ipv4: Avoid using RTO_ONLINK with ip_route_connect().

Now that ip_rt_fix_tos() doesn't reset ->flowi4_scope unconditionally,
we don't have to rely on the RTO_ONLINK bit to properly set the scope
of a flowi4 structure. We can just set ->flowi4_scope explicitly and
avoid using RTO_ONLINK in ->flowi4_tos.

This patch converts callers of ip_route_connect(). Instead of setting
the tos parameter with RT_CONN_FLAGS(sk), as all callers do, we can:

  1- Drop the tos parameter from ip_route_connect(): its value was
     entirely based on sk, which is also passed as parameter.

  2- Set ->flowi4_scope depending on the SOCK_LOCALROUTE socket option
     instead of always initialising it with RT_SCOPE_UNIVERSE (let's
     define ip_sock_rt_scope() for this purpose).

  3- Avoid overloading ->flowi4_tos with RTO_ONLINK: since the scope is
     now properly initialised, we don't need to tell ip_rt_fix_tos() to
     adjust ->flowi4_scope for us. So let's define ip_sock_rt_tos(),
     which is the same as RT_CONN_FLAGS() but without the RTO_ONLINK
     bit overload.

Note:
  In the original ip_route_connect() code, __ip_route_output_key()
  might clear the RTO_ONLINK bit of fl4->flowi4_tos (because of
  ip_rt_fix_tos()). Therefore flowi4_update_output() had to reuse the
  original tos variable. Now that we don't set RTO_ONLINK any more,
  this is not a problem and we can use fl4->flowi4_tos in
  flowi4_update_output().

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 34 insertions, 25 deletions

diff --git a/include/net/route.h b/include/net/route.h
index 25404fc2b483..991a3985712d 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -43,6 +43,19 @@
 #define RT_CONN_FLAGS(sk)   (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
 #define RT_CONN_FLAGS_TOS(sk,tos)   (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE))
 
+static inline __u8 ip_sock_rt_scope(const struct sock *sk)
+{
+	if (sock_flag(sk, SOCK_LOCALROUTE))
+		return RT_SCOPE_LINK;
+
+	return RT_SCOPE_UNIVERSE;
+}
+
+static inline __u8 ip_sock_rt_tos(const struct sock *sk)
+{
+	return RT_TOS(inet_sk(sk)->tos);
+}
+
 struct ip_tunnel_info;
 struct fib_nh;
 struct fib_info;
@@ -289,39 +302,38 @@ static inline char rt_tos2priority(u8 tos)
  * ip_route_newports() calls.
  */
 
-static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 src,
-					 u32 tos, int oif, u8 protocol,
+static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst,
+					 __be32 src, int oif, u8 protocol,
 					 __be16 sport, __be16 dport,
-					 struct sock *sk)
+					 const struct sock *sk)
 {
 	__u8 flow_flags = 0;
 
 	if (inet_sk(sk)->transparent)
 		flow_flags |= FLOWI_FLAG_ANYSRC;
 
-	flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
-			   protocol, flow_flags, dst, src, dport, sport,
-			   sk->sk_uid);
+	flowi4_init_output(fl4, oif, sk->sk_mark, ip_sock_rt_tos(sk),
+			   ip_sock_rt_scope(sk), protocol, flow_flags, dst,
+			   src, dport, sport, sk->sk_uid);
 }
 
-static inline struct rtable *ip_route_connect(struct flowi4 *fl4,
-					      __be32 dst, __be32 src, u32 tos,
-					      int oif, u8 protocol,
+static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst,
+					      __be32 src, int oif, u8 protocol,
 					      __be16 sport, __be16 dport,
 					      struct sock *sk)
 {
 	struct net *net = sock_net(sk);
 	struct rtable *rt;
 
-	ip_route_connect_init(fl4, dst, src, tos, oif, protocol,
-			      sport, dport, sk);
+	ip_route_connect_init(fl4, dst, src, oif, protocol, sport, dport, sk);
 
 	if (!dst || !src) {
 		rt = __ip_route_output_key(net, fl4);
 		if (IS_ERR(rt))
 			return rt;
 		ip_rt_put(rt);
-		flowi4_update_output(fl4, oif, tos, fl4->daddr, fl4->saddr);
+		flowi4_update_output(fl4, oif, fl4->flowi4_tos, fl4->daddr,
+				     fl4->saddr);
 	}
 	security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
 	return ip_route_output_flow(net, fl4, sk);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index ae662567a6cb..82696ab86f74 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -76,9 +76,8 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	orig_dport = usin->sin_port;
 	fl4 = &inet->cork.fl.u.ip4;
 	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);
+			      sk->sk_bound_dev_if, IPPROTO_DCCP, orig_sport,
+			      orig_dport, sk);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 195ecfa2f000..93da9f783bec 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1233,9 +1233,9 @@ static int inet_sk_reselect_saddr(struct sock *sk)
 
 	/* Query new route. */
 	fl4 = &inet->cork.fl.u.ip4;
-	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);
+	rt = ip_route_connect(fl4, daddr, 0, sk->sk_bound_dev_if,
+			      sk->sk_protocol, inet->inet_sport,
+			      inet->inet_dport, sk);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 48f337ccf949..ffd57523331f 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -44,10 +44,9 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
 			saddr = inet->mc_addr;
 	}
 	fl4 = &inet->cork.fl.u.ip4;
-	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);
+	rt = ip_route_connect(fl4, usin->sin_addr.s_addr, saddr, oif,
+			      sk->sk_protocol, inet->inet_sport,
+			      usin->sin_port, sk);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
 		if (err == -ENETUNREACH)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 157265aecbed..2c2d42142555 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -229,9 +229,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	orig_dport = usin->sin_port;
 	fl4 = &inet->cork.fl.u.ip4;
 	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);
+			      sk->sk_bound_dev_if, IPPROTO_TCP, orig_sport,
+			      orig_dport, sk);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
 		if (err == -ENETUNREACH)