new file mode 100644
@@ -0,0 +1,395 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/*
+ * End-to-end eBPF tunnel test suite
+ * The file 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 1: 172.16.1.200, IPv6: 00::22 (underlay)
+ * IP 2: 172.16.1.20, IPv6: 00::bb (underlay)
+ * tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200, IPv6: 1::22 (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, IPv6: 1::11 (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 local_ip=172.16.1.200, remote_ip=172.16.1.100. BPF program choose
+ * the primary or secondary ip of veth1 as the local ip of tunnel. The
+ * choice is made based on the value of bpf map local_ip_map.
+ * 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.
+ */
+
+#include <arpa/inet.h>
+#include <linux/if.h>
+#include <linux/if_tun.h>
+#include <linux/limits.h>
+#include <linux/sysctl.h>
+#include <linux/time_types.h>
+#include <linux/net_tstamp.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "test_tunnel_kern.skel.h"
+
+#define IP4_ADDR_VETH0 "172.16.1.100"
+#define IP4_ADDR1_VETH1 "172.16.1.200"
+#define IP4_ADDR2_VETH1 "172.16.1.20"
+#define IP4_ADDR_TUNL_DEV0 "10.1.1.100"
+#define IP4_ADDR_TUNL_DEV1 "10.1.1.200"
+
+#define IP6_ADDR_VETH0 "::11"
+#define IP6_ADDR1_VETH1 "::22"
+#define IP6_ADDR2_VETH1 "::bb"
+
+#define IP4_ADDR1_HEX_VETH1 0xac1001c8
+#define IP4_ADDR2_HEX_VETH1 0xac100114
+#define IP6_ADDR1_HEX_VETH1 0x22
+#define IP6_ADDR2_HEX_VETH1 0xbb
+
+#define MAC_TUNL_DEV0 "52:54:00:d9:01:00"
+#define MAC_TUNL_DEV1 "52:54:00:d9:02:00"
+
+#define VXLAN_TUNL_DEV0 "vxlan00"
+#define VXLAN_TUNL_DEV1 "vxlan11"
+#define IP6VXLAN_TUNL_DEV0 "ip6vxlan00"
+#define IP6VXLAN_TUNL_DEV1 "ip6vxlan11"
+
+#define SRC_INGRESS_PROG_PIN_FILE "/sys/fs/bpf/tc/test_tunnel_ingress_src"
+#define SRC_EGRESS_PROG_PIN_FILE "/sys/fs/bpf/tc/test_tunnel_egress_src"
+#define DST_EGRESS_PROG_PIN_FILE "/sys/fs/bpf/tc/test_tunnel_egress_dst"
+
+#define PING_ARGS "-c 3 -w 10 -q"
+
+#define SYS(fmt, ...) \
+ ({ \
+ char cmd[1024]; \
+ snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__); \
+ if (!ASSERT_OK(system(cmd), cmd)) \
+ goto fail; \
+ })
+
+#define SYS_NOFAIL(fmt, ...) \
+ ({ \
+ char cmd[1024]; \
+ snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__); \
+ system(cmd); \
+ })
+
+static int config_device(void)
+{
+ SYS("ip netns add at_ns0");
+ SYS("ip link add veth0 type veth peer name veth1");
+ SYS("ip link set veth0 netns at_ns0");
+ SYS("ip addr add " IP4_ADDR1_VETH1 "/24 dev veth1");
+ SYS("ip link set dev veth1 up mtu 1500");
+ SYS("ip netns exec at_ns0 ip addr add " IP4_ADDR_VETH0 "/24 dev veth0");
+ SYS("ip netns exec at_ns0 ip link set dev veth0 up mtu 1500");
+
+ return 0;
+fail:
+ return -1;
+}
+
+static void cleanup(void)
+{
+ SYS_NOFAIL("test -f /var/run/netns/at_ns0 && ip netns delete at_ns0");
+ SYS_NOFAIL("ip link del veth1 2> /dev/null");
+ SYS_NOFAIL("ip link del %s 2> /dev/null", VXLAN_TUNL_DEV1);
+ SYS_NOFAIL("ip link del %s 2> /dev/null", IP6VXLAN_TUNL_DEV1);
+
+ SYS_NOFAIL("rm -rf %s", SRC_INGRESS_PROG_PIN_FILE);
+ SYS_NOFAIL("rm -rf %s", SRC_EGRESS_PROG_PIN_FILE);
+}
+
+static int add_vxlan_tunnel(void)
+{
+ /* at_ns0 namespace */
+ SYS("ip netns exec at_ns0 ip link add dev %s type vxlan external gbp dstport 4789",
+ VXLAN_TUNL_DEV0);
+ SYS("ip netns exec at_ns0 ip link set dev %s address %s up",
+ VXLAN_TUNL_DEV0, MAC_TUNL_DEV0);
+ SYS("ip netns exec at_ns0 ip addr add dev %s %s/24",
+ VXLAN_TUNL_DEV0, IP4_ADDR_TUNL_DEV0);
+ SYS("ip netns exec at_ns0 ip neigh add %s lladdr %s dev %s",
+ IP4_ADDR_TUNL_DEV1, MAC_TUNL_DEV1, VXLAN_TUNL_DEV0);
+
+ /* root namespace */
+ SYS("ip link add dev %s type vxlan external gbp dstport 4789",
+ VXLAN_TUNL_DEV1);
+ SYS("ip link set dev %s address %s up", VXLAN_TUNL_DEV1, MAC_TUNL_DEV1);
+ SYS("ip addr add dev %s %s/24", VXLAN_TUNL_DEV1, IP4_ADDR_TUNL_DEV1);
+ SYS("ip neigh add %s lladdr %s dev %s",
+ IP4_ADDR_TUNL_DEV0, MAC_TUNL_DEV0, VXLAN_TUNL_DEV1);
+
+ return 0;
+fail:
+ return -1;
+}
+
+static int add_ip6vxlan_tunnel(void)
+{
+ SYS("ip netns exec at_ns0 ip -6 addr add %s/96 dev veth0",
+ IP6_ADDR_VETH0);
+ SYS("ip netns exec at_ns0 ip link set dev veth0 up");
+ SYS("ip -6 addr add %s/96 dev veth1", IP6_ADDR1_VETH1);
+ SYS("ip link set dev veth1 up");
+
+ /* at_ns0 namespace */
+ SYS("ip netns exec at_ns0 ip link add dev %s type vxlan external dstport 4789",
+ IP6VXLAN_TUNL_DEV0);
+ SYS("ip netns exec at_ns0 ip addr add dev %s %s/24",
+ IP6VXLAN_TUNL_DEV0, IP4_ADDR_TUNL_DEV0);
+ SYS("ip netns exec at_ns0 ip link set dev %s address %s up",
+ IP6VXLAN_TUNL_DEV0, MAC_TUNL_DEV0);
+
+ /* root namespace */
+ SYS("ip link add dev %s type vxlan external dstport 4789",
+ IP6VXLAN_TUNL_DEV1);
+ SYS("ip addr add dev %s %s/24", IP6VXLAN_TUNL_DEV1, IP4_ADDR_TUNL_DEV1);
+ SYS("ip link set dev %s address %s up",
+ IP6VXLAN_TUNL_DEV1, MAC_TUNL_DEV1);
+
+ return 0;
+fail:
+ return -1;
+}
+
+static int test_ping4(void)
+{
+ /* underlay */
+ SYS("ping " PING_ARGS " %s > /dev/null", IP4_ADDR_VETH0);
+ /* overlay, ping root -> at_ns0 */
+ SYS("ping " PING_ARGS " %s > /dev/null", IP4_ADDR_TUNL_DEV0);
+
+ /* overlay, ping at_ns0 -> root */
+ SYS("ip netns exec at_ns0 ping " PING_ARGS " %s > /dev/null",
+ IP4_ADDR_TUNL_DEV1);
+ return 0;
+fail:
+ return -1;
+}
+
+static void test_vxlan_tunnel(void)
+{
+ struct test_tunnel_kern *skel = NULL;
+ struct nstoken *nstoken;
+ int local_ip_map_fd = 0, key = 0;
+ uint local_ip;
+ int err;
+
+ /* add vxlan tunnel */
+ err = add_vxlan_tunnel();
+ if (!ASSERT_OK(err, "add vxlan tunnel"))
+ goto done;
+
+ /* load and attach bpf prog to tunnel dev tc hook point */
+ skel = test_tunnel_kern__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+ goto done;
+ err = bpf_program__pin(skel->progs.vxlan_set_tunnel_src,
+ SRC_EGRESS_PROG_PIN_FILE);
+ if (!ASSERT_OK(err, "pin " SRC_EGRESS_PROG_PIN_FILE))
+ goto done;
+ err = bpf_program__pin(skel->progs.vxlan_get_tunnel_src,
+ SRC_INGRESS_PROG_PIN_FILE);
+ if (!ASSERT_OK(err, "pin " SRC_INGRESS_PROG_PIN_FILE))
+ goto done;
+ SYS("tc qdisc add dev %s clsact", VXLAN_TUNL_DEV1);
+ SYS("tc filter add dev %s ingress bpf da object-pinned %s",
+ VXLAN_TUNL_DEV1, SRC_INGRESS_PROG_PIN_FILE);
+ SYS("tc filter add dev %s egress bpf da object-pinned %s",
+ VXLAN_TUNL_DEV1, SRC_EGRESS_PROG_PIN_FILE);
+
+ local_ip_map_fd = bpf_map__fd(skel->maps.local_ip_map);
+ if (!ASSERT_GE(local_ip_map_fd, 0, "get local_ip_map fd "))
+ goto done;
+
+ /* load and attach prog set_md to tunnel dev tc hook point at_ns0 */
+ nstoken = open_netns("at_ns0");
+ if (!ASSERT_OK_PTR(nstoken, "setns src"))
+ goto fail;
+ err = bpf_program__pin(skel->progs.vxlan_set_tunnel_dst,
+ DST_EGRESS_PROG_PIN_FILE);
+ if (!ASSERT_OK(err, "pin " DST_EGRESS_PROG_PIN_FILE))
+ goto done;
+ SYS("tc qdisc add dev %s clsact", VXLAN_TUNL_DEV0);
+ SYS("tc filter add dev %s egress bpf da object-pinned %s",
+ VXLAN_TUNL_DEV0, DST_EGRESS_PROG_PIN_FILE);
+ close_netns(nstoken);
+
+ /* use veth1 ip 1 as tunnel source ip */
+ local_ip = IP4_ADDR1_HEX_VETH1;
+ err = bpf_map_update_elem(local_ip_map_fd, &key, &local_ip, BPF_ANY);
+ if (!ASSERT_OK(err, "update bpf local_ip_map"))
+ goto done;
+
+ /* ping test */
+ err = test_ping4();
+ if (!ASSERT_OK(err, "test ping ipv4"))
+ goto done;
+
+ /* use veth1 ip 2 as tunnel source ip */
+ SYS("ip addr add " IP4_ADDR2_VETH1 "/24 dev veth1");
+ local_ip = IP4_ADDR2_HEX_VETH1;
+ err = bpf_map_update_elem(local_ip_map_fd, &key, &local_ip, BPF_ANY);
+ if (!ASSERT_OK(err, "update bpf local_ip_map"))
+ goto done;
+
+ /* ping test */
+ err = test_ping4();
+ if (!ASSERT_OK(err, "test ping ipv4"))
+ goto done;
+
+fail:
+done:
+ if (local_ip_map_fd >= 0)
+ close(local_ip_map_fd);
+ if (skel)
+ test_tunnel_kern__destroy(skel);
+}
+
+static void test_ip6vxlan_tunnel(void)
+{
+ struct test_tunnel_kern *skel = NULL;
+ struct nstoken *nstoken;
+ int local_ip_map_fd = 0, key = 0;
+ uint local_ip;
+ int err;
+
+ /* add vxlan tunnel */
+ err = add_ip6vxlan_tunnel();
+ if (!ASSERT_OK(err, "add ip6vxlan tunnel"))
+ goto done;
+
+ /* load and attach bpf prog to tunnel dev tc hook point */
+ skel = test_tunnel_kern__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+ goto done;
+ err = bpf_program__pin(skel->progs.ip6vxlan_set_tunnel_src,
+ SRC_EGRESS_PROG_PIN_FILE);
+ if (!ASSERT_OK(err, "pin " SRC_EGRESS_PROG_PIN_FILE))
+ goto done;
+ err = bpf_program__pin(skel->progs.ip6vxlan_get_tunnel_src,
+ SRC_INGRESS_PROG_PIN_FILE);
+ if (!ASSERT_OK(err, "pin " SRC_INGRESS_PROG_PIN_FILE))
+ goto done;
+ SYS("tc qdisc add dev %s clsact", IP6VXLAN_TUNL_DEV1);
+ SYS("tc filter add dev %s ingress bpf da object-pinned %s",
+ IP6VXLAN_TUNL_DEV1, SRC_INGRESS_PROG_PIN_FILE);
+ SYS("tc filter add dev %s egress bpf da object-pinned %s",
+ IP6VXLAN_TUNL_DEV1, SRC_EGRESS_PROG_PIN_FILE);
+
+ local_ip_map_fd = bpf_map__fd(skel->maps.local_ip_map);
+ if (!ASSERT_GE(local_ip_map_fd, 0, "get local_ip_map fd "))
+ goto done;
+
+ /* load and attach prog set_md to tunnel dev tc hook point at_ns0 */
+ nstoken = open_netns("at_ns0");
+ if (!ASSERT_OK_PTR(nstoken, "setns src"))
+ goto fail;
+ err = bpf_program__pin(skel->progs.ip6vxlan_set_tunnel_dst,
+ DST_EGRESS_PROG_PIN_FILE);
+ if (!ASSERT_OK(err, "pin " DST_EGRESS_PROG_PIN_FILE))
+ goto done;
+ SYS("tc qdisc add dev %s clsact", IP6VXLAN_TUNL_DEV0);
+ SYS("tc filter add dev %s egress bpf da object-pinned %s",
+ IP6VXLAN_TUNL_DEV0, DST_EGRESS_PROG_PIN_FILE);
+ close_netns(nstoken);
+
+ /* use veth1 ip 1 as tunnel source ip */
+ local_ip = IP6_ADDR1_HEX_VETH1;
+ err = bpf_map_update_elem(local_ip_map_fd, &key, &local_ip, BPF_ANY);
+ if (!ASSERT_OK(err, "update bpf local_ip_map"))
+ goto done;
+
+ /* ping test */
+ err = test_ping4();
+ if (!ASSERT_OK(err, "test ping ipv4"))
+ goto done;
+
+ /* use veth1 ip 2 as tunnel source ip */
+ SYS("ip -6 addr add " IP6_ADDR2_VETH1 "/96 dev veth1");
+ local_ip = IP6_ADDR2_HEX_VETH1;
+ err = bpf_map_update_elem(local_ip_map_fd, &key, &local_ip, BPF_ANY);
+ if (!ASSERT_OK(err, "update bpf local_ip_map"))
+ goto done;
+
+ /* ping test */
+ err = test_ping4();
+ if (!ASSERT_OK(err, "test ping ipv4"))
+ goto done;
+
+fail:
+done:
+ if (local_ip_map_fd >= 0)
+ close(local_ip_map_fd);
+ if (skel)
+ test_tunnel_kern__destroy(skel);
+}
+
+#define RUN_TEST(name) \
+ ({ \
+ if (test__start_subtest(#name)) { \
+ if (ASSERT_OK(config_device(), "config device"))\
+ test_ ## name(); \
+ cleanup(); \
+ } \
+ })
+
+static void *test_tunnel_run_tests(void *arg)
+{
+ cleanup();
+
+ RUN_TEST(vxlan_tunnel);
+ RUN_TEST(ip6vxlan_tunnel);
+
+ return NULL;
+}
+
+void serial_test_tunnel(void)
+{
+ pthread_t test_thread;
+ int err;
+
+ /* Run the tests in their own thread to isolate the namespace changes
+ * so they do not affect the environment of other tests.
+ * (specifically needed because of unshare(CLONE_NEWNS) in open_netns())
+ */
+ err = pthread_create(&test_thread, NULL, &test_tunnel_run_tests, NULL);
+ if (ASSERT_OK(err, "pthread_create"))
+ ASSERT_OK(pthread_join(test_thread, NULL), "pthread_join");
+}
@@ -40,8 +40,16 @@ struct vxlan_metadata {
__u32 gbp;
};
-SEC("gre_set_tunnel")
-int _gre_set_tunnel(struct __sk_buff *skb)
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u32);
+} local_ip_map SEC(".maps");
+
+
+SEC("tc")
+int gre_set_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
@@ -62,8 +70,8 @@ int _gre_set_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("gre_get_tunnel")
-int _gre_get_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int gre_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
@@ -79,8 +87,8 @@ int _gre_get_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("ip6gretap_set_tunnel")
-int _ip6gretap_set_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int ip6gretap_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
int ret;
@@ -103,8 +111,8 @@ int _ip6gretap_set_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("ip6gretap_get_tunnel")
-int _ip6gretap_get_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int ip6gretap_get_tunnel(struct __sk_buff *skb)
{
char fmt[] = "key %d remote ip6 ::%x label %x\n";
struct bpf_tunnel_key key;
@@ -123,8 +131,8 @@ int _ip6gretap_get_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("erspan_set_tunnel")
-int _erspan_set_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int erspan_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
struct erspan_metadata md;
@@ -166,8 +174,8 @@ int _erspan_set_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("erspan_get_tunnel")
-int _erspan_get_tunnel(struct __sk_buff *skb)
+SEC("tc")
+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;
@@ -207,8 +215,8 @@ int _erspan_get_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("ip4ip6erspan_set_tunnel")
-int _ip4ip6erspan_set_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int ip4ip6erspan_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
struct erspan_metadata md;
@@ -251,8 +259,8 @@ int _ip4ip6erspan_set_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("ip4ip6erspan_get_tunnel")
-int _ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
+SEC("tc")
+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;
@@ -293,14 +301,62 @@ int _ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("vxlan_set_tunnel")
-int _vxlan_set_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int vxlan_set_tunnel_dst(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+ struct vxlan_metadata md;
+ __u32 index = 0;
+ __u32 *local_ip = NULL;
+
+ local_ip = bpf_map_lookup_elem(&local_ip_map, &index);
+ if (!local_ip) {
+ log_err(ret);
+ return TC_ACT_SHOT;
+ }
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.local_ipv4 = 0xac100164; /* 172.16.1.100 */
+ key.remote_ipv4 = *local_ip;
+ 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) {
+ log_err(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) {
+ log_err(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("tc")
+int vxlan_set_tunnel_src(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
struct vxlan_metadata md;
+ __u32 index = 0;
+ __u32 *local_ip = NULL;
+
+ local_ip = bpf_map_lookup_elem(&local_ip_map, &index);
+ if (!local_ip) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
__builtin_memset(&key, 0x0, sizeof(key));
+ key.local_ipv4 = *local_ip;
key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
key.tunnel_id = 2;
key.tunnel_tos = 0;
@@ -323,13 +379,22 @@ int _vxlan_set_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("vxlan_get_tunnel")
-int _vxlan_get_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int vxlan_get_tunnel_src(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";
+ char fmt2[] = "local ip 0x%x\n";
+ __u32 index = 0;
+ __u32 *local_ip = NULL;
+
+ local_ip = bpf_map_lookup_elem(&local_ip_map, &index);
+ if (!local_ip) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
if (ret < 0) {
@@ -343,19 +408,65 @@ int _vxlan_get_tunnel(struct __sk_buff *skb)
return TC_ACT_SHOT;
}
- bpf_trace_printk(fmt, sizeof(fmt),
- key.tunnel_id, key.remote_ipv4, md.gbp);
+ if (key.local_ipv4 != *local_ip || md.gbp != 0x800FF) {
+ bpf_printk("vxlan key %d local ip 0x%x remote ip 0x%x gbp 0x%x\n",
+ key.tunnel_id, key.local_ipv4,
+ key.remote_ipv4, md.gbp);
+ bpf_printk("local_ip 0x%x\n", *local_ip);
+ log_err(ret);
+ return TC_ACT_SHOT;
+ }
return TC_ACT_OK;
}
-SEC("ip6vxlan_set_tunnel")
-int _ip6vxlan_set_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int ip6vxlan_set_tunnel_dst(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
int ret;
+ __u32 index = 0;
+ __u32 *local_ip;
+
+ local_ip = bpf_map_lookup_elem(&local_ip_map, &index);
+ if (!local_ip) {
+ log_err(ret);
+ return TC_ACT_SHOT;
+ }
__builtin_memset(&key, 0x0, sizeof(key));
+ key.local_ipv6[3] = bpf_htonl(0x11); /* ::11 */
+ key.remote_ipv6[3] = bpf_htonl(*local_ip);
+ 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) {
+ log_err(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("tc")
+int ip6vxlan_set_tunnel_src(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key;
+ int ret;
+ __u32 index = 0;
+ __u32 *local_ip;
+
+ local_ip = bpf_map_lookup_elem(&local_ip_map, &index);
+ if (!local_ip) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.local_ipv6[3] = bpf_htonl(*local_ip);
key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
key.tunnel_id = 22;
key.tunnel_tos = 0;
@@ -371,12 +482,21 @@ int _ip6vxlan_set_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("ip6vxlan_get_tunnel")
-int _ip6vxlan_get_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int ip6vxlan_get_tunnel_src(struct __sk_buff *skb)
{
char fmt[] = "key %d remote ip6 ::%x label %x\n";
+ char fmt2[] = "local ip6 ::%x\n";
struct bpf_tunnel_key key;
int ret;
+ __u32 index = 0;
+ __u32 *local_ip;
+
+ local_ip = bpf_map_lookup_elem(&local_ip_map, &index);
+ if (!local_ip) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
@@ -385,14 +505,20 @@ int _ip6vxlan_get_tunnel(struct __sk_buff *skb)
return TC_ACT_SHOT;
}
- bpf_trace_printk(fmt, sizeof(fmt),
- key.tunnel_id, key.remote_ipv6[3], key.tunnel_label);
+ if (bpf_ntohl(key.local_ipv6[3]) != *local_ip) {
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id,
+ key.remote_ipv6[3], key.tunnel_label);
+ bpf_trace_printk(fmt2, sizeof(fmt2), key.local_ipv6[3]);
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
return TC_ACT_OK;
}
-SEC("geneve_set_tunnel")
-int _geneve_set_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int geneve_set_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
@@ -429,8 +555,8 @@ int _geneve_set_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("geneve_get_tunnel")
-int _geneve_get_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int geneve_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
@@ -452,8 +578,8 @@ int _geneve_get_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("ip6geneve_set_tunnel")
-int _ip6geneve_set_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int ip6geneve_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
struct geneve_opt gopt;
@@ -490,8 +616,8 @@ int _ip6geneve_set_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("ip6geneve_get_tunnel")
-int _ip6geneve_get_tunnel(struct __sk_buff *skb)
+SEC("tc")
+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;
@@ -515,8 +641,8 @@ int _ip6geneve_get_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("ipip_set_tunnel")
-int _ipip_set_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int ipip_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key = {};
void *data = (void *)(long)skb->data;
@@ -544,8 +670,8 @@ int _ipip_set_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("ipip_get_tunnel")
-int _ipip_get_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int ipip_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
@@ -561,8 +687,8 @@ int _ipip_get_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("ipip6_set_tunnel")
-int _ipip6_set_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int ipip6_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key = {};
void *data = (void *)(long)skb->data;
@@ -592,8 +718,8 @@ int _ipip6_set_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("ipip6_get_tunnel")
-int _ipip6_get_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int ipip6_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
@@ -611,8 +737,8 @@ int _ipip6_get_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("ip6ip6_set_tunnel")
-int _ip6ip6_set_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int ip6ip6_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key = {};
void *data = (void *)(long)skb->data;
@@ -641,8 +767,8 @@ int _ip6ip6_set_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("ip6ip6_get_tunnel")
-int _ip6ip6_get_tunnel(struct __sk_buff *skb)
+SEC("tc")
+int ip6ip6_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
@@ -660,8 +786,8 @@ int _ip6ip6_get_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("xfrm_get_state")
-int _xfrm_get_state(struct __sk_buff *skb)
+SEC("tc")
+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";
@@ -45,6 +45,7 @@
# 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet
# 6) Forward the packet to the overlay tnl dev
+BPF_PIN_TUNNEL_DIR="/sys/fs/bpf/tc/tunnel"
PING_ARG="-c 3 -w 10 -q"
ret=0
GREEN='\033[0;92m'
@@ -155,52 +156,6 @@ add_ip6erspan_tunnel()
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 \
- ip neigh add 10.1.1.200 lladdr 52:54:00:d9:02:00 dev $DEV_NS
- 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
- ip neigh add 10.1.1.100 lladdr 52:54:00:d9:01:00 dev $DEV
-}
-
-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
-
- # 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
@@ -403,58 +358,6 @@ test_ip6erspan()
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
- # 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 ${RED}"FAIL: ip6$TYPE"${NC}
- return 1
- fi
- echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
-}
-
test_geneve()
{
TYPE=geneve
@@ -641,9 +544,11 @@ test_xfrm_tunnel()
config_device
> /sys/kernel/debug/tracing/trace
setup_xfrm_tunnel
+ mkdir -p ${BPF_PIN_TUNNEL_DIR}
+ bpftool prog loadall ./test_tunnel_kern.o ${BPF_PIN_TUNNEL_DIR}
tc qdisc add dev veth1 clsact
- tc filter add dev veth1 proto ip ingress bpf da obj test_tunnel_kern.o \
- sec xfrm_get_state
+ tc filter add dev veth1 proto ip ingress bpf da object-pinned \
+ ${BPF_PIN_TUNNEL_DIR}/xfrm_get_state
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
sleep 1
grep "reqid 1" /sys/kernel/debug/tracing/trace
@@ -666,13 +571,17 @@ attach_bpf()
DEV=$1
SET=$2
GET=$3
+ mkdir -p ${BPF_PIN_TUNNEL_DIR}
+ bpftool prog loadall ./test_tunnel_kern.o ${BPF_PIN_TUNNEL_DIR}/
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
+ tc filter add dev $DEV egress bpf da object-pinned ${BPF_PIN_TUNNEL_DIR}/$SET
+ tc filter add dev $DEV ingress bpf da object-pinned ${BPF_PIN_TUNNEL_DIR}/$GET
}
cleanup()
{
+ rm -rf ${BPF_PIN_TUNNEL_DIR}
+
ip netns delete at_ns0 2> /dev/null
ip link del veth1 2> /dev/null
ip link del ipip11 2> /dev/null
@@ -681,8 +590,6 @@ cleanup()
ip link del gretap11 2> /dev/null
ip link del ip6gre11 2> /dev/null
ip link del ip6gretap11 2> /dev/null
- ip link del vxlan11 2> /dev/null
- ip link del ip6vxlan11 2> /dev/null
ip link del geneve11 2> /dev/null
ip link del ip6geneve11 2> /dev/null
ip link del erspan11 2> /dev/null
@@ -714,7 +621,6 @@ enable_debug()
{
echo 'file ip_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
echo 'file ip6_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
- echo 'file vxlan.c +p' > /sys/kernel/debug/dynamic_debug/control
echo 'file geneve.c +p' > /sys/kernel/debug/dynamic_debug/control
echo 'file ipip.c +p' > /sys/kernel/debug/dynamic_debug/control
}
@@ -750,14 +656,6 @@ bpf_tunnel_test()
test_ip6erspan v2
errors=$(( $errors + $? ))
- echo "Testing VXLAN tunnel..."
- test_vxlan
- errors=$(( $errors + $? ))
-
- echo "Testing IP6VXLAN tunnel..."
- test_ip6vxlan
- errors=$(( $errors + $? ))
-
echo "Testing GENEVE tunnel..."
test_geneve
errors=$(( $errors + $? ))