Merge nuts.davemloft.net:/disk1/BK/xfrm-icmp-2.6

into nuts.davemloft.net:/disk1/BK/net-2.6

include/net/xfrm.h

@@ -421,13 +421,51 @@ static __inline__ int addr_match(void *token1, void *token2, int prefixlen)
 	return 1;
 }
 
+static __inline__
+u16 xfrm_flowi_sport(struct flowi *fl)
+{
+	u16 port;
+	switch(fl->proto) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+		port = fl->fl_ip_sport;
+		break;
+	case IPPROTO_ICMP:
+	case IPPROTO_ICMPV6:
+		port = htons(fl->fl_icmp_type);
+		break;
+	default:
+		port = 0;	/*XXX*/
+	}
+	return port;
+}
+
+static __inline__
+u16 xfrm_flowi_dport(struct flowi *fl)
+{
+	u16 port;
+	switch(fl->proto) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+		port = fl->fl_ip_dport;
+		break;
+	case IPPROTO_ICMP:
+	case IPPROTO_ICMPV6:
+		port = htons(fl->fl_icmp_code);
+		break;
+	default:
+		port = 0;	/*XXX*/
+	}
+	return port;
+}
+
 static inline int
 __xfrm4_selector_match(struct xfrm_selector *sel, struct flowi *fl)
 {
 	return  addr_match(&fl->fl4_dst, &sel->daddr, sel->prefixlen_d) &&
 		addr_match(&fl->fl4_src, &sel->saddr, sel->prefixlen_s) &&
-		!((fl->fl_ip_dport^sel->dport)&sel->dport_mask) &&
-		!((fl->fl_ip_sport^sel->sport)&sel->sport_mask) &&
+		!((xfrm_flowi_dport(fl) ^ sel->dport) & sel->dport_mask) &&
+		!((xfrm_flowi_sport(fl) ^ sel->sport) & sel->sport_mask) &&
 		(fl->proto == sel->proto || !sel->proto) &&
 		(fl->oif == sel->ifindex || !sel->ifindex);
 }
@@ -437,8 +475,8 @@ __xfrm6_selector_match(struct xfrm_selector *sel, struct flowi *fl)
 {
 	return  addr_match(&fl->fl6_dst, &sel->daddr, sel->prefixlen_d) &&
 		addr_match(&fl->fl6_src, &sel->saddr, sel->prefixlen_s) &&
-		!((fl->fl_ip_dport^sel->dport)&sel->dport_mask) &&
-		!((fl->fl_ip_sport^sel->sport)&sel->sport_mask) &&
+		!((xfrm_flowi_dport(fl) ^ sel->dport) & sel->dport_mask) &&
+		!((xfrm_flowi_sport(fl) ^ sel->sport) & sel->sport_mask) &&
 		(fl->proto == sel->proto || !sel->proto) &&
 		(fl->oif == sel->ifindex || !sel->ifindex);
 }

net/ipv4/raw.c

@@ -323,6 +323,51 @@ static int raw_send_hdrinc(struct sock *sk, void *from, int length,
 	return err; 
 }
 
+static void raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
+{
+	struct iovec *iov;
+	u8 *type = NULL;
+	u8 *code = NULL;
+	int probed = 0;
+	int i;
+
+	if (!msg->msg_iov)
+		return;
+
+	for (i = 0; i < msg->msg_iovlen; i++) {
+		iov = &msg->msg_iov[i];
+		if (!iov)
+			continue;
+
+		switch (fl->proto) {
+		case IPPROTO_ICMP:
+			/* check if one-byte field is readable or not. */
+			if (iov->iov_base && iov->iov_len < 1)
+				break;
+
+			if (!type) {
+				type = iov->iov_base;
+				/* check if code field is readable or not. */
+				if (iov->iov_len > 1)
+					code = type + 1;
+			} else if (!code)
+				code = iov->iov_base;
+
+			if (type && code) {
+				fl->fl_icmp_type = *type;
+				fl->fl_icmp_code = *code;
+				probed = 1;
+			}
+			break;
+		default:
+			probed = 1;
+			break;
+		}
+		if (probed)
+			break;
+	}
+}
+
 static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		       size_t len)
 {
@@ -429,6 +474,9 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 				    .proto = inet->hdrincl ? IPPROTO_RAW :
 					    		     sk->sk_protocol,
 				  };
+		if (!inet->hdrincl)
+			raw_probe_proto_opt(&fl, msg);
+
 		err = ip_route_output_flow(&rt, &fl, sk, !(msg->msg_flags&MSG_DONTWAIT));
 	}
 	if (err)

net/ipv4/xfrm4_policy.c

@@ -183,6 +183,15 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl)
 			}
 			break;
 
+		case IPPROTO_ICMP:
+			if (pskb_may_pull(skb, xprth + 2 - skb->data)) {
+				u8 *icmp = xprth;
+
+				fl->fl_icmp_type = icmp[0];
+				fl->fl_icmp_code = icmp[1];
+			}
+			break;
+
 		case IPPROTO_ESP:
 			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				u32 *ehdr = (u32 *)xprth;

net/ipv6/raw.c

@@ -555,6 +555,52 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
 	IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
 	return err; 
 }
+
+static void rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
+{
+	struct iovec *iov;
+	u8 *type = NULL;
+	u8 *code = NULL;
+	int probed = 0;
+	int i;
+
+	if (!msg->msg_iov)
+		return;
+
+	for (i = 0; i < msg->msg_iovlen; i++) {
+		iov = &msg->msg_iov[i];
+		if (!iov)
+			continue;
+
+		switch (fl->proto) {
+		case IPPROTO_ICMPV6:
+			/* check if one-byte field is readable or not. */
+			if (iov->iov_base && iov->iov_len < 1)
+				break;
+
+			if (!type) {
+				type = iov->iov_base;
+				/* check if code field is readable or not. */
+				if (iov->iov_len > 1)
+					code = type + 1;
+			} else if (!code)
+				code = iov->iov_base;
+
+			if (type && code) {
+				fl->fl_icmp_type = *type;
+				fl->fl_icmp_code = *code;
+				probed = 1;
+			}
+			break;
+		default:
+			probed = 1;
+			break;
+		}
+		if (probed)
+			break;
+	}
+}
+
 static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		   struct msghdr *msg, size_t len)
 {
@@ -674,6 +720,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 
 	fl.proto = proto;
+	rawv6_probe_proto_opt(&fl, msg);
+ 
 	ipv6_addr_copy(&fl.fl6_dst, daddr);
 	if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr))
 		ipv6_addr_copy(&fl.fl6_src, &np->saddr);

net/ipv6/xfrm6_policy.c

@@ -213,6 +213,16 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl)
 			fl->proto = nexthdr;
 			return;
 
+		case IPPROTO_ICMPV6:
+			if (pskb_may_pull(skb, skb->nh.raw + offset + 2 - skb->data)) {
+				u8 *icmp = (u8 *)exthdr;
+
+				fl->fl_icmp_type = icmp[0];
+				fl->fl_icmp_code = icmp[1];
+			}
+			fl->proto = nexthdr;
+			return;
+
 		/* XXX Why are there these headers? */
 		case IPPROTO_AH:
 		case IPPROTO_ESP: