From f755be0b1ff429a2ecf709beeb1bcd7abc111c2b Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 12 Sep 2025 14:25:50 +0200 Subject: [PATCH 1/5] mptcp: propagate shutdown to subflows when possible When the MPTCP DATA FIN have been ACKed, there is no more MPTCP related metadata to exchange, and all subflows can be safely shutdown. Before this patch, the subflows were actually terminated at 'close()' time. That's certainly fine most of the time, but not when the userspace 'shutdown()' a connection, without close()ing it. When doing so, the subflows were staying in LAST_ACK state on one side -- and consequently in FIN_WAIT2 on the other side -- until the 'close()' of the MPTCP socket. Now, when the DATA FIN have been ACKed, all subflows are shutdown. A consequence of this is that the TCP 'FIN' flag can be set earlier now, but the end result is the same. This affects the packetdrill tests looking at the end of the MPTCP connections, but for a good reason. Note that tcp_shutdown() will check the subflow state, so no need to do that again before calling it. Fixes: 3721b9b64676 ("mptcp: Track received DATA_FIN sequence number and add related helpers") Cc: stable@vger.kernel.org Fixes: 16a9a9da1723 ("mptcp: Add helper to process acks of DATA_FIN") Reviewed-by: Mat Martineau Reviewed-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250912-net-mptcp-fix-sft-connect-v1-1-d40e77cbbf02@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e6fd97b21e9e..5e497a83e967 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -371,6 +371,20 @@ static void mptcp_close_wake_up(struct sock *sk) sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); } +static void mptcp_shutdown_subflows(struct mptcp_sock *msk) +{ + struct mptcp_subflow_context *subflow; + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; + + slow = lock_sock_fast(ssk); + tcp_shutdown(ssk, SEND_SHUTDOWN); + unlock_sock_fast(ssk, slow); + } +} + /* called under the msk socket lock */ static bool mptcp_pending_data_fin_ack(struct sock *sk) { @@ -395,6 +409,7 @@ static void mptcp_check_data_fin_ack(struct sock *sk) break; case TCP_CLOSING: case TCP_LAST_ACK: + mptcp_shutdown_subflows(msk); mptcp_set_state(sk, TCP_CLOSE); break; } @@ -563,6 +578,7 @@ static bool mptcp_check_data_fin(struct sock *sk) mptcp_set_state(sk, TCP_CLOSING); break; case TCP_FIN_WAIT2: + mptcp_shutdown_subflows(msk); mptcp_set_state(sk, TCP_CLOSE); break; default: From 14e22b43df25dbd4301351b882486ea38892ae4f Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 12 Sep 2025 14:25:51 +0200 Subject: [PATCH 2/5] selftests: mptcp: connect: catch IO errors on listen side IO errors were correctly printed to stderr, and propagated up to the main loop for the server side, but the returned value was ignored. As a consequence, the program for the listener side was no longer exiting with an error code in case of IO issues. Because of that, some issues might not have been seen. But very likely, most issues either had an effect on the client side, or the file transfer was not the expected one, e.g. the connection got reset before the end. Still, it is better to fix this. The main consequence of this issue is the error that was reported by the selftests: the received and sent files were different, and the MIB counters were not printed. Also, when such errors happened during the 'disconnect' tests, the program tried to continue until the timeout. Now when an IO error is detected, the program exits directly with an error. Fixes: 05be5e273c84 ("selftests: mptcp: add disconnect tests") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Reviewed-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250912-net-mptcp-fix-sft-connect-v1-2-d40e77cbbf02@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_connect.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 4f07ac9fa207..1408698df099 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -1093,6 +1093,7 @@ int main_loop_s(int listensock) struct pollfd polls; socklen_t salen; int remotesock; + int err = 0; int fd = 0; again: @@ -1125,7 +1126,7 @@ int main_loop_s(int listensock) SOCK_TEST_TCPULP(remotesock, 0); memset(&winfo, 0, sizeof(winfo)); - copyfd_io(fd, remotesock, 1, true, &winfo); + err = copyfd_io(fd, remotesock, 1, true, &winfo); } else { perror("accept"); return 1; @@ -1134,10 +1135,10 @@ int main_loop_s(int listensock) if (cfg_input) close(fd); - if (--cfg_repeat > 0) + if (!err && --cfg_repeat > 0) goto again; - return 0; + return err; } static void init_rng(void) From 8708c5d8b3fb3f6d5d3b9e6bfe01a505819f519a Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 12 Sep 2025 14:25:52 +0200 Subject: [PATCH 3/5] selftests: mptcp: avoid spurious errors on TCP disconnect The disconnect test-case, with 'plain' TCP sockets generates spurious errors, e.g. 07 ns1 TCP -> ns1 (dead:beef:1::1:10006) MPTCP read: Connection reset by peer read: Connection reset by peer (duration 155ms) [FAIL] client exit code 3, server 3 netns ns1-FloSdv (listener) socket stat for 10006: TcpActiveOpens 2 0.0 TcpPassiveOpens 2 0.0 TcpEstabResets 2 0.0 TcpInSegs 274 0.0 TcpOutSegs 276 0.0 TcpOutRsts 3 0.0 TcpExtPruneCalled 2 0.0 TcpExtRcvPruned 1 0.0 TcpExtTCPPureAcks 104 0.0 TcpExtTCPRcvCollapsed 2 0.0 TcpExtTCPBacklogCoalesce 42 0.0 TcpExtTCPRcvCoalesce 43 0.0 TcpExtTCPChallengeACK 1 0.0 TcpExtTCPFromZeroWindowAdv 42 0.0 TcpExtTCPToZeroWindowAdv 41 0.0 TcpExtTCPWantZeroWindowAdv 13 0.0 TcpExtTCPOrigDataSent 164 0.0 TcpExtTCPDelivered 165 0.0 TcpExtTCPRcvQDrop 1 0.0 In the failing scenarios (TCP -> MPTCP), the involved sockets are actually plain TCP ones, as fallbacks for passive sockets at 2WHS time cause the MPTCP listeners to actually create 'plain' TCP sockets. Similar to commit 218cc166321f ("selftests: mptcp: avoid spurious errors on disconnect"), the root cause is in the user-space bits: the test program tries to disconnect as soon as all the pending data has been spooled, generating an RST. If such option reaches the peer before the connection has reached the closed status, the TCP socket will report an error to the user-space, as per protocol specification, causing the above failure. Note that it looks like this issue got more visible since the "tcp: receiver changes" series from commit 06baf9bfa6ca ("Merge branch 'tcp-receiver-changes'"). Address the issue by explicitly waiting for the TCP sockets (-t) to reach a closed status before performing the disconnect. More precisely, the test program now waits for plain TCP sockets or TCP subflows in addition to the MPTCP sockets that were already monitored. While at it, use 'ss' with '-n' to avoid resolving service names, which is not needed here. Fixes: 218cc166321f ("selftests: mptcp: avoid spurious errors on disconnect") Cc: stable@vger.kernel.org Suggested-by: Paolo Abeni Reviewed-by: Mat Martineau Reviewed-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250912-net-mptcp-fix-sft-connect-v1-3-d40e77cbbf02@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_connect.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 1408698df099..b148cadb96d0 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -1248,7 +1248,7 @@ void xdisconnect(int fd) else xerror("bad family"); - strcpy(cmd, "ss -M | grep -q "); + strcpy(cmd, "ss -Mnt | grep -q "); cmdlen = strlen(cmd); if (!inet_ntop(addr.ss_family, raw_addr, &cmd[cmdlen], sizeof(cmd) - cmdlen)) @@ -1258,7 +1258,7 @@ void xdisconnect(int fd) /* * wait until the pending data is completely flushed and all - * the MPTCP sockets reached the closed status. + * the sockets reached the closed status. * disconnect will bypass/ignore/drop any pending data. */ for (i = 0; ; i += msec_sleep) { From a17c5aa3a32373f80b4714b411bd8d4ffee6fc6a Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 12 Sep 2025 14:25:53 +0200 Subject: [PATCH 4/5] selftests: mptcp: print trailing bytes with od This is better than printing random bytes in the terminal. Note that Jakub suggested 'hexdump', but Mat found out this tool is not often installed by default. 'od' can do a similar job, and it is in the POSIX specs and available in coreutils, so it should be on more systems. While at it, display a few more bytes, just to fill in the two lines. And no need to display the 3rd only line showing the next number of bytes: 0000040. Suggested-by: Jakub Kicinski Suggested-by: Mat Martineau Reviewed-by: Mat Martineau Reviewed-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250912-net-mptcp-fix-sft-connect-v1-4-d40e77cbbf02@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_lib.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 09cd24b2ae46..d62e653d48b0 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -384,7 +384,7 @@ mptcp_lib_make_file() { mptcp_lib_print_file_err() { ls -l "${1}" 1>&2 echo "Trailing bytes are: " - tail -c 27 "${1}" + tail -c 32 "${1}" | od -x | head -n2 } # $1: input file ; $2: output file ; $3: what kind of file From cf74e0aa0eb024741c8b5cb7e839d2824ca77336 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 12 Sep 2025 14:25:54 +0200 Subject: [PATCH 5/5] selftests: mptcp: connect: print pcap prefix To be able to find which capture files have been produced after several runs. This prefix was not printed anywhere before. While at it, always use the same prefix by taking info from ns1, instead of "$connector_ns", which is sometimes ns1, sometimes ns2 in the subtests. Reviewed-by: Mat Martineau Reviewed-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250912-net-mptcp-fix-sft-connect-v1-5-d40e77cbbf02@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_connect.sh | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index c2ab9f7f0d21..47ecb5b3836e 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -211,6 +211,11 @@ if $checksum; then done fi +if $capture; then + rndh="${ns1:4}" + mptcp_lib_pr_info "Packet capture files will have this prefix: ${rndh}-" +fi + set_ethtool_flags() { local ns="$1" local dev="$2" @@ -361,7 +366,6 @@ do_transfer() if $capture; then local capuser - local rndh="${connector_ns:4}" if [ -z $SUDO_USER ] ; then capuser="" else