From 9d8d28738f24b75616d6ca7a27cb4aed88520343 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 2 Jun 2026 22:14:08 +1000 Subject: [PATCH 01/11] mptcp: fix missing wakeups in edge scenarios The mptcp_recvmsg() can fill MPTCP socket receive queue via mptcp_move_skbs(), but currently does not try to wakeup any listener, because the same process is going to check the receive queue soon. When multiple threads are reading from the same fd, the above can cause stall. Add the missing wakeup. Fixes: 6771bfd9ee24 ("mptcp: update mptcp ack sequence from work queue") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-1-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a72a6ad6ee8b..5a20ab2789ae 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2276,6 +2276,10 @@ static bool mptcp_move_skbs(struct sock *sk) mptcp_backlog_spooled(sk, moved, &skbs); } mptcp_data_unlock(sk); + + if (enqueued && mptcp_epollin_ready(sk)) + sk->sk_data_ready(sk); + return enqueued; } From d1918b36edcaed0ec4ef6888b2358c6b1ddcff47 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 2 Jun 2026 22:14:09 +1000 Subject: [PATCH 02/11] mptcp: fix retransmission loop when csum is enabled Sashiko noted that retransmission with csum enabled can actually transmit new data, but currently the relevant code does not update accordingly snd_nxt. The may cause incoming ack drop and an endless retransmission loop. Address the issue incrementing snd_nxt as needed. Fixes: 4e14867d5e91 ("mptcp: tune re-injections for csum enabled mode") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-2-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 5a20ab2789ae..7fac5fac2097 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2869,6 +2869,10 @@ static void __mptcp_retrans(struct sock *sk) msk->bytes_retrans += len; dfrag->already_sent = max(dfrag->already_sent, len); + /* With csum enabled retransmission can send new data. */ + if (after64(dfrag->already_sent + dfrag->data_seq, msk->snd_nxt)) + WRITE_ONCE(msk->snd_nxt, dfrag->already_sent + dfrag->data_seq); + reset_timer: mptcp_check_and_set_pending(sk); From 8ab24fdebc369c0dfb90f82c1650b1e66662bb45 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 2 Jun 2026 22:14:10 +1000 Subject: [PATCH 03/11] mptcp: close TOCTOU race while computing rcv_wnd The MPTCP output path access locklessly the MPTCP-level ack_seq in multiple times, using possibly different values for the data_ack in the DSS option and to compute the announced rcv wnd for the same packet. Refactor the cote to avoid inconsistencies which may confuse the peer. Also ensure that the MPTCP level rcv wnd is updated only when the egress packet actually contains a DSS ack. Fixes: fa3fe2b15031 ("mptcp: track window announced to peer") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-3-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/options.c | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 8a1c5698983c..2d25f319f328 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -570,7 +570,6 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, struct mptcp_ext *mpext; unsigned int ack_size; bool ret = false; - u64 ack_seq; opts->csum_reqd = READ_ONCE(msk->csum_enabled); mpext = skb ? mptcp_get_ext(skb) : NULL; @@ -601,14 +600,11 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, return ret; } - ack_seq = READ_ONCE(msk->ack_seq); if (READ_ONCE(msk->use_64bit_ack)) { ack_size = TCPOLEN_MPTCP_DSS_ACK64; - opts->ext_copy.data_ack = ack_seq; opts->ext_copy.ack64 = 1; } else { ack_size = TCPOLEN_MPTCP_DSS_ACK32; - opts->ext_copy.data_ack32 = (uint32_t)ack_seq; opts->ext_copy.ack64 = 0; } opts->ext_copy.use_ack = 1; @@ -1297,19 +1293,14 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) return true; } -static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th) +static u64 mptcp_set_rwin(struct mptcp_sock *msk, struct tcp_sock *tp, + struct tcphdr *th, u64 ack_seq) { const struct sock *ssk = (const struct sock *)tp; - struct mptcp_subflow_context *subflow; - u64 ack_seq, rcv_wnd_old, rcv_wnd_new; - struct mptcp_sock *msk; + u64 rcv_wnd_old, rcv_wnd_new; u32 new_win; u64 win; - subflow = mptcp_subflow_ctx(ssk); - msk = mptcp_sk(subflow->conn); - - ack_seq = READ_ONCE(msk->ack_seq); rcv_wnd_new = ack_seq + tp->rcv_wnd; rcv_wnd_old = atomic64_read(&msk->rcv_wnd_sent); @@ -1362,7 +1353,7 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th) update_wspace: WRITE_ONCE(msk->old_wspace, tp->rcv_wnd); - subflow->rcv_wnd_sent = rcv_wnd_new; + return rcv_wnd_new; } static void mptcp_track_rwin(struct tcp_sock *tp) @@ -1474,13 +1465,25 @@ void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, *ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags); if (mpext->use_ack) { + struct mptcp_sock *msk; + u64 ack_seq; + + /* DSS option is set only by mptcp_established_options, + * the caller is __tcp_transmit_skb() and ssk is always + * not NULL. + */ + subflow = mptcp_subflow_ctx(ssk); + msk = mptcp_sk(subflow->conn); + ack_seq = READ_ONCE(msk->ack_seq); if (mpext->ack64) { - put_unaligned_be64(mpext->data_ack, ptr); + put_unaligned_be64(ack_seq, ptr); ptr += 2; } else { - put_unaligned_be32(mpext->data_ack32, ptr); + put_unaligned_be32(ack_seq, ptr); ptr += 1; } + subflow->rcv_wnd_sent = mptcp_set_rwin(msk, tp, th, + ack_seq); } if (mpext->use_map) { @@ -1708,9 +1711,6 @@ void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, i += 4; } } - - if (tp) - mptcp_set_rwin(tp, th); } __be32 mptcp_get_reset_option(const struct sk_buff *skb) From da23be77e1292cd611e736c3aa17da633d7ddce7 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 2 Jun 2026 22:14:11 +1000 Subject: [PATCH 04/11] mptcp: allow subflow rcv wnd to shrink In MPTCP connection, the `window` field in the TCP header refers to the MPTCP-level rcv_nxt and it's right edge should not move backward. Such constraint is enforced at DSS option generation time. At the same time, the TCP stack ensures independently that the TCP-level rcv wnd right's edge does not move backward. That in turn causes artificial inflating of the MPTCP rcv window when the incoming data is acked at the TCP level and is OoO in the MPTCP sequence space (or lands in the backlog). As a consequence, the incoming traffic can exceed the receiver rcvbuf size even when the sender is not misbehaving. Prevent such scenario forcibly allowing the TCP subflow to shrink the TCP-level rcv wnd regardless of the current netns setting. Fixes: f3589be0c420 ("mptcp: never shrink offered window") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-4-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/options.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 2d25f319f328..51ca334678b4 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -566,6 +566,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); + struct tcp_sock *tp = tcp_sk(sk); unsigned int dss_size = 0; struct mptcp_ext *mpext; unsigned int ack_size; @@ -614,6 +615,12 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, if (dss_size == 0) ack_size += TCPOLEN_MPTCP_DSS_BASE; + /* The caller is __tcp_transmit_skb(), and will compute the new rcv + * wnd soon: ensure that the window can shrink. + */ + if (skb) + tp->rcv_wnd = tp->rcv_nxt - tp->rcv_wup; + dss_size += ack_size; *size = ALIGN(dss_size, 4); From 14e9fea30b68fc75b2b3d97396a7e6adb544bd2a Mon Sep 17 00:00:00 2001 From: Tao Cui Date: Tue, 2 Jun 2026 22:14:12 +1000 Subject: [PATCH 05/11] mptcp: pm: fix extra_subflows underflow on userspace PM subflow creation The userspace PM increments extra_subflows after __mptcp_subflow_connect() succeeds, but __mptcp_subflow_connect() calls mptcp_pm_close_subflow() on failure to roll back the pre-increment done by the kernel PM's fill_*() helpers. Because the userspace PM hasn't incremented yet at that point, this decrement is spurious and causes extra_subflows to underflow. Fix it by aligning the userspace PM with the kernel PM: increment extra_subflows before calling __mptcp_subflow_connect(), so the existing error path in subflow.c correctly rolls it back on failure. Also simplify the error handling by taking pm.lock only when needed for cleanup. Fixes: 77e4b94a3de6 ("mptcp: update userspace pm infos") Cc: stable@vger.kernel.org Signed-off-by: Tao Cui Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-5-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_userspace.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 8cbc1920afb4..0d3a95e676f1 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -408,19 +408,21 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) local.flags = entry.flags; local.ifindex = entry.ifindex; + spin_lock_bh(&msk->pm.lock); + msk->pm.extra_subflows++; + spin_unlock_bh(&msk->pm.lock); + lock_sock(sk); err = __mptcp_subflow_connect(sk, &local, &addr_r); release_sock(sk); - if (err) + if (err) { GENL_SET_ERR_MSG_FMT(info, "connect error: %d", err); - spin_lock_bh(&msk->pm.lock); - if (err) + spin_lock_bh(&msk->pm.lock); mptcp_userspace_pm_delete_local_addr(msk, &entry); - else - msk->pm.extra_subflows++; - spin_unlock_bh(&msk->pm.lock); + spin_unlock_bh(&msk->pm.lock); + } create_err: sock_put(sk); From 06fd2bec7aebf393288e4b78924482fe170caabc Mon Sep 17 00:00:00 2001 From: Tao Cui Date: Tue, 2 Jun 2026 22:14:13 +1000 Subject: [PATCH 06/11] selftests: mptcp: add test for extra_subflows underflow on userspace PM Add a test to verify that when userspace PM fails to create a subflow (e.g. using an unreachable address), the extra_subflows counter is not decremented below zero. Fixes: 77e4b94a3de6 ("mptcp: update userspace pm infos") Cc: stable@vger.kernel.org Signed-off-by: Tao Cui Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-6-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 5acd12021e6e..4b3f71e66609 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -4100,6 +4100,10 @@ userspace_tests() chk_rm_nr 0 1 chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 + # check counters are not affected by errors at creation time + userspace_pm_add_sf $ns2 10.0.12.2 10 2>/dev/null + chk_mptcp_info subflows 0 subflows 0 + chk_subflows_total 1 1 kill_events_pids mptcp_lib_kill_group_wait $tests_pid fi From 57132affbc89c02e1bf73fdf5724311bdc9a29da Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 2 Jun 2026 22:14:14 +1000 Subject: [PATCH 07/11] mptcp: sockopt: check timestamping ret value sock_set_timestamping() can fail for different reasons. The returned value should then be checked. If sock_set_timestamping() fails for at least one subflow, the first error is now reported to the userspace, similar to what is done with other socket options. Fixes: 9061f24bf82e ("mptcp: sockopt: propagate timestamp request to subflows") Cc: stable@vger.kernel.org Reported-by: Willem de Bruijn Closes: https://lore.kernel.org/willemdebruijn.kernel.178a41a53d041@gmail.com Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-7-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/sockopt.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 87b5796d0135..91aa57f1d0fd 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -241,15 +241,19 @@ static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk, mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + int err; lock_sock(ssk); - sock_set_timestamping(ssk, optname, timestamping); + err = sock_set_timestamping(ssk, optname, timestamping); release_sock(ssk); + + if (err < 0 && ret == 0) + ret = err; } release_sock(sk); - return 0; + return ret; } static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_t optval, From 7690137e70ab0fb1f8b5a30e6f087f8ee908b680 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 2 Jun 2026 22:14:15 +1000 Subject: [PATCH 08/11] mptcp: sockopt: set sockopt on all subflows The mptcp_setsockopt_all_sf(), currently used only with TCP_MAXSEG, stopped when one subflow returned an error. Even if it is not wrong, this is different from the other helpers trying to set the option on all subflows, and then returning an error if at least one of them had an issue. Follow this behaviour, for a question of uniformity. Fixes: 51c5fd09e1b4 ("mptcp: add TCP_MAXSEG sockopt support") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-8-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/sockopt.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 91aa57f1d0fd..fcf6feb2a9eb 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -817,10 +817,11 @@ static int mptcp_setsockopt_all_sf(struct mptcp_sock *msk, int level, mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + int err; - ret = tcp_setsockopt(ssk, level, optname, optval, optlen); - if (ret) - break; + err = tcp_setsockopt(ssk, level, optname, optval, optlen); + if (err < 0 && ret == 0) + ret = err; } if (!ret) From c378b1a6f8dd3e02eb08661f4d5d50f236eead03 Mon Sep 17 00:00:00 2001 From: Gang Yan Date: Tue, 2 Jun 2026 22:14:16 +1000 Subject: [PATCH 09/11] mptcp: check desc->count in read_sock __tcp_read_sock() checks desc->count after each skb is consumed and breaks the loop when it reaches 0. The MPTCP variant lacks this check. This is a functional bug, other subsystems also rely on this check: TLS strparser sets desc->count to 0 once a full TLS record is assembled and depends on this break to stop reading. Add the same desc->count check to __mptcp_read_sock(), mirroring __tcp_read_sock(). Fixes: 250d9766a984 ("mptcp: implement .read_sock") Cc: stable@vger.kernel.org Co-developed-by: Geliang Tang Signed-off-by: Geliang Tang Signed-off-by: Gang Yan Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-9-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 7fac5fac2097..cb9515f505aa 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -4428,6 +4428,8 @@ static int __mptcp_read_sock(struct sock *sk, read_descriptor_t *desc, } mptcp_eat_recv_skb(sk, skb); + if (!desc->count) + break; } if (noack) From 5e939544f9d2b4d5c052a07cfcde97de44263946 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 2 Jun 2026 22:14:17 +1000 Subject: [PATCH 10/11] mptcp: fix uninit-value in mptcp_established_options syzbot reported the following uninit splat: BUG: KMSAN: uninit-value in mptcp_write_data_fin net/mptcp/options.c:542 [inline] BUG: KMSAN: uninit-value in mptcp_established_options_dss net/mptcp/options.c:590 [inline] BUG: KMSAN: uninit-value in mptcp_established_options+0x112f/0x3530 net/mptcp/options.c:874 mptcp_write_data_fin net/mptcp/options.c:542 [inline] mptcp_established_options_dss net/mptcp/options.c:590 [inline] mptcp_established_options+0x112f/0x3530 net/mptcp/options.c:874 tcp_established_options+0x312/0xcc0 net/ipv4/tcp_output.c:1192 __tcp_transmit_skb+0x5dc/0x5fe0 net/ipv4/tcp_output.c:1575 __tcp_send_ack+0x967/0xad0 net/ipv4/tcp_output.c:4499 tcp_send_ack+0x3d/0x60 net/ipv4/tcp_output.c:4505 mptcp_subflow_shutdown+0x164/0x690 net/mptcp/protocol.c:3137 mptcp_check_send_data_fin+0x31b/0x3d0 net/mptcp/protocol.c:3218 __mptcp_wr_shutdown net/mptcp/protocol.c:3234 [inline] __mptcp_close+0x860/0x1360 net/mptcp/protocol.c:3313 mptcp_close+0x42/0x260 net/mptcp/protocol.c:3367 inet_release+0x1ee/0x2a0 net/ipv4/af_inet.c:442 __sock_release net/socket.c:722 [inline] sock_close+0xd6/0x2f0 net/socket.c:1514 __fput+0x60e/0x1010 fs/file_table.c:510 ____fput+0x25/0x30 fs/file_table.c:538 task_work_run+0x208/0x2b0 kernel/task_work.c:233 resume_user_mode_work include/linux/resume_user_mode.h:50 [inline] __exit_to_user_mode_loop kernel/entry/common.c:67 [inline] exit_to_user_mode_loop+0x306/0x1b60 kernel/entry/common.c:98 __exit_to_user_mode_prepare include/linux/irq-entry-common.h:207 [inline] syscall_exit_to_user_mode_prepare include/linux/irq-entry-common.h:238 [inline] syscall_exit_to_user_mode include/linux/entry-common.h:318 [inline] __do_fast_syscall_32+0x2c7/0x460 arch/x86/entry/syscall_32.c:310 do_fast_syscall_32+0x37/0x80 arch/x86/entry/syscall_32.c:332 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/syscall_32.c:370 entry_SYSENTER_compat_after_hwframe+0x84/0x8e Local variable opts created at: __tcp_transmit_skb+0x4d/0x5fe0 net/ipv4/tcp_output.c:1536 __tcp_send_ack+0x967/0xad0 net/ipv4/tcp_output.c:4499 The output path currently omits initializing the mptcp extension `use_map` flag in a few corner cases. Address the issue always zeroing all the extensions flags before eventually initializing the individual bits. To that extent, introduce and use a struct_group to avoid multiple bitwise operations. Fixes: cfcceb7a39fc ("tcp: shrink per-packet memset in __tcp_transmit_skb()") Cc: stable@vger.kernel.org Reported-by: syzbot+ff020673c5e3d94d9478@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=ff020673c5e3d94d9478 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-10-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- include/net/mptcp.h | 7 +++++-- net/mptcp/options.c | 6 +++++- 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/include/net/mptcp.h b/include/net/mptcp.h index f7263fe2a2e4..ee70f597a4de 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -27,7 +27,9 @@ struct mptcp_ext { u32 subflow_seq; u16 data_len; __sum16 csum; - u8 use_map:1, + + struct_group(flags, + u8 use_map:1, dsn64:1, data_fin:1, use_ack:1, @@ -35,9 +37,10 @@ struct mptcp_ext { mpc_map:1, frozen:1, reset_transient:1; - u8 reset_reason:4, + u8 reset_reason:4, csum_reqd:1, infinite_map:1; + ); /* end of flags group */ }; #define MPTCPOPT_HMAC_LEN 20 diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 51ca334678b4..f9f587203c35 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -572,6 +572,11 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, unsigned int ack_size; bool ret = false; + /* Zero `use_ack` and `use_map` flags with one shot. */ + BUILD_BUG_ON(sizeof_field(struct mptcp_ext, flags) != sizeof(u16)); + BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct mptcp_ext, flags), + sizeof(u16))); + *(u16 *)&opts->ext_copy.flags = 0; opts->csum_reqd = READ_ONCE(msk->csum_enabled); mpext = skb ? mptcp_get_ext(skb) : NULL; @@ -595,7 +600,6 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, /* passive sockets msk will set the 'can_ack' after accept(), even * if the first subflow may have the already the remote key handy */ - opts->ext_copy.use_ack = 0; if (!READ_ONCE(msk->can_ack)) { *size = ALIGN(dss_size, 4); return ret; From bd34fa0257261b76964df1c98f44b3cb4ee14620 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 2 Jun 2026 22:14:18 +1000 Subject: [PATCH 11/11] mptcp: add-addr: always drop other suboptions When an ADD_ADDR needs to be sent, it could be prepared if there is enough remaining space and even if the packet is not a pure ACK. But it would be dropped soon after. Indeed, in mptcp_pm_add_addr_signal(), there is enough space to fit a DSS of 20 octets and an ADD_ADDR echo containing an IPv4 address on 8 octets for example. In this case, the packet would be prepared, the MPTCP_ADD_ADDR_ECHO bit would be removed from pm->addr_signal, but the option would be silently dropped in mptcp_established_options_add_addr() not to override DSS info in the union from 'struct mptcp_out_options', and also because mptcp_write_options() will enforce mutually exclusion with DSS. Instead, don't even try to send an ADD_ADDR if it is not a pure ACK. Retry for each new packet until a pure-ACK is emitted. That's fine to do that, because each time an ADD_ADDR (echo) is scheduled, a pure ACK is queued. This also simplifies the code, and the skb checks can be done earlier, before the lock. Note: also, since commit 6d0060f600ad ("mptcp: Write MPTCP DSS headers to outgoing data packets"), opts->ahmac would not have been set to 0 when other suboptions were not dropped, and when sending an ADD_ADDR echo. That would have resulted in sending an ADD_ADDR using garbage info, where there was not enough space, instead of an echo one without the ADD_ADDR HMAC. Fixes: 1bff1e43a30e ("mptcp: optimize out option generation") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-11-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/options.c | 30 +++++++----------------------- net/mptcp/pm.c | 15 ++++----------- net/mptcp/protocol.h | 7 +++---- 3 files changed, 14 insertions(+), 38 deletions(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index f9f587203c35..b3ea7854818f 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -665,7 +665,6 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - bool drop_other_suboptions = false; unsigned int opt_size = *size; struct mptcp_addr_info addr; bool echo; @@ -676,36 +675,20 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * */ if (!mptcp_pm_should_add_signal(msk) || (opts->suboptions & (OPTION_MPTCP_MPJ_ACK | OPTION_MPTCP_MPC_ACK)) || - !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &addr, - &echo, &drop_other_suboptions)) + !skb || !skb_is_tcp_pure_ack(skb) || + !mptcp_pm_add_addr_signal(msk, opt_size, remaining, &addr, &echo)) return false; - /* - * Later on, mptcp_write_options() will enforce mutually exclusion with - * DSS, bail out if such option is set and we can't drop it. - */ - if (drop_other_suboptions) - remaining += opt_size; - else if (opts->suboptions & OPTION_MPTCP_DSS) - return false; + remaining += opt_size; len = mptcp_add_addr_len(addr.family, echo, !!addr.port); if (remaining < len) return false; *size = len; - if (drop_other_suboptions) { - pr_debug("drop other suboptions\n"); - opts->suboptions = 0; - - /* note that e.g. DSS could have written into the memory - * aliased by ahmac, we must reset the field here - * to avoid appending the hmac even for ADD_ADDR echo - * options - */ - opts->ahmac = 0; - *size -= opt_size; - } + pr_debug("drop other suboptions\n"); + opts->suboptions = 0; + *size -= opt_size; opts->addr = addr; opts->suboptions |= OPTION_MPTCP_ADD_ADDR; if (!echo) { @@ -715,6 +698,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * &opts->addr); } else { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX); + opts->ahmac = 0; } pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d\n", opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port)); diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 3e770c7407e1..470501470fe5 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -887,10 +887,9 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq) } } -bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, - unsigned int opt_size, unsigned int remaining, - struct mptcp_addr_info *addr, bool *echo, - bool *drop_other_suboptions) +bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int opt_size, + unsigned int remaining, + struct mptcp_addr_info *addr, bool *echo) { bool skip_add_addr = false; int ret = false; @@ -908,10 +907,7 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, * plain dup-ack from TCP perspective. The other MPTCP-relevant info, * if any, will be carried by the 'original' TCP ack */ - if (skb && skb_is_tcp_pure_ack(skb)) { - remaining += opt_size; - *drop_other_suboptions = true; - } + remaining += opt_size; *echo = mptcp_pm_should_add_signal_echo(msk); if (*echo) { @@ -929,9 +925,6 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, if (remaining < mptcp_add_addr_len(family, *echo, port)) { struct net *net = sock_net((struct sock *)msk); - if (!*drop_other_suboptions) - goto out_unlock; - if (*echo) { MPTCP_INC_STATS(net, MPTCP_MIB_ECHOADDTXDROP); } else { diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index e4f5aba24da7..b93b878478d2 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1229,10 +1229,9 @@ static inline int mptcp_rm_addr_len(const struct mptcp_rm_list *rm_list) return TCPOLEN_MPTCP_RM_ADDR_BASE + roundup(rm_list->nr - 1, 4) + 1; } -bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, - unsigned int opt_size, unsigned int remaining, - struct mptcp_addr_info *addr, bool *echo, - bool *drop_other_suboptions); +bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int opt_size, + unsigned int remaining, + struct mptcp_addr_info *addr, bool *echo); bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, struct mptcp_rm_list *rm_list); int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);