Commit a3522a2e authored by Guillaume Nault's avatar Guillaume Nault Committed by Jakub Kicinski
Browse files

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: default avatarGuillaume Nault <gnault@redhat.com>
Reviewed-by: default avatarDavid Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/dacfd2ab40685e20959ab7b53c427595ba229e7d.1707496938.git.gnault@redhat.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent f25e7b82

include/net/route.h

+2 −5
Original line number Diff line number Diff line
@@ -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));

net/ipv4/af_inet.c

+1 −1
Original line number Diff line number Diff line
@@ -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;

net/ipv4/datagram.c

+1 −1
Original line number Diff line number Diff line
@@ -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);

net/ipv4/inet_connection_sock.c

+1 −1
Original line number Diff line number Diff line
@@ -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)

net/ipv4/ip_output.c

+1 −1
Original line number Diff line number Diff line
@@ -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;