Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next

Steffen Klassert says:

====================
pull request (net-next): ipsec-next 2020-01-21

1) Add support for TCP encapsulation of IKE and ESP messages,
   as defined by RFC 8229. Patchset from Sabrina Dubroca.

Please note that there is a merge conflict in:

net/unix/af_unix.c

between commit:

3c32da19 ("unix: Show number of pending scm files of receive queue in fdinfo")

from the net-next tree and commit:

b50b0580 ("net: add queue argument to __skb_wait_for_more_packets and __skb_{,try_}recv_datagram")

from the ipsec-next tree.

The conflict can be solved as done in linux-next.

Please pull or let me know if there are problems.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/skbuff.h

@@ -3464,7 +3464,8 @@ static inline void skb_frag_list_init(struct sk_buff *skb)
 	for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next)
 
 
-int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
+int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue,
+				int *err, long *timeo_p,
 				const struct sk_buff *skb);
 struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
 					  struct sk_buff_head *queue,
@@ -3473,12 +3474,16 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
 							   struct sk_buff *skb),
 					  int *off, int *err,
 					  struct sk_buff **last);
-struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned flags,
+struct sk_buff *__skb_try_recv_datagram(struct sock *sk,
+					struct sk_buff_head *queue,
+					unsigned int flags,
 					void (*destructor)(struct sock *sk,
 							   struct sk_buff *skb),
 					int *off, int *err,
 					struct sk_buff **last);
-struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
+struct sk_buff *__skb_recv_datagram(struct sock *sk,
+				    struct sk_buff_head *sk_queue,
+				    unsigned int flags,
 				    void (*destructor)(struct sock *sk,
 						       struct sk_buff *skb),
 				    int *off, int *err);

include/net/espintcp.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NET_ESPINTCP_H
+#define _NET_ESPINTCP_H
+
+#include <net/strparser.h>
+#include <linux/skmsg.h>
+
+void __init espintcp_init(void);
+
+int espintcp_push_skb(struct sock *sk, struct sk_buff *skb);
+int espintcp_queue_out(struct sock *sk, struct sk_buff *skb);
+bool tcp_is_ulp_esp(struct sock *sk);
+
+struct espintcp_msg {
+	struct sk_buff *skb;
+	struct sk_msg skmsg;
+	int offset;
+	int len;
+};
+
+struct espintcp_ctx {
+	struct strparser strp;
+	struct sk_buff_head ike_queue;
+	struct sk_buff_head out_queue;
+	struct espintcp_msg partial;
+	void (*saved_data_ready)(struct sock *sk);
+	void (*saved_write_space)(struct sock *sk);
+	struct work_struct work;
+	bool tx_running;
+};
+
+static inline struct espintcp_ctx *espintcp_getctx(const struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	/* RCU is only needed for diag */
+	return (__force void *)icsk->icsk_ulp_data;
+}
+#endif

include/net/xfrm.h

@@ -193,6 +193,7 @@ struct xfrm_state {
 
 	/* Data for encapsulator */
 	struct xfrm_encap_tmpl	*encap;
+	struct sock __rcu	*encap_sk;
 
 	/* Data for care-of address */
 	xfrm_address_t	*coaddr;
@@ -1547,6 +1548,9 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload);
 int xfrm_init_state(struct xfrm_state *x);
 int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type);
 int xfrm_input_resume(struct sk_buff *skb, int nexthdr);
+int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
+			 int (*finish)(struct net *, struct sock *,
+				       struct sk_buff *));
 int xfrm_trans_queue(struct sk_buff *skb,
 		     int (*finish)(struct net *, struct sock *,
 				   struct sk_buff *));

include/uapi/linux/udp.h

@@ -42,5 +42,6 @@ struct udphdr {
 #define UDP_ENCAP_GTP0		4 /* GSM TS 09.60 */
 #define UDP_ENCAP_GTP1U		5 /* 3GPP TS 29.060 */
 #define UDP_ENCAP_RXRPC		6
+#define TCP_ENCAP_ESPINTCP	7 /* Yikes, this is really xfrm encap types. */
 
 #endif /* _UAPI_LINUX_UDP_H */

net/core/datagram.c

@@ -84,7 +84,8 @@ static int receiver_wake_function(wait_queue_entry_t *wait, unsigned int mode, i
 /*
  * Wait for the last received packet to be different from skb
  */
-int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
+int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue,
+				int *err, long *timeo_p,
 				const struct sk_buff *skb)
 {
 	int error;
@@ -97,7 +98,7 @@ int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
 	if (error)
 		goto out_err;
 
-	if (READ_ONCE(sk->sk_receive_queue.prev) != skb)
+	if (READ_ONCE(queue->prev) != skb)
 		goto out;
 
 	/* Socket shut down? */
@@ -209,6 +210,7 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
 /**
  *	__skb_try_recv_datagram - Receive a datagram skbuff
  *	@sk: socket
+ *	@queue: socket queue from which to receive
  *	@flags: MSG\_ flags
  *	@destructor: invoked under the receive lock on successful dequeue
  *	@off: an offset in bytes to peek skb from. Returns an offset
@@ -241,13 +243,14 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
  *	quite explicitly by POSIX 1003.1g, don't change them without having
  *	the standard around please.
  */
-struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
+struct sk_buff *__skb_try_recv_datagram(struct sock *sk,
+					struct sk_buff_head *queue,
+					unsigned int flags,
 					void (*destructor)(struct sock *sk,
 							   struct sk_buff *skb),
 					int *off, int *err,
 					struct sk_buff **last)
 {
-	struct sk_buff_head *queue = &sk->sk_receive_queue;
 	struct sk_buff *skb;
 	unsigned long cpu_flags;
 	/*
@@ -278,7 +281,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
 			break;
 
 		sk_busy_loop(sk, flags & MSG_DONTWAIT);
-	} while (READ_ONCE(sk->sk_receive_queue.prev) != *last);
+	} while (READ_ONCE(queue->prev) != *last);
 
 	error = -EAGAIN;
 
@@ -288,7 +291,9 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
 }
 EXPORT_SYMBOL(__skb_try_recv_datagram);
 
-struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
+struct sk_buff *__skb_recv_datagram(struct sock *sk,
+				    struct sk_buff_head *sk_queue,
+				    unsigned int flags,
 				    void (*destructor)(struct sock *sk,
 						       struct sk_buff *skb),
 				    int *off, int *err)
@@ -299,15 +304,16 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 
 	do {
-		skb = __skb_try_recv_datagram(sk, flags, destructor, off, err,
-					      &last);
+		skb = __skb_try_recv_datagram(sk, sk_queue, flags, destructor,
+					      off, err, &last);
 		if (skb)
 			return skb;
 
 		if (*err != -EAGAIN)
 			break;
 	} while (timeo &&
-		!__skb_wait_for_more_packets(sk, err, &timeo, last));
+		 !__skb_wait_for_more_packets(sk, sk_queue, err,
+					      &timeo, last));
 
 	return NULL;
 }
@@ -318,7 +324,8 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags,
 {
 	int off = 0;
 
-	return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
+	return __skb_recv_datagram(sk, &sk->sk_receive_queue,
+				   flags | (noblock ? MSG_DONTWAIT : 0),
 				   NULL, &off, err);
 }
 EXPORT_SYMBOL(skb_recv_datagram);

net/ipv4/Kconfig

@@ -378,6 +378,17 @@ config INET_ESP_OFFLOAD
 
 	  If unsure, say N.
 
+config INET_ESPINTCP
+	bool "IP: ESP in TCP encapsulation (RFC 8229)"
+	depends on XFRM && INET_ESP
+	select STREAM_PARSER
+	select NET_SOCK_MSG
+	help
+	  Support for RFC 8229 encapsulation of ESP and IKE over
+	  TCP/IPv4 sockets.
+
+	  If unsure, say N.
+
 config INET_IPCOMP
 	tristate "IP: IPComp transformation"
 	select INET_XFRM_TUNNEL

net/ipv4/esp4.c

@@ -18,6 +18,8 @@
 #include <net/icmp.h>
 #include <net/protocol.h>
 #include <net/udp.h>
+#include <net/tcp.h>
+#include <net/espintcp.h>
 
 #include <linux/highmem.h>
 
@@ -117,6 +119,132 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
 			put_page(sg_page(sg));
 }
 
+#ifdef CONFIG_INET_ESPINTCP
+struct esp_tcp_sk {
+	struct sock *sk;
+	struct rcu_head rcu;
+};
+
+static void esp_free_tcp_sk(struct rcu_head *head)
+{
+	struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);
+
+	sock_put(esk->sk);
+	kfree(esk);
+}
+
+static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
+{
+	struct xfrm_encap_tmpl *encap = x->encap;
+	struct esp_tcp_sk *esk;
+	__be16 sport, dport;
+	struct sock *nsk;
+	struct sock *sk;
+
+	sk = rcu_dereference(x->encap_sk);
+	if (sk && sk->sk_state == TCP_ESTABLISHED)
+		return sk;
+
+	spin_lock_bh(&x->lock);
+	sport = encap->encap_sport;
+	dport = encap->encap_dport;
+	nsk = rcu_dereference_protected(x->encap_sk,
+					lockdep_is_held(&x->lock));
+	if (sk && sk == nsk) {
+		esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
+		if (!esk) {
+			spin_unlock_bh(&x->lock);
+			return ERR_PTR(-ENOMEM);
+		}
+		RCU_INIT_POINTER(x->encap_sk, NULL);
+		esk->sk = sk;
+		call_rcu(&esk->rcu, esp_free_tcp_sk);
+	}
+	spin_unlock_bh(&x->lock);
+
+	sk = inet_lookup_established(xs_net(x), &tcp_hashinfo, x->id.daddr.a4,
+				     dport, x->props.saddr.a4, sport, 0);
+	if (!sk)
+		return ERR_PTR(-ENOENT);
+
+	if (!tcp_is_ulp_esp(sk)) {
+		sock_put(sk);
+		return ERR_PTR(-EINVAL);
+	}
+
+	spin_lock_bh(&x->lock);
+	nsk = rcu_dereference_protected(x->encap_sk,
+					lockdep_is_held(&x->lock));
+	if (encap->encap_sport != sport ||
+	    encap->encap_dport != dport) {
+		sock_put(sk);
+		sk = nsk ?: ERR_PTR(-EREMCHG);
+	} else if (sk == nsk) {
+		sock_put(sk);
+	} else {
+		rcu_assign_pointer(x->encap_sk, sk);
+	}
+	spin_unlock_bh(&x->lock);
+
+	return sk;
+}
+
+static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct sock *sk;
+	int err;
+
+	rcu_read_lock();
+
+	sk = esp_find_tcp_sk(x);
+	err = PTR_ERR_OR_ZERO(sk);
+	if (err)
+		goto out;
+
+	bh_lock_sock(sk);
+	if (sock_owned_by_user(sk))
+		err = espintcp_queue_out(sk, skb);
+	else
+		err = espintcp_push_skb(sk, skb);
+	bh_unlock_sock(sk);
+
+out:
+	rcu_read_unlock();
+	return err;
+}
+
+static int esp_output_tcp_encap_cb(struct net *net, struct sock *sk,
+				   struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct xfrm_state *x = dst->xfrm;
+
+	return esp_output_tcp_finish(x, skb);
+}
+
+static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err;
+
+	local_bh_disable();
+	err = xfrm_trans_queue_net(xs_net(x), skb, esp_output_tcp_encap_cb);
+	local_bh_enable();
+
+	/* EINPROGRESS just happens to do the right thing.  It
+	 * actually means that the skb has been consumed and
+	 * isn't coming back.
+	 */
+	return err ?: -EINPROGRESS;
+}
+#else
+static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
+{
+	kfree_skb(skb);
+
+	return -EOPNOTSUPP;
+}
+#endif
+
 static void esp_output_done(struct crypto_async_request *base, int err)
 {
 	struct sk_buff *skb = base->data;
@@ -147,6 +275,10 @@ static void esp_output_done(struct crypto_async_request *base, int err)
 		secpath_reset(skb);
 		xfrm_dev_resume(skb);
 	} else {
+		if (!err &&
+		    x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
+			esp_output_tail_tcp(x, skb);
+		else
 			xfrm_output_resume(skb, err);
 	}
 }
@@ -225,45 +357,100 @@ static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto)
 	tail[plen - 1] = proto;
 }
 
-static int esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
+static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb,
+					       int encap_type,
+					       struct esp_info *esp,
+					       __be16 sport,
+					       __be16 dport)
 {
-	int encap_type;
 	struct udphdr *uh;
 	__be32 *udpdata32;
-	__be16 sport, dport;
-	struct xfrm_encap_tmpl *encap = x->encap;
-	struct ip_esp_hdr *esph = esp->esph;
 	unsigned int len;
 
-	spin_lock_bh(&x->lock);
-	sport = encap->encap_sport;
-	dport = encap->encap_dport;
-	encap_type = encap->encap_type;
-	spin_unlock_bh(&x->lock);
-
 	len = skb->len + esp->tailen - skb_transport_offset(skb);
-	if (len + sizeof(struct iphdr) >= IP_MAX_MTU)
-		return -EMSGSIZE;
+	if (len + sizeof(struct iphdr) > IP_MAX_MTU)
+		return ERR_PTR(-EMSGSIZE);
 
-	uh = (struct udphdr *)esph;
+	uh = (struct udphdr *)esp->esph;
 	uh->source = sport;
 	uh->dest = dport;
 	uh->len = htons(len);
 	uh->check = 0;
 
+	*skb_mac_header(skb) = IPPROTO_UDP;
+
+	if (encap_type == UDP_ENCAP_ESPINUDP_NON_IKE) {
+		udpdata32 = (__be32 *)(uh + 1);
+		udpdata32[0] = udpdata32[1] = 0;
+		return (struct ip_esp_hdr *)(udpdata32 + 2);
+	}
+
+	return (struct ip_esp_hdr *)(uh + 1);
+}
+
+#ifdef CONFIG_INET_ESPINTCP
+static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x,
+						    struct sk_buff *skb,
+						    struct esp_info *esp)
+{
+	__be16 *lenp = (void *)esp->esph;
+	struct ip_esp_hdr *esph;
+	unsigned int len;
+	struct sock *sk;
+
+	len = skb->len + esp->tailen - skb_transport_offset(skb);
+	if (len > IP_MAX_MTU)
+		return ERR_PTR(-EMSGSIZE);
+
+	rcu_read_lock();
+	sk = esp_find_tcp_sk(x);
+	rcu_read_unlock();
+
+	if (IS_ERR(sk))
+		return ERR_CAST(sk);
+
+	*lenp = htons(len);
+	esph = (struct ip_esp_hdr *)(lenp + 1);
+
+	return esph;
+}
+#else
+static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x,
+						    struct sk_buff *skb,
+						    struct esp_info *esp)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+#endif
+
+static int esp_output_encap(struct xfrm_state *x, struct sk_buff *skb,
+			    struct esp_info *esp)
+{
+	struct xfrm_encap_tmpl *encap = x->encap;
+	struct ip_esp_hdr *esph;
+	__be16 sport, dport;
+	int encap_type;
+
+	spin_lock_bh(&x->lock);
+	sport = encap->encap_sport;
+	dport = encap->encap_dport;
+	encap_type = encap->encap_type;
+	spin_unlock_bh(&x->lock);
+
 	switch (encap_type) {
 	default:
 	case UDP_ENCAP_ESPINUDP:
-		esph = (struct ip_esp_hdr *)(uh + 1);
-		break;
 	case UDP_ENCAP_ESPINUDP_NON_IKE:
-		udpdata32 = (__be32 *)(uh + 1);
-		udpdata32[0] = udpdata32[1] = 0;
-		esph = (struct ip_esp_hdr *)(udpdata32 + 2);
+		esph = esp_output_udp_encap(skb, encap_type, esp, sport, dport);
+		break;
+	case TCP_ENCAP_ESPINTCP:
+		esph = esp_output_tcp_encap(x, skb, esp);
 		break;
 	}
 
-	*skb_mac_header(skb) = IPPROTO_UDP;
+	if (IS_ERR(esph))
+		return PTR_ERR(esph);
+
 	esp->esph = esph;
 
 	return 0;
@@ -279,9 +466,9 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 	struct sk_buff *trailer;
 	int tailen = esp->tailen;
 
-	/* this is non-NULL only with UDP Encapsulation */
+	/* this is non-NULL only with TCP/UDP Encapsulation */
 	if (x->encap) {
-		int err = esp_output_udp_encap(x, skb, esp);
+		int err = esp_output_encap(x, skb, esp);
 
 		if (err < 0)
 			return err;
@@ -474,6 +661,9 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 	if (sg != dsg)
 		esp_ssg_unref(x, tmp);
 
+	if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
+		err = esp_output_tail_tcp(x, skb);
+
 error_free:
 	kfree(tmp);
 error:
@@ -600,7 +790,23 @@ int esp_input_done2(struct sk_buff *skb, int err)
 
 	if (x->encap) {
 		struct xfrm_encap_tmpl *encap = x->encap;
+		struct tcphdr *th = (void *)(skb_network_header(skb) + ihl);
 		struct udphdr *uh = (void *)(skb_network_header(skb) + ihl);
+		__be16 source;
+
+		switch (x->encap->encap_type) {
+		case TCP_ENCAP_ESPINTCP:
+			source = th->source;
+			break;
+		case UDP_ENCAP_ESPINUDP:
+		case UDP_ENCAP_ESPINUDP_NON_IKE:
+			source = uh->source;
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			err = -EINVAL;
+			goto out;
+		}
 
 		/*
 		 * 1) if the NAT-T peer's IP or port changed then
@@ -609,11 +815,11 @@ int esp_input_done2(struct sk_buff *skb, int err)
 		 *    SRC ports.
 		 */
 		if (iph->saddr != x->props.saddr.a4 ||
-		    uh->source != encap->encap_sport) {
+		    source != encap->encap_sport) {
 			xfrm_address_t ipaddr;
 
 			ipaddr.a4 = iph->saddr;
-			km_new_mapping(x, &ipaddr, uh->source);
+			km_new_mapping(x, &ipaddr, source);
 
 			/* XXX: perhaps add an extra
 			 * policy check here, to see
@@ -988,6 +1194,14 @@ static int esp_init_state(struct xfrm_state *x)
 		case UDP_ENCAP_ESPINUDP_NON_IKE:
 			x->props.header_len += sizeof(struct udphdr) + 2 * sizeof(u32);
 			break;
+#ifdef CONFIG_INET_ESPINTCP
+		case TCP_ENCAP_ESPINTCP:
+			/* only the length field, TCP encap is done by
+			 * the socket
+			 */
+			x->props.header_len += 2;
+			break;
+#endif
 		}
 	}
 

net/ipv4/udp.c

@@ -1708,7 +1708,8 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
 
 		/* sk_queue is empty, reader_queue may contain peeked packets */
 	} while (timeo &&
-		 !__skb_wait_for_more_packets(sk, &error, &timeo,
+		 !__skb_wait_for_more_packets(sk, &sk->sk_receive_queue,
+					      &error, &timeo,
 					      (struct sk_buff *)sk_queue));
 
 	*err = error;

net/ipv4/xfrm4_protocol.c

@@ -72,6 +72,14 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
 	if (!head)
 		goto out;
 
+	if (!skb_dst(skb)) {
+		const struct iphdr *iph = ip_hdr(skb);
+
+		if (ip_route_input_noref(skb, iph->daddr, iph->saddr,
+					 iph->tos, skb->dev))
+			goto drop;
+	}
+
 	for_each_protocol_rcu(*head, handler)
 		if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL)
 			return ret;
@@ -79,6 +87,7 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
 out:
 	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
 
+drop:
 	kfree_skb(skb);
 	return 0;
 }

net/unix/af_unix.c

@@ -2100,8 +2100,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 		mutex_lock(&u->iolock);
 
 		skip = sk_peek_offset(sk, flags);
-		skb = __skb_try_recv_datagram(sk, flags, scm_stat_del,
-					      &skip, &err, &last);
+		skb = __skb_try_recv_datagram(sk, &sk->sk_receive_queue, flags,
+					      scm_stat_del, &skip, &err, &last);
 		if (skb)
 			break;
 
@@ -2110,7 +2110,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 		if (err != -EAGAIN)
 			break;
 	} while (timeo &&
-		 !__skb_wait_for_more_packets(sk, &err, &timeo, last));
+		 !__skb_wait_for_more_packets(sk, &sk->sk_receive_queue,
+					      &err, &timeo, last));
 
 	if (!skb) { /* implies iolock unlocked */
 		unix_state_lock(sk);

net/xfrm/Makefile

@@ -11,3 +11,4 @@ obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o
 obj-$(CONFIG_XFRM_USER) += xfrm_user.o
 obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o
 obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o
+obj-$(CONFIG_INET_ESPINTCP) += espintcp.o

net/xfrm/xfrm_input.c

@@ -36,6 +36,7 @@ struct xfrm_trans_cb {
 #endif
 	} header;
 	int (*finish)(struct net *net, struct sock *sk, struct sk_buff *skb);
+	struct net *net;
 };
 
 #define XFRM_TRANS_SKB_CB(__skb) ((struct xfrm_trans_cb *)&((__skb)->cb[0]))
@@ -766,10 +767,11 @@ static void xfrm_trans_reinject(unsigned long data)
 	skb_queue_splice_init(&trans->queue, &queue);
 
 	while ((skb = __skb_dequeue(&queue)))
-		XFRM_TRANS_SKB_CB(skb)->finish(dev_net(skb->dev), NULL, skb);
+		XFRM_TRANS_SKB_CB(skb)->finish(XFRM_TRANS_SKB_CB(skb)->net,
+					       NULL, skb);
 }
 
-int xfrm_trans_queue(struct sk_buff *skb,
+int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
 			 int (*finish)(struct net *, struct sock *,
 				       struct sk_buff *))
 {
@@ -780,11 +782,22 @@ int xfrm_trans_queue(struct sk_buff *skb,
 	if (skb_queue_len(&trans->queue) >= netdev_max_backlog)
 		return -ENOBUFS;
 
+	BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb));
+
 	XFRM_TRANS_SKB_CB(skb)->finish = finish;
+	XFRM_TRANS_SKB_CB(skb)->net = net;
 	__skb_queue_tail(&trans->queue, skb);
 	tasklet_schedule(&trans->tasklet);
 	return 0;
 }
+EXPORT_SYMBOL(xfrm_trans_queue_net);
+
+int xfrm_trans_queue(struct sk_buff *skb,
+		     int (*finish)(struct net *, struct sock *,
+				   struct sk_buff *))
+{
+	return xfrm_trans_queue_net(dev_net(skb->dev), skb, finish);
+}
 EXPORT_SYMBOL(xfrm_trans_queue);
 
 void __init xfrm_input_init(void)

net/xfrm/xfrm_policy.c

@@ -39,6 +39,9 @@
 #ifdef CONFIG_XFRM_STATISTICS
 #include <net/snmp.h>
 #endif
+#ifdef CONFIG_INET_ESPINTCP
+#include <net/espintcp.h>
+#endif
 
 #include "xfrm_hash.h"
 
@@ -4157,6 +4160,10 @@ void __init xfrm_init(void)
 	seqcount_init(&xfrm_policy_hash_generation);
 	xfrm_input_init();
 
+#ifdef CONFIG_INET_ESPINTCP
+	espintcp_init();
+#endif
+
 	RCU_INIT_POINTER(xfrm_if_cb, NULL);
 	synchronize_rcu();
 }

net/xfrm/xfrm_state.c

@@ -670,6 +670,9 @@ int __xfrm_state_delete(struct xfrm_state *x)
 		net->xfrm.state_num--;
 		spin_unlock(&net->xfrm.xfrm_state_lock);
 
+		if (x->encap_sk)
+			sock_put(rcu_dereference_raw(x->encap_sk));
+
 		xfrm_dev_state_delete(x);
 
 		/* All xfrm_state objects are created by xfrm_state_alloc.