Merge branch 'vrf-fix-source-address-selection-with-route-leak'

Nicolas Dichtel says:

====================
vrf: fix source address selection with route leak

For patch 1 and 2, I didn't find the exact commit that introduced this bug, but
I suspect it has been here since the first version. I arbitrarily choose one.
====================

Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

6 files changed, 120 insertions, 12 deletions

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index a18ed24fed94..6dbdf60b342f 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -127,18 +127,26 @@ void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args,
 
 static inline int ip6_route_get_saddr(struct net *net, struct fib6_info *f6i,
 				      const struct in6_addr *daddr,
-				      unsigned int prefs,
+				      unsigned int prefs, int l3mdev_index,
 				      struct in6_addr *saddr)
 {
+	struct net_device *l3mdev;
+	struct net_device *dev;
+	bool same_vrf;
 	int err = 0;
 
-	if (f6i && f6i->fib6_prefsrc.plen) {
+	rcu_read_lock();
+
+	l3mdev = dev_get_by_index_rcu(net, l3mdev_index);
+	if (!f6i || !f6i->fib6_prefsrc.plen || l3mdev)
+		dev = f6i ? fib6_info_nh_dev(f6i) : NULL;
+	same_vrf = !l3mdev || l3mdev_master_dev_rcu(dev) == l3mdev;
+	if (f6i && f6i->fib6_prefsrc.plen && same_vrf)
 		*saddr = f6i->fib6_prefsrc.addr;
-	} else {
-		struct net_device *dev = f6i ? fib6_info_nh_dev(f6i) : NULL;
+	else
+		err = ipv6_dev_get_saddr(net, same_vrf ? dev : l3mdev, daddr, prefs, saddr);
 
-		err = ipv6_dev_get_saddr(net, dev, daddr, prefs, saddr);
-	}
+	rcu_read_unlock();
 
 	return err;
 }
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index f669da98d11d..8956026bc0a2 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -2270,6 +2270,15 @@ void fib_select_path(struct net *net, struct fib_result *res,
 		fib_select_default(fl4, res);
 
 check_saddr:
-	if (!fl4->saddr)
-		fl4->saddr = fib_result_prefsrc(net, res);
+	if (!fl4->saddr) {
+		struct net_device *l3mdev;
+
+		l3mdev = dev_get_by_index_rcu(net, fl4->flowi4_l3mdev);
+
+		if (!l3mdev ||
+		    l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) == l3mdev)
+			fl4->saddr = fib_result_prefsrc(net, res);
+		else
+			fl4->saddr = inet_select_addr(l3mdev, 0, RT_SCOPE_LINK);
+	}
 }
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 5c424a0e7232..4f2c5cc31015 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1873,7 +1873,8 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
 							    master, &dst,
 							    scores, hiscore_idx);
 
-			if (scores[hiscore_idx].ifa)
+			if (scores[hiscore_idx].ifa &&
+			    scores[hiscore_idx].scopedist >= 0)
 				goto out;
 		}
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 27d8725445e3..784424ac4147 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1124,6 +1124,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 		from = rt ? rcu_dereference(rt->from) : NULL;
 		err = ip6_route_get_saddr(net, from, &fl6->daddr,
 					  sk ? READ_ONCE(inet6_sk(sk)->srcprefs) : 0,
+					  fl6->flowi6_l3mdev,
 					  &fl6->saddr);
 		rcu_read_unlock();
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8d72ca0b086d..c9a9506b714d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -5689,7 +5689,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 				goto nla_put_failure;
 	} else if (dest) {
 		struct in6_addr saddr_buf;
-		if (ip6_route_get_saddr(net, rt, dest, 0, &saddr_buf) == 0 &&
+		if (ip6_route_get_saddr(net, rt, dest, 0, 0, &saddr_buf) == 0 &&
 		    nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf))
 			goto nla_put_failure;
 	}
diff --git a/tools/testing/selftests/net/vrf_route_leaking.sh b/tools/testing/selftests/net/vrf_route_leaking.sh
index 2da32f4c479b..152171fb1fc8 100755
--- a/tools/testing/selftests/net/vrf_route_leaking.sh
+++ b/tools/testing/selftests/net/vrf_route_leaking.sh
@@ -59,6 +59,7 @@
 # while it is forwarded between different vrfs.
 
 source lib.sh
+PATH=$PWD:$PWD/tools/testing/selftests/net:$PATH
 VERBOSE=0
 PAUSE_ON_FAIL=no
 DEFAULT_TTYPE=sym
@@ -533,6 +534,86 @@ ipv6_ping_frag_asym()
 	ipv6_ping_frag asym
 }
 
+ipv4_ping_local()
+{
+	log_section "IPv4 (sym route): VRF ICMP local error route lookup ping"
+
+	setup_sym
+
+	check_connectivity || return
+
+	run_cmd ip netns exec $r1 ip vrf exec blue ping -c1 -w1 ${H2_N2_IP}
+	log_test $? 0 "VRF ICMP local IPv4"
+}
+
+ipv4_tcp_local()
+{
+	log_section "IPv4 (sym route): VRF tcp local connection"
+
+	setup_sym
+
+	check_connectivity || return
+
+	run_cmd nettest -s -O "$h2" -l ${H2_N2_IP} -I eth0 -3 eth0 &
+	sleep 1
+	run_cmd nettest -N "$r1" -d blue -r ${H2_N2_IP}
+	log_test $? 0 "VRF tcp local connection IPv4"
+}
+
+ipv4_udp_local()
+{
+	log_section "IPv4 (sym route): VRF udp local connection"
+
+	setup_sym
+
+	check_connectivity || return
+
+	run_cmd nettest -s -D -O "$h2" -l ${H2_N2_IP} -I eth0 -3 eth0 &
+	sleep 1
+	run_cmd nettest -D -N "$r1" -d blue -r ${H2_N2_IP}
+	log_test $? 0 "VRF udp local connection IPv4"
+}
+
+ipv6_ping_local()
+{
+	log_section "IPv6 (sym route): VRF ICMP local error route lookup ping"
+
+	setup_sym
+
+	check_connectivity6 || return
+
+	run_cmd ip netns exec $r1 ip vrf exec blue ${ping6} -c1 -w1 ${H2_N2_IP6}
+	log_test $? 0 "VRF ICMP local IPv6"
+}
+
+ipv6_tcp_local()
+{
+	log_section "IPv6 (sym route): VRF tcp local connection"
+
+	setup_sym
+
+	check_connectivity6 || return
+
+	run_cmd nettest -s -6 -O "$h2" -l ${H2_N2_IP6} -I eth0 -3 eth0 &
+	sleep 1
+	run_cmd nettest -6 -N "$r1" -d blue -r ${H2_N2_IP6}
+	log_test $? 0 "VRF tcp local connection IPv6"
+}
+
+ipv6_udp_local()
+{
+	log_section "IPv6 (sym route): VRF udp local connection"
+
+	setup_sym
+
+	check_connectivity6 || return
+
+	run_cmd nettest -s -6 -D -O "$h2" -l ${H2_N2_IP6} -I eth0 -3 eth0 &
+	sleep 1
+	run_cmd nettest -6 -D -N "$r1" -d blue -r ${H2_N2_IP6}
+	log_test $? 0 "VRF udp local connection IPv6"
+}
+
 ################################################################################
 # usage
 
@@ -555,8 +636,10 @@ EOF
 # Some systems don't have a ping6 binary anymore
 command -v ping6 > /dev/null 2>&1 && ping6=$(command -v ping6) || ping6=$(command -v ping)
 
-TESTS_IPV4="ipv4_ping_ttl ipv4_traceroute ipv4_ping_frag ipv4_ping_ttl_asym ipv4_traceroute_asym"
-TESTS_IPV6="ipv6_ping_ttl ipv6_traceroute ipv6_ping_ttl_asym ipv6_traceroute_asym"
+TESTS_IPV4="ipv4_ping_ttl ipv4_traceroute ipv4_ping_frag ipv4_ping_local ipv4_tcp_local
+ipv4_udp_local ipv4_ping_ttl_asym ipv4_traceroute_asym"
+TESTS_IPV6="ipv6_ping_ttl ipv6_traceroute ipv6_ping_local ipv6_tcp_local ipv6_udp_local
+ipv6_ping_ttl_asym ipv6_traceroute_asym"
 
 ret=0
 nsuccess=0
@@ -594,12 +677,18 @@ do
 	ipv4_traceroute|traceroute)      ipv4_traceroute;;&
 	ipv4_traceroute_asym|traceroute) ipv4_traceroute_asym;;&
 	ipv4_ping_frag|ping)             ipv4_ping_frag;;&
+	ipv4_ping_local|ping)            ipv4_ping_local;;&
+	ipv4_tcp_local)                  ipv4_tcp_local;;&
+	ipv4_udp_local)                  ipv4_udp_local;;&
 
 	ipv6_ping_ttl|ping)              ipv6_ping_ttl;;&
 	ipv6_ping_ttl_asym|ping)         ipv6_ping_ttl_asym;;&
 	ipv6_traceroute|traceroute)      ipv6_traceroute;;&
 	ipv6_traceroute_asym|traceroute) ipv6_traceroute_asym;;&
 	ipv6_ping_frag|ping)             ipv6_ping_frag;;&
+	ipv6_ping_local|ping)            ipv6_ping_local;;&
+	ipv6_tcp_local)                  ipv6_tcp_local;;&
+	ipv6_udp_local)                  ipv6_udp_local;;&
 
 	# setup namespaces and config, but do not run any tests
 	setup_sym|setup)                 setup_sym; exit 0;;