From 672e97ef689a38cb20c2cc6a1814298fea34461e Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 18 Oct 2022 10:34:38 +0300 Subject: [PATCH 1/2] net: Fix return value of qdisc ingress handling on success Currently qdisc ingress handling (sch_handle_ingress()) doesn't set a return value and it is left to the old return value of the caller (__netif_receive_skb_core()) which is RX drop, so if the packet is consumed, caller will stop and return this value as if the packet was dropped. This causes a problem in the kernel tcp stack when having a egress tc rule forwarding to a ingress tc rule. The tcp stack sending packets on the device having the egress rule will see the packets as not successfully transmitted (although they actually were), will not advance it's internal state of sent data, and packets returning on such tcp stream will be dropped by the tcp stack with reason ack-of-unsent-data. See reproduction in [0] below. Fix that by setting the return value to RX success if the packet was handled successfully. [0] Reproduction steps: $ ip link add veth1 type veth peer name peer1 $ ip link add veth2 type veth peer name peer2 $ ifconfig peer1 5.5.5.6/24 up $ ip netns add ns0 $ ip link set dev peer2 netns ns0 $ ip netns exec ns0 ifconfig peer2 5.5.5.5/24 up $ ifconfig veth2 0 up $ ifconfig veth1 0 up #ingress forwarding veth1 <-> veth2 $ tc qdisc add dev veth2 ingress $ tc qdisc add dev veth1 ingress $ tc filter add dev veth2 ingress prio 1 proto all flower \ action mirred egress redirect dev veth1 $ tc filter add dev veth1 ingress prio 1 proto all flower \ action mirred egress redirect dev veth2 #steal packet from peer1 egress to veth2 ingress, bypassing the veth pipe $ tc qdisc add dev peer1 clsact $ tc filter add dev peer1 egress prio 20 proto ip flower \ action mirred ingress redirect dev veth1 #run iperf and see connection not running $ iperf3 -s& $ ip netns exec ns0 iperf3 -c 5.5.5.6 -i 1 #delete egress rule, and run again, now should work $ tc filter del dev peer1 egress $ ip netns exec ns0 iperf3 -c 5.5.5.6 -i 1 Fixes: f697c3e8b35c ("[NET]: Avoid unnecessary cloning for ingress filtering") Signed-off-by: Paul Blakey Signed-off-by: David S. Miller --- net/core/dev.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/core/dev.c b/net/core/dev.c index fa53830d0683..3be256051e99 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5136,11 +5136,13 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, case TC_ACT_SHOT: mini_qdisc_qstats_cpu_drop(miniq); kfree_skb_reason(skb, SKB_DROP_REASON_TC_INGRESS); + *ret = NET_RX_DROP; return NULL; case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: consume_skb(skb); + *ret = NET_RX_SUCCESS; return NULL; case TC_ACT_REDIRECT: /* skb_mac_header check was done by cls/act_bpf, so @@ -5153,8 +5155,10 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, *another = true; break; } + *ret = NET_RX_SUCCESS; return NULL; case TC_ACT_CONSUMED: + *ret = NET_RX_SUCCESS; return NULL; default: break; From fd602f5cb52e336d8c06f8da2d80c76ce2905030 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 18 Oct 2022 10:34:39 +0300 Subject: [PATCH 2/2] selftests: add selftest for chaining of tc ingress handling to egress This test runs a simple ingress tc setup between two veth pairs, then adds a egress->ingress rule to test the chaining of tc ingress pipeline to tc egress piepline. Signed-off-by: Paul Blakey Signed-off-by: David S. Miller --- tools/testing/selftests/net/Makefile | 1 + .../net/test_ingress_egress_chaining.sh | 79 +++++++++++++++++++ 2 files changed, 80 insertions(+) create mode 100644 tools/testing/selftests/net/test_ingress_egress_chaining.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 2a6b0bc648c4..69c58362c0ed 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -70,6 +70,7 @@ TEST_PROGS += io_uring_zerocopy_tx.sh TEST_GEN_FILES += bind_bhash TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr +TEST_PROGS += test_ingress_egress_chaining.sh TEST_FILES := settings diff --git a/tools/testing/selftests/net/test_ingress_egress_chaining.sh b/tools/testing/selftests/net/test_ingress_egress_chaining.sh new file mode 100644 index 000000000000..08adff6bb3b6 --- /dev/null +++ b/tools/testing/selftests/net/test_ingress_egress_chaining.sh @@ -0,0 +1,79 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test runs a simple ingress tc setup between two veth pairs, +# and chains a single egress rule to test ingress chaining to egress. +# +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip +fi + +needed_mods="act_mirred cls_flower sch_ingress" +for mod in $needed_mods; do + modinfo $mod &>/dev/null || { echo "SKIP: Need act_mirred module"; exit $ksft_skip; } +done + +ns="ns$((RANDOM%899+100))" +veth1="veth1$((RANDOM%899+100))" +veth2="veth2$((RANDOM%899+100))" +peer1="peer1$((RANDOM%899+100))" +peer2="peer2$((RANDOM%899+100))" +ip_peer1=198.51.100.5 +ip_peer2=198.51.100.6 + +function fail() { + echo "FAIL: $@" >> /dev/stderr + exit 1 +} + +function cleanup() { + killall -q -9 udpgso_bench_rx + ip link del $veth1 &> /dev/null + ip link del $veth2 &> /dev/null + ip netns del $ns &> /dev/null +} +trap cleanup EXIT + +function config() { + echo "Setup veth pairs [$veth1, $peer1], and veth pair [$veth2, $peer2]" + ip link add $veth1 type veth peer name $peer1 + ip link add $veth2 type veth peer name $peer2 + ip addr add $ip_peer1/24 dev $peer1 + ip link set $peer1 up + ip netns add $ns + ip link set dev $peer2 netns $ns + ip netns exec $ns ip addr add $ip_peer2/24 dev $peer2 + ip netns exec $ns ip link set $peer2 up + ip link set $veth1 up + ip link set $veth2 up + + echo "Add tc filter ingress->egress forwarding $veth1 <-> $veth2" + tc qdisc add dev $veth2 ingress + tc qdisc add dev $veth1 ingress + tc filter add dev $veth2 ingress prio 1 proto all flower \ + action mirred egress redirect dev $veth1 + tc filter add dev $veth1 ingress prio 1 proto all flower \ + action mirred egress redirect dev $veth2 + + echo "Add tc filter egress->ingress forwarding $peer1 -> $veth1, bypassing the veth pipe" + tc qdisc add dev $peer1 clsact + tc filter add dev $peer1 egress prio 20 proto ip flower \ + action mirred ingress redirect dev $veth1 +} + +function test_run() { + echo "Run tcp traffic" + ./udpgso_bench_rx -t & + sleep 1 + ip netns exec $ns timeout -k 2 10 ./udpgso_bench_tx -t -l 2 -4 -D $ip_peer1 || fail "traffic failed" + echo "Test passed" +} + +config +test_run +trap - EXIT +cleanup