From 9aa59323f2709370cb4f01acbba599a9167f317b Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 27 Sep 2025 11:40:37 +0200 Subject: [PATCH 1/8] mptcp: leverage skb deferral free Usage of the skb deferral API is straight-forward; with multiple subflows actives this allow moving part of the received application load into multiple CPUs. Also fix a typo in the related comment. Reviewed-by: Geliang Tang Tested-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Paolo Abeni Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250927-net-next-mptcp-rcv-path-imp-v1-1-5da266aa9c1a@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 735a209d4072..62cdd2bcff9d 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1943,12 +1943,13 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, } if (!(flags & MSG_PEEK)) { - /* avoid the indirect call, we know the destructor is sock_wfree */ + /* avoid the indirect call, we know the destructor is sock_rfree */ skb->destructor = NULL; + skb->sk = NULL; atomic_sub(skb->truesize, &sk->sk_rmem_alloc); sk_mem_uncharge(sk, skb->truesize); __skb_unlink(skb, &sk->sk_receive_queue); - __kfree_skb(skb); + skb_attempt_defer_free(skb); msk->bytes_consumed += count; } From a7556779745c047efb7b0ce8732889b0cdc80936 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 27 Sep 2025 11:40:38 +0200 Subject: [PATCH 2/8] tcp: make tcp_rcvbuf_grow() accessible to mptcp code To leverage the auto-tuning improvements brought by commit 2da35e4b4df9 ("Merge branch 'tcp-receive-side-improvements'"), the MPTCP stack need to access the mentioned helper. Acked-by: Geliang Tang Acked-by: Matthieu Baerts (NGI0) Signed-off-by: Paolo Abeni Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250927-net-next-mptcp-rcv-path-imp-v1-2-5da266aa9c1a@kernel.org Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 1 + net/ipv4/tcp_input.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 7c51a0a5ace8..5ca230ed526a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -370,6 +370,7 @@ void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, int *karg); enum skb_drop_reason tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb); +void tcp_rcvbuf_grow(struct sock *sk); void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0a2511ce34db..b44fdc309633 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -891,7 +891,7 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, } } -static void tcp_rcvbuf_grow(struct sock *sk) +void tcp_rcvbuf_grow(struct sock *sk) { const struct net *net = sock_net(sk); struct tcp_sock *tp = tcp_sk(sk); From e118cdc34dd109562b64f6a397f68cd33b041d5b Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 27 Sep 2025 11:40:39 +0200 Subject: [PATCH 3/8] mptcp: rcvbuf auto-tuning improvement Apply to the MPTCP auto-tuning the same improvements introduced for the TCP protocol by the merge commit 2da35e4b4df9 ("Merge branch 'tcp-receive-side-improvements'"). The main difference is that TCP subflow and the main MPTCP socket need to account separately for OoO: MPTCP does not care for TCP-level OoO and vice versa, as a consequence do not reflect MPTCP-level rcvbuf increase due to OoO packets at the subflow level. This refeactor additionally allow dropping the msk receive buffer update at receive time, as the latter only intended to cope with subflow receive buffer increase due to OoO packets. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/487 Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/559 Reviewed-by: Geliang Tang Tested-by: Geliang Tang Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250927-net-next-mptcp-rcv-path-imp-v1-3-5da266aa9c1a@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 97 +++++++++++++++++++++----------------------- net/mptcp/protocol.h | 4 +- 2 files changed, 49 insertions(+), 52 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 62cdd2bcff9d..f994e7f45f7b 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -179,6 +179,35 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to, return mptcp_try_coalesce((struct sock *)msk, to, from); } +/* "inspired" by tcp_rcvbuf_grow(), main difference: + * - mptcp does not maintain a msk-level window clamp + * - returns true when the receive buffer is actually updated + */ +static bool mptcp_rcvbuf_grow(struct sock *sk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + const struct net *net = sock_net(sk); + int rcvwin, rcvbuf, cap; + + if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) || + (sk->sk_userlocks & SOCK_RCVBUF_LOCK)) + return false; + + rcvwin = msk->rcvq_space.space << 1; + + if (!RB_EMPTY_ROOT(&msk->out_of_order_queue)) + rcvwin += MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq - msk->ack_seq; + + cap = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]); + + rcvbuf = min_t(u32, mptcp_space_from_win(sk, rcvwin), cap); + if (rcvbuf > sk->sk_rcvbuf) { + WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); + return true; + } + return false; +} + /* "inspired" by tcp_data_queue_ofo(), main differences: * - use mptcp seqs * - don't cope with sacks @@ -292,6 +321,9 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb) end: skb_condense(skb); skb_set_owner_r(skb, sk); + /* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */ + if (sk->sk_socket) + mptcp_rcvbuf_grow(sk); } static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, @@ -784,18 +816,10 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) return moved; } -static void __mptcp_rcvbuf_update(struct sock *sk, struct sock *ssk) -{ - if (unlikely(ssk->sk_rcvbuf > sk->sk_rcvbuf)) - WRITE_ONCE(sk->sk_rcvbuf, ssk->sk_rcvbuf); -} - static void __mptcp_data_ready(struct sock *sk, struct sock *ssk) { struct mptcp_sock *msk = mptcp_sk(sk); - __mptcp_rcvbuf_update(sk, ssk); - /* Wake-up the reader only for in-sequence data */ if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk)) sk->sk_data_ready(sk); @@ -2014,48 +2038,26 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) if (msk->rcvq_space.copied <= msk->rcvq_space.space) goto new_measure; - if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) && - !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { - u64 rcvwin, grow; - int rcvbuf; + msk->rcvq_space.space = msk->rcvq_space.copied; + if (mptcp_rcvbuf_grow(sk)) { - rcvwin = ((u64)msk->rcvq_space.copied << 1) + 16 * advmss; + /* Make subflows follow along. If we do not do this, we + * get drops at subflow level if skbs can't be moved to + * the mptcp rx queue fast enough (announced rcv_win can + * exceed ssk->sk_rcvbuf). + */ + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk; + bool slow; - grow = rcvwin * (msk->rcvq_space.copied - msk->rcvq_space.space); - - do_div(grow, msk->rcvq_space.space); - rcvwin += (grow << 1); - - rcvbuf = min_t(u64, mptcp_space_from_win(sk, rcvwin), - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); - - if (rcvbuf > sk->sk_rcvbuf) { - u32 window_clamp; - - window_clamp = mptcp_win_from_space(sk, rcvbuf); - WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); - - /* Make subflows follow along. If we do not do this, we - * get drops at subflow level if skbs can't be moved to - * the mptcp rx queue fast enough (announced rcv_win can - * exceed ssk->sk_rcvbuf). - */ - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk; - bool slow; - - ssk = mptcp_subflow_tcp_sock(subflow); - slow = lock_sock_fast(ssk); - WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf); - WRITE_ONCE(tcp_sk(ssk)->window_clamp, window_clamp); - if (tcp_can_send_ack(ssk)) - tcp_cleanup_rbuf(ssk, 1); - unlock_sock_fast(ssk, slow); - } + ssk = mptcp_subflow_tcp_sock(subflow); + slow = lock_sock_fast(ssk); + tcp_sk(ssk)->rcvq_space.space = msk->rcvq_space.copied; + tcp_rcvbuf_grow(ssk); + unlock_sock_fast(ssk, slow); } } - msk->rcvq_space.space = msk->rcvq_space.copied; new_measure: msk->rcvq_space.copied = 0; msk->rcvq_space.time = mstamp; @@ -2084,11 +2086,6 @@ static bool __mptcp_move_skbs(struct sock *sk) if (list_empty(&msk->conn_list)) return false; - /* verify we can move any data from the subflow, eventually updating */ - if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) - mptcp_for_each_subflow(msk, subflow) - __mptcp_rcvbuf_update(sk, subflow->tcp_sock); - subflow = list_first_entry(&msk->conn_list, struct mptcp_subflow_context, node); for (;;) { diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 371084a3fc22..52f9cfa4ce95 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -341,8 +341,8 @@ struct mptcp_sock { struct mptcp_pm_data pm; struct mptcp_sched_ops *sched; struct { - u32 space; /* bytes copied in last measurement window */ - u32 copied; /* bytes copied in this measurement window */ + int space; /* bytes copied in last measurement window */ + int copied; /* bytes copied in this measurement window */ u64 time; /* start time of measurement window */ u64 rtt_us; /* last maximum rtt of subflows */ } rcvq_space; From 9a0afe0db46720ce1a009c7dac168aa0584bd732 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 27 Sep 2025 11:40:40 +0200 Subject: [PATCH 4/8] mptcp: introduce the mptcp_init_skb helper Factor out all the skb initialization step in a new helper and use it. Note that this change moves the MPTCP CB initialization earlier: we can do such step as soon as the skb leaves the subflow socket receive queues. Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Paolo Abeni Reviewed-by: Geliang Tang Tested-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250927-net-next-mptcp-rcv-path-imp-v1-4-5da266aa9c1a@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 46 ++++++++++++++++++++++++-------------------- 1 file changed, 25 insertions(+), 21 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index f994e7f45f7b..832782e23740 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -326,27 +326,11 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb) mptcp_rcvbuf_grow(sk); } -static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, - struct sk_buff *skb, unsigned int offset, - size_t copy_len) +static void mptcp_init_skb(struct sock *ssk, struct sk_buff *skb, int offset, + int copy_len) { - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); - struct sock *sk = (struct sock *)msk; - struct sk_buff *tail; - bool has_rxtstamp; - - __skb_unlink(skb, &ssk->sk_receive_queue); - - skb_ext_reset(skb); - skb_orphan(skb); - - /* try to fetch required memory from subflow */ - if (!sk_rmem_schedule(sk, skb, skb->truesize)) { - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); - goto drop; - } - - has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; + const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + bool has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; /* the skb map_seq accounts for the skb offset: * mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq @@ -358,6 +342,24 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp; MPTCP_SKB_CB(skb)->cant_coalesce = 0; + __skb_unlink(skb, &ssk->sk_receive_queue); + + skb_ext_reset(skb); + skb_dst_drop(skb); +} + +static bool __mptcp_move_skb(struct sock *sk, struct sk_buff *skb) +{ + u64 copy_len = MPTCP_SKB_CB(skb)->end_seq - MPTCP_SKB_CB(skb)->map_seq; + struct mptcp_sock *msk = mptcp_sk(sk); + struct sk_buff *tail; + + /* try to fetch required memory from subflow */ + if (!sk_rmem_schedule(sk, skb, skb->truesize)) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); + goto drop; + } + if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) { /* in sequence */ msk->bytes_received += copy_len; @@ -678,7 +680,9 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, if (offset < skb->len) { size_t len = skb->len - offset; - ret = __mptcp_move_skb(msk, ssk, skb, offset, len) || ret; + mptcp_init_skb(ssk, skb, offset, len); + skb_orphan(skb); + ret = __mptcp_move_skb(sk, skb) || ret; seq += len; if (unlikely(map_remaining < len)) { From c4ebc4ee4e751c6430604c52344d932bf1fde379 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 27 Sep 2025 11:40:41 +0200 Subject: [PATCH 5/8] mptcp: remove unneeded mptcp_move_skb() Since commit b7535cfed223 ("mptcp: drop legacy code around RX EOF"), sk_shutdown can't change during the main recvmsg loop, we can drop the related race breaker. Reviewed-by: Geliang Tang Tested-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Paolo Abeni Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250927-net-next-mptcp-rcv-path-imp-v1-5-5da266aa9c1a@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 832782e23740..26fbd9f6a3f7 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2207,14 +2207,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, break; } - if (sk->sk_shutdown & RCV_SHUTDOWN) { - /* race breaker: the shutdown could be after the - * previous receive queue check - */ - if (__mptcp_move_skbs(sk)) - continue; + if (sk->sk_shutdown & RCV_SHUTDOWN) break; - } if (sk->sk_state == TCP_CLOSE) { copied = -ENOTCONN; From 68c7af988bd137479101e2b40ab5fdd0e0365364 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 27 Sep 2025 11:40:42 +0200 Subject: [PATCH 6/8] mptcp: factor out a basic skb coalesce helper The upcoming patch will introduced backlog processing for MPTCP socket, and we want to leverage coalescing in such data path. Factor out the relevant bits not touching memory accounting to deal with such use-case. Co-developed-by: Geliang Tang Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Paolo Abeni Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250927-net-next-mptcp-rcv-path-imp-v1-6-5da266aa9c1a@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 26fbd9f6a3f7..da21f1807729 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -142,22 +142,33 @@ static void mptcp_drop(struct sock *sk, struct sk_buff *skb) __kfree_skb(skb); } -static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, - struct sk_buff *from) +static bool __mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, + struct sk_buff *from, bool *fragstolen, + int *delta) { - bool fragstolen; - int delta; + int limit = READ_ONCE(sk->sk_rcvbuf); if (unlikely(MPTCP_SKB_CB(to)->cant_coalesce) || MPTCP_SKB_CB(from)->offset || - ((to->len + from->len) > (sk->sk_rcvbuf >> 3)) || - !skb_try_coalesce(to, from, &fragstolen, &delta)) + ((to->len + from->len) > (limit >> 3)) || + !skb_try_coalesce(to, from, fragstolen, delta)) return false; pr_debug("colesced seq %llx into %llx new len %d new end seq %llx\n", MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq, to->len, MPTCP_SKB_CB(from)->end_seq); MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq; + return true; +} + +static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, + struct sk_buff *from) +{ + bool fragstolen; + int delta; + + if (!__mptcp_try_coalesce(sk, to, from, &fragstolen, &delta)) + return false; /* note the fwd memory can reach a negative value after accounting * for the delta, but the later skb free will restore a non From 59701b1870032c1bf32244d87476bcd4b5ecb41b Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 27 Sep 2025 11:40:43 +0200 Subject: [PATCH 7/8] mptcp: minor move_skbs_to_msk() cleanup Such function is called only by __mptcp_data_ready(), which in turn is always invoked when msk is not owned by the user: we can drop the redundant, related check. Additionally mptcp needs to propagate the socket error only for current subflow. Reviewed-by: Geliang Tang Tested-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Paolo Abeni Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250927-net-next-mptcp-rcv-path-imp-v1-7-5da266aa9c1a@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index da21f1807729..0292162a14ee 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -814,12 +814,8 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) moved = __mptcp_move_skbs_from_subflow(msk, ssk); __mptcp_ofo_queue(msk); - if (unlikely(ssk->sk_err)) { - if (!sock_owned_by_user(sk)) - __mptcp_error_report(sk); - else - __set_bit(MPTCP_ERROR_REPORT, &msk->cb_flags); - } + if (unlikely(ssk->sk_err)) + __mptcp_subflow_error_report(sk, ssk); /* If the moves have caught up with the DATA_FIN sequence number * it's time to ack the DATA_FIN and change socket state, but From c912f935a5c7e43f2b6be94d76e4ddbb6ff14c6d Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Sat, 27 Sep 2025 11:40:44 +0200 Subject: [PATCH 8/8] selftests: mptcp: join: validate new laminar endp Here are a few sub-tests for mptcp_join.sh, validating the new 'laminar' endpoint type. In a setup where subflows created using the routing rules would be rejected by the listener, and where the latter announces one IP address, some cases are verified: - Without any 'laminar' endpoints: no new subflows are created. - With one 'laminar' endpoint: a second subflow is created. - With multiple 'laminar' endpoints: 2 IPv4 subflows are created. - With one 'laminar' endpoint, but the server announcing a second IP address, only one subflow is created. - With one 'laminar' + 'subflow' endpoint, the same endpoint is only used once. Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250927-net-next-mptcp-rcv-path-imp-v1-8-5da266aa9c1a@kernel.org Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/mptcp/mptcp_join.sh | 69 +++++++++++++++++++ tools/testing/selftests/net/mptcp/pm_nl_ctl.c | 9 +++ 2 files changed, 78 insertions(+) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index a94b3960ad5e..c90d8e8b95cb 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2320,6 +2320,74 @@ signal_address_tests() fi } +laminar_endp_tests() +{ + # no laminar endpoints: routing rules are used + if reset_with_tcp_filter "without a laminar endpoint" ns1 10.0.2.2 REJECT && + mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; 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 + run_tests $ns1 $ns2 10.0.1.1 + join_syn_tx=1 \ + chk_join_nr 0 0 0 + chk_add_nr 1 1 + fi + + # laminar endpoints: this endpoint is used + if reset_with_tcp_filter "with a laminar endpoint" ns1 10.0.2.2 REJECT && + mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; 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 + pm_nl_add_endpoint $ns2 10.0.3.2 flags laminar + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi + + # laminar endpoints: these endpoints are used + if reset_with_tcp_filter "with multiple laminar endpoints" ns1 10.0.2.2 REJECT && + mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; 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 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns2 dead:beef:3::2 flags laminar + pm_nl_add_endpoint $ns2 10.0.3.2 flags laminar + pm_nl_add_endpoint $ns2 10.0.4.2 flags laminar + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 2 2 + fi + + # laminar endpoints: only one endpoint is used + if reset_with_tcp_filter "single laminar endpoint" ns1 10.0.2.2 REJECT && + mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; 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 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags laminar + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 2 2 + fi + + # laminar endpoints: subflow and laminar flags + if reset_with_tcp_filter "sublow + laminar endpoints" ns1 10.0.2.2 REJECT && + mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then + pm_nl_set_limits $ns1 0 4 + pm_nl_set_limits $ns2 2 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,laminar + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,laminar + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi +} + link_failure_tests() { # accept and use add_addr with additional subflows and link loss @@ -4109,6 +4177,7 @@ all_tests_sorted=( f@subflows_tests e@subflows_error_tests s@signal_address_tests + L@laminar_endp_tests l@link_failure_tests t@add_addr_timeout_tests r@remove_tests diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index d4981b76693b..65b374232ff5 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -830,6 +830,8 @@ int add_addr(int fd, int pm_family, int argc, char *argv[]) flags |= MPTCP_PM_ADDR_FLAG_SUBFLOW; else if (!strcmp(tok, "signal")) flags |= MPTCP_PM_ADDR_FLAG_SIGNAL; + else if (!strcmp(tok, "laminar")) + flags |= MPTCP_PM_ADDR_FLAG_LAMINAR; else if (!strcmp(tok, "backup")) flags |= MPTCP_PM_ADDR_FLAG_BACKUP; else if (!strcmp(tok, "fullmesh")) @@ -1018,6 +1020,13 @@ static void print_addr(struct rtattr *attrs, int len) printf(","); } + if (flags & MPTCP_PM_ADDR_FLAG_LAMINAR) { + printf("laminar"); + flags &= ~MPTCP_PM_ADDR_FLAG_LAMINAR; + if (flags) + printf(","); + } + if (flags & MPTCP_PM_ADDR_FLAG_BACKUP) { printf("backup"); flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP;