ipv{4,6}/raw: fix output xfrm lookup wrt protocol

With a raw socket bound to IPPROTO_RAW (ie with hdrincl enabled), the
protocol field of the flow structure, build by raw_sendmsg() /
rawv6_sendmsg()),  is set to IPPROTO_RAW. This breaks the ipsec policy
lookup when some policies are defined with a protocol in the selector.

For ipv6, the sin6_port field from 'struct sockaddr_in6' could be used to
specify the protocol. Just accept all values for IPPROTO_RAW socket.

For ipv4, the sin_port field of 'struct sockaddr_in' could not be used
without breaking backward compatibility (the value of this field was never
checked). Let's add a new kind of control message, so that the userland
could specify which protocol is used.

Fixes: 1da177e ("Linux-2.6.12-rc2")
CC: [email protected]
Signed-off-by: Nicolas Dichtel <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Paolo Abeni <[email protected]>

Author: NicolasDichtel

include/net/ip.h

@@ -76,6 +76,7 @@ struct ipcm_cookie {
 	__be32			addr;
 	int			oif;
 	struct ip_options_rcu	*opt;
+	__u8			protocol;
 	__u8			ttl;
 	__s16			tos;
 	char			priority;
@@ -96,6 +97,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
 	ipcm->sockc.tsflags = inet->sk.sk_tsflags;
 	ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
 	ipcm->addr = inet->inet_saddr;
+	ipcm->protocol = inet->inet_num;
 }
 
 #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))

include/uapi/linux/in.h

@@ -163,6 +163,7 @@ struct in_addr {
 #define IP_MULTICAST_ALL		49
 #define IP_UNICAST_IF			50
 #define IP_LOCAL_PORT_RANGE		51
+#define IP_PROTOCOL			52
 
 #define MCAST_EXCLUDE	0
 #define MCAST_INCLUDE	1

net/ipv4/ip_sockglue.c

@@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
 			ipc->tos = val;
 			ipc->priority = rt_tos2priority(ipc->tos);
 			break;
-
+		case IP_PROTOCOL:
+			if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+				return -EINVAL;
+			val = *(int *)CMSG_DATA(cmsg);
+			if (val < 1 || val > 255)
+				return -EINVAL;
+			ipc->protocol = val;
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -1761,6 +1768,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_LOCAL_PORT_RANGE:
 		val = inet->local_port_range.hi << 16 | inet->local_port_range.lo;
 		break;
+	case IP_PROTOCOL:
+		val = inet_sk(sk)->inet_num;
+		break;
 	default:
 		sockopt_release_sock(sk);
 		return -ENOPROTOOPT;

net/ipv4/raw.c

@@ -532,6 +532,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 
 	ipcm_init_sk(&ipc, inet);
+	/* Keep backward compat */
+	if (hdrincl)
+		ipc.protocol = IPPROTO_RAW;
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sk, msg, &ipc, false);
@@ -599,7 +602,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos,
 			   RT_SCOPE_UNIVERSE,
-			   hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+			   hdrincl ? ipc.protocol : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk) |
 			    (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
 			   daddr, saddr, 0, 0, sk->sk_uid);

net/ipv6/raw.c

@@ -793,7 +793,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 		if (!proto)
 			proto = inet->inet_num;
-		else if (proto != inet->inet_num)
+		else if (proto != inet->inet_num &&
+			 inet->inet_num != IPPROTO_RAW)
 			return -EINVAL;
 
 		if (proto > 255)