libbpf.c 66.8 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
#ifndef _GNU_SOURCE
13
#define _GNU_SOURCE
14
#endif
15
#include <stdlib.h>
16 17
#include <stdio.h>
#include <stdarg.h>
18
#include <libgen.h>
19
#include <inttypes.h>
20
#include <string.h>
21
#include <unistd.h>
22 23
#include <fcntl.h>
#include <errno.h>
24
#include <asm/unistd.h>
25
#include <linux/err.h>
26
#include <linux/kernel.h>
27
#include <linux/bpf.h>
28
#include <linux/btf.h>
29
#include <linux/filter.h>
30
#include <linux/list.h>
31
#include <linux/limits.h>
32
#include <linux/perf_event.h>
33
#include <linux/ring_buffer.h>
34 35 36
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/vfs.h>
37
#include <tools/libc_compat.h>
38 39
#include <libelf.h>
#include <gelf.h>
40 41

#include "libbpf.h"
42
#include "bpf.h"
43
#include "btf.h"
44
#include "str_error.h"
45
#include "libbpf_util.h"
46

47 48 49 50
#ifndef EM_BPF
#define EM_BPF 247
#endif

51 52 53 54
#ifndef BPF_FS_MAGIC
#define BPF_FS_MAGIC		0xcafe4a11
#endif

55 56
#define __printf(a, b)	__attribute__((format(printf, a, b)))

S
Stanislav Fomichev 已提交
57 58
static int __base_pr(enum libbpf_print_level level, const char *format,
		     va_list args)
59
{
60 61 62
	if (level == LIBBPF_DEBUG)
		return 0;

S
Stanislav Fomichev 已提交
63
	return vfprintf(stderr, format, args);
64 65
}

S
Stanislav Fomichev 已提交
66
static libbpf_print_fn_t __libbpf_pr = __base_pr;
67

68
void libbpf_set_print(libbpf_print_fn_t fn)
69
{
70
	__libbpf_pr = fn;
71
}
72

73 74 75 76 77
__printf(2, 3)
void libbpf_print(enum libbpf_print_level level, const char *format, ...)
{
	va_list args;

78 79 80
	if (!__libbpf_pr)
		return;

81
	va_start(args, format);
82
	__libbpf_pr(level, format, args);
83 84 85
	va_end(args);
}

86 87 88 89 90 91 92 93 94
#define STRERR_BUFSIZE  128

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


95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114
/* 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

115 116 117 118 119
struct bpf_capabilities {
	/* v4.14: kernel support for program & map names. */
	__u32 name:1;
};

120 121 122 123 124 125 126
/*
 * 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;
127
	char *name;
128
	int prog_ifindex;
129
	char *section_name;
S
Stanislav Fomichev 已提交
130 131 132 133
	/* section_name with / replaced by _; makes recursive pinning
	 * in bpf_object__pin_programs easier
	 */
	char *pin_name;
134
	struct bpf_insn *insns;
135
	size_t insns_cnt, main_prog_cnt;
136
	enum bpf_prog_type type;
137

138 139 140 141 142
	struct reloc_desc {
		enum {
			RELO_LD64,
			RELO_CALL,
		} type;
143
		int insn_idx;
144 145 146 147
		union {
			int map_idx;
			int text_off;
		};
148 149
	} *reloc_desc;
	int nr_reloc;
150

151 152 153 154 155
	struct {
		int nr;
		int *fds;
	} instances;
	bpf_program_prep_t preprocessor;
156 157 158 159

	struct bpf_object *obj;
	void *priv;
	bpf_program_clear_priv_t clear_priv;
160 161

	enum bpf_attach_type expected_attach_type;
162 163 164
	int btf_fd;
	void *func_info;
	__u32 func_info_rec_size;
165
	__u32 func_info_cnt;
166 167

	struct bpf_capabilities *caps;
168 169 170 171

	void *line_info;
	__u32 line_info_rec_size;
	__u32 line_info_cnt;
172 173
};

174 175
struct bpf_map {
	int fd;
176
	char *name;
E
Eric Leblond 已提交
177
	size_t offset;
178
	int map_ifindex;
179
	int inner_map_fd;
180
	struct bpf_map_def def;
181 182
	__u32 btf_key_type_id;
	__u32 btf_value_type_id;
183 184 185 186
	void *priv;
	bpf_map_clear_priv_t clear_priv;
};

187 188
static LIST_HEAD(bpf_objects_list);

189
struct bpf_object {
190
	char license[64];
191
	__u32 kern_version;
192

193 194
	struct bpf_program *programs;
	size_t nr_programs;
195 196 197
	struct bpf_map *maps;
	size_t nr_maps;

198
	bool loaded;
199
	bool has_pseudo_calls;
200

201 202 203 204 205 206
	/*
	 * Information when doing elf related work. Only valid if fd
	 * is valid.
	 */
	struct {
		int fd;
207 208
		void *obj_buf;
		size_t obj_buf_sz;
209 210
		Elf *elf;
		GElf_Ehdr ehdr;
211
		Elf_Data *symbols;
212
		size_t strtabidx;
213 214 215 216 217
		struct {
			GElf_Shdr shdr;
			Elf_Data *data;
		} *reloc;
		int nr_reloc;
218
		int maps_shndx;
219
		int text_shndx;
220
	} efile;
221 222 223 224 225 226
	/*
	 * 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;
227

228
	struct btf *btf;
229
	struct btf_ext *btf_ext;
230

231 232 233
	void *priv;
	bpf_object_clear_priv_t clear_priv;

234 235
	struct bpf_capabilities caps;

236 237 238 239
	char path[];
};
#define obj_elf_valid(o)	((o)->efile.elf)

240
void bpf_program__unload(struct bpf_program *prog)
241
{
242 243
	int i;

244 245 246
	if (!prog)
		return;

247 248 249 250 251 252 253 254 255 256 257 258 259 260
	/*
	 * 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);
261 262 263

	zclose(prog->btf_fd);
	zfree(&prog->func_info);
264
	zfree(&prog->line_info);
265 266
}

267 268 269 270 271
static void bpf_program__exit(struct bpf_program *prog)
{
	if (!prog)
		return;

272 273 274 275 276 277
	if (prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

278
	bpf_program__unload(prog);
279
	zfree(&prog->name);
280
	zfree(&prog->section_name);
S
Stanislav Fomichev 已提交
281
	zfree(&prog->pin_name);
282
	zfree(&prog->insns);
283 284 285
	zfree(&prog->reloc_desc);

	prog->nr_reloc = 0;
286 287 288 289
	prog->insns_cnt = 0;
	prog->idx = -1;
}

S
Stanislav Fomichev 已提交
290 291 292 293 294 295 296 297 298 299 300
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;
}

301
static int
302 303
bpf_program__init(void *data, size_t size, char *section_name, int idx,
		  struct bpf_program *prog)
304 305
{
	if (size < sizeof(struct bpf_insn)) {
306
		pr_warning("corrupted section '%s'\n", section_name);
307 308 309 310 311
		return -EINVAL;
	}

	bzero(prog, sizeof(*prog));

312
	prog->section_name = strdup(section_name);
313
	if (!prog->section_name) {
314 315
		pr_warning("failed to alloc name for prog under section(%d) %s\n",
			   idx, section_name);
316 317 318
		goto errout;
	}

S
Stanislav Fomichev 已提交
319 320 321 322 323 324 325
	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;
	}

326 327
	prog->insns = malloc(size);
	if (!prog->insns) {
328 329
		pr_warning("failed to alloc insns for prog under section %s\n",
			   section_name);
330 331 332 333 334 335
		goto errout;
	}
	prog->insns_cnt = size / sizeof(struct bpf_insn);
	memcpy(prog->insns, data,
	       prog->insns_cnt * sizeof(struct bpf_insn));
	prog->idx = idx;
336 337
	prog->instances.fds = NULL;
	prog->instances.nr = -1;
338
	prog->type = BPF_PROG_TYPE_UNSPEC;
339
	prog->btf_fd = -1;
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
	if (err)
		return err;

358
	prog.caps = &obj->caps;
359 360 361
	progs = obj->programs;
	nr_progs = obj->nr_programs;

362
	progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
363 364 365 366 367 368
	if (!progs) {
		/*
		 * In this case the original obj->programs
		 * is still valid, so don't need special treat for
		 * bpf_close_object().
		 */
369 370
		pr_warning("failed to alloc a new program under section '%s'\n",
			   section_name);
371 372 373 374 375 376 377
		bpf_program__exit(&prog);
		return -ENOMEM;
	}

	pr_debug("found program %s\n", prog.section_name);
	obj->programs = progs;
	obj->nr_programs = nr_progs + 1;
378
	prog.obj = obj;
379 380 381 382
	progs[nr_progs] = prog;
	return 0;
}

383 384 385 386 387 388 389 390
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++) {
391
		const char *name = NULL;
392 393 394 395 396 397 398 399 400 401 402

		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;
403 404
			if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL)
				continue;
405 406 407 408 409 410 411 412 413 414 415

			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;
			}
		}

416 417 418
		if (!name && prog->idx == obj->efile.text_shndx)
			name = ".text";

419 420 421 422 423
		if (!name) {
			pr_warning("failed to find sym for prog %s\n",
				   prog->section_name);
			return -EINVAL;
		}
424

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
	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) {
506
			char errmsg[STRERR_BUFSIZE];
507 508
			char *cp = libbpf_strerror_r(errno, errmsg,
						     sizeof(errmsg));
509 510

			pr_warning("failed to open %s: %s\n", obj->path, cp);
511 512 513 514 515 516
			return -errno;
		}

		obj->efile.elf = elf_begin(obj->efile.fd,
				LIBBPF_ELF_C_READ_MMAP,
				NULL);
517 518 519 520 521
	}

	if (!obj->efile.elf) {
		pr_warning("failed to open %s as ELF file\n",
				obj->path);
522
		err = -LIBBPF_ERRNO__LIBELF;
523 524 525 526 527 528
		goto errout;
	}

	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
		pr_warning("failed to get EHDR from %s\n",
				obj->path);
529
		err = -LIBBPF_ERRNO__FORMAT;
530 531 532 533
		goto errout;
	}
	ep = &obj->efile.ehdr;

534 535
	/* Old LLVM set e_machine to EM_NONE */
	if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) {
536 537
		pr_warning("%s is not an eBPF object file\n",
			obj->path);
538
		err = -LIBBPF_ERRNO__FORMAT;
539 540 541 542 543 544 545 546 547
		goto errout;
	}

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

548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565
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:
566
		return -LIBBPF_ERRNO__ENDIAN;
567 568 569 570 571 572
	}

	return 0;

mismatch:
	pr_warning("Error: endianness mismatch.\n");
573
	return -LIBBPF_ERRNO__ENDIAN;
574 575
}

576 577 578 579 580 581 582 583 584 585 586 587 588 589
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)
{
590
	__u32 kver;
591 592 593

	if (size != sizeof(kver)) {
		pr_warning("invalid kver section in %s\n", obj->path);
594
		return -LIBBPF_ERRNO__FORMAT;
595 596 597 598 599 600 601 602
	}
	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
603 604 605 606
static int compare_bpf_map(const void *_a, const void *_b)
{
	const struct bpf_map *a = _a;
	const struct bpf_map *b = _b;
607

E
Eric Leblond 已提交
608
	return a->offset - b->offset;
609 610
}

611 612 613 614 615 616 617 618
static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
{
	if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
	    type == BPF_MAP_TYPE_HASH_OF_MAPS)
		return true;
	return false;
}

619
static int
620
bpf_object__init_maps(struct bpf_object *obj, int flags)
621
{
622
	bool strict = !(flags & MAPS_RELAX_COMPAT);
623
	int i, map_idx, map_def_sz, nr_maps = 0;
E
Eric Leblond 已提交
624 625
	Elf_Scn *scn;
	Elf_Data *data;
626 627
	Elf_Data *symbols = obj->efile.symbols;

E
Eric Leblond 已提交
628 629 630 631 632 633 634 635 636 637 638
	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);
639
		return -EINVAL;
E
Eric Leblond 已提交
640
	}
641

E
Eric Leblond 已提交
642 643 644 645 646 647 648
	/*
	 * 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.
	 */
649 650
	for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
		GElf_Sym sym;
E
Eric Leblond 已提交
651 652 653 654 655 656 657 658 659 660 661 662 663 664 665

		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;

666 667 668 669 670 671 672 673 674
	/* 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
675 676 677 678 679 680 681
	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;

682 683 684 685 686 687
	for (i = 0; i < nr_maps; i++) {
		/*
		 * fill all fd with -1 so won't close incorrect
		 * fd (fd=0 is stdin) when failure (zclose won't close
		 * negative fd)).
		 */
E
Eric Leblond 已提交
688
		obj->maps[i].fd = -1;
689 690
		obj->maps[i].inner_map_fd = -1;
	}
E
Eric Leblond 已提交
691 692 693 694 695 696

	/*
	 * 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;
697
		const char *map_name;
E
Eric Leblond 已提交
698
		struct bpf_map_def *def;
699 700 701

		if (!gelf_getsym(symbols, i, &sym))
			continue;
702
		if (sym.st_shndx != obj->efile.maps_shndx)
703 704 705
			continue;

		map_name = elf_strptr(obj->efile.elf,
706
				      obj->efile.strtabidx,
707
				      sym.st_name);
E
Eric Leblond 已提交
708
		obj->maps[map_idx].offset = sym.st_value;
709
		if (sym.st_value + map_def_sz > data->d_size) {
E
Eric Leblond 已提交
710 711 712
			pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
				   obj->path, map_name);
			return -EINVAL;
713
		}
E
Eric Leblond 已提交
714

715
		obj->maps[map_idx].name = strdup(map_name);
716 717 718 719
		if (!obj->maps[map_idx].name) {
			pr_warning("failed to alloc map name\n");
			return -ENOMEM;
		}
E
Eric Leblond 已提交
720
		pr_debug("map %d is \"%s\"\n", map_idx,
721
			 obj->maps[map_idx].name);
E
Eric Leblond 已提交
722
		def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745
		/*
		 * 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);
746 747
					if (strict)
						return -EINVAL;
748 749 750 751 752
				}
			}
			memcpy(&obj->maps[map_idx].def, def,
			       sizeof(struct bpf_map_def));
		}
E
Eric Leblond 已提交
753
		map_idx++;
754
	}
E
Eric Leblond 已提交
755 756

	qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map);
757
	return 0;
758 759
}

760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777
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;
}

778
static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
779 780 781
{
	Elf *elf = obj->efile.elf;
	GElf_Ehdr *ep = &obj->efile.ehdr;
782
	Elf_Data *btf_ext_data = NULL;
783
	Elf_Scn *scn = NULL;
784
	int idx = 0, err = 0;
785 786 787 788 789

	/* 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);
790
		return -LIBBPF_ERRNO__FORMAT;
791 792 793 794 795 796 797 798 799
	}

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

		idx++;
		if (gelf_getshdr(scn, &sh) != &sh) {
800 801
			pr_warning("failed to get section(%d) header from %s\n",
				   idx, obj->path);
802
			err = -LIBBPF_ERRNO__FORMAT;
803 804 805 806 807
			goto out;
		}

		name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
		if (!name) {
808 809
			pr_warning("failed to get section(%d) name from %s\n",
				   idx, obj->path);
810
			err = -LIBBPF_ERRNO__FORMAT;
811 812 813 814 815
			goto out;
		}

		data = elf_getdata(scn, 0);
		if (!data) {
816 817
			pr_warning("failed to get section(%d) data from %s(%s)\n",
				   idx, name, obj->path);
818
			err = -LIBBPF_ERRNO__FORMAT;
819 820
			goto out;
		}
821 822
		pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n",
			 idx, name, (unsigned long)data->d_size,
823 824
			 (int)sh.sh_link, (unsigned long)sh.sh_flags,
			 (int)sh.sh_type);
825 826 827 828 829 830 831 832 833

		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
834
		else if (strcmp(name, "maps") == 0)
835
			obj->efile.maps_shndx = idx;
836
		else if (strcmp(name, BTF_ELF_SEC) == 0) {
837
			obj->btf = btf__new(data->d_buf, data->d_size);
838 839 840 841 842
			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;
			}
843
		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
844
			btf_ext_data = data;
845
		} else if (sh.sh_type == SHT_SYMTAB) {
846 847 848
			if (obj->efile.symbols) {
				pr_warning("bpf: multiple SYMTAB in %s\n",
					   obj->path);
849
				err = -LIBBPF_ERRNO__FORMAT;
850
			} else {
851
				obj->efile.symbols = data;
852 853
				obj->efile.strtabidx = sh.sh_link;
			}
854 855 856
		} else if ((sh.sh_type == SHT_PROGBITS) &&
			   (sh.sh_flags & SHF_EXECINSTR) &&
			   (data->d_size > 0)) {
857 858
			if (strcmp(name, ".text") == 0)
				obj->efile.text_shndx = idx;
859 860 861
			err = bpf_object__add_program(obj, data->d_buf,
						      data->d_size, name, idx);
			if (err) {
862
				char errmsg[STRERR_BUFSIZE];
863 864
				char *cp = libbpf_strerror_r(-err, errmsg,
							     sizeof(errmsg));
865

866
				pr_warning("failed to alloc program %s (%s): %s",
867
					   name, obj->path, cp);
868
			}
869 870 871
		} else if (sh.sh_type == SHT_REL) {
			void *reloc = obj->efile.reloc;
			int nr_reloc = obj->efile.nr_reloc + 1;
872 873 874 875 876 877 878 879
			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;
			}
880

881 882
			reloc = reallocarray(reloc, nr_reloc,
					     sizeof(*obj->efile.reloc));
883 884 885 886 887 888 889 890 891 892 893 894
			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;
			}
895 896
		} else {
			pr_debug("skip section(%d) %s\n", idx, name);
897
		}
898 899
		if (err)
			goto out;
900
	}
901

902 903 904 905
	if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
		pr_warning("Corrupted ELF file: index of strtab invalid\n");
		return LIBBPF_ERRNO__FORMAT;
	}
906 907 908 909 910 911
	if (btf_ext_data) {
		if (!obj->btf) {
			pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n",
				 BTF_EXT_ELF_SEC, BTF_ELF_SEC);
		} else {
			obj->btf_ext = btf_ext__new(btf_ext_data->d_buf,
912
						    btf_ext_data->d_size);
913 914 915 916 917 918 919 920
			if (IS_ERR(obj->btf_ext)) {
				pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
					   BTF_EXT_ELF_SEC,
					   PTR_ERR(obj->btf_ext));
				obj->btf_ext = NULL;
			}
		}
	}
921
	if (obj->efile.maps_shndx >= 0) {
922
		err = bpf_object__init_maps(obj, flags);
923 924 925 926
		if (err)
			goto out;
	}
	err = bpf_object__init_prog_names(obj);
927 928 929 930
out:
	return err;
}

931 932 933 934 935 936 937 938 939 940 941 942 943 944
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;
}

945 946 947 948 949 950 951 952 953 954 955 956
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;
}

957
static int
958 959
bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
			   Elf_Data *data, struct bpf_object *obj)
960
{
961 962 963 964 965
	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;
966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987
	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);
988
			return -LIBBPF_ERRNO__FORMAT;
989 990 991 992 993 994 995
		}

		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));
996
			return -LIBBPF_ERRNO__FORMAT;
997
		}
D
David Miller 已提交
998 999 1000
		pr_debug("relo for %lld value %lld name %d\n",
			 (long long) (rel.r_info >> 32),
			 (long long) sym.st_value, sym.st_name);
1001

1002
		if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) {
1003 1004 1005 1006 1007 1008 1009 1010
			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);

1011 1012 1013 1014 1015 1016 1017 1018
		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;
1019
			obj->has_pseudo_calls = true;
1020 1021 1022
			continue;
		}

1023 1024 1025
		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);
1026
			return -LIBBPF_ERRNO__RELOC;
1027 1028
		}

1029 1030 1031 1032 1033 1034 1035 1036 1037
		/* 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;
			}
		}

1038 1039 1040
		if (map_idx >= nr_maps) {
			pr_warning("bpf relocation: map_idx %d large than %d\n",
				   (int)map_idx, (int)nr_maps - 1);
1041
			return -LIBBPF_ERRNO__RELOC;
1042 1043
		}

1044
		prog->reloc_desc[i].type = RELO_LD64;
1045 1046 1047 1048 1049 1050
		prog->reloc_desc[i].insn_idx = insn_idx;
		prog->reloc_desc[i].map_idx = map_idx;
	}
	return 0;
}

1051 1052 1053
static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
{
	struct bpf_map_def *def = &map->def;
1054 1055
	__u32 key_type_id, value_type_id;
	int ret;
1056

1057 1058 1059 1060 1061
	ret = btf__get_map_kv_tids(btf, map->name, def->key_size,
				   def->value_size, &key_type_id,
				   &value_type_id);
	if (ret)
		return ret;
1062

1063 1064
	map->btf_key_type_id = key_type_id;
	map->btf_value_type_id = value_type_id;
1065 1066 1067 1068

	return 0;
}

J
Jakub Kicinski 已提交
1069 1070 1071 1072 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
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;
}

1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161
static int
bpf_object__probe_name(struct bpf_object *obj)
{
	struct bpf_load_program_attr attr;
	char *cp, errmsg[STRERR_BUFSIZE];
	struct bpf_insn insns[] = {
		BPF_MOV64_IMM(BPF_REG_0, 0),
		BPF_EXIT_INSN(),
	};
	int ret;

	/* make sure basic loading works */

	memset(&attr, 0, sizeof(attr));
	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
	attr.insns = insns;
	attr.insns_cnt = ARRAY_SIZE(insns);
	attr.license = "GPL";

	ret = bpf_load_program_xattr(&attr, NULL, 0);
	if (ret < 0) {
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
		pr_warning("Error in %s():%s(%d). Couldn't load basic 'r0 = 0' BPF program.\n",
			   __func__, cp, errno);
		return -errno;
	}
	close(ret);

	/* now try the same program, but with the name */

	attr.name = "test";
	ret = bpf_load_program_xattr(&attr, NULL, 0);
	if (ret >= 0) {
		obj->caps.name = 1;
		close(ret);
	}

	return 0;
}

static int
bpf_object__probe_caps(struct bpf_object *obj)
{
	return bpf_object__probe_name(obj);
}

1162 1163 1164
static int
bpf_object__create_maps(struct bpf_object *obj)
{
1165
	struct bpf_create_map_attr create_attr = {};
1166
	unsigned int i;
1167
	int err;
1168

1169
	for (i = 0; i < obj->nr_maps; i++) {
1170 1171
		struct bpf_map *map = &obj->maps[i];
		struct bpf_map_def *def = &map->def;
1172
		char *cp, errmsg[STRERR_BUFSIZE];
1173 1174
		int *pfd = &map->fd;

J
Jakub Kicinski 已提交
1175 1176 1177 1178 1179 1180
		if (map->fd >= 0) {
			pr_debug("skip map create (preset) %s: fd=%d\n",
				 map->name, map->fd);
			continue;
		}

1181 1182
		if (obj->caps.name)
			create_attr.name = map->name;
1183
		create_attr.map_ifindex = map->map_ifindex;
1184 1185 1186 1187 1188 1189
		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;
1190 1191
		create_attr.btf_key_type_id = 0;
		create_attr.btf_value_type_id = 0;
1192 1193 1194
		if (bpf_map_type__is_map_in_map(def->type) &&
		    map->inner_map_fd >= 0)
			create_attr.inner_map_fd = map->inner_map_fd;
1195 1196 1197

		if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) {
			create_attr.btf_fd = btf__fd(obj->btf);
1198 1199
			create_attr.btf_key_type_id = map->btf_key_type_id;
			create_attr.btf_value_type_id = map->btf_value_type_id;
1200 1201 1202
		}

		*pfd = bpf_create_map_xattr(&create_attr);
1203
		if (*pfd < 0 && create_attr.btf_key_type_id) {
1204
			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1205
			pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
1206
				   map->name, cp, errno);
1207
			create_attr.btf_fd = 0;
1208 1209 1210 1211
			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;
1212 1213 1214
			*pfd = bpf_create_map_xattr(&create_attr);
		}

1215 1216 1217
		if (*pfd < 0) {
			size_t j;

1218
			err = *pfd;
1219
			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
E
Eric Leblond 已提交
1220
			pr_warning("failed to create map (name: '%s'): %s\n",
1221
				   map->name, cp);
1222
			for (j = 0; j < i; j++)
1223
				zclose(obj->maps[j].fd);
1224 1225
			return err;
		}
1226
		pr_debug("create map %s: fd=%d\n", map->name, *pfd);
1227 1228 1229 1230 1231
	}

	return 0;
}

1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 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 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288
static int
check_btf_ext_reloc_err(struct bpf_program *prog, int err,
			void *btf_prog_info, const char *info_name)
{
	if (err != -ENOENT) {
		pr_warning("Error in loading %s for sec %s.\n",
			   info_name, prog->section_name);
		return err;
	}

	/* err == -ENOENT (i.e. prog->section_name not found in btf_ext) */

	if (btf_prog_info) {
		/*
		 * Some info has already been found but has problem
		 * in the last btf_ext reloc.  Must have to error
		 * out.
		 */
		pr_warning("Error in relocating %s for sec %s.\n",
			   info_name, prog->section_name);
		return err;
	}

	/*
	 * Have problem loading the very first info.  Ignore
	 * the rest.
	 */
	pr_warning("Cannot find %s for main program sec %s. Ignore all %s.\n",
		   info_name, prog->section_name, info_name);
	return 0;
}

static int
bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj,
			  const char *section_name,  __u32 insn_offset)
{
	int err;

	if (!insn_offset || prog->func_info) {
		/*
		 * !insn_offset => main program
		 *
		 * For sub prog, the main program's func_info has to
		 * be loaded first (i.e. prog->func_info != NULL)
		 */
		err = btf_ext__reloc_func_info(obj->btf, obj->btf_ext,
					       section_name, insn_offset,
					       &prog->func_info,
					       &prog->func_info_cnt);
		if (err)
			return check_btf_ext_reloc_err(prog, err,
						       prog->func_info,
						       "bpf_func_info");

		prog->func_info_rec_size = btf_ext__func_info_rec_size(obj->btf_ext);
	}

1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301
	if (!insn_offset || prog->line_info) {
		err = btf_ext__reloc_line_info(obj->btf, obj->btf_ext,
					       section_name, insn_offset,
					       &prog->line_info,
					       &prog->line_info_cnt);
		if (err)
			return check_btf_ext_reloc_err(prog, err,
						       prog->line_info,
						       "bpf_line_info");

		prog->line_info_rec_size = btf_ext__line_info_rec_size(obj->btf_ext);
	}

1302 1303 1304 1305 1306 1307
	if (!insn_offset)
		prog->btf_fd = btf__fd(obj->btf);

	return 0;
}

1308 1309 1310 1311 1312 1313 1314
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;
1315
	int err;
1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332

	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;
1333
		new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn));
1334 1335 1336 1337
		if (!new_insn) {
			pr_warning("oom in prog realloc\n");
			return -ENOMEM;
		}
1338

1339 1340 1341 1342 1343
		if (obj->btf_ext) {
			err = bpf_program_reloc_btf_ext(prog, obj,
							text->section_name,
							prog->insns_cnt);
			if (err)
1344 1345 1346
				return err;
		}

1347 1348 1349 1350 1351
		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;
1352 1353 1354
		pr_debug("added %zd insn from %s to prog %s\n",
			 text->insns_cnt, text->section_name,
			 prog->section_name);
1355 1356 1357 1358 1359 1360
	}
	insn = &prog->insns[relo->insn_idx];
	insn->imm += prog->main_prog_cnt - relo->insn_idx;
	return 0;
}

W
Wang Nan 已提交
1361
static int
1362
bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
W
Wang Nan 已提交
1363
{
1364
	int i, err;
W
Wang Nan 已提交
1365

1366 1367 1368
	if (!prog)
		return 0;

1369 1370 1371 1372
	if (obj->btf_ext) {
		err = bpf_program_reloc_btf_ext(prog, obj,
						prog->section_name, 0);
		if (err)
1373 1374 1375 1376
			return err;
	}

	if (!prog->reloc_desc)
W
Wang Nan 已提交
1377 1378 1379
		return 0;

	for (i = 0; i < prog->nr_reloc; i++) {
1380 1381 1382
		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
1383

1384 1385
			insn_idx = prog->reloc_desc[i].insn_idx;
			map_idx = prog->reloc_desc[i].map_idx;
W
Wang Nan 已提交
1386

1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398
			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
1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417
		}
	}

	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];

1418
		err = bpf_program__relocate(prog, obj);
W
Wang Nan 已提交
1419 1420 1421 1422 1423 1424 1425 1426 1427
		if (err) {
			pr_warning("failed to relocate '%s'\n",
				   prog->section_name);
			return err;
		}
	}
	return 0;
}

1428 1429 1430 1431 1432 1433
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");
1434
		return -LIBBPF_ERRNO__INTERNAL;
1435 1436 1437 1438 1439 1440 1441 1442 1443 1444
	}

	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__);
1445
			return -LIBBPF_ERRNO__INTERNAL;
1446 1447 1448 1449
		}

		prog = bpf_object__find_prog_by_idx(obj, idx);
		if (!prog) {
1450
			pr_warning("relocation failed: no section(%d)\n", idx);
1451
			return -LIBBPF_ERRNO__RELOC;
1452 1453
		}

1454
		err = bpf_program__collect_reloc(prog,
1455
						 shdr, data,
1456
						 obj);
1457
		if (err)
1458
			return err;
1459 1460 1461 1462
	}
	return 0;
}

1463
static int
1464
load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
1465
	     char *license, __u32 kern_version, int *pfd)
1466
{
1467
	struct bpf_load_program_attr load_attr;
1468
	char *cp, errmsg[STRERR_BUFSIZE];
1469
	char *log_buf;
1470
	int ret;
1471

1472
	memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
1473 1474
	load_attr.prog_type = prog->type;
	load_attr.expected_attach_type = prog->expected_attach_type;
1475 1476
	if (prog->caps->name)
		load_attr.name = prog->name;
1477 1478 1479 1480
	load_attr.insns = insns;
	load_attr.insns_cnt = insns_cnt;
	load_attr.license = license;
	load_attr.kern_version = kern_version;
1481
	load_attr.prog_ifindex = prog->prog_ifindex;
Y
Yonghong Song 已提交
1482
	load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0;
1483 1484
	load_attr.func_info = prog->func_info;
	load_attr.func_info_rec_size = prog->func_info_rec_size;
1485
	load_attr.func_info_cnt = prog->func_info_cnt;
1486 1487 1488
	load_attr.line_info = prog->line_info;
	load_attr.line_info_rec_size = prog->line_info_rec_size;
	load_attr.line_info_cnt = prog->line_info_cnt;
1489
	if (!load_attr.insns || !load_attr.insns_cnt)
1490 1491 1492 1493 1494 1495
		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");

1496
	ret = bpf_load_program_xattr(&load_attr, log_buf, BPF_LOG_BUF_SIZE);
1497 1498 1499 1500 1501 1502 1503

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

1504
	ret = -LIBBPF_ERRNO__LOAD;
1505
	cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1506
	pr_warning("load bpf program failed: %s\n", cp);
1507

1508 1509
	if (log_buf && log_buf[0] != '\0') {
		ret = -LIBBPF_ERRNO__VERIFY;
1510 1511 1512
		pr_warning("-- BEGIN DUMP LOG ---\n");
		pr_warning("\n%s\n", log_buf);
		pr_warning("-- END LOG --\n");
1513 1514 1515
	} 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);
1516
		ret = -LIBBPF_ERRNO__PROG2BIG;
1517
	} else {
1518
		/* Wrong program type? */
1519
		if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) {
1520 1521
			int fd;

1522 1523 1524
			load_attr.prog_type = BPF_PROG_TYPE_KPROBE;
			load_attr.expected_attach_type = 0;
			fd = bpf_load_program_xattr(&load_attr, NULL, 0);
1525 1526 1527 1528 1529
			if (fd >= 0) {
				close(fd);
				ret = -LIBBPF_ERRNO__PROGTYPE;
				goto out;
			}
1530
		}
1531 1532 1533

		if (log_buf)
			ret = -LIBBPF_ERRNO__KVER;
1534 1535 1536 1537 1538 1539 1540
	}

out:
	free(log_buf);
	return ret;
}

1541
int
1542
bpf_program__load(struct bpf_program *prog,
1543
		  char *license, __u32 kern_version)
1544
{
1545
	int err = 0, fd, i;
1546

1547 1548 1549 1550 1551 1552
	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;
		}
1553

1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567
		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);
		}
1568
		err = load_program(prog, prog->insns, prog->insns_cnt,
1569
				   license, kern_version, &fd);
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
		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;
		}

1597
		err = load_program(prog, result.new_insn_ptr,
1598
				   result.new_insn_cnt,
1599
				   license, kern_version, &fd);
1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611

		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:
1612 1613 1614 1615 1616 1617 1618 1619
	if (err)
		pr_warning("failed to load program '%s'\n",
			   prog->section_name);
	zfree(&prog->insns);
	prog->insns_cnt = 0;
	return err;
}

1620 1621 1622 1623 1624 1625
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;
}

1626 1627 1628 1629 1630 1631 1632
static int
bpf_object__load_progs(struct bpf_object *obj)
{
	size_t i;
	int err;

	for (i = 0; i < obj->nr_programs; i++) {
1633
		if (bpf_program__is_function_storage(&obj->programs[i], obj))
1634
			continue;
1635 1636 1637 1638 1639 1640 1641 1642 1643
		err = bpf_program__load(&obj->programs[i],
					obj->license,
					obj->kern_version);
		if (err)
			return err;
	}
	return 0;
}

1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655
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:
1656
	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
1657 1658 1659 1660 1661
	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:
1662
	case BPF_PROG_TYPE_LIRC_MODE2:
1663
	case BPF_PROG_TYPE_SK_REUSEPORT:
1664
	case BPF_PROG_TYPE_FLOW_DISSECTOR:
1665 1666 1667
	case BPF_PROG_TYPE_UNSPEC:
	case BPF_PROG_TYPE_TRACEPOINT:
	case BPF_PROG_TYPE_RAW_TRACEPOINT:
1668 1669 1670
	case BPF_PROG_TYPE_PERF_EVENT:
		return false;
	case BPF_PROG_TYPE_KPROBE:
1671 1672 1673 1674 1675 1676
	default:
		return true;
	}
}

static int bpf_object__validate(struct bpf_object *obj, bool needs_kver)
1677
{
1678
	if (needs_kver && obj->kern_version == 0) {
1679 1680
		pr_warning("%s doesn't provide kernel version\n",
			   obj->path);
1681
		return -LIBBPF_ERRNO__KVERSION;
1682 1683 1684 1685
	}
	return 0;
}

1686
static struct bpf_object *
1687
__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
1688
		   bool needs_kver, int flags)
1689 1690
{
	struct bpf_object *obj;
1691
	int err;
1692 1693 1694

	if (elf_version(EV_CURRENT) == EV_NONE) {
		pr_warning("failed to init libelf for %s\n", path);
1695
		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
1696 1697
	}

1698
	obj = bpf_object__new(path, obj_buf, obj_buf_sz);
1699 1700
	if (IS_ERR(obj))
		return obj;
1701

1702 1703
	CHECK_ERR(bpf_object__elf_init(obj), err, out);
	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
1704
	CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out);
1705
	CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
1706
	CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out);
1707 1708 1709 1710 1711

	bpf_object__elf_finish(obj);
	return obj;
out:
	bpf_object__close(obj);
1712
	return ERR_PTR(err);
1713 1714
}

1715 1716
struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
					    int flags)
1717 1718
{
	/* param validation */
1719
	if (!attr->file)
1720 1721
		return NULL;

1722 1723 1724
	pr_debug("loading %s\n", attr->file);

	return __bpf_object__open(attr->file, NULL, 0,
1725 1726 1727 1728 1729 1730 1731
				  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);
1732 1733 1734 1735 1736 1737 1738 1739
}

struct bpf_object *bpf_object__open(const char *path)
{
	struct bpf_object_open_attr attr = {
		.file		= path,
		.prog_type	= BPF_PROG_TYPE_UNSPEC,
	};
1740

1741
	return bpf_object__open_xattr(&attr);
1742 1743 1744
}

struct bpf_object *bpf_object__open_buffer(void *obj_buf,
1745 1746
					   size_t obj_buf_sz,
					   const char *name)
1747
{
1748 1749
	char tmp_name[64];

1750 1751 1752 1753
	/* param validation */
	if (!obj_buf || obj_buf_sz <= 0)
		return NULL;

1754 1755 1756 1757 1758 1759 1760 1761 1762
	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);
1763

1764
	return __bpf_object__open(name, obj_buf, obj_buf_sz, true, true);
1765 1766
}

1767 1768 1769 1770 1771 1772 1773
int bpf_object__unload(struct bpf_object *obj)
{
	size_t i;

	if (!obj)
		return -EINVAL;

1774 1775
	for (i = 0; i < obj->nr_maps; i++)
		zclose(obj->maps[i].fd);
1776

1777 1778 1779
	for (i = 0; i < obj->nr_programs; i++)
		bpf_program__unload(&obj->programs[i]);

1780 1781 1782 1783 1784
	return 0;
}

int bpf_object__load(struct bpf_object *obj)
{
1785 1786
	int err;

1787 1788 1789 1790 1791 1792 1793 1794 1795
	if (!obj)
		return -EINVAL;

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

	obj->loaded = true;
1796

1797
	CHECK_ERR(bpf_object__probe_caps(obj), err, out);
1798 1799 1800
	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);
1801 1802 1803 1804 1805

	return 0;
out:
	bpf_object__unload(obj);
	pr_warning("failed to load object '%s'\n", obj->path);
1806
	return err;
1807 1808
}

1809 1810
static int check_path(const char *path)
{
1811
	char *cp, errmsg[STRERR_BUFSIZE];
1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824
	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)) {
1825
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1826
		pr_warning("failed to statfs %s: %s\n", dir, cp);
1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841
		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)
{
1842
	char *cp, errmsg[STRERR_BUFSIZE];
1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860
	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)) {
1861
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1862
		pr_warning("failed to pin program: %s\n", cp);
1863 1864 1865 1866 1867 1868 1869
		return -errno;
	}
	pr_debug("pinned program '%s'\n", path);

	return 0;
}

1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897
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;
}

1898 1899
static int make_dir(const char *path)
{
1900
	char *cp, errmsg[STRERR_BUFSIZE];
1901 1902 1903 1904 1905
	int err = 0;

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

1906
	if (err) {
1907
		cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
1908 1909
		pr_warning("failed to mkdir %s: %s\n", path, cp);
	}
1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931
	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;
	}

1932 1933 1934 1935 1936
	if (prog->instances.nr == 1) {
		/* don't create subdirs when pinning single instance */
		return bpf_program__pin_instance(prog, path, 0);
	}

1937 1938 1939 1940
	err = make_dir(path);
	if (err)
		return err;

1941 1942 1943 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 1991 1992 1993 1994 1995 1996
	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;
1997 1998 1999 2000 2001
	}

	if (prog->instances.nr == 1) {
		/* don't create subdirs when pinning single instance */
		return bpf_program__unpin_instance(prog, path, 0);
2002 2003
	}

2004 2005 2006 2007 2008 2009 2010 2011 2012 2013
	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;

2014
		err = bpf_program__unpin_instance(prog, buf, i);
2015 2016 2017 2018
		if (err)
			return err;
	}

2019 2020 2021 2022
	err = rmdir(path);
	if (err)
		return -errno;

2023 2024 2025
	return 0;
}

J
Joe Stringer 已提交
2026 2027
int bpf_map__pin(struct bpf_map *map, const char *path)
{
2028
	char *cp, errmsg[STRERR_BUFSIZE];
J
Joe Stringer 已提交
2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040
	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)) {
2041
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
2042
		pr_warning("failed to pin map: %s\n", cp);
J
Joe Stringer 已提交
2043 2044 2045 2046
		return -errno;
	}

	pr_debug("pinned map '%s'\n", path);
2047

J
Joe Stringer 已提交
2048 2049 2050
	return 0;
}

2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072
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)
2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088
{
	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;

2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135
	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;

2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146
	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;

2147
		err = bpf_map__unpin(map, buf);
2148 2149 2150 2151
		if (err)
			return err;
	}

2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176
	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
2177
			       prog->pin_name);
2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198
		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
2199
			       prog->pin_name);
2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218
		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;

2219 2220 2221 2222 2223
	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
2224
			       prog->pin_name);
2225 2226 2227 2228 2229
		if (len < 0)
			return -EINVAL;
		else if (len >= PATH_MAX)
			return -ENAMETOOLONG;

2230
		err = bpf_program__unpin(prog, buf);
2231 2232 2233 2234 2235 2236 2237
		if (err)
			return err;
	}

	return 0;
}

2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254
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;
}

2255 2256
void bpf_object__close(struct bpf_object *obj)
{
2257 2258
	size_t i;

2259 2260 2261
	if (!obj)
		return;

2262 2263 2264
	if (obj->clear_priv)
		obj->clear_priv(obj, obj->priv);

2265
	bpf_object__elf_finish(obj);
2266
	bpf_object__unload(obj);
2267
	btf__free(obj->btf);
2268
	btf_ext__free(obj->btf_ext);
2269

2270
	for (i = 0; i < obj->nr_maps; i++) {
2271
		zfree(&obj->maps[i].name);
2272 2273 2274 2275 2276 2277 2278 2279
		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;
2280 2281 2282 2283 2284 2285 2286

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

2287
	list_del(&obj->list);
2288 2289
	free(obj);
}
2290

2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309
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;
}

2310
const char *bpf_object__name(struct bpf_object *obj)
2311
{
2312
	return obj ? obj->path : ERR_PTR(-EINVAL);
2313 2314
}

2315
unsigned int bpf_object__kversion(struct bpf_object *obj)
2316
{
2317
	return obj ? obj->kern_version : 0;
2318 2319
}

2320 2321 2322 2323 2324
int bpf_object__btf_fd(const struct bpf_object *obj)
{
	return obj->btf ? btf__fd(obj->btf) : -1;
}

2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340
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);
}

2341
static struct bpf_program *
2342
__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward)
2343
{
2344
	size_t nr_programs = obj->nr_programs;
2345
	ssize_t idx;
2346

2347
	if (!nr_programs)
2348 2349
		return NULL;

2350 2351 2352 2353 2354
	if (!p)
		/* Iter from the beginning */
		return forward ? &obj->programs[0] :
			&obj->programs[nr_programs - 1];

2355
	if (p->obj != obj) {
2356 2357 2358 2359
		pr_warning("error: program handler doesn't match object\n");
		return NULL;
	}

2360
	idx = (p - obj->programs) + (forward ? 1 : -1);
2361
	if (idx >= obj->nr_programs || idx < 0)
2362 2363 2364 2365
		return NULL;
	return &obj->programs[idx];
}

2366 2367 2368 2369 2370 2371
struct bpf_program *
bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
{
	struct bpf_program *prog = prev;

	do {
2372
		prog = __bpf_program__iter(prog, obj, true);
2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383
	} 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;

	do {
2384
		prog = __bpf_program__iter(prog, obj, false);
2385 2386 2387 2388 2389
	} while (prog && bpf_program__is_function_storage(prog, obj));

	return prog;
}

2390 2391
int bpf_program__set_priv(struct bpf_program *prog, void *priv,
			  bpf_program_clear_priv_t clear_priv)
2392 2393 2394 2395 2396 2397 2398 2399 2400
{
	if (prog->priv && prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

2401
void *bpf_program__priv(struct bpf_program *prog)
2402
{
2403
	return prog ? prog->priv : ERR_PTR(-EINVAL);
2404 2405
}

2406 2407 2408 2409 2410
void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex)
{
	prog->prog_ifindex = ifindex;
}

2411
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
2412 2413 2414 2415
{
	const char *title;

	title = prog->section_name;
2416
	if (needs_copy) {
2417 2418 2419
		title = strdup(title);
		if (!title) {
			pr_warning("failed to strdup program title\n");
2420
			return ERR_PTR(-ENOMEM);
2421 2422 2423 2424 2425 2426 2427 2428
		}
	}

	return title;
}

int bpf_program__fd(struct bpf_program *prog)
{
2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463
	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;

2464 2465 2466
	if (!prog)
		return -EINVAL;

2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480
	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;
2481
}
2482

2483
void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
2484 2485 2486 2487 2488 2489 2490 2491 2492 2493
{
	prog->type = type;
}

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

2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507
#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);	\
}							\

2508
BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
2509
BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
2510 2511
BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
2512
BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
2513
BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT);
2514 2515
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
2516

J
John Fastabend 已提交
2517 2518
void bpf_program__set_expected_attach_type(struct bpf_program *prog,
					   enum bpf_attach_type type)
2519 2520 2521 2522
{
	prog->expected_attach_type = type;
}

2523 2524
#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, atype) \
	{ string, sizeof(string) - 1, ptype, eatype, is_attachable, atype }
2525

2526
/* Programs that can NOT be attached. */
2527
#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0)
2528

2529 2530
/* Programs that can be attached. */
#define BPF_APROG_SEC(string, ptype, atype) \
2531
	BPF_PROG_SEC_IMPL(string, ptype, 0, 1, atype)
2532

2533 2534
/* Programs that must specify expected attach type at load time. */
#define BPF_EAPROG_SEC(string, ptype, eatype) \
2535
	BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, eatype)
2536 2537 2538 2539 2540

/* 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)
2541

2542 2543 2544 2545
static const struct {
	const char *sec;
	size_t len;
	enum bpf_prog_type prog_type;
2546
	enum bpf_attach_type expected_attach_type;
2547
	int is_attachable;
2548
	enum bpf_attach_type attach_type;
2549
} section_names[] = {
2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562
	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),
2563 2564 2565 2566
	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),
2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577
	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),
2578 2579 2580 2581
	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),
2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600
	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),
2601
};
2602

2603
#undef BPF_PROG_SEC_IMPL
2604
#undef BPF_PROG_SEC
2605 2606 2607
#undef BPF_APROG_SEC
#undef BPF_EAPROG_SEC
#undef BPF_APROG_COMPAT
2608

2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636
#define MAX_TYPE_NAME_SIZE 32

static char *libbpf_get_type_names(bool attach_type)
{
	int i, len = ARRAY_SIZE(section_names) * MAX_TYPE_NAME_SIZE;
	char *buf;

	buf = malloc(len);
	if (!buf)
		return NULL;

	buf[0] = '\0';
	/* Forge string buf with all available names */
	for (i = 0; i < ARRAY_SIZE(section_names); i++) {
		if (attach_type && !section_names[i].is_attachable)
			continue;

		if (strlen(buf) + strlen(section_names[i].sec) + 2 > len) {
			free(buf);
			return NULL;
		}
		strcat(buf, " ");
		strcat(buf, section_names[i].sec);
	}

	return buf;
}

2637 2638
int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
			     enum bpf_attach_type *expected_attach_type)
2639
{
2640
	char *type_names;
2641 2642
	int i;

2643 2644
	if (!name)
		return -EINVAL;
2645

2646 2647 2648 2649 2650 2651 2652
	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;
	}
2653 2654 2655 2656 2657 2658 2659
	pr_warning("failed to guess program type based on ELF section name '%s'\n", name);
	type_names = libbpf_get_type_names(false);
	if (type_names != NULL) {
		pr_info("supported section(type) names are:%s\n", type_names);
		free(type_names);
	}

2660 2661
	return -EINVAL;
}
2662

2663 2664 2665
int libbpf_attach_type_by_name(const char *name,
			       enum bpf_attach_type *attach_type)
{
2666
	char *type_names;
2667 2668 2669 2670 2671 2672 2673 2674
	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;
2675
		if (!section_names[i].is_attachable)
2676 2677 2678 2679
			return -EINVAL;
		*attach_type = section_names[i].attach_type;
		return 0;
	}
2680 2681 2682 2683 2684 2685 2686
	pr_warning("failed to guess attach type based on ELF section name '%s'\n", name);
	type_names = libbpf_get_type_names(true);
	if (type_names != NULL) {
		pr_info("attachable section(type) names are:%s\n", type_names);
		free(type_names);
	}

2687 2688 2689
	return -EINVAL;
}

2690 2691 2692 2693 2694 2695 2696
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);
2697 2698
}

2699
int bpf_map__fd(struct bpf_map *map)
2700
{
2701
	return map ? map->fd : -EINVAL;
2702 2703
}

2704
const struct bpf_map_def *bpf_map__def(struct bpf_map *map)
2705
{
2706
	return map ? &map->def : ERR_PTR(-EINVAL);
2707 2708
}

2709
const char *bpf_map__name(struct bpf_map *map)
2710
{
2711
	return map ? map->name : NULL;
2712 2713
}

2714
__u32 bpf_map__btf_key_type_id(const struct bpf_map *map)
2715
{
2716
	return map ? map->btf_key_type_id : 0;
2717 2718
}

2719
__u32 bpf_map__btf_value_type_id(const struct bpf_map *map)
2720
{
2721
	return map ? map->btf_value_type_id : 0;
2722 2723
}

2724 2725
int bpf_map__set_priv(struct bpf_map *map, void *priv,
		     bpf_map_clear_priv_t clear_priv)
2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739
{
	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;
}

2740
void *bpf_map__priv(struct bpf_map *map)
2741
{
2742
	return map ? map->priv : ERR_PTR(-EINVAL);
2743 2744
}

2745 2746 2747 2748 2749
bool bpf_map__is_offload_neutral(struct bpf_map *map)
{
	return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
}

2750 2751 2752 2753 2754
void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
{
	map->map_ifindex = ifindex;
}

2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768
int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd)
{
	if (!bpf_map_type__is_map_in_map(map->def.type)) {
		pr_warning("error: unsupported map type\n");
		return -EINVAL;
	}
	if (map->inner_map_fd != -1) {
		pr_warning("error: inner_map_fd already specified\n");
		return -EINVAL;
	}
	map->inner_map_fd = fd;
	return 0;
}

2769 2770
static struct bpf_map *
__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i)
2771
{
2772
	ssize_t idx;
2773 2774 2775 2776 2777 2778 2779 2780
	struct bpf_map *s, *e;

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

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

2781
	if ((m < s) || (m >= e)) {
2782 2783 2784 2785 2786
		pr_warning("error in %s: map handler doesn't belong to object\n",
			   __func__);
		return NULL;
	}

2787 2788
	idx = (m - obj->maps) + i;
	if (idx >= obj->nr_maps || idx < 0)
2789 2790 2791
		return NULL;
	return &obj->maps[idx];
}
2792

2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813
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);
}

2814
struct bpf_map *
2815
bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
2816 2817 2818 2819
{
	struct bpf_map *pos;

	bpf_map__for_each(pos, obj) {
2820
		if (pos->name && !strcmp(pos->name, name))
2821 2822 2823 2824
			return pos;
	}
	return NULL;
}
2825

2826 2827 2828 2829 2830 2831
int
bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name)
{
	return bpf_map__fd(bpf_object__find_map_by_name(obj, name));
}

2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842
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);
}
2843 2844 2845 2846 2847 2848 2849

long libbpf_get_error(const void *ptr)
{
	if (IS_ERR(ptr))
		return PTR_ERR(ptr);
	return 0;
}
2850 2851 2852

int bpf_prog_load(const char *file, enum bpf_prog_type type,
		  struct bpf_object **pobj, int *prog_fd)
2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865
{
	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)
2866
{
2867 2868 2869 2870
	struct bpf_object_open_attr open_attr = {
		.file		= attr->file,
		.prog_type	= attr->prog_type,
	};
2871
	struct bpf_program *prog, *first_prog = NULL;
2872 2873
	enum bpf_attach_type expected_attach_type;
	enum bpf_prog_type prog_type;
2874
	struct bpf_object *obj;
2875
	struct bpf_map *map;
2876 2877
	int err;

2878 2879
	if (!attr)
		return -EINVAL;
2880 2881
	if (!attr->file)
		return -EINVAL;
2882

2883
	obj = bpf_object__open_xattr(&open_attr);
2884
	if (IS_ERR_OR_NULL(obj))
2885 2886
		return -ENOENT;

2887 2888 2889 2890 2891
	bpf_object__for_each_program(prog, obj) {
		/*
		 * If type is not specified, try to guess it based on
		 * section name.
		 */
2892
		prog_type = attr->prog_type;
2893
		prog->prog_ifindex = attr->ifindex;
2894 2895
		expected_attach_type = attr->expected_attach_type;
		if (prog_type == BPF_PROG_TYPE_UNSPEC) {
2896 2897 2898
			err = bpf_program__identify_section(prog, &prog_type,
							    &expected_attach_type);
			if (err < 0) {
2899 2900 2901
				bpf_object__close(obj);
				return -EINVAL;
			}
2902
		}
2903

2904 2905 2906 2907
		bpf_program__set_type(prog, prog_type);
		bpf_program__set_expected_attach_type(prog,
						      expected_attach_type);

2908
		if (!first_prog)
2909 2910 2911
			first_prog = prog;
	}

2912
	bpf_map__for_each(map, obj) {
2913 2914
		if (!bpf_map__is_offload_neutral(map))
			map->map_ifindex = attr->ifindex;
2915 2916
	}

2917 2918 2919 2920
	if (!first_prog) {
		pr_warning("object file doesn't contain bpf program\n");
		bpf_object__close(obj);
		return -ENOENT;
2921 2922
	}

2923 2924 2925 2926 2927 2928 2929
	err = bpf_object__load(obj);
	if (err) {
		bpf_object__close(obj);
		return -EINVAL;
	}

	*pobj = obj;
2930
	*prog_fd = bpf_program__fd(first_prog);
2931 2932
	return 0;
}
2933 2934

enum bpf_perf_event_ret
2935 2936 2937
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)
2938
{
2939
	struct perf_event_mmap_page *header = mmap_mem;
2940
	__u64 data_head = ring_buffer_read_head(header);
2941
	__u64 data_tail = header->data_tail;
2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960
	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;
2961 2962 2963
					ret = LIBBPF_PERF_EVENT_ERROR;
					break;
				}
2964
				*copy_size = ehdr_size;
2965 2966
			}

2967 2968 2969
			memcpy(*copy_mem, copy_start, len_first);
			memcpy(*copy_mem + len_first, base, len_secnd);
			ehdr = *copy_mem;
2970 2971
		}

2972 2973
		ret = fn(ehdr, private_data);
		data_tail += ehdr_size;
2974 2975 2976 2977
		if (ret != LIBBPF_PERF_EVENT_CONT)
			break;
	}

2978
	ring_buffer_write_tail(header, data_tail);
2979 2980
	return ret;
}