Merge tag 'net-6.3-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from netfilter, wifi and ipsec.

  A little more changes than usual, but it's pretty normal for us that
  the rc3/rc4 PRs are oversized as people start testing in earnest.

  Possibly an extra boost from people deploying the 6.1 LTS but that's
  more of an unscientific hunch.

  Current release - regressions:

   - phy: mscc: fix deadlock in phy_ethtool_{get,set}_wol()

   - virtio: vsock: don't use skbuff state to account credit

   - virtio: vsock: don't drop skbuff on copy failure

   - virtio_net: fix page_to_skb() miscalculating the memory size

  Current release - new code bugs:

   - eth: correct xdp_features after device reconfig

   - wifi: nl80211: fix the puncturing bitmap policy

   - net/mlx5e: flower:
      - fix raw counter initialization
      - fix missing error code
      - fix cloned flow attribute

   - ipa:
      - fix some register validity checks
      - fix a surprising number of bad offsets
      - kill FILT_ROUT_CACHE_CFG IPA register

  Previous releases - regressions:

   - tcp: fix bind() conflict check for dual-stack wildcard address

   - veth: fix use after free in XDP_REDIRECT when skb headroom is small

   - ipv4: fix incorrect table ID in IOCTL path

   - ipvlan: make skb->skb_iif track skb->dev for l3s mode

   - mptcp:
      - fix possible deadlock in subflow_error_report
      - fix UaFs when destroying unaccepted and listening sockets

   - dsa: mv88e6xxx: fix max_mtu of 1492 on 6165, 6191, 6220, 6250, 6290

  Previous releases - always broken:

   - tcp: tcp_make_synack() can be called from process context, don't
     assume preemption is disabled when updating stats

   - netfilter: correct length for loading protocol registers

   - virtio_net: add checking sq is full inside xdp xmit

   - bonding: restore IFF_MASTER/SLAVE flags on bond enslave Ethertype
     change

   - phy: nxp-c45-tja11xx: fix MII_BASIC_CONFIG_REV bit number

   - eth: i40e: fix crash during reboot when adapter is in recovery mode

   - eth: ice: avoid deadlock on rtnl lock when auxiliary device
     plug/unplug meets bonding

   - dsa: mt7530:
      - remove now incorrect comment regarding port 5
      - set PLL frequency and trgmii only when trgmii is used

   - eth: mtk_eth_soc: reset PCS state when changing interface types

  Misc:

   - ynl: another license adjustment

   - move the TCA_EXT_WARN_MSG attribute for tc action"

* tag 'net-6.3-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (108 commits)
  selftests: bonding: add tests for ether type changes
  bonding: restore bond's IFF_SLAVE flag if a non-eth dev enslave fails
  bonding: restore IFF_MASTER/SLAVE flags on bond enslave ether type change
  net: renesas: rswitch: Fix GWTSDIE register handling
  net: renesas: rswitch: Fix the output value of quote from rswitch_rx()
  ethernet: sun: add check for the mdesc_grab()
  net: ipa: fix some register validity checks
  net: ipa: kill FILT_ROUT_CACHE_CFG IPA register
  net: ipa: add two missing declarations
  net: ipa: reg: include <linux/bug.h>
  net: xdp: don't call notifiers during driver init
  net/sched: act_api: add specific EXT_WARN_MSG for tc action
  Revert "net/sched: act_api: move TCA_EXT_WARN_MSG to the correct hierarchy"
  net: dsa: microchip: fix RGMII delay configuration on KSZ8765/KSZ8794/KSZ8795
  ynl: make the tooling check the license
  ynl: broaden the license even more
  tools: ynl: make definitions optional again
  hsr: ratelimit only when errors are printed
  qed/qed_mng_tlv: correctly zero out ->min instead of ->hour
  selftests: net: devlink_port_split.py: skip test if no suitable device available
  ...

1 files changed, 32 insertions, 32 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3ad9c46202fc..60b23b2716c4 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -825,7 +825,6 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
 	if (sk->sk_socket && !ssk->sk_socket)
 		mptcp_sock_graft(ssk, sk->sk_socket);
 
-	mptcp_propagate_sndbuf((struct sock *)msk, ssk);
 	mptcp_sockopt_sync_locked(msk, ssk);
 	return true;
 }
@@ -2343,7 +2342,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 		goto out;
 	}
 
-	sock_orphan(ssk);
 	subflow->disposable = 1;
 
 	/* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops
@@ -2351,15 +2349,25 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 	 * reference owned by msk;
 	 */
 	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) {
-			tcp_set_state(ssk, TCP_CLOSE);
-			mptcp_subflow_queue_clean(sk, ssk);
-			inet_csk_listen_stop(ssk);
+		if (ssk->sk_state == TCP_LISTEN)
 			mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
-		}
+
 		__tcp_close(ssk, 0);
 
 		/* close acquired an extra ref */
@@ -2399,9 +2407,10 @@ static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu)
 	return 0;
 }
 
-static void __mptcp_close_subflow(struct mptcp_sock *msk)
+static void __mptcp_close_subflow(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow, *tmp;
+	struct mptcp_sock *msk = mptcp_sk(sk);
 
 	might_sleep();
 
@@ -2415,7 +2424,15 @@ static void __mptcp_close_subflow(struct mptcp_sock *msk)
 		if (!skb_queue_empty_lockless(&ssk->sk_receive_queue))
 			continue;
 
-		mptcp_close_ssk((struct sock *)msk, ssk, subflow);
+		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);
 	}
 }
 
@@ -2624,6 +2641,9 @@ static void mptcp_worker(struct work_struct *work)
 	__mptcp_check_send_data_fin(sk);
 	mptcp_check_data_fin(sk);
 
+	if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
+		__mptcp_close_subflow(sk);
+
 	/* There is no point in keeping around an orphaned sk timedout or
 	 * closed, but we need the msk around to reply to incoming DATA_FIN,
 	 * even if it is orphaned and in FIN_WAIT2 state
@@ -2639,9 +2659,6 @@ static void mptcp_worker(struct work_struct *work)
 		}
 	}
 
-	if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
-		__mptcp_close_subflow(msk);
-
 	if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
 		__mptcp_retrans(sk);
 
@@ -3079,6 +3096,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 	msk->local_key = subflow_req->local_key;
 	msk->token = subflow_req->token;
 	msk->subflow = NULL;
+	msk->in_accept_queue = 1;
 	WRITE_ONCE(msk->fully_established, false);
 	if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD)
 		WRITE_ONCE(msk->csum_enabled, true);
@@ -3096,8 +3114,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 	security_inet_csk_clone(nsk, req);
 	bh_unlock_sock(nsk);
 
-	/* keep a single reference */
-	__sock_put(nsk);
+	/* note: the newly allocated socket refcount is 2 now */
 	return nsk;
 }
 
@@ -3153,8 +3170,6 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 			goto out;
 		}
 
-		/* acquire the 2nd reference for the owning socket */
-		sock_hold(new_mptcp_sock);
 		newsk = new_mptcp_sock;
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
 	} else {
@@ -3705,25 +3720,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 		struct sock *newsk = newsock->sk;
 
 		set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags);
+		msk->in_accept_queue = 0;
 
 		lock_sock(newsk);
 
-		/* PM/worker can now acquire the first subflow socket
-		 * lock without racing with listener queue cleanup,
-		 * we can notify it, if needed.
-		 *
-		 * Even if remote has reset the initial subflow by now
-		 * the refcnt is still at least one.
-		 */
-		subflow = mptcp_subflow_ctx(msk->first);
-		list_add(&subflow->node, &msk->conn_list);
-		sock_hold(msk->first);
-		if (mptcp_is_fully_established(newsk))
-			mptcp_pm_fully_established(msk, msk->first, GFP_KERNEL);
-
-		mptcp_rcv_space_init(msk, msk->first);
-		mptcp_propagate_sndbuf(newsk, msk->first);
-
 		/* set ssk->sk_socket of accept()ed flows to mptcp socket.
 		 * This is needed so NOSPACE flag can be set from tcp stack.
 		 */