1// SPDX-License-Identifier: GPL-2.0
2// Copyright (c) 2018 Facebook
3
4#include <string.h>
5
6#include <linux/stddef.h>
7#include <linux/bpf.h>
8#include <linux/in.h>
9#include <linux/in6.h>
10#include <linux/tcp.h>
11#include <linux/if.h>
12#include <errno.h>
13
14#include <bpf/bpf_helpers.h>
15#include <bpf/bpf_endian.h>
16
17#include "bpf_tcp_helpers.h"
18
19#define SRC_REWRITE_IP4		0x7f000004U
20#define DST_REWRITE_IP4		0x7f000001U
21#define DST_REWRITE_PORT4	4444
22
23#ifndef TCP_CA_NAME_MAX
24#define TCP_CA_NAME_MAX 16
25#endif
26
27#ifndef TCP_NOTSENT_LOWAT
28#define TCP_NOTSENT_LOWAT 25
29#endif
30
31#ifndef IFNAMSIZ
32#define IFNAMSIZ 16
33#endif
34
35__attribute__ ((noinline)) __weak
36int do_bind(struct bpf_sock_addr *ctx)
37{
38	struct sockaddr_in sa = {};
39
40	sa.sin_family = AF_INET;
41	sa.sin_port = bpf_htons(0);
42	sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4);
43
44	if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
45		return 0;
46
47	return 1;
48}
49
50static __inline int verify_cc(struct bpf_sock_addr *ctx,
51			      char expected[TCP_CA_NAME_MAX])
52{
53	char buf[TCP_CA_NAME_MAX];
54	int i;
55
56	if (bpf_getsockopt(ctx, SOL_TCP, TCP_CONGESTION, &buf, sizeof(buf)))
57		return 1;
58
59	for (i = 0; i < TCP_CA_NAME_MAX; i++) {
60		if (buf[i] != expected[i])
61			return 1;
62		if (buf[i] == 0)
63			break;
64	}
65
66	return 0;
67}
68
69static __inline int set_cc(struct bpf_sock_addr *ctx)
70{
71	char reno[TCP_CA_NAME_MAX] = "reno";
72	char cubic[TCP_CA_NAME_MAX] = "cubic";
73
74	if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &reno, sizeof(reno)))
75		return 1;
76	if (verify_cc(ctx, reno))
77		return 1;
78
79	if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &cubic, sizeof(cubic)))
80		return 1;
81	if (verify_cc(ctx, cubic))
82		return 1;
83
84	return 0;
85}
86
87static __inline int bind_to_device(struct bpf_sock_addr *ctx)
88{
89	char veth1[IFNAMSIZ] = "test_sock_addr1";
90	char veth2[IFNAMSIZ] = "test_sock_addr2";
91	char missing[IFNAMSIZ] = "nonexistent_dev";
92	char del_bind[IFNAMSIZ] = "";
93
94	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
95				&veth1, sizeof(veth1)))
96		return 1;
97	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
98				&veth2, sizeof(veth2)))
99		return 1;
100	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
101				&missing, sizeof(missing)) != -ENODEV)
102		return 1;
103	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
104				&del_bind, sizeof(del_bind)))
105		return 1;
106
107	return 0;
108}
109
110static __inline int set_keepalive(struct bpf_sock_addr *ctx)
111{
112	int zero = 0, one = 1;
113
114	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_KEEPALIVE, &one, sizeof(one)))
115		return 1;
116	if (ctx->type == SOCK_STREAM) {
117		if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPIDLE, &one, sizeof(one)))
118			return 1;
119		if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPINTVL, &one, sizeof(one)))
120			return 1;
121		if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPCNT, &one, sizeof(one)))
122			return 1;
123		if (bpf_setsockopt(ctx, SOL_TCP, TCP_SYNCNT, &one, sizeof(one)))
124			return 1;
125		if (bpf_setsockopt(ctx, SOL_TCP, TCP_USER_TIMEOUT, &one, sizeof(one)))
126			return 1;
127	}
128	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_KEEPALIVE, &zero, sizeof(zero)))
129		return 1;
130
131	return 0;
132}
133
134static __inline int set_notsent_lowat(struct bpf_sock_addr *ctx)
135{
136	int lowat = 65535;
137
138	if (ctx->type == SOCK_STREAM) {
139		if (bpf_setsockopt(ctx, SOL_TCP, TCP_NOTSENT_LOWAT, &lowat, sizeof(lowat)))
140			return 1;
141	}
142
143	return 0;
144}
145
146SEC("cgroup/connect4")
147int connect_v4_prog(struct bpf_sock_addr *ctx)
148{
149	struct bpf_sock_tuple tuple = {};
150	struct bpf_sock *sk;
151
152	/* Verify that new destination is available. */
153	memset(&tuple.ipv4.saddr, 0, sizeof(tuple.ipv4.saddr));
154	memset(&tuple.ipv4.sport, 0, sizeof(tuple.ipv4.sport));
155
156	tuple.ipv4.daddr = bpf_htonl(DST_REWRITE_IP4);
157	tuple.ipv4.dport = bpf_htons(DST_REWRITE_PORT4);
158
159	/* Bind to device and unbind it. */
160	if (bind_to_device(ctx))
161		return 0;
162
163	if (set_keepalive(ctx))
164		return 0;
165
166	if (set_notsent_lowat(ctx))
167		return 0;
168
169	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
170		return 0;
171	else if (ctx->type == SOCK_STREAM)
172		sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv4),
173				       BPF_F_CURRENT_NETNS, 0);
174	else
175		sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv4),
176				       BPF_F_CURRENT_NETNS, 0);
177
178	if (!sk)
179		return 0;
180
181	if (sk->src_ip4 != tuple.ipv4.daddr ||
182	    sk->src_port != DST_REWRITE_PORT4) {
183		bpf_sk_release(sk);
184		return 0;
185	}
186
187	bpf_sk_release(sk);
188
189	/* Rewrite congestion control. */
190	if (ctx->type == SOCK_STREAM && set_cc(ctx))
191		return 0;
192
193	/* Rewrite destination. */
194	ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4);
195	ctx->user_port = bpf_htons(DST_REWRITE_PORT4);
196
197	return do_bind(ctx) ? 1 : 0;
198}
199
200char _license[] SEC("license") = "GPL";
201