From: Gang Yan yangang@kylinos.cn

Recently, some mib counters about fallback has been added, this patch provides a method to check the expected behavior of these mib counters during the test execution.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/571 Signed-off-by: Gang Yan yangang@kylinos.cn Reviewed-by: Matthieu Baerts (NGI0) matttbe@kernel.org Signed-off-by: Matthieu Baerts (NGI0) matttbe@kernel.org --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 123 ++++++++++++++++++++++++ 1 file changed, 123 insertions(+)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 82cae37d9c2026cc55466636d53a76f929a03452..2f046167a0b6cc6fb5531a033d8d95c9ea399cf9 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -74,6 +74,17 @@ unset join_create_err unset join_bind_err unset join_connect_err

+unset fb_ns1 +unset fb_ns2 +unset fb_infinite_map_tx +unset fb_dss_corruption +unset fb_simult_conn +unset fb_mpc_passive +unset fb_mpc_active +unset fb_mpc_data +unset fb_md5_sig +unset fb_dss + # generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) || # (ip6 && (ip6[74] & 0xf0) == 0x30)'" CBPF_MPTCP_SUBOPTION_ADD_ADDR="14, @@ -1399,6 +1410,115 @@ chk_join_tx_nr() print_results "join Tx" ${rc} }

+chk_fallback_nr() +{ + local infinite_map_tx=${fb_infinite_map_tx:-0} + local dss_corruption=${fb_dss_corruption:-0} + local simult_conn=${fb_simult_conn:-0} + local mpc_passive=${fb_mpc_passive:-0} + local mpc_active=${fb_mpc_active:-0} + local mpc_data=${fb_mpc_data:-0} + local md5_sig=${fb_md5_sig:-0} + local dss=${fb_dss:-0} + local rc=${KSFT_PASS} + local ns=$1 + local count + + count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtInfiniteMapTx") + if [ -z "$count" ]; then + rc=${KSFT_SKIP} + elif [ "$count" != "$infinite_map_tx" ]; then + rc=${KSFT_FAIL} + print_check "$ns infinite map tx fallback" + fail_test "got $count infinite map tx fallback[s] in $ns expected $infinite_map_tx" + fi + + count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtDSSCorruptionFallback") + if [ -z "$count" ]; then + rc=${KSFT_SKIP} + elif [ "$count" != "$dss_corruption" ]; then + rc=${KSFT_FAIL} + print_check "$ns dss corruption fallback" + fail_test "got $count dss corruption fallback[s] in $ns expected $dss_corruption" + fi + + count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtSimultConnectFallback") + if [ -z "$count" ]; then + rc=${KSFT_SKIP} + elif [ "$count" != "$simult_conn" ]; then + rc=${KSFT_FAIL} + print_check "$ns simult conn fallback" + fail_test "got $count simult conn fallback[s] in $ns expected $simult_conn" + fi + + count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtMPCapableFallbackACK") + if [ -z "$count" ]; then + rc=${KSFT_SKIP} + elif [ "$count" != "$mpc_passive" ]; then + rc=${KSFT_FAIL} + print_check "$ns mpc passive fallback" + fail_test "got $count mpc passive fallback[s] in $ns expected $mpc_passive" + fi + + count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtMPCapableFallbackSYNACK") + if [ -z "$count" ]; then + rc=${KSFT_SKIP} + elif [ "$count" != "$mpc_active" ]; then + rc=${KSFT_FAIL} + print_check "$ns mpc active fallback" + fail_test "got $count mpc active fallback[s] in $ns expected $mpc_active" + fi + + count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtMPCapableDataFallback") + if [ -z "$count" ]; then + rc=${KSFT_SKIP} + elif [ "$count" != "$mpc_data" ]; then + rc=${KSFT_FAIL} + print_check "$ns mpc data fallback" + fail_test "got $count mpc data fallback[s] in $ns expected $mpc_data" + fi + + count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtMD5SigFallback") + if [ -z "$count" ]; then + rc=${KSFT_SKIP} + elif [ "$count" != "$md5_sig" ]; then + rc=${KSFT_FAIL} + print_check "$ns MD5 Sig fallback" + fail_test "got $count MD5 Sig fallback[s] in $ns expected $md5_sig" + fi + + count=$(mptcp_lib_get_counter ${!ns} "MPTcpExtDssFallback") + if [ -z "$count" ]; then + rc=${KSFT_SKIP} + elif [ "$count" != "$dss" ]; then + rc=${KSFT_FAIL} + print_check "$ns dss fallback" + fail_test "got $count dss fallback[s] in $ns expected $dss" + fi + + return $rc +} + +chk_fallback_nr_all() +{ + local netns=("ns1" "ns2") + local fb_ns=("fb_ns1" "fb_ns2") + local rc=${KSFT_PASS} + + for i in 0 1; do + if [ -n "${!fb_ns[i]}" ]; then + eval "${!fb_ns[i]}" \ + chk_fallback_nr ${netns[i]} || rc=${?} + else + chk_fallback_nr ${netns[i]} || rc=${?} + fi + done + + if [ "${rc}" != "${KSFT_PASS}" ]; then + print_results "fallback" ${rc} + fi +} + chk_join_nr() { local syn_nr=$1 @@ -1484,6 +1604,8 @@ chk_join_nr() join_syn_tx="${join_syn_tx:-${syn_nr}}" \ chk_join_tx_nr

+ chk_fallback_nr_all + if $validate_checksum; then chk_csum_nr $csum_ns1 $csum_ns2 chk_fail_nr $fail_nr $fail_nr @@ -3337,6 +3459,7 @@ fail_tests() join_csum_ns1=+1 join_csum_ns2=+0 \ join_fail_nr=1 join_rst_nr=0 join_infi_nr=1 \ join_corrupted_pkts="$(pedit_action_pkts)" \ + fb_ns1="fb_dss=1" fb_ns2="fb_infinite_map_tx=1" \ chk_join_nr 0 0 0 chk_fail_nr 1 -1 invert fi

From: Christoph Paasch cpaasch@openai.com

Accelerated Receive Flow Steering (aRFS) relies on sockets recording their RX flow hash into the rps_sock_flow_table so that incoming packets are steered to the CPU where the application runs.

With MPTCP, the application interacts with the parent MPTCP socket while data is carried over per-subflow TCP sockets. Without recording these subflows, aRFS cannot steer interrupts and RX processing for the flows to the desired CPU.

Record all subflows in the RPS table by calling sock_rps_record_flow() for each subflow at the start of mptcp_sendmsg(), mptcp_recvmsg() and mptcp_stream_accept(), by using the new helper mptcp_rps_record_subflows().

It does not by itself improve throughput, but ensures that IRQ and RX processing are directed to the right CPU, which is a prerequisite for effective aRFS.

Signed-off-by: Christoph Paasch cpaasch@openai.com Reviewed-by: Matthieu Baerts (NGI0) matttbe@kernel.org Signed-off-by: Matthieu Baerts (NGI0) matttbe@kernel.org --- net/mptcp/protocol.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index ad41c48126e44fda646f1ec1c81957db1407a6cc..a8d57b88578dfea807d3d55e430849aa8005c637 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -12,6 +12,7 @@ #include <linux/sched/signal.h> #include <linux/atomic.h> #include <net/aligned_data.h> +#include <net/rps.h> #include <net/sock.h> #include <net/inet_common.h> #include <net/inet_hashtables.h> @@ -1740,6 +1741,20 @@ static u32 mptcp_send_limit(const struct sock *sk) return limit - not_sent; }

+static void mptcp_rps_record_subflows(const struct mptcp_sock *msk) +{ + struct mptcp_subflow_context *subflow; + + if (!rfs_is_needed()) + return; + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + sock_rps_record_flow(ssk); + } +} + static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -1753,6 +1768,8 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)

lock_sock(sk);

+ mptcp_rps_record_subflows(msk); + if (unlikely(inet_test_bit(DEFER_CONNECT, sk) || msg->msg_flags & MSG_FASTOPEN)) { int copied_syn = 0; @@ -2131,6 +2148,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, goto out_err; }

+ mptcp_rps_record_subflows(msk); + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);

len = min_t(size_t, len, INT_MAX); @@ -3922,6 +3941,8 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, mptcp_sock_graft(ssk, newsock); }

+ mptcp_rps_record_subflows(msk); + /* Do late cleanup for the first subflow as necessary. Also * deal with bad peers not doing a complete shutdown. */