libbpf.c 85.8 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
 * Copyright (C) 2019 Isovalent, Inc.
11 12
 */

13
#ifndef _GNU_SOURCE
14
#define _GNU_SOURCE
15
#endif
16
#include <stdlib.h>
17 18
#include <stdio.h>
#include <stdarg.h>
19
#include <libgen.h>
20
#include <inttypes.h>
21
#include <string.h>
22
#include <unistd.h>
23 24
#include <fcntl.h>
#include <errno.h>
25
#include <asm/unistd.h>
26
#include <linux/err.h>
27
#include <linux/kernel.h>
28
#include <linux/bpf.h>
29
#include <linux/btf.h>
30
#include <linux/filter.h>
31
#include <linux/list.h>
32
#include <linux/limits.h>
33
#include <linux/perf_event.h>
34
#include <linux/ring_buffer.h>
35 36 37
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/vfs.h>
38
#include <tools/libc_compat.h>
39 40
#include <libelf.h>
#include <gelf.h>
41 42

#include "libbpf.h"
43
#include "bpf.h"
44
#include "btf.h"
45
#include "str_error.h"
46
#include "libbpf_util.h"
47

48 49 50 51
#ifndef EM_BPF
#define EM_BPF 247
#endif

52 53 54 55
#ifndef BPF_FS_MAGIC
#define BPF_FS_MAGIC		0xcafe4a11
#endif

56 57 58 59 60
/* vsprintf() in __base_pr() uses nonliteral format string. It may break
 * compilation if user enables corresponding warning. Disable it explicitly.
 */
#pragma GCC diagnostic ignored "-Wformat-nonliteral"

61 62
#define __printf(a, b)	__attribute__((format(printf, a, b)))

S
Stanislav Fomichev 已提交
63 64
static int __base_pr(enum libbpf_print_level level, const char *format,
		     va_list args)
65
{
66 67 68
	if (level == LIBBPF_DEBUG)
		return 0;

S
Stanislav Fomichev 已提交
69
	return vfprintf(stderr, format, args);
70 71
}

S
Stanislav Fomichev 已提交
72
static libbpf_print_fn_t __libbpf_pr = __base_pr;
73

74
void libbpf_set_print(libbpf_print_fn_t fn)
75
{
76
	__libbpf_pr = fn;
77
}
78

79 80 81 82 83
__printf(2, 3)
void libbpf_print(enum libbpf_print_level level, const char *format, ...)
{
	va_list args;

84 85 86
	if (!__libbpf_pr)
		return;

87
	va_start(args, format);
88
	__libbpf_pr(level, format, args);
89 90 91
	va_end(args);
}

92 93 94 95 96 97 98 99 100
#define STRERR_BUFSIZE  128

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


101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120
/* 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

121 122 123 124 125
static inline __u64 ptr_to_u64(const void *ptr)
{
	return (__u64) (unsigned long) ptr;
}

126 127 128
struct bpf_capabilities {
	/* v4.14: kernel support for program & map names. */
	__u32 name:1;
129 130
	/* v5.2: kernel support for global data sections. */
	__u32 global_data:1;
131 132
};

133 134 135 136 137 138 139
/*
 * 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;
140
	char *name;
141
	int prog_ifindex;
142
	char *section_name;
S
Stanislav Fomichev 已提交
143 144 145 146
	/* section_name with / replaced by _; makes recursive pinning
	 * in bpf_object__pin_programs easier
	 */
	char *pin_name;
147
	struct bpf_insn *insns;
148
	size_t insns_cnt, main_prog_cnt;
149
	enum bpf_prog_type type;
150

151 152 153 154
	struct reloc_desc {
		enum {
			RELO_LD64,
			RELO_CALL,
155
			RELO_DATA,
156
		} type;
157
		int insn_idx;
158 159 160 161
		union {
			int map_idx;
			int text_off;
		};
162 163
	} *reloc_desc;
	int nr_reloc;
164
	int log_level;
165

166 167 168 169 170
	struct {
		int nr;
		int *fds;
	} instances;
	bpf_program_prep_t preprocessor;
171 172 173 174

	struct bpf_object *obj;
	void *priv;
	bpf_program_clear_priv_t clear_priv;
175 176

	enum bpf_attach_type expected_attach_type;
177 178 179
	int btf_fd;
	void *func_info;
	__u32 func_info_rec_size;
180
	__u32 func_info_cnt;
181 182

	struct bpf_capabilities *caps;
183 184 185 186

	void *line_info;
	__u32 line_info_rec_size;
	__u32 line_info_cnt;
187 188
};

189 190 191 192 193 194 195 196 197 198 199 200 201
enum libbpf_map_type {
	LIBBPF_MAP_UNSPEC,
	LIBBPF_MAP_DATA,
	LIBBPF_MAP_BSS,
	LIBBPF_MAP_RODATA,
};

static const char * const libbpf_type_to_btf_name[] = {
	[LIBBPF_MAP_DATA]	= ".data",
	[LIBBPF_MAP_BSS]	= ".bss",
	[LIBBPF_MAP_RODATA]	= ".rodata",
};

202 203
struct bpf_map {
	int fd;
204
	char *name;
E
Eric Leblond 已提交
205
	size_t offset;
206
	int map_ifindex;
207
	int inner_map_fd;
208
	struct bpf_map_def def;
209 210
	__u32 btf_key_type_id;
	__u32 btf_value_type_id;
211 212
	void *priv;
	bpf_map_clear_priv_t clear_priv;
213 214 215 216 217 218
	enum libbpf_map_type libbpf_type;
};

struct bpf_secdata {
	void *rodata;
	void *data;
219 220
};

221 222
static LIST_HEAD(bpf_objects_list);

223
struct bpf_object {
224
	char name[BPF_OBJ_NAME_LEN];
225
	char license[64];
226
	__u32 kern_version;
227

228 229
	struct bpf_program *programs;
	size_t nr_programs;
230 231
	struct bpf_map *maps;
	size_t nr_maps;
232
	struct bpf_secdata sections;
233

234
	bool loaded;
235
	bool has_pseudo_calls;
236

237 238 239 240 241 242
	/*
	 * Information when doing elf related work. Only valid if fd
	 * is valid.
	 */
	struct {
		int fd;
243 244
		void *obj_buf;
		size_t obj_buf_sz;
245 246
		Elf *elf;
		GElf_Ehdr ehdr;
247
		Elf_Data *symbols;
248 249 250
		Elf_Data *data;
		Elf_Data *rodata;
		Elf_Data *bss;
251
		size_t strtabidx;
252 253 254 255 256
		struct {
			GElf_Shdr shdr;
			Elf_Data *data;
		} *reloc;
		int nr_reloc;
257
		int maps_shndx;
258
		int text_shndx;
259 260 261
		int data_shndx;
		int rodata_shndx;
		int bss_shndx;
262
	} efile;
263 264 265 266 267 268
	/*
	 * 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;
269

270
	struct btf *btf;
271
	struct btf_ext *btf_ext;
272

273 274 275
	void *priv;
	bpf_object_clear_priv_t clear_priv;

276 277
	struct bpf_capabilities caps;

278 279 280 281
	char path[];
};
#define obj_elf_valid(o)	((o)->efile.elf)

282
void bpf_program__unload(struct bpf_program *prog)
283
{
284 285
	int i;

286 287 288
	if (!prog)
		return;

289 290 291 292 293 294 295 296 297 298 299 300 301 302
	/*
	 * 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);
303 304 305

	zclose(prog->btf_fd);
	zfree(&prog->func_info);
306
	zfree(&prog->line_info);
307 308
}

309 310 311 312 313
static void bpf_program__exit(struct bpf_program *prog)
{
	if (!prog)
		return;

314 315 316 317 318 319
	if (prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

320
	bpf_program__unload(prog);
321
	zfree(&prog->name);
322
	zfree(&prog->section_name);
S
Stanislav Fomichev 已提交
323
	zfree(&prog->pin_name);
324
	zfree(&prog->insns);
325 326 327
	zfree(&prog->reloc_desc);

	prog->nr_reloc = 0;
328 329 330 331
	prog->insns_cnt = 0;
	prog->idx = -1;
}

S
Stanislav Fomichev 已提交
332 333 334 335 336 337 338 339 340 341 342
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;
}

343
static int
344 345
bpf_program__init(void *data, size_t size, char *section_name, int idx,
		  struct bpf_program *prog)
346 347
{
	if (size < sizeof(struct bpf_insn)) {
348
		pr_warning("corrupted section '%s'\n", section_name);
349 350 351
		return -EINVAL;
	}

352
	memset(prog, 0, sizeof(*prog));
353

354
	prog->section_name = strdup(section_name);
355
	if (!prog->section_name) {
356 357
		pr_warning("failed to alloc name for prog under section(%d) %s\n",
			   idx, section_name);
358 359 360
		goto errout;
	}

S
Stanislav Fomichev 已提交
361 362 363 364 365 366 367
	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;
	}

368 369
	prog->insns = malloc(size);
	if (!prog->insns) {
370 371
		pr_warning("failed to alloc insns for prog under section %s\n",
			   section_name);
372 373 374 375 376 377
		goto errout;
	}
	prog->insns_cnt = size / sizeof(struct bpf_insn);
	memcpy(prog->insns, data,
	       prog->insns_cnt * sizeof(struct bpf_insn));
	prog->idx = idx;
378 379
	prog->instances.fds = NULL;
	prog->instances.nr = -1;
380
	prog->type = BPF_PROG_TYPE_UNSPEC;
381
	prog->btf_fd = -1;
382 383 384 385 386 387 388 389 390

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

static int
bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
391
			char *section_name, int idx)
392 393 394 395
{
	struct bpf_program prog, *progs;
	int nr_progs, err;

396
	err = bpf_program__init(data, size, section_name, idx, &prog);
397 398 399
	if (err)
		return err;

400
	prog.caps = &obj->caps;
401 402 403
	progs = obj->programs;
	nr_progs = obj->nr_programs;

404
	progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
405 406 407 408 409 410
	if (!progs) {
		/*
		 * In this case the original obj->programs
		 * is still valid, so don't need special treat for
		 * bpf_close_object().
		 */
411 412
		pr_warning("failed to alloc a new program under section '%s'\n",
			   section_name);
413 414 415 416 417 418 419
		bpf_program__exit(&prog);
		return -ENOMEM;
	}

	pr_debug("found program %s\n", prog.section_name);
	obj->programs = progs;
	obj->nr_programs = nr_progs + 1;
420
	prog.obj = obj;
421 422 423 424
	progs[nr_progs] = prog;
	return 0;
}

425 426 427 428 429 430 431 432
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++) {
433
		const char *name = NULL;
434 435 436 437 438 439 440 441 442 443 444

		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;
445 446
			if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL)
				continue;
447 448 449 450 451 452 453 454 455 456 457

			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;
			}
		}

458 459 460
		if (!name && prog->idx == obj->efile.text_shndx)
			name = ".text";

461 462 463 464 465
		if (!name) {
			pr_warning("failed to find sym for prog %s\n",
				   prog->section_name);
			return -EINVAL;
		}
466

467 468 469 470 471 472 473 474 475 476 477
		prog->name = strdup(name);
		if (!prog->name) {
			pr_warning("failed to allocate memory for prog sym %s\n",
				   name);
			return -ENOMEM;
		}
	}

	return 0;
}

478 479 480
static struct bpf_object *bpf_object__new(const char *path,
					  void *obj_buf,
					  size_t obj_buf_sz)
481 482
{
	struct bpf_object *obj;
483
	char *end;
484 485 486 487

	obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1);
	if (!obj) {
		pr_warning("alloc memory failed for %s\n", path);
488
		return ERR_PTR(-ENOMEM);
489 490 491
	}

	strcpy(obj->path, path);
492 493 494 495 496 497
	/* Using basename() GNU version which doesn't modify arg. */
	strncpy(obj->name, basename((void *)path),
		sizeof(obj->name) - 1);
	end = strchr(obj->name, '.');
	if (end)
		*end = 0;
498

499
	obj->efile.fd = -1;
500 501 502 503 504 505 506 507
	/*
	 * 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;
508
	obj->efile.maps_shndx = -1;
509 510 511
	obj->efile.data_shndx = -1;
	obj->efile.rodata_shndx = -1;
	obj->efile.bss_shndx = -1;
512

513
	obj->loaded = false;
514 515 516

	INIT_LIST_HEAD(&obj->list);
	list_add(&obj->list, &bpf_objects_list);
517 518 519 520 521 522 523 524 525 526 527 528
	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;
	}
529
	obj->efile.symbols = NULL;
530 531 532
	obj->efile.data = NULL;
	obj->efile.rodata = NULL;
	obj->efile.bss = NULL;
533 534 535

	zfree(&obj->efile.reloc);
	obj->efile.nr_reloc = 0;
536
	zclose(obj->efile.fd);
537 538
	obj->efile.obj_buf = NULL;
	obj->efile.obj_buf_sz = 0;
539 540 541 542 543 544 545 546 547
}

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");
548
		return -LIBBPF_ERRNO__LIBELF;
549 550
	}

551 552 553 554 555 556 557 558 559 560
	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) {
561
			char errmsg[STRERR_BUFSIZE];
562 563
			char *cp = libbpf_strerror_r(errno, errmsg,
						     sizeof(errmsg));
564 565

			pr_warning("failed to open %s: %s\n", obj->path, cp);
566 567 568 569 570 571
			return -errno;
		}

		obj->efile.elf = elf_begin(obj->efile.fd,
				LIBBPF_ELF_C_READ_MMAP,
				NULL);
572 573 574 575 576
	}

	if (!obj->efile.elf) {
		pr_warning("failed to open %s as ELF file\n",
				obj->path);
577
		err = -LIBBPF_ERRNO__LIBELF;
578 579 580 581 582 583
		goto errout;
	}

	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
		pr_warning("failed to get EHDR from %s\n",
				obj->path);
584
		err = -LIBBPF_ERRNO__FORMAT;
585 586 587 588
		goto errout;
	}
	ep = &obj->efile.ehdr;

589 590
	/* Old LLVM set e_machine to EM_NONE */
	if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) {
591 592
		pr_warning("%s is not an eBPF object file\n",
			obj->path);
593
		err = -LIBBPF_ERRNO__FORMAT;
594 595 596 597 598 599 600 601 602
		goto errout;
	}

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

603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620
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:
621
		return -LIBBPF_ERRNO__ENDIAN;
622 623 624 625 626 627
	}

	return 0;

mismatch:
	pr_warning("Error: endianness mismatch.\n");
628
	return -LIBBPF_ERRNO__ENDIAN;
629 630
}

631 632 633 634 635 636 637 638 639 640 641 642 643 644
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)
{
645
	__u32 kver;
646 647 648

	if (size != sizeof(kver)) {
		pr_warning("invalid kver section in %s\n", obj->path);
649
		return -LIBBPF_ERRNO__FORMAT;
650 651 652 653 654 655 656 657
	}
	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
658 659 660 661
static int compare_bpf_map(const void *_a, const void *_b)
{
	const struct bpf_map *a = _a;
	const struct bpf_map *b = _b;
662

E
Eric Leblond 已提交
663
	return a->offset - b->offset;
664 665
}

666 667 668 669 670 671 672 673
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;
}

674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779
static int bpf_object_search_section_size(const struct bpf_object *obj,
					  const char *name, size_t *d_size)
{
	const GElf_Ehdr *ep = &obj->efile.ehdr;
	Elf *elf = obj->efile.elf;
	Elf_Scn *scn = NULL;
	int idx = 0;

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

		idx++;
		if (gelf_getshdr(scn, &sh) != &sh) {
			pr_warning("failed to get section(%d) header from %s\n",
				   idx, obj->path);
			return -EIO;
		}

		sec_name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
		if (!sec_name) {
			pr_warning("failed to get section(%d) name from %s\n",
				   idx, obj->path);
			return -EIO;
		}

		if (strcmp(name, sec_name))
			continue;

		data = elf_getdata(scn, 0);
		if (!data) {
			pr_warning("failed to get section(%d) data from %s(%s)\n",
				   idx, name, obj->path);
			return -EIO;
		}

		*d_size = data->d_size;
		return 0;
	}

	return -ENOENT;
}

int bpf_object__section_size(const struct bpf_object *obj, const char *name,
			     __u32 *size)
{
	int ret = -ENOENT;
	size_t d_size;

	*size = 0;
	if (!name) {
		return -EINVAL;
	} else if (!strcmp(name, ".data")) {
		if (obj->efile.data)
			*size = obj->efile.data->d_size;
	} else if (!strcmp(name, ".bss")) {
		if (obj->efile.bss)
			*size = obj->efile.bss->d_size;
	} else if (!strcmp(name, ".rodata")) {
		if (obj->efile.rodata)
			*size = obj->efile.rodata->d_size;
	} else {
		ret = bpf_object_search_section_size(obj, name, &d_size);
		if (!ret)
			*size = d_size;
	}

	return *size ? 0 : ret;
}

int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
				__u32 *off)
{
	Elf_Data *symbols = obj->efile.symbols;
	const char *sname;
	size_t si;

	if (!name || !off)
		return -EINVAL;

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

		if (!gelf_getsym(symbols, si, &sym))
			continue;
		if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL ||
		    GELF_ST_TYPE(sym.st_info) != STT_OBJECT)
			continue;

		sname = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
				   sym.st_name);
		if (!sname) {
			pr_warning("failed to get sym name string for var %s\n",
				   name);
			return -EIO;
		}
		if (strcmp(name, sname) == 0) {
			*off = sym.st_value;
			return 0;
		}
	}

	return -ENOENT;
}

780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821
static bool bpf_object__has_maps(const struct bpf_object *obj)
{
	return obj->efile.maps_shndx >= 0 ||
	       obj->efile.data_shndx >= 0 ||
	       obj->efile.rodata_shndx >= 0 ||
	       obj->efile.bss_shndx >= 0;
}

static int
bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map,
			      enum libbpf_map_type type, Elf_Data *data,
			      void **data_buff)
{
	struct bpf_map_def *def = &map->def;
	char map_name[BPF_OBJ_NAME_LEN];

	map->libbpf_type = type;
	map->offset = ~(typeof(map->offset))0;
	snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name,
		 libbpf_type_to_btf_name[type]);
	map->name = strdup(map_name);
	if (!map->name) {
		pr_warning("failed to alloc map name\n");
		return -ENOMEM;
	}

	def->type = BPF_MAP_TYPE_ARRAY;
	def->key_size = sizeof(int);
	def->value_size = data->d_size;
	def->max_entries = 1;
	def->map_flags = type == LIBBPF_MAP_RODATA ?
			 BPF_F_RDONLY_PROG : 0;
	if (data_buff) {
		*data_buff = malloc(data->d_size);
		if (!*data_buff) {
			zfree(&map->name);
			pr_warning("failed to alloc map content buffer\n");
			return -ENOMEM;
		}
		memcpy(*data_buff, data->d_buf, data->d_size);
	}

822
	pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name);
823 824 825
	return 0;
}

826
static int
827
bpf_object__init_maps(struct bpf_object *obj, int flags)
828
{
A
Andrey Ignatov 已提交
829
	int i, map_idx, map_def_sz = 0, nr_syms, nr_maps = 0, nr_maps_glob = 0;
830
	bool strict = !(flags & MAPS_RELAX_COMPAT);
831
	Elf_Data *symbols = obj->efile.symbols;
832 833
	Elf_Data *data = NULL;
	int ret = 0;
834

E
Eric Leblond 已提交
835 836
	if (!symbols)
		return -EINVAL;
837
	nr_syms = symbols->d_size / sizeof(GElf_Sym);
E
Eric Leblond 已提交
838

839 840 841 842 843 844 845 846 847 848 849
	if (obj->efile.maps_shndx >= 0) {
		Elf_Scn *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);
			return -EINVAL;
		}
E
Eric Leblond 已提交
850
	}
851

E
Eric Leblond 已提交
852 853 854 855 856 857 858
	/*
	 * 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.
	 */
859 860 861 862 863 864 865 866 867
	if (obj->caps.global_data) {
		if (obj->efile.data_shndx >= 0)
			nr_maps_glob++;
		if (obj->efile.rodata_shndx >= 0)
			nr_maps_glob++;
		if (obj->efile.bss_shndx >= 0)
			nr_maps_glob++;
	}

868
	for (i = 0; data && i < nr_syms; i++) {
869
		GElf_Sym sym;
E
Eric Leblond 已提交
870 871 872 873 874 875 876 877 878 879 880

		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);
881
	if (!nr_maps && !nr_maps_glob)
E
Eric Leblond 已提交
882 883
		return 0;

884
	/* Assume equally sized map definitions */
885 886 887 888 889 890 891 892
	if (data) {
		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;
		}
893 894
	}

895
	nr_maps += nr_maps_glob;
E
Eric Leblond 已提交
896 897 898 899 900 901 902
	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;

903 904 905 906 907 908
	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
909
		obj->maps[i].fd = -1;
910 911
		obj->maps[i].inner_map_fd = -1;
	}
E
Eric Leblond 已提交
912 913 914 915

	/*
	 * Fill obj->maps using data in "maps" section.
	 */
916
	for (i = 0, map_idx = 0; data && i < nr_syms; i++) {
E
Eric Leblond 已提交
917
		GElf_Sym sym;
918
		const char *map_name;
E
Eric Leblond 已提交
919
		struct bpf_map_def *def;
920 921 922

		if (!gelf_getsym(symbols, i, &sym))
			continue;
923
		if (sym.st_shndx != obj->efile.maps_shndx)
924 925 926
			continue;

		map_name = elf_strptr(obj->efile.elf,
927
				      obj->efile.strtabidx,
928
				      sym.st_name);
929 930

		obj->maps[map_idx].libbpf_type = LIBBPF_MAP_UNSPEC;
E
Eric Leblond 已提交
931
		obj->maps[map_idx].offset = sym.st_value;
932
		if (sym.st_value + map_def_sz > data->d_size) {
E
Eric Leblond 已提交
933 934 935
			pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
				   obj->path, map_name);
			return -EINVAL;
936
		}
E
Eric Leblond 已提交
937

938
		obj->maps[map_idx].name = strdup(map_name);
939 940 941 942
		if (!obj->maps[map_idx].name) {
			pr_warning("failed to alloc map name\n");
			return -ENOMEM;
		}
E
Eric Leblond 已提交
943
		pr_debug("map %d is \"%s\"\n", map_idx,
944
			 obj->maps[map_idx].name);
E
Eric Leblond 已提交
945
		def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968
		/*
		 * 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);
969 970
					if (strict)
						return -EINVAL;
971 972 973 974 975
				}
			}
			memcpy(&obj->maps[map_idx].def, def,
			       sizeof(struct bpf_map_def));
		}
E
Eric Leblond 已提交
976
		map_idx++;
977
	}
E
Eric Leblond 已提交
978

979 980 981
	if (!obj->caps.global_data)
		goto finalize;

982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998
	/*
	 * Populate rest of obj->maps with libbpf internal maps.
	 */
	if (obj->efile.data_shndx >= 0)
		ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
						    LIBBPF_MAP_DATA,
						    obj->efile.data,
						    &obj->sections.data);
	if (!ret && obj->efile.rodata_shndx >= 0)
		ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
						    LIBBPF_MAP_RODATA,
						    obj->efile.rodata,
						    &obj->sections.rodata);
	if (!ret && obj->efile.bss_shndx >= 0)
		ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
						    LIBBPF_MAP_BSS,
						    obj->efile.bss, NULL);
999
finalize:
1000 1001 1002 1003
	if (!ret)
		qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]),
		      compare_bpf_map);
	return ret;
1004 1005
}

1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023
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;
}

1024
static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
1025 1026 1027
{
	Elf *elf = obj->efile.elf;
	GElf_Ehdr *ep = &obj->efile.ehdr;
1028
	Elf_Data *btf_ext_data = NULL;
1029
	Elf_Data *btf_data = NULL;
1030
	Elf_Scn *scn = NULL;
1031
	int idx = 0, err = 0;
1032 1033 1034 1035 1036

	/* 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);
1037
		return -LIBBPF_ERRNO__FORMAT;
1038 1039 1040 1041 1042 1043 1044 1045 1046
	}

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

		idx++;
		if (gelf_getshdr(scn, &sh) != &sh) {
1047 1048
			pr_warning("failed to get section(%d) header from %s\n",
				   idx, obj->path);
1049
			err = -LIBBPF_ERRNO__FORMAT;
1050 1051 1052 1053 1054
			goto out;
		}

		name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
		if (!name) {
1055 1056
			pr_warning("failed to get section(%d) name from %s\n",
				   idx, obj->path);
1057
			err = -LIBBPF_ERRNO__FORMAT;
1058 1059 1060 1061 1062
			goto out;
		}

		data = elf_getdata(scn, 0);
		if (!data) {
1063 1064
			pr_warning("failed to get section(%d) data from %s(%s)\n",
				   idx, name, obj->path);
1065
			err = -LIBBPF_ERRNO__FORMAT;
1066 1067
			goto out;
		}
1068 1069
		pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n",
			 idx, name, (unsigned long)data->d_size,
1070 1071
			 (int)sh.sh_link, (unsigned long)sh.sh_flags,
			 (int)sh.sh_type);
1072

1073
		if (strcmp(name, "license") == 0) {
1074 1075 1076
			err = bpf_object__init_license(obj,
						       data->d_buf,
						       data->d_size);
1077
		} else if (strcmp(name, "version") == 0) {
1078 1079 1080
			err = bpf_object__init_kversion(obj,
							data->d_buf,
							data->d_size);
1081
		} else if (strcmp(name, "maps") == 0) {
1082
			obj->efile.maps_shndx = idx;
1083 1084
		} else if (strcmp(name, BTF_ELF_SEC) == 0) {
			btf_data = data;
1085
		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
1086
			btf_ext_data = data;
1087
		} else if (sh.sh_type == SHT_SYMTAB) {
1088 1089 1090
			if (obj->efile.symbols) {
				pr_warning("bpf: multiple SYMTAB in %s\n",
					   obj->path);
1091
				err = -LIBBPF_ERRNO__FORMAT;
1092
			} else {
1093
				obj->efile.symbols = data;
1094 1095
				obj->efile.strtabidx = sh.sh_link;
			}
1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109
		} else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) {
			if (sh.sh_flags & SHF_EXECINSTR) {
				if (strcmp(name, ".text") == 0)
					obj->efile.text_shndx = idx;
				err = bpf_object__add_program(obj, data->d_buf,
							      data->d_size, name, idx);
				if (err) {
					char errmsg[STRERR_BUFSIZE];
					char *cp = libbpf_strerror_r(-err, errmsg,
								     sizeof(errmsg));

					pr_warning("failed to alloc program %s (%s): %s",
						   name, obj->path, cp);
				}
1110 1111 1112 1113 1114 1115 1116 1117
			} else if (strcmp(name, ".data") == 0) {
				obj->efile.data = data;
				obj->efile.data_shndx = idx;
			} else if (strcmp(name, ".rodata") == 0) {
				obj->efile.rodata = data;
				obj->efile.rodata_shndx = idx;
			} else {
				pr_debug("skip section(%d) %s\n", idx, name);
1118
			}
1119 1120 1121
		} else if (sh.sh_type == SHT_REL) {
			void *reloc = obj->efile.reloc;
			int nr_reloc = obj->efile.nr_reloc + 1;
1122 1123 1124 1125 1126 1127 1128 1129
			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;
			}
1130

1131 1132
			reloc = reallocarray(reloc, nr_reloc,
					     sizeof(*obj->efile.reloc));
1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144
			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;
			}
1145 1146 1147
		} else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) {
			obj->efile.bss = data;
			obj->efile.bss_shndx = idx;
1148 1149
		} else {
			pr_debug("skip section(%d) %s\n", idx, name);
1150
		}
1151 1152
		if (err)
			goto out;
1153
	}
1154

1155 1156 1157 1158
	if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
		pr_warning("Corrupted ELF file: index of strtab invalid\n");
		return LIBBPF_ERRNO__FORMAT;
	}
1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177
	if (btf_data) {
		obj->btf = btf__new(btf_data->d_buf, btf_data->d_size);
		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 {
			err = btf__finalize_data(obj, obj->btf);
			if (!err)
				err = btf__load(obj->btf);
			if (err) {
				pr_warning("Error finalizing and loading %s into kernel: %d. Ignored and continue.\n",
					   BTF_ELF_SEC, err);
				btf__free(obj->btf);
				obj->btf = NULL;
				err = 0;
			}
		}
	}
1178 1179 1180 1181 1182 1183
	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,
1184
						    btf_ext_data->d_size);
1185 1186 1187 1188 1189 1190 1191 1192
			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;
			}
		}
	}
1193
	if (bpf_object__has_maps(obj)) {
1194
		err = bpf_object__init_maps(obj, flags);
1195 1196 1197 1198
		if (err)
			goto out;
	}
	err = bpf_object__init_prog_names(obj);
1199 1200 1201 1202
out:
	return err;
}

1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216
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;
}

1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228
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;
}

1229 1230 1231 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
static bool bpf_object__shndx_is_data(const struct bpf_object *obj,
				      int shndx)
{
	return shndx == obj->efile.data_shndx ||
	       shndx == obj->efile.bss_shndx ||
	       shndx == obj->efile.rodata_shndx;
}

static bool bpf_object__shndx_is_maps(const struct bpf_object *obj,
				      int shndx)
{
	return shndx == obj->efile.maps_shndx;
}

static bool bpf_object__relo_in_known_section(const struct bpf_object *obj,
					      int shndx)
{
	return shndx == obj->efile.text_shndx ||
	       bpf_object__shndx_is_maps(obj, shndx) ||
	       bpf_object__shndx_is_data(obj, shndx);
}

static enum libbpf_map_type
bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx)
{
	if (shndx == obj->efile.data_shndx)
		return LIBBPF_MAP_DATA;
	else if (shndx == obj->efile.bss_shndx)
		return LIBBPF_MAP_BSS;
	else if (shndx == obj->efile.rodata_shndx)
		return LIBBPF_MAP_RODATA;
	else
		return LIBBPF_MAP_UNSPEC;
}

1264
static int
1265 1266
bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
			   Elf_Data *data, struct bpf_object *obj)
1267
{
1268 1269 1270
	Elf_Data *symbols = obj->efile.symbols;
	struct bpf_map *maps = obj->maps;
	size_t nr_maps = obj->nr_maps;
1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287
	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;
1288
		unsigned int shdr_idx;
1289
		struct bpf_insn *insns = prog->insns;
1290 1291
		enum libbpf_map_type type;
		const char *name;
1292 1293 1294 1295
		size_t map_idx;

		if (!gelf_getrel(data, i, &rel)) {
			pr_warning("relocation: failed to get %d reloc\n", i);
1296
			return -LIBBPF_ERRNO__FORMAT;
1297 1298 1299 1300 1301 1302 1303
		}

		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));
1304
			return -LIBBPF_ERRNO__FORMAT;
1305
		}
1306 1307 1308 1309 1310

		name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
				  sym.st_name) ? : "<?>";

		pr_debug("relo for %lld value %lld name %d (\'%s\')\n",
D
David Miller 已提交
1311
			 (long long) (rel.r_info >> 32),
1312
			 (long long) sym.st_value, sym.st_name, name);
1313

1314 1315 1316 1317
		shdr_idx = sym.st_shndx;
		if (!bpf_object__relo_in_known_section(obj, shdr_idx)) {
			pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n",
				   prog->section_name, shdr_idx);
1318 1319 1320 1321 1322 1323
			return -LIBBPF_ERRNO__RELOC;
		}

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

1324 1325 1326 1327 1328 1329 1330 1331
		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;
1332
			obj->has_pseudo_calls = true;
1333 1334 1335
			continue;
		}

1336 1337 1338
		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);
1339
			return -LIBBPF_ERRNO__RELOC;
1340 1341
		}

1342 1343 1344
		if (bpf_object__shndx_is_maps(obj, shdr_idx) ||
		    bpf_object__shndx_is_data(obj, shdr_idx)) {
			type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx);
1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355
			if (type != LIBBPF_MAP_UNSPEC) {
				if (GELF_ST_BIND(sym.st_info) == STB_GLOBAL) {
					pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n",
						   name, insn_idx, insns[insn_idx].code);
					return -LIBBPF_ERRNO__RELOC;
				}
				if (!obj->caps.global_data) {
					pr_warning("bpf: relocation: kernel does not support global \'%s\' variable access in insns[%d]\n",
						   name, insn_idx);
					return -LIBBPF_ERRNO__RELOC;
				}
1356 1357
			}

1358
			for (map_idx = 0; map_idx < nr_maps; map_idx++) {
1359 1360 1361 1362 1363
				if (maps[map_idx].libbpf_type != type)
					continue;
				if (type != LIBBPF_MAP_UNSPEC ||
				    (type == LIBBPF_MAP_UNSPEC &&
				     maps[map_idx].offset == sym.st_value)) {
1364 1365 1366 1367
					pr_debug("relocation: find map %zd (%s) for insn %u\n",
						 map_idx, maps[map_idx].name, insn_idx);
					break;
				}
1368 1369
			}

1370 1371 1372 1373 1374
			if (map_idx >= nr_maps) {
				pr_warning("bpf relocation: map_idx %d large than %d\n",
					   (int)map_idx, (int)nr_maps - 1);
				return -LIBBPF_ERRNO__RELOC;
			}
1375

1376 1377
			prog->reloc_desc[i].type = type != LIBBPF_MAP_UNSPEC ?
						   RELO_DATA : RELO_LD64;
1378 1379 1380
			prog->reloc_desc[i].insn_idx = insn_idx;
			prog->reloc_desc[i].map_idx = map_idx;
		}
1381 1382 1383 1384
	}
	return 0;
}

1385 1386 1387
static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
{
	struct bpf_map_def *def = &map->def;
1388
	__u32 key_type_id = 0, value_type_id = 0;
1389
	int ret;
1390

1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403
	if (!bpf_map__is_internal(map)) {
		ret = btf__get_map_kv_tids(btf, map->name, def->key_size,
					   def->value_size, &key_type_id,
					   &value_type_id);
	} else {
		/*
		 * LLVM annotates global data differently in BTF, that is,
		 * only as '.data', '.bss' or '.rodata'.
		 */
		ret = btf__find_by_name(btf,
				libbpf_type_to_btf_name[map->libbpf_type]);
	}
	if (ret < 0)
1404
		return ret;
1405

1406
	map->btf_key_type_id = key_type_id;
1407 1408
	map->btf_value_type_id = bpf_map__is_internal(map) ?
				 ret : value_type_id;
1409 1410 1411
	return 0;
}

J
Jakub Kicinski 已提交
1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 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 1451 1452 1453 1454 1455 1456 1457 1458
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;
}

1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472
int bpf_map__resize(struct bpf_map *map, __u32 max_entries)
{
	if (!map || !max_entries)
		return -EINVAL;

	/* If map already created, its attributes can't be changed. */
	if (map->fd >= 0)
		return -EBUSY;

	map->def.max_entries = max_entries;

	return 0;
}

1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512
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;
}

1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558
static int
bpf_object__probe_global_data(struct bpf_object *obj)
{
	struct bpf_load_program_attr prg_attr;
	struct bpf_create_map_attr map_attr;
	char *cp, errmsg[STRERR_BUFSIZE];
	struct bpf_insn insns[] = {
		BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16),
		BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
		BPF_MOV64_IMM(BPF_REG_0, 0),
		BPF_EXIT_INSN(),
	};
	int ret, map;

	memset(&map_attr, 0, sizeof(map_attr));
	map_attr.map_type = BPF_MAP_TYPE_ARRAY;
	map_attr.key_size = sizeof(int);
	map_attr.value_size = 32;
	map_attr.max_entries = 1;

	map = bpf_create_map_xattr(&map_attr);
	if (map < 0) {
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
		pr_warning("Error in %s():%s(%d). Couldn't create simple array map.\n",
			   __func__, cp, errno);
		return -errno;
	}

	insns[0].imm = map;

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

	ret = bpf_load_program_xattr(&prg_attr, NULL, 0);
	if (ret >= 0) {
		obj->caps.global_data = 1;
		close(ret);
	}

	close(map);
	return 0;
}

1559 1560 1561
static int
bpf_object__probe_caps(struct bpf_object *obj)
{
1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574
	int (*probe_fn[])(struct bpf_object *obj) = {
		bpf_object__probe_name,
		bpf_object__probe_global_data,
	};
	int i, ret;

	for (i = 0; i < ARRAY_SIZE(probe_fn); i++) {
		ret = probe_fn[i](obj);
		if (ret < 0)
			return ret;
	}

	return 0;
1575 1576
}

1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604
static int
bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
{
	char *cp, errmsg[STRERR_BUFSIZE];
	int err, zero = 0;
	__u8 *data;

	/* Nothing to do here since kernel already zero-initializes .bss map. */
	if (map->libbpf_type == LIBBPF_MAP_BSS)
		return 0;

	data = map->libbpf_type == LIBBPF_MAP_DATA ?
	       obj->sections.data : obj->sections.rodata;

	err = bpf_map_update_elem(map->fd, &zero, data, 0);
	/* Freeze .rodata map as read-only from syscall side. */
	if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) {
		err = bpf_map_freeze(map->fd);
		if (err) {
			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
			pr_warning("Error freezing map(%s) as read-only: %s\n",
				   map->name, cp);
			err = 0;
		}
	}
	return err;
}

1605 1606 1607
static int
bpf_object__create_maps(struct bpf_object *obj)
{
1608
	struct bpf_create_map_attr create_attr = {};
1609
	unsigned int i;
1610
	int err;
1611

1612
	for (i = 0; i < obj->nr_maps; i++) {
1613 1614
		struct bpf_map *map = &obj->maps[i];
		struct bpf_map_def *def = &map->def;
1615
		char *cp, errmsg[STRERR_BUFSIZE];
1616 1617
		int *pfd = &map->fd;

J
Jakub Kicinski 已提交
1618 1619 1620 1621 1622 1623
		if (map->fd >= 0) {
			pr_debug("skip map create (preset) %s: fd=%d\n",
				 map->name, map->fd);
			continue;
		}

1624 1625
		if (obj->caps.name)
			create_attr.name = map->name;
1626
		create_attr.map_ifindex = map->map_ifindex;
1627 1628 1629 1630 1631 1632
		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;
1633 1634
		create_attr.btf_key_type_id = 0;
		create_attr.btf_value_type_id = 0;
1635 1636 1637
		if (bpf_map_type__is_map_in_map(def->type) &&
		    map->inner_map_fd >= 0)
			create_attr.inner_map_fd = map->inner_map_fd;
1638 1639 1640

		if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) {
			create_attr.btf_fd = btf__fd(obj->btf);
1641 1642
			create_attr.btf_key_type_id = map->btf_key_type_id;
			create_attr.btf_value_type_id = map->btf_value_type_id;
1643 1644 1645
		}

		*pfd = bpf_create_map_xattr(&create_attr);
1646
		if (*pfd < 0 && create_attr.btf_key_type_id) {
1647
			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1648
			pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
1649
				   map->name, cp, errno);
1650
			create_attr.btf_fd = 0;
1651 1652 1653 1654
			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;
1655 1656 1657
			*pfd = bpf_create_map_xattr(&create_attr);
		}

1658 1659 1660
		if (*pfd < 0) {
			size_t j;

1661
			err = *pfd;
1662
err_out:
1663
			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
E
Eric Leblond 已提交
1664
			pr_warning("failed to create map (name: '%s'): %s\n",
1665
				   map->name, cp);
1666
			for (j = 0; j < i; j++)
1667
				zclose(obj->maps[j].fd);
1668 1669
			return err;
		}
1670 1671 1672 1673 1674 1675 1676 1677 1678

		if (bpf_map__is_internal(map)) {
			err = bpf_object__populate_internal_map(obj, map);
			if (err < 0) {
				zclose(*pfd);
				goto err_out;
			}
		}

1679
		pr_debug("create map %s: fd=%d\n", map->name, *pfd);
1680 1681 1682 1683 1684
	}

	return 0;
}

1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741
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);
	}

1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754
	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);
	}

1755 1756 1757 1758 1759 1760
	if (!insn_offset)
		prog->btf_fd = btf__fd(obj->btf);

	return 0;
}

1761 1762 1763 1764 1765 1766 1767
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;
1768
	int err;
1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785

	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;
1786
		new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn));
1787 1788 1789 1790
		if (!new_insn) {
			pr_warning("oom in prog realloc\n");
			return -ENOMEM;
		}
1791

1792 1793 1794 1795 1796
		if (obj->btf_ext) {
			err = bpf_program_reloc_btf_ext(prog, obj,
							text->section_name,
							prog->insns_cnt);
			if (err)
1797 1798 1799
				return err;
		}

1800 1801 1802 1803 1804
		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;
1805 1806 1807
		pr_debug("added %zd insn from %s to prog %s\n",
			 text->insns_cnt, text->section_name,
			 prog->section_name);
1808 1809 1810 1811 1812 1813
	}
	insn = &prog->insns[relo->insn_idx];
	insn->imm += prog->main_prog_cnt - relo->insn_idx;
	return 0;
}

W
Wang Nan 已提交
1814
static int
1815
bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
W
Wang Nan 已提交
1816
{
1817
	int i, err;
W
Wang Nan 已提交
1818

1819 1820 1821
	if (!prog)
		return 0;

1822 1823 1824 1825
	if (obj->btf_ext) {
		err = bpf_program_reloc_btf_ext(prog, obj,
						prog->section_name, 0);
		if (err)
1826 1827 1828 1829
			return err;
	}

	if (!prog->reloc_desc)
W
Wang Nan 已提交
1830 1831 1832
		return 0;

	for (i = 0; i < prog->nr_reloc; i++) {
1833 1834 1835
		if (prog->reloc_desc[i].type == RELO_LD64 ||
		    prog->reloc_desc[i].type == RELO_DATA) {
			bool relo_data = prog->reloc_desc[i].type == RELO_DATA;
1836 1837
			struct bpf_insn *insns = prog->insns;
			int insn_idx, map_idx;
W
Wang Nan 已提交
1838

1839 1840
			insn_idx = prog->reloc_desc[i].insn_idx;
			map_idx = prog->reloc_desc[i].map_idx;
W
Wang Nan 已提交
1841

1842
			if (insn_idx + 1 >= (int)prog->insns_cnt) {
1843 1844 1845 1846
				pr_warning("relocation out of range: '%s'\n",
					   prog->section_name);
				return -LIBBPF_ERRNO__RELOC;
			}
1847 1848 1849 1850 1851 1852 1853

			if (!relo_data) {
				insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
			} else {
				insns[insn_idx].src_reg = BPF_PSEUDO_MAP_VALUE;
				insns[insn_idx + 1].imm = insns[insn_idx].imm;
			}
1854
			insns[insn_idx].imm = obj->maps[map_idx].fd;
1855
		} else if (prog->reloc_desc[i].type == RELO_CALL) {
1856 1857 1858 1859
			err = bpf_program__reloc_text(prog, obj,
						      &prog->reloc_desc[i]);
			if (err)
				return err;
W
Wang Nan 已提交
1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878
		}
	}

	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];

1879
		err = bpf_program__relocate(prog, obj);
W
Wang Nan 已提交
1880 1881 1882 1883 1884 1885 1886 1887 1888
		if (err) {
			pr_warning("failed to relocate '%s'\n",
				   prog->section_name);
			return err;
		}
	}
	return 0;
}

1889 1890 1891 1892 1893 1894
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");
1895
		return -LIBBPF_ERRNO__INTERNAL;
1896 1897 1898 1899 1900 1901 1902 1903 1904 1905
	}

	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__);
1906
			return -LIBBPF_ERRNO__INTERNAL;
1907 1908 1909 1910
		}

		prog = bpf_object__find_prog_by_idx(obj, idx);
		if (!prog) {
1911
			pr_warning("relocation failed: no section(%d)\n", idx);
1912
			return -LIBBPF_ERRNO__RELOC;
1913 1914
		}

1915
		err = bpf_program__collect_reloc(prog,
1916
						 shdr, data,
1917
						 obj);
1918
		if (err)
1919
			return err;
1920 1921 1922 1923
	}
	return 0;
}

1924
static int
1925
load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
1926
	     char *license, __u32 kern_version, int *pfd)
1927
{
1928
	struct bpf_load_program_attr load_attr;
1929
	char *cp, errmsg[STRERR_BUFSIZE];
1930
	int log_buf_size = BPF_LOG_BUF_SIZE;
1931
	char *log_buf;
1932
	int ret;
1933

1934
	memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
1935 1936
	load_attr.prog_type = prog->type;
	load_attr.expected_attach_type = prog->expected_attach_type;
1937 1938
	if (prog->caps->name)
		load_attr.name = prog->name;
1939 1940 1941 1942
	load_attr.insns = insns;
	load_attr.insns_cnt = insns_cnt;
	load_attr.license = license;
	load_attr.kern_version = kern_version;
1943
	load_attr.prog_ifindex = prog->prog_ifindex;
Y
Yonghong Song 已提交
1944
	load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0;
1945 1946
	load_attr.func_info = prog->func_info;
	load_attr.func_info_rec_size = prog->func_info_rec_size;
1947
	load_attr.func_info_cnt = prog->func_info_cnt;
1948 1949 1950
	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;
1951
	load_attr.log_level = prog->log_level;
1952
	if (!load_attr.insns || !load_attr.insns_cnt)
1953 1954
		return -EINVAL;

1955 1956
retry_load:
	log_buf = malloc(log_buf_size);
1957 1958 1959
	if (!log_buf)
		pr_warning("Alloc log buffer for bpf loader error, continue without log\n");

1960
	ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size);
1961 1962

	if (ret >= 0) {
1963 1964
		if (load_attr.log_level)
			pr_debug("verifier log:\n%s", log_buf);
1965 1966 1967 1968 1969
		*pfd = ret;
		ret = 0;
		goto out;
	}

1970 1971 1972 1973 1974
	if (errno == ENOSPC) {
		log_buf_size <<= 1;
		free(log_buf);
		goto retry_load;
	}
1975
	ret = -LIBBPF_ERRNO__LOAD;
1976
	cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1977
	pr_warning("load bpf program failed: %s\n", cp);
1978

1979 1980
	if (log_buf && log_buf[0] != '\0') {
		ret = -LIBBPF_ERRNO__VERIFY;
1981 1982 1983
		pr_warning("-- BEGIN DUMP LOG ---\n");
		pr_warning("\n%s\n", log_buf);
		pr_warning("-- END LOG --\n");
1984 1985 1986
	} 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);
1987
		ret = -LIBBPF_ERRNO__PROG2BIG;
1988
	} else {
1989
		/* Wrong program type? */
1990
		if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) {
1991 1992
			int fd;

1993 1994 1995
			load_attr.prog_type = BPF_PROG_TYPE_KPROBE;
			load_attr.expected_attach_type = 0;
			fd = bpf_load_program_xattr(&load_attr, NULL, 0);
1996 1997 1998 1999 2000
			if (fd >= 0) {
				close(fd);
				ret = -LIBBPF_ERRNO__PROGTYPE;
				goto out;
			}
2001
		}
2002 2003 2004

		if (log_buf)
			ret = -LIBBPF_ERRNO__KVER;
2005 2006 2007 2008 2009 2010 2011
	}

out:
	free(log_buf);
	return ret;
}

2012
int
2013
bpf_program__load(struct bpf_program *prog,
2014
		  char *license, __u32 kern_version)
2015
{
2016
	int err = 0, fd, i;
2017

2018 2019 2020 2021 2022 2023
	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;
		}
2024

2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038
		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);
		}
2039
		err = load_program(prog, prog->insns, prog->insns_cnt,
2040
				   license, kern_version, &fd);
2041 2042 2043 2044 2045 2046 2047 2048 2049
		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;

2050
		memset(&result, 0, sizeof(result));
2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067
		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;
		}

2068
		err = load_program(prog, result.new_insn_ptr,
2069
				   result.new_insn_cnt,
2070
				   license, kern_version, &fd);
2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082

		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:
2083 2084 2085 2086 2087 2088 2089 2090
	if (err)
		pr_warning("failed to load program '%s'\n",
			   prog->section_name);
	zfree(&prog->insns);
	prog->insns_cnt = 0;
	return err;
}

2091 2092 2093 2094 2095 2096
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;
}

2097 2098 2099 2100 2101 2102 2103
static int
bpf_object__load_progs(struct bpf_object *obj)
{
	size_t i;
	int err;

	for (i = 0; i < obj->nr_programs; i++) {
2104
		if (bpf_program__is_function_storage(&obj->programs[i], obj))
2105
			continue;
2106 2107 2108 2109 2110 2111 2112 2113 2114
		err = bpf_program__load(&obj->programs[i],
					obj->license,
					obj->kern_version);
		if (err)
			return err;
	}
	return 0;
}

2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126
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:
2127
	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
2128 2129 2130 2131 2132
	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:
2133
	case BPF_PROG_TYPE_LIRC_MODE2:
2134
	case BPF_PROG_TYPE_SK_REUSEPORT:
2135
	case BPF_PROG_TYPE_FLOW_DISSECTOR:
2136 2137 2138
	case BPF_PROG_TYPE_UNSPEC:
	case BPF_PROG_TYPE_TRACEPOINT:
	case BPF_PROG_TYPE_RAW_TRACEPOINT:
2139
	case BPF_PROG_TYPE_PERF_EVENT:
A
Andrey Ignatov 已提交
2140
	case BPF_PROG_TYPE_CGROUP_SYSCTL:
2141 2142
		return false;
	case BPF_PROG_TYPE_KPROBE:
2143 2144 2145 2146 2147 2148
	default:
		return true;
	}
}

static int bpf_object__validate(struct bpf_object *obj, bool needs_kver)
2149
{
2150
	if (needs_kver && obj->kern_version == 0) {
2151 2152
		pr_warning("%s doesn't provide kernel version\n",
			   obj->path);
2153
		return -LIBBPF_ERRNO__KVERSION;
2154 2155 2156 2157
	}
	return 0;
}

2158
static struct bpf_object *
2159
__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
2160
		   bool needs_kver, int flags)
2161 2162
{
	struct bpf_object *obj;
2163
	int err;
2164 2165 2166

	if (elf_version(EV_CURRENT) == EV_NONE) {
		pr_warning("failed to init libelf for %s\n", path);
2167
		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
2168 2169
	}

2170
	obj = bpf_object__new(path, obj_buf, obj_buf_sz);
2171 2172
	if (IS_ERR(obj))
		return obj;
2173

2174 2175
	CHECK_ERR(bpf_object__elf_init(obj), err, out);
	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
2176
	CHECK_ERR(bpf_object__probe_caps(obj), err, out);
2177
	CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out);
2178
	CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
2179
	CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out);
2180 2181 2182 2183 2184

	bpf_object__elf_finish(obj);
	return obj;
out:
	bpf_object__close(obj);
2185
	return ERR_PTR(err);
2186 2187
}

2188 2189
struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
					    int flags)
2190 2191
{
	/* param validation */
2192
	if (!attr->file)
2193 2194
		return NULL;

2195 2196 2197
	pr_debug("loading %s\n", attr->file);

	return __bpf_object__open(attr->file, NULL, 0,
2198 2199 2200 2201 2202 2203 2204
				  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);
2205 2206 2207 2208 2209 2210 2211 2212
}

struct bpf_object *bpf_object__open(const char *path)
{
	struct bpf_object_open_attr attr = {
		.file		= path,
		.prog_type	= BPF_PROG_TYPE_UNSPEC,
	};
2213

2214
	return bpf_object__open_xattr(&attr);
2215 2216 2217
}

struct bpf_object *bpf_object__open_buffer(void *obj_buf,
2218 2219
					   size_t obj_buf_sz,
					   const char *name)
2220
{
2221 2222
	char tmp_name[64];

2223 2224 2225 2226
	/* param validation */
	if (!obj_buf || obj_buf_sz <= 0)
		return NULL;

2227 2228 2229 2230 2231 2232 2233 2234 2235
	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);
2236

2237
	return __bpf_object__open(name, obj_buf, obj_buf_sz, true, true);
2238 2239
}

2240 2241 2242 2243 2244 2245 2246
int bpf_object__unload(struct bpf_object *obj)
{
	size_t i;

	if (!obj)
		return -EINVAL;

2247 2248
	for (i = 0; i < obj->nr_maps; i++)
		zclose(obj->maps[i].fd);
2249

2250 2251 2252
	for (i = 0; i < obj->nr_programs; i++)
		bpf_program__unload(&obj->programs[i]);

2253 2254 2255 2256 2257
	return 0;
}

int bpf_object__load(struct bpf_object *obj)
{
2258 2259
	int err;

2260 2261 2262 2263 2264 2265 2266 2267 2268
	if (!obj)
		return -EINVAL;

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

	obj->loaded = true;
2269 2270 2271 2272

	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);
2273 2274 2275 2276 2277

	return 0;
out:
	bpf_object__unload(obj);
	pr_warning("failed to load object '%s'\n", obj->path);
2278
	return err;
2279 2280
}

2281 2282
static int check_path(const char *path)
{
2283
	char *cp, errmsg[STRERR_BUFSIZE];
2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296
	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)) {
2297
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
2298
		pr_warning("failed to statfs %s: %s\n", dir, cp);
2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313
		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)
{
2314
	char *cp, errmsg[STRERR_BUFSIZE];
2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332
	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)) {
2333
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
2334
		pr_warning("failed to pin program: %s\n", cp);
2335 2336 2337 2338 2339 2340 2341
		return -errno;
	}
	pr_debug("pinned program '%s'\n", path);

	return 0;
}

2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369
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;
}

2370 2371
static int make_dir(const char *path)
{
2372
	char *cp, errmsg[STRERR_BUFSIZE];
2373 2374 2375 2376 2377
	int err = 0;

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

2378
	if (err) {
2379
		cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
2380 2381
		pr_warning("failed to mkdir %s: %s\n", path, cp);
	}
2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403
	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;
	}

2404 2405 2406 2407 2408
	if (prog->instances.nr == 1) {
		/* don't create subdirs when pinning single instance */
		return bpf_program__pin_instance(prog, path, 0);
	}

2409 2410 2411 2412
	err = make_dir(path);
	if (err)
		return err;

2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 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 2464 2465 2466 2467 2468
	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;
2469 2470 2471 2472 2473
	}

	if (prog->instances.nr == 1) {
		/* don't create subdirs when pinning single instance */
		return bpf_program__unpin_instance(prog, path, 0);
2474 2475
	}

2476 2477 2478 2479 2480 2481 2482 2483 2484 2485
	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;

2486
		err = bpf_program__unpin_instance(prog, buf, i);
2487 2488 2489 2490
		if (err)
			return err;
	}

2491 2492 2493 2494
	err = rmdir(path);
	if (err)
		return -errno;

2495 2496 2497
	return 0;
}

J
Joe Stringer 已提交
2498 2499
int bpf_map__pin(struct bpf_map *map, const char *path)
{
2500
	char *cp, errmsg[STRERR_BUFSIZE];
J
Joe Stringer 已提交
2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512
	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)) {
2513
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
2514
		pr_warning("failed to pin map: %s\n", cp);
J
Joe Stringer 已提交
2515 2516 2517 2518
		return -errno;
	}

	pr_debug("pinned map '%s'\n", path);
2519

J
Joe Stringer 已提交
2520 2521 2522
	return 0;
}

2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544
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)
2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560
{
	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;

2561
	bpf_object__for_each_map(map, obj) {
2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607
		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;

2608
	bpf_object__for_each_map(map, obj) {
2609 2610 2611 2612 2613 2614 2615 2616 2617 2618
		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;

2619
		err = bpf_map__unpin(map, buf);
2620 2621 2622 2623
		if (err)
			return err;
	}

2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648
	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
2649
			       prog->pin_name);
2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670
		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
2671
			       prog->pin_name);
2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690
		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;

2691 2692 2693 2694 2695
	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
2696
			       prog->pin_name);
2697 2698 2699 2700 2701
		if (len < 0)
			return -EINVAL;
		else if (len >= PATH_MAX)
			return -ENAMETOOLONG;

2702
		err = bpf_program__unpin(prog, buf);
2703 2704 2705 2706 2707 2708 2709
		if (err)
			return err;
	}

	return 0;
}

2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726
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;
}

2727 2728
void bpf_object__close(struct bpf_object *obj)
{
2729 2730
	size_t i;

2731 2732 2733
	if (!obj)
		return;

2734 2735 2736
	if (obj->clear_priv)
		obj->clear_priv(obj, obj->priv);

2737
	bpf_object__elf_finish(obj);
2738
	bpf_object__unload(obj);
2739
	btf__free(obj->btf);
2740
	btf_ext__free(obj->btf_ext);
2741

2742
	for (i = 0; i < obj->nr_maps; i++) {
2743
		zfree(&obj->maps[i].name);
2744 2745 2746 2747 2748 2749
		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;
	}
2750 2751 2752

	zfree(&obj->sections.rodata);
	zfree(&obj->sections.data);
2753 2754
	zfree(&obj->maps);
	obj->nr_maps = 0;
2755 2756 2757 2758 2759 2760 2761

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

2762
	list_del(&obj->list);
2763 2764
	free(obj);
}
2765

2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784
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;
}

2785
const char *bpf_object__name(struct bpf_object *obj)
2786
{
2787
	return obj ? obj->path : ERR_PTR(-EINVAL);
2788 2789
}

2790
unsigned int bpf_object__kversion(struct bpf_object *obj)
2791
{
2792
	return obj ? obj->kern_version : 0;
2793 2794
}

2795 2796 2797 2798 2799
struct btf *bpf_object__btf(struct bpf_object *obj)
{
	return obj ? obj->btf : NULL;
}

2800 2801 2802 2803 2804
int bpf_object__btf_fd(const struct bpf_object *obj)
{
	return obj->btf ? btf__fd(obj->btf) : -1;
}

2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820
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);
}

2821
static struct bpf_program *
2822
__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward)
2823
{
2824
	size_t nr_programs = obj->nr_programs;
2825
	ssize_t idx;
2826

2827
	if (!nr_programs)
2828 2829
		return NULL;

2830 2831 2832 2833 2834
	if (!p)
		/* Iter from the beginning */
		return forward ? &obj->programs[0] :
			&obj->programs[nr_programs - 1];

2835
	if (p->obj != obj) {
2836 2837 2838 2839
		pr_warning("error: program handler doesn't match object\n");
		return NULL;
	}

2840
	idx = (p - obj->programs) + (forward ? 1 : -1);
2841
	if (idx >= obj->nr_programs || idx < 0)
2842 2843 2844 2845
		return NULL;
	return &obj->programs[idx];
}

2846 2847 2848 2849 2850 2851
struct bpf_program *
bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
{
	struct bpf_program *prog = prev;

	do {
2852
		prog = __bpf_program__iter(prog, obj, true);
2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863
	} 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 {
2864
		prog = __bpf_program__iter(prog, obj, false);
2865 2866 2867 2868 2869
	} while (prog && bpf_program__is_function_storage(prog, obj));

	return prog;
}

2870 2871
int bpf_program__set_priv(struct bpf_program *prog, void *priv,
			  bpf_program_clear_priv_t clear_priv)
2872 2873 2874 2875 2876 2877 2878 2879 2880
{
	if (prog->priv && prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

2881
void *bpf_program__priv(struct bpf_program *prog)
2882
{
2883
	return prog ? prog->priv : ERR_PTR(-EINVAL);
2884 2885
}

2886 2887 2888 2889 2890
void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex)
{
	prog->prog_ifindex = ifindex;
}

2891
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
2892 2893 2894 2895
{
	const char *title;

	title = prog->section_name;
2896
	if (needs_copy) {
2897 2898 2899
		title = strdup(title);
		if (!title) {
			pr_warning("failed to strdup program title\n");
2900
			return ERR_PTR(-ENOMEM);
2901 2902 2903 2904 2905 2906 2907 2908
		}
	}

	return title;
}

int bpf_program__fd(struct bpf_program *prog)
{
2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943
	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;

2944 2945 2946
	if (!prog)
		return -EINVAL;

2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960
	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;
2961
}
2962

2963
void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
2964 2965 2966 2967 2968 2969 2970 2971 2972 2973
{
	prog->type = type;
}

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

2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987
#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);	\
}							\

2988
BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
2989
BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
2990 2991
BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
2992
BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
2993
BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT);
2994 2995
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
2996

J
John Fastabend 已提交
2997 2998
void bpf_program__set_expected_attach_type(struct bpf_program *prog,
					   enum bpf_attach_type type)
2999 3000 3001 3002
{
	prog->expected_attach_type = type;
}

3003 3004
#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, atype) \
	{ string, sizeof(string) - 1, ptype, eatype, is_attachable, atype }
3005

3006
/* Programs that can NOT be attached. */
3007
#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0)
3008

3009 3010
/* Programs that can be attached. */
#define BPF_APROG_SEC(string, ptype, atype) \
3011
	BPF_PROG_SEC_IMPL(string, ptype, 0, 1, atype)
3012

3013 3014
/* Programs that must specify expected attach type at load time. */
#define BPF_EAPROG_SEC(string, ptype, eatype) \
3015
	BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, eatype)
3016 3017 3018 3019 3020

/* 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)
3021

3022 3023 3024 3025
static const struct {
	const char *sec;
	size_t len;
	enum bpf_prog_type prog_type;
3026
	enum bpf_attach_type expected_attach_type;
3027
	int is_attachable;
3028
	enum bpf_attach_type attach_type;
3029
} section_names[] = {
3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042
	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),
3043 3044 3045 3046
	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),
3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057
	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),
3058 3059 3060 3061
	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),
3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080
	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),
A
Andrey Ignatov 已提交
3081 3082
	BPF_EAPROG_SEC("cgroup/sysctl",		BPF_PROG_TYPE_CGROUP_SYSCTL,
						BPF_CGROUP_SYSCTL),
3083
};
3084

3085
#undef BPF_PROG_SEC_IMPL
3086
#undef BPF_PROG_SEC
3087 3088 3089
#undef BPF_APROG_SEC
#undef BPF_EAPROG_SEC
#undef BPF_APROG_COMPAT
3090

3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118
#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;
}

3119 3120
int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
			     enum bpf_attach_type *expected_attach_type)
3121
{
3122
	char *type_names;
3123 3124
	int i;

3125 3126
	if (!name)
		return -EINVAL;
3127

3128 3129 3130 3131 3132 3133 3134
	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;
	}
3135 3136 3137 3138 3139 3140 3141
	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);
	}

3142 3143
	return -EINVAL;
}
3144

3145 3146 3147
int libbpf_attach_type_by_name(const char *name,
			       enum bpf_attach_type *attach_type)
{
3148
	char *type_names;
3149 3150 3151 3152 3153 3154 3155 3156
	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;
3157
		if (!section_names[i].is_attachable)
3158 3159 3160 3161
			return -EINVAL;
		*attach_type = section_names[i].attach_type;
		return 0;
	}
3162 3163 3164 3165 3166 3167 3168
	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);
	}

3169 3170 3171
	return -EINVAL;
}

3172 3173 3174 3175 3176 3177 3178
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);
3179 3180
}

3181
int bpf_map__fd(struct bpf_map *map)
3182
{
3183
	return map ? map->fd : -EINVAL;
3184 3185
}

3186
const struct bpf_map_def *bpf_map__def(struct bpf_map *map)
3187
{
3188
	return map ? &map->def : ERR_PTR(-EINVAL);
3189 3190
}

3191
const char *bpf_map__name(struct bpf_map *map)
3192
{
3193
	return map ? map->name : NULL;
3194 3195
}

3196
__u32 bpf_map__btf_key_type_id(const struct bpf_map *map)
3197
{
3198
	return map ? map->btf_key_type_id : 0;
3199 3200
}

3201
__u32 bpf_map__btf_value_type_id(const struct bpf_map *map)
3202
{
3203
	return map ? map->btf_value_type_id : 0;
3204 3205
}

3206 3207
int bpf_map__set_priv(struct bpf_map *map, void *priv,
		     bpf_map_clear_priv_t clear_priv)
3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221
{
	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;
}

3222
void *bpf_map__priv(struct bpf_map *map)
3223
{
3224
	return map ? map->priv : ERR_PTR(-EINVAL);
3225 3226
}

3227 3228 3229 3230 3231
bool bpf_map__is_offload_neutral(struct bpf_map *map)
{
	return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
}

3232 3233 3234 3235 3236
bool bpf_map__is_internal(struct bpf_map *map)
{
	return map->libbpf_type != LIBBPF_MAP_UNSPEC;
}

3237 3238 3239 3240 3241
void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
{
	map->map_ifindex = ifindex;
}

3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255
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;
}

3256 3257
static struct bpf_map *
__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i)
3258
{
3259
	ssize_t idx;
3260 3261 3262 3263 3264 3265 3266 3267
	struct bpf_map *s, *e;

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

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

3268
	if ((m < s) || (m >= e)) {
3269 3270 3271 3272 3273
		pr_warning("error in %s: map handler doesn't belong to object\n",
			   __func__);
		return NULL;
	}

3274 3275
	idx = (m - obj->maps) + i;
	if (idx >= obj->nr_maps || idx < 0)
3276 3277 3278
		return NULL;
	return &obj->maps[idx];
}
3279

3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300
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);
}

3301
struct bpf_map *
3302
bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
3303 3304 3305
{
	struct bpf_map *pos;

3306
	bpf_object__for_each_map(pos, obj) {
3307
		if (pos->name && !strcmp(pos->name, name))
3308 3309 3310 3311
			return pos;
	}
	return NULL;
}
3312

3313 3314 3315 3316 3317 3318
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));
}

3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329
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);
}
3330 3331 3332 3333 3334 3335 3336

long libbpf_get_error(const void *ptr)
{
	if (IS_ERR(ptr))
		return PTR_ERR(ptr);
	return 0;
}
3337 3338 3339

int bpf_prog_load(const char *file, enum bpf_prog_type type,
		  struct bpf_object **pobj, int *prog_fd)
3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352
{
	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)
3353
{
3354 3355 3356 3357
	struct bpf_object_open_attr open_attr = {
		.file		= attr->file,
		.prog_type	= attr->prog_type,
	};
3358
	struct bpf_program *prog, *first_prog = NULL;
3359 3360
	enum bpf_attach_type expected_attach_type;
	enum bpf_prog_type prog_type;
3361
	struct bpf_object *obj;
3362
	struct bpf_map *map;
3363 3364
	int err;

3365 3366
	if (!attr)
		return -EINVAL;
3367 3368
	if (!attr->file)
		return -EINVAL;
3369

3370
	obj = bpf_object__open_xattr(&open_attr);
3371
	if (IS_ERR_OR_NULL(obj))
3372 3373
		return -ENOENT;

3374 3375 3376 3377 3378
	bpf_object__for_each_program(prog, obj) {
		/*
		 * If type is not specified, try to guess it based on
		 * section name.
		 */
3379
		prog_type = attr->prog_type;
3380
		prog->prog_ifindex = attr->ifindex;
3381 3382
		expected_attach_type = attr->expected_attach_type;
		if (prog_type == BPF_PROG_TYPE_UNSPEC) {
3383 3384 3385
			err = bpf_program__identify_section(prog, &prog_type,
							    &expected_attach_type);
			if (err < 0) {
3386 3387 3388
				bpf_object__close(obj);
				return -EINVAL;
			}
3389
		}
3390

3391 3392 3393 3394
		bpf_program__set_type(prog, prog_type);
		bpf_program__set_expected_attach_type(prog,
						      expected_attach_type);

3395
		prog->log_level = attr->log_level;
3396
		if (!first_prog)
3397 3398 3399
			first_prog = prog;
	}

3400
	bpf_object__for_each_map(map, obj) {
3401 3402
		if (!bpf_map__is_offload_neutral(map))
			map->map_ifindex = attr->ifindex;
3403 3404
	}

3405 3406 3407 3408
	if (!first_prog) {
		pr_warning("object file doesn't contain bpf program\n");
		bpf_object__close(obj);
		return -ENOENT;
3409 3410
	}

3411 3412 3413 3414 3415 3416 3417
	err = bpf_object__load(obj);
	if (err) {
		bpf_object__close(obj);
		return -EINVAL;
	}

	*pobj = obj;
3418
	*prog_fd = bpf_program__fd(first_prog);
3419 3420
	return 0;
}
3421 3422

enum bpf_perf_event_ret
3423 3424 3425
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)
3426
{
3427
	struct perf_event_mmap_page *header = mmap_mem;
3428
	__u64 data_head = ring_buffer_read_head(header);
3429
	__u64 data_tail = header->data_tail;
3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448
	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;
3449 3450 3451
					ret = LIBBPF_PERF_EVENT_ERROR;
					break;
				}
3452
				*copy_size = ehdr_size;
3453 3454
			}

3455 3456 3457
			memcpy(*copy_mem, copy_start, len_first);
			memcpy(*copy_mem + len_first, base, len_secnd);
			ehdr = *copy_mem;
3458 3459
		}

3460 3461
		ret = fn(ehdr, private_data);
		data_tail += ehdr_size;
3462 3463 3464 3465
		if (ret != LIBBPF_PERF_EVENT_CONT)
			break;
	}

3466
	ring_buffer_write_tail(header, data_tail);
3467 3468
	return ret;
}
3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714

struct bpf_prog_info_array_desc {
	int	array_offset;	/* e.g. offset of jited_prog_insns */
	int	count_offset;	/* e.g. offset of jited_prog_len */
	int	size_offset;	/* > 0: offset of rec size,
				 * < 0: fix size of -size_offset
				 */
};

static struct bpf_prog_info_array_desc bpf_prog_info_array_desc[] = {
	[BPF_PROG_INFO_JITED_INSNS] = {
		offsetof(struct bpf_prog_info, jited_prog_insns),
		offsetof(struct bpf_prog_info, jited_prog_len),
		-1,
	},
	[BPF_PROG_INFO_XLATED_INSNS] = {
		offsetof(struct bpf_prog_info, xlated_prog_insns),
		offsetof(struct bpf_prog_info, xlated_prog_len),
		-1,
	},
	[BPF_PROG_INFO_MAP_IDS] = {
		offsetof(struct bpf_prog_info, map_ids),
		offsetof(struct bpf_prog_info, nr_map_ids),
		-(int)sizeof(__u32),
	},
	[BPF_PROG_INFO_JITED_KSYMS] = {
		offsetof(struct bpf_prog_info, jited_ksyms),
		offsetof(struct bpf_prog_info, nr_jited_ksyms),
		-(int)sizeof(__u64),
	},
	[BPF_PROG_INFO_JITED_FUNC_LENS] = {
		offsetof(struct bpf_prog_info, jited_func_lens),
		offsetof(struct bpf_prog_info, nr_jited_func_lens),
		-(int)sizeof(__u32),
	},
	[BPF_PROG_INFO_FUNC_INFO] = {
		offsetof(struct bpf_prog_info, func_info),
		offsetof(struct bpf_prog_info, nr_func_info),
		offsetof(struct bpf_prog_info, func_info_rec_size),
	},
	[BPF_PROG_INFO_LINE_INFO] = {
		offsetof(struct bpf_prog_info, line_info),
		offsetof(struct bpf_prog_info, nr_line_info),
		offsetof(struct bpf_prog_info, line_info_rec_size),
	},
	[BPF_PROG_INFO_JITED_LINE_INFO] = {
		offsetof(struct bpf_prog_info, jited_line_info),
		offsetof(struct bpf_prog_info, nr_jited_line_info),
		offsetof(struct bpf_prog_info, jited_line_info_rec_size),
	},
	[BPF_PROG_INFO_PROG_TAGS] = {
		offsetof(struct bpf_prog_info, prog_tags),
		offsetof(struct bpf_prog_info, nr_prog_tags),
		-(int)sizeof(__u8) * BPF_TAG_SIZE,
	},

};

static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info, int offset)
{
	__u32 *array = (__u32 *)info;

	if (offset >= 0)
		return array[offset / sizeof(__u32)];
	return -(int)offset;
}

static __u64 bpf_prog_info_read_offset_u64(struct bpf_prog_info *info, int offset)
{
	__u64 *array = (__u64 *)info;

	if (offset >= 0)
		return array[offset / sizeof(__u64)];
	return -(int)offset;
}

static void bpf_prog_info_set_offset_u32(struct bpf_prog_info *info, int offset,
					 __u32 val)
{
	__u32 *array = (__u32 *)info;

	if (offset >= 0)
		array[offset / sizeof(__u32)] = val;
}

static void bpf_prog_info_set_offset_u64(struct bpf_prog_info *info, int offset,
					 __u64 val)
{
	__u64 *array = (__u64 *)info;

	if (offset >= 0)
		array[offset / sizeof(__u64)] = val;
}

struct bpf_prog_info_linear *
bpf_program__get_prog_info_linear(int fd, __u64 arrays)
{
	struct bpf_prog_info_linear *info_linear;
	struct bpf_prog_info info = {};
	__u32 info_len = sizeof(info);
	__u32 data_len = 0;
	int i, err;
	void *ptr;

	if (arrays >> BPF_PROG_INFO_LAST_ARRAY)
		return ERR_PTR(-EINVAL);

	/* step 1: get array dimensions */
	err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
	if (err) {
		pr_debug("can't get prog info: %s", strerror(errno));
		return ERR_PTR(-EFAULT);
	}

	/* step 2: calculate total size of all arrays */
	for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
		bool include_array = (arrays & (1UL << i)) > 0;
		struct bpf_prog_info_array_desc *desc;
		__u32 count, size;

		desc = bpf_prog_info_array_desc + i;

		/* kernel is too old to support this field */
		if (info_len < desc->array_offset + sizeof(__u32) ||
		    info_len < desc->count_offset + sizeof(__u32) ||
		    (desc->size_offset > 0 && info_len < desc->size_offset))
			include_array = false;

		if (!include_array) {
			arrays &= ~(1UL << i);	/* clear the bit */
			continue;
		}

		count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
		size  = bpf_prog_info_read_offset_u32(&info, desc->size_offset);

		data_len += count * size;
	}

	/* step 3: allocate continuous memory */
	data_len = roundup(data_len, sizeof(__u64));
	info_linear = malloc(sizeof(struct bpf_prog_info_linear) + data_len);
	if (!info_linear)
		return ERR_PTR(-ENOMEM);

	/* step 4: fill data to info_linear->info */
	info_linear->arrays = arrays;
	memset(&info_linear->info, 0, sizeof(info));
	ptr = info_linear->data;

	for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
		struct bpf_prog_info_array_desc *desc;
		__u32 count, size;

		if ((arrays & (1UL << i)) == 0)
			continue;

		desc  = bpf_prog_info_array_desc + i;
		count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
		size  = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
		bpf_prog_info_set_offset_u32(&info_linear->info,
					     desc->count_offset, count);
		bpf_prog_info_set_offset_u32(&info_linear->info,
					     desc->size_offset, size);
		bpf_prog_info_set_offset_u64(&info_linear->info,
					     desc->array_offset,
					     ptr_to_u64(ptr));
		ptr += count * size;
	}

	/* step 5: call syscall again to get required arrays */
	err = bpf_obj_get_info_by_fd(fd, &info_linear->info, &info_len);
	if (err) {
		pr_debug("can't get prog info: %s", strerror(errno));
		free(info_linear);
		return ERR_PTR(-EFAULT);
	}

	/* step 6: verify the data */
	for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
		struct bpf_prog_info_array_desc *desc;
		__u32 v1, v2;

		if ((arrays & (1UL << i)) == 0)
			continue;

		desc = bpf_prog_info_array_desc + i;
		v1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
		v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
						   desc->count_offset);
		if (v1 != v2)
			pr_warning("%s: mismatch in element count\n", __func__);

		v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
		v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
						   desc->size_offset);
		if (v1 != v2)
			pr_warning("%s: mismatch in rec size\n", __func__);
	}

	/* step 7: update info_len and data_len */
	info_linear->info_len = sizeof(struct bpf_prog_info);
	info_linear->data_len = data_len;

	return info_linear;
}

void bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear)
{
	int i;

	for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
		struct bpf_prog_info_array_desc *desc;
		__u64 addr, offs;

		if ((info_linear->arrays & (1UL << i)) == 0)
			continue;

		desc = bpf_prog_info_array_desc + i;
		addr = bpf_prog_info_read_offset_u64(&info_linear->info,
						     desc->array_offset);
		offs = addr - ptr_to_u64(info_linear->data);
		bpf_prog_info_set_offset_u64(&info_linear->info,
					     desc->array_offset, offs);
	}
}

void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear)
{
	int i;

	for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
		struct bpf_prog_info_array_desc *desc;
		__u64 addr, offs;

		if ((info_linear->arrays & (1UL << i)) == 0)
			continue;

		desc = bpf_prog_info_array_desc + i;
		offs = bpf_prog_info_read_offset_u64(&info_linear->info,
						     desc->array_offset);
		addr = offs + ptr_to_u64(info_linear->data);
		bpf_prog_info_set_offset_u64(&info_linear->info,
					     desc->array_offset, addr);
	}
}