libbpf.c 44.9 KB
Newer Older
1 2
// SPDX-License-Identifier: LGPL-2.1

3 4 5 6 7 8
/*
 * Common eBPF ELF object loading operations.
 *
 * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
 * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
 * Copyright (C) 2015 Huawei Inc.
9
 * Copyright (C) 2017 Nicira, Inc.
W
Wang Nan 已提交
10 11 12 13 14 15 16 17 18 19 20 21 22
 *
 * 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>
23 24 25
 */

#include <stdlib.h>
26 27
#include <stdio.h>
#include <stdarg.h>
28
#include <libgen.h>
29
#include <inttypes.h>
30
#include <string.h>
31
#include <unistd.h>
32 33
#include <fcntl.h>
#include <errno.h>
34
#include <asm/unistd.h>
35
#include <linux/err.h>
36
#include <linux/kernel.h>
37
#include <linux/bpf.h>
38
#include <linux/list.h>
39 40 41 42
#include <linux/limits.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/vfs.h>
43 44
#include <libelf.h>
#include <gelf.h>
45 46

#include "libbpf.h"
47
#include "bpf.h"
48

49 50 51 52
#ifndef EM_BPF
#define EM_BPF 247
#endif

53 54 55 56
#ifndef BPF_FS_MAGIC
#define BPF_FS_MAGIC		0xcafe4a11
#endif

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
#define __printf(a, b)	__attribute__((format(printf, a, b)))

__printf(1, 2)
static int __base_pr(const char *format, ...)
{
	va_list args;
	int err;

	va_start(args, format);
	err = vfprintf(stderr, format, args);
	va_end(args);
	return err;
}

static __printf(1, 2) libbpf_print_fn_t __pr_warning = __base_pr;
static __printf(1, 2) libbpf_print_fn_t __pr_info = __base_pr;
static __printf(1, 2) libbpf_print_fn_t __pr_debug;

#define __pr(func, fmt, ...)	\
do {				\
	if ((func))		\
		(func)("libbpf: " fmt, ##__VA_ARGS__); \
} while (0)

#define pr_warning(fmt, ...)	__pr(__pr_warning, fmt, ##__VA_ARGS__)
#define pr_info(fmt, ...)	__pr(__pr_info, fmt, ##__VA_ARGS__)
#define pr_debug(fmt, ...)	__pr(__pr_debug, fmt, ##__VA_ARGS__)

void libbpf_set_print(libbpf_print_fn_t warn,
		      libbpf_print_fn_t info,
		      libbpf_print_fn_t debug)
{
	__pr_warning = warn;
	__pr_info = info;
	__pr_debug = debug;
}
93

94 95 96 97 98 99 100 101 102 103
#define STRERR_BUFSIZE  128

#define ERRNO_OFFSET(e)		((e) - __LIBBPF_ERRNO__START)
#define ERRCODE_OFFSET(c)	ERRNO_OFFSET(LIBBPF_ERRNO__##c)
#define NR_ERRNO	(__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)

static const char *libbpf_strerror_table[NR_ERRNO] = {
	[ERRCODE_OFFSET(LIBELF)]	= "Something wrong in libelf",
	[ERRCODE_OFFSET(FORMAT)]	= "BPF object format invalid",
	[ERRCODE_OFFSET(KVERSION)]	= "'version' section incorrect or lost",
104
	[ERRCODE_OFFSET(ENDIAN)]	= "Endian mismatch",
105 106 107 108 109
	[ERRCODE_OFFSET(INTERNAL)]	= "Internal error in libbpf",
	[ERRCODE_OFFSET(RELOC)]		= "Relocation failed",
	[ERRCODE_OFFSET(VERIFY)]	= "Kernel verifier blocks program loading",
	[ERRCODE_OFFSET(PROG2BIG)]	= "Program too big",
	[ERRCODE_OFFSET(KVER)]		= "Incorrect kernel version",
110
	[ERRCODE_OFFSET(PROGTYPE)]	= "Kernel doesn't support this program type",
E
Eric Leblond 已提交
111 112
	[ERRCODE_OFFSET(WRNGPID)]	= "Wrong pid in netlink message",
	[ERRCODE_OFFSET(INVSEQ)]	= "Invalid netlink sequence",
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
};

int libbpf_strerror(int err, char *buf, size_t size)
{
	if (!buf || !size)
		return -1;

	err = err > 0 ? err : -err;

	if (err < __LIBBPF_ERRNO__START) {
		int ret;

		ret = strerror_r(err, buf, size);
		buf[size - 1] = '\0';
		return ret;
	}

	if (err < __LIBBPF_ERRNO__END) {
		const char *msg;

		msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
		snprintf(buf, size, "%s", msg);
		buf[size - 1] = '\0';
		return 0;
	}

	snprintf(buf, size, "Unknown libbpf error %d", err);
	buf[size - 1] = '\0';
	return -1;
}

#define CHECK_ERR(action, err, out) do {	\
	err = action;			\
	if (err)			\
		goto out;		\
} while(0)


151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170
/* Copied from tools/perf/util/util.h */
#ifndef zfree
# define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
#endif

#ifndef zclose
# define zclose(fd) ({			\
	int ___err = 0;			\
	if ((fd) >= 0)			\
		___err = close((fd));	\
	fd = -1;			\
	___err; })
#endif

#ifdef HAVE_LIBELF_MMAP_SUPPORT
# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ_MMAP
#else
# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ
#endif

171 172 173 174 175 176 177
/*
 * bpf_prog should be a better name but it has been used in
 * linux/filter.h.
 */
struct bpf_program {
	/* Index in elf obj file, for relocation use. */
	int idx;
178
	char *name;
179 180
	char *section_name;
	struct bpf_insn *insns;
181
	size_t insns_cnt, main_prog_cnt;
182
	enum bpf_prog_type type;
183

184 185 186 187 188
	struct reloc_desc {
		enum {
			RELO_LD64,
			RELO_CALL,
		} type;
189
		int insn_idx;
190 191 192 193
		union {
			int map_idx;
			int text_off;
		};
194 195
	} *reloc_desc;
	int nr_reloc;
196

197 198 199 200 201
	struct {
		int nr;
		int *fds;
	} instances;
	bpf_program_prep_t preprocessor;
202 203 204 205

	struct bpf_object *obj;
	void *priv;
	bpf_program_clear_priv_t clear_priv;
206 207
};

208 209
struct bpf_map {
	int fd;
210
	char *name;
E
Eric Leblond 已提交
211
	size_t offset;
212 213 214 215 216
	struct bpf_map_def def;
	void *priv;
	bpf_map_clear_priv_t clear_priv;
};

217 218
static LIST_HEAD(bpf_objects_list);

219
struct bpf_object {
220 221
	char license[64];
	u32 kern_version;
222

223 224
	struct bpf_program *programs;
	size_t nr_programs;
225 226 227
	struct bpf_map *maps;
	size_t nr_maps;

228
	bool loaded;
229

230 231 232 233 234 235
	/*
	 * Information when doing elf related work. Only valid if fd
	 * is valid.
	 */
	struct {
		int fd;
236 237
		void *obj_buf;
		size_t obj_buf_sz;
238 239
		Elf *elf;
		GElf_Ehdr ehdr;
240
		Elf_Data *symbols;
241
		size_t strtabidx;
242 243 244 245 246
		struct {
			GElf_Shdr shdr;
			Elf_Data *data;
		} *reloc;
		int nr_reloc;
247
		int maps_shndx;
248
		int text_shndx;
249
	} efile;
250 251 252 253 254 255
	/*
	 * All loaded bpf_object is linked in a list, which is
	 * hidden to caller. bpf_objects__<func> handlers deal with
	 * all objects.
	 */
	struct list_head list;
256 257 258 259

	void *priv;
	bpf_object_clear_priv_t clear_priv;

260 261 262 263
	char path[];
};
#define obj_elf_valid(o)	((o)->efile.elf)

264 265
static void bpf_program__unload(struct bpf_program *prog)
{
266 267
	int i;

268 269 270
	if (!prog)
		return;

271 272 273 274 275 276 277 278 279 280 281 282 283 284
	/*
	 * If the object is opened but the program was never loaded,
	 * it is possible that prog->instances.nr == -1.
	 */
	if (prog->instances.nr > 0) {
		for (i = 0; i < prog->instances.nr; i++)
			zclose(prog->instances.fds[i]);
	} else if (prog->instances.nr != -1) {
		pr_warning("Internal error: instances.nr is %d\n",
			   prog->instances.nr);
	}

	prog->instances.nr = -1;
	zfree(&prog->instances.fds);
285 286
}

287 288 289 290 291
static void bpf_program__exit(struct bpf_program *prog)
{
	if (!prog)
		return;

292 293 294 295 296 297
	if (prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

	prog->priv = NULL;
	prog->clear_priv = NULL;

298
	bpf_program__unload(prog);
299
	zfree(&prog->name);
300 301
	zfree(&prog->section_name);
	zfree(&prog->insns);
302 303 304
	zfree(&prog->reloc_desc);

	prog->nr_reloc = 0;
305 306 307 308 309
	prog->insns_cnt = 0;
	prog->idx = -1;
}

static int
310 311
bpf_program__init(void *data, size_t size, char *section_name, int idx,
		  struct bpf_program *prog)
312 313
{
	if (size < sizeof(struct bpf_insn)) {
314
		pr_warning("corrupted section '%s'\n", section_name);
315 316 317 318 319
		return -EINVAL;
	}

	bzero(prog, sizeof(*prog));

320
	prog->section_name = strdup(section_name);
321
	if (!prog->section_name) {
322 323
		pr_warning("failed to alloc name for prog under section(%d) %s\n",
			   idx, section_name);
324 325 326 327 328
		goto errout;
	}

	prog->insns = malloc(size);
	if (!prog->insns) {
329 330
		pr_warning("failed to alloc insns for prog under section %s\n",
			   section_name);
331 332 333 334 335 336
		goto errout;
	}
	prog->insns_cnt = size / sizeof(struct bpf_insn);
	memcpy(prog->insns, data,
	       prog->insns_cnt * sizeof(struct bpf_insn));
	prog->idx = idx;
337 338
	prog->instances.fds = NULL;
	prog->instances.nr = -1;
339
	prog->type = BPF_PROG_TYPE_KPROBE;
340 341 342 343 344 345 346 347 348

	return 0;
errout:
	bpf_program__exit(prog);
	return -ENOMEM;
}

static int
bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
349
			char *section_name, int idx)
350 351 352 353
{
	struct bpf_program prog, *progs;
	int nr_progs, err;

354
	err = bpf_program__init(data, size, section_name, idx, &prog);
355 356 357 358 359 360 361 362 363 364 365 366 367
	if (err)
		return err;

	progs = obj->programs;
	nr_progs = obj->nr_programs;

	progs = realloc(progs, sizeof(progs[0]) * (nr_progs + 1));
	if (!progs) {
		/*
		 * In this case the original obj->programs
		 * is still valid, so don't need special treat for
		 * bpf_close_object().
		 */
368 369
		pr_warning("failed to alloc a new program under section '%s'\n",
			   section_name);
370 371 372 373 374 375 376
		bpf_program__exit(&prog);
		return -ENOMEM;
	}

	pr_debug("found program %s\n", prog.section_name);
	obj->programs = progs;
	obj->nr_programs = nr_progs + 1;
377
	prog.obj = obj;
378 379 380 381
	progs[nr_progs] = prog;
	return 0;
}

382 383 384 385 386 387 388 389
static int
bpf_object__init_prog_names(struct bpf_object *obj)
{
	Elf_Data *symbols = obj->efile.symbols;
	struct bpf_program *prog;
	size_t pi, si;

	for (pi = 0; pi < obj->nr_programs; pi++) {
390
		const char *name = NULL;
391 392

		prog = &obj->programs[pi];
393 394 395 396
		if (prog->idx == obj->efile.text_shndx) {
			name = ".text";
			goto skip_search;
		}
397 398 399 400 401 402 403 404 405

		for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name;
		     si++) {
			GElf_Sym sym;

			if (!gelf_getsym(symbols, si, &sym))
				continue;
			if (sym.st_shndx != prog->idx)
				continue;
406 407
			if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL)
				continue;
408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423

			name = elf_strptr(obj->efile.elf,
					  obj->efile.strtabidx,
					  sym.st_name);
			if (!name) {
				pr_warning("failed to get sym name string for prog %s\n",
					   prog->section_name);
				return -LIBBPF_ERRNO__LIBELF;
			}
		}

		if (!name) {
			pr_warning("failed to find sym for prog %s\n",
				   prog->section_name);
			return -EINVAL;
		}
424
skip_search:
425 426 427 428 429 430 431 432 433 434 435
		prog->name = strdup(name);
		if (!prog->name) {
			pr_warning("failed to allocate memory for prog sym %s\n",
				   name);
			return -ENOMEM;
		}
	}

	return 0;
}

436 437 438
static struct bpf_object *bpf_object__new(const char *path,
					  void *obj_buf,
					  size_t obj_buf_sz)
439 440 441 442 443 444
{
	struct bpf_object *obj;

	obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1);
	if (!obj) {
		pr_warning("alloc memory failed for %s\n", path);
445
		return ERR_PTR(-ENOMEM);
446 447 448 449
	}

	strcpy(obj->path, path);
	obj->efile.fd = -1;
450 451 452 453 454 455 456 457 458

	/*
	 * Caller of this function should also calls
	 * bpf_object__elf_finish() after data collection to return
	 * obj_buf to user. If not, we should duplicate the buffer to
	 * avoid user freeing them before elf finish.
	 */
	obj->efile.obj_buf = obj_buf;
	obj->efile.obj_buf_sz = obj_buf_sz;
459
	obj->efile.maps_shndx = -1;
460

461
	obj->loaded = false;
462 463 464

	INIT_LIST_HEAD(&obj->list);
	list_add(&obj->list, &bpf_objects_list);
465 466 467 468 469 470 471 472 473 474 475 476
	return obj;
}

static void bpf_object__elf_finish(struct bpf_object *obj)
{
	if (!obj_elf_valid(obj))
		return;

	if (obj->efile.elf) {
		elf_end(obj->efile.elf);
		obj->efile.elf = NULL;
	}
477
	obj->efile.symbols = NULL;
478 479 480

	zfree(&obj->efile.reloc);
	obj->efile.nr_reloc = 0;
481
	zclose(obj->efile.fd);
482 483
	obj->efile.obj_buf = NULL;
	obj->efile.obj_buf_sz = 0;
484 485 486 487 488 489 490 491 492
}

static int bpf_object__elf_init(struct bpf_object *obj)
{
	int err = 0;
	GElf_Ehdr *ep;

	if (obj_elf_valid(obj)) {
		pr_warning("elf init: internal error\n");
493
		return -LIBBPF_ERRNO__LIBELF;
494 495
	}

496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513
	if (obj->efile.obj_buf_sz > 0) {
		/*
		 * obj_buf should have been validated by
		 * bpf_object__open_buffer().
		 */
		obj->efile.elf = elf_memory(obj->efile.obj_buf,
					    obj->efile.obj_buf_sz);
	} else {
		obj->efile.fd = open(obj->path, O_RDONLY);
		if (obj->efile.fd < 0) {
			pr_warning("failed to open %s: %s\n", obj->path,
					strerror(errno));
			return -errno;
		}

		obj->efile.elf = elf_begin(obj->efile.fd,
				LIBBPF_ELF_C_READ_MMAP,
				NULL);
514 515 516 517 518
	}

	if (!obj->efile.elf) {
		pr_warning("failed to open %s as ELF file\n",
				obj->path);
519
		err = -LIBBPF_ERRNO__LIBELF;
520 521 522 523 524 525
		goto errout;
	}

	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
		pr_warning("failed to get EHDR from %s\n",
				obj->path);
526
		err = -LIBBPF_ERRNO__FORMAT;
527 528 529 530
		goto errout;
	}
	ep = &obj->efile.ehdr;

531 532
	/* Old LLVM set e_machine to EM_NONE */
	if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) {
533 534
		pr_warning("%s is not an eBPF object file\n",
			obj->path);
535
		err = -LIBBPF_ERRNO__FORMAT;
536 537 538 539 540 541 542 543 544
		goto errout;
	}

	return 0;
errout:
	bpf_object__elf_finish(obj);
	return err;
}

545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562
static int
bpf_object__check_endianness(struct bpf_object *obj)
{
	static unsigned int const endian = 1;

	switch (obj->efile.ehdr.e_ident[EI_DATA]) {
	case ELFDATA2LSB:
		/* We are big endian, BPF obj is little endian. */
		if (*(unsigned char const *)&endian != 1)
			goto mismatch;
		break;

	case ELFDATA2MSB:
		/* We are little endian, BPF obj is big endian. */
		if (*(unsigned char const *)&endian != 0)
			goto mismatch;
		break;
	default:
563
		return -LIBBPF_ERRNO__ENDIAN;
564 565 566 567 568 569
	}

	return 0;

mismatch:
	pr_warning("Error: endianness mismatch.\n");
570
	return -LIBBPF_ERRNO__ENDIAN;
571 572
}

573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590
static int
bpf_object__init_license(struct bpf_object *obj,
			 void *data, size_t size)
{
	memcpy(obj->license, data,
	       min(size, sizeof(obj->license) - 1));
	pr_debug("license of %s is %s\n", obj->path, obj->license);
	return 0;
}

static int
bpf_object__init_kversion(struct bpf_object *obj,
			  void *data, size_t size)
{
	u32 kver;

	if (size != sizeof(kver)) {
		pr_warning("invalid kver section in %s\n", obj->path);
591
		return -LIBBPF_ERRNO__FORMAT;
592 593 594 595 596 597 598 599
	}
	memcpy(&kver, data, sizeof(kver));
	obj->kern_version = kver;
	pr_debug("kernel version of %s is %x\n", obj->path,
		 obj->kern_version);
	return 0;
}

E
Eric Leblond 已提交
600 601 602 603
static int compare_bpf_map(const void *_a, const void *_b)
{
	const struct bpf_map *a = _a;
	const struct bpf_map *b = _b;
604

E
Eric Leblond 已提交
605
	return a->offset - b->offset;
606 607
}

608
static int
E
Eric Leblond 已提交
609
bpf_object__init_maps(struct bpf_object *obj)
610
{
611
	int i, map_idx, map_def_sz, nr_maps = 0;
E
Eric Leblond 已提交
612 613
	Elf_Scn *scn;
	Elf_Data *data;
614 615
	Elf_Data *symbols = obj->efile.symbols;

E
Eric Leblond 已提交
616 617 618 619 620 621 622 623 624 625 626
	if (obj->efile.maps_shndx < 0)
		return -EINVAL;
	if (!symbols)
		return -EINVAL;

	scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx);
	if (scn)
		data = elf_getdata(scn, NULL);
	if (!scn || !data) {
		pr_warning("failed to get Elf_Data from map section %d\n",
			   obj->efile.maps_shndx);
627
		return -EINVAL;
E
Eric Leblond 已提交
628
	}
629

E
Eric Leblond 已提交
630 631 632 633 634 635 636
	/*
	 * Count number of maps. Each map has a name.
	 * Array of maps is not supported: only the first element is
	 * considered.
	 *
	 * TODO: Detect array of map and report error.
	 */
637 638
	for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
		GElf_Sym sym;
E
Eric Leblond 已提交
639 640 641 642 643 644 645 646 647 648 649 650 651 652 653

		if (!gelf_getsym(symbols, i, &sym))
			continue;
		if (sym.st_shndx != obj->efile.maps_shndx)
			continue;
		nr_maps++;
	}

	/* Alloc obj->maps and fill nr_maps. */
	pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path,
		 nr_maps, data->d_size);

	if (!nr_maps)
		return 0;

654 655 656 657 658 659 660 661 662
	/* Assume equally sized map definitions */
	map_def_sz = data->d_size / nr_maps;
	if (!data->d_size || (data->d_size % nr_maps) != 0) {
		pr_warning("unable to determine map definition size "
			   "section %s, %d maps in %zd bytes\n",
			   obj->path, nr_maps, data->d_size);
		return -EINVAL;
	}

E
Eric Leblond 已提交
663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682
	obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
	if (!obj->maps) {
		pr_warning("alloc maps for object failed\n");
		return -ENOMEM;
	}
	obj->nr_maps = nr_maps;

	/*
	 * fill all fd with -1 so won't close incorrect
	 * fd (fd=0 is stdin) when failure (zclose won't close
	 * negative fd)).
	 */
	for (i = 0; i < nr_maps; i++)
		obj->maps[i].fd = -1;

	/*
	 * Fill obj->maps using data in "maps" section.
	 */
	for (i = 0, map_idx = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
		GElf_Sym sym;
683
		const char *map_name;
E
Eric Leblond 已提交
684
		struct bpf_map_def *def;
685 686 687

		if (!gelf_getsym(symbols, i, &sym))
			continue;
688
		if (sym.st_shndx != obj->efile.maps_shndx)
689 690 691
			continue;

		map_name = elf_strptr(obj->efile.elf,
692
				      obj->efile.strtabidx,
693
				      sym.st_name);
E
Eric Leblond 已提交
694
		obj->maps[map_idx].offset = sym.st_value;
695
		if (sym.st_value + map_def_sz > data->d_size) {
E
Eric Leblond 已提交
696 697 698
			pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
				   obj->path, map_name);
			return -EINVAL;
699
		}
E
Eric Leblond 已提交
700

701
		obj->maps[map_idx].name = strdup(map_name);
702 703 704 705
		if (!obj->maps[map_idx].name) {
			pr_warning("failed to alloc map name\n");
			return -ENOMEM;
		}
E
Eric Leblond 已提交
706
		pr_debug("map %d is \"%s\"\n", map_idx,
707
			 obj->maps[map_idx].name);
E
Eric Leblond 已提交
708
		def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737
		/*
		 * If the definition of the map in the object file fits in
		 * bpf_map_def, copy it.  Any extra fields in our version
		 * of bpf_map_def will default to zero as a result of the
		 * calloc above.
		 */
		if (map_def_sz <= sizeof(struct bpf_map_def)) {
			memcpy(&obj->maps[map_idx].def, def, map_def_sz);
		} else {
			/*
			 * Here the map structure being read is bigger than what
			 * we expect, truncate if the excess bits are all zero.
			 * If they are not zero, reject this map as
			 * incompatible.
			 */
			char *b;
			for (b = ((char *)def) + sizeof(struct bpf_map_def);
			     b < ((char *)def) + map_def_sz; b++) {
				if (*b != 0) {
					pr_warning("maps section in %s: \"%s\" "
						   "has unrecognized, non-zero "
						   "options\n",
						   obj->path, map_name);
					return -EINVAL;
				}
			}
			memcpy(&obj->maps[map_idx].def, def,
			       sizeof(struct bpf_map_def));
		}
E
Eric Leblond 已提交
738
		map_idx++;
739
	}
E
Eric Leblond 已提交
740 741

	qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map);
742
	return 0;
743 744
}

745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762
static bool section_have_execinstr(struct bpf_object *obj, int idx)
{
	Elf_Scn *scn;
	GElf_Shdr sh;

	scn = elf_getscn(obj->efile.elf, idx);
	if (!scn)
		return false;

	if (gelf_getshdr(scn, &sh) != &sh)
		return false;

	if (sh.sh_flags & SHF_EXECINSTR)
		return true;

	return false;
}

763 764 765 766 767
static int bpf_object__elf_collect(struct bpf_object *obj)
{
	Elf *elf = obj->efile.elf;
	GElf_Ehdr *ep = &obj->efile.ehdr;
	Elf_Scn *scn = NULL;
768
	int idx = 0, err = 0;
769 770 771 772 773

	/* Elf is corrupted/truncated, avoid calling elf_strptr. */
	if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
		pr_warning("failed to get e_shstrndx from %s\n",
			   obj->path);
774
		return -LIBBPF_ERRNO__FORMAT;
775 776 777 778 779 780 781 782 783
	}

	while ((scn = elf_nextscn(elf, scn)) != NULL) {
		char *name;
		GElf_Shdr sh;
		Elf_Data *data;

		idx++;
		if (gelf_getshdr(scn, &sh) != &sh) {
784 785
			pr_warning("failed to get section(%d) header from %s\n",
				   idx, obj->path);
786
			err = -LIBBPF_ERRNO__FORMAT;
787 788 789 790 791
			goto out;
		}

		name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
		if (!name) {
792 793
			pr_warning("failed to get section(%d) name from %s\n",
				   idx, obj->path);
794
			err = -LIBBPF_ERRNO__FORMAT;
795 796 797 798 799
			goto out;
		}

		data = elf_getdata(scn, 0);
		if (!data) {
800 801
			pr_warning("failed to get section(%d) data from %s(%s)\n",
				   idx, name, obj->path);
802
			err = -LIBBPF_ERRNO__FORMAT;
803 804
			goto out;
		}
805 806
		pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n",
			 idx, name, (unsigned long)data->d_size,
807 808
			 (int)sh.sh_link, (unsigned long)sh.sh_flags,
			 (int)sh.sh_type);
809 810 811 812 813 814 815 816 817

		if (strcmp(name, "license") == 0)
			err = bpf_object__init_license(obj,
						       data->d_buf,
						       data->d_size);
		else if (strcmp(name, "version") == 0)
			err = bpf_object__init_kversion(obj,
							data->d_buf,
							data->d_size);
E
Eric Leblond 已提交
818
		else if (strcmp(name, "maps") == 0)
819
			obj->efile.maps_shndx = idx;
E
Eric Leblond 已提交
820
		else if (sh.sh_type == SHT_SYMTAB) {
821 822 823
			if (obj->efile.symbols) {
				pr_warning("bpf: multiple SYMTAB in %s\n",
					   obj->path);
824
				err = -LIBBPF_ERRNO__FORMAT;
825
			} else {
826
				obj->efile.symbols = data;
827 828
				obj->efile.strtabidx = sh.sh_link;
			}
829 830 831
		} else if ((sh.sh_type == SHT_PROGBITS) &&
			   (sh.sh_flags & SHF_EXECINSTR) &&
			   (data->d_size > 0)) {
832 833
			if (strcmp(name, ".text") == 0)
				obj->efile.text_shndx = idx;
834 835 836
			err = bpf_object__add_program(obj, data->d_buf,
						      data->d_size, name, idx);
			if (err) {
837 838
				char errmsg[STRERR_BUFSIZE];

839 840 841 842
				strerror_r(-err, errmsg, sizeof(errmsg));
				pr_warning("failed to alloc program %s (%s): %s",
					   name, obj->path, errmsg);
			}
843 844 845
		} else if (sh.sh_type == SHT_REL) {
			void *reloc = obj->efile.reloc;
			int nr_reloc = obj->efile.nr_reloc + 1;
846 847 848 849 850 851 852 853
			int sec = sh.sh_info; /* points to other section */

			/* Only do relo for section with exec instructions */
			if (!section_have_execinstr(obj, sec)) {
				pr_debug("skip relo %s(%d) for section(%d)\n",
					 name, idx, sec);
				continue;
			}
854 855 856 857 858 859 860 861 862 863 864 865 866 867 868

			reloc = realloc(reloc,
					sizeof(*obj->efile.reloc) * nr_reloc);
			if (!reloc) {
				pr_warning("realloc failed\n");
				err = -ENOMEM;
			} else {
				int n = nr_reloc - 1;

				obj->efile.reloc = reloc;
				obj->efile.nr_reloc = nr_reloc;

				obj->efile.reloc[n].shdr = sh;
				obj->efile.reloc[n].data = data;
			}
869 870
		} else {
			pr_debug("skip section(%d) %s\n", idx, name);
871
		}
872 873
		if (err)
			goto out;
874
	}
875

876 877 878 879
	if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
		pr_warning("Corrupted ELF file: index of strtab invalid\n");
		return LIBBPF_ERRNO__FORMAT;
	}
880
	if (obj->efile.maps_shndx >= 0) {
E
Eric Leblond 已提交
881
		err = bpf_object__init_maps(obj);
882 883 884 885
		if (err)
			goto out;
	}
	err = bpf_object__init_prog_names(obj);
886 887 888 889
out:
	return err;
}

890 891 892 893 894 895 896 897 898 899 900 901 902 903 904
static struct bpf_program *
bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx)
{
	struct bpf_program *prog;
	size_t i;

	for (i = 0; i < obj->nr_programs; i++) {
		prog = &obj->programs[i];
		if (prog->idx == idx)
			return prog;
	}
	return NULL;
}

static int
905 906
bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
			   Elf_Data *data, struct bpf_object *obj)
907
{
908 909 910 911 912
	Elf_Data *symbols = obj->efile.symbols;
	int text_shndx = obj->efile.text_shndx;
	int maps_shndx = obj->efile.maps_shndx;
	struct bpf_map *maps = obj->maps;
	size_t nr_maps = obj->nr_maps;
913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934
	int i, nrels;

	pr_debug("collecting relocating info for: '%s'\n",
		 prog->section_name);
	nrels = shdr->sh_size / shdr->sh_entsize;

	prog->reloc_desc = malloc(sizeof(*prog->reloc_desc) * nrels);
	if (!prog->reloc_desc) {
		pr_warning("failed to alloc memory in relocation\n");
		return -ENOMEM;
	}
	prog->nr_reloc = nrels;

	for (i = 0; i < nrels; i++) {
		GElf_Sym sym;
		GElf_Rel rel;
		unsigned int insn_idx;
		struct bpf_insn *insns = prog->insns;
		size_t map_idx;

		if (!gelf_getrel(data, i, &rel)) {
			pr_warning("relocation: failed to get %d reloc\n", i);
935
			return -LIBBPF_ERRNO__FORMAT;
936 937 938 939 940 941 942
		}

		if (!gelf_getsym(symbols,
				 GELF_R_SYM(rel.r_info),
				 &sym)) {
			pr_warning("relocation: symbol %"PRIx64" not found\n",
				   GELF_R_SYM(rel.r_info));
943
			return -LIBBPF_ERRNO__FORMAT;
944
		}
D
David Miller 已提交
945 946 947
		pr_debug("relo for %lld value %lld name %d\n",
			 (long long) (rel.r_info >> 32),
			 (long long) sym.st_value, sym.st_name);
948

949
		if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) {
950 951 952 953 954 955 956 957
			pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n",
				   prog->section_name, sym.st_shndx);
			return -LIBBPF_ERRNO__RELOC;
		}

		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
		pr_debug("relocation: insn_idx=%u\n", insn_idx);

958 959 960 961 962 963 964 965 966 967 968
		if (insns[insn_idx].code == (BPF_JMP | BPF_CALL)) {
			if (insns[insn_idx].src_reg != BPF_PSEUDO_CALL) {
				pr_warning("incorrect bpf_call opcode\n");
				return -LIBBPF_ERRNO__RELOC;
			}
			prog->reloc_desc[i].type = RELO_CALL;
			prog->reloc_desc[i].insn_idx = insn_idx;
			prog->reloc_desc[i].text_off = sym.st_value;
			continue;
		}

969 970 971
		if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) {
			pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n",
				   insn_idx, insns[insn_idx].code);
972
			return -LIBBPF_ERRNO__RELOC;
973 974
		}

975 976 977 978 979 980 981 982 983
		/* TODO: 'maps' is sorted. We can use bsearch to make it faster. */
		for (map_idx = 0; map_idx < nr_maps; map_idx++) {
			if (maps[map_idx].offset == sym.st_value) {
				pr_debug("relocation: find map %zd (%s) for insn %u\n",
					 map_idx, maps[map_idx].name, insn_idx);
				break;
			}
		}

984 985 986
		if (map_idx >= nr_maps) {
			pr_warning("bpf relocation: map_idx %d large than %d\n",
				   (int)map_idx, (int)nr_maps - 1);
987
			return -LIBBPF_ERRNO__RELOC;
988 989
		}

990
		prog->reloc_desc[i].type = RELO_LD64;
991 992 993 994 995 996
		prog->reloc_desc[i].insn_idx = insn_idx;
		prog->reloc_desc[i].map_idx = map_idx;
	}
	return 0;
}

997 998 999 1000 1001
static int
bpf_object__create_maps(struct bpf_object *obj)
{
	unsigned int i;

1002 1003 1004
	for (i = 0; i < obj->nr_maps; i++) {
		struct bpf_map_def *def = &obj->maps[i].def;
		int *pfd = &obj->maps[i].fd;
1005

1006 1007 1008 1009 1010
		*pfd = bpf_create_map_name(def->type,
					   obj->maps[i].name,
					   def->key_size,
					   def->value_size,
					   def->max_entries,
1011
					   def->map_flags);
1012 1013 1014 1015
		if (*pfd < 0) {
			size_t j;
			int err = *pfd;

E
Eric Leblond 已提交
1016 1017
			pr_warning("failed to create map (name: '%s'): %s\n",
				   obj->maps[i].name,
1018 1019
				   strerror(errno));
			for (j = 0; j < i; j++)
1020
				zclose(obj->maps[j].fd);
1021 1022
			return err;
		}
E
Eric Leblond 已提交
1023
		pr_debug("create map %s: fd=%d\n", obj->maps[i].name, *pfd);
1024 1025 1026 1027 1028
	}

	return 0;
}

1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062
static int
bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
			struct reloc_desc *relo)
{
	struct bpf_insn *insn, *new_insn;
	struct bpf_program *text;
	size_t new_cnt;

	if (relo->type != RELO_CALL)
		return -LIBBPF_ERRNO__RELOC;

	if (prog->idx == obj->efile.text_shndx) {
		pr_warning("relo in .text insn %d into off %d\n",
			   relo->insn_idx, relo->text_off);
		return -LIBBPF_ERRNO__RELOC;
	}

	if (prog->main_prog_cnt == 0) {
		text = bpf_object__find_prog_by_idx(obj, obj->efile.text_shndx);
		if (!text) {
			pr_warning("no .text section found yet relo into text exist\n");
			return -LIBBPF_ERRNO__RELOC;
		}
		new_cnt = prog->insns_cnt + text->insns_cnt;
		new_insn = realloc(prog->insns, new_cnt * sizeof(*insn));
		if (!new_insn) {
			pr_warning("oom in prog realloc\n");
			return -ENOMEM;
		}
		memcpy(new_insn + prog->insns_cnt, text->insns,
		       text->insns_cnt * sizeof(*insn));
		prog->insns = new_insn;
		prog->main_prog_cnt = prog->insns_cnt;
		prog->insns_cnt = new_cnt;
1063 1064 1065
		pr_debug("added %zd insn from %s to prog %s\n",
			 text->insns_cnt, text->section_name,
			 prog->section_name);
1066 1067 1068 1069 1070 1071
	}
	insn = &prog->insns[relo->insn_idx];
	insn->imm += prog->main_prog_cnt - relo->insn_idx;
	return 0;
}

W
Wang Nan 已提交
1072
static int
1073
bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
W
Wang Nan 已提交
1074
{
1075
	int i, err;
W
Wang Nan 已提交
1076 1077 1078 1079 1080

	if (!prog || !prog->reloc_desc)
		return 0;

	for (i = 0; i < prog->nr_reloc; i++) {
1081 1082 1083
		if (prog->reloc_desc[i].type == RELO_LD64) {
			struct bpf_insn *insns = prog->insns;
			int insn_idx, map_idx;
W
Wang Nan 已提交
1084

1085 1086
			insn_idx = prog->reloc_desc[i].insn_idx;
			map_idx = prog->reloc_desc[i].map_idx;
W
Wang Nan 已提交
1087

1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099
			if (insn_idx >= (int)prog->insns_cnt) {
				pr_warning("relocation out of range: '%s'\n",
					   prog->section_name);
				return -LIBBPF_ERRNO__RELOC;
			}
			insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
			insns[insn_idx].imm = obj->maps[map_idx].fd;
		} else {
			err = bpf_program__reloc_text(prog, obj,
						      &prog->reloc_desc[i]);
			if (err)
				return err;
W
Wang Nan 已提交
1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118
		}
	}

	zfree(&prog->reloc_desc);
	prog->nr_reloc = 0;
	return 0;
}


static int
bpf_object__relocate(struct bpf_object *obj)
{
	struct bpf_program *prog;
	size_t i;
	int err;

	for (i = 0; i < obj->nr_programs; i++) {
		prog = &obj->programs[i];

1119
		err = bpf_program__relocate(prog, obj);
W
Wang Nan 已提交
1120 1121 1122 1123 1124 1125 1126 1127 1128
		if (err) {
			pr_warning("failed to relocate '%s'\n",
				   prog->section_name);
			return err;
		}
	}
	return 0;
}

1129 1130 1131 1132 1133 1134
static int bpf_object__collect_reloc(struct bpf_object *obj)
{
	int i, err;

	if (!obj_elf_valid(obj)) {
		pr_warning("Internal error: elf object is closed\n");
1135
		return -LIBBPF_ERRNO__INTERNAL;
1136 1137 1138 1139 1140 1141 1142 1143 1144 1145
	}

	for (i = 0; i < obj->efile.nr_reloc; i++) {
		GElf_Shdr *shdr = &obj->efile.reloc[i].shdr;
		Elf_Data *data = obj->efile.reloc[i].data;
		int idx = shdr->sh_info;
		struct bpf_program *prog;

		if (shdr->sh_type != SHT_REL) {
			pr_warning("internal error at %d\n", __LINE__);
1146
			return -LIBBPF_ERRNO__INTERNAL;
1147 1148 1149 1150
		}

		prog = bpf_object__find_prog_by_idx(obj, idx);
		if (!prog) {
1151
			pr_warning("relocation failed: no section(%d)\n", idx);
1152
			return -LIBBPF_ERRNO__RELOC;
1153 1154
		}

1155
		err = bpf_program__collect_reloc(prog,
1156
						 shdr, data,
1157
						 obj);
1158
		if (err)
1159
			return err;
1160 1161 1162 1163
	}
	return 0;
}

1164
static int
1165
load_program(enum bpf_prog_type type, const char *name, struct bpf_insn *insns,
1166
	     int insns_cnt, char *license, u32 kern_version, int *pfd)
1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177
{
	int ret;
	char *log_buf;

	if (!insns || !insns_cnt)
		return -EINVAL;

	log_buf = malloc(BPF_LOG_BUF_SIZE);
	if (!log_buf)
		pr_warning("Alloc log buffer for bpf loader error, continue without log\n");

1178 1179
	ret = bpf_load_program_name(type, name, insns, insns_cnt, license,
				    kern_version, log_buf, BPF_LOG_BUF_SIZE);
1180 1181 1182 1183 1184 1185 1186

	if (ret >= 0) {
		*pfd = ret;
		ret = 0;
		goto out;
	}

1187
	ret = -LIBBPF_ERRNO__LOAD;
1188 1189
	pr_warning("load bpf program failed: %s\n", strerror(errno));

1190 1191
	if (log_buf && log_buf[0] != '\0') {
		ret = -LIBBPF_ERRNO__VERIFY;
1192 1193 1194
		pr_warning("-- BEGIN DUMP LOG ---\n");
		pr_warning("\n%s\n", log_buf);
		pr_warning("-- END LOG --\n");
1195 1196 1197 1198
	} else if (insns_cnt >= BPF_MAXINSNS) {
		pr_warning("Program too large (%d insns), at most %d insns\n",
			   insns_cnt, BPF_MAXINSNS);
		ret = -LIBBPF_ERRNO__PROG2BIG;
1199
	} else {
1200 1201 1202 1203
		/* Wrong program type? */
		if (type != BPF_PROG_TYPE_KPROBE) {
			int fd;

1204 1205 1206
			fd = bpf_load_program_name(BPF_PROG_TYPE_KPROBE, name,
						   insns, insns_cnt, license,
						   kern_version, NULL, 0);
1207 1208 1209 1210 1211
			if (fd >= 0) {
				close(fd);
				ret = -LIBBPF_ERRNO__PROGTYPE;
				goto out;
			}
1212
		}
1213 1214 1215

		if (log_buf)
			ret = -LIBBPF_ERRNO__KVER;
1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226
	}

out:
	free(log_buf);
	return ret;
}

static int
bpf_program__load(struct bpf_program *prog,
		  char *license, u32 kern_version)
{
1227
	int err = 0, fd, i;
1228

1229 1230 1231 1232 1233 1234
	if (prog->instances.nr < 0 || !prog->instances.fds) {
		if (prog->preprocessor) {
			pr_warning("Internal error: can't load program '%s'\n",
				   prog->section_name);
			return -LIBBPF_ERRNO__INTERNAL;
		}
1235

1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249
		prog->instances.fds = malloc(sizeof(int));
		if (!prog->instances.fds) {
			pr_warning("Not enough memory for BPF fds\n");
			return -ENOMEM;
		}
		prog->instances.nr = 1;
		prog->instances.fds[0] = -1;
	}

	if (!prog->preprocessor) {
		if (prog->instances.nr != 1) {
			pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
				   prog->section_name, prog->instances.nr);
		}
1250 1251
		err = load_program(prog->type, prog->name, prog->insns,
				   prog->insns_cnt, license, kern_version, &fd);
1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278
		if (!err)
			prog->instances.fds[0] = fd;
		goto out;
	}

	for (i = 0; i < prog->instances.nr; i++) {
		struct bpf_prog_prep_result result;
		bpf_program_prep_t preprocessor = prog->preprocessor;

		bzero(&result, sizeof(result));
		err = preprocessor(prog, i, prog->insns,
				   prog->insns_cnt, &result);
		if (err) {
			pr_warning("Preprocessing the %dth instance of program '%s' failed\n",
				   i, prog->section_name);
			goto out;
		}

		if (!result.new_insn_ptr || !result.new_insn_cnt) {
			pr_debug("Skip loading the %dth instance of program '%s'\n",
				 i, prog->section_name);
			prog->instances.fds[i] = -1;
			if (result.pfd)
				*result.pfd = -1;
			continue;
		}

1279 1280
		err = load_program(prog->type, prog->name,
				   result.new_insn_ptr,
1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294
				   result.new_insn_cnt,
				   license, kern_version, &fd);

		if (err) {
			pr_warning("Loading the %dth instance of program '%s' failed\n",
					i, prog->section_name);
			goto out;
		}

		if (result.pfd)
			*result.pfd = fd;
		prog->instances.fds[i] = fd;
	}
out:
1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309
	if (err)
		pr_warning("failed to load program '%s'\n",
			   prog->section_name);
	zfree(&prog->insns);
	prog->insns_cnt = 0;
	return err;
}

static int
bpf_object__load_progs(struct bpf_object *obj)
{
	size_t i;
	int err;

	for (i = 0; i < obj->nr_programs; i++) {
1310 1311
		if (obj->programs[i].idx == obj->efile.text_shndx)
			continue;
1312 1313 1314 1315 1316 1317 1318 1319 1320
		err = bpf_program__load(&obj->programs[i],
					obj->license,
					obj->kern_version);
		if (err)
			return err;
	}
	return 0;
}

1321 1322 1323 1324 1325
static int bpf_object__validate(struct bpf_object *obj)
{
	if (obj->kern_version == 0) {
		pr_warning("%s doesn't provide kernel version\n",
			   obj->path);
1326
		return -LIBBPF_ERRNO__KVERSION;
1327 1328 1329 1330
	}
	return 0;
}

1331
static struct bpf_object *
1332
__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz)
1333 1334
{
	struct bpf_object *obj;
1335
	int err;
1336 1337 1338

	if (elf_version(EV_CURRENT) == EV_NONE) {
		pr_warning("failed to init libelf for %s\n", path);
1339
		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
1340 1341
	}

1342
	obj = bpf_object__new(path, obj_buf, obj_buf_sz);
1343 1344
	if (IS_ERR(obj))
		return obj;
1345

1346 1347 1348 1349 1350
	CHECK_ERR(bpf_object__elf_init(obj), err, out);
	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
	CHECK_ERR(bpf_object__elf_collect(obj), err, out);
	CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
	CHECK_ERR(bpf_object__validate(obj), err, out);
1351 1352 1353 1354 1355

	bpf_object__elf_finish(obj);
	return obj;
out:
	bpf_object__close(obj);
1356
	return ERR_PTR(err);
1357 1358 1359 1360 1361 1362 1363 1364 1365 1366
}

struct bpf_object *bpf_object__open(const char *path)
{
	/* param validation */
	if (!path)
		return NULL;

	pr_debug("loading %s\n", path);

1367 1368 1369 1370
	return __bpf_object__open(path, NULL, 0);
}

struct bpf_object *bpf_object__open_buffer(void *obj_buf,
1371 1372
					   size_t obj_buf_sz,
					   const char *name)
1373
{
1374 1375
	char tmp_name[64];

1376 1377 1378 1379
	/* param validation */
	if (!obj_buf || obj_buf_sz <= 0)
		return NULL;

1380 1381 1382 1383 1384 1385 1386 1387 1388
	if (!name) {
		snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx",
			 (unsigned long)obj_buf,
			 (unsigned long)obj_buf_sz);
		tmp_name[sizeof(tmp_name) - 1] = '\0';
		name = tmp_name;
	}
	pr_debug("loading object '%s' from buffer\n",
		 name);
1389

1390
	return __bpf_object__open(name, obj_buf, obj_buf_sz);
1391 1392
}

1393 1394 1395 1396 1397 1398 1399
int bpf_object__unload(struct bpf_object *obj)
{
	size_t i;

	if (!obj)
		return -EINVAL;

1400 1401
	for (i = 0; i < obj->nr_maps; i++)
		zclose(obj->maps[i].fd);
1402

1403 1404 1405
	for (i = 0; i < obj->nr_programs; i++)
		bpf_program__unload(&obj->programs[i]);

1406 1407 1408 1409 1410
	return 0;
}

int bpf_object__load(struct bpf_object *obj)
{
1411 1412
	int err;

1413 1414 1415 1416 1417 1418 1419 1420 1421
	if (!obj)
		return -EINVAL;

	if (obj->loaded) {
		pr_warning("object should not be loaded twice\n");
		return -EINVAL;
	}

	obj->loaded = true;
1422 1423 1424 1425

	CHECK_ERR(bpf_object__create_maps(obj), err, out);
	CHECK_ERR(bpf_object__relocate(obj), err, out);
	CHECK_ERR(bpf_object__load_progs(obj), err, out);
1426 1427 1428 1429 1430

	return 0;
out:
	bpf_object__unload(obj);
	pr_warning("failed to load object '%s'\n", obj->path);
1431
	return err;
1432 1433
}

1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543
static int check_path(const char *path)
{
	struct statfs st_fs;
	char *dname, *dir;
	int err = 0;

	if (path == NULL)
		return -EINVAL;

	dname = strdup(path);
	if (dname == NULL)
		return -ENOMEM;

	dir = dirname(dname);
	if (statfs(dir, &st_fs)) {
		pr_warning("failed to statfs %s: %s\n", dir, strerror(errno));
		err = -errno;
	}
	free(dname);

	if (!err && st_fs.f_type != BPF_FS_MAGIC) {
		pr_warning("specified path %s is not on BPF FS\n", path);
		err = -EINVAL;
	}

	return err;
}

int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
			      int instance)
{
	int err;

	err = check_path(path);
	if (err)
		return err;

	if (prog == NULL) {
		pr_warning("invalid program pointer\n");
		return -EINVAL;
	}

	if (instance < 0 || instance >= prog->instances.nr) {
		pr_warning("invalid prog instance %d of prog %s (max %d)\n",
			   instance, prog->section_name, prog->instances.nr);
		return -EINVAL;
	}

	if (bpf_obj_pin(prog->instances.fds[instance], path)) {
		pr_warning("failed to pin program: %s\n", strerror(errno));
		return -errno;
	}
	pr_debug("pinned program '%s'\n", path);

	return 0;
}

static int make_dir(const char *path)
{
	int err = 0;

	if (mkdir(path, 0700) && errno != EEXIST)
		err = -errno;

	if (err)
		pr_warning("failed to mkdir %s: %s\n", path, strerror(-err));
	return err;
}

int bpf_program__pin(struct bpf_program *prog, const char *path)
{
	int i, err;

	err = check_path(path);
	if (err)
		return err;

	if (prog == NULL) {
		pr_warning("invalid program pointer\n");
		return -EINVAL;
	}

	if (prog->instances.nr <= 0) {
		pr_warning("no instances of prog %s to pin\n",
			   prog->section_name);
		return -EINVAL;
	}

	err = make_dir(path);
	if (err)
		return err;

	for (i = 0; i < prog->instances.nr; i++) {
		char buf[PATH_MAX];
		int len;

		len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
		if (len < 0)
			return -EINVAL;
		else if (len >= PATH_MAX)
			return -ENAMETOOLONG;

		err = bpf_program__pin_instance(prog, buf, i);
		if (err)
			return err;
	}

	return 0;
}

J
Joe Stringer 已提交
1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565
int bpf_map__pin(struct bpf_map *map, const char *path)
{
	int err;

	err = check_path(path);
	if (err)
		return err;

	if (map == NULL) {
		pr_warning("invalid map pointer\n");
		return -EINVAL;
	}

	if (bpf_obj_pin(map->fd, path)) {
		pr_warning("failed to pin map: %s\n", strerror(errno));
		return -errno;
	}

	pr_debug("pinned map '%s'\n", path);
	return 0;
}

1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618
int bpf_object__pin(struct bpf_object *obj, const char *path)
{
	struct bpf_program *prog;
	struct bpf_map *map;
	int err;

	if (!obj)
		return -ENOENT;

	if (!obj->loaded) {
		pr_warning("object not yet loaded; load it first\n");
		return -ENOENT;
	}

	err = make_dir(path);
	if (err)
		return err;

	bpf_map__for_each(map, obj) {
		char buf[PATH_MAX];
		int len;

		len = snprintf(buf, PATH_MAX, "%s/%s", path,
			       bpf_map__name(map));
		if (len < 0)
			return -EINVAL;
		else if (len >= PATH_MAX)
			return -ENAMETOOLONG;

		err = bpf_map__pin(map, buf);
		if (err)
			return err;
	}

	bpf_object__for_each_program(prog, obj) {
		char buf[PATH_MAX];
		int len;

		len = snprintf(buf, PATH_MAX, "%s/%s", path,
			       prog->section_name);
		if (len < 0)
			return -EINVAL;
		else if (len >= PATH_MAX)
			return -ENAMETOOLONG;

		err = bpf_program__pin(prog, buf);
		if (err)
			return err;
	}

	return 0;
}

1619 1620
void bpf_object__close(struct bpf_object *obj)
{
1621 1622
	size_t i;

1623 1624 1625
	if (!obj)
		return;

1626 1627 1628
	if (obj->clear_priv)
		obj->clear_priv(obj, obj->priv);

1629
	bpf_object__elf_finish(obj);
1630
	bpf_object__unload(obj);
1631

1632
	for (i = 0; i < obj->nr_maps; i++) {
1633
		zfree(&obj->maps[i].name);
1634 1635 1636 1637 1638 1639 1640 1641
		if (obj->maps[i].clear_priv)
			obj->maps[i].clear_priv(&obj->maps[i],
						obj->maps[i].priv);
		obj->maps[i].priv = NULL;
		obj->maps[i].clear_priv = NULL;
	}
	zfree(&obj->maps);
	obj->nr_maps = 0;
1642 1643 1644 1645 1646 1647 1648

	if (obj->programs && obj->nr_programs) {
		for (i = 0; i < obj->nr_programs; i++)
			bpf_program__exit(&obj->programs[i]);
	}
	zfree(&obj->programs);

1649
	list_del(&obj->list);
1650 1651
	free(obj);
}
1652

1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671
struct bpf_object *
bpf_object__next(struct bpf_object *prev)
{
	struct bpf_object *next;

	if (!prev)
		next = list_first_entry(&bpf_objects_list,
					struct bpf_object,
					list);
	else
		next = list_next_entry(prev, list);

	/* Empty list is noticed here so don't need checking on entry. */
	if (&next->list == &bpf_objects_list)
		return NULL;

	return next;
}

1672
const char *bpf_object__name(struct bpf_object *obj)
1673
{
1674
	return obj ? obj->path : ERR_PTR(-EINVAL);
1675 1676
}

1677
unsigned int bpf_object__kversion(struct bpf_object *obj)
1678
{
1679
	return obj ? obj->kern_version : 0;
1680 1681
}

1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697
int bpf_object__set_priv(struct bpf_object *obj, void *priv,
			 bpf_object_clear_priv_t clear_priv)
{
	if (obj->priv && obj->clear_priv)
		obj->clear_priv(obj, obj->priv);

	obj->priv = priv;
	obj->clear_priv = clear_priv;
	return 0;
}

void *bpf_object__priv(struct bpf_object *obj)
{
	return obj ? obj->priv : ERR_PTR(-EINVAL);
}

1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719
struct bpf_program *
bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
{
	size_t idx;

	if (!obj->programs)
		return NULL;
	/* First handler */
	if (prev == NULL)
		return &obj->programs[0];

	if (prev->obj != obj) {
		pr_warning("error: program handler doesn't match object\n");
		return NULL;
	}

	idx = (prev - obj->programs) + 1;
	if (idx >= obj->nr_programs)
		return NULL;
	return &obj->programs[idx];
}

1720 1721
int bpf_program__set_priv(struct bpf_program *prog, void *priv,
			  bpf_program_clear_priv_t clear_priv)
1722 1723 1724 1725 1726 1727 1728 1729 1730
{
	if (prog->priv && prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

	prog->priv = priv;
	prog->clear_priv = clear_priv;
	return 0;
}

1731
void *bpf_program__priv(struct bpf_program *prog)
1732
{
1733
	return prog ? prog->priv : ERR_PTR(-EINVAL);
1734 1735
}

1736
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
1737 1738 1739 1740
{
	const char *title;

	title = prog->section_name;
1741
	if (needs_copy) {
1742 1743 1744
		title = strdup(title);
		if (!title) {
			pr_warning("failed to strdup program title\n");
1745
			return ERR_PTR(-ENOMEM);
1746 1747 1748 1749 1750 1751 1752 1753
		}
	}

	return title;
}

int bpf_program__fd(struct bpf_program *prog)
{
1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802
	return bpf_program__nth_fd(prog, 0);
}

int bpf_program__set_prep(struct bpf_program *prog, int nr_instances,
			  bpf_program_prep_t prep)
{
	int *instances_fds;

	if (nr_instances <= 0 || !prep)
		return -EINVAL;

	if (prog->instances.nr > 0 || prog->instances.fds) {
		pr_warning("Can't set pre-processor after loading\n");
		return -EINVAL;
	}

	instances_fds = malloc(sizeof(int) * nr_instances);
	if (!instances_fds) {
		pr_warning("alloc memory failed for fds\n");
		return -ENOMEM;
	}

	/* fill all fd with -1 */
	memset(instances_fds, -1, sizeof(int) * nr_instances);

	prog->instances.nr = nr_instances;
	prog->instances.fds = instances_fds;
	prog->preprocessor = prep;
	return 0;
}

int bpf_program__nth_fd(struct bpf_program *prog, int n)
{
	int fd;

	if (n >= prog->instances.nr || n < 0) {
		pr_warning("Can't get the %dth fd from program %s: only %d instances\n",
			   n, prog->section_name, prog->instances.nr);
		return -EINVAL;
	}

	fd = prog->instances.fds[n];
	if (fd < 0) {
		pr_warning("%dth instance of program '%s' is invalid\n",
			   n, prog->section_name);
		return -ENOENT;
	}

	return fd;
1803
}
1804

1805
void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
1806 1807 1808 1809 1810 1811 1812 1813 1814 1815
{
	prog->type = type;
}

static bool bpf_program__is_type(struct bpf_program *prog,
				 enum bpf_prog_type type)
{
	return prog ? (prog->type == type) : false;
}

1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829
#define BPF_PROG_TYPE_FNS(NAME, TYPE)			\
int bpf_program__set_##NAME(struct bpf_program *prog)	\
{							\
	if (!prog)					\
		return -EINVAL;				\
	bpf_program__set_type(prog, TYPE);		\
	return 0;					\
}							\
							\
bool bpf_program__is_##NAME(struct bpf_program *prog)	\
{							\
	return bpf_program__is_type(prog, TYPE);	\
}							\

1830
BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
1831
BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
1832 1833
BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
1834
BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
1835 1836
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
1837

1838
#define BPF_PROG_SEC(string, type) { string, sizeof(string) - 1, type }
1839 1840 1841 1842 1843 1844 1845 1846
static const struct {
	const char *sec;
	size_t len;
	enum bpf_prog_type prog_type;
} section_names[] = {
	BPF_PROG_SEC("socket",		BPF_PROG_TYPE_SOCKET_FILTER),
	BPF_PROG_SEC("kprobe/",		BPF_PROG_TYPE_KPROBE),
	BPF_PROG_SEC("kretprobe/",	BPF_PROG_TYPE_KPROBE),
1847 1848
	BPF_PROG_SEC("classifier",	BPF_PROG_TYPE_SCHED_CLS),
	BPF_PROG_SEC("action",		BPF_PROG_TYPE_SCHED_ACT),
1849 1850 1851 1852 1853 1854
	BPF_PROG_SEC("tracepoint/",	BPF_PROG_TYPE_TRACEPOINT),
	BPF_PROG_SEC("xdp",		BPF_PROG_TYPE_XDP),
	BPF_PROG_SEC("perf_event",	BPF_PROG_TYPE_PERF_EVENT),
	BPF_PROG_SEC("cgroup/skb",	BPF_PROG_TYPE_CGROUP_SKB),
	BPF_PROG_SEC("cgroup/sock",	BPF_PROG_TYPE_CGROUP_SOCK),
	BPF_PROG_SEC("cgroup/dev",	BPF_PROG_TYPE_CGROUP_DEVICE),
1855 1856 1857
	BPF_PROG_SEC("lwt_in",		BPF_PROG_TYPE_LWT_IN),
	BPF_PROG_SEC("lwt_out",		BPF_PROG_TYPE_LWT_OUT),
	BPF_PROG_SEC("lwt_xmit",	BPF_PROG_TYPE_LWT_XMIT),
1858 1859
	BPF_PROG_SEC("sockops",		BPF_PROG_TYPE_SOCK_OPS),
	BPF_PROG_SEC("sk_skb",		BPF_PROG_TYPE_SK_SKB),
1860
	BPF_PROG_SEC("sk_msg",		BPF_PROG_TYPE_SK_MSG),
1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882
};
#undef BPF_PROG_SEC

static enum bpf_prog_type bpf_program__guess_type(struct bpf_program *prog)
{
	int i;

	if (!prog->section_name)
		goto err;

	for (i = 0; i < ARRAY_SIZE(section_names); i++)
		if (strncmp(prog->section_name, section_names[i].sec,
			    section_names[i].len) == 0)
			return section_names[i].prog_type;

err:
	pr_warning("failed to guess program type based on section name %s\n",
		   prog->section_name);

	return BPF_PROG_TYPE_UNSPEC;
}

1883
int bpf_map__fd(struct bpf_map *map)
1884
{
1885
	return map ? map->fd : -EINVAL;
1886 1887
}

1888
const struct bpf_map_def *bpf_map__def(struct bpf_map *map)
1889
{
1890
	return map ? &map->def : ERR_PTR(-EINVAL);
1891 1892
}

1893
const char *bpf_map__name(struct bpf_map *map)
1894
{
1895
	return map ? map->name : NULL;
1896 1897
}

1898 1899
int bpf_map__set_priv(struct bpf_map *map, void *priv,
		     bpf_map_clear_priv_t clear_priv)
1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913
{
	if (!map)
		return -EINVAL;

	if (map->priv) {
		if (map->clear_priv)
			map->clear_priv(map, map->priv);
	}

	map->priv = priv;
	map->clear_priv = clear_priv;
	return 0;
}

1914
void *bpf_map__priv(struct bpf_map *map)
1915
{
1916
	return map ? map->priv : ERR_PTR(-EINVAL);
1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944
}

struct bpf_map *
bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
{
	size_t idx;
	struct bpf_map *s, *e;

	if (!obj || !obj->maps)
		return NULL;

	s = obj->maps;
	e = obj->maps + obj->nr_maps;

	if (prev == NULL)
		return s;

	if ((prev < s) || (prev >= e)) {
		pr_warning("error in %s: map handler doesn't belong to object\n",
			   __func__);
		return NULL;
	}

	idx = (prev - obj->maps) + 1;
	if (idx >= obj->nr_maps)
		return NULL;
	return &obj->maps[idx];
}
1945 1946

struct bpf_map *
1947
bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
1948 1949 1950 1951
{
	struct bpf_map *pos;

	bpf_map__for_each(pos, obj) {
1952
		if (pos->name && !strcmp(pos->name, name))
1953 1954 1955 1956
			return pos;
	}
	return NULL;
}
1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968

struct bpf_map *
bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset)
{
	int i;

	for (i = 0; i < obj->nr_maps; i++) {
		if (obj->maps[i].offset == offset)
			return &obj->maps[i];
	}
	return ERR_PTR(-ENOENT);
}
1969 1970 1971 1972 1973 1974 1975

long libbpf_get_error(const void *ptr)
{
	if (IS_ERR(ptr))
		return PTR_ERR(ptr);
	return 0;
}
1976 1977 1978 1979

int bpf_prog_load(const char *file, enum bpf_prog_type type,
		  struct bpf_object **pobj, int *prog_fd)
{
1980
	struct bpf_program *prog, *first_prog = NULL;
1981 1982 1983 1984 1985 1986 1987
	struct bpf_object *obj;
	int err;

	obj = bpf_object__open(file);
	if (IS_ERR(obj))
		return -ENOENT;

1988 1989 1990 1991 1992
	bpf_object__for_each_program(prog, obj) {
		/*
		 * If type is not specified, try to guess it based on
		 * section name.
		 */
1993
		if (type == BPF_PROG_TYPE_UNSPEC) {
1994 1995 1996 1997 1998
			type = bpf_program__guess_type(prog);
			if (type == BPF_PROG_TYPE_UNSPEC) {
				bpf_object__close(obj);
				return -EINVAL;
			}
1999
		}
2000 2001 2002 2003 2004 2005 2006 2007 2008 2009

		bpf_program__set_type(prog, type);
		if (prog->idx != obj->efile.text_shndx && !first_prog)
			first_prog = prog;
	}

	if (!first_prog) {
		pr_warning("object file doesn't contain bpf program\n");
		bpf_object__close(obj);
		return -ENOENT;
2010 2011
	}

2012 2013 2014 2015 2016 2017 2018
	err = bpf_object__load(obj);
	if (err) {
		bpf_object__close(obj);
		return -EINVAL;
	}

	*pobj = obj;
2019
	*prog_fd = bpf_program__fd(first_prog);
2020 2021
	return 0;
}