From 9e7a67dee27902fedab880b9af909bd4acd0fba9 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 6 Jan 2021 00:15:21 +0100 Subject: selftests: netfilter: add selftest for ipip pmtu discovery with enabled connection tracking Convert Christians bug description into a reproducer. Cc: Shuah Khan Reported-by: Christian Perle Signed-off-by: Florian Westphal Acked-by: Pablo Neira Ayuso Signed-off-by: Jakub Kicinski --- tools/testing/selftests/netfilter/Makefile | 3 +- .../selftests/netfilter/ipip-conntrack-mtu.sh | 206 +++++++++++++++++++++ 2 files changed, 208 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index a374e10ef506..3006a8e5b41a 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -4,7 +4,8 @@ TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \ conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ - nft_queue.sh nft_meta.sh + nft_queue.sh nft_meta.sh \ + ipip-conntrack-mtu.sh LDLIBS = -lmnl TEST_GEN_FILES = nf-queue diff --git a/tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh b/tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh new file mode 100755 index 000000000000..4a6f5c3b3215 --- /dev/null +++ b/tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh @@ -0,0 +1,206 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +# Conntrack needs to reassemble fragments in order to have complete +# packets for rule matching. Reassembly can lead to packet loss. + +# Consider the following setup: +# +--------+ +---------+ +--------+ +# |Router A|-------|Wanrouter|-------|Router B| +# | |.IPIP..| |..IPIP.| | +# +--------+ +---------+ +--------+ +# / mtu 1400 \ +# / \ +#+--------+ +--------+ +#|Client A| |Client B| +#| | | | +#+--------+ +--------+ + +# Router A and Router B use IPIP tunnel interfaces to tunnel traffic +# between Client A and Client B over WAN. Wanrouter has MTU 1400 set +# on its interfaces. + +rnd=$(mktemp -u XXXXXXXX) +rx=$(mktemp) + +r_a="ns-ra-$rnd" +r_b="ns-rb-$rnd" +r_w="ns-rw-$rnd" +c_a="ns-ca-$rnd" +c_b="ns-cb-$rnd" + +checktool (){ + if ! $1 > /dev/null 2>&1; then + echo "SKIP: Could not $2" + exit $ksft_skip + fi +} + +checktool "iptables --version" "run test without iptables" +checktool "ip -Version" "run test without ip tool" +checktool "which nc" "run test without nc (netcat)" +checktool "ip netns add ${r_a}" "create net namespace" + +for n in ${r_b} ${r_w} ${c_a} ${c_b};do + ip netns add ${n} +done + +cleanup() { + for n in ${r_a} ${r_b} ${r_w} ${c_a} ${c_b};do + ip netns del ${n} + done + rm -f ${rx} +} + +trap cleanup EXIT + +test_path() { + msg="$1" + + ip netns exec ${c_b} nc -n -w 3 -q 3 -u -l -p 5000 > ${rx} < /dev/null & + + sleep 1 + for i in 1 2 3; do + head -c1400 /dev/zero | tr "\000" "a" | ip netns exec ${c_a} nc -n -w 1 -u 192.168.20.2 5000 + done + + wait + + bytes=$(wc -c < ${rx}) + + if [ $bytes -eq 1400 ];then + echo "OK: PMTU $msg connection tracking" + else + echo "FAIL: PMTU $msg connection tracking: got $bytes, expected 1400" + exit 1 + fi +} + +# Detailed setup for Router A +# --------------------------- +# Interfaces: +# eth0: 10.2.2.1/24 +# eth1: 192.168.10.1/24 +# ipip0: No IP address, local 10.2.2.1 remote 10.4.4.1 +# Routes: +# 192.168.20.0/24 dev ipip0 (192.168.20.0/24 is subnet of Client B) +# 10.4.4.1 via 10.2.2.254 (Router B via Wanrouter) +# No iptables rules at all. + +ip link add veth0 netns ${r_a} type veth peer name veth0 netns ${r_w} +ip link add veth1 netns ${r_a} type veth peer name veth0 netns ${c_a} + +l_addr="10.2.2.1" +r_addr="10.4.4.1" +ip netns exec ${r_a} ip link add ipip0 type ipip local ${l_addr} remote ${r_addr} mode ipip || exit $ksft_skip + +for dev in lo veth0 veth1 ipip0; do + ip -net ${r_a} link set $dev up +done + +ip -net ${r_a} addr add 10.2.2.1/24 dev veth0 +ip -net ${r_a} addr add 192.168.10.1/24 dev veth1 + +ip -net ${r_a} route add 192.168.20.0/24 dev ipip0 +ip -net ${r_a} route add 10.4.4.0/24 via 10.2.2.254 + +ip netns exec ${r_a} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null + +# Detailed setup for Router B +# --------------------------- +# Interfaces: +# eth0: 10.4.4.1/24 +# eth1: 192.168.20.1/24 +# ipip0: No IP address, local 10.4.4.1 remote 10.2.2.1 +# Routes: +# 192.168.10.0/24 dev ipip0 (192.168.10.0/24 is subnet of Client A) +# 10.2.2.1 via 10.4.4.254 (Router A via Wanrouter) +# No iptables rules at all. + +ip link add veth0 netns ${r_b} type veth peer name veth1 netns ${r_w} +ip link add veth1 netns ${r_b} type veth peer name veth0 netns ${c_b} + +l_addr="10.4.4.1" +r_addr="10.2.2.1" + +ip netns exec ${r_b} ip link add ipip0 type ipip local ${l_addr} remote ${r_addr} mode ipip || exit $ksft_skip + +for dev in lo veth0 veth1 ipip0; do + ip -net ${r_b} link set $dev up +done + +ip -net ${r_b} addr add 10.4.4.1/24 dev veth0 +ip -net ${r_b} addr add 192.168.20.1/24 dev veth1 + +ip -net ${r_b} route add 192.168.10.0/24 dev ipip0 +ip -net ${r_b} route add 10.2.2.0/24 via 10.4.4.254 +ip netns exec ${r_b} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null + +# Client A +ip -net ${c_a} addr add 192.168.10.2/24 dev veth0 +ip -net ${c_a} link set dev lo up +ip -net ${c_a} link set dev veth0 up +ip -net ${c_a} route add default via 192.168.10.1 + +# Client A +ip -net ${c_b} addr add 192.168.20.2/24 dev veth0 +ip -net ${c_b} link set dev veth0 up +ip -net ${c_b} link set dev lo up +ip -net ${c_b} route add default via 192.168.20.1 + +# Wan +ip -net ${r_w} addr add 10.2.2.254/24 dev veth0 +ip -net ${r_w} addr add 10.4.4.254/24 dev veth1 + +ip -net ${r_w} link set dev lo up +ip -net ${r_w} link set dev veth0 up mtu 1400 +ip -net ${r_w} link set dev veth1 up mtu 1400 + +ip -net ${r_a} link set dev veth0 mtu 1400 +ip -net ${r_b} link set dev veth0 mtu 1400 + +ip netns exec ${r_w} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null + +# Path MTU discovery +# ------------------ +# Running tracepath from Client A to Client B shows PMTU discovery is working +# as expected: +# +# clienta:~# tracepath 192.168.20.2 +# 1?: [LOCALHOST] pmtu 1500 +# 1: 192.168.10.1 0.867ms +# 1: 192.168.10.1 0.302ms +# 2: 192.168.10.1 0.312ms pmtu 1480 +# 2: no reply +# 3: 192.168.10.1 0.510ms pmtu 1380 +# 3: 192.168.20.2 2.320ms reached +# Resume: pmtu 1380 hops 3 back 3 + +# ip netns exec ${c_a} traceroute --mtu 192.168.20.2 + +# Router A has learned PMTU (1400) to Router B from Wanrouter. +# Client A has learned PMTU (1400 - IPIP overhead = 1380) to Client B +# from Router A. + +#Send large UDP packet +#--------------------- +#Now we send a 1400 bytes UDP packet from Client A to Client B: + +# clienta:~# head -c1400 /dev/zero | tr "\000" "a" | nc -u 192.168.20.2 5000 +test_path "without" + +# The IPv4 stack on Client A already knows the PMTU to Client B, so the +# UDP packet is sent as two fragments (1380 + 20). Router A forwards the +# fragments between eth1 and ipip0. The fragments fit into the tunnel and +# reach their destination. + +#When sending the large UDP packet again, Router A now reassembles the +#fragments before routing the packet over ipip0. The resulting IPIP +#packet is too big (1400) for the tunnel PMTU (1380) to Router B, it is +#dropped on Router A before sending. + +ip netns exec ${r_a} iptables -A FORWARD -m conntrack --ctstate NEW +test_path "with" -- cgit v1.2.3 From 50c661670f6a3908c273503dfa206dfc7aa54c07 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 6 Jan 2021 00:15:22 +0100 Subject: net: fix pmtu check in nopmtudisc mode For some reason ip_tunnel insist on setting the DF bit anyway when the inner header has the DF bit set, EVEN if the tunnel was configured with 'nopmtudisc'. This means that the script added in the previous commit cannot be made to work by adding the 'nopmtudisc' flag to the ip tunnel configuration. Doing so breaks connectivity even for the without-conntrack/netfilter scenario. When nopmtudisc is set, the tunnel will skip the mtu check, so no icmp error is sent to client. Then, because inner header has DF set, the outer header gets added with DF bit set as well. IP stack then sends an error to itself because the packet exceeds the device MTU. Fixes: 23a3647bc4f93 ("ip_tunnels: Use skb-len to PMTU check.") Cc: Stefano Brivio Signed-off-by: Florian Westphal Acked-by: Pablo Neira Ayuso Signed-off-by: Jakub Kicinski --- net/ipv4/ip_tunnel.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index ee65c9225178..64594aa755f0 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -759,8 +759,11 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } - if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph, - 0, 0, false)) { + df = tnl_params->frag_off; + if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df) + df |= (inner_iph->frag_off & htons(IP_DF)); + + if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, 0, 0, false)) { ip_rt_put(rt); goto tx_error; } @@ -788,10 +791,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ttl = ip4_dst_hoplimit(&rt->dst); } - df = tnl_params->frag_off; - if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df) - df |= (inner_iph->frag_off&htons(IP_DF)); - max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); if (max_headroom > dev->needed_headroom) -- cgit v1.2.3 From bb4cc1a18856a73f0ff5137df0c2a31f4c50f6cf Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 6 Jan 2021 00:15:23 +0100 Subject: net: ip: always refragment ip defragmented packets Conntrack reassembly records the largest fragment size seen in IPCB. However, when this gets forwarded/transmitted, fragmentation will only be forced if one of the fragmented packets had the DF bit set. In that case, a flag in IPCB will force fragmentation even if the MTU is large enough. This should work fine, but this breaks with ip tunnels. Consider client that sends a UDP datagram of size X to another host. The client fragments the datagram, so two packets, of size y and z, are sent. DF bit is not set on any of these packets. Middlebox netfilter reassembles those packets back to single size-X packet, before routing decision. packet-size-vs-mtu checks in ip_forward are irrelevant, because DF bit isn't set. At output time, ip refragmentation is skipped as well because x is still smaller than the mtu of the output device. If ttransmit device is an ip tunnel, the packet size increases to x+overhead. Also, tunnel might be configured to force DF bit on outer header. In this case, packet will be dropped (exceeds MTU) and an ICMP error is generated back to sender. But sender already respects the announced MTU, all the packets that it sent did fit the announced mtu. Force refragmentation as per original sizes unconditionally so ip tunnel will encapsulate the fragments instead. The only other solution I see is to place ip refragmentation in the ip_tunnel code to handle this case. Fixes: d6b915e29f4ad ("ip_fragment: don't forward defragmented DF packet") Reported-by: Christian Perle Signed-off-by: Florian Westphal Acked-by: Pablo Neira Ayuso Signed-off-by: Jakub Kicinski --- net/ipv4/ip_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 89fff5f59eea..2ed0b01f72f0 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -302,7 +302,7 @@ static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff * if (skb_is_gso(skb)) return ip_finish_output_gso(net, sk, skb, mtu); - if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU)) + if (skb->len > mtu || IPCB(skb)->frag_max_size) return ip_fragment(net, sk, skb, mtu, ip_finish_output2); return ip_finish_output2(net, sk, skb); -- cgit v1.2.3