From: Geliang Tang tanggeliang@kylinos.cn

Currently the ADD_ADDR option is retransmitted with a fixed timeout. This patch makes the retransmission timeout adaptive by using the maximum RTO among all the subflows, while still capping it at the configured maximum value (add_addr_timeout_max). This improves responsiveness when establishing new subflows.

Specifically: 1. Adds mptcp_adjust_add_addr_timeout() helper to compute the adaptive timeout. 2. Uses maximum subflow RTO (icsk_rto) when available. 3. Applies exponential backoff based on retransmission count. 4. Maintains fallback to configured max timeout when no RTO data exists.

This slightly changes the behaviour of the MPTCP "add_addr_timeout" sysctl knob to be used as a maximum instead of a fixed value. But this is seen as an improvement: the ADD_ADDR might be sent quicker than before to improve the overall MPTCP connection. Also, the default value is set to 2 min, which was already way too long, and caused the ADD_ADDR not to be retransmitted for connections shorter than 2 minutes.

Suggested-by: Matthieu Baerts (NGI0) matttbe@kernel.org Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/576 Reviewed-by: Christoph Paasch cpaasch@openai.com Signed-off-by: Geliang Tang tanggeliang@kylinos.cn Reviewed-by: Matthieu Baerts (NGI0) matttbe@kernel.org Signed-off-by: Matthieu Baerts (NGI0) matttbe@kernel.org --- Documentation/networking/mptcp-sysctl.rst | 8 +++++--- net/mptcp/pm.c | 28 ++++++++++++++++++++++++---- 2 files changed, 29 insertions(+), 7 deletions(-)

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst index 1683c139821e3ba6d9eaa3c59330a523d29f1164..1eb6af26b4a7acdedd575a126c576210a78f0d4d 100644 --- a/Documentation/networking/mptcp-sysctl.rst +++ b/Documentation/networking/mptcp-sysctl.rst @@ -8,9 +8,11 @@ MPTCP Sysfs variables ===============================

add_addr_timeout - INTEGER (seconds) - Set the timeout after which an ADD_ADDR control message will be - resent to an MPTCP peer that has not acknowledged a previous - ADD_ADDR message. + Set the maximum value of timeout after which an ADD_ADDR control message + will be resent to an MPTCP peer that has not acknowledged a previous + ADD_ADDR message. A dynamically estimated retransmission timeout based + on the estimated connection round-trip-time is used if this value is + lower than the maximum one.

Do not retransmit if set to 0.

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 136a380602cae872b76560649c924330e5f42533..204e1f61212e2be77a8476f024b59be67d04b80a 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -268,6 +268,27 @@ int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk, return -EINVAL; }

+static unsigned int mptcp_adjust_add_addr_timeout(struct mptcp_sock *msk) +{ + const struct net *net = sock_net((struct sock *)msk); + unsigned int rto = mptcp_get_add_addr_timeout(net); + struct mptcp_subflow_context *subflow; + unsigned int max = 0; + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + struct inet_connection_sock *icsk = inet_csk(ssk); + + if (icsk->icsk_rto > max) + max = icsk->icsk_rto; + } + + if (max && max < rto) + rto = max; + + return rto; +} + static void mptcp_pm_add_timer(struct timer_list *timer) { struct mptcp_pm_add_entry *entry = timer_container_of(entry, timer, @@ -292,7 +313,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer) goto out; }

- timeout = mptcp_get_add_addr_timeout(sock_net(sk)); + timeout = mptcp_adjust_add_addr_timeout(msk); if (!timeout) goto out;

@@ -307,7 +328,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer)

if (entry->retrans_times < ADD_ADDR_RETRANS_MAX) sk_reset_timer(sk, timer, - jiffies + timeout); + jiffies + (timeout << entry->retrans_times));

spin_unlock_bh(&msk->pm.lock);

@@ -348,7 +369,6 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, { struct mptcp_pm_add_entry *add_entry = NULL; struct sock *sk = (struct sock *)msk; - struct net *net = sock_net(sk); unsigned int timeout;

lockdep_assert_held(&msk->pm.lock); @@ -374,7 +394,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,

timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0); reset_timer: - timeout = mptcp_get_add_addr_timeout(net); + timeout = mptcp_adjust_add_addr_timeout(msk); if (timeout) sk_reset_timer(sk, &add_entry->add_timer, jiffies + timeout);

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 e85bb62046e020dbacbbd44e1f9e110e1d0104c7..a97b568104bc284f050b2f0e09fe3fdd3341c5cb 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, @@ -1397,6 +1408,115 @@ 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=$1 @@ -1482,6 +1602,8 @@ chk_join_nr() join_syn_tx="${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 $fail_nr @@ -3334,6 +3456,7 @@ fail_tests() join_csum_ns1=+1 join_csum_ns2=+0 \ join_fail_nr=1 join_rst_nr=0 join_infi_nr=1 \ join_corrupted_pkts="$(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. */