When a UDP encapsulation socket (e.g., FOU) receives a multicast packet, __udp4_lib_mcast_deliver() and __udp6_lib_mcast_deliver() call consume_skb() when udp_queue_rcv_skb() returns a positive value. A positive return value from udp_queue_rcv_skb() indicates that the encap_rcv handler (e.g., fou_udp_recv) has consumed the UDP header and wants the packet to be resubmitted to the IP protocol handler for further processing (e.g., as a GRE packet). The unicast path in udp_unicast_rcv_skb() handles this correctly by returning -ret, which propagates up to ip_protocol_deliver_rcu() for resubmission. However, the multicast path destroys the packet via consume_skb() instead of resubmitting it, causing silent packet loss. This affects any UDP encapsulation (FOU, GUE) combined with multicast destination addresses. Fix this by returning -ret instead of calling consume_skb() when the return value is positive, matching the behavior of the unicast path. This avoids growing the call stack compared to calling ip_protocol_deliver_rcu() directly. Signed-off-by: Anton Danilov Assisted-by: Claude:claude-opus-4-6 --- net/ipv4/udp.c | 6 ++++-- net/ipv6/udp.c | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 70f6cbd4ef73..b0910659391e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2475,6 +2475,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct udp_hslot *hslot; struct sk_buff *nskb; bool use_hash2; + int ret; hash2_any = 0; hash2 = 0; @@ -2519,8 +2520,9 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, } if (first) { - if (udp_queue_rcv_skb(first, skb) > 0) - consume_skb(skb); + ret = udp_queue_rcv_skb(first, skb); + if (ret > 0) + return -ret; } else { kfree_skb(skb); __UDP_INC_STATS(net, UDP_MIB_IGNOREDMULTI); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 15e032194ecc..ff2e389e286b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -949,6 +949,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct udp_hslot *hslot; struct sk_buff *nskb; bool use_hash2; + int ret; hash2_any = 0; hash2 = 0; @@ -998,8 +999,9 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, } if (first) { - if (udpv6_queue_rcv_skb(first, skb) > 0) - consume_skb(skb); + ret = udpv6_queue_rcv_skb(first, skb); + if (ret > 0) + return -ret; } else { kfree_skb(skb); __UDP6_INC_STATS(net, UDP_MIB_IGNOREDMULTI); -- 2.47.3 Add a selftest to verify that FOU-encapsulated packets addressed to a multicast destination are correctly resubmitted to the inner protocol handler (GRE) via the UDP multicast delivery path. The test creates two network namespaces connected by a veth pair with a FOU/GRETAP tunnel using a multicast remote address (239.0.0.1). Ping is sent through the tunnel and received packets are counted on the receiver's tunnel interface. A static neighbor entry is configured on the sender because ARP replies from the receiver cannot traverse the unidirectional multicast tunnel back to the sender. The early demux optimization (net.ipv4.ip_early_demux) is disabled on the receiver to force packets through __udp4_lib_mcast_deliver(), which is the code path being tested. Signed-off-by: Anton Danilov Assisted-by: Claude:claude-opus-4-6 --- tools/testing/selftests/net/Makefile | 1 + .../testing/selftests/net/fou_mcast_encap.sh | 112 ++++++++++++++++++ 2 files changed, 113 insertions(+) create mode 100755 tools/testing/selftests/net/fou_mcast_encap.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 708d960ae07d..7e9ae937cffa 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -39,6 +39,7 @@ TEST_PROGS := \ fib_rule_tests.sh \ fib_tests.sh \ fin_ack_lat.sh \ + fou_mcast_encap.sh \ fq_band_pktlimit.sh \ gre_gso.sh \ gre_ipv6_lladdr.sh \ diff --git a/tools/testing/selftests/net/fou_mcast_encap.sh b/tools/testing/selftests/net/fou_mcast_encap.sh new file mode 100755 index 000000000000..8db9633f4c28 --- /dev/null +++ b/tools/testing/selftests/net/fou_mcast_encap.sh @@ -0,0 +1,112 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test that UDP encapsulation (FOU) correctly handles packet resubmit +# when packets are delivered via the multicast UDP delivery path. +# +# When a FOU-encapsulated packet arrives with a multicast destination IP, +# __udp4_lib_mcast_deliver() must resubmit it to the inner protocol +# handler (e.g., GRE) rather than consuming it. This test verifies that +# by creating a FOU/GRETAP tunnel with a multicast remote address and +# sending ping through it. +# +# The early demux optimization can mask this issue by routing packets via +# the unicast path (udp_unicast_rcv_skb), so we disable it to force +# packets through __udp4_lib_mcast_deliver(). + +source lib.sh + +NSENDER="" +NRECV="" + +cleanup() { + cleanup_all_ns +} + +trap cleanup EXIT + +setup() { + setup_ns NSENDER NRECV + + ip link add veth_s type veth peer name veth_r + ip link set veth_s netns "$NSENDER" + ip link set veth_r netns "$NRECV" + + ip -n "$NSENDER" addr add 10.0.0.1/24 dev veth_s + ip -n "$NSENDER" link set veth_s up + + ip -n "$NRECV" addr add 10.0.0.2/24 dev veth_r + ip -n "$NRECV" link set veth_r up + + # Disable early demux to force multicast delivery path + ip netns exec "$NRECV" sysctl -wq net.ipv4.ip_early_demux=0 + + # Join multicast group on receiver + ip -n "$NRECV" addr add 239.0.0.1/32 dev veth_r autojoin + + # Multicast routes + ip -n "$NRECV" route add 239.0.0.0/8 dev veth_r + ip -n "$NSENDER" route add 239.0.0.0/8 dev veth_s + + # Sender: GRETAP with FOU encap (no FOU listener needed on TX side) + ip -n "$NSENDER" link add eoudp0 type gretap \ + remote 239.0.0.1 local 10.0.0.1 \ + encap fou encap-sport 4797 encap-dport 4797 \ + key 239.0.0.1 + ip -n "$NSENDER" link set eoudp0 up + ip -n "$NSENDER" addr add 192.168.99.1/24 dev eoudp0 + + # Receiver: FOU listener + GRETAP + ip netns exec "$NRECV" ip fou add port 4797 ipproto 47 + ip -n "$NRECV" link add eoudp0 type gretap \ + remote 239.0.0.1 local 10.0.0.2 \ + encap fou encap-sport 4797 encap-dport 4797 \ + key 239.0.0.1 + ip -n "$NRECV" link set eoudp0 up + ip -n "$NRECV" addr add 192.168.99.2/24 dev eoudp0 + + # Static neigh entry on sender: ARP replies cannot traverse the + # multicast tunnel back, so pre-populate the neighbor cache. + local recv_mac + recv_mac=$(ip -n "$NRECV" link show eoudp0 | awk '/ether/{print $2}') + ip -n "$NSENDER" neigh add 192.168.99.2 lladdr "$recv_mac" dev eoudp0 +} + +get_rx_packets() { + ip -n "$NRECV" -s link show eoudp0 | awk '/RX:/{getline; print $2}' +} + +test_fou_mcast_encap() { + local count=100 + local rx_before + local rx_after + local rx_delta + + # Warmup: let any initial broadcast/ARP traffic settle + ip netns exec "$NSENDER" ping -c 1 -W 1 192.168.99.2 >/dev/null 2>&1 + sleep 1 + + rx_before=$(get_rx_packets) + ip netns exec "$NSENDER" ping -c $count -W 1 192.168.99.2 >/dev/null 2>&1 + sleep 1 + rx_after=$(get_rx_packets) + + rx_delta=$((rx_after - rx_before)) + + if [ "$rx_delta" -ge "$count" ]; then + echo "PASS: received $rx_delta/$count packets via multicast FOU/GRETAP" + return "$ksft_pass" + elif [ "$rx_delta" -gt 0 ]; then + echo "FAIL: only $rx_delta/$count packets received (partial delivery)" + return "$ksft_fail" + else + echo "FAIL: 0/$count packets received (multicast encap resubmit broken)" + return "$ksft_fail" + fi +} + +echo "TEST: FOU/GRETAP multicast encapsulation resubmit" + +setup +test_fou_mcast_encap +exit $? -- 2.47.3