[PATCH mptcp-net v2 4/6] mptcp: fix shutdown vs fallback race

[Paolo Abeni <pabeni@redhat.com>]

If the MPTCP socket shutdown happens before a fallback
to TCP, and all the pending data have been already spooled,
we never close the TCP connection.

Address the issue explicitly checking for critical condition
at fallback time.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/options.c  |  2 +-
 net/mptcp/protocol.c |  2 +-
 net/mptcp/protocol.h | 19 ++++++++++++++++---
 net/mptcp/subflow.c  |  2 +-
 4 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 0bfa6662447c..57eab237c837 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -966,7 +966,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 			goto reset;
 		subflow->mp_capable = 0;
 		pr_fallback(msk);
-		__mptcp_do_fallback(msk);
+		mptcp_do_fallback(ssk);
 		return false;
 	}
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 50026b8da625..4f4d6c66e190 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1245,7 +1245,7 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk,
 	MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPTX);
 	mptcp_subflow_ctx(ssk)->send_infinite_map = 0;
 	pr_fallback(msk);
-	__mptcp_do_fallback(msk);
+	mptcp_do_fallback(ssk);
 }
 
 static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 077a717799a0..ad9b02b1b3e6 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -941,12 +941,25 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
 	set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
 }
 
-static inline void mptcp_do_fallback(struct sock *sk)
+static inline void mptcp_do_fallback(struct sock *ssk)
 {
-	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
-	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	struct sock *sk = subflow->conn;
+	struct mptcp_sock *msk;
 
+	msk = mptcp_sk(sk);
 	__mptcp_do_fallback(msk);
+	if (READ_ONCE(msk->snd_data_fin_enable) && !(ssk->sk_shutdown & SEND_SHUTDOWN)) {
+		gfp_t saved_allocation = ssk->sk_allocation;
+
+		/* we are in a atomic (BH) scope, override ssk default for data
+		 * fin allocation
+		 */
+		ssk->sk_allocation = GFP_ATOMIC;
+		ssk->sk_shutdown |= SEND_SHUTDOWN;
+		tcp_shutdown(ssk, SEND_SHUTDOWN);
+		ssk->sk_allocation = saved_allocation;
+	}
 }
 
 #define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a)
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 040901c1f40c..75fdc6474d0e 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1273,7 +1273,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 			return false;
 		}
 
-		__mptcp_do_fallback(msk);
+		mptcp_do_fallback(ssk);
 	}
 
 	skb = skb_peek(&ssk->sk_receive_queue);
-- 
2.35.3