ipv4: Set the routing scope properly in ip_route_output_ports().

Set scope automatically in ip_route_output_ports() (using the socket
SOCK_LOCALROUTE flag). This way, callers don't have to overload the
tos with the RTO_ONLINK flag, like RT_CONN_FLAGS() does.

For callers that don't pass a struct sock, this doesn't change anything
as the scope is still set to RT_SCOPE_UNIVERSE when sk is NULL.

Callers that passed a struct sock and used RT_CONN_FLAGS(sk) or
RT_CONN_FLAGS_TOS(sk, tos) for the tos are modified to use
ip_sock_tos(sk) and RT_TOS(tos) respectively, as overloading tos with
the RTO_ONLINK flag now becomes unnecessary.

In drivers/net/amt.c, all ip_route_output_ports() calls use a 0 tos
parameter, ignoring the SOCK_LOCALROUTE flag of the socket. But the sk
parameter is a kernel socket, which doesn't have any configuration path
for setting SOCK_LOCALROUTE anyway. Therefore, ip_route_output_ports()
will continue to initialise scope with RT_SCOPE_UNIVERSE and amt.c
doesn't need to be modified.

Also, remove RT_CONN_FLAGS() and RT_CONN_FLAGS_TOS() from route.h as
these macros are now unused.

The objective is to eventually remove RTO_ONLINK entirely to allow
converting ->flowi4_tos to dscp_t. This will ensure proper isolation
between the DSCP and ECN bits, thus minimising the risk of introducing
bugs where TOS values interfere with ECN.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/dacfd2ab40685e20959ab7b53c427595ba229e7d.1707496938.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 7 insertions, 10 deletions

diff --git a/include/net/route.h b/include/net/route.h
index 980ab474eabd..d4a0147942f1 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -37,9 +37,6 @@
 
 #define RTO_ONLINK	0x01
 
-#define RT_CONN_FLAGS(sk)   (RT_TOS(READ_ONCE(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))
@@ -163,8 +160,8 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi
 						   __u8 proto, __u8 tos, int oif)
 {
 	flowi4_init_output(fl4, oif, sk ? READ_ONCE(sk->sk_mark) : 0, tos,
-			   RT_SCOPE_UNIVERSE, proto,
-			   sk ? inet_sk_flowi_flags(sk) : 0,
+			   sk ? ip_sock_rt_scope(sk) : RT_SCOPE_UNIVERSE,
+			   proto, sk ? inet_sk_flowi_flags(sk) : 0,
 			   daddr, saddr, dport, sport, sock_net_uid(net, sk));
 	if (sk)
 		security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index a5a820ee2026..ad278009e469 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1326,7 +1326,7 @@ int inet_sk_rebuild_header(struct sock *sk)
 	fl4 = &inet->cork.fl.u.ip4;
 	rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr,
 				   inet->inet_dport, inet->inet_sport,
-				   sk->sk_protocol, RT_CONN_FLAGS(sk),
+				   sk->sk_protocol, ip_sock_rt_tos(sk),
 				   sk->sk_bound_dev_if);
 	if (!IS_ERR(rt)) {
 		err = 0;
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 2cc50cbfc2a3..cc6d0bd7b0a9 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -119,7 +119,7 @@ void ip4_datagram_release_cb(struct sock *sk)
 	rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr,
 				   inet->inet_saddr, inet->inet_dport,
 				   inet->inet_sport, sk->sk_protocol,
-				   RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);
+				   ip_sock_rt_tos(sk), sk->sk_bound_dev_if);
 
 	dst = !IS_ERR(rt) ? &rt->dst : NULL;
 	sk_dst_set(sk, dst);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 459af1f89739..747ed7344cbe 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1467,7 +1467,7 @@ static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *f
 	rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr,
 				   inet->inet_saddr, inet->inet_dport,
 				   inet->inet_sport, sk->sk_protocol,
-				   RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);
+				   ip_sock_rt_tos(sk), sk->sk_bound_dev_if);
 	if (IS_ERR(rt))
 		rt = NULL;
 	if (rt)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 41537d18eecf..5b5a0adb927f 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -493,7 +493,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 					   inet->inet_dport,
 					   inet->inet_sport,
 					   sk->sk_protocol,
-					   RT_CONN_FLAGS_TOS(sk, tos),
+					   RT_TOS(tos),
 					   sk->sk_bound_dev_if);
 		if (IS_ERR(rt))
 			goto no_route;
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 9a2a9ed3ba47..970af3983d11 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -478,7 +478,7 @@ static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		rt = ip_route_output_ports(sock_net(sk), fl4, sk,
 					   daddr, inet->inet_saddr,
 					   inet->inet_dport, inet->inet_sport,
-					   sk->sk_protocol, RT_CONN_FLAGS(sk),
+					   sk->sk_protocol, ip_sock_rt_tos(sk),
 					   sk->sk_bound_dev_if);
 		if (IS_ERR(rt))
 			goto no_route;