Skip to contentSkip to conversation

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

PATCH In review Steffen Klassert 3 participants 10 messages Jan 21, 2020 – Aug 24, 2020

Subsystems (5)
lore
Share & tools
lore

Steffen Klassert

author maintainer
#0 lore raw

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.

Thanks!

The following changes since commit e7096c131e5161fa3b8e52a650d7719d2857adfd:

net: WireGuard secure network tunnel (2019-12-08 17:48:42 -0800)

are available in the Git repository at:

git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next.git master

for you to fetch changes up to e27cca96cd68fa2c6814c90f9a1cfd36bb68c593:

xfrm: add espintcp (RFC 8229) (2019-12-09 09:59:07 +0100)

----------------------------------------------------------------
Sabrina Dubroca (6):
net: add queue argument to __skb_wait_for_more_packets and __skb_{,try_}recv_datagram
xfrm: introduce xfrm_trans_queue_net
xfrm: add route lookup to xfrm4_rcv_encap
esp4: prepare esp_input_done2 for non-UDP encapsulation
esp4: split esp_output_udp_encap and introduce esp_output_encap
xfrm: add espintcp (RFC 8229)

 include/linux/skbuff.h    |  11 +-
 include/net/espintcp.h    |  39 ++++
 include/net/xfrm.h        |   4 +
 include/uapi/linux/udp.h  |   1 +
 net/core/datagram.c       |  27 ++-
 net/ipv4/Kconfig          |  11 +
 net/ipv4/esp4.c           | 264 +++++++++++++++++++++---
 net/ipv4/udp.c            |   3 +-
 net/ipv4/xfrm4_protocol.c |   9 +
 net/unix/af_unix.c        |   7 +-
 net/xfrm/Makefile         |   1 +
 net/xfrm/espintcp.c       | 509 ++++++++++++++++++++++++++++++++++++++++++++++
 net/xfrm/xfrm_input.c     |  21 +-
 net/xfrm/xfrm_policy.c    |   7 +
 net/xfrm/xfrm_state.c     |   3 +
 15 files changed, 871 insertions(+), 46 deletions(-)
 create mode 100644 include/net/espintcp.h
 create mode 100644 net/xfrm/espintcp.c
author maintainer
#1 lore raw

PATCH 1/6 net: add queue argument to __skb_wait_for_more_packets and __skb_{,try_}recv_datagram

From: Sabrina Dubroca <[email protected]>

This will be used by ESP over TCP to handle the queue of IKE messages.

---
 include/linux/skbuff.h | 11 ++++++++---
 net/core/datagram.c    | 27 +++++++++++++++++----------
 net/ipv4/udp.c         |  3 ++-
 net/unix/af_unix.c     |  7 ++++---
 4 files changed, 31 insertions(+), 17 deletions(-)
include/linux/skbuff.h +8 -3
index e9133bcf0544..49a10f9cc538 100644
@@ -3459,7 +3459,8 @@ 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,
@@ -3468,12 +3469,16 @@ 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);
net/core/datagram.c +17 -10
index da3c24ed129c..a78e7f864c1e 100644
@@ -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/udp.c +2 -1
index 4da5758cc718..e5738d1217a1 100644
@@ -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/unix/af_unix.c +4 -3
index 7cfdce10de36..a7f707fc4cac 100644
@@ -2058,8 +2058,8 @@ 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, NULL, &skip, &err,
-					      &last);
+		skb = __skb_try_recv_datagram(sk, &sk->sk_receive_queue, flags,
+					      NULL, &skip, &err, &last);
 		if (skb)
 			break;
 
@@ -2068,7 +2068,8 @@ 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);
Signature · 1 line
2.17.1
author maintainer
#2 lore raw

PATCH 2/6 xfrm: introduce xfrm_trans_queue_net

In reply to Steffen Klassert

From: Sabrina Dubroca <[email protected]>

This will be used by TCP encapsulation to write packets to the encap socket without holding the user socket's lock. Without this reinjection, we're already holding the lock of the user socket, and then try to lock the encap socket as well when we enqueue the encrypted packet.

While at it, add a BUILD_BUG_ON like we usually do for skb->cb, since it's missing for struct xfrm_trans_cb.

---
 include/net/xfrm.h    |  3 +++
 net/xfrm/xfrm_input.c | 21 +++++++++++++++++----
 2 files changed, 20 insertions(+), 4 deletions(-)
include/net/xfrm.h +3 -0
index dda3c025452e..56ff86621bb4 100644
@@ -1547,6 +1547,9 @@ 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 *));
net/xfrm/xfrm_input.c +17 -4
index 2c86a2fc3915..aa35f23c4912 100644
@@ -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]))
@@ -766,12 +767,13 @@ 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 (*finish)(struct net *, struct sock *,
-				   struct sk_buff *))
+int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
+			 int (*finish)(struct net *, struct sock *,
+				       struct sk_buff *))
 {
 	struct xfrm_trans_tasklet *trans;
 
@@ -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)
Signature · 1 line
2.17.1
author maintainer
#3 lore raw

PATCH 3/6 xfrm: add route lookup to xfrm4_rcv_encap

In reply to Steffen Klassert

From: Sabrina Dubroca <[email protected]>

At this point, with TCP encapsulation, the dst may be gone, but xfrm_input needs one.

---
 net/ipv4/xfrm4_protocol.c | 9 +++++++++
 1 file changed, 9 insertions(+)
net/ipv4/xfrm4_protocol.c +9 -0
index 8a4285712808..ea595c8549c7 100644
@@ -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;
 }
Signature · 1 line
2.17.1
author maintainer
#4 lore raw

PATCH 4/6 esp4: prepare esp_input_done2 for non-UDP encapsulation

In reply to Steffen Klassert

From: Sabrina Dubroca <[email protected]>

For espintcp encapsulation, we will need to get the source port from the TCP header instead of UDP. Introduce a variable to hold the port.

---
 net/ipv4/esp4.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)
net/ipv4/esp4.c +14 -2
index 5c967764041f..c5d826642229 100644
@@ -601,6 +601,18 @@ int esp_input_done2(struct sk_buff *skb, int err)
 	if (x->encap) {
 		struct xfrm_encap_tmpl *encap = x->encap;
 		struct udphdr *uh = (void *)(skb_network_header(skb) + ihl);
+		__be16 source;
+
+		switch (x->encap->encap_type) {
+		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 +621,11 @@ 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
Signature · 1 line
2.17.1
author maintainer
#5 lore raw

PATCH 5/6 esp4: split esp_output_udp_encap and introduce esp_output_encap

In reply to Steffen Klassert

From: Sabrina Dubroca <[email protected]>

---
 net/ipv4/esp4.c | 57 ++++++++++++++++++++++++++++++++-----------------
 1 file changed, 37 insertions(+), 20 deletions(-)
net/ipv4/esp4.c +37 -20
index c5d826642229..033c61d27148 100644
@@ -225,45 +225,62 @@ 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;
+		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);
+}
+
+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;
 	}
 
-	*skb_mac_header(skb) = IPPROTO_UDP;
+	if (IS_ERR(esph))
+		return PTR_ERR(esph);
+
 	esp->esph = esph;
 
 	return 0;
@@ -281,7 +298,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 
 	/* this is non-NULL only with 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;
Signature · 1 line
2.17.1
author maintainer
#6 lore raw

PATCH 6/6 xfrm: add espintcp (RFC 8229)

In reply to Steffen Klassert

From: Sabrina Dubroca <[email protected]>

TCP encapsulation of IKE and IPsec messages (RFC 8229) is implemented as a TCP ULP, overriding in particular the sendmsg and recvmsg operations. A Stream Parser is used to extract messages out of the TCP stream using the first 2 bytes as length marker. Received IKE messages are put on "ike_queue", waiting to be dequeued by the custom recvmsg implementation. Received ESP messages are sent to XFRM, like with UDP encapsulation.

Some of this code is taken from the original submission by Herbert Xu. Currently, only IPv4 is supported, like for UDP encapsulation.

---
 include/net/espintcp.h   |  39 +++
 include/net/xfrm.h       |   1 +
 include/uapi/linux/udp.h |   1 +
 net/ipv4/Kconfig         |  11 +
 net/ipv4/esp4.c          | 191 ++++++++++++++-
 net/xfrm/Makefile        |   1 +
 net/xfrm/espintcp.c      | 509 +++++++++++++++++++++++++++++++++++++++
 net/xfrm/xfrm_policy.c   |   7 +
 net/xfrm/xfrm_state.c    |   3 +
 9 files changed, 760 insertions(+), 3 deletions(-)
 create mode 100644 include/net/espintcp.h
 create mode 100644 net/xfrm/espintcp.c
include/net/espintcp.h new file +39 -0
new file mode 100644
index 000000000000..dd7026a00066
@@ -0,0 +1,39 @@
+/* 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 +1 -0
index 56ff86621bb4..8f71c111e65a 100644
@@ -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;
include/uapi/linux/udp.h +1 -0
index 30baccb6c9c4..4828794efcf8 100644
@@ -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/ipv4/Kconfig +11 -0
index fc816b187170..f96bd489b362 100644
@@ -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 +188 -3

255 lines not on this page · raw message

net/xfrm/Makefile +1 -0
index fbc4552d17b8..212a4fcb4a88 100644
@@ -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/espintcp.c new file +509 -0

509 lines not on this page · raw message

net/xfrm/xfrm_policy.c +7 -0
index f2d1e573ea55..297d1eb79e5c 100644
@@ -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 +3 -0
index f3423562d933..170d6e7f31d3 100644
@@ -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.
Signature · 1 line
2.17.1
#7 lore raw

Re: [PATCH 6/6] xfrm: add espintcp (RFC 8229)

Quoted 9 lines · Steffen Klassert

From: Sabrina Dubroca <[email protected]>

TCP encapsulation of IKE and IPsec messages (RFC 8229) is implemented as a TCP ULP, overriding in particular the sendmsg and recvmsg operations. A Stream Parser is used to extract messages out of the TCP stream using the first 2 bytes as length marker. Received IKE messages are put on "ike_queue", waiting to be dequeued by the custom recvmsg implementation. Received ESP messages are sent to XFRM, like with UDP encapsulation

...

Quoted 11 lines
net/xfrm/espintcp.c new file +11 -0
+
+static int espintcp_sendskb_locked(struct sock *sk, struct espintcp_msg *emsg,
+				   int flags)
+{
+	do {
+		int ret;
+
+		ret = skb_send_sock_locked(sk, emsg->skb,
+					   emsg->offset, emsg->len);
+		if (ret < 0)
+			return ret;

net/xfrm/espintcp.c line 160

Quoted 10 lines
net/xfrm/espintcp.c new file +10 -0
+
+		emsg->len -= ret;
+		emsg->offset += ret;
+	} while (emsg->len > 0);
+
+	kfree_skb(emsg->skb);
+	memset(emsg, 0, sizeof(*emsg));
+
+	return 0;
+}

Is there any particular reason we use kfree_skb() here instead of consume_skb() ?

Same remark for final kfree_skb() in espintcp_recvmsg()

Thanks.

author maintainer
#8 lore raw

Re: [PATCH 6/6] xfrm: add espintcp (RFC 8229)

Ccing Sabrina.

Quoted 31 lines · Eric Dumazet
Quoted 9 lines · Steffen Klassert

From: Sabrina Dubroca <[email protected]>

TCP encapsulation of IKE and IPsec messages (RFC 8229) is implemented as a TCP ULP, overriding in particular the sendmsg and recvmsg operations. A Stream Parser is used to extract messages out of the TCP stream using the first 2 bytes as length marker. Received IKE messages are put on "ike_queue", waiting to be dequeued by the custom recvmsg implementation. Received ESP messages are sent to XFRM, like with UDP encapsulation

...

Quoted 16 lines
net/xfrm/espintcp.c new file +16 -0
+
+static int espintcp_sendskb_locked(struct sock *sk, struct espintcp_msg *emsg,
+				   int flags)
+{
+	do {
+		int ret;
+
+		ret = skb_send_sock_locked(sk, emsg->skb,
+					   emsg->offset, emsg->len);
+		if (ret < 0)
+			return ret;
+
+		emsg->len -= ret;
+		emsg->offset += ret;
+	} while (emsg->len > 0);
+
Quoted 8 lines

net/xfrm/espintcp.c line 160

Quoted 5 lines
net/xfrm/espintcp.c new file +5 -0
+	kfree_skb(emsg->skb);
+	memset(emsg, 0, sizeof(*emsg));
+
+	return 0;
+}

Is there any particular reason we use kfree_skb() here instead of consume_skb() ?

I guess not. The skb in not dropped due to an error, so consume_skb() seems to be more appropriate.

Quoted 3 lines

Same remark for final kfree_skb() in espintcp_recvmsg()

maintainer
#9 lore raw
In reply to Steffen Klassert

From: Steffen Klassert <[email protected]>
Date: Tue, 21 Jan 2020 08:38:52 +0100

Quoted 13 lines

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:

Quoted 7 lines

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.

Pulled, thanks for the info about the merge conflict.