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, 48 insertions, 8 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index edf14c2c20622..6a817a13b1549 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -560,10 +560,9 @@ static bool mptcp_check_data_fin(struct sock *sk)
 
 static void mptcp_dss_corruption(struct mptcp_sock *msk, struct sock *ssk)
 {
-	if (READ_ONCE(msk->allow_infinite_fallback)) {
+	if (mptcp_try_fallback(ssk)) {
 		MPTCP_INC_STATS(sock_net(ssk),
 				MPTCP_MIB_DSSCORRUPTIONFALLBACK);
-		mptcp_do_fallback(ssk);
 	} else {
 		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSCORRUPTIONRESET);
 		mptcp_subflow_reset(ssk);
@@ -792,7 +791,7 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 static void mptcp_subflow_joined(struct mptcp_sock *msk, struct sock *ssk)
 {
 	mptcp_subflow_ctx(ssk)->map_seq = READ_ONCE(msk->ack_seq);
-	WRITE_ONCE(msk->allow_infinite_fallback, false);
+	msk->allow_infinite_fallback = false;
 	mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC);
 }
 
@@ -803,6 +802,14 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
 	if (sk->sk_state != TCP_ESTABLISHED)
 		return false;
 
+	spin_lock_bh(&msk->fallback_lock);
+	if (!msk->allow_subflows) {
+		spin_unlock_bh(&msk->fallback_lock);
+		return false;
+	}
+	mptcp_subflow_joined(msk, ssk);
+	spin_unlock_bh(&msk->fallback_lock);
+
 	/* attach to msk socket only after we are sure we will deal with it
 	 * at close time
 	 */
@@ -811,7 +818,6 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
 
 	mptcp_subflow_ctx(ssk)->subflow_id = msk->subflow_id++;
 	mptcp_sockopt_sync_locked(msk, ssk);
-	mptcp_subflow_joined(msk, ssk);
 	mptcp_stop_tout_timer(sk);
 	__mptcp_propagate_sndbuf(sk, ssk);
 	return true;
@@ -1136,10 +1142,14 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk,
 	mpext->infinite_map = 1;
 	mpext->data_len = 0;
 
+	if (!mptcp_try_fallback(ssk)) {
+		mptcp_subflow_reset(ssk);
+		return;
+	}
+
 	MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPTX);
 	mptcp_subflow_ctx(ssk)->send_infinite_map = 0;
 	pr_fallback(msk);
-	mptcp_do_fallback(ssk);
 }
 
 #define MPTCP_MAX_GSO_SIZE (GSO_LEGACY_MAX_SIZE - (MAX_TCP_HEADER + 1))
@@ -2543,9 +2553,9 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 
 static void __mptcp_retrans(struct sock *sk)
 {
+	struct mptcp_sendmsg_info info = { .data_lock_held = true, };
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_subflow_context *subflow;
-	struct mptcp_sendmsg_info info = {};
 	struct mptcp_data_frag *dfrag;
 	struct sock *ssk;
 	int ret, err;
@@ -2590,6 +2600,18 @@ static void __mptcp_retrans(struct sock *sk)
 			info.sent = 0;
 			info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len :
 								    dfrag->already_sent;
+
+			/*
+			 * make the whole retrans decision, xmit, disallow
+			 * fallback atomic
+			 */
+			spin_lock_bh(&msk->fallback_lock);
+			if (__mptcp_check_fallback(msk)) {
+				spin_unlock_bh(&msk->fallback_lock);
+				release_sock(ssk);
+				return;
+			}
+
 			while (info.sent < info.limit) {
 				ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
 				if (ret <= 0)
@@ -2603,8 +2625,9 @@ static void __mptcp_retrans(struct sock *sk)
 				len = max(copied, len);
 				tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
 					 info.size_goal);
-				WRITE_ONCE(msk->allow_infinite_fallback, false);
+				msk->allow_infinite_fallback = false;
 			}
+			spin_unlock_bh(&msk->fallback_lock);
 
 			release_sock(ssk);
 		}
@@ -2730,7 +2753,8 @@ static void __mptcp_init_sock(struct sock *sk)
 	WRITE_ONCE(msk->first, NULL);
 	inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
 	WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
-	WRITE_ONCE(msk->allow_infinite_fallback, true);
+	msk->allow_infinite_fallback = true;
+	msk->allow_subflows = true;
 	msk->recovery = false;
 	msk->subflow_id = 1;
 	msk->last_data_sent = tcp_jiffies32;
@@ -2738,6 +2762,7 @@ static void __mptcp_init_sock(struct sock *sk)
 	msk->last_ack_recv = tcp_jiffies32;
 
 	mptcp_pm_data_init(msk);
+	spin_lock_init(&msk->fallback_lock);
 
 	/* re-use the csk retrans timer for MPTCP-level retrans */
 	timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
@@ -3117,7 +3142,16 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 	 * subflow
 	 */
 	mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE);
+
+	/* The first subflow is already in TCP_CLOSE status, the following
+	 * can't overlap with a fallback anymore
+	 */
+	spin_lock_bh(&msk->fallback_lock);
+	msk->allow_subflows = true;
+	msk->allow_infinite_fallback = true;
 	WRITE_ONCE(msk->flags, 0);
+	spin_unlock_bh(&msk->fallback_lock);
+
 	msk->cb_flags = 0;
 	msk->recovery = false;
 	WRITE_ONCE(msk->can_ack, false);
@@ -3524,7 +3558,13 @@ bool mptcp_finish_join(struct sock *ssk)
 
 	/* active subflow, already present inside the conn_list */
 	if (!list_empty(&subflow->node)) {
+		spin_lock_bh(&msk->fallback_lock);
+		if (!msk->allow_subflows) {
+			spin_unlock_bh(&msk->fallback_lock);
+			return false;
+		}
 		mptcp_subflow_joined(msk, ssk);
+		spin_unlock_bh(&msk->fallback_lock);
 		mptcp_propagate_sndbuf(parent, ssk);
 		return true;
 	}