net: allow unbound socket for packets in VRF when tcp_l3mdev_accept set

The commit 3c82a21f43 ("net: allow binding socket in a VRF when
there's an unbound socket") changed the inet socket lookup to avoid
packets in a VRF from matching an unbound socket. This is to ensure the
necessary isolation between the default and other VRFs for routing and
forwarding. VRF-unaware processes running in the default VRF cannot
access another VRF and have to be run with 'ip vrf exec <vrf>'. This is
to be expected with tcp_l3mdev_accept disabled, but could be reallowed
when this sysctl option is enabled. So instead of directly checking dif
and sdif in inet[6]_match, here call inet_sk_bound_dev_eq(). This
allows a match on unbound socket for non-zero sdif i.e. for packets in
a VRF, if tcp_l3mdev_accept is enabled.

Fixes: 3c82a21f43 ("net: allow binding socket in a VRF when there's an unbound socket")
Signed-off-by: Mike Manning <mvrmanning@gmail.com>
Link: https://lore.kernel.org/netdev/a54c149aed38fded2d3b5fdb1a6c89e36a083b74.camel@lasnet.de/
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/inet6_hashtables.h

@@ -110,8 +110,6 @@ static inline bool inet6_match(struct net *net, const struct sock *sk,
 			       const __portpair ports,
 			       const int dif, const int sdif)
 {
-	int bound_dev_if;
-
 	if (!net_eq(sock_net(sk), net) ||
 	    sk->sk_family != AF_INET6 ||
 	    sk->sk_portpair != ports ||
@@ -119,8 +117,9 @@ static inline bool inet6_match(struct net *net, const struct sock *sk,
 	    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
 		return false;
 
-	bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
-	return bound_dev_if == dif || bound_dev_if == sdif;
+	/* READ_ONCE() paired with WRITE_ONCE() in sock_bindtoindex_locked() */
+	return inet_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif,
+				    sdif);
 }
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 

include/net/inet_hashtables.h

@@ -175,17 +175,6 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
 	hashinfo->ehash_locks = NULL;
 }
 
-static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if,
-					int dif, int sdif)
-{
-#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
-	return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept),
-				 bound_dev_if, dif, sdif);
-#else
-	return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
-#endif
-}
-
 struct inet_bind_bucket *
 inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net,
 			struct inet_bind_hashbucket *head,
@@ -271,16 +260,14 @@ static inline bool inet_match(struct net *net, const struct sock *sk,
 			      const __addrpair cookie, const __portpair ports,
 			      int dif, int sdif)
 {
-	int bound_dev_if;
-
 	if (!net_eq(sock_net(sk), net) ||
 	    sk->sk_portpair != ports ||
 	    sk->sk_addrpair != cookie)
 	        return false;
 
-	/* Paired with WRITE_ONCE() from sock_bindtoindex_locked() */
-	bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
-	return bound_dev_if == dif || bound_dev_if == sdif;
+	/* READ_ONCE() paired with WRITE_ONCE() in sock_bindtoindex_locked() */
+	return inet_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif,
+				    sdif);
 }
 
 /* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need

include/net/inet_sock.h

@@ -149,6 +149,17 @@ static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if,
 	return bound_dev_if == dif || bound_dev_if == sdif;
 }
 
+static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if,
+					int dif, int sdif)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept),
+				 bound_dev_if, dif, sdif);
+#else
+	return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
+#endif
+}
+
 struct inet_cork {
 	unsigned int		flags;
 	__be32			addr;