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:

3c32da19a858 ("unix: Show number of pending scm files of receive queue in fdinfo")

from the net-next tree and commit:

b50b0580d27b ("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>

4 files changed, 261 insertions, 26 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index fc816b187170..f96bd489b362 100644
--- a/net/ipv4/Kconfig
+++ b/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
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 5c967764041f..103c7d599a3c 100644
--- a/net/ipv4/esp4.c
+++ b/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;
@@ -147,7 +275,11 @@ static void esp_output_done(struct crypto_async_request *base, int err)
 		secpath_reset(skb);
 		xfrm_dev_resume(skb);
 	} else {
-		xfrm_output_resume(skb, err);
+		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
 		}
 	}
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 208da0917469..e4fd4408b775 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1708,7 +1708,8 @@ busy_check:
 
 		/* 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;
diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c
index 8a4285712808..ea595c8549c7 100644
--- a/net/ipv4/xfrm4_protocol.c
+++ b/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;
 }