summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing/selftests/bpf/progs/test_tc_tunnel.c')
-rw-r--r--tools/testing/selftests/bpf/progs/test_tc_tunnel.c265
1 files changed, 213 insertions, 52 deletions
diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
index 37bce7a7c394..7330c61b5730 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
@@ -2,36 +2,47 @@
/* In-place tunneling */
-#include <stdbool.h>
-#include <string.h>
-
-#include <linux/stddef.h>
-#include <linux/bpf.h>
-#include <linux/if_ether.h>
-#include <linux/in.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <linux/mpls.h>
-#include <linux/tcp.h>
-#include <linux/udp.h>
-#include <linux/pkt_cls.h>
-#include <linux/types.h>
+#include <vmlinux.h>
-#include <bpf/bpf_endian.h>
#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_tracing_net.h"
+#include "bpf_compiler.h"
+
+#pragma GCC diagnostic ignored "-Waddress-of-packed-member"
static const int cfg_port = 8000;
static const int cfg_udp_src = 20000;
+#define ETH_P_MPLS_UC 0x8847
+#define ETH_P_TEB 0x6558
+
+#define MPLS_LS_S_MASK 0x00000100
+#define BPF_F_ADJ_ROOM_ENCAP_L2(len) \
+ (((__u64)len & BPF_ADJ_ROOM_ENCAP_L2_MASK) \
+ << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
+
+#define L2_PAD_SZ (sizeof(struct vxlanhdr) + ETH_HLEN)
+
#define UDP_PORT 5555
#define MPLS_OVER_UDP_PORT 6635
#define ETH_OVER_UDP_PORT 7777
+#define VXLAN_UDP_PORT 8472
+
+#define EXTPROTO_VXLAN 0x1
+
+#define VXLAN_FLAGS bpf_htonl(1<<27)
+#define VNI_ID 1
+#define VXLAN_VNI bpf_htonl(VNI_ID << 8)
+
+#ifndef NEXTHDR_DEST
+#define NEXTHDR_DEST 60
+#endif
/* MPLS label 1000 with S bit (last label) set and ttl of 255. */
static const __u32 mpls_label = __bpf_constant_htonl(1000 << 12 |
MPLS_LS_S_MASK | 0xff);
-
struct gre_hdr {
__be16 flags;
__be16 protocol;
@@ -45,13 +56,13 @@ union l4hdr {
struct v4hdr {
struct iphdr ip;
union l4hdr l4hdr;
- __u8 pad[16]; /* enough space for L2 header */
+ __u8 pad[L2_PAD_SZ]; /* space for L2 header / vxlan header ... */
} __attribute__((packed));
struct v6hdr {
struct ipv6hdr ip;
union l4hdr l4hdr;
- __u8 pad[16]; /* enough space for L2 header */
+ __u8 pad[L2_PAD_SZ]; /* space for L2 header / vxlan header ... */
} __attribute__((packed));
static __always_inline void set_ipv4_csum(struct iphdr *iph)
@@ -62,21 +73,22 @@ static __always_inline void set_ipv4_csum(struct iphdr *iph)
iph->check = 0;
-#pragma clang loop unroll(full)
+ __pragma_loop_unroll_full
for (i = 0, csum = 0; i < sizeof(*iph) >> 1; i++)
csum += *iph16++;
iph->check = ~((csum & 0xffff) + (csum >> 16));
}
-static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
- __u16 l2_proto)
+static __always_inline int __encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
+ __u16 l2_proto, __u16 ext_proto)
{
+ struct iphdr iph_inner = {0};
__u16 udp_dst = UDP_PORT;
- struct iphdr iph_inner;
struct v4hdr h_outer;
struct tcphdr tcph;
int olen, l2_len;
+ __u8 *l2_hdr = NULL;
int tcp_off;
__u64 flags;
@@ -99,7 +111,6 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
return TC_ACT_OK;
/* Derive the IPv4 header fields from the IPv6 header */
- memset(&iph_inner, 0, sizeof(iph_inner));
iph_inner.version = 4;
iph_inner.ihl = 5;
iph_inner.tot_len = bpf_htons(sizeof(iph6_inner) +
@@ -141,7 +152,11 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
break;
case ETH_P_TEB:
l2_len = ETH_HLEN;
- udp_dst = ETH_OVER_UDP_PORT;
+ if (ext_proto & EXTPROTO_VXLAN) {
+ udp_dst = VXLAN_UDP_PORT;
+ l2_len += sizeof(struct vxlanhdr);
+ } else
+ udp_dst = ETH_OVER_UDP_PORT;
break;
}
flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len);
@@ -171,14 +186,26 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
}
/* add L2 encap (if specified) */
+ l2_hdr = (__u8 *)&h_outer + olen;
switch (l2_proto) {
case ETH_P_MPLS_UC:
- *((__u32 *)((__u8 *)&h_outer + olen)) = mpls_label;
+ *(__u32 *)l2_hdr = mpls_label;
break;
case ETH_P_TEB:
- if (bpf_skb_load_bytes(skb, 0, (__u8 *)&h_outer + olen,
- ETH_HLEN))
+ flags |= BPF_F_ADJ_ROOM_ENCAP_L2_ETH;
+
+ if (ext_proto & EXTPROTO_VXLAN) {
+ struct vxlanhdr *vxlan_hdr = (struct vxlanhdr *)l2_hdr;
+
+ vxlan_hdr->vx_flags = VXLAN_FLAGS;
+ vxlan_hdr->vx_vni = VXLAN_VNI;
+
+ l2_hdr += sizeof(struct vxlanhdr);
+ }
+
+ if (bpf_skb_load_bytes(skb, 0, l2_hdr, ETH_HLEN))
return TC_ACT_SHOT;
+
break;
}
olen += l2_len;
@@ -214,14 +241,21 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
return TC_ACT_OK;
}
-static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
+static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
__u16 l2_proto)
{
+ return __encap_ipv4(skb, encap_proto, l2_proto, 0);
+}
+
+static __always_inline int __encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
+ __u16 l2_proto, __u16 ext_proto)
+{
__u16 udp_dst = UDP_PORT;
struct ipv6hdr iph_inner;
struct v6hdr h_outer;
struct tcphdr tcph;
int olen, l2_len;
+ __u8 *l2_hdr = NULL;
__u16 tot_len;
__u64 flags;
@@ -249,7 +283,11 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
break;
case ETH_P_TEB:
l2_len = ETH_HLEN;
- udp_dst = ETH_OVER_UDP_PORT;
+ if (ext_proto & EXTPROTO_VXLAN) {
+ udp_dst = VXLAN_UDP_PORT;
+ l2_len += sizeof(struct vxlanhdr);
+ } else
+ udp_dst = ETH_OVER_UDP_PORT;
break;
}
flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len);
@@ -267,7 +305,7 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src);
h_outer.l4hdr.udp.dest = bpf_htons(udp_dst);
tot_len = bpf_ntohs(iph_inner.payload_len) + sizeof(iph_inner) +
- sizeof(h_outer.l4hdr.udp);
+ sizeof(h_outer.l4hdr.udp) + l2_len;
h_outer.l4hdr.udp.check = 0;
h_outer.l4hdr.udp.len = bpf_htons(tot_len);
break;
@@ -278,13 +316,24 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
}
/* add L2 encap (if specified) */
+ l2_hdr = (__u8 *)&h_outer + olen;
switch (l2_proto) {
case ETH_P_MPLS_UC:
- *((__u32 *)((__u8 *)&h_outer + olen)) = mpls_label;
+ *(__u32 *)l2_hdr = mpls_label;
break;
case ETH_P_TEB:
- if (bpf_skb_load_bytes(skb, 0, (__u8 *)&h_outer + olen,
- ETH_HLEN))
+ flags |= BPF_F_ADJ_ROOM_ENCAP_L2_ETH;
+
+ if (ext_proto & EXTPROTO_VXLAN) {
+ struct vxlanhdr *vxlan_hdr = (struct vxlanhdr *)l2_hdr;
+
+ vxlan_hdr->vx_flags = VXLAN_FLAGS;
+ vxlan_hdr->vx_vni = VXLAN_VNI;
+
+ l2_hdr += sizeof(struct vxlanhdr);
+ }
+
+ if (bpf_skb_load_bytes(skb, 0, l2_hdr, ETH_HLEN))
return TC_ACT_SHOT;
break;
}
@@ -309,7 +358,67 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
return TC_ACT_OK;
}
-SEC("encap_ipip_none")
+static int encap_ipv6_ipip6(struct __sk_buff *skb)
+{
+ struct v6hdr h_outer = {0};
+ struct iphdr iph_inner;
+ struct tcphdr tcph;
+ struct ethhdr eth;
+ __u64 flags;
+ int olen;
+
+ if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner,
+ sizeof(iph_inner)) < 0)
+ return TC_ACT_OK;
+
+ /* filter only packets we want */
+ if (bpf_skb_load_bytes(skb, ETH_HLEN + (iph_inner.ihl << 2),
+ &tcph, sizeof(tcph)) < 0)
+ return TC_ACT_OK;
+
+ if (tcph.dest != __bpf_constant_htons(cfg_port))
+ return TC_ACT_OK;
+
+ olen = sizeof(h_outer.ip);
+
+ flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV6;
+
+ /* add room between mac and network header */
+ if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags))
+ return TC_ACT_SHOT;
+
+ /* prepare new outer network header */
+ h_outer.ip.version = 6;
+ h_outer.ip.hop_limit = iph_inner.ttl;
+ h_outer.ip.saddr.in6_u.u6_addr8[1] = 0xfd;
+ h_outer.ip.saddr.in6_u.u6_addr8[15] = 1;
+ h_outer.ip.daddr.in6_u.u6_addr8[1] = 0xfd;
+ h_outer.ip.daddr.in6_u.u6_addr8[15] = 2;
+ h_outer.ip.payload_len = iph_inner.tot_len;
+ h_outer.ip.nexthdr = IPPROTO_IPIP;
+
+ /* store new outer network header */
+ if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen,
+ BPF_F_INVALIDATE_HASH) < 0)
+ return TC_ACT_SHOT;
+
+ /* update eth->h_proto */
+ if (bpf_skb_load_bytes(skb, 0, &eth, sizeof(eth)) < 0)
+ return TC_ACT_SHOT;
+ eth.h_proto = bpf_htons(ETH_P_IPV6);
+ if (bpf_skb_store_bytes(skb, 0, &eth, sizeof(eth), 0) < 0)
+ return TC_ACT_SHOT;
+
+ return TC_ACT_OK;
+}
+
+static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
+ __u16 l2_proto)
+{
+ return __encap_ipv6(skb, encap_proto, l2_proto, 0);
+}
+
+SEC("tc")
int __encap_ipip_none(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
@@ -318,7 +427,7 @@ int __encap_ipip_none(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("encap_gre_none")
+SEC("tc")
int __encap_gre_none(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
@@ -327,7 +436,7 @@ int __encap_gre_none(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("encap_gre_mpls")
+SEC("tc")
int __encap_gre_mpls(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
@@ -336,7 +445,7 @@ int __encap_gre_mpls(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("encap_gre_eth")
+SEC("tc")
int __encap_gre_eth(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
@@ -345,7 +454,7 @@ int __encap_gre_eth(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("encap_udp_none")
+SEC("tc")
int __encap_udp_none(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
@@ -354,7 +463,7 @@ int __encap_udp_none(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("encap_udp_mpls")
+SEC("tc")
int __encap_udp_mpls(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
@@ -363,7 +472,7 @@ int __encap_udp_mpls(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("encap_udp_eth")
+SEC("tc")
int __encap_udp_eth(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
@@ -372,7 +481,18 @@ int __encap_udp_eth(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("encap_sit_none")
+SEC("tc")
+int __encap_vxlan_eth(struct __sk_buff *skb)
+{
+ if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+ return __encap_ipv4(skb, IPPROTO_UDP,
+ ETH_P_TEB,
+ EXTPROTO_VXLAN);
+ else
+ return TC_ACT_OK;
+}
+
+SEC("tc")
int __encap_sit_none(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -381,7 +501,7 @@ int __encap_sit_none(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("encap_ip6tnl_none")
+SEC("tc")
int __encap_ip6tnl_none(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -390,7 +510,16 @@ int __encap_ip6tnl_none(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("encap_ip6gre_none")
+SEC("tc")
+int __encap_ipip6_none(struct __sk_buff *skb)
+{
+ if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+ return encap_ipv6_ipip6(skb);
+ else
+ return TC_ACT_OK;
+}
+
+SEC("tc")
int __encap_ip6gre_none(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -399,7 +528,7 @@ int __encap_ip6gre_none(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("encap_ip6gre_mpls")
+SEC("tc")
int __encap_ip6gre_mpls(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -408,7 +537,7 @@ int __encap_ip6gre_mpls(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("encap_ip6gre_eth")
+SEC("tc")
int __encap_ip6gre_eth(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -417,7 +546,7 @@ int __encap_ip6gre_eth(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("encap_ip6udp_none")
+SEC("tc")
int __encap_ip6udp_none(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -426,7 +555,7 @@ int __encap_ip6udp_none(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("encap_ip6udp_mpls")
+SEC("tc")
int __encap_ip6udp_mpls(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -435,7 +564,7 @@ int __encap_ip6udp_mpls(struct __sk_buff *skb)
return TC_ACT_OK;
}
-SEC("encap_ip6udp_eth")
+SEC("tc")
int __encap_ip6udp_eth(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -444,16 +573,46 @@ int __encap_ip6udp_eth(struct __sk_buff *skb)
return TC_ACT_OK;
}
+SEC("tc")
+int __encap_ip6vxlan_eth(struct __sk_buff *skb)
+{
+ if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
+ return __encap_ipv6(skb, IPPROTO_UDP,
+ ETH_P_TEB,
+ EXTPROTO_VXLAN);
+ else
+ return TC_ACT_OK;
+}
+
static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
{
- char buf[sizeof(struct v6hdr)];
+ __u64 flags = BPF_F_ADJ_ROOM_FIXED_GSO;
+ struct ipv6_opt_hdr ip6_opt_hdr;
struct gre_hdr greh;
struct udphdr udph;
int olen = len;
switch (proto) {
case IPPROTO_IPIP:
+ flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4;
+ break;
case IPPROTO_IPV6:
+ flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6;
+ break;
+ case NEXTHDR_DEST:
+ if (bpf_skb_load_bytes(skb, off + len, &ip6_opt_hdr,
+ sizeof(ip6_opt_hdr)) < 0)
+ return TC_ACT_OK;
+ switch (ip6_opt_hdr.nexthdr) {
+ case IPPROTO_IPIP:
+ flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4;
+ break;
+ case IPPROTO_IPV6:
+ flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6;
+ break;
+ default:
+ return TC_ACT_OK;
+ }
break;
case IPPROTO_GRE:
olen += sizeof(struct gre_hdr);
@@ -479,14 +638,16 @@ static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
case ETH_OVER_UDP_PORT:
olen += ETH_HLEN;
break;
+ case VXLAN_UDP_PORT:
+ olen += ETH_HLEN + sizeof(struct vxlanhdr);
+ break;
}
break;
default:
return TC_ACT_OK;
}
- if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC,
- BPF_F_ADJ_ROOM_FIXED_GSO))
+ if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC, flags))
return TC_ACT_SHOT;
return TC_ACT_OK;
@@ -519,7 +680,7 @@ static int decap_ipv6(struct __sk_buff *skb)
iph_outer.nexthdr);
}
-SEC("decap")
+SEC("tc")
int decap_f(struct __sk_buff *skb)
{
switch (skb->protocol) {