Merge branch 'ipv6-RT_ONLINK-remove-prep'

Guillaume Nault says:

====================
ipv4: First steps toward removing RTO_ONLINK

RTO_ONLINK is a flag that allows to reduce the scope of route lookups.
It's stored in a normally unused bit of the ->flowi4_tos field, in
struct flowi4. However it has several problems:

 * This bit is also used by ECN. Although ECN bits are supposed to be
   cleared before doing a route lookup, it happened that some code
   paths didn't properly sanitise their ->flowi4_tos. So this mechanism
   is fragile and we had bugs in the past where ECN bits slipped in and
   could end up being erroneously interpreted as RTO_ONLINK.

 * A dscp_t type was recently introduced to ensure ECN bits are cleared
   during route lookups. ->flowi4_tos is the most important structure
   field to convert, but RTO_ONLINK prevents such conversion, as dscp_t
   mandates that ECN bits (where RTO_ONLINK is stored) be zero.

Therefore we need to stop using RTO_ONLINK altogether. Fortunately
RTO_ONLINK isn't a necessity. Instead of passing a flag in ->flowi4_tos
to tell the route lookup function to restrict the scope, we can simply
initialise the scope correctly.

Patch 1 does some preparatory work: it stops resetting ->flowi4_scope
automatically before a route lookup, thus allowing callers to set their
desired scope without having to rely on the RTO_ONLINK flag.

Patch 2-3 convert a few code paths to avoid relying on RTO_ONLINK.

More conversions will have to take place before we can eventually
remove this flag.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 24 insertions, 12 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);