Merge tag 'net-6.3-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from netfilter and bpf.

  There are a few fixes for new code bugs, including the Mellanox one
  noted in the last networking pull. No known regressions outstanding.

  Current release - regressions:

   - sched: clear actions pointer in miss cookie init fail

   - mptcp: fix accept vs worker race

   - bpf: fix bpf_arch_text_poke() with new_addr == NULL on s390

   - eth: bnxt_en: fix a possible NULL pointer dereference in unload
     path

   - eth: veth: take into account peer device for
     NETDEV_XDP_ACT_NDO_XMIT xdp_features flag

  Current release - new code bugs:

   - eth: revert "net/mlx5: Enable management PF initialization"

  Previous releases - regressions:

   - netfilter: fix recent physdev match breakage

   - bpf: fix incorrect verifier pruning due to missing register
     precision taints

   - eth: virtio_net: fix overflow inside xdp_linearize_page()

   - eth: cxgb4: fix use after free bugs caused by circular dependency
     problem

   - eth: mlxsw: pci: fix possible crash during initialization

  Previous releases - always broken:

   - sched: sch_qfq: prevent slab-out-of-bounds in qfq_activate_agg

   - netfilter: validate catch-all set elements

   - bridge: don't notify FDB entries with "master dynamic"

   - eth: bonding: fix memory leak when changing bond type to ethernet

   - eth: i40e: fix accessing vsi->active_filters without holding lock

  Misc:

   - Mat is back as MPTCP co-maintainer"

* tag 'net-6.3-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (33 commits)
  net: bridge: switchdev: don't notify FDB entries with "master dynamic"
  Revert "net/mlx5: Enable management PF initialization"
  MAINTAINERS: Resume MPTCP co-maintainer role
  mailmap: add entries for Mat Martineau
  e1000e: Disable TSO on i219-LM card to increase speed
  bnxt_en: fix free-runnig PHC mode
  net: dsa: microchip: ksz8795: Correctly handle huge frame configuration
  bpf: Fix incorrect verifier pruning due to missing register precision taints
  hamradio: drop ISA_DMA_API dependency
  mlxsw: pci: Fix possible crash during initialization
  mptcp: fix accept vs worker race
  mptcp: stops worker on unaccepted sockets at listener close
  net: rpl: fix rpl header size calculation
  net: vmxnet3: Fix NULL pointer dereference in vmxnet3_rq_rx_complete()
  bonding: Fix memory leak when changing bond type to Ethernet
  veth: take into account peer device for NETDEV_XDP_ACT_NDO_XMIT xdp_features flag
  mlxfw: fix null-ptr-deref in mlxfw_mfa2_tlv_next()
  bnxt_en: Fix a possible NULL pointer dereference in unload path
  bnxt_en: Do not initialize PTP on older P3/P4 chips
  netfilter: nf_tables: tighten netlink attribute requirements for catch-all elements
  ...

1 files changed, 50 insertions, 24 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 06c5872e3b00..b998e9df53ce 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2315,7 +2315,26 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 			      unsigned int flags)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	bool need_push, dispose_it;
+	bool dispose_it, need_push = false;
+
+	/* If the first subflow moved to a close state before accept, e.g. due
+	 * to an incoming reset, mptcp either:
+	 * - if either the subflow or the msk are dead, destroy the context
+	 *   (the subflow socket is deleted by inet_child_forget) and the msk
+	 * - otherwise do nothing at the moment and take action at accept and/or
+	 *   listener shutdown - user-space must be able to accept() the closed
+	 *   socket.
+	 */
+	if (msk->in_accept_queue && msk->first == ssk) {
+		if (!sock_flag(sk, SOCK_DEAD) && !sock_flag(ssk, SOCK_DEAD))
+			return;
+
+		/* ensure later check in mptcp_worker() will dispose the msk */
+		sock_set_flag(sk, SOCK_DEAD);
+		lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
+		mptcp_subflow_drop_ctx(ssk);
+		goto out_release;
+	}
 
 	dispose_it = !msk->subflow || ssk != msk->subflow->sk;
 	if (dispose_it)
@@ -2351,28 +2370,22 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 	if (!inet_csk(ssk)->icsk_ulp_ops) {
 		WARN_ON_ONCE(!sock_flag(ssk, SOCK_DEAD));
 		kfree_rcu(subflow, rcu);
-	} else if (msk->in_accept_queue && msk->first == ssk) {
-		/* if the first subflow moved to a close state, e.g. due to
-		 * incoming reset and we reach here before inet_child_forget()
-		 * the TCP stack could later try to close it via
-		 * inet_csk_listen_stop(), or deliver it to the user space via
-		 * accept().
-		 * We can't delete the subflow - or risk a double free - nor let
-		 * the msk survive - or will be leaked in the non accept scenario:
-		 * fallback and let TCP cope with the subflow cleanup.
-		 */
-		WARN_ON_ONCE(sock_flag(ssk, SOCK_DEAD));
-		mptcp_subflow_drop_ctx(ssk);
 	} else {
 		/* otherwise tcp will dispose of the ssk and subflow ctx */
-		if (ssk->sk_state == TCP_LISTEN)
+		if (ssk->sk_state == TCP_LISTEN) {
+			tcp_set_state(ssk, TCP_CLOSE);
+			mptcp_subflow_queue_clean(sk, ssk);
+			inet_csk_listen_stop(ssk);
 			mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
+		}
 
 		__tcp_close(ssk, 0);
 
 		/* close acquired an extra ref */
 		__sock_put(ssk);
 	}
+
+out_release:
 	release_sock(ssk);
 
 	sock_put(ssk);
@@ -2427,21 +2440,14 @@ static void __mptcp_close_subflow(struct sock *sk)
 		mptcp_close_ssk(sk, ssk, subflow);
 	}
 
-	/* if the MPC subflow has been closed before the msk is accepted,
-	 * msk will never be accept-ed, close it now
-	 */
-	if (!msk->first && msk->in_accept_queue) {
-		sock_set_flag(sk, SOCK_DEAD);
-		inet_sk_state_store(sk, TCP_CLOSE);
-	}
 }
 
-static bool mptcp_check_close_timeout(const struct sock *sk)
+static bool mptcp_should_close(const struct sock *sk)
 {
 	s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp;
 	struct mptcp_subflow_context *subflow;
 
-	if (delta >= TCP_TIMEWAIT_LEN)
+	if (delta >= TCP_TIMEWAIT_LEN || mptcp_sk(sk)->in_accept_queue)
 		return true;
 
 	/* if all subflows are in closed status don't bother with additional
@@ -2649,7 +2655,7 @@ static void mptcp_worker(struct work_struct *work)
 	 * even if it is orphaned and in FIN_WAIT2 state
 	 */
 	if (sock_flag(sk, SOCK_DEAD)) {
-		if (mptcp_check_close_timeout(sk)) {
+		if (mptcp_should_close(sk)) {
 			inet_sk_state_store(sk, TCP_CLOSE);
 			mptcp_do_fastclose(sk);
 		}
@@ -2895,6 +2901,14 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	sock_put(sk);
 }
 
+void __mptcp_unaccepted_force_close(struct sock *sk)
+{
+	sock_set_flag(sk, SOCK_DEAD);
+	inet_sk_state_store(sk, TCP_CLOSE);
+	mptcp_do_fastclose(sk);
+	__mptcp_destroy_sock(sk);
+}
+
 static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
 {
 	/* Concurrent splices from sk_receive_queue into receive_queue will
@@ -3733,6 +3747,18 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 			if (!ssk->sk_socket)
 				mptcp_sock_graft(ssk, newsock);
 		}
+
+		/* Do late cleanup for the first subflow as necessary. Also
+		 * deal with bad peers not doing a complete shutdown.
+		 */
+		if (msk->first &&
+		    unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) {
+			__mptcp_close_ssk(newsk, msk->first,
+					  mptcp_subflow_ctx(msk->first), 0);
+			if (unlikely(list_empty(&msk->conn_list)))
+				inet_sk_state_store(newsk, TCP_CLOSE);
+		}
+
 		release_sock(newsk);
 	}