diff options
Diffstat (limited to 'tools/testing/selftests/net')
55 files changed, 1684 insertions, 2707 deletions
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 8f9850a71f54..6930fe926c58 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -4,10 +4,8 @@ bind_timewait bind_wildcard busy_poller cmsg_sender -diag_uid epoll_busy_poll fin_ack_lat -gro hwtstamp_config io_uring_zerocopy_tx ioam6_parser @@ -18,7 +16,6 @@ ipv6_flowlabel ipv6_flowlabel_mgr ipv6_fragmentation log.txt -msg_oob msg_zerocopy netlink-dumps nettest @@ -35,9 +32,6 @@ reuseport_bpf_numa reuseport_dualstack rxtimestamp sctp_hello -scm_inq -scm_pidfd -scm_rights sk_bind_sendto_listen sk_connect_zero_addr sk_so_peek_off @@ -45,7 +39,6 @@ skf_net_off socket so_incoming_cpu so_netns_cookie -so_peek_off so_txtime so_rcv_listener stress_reuseport_listen @@ -57,7 +50,6 @@ tcp_port_share tfo timestamping tls -toeplitz tools tun txring_overwrite @@ -65,4 +57,3 @@ txtimestamp udpgso udpgso_bench_rx udpgso_bench_tx -unix_connect diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index b5127e968108..b66ba04f19d9 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -38,7 +38,6 @@ TEST_PROGS := \ fq_band_pktlimit.sh \ gre_gso.sh \ gre_ipv6_lladdr.sh \ - gro.sh \ icmp.sh \ icmp_redirect.sh \ io_uring_zerocopy_tx.sh \ @@ -121,8 +120,6 @@ TEST_PROGS := \ # end of TEST_PROGS TEST_PROGS_EXTENDED := \ - toeplitz.sh \ - toeplitz_client.sh \ xfrm_policy_add_speed.sh \ # end of TEST_PROGS_EXTENDED @@ -130,7 +127,6 @@ TEST_GEN_FILES := \ bind_bhash \ cmsg_sender \ fin_ack_lat \ - gro \ hwtstamp_config \ io_uring_zerocopy_tx \ ioam6_parser \ @@ -159,7 +155,6 @@ TEST_GEN_FILES := \ tcp_mmap \ tfo \ timestamping \ - toeplitz \ txring_overwrite \ txtimestamp \ udpgso \ @@ -193,8 +188,6 @@ TEST_FILES := \ in_netns.sh \ lib.sh \ settings \ - setup_loopback.sh \ - setup_veth.sh \ # end of TEST_FILES # YNL files, must be before "include ..lib.mk" diff --git a/tools/testing/selftests/net/af_unix/.gitignore b/tools/testing/selftests/net/af_unix/.gitignore new file mode 100644 index 000000000000..240b26740c9e --- /dev/null +++ b/tools/testing/selftests/net/af_unix/.gitignore @@ -0,0 +1,8 @@ +diag_uid +msg_oob +scm_inq +scm_pidfd +scm_rights +so_peek_off +unix_connect +unix_connreset diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 528d14c598bb..3cd677b72072 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -8,6 +8,7 @@ TEST_GEN_PROGS := \ scm_rights \ so_peek_off \ unix_connect \ + unix_connreset \ # end of TEST_GEN_PROGS include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/so_peek_off.c b/tools/testing/selftests/net/af_unix/so_peek_off.c index 1a77728128e5..86e7b0fb522d 100644 --- a/tools/testing/selftests/net/af_unix/so_peek_off.c +++ b/tools/testing/selftests/net/af_unix/so_peek_off.c @@ -36,8 +36,8 @@ FIXTURE_VARIANT_ADD(so_peek_off, seqpacket) FIXTURE_SETUP(so_peek_off) { struct timeval timeout = { - .tv_sec = 0, - .tv_usec = 3000, + .tv_sec = 5, + .tv_usec = 0, }; int ret; diff --git a/tools/testing/selftests/net/af_unix/unix_connreset.c b/tools/testing/selftests/net/af_unix/unix_connreset.c new file mode 100644 index 000000000000..08c1de8f5a98 --- /dev/null +++ b/tools/testing/selftests/net/af_unix/unix_connreset.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Selftest for AF_UNIX socket close and ECONNRESET behaviour. + * + * This test verifies: + * 1. SOCK_STREAM returns EOF when the peer closes normally. + * 2. SOCK_STREAM returns ECONNRESET if peer closes with unread data. + * 3. SOCK_SEQPACKET returns EOF when the peer closes normally. + * 4. SOCK_SEQPACKET returns ECONNRESET if the peer closes with unread data. + * 5. SOCK_DGRAM does not return ECONNRESET when the peer closes. + * + * These tests document the intended Linux behaviour. + * + */ + +#define _GNU_SOURCE +#include <string.h> +#include <fcntl.h> +#include <unistd.h> +#include <errno.h> +#include <sys/socket.h> +#include <sys/un.h> +#include "../../kselftest_harness.h" + +#define SOCK_PATH "/tmp/af_unix_connreset.sock" + +static void remove_socket_file(void) +{ + unlink(SOCK_PATH); +} + +FIXTURE(unix_sock) +{ + int server; + int client; + int child; +}; + +FIXTURE_VARIANT(unix_sock) +{ + int socket_type; + const char *name; +}; + +FIXTURE_VARIANT_ADD(unix_sock, stream) { + .socket_type = SOCK_STREAM, + .name = "SOCK_STREAM", +}; + +FIXTURE_VARIANT_ADD(unix_sock, dgram) { + .socket_type = SOCK_DGRAM, + .name = "SOCK_DGRAM", +}; + +FIXTURE_VARIANT_ADD(unix_sock, seqpacket) { + .socket_type = SOCK_SEQPACKET, + .name = "SOCK_SEQPACKET", +}; + +FIXTURE_SETUP(unix_sock) +{ + struct sockaddr_un addr = {}; + int err; + + addr.sun_family = AF_UNIX; + strcpy(addr.sun_path, SOCK_PATH); + remove_socket_file(); + + self->server = socket(AF_UNIX, variant->socket_type, 0); + ASSERT_LT(-1, self->server); + + err = bind(self->server, (struct sockaddr *)&addr, sizeof(addr)); + ASSERT_EQ(0, err); + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + err = listen(self->server, 1); + ASSERT_EQ(0, err); + } + + self->client = socket(AF_UNIX, variant->socket_type | SOCK_NONBLOCK, 0); + ASSERT_LT(-1, self->client); + + err = connect(self->client, (struct sockaddr *)&addr, sizeof(addr)); + ASSERT_EQ(0, err); +} + +FIXTURE_TEARDOWN(unix_sock) +{ + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) + close(self->child); + + close(self->client); + close(self->server); + remove_socket_file(); +} + +/* Test 1: peer closes normally */ +TEST_F(unix_sock, eof) +{ + char buf[16] = {}; + ssize_t n; + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + self->child = accept(self->server, NULL, NULL); + ASSERT_LT(-1, self->child); + + close(self->child); + } else { + close(self->server); + } + + n = recv(self->client, buf, sizeof(buf), 0); + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + ASSERT_EQ(0, n); + } else { + ASSERT_EQ(-1, n); + ASSERT_EQ(EAGAIN, errno); + } +} + +/* Test 2: peer closes with unread data */ +TEST_F(unix_sock, reset_unread_behavior) +{ + char buf[16] = {}; + ssize_t n; + + /* Send data that will remain unread */ + send(self->client, "hello", 5, 0); + + if (variant->socket_type == SOCK_DGRAM) { + /* No real connection, just close the server */ + close(self->server); + } else { + self->child = accept(self->server, NULL, NULL); + ASSERT_LT(-1, self->child); + + /* Peer closes before client reads */ + close(self->child); + } + + n = recv(self->client, buf, sizeof(buf), 0); + ASSERT_EQ(-1, n); + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + ASSERT_EQ(ECONNRESET, errno); + } else { + ASSERT_EQ(EAGAIN, errno); + } +} + +/* Test 3: closing unaccepted (embryo) server socket should reset client. */ +TEST_F(unix_sock, reset_closed_embryo) +{ + char buf[16] = {}; + ssize_t n; + + if (variant->socket_type == SOCK_DGRAM) { + snprintf(_metadata->results->reason, + sizeof(_metadata->results->reason), + "Test only applies to SOCK_STREAM and SOCK_SEQPACKET"); + exit(KSFT_XFAIL); + } + + /* Close server without accept()ing */ + close(self->server); + + n = recv(self->client, buf, sizeof(buf), 0); + + ASSERT_EQ(-1, n); + ASSERT_EQ(ECONNRESET, errno); +} + +TEST_HARNESS_MAIN + diff --git a/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh b/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh index 92eb880c52f2..00758f00efbf 100755 --- a/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh +++ b/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh @@ -75,7 +75,7 @@ setup_v4() { ip neigh get $V4_ADDR1 dev veth0 >/dev/null 2>&1 if [ $? -ne 0 ]; then cleanup_v4 - echo "failed" + echo "failed; is the system using MACAddressPolicy=persistent ?" exit 1 fi diff --git a/tools/testing/selftests/net/busy_poll_test.sh b/tools/testing/selftests/net/busy_poll_test.sh index 7d2d40812074..5ec1c85c1623 100755 --- a/tools/testing/selftests/net/busy_poll_test.sh +++ b/tools/testing/selftests/net/busy_poll_test.sh @@ -27,6 +27,8 @@ NAPI_DEFER_HARD_IRQS=100 GRO_FLUSH_TIMEOUT=50000 SUSPEND_TIMEOUT=20000000 +NAPI_THREADED_MODE_BUSY_POLL=2 + setup_ns() { set -e @@ -62,6 +64,9 @@ cleanup_ns() test_busypoll() { suspend_value=${1:-0} + napi_threaded_value=${2:-0} + prefer_busy_poll_value=${3:-$PREFER_BUSY_POLL} + tmp_file=$(mktemp) out_file=$(mktemp) @@ -73,10 +78,11 @@ test_busypoll() -b${SERVER_IP} \ -m${MAX_EVENTS} \ -u${BUSY_POLL_USECS} \ - -P${PREFER_BUSY_POLL} \ + -P${prefer_busy_poll_value} \ -g${BUSY_POLL_BUDGET} \ -i${NSIM_SV_IFIDX} \ -s${suspend_value} \ + -t${napi_threaded_value} \ -o${out_file}& wait_local_port_listen nssv ${SERVER_PORT} tcp @@ -109,6 +115,15 @@ test_busypoll_with_suspend() return $? } +test_busypoll_with_napi_threaded() +{ + # Only enable napi threaded poll. Set suspend timeout and prefer busy + # poll to 0. + test_busypoll 0 ${NAPI_THREADED_MODE_BUSY_POLL} 0 + + return $? +} + ### ### Code start ### @@ -154,6 +169,13 @@ if [ $? -ne 0 ]; then exit 1 fi +test_busypoll_with_napi_threaded +if [ $? -ne 0 ]; then + echo "test_busypoll_with_napi_threaded failed" + cleanup_ns + exit 1 +fi + echo "$NSIM_SV_FD:$NSIM_SV_IFIDX" > $NSIM_DEV_SYS_UNLINK echo $NSIM_CL_ID > $NSIM_DEV_SYS_DEL diff --git a/tools/testing/selftests/net/busy_poller.c b/tools/testing/selftests/net/busy_poller.c index 04c7ff577bb8..3a81f9c94795 100644 --- a/tools/testing/selftests/net/busy_poller.c +++ b/tools/testing/selftests/net/busy_poller.c @@ -65,15 +65,16 @@ static uint32_t cfg_busy_poll_usecs; static uint16_t cfg_busy_poll_budget; static uint8_t cfg_prefer_busy_poll; -/* IRQ params */ +/* NAPI params */ static uint32_t cfg_defer_hard_irqs; static uint64_t cfg_gro_flush_timeout; static uint64_t cfg_irq_suspend_timeout; +static enum netdev_napi_threaded cfg_napi_threaded_poll = NETDEV_NAPI_THREADED_DISABLED; static void usage(const char *filepath) { error(1, 0, - "Usage: %s -p<port> -b<addr> -m<max_events> -u<busy_poll_usecs> -P<prefer_busy_poll> -g<busy_poll_budget> -o<outfile> -d<defer_hard_irqs> -r<gro_flush_timeout> -s<irq_suspend_timeout> -i<ifindex>", + "Usage: %s -p<port> -b<addr> -m<max_events> -u<busy_poll_usecs> -P<prefer_busy_poll> -g<busy_poll_budget> -o<outfile> -d<defer_hard_irqs> -r<gro_flush_timeout> -s<irq_suspend_timeout> -t<napi_threaded_poll> -i<ifindex>", filepath); } @@ -86,7 +87,7 @@ static void parse_opts(int argc, char **argv) if (argc <= 1) usage(argv[0]); - while ((c = getopt(argc, argv, "p:m:b:u:P:g:o:d:r:s:i:")) != -1) { + while ((c = getopt(argc, argv, "p:m:b:u:P:g:o:d:r:s:i:t:")) != -1) { /* most options take integer values, except o and b, so reduce * code duplication a bit for the common case by calling * strtoull here and leave bounds checking and casting per @@ -168,6 +169,12 @@ static void parse_opts(int argc, char **argv) cfg_ifindex = (int)tmp; break; + case 't': + if (tmp > 2) + error(1, ERANGE, "napi threaded poll value must be 0-2"); + + cfg_napi_threaded_poll = (enum netdev_napi_threaded)tmp; + break; } } @@ -247,6 +254,9 @@ static void setup_queue(void) netdev_napi_set_req_set_irq_suspend_timeout(set_req, cfg_irq_suspend_timeout); + if (cfg_napi_threaded_poll) + netdev_napi_set_req_set_threaded(set_req, cfg_napi_threaded_poll); + if (netdev_napi_set(ys, set_req)) error(1, 0, "can't set NAPI params: %s\n", yerr.msg); diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index a94b73a53f72..a88f797c549a 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -11,7 +11,8 @@ TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \ ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics \ ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr \ ipv6_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test \ - ipv4_mpath_list ipv6_mpath_list ipv4_mpath_balance ipv6_mpath_balance" + ipv4_mpath_list ipv6_mpath_list ipv4_mpath_balance ipv6_mpath_balance \ + fib6_ra_to_static" VERBOSE=0 PAUSE_ON_FAIL=no @@ -1476,6 +1477,68 @@ ipv6_route_metrics_test() route_cleanup } +fib6_ra_to_static() +{ + setup + + echo + echo "Fib6 route promotion from RA-learned to static test" + set -e + + # ra6 is required for the test. (ipv6toolkit) + if [ ! -x "$(command -v ra6)" ]; then + echo "SKIP: ra6 not found." + set +e + cleanup &> /dev/null + return + fi + + # Create a pair of veth devices to send a RA message from one + # device to another. + $IP link add veth1 type veth peer name veth2 + $IP link set dev veth1 up + $IP link set dev veth2 up + $IP -6 address add 2001:10::1/64 dev veth1 nodad + $IP -6 address add 2001:10::2/64 dev veth2 nodad + + # Make veth1 ready to receive RA messages. + $NS_EXEC sysctl -wq net.ipv6.conf.veth1.accept_ra=2 + + # Send a RA message with a prefix from veth2. + $NS_EXEC ra6 -i veth2 -d 2001:10::1 -P 2001:12::/64\#LA\#120\#60 + + # Wait for the RA message. + sleep 1 + + # systemd may mess up the test. Make sure that + # systemd-networkd.service and systemd-networkd.socket are stopped. + check_rt_num_clean 2 $($IP -6 route list|grep expires|wc -l) || return + + # Configure static address on the same prefix + $IP -6 address add 2001:12::dead/64 dev veth1 nodad + + # On-link route won't expire anymore, default route still owned by RA + check_rt_num 1 $($IP -6 route list |grep expires|wc -l) + + # Send a second RA message with a prefix from veth2. + $NS_EXEC ra6 -i veth2 -d 2001:10::1 -P 2001:12::/64\#LA\#120\#60 + sleep 1 + + # Expire is not back, on-link route is still static + check_rt_num 1 $($IP -6 route list |grep expires|wc -l) + + $IP -6 address del 2001:12::dead/64 dev veth1 nodad + + # Expire is back, on-link route is now owned by RA again + check_rt_num 2 $($IP -6 route list |grep expires|wc -l) + + log_test $ret 0 "ipv6 promote RA route to static" + + set +e + + cleanup &> /dev/null +} + # add route for a prefix, flushing any existing routes first # expected to be the first step of a test add_route() @@ -2798,6 +2861,7 @@ do ipv6_mpath_list) ipv6_mpath_list_test;; ipv4_mpath_balance) ipv4_mpath_balance_test;; ipv6_mpath_balance) ipv6_mpath_balance_test;; + fib6_ra_to_static) fib6_ra_to_static;; help) echo "Test names: $TESTS"; exit 0;; esac diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index 8c1597ebc2d3..e86d77946585 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -28,6 +28,7 @@ ALL_TESTS=" cfg_test fwd_test ctrl_test + disable_test " NUM_NETIFS=4 @@ -64,7 +65,10 @@ h2_destroy() switch_create() { - ip link add name br0 type bridge vlan_filtering 1 vlan_default_pvid 0 \ + local vlan_filtering=$1; shift + + ip link add name br0 type bridge \ + vlan_filtering "$vlan_filtering" vlan_default_pvid 0 \ mcast_snooping 1 mcast_igmp_version 3 mcast_mld_version 2 bridge vlan add vid 10 dev br0 self bridge vlan add vid 20 dev br0 self @@ -118,7 +122,7 @@ setup_prepare() h1_create h2_create - switch_create + switch_create 1 } cleanup() @@ -1357,6 +1361,98 @@ ctrl_test() ctrl_mldv2_is_in_test } +check_group() +{ + local group=$1; shift + local vid=$1; shift + local should_fail=$1; shift + local when=$1; shift + local -a vidkws + + if ((vid)); then + vidkws=(vid "$vid") + fi + + bridge mdb get dev br0 grp "$group" "${vidkws[@]}" 2>/dev/null | + grep -q "port $swp1" + check_err_fail "$should_fail" $? "$group seen $when snooping disable:" +} + +__disable_test() +{ + local vid=$1; shift + local what=$1; shift + local -a vidkws + + if ((vid)); then + vidkws=(vid "$vid") + fi + + RET=0 + + bridge mdb add dev br0 port "$swp1" grp ff0e::1 permanent \ + "${vidkws[@]}" filter_mode include source_list 2001:db8:1::1 + bridge mdb add dev br0 port "$swp1" grp ff0e::2 permanent \ + "${vidkws[@]}" filter_mode exclude + + bridge mdb add dev br0 port "$swp1" grp ff0e::3 \ + "${vidkws[@]}" filter_mode include source_list 2001:db8:1::2 + bridge mdb add dev br0 port "$swp1" grp ff0e::4 \ + "${vidkws[@]}" filter_mode exclude + + bridge mdb add dev br0 port "$swp1" grp 239.1.1.1 permanent \ + "${vidkws[@]}" filter_mode include source_list 192.0.2.1 + bridge mdb add dev br0 port "$swp1" grp 239.1.1.2 permanent \ + "${vidkws[@]}" filter_mode exclude + + bridge mdb add dev br0 port "$swp1" grp 239.1.1.3 \ + "${vidkws[@]}" filter_mode include source_list 192.0.2.2 + bridge mdb add dev br0 port "$swp1" grp 239.1.1.4 \ + "${vidkws[@]}" filter_mode exclude + + check_group ff0e::1 "$vid" 0 "before" + check_group ff0e::2 "$vid" 0 "before" + check_group ff0e::3 "$vid" 0 "before" + check_group ff0e::4 "$vid" 0 "before" + + check_group 239.1.1.1 "$vid" 0 "before" + check_group 239.1.1.2 "$vid" 0 "before" + check_group 239.1.1.3 "$vid" 0 "before" + check_group 239.1.1.4 "$vid" 0 "before" + + ip link set dev br0 type bridge mcast_snooping 0 + + check_group ff0e::1 "$vid" 0 "after" + check_group ff0e::2 "$vid" 0 "after" + check_group ff0e::3 "$vid" 1 "after" + check_group ff0e::4 "$vid" 1 "after" + + check_group 239.1.1.1 "$vid" 0 "after" + check_group 239.1.1.2 "$vid" 0 "after" + check_group 239.1.1.3 "$vid" 1 "after" + check_group 239.1.1.4 "$vid" 1 "after" + + log_test "$what: Flush after disable" + + ip link set dev br0 type bridge mcast_snooping 1 + sleep 10 +} + +disable_test() +{ + __disable_test 10 802.1q + + switch_destroy + switch_create 0 + setup_wait + + __disable_test 0 802.1d + + switch_destroy + switch_create 1 + setup_wait +} + if ! bridge mdb help 2>&1 | grep -q "flush"; then echo "SKIP: iproute2 too old, missing bridge mdb flush support" exit $ksft_skip diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c deleted file mode 100644 index cfc39f70635d..000000000000 --- a/tools/testing/selftests/net/gro.c +++ /dev/null @@ -1,1366 +0,0 @@ -// 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> - -#include "../kselftest.h" - -#define DPORT 8000 -#define SPORT 1500 -#define PAYLOAD_LEN 100 -#define NUM_PACKETS 4 -#define START_SEQ 100 -#define START_ACK 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)) -#define MIN_EXTHDR_SIZE 8 -#define EXT_PAYLOAD_1 "\x00\x00\x00\x00\x00\x00" -#define EXT_PAYLOAD_2 "\x11\x11\x11\x11\x11\x11" - -#define ipv6_optlen(p) (((p)->hdrlen+1) << 3) /* calculate IPv6 extension header len */ -#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) - -static const char *addr6_src = "fdaa::2"; -static const char *addr6_dst = "fdaa::1"; -static const char *addr4_src = "192.168.1.200"; -static const char *addr4_dst = "192.168.1.100"; -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 bool ipip; -static const int num_flush_id_cases = 6; - -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, opt_ipproto_off; - int next_off; - - if (ipip) - next_off = sizeof(struct iphdr) + offsetof(struct iphdr, protocol); - else if (proto == PF_INET) - next_off = offsetof(struct iphdr, protocol); - else - next_off = offsetof(struct ipv6hdr, nexthdr); - ipproto_off = ETH_HLEN + next_off; - - /* Overridden later if exthdrs are used: */ - opt_ipproto_off = ipproto_off; - - if (strcmp(testname, "ip") == 0) { - if (proto == PF_INET) - optlen = sizeof(struct ip_timestamp); - else { - BUILD_BUG_ON(sizeof(struct ip6_hbh) > MIN_EXTHDR_SIZE); - BUILD_BUG_ON(sizeof(struct ip6_dest) > MIN_EXTHDR_SIZE); - BUILD_BUG_ON(sizeof(struct ip6_frag) > MIN_EXTHDR_SIZE); - - /* same size for HBH and Fragment extension header types */ - optlen = MIN_EXTHDR_SIZE; - opt_ipproto_off = ETH_HLEN + sizeof(struct ipv6hdr) - + offsetof(struct ip6_ext, ip6e_nxt); - } - } - - /* this filter validates the following: - * - packet is IPv4/IPv6 according to the running test. - * - packet is TCP. Also handles the case of one extension header and then TCP. - * - checks the packet tcp dport equals to DPORT. Also handles the case of one - * extension header and then TCP. - */ - 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, 9), - BPF_STMT(BPF_LD + BPF_B + BPF_ABS, ipproto_off), - BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, IPPROTO_TCP, 2, 0), - BPF_STMT(BPF_LD + BPF_B + BPF_ABS, opt_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, addr6_src, &ph6.saddr) != 1) - error(1, errno, "inet_pton6 source ip pseudo"); - if (inet_pton(AF_INET6, addr6_dst, &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, addr4_src, &ph4.saddr) != 1) - error(1, errno, "inet_pton source ip pseudo"); - if (inet_pton(AF_INET, addr4_dst, &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, int protocol) -{ - 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 = protocol; - ip6h->hop_limit = 8; - if (inet_pton(AF_INET6, addr6_src, &ip6h->saddr) != 1) - error(1, errno, "inet_pton source ip6"); - if (inet_pton(AF_INET6, addr6_dst, &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 = protocol; - 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, addr4_src, &iph->saddr) != 1) - error(1, errno, "inet_pton source ip"); - if (inet_pton(AF_INET, addr4_dst, &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); - - if (ipip) { - fill_networklayer(buf + ETH_HLEN, payload_len + sizeof(struct iphdr), - IPPROTO_IPIP); - fill_networklayer(buf + ETH_HLEN + sizeof(struct iphdr), - payload_len, IPPROTO_TCP); - } else { - fill_networklayer(buf + ETH_HLEN, payload_len, IPPROTO_TCP); - } - - 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); - - if (ipip) { - iph += 1; - 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); -} - -static void add_ipv6_exthdr(void *buf, void *optpkt, __u8 exthdr_type, char *ext_payload) -{ - struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr *)(optpkt + tcp_offset); - struct ipv6hdr *iph = (struct ipv6hdr *)(optpkt + ETH_HLEN); - char *exthdr_payload_start = (char *)(exthdr + 1); - - exthdr->hdrlen = 0; - exthdr->nexthdr = IPPROTO_TCP; - - memcpy(exthdr_payload_start, ext_payload, MIN_EXTHDR_SIZE - sizeof(*exthdr)); - - memcpy(optpkt, buf, tcp_offset); - memcpy(optpkt + tcp_offset + MIN_EXTHDR_SIZE, buf + tcp_offset, - sizeof(struct tcphdr) + PAYLOAD_LEN); - - iph->nexthdr = exthdr_type; - iph->payload_len = htons(ntohs(iph->payload_len) + MIN_EXTHDR_SIZE); -} - -static void fix_ip4_checksum(struct iphdr *iph) -{ - iph->check = 0; - iph->check = checksum_fold(iph, sizeof(struct iphdr), 0); -} - -static void send_flush_id_case(int fd, struct sockaddr_ll *daddr, int tcase) -{ - static char buf1[MAX_HDR_LEN + PAYLOAD_LEN]; - static char buf2[MAX_HDR_LEN + PAYLOAD_LEN]; - static char buf3[MAX_HDR_LEN + PAYLOAD_LEN]; - bool send_three = false; - struct iphdr *iph1; - struct iphdr *iph2; - struct iphdr *iph3; - - iph1 = (struct iphdr *)(buf1 + ETH_HLEN); - iph2 = (struct iphdr *)(buf2 + ETH_HLEN); - iph3 = (struct iphdr *)(buf3 + ETH_HLEN); - - create_packet(buf1, 0, 0, PAYLOAD_LEN, 0); - create_packet(buf2, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); - create_packet(buf3, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0); - - switch (tcase) { - case 0: /* DF=1, Incrementing - should coalesce */ - iph1->frag_off |= htons(IP_DF); - iph1->id = htons(8); - - iph2->frag_off |= htons(IP_DF); - iph2->id = htons(9); - break; - - case 1: /* DF=1, Fixed - should coalesce */ - iph1->frag_off |= htons(IP_DF); - iph1->id = htons(8); - - iph2->frag_off |= htons(IP_DF); - iph2->id = htons(8); - break; - - case 2: /* DF=0, Incrementing - should coalesce */ - iph1->frag_off &= ~htons(IP_DF); - iph1->id = htons(8); - - iph2->frag_off &= ~htons(IP_DF); - iph2->id = htons(9); - break; - - case 3: /* DF=0, Fixed - should coalesce */ - iph1->frag_off &= ~htons(IP_DF); - iph1->id = htons(8); - - iph2->frag_off &= ~htons(IP_DF); - iph2->id = htons(8); - break; - - case 4: /* DF=1, two packets incrementing, and one fixed - should - * coalesce only the first two packets - */ - iph1->frag_off |= htons(IP_DF); - iph1->id = htons(8); - - iph2->frag_off |= htons(IP_DF); - iph2->id = htons(9); - - iph3->frag_off |= htons(IP_DF); - iph3->id = htons(9); - send_three = true; - break; - - case 5: /* DF=1, two packets fixed, and one incrementing - should - * coalesce only the first two packets - */ - iph1->frag_off |= htons(IP_DF); - iph1->id = htons(8); - - iph2->frag_off |= htons(IP_DF); - iph2->id = htons(8); - - iph3->frag_off |= htons(IP_DF); - iph3->id = htons(9); - send_three = true; - break; - } - - fix_ip4_checksum(iph1); - fix_ip4_checksum(iph2); - write_packet(fd, buf1, total_hdr_len + PAYLOAD_LEN, daddr); - write_packet(fd, buf2, total_hdr_len + PAYLOAD_LEN, daddr); - - if (send_three) { - fix_ip4_checksum(iph3); - write_packet(fd, buf3, total_hdr_len + PAYLOAD_LEN, daddr); - } -} - -static void test_flush_id(int fd, struct sockaddr_ll *daddr, char *fin_pkt) -{ - for (int i = 0; i < num_flush_id_cases; i++) { - sleep(1); - send_flush_id_case(fd, daddr, i); - sleep(1); - write_packet(fd, fin_pkt, total_hdr_len, daddr); - } -} - -static void send_ipv6_exthdr(int fd, struct sockaddr_ll *daddr, char *ext_data1, char *ext_data2) -{ - static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; - static char exthdr_pck[sizeof(buf) + MIN_EXTHDR_SIZE]; - - create_packet(buf, 0, 0, PAYLOAD_LEN, 0); - add_ipv6_exthdr(buf, exthdr_pck, IPPROTO_DSTOPTS, ext_data1); - write_packet(fd, exthdr_pck, total_hdr_len + PAYLOAD_LEN + MIN_EXTHDR_SIZE, daddr); - - create_packet(buf, PAYLOAD_LEN * 1, 0, PAYLOAD_LEN, 0); - add_ipv6_exthdr(buf, exthdr_pck, IPPROTO_DSTOPTS, ext_data2); - write_packet(fd, exthdr_pck, total_hdr_len + PAYLOAD_LEN + MIN_EXTHDR_SIZE, daddr); -} - -/* 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, IPPROTO_TCP); - 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); - } - sleep(1); - 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 = 3; - 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) { - ip_ext_len = 0; - 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 = MIN_EXTHDR_SIZE; - - 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) -{ - const int fin_delay_us = 100 * 1000; - 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); - /* Adding sleep before sending FIN so that it is not - * received prior to other packets. - */ - usleep(fin_delay_us); - write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - - send_changed_seq(txfd, &daddr); - usleep(fin_delay_us); - write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - - send_changed_ts(txfd, &daddr); - usleep(fin_delay_us); - write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - - send_diff_opt(txfd, &daddr); - usleep(fin_delay_us); - 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); - - test_flush_id(txfd, &daddr, fin_pkt); - } else if (proto == PF_INET6) { - sleep(1); - send_fragment6(txfd, &daddr); - sleep(1); - write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - - sleep(1); - /* send IPv6 packets with ext header with same payload */ - send_ipv6_exthdr(txfd, &daddr, EXT_PAYLOAD_1, EXT_PAYLOAD_1); - sleep(1); - write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - - sleep(1); - /* send IPv6 packets with ext header with different payload */ - send_ipv6_exthdr(txfd, &daddr, EXT_PAYLOAD_1, EXT_PAYLOAD_2); - sleep(1); - 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 && !ipip) ? 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); - - /* is_atomic checks */ - printf("DF=1, Incrementing - should coalesce: "); - correct_payload[0] = PAYLOAD_LEN * 2; - check_recv_pkts(rxfd, correct_payload, 1); - - printf("DF=1, Fixed - should coalesce: "); - correct_payload[0] = PAYLOAD_LEN * 2; - check_recv_pkts(rxfd, correct_payload, 1); - - printf("DF=0, Incrementing - should coalesce: "); - correct_payload[0] = PAYLOAD_LEN * 2; - check_recv_pkts(rxfd, correct_payload, 1); - - printf("DF=0, Fixed - should coalesce: "); - correct_payload[0] = PAYLOAD_LEN * 2; - check_recv_pkts(rxfd, correct_payload, 1); - - printf("DF=1, 2 Incrementing and one fixed - should coalesce only first 2 packets: "); - correct_payload[0] = PAYLOAD_LEN * 2; - correct_payload[1] = PAYLOAD_LEN; - check_recv_pkts(rxfd, correct_payload, 2); - - printf("DF=1, 2 Fixed and one incrementing - should coalesce only first 2 packets: "); - correct_payload[0] = PAYLOAD_LEN * 2; - correct_payload[1] = PAYLOAD_LEN; - 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; - correct_payload[1] = PAYLOAD_LEN; - correct_payload[2] = PAYLOAD_LEN; - check_recv_pkts(rxfd, correct_payload, 3); - - printf("ipv6 with ext header does coalesce: "); - correct_payload[0] = PAYLOAD_LEN * 2; - check_recv_pkts(rxfd, correct_payload, 1); - - printf("ipv6 with ext header with different payloads doesn't coalesce: "); - correct_payload[0] = PAYLOAD_LEN; - correct_payload[1] = PAYLOAD_LEN; - check_recv_pkts(rxfd, correct_payload, 2); - } - } else if (strcmp(testname, "large") == 0) { - int offset = (proto == PF_INET && !ipip) ? 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[] = { - { "daddr", required_argument, NULL, 'd' }, - { "dmac", required_argument, NULL, 'D' }, - { "iface", required_argument, NULL, 'i' }, - { "ipv4", no_argument, NULL, '4' }, - { "ipv6", no_argument, NULL, '6' }, - { "ipip", no_argument, NULL, 'e' }, - { "rx", no_argument, NULL, 'r' }, - { "saddr", required_argument, NULL, 's' }, - { "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:D:ei:rs:S: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 'e': - ipip = true; - proto = PF_INET; - ethhdr_proto = htons(ETH_P_IP); - break; - case 'd': - addr4_dst = addr6_dst = optarg; - break; - case 'D': - dmac = optarg; - break; - case 'i': - ifname = optarg; - break; - case 'r': - tx_socket = false; - break; - case 's': - addr4_src = addr6_src = optarg; - 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 (ipip) { - tcp_offset = ETH_HLEN + sizeof(struct iphdr) * 2; - total_hdr_len = tcp_offset + sizeof(struct tcphdr); - } else 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 { - /* Only the receiver exit status determines test success. */ - gro_receiver(); - fprintf(stderr, "Gro::%s test passed.\n", testname); - } - - return 0; -} diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh deleted file mode 100755 index 4c5144c6f652..000000000000 --- a/tools/testing/selftests/net/gro.sh +++ /dev/null @@ -1,105 +0,0 @@ -#!/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" "ipip") -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 6 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..6}; 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 [[ ${test} == "large" && -n "${KSFT_MACHINE_SLOW}" && \ - ${exit_code} -ne 0 ]]; then - echo "Ignoring errors due to slow environment" 1>&2 - exit_code=0 - fi - if [[ "${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 [[ "${test}" == "all" ]]; then - run_all_tests -else - exit_code=$(run_test "${proto}" "${test}") - exit $exit_code -fi; diff --git a/tools/testing/selftests/net/io_uring_zerocopy_tx.c b/tools/testing/selftests/net/io_uring_zerocopy_tx.c index 76e604e4810e..7bfeeb133705 100644 --- a/tools/testing/selftests/net/io_uring_zerocopy_tx.c +++ b/tools/testing/selftests/net/io_uring_zerocopy_tx.c @@ -106,14 +106,14 @@ static void do_tx(int domain, int type, int protocol) ret = io_uring_queue_init(512, &ring, 0); if (ret) - error(1, ret, "io_uring: queue init"); + error(1, -ret, "io_uring: queue init"); iov.iov_base = payload; iov.iov_len = cfg_payload_len; ret = io_uring_register_buffers(&ring, &iov, 1); if (ret) - error(1, ret, "io_uring: buffer registration"); + error(1, -ret, "io_uring: buffer registration"); tstop = gettimeofday_ms() + cfg_runtime_ms; do { @@ -149,24 +149,24 @@ static void do_tx(int domain, int type, int protocol) ret = io_uring_submit(&ring); if (ret != cfg_nr_reqs) - error(1, ret, "submit"); + error(1, -ret, "submit"); if (cfg_cork) do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 0); for (i = 0; i < cfg_nr_reqs; i++) { ret = io_uring_wait_cqe(&ring, &cqe); if (ret) - error(1, ret, "wait cqe"); + error(1, -ret, "wait cqe"); if (cqe->user_data != NONZC_TAG && cqe->user_data != ZC_TAG) - error(1, -EINVAL, "invalid cqe->user_data"); + error(1, EINVAL, "invalid cqe->user_data"); if (cqe->flags & IORING_CQE_F_NOTIF) { if (cqe->flags & IORING_CQE_F_MORE) - error(1, -EINVAL, "invalid notif flags"); + error(1, EINVAL, "invalid notif flags"); if (compl_cqes <= 0) - error(1, -EINVAL, "notification mismatch"); + error(1, EINVAL, "notification mismatch"); compl_cqes--; i--; io_uring_cqe_seen(&ring); @@ -174,14 +174,14 @@ static void do_tx(int domain, int type, int protocol) } if (cqe->flags & IORING_CQE_F_MORE) { if (cqe->user_data != ZC_TAG) - error(1, cqe->res, "unexpected F_MORE"); + error(1, -cqe->res, "unexpected F_MORE"); compl_cqes++; } if (cqe->res >= 0) { packets++; bytes += cqe->res; } else if (cqe->res != -EAGAIN) { - error(1, cqe->res, "send failed"); + error(1, -cqe->res, "send failed"); } io_uring_cqe_seen(&ring); } @@ -190,11 +190,11 @@ static void do_tx(int domain, int type, int protocol) while (compl_cqes) { ret = io_uring_wait_cqe(&ring, &cqe); if (ret) - error(1, ret, "wait cqe"); + error(1, -ret, "wait cqe"); if (cqe->flags & IORING_CQE_F_MORE) - error(1, -EINVAL, "invalid notif flags"); + error(1, EINVAL, "invalid notif flags"); if (!(cqe->flags & IORING_CQE_F_NOTIF)) - error(1, -EINVAL, "missing notif flag"); + error(1, EINVAL, "missing notif flag"); io_uring_cqe_seen(&ring); compl_cqes--; diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile index ce795bc0a1af..5339f56329e1 100644 --- a/tools/testing/selftests/net/lib/Makefile +++ b/tools/testing/selftests/net/lib/Makefile @@ -8,6 +8,7 @@ CFLAGS += -I../../ TEST_FILES := \ ../../../../net/ynl \ ../../../../../Documentation/netlink/specs \ + ksft_setup_loopback.sh \ # end of TEST_FILES TEST_GEN_FILES := \ diff --git a/tools/testing/selftests/net/lib/ksft_setup_loopback.sh b/tools/testing/selftests/net/lib/ksft_setup_loopback.sh new file mode 100755 index 000000000000..3defbb1919c5 --- /dev/null +++ b/tools/testing/selftests/net/lib/ksft_setup_loopback.sh @@ -0,0 +1,111 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Setup script for running ksft tests over a real interface in loopback mode. +# This scripts replaces the historical setup_loopback.sh. It puts +# a (presumably) real hardware interface into loopback mode, creates macvlan +# interfaces on top and places them in a network namespace for isolation. +# +# NETIF env variable must be exported to indicate the real target device. +# Note that the test will override NETIF with one of the macvlans, the +# actual ksft test will only see the macvlans. +# +# Example use: +# export NETIF=eth0 +# ./net/lib/ksft_setup_loopback.sh ./drivers/net/gro.py + +if [ -z "$NETIF" ]; then + echo "Error: NETIF variable not set" + exit 1 +fi +if ! [ -d "/sys/class/net/$NETIF" ]; then + echo "Error: Can't find $NETIF, invalid netdevice" + exit 1 +fi + +# Save original settings for cleanup +readonly FLUSH_PATH="/sys/class/net/${NETIF}/gro_flush_timeout" +readonly IRQ_PATH="/sys/class/net/${NETIF}/napi_defer_hard_irqs" +FLUSH_TIMEOUT="$(< "${FLUSH_PATH}")" +readonly FLUSH_TIMEOUT +HARD_IRQS="$(< "${IRQ_PATH}")" +readonly HARD_IRQS + +SERVER_NS=$(mktemp -u server-XXXXXXXX) +readonly SERVER_NS +CLIENT_NS=$(mktemp -u client-XXXXXXXX) +readonly CLIENT_NS +readonly SERVER_MAC="aa:00:00:00:00:02" +readonly CLIENT_MAC="aa:00:00:00:00:01" + +# ksft expects addresses to communicate with remote +export LOCAL_V6=2001:db8:1::1 +export REMOTE_V6=2001:db8:1::2 + +cleanup() { + local exit_code=$? + + echo "Cleaning up..." + + # Remove macvlan interfaces and namespaces + ip -netns "${SERVER_NS}" link del dev server 2>/dev/null || true + ip netns del "${SERVER_NS}" 2>/dev/null || true + ip -netns "${CLIENT_NS}" link del dev client 2>/dev/null || true + ip netns del "${CLIENT_NS}" 2>/dev/null || true + + # Disable loopback + ethtool -K "${NETIF}" loopback off 2>/dev/null || true + sleep 1 + + echo "${FLUSH_TIMEOUT}" >"${FLUSH_PATH}" + echo "${HARD_IRQS}" >"${IRQ_PATH}" + + exit $exit_code +} + +trap cleanup EXIT INT TERM + +# Enable loopback mode +echo "Enabling loopback on ${NETIF}..." +ethtool -K "${NETIF}" loopback on || { + echo "Failed to enable loopback mode" + exit 1 +} +# The interface may need time to get carrier back, but selftests +# will wait for carrier, so no need to wait / sleep here. + +# 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}" + +# Create server namespace with macvlan +ip netns add "${SERVER_NS}" +ip link add link "${NETIF}" dev server address "${SERVER_MAC}" type macvlan +ip link set dev server netns "${SERVER_NS}" +ip -netns "${SERVER_NS}" link set dev server up +ip -netns "${SERVER_NS}" addr add $LOCAL_V6/64 dev server +ip -netns "${SERVER_NS}" link set dev lo up + +# Create client namespace with macvlan +ip netns add "${CLIENT_NS}" +ip link add link "${NETIF}" dev client address "${CLIENT_MAC}" type macvlan +ip link set dev client netns "${CLIENT_NS}" +ip -netns "${CLIENT_NS}" link set dev client up +ip -netns "${CLIENT_NS}" addr add $REMOTE_V6/64 dev client +ip -netns "${CLIENT_NS}" link set dev lo up + +echo "Setup complete!" +echo " Device: ${NETIF}" +echo " Server NS: ${SERVER_NS}" +echo " Client NS: ${CLIENT_NS}" +echo "" + +# Setup environment variables for tests +export NETIF=server +export REMOTE_TYPE=netns +export REMOTE_ARGS="${CLIENT_NS}" + +# Run the command +ip netns exec "${SERVER_NS}" "$@" diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py index 97b7cf2b20eb..40f9ce307dd1 100644 --- a/tools/testing/selftests/net/lib/py/__init__.py +++ b/tools/testing/selftests/net/lib/py/__init__.py @@ -8,7 +8,8 @@ from .consts import KSRC from .ksft import KsftFailEx, KsftSkipEx, KsftXfailEx, ksft_pr, ksft_eq, \ ksft_ne, ksft_true, ksft_not_none, ksft_in, ksft_not_in, ksft_is, \ ksft_ge, ksft_gt, ksft_lt, ksft_raises, ksft_busy_wait, \ - ktap_result, ksft_disruptive, ksft_setup, ksft_run, ksft_exit + ktap_result, ksft_disruptive, ksft_setup, ksft_run, ksft_exit, \ + ksft_variants, KsftNamedVariant from .netns import NetNS, NetNSEnter from .nsim import NetdevSim, NetdevSimDev from .utils import CmdExitFailure, fd_read_timeout, cmd, bkg, defer, \ @@ -21,7 +22,7 @@ __all__ = ["KSRC", "ksft_ne", "ksft_true", "ksft_not_none", "ksft_in", "ksft_not_in", "ksft_is", "ksft_ge", "ksft_gt", "ksft_lt", "ksft_raises", "ksft_busy_wait", "ktap_result", "ksft_disruptive", "ksft_setup", - "ksft_run", "ksft_exit", + "ksft_run", "ksft_exit", "ksft_variants", "KsftNamedVariant", "NetNS", "NetNSEnter", "CmdExitFailure", "fd_read_timeout", "cmd", "bkg", "defer", "bpftool", "ip", "ethtool", "bpftrace", "rand_port", diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 83b1574f7719..531e7fa1b3ea 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -1,12 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 -import builtins import functools import inspect import signal import sys import time import traceback +from collections import namedtuple from .consts import KSFT_MAIN_NAME from .utils import global_defer_queue @@ -136,7 +136,7 @@ def ksft_busy_wait(cond, sleep=0.005, deadline=1, comment=""): time.sleep(sleep) -def ktap_result(ok, cnt=1, case="", comment=""): +def ktap_result(ok, cnt=1, case_name="", comment=""): global KSFT_RESULT_ALL KSFT_RESULT_ALL = KSFT_RESULT_ALL and ok @@ -146,8 +146,8 @@ def ktap_result(ok, cnt=1, case="", comment=""): res += "ok " res += str(cnt) + " " res += KSFT_MAIN_NAME - if case: - res += "." + str(case.__name__) + if case_name: + res += "." + case_name if comment: res += " # " + comment print(res, flush=True) @@ -163,7 +163,7 @@ def ksft_flush_defer(): entry = global_defer_queue.pop() try: entry.exec_only() - except: + except Exception: ksft_pr(f"Exception while handling defer / cleanup (callback {i} of {qlen_start})!") tb = traceback.format_exc() for line in tb.strip().split('\n'): @@ -171,6 +171,10 @@ def ksft_flush_defer(): KSFT_RESULT = False +KsftCaseFunction = namedtuple("KsftCaseFunction", + ['name', 'original_func', 'variants']) + + def ksft_disruptive(func): """ Decorator that marks the test as disruptive (e.g. the test @@ -181,11 +185,47 @@ def ksft_disruptive(func): @functools.wraps(func) def wrapper(*args, **kwargs): if not KSFT_DISRUPTIVE: - raise KsftSkipEx(f"marked as disruptive") + raise KsftSkipEx("marked as disruptive") return func(*args, **kwargs) return wrapper +class KsftNamedVariant: + """ Named string name + argument list tuple for @ksft_variants """ + + def __init__(self, name, *params): + self.params = params + self.name = name or "_".join([str(x) for x in self.params]) + + +def ksft_variants(params): + """ + Decorator defining the sets of inputs for a test. + The parameters will be included in the name of the resulting sub-case. + Parameters can be either single object, tuple or a KsftNamedVariant. + The argument can be a list or a generator. + + Example: + + @ksft_variants([ + (1, "a"), + (2, "b"), + KsftNamedVariant("three", 3, "c"), + ]) + def my_case(cfg, a, b): + pass # ... + + ksft_run(cases=[my_case], args=(cfg, )) + + Will generate cases: + my_case.1_a + my_case.2_b + my_case.three + """ + + return lambda func: KsftCaseFunction(func.__name__, func, params) + + def ksft_setup(env): """ Setup test framework global state from the environment. @@ -199,7 +239,7 @@ def ksft_setup(env): return False try: return bool(int(value)) - except: + except Exception: raise Exception(f"failed to parse {name}") if "DISRUPTIVE" in env: @@ -220,9 +260,13 @@ def _ksft_intr(signum, frame): ksft_pr(f"Ignoring SIGTERM (cnt: {term_cnt}), already exiting...") -def ksft_run(cases=None, globs=None, case_pfx=None, args=()): +def _ksft_generate_test_cases(cases, globs, case_pfx, args): + """Generate a flat list of (func, args, name) tuples""" + cases = cases or [] + test_cases = [] + # If using the globs method find all relevant functions if globs and case_pfx: for key, value in globs.items(): if not callable(value): @@ -232,6 +276,27 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()): cases.append(value) break + for func in cases: + if isinstance(func, KsftCaseFunction): + # Parametrized test - create case for each param + for param in func.variants: + if not isinstance(param, KsftNamedVariant): + if not isinstance(param, tuple): + param = (param, ) + param = KsftNamedVariant(None, *param) + + test_cases.append((func.original_func, + (*args, *param.params), + func.name + "." + param.name)) + else: + test_cases.append((func, args, func.__name__)) + + return test_cases + + +def ksft_run(cases=None, globs=None, case_pfx=None, args=()): + test_cases = _ksft_generate_test_cases(cases, globs, case_pfx, args) + global term_cnt term_cnt = 0 prev_sigterm = signal.signal(signal.SIGTERM, _ksft_intr) @@ -239,19 +304,19 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()): totals = {"pass": 0, "fail": 0, "skip": 0, "xfail": 0} print("TAP version 13", flush=True) - print("1.." + str(len(cases)), flush=True) + print("1.." + str(len(test_cases)), flush=True) global KSFT_RESULT cnt = 0 stop = False - for case in cases: + for func, args, name in test_cases: KSFT_RESULT = True cnt += 1 comment = "" cnt_key = "" try: - case(*args) + func(*args) except KsftSkipEx as e: comment = "SKIP " + str(e) cnt_key = 'skip' @@ -268,12 +333,26 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()): KSFT_RESULT = False cnt_key = 'fail' - ksft_flush_defer() + try: + ksft_flush_defer() + except BaseException as e: + tb = traceback.format_exc() + for line in tb.strip().split('\n'): + ksft_pr("Exception|", line) + if isinstance(e, KeyboardInterrupt): + ksft_pr() + ksft_pr("WARN: defer() interrupted, cleanup may be incomplete.") + ksft_pr(" Attempting to finish cleanup before exiting.") + ksft_pr(" Interrupt again to exit immediately.") + ksft_pr() + stop = True + # Flush was interrupted, try to finish the job best we can + ksft_flush_defer() if not cnt_key: cnt_key = 'pass' if KSFT_RESULT else 'fail' - ktap_result(KSFT_RESULT, cnt, case, comment=comment) + ktap_result(KSFT_RESULT, cnt, name, comment=comment) totals[cnt_key] += 1 if stop: diff --git a/tools/testing/selftests/net/lib/py/nsim.py b/tools/testing/selftests/net/lib/py/nsim.py index 1a8cbe9acc48..7c640ed64c0b 100644 --- a/tools/testing/selftests/net/lib/py/nsim.py +++ b/tools/testing/selftests/net/lib/py/nsim.py @@ -27,7 +27,7 @@ class NetdevSim: self.port_index = port_index self.ns = ns self.dfs_dir = "%s/ports/%u/" % (nsimdev.dfs_dir, port_index) - ret = ip("-j link show dev %s" % ifname, ns=ns) + ret = ip("-d -j link show dev %s" % ifname, ns=ns) self.dev = json.loads(ret.stdout)[0] self.ifindex = self.dev["ifindex"] diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py index cb40ecef9456..106ee1f2df86 100644 --- a/tools/testing/selftests/net/lib/py/utils.py +++ b/tools/testing/selftests/net/lib/py/utils.py @@ -32,7 +32,7 @@ class cmd: Use bkg() instead to run a command in the background. """ def __init__(self, comm, shell=None, fail=True, ns=None, background=False, - host=None, timeout=5, ksft_wait=None): + host=None, timeout=5, ksft_ready=None, ksft_wait=None): if ns: comm = f'ip netns exec {ns} ' + comm @@ -52,21 +52,25 @@ class cmd: # ksft_wait lets us wait for the background process to fully start, # we pass an FD to the child process, and wait for it to write back. # Similarly term_fd tells child it's time to exit. - pass_fds = () + pass_fds = [] env = os.environ.copy() if ksft_wait is not None: - rfd, ready_fd = os.pipe() wait_fd, self.ksft_term_fd = os.pipe() - pass_fds = (ready_fd, wait_fd, ) - env["KSFT_READY_FD"] = str(ready_fd) + pass_fds.append(wait_fd) env["KSFT_WAIT_FD"] = str(wait_fd) + ksft_ready = True # ksft_wait implies ready + if ksft_ready is not None: + rfd, ready_fd = os.pipe() + pass_fds.append(ready_fd) + env["KSFT_READY_FD"] = str(ready_fd) self.proc = subprocess.Popen(comm, shell=shell, stdout=subprocess.PIPE, stderr=subprocess.PIPE, pass_fds=pass_fds, env=env) if ksft_wait is not None: - os.close(ready_fd) os.close(wait_fd) + if ksft_ready is not None: + os.close(ready_fd) msg = fd_read_timeout(rfd, ksft_wait) os.close(rfd) if not msg: @@ -116,10 +120,10 @@ class bkg(cmd): with bkg("my_binary", ksft_wait=5): """ def __init__(self, comm, shell=None, fail=None, ns=None, host=None, - exit_wait=False, ksft_wait=None): + exit_wait=False, ksft_ready=None, ksft_wait=None): super().__init__(comm, background=True, shell=shell, fail=fail, ns=ns, host=host, - ksft_wait=ksft_wait) + ksft_ready=ksft_ready, ksft_wait=ksft_wait) self.terminate = not exit_wait and not ksft_wait self._exit_wait = exit_wait self.check_fail = fail diff --git a/tools/testing/selftests/net/lib/xdp_native.bpf.c b/tools/testing/selftests/net/lib/xdp_native.bpf.c index c368fc045f4b..64f05229ab24 100644 --- a/tools/testing/selftests/net/lib/xdp_native.bpf.c +++ b/tools/testing/selftests/net/lib/xdp_native.bpf.c @@ -332,7 +332,7 @@ static __u16 csum_fold_helper(__u32 csum) } static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset, - __u32 hdr_len) + unsigned long hdr_len) { char tmp_buff[MAX_ADJST_OFFSET]; __u32 buff_pos, udp_csum = 0; @@ -422,8 +422,9 @@ static int xdp_adjst_tail(struct xdp_md *ctx, __u16 port) { struct udphdr *udph = NULL; __s32 *adjust_offset, *val; - __u32 key, hdr_len; + unsigned long hdr_len; void *offset_ptr; + __u32 key; __u8 tag; int ret; diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index fc7e22b503d3..404a77bf366a 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -1072,6 +1072,8 @@ static void check_getpeername_connect(int fd) socklen_t salen = sizeof(ss); char a[INET6_ADDRSTRLEN]; char b[INET6_ADDRSTRLEN]; + const char *iface; + size_t len; if (getpeername(fd, (struct sockaddr *)&ss, &salen) < 0) { perror("getpeername"); @@ -1081,7 +1083,13 @@ static void check_getpeername_connect(int fd) xgetnameinfo((struct sockaddr *)&ss, salen, a, sizeof(a), b, sizeof(b)); - if (strcmp(cfg_host, a) || strcmp(cfg_port, b)) + iface = strchr(cfg_host, '%'); + if (iface) + len = iface - cfg_host; + else + len = strlen(cfg_host) + 1; + + if (strncmp(cfg_host, a, len) || strcmp(cfg_port, b)) fprintf(stderr, "%s: %s vs %s, %s vs %s\n", __func__, cfg_host, a, cfg_port, b); } diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 9b7b93f8eb0c..a6447f7a31fe 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -375,81 +375,75 @@ do_transfer() local capfile="${rndh}-${connector_ns:0:3}-${listener_ns:0:3}-${cl_proto}-${srv_proto}-${connect_addr}-${port}" local capopt="-i any -s 65535 -B 32768 ${capuser}" - ip netns exec ${listener_ns} tcpdump ${capopt} -w "${capfile}-listener.pcap" >> "${capout}" 2>&1 & + ip netns exec ${listener_ns} tcpdump ${capopt} \ + -w "${capfile}-listener.pcap" >> "${capout}" 2>&1 & local cappid_listener=$! - ip netns exec ${connector_ns} tcpdump ${capopt} -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 & - local cappid_connector=$! + if [ ${listener_ns} != ${connector_ns} ]; then + ip netns exec ${connector_ns} tcpdump ${capopt} \ + -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 & + local cappid_connector=$! + fi sleep 1 fi - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat -n + mptcp_lib_nstat_init "${listener_ns}" if [ ${listener_ns} != ${connector_ns} ]; then - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat -n - fi - - local stat_synrx_last_l - local stat_ackrx_last_l - local stat_cookietx_last - local stat_cookierx_last - local stat_csum_err_s - local stat_csum_err_c - local stat_tcpfb_last_l - stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") - stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") - stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") - stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") - stat_tcpfb_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") - - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_args $local_addr < "$sin" > "$sout" & + mptcp_lib_nstat_init "${connector_ns}" + fi + + ip netns exec ${listener_ns} \ + ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ + $extra_args $local_addr < "$sin" > "$sout" & local spid=$! mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" local start start=$(date +%s%3N) - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_args $connect_addr < "$cin" > "$cout" & + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_args $connect_addr < "$cin" > "$cout" & local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${listener_ns}" \ + "${connector_ns}" "${port}" "${cpid}" "${spid}" & + local timeout_pid=$! + wait $cpid local retc=$? wait $spid local rets=$? + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + local stop stop=$(date +%s%3N) if $capture; then sleep 1 kill ${cappid_listener} - kill ${cappid_connector} + if [ ${listener_ns} != ${connector_ns} ]; then + kill ${cappid_connector} + fi fi - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat | grep Tcp > /tmp/${listener_ns}.out + mptcp_lib_nstat_get "${listener_ns}" if [ ${listener_ns} != ${connector_ns} ]; then - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat | grep Tcp > /tmp/${connector_ns}.out + mptcp_lib_nstat_get "${connector_ns}" fi local duration duration=$((stop-start)) printf "(duration %05sms) " "${duration}" - if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then mptcp_lib_pr_fail "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ - "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" echo cat "$capout" @@ -463,38 +457,38 @@ do_transfer() rets=$? local extra="" - local stat_synrx_now_l - local stat_ackrx_now_l - local stat_cookietx_now - local stat_cookierx_now - local stat_ooo_now - local stat_tcpfb_now_l - stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") - stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") - stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") - stat_tcpfb_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") - - expect_synrx=$((stat_synrx_last_l)) - expect_ackrx=$((stat_ackrx_last_l)) + local stat_synrx + local stat_ackrx + local stat_cookietx + local stat_cookierx + local stat_ooo + local stat_tcpfb + stat_synrx=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + stat_ackrx=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + stat_cookietx=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") + stat_cookierx=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") + stat_ooo=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") + stat_tcpfb=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") + + expect_synrx=0 + expect_ackrx=0 cookies=$(ip netns exec ${listener_ns} sysctl net.ipv4.tcp_syncookies) cookies=${cookies##*=} if [ ${cl_proto} = "MPTCP" ] && [ ${srv_proto} = "MPTCP" ]; then - expect_synrx=$((stat_synrx_last_l+connect_per_transfer)) - expect_ackrx=$((stat_ackrx_last_l+connect_per_transfer)) + expect_synrx=${connect_per_transfer} + expect_ackrx=${connect_per_transfer} fi - if [ ${stat_synrx_now_l} -lt ${expect_synrx} ]; then - mptcp_lib_pr_fail "lower MPC SYN rx (${stat_synrx_now_l})" \ + if [ ${stat_synrx} -lt ${expect_synrx} ]; then + mptcp_lib_pr_fail "lower MPC SYN rx (${stat_synrx})" \ "than expected (${expect_synrx})" retc=1 fi - if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} ]; then - if [ ${stat_ooo_now} -eq 0 ]; then - mptcp_lib_pr_fail "lower MPC ACK rx (${stat_ackrx_now_l})" \ + if [ ${stat_ackrx} -lt ${expect_ackrx} ]; then + if [ ${stat_ooo} -eq 0 ]; then + mptcp_lib_pr_fail "lower MPC ACK rx (${stat_ackrx})" \ "than expected (${expect_ackrx})" rets=1 else @@ -508,47 +502,45 @@ do_transfer() csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") - local csum_err_s_nr=$((csum_err_s - stat_csum_err_s)) - if [ $csum_err_s_nr -gt 0 ]; then - mptcp_lib_pr_fail "server got ${csum_err_s_nr} data checksum error[s]" + if [ $csum_err_s -gt 0 ]; then + mptcp_lib_pr_fail "server got ${csum_err_s} data checksum error[s]" rets=1 fi - local csum_err_c_nr=$((csum_err_c - stat_csum_err_c)) - if [ $csum_err_c_nr -gt 0 ]; then - mptcp_lib_pr_fail "client got ${csum_err_c_nr} data checksum error[s]" + if [ $csum_err_c -gt 0 ]; then + mptcp_lib_pr_fail "client got ${csum_err_c} data checksum error[s]" retc=1 fi fi - if [ ${stat_ooo_now} -eq 0 ] && [ ${stat_tcpfb_last_l} -ne ${stat_tcpfb_now_l} ]; then + if [ ${stat_ooo} -eq 0 ] && [ ${stat_tcpfb} -gt 0 ]; then mptcp_lib_pr_fail "unexpected fallback to TCP" rets=1 fi if [ $cookies -eq 2 ];then - if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then + if [ $stat_cookietx -eq 0 ] ;then extra+=" WARN: CookieSent: did not advance" fi - if [ $stat_cookierx_last -ge $stat_cookierx_now ] ;then + if [ $stat_cookierx -eq 0 ] ;then extra+=" WARN: CookieRecv: did not advance" fi else - if [ $stat_cookietx_last -ne $stat_cookietx_now ] ;then + if [ $stat_cookietx -gt 0 ] ;then extra+=" WARN: CookieSent: changed" fi - if [ $stat_cookierx_last -ne $stat_cookierx_now ] ;then + if [ $stat_cookierx -gt 0 ] ;then extra+=" WARN: CookieRecv: changed" fi fi - if [ ${stat_synrx_now_l} -gt ${expect_synrx} ]; then + if [ ${stat_synrx} -gt ${expect_synrx} ]; then extra+=" WARN: SYNRX: expect ${expect_synrx}," - extra+=" got ${stat_synrx_now_l} (probably retransmissions)" + extra+=" got ${stat_synrx} (probably retransmissions)" fi - if [ ${stat_ackrx_now_l} -gt ${expect_ackrx} ]; then + if [ ${stat_ackrx} -gt ${expect_ackrx} ]; then extra+=" WARN: ACKRX: expect ${expect_ackrx}," - extra+=" got ${stat_ackrx_now_l} (probably retransmissions)" + extra+=" got ${stat_ackrx} (probably retransmissions)" fi if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 43f31f8d587f..b2e6e548f796 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -62,6 +62,7 @@ unset sflags unset fastclose unset fullmesh unset speed +unset bind_addr unset join_syn_rej unset join_csum_ns1 unset join_csum_ns2 @@ -645,6 +646,27 @@ wait_mpj() done } +wait_ll_ready() +{ + local ns="${1}" + + local i + for i in $(seq 50); do + ip -n "${ns}" -6 addr show scope link | grep "inet6 fe80" | + grep -qw "tentative" || break + sleep 0.1 + done +} + +get_ll_addr() +{ + local ns="${1}" + local iface="${2}" + + ip -n "${ns}" -6 addr show dev "${iface}" scope link | + grep "inet6 fe80" | sed 's#.*\(fe80::.*\)/.*#\1#' +} + kill_events_pids() { mptcp_lib_kill_wait $evts_ns1_pid @@ -951,6 +973,9 @@ do_transfer() local FAILING_LINKS=${FAILING_LINKS:-""} local fastclose=${fastclose:-""} local speed=${speed:-"fast"} + local bind_addr=${bind_addr:-"::"} + local listener_in="${sin}" + local connector_in="${cin}" port=$(get_port) :> "$cout" @@ -958,10 +983,8 @@ do_transfer() cond_start_capture ${listener_ns} - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat -n - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat -n + mptcp_lib_nstat_init "${listener_ns}" + mptcp_lib_nstat_init "${connector_ns}" local extra_args if [ $speed = "fast" ]; then @@ -999,42 +1022,40 @@ do_transfer() extra_srv_args="$extra_args $extra_srv_args" if [ "$test_linkfail" -gt 1 ];then - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_srv_args "::" < "$sinfail" > "$sout" & - else - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_srv_args "::" < "$sin" > "$sout" & + listener_in="${sinfail}" fi + ip netns exec ${listener_ns} \ + ./mptcp_connect -t ${timeout_poll} -l -p ${port} -s ${srv_proto} \ + ${extra_srv_args} "${bind_addr}" < "${listener_in}" > "${sout}" & local spid=$! mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" extra_cl_args="$extra_args $extra_cl_args" if [ "$test_linkfail" -eq 0 ];then - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_cl_args $connect_addr < "$cin" > "$cout" & + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr < "$cin" > "$cout" & elif [ "$test_linkfail" -eq 1 ] || [ "$test_linkfail" -eq 2 ];then + connector_in="${cinsent}" ( cat "$cinfail" ; sleep 2; link_failure $listener_ns ; cat "$cinfail" ) | \ tee "$cinsent" | \ - timeout ${timeout_test} \ ip netns exec ${connector_ns} \ ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ $extra_cl_args $connect_addr > "$cout" & else + connector_in="${cinsent}" tee "$cinsent" < "$cinfail" | \ - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_cl_args $connect_addr > "$cout" & + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr > "$cout" & fi local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${listener_ns}" \ + "${connector_ns}" "${port}" "${cpid}" "${spid}" & + local timeout_pid=$! + pm_nl_set_endpoint $listener_ns $connector_ns $connect_addr check_cestab $listener_ns $connector_ns @@ -1043,31 +1064,26 @@ do_transfer() wait $spid local rets=$? + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + cond_stop_capture - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat | grep Tcp > /tmp/${listener_ns}.out - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat | grep Tcp > /tmp/${connector_ns}.out + mptcp_lib_nstat_get "${listener_ns}" + mptcp_lib_nstat_get "${connector_ns}" - if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then fail_test "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ - "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" return 1 fi - if [ "$test_linkfail" -gt 1 ];then - check_transfer $sinfail $cout "file received by client" $trunc_size - else - check_transfer $sin $cout "file received by client" $trunc_size - fi + check_transfer $listener_in $cout "file received by client" $trunc_size retc=$? - if [ "$test_linkfail" -eq 0 ];then - check_transfer $cin $sout "file received by server" $trunc_size - else - check_transfer $cinsent $sout "file received by server" $trunc_size - fi + check_transfer $connector_in $sout "file received by server" $trunc_size rets=$? [ $retc -eq 0 ] && [ $rets -eq 0 ] @@ -1136,12 +1152,20 @@ run_tests() do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} } +_dump_stats() +{ + local ns="${1}" + local side="${2}" + + mptcp_lib_print_err "${side} ns stats (${ns2})" + mptcp_lib_pr_nstat "${ns}" + echo +} + dump_stats() { - echo Server ns stats - ip netns exec $ns1 nstat -as | grep Tcp - echo Client ns stats - ip netns exec $ns2 nstat -as | grep Tcp + _dump_stats "${ns1}" "Server" + _dump_stats "${ns2}" "Client" } chk_csum_nr() @@ -2952,7 +2976,11 @@ mixed_tests() pm_nl_add_endpoint $ns1 10.0.1.1 flags signal speed=slow \ run_tests $ns1 $ns2 dead:beef:2::1 - chk_join_nr 1 1 1 + if mptcp_lib_kallsyms_has "mptcp_pm_get_endp_fullmesh_max$"; then + chk_join_nr 0 0 0 + else + chk_join_nr 1 1 1 + fi fi # fullmesh still tries to create all the possibly subflows with @@ -3233,6 +3261,133 @@ add_addr_ports_tests() fi } +bind_tests() +{ + # bind to one address should not allow extra subflows to other addresses + if reset "bind main address v4, no join v4"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + bind_addr="10.0.1.1" \ + run_tests $ns1 $ns2 10.0.1.1 + join_syn_tx=1 \ + chk_join_nr 0 0 0 + chk_add_nr 1 1 + fi + + # bind to one address should not allow extra subflows to other addresses + if reset "bind main address v6, no join v6"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + bind_addr="dead:beef:1::1" \ + run_tests $ns1 $ns2 dead:beef:1::1 + join_syn_tx=1 \ + chk_join_nr 0 0 0 + chk_add_nr 1 1 + fi + + # multiple binds to allow extra subflows to other addresses + if reset "multiple bind to allow joins v4"; then + local extra_bind + + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + + # Launching another app listening on a different address + # Note: it could be a totally different app, e.g. nc, socat, ... + ip netns exec ${ns1} ./mptcp_connect -l -t -1 -p "$(get_port)" \ + -s MPTCP 10.0.2.1 & + extra_bind=$! + + bind_addr="10.0.1.1" \ + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + + kill ${extra_bind} + fi + + # multiple binds to allow extra subflows to other addresses + if reset "multiple bind to allow joins v6"; then + local extra_bind + + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + + # Launching another app listening on a different address + # Note: it could be a totally different app, e.g. nc, socat, ... + ip netns exec ${ns1} ./mptcp_connect -l -t -1 -p "$(get_port)" \ + -s MPTCP dead:beef:2::1 & + extra_bind=$! + + bind_addr="dead:beef:1::1" \ + run_tests $ns1 $ns2 dead:beef:1::1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + + kill ${extra_bind} + fi + + # multiple binds to allow extra subflows to other addresses: v6 LL case + if reset "multiple bind to allow joins v6 link-local routing"; then + local extra_bind ns1ll1 ns1ll2 + + ns1ll1="$(get_ll_addr $ns1 ns1eth1)" + ns1ll2="$(get_ll_addr $ns1 ns1eth2)" + + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 "${ns1ll2}" flags signal + + wait_ll_ready $ns1 # to be able to bind + wait_ll_ready $ns2 # also needed to bind on the client side + ip netns exec ${ns1} ./mptcp_connect -l -t -1 -p "$(get_port)" \ + -s MPTCP "${ns1ll2}%ns1eth2" & + extra_bind=$! + + bind_addr="${ns1ll1}%ns1eth1" \ + run_tests $ns1 $ns2 "${ns1ll1}%ns2eth1" + # it is not possible to connect to the announced LL addr without + # specifying the outgoing interface. + join_connect_err=1 \ + chk_join_nr 0 0 0 + chk_add_nr 1 1 + + kill ${extra_bind} + fi + + # multiple binds to allow extra subflows to v6 LL addresses: laminar + if reset "multiple bind to allow joins v6 link-local laminar" && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then + local extra_bind ns1ll1 ns1ll2 ns2ll2 + + ns1ll1="$(get_ll_addr $ns1 ns1eth1)" + ns1ll2="$(get_ll_addr $ns1 ns1eth2)" + ns2ll2="$(get_ll_addr $ns2 ns2eth2)" + + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 "${ns1ll2}" flags signal + pm_nl_add_endpoint $ns2 "${ns2ll2}" flags laminar dev ns2eth2 + + wait_ll_ready $ns1 # to be able to bind + wait_ll_ready $ns2 # also needed to bind on the client side + ip netns exec ${ns1} ./mptcp_connect -l -t -1 -p "$(get_port)" \ + -s MPTCP "${ns1ll2}%ns1eth2" & + extra_bind=$! + + bind_addr="${ns1ll1}%ns1eth1" \ + run_tests $ns1 $ns2 "${ns1ll1}%ns2eth1" + chk_join_nr 1 1 1 + chk_add_nr 1 1 + + kill ${extra_bind} + fi +} + syncookies_tests() { # single subflow, syncookies @@ -4192,6 +4347,7 @@ all_tests_sorted=( M@mixed_tests b@backup_tests p@add_addr_ports_tests + B@bind_tests k@syncookies_tests S@checksum_tests d@deny_join_id0_tests diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index f4388900016a..5fea7e7df628 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -106,23 +106,32 @@ mptcp_lib_pr_info() { mptcp_lib_print_info "INFO: ${*}" } -# $1-2: listener/connector ns ; $3 port ; $4-5 listener/connector stat file +mptcp_lib_pr_nstat() { + local ns="${1}" + local hist="/tmp/${ns}.out" + + if [ -f "${hist}" ]; then + awk '$2 != 0 { print " "$0 }' "${hist}" + else + ip netns exec "${ns}" nstat -as | grep Tcp + fi +} + +# $1-2: listener/connector ns ; $3 port mptcp_lib_pr_err_stats() { local lns="${1}" local cns="${2}" local port="${3}" - local lstat="${4}" - local cstat="${5}" echo -en "${MPTCP_LIB_COLOR_RED}" { printf "\nnetns %s (listener) socket stat for %d:\n" "${lns}" "${port}" ip netns exec "${lns}" ss -Menitam -o "sport = :${port}" - cat "${lstat}" + mptcp_lib_pr_nstat "${lns}" printf "\nnetns %s (connector) socket stat for %d:\n" "${cns}" "${port}" ip netns exec "${cns}" ss -Menitam -o "dport = :${port}" - [ "${lstat}" != "${cstat}" ] && cat "${cstat}" + [ "${lns}" != "${cns}" ] && mptcp_lib_pr_nstat "${cns}" } 1>&2 echo -en "${MPTCP_LIB_COLOR_RESET}" } @@ -341,6 +350,19 @@ mptcp_lib_evts_get_info() { mptcp_lib_get_info_value "${1}" "^type:${3:-1}," } +mptcp_lib_wait_timeout() { + local timeout_test="${1}" + local listener_ns="${2}" + local connector_ns="${3}" + local port="${4}" + shift 4 # rest are PIDs + + sleep "${timeout_test}" + mptcp_lib_print_err "timeout" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" + kill "${@}" 2>/dev/null +} + # $1: PID mptcp_lib_kill_wait() { [ "${1}" -eq 0 ] && return 0 @@ -376,14 +398,36 @@ mptcp_lib_is_v6() { [ -z "${1##*:*}" ] } +mptcp_lib_nstat_init() { + local ns="${1}" + + rm -f "/tmp/${ns}."{nstat,out} + NSTAT_HISTORY="/tmp/${ns}.nstat" ip netns exec "${ns}" nstat -n +} + +mptcp_lib_nstat_get() { + local ns="${1}" + + # filter out non-*TCP stats, and the rate (last column) + NSTAT_HISTORY="/tmp/${ns}.nstat" ip netns exec "${ns}" nstat -sz | + grep -o ".*Tcp\S\+\s\+[0-9]\+" > "/tmp/${ns}.out" +} + # $1: ns, $2: MIB counter +# Get the counter from the history (mptcp_lib_nstat_{init,get}()) if available. +# If not, get the counter from nstat ignoring any history. mptcp_lib_get_counter() { local ns="${1}" local counter="${2}" + local hist="/tmp/${ns}.out" local count - count=$(ip netns exec "${ns}" nstat -asz "${counter}" | - awk 'NR==1 {next} {print $2}') + if [[ -s "${hist}" && "${counter}" == *"Tcp"* ]]; then + count=$(awk "/^${counter} / {print \$2; exit}" "${hist}") + else + count=$(ip netns exec "${ns}" nstat -asz "${counter}" | + awk 'NR==1 {next} {print $2}') + fi if [ -z "${count}" ]; then mptcp_lib_fail_if_expected_feature "${counter} counter" return 1 diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index f01989be6e9b..ab8bce06b262 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -169,41 +169,44 @@ do_transfer() cmsg+=",TCPINQ" fi - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat -n - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat -n - - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ - ${local_addr} < "$sin" > "$sout" & + mptcp_lib_nstat_init "${listener_ns}" + mptcp_lib_nstat_init "${connector_ns}" + + ip netns exec ${listener_ns} \ + $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ + ${local_addr} < "$sin" > "$sout" & local spid=$! - sleep 1 + mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c "${cmsg}" \ - $connect_addr < "$cin" > "$cout" & + ip netns exec ${connector_ns} \ + $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c "${cmsg}" \ + $connect_addr < "$cin" > "$cout" & local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${listener_ns}" \ + "${connector_ns}" "${port}" "${cpid}" "${spid}" & + local timeout_pid=$! + wait $cpid local retc=$? wait $spid local rets=$? - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat | grep Tcp > /tmp/${listener_ns}.out - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat | grep Tcp > /tmp/${connector_ns}.out + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + + mptcp_lib_nstat_get "${listener_ns}" + mptcp_lib_nstat_get "${connector_ns}" print_title "Transfer ${ip:2}" - if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then mptcp_lib_pr_fail "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ - "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" mptcp_lib_result_fail "transfer ${ip}" diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 1903e8e84a31..806aaa7d2d61 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -155,48 +155,53 @@ do_transfer() sleep 1 fi - NSTAT_HISTORY=/tmp/${ns3}.nstat ip netns exec ${ns3} \ - nstat -n - NSTAT_HISTORY=/tmp/${ns1}.nstat ip netns exec ${ns1} \ - nstat -n - - timeout ${timeout_test} \ - ip netns exec ${ns3} \ - ./mptcp_connect -jt ${timeout_poll} -l -p $port -T $max_time \ - 0.0.0.0 < "$sin" > "$sout" & + mptcp_lib_nstat_init "${ns3}" + mptcp_lib_nstat_init "${ns1}" + + ip netns exec ${ns3} \ + ./mptcp_connect -jt ${timeout_poll} -l -p $port -T $max_time \ + 0.0.0.0 < "$sin" > "$sout" & local spid=$! mptcp_lib_wait_local_port_listen "${ns3}" "${port}" - timeout ${timeout_test} \ - ip netns exec ${ns1} \ - ./mptcp_connect -jt ${timeout_poll} -p $port -T $max_time \ - 10.0.3.3 < "$cin" > "$cout" & + ip netns exec ${ns1} \ + ./mptcp_connect -jt ${timeout_poll} -p $port -T $max_time \ + 10.0.3.3 < "$cin" > "$cout" & local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${ns3}" "${ns1}" "${port}" \ + "${cpid}" "${spid}" & + local timeout_pid=$! + wait $cpid local retc=$? wait $spid local rets=$? + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + if $capture; then sleep 1 kill ${cappid_listener} kill ${cappid_connector} fi - NSTAT_HISTORY=/tmp/${ns3}.nstat ip netns exec ${ns3} \ - nstat | grep Tcp > /tmp/${ns3}.out - NSTAT_HISTORY=/tmp/${ns1}.nstat ip netns exec ${ns1} \ - nstat | grep Tcp > /tmp/${ns1}.out + mptcp_lib_nstat_get "${ns3}" + mptcp_lib_nstat_get "${ns1}" cmp $sin $cout > /dev/null 2>&1 local cmps=$? cmp $cin $sout > /dev/null 2>&1 local cmpc=$? - if [ $retc -eq 0 ] && [ $rets -eq 0 ] && \ - [ $cmpc -eq 0 ] && [ $cmps -eq 0 ]; then + if [ $retc -eq 0 ] && [ $rets -eq 0 ] && + [ $cmpc -eq 0 ] && [ $cmps -eq 0 ] && + [ $timeout_pid -eq 0 ]; then printf "%-16s" " max $max_time " mptcp_lib_pr_ok cat "$capout" @@ -204,8 +209,7 @@ do_transfer() fi mptcp_lib_pr_fail "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${ns3}" "${ns1}" "${port}" \ - "/tmp/${ns3}.out" "/tmp/${ns1}.out" + mptcp_lib_pr_err_stats "${ns3}" "${ns1}" "${port}" ls -l $sin $cout ls -l $cin $sout diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 87323942cb8a..e9ae1806ab07 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -211,7 +211,8 @@ make_connection() ip netns exec "$ns1" \ ./mptcp_connect -s MPTCP -w 300 -p $app_port -l $listen_addr > /dev/null 2>&1 & local server_pid=$! - sleep 0.5 + + mptcp_lib_wait_local_port_listen "${ns1}" "${port}" # Run the client, transfer $file and stay connected to the server # to conduct tests diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh index 45832df98295..a68bc882fa4e 100755 --- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh @@ -127,6 +127,8 @@ ip -net "$nsr1" addr add fee1:2::1/64 dev veth1 nodad ip -net "$nsr2" addr add 192.168.10.2/24 dev veth0 ip -net "$nsr2" addr add fee1:2::2/64 dev veth0 nodad +ip netns exec "$nsr1" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec "$nsr2" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null for i in 0 1; do ip netns exec "$nsr1" sysctl net.ipv4.conf.veth$i.forwarding=1 > /dev/null ip netns exec "$nsr2" sysctl net.ipv4.conf.veth$i.forwarding=1 > /dev/null @@ -153,7 +155,9 @@ ip -net "$ns1" route add default via dead:1::1 ip -net "$ns2" route add default via dead:2::1 ip -net "$nsr1" route add default via 192.168.10.2 +ip -6 -net "$nsr1" route add default via fee1:2::2 ip -net "$nsr2" route add default via 192.168.10.1 +ip -6 -net "$nsr2" route add default via fee1:2::1 ip netns exec "$nsr1" nft -f - <<EOF table inet filter { @@ -352,8 +356,9 @@ test_tcp_forwarding_ip() local nsa=$1 local nsb=$2 local pmtu=$3 - local dstip=$4 - local dstport=$5 + local proto=$4 + local dstip=$5 + local dstport=$6 local lret=0 local socatc local socatl @@ -363,12 +368,14 @@ test_tcp_forwarding_ip() infile="$nsin_small" fi - timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$infile" > "$ns2out" & + timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -${proto} \ + TCP"${proto}"-LISTEN:12345,reuseaddr STDIO < "$infile" > "$ns2out" & lpid=$! busywait 1000 listener_ready - timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$infile" > "$ns1out" + timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -${proto} \ + TCP"${proto}":"$dstip":"$dstport" STDIO < "$infile" > "$ns1out" socatc=$? wait $lpid @@ -394,8 +401,11 @@ test_tcp_forwarding_ip() test_tcp_forwarding() { local pmtu="$3" + local proto="$4" + local dstip="$5" + local dstport="$6" - test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345 + test_tcp_forwarding_ip "$1" "$2" "$pmtu" "$proto" "$dstip" "$dstport" return $? } @@ -403,6 +413,9 @@ test_tcp_forwarding() test_tcp_forwarding_set_dscp() { local pmtu="$3" + local proto="$4" + local dstip="$5" + local dstport="$6" ip netns exec "$nsr1" nft -f - <<EOF table netdev dscpmangle { @@ -413,7 +426,7 @@ table netdev dscpmangle { } EOF if [ $? -eq 0 ]; then - test_tcp_forwarding_ip "$1" "$2" "$3" 10.0.2.99 12345 + test_tcp_forwarding_ip "$1" "$2" "$pmtu" "$proto" "$dstip" "$dstport" check_dscp "dscp_ingress" "$pmtu" ip netns exec "$nsr1" nft delete table netdev dscpmangle @@ -430,7 +443,7 @@ table netdev dscpmangle { } EOF if [ $? -eq 0 ]; then - test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345 + test_tcp_forwarding_ip "$1" "$2" "$pmtu" "$proto" "$dstip" "$dstport" check_dscp "dscp_egress" "$pmtu" ip netns exec "$nsr1" nft delete table netdev dscpmangle @@ -441,7 +454,7 @@ fi # partial. If flowtable really works, then both dscp-is-0 and dscp-is-cs3 # counters should have seen packets (before and after ft offload kicks in). ip netns exec "$nsr1" nft -a insert rule inet filter forward ip dscp set cs3 - test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345 + test_tcp_forwarding_ip "$1" "$2" "$pmtu" "$proto" "$dstip" "$dstport" check_dscp "dscp_fwd" "$pmtu" } @@ -455,7 +468,7 @@ test_tcp_forwarding_nat() [ "$pmtu" -eq 0 ] && what="$what (pmtu disabled)" - test_tcp_forwarding_ip "$nsa" "$nsb" "$pmtu" 10.0.2.99 12345 + test_tcp_forwarding_ip "$nsa" "$nsb" "$pmtu" 4 10.0.2.99 12345 lret=$? if [ "$lret" -eq 0 ] ; then @@ -465,7 +478,7 @@ test_tcp_forwarding_nat() echo "PASS: flow offload for ns1/ns2 with masquerade $what" fi - test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.6.6.6 1666 + test_tcp_forwarding_ip "$1" "$2" "$pmtu" 4 10.6.6.6 1666 lret=$? if [ "$pmtu" -eq 1 ] ;then check_counters "flow offload for ns1/ns2 with dnat $what" @@ -487,7 +500,7 @@ make_file "$nsin_small" "$filesize_small" # Due to MTU mismatch in both directions, all packets (except small packets like pure # acks) have to be handled by normal forwarding path. Therefore, packet counters # are not checked. -if test_tcp_forwarding "$ns1" "$ns2" 0; then +if test_tcp_forwarding "$ns1" "$ns2" 0 4 10.0.2.99 12345; then echo "PASS: flow offloaded for ns1/ns2" else echo "FAIL: flow offload for ns1/ns2:" 1>&2 @@ -495,6 +508,14 @@ else ret=1 fi +if test_tcp_forwarding "$ns1" "$ns2" 0 6 "[dead:2::99]" 12345; then + echo "PASS: IPv6 flow offloaded for ns1/ns2" +else + echo "FAIL: IPv6 flow offload for ns1/ns2:" 1>&2 + ip netns exec "$nsr1" nft list ruleset + ret=1 +fi + # delete default route, i.e. ns2 won't be able to reach ns1 and # will depend on ns1 being masqueraded in nsr1. # expect ns1 has nsr1 address. @@ -520,7 +541,7 @@ table ip nat { EOF check_dscp "dscp_none" "0" -if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 0 ""; then +if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 0 4 10.0.2.99 12345; then echo "FAIL: flow offload for ns1/ns2 with dscp update and no pmtu discovery" 1>&2 exit 0 fi @@ -546,7 +567,7 @@ ip netns exec "$ns2" sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null ip netns exec "$ns2" nft reset counters table inet filter >/dev/null -if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 1 ""; then +if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 1 4 10.0.2.99 12345; then echo "FAIL: flow offload for ns1/ns2 with dscp update and pmtu discovery" 1>&2 exit 0 fi @@ -558,6 +579,73 @@ if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 ""; then ip netns exec "$nsr1" nft list ruleset fi +# IPIP tunnel test: +# Add IPIP tunnel interfaces and check flowtable acceleration. +test_ipip() { +if ! ip -net "$nsr1" link add name tun0 type ipip \ + local 192.168.10.1 remote 192.168.10.2 >/dev/null;then + echo "SKIP: could not add ipip tunnel" + [ "$ret" -eq 0 ] && ret=$ksft_skip + return +fi +ip -net "$nsr1" link set tun0 up +ip -net "$nsr1" addr add 192.168.100.1/24 dev tun0 +ip netns exec "$nsr1" sysctl net.ipv4.conf.tun0.forwarding=1 > /dev/null + +ip -net "$nsr2" link add name tun0 type ipip local 192.168.10.2 remote 192.168.10.1 +ip -net "$nsr2" link set tun0 up +ip -net "$nsr2" addr add 192.168.100.2/24 dev tun0 +ip netns exec "$nsr2" sysctl net.ipv4.conf.tun0.forwarding=1 > /dev/null + +ip -net "$nsr1" route change default via 192.168.100.2 +ip -net "$nsr2" route change default via 192.168.100.1 +ip -net "$ns2" route add default via 10.0.2.1 + +ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif tun0 accept' +ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif "veth0" tcp sport 12345 ct mark set 1 flow add @f1 counter name routed_repl accept' + +if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 "IPIP tunnel"; then + echo "FAIL: flow offload for ns1/ns2 with IPIP tunnel" 1>&2 + ip netns exec "$nsr1" nft list ruleset + ret=1 +fi + +# Create vlan tagged devices for IPIP traffic. +ip -net "$nsr1" link add link veth1 name veth1.10 type vlan id 10 +ip -net "$nsr1" link set veth1.10 up +ip -net "$nsr1" addr add 192.168.20.1/24 dev veth1.10 +ip netns exec "$nsr1" sysctl net.ipv4.conf.veth1/10.forwarding=1 > /dev/null +ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif veth1.10 accept' +ip -net "$nsr1" link add name tun1 type ipip local 192.168.20.1 remote 192.168.20.2 +ip -net "$nsr1" link set tun1 up +ip -net "$nsr1" addr add 192.168.200.1/24 dev tun1 +ip -net "$nsr1" route change default via 192.168.200.2 +ip netns exec "$nsr1" sysctl net.ipv4.conf.tun1.forwarding=1 > /dev/null +ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif tun1 accept' + +ip -net "$nsr2" link add link veth0 name veth0.10 type vlan id 10 +ip -net "$nsr2" link set veth0.10 up +ip -net "$nsr2" addr add 192.168.20.2/24 dev veth0.10 +ip netns exec "$nsr2" sysctl net.ipv4.conf.veth0/10.forwarding=1 > /dev/null +ip -net "$nsr2" link add name tun1 type ipip local 192.168.20.2 remote 192.168.20.1 +ip -net "$nsr2" link set tun1 up +ip -net "$nsr2" addr add 192.168.200.2/24 dev tun1 +ip -net "$nsr2" route change default via 192.168.200.1 +ip netns exec "$nsr2" sysctl net.ipv4.conf.tun1.forwarding=1 > /dev/null + +if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 "IPIP tunnel over vlan"; then + echo "FAIL: flow offload for ns1/ns2 with IPIP tunnel over vlan" 1>&2 + ip netns exec "$nsr1" nft list ruleset + ret=1 +fi + +# Restore the previous configuration +ip -net "$nsr1" route change default via 192.168.10.2 +ip -net "$nsr2" route change default via 192.168.10.1 +ip -net "$ns2" route del default via 10.0.2.1 +} + # Another test: # Add bridge interface br0 to Router1, with NAT enabled. test_bridge() { @@ -643,6 +731,8 @@ ip -net "$nsr1" addr add dead:1::1/64 dev veth0 nodad ip -net "$nsr1" link set up dev veth0 } +test_ipip + test_bridge KEY_SHA="0x"$(ps -af | sha1sum | cut -d " " -f 1) @@ -683,7 +773,7 @@ ip -net "$ns2" route del 192.168.10.1 via 10.0.2.1 ip -net "$ns2" route add default via 10.0.2.1 ip -net "$ns2" route add default via dead:2::1 -if test_tcp_forwarding "$ns1" "$ns2" 1; then +if test_tcp_forwarding "$ns1" "$ns2" 1 4 10.0.2.99 12345; then check_counters "ipsec tunnel mode for ns1/ns2" else echo "FAIL: ipsec tunnel mode for ns1/ns2" @@ -691,6 +781,14 @@ else ip netns exec "$nsr1" cat /proc/net/xfrm_stat 1>&2 fi +if test_tcp_forwarding "$ns1" "$ns2" 1 6 "[dead:2::99]" 12345; then + check_counters "IPv6 ipsec tunnel mode for ns1/ns2" +else + echo "FAIL: IPv6 ipsec tunnel mode for ns1/ns2" + ip netns exec "$nsr1" nft list ruleset 1>&2 + ip netns exec "$nsr1" cat /proc/net/xfrm_stat 1>&2 +fi + if [ "$1" = "" ]; then low=1280 mtu=$((65536 - low)) diff --git a/tools/testing/selftests/net/netfilter/sctp_collision.c b/tools/testing/selftests/net/netfilter/sctp_collision.c index 21bb1cfd8a85..b282d1785c9b 100644 --- a/tools/testing/selftests/net/netfilter/sctp_collision.c +++ b/tools/testing/selftests/net/netfilter/sctp_collision.c @@ -9,9 +9,10 @@ int main(int argc, char *argv[]) { struct sockaddr_in saddr = {}, daddr = {}; - int sd, ret, len = sizeof(daddr); + socklen_t len = sizeof(daddr); struct timeval tv = {25, 0}; char buf[] = "hello"; + int sd, ret; if (argc != 6 || (strcmp(argv[1], "server") && strcmp(argv[1], "client"))) { printf("%s <server|client> <LOCAL_IP> <LOCAL_PORT> <REMOTE_IP> <REMOTE_PORT>\n", diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c index 7618ebe528a4..679b6c77ace7 100644 --- a/tools/testing/selftests/net/netlink-dumps.c +++ b/tools/testing/selftests/net/netlink-dumps.c @@ -143,6 +143,7 @@ TEST(dump_extack) EXPECT_EQ(n, -1); EXPECT_EQ(errno, ENOBUFS); + ret = NO_CTRL; for (i = 0; i < cnt; i++) { struct ext_ack ea = {}; diff --git a/tools/testing/selftests/net/packetdrill/tcp_rto_synack_rto_max.pkt b/tools/testing/selftests/net/packetdrill/tcp_rto_synack_rto_max.pkt new file mode 100644 index 000000000000..47550df124ce --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rto_synack_rto_max.pkt @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Test SYN+ACK RTX with 1s RTO. +// +`./defaults.sh + ./set_sysctls.py /proc/sys/net/ipv4/tcp_rto_max_ms=1000` + +// +// Test 1: TFO SYN+ACK +// + 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0 + + +0 < S 0:10(10) win 1000 <mss 1460,sackOK,nop,nop,FO TFO_COOKIE,nop,nop> + +0 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK> + +// RTO must be capped to 1s + +1 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK> + +1 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK> + +1 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK> + + +0 < . 11:11(0) ack 1 win 1000 <mss 1460,nop,nop,sackOK> + +0 accept(3, ..., ...) = 4 + +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) != 0, tcpi_options }% + + +0 close(4) = 0 + +0 close(3) = 0 + + +// +// Test 2: non-TFO SYN+ACK +// + +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 1000 <mss 1460,sackOK,nop,nop> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> + +// RTO must be capped to 1s + +1 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> + +1 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> + +1 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> + + +0 < . 1:1(0) ack 1 win 1000 <mss 1460,nop,nop,sackOK> + +0 accept(3, ..., ...) = 4 + +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) == 0, tcpi_options }% + + +0 close(4) = 0 + +0 close(3) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt index b2b2cdf27e20..454441e7ecff 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt @@ -1,6 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 // Test that we correctly skip zero-length IOVs. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt index 183051ba0cae..6882b8240a8a 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt @@ -23,14 +23,16 @@ // install a qdisc dropping all packets +0 `tc qdisc delete dev tun0 root 2>/dev/null ; tc qdisc add dev tun0 root pfifo limit 0` + +0 write(4, ..., 24) = 24 // When qdisc is congested we retry every 500ms // (TCP_RESOURCE_PROBE_INTERVAL) and therefore // we retry 6 times before hitting 3s timeout. // First verify that the connection is alive: -+3.250 write(4, ..., 24) = 24 ++3 write(4, ..., 24) = 24 + // Now verify that shortly after that the socket is dead: - +.100 write(4, ..., 24) = -1 ETIMEDOUT (Connection timed out) ++1 write(4, ..., 24) = -1 ETIMEDOUT (Connection timed out) +0 %{ assert tcpi_probes == 6, tcpi_probes; \ assert tcpi_backoff == 0, tcpi_backoff }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt index a82c8899d36b..0a0700afdaa3 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt @@ -4,6 +4,8 @@ // send a packet with MSG_ZEROCOPY and receive the notification ID // repeat and verify IDs are consecutive +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt index c01915e7f4a1..df91675d2991 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt @@ -3,6 +3,8 @@ // // send multiple packets, then read one range of all notifications. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt index 6509882932e9..2963cfcb14df 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Minimal client-side zerocopy test +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt index 2cd78755cb2a..ea0c2fa73c2d 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt @@ -7,6 +7,8 @@ // First send on a closed socket and wait for (absent) notification. // Then connect and send and verify that notification nr. is zero. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt index 7671c20e01cf..4df978a9b82e 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt @@ -7,6 +7,9 @@ // fire two sends with MSG_ZEROCOPY and receive the acks. confirm that EPOLLERR // is correctly fired only once, when EPOLLET is set. send another packet with // MSG_ZEROCOPY. confirm that EPOLLERR is correctly fired again only once. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt index fadc480fdb7f..36b6edc4858c 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt @@ -8,6 +8,9 @@ // fire two sends with MSG_ZEROCOPY and receive the acks. confirm that EPOLLERR // is correctly fired only once, when EPOLLET is set. send another packet with // MSG_ZEROCOPY. confirm that EPOLLERR is correctly fired again only once. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt index 5bfa0d1d2f4a..1bea6f3b4558 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt @@ -8,6 +8,9 @@ // is correctly fired only once, when EPOLLONESHOT is set. send another packet // with MSG_ZEROCOPY. confirm that EPOLLERR is not fired. Rearm the FD and // confirm that EPOLLERR is correctly set. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt index 4a73bbf46961..e27c21ff5d18 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt @@ -8,6 +8,8 @@ // one will have no data in the initial send. On return 0 the // zerocopy notification counter is not incremented. Verify this too. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` // Send a FastOpen request, no cookie yet so no data in SYN diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt index 36086c5877ce..b1fa77c77dfa 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt @@ -4,6 +4,8 @@ // send data with MSG_FASTOPEN | MSG_ZEROCOPY and verify that the // kernel returns the notification ID. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh ./set_sysctls.py /proc/sys/net/ipv4/tcp_fastopen=0x207` diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt index 672f817faca0..2f5317d0a9fa 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt @@ -7,6 +7,8 @@ // because each iovec element becomes a frag // 3) the PSH bit is set on an skb when it runs out of fragments +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt index a9a1ac0aea4f..9d5272c6b207 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt @@ -4,6 +4,8 @@ // verify that SO_EE_CODE_ZEROCOPY_COPIED is set on zerocopy // packets of all sizes, including the smallest payload, 1B. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 163a084d525d..248c2b91fe42 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -8,6 +8,7 @@ ALL_TESTS=" kci_test_polrouting kci_test_route_get kci_test_addrlft + kci_test_addrlft_route_cleanup kci_test_promote_secondaries kci_test_tc kci_test_gre @@ -323,6 +324,25 @@ kci_test_addrlft() end_test "PASS: preferred_lft addresses have expired" } +kci_test_addrlft_route_cleanup() +{ + local ret=0 + local test_addr="2001:db8:99::1/64" + local test_prefix="2001:db8:99::/64" + + run_cmd ip -6 addr add $test_addr dev "$devdummy" valid_lft 300 preferred_lft 300 + run_cmd_grep "$test_prefix proto kernel" ip -6 route show dev "$devdummy" + run_cmd ip -6 addr del $test_addr dev "$devdummy" + run_cmd_grep_fail "$test_prefix" ip -6 route show dev "$devdummy" + + if [ $ret -ne 0 ]; then + end_test "FAIL: route not cleaned up when address with valid_lft deleted" + return 1 + fi + + end_test "PASS: route cleaned up when address with valid_lft deleted" +} + kci_test_promote_secondaries() { run_cmd ifconfig "$devdummy" diff --git a/tools/testing/selftests/net/setup_loopback.sh b/tools/testing/selftests/net/setup_loopback.sh deleted file mode 100644 index 2070b57849de..000000000000 --- a/tools/testing/selftests/net/setup_loopback.sh +++ /dev/null @@ -1,120 +0,0 @@ -#!/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="$(< ${FLUSH_PATH})" -readonly HARD_IRQS="$(< ${IRQ_PATH})" -readonly server_ns=$(mktemp -u server-XXXXXXXX) -readonly client_ns=$(mktemp -u client-XXXXXXXX) - -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}" >"${IRQ_PATH}" -} diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh deleted file mode 100644 index 152bf4c65747..000000000000 --- a/tools/testing/selftests/net/setup_veth.sh +++ /dev/null @@ -1,45 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -readonly server_ns=$(mktemp -u server-XXXXXXXX) -readonly client_ns=$(mktemp -u client-XXXXXXXX) - -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 "${ns_name}" - echo 200000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" - echo 1 > "/sys/class/net/${ns_dev}/napi_defer_hard_irqs" - ip link set dev "${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/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index 8457b7ccbc09..b76df1efc2ef 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -174,7 +174,7 @@ static int do_recv_errqueue_timeout(int fdt) msg.msg_controllen = sizeof(control); while (1) { - const char *reason; + const char *reason = NULL; ret = recvmsg(fdt, &msg, MSG_ERRQUEUE); if (ret == -1 && errno == EAGAIN) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 5c6d8215021c..da1b50b30719 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -2856,6 +2856,147 @@ TEST_F(tls_err, oob_pressure) EXPECT_EQ(send(self->fd2, buf, 5, MSG_OOB), 5); } +/* + * Parse a stream of TLS records and ensure that each record respects + * the specified @max_payload_len. + */ +static size_t parse_tls_records(struct __test_metadata *_metadata, + const __u8 *rx_buf, int rx_len, int overhead, + __u16 max_payload_len) +{ + const __u8 *rec = rx_buf; + size_t total_plaintext_rx = 0; + const __u8 rec_header_len = 5; + + while (rec < rx_buf + rx_len) { + __u16 record_payload_len; + __u16 plaintext_len; + + /* Sanity check that it's a TLS header for application data */ + ASSERT_EQ(rec[0], 23); + ASSERT_EQ(rec[1], 0x3); + ASSERT_EQ(rec[2], 0x3); + + memcpy(&record_payload_len, rec + 3, 2); + record_payload_len = ntohs(record_payload_len); + ASSERT_GE(record_payload_len, overhead); + + plaintext_len = record_payload_len - overhead; + total_plaintext_rx += plaintext_len; + + /* Plaintext must not exceed the specified limit */ + ASSERT_LE(plaintext_len, max_payload_len); + rec += rec_header_len + record_payload_len; + } + + return total_plaintext_rx; +} + +TEST(tls_12_tx_max_payload_len) +{ + struct tls_crypto_info_keys tls12; + int cfd, ret, fd, overhead; + size_t total_plaintext_rx = 0; + __u8 tx[1024], rx[2000]; + __u16 limit = 128; + __u16 opt = 0; + unsigned int optlen = sizeof(opt); + bool notls; + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_CCM_128, + &tls12, 0); + + ulp_sock_pair(_metadata, &fd, &cfd, ¬ls); + + if (notls) + exit(KSFT_SKIP); + + /* Don't install keys on fd, we'll parse raw records */ + ret = setsockopt(cfd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(cfd, SOL_TLS, TLS_TX_MAX_PAYLOAD_LEN, &limit, + sizeof(limit)); + ASSERT_EQ(ret, 0); + + ret = getsockopt(cfd, SOL_TLS, TLS_TX_MAX_PAYLOAD_LEN, &opt, &optlen); + EXPECT_EQ(ret, 0); + EXPECT_EQ(limit, opt); + EXPECT_EQ(optlen, sizeof(limit)); + + memset(tx, 0, sizeof(tx)); + ASSERT_EQ(send(cfd, tx, sizeof(tx), 0), sizeof(tx)); + close(cfd); + + ret = recv(fd, rx, sizeof(rx), 0); + + /* + * 16B tag + 8B IV -- record header (5B) is not counted but we'll + * need it to walk the record stream + */ + overhead = 16 + 8; + total_plaintext_rx = parse_tls_records(_metadata, rx, ret, overhead, + limit); + + ASSERT_EQ(total_plaintext_rx, sizeof(tx)); + close(fd); +} + +TEST(tls_12_tx_max_payload_len_open_rec) +{ + struct tls_crypto_info_keys tls12; + int cfd, ret, fd, overhead; + size_t total_plaintext_rx = 0; + __u8 tx[1024], rx[2000]; + __u16 tx_partial = 256; + __u16 og_limit = 512, limit = 128; + bool notls; + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_CCM_128, + &tls12, 0); + + ulp_sock_pair(_metadata, &fd, &cfd, ¬ls); + + if (notls) + exit(KSFT_SKIP); + + /* Don't install keys on fd, we'll parse raw records */ + ret = setsockopt(cfd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(cfd, SOL_TLS, TLS_TX_MAX_PAYLOAD_LEN, &og_limit, + sizeof(og_limit)); + ASSERT_EQ(ret, 0); + + memset(tx, 0, sizeof(tx)); + ASSERT_EQ(send(cfd, tx, tx_partial, MSG_MORE), tx_partial); + + /* + * Changing the payload limit with a pending open record should + * not be allowed. + */ + ret = setsockopt(cfd, SOL_TLS, TLS_TX_MAX_PAYLOAD_LEN, &limit, + sizeof(limit)); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EBUSY); + + ASSERT_EQ(send(cfd, tx + tx_partial, sizeof(tx) - tx_partial, MSG_EOR), + sizeof(tx) - tx_partial); + close(cfd); + + ret = recv(fd, rx, sizeof(rx), 0); + + /* + * 16B tag + 8B IV -- record header (5B) is not counted but we'll + * need it to walk the record stream + */ + overhead = 16 + 8; + total_plaintext_rx = parse_tls_records(_metadata, rx, ret, overhead, + og_limit); + ASSERT_EQ(total_plaintext_rx, sizeof(tx)); + close(fd); +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; diff --git a/tools/testing/selftests/net/toeplitz.c b/tools/testing/selftests/net/toeplitz.c deleted file mode 100644 index 9ba03164d73a..000000000000 --- a/tools/testing/selftests/net/toeplitz.c +++ /dev/null @@ -1,589 +0,0 @@ -// 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> - -#include "../kselftest.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 bool 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 false; - - 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; - - return true; -} - -/* 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++) - do {} while (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 / 8; - 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 = 16; - - 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 = ARRAY_SIZE(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 = ARRAY_SIZE(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:uv", 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 deleted file mode 100755 index 8ff172f7bb1b..000000000000 --- a/tools/testing/selftests/net/toeplitz.sh +++ /dev/null @@ -1,199 +0,0 @@ -#!/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}" | - grep -E [[: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 "${exit_code}" diff --git a/tools/testing/selftests/net/toeplitz_client.sh b/tools/testing/selftests/net/toeplitz_client.sh deleted file mode 100755 index 2fef34f4aba1..000000000000 --- a/tools/testing/selftests/net/toeplitz_client.sh +++ /dev/null @@ -1,28 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# A simple program for generating traffic for the toeplitz test. -# -# This program sends packets periodically for, conservatively, 20 seconds. The -# intent is for the calling program to kill this program once it is no longer -# needed, rather than waiting for the 20 second expiration. - -send_traffic() { - expiration=$((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/traceroute.sh b/tools/testing/selftests/net/traceroute.sh index dbb34c7e09ce..a7c6ab8a0347 100755 --- a/tools/testing/selftests/net/traceroute.sh +++ b/tools/testing/selftests/net/traceroute.sh @@ -36,6 +36,35 @@ run_cmd() return $rc } +__check_traceroute_version() +{ + local cmd=$1; shift + local req_ver=$1; shift + local ver + + req_ver=$(echo "$req_ver" | sed 's/\.//g') + ver=$($cmd -V 2>&1 | grep -Eo '[0-9]+.[0-9]+.[0-9]+' | sed 's/\.//g') + if [[ $ver -lt $req_ver ]]; then + return 1 + else + return 0 + fi +} + +check_traceroute6_version() +{ + local req_ver=$1; shift + + __check_traceroute_version traceroute6 "$req_ver" +} + +check_traceroute_version() +{ + local req_ver=$1; shift + + __check_traceroute_version traceroute "$req_ver" +} + ################################################################################ # create namespaces and interconnects @@ -59,6 +88,8 @@ create_ns() ip netns exec ${ns} ip -6 ro add unreachable default metric 8192 ip netns exec ${ns} sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ${ns} sysctl -qw net.ipv4.icmp_ratelimit=0 + ip netns exec ${ns} sysctl -qw net.ipv6.icmp.ratelimit=0 ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.forwarding=1 ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.forwarding=1 @@ -298,6 +329,144 @@ run_traceroute6_vrf() } ################################################################################ +# traceroute6 with ICMP extensions test +# +# Verify that in this scenario +# +# ---- ---- ---- +# |H1|--------------------------|R1|--------------------------|H2| +# ---- N1 ---- N2 ---- +# +# ICMP extensions are correctly reported. The loopback interfaces on all the +# nodes are assigned global addresses and the interfaces connecting the nodes +# are assigned IPv6 link-local addresses. + +cleanup_traceroute6_ext() +{ + cleanup_all_ns +} + +setup_traceroute6_ext() +{ + # Start clean + cleanup_traceroute6_ext + + setup_ns h1 r1 h2 + create_ns "$h1" + create_ns "$r1" + create_ns "$h2" + + # Setup N1 + connect_ns "$h1" eth1 - fe80::1/64 "$r1" eth1 - fe80::2/64 + # Setup N2 + connect_ns "$r1" eth2 - fe80::3/64 "$h2" eth2 - fe80::4/64 + + # Setup H1 + ip -n "$h1" address add 2001:db8:1::1/128 dev lo + ip -n "$h1" route add ::/0 nexthop via fe80::2 dev eth1 + + # Setup R1 + ip -n "$r1" address add 2001:db8:1::2/128 dev lo + ip -n "$r1" route add 2001:db8:1::1/128 nexthop via fe80::1 dev eth1 + ip -n "$r1" route add 2001:db8:1::3/128 nexthop via fe80::4 dev eth2 + + # Setup H2 + ip -n "$h2" address add 2001:db8:1::3/128 dev lo + ip -n "$h2" route add ::/0 nexthop via fe80::3 dev eth2 + + # Prime the network + ip netns exec "$h1" ping6 -c5 2001:db8:1::3 >/dev/null 2>&1 +} + +traceroute6_ext_iio_iif_test() +{ + local r1_ifindex h2_ifindex + local pkt_len=$1; shift + + # Test that incoming interface info is not appended by default. + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep INC" + check_fail $? "Incoming interface info appended by default when should not" + + # Test that the extension is appended when enabled. + run_cmd "$r1" "bash -c \"echo 0x01 > /proc/sys/net/ipv6/icmp/errors_extension_mask\"" + check_err $? "Failed to enable incoming interface info extension on R1" + + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep INC" + check_err $? "Incoming interface info not appended after enable" + + # Test that the extension is not appended when disabled. + run_cmd "$r1" "bash -c \"echo 0x00 > /proc/sys/net/ipv6/icmp/errors_extension_mask\"" + check_err $? "Failed to disable incoming interface info extension on R1" + + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep INC" + check_fail $? "Incoming interface info appended after disable" + + # Test that the extension is sent correctly from both R1 and H2. + run_cmd "$r1" "sysctl -w net.ipv6.icmp.errors_extension_mask=0x01" + r1_ifindex=$(ip -n "$r1" -j link show dev eth1 | jq '.[]["ifindex"]') + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep '<INC:$r1_ifindex,\"eth1\",mtu=1500>'" + check_err $? "Wrong incoming interface info reported from R1" + + run_cmd "$h2" "sysctl -w net.ipv6.icmp.errors_extension_mask=0x01" + h2_ifindex=$(ip -n "$h2" -j link show dev eth2 | jq '.[]["ifindex"]') + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep '<INC:$h2_ifindex,\"eth2\",mtu=1500>'" + check_err $? "Wrong incoming interface info reported from H2" + + # Add a global address on the incoming interface of R1 and check that + # it is reported. + run_cmd "$r1" "ip address add 2001:db8:100::1/64 dev eth1 nodad" + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep '<INC:$r1_ifindex,2001:db8:100::1,\"eth1\",mtu=1500>'" + check_err $? "Wrong incoming interface info reported from R1 after address addition" + run_cmd "$r1" "ip address del 2001:db8:100::1/64 dev eth1" + + # Change name and MTU and make sure the result is still correct. + run_cmd "$r1" "ip link set dev eth1 name eth1tag mtu 1501" + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep '<INC:$r1_ifindex,\"eth1tag\",mtu=1501>'" + check_err $? "Wrong incoming interface info reported from R1 after name and MTU change" + run_cmd "$r1" "ip link set dev eth1tag name eth1 mtu 1500" + + run_cmd "$r1" "sysctl -w net.ipv6.icmp.errors_extension_mask=0x00" + run_cmd "$h2" "sysctl -w net.ipv6.icmp.errors_extension_mask=0x00" +} + +run_traceroute6_ext() +{ + # Need at least version 2.1.5 for RFC 5837 support. + if ! check_traceroute6_version 2.1.5; then + log_test_skip "traceroute6 too old, missing ICMP extensions support" + return + fi + + setup_traceroute6_ext + + RET=0 + + ## General ICMP extensions tests + + # Test that ICMP extensions are disabled by default. + run_cmd "$h1" "sysctl net.ipv6.icmp.errors_extension_mask | grep \"= 0$\"" + check_err $? "ICMP extensions are not disabled by default" + + # Test that unsupported values are rejected. Do not use "sysctl" as + # older versions do not return an error code upon failure. + run_cmd "$h1" "bash -c \"echo 0x80 > /proc/sys/net/ipv6/icmp/errors_extension_mask\"" + check_fail $? "Unsupported sysctl value was not rejected" + + ## Extension-specific tests + + # Incoming interface info test. Test with various packet sizes, + # including the default one. + traceroute6_ext_iio_iif_test + traceroute6_ext_iio_iif_test 127 + traceroute6_ext_iio_iif_test 128 + traceroute6_ext_iio_iif_test 129 + + log_test "IPv6 traceroute with ICMP extensions" + + cleanup_traceroute6_ext +} + +################################################################################ # traceroute test # # Verify that traceroute from H1 to H2 shows 1.0.3.1 and 1.0.1.1 when @@ -438,14 +607,157 @@ run_traceroute_vrf() } ################################################################################ +# traceroute with ICMP extensions test +# +# Verify that in this scenario +# +# ---- ---- ---- +# |H1|--------------------------|R1|--------------------------|H2| +# ---- N1 ---- N2 ---- +# +# ICMP extensions are correctly reported. The loopback interfaces on all the +# nodes are assigned global addresses and the interfaces connecting the nodes +# are assigned IPv6 link-local addresses. + +cleanup_traceroute_ext() +{ + cleanup_all_ns +} + +setup_traceroute_ext() +{ + # Start clean + cleanup_traceroute_ext + + setup_ns h1 r1 h2 + create_ns "$h1" + create_ns "$r1" + create_ns "$h2" + + # Setup N1 + connect_ns "$h1" eth1 - fe80::1/64 "$r1" eth1 - fe80::2/64 + # Setup N2 + connect_ns "$r1" eth2 - fe80::3/64 "$h2" eth2 - fe80::4/64 + + # Setup H1 + ip -n "$h1" address add 192.0.2.1/32 dev lo + ip -n "$h1" route add 0.0.0.0/0 nexthop via inet6 fe80::2 dev eth1 + + # Setup R1 + ip -n "$r1" address add 192.0.2.2/32 dev lo + ip -n "$r1" route add 192.0.2.1/32 nexthop via inet6 fe80::1 dev eth1 + ip -n "$r1" route add 192.0.2.3/32 nexthop via inet6 fe80::4 dev eth2 + + # Setup H2 + ip -n "$h2" address add 192.0.2.3/32 dev lo + ip -n "$h2" route add 0.0.0.0/0 nexthop via inet6 fe80::3 dev eth2 + + # Prime the network + ip netns exec "$h1" ping -c5 192.0.2.3 >/dev/null 2>&1 +} + +traceroute_ext_iio_iif_test() +{ + local r1_ifindex h2_ifindex + local pkt_len=$1; shift + + # Test that incoming interface info is not appended by default. + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep INC" + check_fail $? "Incoming interface info appended by default when should not" + + # Test that the extension is appended when enabled. + run_cmd "$r1" "bash -c \"echo 0x01 > /proc/sys/net/ipv4/icmp_errors_extension_mask\"" + check_err $? "Failed to enable incoming interface info extension on R1" + + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep INC" + check_err $? "Incoming interface info not appended after enable" + + # Test that the extension is not appended when disabled. + run_cmd "$r1" "bash -c \"echo 0x00 > /proc/sys/net/ipv4/icmp_errors_extension_mask\"" + check_err $? "Failed to disable incoming interface info extension on R1" + + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep INC" + check_fail $? "Incoming interface info appended after disable" + + # Test that the extension is sent correctly from both R1 and H2. + run_cmd "$r1" "sysctl -w net.ipv4.icmp_errors_extension_mask=0x01" + r1_ifindex=$(ip -n "$r1" -j link show dev eth1 | jq '.[]["ifindex"]') + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep '<INC:$r1_ifindex,\"eth1\",mtu=1500>'" + check_err $? "Wrong incoming interface info reported from R1" + + run_cmd "$h2" "sysctl -w net.ipv4.icmp_errors_extension_mask=0x01" + h2_ifindex=$(ip -n "$h2" -j link show dev eth2 | jq '.[]["ifindex"]') + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep '<INC:$h2_ifindex,\"eth2\",mtu=1500>'" + check_err $? "Wrong incoming interface info reported from H2" + + # Add a global address on the incoming interface of R1 and check that + # it is reported. + run_cmd "$r1" "ip address add 198.51.100.1/24 dev eth1" + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep '<INC:$r1_ifindex,198.51.100.1,\"eth1\",mtu=1500>'" + check_err $? "Wrong incoming interface info reported from R1 after address addition" + run_cmd "$r1" "ip address del 198.51.100.1/24 dev eth1" + + # Change name and MTU and make sure the result is still correct. + # Re-add the route towards H1 since it was deleted when we removed the + # last IPv4 address from eth1 on R1. + run_cmd "$r1" "ip route add 192.0.2.1/32 nexthop via inet6 fe80::1 dev eth1" + run_cmd "$r1" "ip link set dev eth1 name eth1tag mtu 1501" + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep '<INC:$r1_ifindex,\"eth1tag\",mtu=1501>'" + check_err $? "Wrong incoming interface info reported from R1 after name and MTU change" + run_cmd "$r1" "ip link set dev eth1tag name eth1 mtu 1500" + + run_cmd "$r1" "sysctl -w net.ipv4.icmp_errors_extension_mask=0x00" + run_cmd "$h2" "sysctl -w net.ipv4.icmp_errors_extension_mask=0x00" +} + +run_traceroute_ext() +{ + # Need at least version 2.1.5 for RFC 5837 support. + if ! check_traceroute_version 2.1.5; then + log_test_skip "traceroute too old, missing ICMP extensions support" + return + fi + + setup_traceroute_ext + + RET=0 + + ## General ICMP extensions tests + + # Test that ICMP extensions are disabled by default. + run_cmd "$h1" "sysctl net.ipv4.icmp_errors_extension_mask | grep \"= 0$\"" + check_err $? "ICMP extensions are not disabled by default" + + # Test that unsupported values are rejected. Do not use "sysctl" as + # older versions do not return an error code upon failure. + run_cmd "$h1" "bash -c \"echo 0x80 > /proc/sys/net/ipv4/icmp_errors_extension_mask\"" + check_fail $? "Unsupported sysctl value was not rejected" + + ## Extension-specific tests + + # Incoming interface info test. Test with various packet sizes, + # including the default one. + traceroute_ext_iio_iif_test + traceroute_ext_iio_iif_test 127 + traceroute_ext_iio_iif_test 128 + traceroute_ext_iio_iif_test 129 + + log_test "IPv4 traceroute with ICMP extensions" + + cleanup_traceroute_ext +} + +################################################################################ # Run tests run_tests() { run_traceroute6 run_traceroute6_vrf + run_traceroute6_ext run_traceroute run_traceroute_vrf + run_traceroute_ext } ################################################################################ @@ -462,6 +774,7 @@ done require_command traceroute6 require_command traceroute +require_command jq run_tests diff --git a/tools/testing/selftests/net/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c index dae91eb97d69..bcc14688661d 100644 --- a/tools/testing/selftests/net/txtimestamp.c +++ b/tools/testing/selftests/net/txtimestamp.c @@ -217,7 +217,7 @@ static void print_timestamp_usr(void) static void print_timestamp(struct scm_timestamping *tss, int tstype, int tskey, int payload_len) { - const char *tsname; + const char *tsname = NULL; validate_key(tskey, tstype); |