[IPV6]: Audit all ip6_dst_lookup/ip6_dst_store calls

The current users of ip6_dst_lookup can be divided into two classes:

1) The caller holds no locks and is in user-context (UDP).
2) The caller does not want to lookup the dst cache at all.

The second class covers everyone except UDP because most people do
the cache lookup directly before calling ip6_dst_lookup.  This patch
adds ip6_sk_dst_lookup for the first class.

Similarly ip6_dst_store users can be divded into those that need to
take the socket dst lock and those that don't.  This patch adds
__ip6_dst_store for those (everyone except UDP/datagram) that don't
need an extra lock.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/ip6_route.h

@@ -139,16 +139,22 @@ extern rwlock_t rt6_lock;
 /*
  *	Store a destination cache entry in a socket
  */
-static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst,
+static inline void __ip6_dst_store(struct sock *sk, struct dst_entry *dst,
 				   struct in6_addr *daddr)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct rt6_info *rt = (struct rt6_info *) dst;
 
-	write_lock(&sk->sk_dst_lock);
 	sk_setup_caps(sk, dst);
 	np->daddr_cache = daddr;
 	np->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
+}
+
+static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst,
+				 struct in6_addr *daddr)
+{
+	write_lock(&sk->sk_dst_lock);
+	__ip6_dst_store(sk, dst, daddr);
 	write_unlock(&sk->sk_dst_lock);
 }
 

include/net/ipv6.h

@@ -468,6 +468,9 @@ extern void			ip6_flush_pending_frames(struct sock *sk);
 extern int			ip6_dst_lookup(struct sock *sk,
 					       struct dst_entry **dst,
 					       struct flowi *fl);
+extern int			ip6_sk_dst_lookup(struct sock *sk,
+						  struct dst_entry **dst,
+						  struct flowi *fl);
 
 /*
  *	skb processing functions

net/dccp/ipv6.c

@@ -230,7 +230,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	ipv6_addr_copy(&np->saddr, saddr);
 	inet->rcv_saddr = LOOPBACK4_IPV6;
 
-	ip6_dst_store(sk, dst, NULL);
+	__ip6_dst_store(sk, dst, NULL);
 
 	icsk->icsk_ext_hdr_len = 0;
 	if (np->opt != NULL)
@@ -863,7 +863,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 	 * comment in that function for the gory details. -acme
 	 */
 
-	ip6_dst_store(newsk, dst, NULL);
+	__ip6_dst_store(newsk, dst, NULL);
 	newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM |
 						      NETIF_F_TSO);
 	newdp6 = (struct dccp6_sock *)newsk;

net/ipv6/af_inet6.c

@@ -658,7 +658,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
 			return err;
 		}
 
-		ip6_dst_store(sk, dst, NULL);
+		__ip6_dst_store(sk, dst, NULL);
 	}
 
 	return 0;

net/ipv6/inet6_connection_sock.c

@@ -185,7 +185,7 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok)
 			return err;
 		}
 
-		ip6_dst_store(sk, dst, NULL);
+		__ip6_dst_store(sk, dst, NULL);
 	}
 
 	skb->dst = dst_clone(dst);

net/ipv6/ip6_output.c

@@ -723,17 +723,15 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	return err;
 }
 
-int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl)
+static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
+					  struct dst_entry *dst,
+					  struct flowi *fl)
 {
-	int err = 0;
-
-	*dst = NULL;
-	if (sk) {
 	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct rt6_info *rt = (struct rt6_info *)dst;
 
-		*dst = sk_dst_check(sk, np->dst_cookie);
-		if (*dst) {
-			struct rt6_info *rt = (struct rt6_info*)*dst;
+	if (!dst)
+		goto out;
 
 	/* Yes, checking route validity in not connected
 	 * case is not very simple. Take into account,
@@ -753,18 +751,23 @@ int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl)
 	 * 2. oif also should be the same.
 	 */
 	if (((rt->rt6i_dst.plen != 128 ||
-			      !ipv6_addr_equal(&fl->fl6_dst,
-					       &rt->rt6i_dst.addr))
+	      !ipv6_addr_equal(&fl->fl6_dst, &rt->rt6i_dst.addr))
 	     && (np->daddr_cache == NULL ||
-				 !ipv6_addr_equal(&fl->fl6_dst,
-						  np->daddr_cache)))
-			    || (fl->oif && fl->oif != (*dst)->dev->ifindex)) {
-				dst_release(*dst);
-				*dst = NULL;
-			}
-		}
+		 !ipv6_addr_equal(&fl->fl6_dst, np->daddr_cache)))
+	    || (fl->oif && fl->oif != dst->dev->ifindex)) {
+		dst_release(dst);
+		dst = NULL;
 	}
 
+out:
+	return dst;
+}
+
+static int ip6_dst_lookup_tail(struct sock *sk,
+			       struct dst_entry **dst, struct flowi *fl)
+{
+	int err;
+
 	if (*dst == NULL)
 		*dst = ip6_route_output(sk, fl);
 
@@ -773,7 +776,6 @@ int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl)
 
 	if (ipv6_addr_any(&fl->fl6_src)) {
 		err = ipv6_get_saddr(*dst, &fl->fl6_dst, &fl->fl6_src);
-
 		if (err)
 			goto out_err_release;
 	}
@@ -786,8 +788,48 @@ int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl)
 	return err;
 }
 
+/**
+ *	ip6_dst_lookup - perform route lookup on flow
+ *	@sk: socket which provides route info
+ *	@dst: pointer to dst_entry * for result
+ *	@fl: flow to lookup
+ *
+ *	This function performs a route lookup on the given flow.
+ *
+ *	It returns zero on success, or a standard errno code on error.
+ */
+int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl)
+{
+	*dst = NULL;
+	return ip6_dst_lookup_tail(sk, dst, fl);
+}
 EXPORT_SYMBOL_GPL(ip6_dst_lookup);
 
+/**
+ *	ip6_sk_dst_lookup - perform socket cached route lookup on flow
+ *	@sk: socket which provides the dst cache and route info
+ *	@dst: pointer to dst_entry * for result
+ *	@fl: flow to lookup
+ *
+ *	This function performs a route lookup on the given flow with the
+ *	possibility of using the cached route in the socket if it is valid.
+ *	It will take the socket dst lock when operating on the dst cache.
+ *	As a result, this function can only be used in process context.
+ *
+ *	It returns zero on success, or a standard errno code on error.
+ */
+int ip6_sk_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl)
+{
+	*dst = NULL;
+	if (sk) {
+		*dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
+		*dst = ip6_sk_dst_check(sk, *dst, fl);
+	}
+
+	return ip6_dst_lookup_tail(sk, dst, fl);
+}
+EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup);
+
 static inline int ip6_ufo_append_data(struct sock *sk,
 			int getfrag(void *from, char *to, int offset, int len,
 			int odd, struct sk_buff *skb),

net/ipv6/tcp_ipv6.c

@@ -270,7 +270,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	inet->rcv_saddr = LOOPBACK4_IPV6;
 
 	sk->sk_gso_type = SKB_GSO_TCPV6;
-	ip6_dst_store(sk, dst, NULL);
+	__ip6_dst_store(sk, dst, NULL);
 
 	icsk->icsk_ext_hdr_len = 0;
 	if (np->opt)
@@ -947,7 +947,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	 */
 
 	sk->sk_gso_type = SKB_GSO_TCPV6;
-	ip6_dst_store(newsk, dst, NULL);
+	__ip6_dst_store(newsk, dst, NULL);
 
 	newtcp6sk = (struct tcp6_sock *)newsk;
 	inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;

net/ipv6/udp.c

@@ -782,7 +782,7 @@ static int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		connected = 0;
 	}
 
-	err = ip6_dst_lookup(sk, &dst, fl);
+	err = ip6_sk_dst_lookup(sk, &dst, fl);
 	if (err)
 		goto out;
 	if (final_p)