linux/tools/testing/selftests/bpf/progs/test_tunnel_kern.c

949 lines
20 KiB
C
Raw Normal View History

// 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 "vmlinux.h"
#include <bpf/bpf_core_read.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
#include "bpf_kfuncs.h"
#include "bpf_tracing_net.h"
#define log_err(__ret) bpf_printk("ERROR line:%d ret:%d\n", __LINE__, __ret)
#define VXLAN_UDP_PORT 4789
#define ETH_P_IP 0x0800
#define PACKET_HOST 0
#define TUNNEL_CSUM bpf_htons(0x01)
#define TUNNEL_KEY bpf_htons(0x04)
selftests/bpf: Don't assign outer source IP to host The previous commit fixed a bug in the bpf_skb_set_tunnel_key helper to avoid dropping packets whose outer source IP address isn't assigned to a host interface. This commit changes the corresponding selftest to not assign the outer source IP address to an interface. Not assigning the source IP to an interface causes two issues in the existing test: 1. The ARP requests will fail for that IP address so we need to add the ARP entry manually. 2. The encapsulated ICMP echo reply traffic will not reach the VXLAN device. It will be dropped by the stack before, because the outer destination IP is unknown. To solve 2., we have two choices. Either we perform decapsulation ourselves in a BPF program attached at veth1 (the base device for the VXLAN device), or we switch the outer destination address when we receive the packet at veth1, such that the stack properly demultiplexes it to the VXLAN device afterward. This commit implements the second approach, where we switch the outer destination address from the unassigned IP address to the assigned one, only for VXLAN traffic ingressing veth1. Then, at the vxlan device, the BPF program that checks the output of bpf_skb_get_tunnel_key needs to be updated as the expected local IP address is now the unassigned one. Signed-off-by: Paul Chaignon <paul@isovalent.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/4addde76eaf3477a58975bef15ed2788c44e5f55.1658759380.git.paul@isovalent.com
2022-07-25 16:32:53 +02:00
/* Only IPv4 address assigned to veth1.
* 172.16.1.200
*/
#define ASSIGNED_ADDR_VETH1 0xac1001c8
int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx,
struct bpf_fou_encap *encap, int type) __ksym;
int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx,
struct bpf_fou_encap *encap) __ksym;
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__uint(max_entries, 1);
__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;
__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) {
log_err(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("tc")
int gre_set_tunnel_no_key(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_ttl = 64;
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_ZERO_CSUM_TX | BPF_F_SEQ_NUMBER |
BPF_F_NO_TUNNEL_KEY);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("tc")
int gre_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
bpf_printk("key %d remote ip 0x%x\n", key.tunnel_id, key.remote_ipv4);
return TC_ACT_OK;
}
SEC("tc")
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) {
log_err(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("tc")
int ip6gretap_get_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
int ret;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
bpf_printk("key %d remote ip6 ::%x label %x\n",
key.tunnel_id, key.remote_ipv6[3], key.tunnel_label);
return TC_ACT_OK;
}
SEC("tc")
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) {
log_err(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;
BPF_CORE_WRITE_BITFIELD(&md.u.md2, dir, direction);
BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid, (hwid & 0xf));
BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid_upper, (hwid >> 4) & 0x3);
#endif
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 erspan_get_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
struct erspan_metadata md;
int ret;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md));
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
bpf_printk("key %d remote ip 0x%x erspan version %d\n",
key.tunnel_id, key.remote_ipv4, md.version);
#ifdef ERSPAN_V1
index = bpf_ntohl(md.u.index);
bpf_printk("\tindex %x\n", index);
#else
bpf_printk("\tdirection %d hwid %x timestamp %u\n",
BPF_CORE_READ_BITFIELD(&md.u.md2, dir),
(BPF_CORE_READ_BITFIELD(&md.u.md2, hwid_upper) << 4) +
BPF_CORE_READ_BITFIELD(&md.u.md2, hwid),
bpf_ntohl(md.u.md2.timestamp));
#endif
return TC_ACT_OK;
}
SEC("tc")
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) {
log_err(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;
BPF_CORE_WRITE_BITFIELD(&md.u.md2, dir, direction);
BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid, (hwid & 0xf));
BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid_upper, (hwid >> 4) & 0x3);
#endif
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 ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
struct erspan_metadata md;
int ret;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md));
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
bpf_printk("ip6erspan get key %d remote ip6 ::%x erspan version %d\n",
key.tunnel_id, key.remote_ipv4, md.version);
#ifdef ERSPAN_V1
index = bpf_ntohl(md.u.index);
bpf_printk("\tindex %x\n", index);
#else
bpf_printk("\tdirection %d hwid %x timestamp %u\n",
BPF_CORE_READ_BITFIELD(&md.u.md2, dir),
(BPF_CORE_READ_BITFIELD(&md.u.md2, hwid_upper) << 4) +
BPF_CORE_READ_BITFIELD(&md.u.md2, hwid),
bpf_ntohl(md.u.md2.timestamp));
#endif
return TC_ACT_OK;
}
SEC("tc")
int vxlan_set_tunnel_dst(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
struct vxlan_metadata md;
__u32 index = 0;
__u32 *local_ip = NULL;
selftests/bpf: Add -Wuninitialized flag to bpf prog flags Per C99 standard [0], Section 6.7.8, Paragraph 10: If an object that has automatic storage duration is not initialized explicitly, its value is indeterminate. And in the same document, in appendix "J.2 Undefined behavior": The behavior is undefined in the following circumstances: [...] The value of an object with automatic storage duration is used while it is indeterminate (6.2.4, 6.7.8, 6.8). This means that use of an uninitialized stack variable is undefined behavior, and therefore that clang can choose to do a variety of scary things, such as not generating bytecode for "bunch of useful code" in the below example: void some_func() { int i; if (!i) return; // bunch of useful code } To add insult to injury, if some_func above is a helper function for some BPF program, clang can choose to not generate an "exit" insn, causing verifier to fail with "last insn is not an exit or jmp". Going from that verification failure to the root cause of uninitialized use is certain to be frustrating. This patch adds -Wuninitialized to the cflags for selftest BPF progs and fixes up existing instances of uninitialized use. [0]: https://www.open-std.org/jtc1/sc22/WG14/www/docs/n1256.pdf Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com> Cc: David Vernet <void@manifault.com> Cc: Tejun Heo <tj@kernel.org> Acked-by: David Vernet <void@manifault.com> Link: https://lore.kernel.org/r/20230303005500.1614874-1-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-03-02 16:55:00 -08:00
int ret = 0;
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)
{
struct bpf_tunnel_key key;
struct vxlan_metadata md;
__u32 index = 0;
__u32 *local_ip = NULL;
selftests/bpf: Add -Wuninitialized flag to bpf prog flags Per C99 standard [0], Section 6.7.8, Paragraph 10: If an object that has automatic storage duration is not initialized explicitly, its value is indeterminate. And in the same document, in appendix "J.2 Undefined behavior": The behavior is undefined in the following circumstances: [...] The value of an object with automatic storage duration is used while it is indeterminate (6.2.4, 6.7.8, 6.8). This means that use of an uninitialized stack variable is undefined behavior, and therefore that clang can choose to do a variety of scary things, such as not generating bytecode for "bunch of useful code" in the below example: void some_func() { int i; if (!i) return; // bunch of useful code } To add insult to injury, if some_func above is a helper function for some BPF program, clang can choose to not generate an "exit" insn, causing verifier to fail with "last insn is not an exit or jmp". Going from that verification failure to the root cause of uninitialized use is certain to be frustrating. This patch adds -Wuninitialized to the cflags for selftest BPF progs and fixes up existing instances of uninitialized use. [0]: https://www.open-std.org/jtc1/sc22/WG14/www/docs/n1256.pdf Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com> Cc: David Vernet <void@manifault.com> Cc: Tejun Heo <tj@kernel.org> Acked-by: David Vernet <void@manifault.com> Link: https://lore.kernel.org/r/20230303005500.1614874-1-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-03-02 16:55:00 -08:00
int ret = 0;
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 = *local_ip;
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) {
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_get_tunnel_src(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
struct vxlan_metadata md;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_FLAGS);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md));
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
if (key.local_ipv4 != ASSIGNED_ADDR_VETH1 || md.gbp != 0x800FF ||
!(key.tunnel_flags & TUNNEL_KEY) ||
(key.tunnel_flags & TUNNEL_CSUM)) {
bpf_printk("vxlan key %d local ip 0x%x remote ip 0x%x gbp 0x%x flags 0x%x\n",
key.tunnel_id, key.local_ipv4,
key.remote_ipv4, md.gbp,
bpf_ntohs(key.tunnel_flags));
log_err(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
selftests/bpf: Don't assign outer source IP to host The previous commit fixed a bug in the bpf_skb_set_tunnel_key helper to avoid dropping packets whose outer source IP address isn't assigned to a host interface. This commit changes the corresponding selftest to not assign the outer source IP address to an interface. Not assigning the source IP to an interface causes two issues in the existing test: 1. The ARP requests will fail for that IP address so we need to add the ARP entry manually. 2. The encapsulated ICMP echo reply traffic will not reach the VXLAN device. It will be dropped by the stack before, because the outer destination IP is unknown. To solve 2., we have two choices. Either we perform decapsulation ourselves in a BPF program attached at veth1 (the base device for the VXLAN device), or we switch the outer destination address when we receive the packet at veth1, such that the stack properly demultiplexes it to the VXLAN device afterward. This commit implements the second approach, where we switch the outer destination address from the unassigned IP address to the assigned one, only for VXLAN traffic ingressing veth1. Then, at the vxlan device, the BPF program that checks the output of bpf_skb_get_tunnel_key needs to be updated as the expected local IP address is now the unassigned one. Signed-off-by: Paul Chaignon <paul@isovalent.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/4addde76eaf3477a58975bef15ed2788c44e5f55.1658759380.git.paul@isovalent.com
2022-07-25 16:32:53 +02:00
SEC("tc")
int veth_set_outer_dst(struct __sk_buff *skb)
{
struct ethhdr *eth = (struct ethhdr *)(long)skb->data;
__u32 assigned_ip = bpf_htonl(ASSIGNED_ADDR_VETH1);
void *data_end = (void *)(long)skb->data_end;
struct udphdr *udph;
struct iphdr *iph;
int ret = 0;
__s64 csum;
if ((void *)eth + sizeof(*eth) > data_end) {
log_err(ret);
return TC_ACT_SHOT;
}
if (eth->h_proto != bpf_htons(ETH_P_IP))
return TC_ACT_OK;
iph = (struct iphdr *)(eth + 1);
if ((void *)iph + sizeof(*iph) > data_end) {
log_err(ret);
return TC_ACT_SHOT;
}
if (iph->protocol != IPPROTO_UDP)
return TC_ACT_OK;
udph = (struct udphdr *)(iph + 1);
if ((void *)udph + sizeof(*udph) > data_end) {
log_err(ret);
return TC_ACT_SHOT;
}
if (udph->dest != bpf_htons(VXLAN_UDP_PORT))
return TC_ACT_OK;
if (iph->daddr != assigned_ip) {
csum = bpf_csum_diff(&iph->daddr, sizeof(__u32), &assigned_ip,
sizeof(__u32), 0);
if (bpf_skb_store_bytes(skb, ETH_HLEN + offsetof(struct iphdr, daddr),
&assigned_ip, sizeof(__u32), 0) < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
if (bpf_l3_csum_replace(skb, ETH_HLEN + offsetof(struct iphdr, check),
0, csum, 0) < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
bpf_skb_change_type(skb, PACKET_HOST);
}
return TC_ACT_OK;
}
SEC("tc")
int ip6vxlan_set_tunnel_dst(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
__u32 index = 0;
__u32 *local_ip;
selftests/bpf: Add -Wuninitialized flag to bpf prog flags Per C99 standard [0], Section 6.7.8, Paragraph 10: If an object that has automatic storage duration is not initialized explicitly, its value is indeterminate. And in the same document, in appendix "J.2 Undefined behavior": The behavior is undefined in the following circumstances: [...] The value of an object with automatic storage duration is used while it is indeterminate (6.2.4, 6.7.8, 6.8). This means that use of an uninitialized stack variable is undefined behavior, and therefore that clang can choose to do a variety of scary things, such as not generating bytecode for "bunch of useful code" in the below example: void some_func() { int i; if (!i) return; // bunch of useful code } To add insult to injury, if some_func above is a helper function for some BPF program, clang can choose to not generate an "exit" insn, causing verifier to fail with "last insn is not an exit or jmp". Going from that verification failure to the root cause of uninitialized use is certain to be frustrating. This patch adds -Wuninitialized to the cflags for selftest BPF progs and fixes up existing instances of uninitialized use. [0]: https://www.open-std.org/jtc1/sc22/WG14/www/docs/n1256.pdf Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com> Cc: David Vernet <void@manifault.com> Cc: Tejun Heo <tj@kernel.org> Acked-by: David Vernet <void@manifault.com> Link: https://lore.kernel.org/r/20230303005500.1614874-1-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-03-02 16:55:00 -08:00
int ret = 0;
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;
__u32 index = 0;
__u32 *local_ip;
selftests/bpf: Add -Wuninitialized flag to bpf prog flags Per C99 standard [0], Section 6.7.8, Paragraph 10: If an object that has automatic storage duration is not initialized explicitly, its value is indeterminate. And in the same document, in appendix "J.2 Undefined behavior": The behavior is undefined in the following circumstances: [...] The value of an object with automatic storage duration is used while it is indeterminate (6.2.4, 6.7.8, 6.8). This means that use of an uninitialized stack variable is undefined behavior, and therefore that clang can choose to do a variety of scary things, such as not generating bytecode for "bunch of useful code" in the below example: void some_func() { int i; if (!i) return; // bunch of useful code } To add insult to injury, if some_func above is a helper function for some BPF program, clang can choose to not generate an "exit" insn, causing verifier to fail with "last insn is not an exit or jmp". Going from that verification failure to the root cause of uninitialized use is certain to be frustrating. This patch adds -Wuninitialized to the cflags for selftest BPF progs and fixes up existing instances of uninitialized use. [0]: https://www.open-std.org/jtc1/sc22/WG14/www/docs/n1256.pdf Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com> Cc: David Vernet <void@manifault.com> Cc: Tejun Heo <tj@kernel.org> Acked-by: David Vernet <void@manifault.com> Link: https://lore.kernel.org/r/20230303005500.1614874-1-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-03-02 16:55:00 -08:00
int ret = 0;
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(*local_ip);
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) {
log_err(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("tc")
int ip6vxlan_get_tunnel_src(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
__u32 index = 0;
__u32 *local_ip;
selftests/bpf: Add -Wuninitialized flag to bpf prog flags Per C99 standard [0], Section 6.7.8, Paragraph 10: If an object that has automatic storage duration is not initialized explicitly, its value is indeterminate. And in the same document, in appendix "J.2 Undefined behavior": The behavior is undefined in the following circumstances: [...] The value of an object with automatic storage duration is used while it is indeterminate (6.2.4, 6.7.8, 6.8). This means that use of an uninitialized stack variable is undefined behavior, and therefore that clang can choose to do a variety of scary things, such as not generating bytecode for "bunch of useful code" in the below example: void some_func() { int i; if (!i) return; // bunch of useful code } To add insult to injury, if some_func above is a helper function for some BPF program, clang can choose to not generate an "exit" insn, causing verifier to fail with "last insn is not an exit or jmp". Going from that verification failure to the root cause of uninitialized use is certain to be frustrating. This patch adds -Wuninitialized to the cflags for selftest BPF progs and fixes up existing instances of uninitialized use. [0]: https://www.open-std.org/jtc1/sc22/WG14/www/docs/n1256.pdf Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com> Cc: David Vernet <void@manifault.com> Cc: Tejun Heo <tj@kernel.org> Acked-by: David Vernet <void@manifault.com> Link: https://lore.kernel.org/r/20230303005500.1614874-1-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-03-02 16:55:00 -08:00
int ret = 0;
local_ip = bpf_map_lookup_elem(&local_ip_map, &index);
if (!local_ip) {
log_err(ret);
return TC_ACT_SHOT;
}
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6 | BPF_F_TUNINFO_FLAGS);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
if (bpf_ntohl(key.local_ipv6[3]) != *local_ip ||
!(key.tunnel_flags & TUNNEL_KEY) ||
!(key.tunnel_flags & TUNNEL_CSUM)) {
bpf_printk("ip6vxlan key %d local ip6 ::%x remote ip6 ::%x label 0x%x flags 0x%x\n",
key.tunnel_id, bpf_ntohl(key.local_ipv6[3]),
bpf_ntohl(key.remote_ipv6[3]), key.tunnel_label,
bpf_ntohs(key.tunnel_flags));
bpf_printk("local_ip 0x%x\n", *local_ip);
log_err(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("tc")
int geneve_set_tunnel(struct __sk_buff *skb)
{
int ret;
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) {
log_err(ret);
return TC_ACT_SHOT;
}
ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt));
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("tc")
int geneve_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
struct geneve_opt gopt;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
if (ret < 0)
gopt.opt_class = 0;
bpf_printk("key %d remote ip 0x%x geneve class 0x%x\n",
key.tunnel_id, key.remote_ipv4, gopt.opt_class);
return TC_ACT_OK;
}
SEC("tc")
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) {
log_err(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) {
log_err(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("tc")
int ip6geneve_get_tunnel(struct __sk_buff *skb)
{
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) {
log_err(ret);
return TC_ACT_SHOT;
}
ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
if (ret < 0)
gopt.opt_class = 0;
bpf_printk("key %d remote ip 0x%x geneve class 0x%x\n",
key.tunnel_id, key.remote_ipv4, gopt.opt_class);
return TC_ACT_OK;
}
SEC("tc")
int ipip_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key = {};
void *data = (void *)(long)skb->data;
struct iphdr *iph = data;
void *data_end = (void *)(long)skb->data_end;
int ret;
/* single length check */
if (data + sizeof(*iph) > data_end) {
log_err(1);
return TC_ACT_SHOT;
}
key.tunnel_ttl = 64;
if (iph->protocol == IPPROTO_ICMP) {
key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
}
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("tc")
int ipip_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
bpf_printk("remote ip 0x%x\n", key.remote_ipv4);
return TC_ACT_OK;
}
SEC("tc")
int ipip_gue_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key = {};
struct bpf_fou_encap encap = {};
void *data = (void *)(long)skb->data;
struct iphdr *iph = data;
void *data_end = (void *)(long)skb->data_end;
int ret;
if (data + sizeof(*iph) > data_end) {
log_err(1);
return TC_ACT_SHOT;
}
key.tunnel_ttl = 64;
if (iph->protocol == IPPROTO_ICMP)
key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
encap.sport = 0;
encap.dport = bpf_htons(5555);
ret = bpf_skb_set_fou_encap(skb, &encap, FOU_BPF_ENCAP_GUE);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("tc")
int ipip_fou_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key = {};
struct bpf_fou_encap encap = {};
void *data = (void *)(long)skb->data;
struct iphdr *iph = data;
void *data_end = (void *)(long)skb->data_end;
int ret;
if (data + sizeof(*iph) > data_end) {
log_err(1);
return TC_ACT_SHOT;
}
key.tunnel_ttl = 64;
if (iph->protocol == IPPROTO_ICMP)
key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
encap.sport = 0;
encap.dport = bpf_htons(5555);
ret = bpf_skb_set_fou_encap(skb, &encap, FOU_BPF_ENCAP_FOU);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("tc")
int ipip_encap_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key = {};
struct bpf_fou_encap encap = {};
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
ret = bpf_skb_get_fou_encap(skb, &encap);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
if (bpf_ntohs(encap.dport) != 5555)
return TC_ACT_SHOT;
bpf_printk("%d remote ip 0x%x, sport %d, dport %d\n", ret,
key.remote_ipv4, bpf_ntohs(encap.sport),
bpf_ntohs(encap.dport));
return TC_ACT_OK;
}
SEC("tc")
int ipip6_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key = {};
void *data = (void *)(long)skb->data;
struct iphdr *iph = data;
void *data_end = (void *)(long)skb->data_end;
int ret;
/* single length check */
if (data + sizeof(*iph) > data_end) {
log_err(1);
return TC_ACT_SHOT;
}
__builtin_memset(&key, 0x0, sizeof(key));
key.tunnel_ttl = 64;
if (iph->protocol == IPPROTO_ICMP) {
key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
}
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 ipip6_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
bpf_printk("remote ip6 %x::%x\n", bpf_htonl(key.remote_ipv6[0]),
bpf_htonl(key.remote_ipv6[3]));
return TC_ACT_OK;
}
SEC("tc")
int ip6ip6_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key = {};
void *data = (void *)(long)skb->data;
struct ipv6hdr *iph = data;
void *data_end = (void *)(long)skb->data_end;
int ret;
/* single length check */
if (data + sizeof(*iph) > data_end) {
log_err(1);
return TC_ACT_SHOT;
}
key.tunnel_ttl = 64;
if (iph->nexthdr == 58 /* NEXTHDR_ICMP */) {
key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
}
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 ip6ip6_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
log_err(ret);
return TC_ACT_SHOT;
}
bpf_printk("remote ip6 %x::%x\n", bpf_htonl(key.remote_ipv6[0]),
bpf_htonl(key.remote_ipv6[3]));
return TC_ACT_OK;
}
SEC("tc")
int xfrm_get_state(struct __sk_buff *skb)
{
struct bpf_xfrm_state x;
int ret;
ret = bpf_skb_get_xfrm_state(skb, 0, &x, sizeof(x), 0);
if (ret < 0)
return TC_ACT_OK;
bpf_printk("reqid %d spi 0x%x remote ip 0x%x\n",
x.reqid, bpf_ntohl(x.spi),
bpf_ntohl(x.remote_ipv4));
return TC_ACT_OK;
}
char _license[] SEC("license") = "GPL";