[IPV4/6]: Check if packet was actually delivered to a raw socket to decide whether to send an ICMP unreachable

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/raw.h

@@ -37,6 +37,6 @@ extern struct sock *__raw_v4_lookup(struct sock *sk, unsigned short num,
 				    unsigned long raddr, unsigned long laddr,
 				    int dif);
 
-extern void raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash);
+extern int raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash);
 
 #endif	/* _RAW_H */

include/net/rawv6.h

@@ -7,7 +7,7 @@
 extern struct hlist_head raw_v6_htable[RAWV6_HTABLE_SIZE];
 extern rwlock_t raw_v6_lock;
 
-extern void ipv6_raw_deliver(struct sk_buff *skb, int nexthdr);
+extern int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr);
 
 extern struct sock *__raw_v6_lookup(struct sock *sk, unsigned short num,
 				    struct in6_addr *loc_addr, struct in6_addr *rmt_addr,

net/ipv4/ip_input.c

@@ -225,8 +225,8 @@ static inline int ip_local_deliver_finish(struct sk_buff *skb)
 		/* If there maybe a raw socket we must check - if not we
 		 * don't care less
 		 */
-		if (raw_sk)
-			raw_v4_input(skb, skb->nh.iph, hash);
+		if (raw_sk && !raw_v4_input(skb, skb->nh.iph, hash))
+			raw_sk = NULL;
 
 		if ((ipprot = rcu_dereference(inet_protos[hash])) != NULL) {
 			int ret;

net/ipv4/raw.c

@@ -150,10 +150,11 @@ static __inline__ int icmp_filter(struct sock *sk, struct sk_buff *skb)
  * RFC 1122: SHOULD pass TOS value up to the transport layer.
  * -> It does. And not only TOS, but all IP header.
  */
-void raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash)
+int raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash)
 {
 	struct sock *sk;
 	struct hlist_head *head;
+	int delivered = 0;
 
 	read_lock(&raw_v4_lock);
 	head = &raw_v4_htable[hash];
@@ -164,6 +165,7 @@ void raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash)
 			     skb->dev->ifindex);
 
 	while (sk) {
+		delivered = 1;
 		if (iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) {
 			struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);
 
@@ -177,6 +179,7 @@ void raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash)
 	}
 out:
 	read_unlock(&raw_v4_lock);
+	return delivered;
 }
 
 void raw_err (struct sock *sk, struct sk_buff *skb, u32 info)

net/ipv6/ip6_input.c

@@ -166,8 +166,8 @@ resubmit:
 	nexthdr = skb->nh.raw[nhoff];
 
 	raw_sk = sk_head(&raw_v6_htable[nexthdr & (MAX_INET_PROTOS - 1)]);
-	if (raw_sk)
-		ipv6_raw_deliver(skb, nexthdr);
+	if (raw_sk && !ipv6_raw_deliver(skb, nexthdr))
+		raw_sk = NULL;
 
 	hash = nexthdr & (MAX_INET_PROTOS - 1);
 	if ((ipprot = rcu_dereference(inet6_protos[hash])) != NULL) {

net/ipv6/raw.c

@@ -141,11 +141,12 @@ static __inline__ int icmpv6_filter(struct sock *sk, struct sk_buff *skb)
  *
  *	Caller owns SKB so we must make clones.
  */
-void ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
+int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
 {
 	struct in6_addr *saddr;
 	struct in6_addr *daddr;
 	struct sock *sk;
+	int delivered = 0;
 	__u8 hash;
 
 	saddr = &skb->nh.ipv6h->saddr;
@@ -167,6 +168,7 @@ void ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
 	sk = __raw_v6_lookup(sk, nexthdr, daddr, saddr, skb->dev->ifindex);
 
 	while (sk) {
+		delivered = 1;
 		if (nexthdr != IPPROTO_ICMPV6 || !icmpv6_filter(sk, skb)) {
 			struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);
 
@@ -179,6 +181,7 @@ void ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
 	}
 out:
 	read_unlock(&raw_v6_lock);
+	return delivered;
 }
 
 /* This cleans up af_inet6 a bit. -DaveM */