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
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
|
/* Copyright (c) 2016 Thomas Graf <tgraf@tgraf.ch>
*
* 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 <linux/kernel.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/types.h>
#include <linux/bpf.h>
#include <net/lwtunnel.h>
struct bpf_lwt_prog {
struct bpf_prog *prog;
char *name;
};
struct bpf_lwt {
struct bpf_lwt_prog in;
struct bpf_lwt_prog out;
struct bpf_lwt_prog xmit;
int family;
};
#define MAX_PROG_NAME 256
static inline struct bpf_lwt *bpf_lwt_lwtunnel(struct lwtunnel_state *lwt)
{
return (struct bpf_lwt *)lwt->data;
}
#define NO_REDIRECT false
#define CAN_REDIRECT true
static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
struct dst_entry *dst, bool can_redirect)
{
int ret;
/* Preempt disable is needed to protect per-cpu redirect_info between
* BPF prog and skb_do_redirect(). The call_rcu in bpf_prog_put() and
* access to maps strictly require a rcu_read_lock() for protection,
* mixing with BH RCU lock doesn't work.
*/
preempt_disable();
rcu_read_lock();
bpf_compute_data_end(skb);
ret = bpf_prog_run_save_cb(lwt->prog, skb);
rcu_read_unlock();
switch (ret) {
case BPF_OK:
break;
case BPF_REDIRECT:
if (unlikely(!can_redirect)) {
pr_warn_once("Illegal redirect return code in prog %s\n",
lwt->name ? : "<unknown>");
ret = BPF_OK;
} else {
ret = skb_do_redirect(skb);
if (ret == 0)
ret = BPF_REDIRECT;
}
break;
case BPF_DROP:
kfree_skb(skb);
ret = -EPERM;
break;
default:
pr_warn_once("bpf-lwt: Illegal return value %u, expect packet loss\n", ret);
kfree_skb(skb);
ret = -EINVAL;
break;
}
preempt_enable();
return ret;
}
static int bpf_input(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct bpf_lwt *bpf;
int ret;
bpf = bpf_lwt_lwtunnel(dst->lwtstate);
if (bpf->in.prog) {
ret = run_lwt_bpf(skb, &bpf->in, dst, NO_REDIRECT);
if (ret < 0)
return ret;
}
if (unlikely(!dst->lwtstate->orig_input)) {
pr_warn_once("orig_input not set on dst for prog %s\n",
bpf->out.name);
kfree_skb(skb);
return -EINVAL;
}
return dst->lwtstate->orig_input(skb);
}
static int bpf_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct bpf_lwt *bpf;
int ret;
bpf = bpf_lwt_lwtunnel(dst->lwtstate);
if (bpf->out.prog) {
ret = run_lwt_bpf(skb, &bpf->out, dst, NO_REDIRECT);
if (ret < 0)
return ret;
}
if (unlikely(!dst->lwtstate->orig_output)) {
pr_warn_once("orig_output not set on dst for prog %s\n",
bpf->out.name);
kfree_skb(skb);
return -EINVAL;
}
return dst->lwtstate->orig_output(net, sk, skb);
}
static int xmit_check_hhlen(struct sk_buff *skb)
{
int hh_len = skb_dst(skb)->dev->hard_header_len;
if (skb_headroom(skb) < hh_len) {
int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb));
if (pskb_expand_head(skb, nhead, 0, GFP_ATOMIC))
return -ENOMEM;
}
return 0;
}
static int bpf_xmit(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct bpf_lwt *bpf;
bpf = bpf_lwt_lwtunnel(dst->lwtstate);
if (bpf->xmit.prog) {
int ret;
ret = run_lwt_bpf(skb, &bpf->xmit, dst, CAN_REDIRECT);
switch (ret) {
case BPF_OK:
/* If the header was expanded, headroom might be too
* small for L2 header to come, expand as needed.
*/
ret = xmit_check_hhlen(skb);
if (unlikely(ret))
return ret;
return LWTUNNEL_XMIT_CONTINUE;
case BPF_REDIRECT:
return LWTUNNEL_XMIT_DONE;
default:
return ret;
}
}
return LWTUNNEL_XMIT_CONTINUE;
}
static void bpf_lwt_prog_destroy(struct bpf_lwt_prog *prog)
{
if (prog->prog)
bpf_prog_put(prog->prog);
kfree(prog->name);
}
static void bpf_destroy_state(struct lwtunnel_state *lwt)
{
struct bpf_lwt *bpf = bpf_lwt_lwtunnel(lwt);
bpf_lwt_prog_destroy(&bpf->in);
bpf_lwt_prog_destroy(&bpf->out);
bpf_lwt_prog_destroy(&bpf->xmit);
}
static const struct nla_policy bpf_prog_policy[LWT_BPF_PROG_MAX + 1] = {
[LWT_BPF_PROG_FD] = { .type = NLA_U32, },
[LWT_BPF_PROG_NAME] = { .type = NLA_NUL_STRING,
.len = MAX_PROG_NAME },
};
static int bpf_parse_prog(struct nlattr *attr, struct bpf_lwt_prog *prog,
enum bpf_prog_type type)
{
struct nlattr *tb[LWT_BPF_PROG_MAX + 1];
struct bpf_prog *p;
int ret;
u32 fd;
ret = nla_parse_nested(tb, LWT_BPF_PROG_MAX, attr, bpf_prog_policy,
NULL);
if (ret < 0)
return ret;
if (!tb[LWT_BPF_PROG_FD] || !tb[LWT_BPF_PROG_NAME])
return -EINVAL;
prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_KERNEL);
if (!prog->name)
return -ENOMEM;
fd = nla_get_u32(tb[LWT_BPF_PROG_FD]);
p = bpf_prog_get_type(fd, type);
if (IS_ERR(p))
return PTR_ERR(p);
prog->prog = p;
return 0;
}
static const struct nla_policy bpf_nl_policy[LWT_BPF_MAX + 1] = {
[LWT_BPF_IN] = { .type = NLA_NESTED, },
[LWT_BPF_OUT] = { .type = NLA_NESTED, },
[LWT_BPF_XMIT] = { .type = NLA_NESTED, },
[LWT_BPF_XMIT_HEADROOM] = { .type = NLA_U32 },
};
static int bpf_build_state(struct nlattr *nla,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts)
{
struct nlattr *tb[LWT_BPF_MAX + 1];
struct lwtunnel_state *newts;
struct bpf_lwt *bpf;
int ret;
if (family != AF_INET && family != AF_INET6)
return -EAFNOSUPPORT;
ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy, NULL);
if (ret < 0)
return ret;
if (!tb[LWT_BPF_IN] && !tb[LWT_BPF_OUT] && !tb[LWT_BPF_XMIT])
return -EINVAL;
newts = lwtunnel_state_alloc(sizeof(*bpf));
if (!newts)
return -ENOMEM;
newts->type = LWTUNNEL_ENCAP_BPF;
bpf = bpf_lwt_lwtunnel(newts);
if (tb[LWT_BPF_IN]) {
newts->flags |= LWTUNNEL_STATE_INPUT_REDIRECT;
ret = bpf_parse_prog(
|