@@ -52,6 +52,21 @@ struct vxlan_metadata {
__u32 gbp;
};
+struct bpf_fou_encap {
+ __be16 sport;
+ __be16 dport;
+};
+
+enum bpf_fou_encap_type {
+ FOU_BPF_ENCAP_FOU,
+ FOU_BPF_ENCAP_GUE,
+};
+
+int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx,
+ struct bpf_fou_encap *encap, int type) __ksym;
+int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx,
+ struct bpf_fou_encap *encap) __ksym;
+
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__uint(max_entries, 1);
@@ -749,6 +764,108 @@ int ipip_get_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
+SEC("tc")
+int ipip_gue_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key = {};
+ struct bpf_fou_encap encap = {};
+ void *data = (void *)(long)skb->data;
+ struct iphdr *iph = data;
+ void *data_end = (void *)(long)skb->data_end;
+ int ret;
+
+ if (data + sizeof(*iph) > data_end) {
+ log_err(1);
+ return TC_ACT_SHOT;
+ }
+
+ key.tunnel_ttl = 64;
+ if (iph->protocol == IPPROTO_ICMP)
+ key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
+ if (ret < 0) {
+ log_err(ret);
+ return TC_ACT_SHOT;
+ }
+
+ encap.sport = 0;
+ encap.dport = bpf_htons(5555);
+
+ ret = bpf_skb_set_fou_encap(skb, &encap, FOU_BPF_ENCAP_GUE);
+ if (ret < 0) {
+ log_err(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("tc")
+int ipip_fou_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key = {};
+ struct bpf_fou_encap encap = {};
+ void *data = (void *)(long)skb->data;
+ struct iphdr *iph = data;
+ void *data_end = (void *)(long)skb->data_end;
+ int ret;
+
+ if (data + sizeof(*iph) > data_end) {
+ log_err(1);
+ return TC_ACT_SHOT;
+ }
+
+ key.tunnel_ttl = 64;
+ if (iph->protocol == IPPROTO_ICMP)
+ key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
+ if (ret < 0) {
+ log_err(ret);
+ return TC_ACT_SHOT;
+ }
+
+ encap.sport = 0;
+ encap.dport = bpf_htons(5555);
+
+ ret = bpf_skb_set_fou_encap(skb, &encap, FOU_BPF_ENCAP_FOU);
+ if (ret < 0) {
+ log_err(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("tc")
+int ipip_encap_get_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key = {};
+ struct bpf_fou_encap encap = {};
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+ if (ret < 0) {
+ log_err(ret);
+ return TC_ACT_SHOT;
+ }
+
+ ret = bpf_skb_get_fou_encap(skb, &encap);
+ if (ret < 0) {
+ log_err(ret);
+ return TC_ACT_SHOT;
+ }
+
+ if (bpf_ntohs(encap.dport) != 5555)
+ return TC_ACT_SHOT;
+
+ bpf_printk("%d remote ip 0x%x, sport %d, dport %d\n", ret,
+ key.remote_ipv4, bpf_ntohs(encap.sport),
+ bpf_ntohs(encap.dport));
+ return TC_ACT_OK;
+}
+
SEC("tc")
int ipip6_set_tunnel(struct __sk_buff *skb)
{
@@ -212,6 +212,24 @@ add_ipip_tunnel()
ip addr add dev $DEV 10.1.1.200/24
}
+add_ipip_encap_tunnel()
+{
+ # at_ns0 namespace
+ ip netns exec at_ns0 ip fou add port 5555 $IPPROTO
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE \
+ local 172.16.1.100 remote 172.16.1.200 \
+ encap $ENCAP encap-sport auto encap-dport 5555 noencap-csum
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+
+ # root namespace
+ ip fou add port 5555 $IPPROTO
+ ip link add dev $DEV type $TYPE external
+ ip link set dev $DEV up
+ ip addr add dev $DEV 10.1.1.200/24
+}
+
add_ip6tnl_tunnel()
{
ip netns exec at_ns0 ip addr add ::11/96 dev veth0
@@ -461,6 +479,60 @@ test_ipip()
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
+test_ipip_gue()
+{
+ TYPE=ipip
+ DEV_NS=ipip00
+ DEV=ipip11
+ ret=0
+ ENCAP=gue
+ IPPROTO=$ENCAP
+
+ check $TYPE
+ config_device
+ add_ipip_encap_tunnel
+ ip link set dev veth1 mtu 1500
+ attach_bpf $DEV ipip_gue_set_tunnel ipip_encap_get_tunnel
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE (GUE)"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE (GUE)"${NC}
+}
+
+test_ipip_fou()
+{
+ TYPE=ipip
+ DEV_NS=ipip00
+ DEV=ipip11
+ ret=0
+ ENCAP=fou
+ IPPROTO="ipproto 4"
+
+ check $TYPE
+ config_device
+ add_ipip_encap_tunnel
+ ip link set dev veth1 mtu 1500
+ attach_bpf $DEV ipip_fou_set_tunnel ipip_encap_get_tunnel
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE (FOU)"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE (FOU)"${NC}
+}
+
test_ipip6()
{
TYPE=ip6tnl
@@ -634,6 +706,7 @@ cleanup()
ip xfrm policy delete dir in src 10.1.1.100/32 dst 10.1.1.200/32 2> /dev/null
ip xfrm state delete src 172.16.1.100 dst 172.16.1.200 proto esp spi 0x1 2> /dev/null
ip xfrm state delete src 172.16.1.200 dst 172.16.1.100 proto esp spi 0x2 2> /dev/null
+ ip fou del port 5555 gue 2> /dev/null
}
cleanup_exit()
@@ -708,6 +781,14 @@ bpf_tunnel_test()
test_ipip
errors=$(( $errors + $? ))
+ echo "Testing IPIP (GUE) tunnel..."
+ test_ipip_gue
+ errors=$(( $errors + $? ))
+
+ echo "Testing IPIP (FOU) tunnel..."
+ test_ipip_fou
+ errors=$(( $errors + $? ))
+
echo "Testing IPIP6 tunnel..."
test_ipip6
errors=$(( $errors + $? ))
Add tests for FOU and GUE encapsulation via the bpf_skb_{set,get}_fou_encap kfuncs, using ipip devices in collect-metadata mode. These tests make sure that we can successfully set and obtain FOU and GUE encap parameters using ingress / egress BPF tc-hooks. Signed-off-by: Christian Ehrig <cehrig@cloudflare.com> --- .../selftests/bpf/progs/test_tunnel_kern.c | 117 ++++++++++++++++++ tools/testing/selftests/bpf/test_tunnel.sh | 81 ++++++++++++ 2 files changed, 198 insertions(+)