selftests: netfilter: add a vrf+conntrack testcase

Rework the reproducer for the vrf+conntrack regression reported
by Eugene into a selftest and also add a test for ip masquerading
that Lahav fixed recently.

With net or net-next tree, the first test fails and the latter
two pass.

With 09e856d54b ("vrf: Reset skb conntrack connection on VRF rcv")
reverted first test passes but the last two fail.

A proper fix needs more work, for time being a revert seems to be
the best choice, snat/masquerade did not work before the fix.

Link: https://lore.kernel.org/netdev/378ca299-4474-7e9a-3d36-2350c8c98995@gmail.com/T/#m95358a31810df7392f541f99d187227bc75c9963
Reported-by: Eugene Crosser <crosser@average.org>
Cc: Lahav Schlesinger <lschlesinger@drivenets.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This commit is contained in:
Florian Westphal 2021-10-18 14:38:13 +02:00 committed by Pablo Neira Ayuso
parent c45231a766
commit 33b8aad21a
2 changed files with 221 additions and 1 deletions

View File

@ -5,7 +5,8 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.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 nf_nat_edemux.sh \
ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh
ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \
conntrack_vrf.sh
LDLIBS = -lmnl
TEST_GEN_FILES = nf-queue

View File

@ -0,0 +1,219 @@
#!/bin/sh
# This script demonstrates interaction of conntrack and vrf.
# The vrf driver calls the netfilter hooks again, with oif/iif
# pointing at the VRF device.
#
# For ingress, this means first iteration has iifname of lower/real
# device. In this script, thats veth0.
# Second iteration is iifname set to vrf device, tvrf in this script.
#
# For egress, this is reversed: first iteration has the vrf device,
# second iteration is done with the lower/real/veth0 device.
#
# test_ct_zone_in demonstrates unexpected change of nftables
# behavior # caused by commit 09e856d54bda5f28 "vrf: Reset skb conntrack
# connection on VRF rcv"
#
# It was possible to assign conntrack zone to a packet (or mark it for
# `notracking`) in the prerouting chain before conntrack, based on real iif.
#
# After the change, the zone assignment is lost and the zone is assigned based
# on the VRF master interface (in case such a rule exists).
# assignment is lost. Instead, assignment based on the `iif` matching
# Thus it is impossible to distinguish packets based on the original
# interface.
#
# test_masquerade_vrf and test_masquerade_veth0 demonstrate the problem
# that was supposed to be fixed by the commit mentioned above to make sure
# that any fix to test case 1 won't break masquerade again.
ksft_skip=4
IP0=172.30.30.1
IP1=172.30.30.2
PFXL=30
ret=0
sfx=$(mktemp -u "XXXXXXXX")
ns0="ns0-$sfx"
ns1="ns1-$sfx"
cleanup()
{
ip netns pids $ns0 | xargs kill 2>/dev/null
ip netns pids $ns1 | xargs kill 2>/dev/null
ip netns del $ns0 $ns1
}
nft --version > /dev/null 2>&1
if [ $? -ne 0 ];then
echo "SKIP: Could not run test without nft tool"
exit $ksft_skip
fi
ip -Version > /dev/null 2>&1
if [ $? -ne 0 ];then
echo "SKIP: Could not run test without ip tool"
exit $ksft_skip
fi
ip netns add "$ns0"
if [ $? -ne 0 ];then
echo "SKIP: Could not create net namespace $ns0"
exit $ksft_skip
fi
ip netns add "$ns1"
trap cleanup EXIT
ip netns exec $ns0 sysctl -q -w net.ipv4.conf.default.rp_filter=0
ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0
ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0
ip link add veth0 netns "$ns0" type veth peer name veth0 netns "$ns1" > /dev/null 2>&1
if [ $? -ne 0 ];then
echo "SKIP: Could not add veth device"
exit $ksft_skip
fi
ip -net $ns0 li add tvrf type vrf table 9876
if [ $? -ne 0 ];then
echo "SKIP: Could not add vrf device"
exit $ksft_skip
fi
ip -net $ns0 li set lo up
ip -net $ns0 li set veth0 master tvrf
ip -net $ns0 li set tvrf up
ip -net $ns0 li set veth0 up
ip -net $ns1 li set veth0 up
ip -net $ns0 addr add $IP0/$PFXL dev veth0
ip -net $ns1 addr add $IP1/$PFXL dev veth0
ip netns exec $ns1 iperf3 -s > /dev/null 2>&1&
if [ $? -ne 0 ];then
echo "SKIP: Could not start iperf3"
exit $ksft_skip
fi
# test vrf ingress handling.
# The incoming connection should be placed in conntrack zone 1,
# as decided by the first iteration of the ruleset.
test_ct_zone_in()
{
ip netns exec $ns0 nft -f - <<EOF
table testct {
chain rawpre {
type filter hook prerouting priority raw;
iif { veth0, tvrf } counter meta nftrace set 1
iif veth0 counter ct zone set 1 counter return
iif tvrf counter ct zone set 2 counter return
ip protocol icmp counter
notrack counter
}
chain rawout {
type filter hook output priority raw;
oif veth0 counter ct zone set 1 counter return
oif tvrf counter ct zone set 2 counter return
notrack counter
}
}
EOF
ip netns exec $ns1 ping -W 1 -c 1 -I veth0 $IP0 > /dev/null
# should be in zone 1, not zone 2
count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 1 2>/dev/null | wc -l)
if [ $count -eq 1 ]; then
echo "PASS: entry found in conntrack zone 1"
else
echo "FAIL: entry not found in conntrack zone 1"
count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 2 2> /dev/null | wc -l)
if [ $count -eq 1 ]; then
echo "FAIL: entry found in zone 2 instead"
else
echo "FAIL: entry not in zone 1 or 2, dumping table"
ip netns exec $ns0 conntrack -L
ip netns exec $ns0 nft list ruleset
fi
fi
}
# add masq rule that gets evaluated w. outif set to vrf device.
# This tests the first iteration of the packet through conntrack,
# oifname is the vrf device.
test_masquerade_vrf()
{
ip netns exec $ns0 conntrack -F 2>/dev/null
ip netns exec $ns0 nft -f - <<EOF
flush ruleset
table ip nat {
chain postrouting {
type nat hook postrouting priority 0;
# NB: masquerade should always be combined with 'oif(name) bla',
# lack of this is intentional here, we want to exercise double-snat.
ip saddr 172.30.30.0/30 counter masquerade random
}
}
EOF
ip netns exec $ns0 ip vrf exec tvrf iperf3 -t 1 -c $IP1 >/dev/null
if [ $? -ne 0 ]; then
echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on vrf device"
ret=1
return
fi
# must also check that nat table was evaluated on second (lower device) iteration.
ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2'
if [ $? -eq 0 ]; then
echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device"
else
echo "FAIL: vrf masq rule has unexpected counter value"
ret=1
fi
}
# add masq rule that gets evaluated w. outif set to veth device.
# This tests the 2nd iteration of the packet through conntrack,
# oifname is the lower device (veth0 in this case).
test_masquerade_veth()
{
ip netns exec $ns0 conntrack -F 2>/dev/null
ip netns exec $ns0 nft -f - <<EOF
flush ruleset
table ip nat {
chain postrouting {
type nat hook postrouting priority 0;
meta oif veth0 ip saddr 172.30.30.0/30 counter masquerade random
}
}
EOF
ip netns exec $ns0 ip vrf exec tvrf iperf3 -t 1 -c $IP1 > /dev/null
if [ $? -ne 0 ]; then
echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on veth device"
ret=1
return
fi
# must also check that nat table was evaluated on second (lower device) iteration.
ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2'
if [ $? -eq 0 ]; then
echo "PASS: iperf3 connect with masquerade + sport rewrite on veth device"
else
echo "FAIL: vrf masq rule has unexpected counter value"
ret=1
fi
}
test_ct_zone_in
test_masquerade_vrf
test_masquerade_veth
exit $ret