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>

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);

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);
 

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);
 

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)

net/ipv4/route.c

@@ -503,28 +503,29 @@ static void ip_rt_fix_tos(struct flowi4 *fl4)
 	__u8 tos = RT_FL_TOS(fl4);
 
 	fl4->flowi4_tos = tos & IPTOS_RT_MASK;
-	fl4->flowi4_scope = tos & RTO_ONLINK ?
-			    RT_SCOPE_LINK : RT_SCOPE_UNIVERSE;
+	if (tos & RTO_ONLINK)
+		fl4->flowi4_scope = RT_SCOPE_LINK;
 }
 
 static void __build_flow_key(const struct net *net, struct flowi4 *fl4,
-			     const struct sock *sk,
-			     const struct iphdr *iph,
-			     int oif, u8 tos,
-			     u8 prot, u32 mark, int flow_flags)
+			     const struct sock *sk, const struct iphdr *iph,
+			     int oif, __u8 tos, u8 prot, u32 mark,
+			     int flow_flags)
 {
+	__u8 scope = RT_SCOPE_UNIVERSE;
+
 	if (sk) {
 		const struct inet_sock *inet = inet_sk(sk);
 
 		oif = sk->sk_bound_dev_if;
 		mark = sk->sk_mark;
-		tos = RT_CONN_FLAGS(sk);
+		tos = ip_sock_rt_tos(sk);
+		scope = ip_sock_rt_scope(sk);
 		prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol;
 	}
-	flowi4_init_output(fl4, oif, mark, tos,
-			   RT_SCOPE_UNIVERSE, prot,
-			   flow_flags,
-			   iph->daddr, iph->saddr, 0, 0,
+
+	flowi4_init_output(fl4, oif, mark, tos & IPTOS_RT_MASK, scope,
+			   prot, flow_flags, iph->daddr, iph->saddr, 0, 0,
 			   sock_net_uid(net, sk));
 }
 
@@ -534,9 +535,9 @@ static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
 	const struct net *net = dev_net(skb->dev);
 	const struct iphdr *iph = ip_hdr(skb);
 	int oif = skb->dev->ifindex;
-	u8 tos = RT_TOS(iph->tos);
 	u8 prot = iph->protocol;
 	u32 mark = skb->mark;
+	__u8 tos = iph->tos;
 
 	__build_flow_key(net, fl4, sk, iph, oif, tos, prot, mark, 0);
 }
@@ -552,7 +553,8 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
 	if (inet_opt && inet_opt->opt.srr)
 		daddr = inet_opt->opt.faddr;
 	flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
-			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
+			   ip_sock_rt_tos(sk) & IPTOS_RT_MASK,
+			   ip_sock_rt_scope(sk),
 			   inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk),
 			   daddr, inet->inet_saddr, 0, 0, sk->sk_uid);
@@ -825,14 +827,13 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
 	const struct iphdr *iph = (const struct iphdr *) skb->data;
 	struct net *net = dev_net(skb->dev);
 	int oif = skb->dev->ifindex;
-	u8 tos = RT_TOS(iph->tos);
 	u8 prot = iph->protocol;
 	u32 mark = skb->mark;
+	__u8 tos = iph->tos;
 
 	rt = (struct rtable *) dst;
 
 	__build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0);
-	ip_rt_fix_tos(&fl4);
 	__ip_do_redirect(rt, skb, &fl4, true);
 }
 
@@ -1061,7 +1062,6 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 	struct flowi4 fl4;
 
 	ip_rt_build_flow_key(&fl4, sk, skb);
-	ip_rt_fix_tos(&fl4);
 
 	/* Don't make lookup fail for bridged encapsulations */
 	if (skb && netif_is_any_bridge_port(skb->dev))
@@ -1078,8 +1078,8 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
 	struct rtable *rt;
 	u32 mark = IP4_REPLY_MARK(net, skb->mark);
 
-	__build_flow_key(net, &fl4, NULL, iph, oif,
-			 RT_TOS(iph->tos), protocol, mark, 0);
+	__build_flow_key(net, &fl4, NULL, iph, oif, iph->tos, protocol, mark,
+			 0);
 	rt = __ip_route_output_key(net, &fl4);
 	if (!IS_ERR(rt)) {
 		__ip_rt_update_pmtu(rt, &fl4, mtu);
@@ -1136,8 +1136,6 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 			goto out;
 
 		new = true;
-	} else {
-		ip_rt_fix_tos(&fl4);
 	}
 
 	__ip_rt_update_pmtu((struct rtable *)xfrm_dst_path(&rt->dst), &fl4, mtu);
@@ -1169,8 +1167,7 @@ void ipv4_redirect(struct sk_buff *skb, struct net *net,
 	struct flowi4 fl4;
 	struct rtable *rt;
 
-	__build_flow_key(net, &fl4, NULL, iph, oif,
-			 RT_TOS(iph->tos), protocol, 0, 0);
+	__build_flow_key(net, &fl4, NULL, iph, oif, iph->tos, protocol, 0, 0);
 	rt = __ip_route_output_key(net, &fl4);
 	if (!IS_ERR(rt)) {
 		__ip_do_redirect(rt, skb, &fl4, false);

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)