Merge branch 'mptcp-properly-clean-up-unaccepted-subflows'

Mat Martineau says:

====================
mptcp: Properly clean up unaccepted subflows

Patch 1 factors out part of the mptcp_close() function for use by a caller
that already owns the socket lock. This is a prerequisite for patch 2.

Patch 2 is the fix that fully cleans up the unaccepted subflow sockets.
====================

Link: https://lore.kernel.org/r/20220927193158.195729-1-mathew.j.martineau@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 22 insertions, 29 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 969b33a9dd6473..f8897a70c11d48 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2662,7 +2662,7 @@ static void __mptcp_clear_xmit(struct sock *sk)
 		dfrag_clear(sk, dfrag);
 }
 
-static void mptcp_cancel_work(struct sock *sk)
+void mptcp_cancel_work(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
@@ -2802,13 +2802,12 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	sock_put(sk);
 }
 
-static void mptcp_close(struct sock *sk, long timeout)
+bool __mptcp_close(struct sock *sk, long timeout)
 {
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	bool do_cancel_work = false;
 
-	lock_sock(sk);
 	sk->sk_shutdown = SHUTDOWN_MASK;
 
 	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
@@ -2850,6 +2849,17 @@ cleanup:
 	} else {
 		mptcp_reset_timeout(msk, 0);
 	}
+
+	return do_cancel_work;
+}
+
+static void mptcp_close(struct sock *sk, long timeout)
+{
+	bool do_cancel_work;
+
+	lock_sock(sk);
+
+	do_cancel_work = __mptcp_close(sk, timeout);
 	release_sock(sk);
 	if (do_cancel_work)
 		mptcp_cancel_work(sk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 132d50833df18e..8f372b8f059c6f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -612,6 +612,8 @@ void mptcp_subflow_reset(struct sock *ssk);
 void mptcp_subflow_queue_clean(struct sock *ssk);
 void mptcp_sock_graft(struct sock *sk, struct socket *parent);
 struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);
+bool __mptcp_close(struct sock *sk, long timeout);
+void mptcp_cancel_work(struct sock *sk);
 
 bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
 			   const struct mptcp_addr_info *b, bool use_port);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index c7d49fb6e7bdbe..07dd23d0fe04ac 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -602,30 +602,6 @@ static bool subflow_hmac_valid(const struct request_sock *req,
 	return !crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN);
 }
 
-static void mptcp_sock_destruct(struct sock *sk)
-{
-	/* if new mptcp socket isn't accepted, it is free'd
-	 * from the tcp listener sockets request queue, linked
-	 * from req->sk.  The tcp socket is released.
-	 * This calls the ULP release function which will
-	 * also remove the mptcp socket, via
-	 * sock_put(ctx->conn).
-	 *
-	 * Problem is that the mptcp socket will be in
-	 * ESTABLISHED state and will not have the SOCK_DEAD flag.
-	 * Both result in warnings from inet_sock_destruct.
-	 */
-	if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
-		sk->sk_state = TCP_CLOSE;
-		WARN_ON_ONCE(sk->sk_socket);
-		sock_orphan(sk);
-	}
-
-	/* We don't need to clear msk->subflow, as it's still NULL at this point */
-	mptcp_destroy_common(mptcp_sk(sk), 0);
-	inet_sock_destruct(sk);
-}
-
 static void mptcp_force_close(struct sock *sk)
 {
 	/* the msk is not yet exposed to user-space */
@@ -768,7 +744,6 @@ create_child:
 			/* new mpc subflow takes ownership of the newly
 			 * created mptcp socket
 			 */
-			new_msk->sk_destruct = mptcp_sock_destruct;
 			mptcp_sk(new_msk)->setsockopt_seq = ctx->setsockopt_seq;
 			mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1);
 			mptcp_token_accept(subflow_req, mptcp_sk(new_msk));
@@ -1763,13 +1738,19 @@ void mptcp_subflow_queue_clean(struct sock *listener_ssk)
 
 	for (msk = head; msk; msk = next) {
 		struct sock *sk = (struct sock *)msk;
-		bool slow;
+		bool slow, do_cancel_work;
 
+		sock_hold(sk);
 		slow = lock_sock_fast_nested(sk);
 		next = msk->dl_next;
 		msk->first = NULL;
 		msk->dl_next = NULL;
+
+		do_cancel_work = __mptcp_close(sk, 0);
 		unlock_sock_fast(sk, slow);
+		if (do_cancel_work)
+			mptcp_cancel_work(sk);
+		sock_put(sk);
 	}
 
 	/* we are still under the listener msk socket lock */