From d8c444d540beaa39aff834c5b83df7e86a1ae765 Mon Sep 17 00:00:00 2001 From: Shijie Luo Date: Tue, 18 Jun 2019 15:14:03 +0000 Subject: [PATCH 1/3] ipv4: fix inet_select_addr() when enable route_localnet Suppose we have two interfaces eth0 and eth1 in two hosts, follow the same steps in the two hosts: # sysctl -w net.ipv4.conf.eth1.route_localnet=1 # sysctl -w net.ipv4.conf.eth1.arp_announce=2 # ip route del 127.0.0.0/8 dev lo table local and then set ip to eth1 in host1 like: # ifconfig eth1 127.25.3.4/24 set ip to eth2 in host2 and ping host1: # ifconfig eth1 127.25.3.14/24 # ping -I eth1 127.25.3.4 Well, host2 cannot connect to host1. When set a ip address with head 127, the scope of the address defaults to RT_SCOPE_HOST. In this situation, host2 will use arp_solicit() to send a arp request for the mac address of host1 with ip address 127.25.3.14. When arp_announce=2, inet_select_addr() cannot select a correct saddr with condition ifa->ifa_scope > scope, because ifa_scope is RT_SCOPE_HOST and scope is RT_SCOPE_LINK. Then, inet_select_addr() will go to no_in_dev to lookup all interfaces to find a primary ip and finally get the primary ip of eth0. Here I add a localnet_scope defaults to RT_SCOPE_HOST, and when route_localnet is enabled, this value changes to RT_SCOPE_LINK to make inet_select_addr() find a correct primary ip as saddr of arp request. Fixes: d0daebc3d622 ("ipv4: Add interface option to enable routing of 127.0.0.0/8") Signed-off-by: Shijie Luo Signed-off-by: Zhiqiang Liu Signed-off-by: David S. Miller --- net/ipv4/devinet.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 914ccc7f192a..6fd4628d10b9 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1287,6 +1287,7 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) { const struct in_ifaddr *ifa; __be32 addr = 0; + unsigned char localnet_scope = RT_SCOPE_HOST; struct in_device *in_dev; struct net *net = dev_net(dev); int master_idx; @@ -1296,10 +1297,13 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) if (!in_dev) goto no_in_dev; + if (unlikely(IN_DEV_ROUTE_LOCALNET(in_dev))) + localnet_scope = RT_SCOPE_LINK; + in_dev_for_each_ifa_rcu(ifa, in_dev) { if (ifa->ifa_flags & IFA_F_SECONDARY) continue; - if (ifa->ifa_scope > scope) + if (min(ifa->ifa_scope, localnet_scope) > scope) continue; if (!dst || inet_ifa_match(dst, ifa)) { addr = ifa->ifa_local; From 650638a7c6e60a198573873972aafb065f200056 Mon Sep 17 00:00:00 2001 From: Shijie Luo Date: Tue, 18 Jun 2019 15:14:04 +0000 Subject: [PATCH 2/3] ipv4: fix confirm_addr_indev() when enable route_localnet When arp_ignore=3, the NIC won't reply for scope host addresses, but if enable route_locanet, we need to reply ip address with head 127 and scope RT_SCOPE_HOST. Fixes: d0daebc3d622 ("ipv4: Add interface option to enable routing of 127.0.0.0/8") Signed-off-by: Shijie Luo Signed-off-by: Zhiqiang Liu Signed-off-by: David S. Miller --- net/ipv4/devinet.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 6fd4628d10b9..7874303220c5 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1356,14 +1356,20 @@ EXPORT_SYMBOL(inet_select_addr); static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, __be32 local, int scope) { + unsigned char localnet_scope = RT_SCOPE_HOST; const struct in_ifaddr *ifa; __be32 addr = 0; int same = 0; + if (unlikely(IN_DEV_ROUTE_LOCALNET(in_dev))) + localnet_scope = RT_SCOPE_LINK; + in_dev_for_each_ifa_rcu(ifa, in_dev) { + unsigned char min_scope = min(ifa->ifa_scope, localnet_scope); + if (!addr && (local == ifa->ifa_local || !local) && - ifa->ifa_scope <= scope) { + min_scope <= scope) { addr = ifa->ifa_local; if (same) break; @@ -1378,7 +1384,7 @@ static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, if (inet_ifa_match(addr, ifa)) break; /* No, then can we use new local src? */ - if (ifa->ifa_scope <= scope) { + if (min_scope <= scope) { addr = ifa->ifa_local; break; } From 58ade67b021549d540e2ed4be6971c5e3240388f Mon Sep 17 00:00:00 2001 From: Shijie Luo Date: Tue, 18 Jun 2019 15:14:05 +0000 Subject: [PATCH 3/3] selftests: add route_localnet test script Add a simple scripts to exercise several situations when enable route_localnet. Signed-off-by: Shijie Luo Signed-off-by: Zhiqiang liu Signed-off-by: David S. Miller --- tools/testing/selftests/net/route_localnet.sh | 74 +++++++++++++++++++ 1 file changed, 74 insertions(+) create mode 100755 tools/testing/selftests/net/route_localnet.sh diff --git a/tools/testing/selftests/net/route_localnet.sh b/tools/testing/selftests/net/route_localnet.sh new file mode 100755 index 000000000000..116bfeab72fa --- /dev/null +++ b/tools/testing/selftests/net/route_localnet.sh @@ -0,0 +1,74 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Run a couple of tests when route_localnet = 1. + +readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" + +setup() { + ip netns add "${PEER_NS}" + ip -netns "${PEER_NS}" link set dev lo up + ip link add name veth0 type veth peer name veth1 + ip link set dev veth0 up + ip link set dev veth1 netns "${PEER_NS}" + + # Enable route_localnet and delete useless route 127.0.0.0/8. + sysctl -w net.ipv4.conf.veth0.route_localnet=1 + ip netns exec "${PEER_NS}" sysctl -w net.ipv4.conf.veth1.route_localnet=1 + ip route del 127.0.0.0/8 dev lo table local + ip netns exec "${PEER_NS}" ip route del 127.0.0.0/8 dev lo table local + + ifconfig veth0 127.25.3.4/24 up + ip netns exec "${PEER_NS}" ifconfig veth1 127.25.3.14/24 up + + ip route flush cache + ip netns exec "${PEER_NS}" ip route flush cache +} + +cleanup() { + ip link del veth0 + ip route add local 127.0.0.0/8 dev lo proto kernel scope host src 127.0.0.1 + local -r ns="$(ip netns list|grep $PEER_NS)" + [ -n "$ns" ] && ip netns del $ns 2>/dev/null +} + +# Run test when arp_announce = 2. +run_arp_announce_test() { + echo "run arp_announce test" + setup + + sysctl -w net.ipv4.conf.veth0.arp_announce=2 + ip netns exec "${PEER_NS}" sysctl -w net.ipv4.conf.veth1.arp_announce=2 + ping -c5 -I veth0 127.25.3.14 + if [ $? -ne 0 ];then + echo "failed" + else + echo "ok" + fi + + cleanup +} + +# Run test when arp_ignore = 3. +run_arp_ignore_test() { + echo "run arp_ignore test" + setup + + sysctl -w net.ipv4.conf.veth0.arp_ignore=3 + ip netns exec "${PEER_NS}" sysctl -w net.ipv4.conf.veth1.arp_ignore=3 + ping -c5 -I veth0 127.25.3.14 + if [ $? -ne 0 ];then + echo "failed" + else + echo "ok" + fi + + cleanup +} + +run_all_tests() { + run_arp_announce_test + run_arp_ignore_test +} + +run_all_tests