The patch migrates the original tests at samples/bpf/tcbpf2_kern.c
and samples/bpf/test_tunnel_bpf.sh to selftests. There are a couple
changes from the original:
1) add ipv6 vxlan, ipv6 geneve, ipv6 ipip tests
2) simplify the original ipip tests (remove iperf tests)
3) improve documentation
4) use bpf_ntoh* and bpf_hton* api
In summary, 'test_tunnel_kern.o' contains the following bpf program:
GRE: gre_set_tunnel, gre_get_tunnel
IP6GRE: ip6gretap_set_tunnel, ip6gretap_get_tunnel
ERSPAN: erspan_set_tunnel, erspan_get_tunnel
IP6ERSPAN: ip4ip6erspan_set_tunnel, ip4ip6erspan_get_tunnel
VXLAN: vxlan_set_tunnel, vxlan_get_tunnel
IP6VXLAN: ip6vxlan_set_tunnel, ip6vxlan_get_tunnel
GENEVE: geneve_set_tunnel, geneve_get_tunnel
IP6GENEVE: ip6geneve_set_tunnel, ip6geneve_get_tunnel
IPIP: ipip_set_tunnel, ipip_get_tunnel
IP6IP: ipip6_set_tunnel, ipip6_get_tunnel,
ip6ip6_set_tunnel, ip6ip6_get_tunnel
Signed-off-by: William Tu <u9012...@gmail.com>
---
samples/bpf/Makefile | 1 -
samples/bpf/tcbpf2_kern.c | 612 ----------------------
samples/bpf/test_tunnel_bpf.sh | 390 --------------
tools/testing/selftests/bpf/Makefile | 5 +-
tools/testing/selftests/bpf/test_tunnel.sh | 651 +++++++++++++++++++++++
tools/testing/selftests/bpf/test_tunnel_kern.c | 691 +++++++++++++++++++++++++
6 files changed, 1345 insertions(+), 1005 deletions(-)
delete mode 100644 samples/bpf/tcbpf2_kern.c
delete mode 100755 samples/bpf/test_tunnel_bpf.sh
create mode 100755 tools/testing/selftests/bpf/test_tunnel.sh
create mode 100644 tools/testing/selftests/bpf/test_tunnel_kern.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index aa8c392e2e52..b853581592fd 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -114,7 +114,6 @@ always += sock_flags_kern.o
always += test_probe_write_user_kern.o
always += trace_output_kern.o
always += tcbpf1_kern.o
-always += tcbpf2_kern.o
always += tc_l2_redirect_kern.o
always += lathist_kern.o
always += offwaketime_kern.o
diff --git a/samples/bpf/tcbpf2_kern.c b/samples/bpf/tcbpf2_kern.c
deleted file mode 100644
index fa260c750fb1..000000000000
--- a/samples/bpf/tcbpf2_kern.c
+++ /dev/null
@@ -1,612 +0,0 @@
-/* Copyright (c) 2016 VMware
- * Copyright (c) 2016 Facebook
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- */
-#define KBUILD_MODNAME "foo"
-#include <uapi/linux/bpf.h>
-#include <uapi/linux/if_ether.h>
-#include <uapi/linux/if_packet.h>
-#include <uapi/linux/ip.h>
-#include <uapi/linux/ipv6.h>
-#include <uapi/linux/in.h>
-#include <uapi/linux/tcp.h>
-#include <uapi/linux/filter.h>
-#include <uapi/linux/pkt_cls.h>
-#include <uapi/linux/erspan.h>
-#include <net/ipv6.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
-
-#define _htonl __builtin_bswap32
-#define ERROR(ret) do {\
- char fmt[] = "ERROR line:%d ret:%d\n";\
- bpf_trace_printk(fmt, sizeof(fmt), __LINE__, ret); \
- } while(0)
-
-struct geneve_opt {
- __be16 opt_class;
- u8 type;
- u8 length:5;
- u8 r3:1;
- u8 r2:1;
- u8 r1:1;
- u8 opt_data[8]; /* hard-coded to 8 byte */
-};
-
-struct vxlan_metadata {
- u32 gbp;
-};
-
-SEC("gre_set_tunnel")
-int _gre_set_tunnel(struct __sk_buff *skb)
-{
- int ret;
- struct bpf_tunnel_key key;
-
- __builtin_memset(&key, 0x0, sizeof(key));
- key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
- key.tunnel_id = 2;
- key.tunnel_tos = 0;
- key.tunnel_ttl = 64;
-
- ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
- BPF_F_ZERO_CSUM_TX | BPF_F_SEQ_NUMBER);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- return TC_ACT_OK;
-}
-
-SEC("gre_get_tunnel")
-int _gre_get_tunnel(struct __sk_buff *skb)
-{
- int ret;
- struct bpf_tunnel_key key;
- char fmt[] = "key %d remote ip 0x%x\n";
-
- ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- bpf_trace_printk(fmt, sizeof(fmt), key.tunnel_id, key.remote_ipv4);
- return TC_ACT_OK;
-}
-
-SEC("ip6gretap_set_tunnel")
-int _ip6gretap_set_tunnel(struct __sk_buff *skb)
-{
- struct bpf_tunnel_key key;
- int ret;
-
- __builtin_memset(&key, 0x0, sizeof(key));
- key.remote_ipv6[3] = _htonl(0x11); /* ::11 */
- key.tunnel_id = 2;
- key.tunnel_tos = 0;
- key.tunnel_ttl = 64;
- key.tunnel_label = 0xabcde;
-
- ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
- BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX |
- BPF_F_SEQ_NUMBER);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- return TC_ACT_OK;
-}
-
-SEC("ip6gretap_get_tunnel")
-int _ip6gretap_get_tunnel(struct __sk_buff *skb)
-{
- char fmt[] = "key %d remote ip6 ::%x label %x\n";
- struct bpf_tunnel_key key;
- int ret;
-
- ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
- BPF_F_TUNINFO_IPV6);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- bpf_trace_printk(fmt, sizeof(fmt),
- key.tunnel_id, key.remote_ipv6[3], key.tunnel_label);
-
- return TC_ACT_OK;
-}
-
-SEC("erspan_set_tunnel")
-int _erspan_set_tunnel(struct __sk_buff *skb)
-{
- struct bpf_tunnel_key key;
- struct erspan_metadata md;
- int ret;
-
- __builtin_memset(&key, 0x0, sizeof(key));
- key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
- key.tunnel_id = 2;
- key.tunnel_tos = 0;
- key.tunnel_ttl = 64;
-
- ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_ZERO_CSUM_TX);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- __builtin_memset(&md, 0, sizeof(md));
-#ifdef ERSPAN_V1
- md.version = 1;
- md.u.index = bpf_htonl(123);
-#else
- u8 direction = 1;
- u8 hwid = 7;
-
- md.version = 2;
- md.u.md2.dir = direction;
- md.u.md2.hwid = hwid & 0xf;
- md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
-#endif
-
- ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- return TC_ACT_OK;
-}
-
-SEC("erspan_get_tunnel")
-int _erspan_get_tunnel(struct __sk_buff *skb)
-{
- char fmt[] = "key %d remote ip 0x%x erspan version %d\n";
- struct bpf_tunnel_key key;
- struct erspan_metadata md;
- u32 index;
- int ret;
-
- ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md));
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- bpf_trace_printk(fmt, sizeof(fmt),
- key.tunnel_id, key.remote_ipv4, md.version);
-
-#ifdef ERSPAN_V1
- char fmt2[] = "\tindex %x\n";
-
- index = bpf_ntohl(md.u.index);
- bpf_trace_printk(fmt2, sizeof(fmt2), index);
-#else
- char fmt2[] = "\tdirection %d hwid %x timestamp %u\n";
-
- bpf_trace_printk(fmt2, sizeof(fmt2),
- md.u.md2.dir,
- (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
- bpf_ntohl(md.u.md2.timestamp));
-#endif
-
- return TC_ACT_OK;
-}
-
-SEC("ip4ip6erspan_set_tunnel")
-int _ip4ip6erspan_set_tunnel(struct __sk_buff *skb)
-{
- struct bpf_tunnel_key key;
- struct erspan_metadata md;
- int ret;
-
- __builtin_memset(&key, 0x0, sizeof(key));
- key.remote_ipv6[3] = _htonl(0x11);
- key.tunnel_id = 2;
- key.tunnel_tos = 0;
- key.tunnel_ttl = 64;
-
- ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
- BPF_F_TUNINFO_IPV6);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- __builtin_memset(&md, 0, sizeof(md));
-
-#ifdef ERSPAN_V1
- md.u.index = htonl(123);
- md.version = 1;
-#else
- u8 direction = 0;
- u8 hwid = 17;
-
- md.version = 2;
- md.u.md2.dir = direction;
- md.u.md2.hwid = hwid & 0xf;
- md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
-#endif
-
- ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- return TC_ACT_OK;
-}
-
-SEC("ip4ip6erspan_get_tunnel")
-int _ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
-{
- char fmt[] = "ip6erspan get key %d remote ip6 ::%x erspan version %d\n";
- struct bpf_tunnel_key key;
- struct erspan_metadata md;
- u32 index;
- int ret;
-
- ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md));
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- bpf_trace_printk(fmt, sizeof(fmt),
- key.tunnel_id, key.remote_ipv4, md.version);
-
-#ifdef ERSPAN_V1
- char fmt2[] = "\tindex %x\n";
-
- index = bpf_ntohl(md.u.index);
- bpf_trace_printk(fmt2, sizeof(fmt2), index);
-#else
- char fmt2[] = "\tdirection %d hwid %x timestamp %u\n";
-
- bpf_trace_printk(fmt2, sizeof(fmt2),
- md.u.md2.dir,
- (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
- bpf_ntohl(md.u.md2.timestamp));
-#endif
-
- return TC_ACT_OK;
-}
-
-SEC("vxlan_set_tunnel")
-int _vxlan_set_tunnel(struct __sk_buff *skb)
-{
- int ret;
- struct bpf_tunnel_key key;
- struct vxlan_metadata md;
-
- __builtin_memset(&key, 0x0, sizeof(key));
- key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
- key.tunnel_id = 2;
- key.tunnel_tos = 0;
- key.tunnel_ttl = 64;
-
- ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_ZERO_CSUM_TX);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- md.gbp = 0x800FF; /* Set VXLAN Group Policy extension */
- ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- return TC_ACT_OK;
-}
-
-SEC("vxlan_get_tunnel")
-int _vxlan_get_tunnel(struct __sk_buff *skb)
-{
- int ret;
- struct bpf_tunnel_key key;
- struct vxlan_metadata md;
- char fmt[] = "key %d remote ip 0x%x vxlan gbp 0x%x\n";
-
- ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md));
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- bpf_trace_printk(fmt, sizeof(fmt),
- key.tunnel_id, key.remote_ipv4, md.gbp);
-
- return TC_ACT_OK;
-}
-
-SEC("geneve_set_tunnel")
-int _geneve_set_tunnel(struct __sk_buff *skb)
-{
- int ret, ret2;
- struct bpf_tunnel_key key;
- struct geneve_opt gopt;
-
- __builtin_memset(&key, 0x0, sizeof(key));
- key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
- key.tunnel_id = 2;
- key.tunnel_tos = 0;
- key.tunnel_ttl = 64;
-
- __builtin_memset(&gopt, 0x0, sizeof(gopt));
- gopt.opt_class = 0x102; /* Open Virtual Networking (OVN) */
- gopt.type = 0x08;
- gopt.r1 = 0;
- gopt.r2 = 0;
- gopt.r3 = 0;
- gopt.length = 2; /* 4-byte multiple */
- *(int *) &gopt.opt_data = 0xdeadbeef;
-
- ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_ZERO_CSUM_TX);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt));
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- return TC_ACT_OK;
-}
-
-SEC("geneve_get_tunnel")
-int _geneve_get_tunnel(struct __sk_buff *skb)
-{
- int ret;
- struct bpf_tunnel_key key;
- struct geneve_opt gopt;
- char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n";
-
- ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- bpf_trace_printk(fmt, sizeof(fmt),
- key.tunnel_id, key.remote_ipv4, gopt.opt_class);
- return TC_ACT_OK;
-}
-
-SEC("ipip_set_tunnel")
-int _ipip_set_tunnel(struct __sk_buff *skb)
-{
- struct bpf_tunnel_key key = {};
- void *data = (void *)(long)skb->data;
- struct iphdr *iph = data;
- struct tcphdr *tcp = data + sizeof(*iph);
- void *data_end = (void *)(long)skb->data_end;
- int ret;
-
- /* single length check */
- if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
- ERROR(1);
- return TC_ACT_SHOT;
- }
-
- key.tunnel_ttl = 64;
- if (iph->protocol == IPPROTO_ICMP) {
- key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
- } else {
- if (iph->protocol != IPPROTO_TCP || iph->ihl != 5)
- return TC_ACT_SHOT;
-
- if (tcp->dest == htons(5200))
- key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
- else if (tcp->dest == htons(5201))
- key.remote_ipv4 = 0xac100165; /* 172.16.1.101 */
- else
- return TC_ACT_SHOT;
- }
-
- ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- return TC_ACT_OK;
-}
-
-SEC("ipip_get_tunnel")
-int _ipip_get_tunnel(struct __sk_buff *skb)
-{
- int ret;
- struct bpf_tunnel_key key;
- char fmt[] = "remote ip 0x%x\n";
-
- ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- bpf_trace_printk(fmt, sizeof(fmt), key.remote_ipv4);
- return TC_ACT_OK;
-}
-
-SEC("ipip6_set_tunnel")
-int _ipip6_set_tunnel(struct __sk_buff *skb)
-{
- struct bpf_tunnel_key key = {};
- void *data = (void *)(long)skb->data;
- struct iphdr *iph = data;
- struct tcphdr *tcp = data + sizeof(*iph);
- void *data_end = (void *)(long)skb->data_end;
- int ret;
-
- /* single length check */
- if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
- ERROR(1);
- return TC_ACT_SHOT;
- }
-
- key.remote_ipv6[0] = _htonl(0x2401db00);
- key.tunnel_ttl = 64;
-
- if (iph->protocol == IPPROTO_ICMP) {
- key.remote_ipv6[3] = _htonl(1);
- } else {
- if (iph->protocol != IPPROTO_TCP || iph->ihl != 5) {
- ERROR(iph->protocol);
- return TC_ACT_SHOT;
- }
-
- if (tcp->dest == htons(5200)) {
- key.remote_ipv6[3] = _htonl(1);
- } else if (tcp->dest == htons(5201)) {
- key.remote_ipv6[3] = _htonl(2);
- } else {
- ERROR(tcp->dest);
- return TC_ACT_SHOT;
- }
- }
-
- ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- return TC_ACT_OK;
-}
-
-SEC("ipip6_get_tunnel")
-int _ipip6_get_tunnel(struct __sk_buff *skb)
-{
- int ret;
- struct bpf_tunnel_key key;
- char fmt[] = "remote ip6 %x::%x\n";
-
- ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- bpf_trace_printk(fmt, sizeof(fmt), _htonl(key.remote_ipv6[0]),
- _htonl(key.remote_ipv6[3]));
- return TC_ACT_OK;
-}
-
-SEC("ip6ip6_set_tunnel")
-int _ip6ip6_set_tunnel(struct __sk_buff *skb)
-{
- struct bpf_tunnel_key key = {};
- void *data = (void *)(long)skb->data;
- struct ipv6hdr *iph = data;
- struct tcphdr *tcp = data + sizeof(*iph);
- void *data_end = (void *)(long)skb->data_end;
- int ret;
-
- /* single length check */
- if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
- ERROR(1);
- return TC_ACT_SHOT;
- }
-
- key.remote_ipv6[0] = _htonl(0x2401db00);
- key.tunnel_ttl = 64;
-
- if (iph->nexthdr == NEXTHDR_ICMP) {
- key.remote_ipv6[3] = _htonl(1);
- } else {
- if (iph->nexthdr != NEXTHDR_TCP) {
- ERROR(iph->nexthdr);
- return TC_ACT_SHOT;
- }
-
- if (tcp->dest == htons(5200)) {
- key.remote_ipv6[3] = _htonl(1);
- } else if (tcp->dest == htons(5201)) {
- key.remote_ipv6[3] = _htonl(2);
- } else {
- ERROR(tcp->dest);
- return TC_ACT_SHOT;
- }
- }
-
- ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- return TC_ACT_OK;
-}
-
-SEC("ip6ip6_get_tunnel")
-int _ip6ip6_get_tunnel(struct __sk_buff *skb)
-{
- int ret;
- struct bpf_tunnel_key key;
- char fmt[] = "remote ip6 %x::%x\n";
-
- ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
-
- bpf_trace_printk(fmt, sizeof(fmt), _htonl(key.remote_ipv6[0]),
- _htonl(key.remote_ipv6[3]));
- return TC_ACT_OK;
-}
-
-SEC("xfrm_get_state")
-int _xfrm_get_state(struct __sk_buff *skb)
-{
- struct bpf_xfrm_state x;
- char fmt[] = "reqid %d spi 0x%x remote ip 0x%x\n";
- int ret;
-
- ret = bpf_skb_get_xfrm_state(skb, 0, &x, sizeof(x), 0);
- if (ret < 0)
- return TC_ACT_OK;
-
- bpf_trace_printk(fmt, sizeof(fmt), x.reqid, bpf_ntohl(x.spi),
- bpf_ntohl(x.remote_ipv4));
- return TC_ACT_OK;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/test_tunnel_bpf.sh b/samples/bpf/test_tunnel_bpf.sh
deleted file mode 100755
index 9c534dc07b36..000000000000
--- a/samples/bpf/test_tunnel_bpf.sh
+++ /dev/null
@@ -1,390 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-# In Namespace 0 (at_ns0) using native tunnel
-# Overlay IP: 10.1.1.100
-# local 192.16.1.100 remote 192.16.1.200
-# veth0 IP: 172.16.1.100, tunnel dev <type>00
-
-# Out of Namespace using BPF set/get on lwtunnel
-# Overlay IP: 10.1.1.200
-# local 172.16.1.200 remote 172.16.1.100
-# veth1 IP: 172.16.1.200, tunnel dev <type>11
-
-function config_device {
- ip netns add at_ns0
- ip link add veth0 type veth peer name veth1
- ip link set veth0 netns at_ns0
- ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0
- ip netns exec at_ns0 ip link set dev veth0 up
- ip link set dev veth1 up mtu 1500
- ip addr add dev veth1 172.16.1.200/24
-}
-
-function add_gre_tunnel {
- # in namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq key 2 \
- local 172.16.1.100 remote 172.16.1.200
- 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
-
- # out of namespace
- ip link add dev $DEV type $TYPE key 2 external
- ip link set dev $DEV up
- ip addr add dev $DEV 10.1.1.200/24
-}
-
-function add_ip6gretap_tunnel {
-
- # assign ipv6 address
- ip netns exec at_ns0 ip addr add ::11/96 dev veth0
- ip netns exec at_ns0 ip link set dev veth0 up
- ip addr add dev veth1 ::22/96
- ip link set dev veth1 up
-
- # in namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \
- local ::11 remote ::22
-
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
- ip netns exec at_ns0 ip addr add dev $DEV_NS fc80::100/96
- ip netns exec at_ns0 ip link set dev $DEV_NS up
-
- # out of namespace
- ip link add dev $DEV type $TYPE external
- ip addr add dev $DEV 10.1.1.200/24
- ip addr add dev $DEV fc80::200/24
- ip link set dev $DEV up
-}
-
-function add_erspan_tunnel {
- # in namespace
- if [ "$1" == "v1" ]; then
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq key 2 \
- local 172.16.1.100 remote 172.16.1.200 \
- erspan_ver 1 erspan 123
- else
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq key 2 \
- local 172.16.1.100 remote 172.16.1.200 \
- erspan_ver 2 erspan_dir egress erspan_hwid 3
- fi
- 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
-
- # out of namespace
- ip link add dev $DEV type $TYPE external
- ip link set dev $DEV up
- ip addr add dev $DEV 10.1.1.200/24
-}
-
-function add_ip6erspan_tunnel {
-
- # assign ipv6 address
- ip netns exec at_ns0 ip addr add ::11/96 dev veth0
- ip netns exec at_ns0 ip link set dev veth0 up
- ip addr add dev veth1 ::22/96
- ip link set dev veth1 up
-
- # in namespace
- if [ "$1" == "v1" ]; then
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq key 2 \
- local ::11 remote ::22 \
- erspan_ver 1 erspan 123
- else
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq key 2 \
- local ::11 remote ::22 \
- erspan_ver 2 erspan_dir egress erspan_hwid 7
- fi
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
- ip netns exec at_ns0 ip link set dev $DEV_NS up
-
- # out of namespace
- ip link add dev $DEV type $TYPE external
- ip addr add dev $DEV 10.1.1.200/24
- ip link set dev $DEV up
-}
-
-function add_vxlan_tunnel {
- # Set static ARP entry here because iptables set-mark works
- # on L3 packet, as a result not applying to ARP packets,
- # causing errors at get_tunnel_{key/opt}.
-
- # in namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE id 2 dstport 4789 gbp remote
172.16.1.200
- ip netns exec at_ns0 ip link set dev $DEV_NS address 52:54:00:d9:01:00
up
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
- ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00
- ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF
-
- # out of namespace
- ip link add dev $DEV type $TYPE external gbp dstport 4789
- ip link set dev $DEV address 52:54:00:d9:02:00 up
- ip addr add dev $DEV 10.1.1.200/24
- arp -s 10.1.1.100 52:54:00:d9:01:00
-}
-
-function add_geneve_tunnel {
- # in namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE id 2 dstport 6081 remote
172.16.1.200
- 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
-
- # out of namespace
- ip link add dev $DEV type $TYPE dstport 6081 external
- ip link set dev $DEV up
- ip addr add dev $DEV 10.1.1.200/24
-}
-
-function add_ipip_tunnel {
- # in namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE local 172.16.1.100 remote
172.16.1.200
- 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
-
- # out of namespace
- ip link add dev $DEV type $TYPE external
- ip link set dev $DEV up
- ip addr add dev $DEV 10.1.1.200/24
-}
-
-function setup_xfrm_tunnel {
- auth=0x$(printf '1%.0s' {1..40})
- enc=0x$(printf '2%.0s' {1..32})
- spi_in_to_out=0x1
- spi_out_to_in=0x2
- # in namespace
- # in -> out
- ip netns exec at_ns0 \
- ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
- spi $spi_in_to_out reqid 1 mode tunnel \
- auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
- ip netns exec at_ns0 \
- ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir out \
- tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
- mode tunnel
- # out -> in
- ip netns exec at_ns0 \
- ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
- spi $spi_out_to_in reqid 2 mode tunnel \
- auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
- ip netns exec at_ns0 \
- ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir in \
- tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
- mode tunnel
- # address & route
- ip netns exec at_ns0 \
- ip addr add dev veth0 10.1.1.100/32
- ip netns exec at_ns0 \
- ip route add 10.1.1.200 dev veth0 via 172.16.1.200 \
- src 10.1.1.100
-
- # out of namespace
- # in -> out
- ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
- spi $spi_in_to_out reqid 1 mode tunnel \
- auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
- ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir in \
- tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
- mode tunnel
- # out -> in
- ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
- spi $spi_out_to_in reqid 2 mode tunnel \
- auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
- ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir out \
- tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
- mode tunnel
- # address & route
- ip addr add dev veth1 10.1.1.200/32
- ip route add 10.1.1.100 dev veth1 via 172.16.1.100 src 10.1.1.200
-}
-
-function attach_bpf {
- DEV=$1
- SET_TUNNEL=$2
- GET_TUNNEL=$3
- tc qdisc add dev $DEV clsact
- tc filter add dev $DEV egress bpf da obj tcbpf2_kern.o sec $SET_TUNNEL
- tc filter add dev $DEV ingress bpf da obj tcbpf2_kern.o sec $GET_TUNNEL
-}
-
-function test_gre {
- TYPE=gretap
- DEV_NS=gretap00
- DEV=gretap11
- config_device
- add_gre_tunnel
- attach_bpf $DEV gre_set_tunnel gre_get_tunnel
- ping -c 1 10.1.1.100
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- cleanup
-}
-
-function test_ip6gre {
- TYPE=ip6gre
- DEV_NS=ip6gre00
- DEV=ip6gre11
- config_device
- # reuse the ip6gretap function
- add_ip6gretap_tunnel
- attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
- # underlay
- ping6 -c 4 ::11
- # overlay: ipv4 over ipv6
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- ping -c 1 10.1.1.100
- # overlay: ipv6 over ipv6
- ip netns exec at_ns0 ping6 -c 1 fc80::200
- cleanup
-}
-
-function test_ip6gretap {
- TYPE=ip6gretap
- DEV_NS=ip6gretap00
- DEV=ip6gretap11
- config_device
- add_ip6gretap_tunnel
- attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
- # underlay
- ping6 -c 4 ::11
- # overlay: ipv4 over ipv6
- ip netns exec at_ns0 ping -i .2 -c 1 10.1.1.200
- ping -c 1 10.1.1.100
- # overlay: ipv6 over ipv6
- ip netns exec at_ns0 ping6 -c 1 fc80::200
- cleanup
-}
-
-function test_erspan {
- TYPE=erspan
- DEV_NS=erspan00
- DEV=erspan11
- config_device
- add_erspan_tunnel $1
- attach_bpf $DEV erspan_set_tunnel erspan_get_tunnel
- ping -c 1 10.1.1.100
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- cleanup
-}
-
-function test_ip6erspan {
- TYPE=ip6erspan
- DEV_NS=ip6erspan00
- DEV=ip6erspan11
- config_device
- add_ip6erspan_tunnel $1
- attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel
- ping6 -c 3 ::11
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- cleanup
-}
-
-function test_vxlan {
- TYPE=vxlan
- DEV_NS=vxlan00
- DEV=vxlan11
- config_device
- add_vxlan_tunnel
- attach_bpf $DEV vxlan_set_tunnel vxlan_get_tunnel
- ping -c 1 10.1.1.100
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- cleanup
-}
-
-function test_geneve {
- TYPE=geneve
- DEV_NS=geneve00
- DEV=geneve11
- config_device
- add_geneve_tunnel
- attach_bpf $DEV geneve_set_tunnel geneve_get_tunnel
- ping -c 1 10.1.1.100
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- cleanup
-}
-
-function test_ipip {
- TYPE=ipip
- DEV_NS=ipip00
- DEV=ipip11
- config_device
- tcpdump -nei veth1 &
- cat /sys/kernel/debug/tracing/trace_pipe &
- add_ipip_tunnel
- ethtool -K veth1 gso off gro off rx off tx off
- ip link set dev veth1 mtu 1500
- attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel
- ping -c 1 10.1.1.100
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- ip netns exec at_ns0 iperf -sD -p 5200 > /dev/null
- sleep 0.2
- iperf -c 10.1.1.100 -n 5k -p 5200
- cleanup
-}
-
-function test_xfrm_tunnel {
- config_device
- tcpdump -nei veth1 ip &
- output=$(mktemp)
- cat /sys/kernel/debug/tracing/trace_pipe | tee $output &
- setup_xfrm_tunnel
- tc qdisc add dev veth1 clsact
- tc filter add dev veth1 proto ip ingress bpf da obj tcbpf2_kern.o \
- sec xfrm_get_state
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- grep "reqid 1" $output
- grep "spi 0x1" $output
- grep "remote ip 0xac100164" $output
- cleanup
-}
-
-function cleanup {
- set +ex
- pkill iperf
- ip netns delete at_ns0
- ip link del veth1
- ip link del ipip11
- ip link del gretap11
- ip link del ip6gre11
- ip link del ip6gretap11
- ip link del vxlan11
- ip link del geneve11
- ip link del erspan11
- ip link del ip6erspan11
- ip x s flush
- ip x p flush
- pkill tcpdump
- pkill cat
- set -ex
-}
-
-trap cleanup 0 2 3 6 9
-cleanup
-echo "Testing GRE tunnel..."
-test_gre
-echo "Testing IP6GRE tunnel..."
-test_ip6gre
-echo "Testing IP6GRETAP tunnel..."
-test_ip6gretap
-echo "Testing ERSPAN tunnel..."
-test_erspan v1
-test_erspan v2
-echo "Testing IP6ERSPAN tunnel..."
-test_ip6erspan v1
-test_ip6erspan v2
-echo "Testing VXLAN tunnel..."
-test_vxlan
-echo "Testing GENEVE tunnel..."
-test_geneve
-echo "Testing IPIP tunnel..."
-test_ipip
-echo "Testing IPSec tunnel..."
-test_xfrm_tunnel
-echo "*** PASS ***"
diff --git a/tools/testing/selftests/bpf/Makefile
b/tools/testing/selftests/bpf/Makefile
index 0c19d5e08f08..b64a7a39cbc8 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -32,7 +32,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o
test_tcp_estats.o test
test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \
sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o
test_adjust_tail.o \
- test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o
+ test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o
# Order correspond to 'make run_tests' order
TEST_PROGS := test_kmod.sh \
@@ -40,7 +40,8 @@ TEST_PROGS := test_kmod.sh \
test_xdp_redirect.sh \
test_xdp_meta.sh \
test_offload.py \
- test_sock_addr.sh
+ test_sock_addr.sh \
+ test_tunnel.sh
# Compile but not part of 'make run_tests'
TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr
diff --git a/tools/testing/selftests/bpf/test_tunnel.sh
b/tools/testing/selftests/bpf/test_tunnel.sh
new file mode 100755
index 000000000000..7fce054eaebd
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tunnel.sh
@@ -0,0 +1,651 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# End-to-end eBPF tunnel test suite
+# The script tests BPF network tunnel implementation.
+#
+# Topology:
+# ---------
+# root namespace | at_ns0 namespace
+# |
+# ----------- | -----------
+# | tnl dev | | | tnl dev | (overlay network)
+# ----------- | -----------
+# metadata-mode | native-mode
+# with bpf |
+# |
+# ---------- | ----------
+# | veth1 | --------- | veth0 | (underlay network)
+# ---------- peer ----------
+#
+#
+# Device Configuration
+# --------------------
+# Root namespace with metadata-mode tunnel + BPF
+# Device names and addresses:
+# veth1 IP: 172.16.1.200, IPv6: 00::22 (underlay)
+# tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200 (overlay)
+#
+# Namespace at_ns0 with native tunnel
+# Device names and addresses:
+# veth0 IPv4: 172.16.1.100, IPv6: 00::11 (underlay)
+# tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100 (overlay)
+#
+#
+# End-to-end ping packet flow
+# ---------------------------
+# Most of the tests start by namespace creation, device configuration,
+# then ping the underlay and overlay network. When doing 'ping 10.1.1.100'
+# from root namespace, the following operations happen:
+# 1) Route lookup shows 10.1.1.100/24 belongs to tnl dev, fwd to tnl dev.
+# 2) Tnl device's egress BPF program is triggered and set the tunnel metadata,
+# with remote_ip=172.16.1.200 and others.
+# 3) Outer tunnel header is prepended and route the packet to veth1's egress
+# 4) veth0's ingress queue receive the tunneled packet at namespace at_ns0
+# 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet
+# 6) Forward the packet to the overlay tnl dev
+
+PING_ARG="-c 3 -w 10 -q"
+ret=0
+GREEN='\033[0;92m'
+RED='\033[0;31m'
+NC='\033[0m' # No Color
+
+config_device()
+{
+ ip netns add at_ns0
+ ip link add veth0 type veth peer name veth1
+ ip link set veth0 netns at_ns0
+ ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip link set dev veth1 up mtu 1500
+ ip addr add dev veth1 172.16.1.200/24
+}
+
+add_gre_tunnel()
+{
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq key 2 \
+ local 172.16.1.100 remote 172.16.1.200
+ 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 link add dev $DEV type $TYPE key 2 external
+ ip link set dev $DEV up
+ ip addr add dev $DEV 10.1.1.200/24
+}
+
+add_ip6gretap_tunnel()
+{
+
+ # assign ipv6 address
+ ip netns exec at_ns0 ip addr add ::11/96 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip addr add dev veth1 ::22/96
+ ip link set dev veth1 up
+
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \
+ local ::11 remote ::22
+
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ ip netns exec at_ns0 ip addr add dev $DEV_NS fc80::100/96
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external
+ ip addr add dev $DEV 10.1.1.200/24
+ ip addr add dev $DEV fc80::200/24
+ ip link set dev $DEV up
+}
+
+add_erspan_tunnel()
+{
+ # at_ns0 namespace
+ if [ "$1" == "v1" ]; then
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq key 2 \
+ local 172.16.1.100 remote 172.16.1.200 \
+ erspan_ver 1 erspan 123
+ else
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq key 2 \
+ local 172.16.1.100 remote 172.16.1.200 \
+ erspan_ver 2 erspan_dir egress erspan_hwid 3
+ fi
+ 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 link add dev $DEV type $TYPE external
+ ip link set dev $DEV up
+ ip addr add dev $DEV 10.1.1.200/24
+}
+
+add_ip6erspan_tunnel()
+{
+
+ # assign ipv6 address
+ ip netns exec at_ns0 ip addr add ::11/96 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip addr add dev veth1 ::22/96
+ ip link set dev veth1 up
+
+ # at_ns0 namespace
+ if [ "$1" == "v1" ]; then
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq key 2 \
+ local ::11 remote ::22 \
+ erspan_ver 1 erspan 123
+ else
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq key 2 \
+ local ::11 remote ::22 \
+ erspan_ver 2 erspan_dir egress erspan_hwid 7
+ fi
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external
+ ip addr add dev $DEV 10.1.1.200/24
+ ip link set dev $DEV up
+}
+
+add_vxlan_tunnel()
+{
+ # Set static ARP entry here because iptables set-mark works
+ # on L3 packet, as a result not applying to ARP packets,
+ # causing errors at get_tunnel_{key/opt}.
+
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE id 2 dstport 4789 gbp remote
172.16.1.200
+ ip netns exec at_ns0 ip link set dev $DEV_NS address 52:54:00:d9:01:00
up
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00
+ ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external gbp dstport 4789
+ ip link set dev $DEV address 52:54:00:d9:02:00 up
+ ip addr add dev $DEV 10.1.1.200/24
+ arp -s 10.1.1.100 52:54:00:d9:01:00
+}
+
+add_ip6vxlan_tunnel()
+{
+ #ip netns exec at_ns0 ip -4 addr del 172.16.1.100 dev veth0
+ ip netns exec at_ns0 ip -6 addr add ::11/96 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ #ip -4 addr del 172.16.1.200 dev veth1
+ ip -6 addr add dev veth1 ::22/96
+ ip link set dev veth1 up
+
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE id 22 dstport 4789 \
+ local ::11 remote ::22
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+
+ echo "set dev done" > /dev/kmsg
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external dstport 4789
+ ip addr add dev $DEV 10.1.1.200/24
+ ip link set dev $DEV up
+}
+
+add_geneve_tunnel()
+{
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE \
+ id 2 dstport 6081 remote 172.16.1.200
+ 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 link add dev $DEV type $TYPE dstport 6081 external
+ ip link set dev $DEV up
+ ip addr add dev $DEV 10.1.1.200/24
+}
+
+add_ip6geneve_tunnel()
+{
+ ip netns exec at_ns0 ip addr add ::11/96 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip addr add dev veth1 ::22/96
+ ip link set dev veth1 up
+
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE id 22 \
+ remote ::22 # geneve has no local option
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external
+ ip addr add dev $DEV 10.1.1.200/24
+ ip link set dev $DEV up
+}
+
+add_ipip_tunnel()
+{
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE \
+ local 172.16.1.100 remote 172.16.1.200
+ 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 link add dev $DEV type $TYPE external
+ ip link set dev $DEV up
+ ip addr add dev $DEV 10.1.1.200/24
+}
+
+add_ipip6tnl_tunnel()
+{
+ ip netns exec at_ns0 ip addr add ::11/96 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip addr add dev veth1 ::22/96
+ ip link set dev veth1 up
+
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE \
+ local ::11 remote ::22
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external
+ ip addr add dev $DEV 10.1.1.200/24
+ ip link set dev $DEV up
+}
+
+test_gre()
+{
+ TYPE=gretap
+ DEV_NS=gretap00
+ DEV=gretap11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_gre_tunnel
+ attach_bpf $DEV gre_set_tunnel gre_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: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ip6gre()
+{
+ TYPE=ip6gre
+ DEV_NS=ip6gre00
+ DEV=ip6gre11
+ ret=0
+
+ check $TYPE
+ config_device
+ # reuse the ip6gretap function
+ add_ip6gretap_tunnel
+ attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
+ # underlay
+ ping6 $PING_ARG ::11
+ # overlay: ipv4 over ipv6
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ # overlay: ipv6 over ipv6
+ ip netns exec at_ns0 ping6 $PING_ARG fc80::200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ip6gretap()
+{
+ TYPE=ip6gretap
+ DEV_NS=ip6gretap00
+ DEV=ip6gretap11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ip6gretap_tunnel
+ attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
+ # underlay
+ ping6 $PING_ARG ::11
+ # overlay: ipv4 over ipv6
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ # overlay: ipv6 over ipv6
+ ip netns exec at_ns0 ping6 $PING_ARG fc80::200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_erspan()
+{
+ TYPE=erspan
+ DEV_NS=erspan00
+ DEV=erspan11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_erspan_tunnel $1
+ attach_bpf $DEV erspan_set_tunnel erspan_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: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ip6erspan()
+{
+ TYPE=ip6erspan
+ DEV_NS=ip6erspan00
+ DEV=ip6erspan11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ip6erspan_tunnel $1
+ attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel
+ ping6 $PING_ARG ::11
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_vxlan()
+{
+ TYPE=vxlan
+ DEV_NS=vxlan00
+ DEV=vxlan11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_vxlan_tunnel
+ attach_bpf $DEV vxlan_set_tunnel vxlan_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: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ip6vxlan()
+{
+ TYPE=vxlan
+ DEV_NS=ip6vxlan00
+ DEV=ip6vxlan11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ip6vxlan_tunnel
+ ip link set dev veth1 mtu 1500
+ attach_bpf $DEV ip6vxlan_set_tunnel ip6vxlan_get_tunnel
+ echo "set bpf done" > /dev/kmsg
+ # underlay
+ ping6 $PING_ARG ::11
+ echo "ping underlay" > /dev/kmsg
+ # ip4 over ip6
+ ping $PING_ARG 10.1.1.100
+ echo "ping overlay" > /dev/kmsg
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: ip6$TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
+}
+
+test_geneve()
+{
+ TYPE=geneve
+ DEV_NS=geneve00
+ DEV=geneve11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_geneve_tunnel
+ attach_bpf $DEV geneve_set_tunnel geneve_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: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ip6geneve()
+{
+ TYPE=geneve
+ DEV_NS=ip6geneve00
+ DEV=ip6geneve11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ip6geneve_tunnel
+ attach_bpf $DEV ip6geneve_set_tunnel ip6geneve_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 ${RED}"FAIL: ip6$TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
+}
+
+test_ipip()
+{
+ TYPE=ipip
+ DEV_NS=ipip00
+ DEV=ipip11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ipip_tunnel
+ ip link set dev veth1 mtu 1500
+ attach_bpf $DEV ipip_set_tunnel ipip_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: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ipip6()
+{
+ TYPE=ip6tnl
+ DEV_NS=ipip6tnl00
+ DEV=ipip6tnl11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ipip6tnl_tunnel
+ ip link set dev veth1 mtu 1500
+ attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel
+ # underlay
+ ping6 $PING_ARG ::11
+ # ip4 over ip6
+ 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: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+attach_bpf()
+{
+ DEV=$1
+ SET=$2
+ GET=$3
+ tc qdisc add dev $DEV clsact
+ tc filter add dev $DEV egress bpf da obj test_tunnel_kern.o sec $SET
+ tc filter add dev $DEV ingress bpf da obj test_tunnel_kern.o sec $GET
+}
+
+cleanup()
+{
+ ip netns delete at_ns0 2> /dev/null
+ ip link del veth1 2> /dev/null
+ ip link del ipip11 2> /dev/null
+ ip link del ipip6tnl11 2> /dev/null
+ ip link del gretap11 2> /dev/null
+ ip link del ip6gre11 2> /dev/null
+ ip link del ip6gretap11 2> /dev/null
+ ip link del vxlan11 2> /dev/null
+ ip link del ip6vxlan11 2> /dev/null
+ ip link del geneve11 2> /dev/null
+ ip link del ip6geneve11 2> /dev/null
+ ip link del erspan11 2> /dev/null
+ ip link del ip6erspan11 2> /dev/null
+}
+
+cleanup_exit()
+{
+ echo "CATCH SIGKILL or SIGINT, cleanup and exit"
+ cleanup
+ exit 0
+}
+
+check()
+{
+ ip link help $1 2>&1 | grep -q "^Usage:"
+ if [ $? -ne 0 ];then
+ echo "SKIP $1: iproute2 not support"
+ cleanup
+ return 1
+ fi
+}
+
+enable_debug()
+{
+ echo 'file ip_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
+ echo 'file ip6_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
+ echo 'file vxlan.c +p' > /sys/kernel/debug/dynamic_debug/control
+ echo 'file geneve.c +p' > /sys/kernel/debug/dynamic_debug/control
+ echo 'file ipip.c +p' > /sys/kernel/debug/dynamic_debug/control
+}
+
+check_err()
+{
+ if [ $ret -eq 0 ]; then
+ ret=$1
+ fi
+}
+
+bpf_tunnel_test()
+{
+ echo "Testing GRE tunnel..."
+ test_gre
+ echo "Testing IP6GRE tunnel..."
+ test_ip6gre
+ echo "Testing IP6GRETAP tunnel..."
+ test_ip6gretap
+ echo "Testing ERSPAN tunnel..."
+ test_erspan v2
+ echo "Testing IP6ERSPAN tunnel..."
+ test_ip6erspan v2
+ echo "Testing VXLAN tunnel..."
+ test_vxlan
+ echo "Testing IP6VXLAN tunnel..."
+ test_ip6vxlan
+ echo "Testing GENEVE tunnel..."
+ test_geneve
+ echo "Testing IP6GENEVE tunnel..."
+ test_ip6geneve
+ echo "Testing IPIP tunnel..."
+ test_ipip
+ echo "Testing IPIP6 tunnel..."
+ test_ipip6
+}
+
+trap cleanup 0 3 6
+trap cleanup_exit 2 9
+
+cleanup
+bpf_tunnel_test
+
+exit 0
diff --git a/tools/testing/selftests/bpf/test_tunnel_kern.c
b/tools/testing/selftests/bpf/test_tunnel_kern.c
new file mode 100644
index 000000000000..0bf642c530fd
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tunnel_kern.c
@@ -0,0 +1,691 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2016 VMware
+ * Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stddef.h>
+#include <string.h>
+#include <arpa/inet.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <linux/tcp.h>
+#include <linux/socket.h>
+#include <linux/pkt_cls.h>
+#include <linux/erspan.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define ERROR(ret) do {\
+ char fmt[] = "ERROR line:%d ret:%d\n";\
+ bpf_trace_printk(fmt, sizeof(fmt), __LINE__, ret); \
+ } while(0)
+
+int _version SEC("version") = 1;
+
+struct geneve_opt {
+ __be16 opt_class;
+ __u8 type;
+ __u8 length:5;
+ __u8 r3:1;
+ __u8 r2:1;
+ __u8 r1:1;
+ __u8 opt_data[8]; /* hard-coded to 8 byte */
+};
+
+struct vxlan_metadata {
+ __u32 gbp;
+};
+
+SEC("gre_set_tunnel")
+int _gre_set_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+ key.tunnel_id = 2;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_ZERO_CSUM_TX | BPF_F_SEQ_NUMBER);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("gre_get_tunnel")
+int _gre_get_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+ char fmt[] = "key %d remote ip 0x%x\n";
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt), key.tunnel_id, key.remote_ipv4);
+ return TC_ACT_OK;
+}
+
+SEC("ip6gretap_set_tunnel")
+int _ip6gretap_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key;
+ int ret;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
+ key.tunnel_id = 2;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+ key.tunnel_label = 0xabcde;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX |
+ BPF_F_SEQ_NUMBER);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ip6gretap_get_tunnel")
+int _ip6gretap_get_tunnel(struct __sk_buff *skb)
+{
+ char fmt[] = "key %d remote ip6 ::%x label %x\n";
+ struct bpf_tunnel_key key;
+ int ret;
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv6[3], key.tunnel_label);
+
+ return TC_ACT_OK;
+}
+
+SEC("erspan_set_tunnel")
+int _erspan_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key;
+ struct erspan_metadata md;
+ int ret;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+ key.tunnel_id = 2;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_ZERO_CSUM_TX);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ __builtin_memset(&md, 0, sizeof(md));
+#ifdef ERSPAN_V1
+ md.version = 1;
+ md.u.index = bpf_htonl(123);
+#else
+ __u8 direction = 1;
+ __u8 hwid = 7;
+
+ md.version = 2;
+ md.u.md2.dir = direction;
+ md.u.md2.hwid = hwid & 0xf;
+ md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
+#endif
+
+ ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("erspan_get_tunnel")
+int _erspan_get_tunnel(struct __sk_buff *skb)
+{
+ char fmt[] = "key %d remote ip 0x%x erspan version %d\n";
+ struct bpf_tunnel_key key;
+ struct erspan_metadata md;
+ __u32 index;
+ int ret;
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv4, md.version);
+
+#ifdef ERSPAN_V1
+ char fmt2[] = "\tindex %x\n";
+
+ index = bpf_ntohl(md.u.index);
+ bpf_trace_printk(fmt2, sizeof(fmt2), index);
+#else
+ char fmt2[] = "\tdirection %d hwid %x timestamp %u\n";
+
+ bpf_trace_printk(fmt2, sizeof(fmt2),
+ md.u.md2.dir,
+ (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
+ bpf_ntohl(md.u.md2.timestamp));
+#endif
+
+ return TC_ACT_OK;
+}
+
+SEC("ip4ip6erspan_set_tunnel")
+int _ip4ip6erspan_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key;
+ struct erspan_metadata md;
+ int ret;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv6[3] = bpf_htonl(0x11);
+ key.tunnel_id = 2;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ __builtin_memset(&md, 0, sizeof(md));
+
+#ifdef ERSPAN_V1
+ md.u.index = bpf_htonl(123);
+ md.version = 1;
+#else
+ __u8 direction = 0;
+ __u8 hwid = 17;
+
+ md.version = 2;
+ md.u.md2.dir = direction;
+ md.u.md2.hwid = hwid & 0xf;
+ md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
+#endif
+
+ ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ip4ip6erspan_get_tunnel")
+int _ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
+{
+ char fmt[] = "ip6erspan get key %d remote ip6 ::%x erspan version %d\n";
+ struct bpf_tunnel_key key;
+ struct erspan_metadata md;
+ __u32 index;
+ int ret;
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv4, md.version);
+
+#ifdef ERSPAN_V1
+ char fmt2[] = "\tindex %x\n";
+
+ index = bpf_ntohl(md.u.index);
+ bpf_trace_printk(fmt2, sizeof(fmt2), index);
+#else
+ char fmt2[] = "\tdirection %d hwid %x timestamp %u\n";
+
+ bpf_trace_printk(fmt2, sizeof(fmt2),
+ md.u.md2.dir,
+ (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
+ bpf_ntohl(md.u.md2.timestamp));
+#endif
+
+ return TC_ACT_OK;
+}
+
+SEC("vxlan_set_tunnel")
+int _vxlan_set_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+ struct vxlan_metadata md;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+ key.tunnel_id = 2;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_ZERO_CSUM_TX);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ md.gbp = 0x800FF; /* Set VXLAN Group Policy extension */
+ ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("vxlan_get_tunnel")
+int _vxlan_get_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+ struct vxlan_metadata md;
+ char fmt[] = "key %d remote ip 0x%x vxlan gbp 0x%x\n";
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv4, md.gbp);
+
+ return TC_ACT_OK;
+}
+
+SEC("ip6vxlan_set_tunnel")
+int _ip6vxlan_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key;
+ int ret;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
+ key.tunnel_id = 22;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ip6vxlan_get_tunnel")
+int _ip6vxlan_get_tunnel(struct __sk_buff *skb)
+{
+ char fmt[] = "key %d remote ip6 ::%x label %x\n";
+ struct bpf_tunnel_key key;
+ int ret;
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv6[3], key.tunnel_label);
+
+ return TC_ACT_OK;
+}
+
+SEC("geneve_set_tunnel")
+int _geneve_set_tunnel(struct __sk_buff *skb)
+{
+ int ret, ret2;
+ struct bpf_tunnel_key key;
+ struct geneve_opt gopt;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+ key.tunnel_id = 2;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ __builtin_memset(&gopt, 0x0, sizeof(gopt));
+ gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */
+ gopt.type = 0x08;
+ gopt.r1 = 0;
+ gopt.r2 = 0;
+ gopt.r3 = 0;
+ gopt.length = 2; /* 4-byte multiple */
+ *(int *) &gopt.opt_data = bpf_htonl(0xdeadbeef);
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_ZERO_CSUM_TX);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("geneve_get_tunnel")
+int _geneve_get_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+ struct geneve_opt gopt;
+ char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n";
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv4, gopt.opt_class);
+ return TC_ACT_OK;
+}
+
+SEC("ip6geneve_set_tunnel")
+int _ip6geneve_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key;
+ struct geneve_opt gopt;
+ int ret;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
+ key.tunnel_id = 22;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ __builtin_memset(&gopt, 0x0, sizeof(gopt));
+ gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */
+ gopt.type = 0x08;
+ gopt.r1 = 0;
+ gopt.r2 = 0;
+ gopt.r3 = 0;
+ gopt.length = 2; /* 4-byte multiple */
+ *(int *) &gopt.opt_data = bpf_htonl(0xfeedbeef);
+
+ ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ip6geneve_get_tunnel")
+int _ip6geneve_get_tunnel(struct __sk_buff *skb)
+{
+ char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n";
+ struct bpf_tunnel_key key;
+ struct geneve_opt gopt;
+ int ret;
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv4, gopt.opt_class);
+
+ return TC_ACT_OK;
+}
+
+SEC("ipip_set_tunnel")
+int _ipip_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key = {};
+ void *data = (void *)(long)skb->data;
+ struct iphdr *iph = data;
+ struct tcphdr *tcp = data + sizeof(*iph);
+ void *data_end = (void *)(long)skb->data_end;
+ int ret;
+
+ /* single length check */
+ if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
+ ERROR(1);
+ return TC_ACT_SHOT;
+ }
+
+ key.tunnel_ttl = 64;
+ if (iph->protocol == IPPROTO_ICMP) {
+ key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+ } else {
+ if (iph->protocol != IPPROTO_TCP || iph->ihl != 5)
+ return TC_ACT_SHOT;
+
+ if (tcp->dest == bpf_htons(5200))
+ key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+ else if (tcp->dest == bpf_htons(5201))
+ key.remote_ipv4 = 0xac100165; /* 172.16.1.101 */
+ else
+ return TC_ACT_SHOT;
+ }
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ipip_get_tunnel")
+int _ipip_get_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+ char fmt[] = "remote ip 0x%x\n";
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt), key.remote_ipv4);
+ return TC_ACT_OK;
+}
+
+SEC("ipip6_set_tunnel")
+int _ipip6_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key = {};
+ void *data = (void *)(long)skb->data;
+ struct iphdr *iph = data;
+ struct tcphdr *tcp = data + sizeof(*iph);
+ void *data_end = (void *)(long)skb->data_end;
+ int ret;
+
+ /* single length check */
+ if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
+ ERROR(1);
+ return TC_ACT_SHOT;
+ }
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ipip6_get_tunnel")
+int _ipip6_get_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+ char fmt[] = "remote ip6 %x::%x\n";
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]),
+ bpf_htonl(key.remote_ipv6[3]));
+ return TC_ACT_OK;
+}
+
+SEC("ip6ip6_set_tunnel")
+int _ip6ip6_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key = {};
+ void *data = (void *)(long)skb->data;
+ struct ipv6hdr *iph = data;
+ struct tcphdr *tcp = data + sizeof(*iph);
+ void *data_end = (void *)(long)skb->data_end;
+ int ret;
+
+ /* single length check */
+ if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
+ ERROR(1);
+ return TC_ACT_SHOT;
+ }
+
+ key.remote_ipv6[0] = bpf_htonl(0x2401db00);
+ key.tunnel_ttl = 64;
+
+ if (iph->nexthdr == 58 /* NEXTHDR_ICMP */) {
+ key.remote_ipv6[3] = bpf_htonl(1);
+ } else {
+ if (iph->nexthdr != 6 /* NEXTHDR_TCP */) {
+ ERROR(iph->nexthdr);
+ return TC_ACT_SHOT;
+ }
+
+ if (tcp->dest == bpf_htons(5200)) {
+ key.remote_ipv6[3] = bpf_htonl(1);
+ } else if (tcp->dest == bpf_htons(5201)) {
+ key.remote_ipv6[3] = bpf_htonl(2);
+ } else {
+ ERROR(tcp->dest);
+ return TC_ACT_SHOT;
+ }
+ }
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ip6ip6_get_tunnel")
+int _ip6ip6_get_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+ char fmt[] = "remote ip6 %x::%x\n";
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]),
+ bpf_htonl(key.remote_ipv6[3]));
+ return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";
--
2.7.4
