libbpf.c 62.5 KB
Newer Older
1
// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
2

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.
10 11
 */

12
#define _GNU_SOURCE
13
#include <stdlib.h>
14 15
#include <stdio.h>
#include <stdarg.h>
16
#include <libgen.h>
17
#include <inttypes.h>
18
#include <string.h>
19
#include <unistd.h>
20 21
#include <fcntl.h>
#include <errno.h>
22
#include <asm/unistd.h>
23
#include <linux/err.h>
24
#include <linux/kernel.h>
25
#include <linux/bpf.h>
26
#include <linux/btf.h>
27
#include <linux/list.h>
28
#include <linux/limits.h>
29
#include <linux/perf_event.h>
30
#include <linux/ring_buffer.h>
31 32 33
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/vfs.h>
34
#include <tools/libc_compat.h>
35 36
#include <libelf.h>
#include <gelf.h>
37 38

#include "libbpf.h"
39
#include "bpf.h"
40
#include "btf.h"
41
#include "str_error.h"
42

43 44 45 46
#ifndef EM_BPF
#define EM_BPF 247
#endif

47 48 49 50
#ifndef BPF_FS_MAGIC
#define BPF_FS_MAGIC		0xcafe4a11
#endif

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
#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;
}
87

88 89 90 91 92 93 94 95 96
#define STRERR_BUFSIZE  128

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


97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116
/* 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

117 118 119 120 121 122 123
/*
 * 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;
124
	char *name;
125
	int prog_ifindex;
126
	char *section_name;
S
Stanislav Fomichev 已提交
127 128 129 130
	/* section_name with / replaced by _; makes recursive pinning
	 * in bpf_object__pin_programs easier
	 */
	char *pin_name;
131
	struct bpf_insn *insns;
132
	size_t insns_cnt, main_prog_cnt;
133
	enum bpf_prog_type type;
134

135 136 137 138 139
	struct reloc_desc {
		enum {
			RELO_LD64,
			RELO_CALL,
		} type;
140
		int insn_idx;
141 142 143 144
		union {
			int map_idx;
			int text_off;
		};
145 146
	} *reloc_desc;
	int nr_reloc;
147

148 149 150 151 152
	struct {
		int nr;
		int *fds;
	} instances;
	bpf_program_prep_t preprocessor;
153 154 155 156

	struct bpf_object *obj;
	void *priv;
	bpf_program_clear_priv_t clear_priv;
157 158

	enum bpf_attach_type expected_attach_type;
159 160
};

161 162
struct bpf_map {
	int fd;
163
	char *name;
E
Eric Leblond 已提交
164
	size_t offset;
165
	int map_ifindex;
166
	struct bpf_map_def def;
167 168
	__u32 btf_key_type_id;
	__u32 btf_value_type_id;
169 170 171 172
	void *priv;
	bpf_map_clear_priv_t clear_priv;
};

173 174
static LIST_HEAD(bpf_objects_list);

175
struct bpf_object {
176
	char license[64];
177
	__u32 kern_version;
178

179 180
	struct bpf_program *programs;
	size_t nr_programs;
181 182 183
	struct bpf_map *maps;
	size_t nr_maps;

184
	bool loaded;
185
	bool has_pseudo_calls;
186

187 188 189 190 191 192
	/*
	 * Information when doing elf related work. Only valid if fd
	 * is valid.
	 */
	struct {
		int fd;
193 194
		void *obj_buf;
		size_t obj_buf_sz;
195 196
		Elf *elf;
		GElf_Ehdr ehdr;
197
		Elf_Data *symbols;
198
		size_t strtabidx;
199 200 201 202 203
		struct {
			GElf_Shdr shdr;
			Elf_Data *data;
		} *reloc;
		int nr_reloc;
204
		int maps_shndx;
205
		int text_shndx;
206
	} efile;
207 208 209 210 211 212
	/*
	 * 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;
213

214 215
	struct btf *btf;

216 217 218
	void *priv;
	bpf_object_clear_priv_t clear_priv;

219 220 221 222
	char path[];
};
#define obj_elf_valid(o)	((o)->efile.elf)

223
void bpf_program__unload(struct bpf_program *prog)
224
{
225 226
	int i;

227 228 229
	if (!prog)
		return;

230 231 232 233 234 235 236 237 238 239 240 241 242 243
	/*
	 * 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);
244 245
}

246 247 248 249 250
static void bpf_program__exit(struct bpf_program *prog)
{
	if (!prog)
		return;

251 252 253 254 255 256
	if (prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

257
	bpf_program__unload(prog);
258
	zfree(&prog->name);
259
	zfree(&prog->section_name);
S
Stanislav Fomichev 已提交
260
	zfree(&prog->pin_name);
261
	zfree(&prog->insns);
262 263 264
	zfree(&prog->reloc_desc);

	prog->nr_reloc = 0;
265 266 267 268
	prog->insns_cnt = 0;
	prog->idx = -1;
}

S
Stanislav Fomichev 已提交
269 270 271 272 273 274 275 276 277 278 279
static char *__bpf_program__pin_name(struct bpf_program *prog)
{
	char *name, *p;

	name = p = strdup(prog->section_name);
	while ((p = strchr(p, '/')))
		*p = '_';

	return name;
}

280
static int
281 282
bpf_program__init(void *data, size_t size, char *section_name, int idx,
		  struct bpf_program *prog)
283 284
{
	if (size < sizeof(struct bpf_insn)) {
285
		pr_warning("corrupted section '%s'\n", section_name);
286 287 288 289 290
		return -EINVAL;
	}

	bzero(prog, sizeof(*prog));

291
	prog->section_name = strdup(section_name);
292
	if (!prog->section_name) {
293 294
		pr_warning("failed to alloc name for prog under section(%d) %s\n",
			   idx, section_name);
295 296 297
		goto errout;
	}

S
Stanislav Fomichev 已提交
298 299 300 301 302 303 304
	prog->pin_name = __bpf_program__pin_name(prog);
	if (!prog->pin_name) {
		pr_warning("failed to alloc pin name for prog under section(%d) %s\n",
			   idx, section_name);
		goto errout;
	}

305 306
	prog->insns = malloc(size);
	if (!prog->insns) {
307 308
		pr_warning("failed to alloc insns for prog under section %s\n",
			   section_name);
309 310 311 312 313 314
		goto errout;
	}
	prog->insns_cnt = size / sizeof(struct bpf_insn);
	memcpy(prog->insns, data,
	       prog->insns_cnt * sizeof(struct bpf_insn));
	prog->idx = idx;
315 316
	prog->instances.fds = NULL;
	prog->instances.nr = -1;
317
	prog->type = BPF_PROG_TYPE_KPROBE;
318 319 320 321 322 323 324 325 326

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

static int
bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
327
			char *section_name, int idx)
328 329 330 331
{
	struct bpf_program prog, *progs;
	int nr_progs, err;

332
	err = bpf_program__init(data, size, section_name, idx, &prog);
333 334 335 336 337 338
	if (err)
		return err;

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

339
	progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
340 341 342 343 344 345
	if (!progs) {
		/*
		 * In this case the original obj->programs
		 * is still valid, so don't need special treat for
		 * bpf_close_object().
		 */
346 347
		pr_warning("failed to alloc a new program under section '%s'\n",
			   section_name);
348 349 350 351 352 353 354
		bpf_program__exit(&prog);
		return -ENOMEM;
	}

	pr_debug("found program %s\n", prog.section_name);
	obj->programs = progs;
	obj->nr_programs = nr_progs + 1;
355
	prog.obj = obj;
356 357 358 359
	progs[nr_progs] = prog;
	return 0;
}

360 361 362 363 364 365 366 367
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++) {
368
		const char *name = NULL;
369 370 371 372 373 374 375 376 377 378 379

		prog = &obj->programs[pi];

		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;
380 381
			if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL)
				continue;
382 383 384 385 386 387 388 389 390 391 392

			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;
			}
		}

393 394 395
		if (!name && prog->idx == obj->efile.text_shndx)
			name = ".text";

396 397 398 399 400
		if (!name) {
			pr_warning("failed to find sym for prog %s\n",
				   prog->section_name);
			return -EINVAL;
		}
401

402 403 404 405 406 407 408 409 410 411 412
		prog->name = strdup(name);
		if (!prog->name) {
			pr_warning("failed to allocate memory for prog sym %s\n",
				   name);
			return -ENOMEM;
		}
	}

	return 0;
}

413 414 415
static struct bpf_object *bpf_object__new(const char *path,
					  void *obj_buf,
					  size_t obj_buf_sz)
416 417 418 419 420 421
{
	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);
422
		return ERR_PTR(-ENOMEM);
423 424 425 426
	}

	strcpy(obj->path, path);
	obj->efile.fd = -1;
427 428 429 430 431 432 433 434 435

	/*
	 * 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;
436
	obj->efile.maps_shndx = -1;
437

438
	obj->loaded = false;
439 440 441

	INIT_LIST_HEAD(&obj->list);
	list_add(&obj->list, &bpf_objects_list);
442 443 444 445 446 447 448 449 450 451 452 453
	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;
	}
454
	obj->efile.symbols = NULL;
455 456 457

	zfree(&obj->efile.reloc);
	obj->efile.nr_reloc = 0;
458
	zclose(obj->efile.fd);
459 460
	obj->efile.obj_buf = NULL;
	obj->efile.obj_buf_sz = 0;
461 462 463 464 465 466 467 468 469
}

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");
470
		return -LIBBPF_ERRNO__LIBELF;
471 472
	}

473 474 475 476 477 478 479 480 481 482
	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) {
483
			char errmsg[STRERR_BUFSIZE];
484 485
			char *cp = libbpf_strerror_r(errno, errmsg,
						     sizeof(errmsg));
486 487

			pr_warning("failed to open %s: %s\n", obj->path, cp);
488 489 490 491 492 493
			return -errno;
		}

		obj->efile.elf = elf_begin(obj->efile.fd,
				LIBBPF_ELF_C_READ_MMAP,
				NULL);
494 495 496 497 498
	}

	if (!obj->efile.elf) {
		pr_warning("failed to open %s as ELF file\n",
				obj->path);
499
		err = -LIBBPF_ERRNO__LIBELF;
500 501 502 503 504 505
		goto errout;
	}

	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
		pr_warning("failed to get EHDR from %s\n",
				obj->path);
506
		err = -LIBBPF_ERRNO__FORMAT;
507 508 509 510
		goto errout;
	}
	ep = &obj->efile.ehdr;

511 512
	/* Old LLVM set e_machine to EM_NONE */
	if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) {
513 514
		pr_warning("%s is not an eBPF object file\n",
			obj->path);
515
		err = -LIBBPF_ERRNO__FORMAT;
516 517 518 519 520 521 522 523 524
		goto errout;
	}

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

525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542
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:
543
		return -LIBBPF_ERRNO__ENDIAN;
544 545 546 547 548 549
	}

	return 0;

mismatch:
	pr_warning("Error: endianness mismatch.\n");
550
	return -LIBBPF_ERRNO__ENDIAN;
551 552
}

553 554 555 556 557 558 559 560 561 562 563 564 565 566
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)
{
567
	__u32 kver;
568 569 570

	if (size != sizeof(kver)) {
		pr_warning("invalid kver section in %s\n", obj->path);
571
		return -LIBBPF_ERRNO__FORMAT;
572 573 574 575 576 577 578 579
	}
	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
580 581 582 583
static int compare_bpf_map(const void *_a, const void *_b)
{
	const struct bpf_map *a = _a;
	const struct bpf_map *b = _b;
584

E
Eric Leblond 已提交
585
	return a->offset - b->offset;
586 587
}

588
static int
589
bpf_object__init_maps(struct bpf_object *obj, int flags)
590
{
591
	bool strict = !(flags & MAPS_RELAX_COMPAT);
592
	int i, map_idx, map_def_sz, nr_maps = 0;
E
Eric Leblond 已提交
593 594
	Elf_Scn *scn;
	Elf_Data *data;
595 596
	Elf_Data *symbols = obj->efile.symbols;

E
Eric Leblond 已提交
597 598 599 600 601 602 603 604 605 606 607
	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);
608
		return -EINVAL;
E
Eric Leblond 已提交
609
	}
610

E
Eric Leblond 已提交
611 612 613 614 615 616 617
	/*
	 * 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.
	 */
618 619
	for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
		GElf_Sym sym;
E
Eric Leblond 已提交
620 621 622 623 624 625 626 627 628 629 630 631 632 633 634

		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;

635 636 637 638 639 640 641 642 643
	/* 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
644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663
	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;
664
		const char *map_name;
E
Eric Leblond 已提交
665
		struct bpf_map_def *def;
666 667 668

		if (!gelf_getsym(symbols, i, &sym))
			continue;
669
		if (sym.st_shndx != obj->efile.maps_shndx)
670 671 672
			continue;

		map_name = elf_strptr(obj->efile.elf,
673
				      obj->efile.strtabidx,
674
				      sym.st_name);
E
Eric Leblond 已提交
675
		obj->maps[map_idx].offset = sym.st_value;
676
		if (sym.st_value + map_def_sz > data->d_size) {
E
Eric Leblond 已提交
677 678 679
			pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
				   obj->path, map_name);
			return -EINVAL;
680
		}
E
Eric Leblond 已提交
681

682
		obj->maps[map_idx].name = strdup(map_name);
683 684 685 686
		if (!obj->maps[map_idx].name) {
			pr_warning("failed to alloc map name\n");
			return -ENOMEM;
		}
E
Eric Leblond 已提交
687
		pr_debug("map %d is \"%s\"\n", map_idx,
688
			 obj->maps[map_idx].name);
E
Eric Leblond 已提交
689
		def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712
		/*
		 * 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);
713 714
					if (strict)
						return -EINVAL;
715 716 717 718 719
				}
			}
			memcpy(&obj->maps[map_idx].def, def,
			       sizeof(struct bpf_map_def));
		}
E
Eric Leblond 已提交
720
		map_idx++;
721
	}
E
Eric Leblond 已提交
722 723

	qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map);
724
	return 0;
725 726
}

727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744
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;
}

745
static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
746 747 748 749
{
	Elf *elf = obj->efile.elf;
	GElf_Ehdr *ep = &obj->efile.ehdr;
	Elf_Scn *scn = NULL;
750
	int idx = 0, err = 0;
751 752 753 754 755

	/* 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);
756
		return -LIBBPF_ERRNO__FORMAT;
757 758 759 760 761 762 763 764 765
	}

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

		idx++;
		if (gelf_getshdr(scn, &sh) != &sh) {
766 767
			pr_warning("failed to get section(%d) header from %s\n",
				   idx, obj->path);
768
			err = -LIBBPF_ERRNO__FORMAT;
769 770 771 772 773
			goto out;
		}

		name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
		if (!name) {
774 775
			pr_warning("failed to get section(%d) name from %s\n",
				   idx, obj->path);
776
			err = -LIBBPF_ERRNO__FORMAT;
777 778 779 780 781
			goto out;
		}

		data = elf_getdata(scn, 0);
		if (!data) {
782 783
			pr_warning("failed to get section(%d) data from %s(%s)\n",
				   idx, name, obj->path);
784
			err = -LIBBPF_ERRNO__FORMAT;
785 786
			goto out;
		}
787 788
		pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n",
			 idx, name, (unsigned long)data->d_size,
789 790
			 (int)sh.sh_link, (unsigned long)sh.sh_flags,
			 (int)sh.sh_type);
791 792 793 794 795 796 797 798 799

		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
800
		else if (strcmp(name, "maps") == 0)
801
			obj->efile.maps_shndx = idx;
802 803 804 805 806 807 808 809 810
		else if (strcmp(name, BTF_ELF_SEC) == 0) {
			obj->btf = btf__new(data->d_buf, data->d_size,
					    __pr_debug);
			if (IS_ERR(obj->btf)) {
				pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
					   BTF_ELF_SEC, PTR_ERR(obj->btf));
				obj->btf = NULL;
			}
		} else if (sh.sh_type == SHT_SYMTAB) {
811 812 813
			if (obj->efile.symbols) {
				pr_warning("bpf: multiple SYMTAB in %s\n",
					   obj->path);
814
				err = -LIBBPF_ERRNO__FORMAT;
815
			} else {
816
				obj->efile.symbols = data;
817 818
				obj->efile.strtabidx = sh.sh_link;
			}
819 820 821
		} else if ((sh.sh_type == SHT_PROGBITS) &&
			   (sh.sh_flags & SHF_EXECINSTR) &&
			   (data->d_size > 0)) {
822 823
			if (strcmp(name, ".text") == 0)
				obj->efile.text_shndx = idx;
824 825 826
			err = bpf_object__add_program(obj, data->d_buf,
						      data->d_size, name, idx);
			if (err) {
827
				char errmsg[STRERR_BUFSIZE];
828 829
				char *cp = libbpf_strerror_r(-err, errmsg,
							     sizeof(errmsg));
830

831
				pr_warning("failed to alloc program %s (%s): %s",
832
					   name, obj->path, cp);
833
			}
834 835 836
		} else if (sh.sh_type == SHT_REL) {
			void *reloc = obj->efile.reloc;
			int nr_reloc = obj->efile.nr_reloc + 1;
837 838 839 840 841 842 843 844
			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;
			}
845

846 847
			reloc = reallocarray(reloc, nr_reloc,
					     sizeof(*obj->efile.reloc));
848 849 850 851 852 853 854 855 856 857 858 859
			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;
			}
860 861
		} else {
			pr_debug("skip section(%d) %s\n", idx, name);
862
		}
863 864
		if (err)
			goto out;
865
	}
866

867 868 869 870
	if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
		pr_warning("Corrupted ELF file: index of strtab invalid\n");
		return LIBBPF_ERRNO__FORMAT;
	}
871
	if (obj->efile.maps_shndx >= 0) {
872
		err = bpf_object__init_maps(obj, flags);
873 874 875 876
		if (err)
			goto out;
	}
	err = bpf_object__init_prog_names(obj);
877 878 879 880
out:
	return err;
}

881 882 883 884 885 886 887 888 889 890 891 892 893 894
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;
}

895 896 897 898 899 900 901 902 903 904 905 906
struct bpf_program *
bpf_object__find_program_by_title(struct bpf_object *obj, const char *title)
{
	struct bpf_program *pos;

	bpf_object__for_each_program(pos, obj) {
		if (pos->section_name && !strcmp(pos->section_name, title))
			return pos;
	}
	return NULL;
}

907
static int
908 909
bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
			   Elf_Data *data, struct bpf_object *obj)
910
{
911 912 913 914 915
	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;
916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937
	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);
938
			return -LIBBPF_ERRNO__FORMAT;
939 940 941 942 943 944 945
		}

		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));
946
			return -LIBBPF_ERRNO__FORMAT;
947
		}
D
David Miller 已提交
948 949 950
		pr_debug("relo for %lld value %lld name %d\n",
			 (long long) (rel.r_info >> 32),
			 (long long) sym.st_value, sym.st_name);
951

952
		if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) {
953 954 955 956 957 958 959 960
			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);

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;
969
			obj->has_pseudo_calls = true;
970 971 972
			continue;
		}

973 974 975
		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);
976
			return -LIBBPF_ERRNO__RELOC;
977 978
		}

979 980 981 982 983 984 985 986 987
		/* 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;
			}
		}

988 989 990
		if (map_idx >= nr_maps) {
			pr_warning("bpf relocation: map_idx %d large than %d\n",
				   (int)map_idx, (int)nr_maps - 1);
991
			return -LIBBPF_ERRNO__RELOC;
992 993
		}

994
		prog->reloc_desc[i].type = RELO_LD64;
995 996 997 998 999 1000
		prog->reloc_desc[i].insn_idx = insn_idx;
		prog->reloc_desc[i].map_idx = map_idx;
	}
	return 0;
}

1001 1002
static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
{
1003 1004
	const struct btf_type *container_type;
	const struct btf_member *key, *value;
1005 1006
	struct bpf_map_def *def = &map->def;
	const size_t max_name = 256;
1007
	char container_name[max_name];
1008
	__s64 key_size, value_size;
1009
	__s32 container_id;
1010

1011 1012 1013
	if (snprintf(container_name, max_name, "____btf_map_%s", map->name) ==
	    max_name) {
		pr_warning("map:%s length of '____btf_map_%s' is too long\n",
1014 1015 1016 1017
			   map->name, map->name);
		return -EINVAL;
	}

1018 1019 1020 1021 1022
	container_id = btf__find_by_name(btf, container_name);
	if (container_id < 0) {
		pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n",
			 map->name, container_name);
		return container_id;
1023 1024
	}

1025 1026 1027 1028 1029
	container_type = btf__type_by_id(btf, container_id);
	if (!container_type) {
		pr_warning("map:%s cannot find BTF type for container_id:%u\n",
			   map->name, container_id);
		return -EINVAL;
1030 1031
	}

1032 1033 1034 1035
	if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT ||
	    BTF_INFO_VLEN(container_type->info) < 2) {
		pr_warning("map:%s container_name:%s is an invalid container struct\n",
			   map->name, container_name);
1036 1037 1038
		return -EINVAL;
	}

1039 1040 1041 1042 1043 1044 1045 1046
	key = (struct btf_member *)(container_type + 1);
	value = key + 1;

	key_size = btf__resolve_size(btf, key->type);
	if (key_size < 0) {
		pr_warning("map:%s invalid BTF key_type_size\n",
			   map->name);
		return key_size;
1047 1048
	}

1049 1050 1051 1052
	if (def->key_size != key_size) {
		pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n",
			   map->name, (__u32)key_size, def->key_size);
		return -EINVAL;
1053 1054
	}

1055
	value_size = btf__resolve_size(btf, value->type);
1056
	if (value_size < 0) {
1057
		pr_warning("map:%s invalid BTF value_type_size\n", map->name);
1058 1059 1060 1061
		return value_size;
	}

	if (def->value_size != value_size) {
1062 1063
		pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n",
			   map->name, (__u32)value_size, def->value_size);
1064 1065 1066
		return -EINVAL;
	}

1067 1068
	map->btf_key_type_id = key->type;
	map->btf_value_type_id = value->type;
1069 1070 1071 1072

	return 0;
}

J
Jakub Kicinski 已提交
1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119
int bpf_map__reuse_fd(struct bpf_map *map, int fd)
{
	struct bpf_map_info info = {};
	__u32 len = sizeof(info);
	int new_fd, err;
	char *new_name;

	err = bpf_obj_get_info_by_fd(fd, &info, &len);
	if (err)
		return err;

	new_name = strdup(info.name);
	if (!new_name)
		return -errno;

	new_fd = open("/", O_RDONLY | O_CLOEXEC);
	if (new_fd < 0)
		goto err_free_new_name;

	new_fd = dup3(fd, new_fd, O_CLOEXEC);
	if (new_fd < 0)
		goto err_close_new_fd;

	err = zclose(map->fd);
	if (err)
		goto err_close_new_fd;
	free(map->name);

	map->fd = new_fd;
	map->name = new_name;
	map->def.type = info.type;
	map->def.key_size = info.key_size;
	map->def.value_size = info.value_size;
	map->def.max_entries = info.max_entries;
	map->def.map_flags = info.map_flags;
	map->btf_key_type_id = info.btf_key_type_id;
	map->btf_value_type_id = info.btf_value_type_id;

	return 0;

err_close_new_fd:
	close(new_fd);
err_free_new_name:
	free(new_name);
	return -errno;
}

1120 1121 1122
static int
bpf_object__create_maps(struct bpf_object *obj)
{
1123
	struct bpf_create_map_attr create_attr = {};
1124
	unsigned int i;
1125
	int err;
1126

1127
	for (i = 0; i < obj->nr_maps; i++) {
1128 1129
		struct bpf_map *map = &obj->maps[i];
		struct bpf_map_def *def = &map->def;
1130
		char *cp, errmsg[STRERR_BUFSIZE];
1131 1132
		int *pfd = &map->fd;

J
Jakub Kicinski 已提交
1133 1134 1135 1136 1137 1138
		if (map->fd >= 0) {
			pr_debug("skip map create (preset) %s: fd=%d\n",
				 map->name, map->fd);
			continue;
		}

1139
		create_attr.name = map->name;
1140
		create_attr.map_ifindex = map->map_ifindex;
1141 1142 1143 1144 1145 1146
		create_attr.map_type = def->type;
		create_attr.map_flags = def->map_flags;
		create_attr.key_size = def->key_size;
		create_attr.value_size = def->value_size;
		create_attr.max_entries = def->max_entries;
		create_attr.btf_fd = 0;
1147 1148
		create_attr.btf_key_type_id = 0;
		create_attr.btf_value_type_id = 0;
1149 1150 1151

		if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) {
			create_attr.btf_fd = btf__fd(obj->btf);
1152 1153
			create_attr.btf_key_type_id = map->btf_key_type_id;
			create_attr.btf_value_type_id = map->btf_value_type_id;
1154 1155 1156
		}

		*pfd = bpf_create_map_xattr(&create_attr);
1157
		if (*pfd < 0 && create_attr.btf_key_type_id) {
1158
			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1159
			pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
1160
				   map->name, cp, errno);
1161
			create_attr.btf_fd = 0;
1162 1163 1164 1165
			create_attr.btf_key_type_id = 0;
			create_attr.btf_value_type_id = 0;
			map->btf_key_type_id = 0;
			map->btf_value_type_id = 0;
1166 1167 1168
			*pfd = bpf_create_map_xattr(&create_attr);
		}

1169 1170 1171
		if (*pfd < 0) {
			size_t j;

1172
			err = *pfd;
1173
			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
E
Eric Leblond 已提交
1174
			pr_warning("failed to create map (name: '%s'): %s\n",
1175
				   map->name, cp);
1176
			for (j = 0; j < i; j++)
1177
				zclose(obj->maps[j].fd);
1178 1179
			return err;
		}
1180
		pr_debug("create map %s: fd=%d\n", map->name, *pfd);
1181 1182 1183 1184 1185
	}

	return 0;
}

1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209
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;
1210
		new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn));
1211 1212 1213 1214 1215 1216 1217 1218 1219
		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;
1220 1221 1222
		pr_debug("added %zd insn from %s to prog %s\n",
			 text->insns_cnt, text->section_name,
			 prog->section_name);
1223 1224 1225 1226 1227 1228
	}
	insn = &prog->insns[relo->insn_idx];
	insn->imm += prog->main_prog_cnt - relo->insn_idx;
	return 0;
}

W
Wang Nan 已提交
1229
static int
1230
bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
W
Wang Nan 已提交
1231
{
1232
	int i, err;
W
Wang Nan 已提交
1233 1234 1235 1236 1237

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

	for (i = 0; i < prog->nr_reloc; i++) {
1238 1239 1240
		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
1241

1242 1243
			insn_idx = prog->reloc_desc[i].insn_idx;
			map_idx = prog->reloc_desc[i].map_idx;
W
Wang Nan 已提交
1244

1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256
			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
1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275
		}
	}

	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];

1276
		err = bpf_program__relocate(prog, obj);
W
Wang Nan 已提交
1277 1278 1279 1280 1281 1282 1283 1284 1285
		if (err) {
			pr_warning("failed to relocate '%s'\n",
				   prog->section_name);
			return err;
		}
	}
	return 0;
}

1286 1287 1288 1289 1290 1291
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");
1292
		return -LIBBPF_ERRNO__INTERNAL;
1293 1294 1295 1296 1297 1298 1299 1300 1301 1302
	}

	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__);
1303
			return -LIBBPF_ERRNO__INTERNAL;
1304 1305 1306 1307
		}

		prog = bpf_object__find_prog_by_idx(obj, idx);
		if (!prog) {
1308
			pr_warning("relocation failed: no section(%d)\n", idx);
1309
			return -LIBBPF_ERRNO__RELOC;
1310 1311
		}

1312
		err = bpf_program__collect_reloc(prog,
1313
						 shdr, data,
1314
						 obj);
1315
		if (err)
1316
			return err;
1317 1318 1319 1320
	}
	return 0;
}

1321
static int
1322 1323
load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
	     const char *name, struct bpf_insn *insns, int insns_cnt,
1324
	     char *license, __u32 kern_version, int *pfd, int prog_ifindex)
1325
{
1326
	struct bpf_load_program_attr load_attr;
1327
	char *cp, errmsg[STRERR_BUFSIZE];
1328
	char *log_buf;
1329
	int ret;
1330

1331 1332 1333 1334 1335 1336 1337 1338
	memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
	load_attr.prog_type = type;
	load_attr.expected_attach_type = expected_attach_type;
	load_attr.name = name;
	load_attr.insns = insns;
	load_attr.insns_cnt = insns_cnt;
	load_attr.license = license;
	load_attr.kern_version = kern_version;
1339
	load_attr.prog_ifindex = prog_ifindex;
1340 1341

	if (!load_attr.insns || !load_attr.insns_cnt)
1342 1343 1344 1345 1346 1347
		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");

1348
	ret = bpf_load_program_xattr(&load_attr, log_buf, BPF_LOG_BUF_SIZE);
1349 1350 1351 1352 1353 1354 1355

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

1356
	ret = -LIBBPF_ERRNO__LOAD;
1357
	cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1358
	pr_warning("load bpf program failed: %s\n", cp);
1359

1360 1361
	if (log_buf && log_buf[0] != '\0') {
		ret = -LIBBPF_ERRNO__VERIFY;
1362 1363 1364
		pr_warning("-- BEGIN DUMP LOG ---\n");
		pr_warning("\n%s\n", log_buf);
		pr_warning("-- END LOG --\n");
1365 1366 1367
	} else if (load_attr.insns_cnt >= BPF_MAXINSNS) {
		pr_warning("Program too large (%zu insns), at most %d insns\n",
			   load_attr.insns_cnt, BPF_MAXINSNS);
1368
		ret = -LIBBPF_ERRNO__PROG2BIG;
1369
	} else {
1370
		/* Wrong program type? */
1371
		if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) {
1372 1373
			int fd;

1374 1375 1376
			load_attr.prog_type = BPF_PROG_TYPE_KPROBE;
			load_attr.expected_attach_type = 0;
			fd = bpf_load_program_xattr(&load_attr, NULL, 0);
1377 1378 1379 1380 1381
			if (fd >= 0) {
				close(fd);
				ret = -LIBBPF_ERRNO__PROGTYPE;
				goto out;
			}
1382
		}
1383 1384 1385

		if (log_buf)
			ret = -LIBBPF_ERRNO__KVER;
1386 1387 1388 1389 1390 1391 1392
	}

out:
	free(log_buf);
	return ret;
}

1393
int
1394
bpf_program__load(struct bpf_program *prog,
1395
		  char *license, __u32 kern_version)
1396
{
1397
	int err = 0, fd, i;
1398

1399 1400 1401 1402 1403 1404
	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;
		}
1405

1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419
		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);
		}
1420 1421
		err = load_program(prog->type, prog->expected_attach_type,
				   prog->name, prog->insns, prog->insns_cnt,
1422 1423
				   license, kern_version, &fd,
				   prog->prog_ifindex);
1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450
		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;
		}

1451 1452
		err = load_program(prog->type, prog->expected_attach_type,
				   prog->name, result.new_insn_ptr,
1453
				   result.new_insn_cnt,
1454 1455
				   license, kern_version, &fd,
				   prog->prog_ifindex);
1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467

		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:
1468 1469 1470 1471 1472 1473 1474 1475
	if (err)
		pr_warning("failed to load program '%s'\n",
			   prog->section_name);
	zfree(&prog->insns);
	prog->insns_cnt = 0;
	return err;
}

1476 1477 1478 1479 1480 1481
static bool bpf_program__is_function_storage(struct bpf_program *prog,
					     struct bpf_object *obj)
{
	return prog->idx == obj->efile.text_shndx && obj->has_pseudo_calls;
}

1482 1483 1484 1485 1486 1487 1488
static int
bpf_object__load_progs(struct bpf_object *obj)
{
	size_t i;
	int err;

	for (i = 0; i < obj->nr_programs; i++) {
1489
		if (bpf_program__is_function_storage(&obj->programs[i], obj))
1490
			continue;
1491 1492 1493 1494 1495 1496 1497 1498 1499
		err = bpf_program__load(&obj->programs[i],
					obj->license,
					obj->kern_version);
		if (err)
			return err;
	}
	return 0;
}

1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511
static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
{
	switch (type) {
	case BPF_PROG_TYPE_SOCKET_FILTER:
	case BPF_PROG_TYPE_SCHED_CLS:
	case BPF_PROG_TYPE_SCHED_ACT:
	case BPF_PROG_TYPE_XDP:
	case BPF_PROG_TYPE_CGROUP_SKB:
	case BPF_PROG_TYPE_CGROUP_SOCK:
	case BPF_PROG_TYPE_LWT_IN:
	case BPF_PROG_TYPE_LWT_OUT:
	case BPF_PROG_TYPE_LWT_XMIT:
1512
	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
1513 1514 1515 1516 1517
	case BPF_PROG_TYPE_SOCK_OPS:
	case BPF_PROG_TYPE_SK_SKB:
	case BPF_PROG_TYPE_CGROUP_DEVICE:
	case BPF_PROG_TYPE_SK_MSG:
	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
1518
	case BPF_PROG_TYPE_LIRC_MODE2:
1519
	case BPF_PROG_TYPE_SK_REUSEPORT:
1520
	case BPF_PROG_TYPE_FLOW_DISSECTOR:
1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532
		return false;
	case BPF_PROG_TYPE_UNSPEC:
	case BPF_PROG_TYPE_KPROBE:
	case BPF_PROG_TYPE_TRACEPOINT:
	case BPF_PROG_TYPE_PERF_EVENT:
	case BPF_PROG_TYPE_RAW_TRACEPOINT:
	default:
		return true;
	}
}

static int bpf_object__validate(struct bpf_object *obj, bool needs_kver)
1533
{
1534
	if (needs_kver && obj->kern_version == 0) {
1535 1536
		pr_warning("%s doesn't provide kernel version\n",
			   obj->path);
1537
		return -LIBBPF_ERRNO__KVERSION;
1538 1539 1540 1541
	}
	return 0;
}

1542
static struct bpf_object *
1543
__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
1544
		   bool needs_kver, int flags)
1545 1546
{
	struct bpf_object *obj;
1547
	int err;
1548 1549 1550

	if (elf_version(EV_CURRENT) == EV_NONE) {
		pr_warning("failed to init libelf for %s\n", path);
1551
		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
1552 1553
	}

1554
	obj = bpf_object__new(path, obj_buf, obj_buf_sz);
1555 1556
	if (IS_ERR(obj))
		return obj;
1557

1558 1559
	CHECK_ERR(bpf_object__elf_init(obj), err, out);
	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
1560
	CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out);
1561
	CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
1562
	CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out);
1563 1564 1565 1566 1567

	bpf_object__elf_finish(obj);
	return obj;
out:
	bpf_object__close(obj);
1568
	return ERR_PTR(err);
1569 1570
}

1571 1572
struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
					    int flags)
1573 1574
{
	/* param validation */
1575
	if (!attr->file)
1576 1577
		return NULL;

1578 1579 1580
	pr_debug("loading %s\n", attr->file);

	return __bpf_object__open(attr->file, NULL, 0,
1581 1582 1583 1584 1585 1586 1587
				  bpf_prog_type__needs_kver(attr->prog_type),
				  flags);
}

struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr)
{
	return __bpf_object__open_xattr(attr, 0);
1588 1589 1590 1591 1592 1593 1594 1595
}

struct bpf_object *bpf_object__open(const char *path)
{
	struct bpf_object_open_attr attr = {
		.file		= path,
		.prog_type	= BPF_PROG_TYPE_UNSPEC,
	};
1596

1597
	return bpf_object__open_xattr(&attr);
1598 1599 1600
}

struct bpf_object *bpf_object__open_buffer(void *obj_buf,
1601 1602
					   size_t obj_buf_sz,
					   const char *name)
1603
{
1604 1605
	char tmp_name[64];

1606 1607 1608 1609
	/* param validation */
	if (!obj_buf || obj_buf_sz <= 0)
		return NULL;

1610 1611 1612 1613 1614 1615 1616 1617 1618
	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);
1619

1620
	return __bpf_object__open(name, obj_buf, obj_buf_sz, true, true);
1621 1622
}

1623 1624 1625 1626 1627 1628 1629
int bpf_object__unload(struct bpf_object *obj)
{
	size_t i;

	if (!obj)
		return -EINVAL;

1630 1631
	for (i = 0; i < obj->nr_maps; i++)
		zclose(obj->maps[i].fd);
1632

1633 1634 1635
	for (i = 0; i < obj->nr_programs; i++)
		bpf_program__unload(&obj->programs[i]);

1636 1637 1638 1639 1640
	return 0;
}

int bpf_object__load(struct bpf_object *obj)
{
1641 1642
	int err;

1643 1644 1645 1646 1647 1648 1649 1650 1651
	if (!obj)
		return -EINVAL;

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

	obj->loaded = true;
1652 1653 1654 1655

	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);
1656 1657 1658 1659 1660

	return 0;
out:
	bpf_object__unload(obj);
	pr_warning("failed to load object '%s'\n", obj->path);
1661
	return err;
1662 1663
}

1664 1665
static int check_path(const char *path)
{
1666
	char *cp, errmsg[STRERR_BUFSIZE];
1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679
	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)) {
1680
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1681
		pr_warning("failed to statfs %s: %s\n", dir, cp);
1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696
		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)
{
1697
	char *cp, errmsg[STRERR_BUFSIZE];
1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715
	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)) {
1716
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1717
		pr_warning("failed to pin program: %s\n", cp);
1718 1719 1720 1721 1722 1723 1724
		return -errno;
	}
	pr_debug("pinned program '%s'\n", path);

	return 0;
}

1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752
int bpf_program__unpin_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;
	}

	err = unlink(path);
	if (err != 0)
		return -errno;
	pr_debug("unpinned program '%s'\n", path);

	return 0;
}

1753 1754
static int make_dir(const char *path)
{
1755
	char *cp, errmsg[STRERR_BUFSIZE];
1756 1757 1758 1759 1760
	int err = 0;

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

1761
	if (err) {
1762
		cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
1763 1764
		pr_warning("failed to mkdir %s: %s\n", path, cp);
	}
1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786
	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;
	}

1787 1788 1789 1790 1791
	if (prog->instances.nr == 1) {
		/* don't create subdirs when pinning single instance */
		return bpf_program__pin_instance(prog, path, 0);
	}

1792 1793 1794 1795
	err = make_dir(path);
	if (err)
		return err;

1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851
	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) {
			err = -EINVAL;
			goto err_unpin;
		} else if (len >= PATH_MAX) {
			err = -ENAMETOOLONG;
			goto err_unpin;
		}

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

	return 0;

err_unpin:
	for (i = i - 1; i >= 0; i--) {
		char buf[PATH_MAX];
		int len;

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

		bpf_program__unpin_instance(prog, buf, i);
	}

	rmdir(path);

	return err;
}

int bpf_program__unpin(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;
1852 1853 1854 1855 1856
	}

	if (prog->instances.nr == 1) {
		/* don't create subdirs when pinning single instance */
		return bpf_program__unpin_instance(prog, path, 0);
1857 1858
	}

1859 1860 1861 1862 1863 1864 1865 1866 1867 1868
	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;

1869
		err = bpf_program__unpin_instance(prog, buf, i);
1870 1871 1872 1873
		if (err)
			return err;
	}

1874 1875 1876 1877
	err = rmdir(path);
	if (err)
		return -errno;

1878 1879 1880
	return 0;
}

J
Joe Stringer 已提交
1881 1882
int bpf_map__pin(struct bpf_map *map, const char *path)
{
1883
	char *cp, errmsg[STRERR_BUFSIZE];
J
Joe Stringer 已提交
1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895
	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)) {
1896
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1897
		pr_warning("failed to pin map: %s\n", cp);
J
Joe Stringer 已提交
1898 1899 1900 1901
		return -errno;
	}

	pr_debug("pinned map '%s'\n", path);
1902

J
Joe Stringer 已提交
1903 1904 1905
	return 0;
}

1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927
int bpf_map__unpin(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;
	}

	err = unlink(path);
	if (err != 0)
		return -errno;
	pr_debug("unpinned map '%s'\n", path);

	return 0;
}

int bpf_object__pin_maps(struct bpf_object *obj, const char *path)
1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943
{
	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;

1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990
	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) {
			err = -EINVAL;
			goto err_unpin_maps;
		} else if (len >= PATH_MAX) {
			err = -ENAMETOOLONG;
			goto err_unpin_maps;
		}

		err = bpf_map__pin(map, buf);
		if (err)
			goto err_unpin_maps;
	}

	return 0;

err_unpin_maps:
	while ((map = bpf_map__prev(map, obj))) {
		char buf[PATH_MAX];
		int len;

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

		bpf_map__unpin(map, buf);
	}

	return err;
}

int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
{
	struct bpf_map *map;
	int err;

	if (!obj)
		return -ENOENT;

1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001
	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;

2002
		err = bpf_map__unpin(map, buf);
2003 2004 2005 2006
		if (err)
			return err;
	}

2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031
	return 0;
}

int bpf_object__pin_programs(struct bpf_object *obj, const char *path)
{
	struct bpf_program *prog;
	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_object__for_each_program(prog, obj) {
		char buf[PATH_MAX];
		int len;

		len = snprintf(buf, PATH_MAX, "%s/%s", path,
S
Stanislav Fomichev 已提交
2032
			       prog->pin_name);
2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053
		if (len < 0) {
			err = -EINVAL;
			goto err_unpin_programs;
		} else if (len >= PATH_MAX) {
			err = -ENAMETOOLONG;
			goto err_unpin_programs;
		}

		err = bpf_program__pin(prog, buf);
		if (err)
			goto err_unpin_programs;
	}

	return 0;

err_unpin_programs:
	while ((prog = bpf_program__prev(prog, obj))) {
		char buf[PATH_MAX];
		int len;

		len = snprintf(buf, PATH_MAX, "%s/%s", path,
S
Stanislav Fomichev 已提交
2054
			       prog->pin_name);
2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073
		if (len < 0)
			continue;
		else if (len >= PATH_MAX)
			continue;

		bpf_program__unpin(prog, buf);
	}

	return err;
}

int bpf_object__unpin_programs(struct bpf_object *obj, const char *path)
{
	struct bpf_program *prog;
	int err;

	if (!obj)
		return -ENOENT;

2074 2075 2076 2077 2078
	bpf_object__for_each_program(prog, obj) {
		char buf[PATH_MAX];
		int len;

		len = snprintf(buf, PATH_MAX, "%s/%s", path,
S
Stanislav Fomichev 已提交
2079
			       prog->pin_name);
2080 2081 2082 2083 2084
		if (len < 0)
			return -EINVAL;
		else if (len >= PATH_MAX)
			return -ENAMETOOLONG;

2085
		err = bpf_program__unpin(prog, buf);
2086 2087 2088 2089 2090 2091 2092
		if (err)
			return err;
	}

	return 0;
}

2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109
int bpf_object__pin(struct bpf_object *obj, const char *path)
{
	int err;

	err = bpf_object__pin_maps(obj, path);
	if (err)
		return err;

	err = bpf_object__pin_programs(obj, path);
	if (err) {
		bpf_object__unpin_maps(obj, path);
		return err;
	}

	return 0;
}

2110 2111
void bpf_object__close(struct bpf_object *obj)
{
2112 2113
	size_t i;

2114 2115 2116
	if (!obj)
		return;

2117 2118 2119
	if (obj->clear_priv)
		obj->clear_priv(obj, obj->priv);

2120
	bpf_object__elf_finish(obj);
2121
	bpf_object__unload(obj);
2122
	btf__free(obj->btf);
2123

2124
	for (i = 0; i < obj->nr_maps; i++) {
2125
		zfree(&obj->maps[i].name);
2126 2127 2128 2129 2130 2131 2132 2133
		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;
2134 2135 2136 2137 2138 2139 2140

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

2141
	list_del(&obj->list);
2142 2143
	free(obj);
}
2144

2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163
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;
}

2164
const char *bpf_object__name(struct bpf_object *obj)
2165
{
2166
	return obj ? obj->path : ERR_PTR(-EINVAL);
2167 2168
}

2169
unsigned int bpf_object__kversion(struct bpf_object *obj)
2170
{
2171
	return obj ? obj->kern_version : 0;
2172 2173
}

2174 2175 2176 2177 2178
int bpf_object__btf_fd(const struct bpf_object *obj)
{
	return obj->btf ? btf__fd(obj->btf) : -1;
}

2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194
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);
}

2195
static struct bpf_program *
2196
__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, int i)
2197
{
2198
	ssize_t idx;
2199 2200 2201 2202

	if (!obj->programs)
		return NULL;

2203
	if (p->obj != obj) {
2204 2205 2206 2207
		pr_warning("error: program handler doesn't match object\n");
		return NULL;
	}

2208 2209
	idx = (p - obj->programs) + i;
	if (idx >= obj->nr_programs || idx < 0)
2210 2211 2212 2213
		return NULL;
	return &obj->programs[idx];
}

2214 2215 2216 2217 2218
struct bpf_program *
bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
{
	struct bpf_program *prog = prev;

2219 2220 2221
	if (prev == NULL)
		return obj->programs;

2222
	do {
2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241
		prog = __bpf_program__iter(prog, obj, 1);
	} while (prog && bpf_program__is_function_storage(prog, obj));

	return prog;
}

struct bpf_program *
bpf_program__prev(struct bpf_program *next, struct bpf_object *obj)
{
	struct bpf_program *prog = next;

	if (next == NULL) {
		if (!obj->nr_programs)
			return NULL;
		return obj->programs + obj->nr_programs - 1;
	}

	do {
		prog = __bpf_program__iter(prog, obj, -1);
2242 2243 2244 2245 2246
	} while (prog && bpf_program__is_function_storage(prog, obj));

	return prog;
}

2247 2248
int bpf_program__set_priv(struct bpf_program *prog, void *priv,
			  bpf_program_clear_priv_t clear_priv)
2249 2250 2251 2252 2253 2254 2255 2256 2257
{
	if (prog->priv && prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

2258
void *bpf_program__priv(struct bpf_program *prog)
2259
{
2260
	return prog ? prog->priv : ERR_PTR(-EINVAL);
2261 2262
}

2263 2264 2265 2266 2267
void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex)
{
	prog->prog_ifindex = ifindex;
}

2268
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
2269 2270 2271 2272
{
	const char *title;

	title = prog->section_name;
2273
	if (needs_copy) {
2274 2275 2276
		title = strdup(title);
		if (!title) {
			pr_warning("failed to strdup program title\n");
2277
			return ERR_PTR(-ENOMEM);
2278 2279 2280 2281 2282 2283 2284 2285
		}
	}

	return title;
}

int bpf_program__fd(struct bpf_program *prog)
{
2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320
	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;

2321 2322 2323
	if (!prog)
		return -EINVAL;

2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337
	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;
2338
}
2339

2340
void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
2341 2342 2343 2344 2345 2346 2347 2348 2349 2350
{
	prog->type = type;
}

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

2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364
#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);	\
}							\

2365
BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
2366
BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
2367 2368
BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
2369
BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
2370
BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT);
2371 2372
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
2373

J
John Fastabend 已提交
2374 2375
void bpf_program__set_expected_attach_type(struct bpf_program *prog,
					   enum bpf_attach_type type)
2376 2377 2378 2379
{
	prog->expected_attach_type = type;
}

2380 2381
#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, atype) \
	{ string, sizeof(string) - 1, ptype, eatype, is_attachable, atype }
2382

2383
/* Programs that can NOT be attached. */
2384
#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0)
2385

2386 2387
/* Programs that can be attached. */
#define BPF_APROG_SEC(string, ptype, atype) \
2388
	BPF_PROG_SEC_IMPL(string, ptype, 0, 1, atype)
2389

2390 2391
/* Programs that must specify expected attach type at load time. */
#define BPF_EAPROG_SEC(string, ptype, eatype) \
2392
	BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, eatype)
2393 2394 2395 2396 2397

/* Programs that can be attached but attach type can't be identified by section
 * name. Kept for backward compatibility.
 */
#define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype)
2398

2399 2400 2401 2402
static const struct {
	const char *sec;
	size_t len;
	enum bpf_prog_type prog_type;
2403
	enum bpf_attach_type expected_attach_type;
2404
	int is_attachable;
2405
	enum bpf_attach_type attach_type;
2406
} section_names[] = {
2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419
	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),
	BPF_PROG_SEC("classifier",		BPF_PROG_TYPE_SCHED_CLS),
	BPF_PROG_SEC("action",			BPF_PROG_TYPE_SCHED_ACT),
	BPF_PROG_SEC("tracepoint/",		BPF_PROG_TYPE_TRACEPOINT),
	BPF_PROG_SEC("raw_tracepoint/",		BPF_PROG_TYPE_RAW_TRACEPOINT),
	BPF_PROG_SEC("xdp",			BPF_PROG_TYPE_XDP),
	BPF_PROG_SEC("perf_event",		BPF_PROG_TYPE_PERF_EVENT),
	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),
	BPF_PROG_SEC("lwt_seg6local",		BPF_PROG_TYPE_LWT_SEG6LOCAL),
2420 2421 2422 2423
	BPF_APROG_SEC("cgroup_skb/ingress",	BPF_PROG_TYPE_CGROUP_SKB,
						BPF_CGROUP_INET_INGRESS),
	BPF_APROG_SEC("cgroup_skb/egress",	BPF_PROG_TYPE_CGROUP_SKB,
						BPF_CGROUP_INET_EGRESS),
2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434
	BPF_APROG_COMPAT("cgroup/skb",		BPF_PROG_TYPE_CGROUP_SKB),
	BPF_APROG_SEC("cgroup/sock",		BPF_PROG_TYPE_CGROUP_SOCK,
						BPF_CGROUP_INET_SOCK_CREATE),
	BPF_EAPROG_SEC("cgroup/post_bind4",	BPF_PROG_TYPE_CGROUP_SOCK,
						BPF_CGROUP_INET4_POST_BIND),
	BPF_EAPROG_SEC("cgroup/post_bind6",	BPF_PROG_TYPE_CGROUP_SOCK,
						BPF_CGROUP_INET6_POST_BIND),
	BPF_APROG_SEC("cgroup/dev",		BPF_PROG_TYPE_CGROUP_DEVICE,
						BPF_CGROUP_DEVICE),
	BPF_APROG_SEC("sockops",		BPF_PROG_TYPE_SOCK_OPS,
						BPF_CGROUP_SOCK_OPS),
2435 2436 2437 2438
	BPF_APROG_SEC("sk_skb/stream_parser",	BPF_PROG_TYPE_SK_SKB,
						BPF_SK_SKB_STREAM_PARSER),
	BPF_APROG_SEC("sk_skb/stream_verdict",	BPF_PROG_TYPE_SK_SKB,
						BPF_SK_SKB_STREAM_VERDICT),
2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457
	BPF_APROG_COMPAT("sk_skb",		BPF_PROG_TYPE_SK_SKB),
	BPF_APROG_SEC("sk_msg",			BPF_PROG_TYPE_SK_MSG,
						BPF_SK_MSG_VERDICT),
	BPF_APROG_SEC("lirc_mode2",		BPF_PROG_TYPE_LIRC_MODE2,
						BPF_LIRC_MODE2),
	BPF_APROG_SEC("flow_dissector",		BPF_PROG_TYPE_FLOW_DISSECTOR,
						BPF_FLOW_DISSECTOR),
	BPF_EAPROG_SEC("cgroup/bind4",		BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
						BPF_CGROUP_INET4_BIND),
	BPF_EAPROG_SEC("cgroup/bind6",		BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
						BPF_CGROUP_INET6_BIND),
	BPF_EAPROG_SEC("cgroup/connect4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
						BPF_CGROUP_INET4_CONNECT),
	BPF_EAPROG_SEC("cgroup/connect6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
						BPF_CGROUP_INET6_CONNECT),
	BPF_EAPROG_SEC("cgroup/sendmsg4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
						BPF_CGROUP_UDP4_SENDMSG),
	BPF_EAPROG_SEC("cgroup/sendmsg6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
						BPF_CGROUP_UDP6_SENDMSG),
2458
};
2459

2460
#undef BPF_PROG_SEC_IMPL
2461
#undef BPF_PROG_SEC
2462 2463 2464
#undef BPF_APROG_SEC
#undef BPF_EAPROG_SEC
#undef BPF_APROG_COMPAT
2465

2466 2467
int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
			     enum bpf_attach_type *expected_attach_type)
2468 2469 2470
{
	int i;

2471 2472
	if (!name)
		return -EINVAL;
2473

2474 2475 2476 2477 2478 2479 2480 2481 2482
	for (i = 0; i < ARRAY_SIZE(section_names); i++) {
		if (strncmp(name, section_names[i].sec, section_names[i].len))
			continue;
		*prog_type = section_names[i].prog_type;
		*expected_attach_type = section_names[i].expected_attach_type;
		return 0;
	}
	return -EINVAL;
}
2483

2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494
int libbpf_attach_type_by_name(const char *name,
			       enum bpf_attach_type *attach_type)
{
	int i;

	if (!name)
		return -EINVAL;

	for (i = 0; i < ARRAY_SIZE(section_names); i++) {
		if (strncmp(name, section_names[i].sec, section_names[i].len))
			continue;
2495
		if (!section_names[i].is_attachable)
2496 2497 2498 2499 2500 2501 2502
			return -EINVAL;
		*attach_type = section_names[i].attach_type;
		return 0;
	}
	return -EINVAL;
}

2503 2504 2505 2506 2507 2508 2509
static int
bpf_program__identify_section(struct bpf_program *prog,
			      enum bpf_prog_type *prog_type,
			      enum bpf_attach_type *expected_attach_type)
{
	return libbpf_prog_type_by_name(prog->section_name, prog_type,
					expected_attach_type);
2510 2511
}

2512
int bpf_map__fd(struct bpf_map *map)
2513
{
2514
	return map ? map->fd : -EINVAL;
2515 2516
}

2517
const struct bpf_map_def *bpf_map__def(struct bpf_map *map)
2518
{
2519
	return map ? &map->def : ERR_PTR(-EINVAL);
2520 2521
}

2522
const char *bpf_map__name(struct bpf_map *map)
2523
{
2524
	return map ? map->name : NULL;
2525 2526
}

2527
__u32 bpf_map__btf_key_type_id(const struct bpf_map *map)
2528
{
2529
	return map ? map->btf_key_type_id : 0;
2530 2531
}

2532
__u32 bpf_map__btf_value_type_id(const struct bpf_map *map)
2533
{
2534
	return map ? map->btf_value_type_id : 0;
2535 2536
}

2537 2538
int bpf_map__set_priv(struct bpf_map *map, void *priv,
		     bpf_map_clear_priv_t clear_priv)
2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552
{
	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;
}

2553
void *bpf_map__priv(struct bpf_map *map)
2554
{
2555
	return map ? map->priv : ERR_PTR(-EINVAL);
2556 2557
}

2558 2559 2560 2561 2562
bool bpf_map__is_offload_neutral(struct bpf_map *map)
{
	return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
}

2563 2564 2565 2566 2567
void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
{
	map->map_ifindex = ifindex;
}

2568 2569
static struct bpf_map *
__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i)
2570
{
2571
	ssize_t idx;
2572 2573 2574 2575 2576 2577 2578 2579
	struct bpf_map *s, *e;

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

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

2580
	if ((m < s) || (m >= e)) {
2581 2582 2583 2584 2585
		pr_warning("error in %s: map handler doesn't belong to object\n",
			   __func__);
		return NULL;
	}

2586 2587
	idx = (m - obj->maps) + i;
	if (idx >= obj->nr_maps || idx < 0)
2588 2589 2590
		return NULL;
	return &obj->maps[idx];
}
2591

2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612
struct bpf_map *
bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
{
	if (prev == NULL)
		return obj->maps;

	return __bpf_map__iter(prev, obj, 1);
}

struct bpf_map *
bpf_map__prev(struct bpf_map *next, struct bpf_object *obj)
{
	if (next == NULL) {
		if (!obj->nr_maps)
			return NULL;
		return obj->maps + obj->nr_maps - 1;
	}

	return __bpf_map__iter(next, obj, -1);
}

2613
struct bpf_map *
2614
bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
2615 2616 2617 2618
{
	struct bpf_map *pos;

	bpf_map__for_each(pos, obj) {
2619
		if (pos->name && !strcmp(pos->name, name))
2620 2621 2622 2623
			return pos;
	}
	return NULL;
}
2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635

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);
}
2636 2637 2638 2639 2640 2641 2642

long libbpf_get_error(const void *ptr)
{
	if (IS_ERR(ptr))
		return PTR_ERR(ptr);
	return 0;
}
2643 2644 2645

int bpf_prog_load(const char *file, enum bpf_prog_type type,
		  struct bpf_object **pobj, int *prog_fd)
2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658
{
	struct bpf_prog_load_attr attr;

	memset(&attr, 0, sizeof(struct bpf_prog_load_attr));
	attr.file = file;
	attr.prog_type = type;
	attr.expected_attach_type = 0;

	return bpf_prog_load_xattr(&attr, pobj, prog_fd);
}

int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
			struct bpf_object **pobj, int *prog_fd)
2659
{
2660 2661 2662 2663
	struct bpf_object_open_attr open_attr = {
		.file		= attr->file,
		.prog_type	= attr->prog_type,
	};
2664
	struct bpf_program *prog, *first_prog = NULL;
2665 2666
	enum bpf_attach_type expected_attach_type;
	enum bpf_prog_type prog_type;
2667
	struct bpf_object *obj;
2668
	struct bpf_map *map;
2669 2670
	int err;

2671 2672
	if (!attr)
		return -EINVAL;
2673 2674
	if (!attr->file)
		return -EINVAL;
2675

2676
	obj = bpf_object__open_xattr(&open_attr);
2677
	if (IS_ERR_OR_NULL(obj))
2678 2679
		return -ENOENT;

2680 2681 2682 2683 2684
	bpf_object__for_each_program(prog, obj) {
		/*
		 * If type is not specified, try to guess it based on
		 * section name.
		 */
2685
		prog_type = attr->prog_type;
2686
		prog->prog_ifindex = attr->ifindex;
2687 2688
		expected_attach_type = attr->expected_attach_type;
		if (prog_type == BPF_PROG_TYPE_UNSPEC) {
2689 2690 2691 2692 2693
			err = bpf_program__identify_section(prog, &prog_type,
							    &expected_attach_type);
			if (err < 0) {
				pr_warning("failed to guess program type based on section name %s\n",
					   prog->section_name);
2694 2695 2696
				bpf_object__close(obj);
				return -EINVAL;
			}
2697
		}
2698

2699 2700 2701 2702
		bpf_program__set_type(prog, prog_type);
		bpf_program__set_expected_attach_type(prog,
						      expected_attach_type);

2703
		if (!first_prog)
2704 2705 2706
			first_prog = prog;
	}

2707
	bpf_map__for_each(map, obj) {
2708 2709
		if (!bpf_map__is_offload_neutral(map))
			map->map_ifindex = attr->ifindex;
2710 2711
	}

2712 2713 2714 2715
	if (!first_prog) {
		pr_warning("object file doesn't contain bpf program\n");
		bpf_object__close(obj);
		return -ENOENT;
2716 2717
	}

2718 2719 2720 2721 2722 2723 2724
	err = bpf_object__load(obj);
	if (err) {
		bpf_object__close(obj);
		return -EINVAL;
	}

	*pobj = obj;
2725
	*prog_fd = bpf_program__fd(first_prog);
2726 2727
	return 0;
}
2728 2729

enum bpf_perf_event_ret
2730 2731 2732
bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
			   void **copy_mem, size_t *copy_size,
			   bpf_perf_event_print_t fn, void *private_data)
2733
{
2734
	struct perf_event_mmap_page *header = mmap_mem;
2735
	__u64 data_head = ring_buffer_read_head(header);
2736
	__u64 data_tail = header->data_tail;
2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755
	void *base = ((__u8 *)header) + page_size;
	int ret = LIBBPF_PERF_EVENT_CONT;
	struct perf_event_header *ehdr;
	size_t ehdr_size;

	while (data_head != data_tail) {
		ehdr = base + (data_tail & (mmap_size - 1));
		ehdr_size = ehdr->size;

		if (((void *)ehdr) + ehdr_size > base + mmap_size) {
			void *copy_start = ehdr;
			size_t len_first = base + mmap_size - copy_start;
			size_t len_secnd = ehdr_size - len_first;

			if (*copy_size < ehdr_size) {
				free(*copy_mem);
				*copy_mem = malloc(ehdr_size);
				if (!*copy_mem) {
					*copy_size = 0;
2756 2757 2758
					ret = LIBBPF_PERF_EVENT_ERROR;
					break;
				}
2759
				*copy_size = ehdr_size;
2760 2761
			}

2762 2763 2764
			memcpy(*copy_mem, copy_start, len_first);
			memcpy(*copy_mem + len_first, base, len_secnd);
			ehdr = *copy_mem;
2765 2766
		}

2767 2768
		ret = fn(ehdr, private_data);
		data_tail += ehdr_size;
2769 2770 2771 2772
		if (ret != LIBBPF_PERF_EVENT_CONT)
			break;
	}

2773
	ring_buffer_write_tail(header, data_tail);
2774 2775
	return ret;
}