Merge branch 'RTO_ONLINK'

Guillaume Nault says:

====================
ipv4: Remove RTO_ONLINK from udp, ping and raw sockets.

udp_sendmsg(), ping_v4_sendmsg() and raw_sendmsg() use similar patterns
for restricting their route lookup to on-link hosts. Although they use
slightly different code, they all use RTO_ONLINK to override the least
significant bit of their tos value.

RTO_ONLINK is used to restrict the route scope even when the scope is
set to RT_SCOPE_UNIVERSE. Therefore it isn't necessary: we can properly
set the scope to RT_SCOPE_LINK instead.

Removing RTO_ONLINK will allow to convert .flowi4_tos to dscp_t in the
future, thus allowing to properly separate the DSCP from the ECN bits
in the networking stack.

This patch series defines a common helper to figure out what's the
scope of the route lookup. This unifies the way udp, ping and raw
sockets get their routing scope and removes their dependency on
RTO_ONLINK.
====================

Signed-off-by: David S. Miller <[email protected]>

4 files changed, 27 insertions, 31 deletions

diff --git a/include/net/ip.h b/include/net/ip.h
index 7627a4df893b..8a3860a916dc 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -240,14 +240,22 @@ static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
 	return __ip_make_skb(sk, fl4, &sk->sk_write_queue, &inet_sk(sk)->cork.base);
 }
 
-static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet)
+/* Get the route scope that should be used when sending a packet. */
+static inline u8 ip_sendmsg_scope(const struct inet_sock *inet,
+				  const struct ipcm_cookie *ipc,
+				  const struct msghdr *msg)
 {
-	return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(inet->tos);
+	if (sock_flag(&inet->sk, SOCK_LOCALROUTE) ||
+	    msg->msg_flags & MSG_DONTROUTE ||
+	    (ipc->opt && ipc->opt->opt.is_strictroute))
+		return RT_SCOPE_LINK;
+
+	return RT_SCOPE_UNIVERSE;
 }
 
-static inline __u8 get_rtconn_flags(struct ipcm_cookie* ipc, struct sock* sk)
+static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet)
 {
-	return (ipc->tos != -1) ? RT_CONN_FLAGS_TOS(sk, ipc->tos) : RT_CONN_FLAGS(sk);
+	return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(inet->tos);
 }
 
 /* datagram.c */
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 3793c81bda8a..25dd78cee179 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -705,7 +705,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	struct ip_options_data opt_copy;
 	int free = 0;
 	__be32 saddr, daddr, faddr;
-	u8  tos;
+	u8 tos, scope;
 	int err;
 
 	pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
@@ -769,11 +769,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		faddr = ipc.opt->opt.faddr;
 	}
 	tos = get_rttos(&ipc, inet);
-	if (sock_flag(sk, SOCK_LOCALROUTE) ||
-	    (msg->msg_flags & MSG_DONTROUTE) ||
-	    (ipc.opt && ipc.opt->opt.is_strictroute)) {
-		tos |= RTO_ONLINK;
-	}
+	scope = ip_sendmsg_scope(inet, &ipc, msg);
 
 	if (ipv4_is_multicast(daddr)) {
 		if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
@@ -783,10 +779,9 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	} else if (!ipc.oif)
 		ipc.oif = inet->uc_index;
 
-	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos,
-			   RT_SCOPE_UNIVERSE, sk->sk_protocol,
-			   inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
-			   sk->sk_uid);
+	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope,
+			   sk->sk_protocol, inet_sk_flowi_flags(sk), faddr,
+			   saddr, 0, 0, sk->sk_uid);
 
 	fl4.fl4_icmp_type = user_icmph.type;
 	fl4.fl4_icmp_code = user_icmph.code;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index ff712bf2a98d..8b7b5c842bdd 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -476,10 +476,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	struct ipcm_cookie ipc;
 	struct rtable *rt = NULL;
 	struct flowi4 fl4;
+	u8 tos, scope;
 	int free = 0;
 	__be32 daddr;
 	__be32 saddr;
-	u8  tos;
 	int err;
 	struct ip_options_data opt_copy;
 	struct raw_frag_vec rfv;
@@ -572,9 +572,8 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			daddr = ipc.opt->opt.faddr;
 		}
 	}
-	tos = get_rtconn_flags(&ipc, sk);
-	if (msg->msg_flags & MSG_DONTROUTE)
-		tos |= RTO_ONLINK;
+	tos = get_rttos(&ipc, inet);
+	scope = ip_sendmsg_scope(inet, &ipc, msg);
 
 	if (ipv4_is_multicast(daddr)) {
 		if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
@@ -597,8 +596,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		}
 	}
 
-	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos,
-			   RT_SCOPE_UNIVERSE,
+	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope,
 			   hdrincl ? IPPROTO_RAW : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk) |
 			    (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 2879dc6d66ea..e992dd5392e3 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1062,8 +1062,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	int free = 0;
 	int connected = 0;
 	__be32 daddr, faddr, saddr;
+	u8 tos, scope;
 	__be16 dport;
-	u8  tos;
 	int err, is_udplite = IS_UDPLITE(sk);
 	int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE;
 	int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
@@ -1183,12 +1183,9 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		connected = 0;
 	}
 	tos = get_rttos(&ipc, inet);
-	if (sock_flag(sk, SOCK_LOCALROUTE) ||
-	    (msg->msg_flags & MSG_DONTROUTE) ||
-	    (ipc.opt && ipc.opt->opt.is_strictroute)) {
-		tos |= RTO_ONLINK;
+	scope = ip_sendmsg_scope(inet, &ipc, msg);
+	if (scope == RT_SCOPE_LINK)
 		connected = 0;
-	}
 
 	if (ipv4_is_multicast(daddr)) {
 		if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
@@ -1221,11 +1218,9 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 		fl4 = &fl4_stack;
 
-		flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos,
-				   RT_SCOPE_UNIVERSE, sk->sk_protocol,
-				   flow_flags,
-				   faddr, saddr, dport, inet->inet_sport,
-				   sk->sk_uid);
+		flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos, scope,
+				   sk->sk_protocol, flow_flags, faddr, saddr,
+				   dport, inet->inet_sport, sk->sk_uid);
 
 		security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
 		rt = ip_route_output_flow(net, fl4, sk);