From: Geliang Tang <geliang.tang@suse.com>

commit 14c56686a64c65ba716ff48f1f4b19c85f4cb2a9 upstream.

When closing the first subflow, the MPTCP protocol unconditionally
calls tcp_disconnect(), which in turn generates a reset if the subflow
is established.

That is unexpected and different from what MPTCP does with MPJ
subflows, where resets are generated only on FASTCLOSE and other edge
scenarios.

We can't reuse for the first subflow the same code in place for MPJ
subflows, as MPTCP clean them up completely via a tcp_close() call,
while must keep the first subflow socket alive for later re-usage, due
to implementation constraints.

This patch adds a new helper __mptcp_subflow_disconnect() that
encapsulates, a logic similar to tcp_close, issuing a reset only when
the MPTCP_CF_FASTCLOSE flag is set, and performing a clean shutdown
otherwise.

Fixes: c2b2ae3925b6 ("mptcp: handle correctly disconnect() failures")
Cc: stable@vger.kernel.org
Reviewed-by: Matthieu Baerts <matttbe@kernel.org>
Co-developed-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20231018-send-net-20231018-v1-4-17ecb002e41d@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Matthieu Baerts <matttbe@kernel.org>
---
Backport notes:
  - One conflict due to 39880bd808ad ("mptcp: get rid of msk->subflow")
    introduced in v6.6. In previous versions, the socket state needs to
    be set to SS_UNCONNECTED.
---
 net/mptcp/protocol.c | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 881e05193ac9..0a66181b56cd 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2374,6 +2374,26 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
 #define MPTCP_CF_PUSH		BIT(1)
 #define MPTCP_CF_FASTCLOSE	BIT(2)
 
+/* be sure to send a reset only if the caller asked for it, also
+ * clean completely the subflow status when the subflow reaches
+ * TCP_CLOSE state
+ */
+static void __mptcp_subflow_disconnect(struct sock *ssk,
+				       struct mptcp_subflow_context *subflow,
+				       unsigned int flags)
+{
+	if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    (flags & MPTCP_CF_FASTCLOSE)) {
+		/* The MPTCP code never wait on the subflow sockets, TCP-level
+		 * disconnect should never fail
+		 */
+		WARN_ON_ONCE(tcp_disconnect(ssk, 0));
+		mptcp_subflow_ctx_reset(subflow);
+	} else {
+		tcp_shutdown(ssk, SEND_SHUTDOWN);
+	}
+}
+
 /* subflow sockets can be either outgoing (connect) or incoming
  * (accept).
  *
@@ -2411,7 +2431,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 	lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
 
 	if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) {
-		/* be sure to force the tcp_disconnect() path,
+		/* be sure to force the tcp_close path
 		 * to generate the egress reset
 		 */
 		ssk->sk_lingertime = 0;
@@ -2421,12 +2441,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 
 	need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk);
 	if (!dispose_it) {
-		/* The MPTCP code never wait on the subflow sockets, TCP-level
-		 * disconnect should never fail
-		 */
-		WARN_ON_ONCE(tcp_disconnect(ssk, 0));
+		__mptcp_subflow_disconnect(ssk, subflow, flags);
 		msk->subflow->state = SS_UNCONNECTED;
-		mptcp_subflow_ctx_reset(subflow);
 		release_sock(ssk);
 
 		goto out;
-- 
2.40.1