Merge branch 'mptcp-fixes-for-connect-selftest-flakes'

Matthieu Baerts says:

====================
mptcp: fixes for connect selftest flakes

Last week, Jakub reported [1] that the MPTCP Connect selftest was
unstable. It looked like it started after the introduction of some fixes
[2]. After analysis from Paolo, these patches revealed existing bugs,
that should be fixed by the following patches.

- Patch 1: Make sure ACK are sent when MPTCP-level window re-opens. In
  some corner cases, the other peer was not notified when more data
  could be sent. A fix for v5.11, but depending on a feature introduced
  in v5.19.

- Patch 2: Fix spurious wake-up under memory pressure. In this
  situation, the userspace could be invited to read data not being there
  yet. A fix for v6.7.

- Patch 3: Fix a false positive error when running the MPTCP Connect
  selftest with the "disconnect" cases. The userspace could disconnect
  the socket too soon, which would reset (MP_FASTCLOSE) the connection,
  interpreted as an error by the test. A fix for v5.17.

Link: https://lore.kernel.org/20250107131845.5e5de3c5@kernel.org [1]
Link: https://lore.kernel.org/20241230-net-mptcp-rbuf-fixes-v1-0-8608af434ceb@kernel.org [2]
====================

Link: https://patch.msgid.link/20250113-net-mptcp-connect-st-flakes-v1-0-0d986ee7b1b6@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 43 insertions, 15 deletions

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index a62bc874bf1e..123f3f297284 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -607,7 +607,6 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 	}
 	opts->ext_copy.use_ack = 1;
 	opts->suboptions = OPTION_MPTCP_DSS;
-	WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk));
 
 	/* Add kind/length/subtype/flag overhead if mapping is not populated */
 	if (dss_size == 0)
@@ -1288,7 +1287,7 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th)
 			}
 			MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICT);
 		}
-		return;
+		goto update_wspace;
 	}
 
 	if (rcv_wnd_new != rcv_wnd_old) {
@@ -1313,6 +1312,9 @@ raise_win:
 		th->window = htons(new_win);
 		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDSHARED);
 	}
+
+update_wspace:
+	WRITE_ONCE(msk->old_wspace, tp->rcv_wnd);
 }
 
 __sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index a93e661ef5c4..73526f1d768f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -760,10 +760,15 @@ static inline u64 mptcp_data_avail(const struct mptcp_sock *msk)
 
 static inline bool mptcp_epollin_ready(const struct sock *sk)
 {
+	u64 data_avail = mptcp_data_avail(mptcp_sk(sk));
+
+	if (!data_avail)
+		return false;
+
 	/* mptcp doesn't have to deal with small skbs in the receive queue,
-	 * at it can always coalesce them
+	 * as it can always coalesce them
 	 */
-	return (mptcp_data_avail(mptcp_sk(sk)) >= sk->sk_rcvlowat) ||
+	return (data_avail >= sk->sk_rcvlowat) ||
 	       (mem_cgroup_sockets_enabled && sk->sk_memcg &&
 		mem_cgroup_under_socket_pressure(sk->sk_memcg)) ||
 	       READ_ONCE(tcp_memory_pressure);
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 4209b9569039..414addef9a45 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -25,6 +25,8 @@
 #include <sys/types.h>
 #include <sys/mman.h>
 
+#include <arpa/inet.h>
+
 #include <netdb.h>
 #include <netinet/in.h>
 
@@ -1211,23 +1213,42 @@ static void parse_setsock_options(const char *name)
 	exit(1);
 }
 
-void xdisconnect(int fd, int addrlen)
+void xdisconnect(int fd)
 {
-	struct sockaddr_storage empty;
+	socklen_t addrlen = sizeof(struct sockaddr_storage);
+	struct sockaddr_storage addr, empty;
 	int msec_sleep = 10;
-	int queued = 1;
-	int i;
+	void *raw_addr;
+	int i, cmdlen;
+	char cmd[128];
+
+	/* get the local address and convert it to string */
+	if (getsockname(fd, (struct sockaddr *)&addr, &addrlen) < 0)
+		xerror("getsockname");
+
+	if (addr.ss_family == AF_INET)
+		raw_addr = &(((struct sockaddr_in *)&addr)->sin_addr);
+	else if (addr.ss_family == AF_INET6)
+		raw_addr = &(((struct sockaddr_in6 *)&addr)->sin6_addr);
+	else
+		xerror("bad family");
+
+	strcpy(cmd, "ss -M | grep -q ");
+	cmdlen = strlen(cmd);
+	if (!inet_ntop(addr.ss_family, raw_addr, &cmd[cmdlen],
+		       sizeof(cmd) - cmdlen))
+		xerror("inet_ntop");
 
 	shutdown(fd, SHUT_WR);
 
-	/* while until the pending data is completely flushed, the later
+	/*
+	 * wait until the pending data is completely flushed and all
+	 * the MPTCP sockets reached the closed status.
 	 * disconnect will bypass/ignore/drop any pending data.
 	 */
 	for (i = 0; ; i += msec_sleep) {
-		if (ioctl(fd, SIOCOUTQ, &queued) < 0)
-			xerror("can't query out socket queue: %d", errno);
-
-		if (!queued)
+		/* closed socket are not listed by 'ss' */
+		if (system(cmd) != 0)
 			break;
 
 		if (i > poll_timeout)
@@ -1281,9 +1302,9 @@ again:
 		return ret;
 
 	if (cfg_truncate > 0) {
-		xdisconnect(fd, peer->ai_addrlen);
+		xdisconnect(fd);
 	} else if (--cfg_repeat > 0) {
-		xdisconnect(fd, peer->ai_addrlen);
+		xdisconnect(fd);
 
 		/* the socket could be unblocking at this point, we need the
 		 * connect to be blocking