forked from iovisor/bcc
-
Notifications
You must be signed in to change notification settings - Fork 0
/
libbpf.c
392 lines (327 loc) · 10.8 KB
/
libbpf.c
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
/*
* Copyright (c) 2015 PLUMgrid, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http:https://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#include <arpa/inet.h>
#include <errno.h>
#include <fcntl.h>
#include <linux/bpf.h>
#include <linux/if_packet.h>
#include <linux/pkt_cls.h>
#include <linux/perf_event.h>
#include <linux/rtnetlink.h>
#include <linux/unistd.h>
#include <linux/version.h>
#include <net/ethernet.h>
#include <net/if.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/ioctl.h>
#include <sys/resource.h>
#include <unistd.h>
#include "libbpf.h"
#include "perf_reader.h"
// TODO: remove these defines when linux-libc-dev exports them properly
#ifndef __NR_bpf
#if defined(__powerpc64__)
#define __NR_bpf 361
#else
#define __NR_bpf 321
#endif
#endif
#ifndef SO_ATTACH_BPF
#define SO_ATTACH_BPF 50
#endif
#ifndef PERF_EVENT_IOC_SET_BPF
#define PERF_EVENT_IOC_SET_BPF _IOW('$', 8, __u32)
#endif
#ifndef PERF_FLAG_FD_CLOEXEC
#define PERF_FLAG_FD_CLOEXEC (1UL << 3)
#endif
static __u64 ptr_to_u64(void *ptr)
{
return (__u64) (unsigned long) ptr;
}
int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries)
{
union bpf_attr attr;
memset(&attr, 0, sizeof(attr));
attr.map_type = map_type;
attr.key_size = key_size;
attr.value_size = value_size;
attr.max_entries = max_entries;
int ret = syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr));
if (ret < 0 && errno == EPERM) {
// see note below about the rationale for this retry
struct rlimit rl = {};
if (getrlimit(RLIMIT_MEMLOCK, &rl) == 0) {
rl.rlim_max = RLIM_INFINITY;
rl.rlim_cur = rl.rlim_max;
if (setrlimit(RLIMIT_MEMLOCK, &rl) == 0)
ret = syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr));
}
}
return ret;
}
int bpf_update_elem(int fd, void *key, void *value, unsigned long long flags)
{
union bpf_attr attr;
memset(&attr, 0, sizeof(attr));
attr.map_fd = fd;
attr.key = ptr_to_u64(key);
attr.value = ptr_to_u64(value);
attr.flags = flags;
return syscall(__NR_bpf, BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
}
int bpf_lookup_elem(int fd, void *key, void *value)
{
union bpf_attr attr;
memset(&attr, 0, sizeof(attr));
attr.map_fd = fd;
attr.key = ptr_to_u64(key);
attr.value = ptr_to_u64(value);
return syscall(__NR_bpf, BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
}
int bpf_delete_elem(int fd, void *key)
{
union bpf_attr attr;
memset(&attr, 0, sizeof(attr));
attr.map_fd = fd;
attr.key = ptr_to_u64(key);
return syscall(__NR_bpf, BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
}
int bpf_get_next_key(int fd, void *key, void *next_key)
{
union bpf_attr attr;
memset(&attr, 0, sizeof(attr));
attr.map_fd = fd;
attr.key = ptr_to_u64(key);
attr.next_key = ptr_to_u64(next_key);
return syscall(__NR_bpf, BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
}
#define ROUND_UP(x, n) (((x) + (n) - 1u) & ~((n) - 1u))
char bpf_log_buf[LOG_BUF_SIZE];
int bpf_prog_load(enum bpf_prog_type prog_type,
const struct bpf_insn *insns, int prog_len,
const char *license, unsigned kern_version,
char *log_buf, unsigned log_buf_size)
{
union bpf_attr attr;
memset(&attr, 0, sizeof(attr));
attr.prog_type = prog_type;
attr.insns = ptr_to_u64((void *) insns);
attr.insn_cnt = prog_len / sizeof(struct bpf_insn);
attr.license = ptr_to_u64((void *) license);
attr.log_buf = ptr_to_u64(log_buf);
attr.log_size = log_buf_size;
attr.log_level = log_buf ? 1 : 0;
attr.kern_version = kern_version;
if (log_buf)
log_buf[0] = 0;
int ret = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
if (ret < 0 && errno == EPERM) {
// When EPERM is returned, two reasons are possible:
// 1. user has no permissions for bpf()
// 2. user has insufficent rlimit for locked memory
// Unfortunately, there is no api to inspect the current usage of locked
// mem for the user, so an accurate calculation of how much memory to lock
// for this new program is difficult to calculate. As a hack, bump the limit
// to unlimited. If program load fails again, return the error.
struct rlimit rl = {};
if (getrlimit(RLIMIT_MEMLOCK, &rl) == 0) {
rl.rlim_max = RLIM_INFINITY;
rl.rlim_cur = rl.rlim_max;
if (setrlimit(RLIMIT_MEMLOCK, &rl) == 0)
ret = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
}
}
if (ret < 0 && !log_buf) {
// caller did not specify log_buf but failure should be printed,
// so call recursively and print the result to stderr
bpf_prog_load(prog_type, insns, prog_len, license, kern_version,
bpf_log_buf, LOG_BUF_SIZE);
fprintf(stderr, "bpf: %s\n%s\n", strerror(errno), bpf_log_buf);
}
return ret;
}
int bpf_open_raw_sock(const char *name)
{
struct sockaddr_ll sll;
int sock;
sock = socket(PF_PACKET, SOCK_RAW | SOCK_NONBLOCK | SOCK_CLOEXEC, htons(ETH_P_ALL));
if (sock < 0) {
printf("cannot create raw socket\n");
return -1;
}
memset(&sll, 0, sizeof(sll));
sll.sll_family = AF_PACKET;
sll.sll_ifindex = if_nametoindex(name);
sll.sll_protocol = htons(ETH_P_ALL);
if (bind(sock, (struct sockaddr *)&sll, sizeof(sll)) < 0) {
printf("bind to %s: %s\n", name, strerror(errno));
close(sock);
return -1;
}
return sock;
}
int bpf_attach_socket(int sock, int prog) {
return setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog, sizeof(prog));
}
static int bpf_attach_tracing_event(int progfd, const char *event_path,
struct perf_reader *reader, int pid, int cpu, int group_fd) {
int efd = -1, pfd;
ssize_t bytes;
char buf[256];
struct perf_event_attr attr = {};
snprintf(buf, sizeof(buf), "%s/id", event_path);
efd = open(buf, O_RDONLY, 0);
if (efd < 0) {
fprintf(stderr, "open(%s): %s\n", buf, strerror(errno));
goto error;
}
bytes = read(efd, buf, sizeof(buf));
if (bytes <= 0 || bytes >= sizeof(buf)) {
fprintf(stderr, "read(%s): %s\n", buf, strerror(errno));
goto error;
}
buf[bytes] = '\0';
attr.config = strtol(buf, NULL, 0);
attr.type = PERF_TYPE_TRACEPOINT;
attr.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_CALLCHAIN;
attr.sample_period = 1;
attr.wakeup_events = 1;
pfd = syscall(__NR_perf_event_open, &attr, pid, cpu, group_fd, PERF_FLAG_FD_CLOEXEC);
if (pfd < 0) {
fprintf(stderr, "perf_event_open(%s/id): %s\n", event_path, strerror(errno));
goto error;
}
perf_reader_set_fd(reader, pfd);
if (perf_reader_mmap(reader, attr.type, attr.sample_type) < 0)
goto error;
if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, progfd) < 0) {
perror("ioctl(PERF_EVENT_IOC_SET_BPF)");
goto error;
}
if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
perror("ioctl(PERF_EVENT_IOC_ENABLE)");
goto error;
}
return 0;
error:
if (efd >= 0)
close(efd);
return -1;
}
static void * bpf_attach_probe(int progfd, const char *event,
const char *event_desc, const char *event_type,
pid_t pid, int cpu, int group_fd,
perf_reader_cb cb, void *cb_cookie) {
int kfd = -1;
char buf[256];
struct perf_reader *reader = NULL;
reader = perf_reader_new(cb, NULL, cb_cookie);
if (!reader)
goto error;
snprintf(buf, sizeof(buf), "/sys/kernel/debug/tracing/%s_events", event_type);
kfd = open(buf, O_WRONLY | O_APPEND, 0);
if (kfd < 0) {
fprintf(stderr, "open(%s): %s\n", buf, strerror(errno));
goto error;
}
if (write(kfd, event_desc, strlen(event_desc)) < 0) {
fprintf(stderr, "write(%s, \"%s\") failed: %s\n", buf, event_desc, strerror(errno));
if (errno == EINVAL)
fprintf(stderr, "check dmesg output for possible cause\n");
goto error;
}
snprintf(buf, sizeof(buf), "/sys/kernel/debug/tracing/events/%ss/%s", event_type, event);
if (bpf_attach_tracing_event(progfd, buf, reader, pid, cpu, group_fd) < 0)
goto error;
return reader;
error:
if (kfd >= 0)
close(kfd);
if (reader)
perf_reader_free(reader);
return NULL;
}
void * bpf_attach_kprobe(int progfd, const char *event,
const char *event_desc,
pid_t pid, int cpu, int group_fd,
perf_reader_cb cb, void *cb_cookie) {
return bpf_attach_probe(progfd, event, event_desc, "kprobe", pid, cpu, group_fd, cb, cb_cookie);
}
void * bpf_attach_uprobe(int progfd, const char *event,
const char *event_desc,
pid_t pid, int cpu, int group_fd,
perf_reader_cb cb, void *cb_cookie) {
return bpf_attach_probe(progfd, event, event_desc, "uprobe", pid, cpu, group_fd, cb, cb_cookie);
}
static int bpf_detach_probe(const char *event_desc, const char *event_type) {
int kfd = -1;
char buf[256];
snprintf(buf, sizeof(buf), "/sys/kernel/debug/tracing/%s_events", event_type);
kfd = open(buf, O_WRONLY | O_APPEND, 0);
if (kfd < 0) {
fprintf(stderr, "open(%s): %s\n", buf, strerror(errno));
goto error;
}
if (write(kfd, event_desc, strlen(event_desc)) < 0) {
fprintf(stderr, "write(%s): %s\n", buf, strerror(errno));
goto error;
}
return 0;
error:
if (kfd >= 0)
close(kfd);
return -1;
}
int bpf_detach_kprobe(const char *event_desc) {
return bpf_detach_probe(event_desc, "kprobe");
}
int bpf_detach_uprobe(const char *event_desc) {
return bpf_detach_probe(event_desc, "uprobe");
}
void * bpf_open_perf_buffer(perf_reader_raw_cb raw_cb, void *cb_cookie, int pid, int cpu) {
int pfd;
struct perf_event_attr attr = {};
struct perf_reader *reader = NULL;
reader = perf_reader_new(NULL, raw_cb, cb_cookie);
if (!reader)
goto error;
attr.config = 10;//PERF_COUNT_SW_BPF_OUTPUT;
attr.type = PERF_TYPE_SOFTWARE;
attr.sample_type = PERF_SAMPLE_RAW;
attr.sample_period = 1;
attr.wakeup_events = 1;
pfd = syscall(__NR_perf_event_open, &attr, pid, cpu, -1, PERF_FLAG_FD_CLOEXEC);
if (pfd < 0) {
fprintf(stderr, "perf_event_open: %s\n", strerror(errno));
fprintf(stderr, " (check your kernel for PERF_COUNT_SW_BPF_OUTPUT support, 4.4 or newer)\n");
goto error;
}
perf_reader_set_fd(reader, pfd);
if (perf_reader_mmap(reader, attr.type, attr.sample_type) < 0)
goto error;
if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
perror("ioctl(PERF_EVENT_IOC_ENABLE)");
goto error;
}
return reader;
error:
if (reader)
perf_reader_free(reader);
return NULL;
}