bpf.c 15.7 KB
Newer Older
1
// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
2

3 4 5 6 7 8
/*
 * common eBPF ELF operations.
 *
 * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
 * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
 * Copyright (C) 2015 Huawei Inc.
W
Wang Nan 已提交
9 10 11 12 13 14 15 16 17 18 19 20 21
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation;
 * version 2.1 of the License (not later!)
 *
 * 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 Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this program; if not,  see <http://www.gnu.org/licenses>
22 23 24 25 26 27 28 29
 */

#include <stdlib.h>
#include <memory.h>
#include <unistd.h>
#include <asm/unistd.h>
#include <linux/bpf.h>
#include "bpf.h"
E
Eric Leblond 已提交
30 31
#include "libbpf.h"
#include <errno.h>
32 33

/*
34
 * When building perf, unistd.h is overridden. __NR_bpf is
35
 * required to be defined explicitly.
36 37 38 39 40 41 42 43
 */
#ifndef __NR_bpf
# if defined(__i386__)
#  define __NR_bpf 357
# elif defined(__x86_64__)
#  define __NR_bpf 321
# elif defined(__aarch64__)
#  define __NR_bpf 280
44 45
# elif defined(__sparc__)
#  define __NR_bpf 349
46 47
# elif defined(__s390__)
#  define __NR_bpf 351
48 49 50 51 52
# else
#  error __NR_bpf not defined. libbpf does not support your arch.
# endif
#endif

E
Eric Leblond 已提交
53
#ifndef min
54
#define min(x, y) ((x) < (y) ? (x) : (y))
E
Eric Leblond 已提交
55
#endif
56

M
Mickaël Salaün 已提交
57
static inline __u64 ptr_to_u64(const void *ptr)
58 59 60 61
{
	return (__u64) (unsigned long) ptr;
}

M
Mickaël Salaün 已提交
62 63
static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
			  unsigned int size)
64 65 66 67
{
	return syscall(__NR_bpf, cmd, attr, size);
}

68
int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
69
{
70
	__u32 name_len = create_attr->name ? strlen(create_attr->name) : 0;
71 72 73 74
	union bpf_attr attr;

	memset(&attr, '\0', sizeof(attr));

75 76 77 78 79 80 81 82 83
	attr.map_type = create_attr->map_type;
	attr.key_size = create_attr->key_size;
	attr.value_size = create_attr->value_size;
	attr.max_entries = create_attr->max_entries;
	attr.map_flags = create_attr->map_flags;
	memcpy(attr.map_name, create_attr->name,
	       min(name_len, BPF_OBJ_NAME_LEN - 1));
	attr.numa_node = create_attr->numa_node;
	attr.btf_fd = create_attr->btf_fd;
84 85
	attr.btf_key_type_id = create_attr->btf_key_type_id;
	attr.btf_value_type_id = create_attr->btf_value_type_id;
86
	attr.map_ifindex = create_attr->map_ifindex;
87
	attr.inner_map_fd = create_attr->inner_map_fd;
88

89
	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
90
}
91

92 93 94 95 96 97 98 99 100 101 102 103
int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
			int key_size, int value_size, int max_entries,
			__u32 map_flags, int node)
{
	struct bpf_create_map_attr map_attr = {};

	map_attr.name = name;
	map_attr.map_type = map_type;
	map_attr.map_flags = map_flags;
	map_attr.key_size = key_size;
	map_attr.value_size = value_size;
	map_attr.max_entries = max_entries;
104
	if (node >= 0) {
105 106
		map_attr.numa_node = node;
		map_attr.map_flags |= BPF_F_NUMA_NODE;
107
	}
108

109
	return bpf_create_map_xattr(&map_attr);
110
}
111

112 113 114
int bpf_create_map(enum bpf_map_type map_type, int key_size,
		   int value_size, int max_entries, __u32 map_flags)
{
115 116 117 118 119 120 121 122 123
	struct bpf_create_map_attr map_attr = {};

	map_attr.map_type = map_type;
	map_attr.map_flags = map_flags;
	map_attr.key_size = key_size;
	map_attr.value_size = value_size;
	map_attr.max_entries = max_entries;

	return bpf_create_map_xattr(&map_attr);
124 125
}

126 127 128 129
int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
			int key_size, int value_size, int max_entries,
			__u32 map_flags)
{
130 131 132 133 134 135 136 137 138 139
	struct bpf_create_map_attr map_attr = {};

	map_attr.name = name;
	map_attr.map_type = map_type;
	map_attr.map_flags = map_flags;
	map_attr.key_size = key_size;
	map_attr.value_size = value_size;
	map_attr.max_entries = max_entries;

	return bpf_create_map_xattr(&map_attr);
140 141 142 143
}

int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
			       int key_size, int inner_map_fd, int max_entries,
144
			       __u32 map_flags, int node)
M
Martin KaFai Lau 已提交
145
{
146
	__u32 name_len = name ? strlen(name) : 0;
M
Martin KaFai Lau 已提交
147 148 149 150 151 152 153 154 155 156
	union bpf_attr attr;

	memset(&attr, '\0', sizeof(attr));

	attr.map_type = map_type;
	attr.key_size = key_size;
	attr.value_size = 4;
	attr.inner_map_fd = inner_map_fd;
	attr.max_entries = max_entries;
	attr.map_flags = map_flags;
157 158
	memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1));

159 160 161 162
	if (node >= 0) {
		attr.map_flags |= BPF_F_NUMA_NODE;
		attr.numa_node = node;
	}
M
Martin KaFai Lau 已提交
163 164 165 166

	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
}

167 168 169
int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name,
			  int key_size, int inner_map_fd, int max_entries,
			  __u32 map_flags)
170
{
171 172 173
	return bpf_create_map_in_map_node(map_type, name, key_size,
					  inner_map_fd, max_entries, map_flags,
					  -1);
174 175
}

176 177
int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
			   char *log_buf, size_t log_buf_sz)
178 179
{
	union bpf_attr attr;
180
	void *finfo = NULL;
181 182 183 184 185 186 187
	__u32 name_len;
	int fd;

	if (!load_attr)
		return -EINVAL;

	name_len = load_attr->name ? strlen(load_attr->name) : 0;
188 189

	bzero(&attr, sizeof(attr));
190 191 192 193 194
	attr.prog_type = load_attr->prog_type;
	attr.expected_attach_type = load_attr->expected_attach_type;
	attr.insn_cnt = (__u32)load_attr->insns_cnt;
	attr.insns = ptr_to_u64(load_attr->insns);
	attr.license = ptr_to_u64(load_attr->license);
195 196 197
	attr.log_buf = ptr_to_u64(NULL);
	attr.log_size = 0;
	attr.log_level = 0;
198
	attr.kern_version = load_attr->kern_version;
199
	attr.prog_ifindex = load_attr->prog_ifindex;
200 201 202 203
	attr.prog_btf_fd = load_attr->prog_btf_fd;
	attr.func_info_rec_size = load_attr->func_info_rec_size;
	attr.func_info_cnt = load_attr->func_info_cnt;
	attr.func_info = ptr_to_u64(load_attr->func_info);
204 205
	memcpy(attr.prog_name, load_attr->name,
	       min(name_len, BPF_OBJ_NAME_LEN - 1));
206 207 208 209 210

	fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
	if (fd >= 0 || !log_buf || !log_buf_sz)
		return fd;

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
	/* After bpf_prog_load, the kernel may modify certain attributes
	 * to give user space a hint how to deal with loading failure.
	 * Check to see whether we can make some changes and load again.
	 */
	if (errno == E2BIG && attr.func_info_cnt &&
	    attr.func_info_rec_size < load_attr->func_info_rec_size) {
		__u32 actual_rec_size = load_attr->func_info_rec_size;
		__u32 expected_rec_size = attr.func_info_rec_size;
		__u32 finfo_cnt = load_attr->func_info_cnt;
		__u64 finfo_len = actual_rec_size * finfo_cnt;
		const void *orecord;
		void *nrecord;
		int i;

		finfo = malloc(finfo_len);
		if (!finfo)
			/* further try with log buffer won't help */
			return fd;

		/* zero out bytes kernel does not understand */
		orecord = load_attr->func_info;
		nrecord = finfo;
		for (i = 0; i < load_attr->func_info_cnt; i++) {
			memcpy(nrecord, orecord, expected_rec_size);
			memset(nrecord + expected_rec_size, 0,
			       actual_rec_size - expected_rec_size);
			orecord += actual_rec_size;
			nrecord += actual_rec_size;
		}

		/* try with corrected func info records */
		attr.func_info = ptr_to_u64(finfo);
		attr.func_info_rec_size = load_attr->func_info_rec_size;

		fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));

		if (fd >= 0 || !log_buf || !log_buf_sz)
			goto done;
	}

251 252 253 254 255
	/* Try again with log */
	attr.log_buf = ptr_to_u64(log_buf);
	attr.log_size = log_buf_sz;
	attr.log_level = 1;
	log_buf[0] = 0;
256 257 258 259
	fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
done:
	free(finfo);
	return fd;
260
}
261

262 263 264 265 266
int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
		     size_t insns_cnt, const char *license,
		     __u32 kern_version, char *log_buf,
		     size_t log_buf_sz)
{
267 268 269 270 271 272 273 274 275 276 277 278
	struct bpf_load_program_attr load_attr;

	memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
	load_attr.prog_type = type;
	load_attr.expected_attach_type = 0;
	load_attr.name = NULL;
	load_attr.insns = insns;
	load_attr.insns_cnt = insns_cnt;
	load_attr.license = license;
	load_attr.kern_version = kern_version;

	return bpf_load_program_xattr(&load_attr, log_buf, log_buf_sz);
279 280
}

281
int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
D
David Miller 已提交
282 283 284
		       size_t insns_cnt, __u32 prog_flags, const char *license,
		       __u32 kern_version, char *log_buf, size_t log_buf_sz,
		       int log_level)
285 286 287 288 289 290 291 292 293 294
{
	union bpf_attr attr;

	bzero(&attr, sizeof(attr));
	attr.prog_type = type;
	attr.insn_cnt = (__u32)insns_cnt;
	attr.insns = ptr_to_u64(insns);
	attr.license = ptr_to_u64(license);
	attr.log_buf = ptr_to_u64(log_buf);
	attr.log_size = log_buf_sz;
295
	attr.log_level = log_level;
296 297
	log_buf[0] = 0;
	attr.kern_version = kern_version;
D
David Miller 已提交
298
	attr.prog_flags = prog_flags;
299 300 301 302

	return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
}

303
int bpf_map_update_elem(int fd, const void *key, const void *value,
304
			__u64 flags)
305 306 307 308 309 310 311 312 313 314 315
{
	union bpf_attr attr;

	bzero(&attr, sizeof(attr));
	attr.map_fd = fd;
	attr.key = ptr_to_u64(key);
	attr.value = ptr_to_u64(value);
	attr.flags = flags;

	return sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
}
316

317
int bpf_map_lookup_elem(int fd, const void *key, void *value)
318 319 320 321 322 323 324 325 326 327 328
{
	union bpf_attr attr;

	bzero(&attr, sizeof(attr));
	attr.map_fd = fd;
	attr.key = ptr_to_u64(key);
	attr.value = ptr_to_u64(value);

	return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
}

329 330 331 332 333 334 335 336 337 338 339 340
int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
{
	union bpf_attr attr;

	bzero(&attr, sizeof(attr));
	attr.map_fd = fd;
	attr.key = ptr_to_u64(key);
	attr.value = ptr_to_u64(value);

	return sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
}

341
int bpf_map_delete_elem(int fd, const void *key)
342 343 344 345 346 347 348 349 350 351
{
	union bpf_attr attr;

	bzero(&attr, sizeof(attr));
	attr.map_fd = fd;
	attr.key = ptr_to_u64(key);

	return sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
}

352
int bpf_map_get_next_key(int fd, const void *key, void *next_key)
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
{
	union bpf_attr attr;

	bzero(&attr, sizeof(attr));
	attr.map_fd = fd;
	attr.key = ptr_to_u64(key);
	attr.next_key = ptr_to_u64(next_key);

	return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
}

int bpf_obj_pin(int fd, const char *pathname)
{
	union bpf_attr attr;

	bzero(&attr, sizeof(attr));
	attr.pathname = ptr_to_u64((void *)pathname);
	attr.bpf_fd = fd;

	return sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr));
}

int bpf_obj_get(const char *pathname)
{
	union bpf_attr attr;

	bzero(&attr, sizeof(attr));
	attr.pathname = ptr_to_u64((void *)pathname);

	return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
}
384

385 386
int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
		    unsigned int flags)
387 388 389 390 391
{
	union bpf_attr attr;

	bzero(&attr, sizeof(attr));
	attr.target_fd	   = target_fd;
392
	attr.attach_bpf_fd = prog_fd;
393
	attr.attach_type   = type;
394
	attr.attach_flags  = flags;
395 396 397 398 399 400 401 402 403 404 405 406 407 408

	return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
}

int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
{
	union bpf_attr attr;

	bzero(&attr, sizeof(attr));
	attr.target_fd	 = target_fd;
	attr.attach_type = type;

	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
}
409

410 411 412 413 414 415 416 417 418 419 420 421
int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
{
	union bpf_attr attr;

	bzero(&attr, sizeof(attr));
	attr.target_fd	 = target_fd;
	attr.attach_bpf_fd = prog_fd;
	attr.attach_type = type;

	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
}

422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441
int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
		   __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt)
{
	union bpf_attr attr;
	int ret;

	bzero(&attr, sizeof(attr));
	attr.query.target_fd	= target_fd;
	attr.query.attach_type	= type;
	attr.query.query_flags	= query_flags;
	attr.query.prog_cnt	= *prog_cnt;
	attr.query.prog_ids	= ptr_to_u64(prog_ids);

	ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr));
	if (attach_flags)
		*attach_flags = attr.query.attach_flags;
	*prog_cnt = attr.query.prog_cnt;
	return ret;
}

442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464
int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
		      void *data_out, __u32 *size_out, __u32 *retval,
		      __u32 *duration)
{
	union bpf_attr attr;
	int ret;

	bzero(&attr, sizeof(attr));
	attr.test.prog_fd = prog_fd;
	attr.test.data_in = ptr_to_u64(data);
	attr.test.data_out = ptr_to_u64(data_out);
	attr.test.data_size_in = size;
	attr.test.repeat = repeat;

	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
	if (size_out)
		*size_out = attr.test.data_size_out;
	if (retval)
		*retval = attr.test.retval;
	if (duration)
		*duration = attr.test.duration;
	return ret;
}
M
Martin KaFai Lau 已提交
465

L
Lorenz Bauer 已提交
466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488
int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
{
	union bpf_attr attr;
	int ret;

	if (!test_attr->data_out && test_attr->data_size_out > 0)
		return -EINVAL;

	bzero(&attr, sizeof(attr));
	attr.test.prog_fd = test_attr->prog_fd;
	attr.test.data_in = ptr_to_u64(test_attr->data_in);
	attr.test.data_out = ptr_to_u64(test_attr->data_out);
	attr.test.data_size_in = test_attr->data_size_in;
	attr.test.data_size_out = test_attr->data_size_out;
	attr.test.repeat = test_attr->repeat;

	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
	test_attr->data_size_out = attr.test.data_size_out;
	test_attr->retval = attr.test.retval;
	test_attr->duration = attr.test.duration;
	return ret;
}

M
Martin KaFai Lau 已提交
489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538
int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id)
{
	union bpf_attr attr;
	int err;

	bzero(&attr, sizeof(attr));
	attr.start_id = start_id;

	err = sys_bpf(BPF_PROG_GET_NEXT_ID, &attr, sizeof(attr));
	if (!err)
		*next_id = attr.next_id;

	return err;
}

int bpf_map_get_next_id(__u32 start_id, __u32 *next_id)
{
	union bpf_attr attr;
	int err;

	bzero(&attr, sizeof(attr));
	attr.start_id = start_id;

	err = sys_bpf(BPF_MAP_GET_NEXT_ID, &attr, sizeof(attr));
	if (!err)
		*next_id = attr.next_id;

	return err;
}

int bpf_prog_get_fd_by_id(__u32 id)
{
	union bpf_attr attr;

	bzero(&attr, sizeof(attr));
	attr.prog_id = id;

	return sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
}

int bpf_map_get_fd_by_id(__u32 id)
{
	union bpf_attr attr;

	bzero(&attr, sizeof(attr));
	attr.map_id = id;

	return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
}

539 540 541 542 543 544 545 546 547 548
int bpf_btf_get_fd_by_id(__u32 id)
{
	union bpf_attr attr;

	bzero(&attr, sizeof(attr));
	attr.btf_id = id;

	return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
}

M
Martin KaFai Lau 已提交
549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564
int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len)
{
	union bpf_attr attr;
	int err;

	bzero(&attr, sizeof(attr));
	attr.info.bpf_fd = prog_fd;
	attr.info.info_len = *info_len;
	attr.info.info = ptr_to_u64(info);

	err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, sizeof(attr));
	if (!err)
		*info_len = attr.info.info_len;

	return err;
}
E
Eric Leblond 已提交
565

566 567 568 569 570 571 572 573 574 575 576
int bpf_raw_tracepoint_open(const char *name, int prog_fd)
{
	union bpf_attr attr;

	bzero(&attr, sizeof(attr));
	attr.raw_tracepoint.name = ptr_to_u64(name);
	attr.raw_tracepoint.prog_fd = prog_fd;

	return sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
}

577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600
int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
		 bool do_log)
{
	union bpf_attr attr = {};
	int fd;

	attr.btf = ptr_to_u64(btf);
	attr.btf_size = btf_size;

retry:
	if (do_log && log_buf && log_buf_size) {
		attr.btf_log_level = 1;
		attr.btf_log_size = log_buf_size;
		attr.btf_log_buf = ptr_to_u64(log_buf);
	}

	fd = sys_bpf(BPF_BTF_LOAD, &attr, sizeof(attr));
	if (fd == -1 && !do_log && log_buf && log_buf_size) {
		do_log = true;
		goto retry;
	}

	return fd;
}
601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623

int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
		      __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset,
		      __u64 *probe_addr)
{
	union bpf_attr attr = {};
	int err;

	attr.task_fd_query.pid = pid;
	attr.task_fd_query.fd = fd;
	attr.task_fd_query.flags = flags;
	attr.task_fd_query.buf = ptr_to_u64(buf);
	attr.task_fd_query.buf_len = *buf_len;

	err = sys_bpf(BPF_TASK_FD_QUERY, &attr, sizeof(attr));
	*buf_len = attr.task_fd_query.buf_len;
	*prog_id = attr.task_fd_query.prog_id;
	*fd_type = attr.task_fd_query.fd_type;
	*probe_offset = attr.task_fd_query.probe_offset;
	*probe_addr = attr.task_fd_query.probe_addr;

	return err;
}