) +bit2size=( 4 4 4 4 4 4 4 4 8 8 8 4 4 4 4 4 4 4 4 4 4 4 4 ) + + +################################################################################ +# # +# OUTPUT tests # +# # +# Two nodes (sender/receiver), IOAM disabled on ingress for the receiver. # +################################################################################ + +out_undef_ns() +{ + ############################################################################## + # Make sure that the encap node won't fill the trace if the chosen IOAM # + # namespace is not configured locally. # + ############################################################################## + local desc="Unknown IOAM namespace" + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ + type 0x800000 ns 0 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ + db01::1 veth0 0x800000 0 +} + +out_no_room() +{ + ############################################################################## + # Make sure that the encap node won't fill the trace and will set the # + # Overflow flag since there is no room enough for its data. # + ############################################################################## + local desc="Missing trace room" + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ + type 0xc00000 ns 123 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ + db01::1 veth0 0xc00000 123 +} + +out_bits() +{ + ############################################################################## + # Make sure that, for each trace type bit, the encap node will either: # + # (i) fill the trace with its data when it is a supported bit # + # (ii) not fill the trace with its data when it is an unsupported bit # + ############################################################################## + local desc="Trace type with bit <n> only" + + local tmp=${bit2size[22]} + bit2size[22]=$(( $tmp + ${#ALPHA[9]} + ((4 - (${#ALPHA[9]} % 4)) % 4) )) + + for i in {0..22} + do + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace \ + prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} dev veth0 + + run_test "out_bit$i" "${desc/<n>/$i}" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 ${bit2type[$i]} 123 + done + + bit2size[22]=$tmp +} + +out_full_supp_trace() +{ + ############################################################################## + # Make sure that the encap node will correctly fill a full trace. Be careful,# + # "full trace" here does NOT mean all bits (only supported ones). # + ############################################################################## + local desc="Full supported trace" + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ + type 0xfff002 ns 123 size 100 dev veth0 + + run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ + db01::1 veth0 0xfff002 123 +} + + +################################################################################ +# # +# INPUT tests # +# # +# Two nodes (sender/receiver), the sender MUST NOT fill the trace upon # +# insertion -> the IOAM namespace configured on the sender is removed # +# and is used in the inserted trace to force the sender not to fill it. # +################################################################################ + +in_undef_ns() +{ + ############################################################################## + # Make sure that the receiving node won't fill the trace if the related IOAM # + # namespace is not configured locally. # + ############################################################################## + local desc="Unknown IOAM namespace" + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ + type 0x800000 ns 0 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ + db01::1 veth0 0x800000 0 +} + +in_no_room() +{ + ############################################################################## + # Make sure that the receiving node won't fill the trace and will set the # + # Overflow flag if there is no room enough for its data. # + ############################################################################## + local desc="Missing trace room" + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ + type 0xc00000 ns 123 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ + db01::1 veth0 0xc00000 123 +} + +in_bits() +{ + ############################################################################## + # Make sure that, for each trace type bit, the receiving node will either: # + # (i) fill the trace with its data when it is a supported bit # + # (ii) not fill the trace with its data when it is an unsupported bit # + ############################################################################## + local desc="Trace type with bit <n> only" + + local tmp=${bit2size[22]} + bit2size[22]=$(( $tmp + ${#BETA[9]} + ((4 - (${#BETA[9]} % 4)) % 4) )) + + for i in {0..22} + do + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace \ + prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} dev veth0 + + run_test "in_bit$i" "${desc/<n>/$i}" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 ${bit2type[$i]} 123 + done + + bit2size[22]=$tmp +} + +in_oflag() +{ + ############################################################################## + # Make sure that the receiving node won't fill the trace since the Overflow # + # flag is set. # + ############################################################################## + local desc="Overflow flag is set" + + # Exception: + # Here, we need the sender to set the Overflow flag. For that, we will add + # back the IOAM namespace that was previously configured on the sender. + ip -netns ioam-node-alpha ioam namespace add 123 + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ + type 0xc00000 ns 123 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ + db01::1 veth0 0xc00000 123 + + # And we clean the exception for this test to get things back to normal for + # other INPUT tests + ip -netns ioam-node-alpha ioam namespace del 123 +} + +in_full_supp_trace() +{ + ############################################################################## + # Make sure that the receiving node will correctly fill a full trace. Be # + # careful, "full trace" here does NOT mean all bits (only supported ones). # + ############################################################################## + local desc="Full supported trace" + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ + type 0xfff002 ns 123 size 80 dev veth0 + + run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ + db01::1 veth0 0xfff002 123 +} + + +################################################################################ +# # +# GLOBAL tests # +# # +# Three nodes (sender/router/receiver), IOAM fully enabled on every node. # +################################################################################ + +fwd_full_supp_trace() +{ + ############################################################################## + # Make sure that all three nodes correctly filled the full supported trace # + # by checking that the trace data is consistent with the predefined config. # + ############################################################################## + local desc="Forward - Full supported trace" + + ip -netns ioam-node-alpha route change db02::/64 encap ioam6 trace prealloc \ + type 0xfff002 ns 123 size 244 via db01::1 dev veth0 + + run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-gamma db01::2 \ + db02::2 veth0 0xfff002 123 +} + + +################################################################################ +# # +# MAIN # +# # +################################################################################ + +if [ "$(id -u)" -ne 0 ] +then + echo "SKIP: Need root privileges" + exit 1 +fi + +if [ ! -x "$(command -v ip)" ] +then + echo "SKIP: Could not run test without ip tool" + exit 1 +fi + +ip ioam &>/dev/null +if [ $? = 1 ] +then + echo "SKIP: iproute2 too old, missing ioam command" + exit 1 +fi + +check_kernel_compatibility + +cleanup &>/dev/null +setup +run +cleanup &>/dev/null diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c new file mode 100644 index 000000000000..d376cb2c383c --- /dev/null +++ b/tools/testing/selftests/net/ioam6_parser.c @@ -0,0 +1,720 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Author: Justin Iurman (justin.iurman@uliege.be) + * + * IOAM tester for IPv6, see ioam6.sh for details on each test case. + */ +#include <arpa/inet.h> +#include <errno.h> +#include <limits.h> +#include <linux/const.h> +#include <linux/if_ether.h> +#include <linux/ioam6.h> +#include <linux/ipv6.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +struct ioam_config { + __u32 id; + __u64 wide; + __u16 ingr_id; + __u16 egr_id; + __u32 ingr_wide; + __u32 egr_wide; + __u32 ns_data; + __u64 ns_wide; + __u32 sc_id; + __u8 hlim; + char *sc_data; +}; + +/* + * Be careful if you modify structs below - everything MUST be kept synchronized + * with configurations inside ioam6.sh and always reflect the same. + */ + +static struct ioam_config node1 = { + .id = 1, + .wide = 11111111, + .ingr_id = 0xffff, /* default value */ + .egr_id = 101, + .ingr_wide = 0xffffffff, /* default value */ + .egr_wide = 101101, + .ns_data = 0xdeadbee0, + .ns_wide = 0xcafec0caf00dc0de, + .sc_id = 777, + .sc_data = "something that will be 4n-aligned", + .hlim = 64, +}; + +static struct ioam_config node2 = { + .id = 2, + .wide = 22222222, + .ingr_id = 201, + .egr_id = 202, + .ingr_wide = 201201, + .egr_wide = 202202, + .ns_data = 0xdeadbee1, + .ns_wide = 0xcafec0caf11dc0de, + .sc_id = 666, + .sc_data = "Hello there -Obi", + .hlim = 63, +}; + +static struct ioam_config node3 = { + .id = 3, + .wide = 33333333, + .ingr_id = 301, + .egr_id = 0xffff, /* default value */ + .ingr_wide = 301301, + .egr_wide = 0xffffffff, /* default value */ + .ns_data = 0xdeadbee2, + .ns_wide = 0xcafec0caf22dc0de, + .sc_id = 0xffffff, /* default value */ + .sc_data = NULL, + .hlim = 62, +}; + +enum { + /********** + * OUTPUT * + **********/ + TEST_OUT_UNDEF_NS, + TEST_OUT_NO_ROOM, + TEST_OUT_BIT0, + TEST_OUT_BIT1, + TEST_OUT_BIT2, + TEST_OUT_BIT3, + TEST_OUT_BIT4, + TEST_OUT_BIT5, + TEST_OUT_BIT6, + TEST_OUT_BIT7, + TEST_OUT_BIT8, + TEST_OUT_BIT9, + TEST_OUT_BIT10, + TEST_OUT_BIT11, + TEST_OUT_BIT12, + TEST_OUT_BIT13, + TEST_OUT_BIT14, + TEST_OUT_BIT15, + TEST_OUT_BIT16, + TEST_OUT_BIT17, + TEST_OUT_BIT18, + TEST_OUT_BIT19, + TEST_OUT_BIT20, + TEST_OUT_BIT21, + TEST_OUT_BIT22, + TEST_OUT_FULL_SUPP_TRACE, + + /********* + * INPUT * + *********/ + TEST_IN_UNDEF_NS, + TEST_IN_NO_ROOM, + TEST_IN_OFLAG, + TEST_IN_BIT0, + TEST_IN_BIT1, + TEST_IN_BIT2, + TEST_IN_BIT3, + TEST_IN_BIT4, + TEST_IN_BIT5, + TEST_IN_BIT6, + TEST_IN_BIT7, + TEST_IN_BIT8, + TEST_IN_BIT9, + TEST_IN_BIT10, + TEST_IN_BIT11, + TEST_IN_BIT12, + TEST_IN_BIT13, + TEST_IN_BIT14, + TEST_IN_BIT15, + TEST_IN_BIT16, + TEST_IN_BIT17, + TEST_IN_BIT18, + TEST_IN_BIT19, + TEST_IN_BIT20, + TEST_IN_BIT21, + TEST_IN_BIT22, + TEST_IN_FULL_SUPP_TRACE, + + /********** + * GLOBAL * + **********/ + TEST_FWD_FULL_SUPP_TRACE, + + __TEST_MAX, +}; + +static int check_ioam_header(int tid, struct ioam6_trace_hdr *ioam6h, + __u32 trace_type, __u16 ioam_ns) +{ + if (__be16_to_cpu(ioam6h->namespace_id) != ioam_ns || + __be32_to_cpu(ioam6h->type_be32) != (trace_type << 8)) + return 1; + + switch (tid) { + case TEST_OUT_UNDEF_NS: + case TEST_IN_UNDEF_NS: + return ioam6h->overflow || + ioam6h->nodelen != 1 || + ioam6h->remlen != 1; + + case TEST_OUT_NO_ROOM: + case TEST_IN_NO_ROOM: + case TEST_IN_OFLAG: + return !ioam6h->overflow || + ioam6h->nodelen != 2 || + ioam6h->remlen != 1; + + case TEST_OUT_BIT0: + case TEST_IN_BIT0: + case TEST_OUT_BIT1: + case TEST_IN_BIT1: + case TEST_OUT_BIT2: + case TEST_IN_BIT2: + case TEST_OUT_BIT3: + case TEST_IN_BIT3: + case TEST_OUT_BIT4: + case TEST_IN_BIT4: + case TEST_OUT_BIT5: + case TEST_IN_BIT5: + case TEST_OUT_BIT6: + case TEST_IN_BIT6: + case TEST_OUT_BIT7: + case TEST_IN_BIT7: + case TEST_OUT_BIT11: + case TEST_IN_BIT11: + return ioam6h->overflow || + ioam6h->nodelen != 1 || + ioam6h->remlen; + + case TEST_OUT_BIT8: + case TEST_IN_BIT8: + case TEST_OUT_BIT9: + case TEST_IN_BIT9: + case TEST_OUT_BIT10: + case TEST_IN_BIT10: + return ioam6h->overflow || + ioam6h->nodelen != 2 || + ioam6h->remlen; + + case TEST_OUT_BIT12: + case TEST_IN_BIT12: + case TEST_OUT_BIT13: + case TEST_IN_BIT13: + case TEST_OUT_BIT14: + case TEST_IN_BIT14: + case TEST_OUT_BIT15: + case TEST_IN_BIT15: + case TEST_OUT_BIT16: + case TEST_IN_BIT16: + case TEST_OUT_BIT17: + case TEST_IN_BIT17: + case TEST_OUT_BIT18: + case TEST_IN_BIT18: + case TEST_OUT_BIT19: + case TEST_IN_BIT19: + case TEST_OUT_BIT20: + case TEST_IN_BIT20: + case TEST_OUT_BIT21: + case TEST_IN_BIT21: + return ioam6h->overflow || + ioam6h->nodelen || + ioam6h->remlen != 1; + + case TEST_OUT_BIT22: + case TEST_IN_BIT22: + return ioam6h->overflow || + ioam6h->nodelen || + ioam6h->remlen; + + case TEST_OUT_FULL_SUPP_TRACE: + case TEST_IN_FULL_SUPP_TRACE: + case TEST_FWD_FULL_SUPP_TRACE: + return ioam6h->overflow || + ioam6h->nodelen != 15 || + ioam6h->remlen; + + default: + break; + } + + return 1; +} + +static int check_ioam6_data(__u8 **p, struct ioam6_trace_hdr *ioam6h, + const struct ioam_config cnf) +{ + unsigned int len; + __u8 aligned; + __u64 raw64; + __u32 raw32; + + if (ioam6h->type.bit0) { + raw32 = __be32_to_cpu(*((__u32 *)*p)); + if (cnf.hlim != (raw32 >> 24) || cnf.id != (raw32 & 0xffffff)) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit1) { + raw32 = __be32_to_cpu(*((__u32 *)*p)); + if (cnf.ingr_id != (raw32 >> 16) || + cnf.egr_id != (raw32 & 0xffff)) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit2) + *p += sizeof(__u32); + + if (ioam6h->type.bit3) + *p += sizeof(__u32); + + if (ioam6h->type.bit4) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit5) { + if (__be32_to_cpu(*((__u32 *)*p)) != cnf.ns_data) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit6) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit7) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit8) { + raw64 = __be64_to_cpu(*((__u64 *)*p)); + if (cnf.hlim != (raw64 >> 56) || + cnf.wide != (raw64 & 0xffffffffffffff)) + return 1; + *p += sizeof(__u64); + } + + if (ioam6h->type.bit9) { + if (__be32_to_cpu(*((__u32 *)*p)) != cnf.ingr_wide) + return 1; + *p += sizeof(__u32); + + if (__be32_to_cpu(*((__u32 *)*p)) != cnf.egr_wide) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit10) { + if (__be64_to_cpu(*((__u64 *)*p)) != cnf.ns_wide) + return 1; + *p += sizeof(__u64); + } + + if (ioam6h->type.bit11) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit22) { + len = cnf.sc_data ? strlen(cnf.sc_data) : 0; + aligned = cnf.sc_data ? __ALIGN_KERNEL(len, 4) : 0; + + raw32 = __be32_to_cpu(*((__u32 *)*p)); + if (aligned != (raw32 >> 24) * 4 || + cnf.sc_id != (raw32 & 0xffffff)) + return 1; + *p += sizeof(__u32); + + if (cnf.sc_data) { + if (strncmp((char *)*p, cnf.sc_data, len)) + return 1; + + *p += len; + aligned -= len; + + while (aligned--) { + if (**p != '\0') + return 1; + *p += sizeof(__u8); + } + } + } + + return 0; +} + +static int check_ioam_header_and_data(int tid, struct ioam6_trace_hdr *ioam6h, + __u32 trace_type, __u16 ioam_ns) +{ + __u8 *p; + + if (check_ioam_header(tid, ioam6h, trace_type, ioam_ns)) + return 1; + + p = ioam6h->data + ioam6h->remlen * 4; + + switch (tid) { + case TEST_OUT_BIT0: + case TEST_OUT_BIT1: + case TEST_OUT_BIT2: + case TEST_OUT_BIT3: + case TEST_OUT_BIT4: + case TEST_OUT_BIT5: + case TEST_OUT_BIT6: + case TEST_OUT_BIT7: + case TEST_OUT_BIT8: + case TEST_OUT_BIT9: + case TEST_OUT_BIT10: + case TEST_OUT_BIT11: + case TEST_OUT_BIT22: + case TEST_OUT_FULL_SUPP_TRACE: + return check_ioam6_data(&p, ioam6h, node1); + + case TEST_IN_BIT0: + case TEST_IN_BIT1: + case TEST_IN_BIT2: + case TEST_IN_BIT3: + case TEST_IN_BIT4: + case TEST_IN_BIT5: + case TEST_IN_BIT6: + case TEST_IN_BIT7: + case TEST_IN_BIT8: + case TEST_IN_BIT9: + case TEST_IN_BIT10: + case TEST_IN_BIT11: + case TEST_IN_BIT22: + case TEST_IN_FULL_SUPP_TRACE: + { + __u32 tmp32 = node2.egr_wide; + __u16 tmp16 = node2.egr_id; + int res; + + node2.egr_id = 0xffff; + node2.egr_wide = 0xffffffff; + + res = check_ioam6_data(&p, ioam6h, node2); + + node2.egr_id = tmp16; + node2.egr_wide = tmp32; + + return res; + } + + case TEST_FWD_FULL_SUPP_TRACE: + if (check_ioam6_data(&p, ioam6h, node3)) + return 1; + if (check_ioam6_data(&p, ioam6h, node2)) + return 1; + return check_ioam6_data(&p, ioam6h, node1); + + default: + break; + } + + return 1; +} + +static int str2id(const char *tname) +{ + if (!strcmp("out_undef_ns", tname)) + return TEST_OUT_UNDEF_NS; + if (!strcmp("out_no_room", tname)) + return TEST_OUT_NO_ROOM; + if (!strcmp("out_bit0", tname)) + return TEST_OUT_BIT0; + if (!strcmp("out_bit1", tname)) + return TEST_OUT_BIT1; + if (!strcmp("out_bit2", tname)) + return TEST_OUT_BIT2; + if (!strcmp("out_bit3", tname)) + return TEST_OUT_BIT3; + if (!strcmp("out_bit4", tname)) + return TEST_OUT_BIT4; + if (!strcmp("out_bit5", tname)) + return TEST_OUT_BIT5; + if (!strcmp("out_bit6", tname)) + return TEST_OUT_BIT6; + if (!strcmp("out_bit7", tname)) + return TEST_OUT_BIT7; + if (!strcmp("out_bit8", tname)) + return TEST_OUT_BIT8; + if (!strcmp("out_bit9", tname)) + return TEST_OUT_BIT9; + if (!strcmp("out_bit10", tname)) + return TEST_OUT_BIT10; + if (!strcmp("out_bit11", tname)) + return TEST_OUT_BIT11; + if (!strcmp("out_bit12", tname)) + return TEST_OUT_BIT12; + if (!strcmp("out_bit13", tname)) + return TEST_OUT_BIT13; + if (!strcmp("out_bit14", tname)) + return TEST_OUT_BIT14; + if (!strcmp("out_bit15", tname)) + return TEST_OUT_BIT15; + if (!strcmp("out_bit16", tname)) + return TEST_OUT_BIT16; + if (!strcmp("out_bit17", tname)) + return TEST_OUT_BIT17; + if (!strcmp("out_bit18", tname)) + return TEST_OUT_BIT18; + if (!strcmp("out_bit19", tname)) + return TEST_OUT_BIT19; + if (!strcmp("out_bit20", tname)) + return TEST_OUT_BIT20; + if (!strcmp("out_bit21", tname)) + return TEST_OUT_BIT21; + if (!strcmp("out_bit22", tname)) + return TEST_OUT_BIT22; + if (!strcmp("out_full_supp_trace", tname)) + return TEST_OUT_FULL_SUPP_TRACE; + if (!strcmp("in_undef_ns", tname)) + return TEST_IN_UNDEF_NS; + if (!strcmp("in_no_room", tname)) + return TEST_IN_NO_ROOM; + if (!strcmp("in_oflag", tname)) + return TEST_IN_OFLAG; + if (!strcmp("in_bit0", tname)) + return TEST_IN_BIT0; + if (!strcmp("in_bit1", tname)) + return TEST_IN_BIT1; + if (!strcmp("in_bit2", tname)) + return TEST_IN_BIT2; + if (!strcmp("in_bit3", tname)) + return TEST_IN_BIT3; + if (!strcmp("in_bit4", tname)) + return TEST_IN_BIT4; + if (!strcmp("in_bit5", tname)) + return TEST_IN_BIT5; + if (!strcmp("in_bit6", tname)) + return TEST_IN_BIT6; + if (!strcmp("in_bit7", tname)) + return TEST_IN_BIT7; + if (!strcmp("in_bit8", tname)) + return TEST_IN_BIT8; + if (!strcmp("in_bit9", tname)) + return TEST_IN_BIT9; + if (!strcmp("in_bit10", tname)) + return TEST_IN_BIT10; + if (!strcmp("in_bit11", tname)) + return TEST_IN_BIT11; + if (!strcmp("in_bit12", tname)) + return TEST_IN_BIT12; + if (!strcmp("in_bit13", tname)) + return TEST_IN_BIT13; + if (!strcmp("in_bit14", tname)) + return TEST_IN_BIT14; + if (!strcmp("in_bit15", tname)) + return TEST_IN_BIT15; + if (!strcmp("in_bit16", tname)) + return TEST_IN_BIT16; + if (!strcmp("in_bit17", tname)) + return TEST_IN_BIT17; + if (!strcmp("in_bit18", tname)) + return TEST_IN_BIT18; + if (!strcmp("in_bit19", tname)) + return TEST_IN_BIT19; + if (!strcmp("in_bit20", tname)) + return TEST_IN_BIT20; + if (!strcmp("in_bit21", tname)) + return TEST_IN_BIT21; + if (!strcmp("in_bit22", tname)) + return TEST_IN_BIT22; + if (!strcmp("in_full_supp_trace", tname)) + return TEST_IN_FULL_SUPP_TRACE; + if (!strcmp("fwd_full_supp_trace", tname)) + return TEST_FWD_FULL_SUPP_TRACE; + + return -1; +} + +static int ipv6_addr_equal(const struct in6_addr *a1, const struct in6_addr *a2) +{ + return ((a1->s6_addr32[0] ^ a2->s6_addr32[0]) | + (a1->s6_addr32[1] ^ a2->s6_addr32[1]) | + (a1->s6_addr32[2] ^ a2->s6_addr32[2]) | + (a1->s6_addr32[3] ^ a2->s6_addr32[3])) == 0; +} + +static int get_u32(__u32 *val, const char *arg, int base) +{ + unsigned long res; + char *ptr; + + if (!arg || !*arg) + return -1; + res = strtoul(arg, &ptr, base); + + if (!ptr || ptr == arg || *ptr) + return -1; + + if (res == ULONG_MAX && errno == ERANGE) + return -1; + + if (res > 0xFFFFFFFFUL) + return -1; + + *val = res; + return 0; +} + +static int get_u16(__u16 *val, const char *arg, int base) +{ + unsigned long res; + char *ptr; + + if (!arg || !*arg) + return -1; + res = strtoul(arg, &ptr, base); + + if (!ptr || ptr == arg || *ptr) + return -1; + + if (res == ULONG_MAX && errno == ERANGE) + return -1; + + if (res > 0xFFFFUL) + return -1; + + *val = res; + return 0; +} + +static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = { + [TEST_OUT_UNDEF_NS] = check_ioam_header, + [TEST_OUT_NO_ROOM] = check_ioam_header, + [TEST_OUT_BIT0] = check_ioam_header_and_data, + [TEST_OUT_BIT1] = check_ioam_header_and_data, + [TEST_OUT_BIT2] = check_ioam_header_and_data, + [TEST_OUT_BIT3] = check_ioam_header_and_data, + [TEST_OUT_BIT4] = check_ioam_header_and_data, + [TEST_OUT_BIT5] = check_ioam_header_and_data, + [TEST_OUT_BIT6] = check_ioam_header_and_data, + [TEST_OUT_BIT7] = check_ioam_header_and_data, + [TEST_OUT_BIT8] = check_ioam_header_and_data, + [TEST_OUT_BIT9] = check_ioam_header_and_data, + [TEST_OUT_BIT10] = check_ioam_header_and_data, + [TEST_OUT_BIT11] = check_ioam_header_and_data, + [TEST_OUT_BIT12] = check_ioam_header, + [TEST_OUT_BIT13] = check_ioam_header, + [TEST_OUT_BIT14] = check_ioam_header, + [TEST_OUT_BIT15] = check_ioam_header, + [TEST_OUT_BIT16] = check_ioam_header, + [TEST_OUT_BIT17] = check_ioam_header, + [TEST_OUT_BIT18] = check_ioam_header, + [TEST_OUT_BIT19] = check_ioam_header, + [TEST_OUT_BIT20] = check_ioam_header, + [TEST_OUT_BIT21] = check_ioam_header, + [TEST_OUT_BIT22] = check_ioam_header_and_data, + [TEST_OUT_FULL_SUPP_TRACE] = check_ioam_header_and_data, + [TEST_IN_UNDEF_NS] = check_ioam_header, + [TEST_IN_NO_ROOM] = check_ioam_header, + [TEST_IN_OFLAG] = check_ioam_header, + [TEST_IN_BIT0] = check_ioam_header_and_data, + [TEST_IN_BIT1] = check_ioam_header_and_data, + [TEST_IN_BIT2] = check_ioam_header_and_data, + [TEST_IN_BIT3] = check_ioam_header_and_data, + [TEST_IN_BIT4] = check_ioam_header_and_data, + [TEST_IN_BIT5] = check_ioam_header_and_data, + [TEST_IN_BIT6] = check_ioam_header_and_data, + [TEST_IN_BIT7] = check_ioam_header_and_data, + [TEST_IN_BIT8] = check_ioam_header_and_data, + [TEST_IN_BIT9] = check_ioam_header_and_data, + [TEST_IN_BIT10] = check_ioam_header_and_data, + [TEST_IN_BIT11] = check_ioam_header_and_data, + [TEST_IN_BIT12] = check_ioam_header, + [TEST_IN_BIT13] = check_ioam_header, + [TEST_IN_BIT14] = check_ioam_header, + [TEST_IN_BIT15] = check_ioam_header, + [TEST_IN_BIT16] = check_ioam_header, + [TEST_IN_BIT17] = check_ioam_header, + [TEST_IN_BIT18] = check_ioam_header, + [TEST_IN_BIT19] = check_ioam_header, + [TEST_IN_BIT20] = check_ioam_header, + [TEST_IN_BIT21] = check_ioam_header, + [TEST_IN_BIT22] = check_ioam_header_and_data, + [TEST_IN_FULL_SUPP_TRACE] = check_ioam_header_and_data, + [TEST_FWD_FULL_SUPP_TRACE] = check_ioam_header_and_data, +}; + +int main(int argc, char **argv) +{ + int fd, size, hoplen, tid, ret = 1; + struct in6_addr src, dst; + struct ioam6_hdr *opt; + struct ipv6hdr *ip6h; + __u8 buffer[400], *p; + __u16 ioam_ns; + __u32 tr_type; + + if (argc != 7) + goto out; + + tid = str2id(argv[2]); + if (tid < 0 || !func[tid]) + goto out; + + if (inet_pton(AF_INET6, argv[3], &src) != 1 || + inet_pton(AF_INET6, argv[4], &dst) != 1) + goto out; + + if (get_u32(&tr_type, argv[5], 16) || + get_u16(&ioam_ns, argv[6], 0)) + goto out; + + fd = socket(AF_PACKET, SOCK_DGRAM, __cpu_to_be16(ETH_P_IPV6)); + if (!fd) + goto out; + + if (setsockopt(fd, SOL_SOCKET, SO_BINDTODEVICE, + argv[1], strlen(argv[1]))) + goto close; + +recv: + size = recv(fd, buffer, sizeof(buffer), 0); + if (size <= 0) + goto close; + + ip6h = (struct ipv6hdr *)buffer; + + if (!ipv6_addr_equal(&ip6h->saddr, &src) || + !ipv6_addr_equal(&ip6h->daddr, &dst)) + goto recv; + + if (ip6h->nexthdr != IPPROTO_HOPOPTS) + goto close; + + p = buffer + sizeof(*ip6h); + hoplen = (p[1] + 1) << 3; + p += sizeof(struct ipv6_hopopt_hdr); + + while (hoplen > 0) { + opt = (struct ioam6_hdr *)p; + + if (opt->opt_type == IPV6_TLV_IOAM && + opt->type == IOAM6_TYPE_PREALLOC) { + p += sizeof(*opt); + ret = func[tid](tid, (struct ioam6_trace_hdr *)p, + tr_type, ioam_ns); + break; + } + + p += opt->opt_len + 2; + hoplen -= opt->opt_len + 2; + } +close: + close(fd); +out: + return ret; +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index f02f4de2f3a0..255793c5ac4f 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3,8 +3,10 @@ ret=0 sin="" +sinfail="" sout="" cin="" +cinfail="" cinsent="" cout="" ksft_skip=4 @@ -76,6 +78,14 @@ init() done } +init_shapers() +{ + 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 "$capout" @@ -88,8 +98,8 @@ cleanup_partial() cleanup() { - rm -f "$cin" "$cout" - rm -f "$sin" "$sout" "$cinsent" + rm -f "$cin" "$cout" "$sinfail" + rm -f "$sin" "$sout" "$cinsent" "$cinfail" cleanup_partial } @@ -211,11 +221,15 @@ link_failure() { ns="$1" - l=$((RANDOM%4)) - l=$((l+1)) + if [ -z "$FAILING_LINKS" ]; then + l=$((RANDOM%4)) + FAILING_LINKS=$((l+1)) + fi - veth="ns1eth$l" - ip -net "$ns" link set "$veth" down + for l in $FAILING_LINKS; do + veth="ns1eth$l" + ip -net "$ns" link set "$veth" down + done } # $1: IP address @@ -280,10 +294,17 @@ do_transfer() local_addr="0.0.0.0" fi - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - ${local_addr} < "$sin" > "$sout" & + if [ "$test_link_fail" -eq 2 ];then + timeout ${timeout_test} \ + ip netns exec ${listener_ns} \ + $mptcp_connect -t ${timeout_poll} -l -p $port -s ${cl_proto} \ + ${local_addr} < "$sinfail" > "$sout" & + else + timeout ${timeout_test} \ + ip netns exec ${listener_ns} \ + $mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ + ${local_addr} < "$sin" > "$sout" & + fi spid=$! sleep 1 @@ -294,7 +315,7 @@ do_transfer() $mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ $connect_addr < "$cin" > "$cout" & else - ( cat "$cin" ; sleep 2; link_failure $listener_ns ; cat "$cin" ) | \ + ( cat "$cinfail" ; sleep 2; link_failure $listener_ns ; cat "$cinfail" ) | \ tee "$cinsent" | \ timeout ${timeout_test} \ ip netns exec ${connector_ns} \ @@ -323,17 +344,18 @@ do_transfer() let rm_nr_ns1=-addr_nr_ns1 if [ $rm_nr_ns1 -lt 8 ]; then counter=1 + pos=1 dump=(`ip netns exec ${listener_ns} ./pm_nl_ctl dump`) if [ ${#dump[@]} -gt 0 ]; then - id=${dump[1]} sleep 1 while [ $counter -le $rm_nr_ns1 ] do + id=${dump[$pos]} ip netns exec ${listener_ns} ./pm_nl_ctl del $id sleep 1 let counter+=1 - let id+=1 + let pos+=5 done fi elif [ $rm_nr_ns1 -eq 8 ]; then @@ -345,6 +367,12 @@ do_transfer() fi fi + flags="subflow" + if [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then + flags="${flags},fullmesh" + addr_nr_ns2=${addr_nr_ns2:9} + fi + if [ $addr_nr_ns2 -gt 0 ]; then let add_nr_ns2=addr_nr_ns2 counter=3 @@ -356,7 +384,7 @@ do_transfer() else addr="10.0.$counter.2" fi - ip netns exec $ns2 ./pm_nl_ctl add $addr flags subflow + ip netns exec $ns2 ./pm_nl_ctl add $addr flags $flags let counter+=1 let add_nr_ns2-=1 done @@ -365,17 +393,18 @@ do_transfer() let rm_nr_ns2=-addr_nr_ns2 if [ $rm_nr_ns2 -lt 8 ]; then counter=1 + pos=1 dump=(`ip netns exec ${connector_ns} ./pm_nl_ctl dump`) if [ ${#dump[@]} -gt 0 ]; then - id=${dump[1]} sleep 1 while [ $counter -le $rm_nr_ns2 ] do + id=${dump[$pos]} ip netns exec ${connector_ns} ./pm_nl_ctl del $id sleep 1 let counter+=1 - let id+=1 + let pos+=5 done fi elif [ $rm_nr_ns2 -eq 8 ]; then @@ -434,7 +463,11 @@ do_transfer() return 1 fi - check_transfer $sin $cout "file received by client" + if [ "$test_link_fail" -eq 2 ];then + check_transfer $sinfail $cout "file received by client" + else + check_transfer $sin $cout "file received by client" + fi retc=$? if [ "$test_link_fail" -eq 0 ];then check_transfer $cin $sout "file received by server" @@ -477,29 +510,33 @@ run_tests() lret=0 oldin="" - if [ "$test_linkfail" -eq 1 ];then - size=$((RANDOM%1024)) + # create the input file for the failure test when + # the first failure test run + if [ "$test_linkfail" -ne 0 -a -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*128)) + size=$((size*8192)) + size=$((size + ( $RANDOM % 8192) )) - oldin=$(mktemp) - cp "$cin" "$oldin" - make_file "$cin" "client" $size + cinfail=$(mktemp) + make_file "$cinfail" "client" $size fi - do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \ - ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${bkup} - lret=$? + if [ "$test_linkfail" -eq 2 -a -z "$sinfail" ]; then + size=$((RANDOM%16)) + size=$((size+1)) + size=$((size*2048)) - if [ "$test_linkfail" -eq 1 ];then - cp "$oldin" "$cin" - rm -f "$oldin" + sinfail=$(mktemp) + make_file "$sinfail" "server" $size fi - if [ $lret -ne 0 ]; then - ret=$lret - return - fi + do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \ + ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${bkup} + lret=$? } chk_csum_nr() @@ -541,6 +578,43 @@ chk_csum_nr() fi } +chk_fail_nr() +{ + local mp_fail_nr_tx=$1 + local mp_fail_nr_rx=$2 + local count + local dump_stats + + printf "%-39s %s" " " "ftx" + count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPFailTx | awk '{print $2}'` + [ -z "$count" ] && count=0 + if [ "$count" != "$mp_fail_nr_tx" ]; then + echo "[fail] got $count MP_FAIL[s] TX expected $mp_fail_nr_tx" + ret=1 + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - frx " + count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPFailRx | awk '{print $2}'` + [ -z "$count" ] && count=0 + if [ "$count" != "$mp_fail_nr_rx" ]; then + echo "[fail] got $count MP_FAIL[s] RX expected $mp_fail_nr_rx" + ret=1 + dump_stats=1 + else + echo "[ ok ]" + fi + + if [ "${dump_stats}" = 1 ]; then + echo Server ns stats + ip netns exec $ns1 nstat -as | grep MPTcp + echo Client ns stats + ip netns exec $ns2 nstat -as | grep MPTcp + fi +} + chk_join_nr() { local msg="$1" @@ -590,6 +664,47 @@ chk_join_nr() fi if [ $checksum -eq 1 ]; then chk_csum_nr + chk_fail_nr 0 0 + 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 "%-39s %-18s" " " "stale" + stale_nr=`ip netns exec $ns nstat -as | grep MPTcpExtSubflowStale | awk '{print $2}'` + [ -z "$stale_nr" ] && stale_nr=0 + recover_nr=`ip netns exec $ns nstat -as | grep MPTcpExtSubflowRecover | awk '{print $2}'` + [ -z "$recover_nr" ] && recover_nr=0 + + if [ $stale_nr -lt $stale_min ] || + [ $stale_max -gt 0 -a $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 $stale_delta " + ret=1 + dump_stats=1 + else + echo "[ ok ]" + fi + + if [ "${dump_stats}" = 1 ]; then + echo $ns stats + ip netns exec $ns ip -s link show + ip netns exec $ns nstat -as | grep MPTcp fi } @@ -801,6 +916,27 @@ chk_prio_nr() fi } +chk_link_usage() +{ + local ns=$1 + local link=$2 + local out=$3 + local expected_rate=$4 + local tx_link=`ip netns exec $ns cat /sys/class/net/$link/statistics/tx_bytes` + local tx_total=`ls -l $out | awk '{print $5}'` + local tx_rate=$((tx_link * 100 / $tx_total)) + local tolerance=5 + + printf "%-39s %-18s" " " "link usage" + if [ $tx_rate -lt $((expected_rate - $tolerance)) -o \ + $tx_rate -gt $((expected_rate + $tolerance)) ]; then + echo "[fail] got $tx_rate% usage, expected $expected_rate%" + ret=1 + else + echo "[ ok ]" + fi +} + subflows_tests() { reset @@ -918,20 +1054,101 @@ signal_address_tests() run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal invalid addresses" 1 1 1 chk_add_nr 3 3 + + # signal addresses race test + reset + ip netns exec $ns1 ./pm_nl_ctl limits 4 4 + ip netns exec $ns2 ./pm_nl_ctl limits 4 4 + ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 flags signal + ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal + ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal + ip netns exec $ns2 ./pm_nl_ctl add 10.0.1.2 flags signal + ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags signal + ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags signal + ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_add_nr 4 4 } link_failure_tests() { # accept and use add_addr with additional subflows and link loss reset + + # 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 ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow + ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow + ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 dev ns2eth4 flags subflow run_tests $ns1 $ns2 10.0.1.1 1 chk_join_nr "multiple flows, signal, link failure" 3 3 3 chk_add_nr 1 1 + chk_stale_nr $ns2 1 5 1 + + # accept and use add_addr with additional subflows and link loss + # for bidirectional transfer + reset + init_shapers + ip netns exec $ns1 ./pm_nl_ctl limits 0 3 + ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal + ip netns exec $ns2 ./pm_nl_ctl limits 1 3 + ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow + ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 dev ns2eth4 flags subflow + run_tests $ns1 $ns2 10.0.1.1 2 + chk_join_nr "multi flows, signal, bidi, link fail" 3 3 3 + chk_add_nr 1 1 + chk_stale_nr $ns2 1 -1 1 + + # 2 subflows plus 1 backup subflow with a lossy link, backup + # will never be used + reset + init_shapers + ip netns exec $ns1 ./pm_nl_ctl limits 0 2 + ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal + ip netns exec $ns2 ./pm_nl_ctl limits 1 2 + export FAILING_LINKS="1" + ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow,backup + run_tests $ns1 $ns2 10.0.1.1 1 + chk_join_nr "backup subflow unused, link failure" 2 2 2 + chk_add_nr 1 1 + chk_link_usage $ns2 ns2eth3 $cinsent 0 + + # 2 lossy links after half transfer, backup will get half of + # the traffic + reset + init_shapers + ip netns exec $ns1 ./pm_nl_ctl limits 0 2 + ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal + ip netns exec $ns2 ./pm_nl_ctl limits 1 2 + ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow,backup + export FAILING_LINKS="1 2" + run_tests $ns1 $ns2 10.0.1.1 1 + chk_join_nr "backup flow used, multi links fail" 2 2 2 + chk_add_nr 1 1 + chk_stale_nr $ns2 2 4 2 + chk_link_usage $ns2 ns2eth3 $cinsent 50 + + # use a backup subflow with the first subflow on a lossy link + # for bidirectional transfer + reset + init_shapers + ip netns exec $ns1 ./pm_nl_ctl limits 0 2 + ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal + ip netns exec $ns2 ./pm_nl_ctl limits 1 3 + ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow,backup + run_tests $ns1 $ns2 10.0.1.1 2 + chk_join_nr "backup flow used, bidi, link failure" 2 2 2 + chk_add_nr 1 1 + chk_stale_nr $ns2 1 -1 2 + chk_link_usage $ns2 ns2eth3 $cinsent 50 } add_addr_timeout_tests() @@ -1530,6 +1747,55 @@ deny_join_id0_tests() chk_join_nr "subflow and address allow join id0 2" 1 1 1 } +fullmesh_tests() +{ + # fullmesh 1 + # 2 fullmesh addrs in ns2, added before the connection, + # 1 non-fullmesh addr in ns1, added during the connection. + reset + ip netns exec $ns1 ./pm_nl_ctl limits 0 4 + ip netns exec $ns2 ./pm_nl_ctl limits 1 4 + ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow,fullmesh + ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow,fullmesh + run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow + chk_join_nr "fullmesh test 2x1" 4 4 4 + chk_add_nr 1 1 + + # fullmesh 2 + # 1 non-fullmesh addr in ns1, added before the connection, + # 1 fullmesh addr in ns2, added during the connection. + reset + ip netns exec $ns1 ./pm_nl_ctl limits 1 3 + ip netns exec $ns2 ./pm_nl_ctl limits 1 3 + ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow + chk_join_nr "fullmesh test 1x1" 3 3 3 + chk_add_nr 1 1 + + # fullmesh 3 + # 1 non-fullmesh addr in ns1, added before the connection, + # 2 fullmesh addrs in ns2, added during the connection. + reset + ip netns exec $ns1 ./pm_nl_ctl limits 2 5 + ip netns exec $ns2 ./pm_nl_ctl limits 1 5 + ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow + chk_join_nr "fullmesh test 1x2" 5 5 5 + chk_add_nr 1 1 + + # 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. + reset + ip netns exec $ns1 ./pm_nl_ctl limits 2 4 + ip netns exec $ns2 ./pm_nl_ctl limits 1 4 + ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow + chk_join_nr "fullmesh test 1x2, limited" 4 4 4 + chk_add_nr 1 1 +} + all_tests() { subflows_tests @@ -1545,6 +1811,7 @@ all_tests() syncookies_tests checksum_tests deny_join_id0_tests + fullmesh_tests } usage() @@ -1563,6 +1830,7 @@ usage() echo " -k syncookies_tests" echo " -S checksum_tests" echo " -d deny_join_id0_tests" + echo " -m fullmesh_tests" echo " -c capture pcap files" echo " -C enable data checksum" echo " -h help" @@ -1598,7 +1866,7 @@ if [ $do_all_tests -eq 1 ]; then exit $ret fi -while getopts 'fsltra64bpkdchCS' opt; do +while getopts 'fsltra64bpkdmchCS' opt; do case $opt in f) subflows_tests @@ -1639,6 +1907,9 @@ while getopts 'fsltra64bpkdchCS' opt; do d) deny_join_id0_tests ;; + m) + fullmesh_tests + ;; c) ;; C) diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index 115decfdc1ef..354784512748 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -25,7 +25,7 @@ static void syntax(char *argv[]) { fprintf(stderr, "%s add|get|set|del|flush|dump|accept [<args>]\n", argv[0]); - fprintf(stderr, "\tadd [flags signal|subflow|backup] [id <nr>] [dev <name>] <ip>\n"); + fprintf(stderr, "\tadd [flags signal|subflow|backup|fullmesh] [id <nr>] [dev <name>] <ip>\n"); fprintf(stderr, "\tdel <id> [<ip>]\n"); fprintf(stderr, "\tget <id>\n"); fprintf(stderr, "\tset <ip> [flags backup|nobackup]\n"); @@ -236,11 +236,18 @@ int add_addr(int fd, int pm_family, int argc, char *argv[]) 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); @@ -422,6 +429,13 @@ static void print_addr(struct rtattr *attrs, int len) printf(","); } + if (flags & MPTCP_PM_ADDR_FLAG_FULLMESH) { + printf("fullmesh"); + flags &= ~MPTCP_PM_ADDR_FLAG_FULLMESH; + if (flags) + printf(","); + } + /* bump unknown flags, if any */ if (flags) printf("0x%x", flags); diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index fd63ebfe9a2b..910d8126af8f 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -22,8 +22,8 @@ usage() { cleanup() { - rm -f "$cin" "$cout" - rm -f "$sin" "$sout" + rm -f "$cout" "$sout" + rm -f "$large" "$small" rm -f "$capout" local netns diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index db4521335722..3653d6468c67 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -111,8 +111,8 @@ static int sock_fanout_open(uint16_t typeflags, uint16_t group_id) static void sock_fanout_set_cbpf(int fd) { struct sock_filter bpf_filter[] = { - BPF_STMT(BPF_LD+BPF_B+BPF_ABS, 80), /* ldb [80] */ - BPF_STMT(BPF_RET+BPF_A, 0), /* ret A */ + BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 80), /* ldb [80] */ + BPF_STMT(BPF_RET | BPF_A, 0), /* ret A */ }; struct sock_fprog bpf_prog; diff --git a/tools/testing/selftests/net/psock_snd.sh b/tools/testing/selftests/net/psock_snd.sh index 170be65e0816..1cbfeb5052ec 100755 --- a/tools/testing/selftests/net/psock_snd.sh +++ b/tools/testing/selftests/net/psock_snd.sh @@ -86,9 +86,6 @@ echo "raw truncate hlen - 1 (expected to fail: EINVAL)" echo "raw gso min size" ./in_netns.sh ./psock_snd -v -c -g -l "${mss_exceeds}" -echo "raw gso min size - 1 (expected to fail)" -(! ./in_netns.sh ./psock_snd -v -c -g -l "${mss}") - echo "raw gso max size" ./in_netns.sh ./psock_snd -v -c -g -l "${max_mss}" diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests index 8b42e8b04e0f..a59cb6a3c4f5 100755 --- a/tools/testing/selftests/net/run_afpackettests +++ b/tools/testing/selftests/net/run_afpackettests @@ -1,9 +1,12 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + if [ $(id -u) != 0 ]; then echo $msg must be run as root >&2 - exit 0 + exit $ksft_skip fi ret=0 diff --git a/tools/testing/selftests/net/setup_loopback.sh b/tools/testing/selftests/net/setup_loopback.sh new file mode 100755 index 000000000000..e57bbfbc5208 --- /dev/null +++ b/tools/testing/selftests/net/setup_loopback.sh @@ -0,0 +1,118 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +readonly FLUSH_PATH="/sys/class/net/${dev}/gro_flush_timeout" +readonly IRQ_PATH="/sys/class/net/${dev}/napi_defer_hard_irqs" +readonly FLUSH_TIMEOUT="$(< ${FLUSH_PATH})" +readonly HARD_IRQS="$(< ${IRQ_PATH})" + +netdev_check_for_carrier() { + local -r dev="$1" + + for i in {1..5}; do + carrier="$(cat /sys/class/net/${dev}/carrier)" + if [[ "${carrier}" -ne 1 ]] ; then + echo "carrier not ready yet..." >&2 + sleep 1 + else + echo "carrier ready" >&2 + break + fi + done + echo "${carrier}" +} + +# Assumes that there is no existing ipvlan device on the physical device +setup_loopback_environment() { + local dev="$1" + + # Fail hard if cannot turn on loopback mode for current NIC + ethtool -K "${dev}" loopback on || exit 1 + sleep 1 + + # Check for the carrier + carrier=$(netdev_check_for_carrier ${dev}) + if [[ "${carrier}" -ne 1 ]] ; then + echo "setup_loopback_environment failed" + exit 1 + fi +} + +setup_macvlan_ns(){ + local -r link_dev="$1" + local -r ns_name="$2" + local -r ns_dev="$3" + local -r ns_mac="$4" + local -r addr="$5" + + ip link add link "${link_dev}" dev "${ns_dev}" \ + address "${ns_mac}" type macvlan + exit_code=$? + if [[ "${exit_code}" -ne 0 ]]; then + echo "setup_macvlan_ns failed" + exit $exit_code + fi + + [[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}" + ip link set dev "${ns_dev}" netns "${ns_name}" + ip -netns "${ns_name}" link set dev "${ns_dev}" up + if [[ -n "${addr}" ]]; then + ip -netns "${ns_name}" addr add dev "${ns_dev}" "${addr}" + fi + + sleep 1 +} + +cleanup_macvlan_ns(){ + while (( $# >= 2 )); do + ns_name="$1" + ns_dev="$2" + ip -netns "${ns_name}" link del dev "${ns_dev}" + ip netns del "${ns_name}" + shift 2 + done +} + +cleanup_loopback(){ + local -r dev="$1" + + ethtool -K "${dev}" loopback off + sleep 1 + + # Check for the carrier + carrier=$(netdev_check_for_carrier ${dev}) + if [[ "${carrier}" -ne 1 ]] ; then + echo "setup_loopback_environment failed" + exit 1 + fi +} + +setup_interrupt() { + # Use timer on host to trigger the network stack + # Also disable device interrupt to not depend on NIC interrupt + # Reduce test flakiness caused by unexpected interrupts + echo 100000 >"${FLUSH_PATH}" + echo 50 >"${IRQ_PATH}" +} + +setup_ns() { + # Set up server_ns namespace and client_ns namespace + setup_macvlan_ns "${dev}" server_ns server "${SERVER_MAC}" + setup_macvlan_ns "${dev}" client_ns client "${CLIENT_MAC}" +} + +cleanup_ns() { + cleanup_macvlan_ns server_ns server client_ns client +} + +setup() { + setup_loopback_environment "${dev}" + setup_interrupt +} + +cleanup() { + cleanup_loopback "${dev}" + + echo "${FLUSH_TIMEOUT}" >"${FLUSH_PATH}" + echo "${HARD_IRQS}" >"${IRQ_PATH}" +} diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh new file mode 100644 index 000000000000..1003ddf7b3b2 --- /dev/null +++ b/tools/testing/selftests/net/setup_veth.sh @@ -0,0 +1,41 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +setup_veth_ns() { + local -r link_dev="$1" + local -r ns_name="$2" + local -r ns_dev="$3" + local -r ns_mac="$4" + + [[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}" + echo 100000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" + ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535 + ip -netns "${ns_name}" link set dev "${ns_dev}" up + + ip netns exec "${ns_name}" ethtool -K "${ns_dev}" gro on tso off +} + +setup_ns() { + # Set up server_ns namespace and client_ns namespace + ip link add name server type veth peer name client + + setup_veth_ns "${dev}" server_ns server "${SERVER_MAC}" + setup_veth_ns "${dev}" client_ns client "${CLIENT_MAC}" +} + +cleanup_ns() { + local ns_name + + for ns_name in client_ns server_ns; do + [[ -e /var/run/netns/"${ns_name}" ]] && ip netns del "${ns_name}" + done +} + +setup() { + # no global init setup step needed + : +} + +cleanup() { + cleanup_ns +} diff --git a/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh index 75ada17ac061..aebaab8ce44c 100755 --- a/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh @@ -193,6 +193,9 @@ # +---------------------------------------------------+ # +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + readonly LOCALSID_TABLE_ID=90 readonly IPv6_RT_NETWORK=fd00 readonly IPv6_HS_NETWORK=cafe @@ -543,18 +546,18 @@ host_vpn_isolation_tests() if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" - exit 0 + exit $ksft_skip fi if [ ! -x "$(command -v ip)" ]; then echo "SKIP: Could not run test without ip tool" - exit 0 + exit $ksft_skip fi modprobe vrf &>/dev/null if [ ! -e /proc/sys/net/vrf/strict_mode ]; then echo "SKIP: vrf sysctl does not exist" - exit 0 + exit $ksft_skip fi cleanup &>/dev/null diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh index ad7a9fc59934..1003119773e5 100755 --- a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh @@ -163,6 +163,9 @@ # +---------------------------------------------------+ # +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + readonly LOCALSID_TABLE_ID=90 readonly IPv6_RT_NETWORK=fd00 readonly IPv4_HS_NETWORK=10.0.0 @@ -464,18 +467,18 @@ host_vpn_isolation_tests() if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" - exit 0 + exit $ksft_skip fi if [ ! -x "$(command -v ip)" ]; then echo "SKIP: Could not run test without ip tool" - exit 0 + exit $ksft_skip fi modprobe vrf &>/dev/null if [ ! -e /proc/sys/net/vrf/strict_mode ]; then echo "SKIP: vrf sysctl does not exist" - exit 0 + exit $ksft_skip fi cleanup &>/dev/null diff --git a/tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh index 68708f5e26a0..b9b06ef80d88 100755 --- a/tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh @@ -164,6 +164,9 @@ # +---------------------------------------------------+ # +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + readonly LOCALSID_TABLE_ID=90 readonly IPv6_RT_NETWORK=fd00 readonly IPv6_HS_NETWORK=cafe @@ -472,18 +475,18 @@ host_vpn_isolation_tests() if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" - exit 0 + exit $ksft_skip fi if [ ! -x "$(command -v ip)" ]; then echo "SKIP: Could not run test without ip tool" - exit 0 + exit $ksft_skip fi modprobe vrf &>/dev/null if [ ! -e /proc/sys/net/vrf/strict_mode ]; then echo "SKIP: vrf sysctl does not exist" - exit 0 + exit $ksft_skip fi cleanup &>/dev/null diff --git a/tools/testing/selftests/net/toeplitz.c b/tools/testing/selftests/net/toeplitz.c new file mode 100644 index 000000000000..710ac956bdb3 --- /dev/null +++ b/tools/testing/selftests/net/toeplitz.c @@ -0,0 +1,585 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Toeplitz test + * + * 1. Read packets and their rx_hash using PF_PACKET/TPACKET_V3 + * 2. Compute the rx_hash in software based on the packet contents + * 3. Compare the two + * + * Optionally, either '-C $rx_irq_cpu_list' or '-r $rps_bitmap' may be given. + * + * If '-C $rx_irq_cpu_list' is given, also + * + * 4. Identify the cpu on which the packet arrived with PACKET_FANOUT_CPU + * 5. Compute the rxqueue that RSS would select based on this rx_hash + * 6. Using the $rx_irq_cpu_list map, identify the arriving cpu based on rxq irq + * 7. Compare the cpus from 4 and 6 + * + * Else if '-r $rps_bitmap' is given, also + * + * 4. Identify the cpu on which the packet arrived with PACKET_FANOUT_CPU + * 5. Compute the cpu that RPS should select based on rx_hash and $rps_bitmap + * 6. Compare the cpus from 4 and 5 + */ + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <errno.h> +#include <error.h> +#include <fcntl.h> +#include <getopt.h> +#include <linux/filter.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <net/if.h> +#include <netdb.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/tcp.h> +#include <netinet/udp.h> +#include <poll.h> +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/sysinfo.h> +#include <sys/time.h> +#include <sys/types.h> +#include <unistd.h> + +#define TOEPLITZ_KEY_MIN_LEN 40 +#define TOEPLITZ_KEY_MAX_LEN 60 + +#define TOEPLITZ_STR_LEN(K) (((K) * 3) - 1) /* hex encoded: AA:BB:CC:...:ZZ */ +#define TOEPLITZ_STR_MIN_LEN TOEPLITZ_STR_LEN(TOEPLITZ_KEY_MIN_LEN) +#define TOEPLITZ_STR_MAX_LEN TOEPLITZ_STR_LEN(TOEPLITZ_KEY_MAX_LEN) + +#define FOUR_TUPLE_MAX_LEN ((sizeof(struct in6_addr) * 2) + (sizeof(uint16_t) * 2)) + +#define RSS_MAX_CPUS (1 << 16) /* real constraint is PACKET_FANOUT_MAX */ + +#define RPS_MAX_CPUS 16UL /* must be a power of 2 */ + +/* configuration options (cmdline arguments) */ +static uint16_t cfg_dport = 8000; +static int cfg_family = AF_INET6; +static char *cfg_ifname = "eth0"; +static int cfg_num_queues; +static int cfg_num_rps_cpus; +static bool cfg_sink; +static int cfg_type = SOCK_STREAM; +static int cfg_timeout_msec = 1000; +static bool cfg_verbose; + +/* global vars */ +static int num_cpus; +static int ring_block_nr; +static int ring_block_sz; + +/* stats */ +static int frames_received; +static int frames_nohash; +static int frames_error; + +#define log_verbose(args...) do { if (cfg_verbose) fprintf(stderr, args); } while (0) + +/* tpacket ring */ +struct ring_state { + int fd; + char *mmap; + int idx; + int cpu; +}; + +static unsigned int rx_irq_cpus[RSS_MAX_CPUS]; /* map from rxq to cpu */ +static int rps_silo_to_cpu[RPS_MAX_CPUS]; +static unsigned char toeplitz_key[TOEPLITZ_KEY_MAX_LEN]; +static struct ring_state rings[RSS_MAX_CPUS]; + +static inline uint32_t toeplitz(const unsigned char *four_tuple, + const unsigned char *key) +{ + int i, bit, ret = 0; + uint32_t key32; + + key32 = ntohl(*((uint32_t *)key)); + key += 4; + + for (i = 0; i < FOUR_TUPLE_MAX_LEN; i++) { + for (bit = 7; bit >= 0; bit--) { + if (four_tuple[i] & (1 << bit)) + ret ^= key32; + + key32 <<= 1; + key32 |= !!(key[0] & (1 << bit)); + } + key++; + } + + return ret; +} + +/* Compare computed cpu with arrival cpu from packet_fanout_cpu */ +static void verify_rss(uint32_t rx_hash, int cpu) +{ + int queue = rx_hash % cfg_num_queues; + + log_verbose(" rxq %d (cpu %d)", queue, rx_irq_cpus[queue]); + if (rx_irq_cpus[queue] != cpu) { + log_verbose(". error: rss cpu mismatch (%d)", cpu); + frames_error++; + } +} + +static void verify_rps(uint64_t rx_hash, int cpu) +{ + int silo = (rx_hash * cfg_num_rps_cpus) >> 32; + + log_verbose(" silo %d (cpu %d)", silo, rps_silo_to_cpu[silo]); + if (rps_silo_to_cpu[silo] != cpu) { + log_verbose(". error: rps cpu mismatch (%d)", cpu); + frames_error++; + } +} + +static void log_rxhash(int cpu, uint32_t rx_hash, + const char *addrs, int addr_len) +{ + char saddr[INET6_ADDRSTRLEN], daddr[INET6_ADDRSTRLEN]; + uint16_t *ports; + + if (!inet_ntop(cfg_family, addrs, saddr, sizeof(saddr)) || + !inet_ntop(cfg_family, addrs + addr_len, daddr, sizeof(daddr))) + error(1, 0, "address parse error"); + + ports = (void *)addrs + (addr_len * 2); + log_verbose("cpu %d: rx_hash 0x%08x [saddr %s daddr %s sport %02hu dport %02hu]", + cpu, rx_hash, saddr, daddr, + ntohs(ports[0]), ntohs(ports[1])); +} + +/* Compare computed rxhash with rxhash received from tpacket_v3 */ +static void verify_rxhash(const char *pkt, uint32_t rx_hash, int cpu) +{ + unsigned char four_tuple[FOUR_TUPLE_MAX_LEN] = {0}; + uint32_t rx_hash_sw; + const char *addrs; + int addr_len; + + if (cfg_family == AF_INET) { + addr_len = sizeof(struct in_addr); + addrs = pkt + offsetof(struct iphdr, saddr); + } else { + addr_len = sizeof(struct in6_addr); + addrs = pkt + offsetof(struct ip6_hdr, ip6_src); + } + + memcpy(four_tuple, addrs, (addr_len * 2) + (sizeof(uint16_t) * 2)); + rx_hash_sw = toeplitz(four_tuple, toeplitz_key); + + if (cfg_verbose) + log_rxhash(cpu, rx_hash, addrs, addr_len); + + if (rx_hash != rx_hash_sw) { + log_verbose(" != expected 0x%x\n", rx_hash_sw); + frames_error++; + return; + } + + log_verbose(" OK"); + if (cfg_num_queues) + verify_rss(rx_hash, cpu); + else if (cfg_num_rps_cpus) + verify_rps(rx_hash, cpu); + log_verbose("\n"); +} + +static char *recv_frame(const struct ring_state *ring, char *frame) +{ + struct tpacket3_hdr *hdr = (void *)frame; + + if (hdr->hv1.tp_rxhash) + verify_rxhash(frame + hdr->tp_net, hdr->hv1.tp_rxhash, + ring->cpu); + else + frames_nohash++; + + return frame + hdr->tp_next_offset; +} + +/* A single TPACKET_V3 block can hold multiple frames */ +static void recv_block(struct ring_state *ring) +{ + struct tpacket_block_desc *block; + char *frame; + int i; + + block = (void *)(ring->mmap + ring->idx * ring_block_sz); + if (!(block->hdr.bh1.block_status & TP_STATUS_USER)) + return; + + frame = (char *)block; + frame += block->hdr.bh1.offset_to_first_pkt; + + for (i = 0; i < block->hdr.bh1.num_pkts; i++) { + frame = recv_frame(ring, frame); + frames_received++; + } + + block->hdr.bh1.block_status = TP_STATUS_KERNEL; + ring->idx = (ring->idx + 1) % ring_block_nr; +} + +/* simple test: sleep once unconditionally and then process all rings */ +static void process_rings(void) +{ + int i; + + usleep(1000 * cfg_timeout_msec); + + for (i = 0; i < num_cpus; i++) + recv_block(&rings[i]); + + fprintf(stderr, "count: pass=%u nohash=%u fail=%u\n", + frames_received - frames_nohash - frames_error, + frames_nohash, frames_error); +} + +static char *setup_ring(int fd) +{ + struct tpacket_req3 req3 = {0}; + void *ring; + + req3.tp_retire_blk_tov = cfg_timeout_msec; + req3.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH; + + req3.tp_frame_size = 2048; + req3.tp_frame_nr = 1 << 10; + req3.tp_block_nr = 2; + + req3.tp_block_size = req3.tp_frame_size * req3.tp_frame_nr; + req3.tp_block_size /= req3.tp_block_nr; + + if (setsockopt(fd, SOL_PACKET, PACKET_RX_RING, &req3, sizeof(req3))) + error(1, errno, "setsockopt PACKET_RX_RING"); + + ring_block_sz = req3.tp_block_size; + ring_block_nr = req3.tp_block_nr; + + ring = mmap(0, req3.tp_block_size * req3.tp_block_nr, + PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_LOCKED | MAP_POPULATE, fd, 0); + if (ring == MAP_FAILED) + error(1, 0, "mmap failed"); + + return ring; +} + +static void __set_filter(int fd, int off_proto, uint8_t proto, int off_dport) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD + BPF_B + BPF_ABS, SKF_AD_OFF + SKF_AD_PKTTYPE), + BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, PACKET_HOST, 0, 4), + BPF_STMT(BPF_LD + BPF_B + BPF_ABS, off_proto), + BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, proto, 0, 2), + BPF_STMT(BPF_LD + BPF_H + BPF_ABS, off_dport), + BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, cfg_dport, 1, 0), + BPF_STMT(BPF_RET + BPF_K, 0), + BPF_STMT(BPF_RET + BPF_K, 0xFFFF), + }; + struct sock_fprog prog = {}; + + prog.filter = filter; + prog.len = sizeof(filter) / sizeof(struct sock_filter); + if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &prog, sizeof(prog))) + error(1, errno, "setsockopt filter"); +} + +/* filter on transport protocol and destination port */ +static void set_filter(int fd) +{ + const int off_dport = offsetof(struct tcphdr, dest); /* same for udp */ + uint8_t proto; + + proto = cfg_type == SOCK_STREAM ? IPPROTO_TCP : IPPROTO_UDP; + if (cfg_family == AF_INET) + __set_filter(fd, offsetof(struct iphdr, protocol), proto, + sizeof(struct iphdr) + off_dport); + else + __set_filter(fd, offsetof(struct ip6_hdr, ip6_nxt), proto, + sizeof(struct ip6_hdr) + off_dport); +} + +/* drop everything: used temporarily during setup */ +static void set_filter_null(int fd) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_RET + BPF_K, 0), + }; + struct sock_fprog prog = {}; + + prog.filter = filter; + prog.len = sizeof(filter) / sizeof(struct sock_filter); + if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &prog, sizeof(prog))) + error(1, errno, "setsockopt filter"); +} + +static int create_ring(char **ring) +{ + struct fanout_args args = { + .id = 1, + .type_flags = PACKET_FANOUT_CPU, + .max_num_members = RSS_MAX_CPUS + }; + struct sockaddr_ll ll = { 0 }; + int fd, val; + + fd = socket(PF_PACKET, SOCK_DGRAM, 0); + if (fd == -1) + error(1, errno, "socket creation failed"); + + val = TPACKET_V3; + if (setsockopt(fd, SOL_PACKET, PACKET_VERSION, &val, sizeof(val))) + error(1, errno, "setsockopt PACKET_VERSION"); + *ring = setup_ring(fd); + + /* block packets until all rings are added to the fanout group: + * else packets can arrive during setup and get misclassified + */ + set_filter_null(fd); + + ll.sll_family = AF_PACKET; + ll.sll_ifindex = if_nametoindex(cfg_ifname); + ll.sll_protocol = cfg_family == AF_INET ? htons(ETH_P_IP) : + htons(ETH_P_IPV6); + if (bind(fd, (void *)&ll, sizeof(ll))) + error(1, errno, "bind"); + + /* must come after bind: verifies all programs in group match */ + if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT, &args, sizeof(args))) { + /* on failure, retry using old API if that is sufficient: + * it has a hard limit of 256 sockets, so only try if + * (a) only testing rxhash, not RSS or (b) <= 256 cpus. + * in this API, the third argument is left implicit. + */ + if (cfg_num_queues || num_cpus > 256 || + setsockopt(fd, SOL_PACKET, PACKET_FANOUT, + &args, sizeof(uint32_t))) + error(1, errno, "setsockopt PACKET_FANOUT cpu"); + } + + return fd; +} + +/* setup inet(6) socket to blackhole the test traffic, if arg '-s' */ +static int setup_sink(void) +{ + int fd, val; + + fd = socket(cfg_family, cfg_type, 0); + if (fd == -1) + error(1, errno, "socket %d.%d", cfg_family, cfg_type); + + val = 1 << 20; + if (setsockopt(fd, SOL_SOCKET, SO_RCVBUFFORCE, &val, sizeof(val))) + error(1, errno, "setsockopt rcvbuf"); + + return fd; +} + +static void setup_rings(void) +{ + int i; + + for (i = 0; i < num_cpus; i++) { + rings[i].cpu = i; + rings[i].fd = create_ring(&rings[i].mmap); + } + + /* accept packets once all rings in the fanout group are up */ + for (i = 0; i < num_cpus; i++) + set_filter(rings[i].fd); +} + +static void cleanup_rings(void) +{ + int i; + + for (i = 0; i < num_cpus; i++) { + if (munmap(rings[i].mmap, ring_block_nr * ring_block_sz)) + error(1, errno, "munmap"); + if (close(rings[i].fd)) + error(1, errno, "close"); + } +} + +static void parse_cpulist(const char *arg) +{ + do { + rx_irq_cpus[cfg_num_queues++] = strtol(arg, NULL, 10); + + arg = strchr(arg, ','); + if (!arg) + break; + arg++; // skip ',' + } while (1); +} + +static void show_cpulist(void) +{ + int i; + + for (i = 0; i < cfg_num_queues; i++) + fprintf(stderr, "rxq %d: cpu %d\n", i, rx_irq_cpus[i]); +} + +static void show_silos(void) +{ + int i; + + for (i = 0; i < cfg_num_rps_cpus; i++) + fprintf(stderr, "silo %d: cpu %d\n", i, rps_silo_to_cpu[i]); +} + +static void parse_toeplitz_key(const char *str, int slen, unsigned char *key) +{ + int i, ret, off; + + if (slen < TOEPLITZ_STR_MIN_LEN || + slen > TOEPLITZ_STR_MAX_LEN + 1) + error(1, 0, "invalid toeplitz key"); + + for (i = 0, off = 0; off < slen; i++, off += 3) { + ret = sscanf(str + off, "%hhx", &key[i]); + if (ret != 1) + error(1, 0, "key parse error at %d off %d len %d", + i, off, slen); + } +} + +static void parse_rps_bitmap(const char *arg) +{ + unsigned long bitmap; + int i; + + bitmap = strtoul(arg, NULL, 0); + + if (bitmap & ~(RPS_MAX_CPUS - 1)) + error(1, 0, "rps bitmap 0x%lx out of bounds 0..%lu", + bitmap, RPS_MAX_CPUS - 1); + + for (i = 0; i < RPS_MAX_CPUS; i++) + if (bitmap & 1UL << i) + rps_silo_to_cpu[cfg_num_rps_cpus++] = i; +} + +static void parse_opts(int argc, char **argv) +{ + static struct option long_options[] = { + {"dport", required_argument, 0, 'd'}, + {"cpus", required_argument, 0, 'C'}, + {"key", required_argument, 0, 'k'}, + {"iface", required_argument, 0, 'i'}, + {"ipv4", no_argument, 0, '4'}, + {"ipv6", no_argument, 0, '6'}, + {"sink", no_argument, 0, 's'}, + {"tcp", no_argument, 0, 't'}, + {"timeout", required_argument, 0, 'T'}, + {"udp", no_argument, 0, 'u'}, + {"verbose", no_argument, 0, 'v'}, + {"rps", required_argument, 0, 'r'}, + {0, 0, 0, 0} + }; + bool have_toeplitz = false; + int index, c; + + while ((c = getopt_long(argc, argv, "46C:d:i:k:r:stT:u:v", long_options, &index)) != -1) { + switch (c) { + case '4': + cfg_family = AF_INET; + break; + case '6': + cfg_family = AF_INET6; + break; + case 'C': + parse_cpulist(optarg); + break; + case 'd': + cfg_dport = strtol(optarg, NULL, 0); + break; + case 'i': + cfg_ifname = optarg; + break; + case 'k': + parse_toeplitz_key(optarg, strlen(optarg), + toeplitz_key); + have_toeplitz = true; + break; + case 'r': + parse_rps_bitmap(optarg); + break; + case 's': + cfg_sink = true; + break; + case 't': + cfg_type = SOCK_STREAM; + break; + case 'T': + cfg_timeout_msec = strtol(optarg, NULL, 0); + break; + case 'u': + cfg_type = SOCK_DGRAM; + break; + case 'v': + cfg_verbose = true; + break; + + default: + error(1, 0, "unknown option %c", optopt); + break; + } + } + + if (!have_toeplitz) + error(1, 0, "Must supply rss key ('-k')"); + + num_cpus = get_nprocs(); + if (num_cpus > RSS_MAX_CPUS) + error(1, 0, "increase RSS_MAX_CPUS"); + + if (cfg_num_queues && cfg_num_rps_cpus) + error(1, 0, + "Can't supply both RSS cpus ('-C') and RPS map ('-r')"); + if (cfg_verbose) { + show_cpulist(); + show_silos(); + } +} + +int main(int argc, char **argv) +{ + const int min_tests = 10; + int fd_sink = -1; + + parse_opts(argc, argv); + + if (cfg_sink) + fd_sink = setup_sink(); + + setup_rings(); + process_rings(); + cleanup_rings(); + + if (cfg_sink && close(fd_sink)) + error(1, errno, "close sink"); + + if (frames_received - frames_nohash < min_tests) + error(1, 0, "too few frames for verification"); + + return frames_error; +} diff --git a/tools/testing/selftests/net/toeplitz.sh b/tools/testing/selftests/net/toeplitz.sh new file mode 100755 index 000000000000..0a49907cd4fe --- /dev/null +++ b/tools/testing/selftests/net/toeplitz.sh @@ -0,0 +1,199 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# extended toeplitz test: test rxhash plus, optionally, either (1) rss mapping +# from rxhash to rx queue ('-rss') or (2) rps mapping from rxhash to cpu +# ('-rps <rps_map>') +# +# irq-pattern-prefix can be derived from /sys/kernel/irq/*/action, +# which is a driver-specific encoding. +# +# invoke as ./toeplitz.sh (-i <iface>) -u|-t -4|-6 \ +# [(-rss -irq_prefix <irq-pattern-prefix>)|(-rps <rps_map>)] + +source setup_loopback.sh +readonly SERVER_IP4="192.168.1.200/24" +readonly SERVER_IP6="fda8::1/64" +readonly SERVER_MAC="aa:00:00:00:00:02" + +readonly CLIENT_IP4="192.168.1.100/24" +readonly CLIENT_IP6="fda8::2/64" +readonly CLIENT_MAC="aa:00:00:00:00:01" + +PORT=8000 +KEY="$(</proc/sys/net/core/netdev_rss_key)" +TEST_RSS=false +RPS_MAP="" +PROTO_FLAG="" +IP_FLAG="" +DEV="eth0" + +# Return the number of rxqs among which RSS is configured to spread packets. +# This is determined by reading the RSS indirection table using ethtool. +get_rss_cfg_num_rxqs() { + echo $(ethtool -x "${DEV}" | + egrep [[:space:]]+[0-9]+:[[:space:]]+ | + cut -d: -f2- | + awk '{$1=$1};1' | + tr ' ' '\n' | + sort -u | + wc -l) +} + +# Return a list of the receive irq handler cpus. +# The list is ordered by the irqs, so first rxq-0 cpu, then rxq-1 cpu, etc. +# Reads /sys/kernel/irq/ in order, so algorithm depends on +# irq_{rxq-0} < irq_{rxq-1}, etc. +get_rx_irq_cpus() { + CPUS="" + # sort so that irq 2 is read before irq 10 + SORTED_IRQS=$(for i in /sys/kernel/irq/*; do echo $i; done | sort -V) + # Consider only as many queues as RSS actually uses. We assume that + # if RSS_CFG_NUM_RXQS=N, then RSS uses rxqs 0-(N-1). + RSS_CFG_NUM_RXQS=$(get_rss_cfg_num_rxqs) + RXQ_COUNT=0 + + for i in ${SORTED_IRQS} + do + [[ "${RXQ_COUNT}" -lt "${RSS_CFG_NUM_RXQS}" ]] || break + # lookup relevant IRQs by action name + [[ -e "$i/actions" ]] || continue + cat "$i/actions" | grep -q "${IRQ_PATTERN}" || continue + irqname=$(<"$i/actions") + + # does the IRQ get called + irqcount=$(cat "$i/per_cpu_count" | tr -d '0,') + [[ -n "${irqcount}" ]] || continue + + # lookup CPU + irq=$(basename "$i") + cpu=$(cat "/proc/irq/$irq/smp_affinity_list") + + if [[ -z "${CPUS}" ]]; then + CPUS="${cpu}" + else + CPUS="${CPUS},${cpu}" + fi + RXQ_COUNT=$((RXQ_COUNT+1)) + done + + echo "${CPUS}" +} + +get_disable_rfs_cmd() { + echo "echo 0 > /proc/sys/net/core/rps_sock_flow_entries;" +} + +get_set_rps_bitmaps_cmd() { + CMD="" + for i in /sys/class/net/${DEV}/queues/rx-*/rps_cpus + do + CMD="${CMD} echo $1 > ${i};" + done + + echo "${CMD}" +} + +get_disable_rps_cmd() { + echo "$(get_set_rps_bitmaps_cmd 0)" +} + +die() { + echo "$1" + exit 1 +} + +check_nic_rxhash_enabled() { + local -r pattern="receive-hashing:\ on" + + ethtool -k "${DEV}" | grep -q "${pattern}" || die "rxhash must be enabled" +} + +parse_opts() { + local prog=$0 + shift 1 + + while [[ "$1" =~ "-" ]]; do + if [[ "$1" = "-irq_prefix" ]]; then + shift + IRQ_PATTERN="^$1-[0-9]*$" + elif [[ "$1" = "-u" || "$1" = "-t" ]]; then + PROTO_FLAG="$1" + elif [[ "$1" = "-4" ]]; then + IP_FLAG="$1" + SERVER_IP="${SERVER_IP4}" + CLIENT_IP="${CLIENT_IP4}" + elif [[ "$1" = "-6" ]]; then + IP_FLAG="$1" + SERVER_IP="${SERVER_IP6}" + CLIENT_IP="${CLIENT_IP6}" + elif [[ "$1" = "-rss" ]]; then + TEST_RSS=true + elif [[ "$1" = "-rps" ]]; then + shift + RPS_MAP="$1" + elif [[ "$1" = "-i" ]]; then + shift + DEV="$1" + else + die "Usage: ${prog} (-i <iface>) -u|-t -4|-6 \ + [(-rss -irq_prefix <irq-pattern-prefix>)|(-rps <rps_map>)]" + fi + shift + done +} + +setup() { + setup_loopback_environment "${DEV}" + + # Set up server_ns namespace and client_ns namespace + setup_macvlan_ns "${DEV}" server_ns server \ + "${SERVER_MAC}" "${SERVER_IP}" + setup_macvlan_ns "${DEV}" client_ns client \ + "${CLIENT_MAC}" "${CLIENT_IP}" +} + +cleanup() { + cleanup_macvlan_ns server_ns server client_ns client + cleanup_loopback "${DEV}" +} + +parse_opts $0 $@ + +setup +trap cleanup EXIT + +check_nic_rxhash_enabled + +# Actual test starts here +if [[ "${TEST_RSS}" = true ]]; then + # RPS/RFS must be disabled because they move packets between cpus, + # which breaks the PACKET_FANOUT_CPU identification of RSS decisions. + eval "$(get_disable_rfs_cmd) $(get_disable_rps_cmd)" \ + ip netns exec server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \ + -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 \ + -C "$(get_rx_irq_cpus)" -s -v & +elif [[ ! -z "${RPS_MAP}" ]]; then + eval "$(get_disable_rfs_cmd) $(get_set_rps_bitmaps_cmd ${RPS_MAP})" \ + ip netns exec server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \ + -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 \ + -r "0x${RPS_MAP}" -s -v & +else + ip netns exec server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \ + -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 -s -v & +fi + +server_pid=$! + +ip netns exec client_ns ./toeplitz_client.sh "${PROTO_FLAG}" \ + "${IP_FLAG}" "${SERVER_IP%%/*}" "${PORT}" & + +client_pid=$! + +wait "${server_pid}" +exit_code=$? +kill -9 "${client_pid}" +if [[ "${exit_code}" -eq 0 ]]; then + echo "Test Succeeded!" +fi +exit "${exit_code}" diff --git a/tools/testing/selftests/net/toeplitz_client.sh b/tools/testing/selftests/net/toeplitz_client.sh new file mode 100755 index 000000000000..2fef34f4aba1 --- /dev/null +++ b/tools/testing/selftests/net/toeplitz_client.sh @@ -0,0 +1,28 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# A simple program for generating traffic for the toeplitz test. +# +# This program sends packets periodically for, conservatively, 20 seconds. The +# intent is for the calling program to kill this program once it is no longer +# needed, rather than waiting for the 20 second expiration. + +send_traffic() { + expiration=$((SECONDS+20)) + while [[ "${SECONDS}" -lt "${expiration}" ]] + do + if [[ "${PROTO}" == "-u" ]]; then + echo "msg $i" | nc "${IPVER}" -u -w 0 "${ADDR}" "${PORT}" + else + echo "msg $i" | nc "${IPVER}" -w 0 "${ADDR}" "${PORT}" + fi + sleep 0.001 + done +} + +PROTO=$1 +IPVER=$2 +ADDR=$3 +PORT=$4 + +send_traffic diff --git a/tools/testing/selftests/net/unicast_extensions.sh b/tools/testing/selftests/net/unicast_extensions.sh index 66354cdd5ce4..2d10ccac898a 100755 --- a/tools/testing/selftests/net/unicast_extensions.sh +++ b/tools/testing/selftests/net/unicast_extensions.sh @@ -28,12 +28,15 @@ # These tests provide an easy way to flip the expected result of any # of these behaviors for testing kernel patches that change them. +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + # nettest can be run from PATH or from same directory as this selftest if ! which nettest >/dev/null; then PATH=$PWD:$PATH if ! which nettest >/dev/null; then echo "'nettest' command not found; skipping tests" - exit 0 + exit $ksft_skip fi fi diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh index 11d7cdb898c0..19eac3e44c06 100755 --- a/tools/testing/selftests/net/veth.sh +++ b/tools/testing/selftests/net/veth.sh @@ -13,7 +13,7 @@ readonly NS_DST=$BASE$DST readonly BM_NET_V4=192.168.1. readonly BM_NET_V6=2001:db8:: -readonly NPROCS=`nproc` +readonly CPUS=`nproc` ret=0 cleanup() { @@ -75,6 +75,29 @@ chk_tso_flag() { __chk_flag "$1" $2 $3 tcp-segmentation-offload } +chk_channels() { + local msg="$1" + local target=$2 + local rx=$3 + local tx=$4 + + local dev=veth$target + + local cur_rx=`ip netns exec $BASE$target ethtool -l $dev |\ + grep RX: | tail -n 1 | awk '{print $2}' ` + local cur_tx=`ip netns exec $BASE$target ethtool -l $dev |\ + grep TX: | tail -n 1 | awk '{print $2}'` + local cur_combined=`ip netns exec $BASE$target ethtool -l $dev |\ + grep Combined: | tail -n 1 | awk '{print $2}'` + + printf "%-60s" "$msg" + if [ "$cur_rx" = "$rx" -a "$cur_tx" = "$tx" -a "$cur_combined" = "n/a" ]; then + echo " ok " + else + echo " fail rx:$rx:$cur_rx tx:$tx:$cur_tx combined:n/a:$cur_combined" + fi +} + chk_gro() { local msg="$1" local expected=$2 @@ -107,11 +130,100 @@ chk_gro() { fi } +__change_channels() +{ + local cur_cpu + local end=$1 + local cur + local i + + while true; do + printf -v cur '%(%s)T' + [ $cur -le $end ] || break + + for i in `seq 1 $CPUS`; do + ip netns exec $NS_SRC ethtool -L veth$SRC rx $i tx $i + ip netns exec $NS_DST ethtool -L veth$DST rx $i tx $i + done + + for i in `seq 1 $((CPUS - 1))`; do + cur_cpu=$((CPUS - $i)) + ip netns exec $NS_SRC ethtool -L veth$SRC rx $cur_cpu tx $cur_cpu + ip netns exec $NS_DST ethtool -L veth$DST rx $cur_cpu tx $cur_cpu + done + done +} + +__send_data() { + local end=$1 + + while true; do + printf -v cur '%(%s)T' + [ $cur -le $end ] || break + + ip netns exec $NS_SRC ./udpgso_bench_tx -4 -s 1000 -M 300 -D $BM_NET_V4$DST + done +} + +do_stress() { + local end + printf -v end '%(%s)T' + end=$((end + $STRESS)) + + ip netns exec $NS_SRC ethtool -L veth$SRC rx 3 tx 3 + ip netns exec $NS_DST ethtool -L veth$DST rx 3 tx 3 + + ip netns exec $NS_DST ./udpgso_bench_rx & + local rx_pid=$! + + echo "Running stress test for $STRESS seconds..." + __change_channels $end & + local ch_pid=$! + __send_data $end & + local data_pid_1=$! + __send_data $end & + local data_pid_2=$! + __send_data $end & + local data_pid_3=$! + __send_data $end & + local data_pid_4=$! + + wait $ch_pid $data_pid_1 $data_pid_2 $data_pid_3 $data_pid_4 + kill -9 $rx_pid + echo "done" + + # restore previous setting + ip netns exec $NS_SRC ethtool -L veth$SRC rx 2 tx 2 + ip netns exec $NS_DST ethtool -L veth$DST rx 2 tx 1 +} + +usage() { + echo "Usage: $0 [-h] [-s <seconds>]" + echo -e "\t-h: show this help" + echo -e "\t-s: run optional stress tests for the given amount of seconds" +} + +STRESS=0 +while getopts "hs:" option; do + case "$option" in + "h") + usage $0 + exit 0 + ;; + "s") + STRESS=$OPTARG + ;; + esac +done + if [ ! -f ../bpf/xdp_dummy.o ]; then echo "Missing xdp_dummy helper. Build bpf selftest first" exit 1 fi +[ $CPUS -lt 2 ] && echo "Only one CPU available, some tests will be skipped" +[ $STRESS -gt 0 -a $CPUS -lt 3 ] && echo " stress test will be skipped, too" + create_ns chk_gro_flag "default - gro flag" $SRC off chk_gro_flag " - peer gro flag" $DST off @@ -134,6 +246,8 @@ chk_gro " - aggregation with TSO off" 1 cleanup create_ns +chk_channels "default channels" $DST 1 1 + ip -n $NS_DST link set dev veth$DST down ip netns exec $NS_DST ethtool -K veth$DST gro on chk_gro_flag "with gro enabled on link down - gro flag" $DST on @@ -147,6 +261,56 @@ chk_gro " - aggregation with TSO off" 1 cleanup create_ns + +CUR_TX=1 +CUR_RX=1 +if [ $CPUS -gt 1 ]; then + ip netns exec $NS_DST ethtool -L veth$DST tx 2 + chk_channels "setting tx channels" $DST 1 2 + CUR_TX=2 +fi + +if [ $CPUS -gt 2 ]; then + ip netns exec $NS_DST ethtool -L veth$DST rx 3 tx 3 + chk_channels "setting both rx and tx channels" $DST 3 3 + CUR_RX=3 + CUR_TX=3 +fi + +ip netns exec $NS_DST ethtool -L veth$DST combined 2 2>/dev/null +chk_channels "bad setting: combined channels" $DST $CUR_RX $CUR_TX + +ip netns exec $NS_DST ethtool -L veth$DST tx $((CPUS + 1)) 2>/dev/null +chk_channels "setting invalid channels nr" $DST $CUR_RX $CUR_TX + +if [ $CPUS -gt 1 ]; then + # this also tests queues nr reduction + ip netns exec $NS_DST ethtool -L veth$DST rx 1 tx 2 2>/dev/null + ip netns exec $NS_SRC ethtool -L veth$SRC rx 1 tx 2 2>/dev/null + printf "%-60s" "bad setting: XDP with RX nr less than TX" + ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o \ + section xdp_dummy 2>/dev/null &&\ + echo "fail - set operation successful ?!?" || echo " ok " + + # the following tests will run with multiple channels active + ip netns exec $NS_SRC ethtool -L veth$SRC rx 2 + ip netns exec $NS_DST ethtool -L veth$DST rx 2 + ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o \ + section xdp_dummy 2>/dev/null + printf "%-60s" "bad setting: reducing RX nr below peer TX with XDP set" + ip netns exec $NS_DST ethtool -L veth$DST rx 1 2>/dev/null &&\ + echo "fail - set operation successful ?!?" || echo " ok " + CUR_RX=2 + CUR_TX=2 +fi + +if [ $CPUS -gt 2 ]; then + printf "%-60s" "bad setting: increasing peer TX nr above RX with XDP set" + ip netns exec $NS_SRC ethtool -L veth$SRC tx 3 2>/dev/null &&\ + echo "fail - set operation successful ?!?" || echo " ok " + chk_channels "setting invalid channels nr" $DST 2 2 +fi + ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o section xdp_dummy 2>/dev/null chk_gro_flag "with xdp attached - gro flag" $DST on chk_gro_flag " - peer gro flag" $SRC off @@ -167,10 +331,27 @@ chk_gro_flag " - after gro on xdp off, gro flag" $DST on chk_gro_flag " - peer gro flag" $SRC off chk_tso_flag " - tso flag" $SRC on chk_tso_flag " - peer tso flag" $DST on + +if [ $CPUS -gt 1 ]; then + ip netns exec $NS_DST ethtool -L veth$DST tx 1 + chk_channels "decreasing tx channels with device down" $DST 2 1 +fi + ip -n $NS_DST link set dev veth$DST up ip -n $NS_SRC link set dev veth$SRC up chk_gro " - aggregation" 1 +if [ $CPUS -gt 1 ]; then + [ $STRESS -gt 0 -a $CPUS -gt 2 ] && do_stress + + ip -n $NS_DST link set dev veth$DST down + ip -n $NS_SRC link set dev veth$SRC down + ip netns exec $NS_DST ethtool -L veth$DST tx 2 + chk_channels "increasing tx channels with device down" $DST 2 2 + ip -n $NS_DST link set dev veth$DST up + ip -n $NS_SRC link set dev veth$SRC up +fi + ip netns exec $NS_DST ethtool -K veth$DST gro off ip netns exec $NS_SRC ethtool -K veth$SRC tx-udp-segmentation off chk_gro "aggregation again with default and TSO off" 10 diff --git a/tools/testing/selftests/net/vrf_strict_mode_test.sh b/tools/testing/selftests/net/vrf_strict_mode_test.sh index 18b982d611de..865d53c1781c 100755 --- a/tools/testing/selftests/net/vrf_strict_mode_test.sh +++ b/tools/testing/selftests/net/vrf_strict_mode_test.sh @@ -3,6 +3,9 @@ # This test is designed for testing the new VRF strict_mode functionality. +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + ret=0 # identifies the "init" network namespace which is often called root network @@ -371,18 +374,18 @@ vrf_strict_mode_check_support() if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" - exit 0 + exit $ksft_skip fi if [ ! -x "$(command -v ip)" ]; then echo "SKIP: Could not run test without ip tool" - exit 0 + exit $ksft_skip fi modprobe vrf &>/dev/null if [ ! -e /proc/sys/net/vrf/strict_mode ]; then echo "SKIP: vrf sysctl does not exist" - exit 0 + exit $ksft_skip fi cleanup &> /dev/null |