summaryrefslogtreecommitdiffstats
path: root/samples/sockmap/sockmap_kern.c
blob: 9ff8bc5dc20619220621bfec182ef766af6c3c1b (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io
 *
 * 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.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 */
#include <uapi/linux/bpf.h>
#include <uapi/linux/if_ether.h>
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include "../../tools/testing/selftests/bpf/bpf_helpers.h"
#include "../../tools/testing/selftests/bpf/bpf_endian.h"

/* Sockmap sample program connects a client and a backend together
 * using cgroups.
 *
 *    client:X <---> frontend:80 client:X <---> backend:80
 *
 * For simplicity we hard code values here and bind 1:1. The hard
 * coded values are part of the setup in sockmap.sh script that
 * is associated with this BPF program.
 *
 * The bpf_printk is verbose and prints information as connections
 * are established and verdicts are decided.
 */

#define bpf_printk(fmt, ...)					\
({								\
	       char ____fmt[] = fmt;				\
	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
				##__VA_ARGS__);			\
})

struct bpf_map_def SEC("maps") sock_map = {
	.type = BPF_MAP_TYPE_SOCKMAP,
	.key_size = sizeof(int),
	.value_size = sizeof(int),
	.max_entries = 20,
};

struct bpf_map_def SEC("maps") sock_map_txmsg = {
	.type = BPF_MAP_TYPE_SOCKMAP,
	.key_size = sizeof(int),
	.value_size = sizeof(int),
	.max_entries = 20,
};

struct bpf_map_def SEC("maps") sock_map_redir = {
	.type = BPF_MAP_TYPE_SOCKMAP,
	.key_size = sizeof(int),
	.value_size = sizeof(int),
	.max_entries = 20,
};

struct bpf_map_def SEC("maps") sock_apply_bytes = {
	.type = BPF_MAP_TYPE_ARRAY,
	.key_size = sizeof(int),
	.value_size = sizeof(int),
	.max_entries = 1
};

struct bpf_map_def SEC("maps") sock_cork_bytes = {
	.type = BPF_MAP_TYPE_ARRAY,
	.key_size = sizeof(int),
	.value_size = sizeof(int),
	.max_entries = 1
};

struct bpf_map_def SEC("maps") sock_pull_bytes = {
	.type = BPF_MAP_TYPE_ARRAY,
	.key_size = sizeof(int),
	.value_size = sizeof(int),
	.max_entries = 2
};

struct bpf_map_def SEC("maps") sock_redir_flags = {
	.type = BPF_MAP_TYPE_ARRAY,
	.key_size = sizeof(int),
	.value_size = sizeof(int),
	.max_entries = 1
};

struct bpf_map_def SEC("maps") sock_skb_opts = {
	.type = BPF_MAP_TYPE_ARRAY,
	.key_size = sizeof(int),
	.value_size = sizeof(int),
	.max_entries = 1
};

SEC("sk_skb1")
int bpf_prog1(struct __sk_buff *skb)
{
	return skb->len;
}

SEC("sk_skb2")
int bpf_prog2(struct __sk_buff *skb)
{
	__u32 lport = skb->local_port;
	__u32 rport = skb->remote_port;
	int len, *f, ret, zero = 0;
	__u64 flags = 0;

	if (lport == 10000)
		ret = 10;
	else
		ret = 1;

	len = (__u32)skb->data_end - (__u32)skb->data;
	f = bpf_map_lookup_elem(&sock_skb_opts, &zero);
	if (f && *f) {
		ret = 3;
		flags = *f;
	}

	bpf_printk("sk_skb2: redirect(%iB) flags=%i\n",
		   len, flags);
	return bpf_sk_redirect_map(skb, &sock_map, ret, flags);
}

SEC("sockops")
int bpf_sockmap(struct bpf_sock_ops *skops)
{
	__u32 lport, rport;
	int op, err = 0, index, key, ret;


	op = (int) skops->op;

	switch (op) {
	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
		lport = skops->local_port;
		rport = skops->remote_port;

		if (lport == 10000) {
			ret = 1;
			err = bpf_sock_map_update(skops, &sock_map, &ret,
						  BPF_NOEXIST);
			bpf_printk("passive(%i -> %i) map ctx update err: %d\n",
				   lport, bpf_ntohl(rport), err);
		}
		break;
	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
		lport = skops->local_port;
		rport = skops->remote_port;

		if (bpf_ntohl(rport) == 10001) {
			ret = 10;
			err = bpf_sock_map_update(skops, &sock_map, &ret,
						  BPF_NOEXIST);
			bpf_printk("active(%i -> %i) map ctx update err: %d\n",
				   lport, bpf_ntohl(rport), err);
		}
		break;
	default:
		break;
	}

	return 0;
}

SEC("sk_msg1")
int bpf_prog4(struct sk_msg_md *msg)
{
	int *bytes, zero = 0, one = 1;
	int *start, *end;

	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
	if (bytes)
		bpf_msg_apply_bytes(msg, *bytes);
	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
	if (bytes)
		bpf_msg_cork_bytes(msg, *bytes);
	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
	if (start && end)
		bpf_msg_pull_data(msg, *start, *end, 0);
	return SK_PASS;
}

SEC("sk_msg2")
int bpf_prog5(struct sk_msg_md *msg)
{
	int err1 = -1, err2 = -1, zero = 0, one = 1;
	int *bytes, *start, *end, len1, len2;

	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
	if (bytes)
		err1 = bpf_msg_apply_bytes(msg, *bytes);
	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
	if (bytes)
		err2 = bpf_msg_cork_bytes(msg, *bytes);
	len1 = (__u64)msg->data_end - (__u64)msg->data;
	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
	if (start && end) {
		int err;

		bpf_printk("sk_msg2: pull(%i:%i)\n",
			   start ? *start : 0, end ? *end : 0);
		err = bpf_msg_pull_data(msg, *start, *end, 0);
		if (err)
			bpf_printk("sk_msg2: pull_data err %i\n",
				   err);
		len2 = (__u64)msg->data_end - (__u64)msg->data;
		bpf_printk("sk_msg2: length update %i->%i\n",
			   len1, len2);
	}
	bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n",
		   len1, err1, err2);
	return SK_PASS;
}

SEC("sk_msg3")
int bpf_prog6(struct sk_msg_md *msg)
{
	int *bytes, zero = 0, one = 1, key = 0;
	int *start, *end, *f;
	__u64 flags = 0;

	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
	if (bytes)
		bpf_msg_apply_bytes(msg, *bytes);
	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
	if (bytes)
		bpf_msg_cork_bytes(msg, *bytes);
	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
	if (start && end)
		bpf_msg_pull_data(msg, *start, *end, 0);
	f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
	if (f && *f) {
		key = 2;
		flags = *f;
	}
	return bpf_msg_redirect_map(msg, &sock_map_redir, key, flags);
}

SEC("sk_msg4")
int bpf_prog7(struct sk_msg_md *msg)
{
	int err1 = 0, err2 = 0, zero = 0, one = 1, key = 0;
	int *f, *bytes, *start, *end, len1, len2;
	__u64 flags = 0;

		int err;
	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
	if (bytes)
		err1 = bpf_msg_apply_bytes(msg, *bytes);
	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
	if (bytes)
		err2 = bpf_msg_cork_bytes(msg, *bytes);
	len1 = (__u64)msg->data_end - (__u64)msg->data;
	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
	if (start && end) {

		bpf_printk("sk_msg2: pull(%i:%i)\n",
			   start ? *start : 0, end ? *end : 0);
		err = bpf_msg_pull_data(msg, *start, *end, 0);
		if (err)
			bpf_printk("sk_msg2: pull_data err %i\n",
				   err);
		len2 = (__u64)msg->data_end - (__u64)msg->data;
		bpf_printk("sk_msg2: length update %i->%i\n",
			   len1, len2);
	}
	f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
	if (f && *f) {
		key = 2;
		flags = *f;
	}
	bpf_printk("sk_msg3: redirect(%iB) flags=%i err=%i\n",
		   len1, flags, err1 ? err1 : err2);
	err = bpf_msg_redirect_map(msg, &sock_map_redir, key, flags);
	bpf_printk("sk_msg3: err %i\n", err);
	return err;
}

SEC("sk_msg5")
int bpf_prog8(struct sk_msg_md *msg)
{
	void *data_end = (void *)(long) msg->data_end;
	void *data = (void *)(long) msg->data;
	int ret = 0, *bytes, zero = 0;

	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
	if (bytes) {
		ret = bpf_msg_apply_bytes(msg, *bytes);
		if (ret)
			return SK_DROP;
	} else {
		return SK_DROP;
	}
	return SK_PASS;
}
SEC("sk_msg6")
int bpf_prog9(struct sk_msg_md *msg)
{
	void *data_end = (void *)(long) msg->data_end;
	void *data = (void *)(long) msg->data;
	int ret = 0, *bytes, zero = 0;

	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
	if (bytes) {
		if (((__u64)data_end - (__u64)data) >= *bytes)
			return SK_PASS;
		ret = bpf_msg_cork_bytes(msg, *bytes);
		if (ret)
			return SK_DROP;
	}
	return SK_PASS;
}

SEC("sk_msg7")
int bpf_prog10(struct sk_msg_md *msg)
{
	int *bytes, zero = 0, one = 1;
	int *start, *end;

	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
	if (bytes)
		bpf_msg_apply_bytes(msg, *bytes);
	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
	if (bytes)
		bpf_msg_cork_bytes(msg, *bytes);
	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
	if (start && end)
		bpf_msg_pull_data(msg, *start, *end, 0);

	return SK_DROP;
}


char _license[] SEC("license") = "GPL";