[PATCH 6.18.y 4/4] mptcp: do not reschedule the RTX timer for fallback sockets

[Sasha Levin <sashal@kernel.org>]

From: Paolo Abeni <pabeni@redhat.com>

[ Upstream commit e2ab913f68c7d11e2561b8a8ad0b87ffefcad667 ]

On fallback socket the retrans timer is a quite convoluted no-op, but
currently nothing prevents the MPTCP core to keep rescheduling it.

Additionally gate RTX timer reset to the msk not being fallen back to
TCP yet. To avoid adding multiple tests in fast-path, use a new flags
bit for such condition.

The RTX enable bit is clear at close time and set before the msk could
start retransmitting, with a couple of caveats:

- passive sockets inherit the bit from the listener msk; set the bit on
  such socket to avoid flipping it in the fast-path, even if the
  listener will obviously never retransmit.

- while fastopening (MPTFO), mptcp_sendmsg_fastopen still ends-up
  calling mptcp_connect via tcp_sendmsg_fastopen ->
  __inet_stream_connect(ssk->sk_socket), and the first subflow's
  sk_socket points to the msk one.

Fixes: b51f9b80c032 ("mptcp: introduce MPTCP retransmission timer")
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-1-df1de70348b6@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/mptcp/protocol.c | 13 ++++++++++---
 net/mptcp/protocol.h |  1 +
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 2dd6840089f86..fd3873bec8088 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -93,6 +93,7 @@ bool __mptcp_try_fallback(struct mptcp_sock *msk, int fb_mib)
 
 	msk->allow_subflows = false;
 	set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
+	clear_bit(MPTCP_RTX_ENABLED, &msk->flags);
 	__MPTCP_INC_STATS(net, fb_mib);
 	spin_unlock_bh(&msk->fallback_lock);
 	return true;
@@ -939,13 +940,14 @@ static bool mptcp_rtx_timer_pending(struct sock *sk)
 
 static void mptcp_reset_rtx_timer(struct sock *sk)
 {
+	struct mptcp_sock *msk = mptcp_sk(sk);
 	unsigned long tout;
 
-	/* prevent rescheduling on close */
-	if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE))
+	/* Prevent rescheduling on close and in case of fallback. */
+	if (!test_bit(MPTCP_RTX_ENABLED, &msk->flags))
 		return;
 
-	tout = mptcp_sk(sk)->timer_ival;
+	tout = msk->timer_ival;
 	sk_reset_timer(sk, &sk->mptcp_retransmit_timer, jiffies + tout);
 }
 
@@ -3051,6 +3053,9 @@ void mptcp_set_state(struct sock *sk, int state)
 		 * transition from TCP_SYN_RECV to TCP_CLOSE_WAIT.
 		 */
 		break;
+	case TCP_CLOSE:
+		clear_bit(MPTCP_RTX_ENABLED, &mptcp_sk(sk)->flags);
+		fallthrough;
 	default:
 		if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT)
 			MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB);
@@ -3851,6 +3856,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (IS_ERR(ssk))
 		return PTR_ERR(ssk);
 
+	set_bit(MPTCP_RTX_ENABLED, &msk->flags);
 	mptcp_set_state(sk, TCP_SYN_SENT);
 	subflow = mptcp_subflow_ctx(ssk);
 #ifdef CONFIG_TCP_MD5SIG
@@ -3998,6 +4004,7 @@ static int mptcp_listen(struct socket *sock, int backlog)
 		goto unlock;
 	}
 
+	set_bit(MPTCP_RTX_ENABLED, &msk->flags);
 	mptcp_set_state(sk, TCP_LISTEN);
 	sock_set_flag(sk, SOCK_RCU_FREE);
 
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 6eab87ce7b353..4e9d139be69be 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -116,6 +116,7 @@
 #define MPTCP_WORK_RTX		1
 #define MPTCP_FALLBACK_DONE	2
 #define MPTCP_WORK_CLOSE_SUBFLOW 3
+#define MPTCP_RTX_ENABLED	4
 
 /* MPTCP socket release cb flags */
 #define MPTCP_PUSH_PENDING	1
-- 
2.53.0