mptcp: fix rcv space initialization

commit 013e3179dbd2bc756ce1dd90354abac62f65b739 upstream.

mptcp_rcv_space_init() is supposed to happen under the msk socket
lock, but active msk socket does that without such protection.

Leverage the existing mptcp_propagate_state() helper to that extent.
We need to ensure mptcp_rcv_space_init will happen before
mptcp_rcv_space_adjust(), and the release_cb does not assure that:
explicitly check for such condition.

While at it, move the wnd_end initialization out of mptcp_rcv_space_init(),
it never belonged there.

Note that the race does not produce ill effect in practice, but
change allows cleaning-up and defying better the locking model.

Fixes: a6b118febbab ("mptcp: add receive buffer auto-tuning")
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 10 insertions, 7 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index f5368d5a442d..9d4d5dbdbb53 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1967,6 +1967,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 	if (copied <= 0)
 		return;
 
+	if (!msk->rcvspace_init)
+		mptcp_rcv_space_init(msk, msk->first);
+
 	msk->rcvq_space.copied += copied;
 
 	mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC);
@@ -3151,6 +3154,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 	msk->bytes_received = 0;
 	msk->bytes_sent = 0;
 	msk->bytes_retrans = 0;
+	msk->rcvspace_init = 0;
 
 	WRITE_ONCE(sk->sk_shutdown, 0);
 	sk_error_report(sk);
@@ -3238,6 +3242,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
 {
 	const struct tcp_sock *tp = tcp_sk(ssk);
 
+	msk->rcvspace_init = 1;
 	msk->rcvq_space.copied = 0;
 	msk->rcvq_space.rtt_us = 0;
 
@@ -3248,8 +3253,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
 				      TCP_INIT_CWND * tp->advmss);
 	if (msk->rcvq_space.space == 0)
 		msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT;
-
-	WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
 }
 
 static struct sock *mptcp_accept(struct sock *ssk, int flags, int *err,
@@ -3507,10 +3510,9 @@ void mptcp_finish_connect(struct sock *ssk)
 	WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
 	WRITE_ONCE(msk->snd_nxt, msk->write_seq);
 	WRITE_ONCE(msk->snd_una, msk->write_seq);
+	WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
 
 	mptcp_pm_new_connection(msk, ssk, 0);
-
-	mptcp_rcv_space_init(msk, ssk);
 }
 
 void mptcp_sock_graft(struct sock *sk, struct socket *parent)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 377c61163494..891757e22f3e 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -301,7 +301,8 @@ struct mptcp_sock {
 			nodelay:1,
 			fastopening:1,
 			in_accept_queue:1,
-			free_first:1;
+			free_first:1,
+			rcvspace_init:1;
 	struct work_struct work;
 	struct sk_buff  *ooo_last_skb;
 	struct rb_root  out_of_order_queue;
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index d3c5ecf8ddf5..8c7e22a9a37b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -424,6 +424,8 @@ void __mptcp_sync_state(struct sock *sk, int state)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
 	__mptcp_propagate_sndbuf(sk, msk->first);
+	if (!msk->rcvspace_init)
+		mptcp_rcv_space_init(msk, msk->first);
 	if (sk->sk_state == TCP_SYN_SENT) {
 		inet_sk_state_store(sk, state);
 		sk->sk_state_change(sk);
@@ -545,7 +547,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		}
 	} else if (mptcp_check_fallback(sk)) {
 fallback:
-		mptcp_rcv_space_init(msk, sk);
 		mptcp_propagate_state(parent, sk);
 	}
 	return;
@@ -1736,7 +1737,6 @@ static void subflow_state_change(struct sock *sk)
 	msk = mptcp_sk(parent);
 	if (subflow_simultaneous_connect(sk)) {
 		mptcp_do_fallback(sk);
-		mptcp_rcv_space_init(msk, sk);
 		pr_fallback(msk);
 		subflow->conn_finished = 1;
 		mptcp_propagate_state(parent, sk);