ipv4: Sanitize and simplify ip_route_{connect,newports}()

These functions are used together as a unit for route resolution
during connect().  They address the chicken-and-egg problem that
exists when ports need to be allocated during connect() processing,
yet such port allocations require addressing information from the
routing code.

It's currently more heavy handed than it needs to be, and in
particular we allocate and initialize a flow object twice.

Let the callers provide the on-stack flow object.  That way we only
need to initialize it once in the ip_route_connect() call.

Later, if ip_route_newports() needs to do anything, it re-uses that
flow object as-is except for the ports which it updates before the
route re-lookup.

Also, describe why this set of facilities are needed and how it works
in a big comment.

Signed-off-by: David S. Miller <davem@davemloft.net>
Reviewed-by: Eric Dumazet <eric.dumazet@gmail.com>

5 files changed, 18 insertions, 16 deletions

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index ae451c6d83ba..b92ab655d44e 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -40,12 +40,13 @@
 
 int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
+	const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
 	struct inet_sock *inet = inet_sk(sk);
 	struct dccp_sock *dp = dccp_sk(sk);
-	const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
 	__be16 orig_sport, orig_dport;
-	struct rtable *rt;
 	__be32 daddr, nexthop;
+	struct flowi4 fl4;
+	struct rtable *rt;
 	int err;
 
 	dp->dccps_role = DCCP_ROLE_CLIENT;
@@ -65,7 +66,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	orig_sport = inet->inet_sport;
 	orig_dport = usin->sin_port;
-	rt = ip_route_connect(nexthop, inet->inet_saddr,
+	rt = ip_route_connect(&fl4, nexthop, inet->inet_saddr,
 			      RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
 			      IPPROTO_DCCP,
 			      orig_sport, orig_dport, sk, true);
@@ -101,8 +102,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (err != 0)
 		goto failure;
 
-	rt = ip_route_newports(rt, IPPROTO_DCCP,
-			       orig_sport, orig_dport,
+	rt = ip_route_newports(&fl4, rt, orig_sport, orig_dport,
 			       inet->inet_sport, inet->inet_dport, sk);
 	if (IS_ERR(rt)) {
 		rt = NULL;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index cae75ef21fea..0413af3e2285 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1103,6 +1103,7 @@ static int inet_sk_reselect_saddr(struct sock *sk)
 	struct inet_sock *inet = inet_sk(sk);
 	__be32 old_saddr = inet->inet_saddr;
 	__be32 daddr = inet->inet_daddr;
+	struct flowi4 fl4;
 	struct rtable *rt;
 	__be32 new_saddr;
 
@@ -1110,7 +1111,7 @@ static int inet_sk_reselect_saddr(struct sock *sk)
 		daddr = inet->opt->faddr;
 
 	/* Query new route. */
-	rt = ip_route_connect(daddr, 0, RT_CONN_FLAGS(sk),
+	rt = ip_route_connect(&fl4, daddr, 0, RT_CONN_FLAGS(sk),
 			      sk->sk_bound_dev_if, sk->sk_protocol,
 			      inet->inet_sport, inet->inet_dport, sk, false);
 	if (IS_ERR(rt))
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 85bd24ca4f6d..216ba2338b64 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -24,6 +24,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct sockaddr_in *usin = (struct sockaddr_in *) uaddr;
+	struct flowi4 fl4;
 	struct rtable *rt;
 	__be32 saddr;
 	int oif;
@@ -46,7 +47,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		if (!saddr)
 			saddr = inet->mc_addr;
 	}
-	rt = ip_route_connect(usin->sin_addr.s_addr, saddr,
+	rt = ip_route_connect(&fl4, usin->sin_addr.s_addr, saddr,
 			      RT_CONN_FLAGS(sk), oif,
 			      sk->sk_protocol,
 			      inet->inet_sport, usin->sin_port, sk, true);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index edf18bd74b87..310454c2f4d1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -146,12 +146,13 @@ EXPORT_SYMBOL_GPL(tcp_twsk_unique);
 /* This will initiate an outgoing connection. */
 int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
+	struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
 	struct inet_sock *inet = inet_sk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
 	__be16 orig_sport, orig_dport;
-	struct rtable *rt;
 	__be32 daddr, nexthop;
+	struct flowi4 fl4;
+	struct rtable *rt;
 	int err;
 
 	if (addr_len < sizeof(struct sockaddr_in))
@@ -169,7 +170,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	orig_sport = inet->inet_sport;
 	orig_dport = usin->sin_port;
-	rt = ip_route_connect(nexthop, inet->inet_saddr,
+	rt = ip_route_connect(&fl4, nexthop, inet->inet_saddr,
 			      RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
 			      IPPROTO_TCP,
 			      orig_sport, orig_dport, sk, true);
@@ -236,8 +237,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (err)
 		goto failure;
 
-	rt = ip_route_newports(rt, IPPROTO_TCP,
-			       orig_sport, orig_dport,
+	rt = ip_route_newports(&fl4, rt, orig_sport, orig_dport,
 			       inet->inet_sport, inet->inet_dport, sk);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index fce9bd3bd3fe..cc673677c5de 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -296,12 +296,12 @@ out_in_use:
 
 static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
-	int rc;
-	struct inet_sock *inet = inet_sk(sk);
 	struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *) uaddr;
+	struct inet_sock *inet = inet_sk(sk);
+	struct flowi4 fl4;
 	struct rtable *rt;
 	__be32 saddr;
-	int oif;
+	int oif, rc;
 
 	rc = -EINVAL;
 	if (addr_len < sizeof(*lsa))
@@ -320,7 +320,7 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
 	if (ipv4_is_multicast(lsa->l2tp_addr.s_addr))
 		goto out;
 
-	rt = ip_route_connect(lsa->l2tp_addr.s_addr, saddr,
+	rt = ip_route_connect(&fl4, lsa->l2tp_addr.s_addr, saddr,
 			      RT_CONN_FLAGS(sk), oif,
 			      IPPROTO_L2TP,
 			      0, 0, sk, true);