Merge branch 'selftests-mptcp-avoid-spurious-errors-on-tcp-disconnect'

Matthieu Baerts says:

====================
selftests: mptcp: avoid spurious errors on TCP disconnect

This series should fix the recent instabilities seen by MPTCP and NIPA
CIs where the 'mptcp_connect.sh' tests fail regularly when running the
'disconnect' subtests with "plain" TCP sockets, e.g.

  # INFO: disconnect
  # 63 ns1 MPTCP -> ns1 (10.0.1.1:20001      ) MPTCP     (duration   996ms) [ OK ]
  # 64 ns1 MPTCP -> ns1 (10.0.1.1:20002      ) TCP       (duration   851ms) [ OK ]
  # 65 ns1 TCP   -> ns1 (10.0.1.1:20003      ) MPTCP     Unexpected revents: POLLERR/POLLNVAL(19)
  # (duration   896ms) [FAIL] file received by server does not match (in, out):
  # -rw-r--r-- 1 root root 11112852 Aug 19 09:16 /tmp/tmp.hlJe5DoMoq.disconnect
  # Trailing bytes are:
  # /{ga 6@=#.8:-rw------- 1 root root 10085368 Aug 19 09:16 /tmp/tmp.blClunilxx
  # Trailing bytes are:
  # /{ga 6@=#.8:66 ns1 MPTCP -> ns1 (dead:beef:1::1:20004) MPTCP     (duration   987ms) [ OK ]
  # 67 ns1 MPTCP -> ns1 (dead:beef:1::1:20005) TCP       (duration   911ms) [ OK ]
  # 68 ns1 TCP   -> ns1 (dead:beef:1::1:20006) MPTCP     (duration   980ms) [ OK ]
  # [FAIL] Tests of the full disconnection have failed

These issues started to be visible after some behavioural changes in
TCP, where too quick re-connections after a shutdown() can now be more
easily rejected. Patch 3 modifies the selftests to wait, but this
resolution revealed an issue in MPTCP which is fixed by patch 1 (a fix
for v5.9 kernel).

Patches 2 and 4 improve some errors reported by the selftests, and patch
5 helps with the debugging of such issues.
====================

Link: https://patch.msgid.link/20250912-net-mptcp-fix-sft-connect-v1-0-d40e77cbbf02@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 28 insertions, 7 deletions

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:
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 4f07ac9fa207..b148cadb96d0 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 @@ again:
 		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 @@ again:
 	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)
@@ -1247,7 +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))
@@ -1257,7 +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) {
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 $SUDO_USER ] ; then
 			capuser=""
 		else
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index 09cd24b2ae46..d62e653d48b0 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -384,7 +384,7 @@ mptcp_lib_make_file() {
 mptcp_lib_print_file_err() {
 	ls -l "${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