Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

Conflicts:

tools/testing/selftests/net/fcnal-test.sh
  d7a2fc1437f7 ("selftests: net: fcnal-test: check if FIPS mode is enabled")
  dd017c72dde6 ("selftests: fcnal: Test SO_DONTROUTE on TCP sockets.")
https://lore.kernel.org/all/5007b52c-dd16-dbf6-8d64-b9701bfa498b@tessares.net/
https://lore.kernel.org/all/20230619105427.4a0df9b3@canb.auug.org.au/

No adjacent changes.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

26 files changed, 603 insertions, 223 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 8ec8f4c9911f..5f1747c12004 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1373,12 +1373,6 @@ set_sndbuf:
 		__sock_set_mark(sk, val);
 		break;
 	case SO_RCVMARK:
-		if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
-		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
-			ret = -EPERM;
-			break;
-		}
-
 		sock_valbool_flag(sk, SOCK_RCVMARK, valbool);
 		break;
 
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index ab1afe67fd18..1afed89e03c0 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -403,6 +403,24 @@ static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst)
 	return 0;
 }
 
+static struct dsa_port *
+dsa_switch_preferred_default_local_cpu_port(struct dsa_switch *ds)
+{
+	struct dsa_port *cpu_dp;
+
+	if (!ds->ops->preferred_default_local_cpu_port)
+		return NULL;
+
+	cpu_dp = ds->ops->preferred_default_local_cpu_port(ds);
+	if (!cpu_dp)
+		return NULL;
+
+	if (WARN_ON(!dsa_port_is_cpu(cpu_dp) || cpu_dp->ds != ds))
+		return NULL;
+
+	return cpu_dp;
+}
+
 /* Perform initial assignment of CPU ports to user ports and DSA links in the
  * fabric, giving preference to CPU ports local to each switch. Default to
  * using the first CPU port in the switch tree if the port does not have a CPU
@@ -410,12 +428,16 @@ static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst)
  */
 static int dsa_tree_setup_cpu_ports(struct dsa_switch_tree *dst)
 {
-	struct dsa_port *cpu_dp, *dp;
+	struct dsa_port *preferred_cpu_dp, *cpu_dp, *dp;
 
 	list_for_each_entry(cpu_dp, &dst->ports, list) {
 		if (!dsa_port_is_cpu(cpu_dp))
 			continue;
 
+		preferred_cpu_dp = dsa_switch_preferred_default_local_cpu_port(cpu_dp->ds);
+		if (preferred_cpu_dp && preferred_cpu_dp != cpu_dp)
+			continue;
+
 		/* Prefer a local CPU port */
 		dsa_switch_for_each_port(dp, cpu_dp->ds) {
 			/* Prefer the first local CPU port found */
diff --git a/net/ieee802154/trace.h b/net/ieee802154/trace.h
index e5d8439b9e45..c16db0b326fa 100644
--- a/net/ieee802154/trace.h
+++ b/net/ieee802154/trace.h
@@ -13,7 +13,7 @@
 
 #define MAXNAME		32
 #define WPAN_PHY_ENTRY	__array(char, wpan_phy_name, MAXNAME)
-#define WPAN_PHY_ASSIGN	strlcpy(__entry->wpan_phy_name,	 \
+#define WPAN_PHY_ASSIGN	strscpy(__entry->wpan_phy_name,	 \
 				wpan_phy_name(wpan_phy), \
 				MAXNAME)
 #define WPAN_PHY_PR_FMT	"%s"
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 12c5fb3c6e1e..10e96ed6c9e3 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -341,6 +341,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features_
 
 	secpath_reset(skb);
 
+	if (skb_needs_linearize(skb, skb->dev->features) &&
+	    __skb_linearize(skb))
+		return -ENOMEM;
 	return 0;
 }
 
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index ad2afeef4f10..eac206a290d0 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -164,6 +164,7 @@ drop:
 	kfree_skb(skb);
 	return 0;
 }
+EXPORT_SYMBOL(xfrm4_udp_encap_rcv);
 
 int xfrm4_rcv(struct sk_buff *skb)
 {
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index b33c7de5bdbc..a189e08370a5 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -375,6 +375,9 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features
 
 	secpath_reset(skb);
 
+	if (skb_needs_linearize(skb, skb->dev->features) &&
+	    __skb_linearize(skb))
+		return -ENOMEM;
 	return 0;
 }
 
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 04cbeefd8982..4907ab241d6b 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -86,6 +86,9 @@ int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
 	__be32 *udpdata32;
 	__u16 encap_type = up->encap_type;
 
+	if (skb->protocol == htons(ETH_P_IP))
+		return xfrm4_udp_encap_rcv(sk, skb);
+
 	/* if this is not encapsulated socket, then just return now */
 	if (!encap_type)
 		return 1;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index ed9939466198..e2a973309bf7 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2110,7 +2110,7 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 	/* either the frame has been decrypted or will be dropped */
 	status->flag |= RX_FLAG_DECRYPTED;
 
-	if (unlikely(ieee80211_is_beacon(fc) && result == RX_DROP_UNUSABLE &&
+	if (unlikely(ieee80211_is_beacon(fc) && (result & RX_DROP_UNUSABLE) &&
 		     rx->sdata->dev))
 		cfg80211_rx_unprot_mlme_mgmt(rx->sdata->dev,
 					     skb->data, skb->len);
diff --git a/net/mac802154/trace.h b/net/mac802154/trace.h
index 689396d6c76a..1574ecc48075 100644
--- a/net/mac802154/trace.h
+++ b/net/mac802154/trace.h
@@ -14,7 +14,7 @@
 
 #define MAXNAME		32
 #define LOCAL_ENTRY	__array(char, wpan_phy_name, MAXNAME)
-#define LOCAL_ASSIGN	strlcpy(__entry->wpan_phy_name, \
+#define LOCAL_ASSIGN	strscpy(__entry->wpan_phy_name, \
 				wpan_phy_name(local->hw.phy), MAXNAME)
 #define LOCAL_PR_FMT	"%s"
 #define LOCAL_PR_ARG	__entry->wpan_phy_name
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 547e51c65480..5692daf57a4d 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1046,6 +1046,7 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 	if (err)
 		return err;
 
+	inet_sk_state_store(newsk, TCP_LISTEN);
 	err = kernel_listen(ssock, backlog);
 	if (err)
 		return err;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index f65eec3e0d22..bd023debedc8 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -44,7 +44,7 @@ enum {
 static struct percpu_counter mptcp_sockets_allocated ____cacheline_aligned_in_smp;
 
 static void __mptcp_destroy_sock(struct sock *sk);
-static void __mptcp_check_send_data_fin(struct sock *sk);
+static void mptcp_check_send_data_fin(struct sock *sk);
 
 DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
 static struct net_device mptcp_napi_dev;
@@ -426,8 +426,7 @@ static bool mptcp_pending_data_fin_ack(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	return !__mptcp_check_fallback(msk) &&
-	       ((1 << sk->sk_state) &
+	return ((1 << sk->sk_state) &
 		(TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) &&
 	       msk->write_seq == READ_ONCE(msk->snd_una);
 }
@@ -585,9 +584,6 @@ static bool mptcp_check_data_fin(struct sock *sk)
 	u64 rcv_data_fin_seq;
 	bool ret = false;
 
-	if (__mptcp_check_fallback(msk))
-		return ret;
-
 	/* Need to ack a DATA_FIN received from a peer while this side
 	 * of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2.
 	 * msk->rcv_data_fin was set when parsing the incoming options
@@ -625,7 +621,8 @@ static bool mptcp_check_data_fin(struct sock *sk)
 		}
 
 		ret = true;
-		mptcp_send_ack(msk);
+		if (!__mptcp_check_fallback(msk))
+			mptcp_send_ack(msk);
 		mptcp_close_wake_up(sk);
 	}
 	return ret;
@@ -854,12 +851,12 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
 	return true;
 }
 
-static void __mptcp_flush_join_list(struct sock *sk)
+static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list)
 {
 	struct mptcp_subflow_context *tmp, *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	list_for_each_entry_safe(subflow, tmp, &msk->join_list, node) {
+	list_for_each_entry_safe(subflow, tmp, join_list, node) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		bool slow = lock_sock_fast(ssk);
 
@@ -901,49 +898,6 @@ bool mptcp_schedule_work(struct sock *sk)
 	return false;
 }
 
-void mptcp_subflow_eof(struct sock *sk)
-{
-	if (!test_and_set_bit(MPTCP_WORK_EOF, &mptcp_sk(sk)->flags))
-		mptcp_schedule_work(sk);
-}
-
-static void mptcp_check_for_eof(struct mptcp_sock *msk)
-{
-	struct mptcp_subflow_context *subflow;
-	struct sock *sk = (struct sock *)msk;
-	int receivers = 0;
-
-	mptcp_for_each_subflow(msk, subflow)
-		receivers += !subflow->rx_eof;
-	if (receivers)
-		return;
-
-	if (!(sk->sk_shutdown & RCV_SHUTDOWN)) {
-		/* hopefully temporary hack: propagate shutdown status
-		 * to msk, when all subflows agree on it
-		 */
-		WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN);
-
-		smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
-		sk->sk_data_ready(sk);
-	}
-
-	switch (sk->sk_state) {
-	case TCP_ESTABLISHED:
-		inet_sk_state_store(sk, TCP_CLOSE_WAIT);
-		break;
-	case TCP_FIN_WAIT1:
-		inet_sk_state_store(sk, TCP_CLOSING);
-		break;
-	case TCP_FIN_WAIT2:
-		inet_sk_state_store(sk, TCP_CLOSE);
-		break;
-	default:
-		return;
-	}
-	mptcp_close_wake_up(sk);
-}
-
 static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow;
@@ -1609,7 +1563,7 @@ out:
 	if (!mptcp_timer_pending(sk))
 		mptcp_reset_timer(sk);
 	if (do_check_data_fin)
-		__mptcp_check_send_data_fin(sk);
+		mptcp_check_send_data_fin(sk);
 }
 
 static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first)
@@ -1727,7 +1681,13 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 		if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR)
 			*copied_syn = 0;
 	} else if (ret && ret != -EINPROGRESS) {
-		mptcp_disconnect(sk, 0);
+		/* The disconnect() op called by tcp_sendmsg_fastopen()/
+		 * __inet_stream_connect() can fail, due to looking check,
+		 * see mptcp_disconnect().
+		 * Attempt it again outside the problematic scope.
+		 */
+		if (!mptcp_disconnect(sk, 0))
+			sk->sk_socket->state = SS_UNCONNECTED;
 	}
 	inet_sk(sk)->defer_connect = 0;
 
@@ -2158,9 +2118,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 				break;
 			}
 
-			if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
-				mptcp_check_for_eof(msk);
-
 			if (sk->sk_shutdown & RCV_SHUTDOWN) {
 				/* race breaker: the shutdown could be after the
 				 * previous receive queue check
@@ -2389,7 +2346,10 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 
 	need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk);
 	if (!dispose_it) {
-		tcp_disconnect(ssk, 0);
+		/* The MPTCP code never wait on the subflow sockets, TCP-level
+		 * disconnect should never fail
+		 */
+		WARN_ON_ONCE(tcp_disconnect(ssk, 0));
 		msk->subflow->state = SS_UNCONNECTED;
 		mptcp_subflow_ctx_reset(subflow);
 		release_sock(ssk);
@@ -2408,13 +2368,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 		kfree_rcu(subflow, rcu);
 	} 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);
-			mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
-		}
-
 		__tcp_close(ssk, 0);
 
 		/* close acquired an extra ref */
@@ -2673,16 +2626,12 @@ static void mptcp_worker(struct work_struct *work)
 	if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN)))
 		goto unlock;
 
-	mptcp_check_data_fin_ack(sk);
-
 	mptcp_check_fastclose(msk);
 
 	mptcp_pm_nl_work(msk);
 
-	if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
-		mptcp_check_for_eof(msk);
-
-	__mptcp_check_send_data_fin(sk);
+	mptcp_check_send_data_fin(sk);
+	mptcp_check_data_fin_ack(sk);
 	mptcp_check_data_fin(sk);
 
 	if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
@@ -2814,13 +2763,19 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
 			break;
 		fallthrough;
 	case TCP_SYN_SENT:
-		tcp_disconnect(ssk, O_NONBLOCK);
+		WARN_ON_ONCE(tcp_disconnect(ssk, O_NONBLOCK));
 		break;
 	default:
 		if (__mptcp_check_fallback(mptcp_sk(sk))) {
 			pr_debug("Fallback");
 			ssk->sk_shutdown |= how;
 			tcp_shutdown(ssk, how);
+
+			/* simulate the data_fin ack reception to let the state
+			 * machine move forward
+			 */
+			WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt);
+			mptcp_schedule_work(sk);
 		} else {
 			pr_debug("Sending DATA_FIN on subflow %p", ssk);
 			tcp_send_ack(ssk);
@@ -2860,7 +2815,7 @@ static int mptcp_close_state(struct sock *sk)
 	return next & TCP_ACTION_FIN;
 }
 
-static void __mptcp_check_send_data_fin(struct sock *sk)
+static void mptcp_check_send_data_fin(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
@@ -2878,19 +2833,6 @@ static void __mptcp_check_send_data_fin(struct sock *sk)
 
 	WRITE_ONCE(msk->snd_nxt, msk->write_seq);
 
-	/* fallback socket will not get data_fin/ack, can move to the next
-	 * state now
-	 */
-	if (__mptcp_check_fallback(msk)) {
-		WRITE_ONCE(msk->snd_una, msk->write_seq);
-		if ((1 << sk->sk_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) {
-			inet_sk_state_store(sk, TCP_CLOSE);
-			mptcp_close_wake_up(sk);
-		} else if (sk->sk_state == TCP_FIN_WAIT1) {
-			inet_sk_state_store(sk, TCP_FIN_WAIT2);
-		}
-	}
-
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
 
@@ -2910,7 +2852,7 @@ static void __mptcp_wr_shutdown(struct sock *sk)
 	WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
 	WRITE_ONCE(msk->snd_data_fin_enable, 1);
 
-	__mptcp_check_send_data_fin(sk);
+	mptcp_check_send_data_fin(sk);
 }
 
 static void __mptcp_destroy_sock(struct sock *sk)
@@ -2954,10 +2896,24 @@ static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
 	return EPOLLIN | EPOLLRDNORM;
 }
 
-static void mptcp_listen_inuse_dec(struct sock *sk)
+static void mptcp_check_listen_stop(struct sock *sk)
 {
-	if (inet_sk_state_load(sk) == TCP_LISTEN)
-		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+	struct sock *ssk;
+
+	if (inet_sk_state_load(sk) != TCP_LISTEN)
+		return;
+
+	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+	ssk = mptcp_sk(sk)->first;
+	if (WARN_ON_ONCE(!ssk || inet_sk_state_load(ssk) != TCP_LISTEN))
+		return;
+
+	lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
+	mptcp_subflow_queue_clean(sk, ssk);
+	inet_csk_listen_stop(ssk);
+	mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
+	tcp_set_state(ssk, TCP_CLOSE);
+	release_sock(ssk);
 }
 
 bool __mptcp_close(struct sock *sk, long timeout)
@@ -2970,7 +2926,7 @@ bool __mptcp_close(struct sock *sk, long timeout)
 	WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
 
 	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
-		mptcp_listen_inuse_dec(sk);
+		mptcp_check_listen_stop(sk);
 		inet_sk_state_store(sk, TCP_CLOSE);
 		goto cleanup;
 	}
@@ -3073,15 +3029,20 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
+	/* Deny disconnect if other threads are blocked in sk_wait_event()
+	 * or inet_wait_for_connect().
+	 */
+	if (sk->sk_wait_pending)
+		return -EBUSY;
+
 	/* We are on the fastopen error path. We can't call straight into the
 	 * subflows cleanup code due to lock nesting (we are already under
-	 * msk->firstsocket lock). Do nothing and leave the cleanup to the
-	 * caller.
+	 * msk->firstsocket lock).
 	 */
 	if (msk->fastopening)
-		return 0;
+		return -EBUSY;
 
-	mptcp_listen_inuse_dec(sk);
+	mptcp_check_listen_stop(sk);
 	inet_sk_state_store(sk, TCP_CLOSE);
 
 	mptcp_stop_timer(sk);
@@ -3144,6 +3105,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 		inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk);
 #endif
 
+	nsk->sk_wait_pending = 0;
 	__mptcp_init_sock(nsk);
 
 	msk = mptcp_sk(nsk);
@@ -3334,9 +3296,14 @@ static void mptcp_release_cb(struct sock *sk)
 	for (;;) {
 		unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) |
 				      msk->push_pending;
+		struct list_head join_list;
+
 		if (!flags)
 			break;
 
+		INIT_LIST_HEAD(&join_list);
+		list_splice_init(&msk->join_list, &join_list);
+
 		/* the following actions acquire the subflow socket lock
 		 *
 		 * 1) can't be invoked in atomic scope
@@ -3347,8 +3314,9 @@ static void mptcp_release_cb(struct sock *sk)
 		msk->push_pending = 0;
 		msk->cb_flags &= ~flags;
 		spin_unlock_bh(&sk->sk_lock.slock);
+
 		if (flags & BIT(MPTCP_FLUSH_JOIN_LIST))
-			__mptcp_flush_join_list(sk);
+			__mptcp_flush_join_list(sk, &join_list);
 		if (flags & BIT(MPTCP_PUSH_PENDING))
 			__mptcp_push_pending(sk, 0);
 		if (flags & BIT(MPTCP_RETRANSMIT))
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 3a1a64cdeba6..37fbe22e2433 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -113,7 +113,6 @@
 /* MPTCP socket atomic flags */
 #define MPTCP_NOSPACE		1
 #define MPTCP_WORK_RTX		2
-#define MPTCP_WORK_EOF		3
 #define MPTCP_FALLBACK_DONE	4
 #define MPTCP_WORK_CLOSE_SUBFLOW 5
 
@@ -481,14 +480,13 @@ struct mptcp_subflow_context {
 		send_mp_fail : 1,
 		send_fastclose : 1,
 		send_infinite_map : 1,
-		rx_eof : 1,
 		remote_key_valid : 1,        /* received the peer key from */
 		disposable : 1,	    /* ctx can be free at ulp release time */
 		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
 		local_id_valid : 1, /* local_id is correctly initialized */
 		valid_csum_seen : 1,        /* at least one csum validated */
 		is_mptfo : 1,	    /* subflow is doing TFO */
-		__unused : 8;
+		__unused : 9;
 	enum mptcp_data_avail data_avail;
 	u32	remote_nonce;
 	u64	thmac;
@@ -728,7 +726,6 @@ static inline u64 mptcp_expand_seq(u64 old_seq, u64 cur_seq, bool use_64bit)
 void __mptcp_check_push(struct sock *sk, struct sock *ssk);
 void __mptcp_data_acked(struct sock *sk);
 void __mptcp_error_report(struct sock *sk);
-void mptcp_subflow_eof(struct sock *sk);
 bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit);
 static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk)
 {
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 222dfcdadf2e..285e8ff74277 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1751,14 +1751,16 @@ static void subflow_state_change(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct sock *parent = subflow->conn;
+	struct mptcp_sock *msk;
 
 	__subflow_state_change(sk);
 
+	msk = mptcp_sk(parent);
 	if (subflow_simultaneous_connect(sk)) {
 		mptcp_propagate_sndbuf(parent, sk);
 		mptcp_do_fallback(sk);
-		mptcp_rcv_space_init(mptcp_sk(parent), sk);
-		pr_fallback(mptcp_sk(parent));
+		mptcp_rcv_space_init(msk, sk);
+		pr_fallback(msk);
 		subflow->conn_finished = 1;
 		mptcp_set_connected(parent);
 	}
@@ -1774,11 +1776,12 @@ static void subflow_state_change(struct sock *sk)
 
 	subflow_sched_work_if_closed(mptcp_sk(parent), sk);
 
-	if (__mptcp_check_fallback(mptcp_sk(parent)) &&
-	    !subflow->rx_eof && subflow_is_done(sk)) {
-		subflow->rx_eof = 1;
-		mptcp_subflow_eof(parent);
-	}
+	/* when the fallback subflow closes the rx side, trigger a 'dummy'
+	 * ingress data fin, so that the msk state will follow along
+	 */
+	if (__mptcp_check_fallback(msk) && subflow_is_done(sk) && msk->first == sk &&
+	    mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true))
+		mptcp_schedule_work(parent);
 }
 
 void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index c7652da78c88..9193e109e6b3 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -1207,6 +1207,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	skb->transport_header = skb->network_header;
 
 	skb_set_inner_ipproto(skb, next_protocol);
+	skb_set_inner_mac_header(skb, skb_inner_network_offset(skb));
 
 	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
 		bool check = false;
@@ -1349,6 +1350,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	skb->transport_header = skb->network_header;
 
 	skb_set_inner_ipproto(skb, next_protocol);
+	skb_set_inner_mac_header(skb, skb_inner_network_offset(skb));
 
 	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
 		bool check = false;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 486d24b83fa9..d543787fc851 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -151,6 +151,7 @@ static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx,
 		return NULL;
 
 	INIT_LIST_HEAD(&trans->list);
+	INIT_LIST_HEAD(&trans->binding_list);
 	trans->msg_type = msg_type;
 	trans->ctx	= *ctx;
 
@@ -163,13 +164,20 @@ static struct nft_trans *nft_trans_alloc(const struct nft_ctx *ctx,
 	return nft_trans_alloc_gfp(ctx, msg_type, size, GFP_KERNEL);
 }
 
-static void nft_trans_destroy(struct nft_trans *trans)
+static void nft_trans_list_del(struct nft_trans *trans)
 {
 	list_del(&trans->list);
+	list_del(&trans->binding_list);
+}
+
+static void nft_trans_destroy(struct nft_trans *trans)
+{
+	nft_trans_list_del(trans);
 	kfree(trans);
 }
 
-static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set)
+static void __nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set,
+				 bool bind)
 {
 	struct nftables_pernet *nft_net;
 	struct net *net = ctx->net;
@@ -183,16 +191,80 @@ static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set)
 		switch (trans->msg_type) {
 		case NFT_MSG_NEWSET:
 			if (nft_trans_set(trans) == set)
-				nft_trans_set_bound(trans) = true;
+				nft_trans_set_bound(trans) = bind;
 			break;
 		case NFT_MSG_NEWSETELEM:
 			if (nft_trans_elem_set(trans) == set)
-				nft_trans_elem_set_bound(trans) = true;
+				nft_trans_elem_set_bound(trans) = bind;
 			break;
 		}
 	}
 }
 
+static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set)
+{
+	return __nft_set_trans_bind(ctx, set, true);
+}
+
+static void nft_set_trans_unbind(const struct nft_ctx *ctx, struct nft_set *set)
+{
+	return __nft_set_trans_bind(ctx, set, false);
+}
+
+static void __nft_chain_trans_bind(const struct nft_ctx *ctx,
+				   struct nft_chain *chain, bool bind)
+{
+	struct nftables_pernet *nft_net;
+	struct net *net = ctx->net;
+	struct nft_trans *trans;
+
+	if (!nft_chain_binding(chain))
+		return;
+
+	nft_net = nft_pernet(net);
+	list_for_each_entry_reverse(trans, &nft_net->commit_list, list) {
+		switch (trans->msg_type) {
+		case NFT_MSG_NEWCHAIN:
+			if (nft_trans_chain(trans) == chain)
+				nft_trans_chain_bound(trans) = bind;
+			break;
+		case NFT_MSG_NEWRULE:
+			if (trans->ctx.chain == chain)
+				nft_trans_rule_bound(trans) = bind;
+			break;
+		}
+	}
+}
+
+static void nft_chain_trans_bind(const struct nft_ctx *ctx,
+				 struct nft_chain *chain)
+{
+	__nft_chain_trans_bind(ctx, chain, true);
+}
+
+int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain)
+{
+	if (!nft_chain_binding(chain))
+		return 0;
+
+	if (nft_chain_binding(ctx->chain))
+		return -EOPNOTSUPP;
+
+	if (chain->bound)
+		return -EBUSY;
+
+	chain->bound = true;
+	chain->use++;
+	nft_chain_trans_bind(ctx, chain);
+
+	return 0;
+}
+
+void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain)
+{
+	__nft_chain_trans_bind(ctx, chain, false);
+}
+
 static int nft_netdev_register_hooks(struct net *net,
 				     struct list_head *hook_list)
 {
@@ -292,6 +364,19 @@ static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *tr
 {
 	struct nftables_pernet *nft_net = nft_pernet(net);
 
+	switch (trans->msg_type) {
+	case NFT_MSG_NEWSET:
+		if (!nft_trans_set_update(trans) &&
+		    nft_set_is_anonymous(nft_trans_set(trans)))
+			list_add_tail(&trans->binding_list, &nft_net->binding_list);
+		break;
+	case NFT_MSG_NEWCHAIN:
+		if (!nft_trans_chain_update(trans) &&
+		    nft_chain_binding(nft_trans_chain(trans)))
+			list_add_tail(&trans->binding_list, &nft_net->binding_list);
+		break;
+	}
+
 	list_add_tail(&trans->list, &nft_net->commit_list);
 }
 
@@ -338,8 +423,9 @@ static struct nft_trans *nft_trans_chain_add(struct nft_ctx *ctx, int msg_type)
 				ntohl(nla_get_be32(ctx->nla[NFTA_CHAIN_ID]));
 		}
 	}
-
+	nft_trans_chain(trans) = ctx->chain;
 	nft_trans_commit_list_add_tail(ctx->net, trans);
+
 	return trans;
 }
 
@@ -357,8 +443,7 @@ static int nft_delchain(struct nft_ctx *ctx)
 	return 0;
 }
 
-static void nft_rule_expr_activate(const struct nft_ctx *ctx,
-				   struct nft_rule *rule)
+void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule)
 {
 	struct nft_expr *expr;
 
@@ -371,9 +456,8 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx,
 	}
 }
 
-static void nft_rule_expr_deactivate(const struct nft_ctx *ctx,
-				     struct nft_rule *rule,
-				     enum nft_trans_phase phase)
+void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_rule *rule,
+			      enum nft_trans_phase phase)
 {
 	struct nft_expr *expr;
 
@@ -495,6 +579,58 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
 	return __nft_trans_set_add(ctx, msg_type, set, NULL);
 }
 
+static void nft_setelem_data_deactivate(const struct net *net,
+					const struct nft_set *set,
+					struct nft_set_elem *elem);
+
+static int nft_mapelem_deactivate(const struct nft_ctx *ctx,
+				  struct nft_set *set,
+				  const struct nft_set_iter *iter,
+				  struct nft_set_elem *elem)
+{
+	nft_setelem_data_deactivate(ctx->net, set, elem);
+
+	return 0;
+}
+
+struct nft_set_elem_catchall {
+	struct list_head	list;
+	struct rcu_head		rcu;
+	void			*elem;
+};
+
+static void nft_map_catchall_deactivate(const struct nft_ctx *ctx,
+					struct nft_set *set)
+{
+	u8 genmask = nft_genmask_next(ctx->net);
+	struct nft_set_elem_catchall *catchall;
+	struct nft_set_elem elem;
+	struct nft_set_ext *ext;
+
+	list_for_each_entry(catchall, &set->catchall_list, list) {
+		ext = nft_set_elem_ext(set, catchall->elem);
+		if (!nft_set_elem_active(ext, genmask))
+			continue;
+
+		elem.priv = catchall->elem;
+		nft_setelem_data_deactivate(ctx->net, set, &elem);
+		break;
+	}
+}
+
+static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set)
+{
+	struct nft_set_iter iter = {
+		.genmask	= nft_genmask_next(ctx->net),
+		.fn		= nft_mapelem_deactivate,
+	};
+
+	set->ops->walk(ctx, set, &iter);
+	WARN_ON_ONCE(iter.err);
+
+	nft_map_catchall_deactivate(ctx, set);
+}
+
 static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set)
 {
 	int err;
@@ -503,6 +639,9 @@ static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set)
 	if (err < 0)
 		return err;
 
+	if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT))
+		nft_map_deactivate(ctx, set);
+
 	nft_deactivate_next(ctx->net, set);
 	ctx->table->use--;
 
@@ -2226,7 +2365,7 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family,
 	return 0;
 }
 
-static int nft_chain_add(struct nft_table *table, struct nft_chain *chain)
+int nft_chain_add(struct nft_table *table, struct nft_chain *chain)
 {
 	int err;
 
@@ -2528,6 +2667,8 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 	nft_trans_basechain(trans) = basechain;
 	INIT_LIST_HEAD(&nft_trans_chain_hooks(trans));
 	list_splice(&hook.list, &nft_trans_chain_hooks(trans));
+	if (nla[NFTA_CHAIN_HOOK])
+		module_put(hook.type->owner);
 
 	nft_trans_commit_list_add_tail(ctx->net, trans);
 
@@ -2670,21 +2811,18 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info,
 	return nf_tables_addchain(&ctx, family, genmask, policy, flags, extack);
 }
 
-static int nft_delchain_hook(struct nft_ctx *ctx, struct nft_chain *chain,
+static int nft_delchain_hook(struct nft_ctx *ctx,
+			     struct nft_base_chain *basechain,
 			     struct netlink_ext_ack *extack)
 {
+	const struct nft_chain *chain = &basechain->chain;
 	const struct nlattr * const *nla = ctx->nla;
 	struct nft_chain_hook chain_hook = {};
-	struct nft_base_chain *basechain;
 	struct nft_hook *this, *hook;
 	LIST_HEAD(chain_del_list);
 	struct nft_trans *trans;
 	int err;
 
-	if (!nft_is_base_chain(chain))
-		return -EOPNOTSUPP;
-
-	basechain = nft_base_chain(chain);
 	err = nft_chain_parse_hook(ctx->net, basechain, nla, &chain_hook,
 				   ctx->family, chain->flags, extack);
 	if (err < 0)
@@ -2769,7 +2907,12 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info,
 		if (chain->flags & NFT_CHAIN_HW_OFFLOAD)
 			return -EOPNOTSUPP;
 
-		return nft_delchain_hook(&ctx, chain, extack);
+		if (nft_is_base_chain(chain)) {
+			struct nft_base_chain *basechain = nft_base_chain(chain);
+
+			if (nft_base_chain_netdev(table->family, basechain->ops.hooknum))
+				return nft_delchain_hook(&ctx, basechain, extack);
+		}
 	}
 
 	if (info->nlh->nlmsg_flags & NLM_F_NONREC &&
@@ -3490,8 +3633,7 @@ err_fill_rule_info:
 	return err;
 }
 
-static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
-				   struct nft_rule *rule)
+void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule)
 {
 	struct nft_expr *expr, *next;
 
@@ -3508,7 +3650,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
 	kfree(rule);
 }
 
-void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule)
+static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule)
 {
 	nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE);
 	nf_tables_rule_destroy(ctx, rule);
@@ -3596,12 +3738,6 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set,
 	return 0;
 }
 
-struct nft_set_elem_catchall {
-	struct list_head	list;
-	struct rcu_head		rcu;
-	void			*elem;
-};
-
 int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set)
 {
 	u8 genmask = nft_genmask_next(ctx->net);
@@ -3844,7 +3980,7 @@ err_destroy_flow_rule:
 	if (flow)
 		nft_flow_rule_destroy(flow);
 err_release_rule:
-	nft_rule_expr_deactivate(&ctx, rule, NFT_TRANS_PREPARE);
+	nft_rule_expr_deactivate(&ctx, rule, NFT_TRANS_PREPARE_ERROR);
 	nf_tables_rule_destroy(&ctx, rule);
 err_release_expr:
 	for (i = 0; i < n; i++) {
@@ -4777,6 +4913,9 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
 		if (!(flags & NFT_SET_TIMEOUT))
 			return -EINVAL;
 
+		if (flags & NFT_SET_ANONYMOUS)
+			return -EOPNOTSUPP;
+
 		err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &desc.timeout);
 		if (err)
 			return err;
@@ -4785,6 +4924,10 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
 	if (nla[NFTA_SET_GC_INTERVAL] != NULL) {
 		if (!(flags & NFT_SET_TIMEOUT))
 			return -EINVAL;
+
+		if (flags & NFT_SET_ANONYMOUS)
+			return -EOPNOTSUPP;
+
 		desc.gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL]));
 	}
 
@@ -4831,6 +4974,9 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
 		if (info->nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
 
+		if (nft_set_is_anonymous(set))
+			return -EOPNOTSUPP;
+
 		err = nft_set_expr_alloc(&ctx, set, nla, exprs, &num_exprs, flags);
 		if (err < 0)
 			return err;
@@ -4934,7 +5080,7 @@ err_set_expr_alloc:
 	for (i = 0; i < set->num_exprs; i++)
 		nft_expr_destroy(&ctx, set->exprs[i]);
 err_set_destroy:
-	ops->destroy(set);
+	ops->destroy(&ctx, set);
 err_set_init:
 	kfree(set->name);
 err_set_name:
@@ -4949,7 +5095,7 @@ static void nft_set_catchall_destroy(const struct nft_ctx *ctx,
 
 	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
 		list_del_rcu(&catchall->list);
-		nft_set_elem_destroy(set, catchall->elem, true);
+		nf_tables_set_elem_destroy(ctx, set, catchall->elem);
 		kfree_rcu(catchall, rcu);
 	}
 }
@@ -4964,7 +5110,7 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set)
 	for (i = 0; i < set->num_exprs; i++)
 		nft_expr_destroy(ctx, set->exprs[i]);
 
-	set->ops->destroy(set);
+	set->ops->destroy(ctx, set);
 	nft_set_catchall_destroy(ctx, set);
 	kfree(set->name);
 	kvfree(set);
@@ -5129,10 +5275,60 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
 	}
 }
 
+static void nft_setelem_data_activate(const struct net *net,
+				      const struct nft_set *set,
+				      struct nft_set_elem *elem);
+
+static int nft_mapelem_activate(const struct nft_ctx *ctx,
+				struct nft_set *set,
+				const struct nft_set_iter *iter,
+				struct nft_set_elem *elem)
+{
+	nft_setelem_data_activate(ctx->net, set, elem);
+
+	return 0;
+}
+
+static void nft_map_catchall_activate(const struct nft_ctx *ctx,
+				      struct nft_set *set)
+{
+	u8 genmask = nft_genmask_next(ctx->net);
+	struct nft_set_elem_catchall *catchall;
+	struct nft_set_elem elem;
+	struct nft_set_ext *ext;
+
+	list_for_each_entry(catchall, &set->catchall_list, list) {
+		ext = nft_set_elem_ext(set, catchall->elem);
+		if (!nft_set_elem_active(ext, genmask))
+			continue;
+
+		elem.priv = catchall->elem;
+		nft_setelem_data_activate(ctx->net, set, &elem);
+		break;
+	}
+}
+
+static void nft_map_activate(const struct nft_ctx *ctx, struct nft_set *set)
+{
+	struct nft_set_iter iter = {
+		.genmask	= nft_genmask_next(ctx->net),
+		.fn		= nft_mapelem_activate,
+	};
+
+	set->ops->walk(ctx, set, &iter);
+	WARN_ON_ONCE(iter.err);
+
+	nft_map_catchall_activate(ctx, set);
+}
+
 void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set)
 {
-	if (nft_set_is_anonymous(set))
+	if (nft_set_is_anonymous(set)) {
+		if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT))
+			nft_map_activate(ctx, set);
+
 		nft_clear(ctx->net, set);
+	}
 
 	set->use++;
 }
@@ -5143,14 +5339,28 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
 			      enum nft_trans_phase phase)
 {
 	switch (phase) {
-	case NFT_TRANS_PREPARE:
+	case NFT_TRANS_PREPARE_ERROR:
+		nft_set_trans_unbind(ctx, set);
 		if (nft_set_is_anonymous(set))
 			nft_deactivate_next(ctx->net, set);
 
 		set->use--;
+		break;
+	case NFT_TRANS_PREPARE:
+		if (nft_set_is_anonymous(set)) {
+			if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT))
+				nft_map_deactivate(ctx, set);
+
+			nft_deactivate_next(ctx->net, set);
+		}
+		set->use--;
 		return;
 	case NFT_TRANS_ABORT:
 	case NFT_TRANS_RELEASE:
+		if (nft_set_is_anonymous(set) &&
+		    set->flags & (NFT_SET_MAP | NFT_SET_OBJECT))
+			nft_map_deactivate(ctx, set);
+
 		set->use--;
 		fallthrough;
 	default:
@@ -5903,6 +6113,7 @@ static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx,
 		__nft_set_elem_expr_destroy(ctx, expr);
 }
 
+/* Drop references and destroy. Called from gc, dynset and abort path. */
 void nft_set_elem_destroy(const struct nft_set *set, void *elem,
 			  bool destroy_expr)
 {
@@ -5924,11 +6135,11 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem,
 }
 EXPORT_SYMBOL_GPL(nft_set_elem_destroy);
 
-/* Only called from commit path, nft_setelem_data_deactivate() already deals
- * with the refcounting from the preparation phase.
+/* Destroy element. References have been already dropped in the preparation
+ * path via nft_setelem_data_deactivate().
  */
-static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx,
-				       const struct nft_set *set, void *elem)
+void nf_tables_set_elem_destroy(const struct nft_ctx *ctx,
+				const struct nft_set *set, void *elem)
 {
 	struct nft_set_ext *ext = nft_set_elem_ext(set, elem);
 
@@ -6491,19 +6702,19 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	if (flags)
 		*nft_set_ext_flags(ext) = flags;
 
+	if (obj) {
+		*nft_set_ext_obj(ext) = obj;
+		obj->use++;
+	}
 	if (ulen > 0) {
 		if (nft_set_ext_check(&tmpl, NFT_SET_EXT_USERDATA, ulen) < 0) {
 			err = -EINVAL;
-			goto err_elem_userdata;
+			goto err_elem_free;
 		}
 		udata = nft_set_ext_userdata(ext);
 		udata->len = ulen - 1;
 		nla_memcpy(&udata->data, nla[NFTA_SET_ELEM_USERDATA], ulen);
 	}
-	if (obj) {
-		*nft_set_ext_obj(ext) = obj;
-		obj->use++;
-	}
 	err = nft_set_elem_expr_setup(ctx, &tmpl, ext, expr_array, num_exprs);
 	if (err < 0)
 		goto err_elem_free;
@@ -6561,10 +6772,7 @@ err_set_full:
 err_element_clash:
 	kfree(trans);
 err_elem_free:
-	if (obj)
-		obj->use--;
-err_elem_userdata:
-	nf_tables_set_elem_destroy(ctx, set, elem.priv);
+	nft_set_elem_destroy(set, elem.priv, true);
 err_parse_data:
 	if (nla[NFTA_SET_ELEM_DATA] != NULL)
 		nft_data_release(&elem.data.val, desc.type);
@@ -6608,7 +6816,8 @@ static int nf_tables_newsetelem(struct sk_buff *skb,
 	if (IS_ERR(set))
 		return PTR_ERR(set);
 
-	if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT)
+	if (!list_empty(&set->bindings) &&
+	    (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS)))
 		return -EBUSY;
 
 	nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla);
@@ -6641,7 +6850,6 @@ static int nf_tables_newsetelem(struct sk_buff *skb,
 void nft_data_hold(const struct nft_data *data, enum nft_data_types type)
 {
 	struct nft_chain *chain;
-	struct nft_rule *rule;
 
 	if (type == NFT_DATA_VERDICT) {
 		switch (data->verdict.code) {
@@ -6649,15 +6857,6 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type)
 		case NFT_GOTO:
 			chain = data->verdict.chain;
 			chain->use++;
-
-			if (!nft_chain_is_bound(chain))
-				break;
-
-			chain->table->use++;
-			list_for_each_entry(rule, &chain->rules, list)
-				chain->use++;
-
-			nft_chain_add(chain->table, chain);
 			break;
 		}
 	}
@@ -6892,7 +7091,9 @@ static int nf_tables_delsetelem(struct sk_buff *skb,
 	set = nft_set_lookup(table, nla[NFTA_SET_ELEM_LIST_SET], genmask);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
-	if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT)
+
+	if (!list_empty(&set->bindings) &&
+	    (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS)))
 		return -EBUSY;
 
 	nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla);
@@ -7674,6 +7875,7 @@ void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx,
 				    enum nft_trans_phase phase)
 {
 	switch (phase) {
+	case NFT_TRANS_PREPARE_ERROR:
 	case NFT_TRANS_PREPARE:
 	case NFT_TRANS_ABORT:
 	case NFT_TRANS_RELEASE:
@@ -8946,7 +9148,7 @@ static void nf_tables_trans_destroy_work(struct work_struct *w)
 	synchronize_rcu();
 
 	list_for_each_entry_safe(trans, next, &head, list) {
-		list_del(&trans->list);
+		nft_trans_list_del(trans);
 		nft_commit_release(trans);
 	}
 }
@@ -9311,6 +9513,27 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 		return 0;
 	}
 
+	list_for_each_entry(trans, &nft_net->binding_list, binding_list) {
+		switch (trans->msg_type) {
+		case NFT_MSG_NEWSET:
+			if (!nft_trans_set_update(trans) &&
+			    nft_set_is_anonymous(nft_trans_set(trans)) &&
+			    !nft_trans_set_bound(trans)) {
+				pr_warn_once("nftables ruleset with unbound set\n");
+				return -EINVAL;
+			}
+			break;
+		case NFT_MSG_NEWCHAIN:
+			if (!nft_trans_chain_update(trans) &&
+			    nft_chain_binding(nft_trans_chain(trans)) &&
+			    !nft_trans_chain_bound(trans)) {
+				pr_warn_once("nftables ruleset with unbound chain\n");
+				return -EINVAL;
+			}
+			break;
+		}
+	}
+
 	/* 0. Validate ruleset, otherwise roll back for error reporting. */
 	if (nf_tables_validate(net) < 0)
 		return -EAGAIN;
@@ -9680,7 +9903,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 				kfree(nft_trans_chain_name(trans));
 				nft_trans_destroy(trans);
 			} else {
-				if (nft_chain_is_bound(trans->ctx.chain)) {
+				if (nft_trans_chain_bound(trans)) {
 					nft_trans_destroy(trans);
 					break;
 				}
@@ -9703,6 +9926,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_NEWRULE:
+			if (nft_trans_rule_bound(trans)) {
+				nft_trans_destroy(trans);
+				break;
+			}
 			trans->ctx.chain->use--;
 			list_del_rcu(&nft_trans_rule(trans)->list);
 			nft_rule_expr_deactivate(&trans->ctx,
@@ -9737,6 +9964,9 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 		case NFT_MSG_DESTROYSET:
 			trans->ctx.table->use++;
 			nft_clear(trans->ctx.net, nft_trans_set(trans));
+			if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT))
+				nft_map_activate(&trans->ctx, nft_trans_set(trans));
+
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_NEWSETELEM:
@@ -9817,7 +10047,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 
 	list_for_each_entry_safe_reverse(trans, next,
 					 &nft_net->commit_list, list) {
-		list_del(&trans->list);
+		nft_trans_list_del(trans);
 		nf_tables_abort_release(trans);
 	}
 
@@ -10266,22 +10496,12 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 static void nft_verdict_uninit(const struct nft_data *data)
 {
 	struct nft_chain *chain;
-	struct nft_rule *rule;
 
 	switch (data->verdict.code) {
 	case NFT_JUMP:
 	case NFT_GOTO:
 		chain = data->verdict.chain;
 		chain->use--;
-
-		if (!nft_chain_is_bound(chain))
-			break;
-
-		chain->table->use--;
-		list_for_each_entry(rule, &chain->rules, list)
-			chain->use--;
-
-		nft_chain_del(chain);
 		break;
 	}
 }
@@ -10516,6 +10736,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table)
 	list_for_each_entry_safe(set, ns, &table->sets, list) {
 		list_del(&set->list);
 		table->use--;
+		if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT))
+			nft_map_deactivate(&ctx, set);
+
 		nft_set_destroy(&ctx, set);
 	}
 	list_for_each_entry_safe(obj, ne, &table->objects, list) {
@@ -10600,6 +10823,7 @@ static int __net_init nf_tables_init_net(struct net *net)
 
 	INIT_LIST_HEAD(&nft_net->tables);
 	INIT_LIST_HEAD(&nft_net->commit_list);
+	INIT_LIST_HEAD(&nft_net->binding_list);
 	INIT_LIST_HEAD(&nft_net->module_list);
 	INIT_LIST_HEAD(&nft_net->notify_list);
 	mutex_init(&nft_net->commit_mutex);
diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index ee6840bd5933..8f1bfa6ccc2d 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -439,3 +439,4 @@ module_init(nfnl_osf_init);
 module_exit(nfnl_osf_fini);
 
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF);
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index c9d2f7c29f53..3d76ebfe8939 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -76,11 +76,9 @@ static int nft_immediate_init(const struct nft_ctx *ctx,
 		switch (priv->data.verdict.code) {
 		case NFT_JUMP:
 		case NFT_GOTO:
-			if (nft_chain_is_bound(chain)) {
-				err = -EBUSY;
-				goto err1;
-			}
-			chain->bound = true;
+			err = nf_tables_bind_chain(ctx, chain);
+			if (err < 0)
+				return err;
 			break;
 		default:
 			break;
@@ -98,6 +96,31 @@ static void nft_immediate_activate(const struct nft_ctx *ctx,
 				   const struct nft_expr *expr)
 {
 	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+	const struct nft_data *data = &priv->data;
+	struct nft_ctx chain_ctx;
+	struct nft_chain *chain;
+	struct nft_rule *rule;
+
+	if (priv->dreg == NFT_REG_VERDICT) {
+		switch (data->verdict.code) {
+		case NFT_JUMP:
+		case NFT_GOTO:
+			chain = data->verdict.chain;
+			if (!nft_chain_binding(chain))
+				break;
+
+			chain_ctx = *ctx;
+			chain_ctx.chain = chain;
+
+			list_for_each_entry(rule, &chain->rules, list)
+				nft_rule_expr_activate(&chain_ctx, rule);
+
+			nft_clear(ctx->net, chain);
+			break;
+		default:
+			break;
+		}
+	}
 
 	return nft_data_hold(&priv->data, nft_dreg_to_type(priv->dreg));
 }
@@ -107,6 +130,43 @@ static void nft_immediate_deactivate(const struct nft_ctx *ctx,
 				     enum nft_trans_phase phase)
 {
 	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+	const struct nft_data *data = &priv->data;
+	struct nft_ctx chain_ctx;
+	struct nft_chain *chain;
+	struct nft_rule *rule;
+
+	if (priv->dreg == NFT_REG_VERDICT) {
+		switch (data->verdict.code) {
+		case NFT_JUMP:
+		case NFT_GOTO:
+			chain = data->verdict.chain;
+			if (!nft_chain_binding(chain))
+				break;
+
+			chain_ctx = *ctx;
+			chain_ctx.chain = chain;
+
+			list_for_each_entry(rule, &chain->rules, list)
+				nft_rule_expr_deactivate(&chain_ctx, rule, phase);
+
+			switch (phase) {
+			case NFT_TRANS_PREPARE_ERROR:
+				nf_tables_unbind_chain(ctx, chain);
+				fallthrough;
+			case NFT_TRANS_PREPARE:
+				nft_deactivate_next(ctx->net, chain);
+				break;
+			default:
+				nft_chain_del(chain);
+				chain->bound = false;
+				chain->table->use--;
+				break;
+			}
+			break;
+		default:
+			break;
+		}
+	}
 
 	if (phase == NFT_TRANS_COMMIT)
 		return;
@@ -131,15 +191,27 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx,
 	case NFT_GOTO:
 		chain = data->verdict.chain;
 
-		if (!nft_chain_is_bound(chain))
+		if (!nft_chain_binding(chain))
+			break;
+
+		/* Rule construction failed, but chain is already bound:
+		 * let the transaction records release this chain and its rules.
+		 */
+		if (chain->bound) {
+			chain->use--;
 			break;
+		}
 
+		/* Rule has been deleted, release chain and its rules. */
 		chain_ctx = *ctx;
 		chain_ctx.chain = chain;
 
-		list_for_each_entry_safe(rule, n, &chain->rules, list)
-			nf_tables_rule_release(&chain_ctx, rule);
-
+		chain->use--;
+		list_for_each_entry_safe(rule, n, &chain->rules, list) {
+			chain->use--;
+			list_del(&rule->list);
+			nf_tables_rule_destroy(&chain_ctx, rule);
+		}
 		nf_tables_chain_destroy(&chain_ctx);
 		break;
 	default:
diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index 96081ac8d2b4..1e5e7a181e0b 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -271,13 +271,14 @@ static int nft_bitmap_init(const struct nft_set *set,
 	return 0;
 }
 
-static void nft_bitmap_destroy(const struct nft_set *set)
+static void nft_bitmap_destroy(const struct nft_ctx *ctx,
+			       const struct nft_set *set)
 {
 	struct nft_bitmap *priv = nft_set_priv(set);
 	struct nft_bitmap_elem *be, *n;
 
 	list_for_each_entry_safe(be, n, &priv->list, head)
-		nft_set_elem_destroy(set, be, true);
+		nf_tables_set_elem_destroy(ctx, set, be);
 }
 
 static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features,
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 76de6c8d9865..0b73cb0e752f 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -400,19 +400,31 @@ static int nft_rhash_init(const struct nft_set *set,
 	return 0;
 }
 
+struct nft_rhash_ctx {
+	const struct nft_ctx	ctx;
+	const struct nft_set	*set;
+};
+
 static void nft_rhash_elem_destroy(void *ptr, void *arg)
 {
-	nft_set_elem_destroy(arg, ptr, true);
+	struct nft_rhash_ctx *rhash_ctx = arg;
+
+	nf_tables_set_elem_destroy(&rhash_ctx->ctx, rhash_ctx->set, ptr);
 }
 
-static void nft_rhash_destroy(const struct nft_set *set)
+static void nft_rhash_destroy(const struct nft_ctx *ctx,
+			      const struct nft_set *set)
 {
 	struct nft_rhash *priv = nft_set_priv(set);
+	struct nft_rhash_ctx rhash_ctx = {
+		.ctx	= *ctx,
+		.set	= set,
+	};
 
 	cancel_delayed_work_sync(&priv->gc_work);
 	rcu_barrier();
 	rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy,
-				    (void *)set);
+				    (void *)&rhash_ctx);
 }
 
 /* Number of buckets is stored in u32, so cap our result to 1U<<31 */
@@ -643,7 +655,8 @@ static int nft_hash_init(const struct nft_set *set,
 	return 0;
 }
 
-static void nft_hash_destroy(const struct nft_set *set)
+static void nft_hash_destroy(const struct nft_ctx *ctx,
+			     const struct nft_set *set)
 {
 	struct nft_hash *priv = nft_set_priv(set);
 	struct nft_hash_elem *he;
@@ -653,7 +666,7 @@ static void nft_hash_destroy(const struct nft_set *set)
 	for (i = 0; i < priv->buckets; i++) {
 		hlist_for_each_entry_safe(he, next, &priv->table[i], node) {
 			hlist_del_rcu(&he->node);
-			nft_set_elem_destroy(set, he, true);
+			nf_tables_set_elem_destroy(ctx, set, he);
 		}
 	}
 }
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 83131f23ad2d..db526cb7a485 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -1973,12 +1973,16 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set,
 			    struct nft_set_iter *iter)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
+	struct net *net = read_pnet(&set->net);
 	struct nft_pipapo_match *m;
 	struct nft_pipapo_field *f;
 	int i, r;
 
 	rcu_read_lock();
-	m = rcu_dereference(priv->match);
+	if (iter->genmask == nft_genmask_cur(net))
+		m = rcu_dereference(priv->match);
+	else
+		m = priv->clone;
 
 	if (unlikely(!m))
 		goto out;
@@ -2146,10 +2150,12 @@ out_scratch:
 
 /**
  * nft_set_pipapo_match_destroy() - Destroy elements from key mapping array
+ * @ctx:	context
  * @set:	nftables API set representation
  * @m:		matching data pointing to key mapping array
  */
-static void nft_set_pipapo_match_destroy(const struct nft_set *set,
+static void nft_set_pipapo_match_destroy(const struct nft_ctx *ctx,
+					 const struct nft_set *set,
 					 struct nft_pipapo_match *m)
 {
 	struct nft_pipapo_field *f;
@@ -2166,15 +2172,17 @@ static void nft_set_pipapo_match_destroy(const struct nft_set *set,
 
 		e = f->mt[r].e;
 
-		nft_set_elem_destroy(set, e, true);
+		nf_tables_set_elem_destroy(ctx, set, e);
 	}
 }
 
 /**
  * nft_pipapo_destroy() - Free private data for set and all committed elements
+ * @ctx:	context
  * @set:	nftables API set representation
  */
-static void nft_pipapo_destroy(const struct nft_set *set)
+static void nft_pipapo_destroy(const struct nft_ctx *ctx,
+			       const struct nft_set *set)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
 	struct nft_pipapo_match *m;
@@ -2184,7 +2192,7 @@ static void nft_pipapo_destroy(const struct nft_set *set)
 	if (m) {
 		rcu_barrier();
 
-		nft_set_pipapo_match_destroy(set, m);
+		nft_set_pipapo_match_destroy(ctx, set, m);
 
 #ifdef NFT_PIPAPO_ALIGN
 		free_percpu(m->scratch_aligned);
@@ -2201,7 +2209,7 @@ static void nft_pipapo_destroy(const struct nft_set *set)
 		m = priv->clone;
 
 		if (priv->dirty)
-			nft_set_pipapo_match_destroy(set, m);
+			nft_set_pipapo_match_destroy(ctx, set, m);
 
 #ifdef NFT_PIPAPO_ALIGN
 		free_percpu(priv->clone->scratch_aligned);
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 2f114aa10f1a..5c05c9b990fb 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -664,7 +664,8 @@ static int nft_rbtree_init(const struct nft_set *set,
 	return 0;
 }
 
-static void nft_rbtree_destroy(const struct nft_set *set)
+static void nft_rbtree_destroy(const struct nft_ctx *ctx,
+			       const struct nft_set *set)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe;
@@ -675,7 +676,7 @@ static void nft_rbtree_destroy(const struct nft_set *set)
 	while ((node = priv->root.rb_node) != NULL) {
 		rb_erase(node, &priv->root);
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
-		nft_set_elem_destroy(set, rbe, true);
+		nf_tables_set_elem_destroy(ctx, set, rbe);
 	}
 }
 
diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c
index e1990baf3a3b..dc9485854002 100644
--- a/net/netfilter/xt_osf.c
+++ b/net/netfilter/xt_osf.c
@@ -71,4 +71,3 @@ MODULE_AUTHOR("Evgeniy Polyakov <zbr@ioremap.net>");
 MODULE_DESCRIPTION("Passive OS fingerprint matching.");
 MODULE_ALIAS("ipt_osf");
 MODULE_ALIAS("ip6t_osf");
-MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF);
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 0c9e93d66c50..33c0dbe35956 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -967,6 +967,7 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
 	if (ret < 0)
 		return ret;
 
+	sch_tree_lock(sch);
 	/* backup q->clg and q->loss_model */
 	old_clg = q->clg;
 	old_loss_model = q->loss_model;
@@ -975,7 +976,7 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
 		ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]);
 		if (ret) {
 			q->loss_model = old_loss_model;
-			return ret;
+			goto unlock;
 		}
 	} else {
 		q->loss_model = CLG_RANDOM;
@@ -1042,6 +1043,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
 	/* capping jitter to the range acceptable by tabledist() */
 	q->jitter = min_t(s64, abs(q->jitter), INT_MAX);
 
+unlock:
+	sch_tree_unlock(sch);
 	return ret;
 
 get_table_failure:
@@ -1051,7 +1054,8 @@ get_table_failure:
 	 */
 	q->clg = old_clg;
 	q->loss_model = old_loss_model;
-	return ret;
+
+	goto unlock;
 }
 
 static int netem_init(struct Qdisc *sch, struct nlattr *opt,
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 39fb91ff23d9..815b38080401 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -131,6 +131,7 @@ struct sec_path *secpath_set(struct sk_buff *skb)
 	memset(sp->ovec, 0, sizeof(sp->ovec));
 	sp->olen = 0;
 	sp->len = 0;
+	sp->verified_cnt = 0;
 
 	return sp;
 }
@@ -330,11 +331,10 @@ xfrm_inner_mode_encap_remove(struct xfrm_state *x,
 {
 	switch (x->props.mode) {
 	case XFRM_MODE_BEET:
-		switch (XFRM_MODE_SKB_CB(skb)->protocol) {
-		case IPPROTO_IPIP:
-		case IPPROTO_BEETPH:
+		switch (x->sel.family) {
+		case AF_INET:
 			return xfrm4_remove_beet_encap(x, skb);
-		case IPPROTO_IPV6:
+		case AF_INET6:
 			return xfrm6_remove_beet_encap(x, skb);
 		}
 		break;
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index 0ee864a76579..a3319965470a 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -311,6 +311,52 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet)
 	skb->mark = 0;
 }
 
+static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi,
+		       int encap_type, unsigned short family)
+{
+	struct sec_path *sp;
+
+	sp = skb_sec_path(skb);
+	if (sp && (sp->len || sp->olen) &&
+	    !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+		goto discard;
+
+	XFRM_SPI_SKB_CB(skb)->family = family;
+	if (family == AF_INET) {
+		XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
+	} else {
+		XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr);
+		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL;
+	}
+
+	return xfrm_input(skb, nexthdr, spi, encap_type);
+discard:
+	kfree_skb(skb);
+	return 0;
+}
+
+static int xfrmi4_rcv(struct sk_buff *skb)
+{
+	return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET);
+}
+
+static int xfrmi6_rcv(struct sk_buff *skb)
+{
+	return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff],
+			   0, 0, AF_INET6);
+}
+
+static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
+{
+	return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET);
+}
+
+static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
+{
+	return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6);
+}
+
 static int xfrmi_rcv_cb(struct sk_buff *skb, int err)
 {
 	const struct xfrm_mode *inner_mode;
@@ -946,8 +992,8 @@ static struct pernet_operations xfrmi_net_ops = {
 };
 
 static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = {
-	.handler	=	xfrm6_rcv,
-	.input_handler	=	xfrm_input,
+	.handler	=	xfrmi6_rcv,
+	.input_handler	=	xfrmi6_input,
 	.cb_handler	=	xfrmi_rcv_cb,
 	.err_handler	=	xfrmi6_err,
 	.priority	=	10,
@@ -997,8 +1043,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = {
 #endif
 
 static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = {
-	.handler	=	xfrm4_rcv,
-	.input_handler	=	xfrm_input,
+	.handler	=	xfrmi4_rcv,
+	.input_handler	=	xfrmi4_input,
 	.cb_handler	=	xfrmi_rcv_cb,
 	.err_handler	=	xfrmi4_err,
 	.priority	=	10,
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 6d15788b5123..e7617c9959c3 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1831,6 +1831,7 @@ again:
 
 		__xfrm_policy_unlink(pol, dir);
 		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+		xfrm_dev_policy_delete(pol);
 		cnt++;
 		xfrm_audit_policy_delete(pol, 1, task_valid);
 		xfrm_policy_kill(pol);
@@ -1869,6 +1870,7 @@ again:
 
 		__xfrm_policy_unlink(pol, dir);
 		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+		xfrm_dev_policy_delete(pol);
 		cnt++;
 		xfrm_audit_policy_delete(pol, 1, task_valid);
 		xfrm_policy_kill(pol);
@@ -3349,6 +3351,13 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star
 		if (xfrm_state_ok(tmpl, sp->xvec[idx], family, if_id))
 			return ++idx;
 		if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) {
+			if (idx < sp->verified_cnt) {
+				/* Secpath entry previously verified, consider optional and
+				 * continue searching
+				 */
+				continue;
+			}
+
 			if (start == -1)
 				start = -2-idx;
 			break;
@@ -3723,6 +3732,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		 * Order is _important_. Later we will implement
 		 * some barriers, but at the moment barriers
 		 * are implied between each two transformations.
+		 * Upon success, marks secpath entries as having been
+		 * verified to allow them to be skipped in future policy
+		 * checks (e.g. nested tunnels).
 		 */
 		for (i = xfrm_nr-1, k = 0; i >= 0; i--) {
 			k = xfrm_policy_ok(tpp[i], sp, k, family, if_id);
@@ -3741,6 +3753,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		}
 
 		xfrm_pols_put(pols, npols);
+		sp->verified_cnt = k;
+
 		return 1;
 	}
 	XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK);