Merge tag 'net-6.16-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/netHEADmaster

Pull networking fixes from Jakub Kicinski:
 "Including fixes from Bluetooth, CAN, WiFi and Netfilter.

  More code here than I would have liked. That said, better now than
  next week. Nothing particularly scary stands out. The improvement to
  the OpenVPN input validation is a bit large but better get them in
  before the code makes it to a final release. Some of the changes we
  got from sub-trees could have been split better between the fix and
  -next refactoring, IMHO, that has been communicated.

  We have one known regression in a TI AM65 board not getting link. The
  investigation is going a bit slow, a number of people are on vacation.
  We'll try to wrap it up, but don't think it should hold up the
  release.

  Current release - fix to a fix:

   - Bluetooth: L2CAP: fix attempting to adjust outgoing MTU, it broke
     some headphones and speakers

  Current release - regressions:

   - wifi: ath12k: fix packets received in WBM error ring with REO LUT
     enabled, fix Rx performance regression

   - wifi: iwlwifi:
       - fix crash due to a botched indexing conversion
       - mask reserved bits in chan_state_active_bitmap, avoid FW assert()

  Current release - new code bugs:

   - nf_conntrack: fix crash due to removal of uninitialised entry

   - eth: airoha: fix potential UaF in airoha_npu_get()

  Previous releases - regressions:

   - net: fix segmentation after TCP/UDP fraglist GRO

   - af_packet: fix the SO_SNDTIMEO constraint not taking effect and a
     potential soft lockup waiting for a completion

   - rpl: fix UaF in rpl_do_srh_inline() for sneaky skb geometry

   - virtio-net: fix recursive rtnl_lock() during probe()

   - eth: stmmac: populate entire system_counterval_t in get_time_fn()

   - eth: libwx: fix a number of crashes in the driver Rx path

   - hv_netvsc: prevent IPv6 addrconf after IFF_SLAVE lost that meaning

  Previous releases - always broken:

   - mptcp: fix races in handling connection fallback to pure TCP

   - rxrpc: assorted error handling and race fixes

   - sched: another batch of "security" fixes for qdiscs (QFQ, HTB)

   - tls: always refresh the queue when reading sock, avoid UaF

   - phy: don't register LEDs for genphy, avoid deadlock

   - Bluetooth: btintel: check if controller is ISO capable on
     btintel_classify_pkt_type(), work around FW returning incorrect
     capabilities

  Misc:

   - make OpenVPN Netlink input checking more strict before it makes it
     to a final release

   - wifi: cfg80211: remove scan request n_channels __counted_by, it's
     only yielding false positives"

* tag 'net-6.16-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (66 commits)
  rxrpc: Fix to use conn aborts for conn-wide failures
  rxrpc: Fix transmission of an abort in response to an abort
  rxrpc: Fix notification vs call-release vs recvmsg
  rxrpc: Fix recv-recv race of completed call
  rxrpc: Fix irq-disabled in local_bh_enable()
  selftests/tc-testing: Test htb_dequeue_tree with deactivation and row emptying
  net/sched: Return NULL when htb_lookup_leaf encounters an empty rbtree
  net: bridge: Do not offload IGMP/MLD messages
  selftests: Add test cases for vlan_filter modification during runtime
  net: vlan: fix VLAN 0 refcount imbalance of toggling filtering during runtime
  tls: always refresh the queue when reading sock
  virtio-net: fix recursived rtnl_lock() during probe()
  net/mlx5: Update the list of the PCI supported devices
  hv_netvsc: Set VF priv_flags to IFF_NO_ADDRCONF before open to prevent IPv6 addrconf
  phonet/pep: Move call to pn_skb_get_dst_sockaddr() earlier in pep_sock_accept()
  Bluetooth: L2CAP: Fix attempting to adjust outgoing MTU
  netfilter: nf_conntrack: fix crash due to removal of uninitialised entry
  net: fix segmentation after TCP/UDP fraglist GRO
  ipv6: mcast: Delay put pmc->idev in mld_del_delrec()
  net: airoha: fix potential use-after-free in airoha_npu_get()
  ...

1 files changed, 19 insertions, 11 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 15613d691bfef..1802bc5435a1a 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -544,9 +544,11 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 	mptcp_get_options(skb, &mp_opt);
 	if (subflow->request_mptcp) {
 		if (!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYNACK)) {
+			if (!mptcp_try_fallback(sk))
+				goto do_reset;
+
 			MPTCP_INC_STATS(sock_net(sk),
 					MPTCP_MIB_MPCAPABLEACTIVEFALLBACK);
-			mptcp_do_fallback(sk);
 			pr_fallback(msk);
 			goto fallback;
 		}
@@ -1300,20 +1302,29 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss
 		mptcp_schedule_work(sk);
 }
 
-static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
+static bool mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	unsigned long fail_tout;
 
+	/* we are really failing, prevent any later subflow join */
+	spin_lock_bh(&msk->fallback_lock);
+	if (!msk->allow_infinite_fallback) {
+		spin_unlock_bh(&msk->fallback_lock);
+		return false;
+	}
+	msk->allow_subflows = false;
+	spin_unlock_bh(&msk->fallback_lock);
+
 	/* graceful failure can happen only on the MPC subflow */
 	if (WARN_ON_ONCE(ssk != READ_ONCE(msk->first)))
-		return;
+		return false;
 
 	/* since the close timeout take precedence on the fail one,
 	 * no need to start the latter when the first is already set
 	 */
 	if (sock_flag((struct sock *)msk, SOCK_DEAD))
-		return;
+		return true;
 
 	/* we don't need extreme accuracy here, use a zero fail_tout as special
 	 * value meaning no fail timeout at all;
@@ -1325,6 +1336,7 @@ static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
 	tcp_send_ack(ssk);
 
 	mptcp_reset_tout_timer(msk, subflow->fail_tout);
+	return true;
 }
 
 static bool subflow_check_data_avail(struct sock *ssk)
@@ -1385,17 +1397,16 @@ fallback:
 		    (subflow->mp_join || subflow->valid_csum_seen)) {
 			subflow->send_mp_fail = 1;
 
-			if (!READ_ONCE(msk->allow_infinite_fallback)) {
+			if (!mptcp_subflow_fail(msk, ssk)) {
 				subflow->reset_transient = 0;
 				subflow->reset_reason = MPTCP_RST_EMIDDLEBOX;
 				goto reset;
 			}
-			mptcp_subflow_fail(msk, ssk);
 			WRITE_ONCE(subflow->data_avail, true);
 			return true;
 		}
 
-		if (!READ_ONCE(msk->allow_infinite_fallback)) {
+		if (!mptcp_try_fallback(ssk)) {
 			/* fatal protocol error, close the socket.
 			 * subflow_error_report() will introduce the appropriate barriers
 			 */
@@ -1413,8 +1424,6 @@ reset:
 			WRITE_ONCE(subflow->data_avail, false);
 			return false;
 		}
-
-		mptcp_do_fallback(ssk);
 	}
 
 	skb = skb_peek(&ssk->sk_receive_queue);
@@ -1679,7 +1688,6 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_pm_local *local,
 	/* discard the subflow socket */
 	mptcp_sock_graft(ssk, sk->sk_socket);
 	iput(SOCK_INODE(sf));
-	WRITE_ONCE(msk->allow_infinite_fallback, false);
 	mptcp_stop_tout_timer(sk);
 	return 0;
 
@@ -1851,7 +1859,7 @@ static void subflow_state_change(struct sock *sk)
 
 	msk = mptcp_sk(parent);
 	if (subflow_simultaneous_connect(sk)) {
-		mptcp_do_fallback(sk);
+		WARN_ON_ONCE(!mptcp_try_fallback(sk));
 		pr_fallback(msk);
 		subflow->conn_finished = 1;
 		mptcp_propagate_state(parent, sk, subflow, NULL);