libbpf.c 84.1 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;
}

126 127 128 129 130
struct bpf_capabilities {
	/* v4.14: kernel support for program & map names. */
	__u32 name:1;
};

131 132 133 134 135 136 137
/*
 * 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;
138
	char *name;
139
	int prog_ifindex;
140
	char *section_name;
S
Stanislav Fomichev 已提交
141 142 143 144
	/* section_name with / replaced by _; makes recursive pinning
	 * in bpf_object__pin_programs easier
	 */
	char *pin_name;
145
	struct bpf_insn *insns;
146
	size_t insns_cnt, main_prog_cnt;
147
	enum bpf_prog_type type;
148

149 150 151 152
	struct reloc_desc {
		enum {
			RELO_LD64,
			RELO_CALL,
153
			RELO_DATA,
154
		} type;
155
		int insn_idx;
156 157 158 159
		union {
			int map_idx;
			int text_off;
		};
160 161
	} *reloc_desc;
	int nr_reloc;
162
	int log_level;
163

164 165 166 167 168
	struct {
		int nr;
		int *fds;
	} instances;
	bpf_program_prep_t preprocessor;
169 170 171 172

	struct bpf_object *obj;
	void *priv;
	bpf_program_clear_priv_t clear_priv;
173 174

	enum bpf_attach_type expected_attach_type;
175 176 177
	int btf_fd;
	void *func_info;
	__u32 func_info_rec_size;
178
	__u32 func_info_cnt;
179 180

	struct bpf_capabilities *caps;
181 182 183 184

	void *line_info;
	__u32 line_info_rec_size;
	__u32 line_info_cnt;
185 186
};

187 188 189 190 191 192 193 194 195 196 197 198 199
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",
};

200 201
struct bpf_map {
	int fd;
202
	char *name;
E
Eric Leblond 已提交
203
	size_t offset;
204
	int map_ifindex;
205
	int inner_map_fd;
206
	struct bpf_map_def def;
207 208
	__u32 btf_key_type_id;
	__u32 btf_value_type_id;
209 210
	void *priv;
	bpf_map_clear_priv_t clear_priv;
211 212 213 214 215 216
	enum libbpf_map_type libbpf_type;
};

struct bpf_secdata {
	void *rodata;
	void *data;
217 218
};

219 220
static LIST_HEAD(bpf_objects_list);

221
struct bpf_object {
222
	char name[BPF_OBJ_NAME_LEN];
223
	char license[64];
224
	__u32 kern_version;
225

226 227
	struct bpf_program *programs;
	size_t nr_programs;
228 229
	struct bpf_map *maps;
	size_t nr_maps;
230
	struct bpf_secdata sections;
231

232
	bool loaded;
233
	bool has_pseudo_calls;
234

235 236 237 238 239 240
	/*
	 * Information when doing elf related work. Only valid if fd
	 * is valid.
	 */
	struct {
		int fd;
241 242
		void *obj_buf;
		size_t obj_buf_sz;
243 244
		Elf *elf;
		GElf_Ehdr ehdr;
245
		Elf_Data *symbols;
246 247 248
		Elf_Data *data;
		Elf_Data *rodata;
		Elf_Data *bss;
249
		size_t strtabidx;
250 251 252 253 254
		struct {
			GElf_Shdr shdr;
			Elf_Data *data;
		} *reloc;
		int nr_reloc;
255
		int maps_shndx;
256
		int text_shndx;
257 258 259
		int data_shndx;
		int rodata_shndx;
		int bss_shndx;
260
	} efile;
261 262 263 264 265 266
	/*
	 * 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;
267

268
	struct btf *btf;
269
	struct btf_ext *btf_ext;
270

271 272 273
	void *priv;
	bpf_object_clear_priv_t clear_priv;

274 275
	struct bpf_capabilities caps;

276 277 278 279
	char path[];
};
#define obj_elf_valid(o)	((o)->efile.elf)

280
void bpf_program__unload(struct bpf_program *prog)
281
{
282 283
	int i;

284 285 286
	if (!prog)
		return;

287 288 289 290 291 292 293 294 295 296 297 298 299 300
	/*
	 * 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);
301 302 303

	zclose(prog->btf_fd);
	zfree(&prog->func_info);
304
	zfree(&prog->line_info);
305 306
}

307 308 309 310 311
static void bpf_program__exit(struct bpf_program *prog)
{
	if (!prog)
		return;

312 313 314 315 316 317
	if (prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

318
	bpf_program__unload(prog);
319
	zfree(&prog->name);
320
	zfree(&prog->section_name);
S
Stanislav Fomichev 已提交
321
	zfree(&prog->pin_name);
322
	zfree(&prog->insns);
323 324 325
	zfree(&prog->reloc_desc);

	prog->nr_reloc = 0;
326 327 328 329
	prog->insns_cnt = 0;
	prog->idx = -1;
}

S
Stanislav Fomichev 已提交
330 331 332 333 334 335 336 337 338 339 340
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;
}

341
static int
342 343
bpf_program__init(void *data, size_t size, char *section_name, int idx,
		  struct bpf_program *prog)
344 345
{
	if (size < sizeof(struct bpf_insn)) {
346
		pr_warning("corrupted section '%s'\n", section_name);
347 348 349
		return -EINVAL;
	}

350
	memset(prog, 0, sizeof(*prog));
351

352
	prog->section_name = strdup(section_name);
353
	if (!prog->section_name) {
354 355
		pr_warning("failed to alloc name for prog under section(%d) %s\n",
			   idx, section_name);
356 357 358
		goto errout;
	}

S
Stanislav Fomichev 已提交
359 360 361 362 363 364 365
	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;
	}

366 367
	prog->insns = malloc(size);
	if (!prog->insns) {
368 369
		pr_warning("failed to alloc insns for prog under section %s\n",
			   section_name);
370 371 372 373 374 375
		goto errout;
	}
	prog->insns_cnt = size / sizeof(struct bpf_insn);
	memcpy(prog->insns, data,
	       prog->insns_cnt * sizeof(struct bpf_insn));
	prog->idx = idx;
376 377
	prog->instances.fds = NULL;
	prog->instances.nr = -1;
378
	prog->type = BPF_PROG_TYPE_UNSPEC;
379
	prog->btf_fd = -1;
380 381 382 383 384 385 386 387 388

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

static int
bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
389
			char *section_name, int idx)
390 391 392 393
{
	struct bpf_program prog, *progs;
	int nr_progs, err;

394
	err = bpf_program__init(data, size, section_name, idx, &prog);
395 396 397
	if (err)
		return err;

398
	prog.caps = &obj->caps;
399 400 401
	progs = obj->programs;
	nr_progs = obj->nr_programs;

402
	progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
403 404 405 406 407 408
	if (!progs) {
		/*
		 * In this case the original obj->programs
		 * is still valid, so don't need special treat for
		 * bpf_close_object().
		 */
409 410
		pr_warning("failed to alloc a new program under section '%s'\n",
			   section_name);
411 412 413 414 415 416 417
		bpf_program__exit(&prog);
		return -ENOMEM;
	}

	pr_debug("found program %s\n", prog.section_name);
	obj->programs = progs;
	obj->nr_programs = nr_progs + 1;
418
	prog.obj = obj;
419 420 421 422
	progs[nr_progs] = prog;
	return 0;
}

423 424 425 426 427 428 429 430
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++) {
431
		const char *name = NULL;
432 433 434 435 436 437 438 439 440 441 442

		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;
443 444
			if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL)
				continue;
445 446 447 448 449 450 451 452 453 454 455

			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;
			}
		}

456 457 458
		if (!name && prog->idx == obj->efile.text_shndx)
			name = ".text";

459 460 461 462 463
		if (!name) {
			pr_warning("failed to find sym for prog %s\n",
				   prog->section_name);
			return -EINVAL;
		}
464

465 466 467 468 469 470 471 472 473 474 475
		prog->name = strdup(name);
		if (!prog->name) {
			pr_warning("failed to allocate memory for prog sym %s\n",
				   name);
			return -ENOMEM;
		}
	}

	return 0;
}

476 477 478
static struct bpf_object *bpf_object__new(const char *path,
					  void *obj_buf,
					  size_t obj_buf_sz)
479 480
{
	struct bpf_object *obj;
481
	char *end;
482 483 484 485

	obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1);
	if (!obj) {
		pr_warning("alloc memory failed for %s\n", path);
486
		return ERR_PTR(-ENOMEM);
487 488 489
	}

	strcpy(obj->path, path);
490 491 492 493 494 495
	/* 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;
496

497
	obj->efile.fd = -1;
498 499 500 501 502 503 504 505
	/*
	 * 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;
506
	obj->efile.maps_shndx = -1;
507 508 509
	obj->efile.data_shndx = -1;
	obj->efile.rodata_shndx = -1;
	obj->efile.bss_shndx = -1;
510

511
	obj->loaded = false;
512 513 514

	INIT_LIST_HEAD(&obj->list);
	list_add(&obj->list, &bpf_objects_list);
515 516 517 518 519 520 521 522 523 524 525 526
	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;
	}
527
	obj->efile.symbols = NULL;
528 529 530
	obj->efile.data = NULL;
	obj->efile.rodata = NULL;
	obj->efile.bss = NULL;
531 532 533

	zfree(&obj->efile.reloc);
	obj->efile.nr_reloc = 0;
534
	zclose(obj->efile.fd);
535 536
	obj->efile.obj_buf = NULL;
	obj->efile.obj_buf_sz = 0;
537 538 539 540 541 542 543 544 545
}

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");
546
		return -LIBBPF_ERRNO__LIBELF;
547 548
	}

549 550 551 552 553 554 555 556 557 558
	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) {
559
			char errmsg[STRERR_BUFSIZE];
560 561
			char *cp = libbpf_strerror_r(errno, errmsg,
						     sizeof(errmsg));
562 563

			pr_warning("failed to open %s: %s\n", obj->path, cp);
564 565 566 567 568 569
			return -errno;
		}

		obj->efile.elf = elf_begin(obj->efile.fd,
				LIBBPF_ELF_C_READ_MMAP,
				NULL);
570 571 572 573 574
	}

	if (!obj->efile.elf) {
		pr_warning("failed to open %s as ELF file\n",
				obj->path);
575
		err = -LIBBPF_ERRNO__LIBELF;
576 577 578 579 580 581
		goto errout;
	}

	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
		pr_warning("failed to get EHDR from %s\n",
				obj->path);
582
		err = -LIBBPF_ERRNO__FORMAT;
583 584 585 586
		goto errout;
	}
	ep = &obj->efile.ehdr;

587 588
	/* Old LLVM set e_machine to EM_NONE */
	if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) {
589 590
		pr_warning("%s is not an eBPF object file\n",
			obj->path);
591
		err = -LIBBPF_ERRNO__FORMAT;
592 593 594 595 596 597 598 599 600
		goto errout;
	}

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

601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618
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:
619
		return -LIBBPF_ERRNO__ENDIAN;
620 621 622 623 624 625
	}

	return 0;

mismatch:
	pr_warning("Error: endianness mismatch.\n");
626
	return -LIBBPF_ERRNO__ENDIAN;
627 628
}

629 630 631 632 633 634 635 636 637 638 639 640 641 642
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)
{
643
	__u32 kver;
644 645 646

	if (size != sizeof(kver)) {
		pr_warning("invalid kver section in %s\n", obj->path);
647
		return -LIBBPF_ERRNO__FORMAT;
648 649 650 651 652 653 654 655
	}
	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
656 657 658 659
static int compare_bpf_map(const void *_a, const void *_b)
{
	const struct bpf_map *a = _a;
	const struct bpf_map *b = _b;
660

E
Eric Leblond 已提交
661
	return a->offset - b->offset;
662 663
}

664 665 666 667 668 669 670 671
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;
}

672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777
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;
}

778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823
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);
	}

	pr_debug("map %ld is \"%s\"\n", map - obj->maps, map->name);
	return 0;
}

824
static int
825
bpf_object__init_maps(struct bpf_object *obj, int flags)
826
{
827
	int i, map_idx, map_def_sz, nr_syms, nr_maps = 0, nr_maps_glob = 0;
828
	bool strict = !(flags & MAPS_RELAX_COMPAT);
829
	Elf_Data *symbols = obj->efile.symbols;
830 831
	Elf_Data *data = NULL;
	int ret = 0;
832

E
Eric Leblond 已提交
833 834
	if (!symbols)
		return -EINVAL;
835
	nr_syms = symbols->d_size / sizeof(GElf_Sym);
E
Eric Leblond 已提交
836

837 838 839 840 841 842 843 844 845 846 847
	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
848
	}
849

E
Eric Leblond 已提交
850 851 852 853 854 855 856
	/*
	 * 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.
	 */
857 858 859 860 861 862 863
	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++;
	for (i = 0; data && i < nr_syms; i++) {
864
		GElf_Sym sym;
E
Eric Leblond 已提交
865 866 867 868 869 870 871 872 873 874 875

		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);
876
	if (!nr_maps && !nr_maps_glob)
E
Eric Leblond 已提交
877 878
		return 0;

879
	/* Assume equally sized map definitions */
880 881 882 883 884 885 886 887
	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;
		}
888 889
	}

890
	nr_maps += nr_maps_glob;
E
Eric Leblond 已提交
891 892 893 894 895 896 897
	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;

898 899 900 901 902 903
	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
904
		obj->maps[i].fd = -1;
905 906
		obj->maps[i].inner_map_fd = -1;
	}
E
Eric Leblond 已提交
907 908 909 910

	/*
	 * Fill obj->maps using data in "maps" section.
	 */
911
	for (i = 0, map_idx = 0; data && i < nr_syms; i++) {
E
Eric Leblond 已提交
912
		GElf_Sym sym;
913
		const char *map_name;
E
Eric Leblond 已提交
914
		struct bpf_map_def *def;
915 916 917

		if (!gelf_getsym(symbols, i, &sym))
			continue;
918
		if (sym.st_shndx != obj->efile.maps_shndx)
919 920 921
			continue;

		map_name = elf_strptr(obj->efile.elf,
922
				      obj->efile.strtabidx,
923
				      sym.st_name);
924 925

		obj->maps[map_idx].libbpf_type = LIBBPF_MAP_UNSPEC;
E
Eric Leblond 已提交
926
		obj->maps[map_idx].offset = sym.st_value;
927
		if (sym.st_value + map_def_sz > data->d_size) {
E
Eric Leblond 已提交
928 929 930
			pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
				   obj->path, map_name);
			return -EINVAL;
931
		}
E
Eric Leblond 已提交
932

933
		obj->maps[map_idx].name = strdup(map_name);
934 935 936 937
		if (!obj->maps[map_idx].name) {
			pr_warning("failed to alloc map name\n");
			return -ENOMEM;
		}
E
Eric Leblond 已提交
938
		pr_debug("map %d is \"%s\"\n", map_idx,
939
			 obj->maps[map_idx].name);
E
Eric Leblond 已提交
940
		def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963
		/*
		 * 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);
964 965
					if (strict)
						return -EINVAL;
966 967 968 969 970
				}
			}
			memcpy(&obj->maps[map_idx].def, def,
			       sizeof(struct bpf_map_def));
		}
E
Eric Leblond 已提交
971
		map_idx++;
972
	}
E
Eric Leblond 已提交
973

974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994
	/*
	 * 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);
	if (!ret)
		qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]),
		      compare_bpf_map);
	return ret;
995 996
}

997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014
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;
}

1015
static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
1016 1017 1018
{
	Elf *elf = obj->efile.elf;
	GElf_Ehdr *ep = &obj->efile.ehdr;
1019
	Elf_Data *btf_ext_data = NULL;
1020
	Elf_Data *btf_data = NULL;
1021
	Elf_Scn *scn = NULL;
1022
	int idx = 0, err = 0;
1023 1024 1025 1026 1027

	/* 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);
1028
		return -LIBBPF_ERRNO__FORMAT;
1029 1030 1031 1032 1033 1034 1035 1036 1037
	}

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

		idx++;
		if (gelf_getshdr(scn, &sh) != &sh) {
1038 1039
			pr_warning("failed to get section(%d) header from %s\n",
				   idx, obj->path);
1040
			err = -LIBBPF_ERRNO__FORMAT;
1041 1042 1043 1044 1045
			goto out;
		}

		name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
		if (!name) {
1046 1047
			pr_warning("failed to get section(%d) name from %s\n",
				   idx, obj->path);
1048
			err = -LIBBPF_ERRNO__FORMAT;
1049 1050 1051 1052 1053
			goto out;
		}

		data = elf_getdata(scn, 0);
		if (!data) {
1054 1055
			pr_warning("failed to get section(%d) data from %s(%s)\n",
				   idx, name, obj->path);
1056
			err = -LIBBPF_ERRNO__FORMAT;
1057 1058
			goto out;
		}
1059 1060
		pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n",
			 idx, name, (unsigned long)data->d_size,
1061 1062
			 (int)sh.sh_link, (unsigned long)sh.sh_flags,
			 (int)sh.sh_type);
1063

1064
		if (strcmp(name, "license") == 0) {
1065 1066 1067
			err = bpf_object__init_license(obj,
						       data->d_buf,
						       data->d_size);
1068
		} else if (strcmp(name, "version") == 0) {
1069 1070 1071
			err = bpf_object__init_kversion(obj,
							data->d_buf,
							data->d_size);
1072
		} else if (strcmp(name, "maps") == 0) {
1073
			obj->efile.maps_shndx = idx;
1074 1075
		} else if (strcmp(name, BTF_ELF_SEC) == 0) {
			btf_data = data;
1076
		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
1077
			btf_ext_data = data;
1078
		} else if (sh.sh_type == SHT_SYMTAB) {
1079 1080 1081
			if (obj->efile.symbols) {
				pr_warning("bpf: multiple SYMTAB in %s\n",
					   obj->path);
1082
				err = -LIBBPF_ERRNO__FORMAT;
1083
			} else {
1084
				obj->efile.symbols = data;
1085 1086
				obj->efile.strtabidx = sh.sh_link;
			}
1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100
		} 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);
				}
1101 1102 1103 1104 1105 1106 1107 1108
			} 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);
1109
			}
1110 1111 1112
		} else if (sh.sh_type == SHT_REL) {
			void *reloc = obj->efile.reloc;
			int nr_reloc = obj->efile.nr_reloc + 1;
1113 1114 1115 1116 1117 1118 1119 1120
			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;
			}
1121

1122 1123
			reloc = reallocarray(reloc, nr_reloc,
					     sizeof(*obj->efile.reloc));
1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135
			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;
			}
1136 1137 1138
		} else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) {
			obj->efile.bss = data;
			obj->efile.bss_shndx = idx;
1139 1140
		} else {
			pr_debug("skip section(%d) %s\n", idx, name);
1141
		}
1142 1143
		if (err)
			goto out;
1144
	}
1145

1146 1147 1148 1149
	if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
		pr_warning("Corrupted ELF file: index of strtab invalid\n");
		return LIBBPF_ERRNO__FORMAT;
	}
1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168
	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;
			}
		}
	}
1169 1170 1171 1172 1173 1174
	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,
1175
						    btf_ext_data->d_size);
1176 1177 1178 1179 1180 1181 1182 1183
			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;
			}
		}
	}
1184
	if (bpf_object__has_maps(obj)) {
1185
		err = bpf_object__init_maps(obj, flags);
1186 1187 1188 1189
		if (err)
			goto out;
	}
	err = bpf_object__init_prog_names(obj);
1190 1191 1192 1193
out:
	return err;
}

1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207
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;
}

1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219
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;
}

1220 1221 1222 1223 1224 1225 1226 1227 1228 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
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;
}

1255
static int
1256 1257
bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
			   Elf_Data *data, struct bpf_object *obj)
1258
{
1259 1260 1261
	Elf_Data *symbols = obj->efile.symbols;
	struct bpf_map *maps = obj->maps;
	size_t nr_maps = obj->nr_maps;
1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278
	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;
1279
		unsigned int shdr_idx;
1280
		struct bpf_insn *insns = prog->insns;
1281 1282
		enum libbpf_map_type type;
		const char *name;
1283 1284 1285 1286
		size_t map_idx;

		if (!gelf_getrel(data, i, &rel)) {
			pr_warning("relocation: failed to get %d reloc\n", i);
1287
			return -LIBBPF_ERRNO__FORMAT;
1288 1289 1290 1291 1292 1293 1294
		}

		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));
1295
			return -LIBBPF_ERRNO__FORMAT;
1296
		}
1297 1298 1299 1300 1301

		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
1302
			 (long long) (rel.r_info >> 32),
1303
			 (long long) sym.st_value, sym.st_name, name);
1304

1305 1306 1307 1308
		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);
1309 1310 1311 1312 1313 1314
			return -LIBBPF_ERRNO__RELOC;
		}

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

1315 1316 1317 1318 1319 1320 1321 1322
		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;
1323
			obj->has_pseudo_calls = true;
1324 1325 1326
			continue;
		}

1327 1328 1329
		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);
1330
			return -LIBBPF_ERRNO__RELOC;
1331 1332
		}

1333 1334 1335 1336 1337 1338 1339 1340 1341 1342
		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);
			if (type != LIBBPF_MAP_UNSPEC &&
			    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;
			}

1343
			for (map_idx = 0; map_idx < nr_maps; map_idx++) {
1344 1345 1346 1347 1348
				if (maps[map_idx].libbpf_type != type)
					continue;
				if (type != LIBBPF_MAP_UNSPEC ||
				    (type == LIBBPF_MAP_UNSPEC &&
				     maps[map_idx].offset == sym.st_value)) {
1349 1350 1351 1352
					pr_debug("relocation: find map %zd (%s) for insn %u\n",
						 map_idx, maps[map_idx].name, insn_idx);
					break;
				}
1353 1354
			}

1355 1356 1357 1358 1359
			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;
			}
1360

1361 1362
			prog->reloc_desc[i].type = type != LIBBPF_MAP_UNSPEC ?
						   RELO_DATA : RELO_LD64;
1363 1364 1365
			prog->reloc_desc[i].insn_idx = insn_idx;
			prog->reloc_desc[i].map_idx = map_idx;
		}
1366 1367 1368 1369
	}
	return 0;
}

1370 1371 1372
static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
{
	struct bpf_map_def *def = &map->def;
1373
	__u32 key_type_id = 0, value_type_id = 0;
1374
	int ret;
1375

1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388
	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)
1389
		return ret;
1390

1391
	map->btf_key_type_id = key_type_id;
1392 1393
	map->btf_value_type_id = bpf_map__is_internal(map) ?
				 ret : value_type_id;
1394 1395 1396
	return 0;
}

J
Jakub Kicinski 已提交
1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 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
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;
}

1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457
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;
}

1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503
static int
bpf_object__probe_name(struct bpf_object *obj)
{
	struct bpf_load_program_attr attr;
	char *cp, errmsg[STRERR_BUFSIZE];
	struct bpf_insn insns[] = {
		BPF_MOV64_IMM(BPF_REG_0, 0),
		BPF_EXIT_INSN(),
	};
	int ret;

	/* make sure basic loading works */

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

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

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

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

	return 0;
}

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

1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531
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;
}

1532 1533 1534
static int
bpf_object__create_maps(struct bpf_object *obj)
{
1535
	struct bpf_create_map_attr create_attr = {};
1536
	unsigned int i;
1537
	int err;
1538

1539
	for (i = 0; i < obj->nr_maps; i++) {
1540 1541
		struct bpf_map *map = &obj->maps[i];
		struct bpf_map_def *def = &map->def;
1542
		char *cp, errmsg[STRERR_BUFSIZE];
1543 1544
		int *pfd = &map->fd;

J
Jakub Kicinski 已提交
1545 1546 1547 1548 1549 1550
		if (map->fd >= 0) {
			pr_debug("skip map create (preset) %s: fd=%d\n",
				 map->name, map->fd);
			continue;
		}

1551 1552
		if (obj->caps.name)
			create_attr.name = map->name;
1553
		create_attr.map_ifindex = map->map_ifindex;
1554 1555 1556 1557 1558 1559
		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;
1560 1561
		create_attr.btf_key_type_id = 0;
		create_attr.btf_value_type_id = 0;
1562 1563 1564
		if (bpf_map_type__is_map_in_map(def->type) &&
		    map->inner_map_fd >= 0)
			create_attr.inner_map_fd = map->inner_map_fd;
1565 1566 1567

		if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) {
			create_attr.btf_fd = btf__fd(obj->btf);
1568 1569
			create_attr.btf_key_type_id = map->btf_key_type_id;
			create_attr.btf_value_type_id = map->btf_value_type_id;
1570 1571 1572
		}

		*pfd = bpf_create_map_xattr(&create_attr);
1573
		if (*pfd < 0 && create_attr.btf_key_type_id) {
1574
			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1575
			pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
1576
				   map->name, cp, errno);
1577
			create_attr.btf_fd = 0;
1578 1579 1580 1581
			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;
1582 1583 1584
			*pfd = bpf_create_map_xattr(&create_attr);
		}

1585 1586 1587
		if (*pfd < 0) {
			size_t j;

1588
			err = *pfd;
1589
err_out:
1590
			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
E
Eric Leblond 已提交
1591
			pr_warning("failed to create map (name: '%s'): %s\n",
1592
				   map->name, cp);
1593
			for (j = 0; j < i; j++)
1594
				zclose(obj->maps[j].fd);
1595 1596
			return err;
		}
1597 1598 1599 1600 1601 1602 1603 1604 1605

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

1606
		pr_debug("create map %s: fd=%d\n", map->name, *pfd);
1607 1608 1609 1610 1611
	}

	return 0;
}

1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668
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);
	}

1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681
	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);
	}

1682 1683 1684 1685 1686 1687
	if (!insn_offset)
		prog->btf_fd = btf__fd(obj->btf);

	return 0;
}

1688 1689 1690 1691 1692 1693 1694
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;
1695
	int err;
1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712

	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;
1713
		new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn));
1714 1715 1716 1717
		if (!new_insn) {
			pr_warning("oom in prog realloc\n");
			return -ENOMEM;
		}
1718

1719 1720 1721 1722 1723
		if (obj->btf_ext) {
			err = bpf_program_reloc_btf_ext(prog, obj,
							text->section_name,
							prog->insns_cnt);
			if (err)
1724 1725 1726
				return err;
		}

1727 1728 1729 1730 1731
		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;
1732 1733 1734
		pr_debug("added %zd insn from %s to prog %s\n",
			 text->insns_cnt, text->section_name,
			 prog->section_name);
1735 1736 1737 1738 1739 1740
	}
	insn = &prog->insns[relo->insn_idx];
	insn->imm += prog->main_prog_cnt - relo->insn_idx;
	return 0;
}

W
Wang Nan 已提交
1741
static int
1742
bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
W
Wang Nan 已提交
1743
{
1744
	int i, err;
W
Wang Nan 已提交
1745

1746 1747 1748
	if (!prog)
		return 0;

1749 1750 1751 1752
	if (obj->btf_ext) {
		err = bpf_program_reloc_btf_ext(prog, obj,
						prog->section_name, 0);
		if (err)
1753 1754 1755 1756
			return err;
	}

	if (!prog->reloc_desc)
W
Wang Nan 已提交
1757 1758 1759
		return 0;

	for (i = 0; i < prog->nr_reloc; i++) {
1760 1761 1762
		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;
1763 1764
			struct bpf_insn *insns = prog->insns;
			int insn_idx, map_idx;
W
Wang Nan 已提交
1765

1766 1767
			insn_idx = prog->reloc_desc[i].insn_idx;
			map_idx = prog->reloc_desc[i].map_idx;
W
Wang Nan 已提交
1768

1769
			if (insn_idx + 1 >= (int)prog->insns_cnt) {
1770 1771 1772 1773
				pr_warning("relocation out of range: '%s'\n",
					   prog->section_name);
				return -LIBBPF_ERRNO__RELOC;
			}
1774 1775 1776 1777 1778 1779 1780

			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;
			}
1781
			insns[insn_idx].imm = obj->maps[map_idx].fd;
1782
		} else if (prog->reloc_desc[i].type == RELO_CALL) {
1783 1784 1785 1786
			err = bpf_program__reloc_text(prog, obj,
						      &prog->reloc_desc[i]);
			if (err)
				return err;
W
Wang Nan 已提交
1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805
		}
	}

	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];

1806
		err = bpf_program__relocate(prog, obj);
W
Wang Nan 已提交
1807 1808 1809 1810 1811 1812 1813 1814 1815
		if (err) {
			pr_warning("failed to relocate '%s'\n",
				   prog->section_name);
			return err;
		}
	}
	return 0;
}

1816 1817 1818 1819 1820 1821
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");
1822
		return -LIBBPF_ERRNO__INTERNAL;
1823 1824 1825 1826 1827 1828 1829 1830 1831 1832
	}

	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__);
1833
			return -LIBBPF_ERRNO__INTERNAL;
1834 1835 1836 1837
		}

		prog = bpf_object__find_prog_by_idx(obj, idx);
		if (!prog) {
1838
			pr_warning("relocation failed: no section(%d)\n", idx);
1839
			return -LIBBPF_ERRNO__RELOC;
1840 1841
		}

1842
		err = bpf_program__collect_reloc(prog,
1843
						 shdr, data,
1844
						 obj);
1845
		if (err)
1846
			return err;
1847 1848 1849 1850
	}
	return 0;
}

1851
static int
1852
load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
1853
	     char *license, __u32 kern_version, int *pfd)
1854
{
1855
	struct bpf_load_program_attr load_attr;
1856
	char *cp, errmsg[STRERR_BUFSIZE];
1857
	int log_buf_size = BPF_LOG_BUF_SIZE;
1858
	char *log_buf;
1859
	int ret;
1860

1861
	memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
1862 1863
	load_attr.prog_type = prog->type;
	load_attr.expected_attach_type = prog->expected_attach_type;
1864 1865
	if (prog->caps->name)
		load_attr.name = prog->name;
1866 1867 1868 1869
	load_attr.insns = insns;
	load_attr.insns_cnt = insns_cnt;
	load_attr.license = license;
	load_attr.kern_version = kern_version;
1870
	load_attr.prog_ifindex = prog->prog_ifindex;
Y
Yonghong Song 已提交
1871
	load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0;
1872 1873
	load_attr.func_info = prog->func_info;
	load_attr.func_info_rec_size = prog->func_info_rec_size;
1874
	load_attr.func_info_cnt = prog->func_info_cnt;
1875 1876 1877
	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;
1878
	load_attr.log_level = prog->log_level;
1879
	if (!load_attr.insns || !load_attr.insns_cnt)
1880 1881
		return -EINVAL;

1882 1883
retry_load:
	log_buf = malloc(log_buf_size);
1884 1885 1886
	if (!log_buf)
		pr_warning("Alloc log buffer for bpf loader error, continue without log\n");

1887
	ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size);
1888 1889

	if (ret >= 0) {
1890 1891
		if (load_attr.log_level)
			pr_debug("verifier log:\n%s", log_buf);
1892 1893 1894 1895 1896
		*pfd = ret;
		ret = 0;
		goto out;
	}

1897 1898 1899 1900 1901
	if (errno == ENOSPC) {
		log_buf_size <<= 1;
		free(log_buf);
		goto retry_load;
	}
1902
	ret = -LIBBPF_ERRNO__LOAD;
1903
	cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1904
	pr_warning("load bpf program failed: %s\n", cp);
1905

1906 1907
	if (log_buf && log_buf[0] != '\0') {
		ret = -LIBBPF_ERRNO__VERIFY;
1908 1909 1910
		pr_warning("-- BEGIN DUMP LOG ---\n");
		pr_warning("\n%s\n", log_buf);
		pr_warning("-- END LOG --\n");
1911 1912 1913
	} 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);
1914
		ret = -LIBBPF_ERRNO__PROG2BIG;
1915
	} else {
1916
		/* Wrong program type? */
1917
		if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) {
1918 1919
			int fd;

1920 1921 1922
			load_attr.prog_type = BPF_PROG_TYPE_KPROBE;
			load_attr.expected_attach_type = 0;
			fd = bpf_load_program_xattr(&load_attr, NULL, 0);
1923 1924 1925 1926 1927
			if (fd >= 0) {
				close(fd);
				ret = -LIBBPF_ERRNO__PROGTYPE;
				goto out;
			}
1928
		}
1929 1930 1931

		if (log_buf)
			ret = -LIBBPF_ERRNO__KVER;
1932 1933 1934 1935 1936 1937 1938
	}

out:
	free(log_buf);
	return ret;
}

1939
int
1940
bpf_program__load(struct bpf_program *prog,
1941
		  char *license, __u32 kern_version)
1942
{
1943
	int err = 0, fd, i;
1944

1945 1946 1947 1948 1949 1950
	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;
		}
1951

1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965
		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);
		}
1966
		err = load_program(prog, prog->insns, prog->insns_cnt,
1967
				   license, kern_version, &fd);
1968 1969 1970 1971 1972 1973 1974 1975 1976
		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;

1977
		memset(&result, 0, sizeof(result));
1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994
		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;
		}

1995
		err = load_program(prog, result.new_insn_ptr,
1996
				   result.new_insn_cnt,
1997
				   license, kern_version, &fd);
1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009

		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:
2010 2011 2012 2013 2014 2015 2016 2017
	if (err)
		pr_warning("failed to load program '%s'\n",
			   prog->section_name);
	zfree(&prog->insns);
	prog->insns_cnt = 0;
	return err;
}

2018 2019 2020 2021 2022 2023
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;
}

2024 2025 2026 2027 2028 2029 2030
static int
bpf_object__load_progs(struct bpf_object *obj)
{
	size_t i;
	int err;

	for (i = 0; i < obj->nr_programs; i++) {
2031
		if (bpf_program__is_function_storage(&obj->programs[i], obj))
2032
			continue;
2033 2034 2035 2036 2037 2038 2039 2040 2041
		err = bpf_program__load(&obj->programs[i],
					obj->license,
					obj->kern_version);
		if (err)
			return err;
	}
	return 0;
}

2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053
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:
2054
	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
2055 2056 2057 2058 2059
	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:
2060
	case BPF_PROG_TYPE_LIRC_MODE2:
2061
	case BPF_PROG_TYPE_SK_REUSEPORT:
2062
	case BPF_PROG_TYPE_FLOW_DISSECTOR:
2063 2064 2065
	case BPF_PROG_TYPE_UNSPEC:
	case BPF_PROG_TYPE_TRACEPOINT:
	case BPF_PROG_TYPE_RAW_TRACEPOINT:
2066 2067 2068
	case BPF_PROG_TYPE_PERF_EVENT:
		return false;
	case BPF_PROG_TYPE_KPROBE:
2069 2070 2071 2072 2073 2074
	default:
		return true;
	}
}

static int bpf_object__validate(struct bpf_object *obj, bool needs_kver)
2075
{
2076
	if (needs_kver && obj->kern_version == 0) {
2077 2078
		pr_warning("%s doesn't provide kernel version\n",
			   obj->path);
2079
		return -LIBBPF_ERRNO__KVERSION;
2080 2081 2082 2083
	}
	return 0;
}

2084
static struct bpf_object *
2085
__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
2086
		   bool needs_kver, int flags)
2087 2088
{
	struct bpf_object *obj;
2089
	int err;
2090 2091 2092

	if (elf_version(EV_CURRENT) == EV_NONE) {
		pr_warning("failed to init libelf for %s\n", path);
2093
		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
2094 2095
	}

2096
	obj = bpf_object__new(path, obj_buf, obj_buf_sz);
2097 2098
	if (IS_ERR(obj))
		return obj;
2099

2100 2101
	CHECK_ERR(bpf_object__elf_init(obj), err, out);
	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
2102
	CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out);
2103
	CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
2104
	CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out);
2105 2106 2107 2108 2109

	bpf_object__elf_finish(obj);
	return obj;
out:
	bpf_object__close(obj);
2110
	return ERR_PTR(err);
2111 2112
}

2113 2114
struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
					    int flags)
2115 2116
{
	/* param validation */
2117
	if (!attr->file)
2118 2119
		return NULL;

2120 2121 2122
	pr_debug("loading %s\n", attr->file);

	return __bpf_object__open(attr->file, NULL, 0,
2123 2124 2125 2126 2127 2128 2129
				  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);
2130 2131 2132 2133 2134 2135 2136 2137
}

struct bpf_object *bpf_object__open(const char *path)
{
	struct bpf_object_open_attr attr = {
		.file		= path,
		.prog_type	= BPF_PROG_TYPE_UNSPEC,
	};
2138

2139
	return bpf_object__open_xattr(&attr);
2140 2141 2142
}

struct bpf_object *bpf_object__open_buffer(void *obj_buf,
2143 2144
					   size_t obj_buf_sz,
					   const char *name)
2145
{
2146 2147
	char tmp_name[64];

2148 2149 2150 2151
	/* param validation */
	if (!obj_buf || obj_buf_sz <= 0)
		return NULL;

2152 2153 2154 2155 2156 2157 2158 2159 2160
	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);
2161

2162
	return __bpf_object__open(name, obj_buf, obj_buf_sz, true, true);
2163 2164
}

2165 2166 2167 2168 2169 2170 2171
int bpf_object__unload(struct bpf_object *obj)
{
	size_t i;

	if (!obj)
		return -EINVAL;

2172 2173
	for (i = 0; i < obj->nr_maps; i++)
		zclose(obj->maps[i].fd);
2174

2175 2176 2177
	for (i = 0; i < obj->nr_programs; i++)
		bpf_program__unload(&obj->programs[i]);

2178 2179 2180 2181 2182
	return 0;
}

int bpf_object__load(struct bpf_object *obj)
{
2183 2184
	int err;

2185 2186 2187 2188 2189 2190 2191 2192 2193
	if (!obj)
		return -EINVAL;

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

	obj->loaded = true;
2194

2195
	CHECK_ERR(bpf_object__probe_caps(obj), err, out);
2196 2197 2198
	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);
2199 2200 2201 2202 2203

	return 0;
out:
	bpf_object__unload(obj);
	pr_warning("failed to load object '%s'\n", obj->path);
2204
	return err;
2205 2206
}

2207 2208
static int check_path(const char *path)
{
2209
	char *cp, errmsg[STRERR_BUFSIZE];
2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222
	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)) {
2223
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
2224
		pr_warning("failed to statfs %s: %s\n", dir, cp);
2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239
		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)
{
2240
	char *cp, errmsg[STRERR_BUFSIZE];
2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258
	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)) {
2259
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
2260
		pr_warning("failed to pin program: %s\n", cp);
2261 2262 2263 2264 2265 2266 2267
		return -errno;
	}
	pr_debug("pinned program '%s'\n", path);

	return 0;
}

2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295
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;
}

2296 2297
static int make_dir(const char *path)
{
2298
	char *cp, errmsg[STRERR_BUFSIZE];
2299 2300 2301 2302 2303
	int err = 0;

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

2304
	if (err) {
2305
		cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
2306 2307
		pr_warning("failed to mkdir %s: %s\n", path, cp);
	}
2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329
	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;
	}

2330 2331 2332 2333 2334
	if (prog->instances.nr == 1) {
		/* don't create subdirs when pinning single instance */
		return bpf_program__pin_instance(prog, path, 0);
	}

2335 2336 2337 2338
	err = make_dir(path);
	if (err)
		return err;

2339 2340 2341 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 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394
	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;
2395 2396 2397 2398 2399
	}

	if (prog->instances.nr == 1) {
		/* don't create subdirs when pinning single instance */
		return bpf_program__unpin_instance(prog, path, 0);
2400 2401
	}

2402 2403 2404 2405 2406 2407 2408 2409 2410 2411
	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;

2412
		err = bpf_program__unpin_instance(prog, buf, i);
2413 2414 2415 2416
		if (err)
			return err;
	}

2417 2418 2419 2420
	err = rmdir(path);
	if (err)
		return -errno;

2421 2422 2423
	return 0;
}

J
Joe Stringer 已提交
2424 2425
int bpf_map__pin(struct bpf_map *map, const char *path)
{
2426
	char *cp, errmsg[STRERR_BUFSIZE];
J
Joe Stringer 已提交
2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438
	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)) {
2439
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
2440
		pr_warning("failed to pin map: %s\n", cp);
J
Joe Stringer 已提交
2441 2442 2443 2444
		return -errno;
	}

	pr_debug("pinned map '%s'\n", path);
2445

J
Joe Stringer 已提交
2446 2447 2448
	return 0;
}

2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470
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)
2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486
{
	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;

2487
	bpf_object__for_each_map(map, obj) {
2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533
		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;

2534
	bpf_object__for_each_map(map, obj) {
2535 2536 2537 2538 2539 2540 2541 2542 2543 2544
		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;

2545
		err = bpf_map__unpin(map, buf);
2546 2547 2548 2549
		if (err)
			return err;
	}

2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574
	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
2575
			       prog->pin_name);
2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596
		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
2597
			       prog->pin_name);
2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616
		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;

2617 2618 2619 2620 2621
	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
2622
			       prog->pin_name);
2623 2624 2625 2626 2627
		if (len < 0)
			return -EINVAL;
		else if (len >= PATH_MAX)
			return -ENAMETOOLONG;

2628
		err = bpf_program__unpin(prog, buf);
2629 2630 2631 2632 2633 2634 2635
		if (err)
			return err;
	}

	return 0;
}

2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652
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;
}

2653 2654
void bpf_object__close(struct bpf_object *obj)
{
2655 2656
	size_t i;

2657 2658 2659
	if (!obj)
		return;

2660 2661 2662
	if (obj->clear_priv)
		obj->clear_priv(obj, obj->priv);

2663
	bpf_object__elf_finish(obj);
2664
	bpf_object__unload(obj);
2665
	btf__free(obj->btf);
2666
	btf_ext__free(obj->btf_ext);
2667

2668
	for (i = 0; i < obj->nr_maps; i++) {
2669
		zfree(&obj->maps[i].name);
2670 2671 2672 2673 2674 2675
		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;
	}
2676 2677 2678

	zfree(&obj->sections.rodata);
	zfree(&obj->sections.data);
2679 2680
	zfree(&obj->maps);
	obj->nr_maps = 0;
2681 2682 2683 2684 2685 2686 2687

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

2688
	list_del(&obj->list);
2689 2690
	free(obj);
}
2691

2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710
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;
}

2711
const char *bpf_object__name(struct bpf_object *obj)
2712
{
2713
	return obj ? obj->path : ERR_PTR(-EINVAL);
2714 2715
}

2716
unsigned int bpf_object__kversion(struct bpf_object *obj)
2717
{
2718
	return obj ? obj->kern_version : 0;
2719 2720
}

2721 2722 2723 2724 2725
struct btf *bpf_object__btf(struct bpf_object *obj)
{
	return obj ? obj->btf : NULL;
}

2726 2727 2728 2729 2730
int bpf_object__btf_fd(const struct bpf_object *obj)
{
	return obj->btf ? btf__fd(obj->btf) : -1;
}

2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746
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);
}

2747
static struct bpf_program *
2748
__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward)
2749
{
2750
	size_t nr_programs = obj->nr_programs;
2751
	ssize_t idx;
2752

2753
	if (!nr_programs)
2754 2755
		return NULL;

2756 2757 2758 2759 2760
	if (!p)
		/* Iter from the beginning */
		return forward ? &obj->programs[0] :
			&obj->programs[nr_programs - 1];

2761
	if (p->obj != obj) {
2762 2763 2764 2765
		pr_warning("error: program handler doesn't match object\n");
		return NULL;
	}

2766
	idx = (p - obj->programs) + (forward ? 1 : -1);
2767
	if (idx >= obj->nr_programs || idx < 0)
2768 2769 2770 2771
		return NULL;
	return &obj->programs[idx];
}

2772 2773 2774 2775 2776 2777
struct bpf_program *
bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
{
	struct bpf_program *prog = prev;

	do {
2778
		prog = __bpf_program__iter(prog, obj, true);
2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789
	} 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 {
2790
		prog = __bpf_program__iter(prog, obj, false);
2791 2792 2793 2794 2795
	} while (prog && bpf_program__is_function_storage(prog, obj));

	return prog;
}

2796 2797
int bpf_program__set_priv(struct bpf_program *prog, void *priv,
			  bpf_program_clear_priv_t clear_priv)
2798 2799 2800 2801 2802 2803 2804 2805 2806
{
	if (prog->priv && prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

2807
void *bpf_program__priv(struct bpf_program *prog)
2808
{
2809
	return prog ? prog->priv : ERR_PTR(-EINVAL);
2810 2811
}

2812 2813 2814 2815 2816
void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex)
{
	prog->prog_ifindex = ifindex;
}

2817
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
2818 2819 2820 2821
{
	const char *title;

	title = prog->section_name;
2822
	if (needs_copy) {
2823 2824 2825
		title = strdup(title);
		if (!title) {
			pr_warning("failed to strdup program title\n");
2826
			return ERR_PTR(-ENOMEM);
2827 2828 2829 2830 2831 2832 2833 2834
		}
	}

	return title;
}

int bpf_program__fd(struct bpf_program *prog)
{
2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869
	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;

2870 2871 2872
	if (!prog)
		return -EINVAL;

2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886
	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;
2887
}
2888

2889
void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
2890 2891 2892 2893 2894 2895 2896 2897 2898 2899
{
	prog->type = type;
}

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

2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913
#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);	\
}							\

2914
BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
2915
BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
2916 2917
BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
2918
BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
2919
BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT);
2920 2921
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
2922

J
John Fastabend 已提交
2923 2924
void bpf_program__set_expected_attach_type(struct bpf_program *prog,
					   enum bpf_attach_type type)
2925 2926 2927 2928
{
	prog->expected_attach_type = type;
}

2929 2930
#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, atype) \
	{ string, sizeof(string) - 1, ptype, eatype, is_attachable, atype }
2931

2932
/* Programs that can NOT be attached. */
2933
#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0)
2934

2935 2936
/* Programs that can be attached. */
#define BPF_APROG_SEC(string, ptype, atype) \
2937
	BPF_PROG_SEC_IMPL(string, ptype, 0, 1, atype)
2938

2939 2940
/* Programs that must specify expected attach type at load time. */
#define BPF_EAPROG_SEC(string, ptype, eatype) \
2941
	BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, eatype)
2942 2943 2944 2945 2946

/* 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)
2947

2948 2949 2950 2951
static const struct {
	const char *sec;
	size_t len;
	enum bpf_prog_type prog_type;
2952
	enum bpf_attach_type expected_attach_type;
2953
	int is_attachable;
2954
	enum bpf_attach_type attach_type;
2955
} section_names[] = {
2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968
	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),
2969 2970 2971 2972
	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),
2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983
	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),
2984 2985 2986 2987
	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),
2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006
	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),
3007
};
3008

3009
#undef BPF_PROG_SEC_IMPL
3010
#undef BPF_PROG_SEC
3011 3012 3013
#undef BPF_APROG_SEC
#undef BPF_EAPROG_SEC
#undef BPF_APROG_COMPAT
3014

3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042
#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;
}

3043 3044
int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
			     enum bpf_attach_type *expected_attach_type)
3045
{
3046
	char *type_names;
3047 3048
	int i;

3049 3050
	if (!name)
		return -EINVAL;
3051

3052 3053 3054 3055 3056 3057 3058
	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;
	}
3059 3060 3061 3062 3063 3064 3065
	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);
	}

3066 3067
	return -EINVAL;
}
3068

3069 3070 3071
int libbpf_attach_type_by_name(const char *name,
			       enum bpf_attach_type *attach_type)
{
3072
	char *type_names;
3073 3074 3075 3076 3077 3078 3079 3080
	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;
3081
		if (!section_names[i].is_attachable)
3082 3083 3084 3085
			return -EINVAL;
		*attach_type = section_names[i].attach_type;
		return 0;
	}
3086 3087 3088 3089 3090 3091 3092
	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);
	}

3093 3094 3095
	return -EINVAL;
}

3096 3097 3098 3099 3100 3101 3102
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);
3103 3104
}

3105
int bpf_map__fd(struct bpf_map *map)
3106
{
3107
	return map ? map->fd : -EINVAL;
3108 3109
}

3110
const struct bpf_map_def *bpf_map__def(struct bpf_map *map)
3111
{
3112
	return map ? &map->def : ERR_PTR(-EINVAL);
3113 3114
}

3115
const char *bpf_map__name(struct bpf_map *map)
3116
{
3117
	return map ? map->name : NULL;
3118 3119
}

3120
__u32 bpf_map__btf_key_type_id(const struct bpf_map *map)
3121
{
3122
	return map ? map->btf_key_type_id : 0;
3123 3124
}

3125
__u32 bpf_map__btf_value_type_id(const struct bpf_map *map)
3126
{
3127
	return map ? map->btf_value_type_id : 0;
3128 3129
}

3130 3131
int bpf_map__set_priv(struct bpf_map *map, void *priv,
		     bpf_map_clear_priv_t clear_priv)
3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145
{
	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;
}

3146
void *bpf_map__priv(struct bpf_map *map)
3147
{
3148
	return map ? map->priv : ERR_PTR(-EINVAL);
3149 3150
}

3151 3152 3153 3154 3155
bool bpf_map__is_offload_neutral(struct bpf_map *map)
{
	return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
}

3156 3157 3158 3159 3160
bool bpf_map__is_internal(struct bpf_map *map)
{
	return map->libbpf_type != LIBBPF_MAP_UNSPEC;
}

3161 3162 3163 3164 3165
void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
{
	map->map_ifindex = ifindex;
}

3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179
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;
}

3180 3181
static struct bpf_map *
__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i)
3182
{
3183
	ssize_t idx;
3184 3185 3186 3187 3188 3189 3190 3191
	struct bpf_map *s, *e;

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

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

3192
	if ((m < s) || (m >= e)) {
3193 3194 3195 3196 3197
		pr_warning("error in %s: map handler doesn't belong to object\n",
			   __func__);
		return NULL;
	}

3198 3199
	idx = (m - obj->maps) + i;
	if (idx >= obj->nr_maps || idx < 0)
3200 3201 3202
		return NULL;
	return &obj->maps[idx];
}
3203

3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224
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);
}

3225
struct bpf_map *
3226
bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
3227 3228 3229
{
	struct bpf_map *pos;

3230
	bpf_object__for_each_map(pos, obj) {
3231
		if (pos->name && !strcmp(pos->name, name))
3232 3233 3234 3235
			return pos;
	}
	return NULL;
}
3236

3237 3238 3239 3240 3241 3242
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));
}

3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253
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);
}
3254 3255 3256 3257 3258 3259 3260

long libbpf_get_error(const void *ptr)
{
	if (IS_ERR(ptr))
		return PTR_ERR(ptr);
	return 0;
}
3261 3262 3263

int bpf_prog_load(const char *file, enum bpf_prog_type type,
		  struct bpf_object **pobj, int *prog_fd)
3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276
{
	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)
3277
{
3278 3279 3280 3281
	struct bpf_object_open_attr open_attr = {
		.file		= attr->file,
		.prog_type	= attr->prog_type,
	};
3282
	struct bpf_program *prog, *first_prog = NULL;
3283 3284
	enum bpf_attach_type expected_attach_type;
	enum bpf_prog_type prog_type;
3285
	struct bpf_object *obj;
3286
	struct bpf_map *map;
3287 3288
	int err;

3289 3290
	if (!attr)
		return -EINVAL;
3291 3292
	if (!attr->file)
		return -EINVAL;
3293

3294
	obj = bpf_object__open_xattr(&open_attr);
3295
	if (IS_ERR_OR_NULL(obj))
3296 3297
		return -ENOENT;

3298 3299 3300 3301 3302
	bpf_object__for_each_program(prog, obj) {
		/*
		 * If type is not specified, try to guess it based on
		 * section name.
		 */
3303
		prog_type = attr->prog_type;
3304
		prog->prog_ifindex = attr->ifindex;
3305 3306
		expected_attach_type = attr->expected_attach_type;
		if (prog_type == BPF_PROG_TYPE_UNSPEC) {
3307 3308 3309
			err = bpf_program__identify_section(prog, &prog_type,
							    &expected_attach_type);
			if (err < 0) {
3310 3311 3312
				bpf_object__close(obj);
				return -EINVAL;
			}
3313
		}
3314

3315 3316 3317 3318
		bpf_program__set_type(prog, prog_type);
		bpf_program__set_expected_attach_type(prog,
						      expected_attach_type);

3319
		prog->log_level = attr->log_level;
3320
		if (!first_prog)
3321 3322 3323
			first_prog = prog;
	}

3324
	bpf_object__for_each_map(map, obj) {
3325 3326
		if (!bpf_map__is_offload_neutral(map))
			map->map_ifindex = attr->ifindex;
3327 3328
	}

3329 3330 3331 3332
	if (!first_prog) {
		pr_warning("object file doesn't contain bpf program\n");
		bpf_object__close(obj);
		return -ENOENT;
3333 3334
	}

3335 3336 3337 3338 3339 3340 3341
	err = bpf_object__load(obj);
	if (err) {
		bpf_object__close(obj);
		return -EINVAL;
	}

	*pobj = obj;
3342
	*prog_fd = bpf_program__fd(first_prog);
3343 3344
	return 0;
}
3345 3346

enum bpf_perf_event_ret
3347 3348 3349
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)
3350
{
3351
	struct perf_event_mmap_page *header = mmap_mem;
3352
	__u64 data_head = ring_buffer_read_head(header);
3353
	__u64 data_tail = header->data_tail;
3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372
	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;
3373 3374 3375
					ret = LIBBPF_PERF_EVENT_ERROR;
					break;
				}
3376
				*copy_size = ehdr_size;
3377 3378
			}

3379 3380 3381
			memcpy(*copy_mem, copy_start, len_first);
			memcpy(*copy_mem + len_first, base, len_secnd);
			ehdr = *copy_mem;
3382 3383
		}

3384 3385
		ret = fn(ehdr, private_data);
		data_tail += ehdr_size;
3386 3387 3388 3389
		if (ret != LIBBPF_PERF_EVENT_CONT)
			break;
	}

3390
	ring_buffer_write_tail(header, data_tail);
3391 3392
	return ret;
}
3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 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

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);
	}
}