libbpf.c 101.5 KB
Newer Older
1
// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
2

3 4 5 6 7 8
/*
 * Common eBPF ELF object loading operations.
 *
 * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
 * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
 * Copyright (C) 2015 Huawei Inc.
9
 * Copyright (C) 2017 Nicira, Inc.
10
 * 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_internal.h"
47

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

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

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

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

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

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

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

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

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

84 85 86
	if (!__libbpf_pr)
		return;

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

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

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


101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120
/* Copied from tools/perf/util/util.h */
#ifndef zfree
# define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
#endif

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

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

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

126 127 128
struct bpf_capabilities {
	/* v4.14: kernel support for program & map names. */
	__u32 name:1;
129 130
	/* v5.2: kernel support for global data sections. */
	__u32 global_data:1;
131 132 133 134
	/* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */
	__u32 btf_func:1;
	/* BTF_KIND_VAR and BTF_KIND_DATASEC support */
	__u32 btf_datasec:1;
135 136
};

137 138 139 140 141 142 143
/*
 * 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;
144
	char *name;
145
	int prog_ifindex;
146
	char *section_name;
S
Stanislav Fomichev 已提交
147 148 149 150
	/* section_name with / replaced by _; makes recursive pinning
	 * in bpf_object__pin_programs easier
	 */
	char *pin_name;
151
	struct bpf_insn *insns;
152
	size_t insns_cnt, main_prog_cnt;
153
	enum bpf_prog_type type;
154

155 156 157 158
	struct reloc_desc {
		enum {
			RELO_LD64,
			RELO_CALL,
159
			RELO_DATA,
160
		} type;
161
		int insn_idx;
162 163 164 165
		union {
			int map_idx;
			int text_off;
		};
166 167
	} *reloc_desc;
	int nr_reloc;
168
	int log_level;
169

170 171 172 173 174
	struct {
		int nr;
		int *fds;
	} instances;
	bpf_program_prep_t preprocessor;
175 176 177 178

	struct bpf_object *obj;
	void *priv;
	bpf_program_clear_priv_t clear_priv;
179 180

	enum bpf_attach_type expected_attach_type;
181 182 183
	int btf_fd;
	void *func_info;
	__u32 func_info_rec_size;
184
	__u32 func_info_cnt;
185 186

	struct bpf_capabilities *caps;
187 188 189 190

	void *line_info;
	__u32 line_info_rec_size;
	__u32 line_info_cnt;
191
	__u32 prog_flags;
192 193
};

194 195 196 197 198 199 200 201 202 203 204 205 206
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",
};

207 208
struct bpf_map {
	int fd;
209
	char *name;
210 211
	int sec_idx;
	size_t sec_offset;
212
	int map_ifindex;
213
	int inner_map_fd;
214
	struct bpf_map_def def;
215 216
	__u32 btf_key_type_id;
	__u32 btf_value_type_id;
217 218
	void *priv;
	bpf_map_clear_priv_t clear_priv;
219 220 221 222 223 224
	enum libbpf_map_type libbpf_type;
};

struct bpf_secdata {
	void *rodata;
	void *data;
225 226
};

227 228
static LIST_HEAD(bpf_objects_list);

229
struct bpf_object {
230
	char name[BPF_OBJ_NAME_LEN];
231
	char license[64];
232
	__u32 kern_version;
233

234 235
	struct bpf_program *programs;
	size_t nr_programs;
236 237
	struct bpf_map *maps;
	size_t nr_maps;
238
	size_t maps_cap;
239
	struct bpf_secdata sections;
240

241
	bool loaded;
242
	bool has_pseudo_calls;
243

244 245 246 247 248 249
	/*
	 * Information when doing elf related work. Only valid if fd
	 * is valid.
	 */
	struct {
		int fd;
250 251
		void *obj_buf;
		size_t obj_buf_sz;
252 253
		Elf *elf;
		GElf_Ehdr ehdr;
254
		Elf_Data *symbols;
255 256 257
		Elf_Data *data;
		Elf_Data *rodata;
		Elf_Data *bss;
258
		size_t strtabidx;
259 260 261 262 263
		struct {
			GElf_Shdr shdr;
			Elf_Data *data;
		} *reloc;
		int nr_reloc;
264
		int maps_shndx;
265
		int btf_maps_shndx;
266
		int text_shndx;
267 268 269
		int data_shndx;
		int rodata_shndx;
		int bss_shndx;
270
	} efile;
271 272 273 274 275 276
	/*
	 * 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;
277

278
	struct btf *btf;
279
	struct btf_ext *btf_ext;
280

281 282 283
	void *priv;
	bpf_object_clear_priv_t clear_priv;

284 285
	struct bpf_capabilities caps;

286 287 288 289
	char path[];
};
#define obj_elf_valid(o)	((o)->efile.elf)

290
void bpf_program__unload(struct bpf_program *prog)
291
{
292 293
	int i;

294 295 296
	if (!prog)
		return;

297 298 299 300 301 302 303 304 305 306 307 308 309 310
	/*
	 * 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);
311 312 313

	zclose(prog->btf_fd);
	zfree(&prog->func_info);
314
	zfree(&prog->line_info);
315 316
}

317 318 319 320 321
static void bpf_program__exit(struct bpf_program *prog)
{
	if (!prog)
		return;

322 323 324 325 326 327
	if (prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

328
	bpf_program__unload(prog);
329
	zfree(&prog->name);
330
	zfree(&prog->section_name);
S
Stanislav Fomichev 已提交
331
	zfree(&prog->pin_name);
332
	zfree(&prog->insns);
333 334 335
	zfree(&prog->reloc_desc);

	prog->nr_reloc = 0;
336 337 338 339
	prog->insns_cnt = 0;
	prog->idx = -1;
}

S
Stanislav Fomichev 已提交
340 341 342 343 344 345 346 347 348 349 350
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;
}

351
static int
352 353
bpf_program__init(void *data, size_t size, char *section_name, int idx,
		  struct bpf_program *prog)
354
{
355 356 357 358 359
	const size_t bpf_insn_sz = sizeof(struct bpf_insn);

	if (size == 0 || size % bpf_insn_sz) {
		pr_warning("corrupted section '%s', size: %zu\n",
			   section_name, size);
360 361 362
		return -EINVAL;
	}

363
	memset(prog, 0, sizeof(*prog));
364

365
	prog->section_name = strdup(section_name);
366
	if (!prog->section_name) {
367 368
		pr_warning("failed to alloc name for prog under section(%d) %s\n",
			   idx, section_name);
369 370 371
		goto errout;
	}

S
Stanislav Fomichev 已提交
372 373 374 375 376 377 378
	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;
	}

379 380
	prog->insns = malloc(size);
	if (!prog->insns) {
381 382
		pr_warning("failed to alloc insns for prog under section %s\n",
			   section_name);
383 384
		goto errout;
	}
385 386
	prog->insns_cnt = size / bpf_insn_sz;
	memcpy(prog->insns, data, size);
387
	prog->idx = idx;
388 389
	prog->instances.fds = NULL;
	prog->instances.nr = -1;
390
	prog->type = BPF_PROG_TYPE_UNSPEC;
391
	prog->btf_fd = -1;
392 393 394 395 396 397 398 399 400

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

static int
bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
401
			char *section_name, int idx)
402 403 404 405
{
	struct bpf_program prog, *progs;
	int nr_progs, err;

406
	err = bpf_program__init(data, size, section_name, idx, &prog);
407 408 409
	if (err)
		return err;

410
	prog.caps = &obj->caps;
411 412 413
	progs = obj->programs;
	nr_progs = obj->nr_programs;

414
	progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
415 416 417 418 419 420
	if (!progs) {
		/*
		 * In this case the original obj->programs
		 * is still valid, so don't need special treat for
		 * bpf_close_object().
		 */
421 422
		pr_warning("failed to alloc a new program under section '%s'\n",
			   section_name);
423 424 425 426 427 428 429
		bpf_program__exit(&prog);
		return -ENOMEM;
	}

	pr_debug("found program %s\n", prog.section_name);
	obj->programs = progs;
	obj->nr_programs = nr_progs + 1;
430
	prog.obj = obj;
431 432 433 434
	progs[nr_progs] = prog;
	return 0;
}

435 436 437 438 439 440 441 442
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++) {
443
		const char *name = NULL;
444 445 446 447 448 449 450 451 452 453 454

		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;
455 456
			if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL)
				continue;
457 458 459 460 461 462 463 464 465 466 467

			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;
			}
		}

468 469 470
		if (!name && prog->idx == obj->efile.text_shndx)
			name = ".text";

471 472 473 474 475
		if (!name) {
			pr_warning("failed to find sym for prog %s\n",
				   prog->section_name);
			return -EINVAL;
		}
476

477 478 479 480 481 482 483 484 485 486 487
		prog->name = strdup(name);
		if (!prog->name) {
			pr_warning("failed to allocate memory for prog sym %s\n",
				   name);
			return -ENOMEM;
		}
	}

	return 0;
}

488 489 490
static struct bpf_object *bpf_object__new(const char *path,
					  void *obj_buf,
					  size_t obj_buf_sz)
491 492
{
	struct bpf_object *obj;
493
	char *end;
494 495 496 497

	obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1);
	if (!obj) {
		pr_warning("alloc memory failed for %s\n", path);
498
		return ERR_PTR(-ENOMEM);
499 500 501
	}

	strcpy(obj->path, path);
502
	/* Using basename() GNU version which doesn't modify arg. */
503
	strncpy(obj->name, basename((void *)path), sizeof(obj->name) - 1);
504 505 506
	end = strchr(obj->name, '.');
	if (end)
		*end = 0;
507

508
	obj->efile.fd = -1;
509
	/*
510
	 * Caller of this function should also call
511 512 513 514 515 516
	 * 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;
517
	obj->efile.maps_shndx = -1;
518
	obj->efile.btf_maps_shndx = -1;
519 520 521
	obj->efile.data_shndx = -1;
	obj->efile.rodata_shndx = -1;
	obj->efile.bss_shndx = -1;
522

523
	obj->loaded = false;
524 525 526

	INIT_LIST_HEAD(&obj->list);
	list_add(&obj->list, &bpf_objects_list);
527 528 529 530 531 532 533 534 535 536 537 538
	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;
	}
539
	obj->efile.symbols = NULL;
540 541 542
	obj->efile.data = NULL;
	obj->efile.rodata = NULL;
	obj->efile.bss = NULL;
543 544 545

	zfree(&obj->efile.reloc);
	obj->efile.nr_reloc = 0;
546
	zclose(obj->efile.fd);
547 548
	obj->efile.obj_buf = NULL;
	obj->efile.obj_buf_sz = 0;
549 550 551 552 553 554 555 556 557
}

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");
558
		return -LIBBPF_ERRNO__LIBELF;
559 560
	}

561 562 563 564 565 566 567 568 569 570
	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) {
571
			char errmsg[STRERR_BUFSIZE], *cp;
572

573 574
			err = -errno;
			cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
575
			pr_warning("failed to open %s: %s\n", obj->path, cp);
576
			return err;
577 578 579
		}

		obj->efile.elf = elf_begin(obj->efile.fd,
580
					   LIBBPF_ELF_C_READ_MMAP, NULL);
581 582 583
	}

	if (!obj->efile.elf) {
584
		pr_warning("failed to open %s as ELF file\n", obj->path);
585
		err = -LIBBPF_ERRNO__LIBELF;
586 587 588 589
		goto errout;
	}

	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
590
		pr_warning("failed to get EHDR from %s\n", obj->path);
591
		err = -LIBBPF_ERRNO__FORMAT;
592 593 594 595
		goto errout;
	}
	ep = &obj->efile.ehdr;

596
	/* Old LLVM set e_machine to EM_NONE */
597 598 599
	if (ep->e_type != ET_REL ||
	    (ep->e_machine && ep->e_machine != EM_BPF)) {
		pr_warning("%s is not an eBPF object file\n", obj->path);
600
		err = -LIBBPF_ERRNO__FORMAT;
601 602 603 604 605 606 607 608 609
		goto errout;
	}

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

610
static int bpf_object__check_endianness(struct bpf_object *obj)
611
{
612 613 614 615 616 617 618 619 620 621
#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
	if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB)
		return 0;
#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
	if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB)
		return 0;
#else
# error "Unrecognized __BYTE_ORDER__"
#endif
	pr_warning("endianness mismatch.\n");
622
	return -LIBBPF_ERRNO__ENDIAN;
623 624
}

625
static int
626
bpf_object__init_license(struct bpf_object *obj, void *data, size_t size)
627
{
628
	memcpy(obj->license, data, min(size, sizeof(obj->license) - 1));
629 630 631 632 633
	pr_debug("license of %s is %s\n", obj->path, obj->license);
	return 0;
}

static int
634
bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size)
635
{
636
	__u32 kver;
637 638 639

	if (size != sizeof(kver)) {
		pr_warning("invalid kver section in %s\n", obj->path);
640
		return -LIBBPF_ERRNO__FORMAT;
641 642 643
	}
	memcpy(&kver, data, sizeof(kver));
	obj->kern_version = kver;
644
	pr_debug("kernel version of %s is %x\n", obj->path, obj->kern_version);
645 646 647
	return 0;
}

E
Eric Leblond 已提交
648 649 650 651
static int compare_bpf_map(const void *_a, const void *_b)
{
	const struct bpf_map *a = _a;
	const struct bpf_map *b = _b;
652

653 654 655
	if (a->sec_idx != b->sec_idx)
		return a->sec_idx - b->sec_idx;
	return a->sec_offset - b->sec_offset;
656 657
}

658 659 660 661 662 663 664 665
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;
}

666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771
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;
}

772
static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
773
{
774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803
	struct bpf_map *new_maps;
	size_t new_cap;
	int i;

	if (obj->nr_maps < obj->maps_cap)
		return &obj->maps[obj->nr_maps++];

	new_cap = max(4ul, obj->maps_cap * 3 / 2);
	new_maps = realloc(obj->maps, new_cap * sizeof(*obj->maps));
	if (!new_maps) {
		pr_warning("alloc maps for object failed\n");
		return ERR_PTR(-ENOMEM);
	}

	obj->maps_cap = new_cap;
	obj->maps = new_maps;

	/* zero out new maps */
	memset(obj->maps + obj->nr_maps, 0,
	       (obj->maps_cap - obj->nr_maps) * sizeof(*obj->maps));
	/*
	 * fill all fd with -1 so won't close incorrect fd (fd=0 is stdin)
	 * when failure (zclose won't close negative fd)).
	 */
	for (i = obj->nr_maps; i < obj->maps_cap; i++) {
		obj->maps[i].fd = -1;
		obj->maps[i].inner_map_fd = -1;
	}

	return &obj->maps[obj->nr_maps++];
804 805 806
}

static int
807
bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
808
			      int sec_idx, Elf_Data *data, void **data_buff)
809 810
{
	char map_name[BPF_OBJ_NAME_LEN];
811 812 813 814 815 816
	struct bpf_map_def *def;
	struct bpf_map *map;

	map = bpf_object__add_map(obj);
	if (IS_ERR(map))
		return PTR_ERR(map);
817 818

	map->libbpf_type = type;
819 820
	map->sec_idx = sec_idx;
	map->sec_offset = 0;
821 822 823 824 825 826 827
	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;
	}
828 829
	pr_debug("map '%s' (global data): at sec_idx %d, offset %zu.\n",
		 map_name, map->sec_idx, map->sec_offset);
830

831
	def = &map->def;
832 833 834 835
	def->type = BPF_MAP_TYPE_ARRAY;
	def->key_size = sizeof(int);
	def->value_size = data->d_size;
	def->max_entries = 1;
836
	def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0;
837 838 839 840 841 842 843 844 845 846
	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);
	}

847
	pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name);
848 849 850
	return 0;
}

851 852 853 854 855 856 857 858 859 860 861
static int bpf_object__init_global_data_maps(struct bpf_object *obj)
{
	int err;

	if (!obj->caps.global_data)
		return 0;
	/*
	 * Populate obj->maps with libbpf internal maps.
	 */
	if (obj->efile.data_shndx >= 0) {
		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA,
862
						    obj->efile.data_shndx,
863 864 865 866 867 868 869
						    obj->efile.data,
						    &obj->sections.data);
		if (err)
			return err;
	}
	if (obj->efile.rodata_shndx >= 0) {
		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA,
870
						    obj->efile.rodata_shndx,
871 872 873 874 875 876 877
						    obj->efile.rodata,
						    &obj->sections.rodata);
		if (err)
			return err;
	}
	if (obj->efile.bss_shndx >= 0) {
		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS,
878
						    obj->efile.bss_shndx,
879 880 881 882 883 884 885 886
						    obj->efile.bss, NULL);
		if (err)
			return err;
	}
	return 0;
}

static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
887 888
{
	Elf_Data *symbols = obj->efile.symbols;
889
	int i, map_def_sz = 0, nr_maps = 0, nr_syms;
890
	Elf_Data *data = NULL;
891 892 893 894
	Elf_Scn *scn;

	if (obj->efile.maps_shndx < 0)
		return 0;
895

E
Eric Leblond 已提交
896 897
	if (!symbols)
		return -EINVAL;
898

899 900 901 902 903 904 905
	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
906
	}
907

E
Eric Leblond 已提交
908 909 910 911 912 913 914
	/*
	 * 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.
	 */
915 916
	nr_syms = symbols->d_size / sizeof(GElf_Sym);
	for (i = 0; i < nr_syms; i++) {
917
		GElf_Sym sym;
E
Eric Leblond 已提交
918 919 920 921 922 923 924

		if (!gelf_getsym(symbols, i, &sym))
			continue;
		if (sym.st_shndx != obj->efile.maps_shndx)
			continue;
		nr_maps++;
	}
925
	/* Assume equally sized map definitions */
926 927 928 929 930 931 932 933 934
	pr_debug("maps in %s: %d maps in %zd bytes\n",
		 obj->path, nr_maps, data->d_size);

	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;
935
	}
E
Eric Leblond 已提交
936

937 938
	/* Fill obj->maps using data in "maps" section.  */
	for (i = 0; i < nr_syms; i++) {
E
Eric Leblond 已提交
939
		GElf_Sym sym;
940
		const char *map_name;
E
Eric Leblond 已提交
941
		struct bpf_map_def *def;
942
		struct bpf_map *map;
943 944 945

		if (!gelf_getsym(symbols, i, &sym))
			continue;
946
		if (sym.st_shndx != obj->efile.maps_shndx)
947 948
			continue;

949 950 951 952 953
		map = bpf_object__add_map(obj);
		if (IS_ERR(map))
			return PTR_ERR(map);

		map_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
954
				      sym.st_name);
955 956
		if (!map_name) {
			pr_warning("failed to get map #%d name sym string for obj %s\n",
957
				   i, obj->path);
958 959
			return -LIBBPF_ERRNO__FORMAT;
		}
960

961
		map->libbpf_type = LIBBPF_MAP_UNSPEC;
962 963 964 965
		map->sec_idx = sym.st_shndx;
		map->sec_offset = sym.st_value;
		pr_debug("map '%s' (legacy): at sec_idx %d, offset %zu.\n",
			 map_name, map->sec_idx, map->sec_offset);
966
		if (sym.st_value + map_def_sz > data->d_size) {
E
Eric Leblond 已提交
967 968 969
			pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
				   obj->path, map_name);
			return -EINVAL;
970
		}
E
Eric Leblond 已提交
971

972 973
		map->name = strdup(map_name);
		if (!map->name) {
974 975 976
			pr_warning("failed to alloc map name\n");
			return -ENOMEM;
		}
977
		pr_debug("map %d is \"%s\"\n", i, map->name);
E
Eric Leblond 已提交
978
		def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
979 980 981 982 983 984 985
		/*
		 * 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)) {
986
			memcpy(&map->def, def, map_def_sz);
987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001
		} 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);
1002 1003
					if (strict)
						return -EINVAL;
1004 1005
				}
			}
1006
			memcpy(&map->def, def, sizeof(struct bpf_map_def));
1007
		}
1008
	}
1009 1010
	return 0;
}
E
Eric Leblond 已提交
1011

1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 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 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317
static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf,
						     __u32 id)
{
	const struct btf_type *t = btf__type_by_id(btf, id);

	while (true) {
		switch (BTF_INFO_KIND(t->info)) {
		case BTF_KIND_VOLATILE:
		case BTF_KIND_CONST:
		case BTF_KIND_RESTRICT:
		case BTF_KIND_TYPEDEF:
			t = btf__type_by_id(btf, t->type);
			break;
		default:
			return t;
		}
	}
}

static bool get_map_field_int(const char *map_name,
			      const struct btf *btf,
			      const struct btf_type *def,
			      const struct btf_member *m,
			      const void *data, __u32 *res) {
	const struct btf_type *t = skip_mods_and_typedefs(btf, m->type);
	const char *name = btf__name_by_offset(btf, m->name_off);
	__u32 int_info = *(const __u32 *)(const void *)(t + 1);

	if (BTF_INFO_KIND(t->info) != BTF_KIND_INT) {
		pr_warning("map '%s': attr '%s': expected INT, got %u.\n",
			   map_name, name, BTF_INFO_KIND(t->info));
		return false;
	}
	if (t->size != 4 || BTF_INT_BITS(int_info) != 32 ||
	    BTF_INT_OFFSET(int_info)) {
		pr_warning("map '%s': attr '%s': expected 32-bit non-bitfield integer, "
			   "got %u-byte (%d-bit) one with bit offset %d.\n",
			   map_name, name, t->size, BTF_INT_BITS(int_info),
			   BTF_INT_OFFSET(int_info));
		return false;
	}
	if (BTF_INFO_KFLAG(def->info) && BTF_MEMBER_BITFIELD_SIZE(m->offset)) {
		pr_warning("map '%s': attr '%s': bitfield is not supported.\n",
			   map_name, name);
		return false;
	}
	if (m->offset % 32) {
		pr_warning("map '%s': attr '%s': unaligned fields are not supported.\n",
			   map_name, name);
		return false;
	}

	*res = *(const __u32 *)(data + m->offset / 8);
	return true;
}

static int bpf_object__init_user_btf_map(struct bpf_object *obj,
					 const struct btf_type *sec,
					 int var_idx, int sec_idx,
					 const Elf_Data *data, bool strict)
{
	const struct btf_type *var, *def, *t;
	const struct btf_var_secinfo *vi;
	const struct btf_var *var_extra;
	const struct btf_member *m;
	const void *def_data;
	const char *map_name;
	struct bpf_map *map;
	int vlen, i;

	vi = (const struct btf_var_secinfo *)(const void *)(sec + 1) + var_idx;
	var = btf__type_by_id(obj->btf, vi->type);
	var_extra = (const void *)(var + 1);
	map_name = btf__name_by_offset(obj->btf, var->name_off);
	vlen = BTF_INFO_VLEN(var->info);

	if (map_name == NULL || map_name[0] == '\0') {
		pr_warning("map #%d: empty name.\n", var_idx);
		return -EINVAL;
	}
	if ((__u64)vi->offset + vi->size > data->d_size) {
		pr_warning("map '%s' BTF data is corrupted.\n", map_name);
		return -EINVAL;
	}
	if (BTF_INFO_KIND(var->info) != BTF_KIND_VAR) {
		pr_warning("map '%s': unexpected var kind %u.\n",
			   map_name, BTF_INFO_KIND(var->info));
		return -EINVAL;
	}
	if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED &&
	    var_extra->linkage != BTF_VAR_STATIC) {
		pr_warning("map '%s': unsupported var linkage %u.\n",
			   map_name, var_extra->linkage);
		return -EOPNOTSUPP;
	}

	def = skip_mods_and_typedefs(obj->btf, var->type);
	if (BTF_INFO_KIND(def->info) != BTF_KIND_STRUCT) {
		pr_warning("map '%s': unexpected def kind %u.\n",
			   map_name, BTF_INFO_KIND(var->info));
		return -EINVAL;
	}
	if (def->size > vi->size) {
		pr_warning("map '%s': invalid def size.\n", map_name);
		return -EINVAL;
	}

	map = bpf_object__add_map(obj);
	if (IS_ERR(map))
		return PTR_ERR(map);
	map->name = strdup(map_name);
	if (!map->name) {
		pr_warning("map '%s': failed to alloc map name.\n", map_name);
		return -ENOMEM;
	}
	map->libbpf_type = LIBBPF_MAP_UNSPEC;
	map->def.type = BPF_MAP_TYPE_UNSPEC;
	map->sec_idx = sec_idx;
	map->sec_offset = vi->offset;
	pr_debug("map '%s': at sec_idx %d, offset %zu.\n",
		 map_name, map->sec_idx, map->sec_offset);

	def_data = data->d_buf + vi->offset;
	vlen = BTF_INFO_VLEN(def->info);
	m = (const void *)(def + 1);
	for (i = 0; i < vlen; i++, m++) {
		const char *name = btf__name_by_offset(obj->btf, m->name_off);

		if (!name) {
			pr_warning("map '%s': invalid field #%d.\n",
				   map_name, i);
			return -EINVAL;
		}
		if (strcmp(name, "type") == 0) {
			if (!get_map_field_int(map_name, obj->btf, def, m,
					       def_data, &map->def.type))
				return -EINVAL;
			pr_debug("map '%s': found type = %u.\n",
				 map_name, map->def.type);
		} else if (strcmp(name, "max_entries") == 0) {
			if (!get_map_field_int(map_name, obj->btf, def, m,
					       def_data, &map->def.max_entries))
				return -EINVAL;
			pr_debug("map '%s': found max_entries = %u.\n",
				 map_name, map->def.max_entries);
		} else if (strcmp(name, "map_flags") == 0) {
			if (!get_map_field_int(map_name, obj->btf, def, m,
					       def_data, &map->def.map_flags))
				return -EINVAL;
			pr_debug("map '%s': found map_flags = %u.\n",
				 map_name, map->def.map_flags);
		} else if (strcmp(name, "key_size") == 0) {
			__u32 sz;

			if (!get_map_field_int(map_name, obj->btf, def, m,
					       def_data, &sz))
				return -EINVAL;
			pr_debug("map '%s': found key_size = %u.\n",
				 map_name, sz);
			if (map->def.key_size && map->def.key_size != sz) {
				pr_warning("map '%s': conflictling key size %u != %u.\n",
					   map_name, map->def.key_size, sz);
				return -EINVAL;
			}
			map->def.key_size = sz;
		} else if (strcmp(name, "key") == 0) {
			__s64 sz;

			t = btf__type_by_id(obj->btf, m->type);
			if (!t) {
				pr_warning("map '%s': key type [%d] not found.\n",
					   map_name, m->type);
				return -EINVAL;
			}
			if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) {
				pr_warning("map '%s': key spec is not PTR: %u.\n",
					   map_name, BTF_INFO_KIND(t->info));
				return -EINVAL;
			}
			sz = btf__resolve_size(obj->btf, t->type);
			if (sz < 0) {
				pr_warning("map '%s': can't determine key size for type [%u]: %lld.\n",
					   map_name, t->type, sz);
				return sz;
			}
			pr_debug("map '%s': found key [%u], sz = %lld.\n",
				 map_name, t->type, sz);
			if (map->def.key_size && map->def.key_size != sz) {
				pr_warning("map '%s': conflictling key size %u != %lld.\n",
					   map_name, map->def.key_size, sz);
				return -EINVAL;
			}
			map->def.key_size = sz;
			map->btf_key_type_id = t->type;
		} else if (strcmp(name, "value_size") == 0) {
			__u32 sz;

			if (!get_map_field_int(map_name, obj->btf, def, m,
					       def_data, &sz))
				return -EINVAL;
			pr_debug("map '%s': found value_size = %u.\n",
				 map_name, sz);
			if (map->def.value_size && map->def.value_size != sz) {
				pr_warning("map '%s': conflictling value size %u != %u.\n",
					   map_name, map->def.value_size, sz);
				return -EINVAL;
			}
			map->def.value_size = sz;
		} else if (strcmp(name, "value") == 0) {
			__s64 sz;

			t = btf__type_by_id(obj->btf, m->type);
			if (!t) {
				pr_warning("map '%s': value type [%d] not found.\n",
					   map_name, m->type);
				return -EINVAL;
			}
			if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) {
				pr_warning("map '%s': value spec is not PTR: %u.\n",
					   map_name, BTF_INFO_KIND(t->info));
				return -EINVAL;
			}
			sz = btf__resolve_size(obj->btf, t->type);
			if (sz < 0) {
				pr_warning("map '%s': can't determine value size for type [%u]: %lld.\n",
					   map_name, t->type, sz);
				return sz;
			}
			pr_debug("map '%s': found value [%u], sz = %lld.\n",
				 map_name, t->type, sz);
			if (map->def.value_size && map->def.value_size != sz) {
				pr_warning("map '%s': conflictling value size %u != %lld.\n",
					   map_name, map->def.value_size, sz);
				return -EINVAL;
			}
			map->def.value_size = sz;
			map->btf_value_type_id = t->type;
		} else {
			if (strict) {
				pr_warning("map '%s': unknown field '%s'.\n",
					   map_name, name);
				return -ENOTSUP;
			}
			pr_debug("map '%s': ignoring unknown field '%s'.\n",
				 map_name, name);
		}
	}

	if (map->def.type == BPF_MAP_TYPE_UNSPEC) {
		pr_warning("map '%s': map type isn't specified.\n", map_name);
		return -EINVAL;
	}

	return 0;
}

static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict)
{
	const struct btf_type *sec = NULL;
	int nr_types, i, vlen, err;
	const struct btf_type *t;
	const char *name;
	Elf_Data *data;
	Elf_Scn *scn;

	if (obj->efile.btf_maps_shndx < 0)
		return 0;

	scn = elf_getscn(obj->efile.elf, obj->efile.btf_maps_shndx);
	if (scn)
		data = elf_getdata(scn, NULL);
	if (!scn || !data) {
		pr_warning("failed to get Elf_Data from map section %d (%s)\n",
			   obj->efile.maps_shndx, MAPS_ELF_SEC);
		return -EINVAL;
	}

	nr_types = btf__get_nr_types(obj->btf);
	for (i = 1; i <= nr_types; i++) {
		t = btf__type_by_id(obj->btf, i);
		if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC)
			continue;
		name = btf__name_by_offset(obj->btf, t->name_off);
		if (strcmp(name, MAPS_ELF_SEC) == 0) {
			sec = t;
			break;
		}
	}

	if (!sec) {
		pr_warning("DATASEC '%s' not found.\n", MAPS_ELF_SEC);
		return -ENOENT;
	}

	vlen = BTF_INFO_VLEN(sec->info);
	for (i = 0; i < vlen; i++) {
		err = bpf_object__init_user_btf_map(obj, sec, i,
						    obj->efile.btf_maps_shndx,
						    data, strict);
		if (err)
			return err;
	}

	return 0;
}

1318 1319 1320 1321
static int bpf_object__init_maps(struct bpf_object *obj, int flags)
{
	bool strict = !(flags & MAPS_RELAX_COMPAT);
	int err;
1322

1323 1324 1325 1326
	err = bpf_object__init_user_maps(obj, strict);
	if (err)
		return err;

1327 1328 1329 1330
	err = bpf_object__init_user_btf_maps(obj, strict);
	if (err)
		return err;

1331 1332 1333 1334 1335
	err = bpf_object__init_global_data_maps(obj);
	if (err)
		return err;

	if (obj->nr_maps) {
1336 1337
		qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]),
		      compare_bpf_map);
1338 1339
	}
	return 0;
1340 1341
}

1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359
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;
}

1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 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
static void bpf_object__sanitize_btf(struct bpf_object *obj)
{
	bool has_datasec = obj->caps.btf_datasec;
	bool has_func = obj->caps.btf_func;
	struct btf *btf = obj->btf;
	struct btf_type *t;
	int i, j, vlen;
	__u16 kind;

	if (!obj->btf || (has_func && has_datasec))
		return;

	for (i = 1; i <= btf__get_nr_types(btf); i++) {
		t = (struct btf_type *)btf__type_by_id(btf, i);
		kind = BTF_INFO_KIND(t->info);

		if (!has_datasec && kind == BTF_KIND_VAR) {
			/* replace VAR with INT */
			t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
			t->size = sizeof(int);
			*(int *)(t+1) = BTF_INT_ENC(0, 0, 32);
		} else if (!has_datasec && kind == BTF_KIND_DATASEC) {
			/* replace DATASEC with STRUCT */
			struct btf_var_secinfo *v = (void *)(t + 1);
			struct btf_member *m = (void *)(t + 1);
			struct btf_type *vt;
			char *name;

			name = (char *)btf__name_by_offset(btf, t->name_off);
			while (*name) {
				if (*name == '.')
					*name = '_';
				name++;
			}

			vlen = BTF_INFO_VLEN(t->info);
			t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, vlen);
			for (j = 0; j < vlen; j++, v++, m++) {
				/* order of field assignments is important */
				m->offset = v->offset * 8;
				m->type = v->type;
				/* preserve variable name as member name */
				vt = (void *)btf__type_by_id(btf, v->type);
				m->name_off = vt->name_off;
			}
		} else if (!has_func && kind == BTF_KIND_FUNC_PROTO) {
			/* replace FUNC_PROTO with ENUM */
			vlen = BTF_INFO_VLEN(t->info);
			t->info = BTF_INFO_ENC(BTF_KIND_ENUM, 0, vlen);
			t->size = sizeof(__u32); /* kernel enforced */
		} else if (!has_func && kind == BTF_KIND_FUNC) {
			/* replace FUNC with TYPEDEF */
			t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0);
		}
	}
}

static void bpf_object__sanitize_btf_ext(struct bpf_object *obj)
{
	if (!obj->btf_ext)
		return;

	if (!obj->caps.btf_func) {
		btf_ext__free(obj->btf_ext);
		obj->btf_ext = NULL;
	}
}

1428 1429 1430 1431 1432
static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj)
{
	return obj->efile.btf_maps_shndx >= 0;
}

1433
static int bpf_object__init_btf(struct bpf_object *obj,
1434 1435 1436
				Elf_Data *btf_data,
				Elf_Data *btf_ext_data)
{
1437
	bool btf_required = bpf_object__is_btf_mandatory(obj);
1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470
	int err = 0;

	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: %d.\n",
				   BTF_ELF_SEC, err);
			goto out;
		}
		err = btf__finalize_data(obj, obj->btf);
		if (err) {
			pr_warning("Error finalizing %s: %d.\n",
				   BTF_ELF_SEC, err);
			goto out;
		}
	}
	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);
			goto out;
		}
		obj->btf_ext = btf_ext__new(btf_ext_data->d_buf,
					    btf_ext_data->d_size);
		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;
			goto out;
		}
	}
out:
	if (err || IS_ERR(obj->btf)) {
1471 1472 1473 1474
		if (btf_required)
			err = err ? : PTR_ERR(obj->btf);
		else
			err = 0;
1475 1476 1477 1478
		if (!IS_ERR_OR_NULL(obj->btf))
			btf__free(obj->btf);
		obj->btf = NULL;
	}
1479 1480 1481 1482
	if (btf_required && !obj->btf) {
		pr_warning("BTF is required, but is missing or corrupted.\n");
		return err == 0 ? -ENOENT : err;
	}
1483 1484 1485
	return 0;
}

1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501
static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
{
	int err = 0;

	if (!obj->btf)
		return 0;

	bpf_object__sanitize_btf(obj);
	bpf_object__sanitize_btf_ext(obj);

	err = btf__load(obj->btf);
	if (err) {
		pr_warning("Error loading %s into kernel: %d.\n",
			   BTF_ELF_SEC, err);
		btf__free(obj->btf);
		obj->btf = NULL;
1502 1503
		if (bpf_object__is_btf_mandatory(obj))
			return err;
1504 1505 1506 1507
	}
	return 0;
}

1508
static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
1509 1510 1511
{
	Elf *elf = obj->efile.elf;
	GElf_Ehdr *ep = &obj->efile.ehdr;
1512
	Elf_Data *btf_ext_data = NULL;
1513
	Elf_Data *btf_data = NULL;
1514
	Elf_Scn *scn = NULL;
1515
	int idx = 0, err = 0;
1516 1517 1518

	/* Elf is corrupted/truncated, avoid calling elf_strptr. */
	if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
1519
		pr_warning("failed to get e_shstrndx from %s\n", obj->path);
1520
		return -LIBBPF_ERRNO__FORMAT;
1521 1522 1523 1524 1525 1526 1527 1528 1529
	}

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

		idx++;
		if (gelf_getshdr(scn, &sh) != &sh) {
1530 1531
			pr_warning("failed to get section(%d) header from %s\n",
				   idx, obj->path);
1532
			return -LIBBPF_ERRNO__FORMAT;
1533 1534 1535 1536
		}

		name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
		if (!name) {
1537 1538
			pr_warning("failed to get section(%d) name from %s\n",
				   idx, obj->path);
1539
			return -LIBBPF_ERRNO__FORMAT;
1540 1541 1542 1543
		}

		data = elf_getdata(scn, 0);
		if (!data) {
1544 1545
			pr_warning("failed to get section(%d) data from %s(%s)\n",
				   idx, name, obj->path);
1546
			return -LIBBPF_ERRNO__FORMAT;
1547
		}
1548 1549
		pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n",
			 idx, name, (unsigned long)data->d_size,
1550 1551
			 (int)sh.sh_link, (unsigned long)sh.sh_flags,
			 (int)sh.sh_type);
1552

1553
		if (strcmp(name, "license") == 0) {
1554 1555 1556
			err = bpf_object__init_license(obj,
						       data->d_buf,
						       data->d_size);
1557 1558
			if (err)
				return err;
1559
		} else if (strcmp(name, "version") == 0) {
1560 1561 1562
			err = bpf_object__init_kversion(obj,
							data->d_buf,
							data->d_size);
1563 1564
			if (err)
				return err;
1565
		} else if (strcmp(name, "maps") == 0) {
1566
			obj->efile.maps_shndx = idx;
1567 1568
		} else if (strcmp(name, MAPS_ELF_SEC) == 0) {
			obj->efile.btf_maps_shndx = idx;
1569 1570
		} else if (strcmp(name, BTF_ELF_SEC) == 0) {
			btf_data = data;
1571
		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
1572
			btf_ext_data = data;
1573
		} else if (sh.sh_type == SHT_SYMTAB) {
1574 1575 1576
			if (obj->efile.symbols) {
				pr_warning("bpf: multiple SYMTAB in %s\n",
					   obj->path);
1577
				return -LIBBPF_ERRNO__FORMAT;
1578
			}
1579 1580
			obj->efile.symbols = data;
			obj->efile.strtabidx = sh.sh_link;
1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593
		} 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);
1594
					return err;
1595
				}
1596 1597 1598 1599 1600 1601 1602 1603
			} 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);
1604
			}
1605
		} else if (sh.sh_type == SHT_REL) {
1606
			int nr_reloc = obj->efile.nr_reloc;
1607
			void *reloc = obj->efile.reloc;
1608 1609 1610 1611 1612 1613 1614 1615
			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;
			}
1616

1617
			reloc = reallocarray(reloc, nr_reloc + 1,
1618
					     sizeof(*obj->efile.reloc));
1619 1620
			if (!reloc) {
				pr_warning("realloc failed\n");
1621 1622
				return -ENOMEM;
			}
1623

1624 1625
			obj->efile.reloc = reloc;
			obj->efile.nr_reloc++;
1626

1627 1628
			obj->efile.reloc[nr_reloc].shdr = sh;
			obj->efile.reloc[nr_reloc].data = data;
1629 1630 1631
		} else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) {
			obj->efile.bss = data;
			obj->efile.bss_shndx = idx;
1632 1633
		} else {
			pr_debug("skip section(%d) %s\n", idx, name);
1634
		}
1635
	}
1636

1637 1638
	if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
		pr_warning("Corrupted ELF file: index of strtab invalid\n");
1639
		return -LIBBPF_ERRNO__FORMAT;
1640
	}
1641
	err = bpf_object__init_btf(obj, btf_data, btf_ext_data);
1642
	if (!err)
1643
		err = bpf_object__init_maps(obj, flags);
1644 1645
	if (!err)
		err = bpf_object__sanitize_and_load_btf(obj);
1646 1647
	if (!err)
		err = bpf_object__init_prog_names(obj);
1648 1649 1650
	return err;
}

1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664
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;
}

1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676
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;
}

1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687
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)
{
1688 1689
	return shndx == obj->efile.maps_shndx ||
	       shndx == obj->efile.btf_maps_shndx;
1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712
}

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;
}

1713
static int
1714 1715
bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
			   Elf_Data *data, struct bpf_object *obj)
1716
{
1717 1718 1719
	Elf_Data *symbols = obj->efile.symbols;
	struct bpf_map *maps = obj->maps;
	size_t nr_maps = obj->nr_maps;
1720 1721
	int i, nrels;

1722
	pr_debug("collecting relocating info for: '%s'\n", prog->section_name);
1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733
	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++) {
		struct bpf_insn *insns = prog->insns;
1734
		enum libbpf_map_type type;
1735 1736
		unsigned int insn_idx;
		unsigned int shdr_idx;
1737
		const char *name;
1738
		size_t map_idx;
1739 1740
		GElf_Sym sym;
		GElf_Rel rel;
1741 1742 1743

		if (!gelf_getrel(data, i, &rel)) {
			pr_warning("relocation: failed to get %d reloc\n", i);
1744
			return -LIBBPF_ERRNO__FORMAT;
1745 1746
		}

1747
		if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
1748 1749
			pr_warning("relocation: symbol %"PRIx64" not found\n",
				   GELF_R_SYM(rel.r_info));
1750
			return -LIBBPF_ERRNO__FORMAT;
1751
		}
1752 1753 1754 1755 1756

		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
1757
			 (long long) (rel.r_info >> 32),
1758
			 (long long) sym.st_value, sym.st_name, name);
1759

1760 1761 1762 1763
		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);
1764 1765 1766 1767 1768 1769
			return -LIBBPF_ERRNO__RELOC;
		}

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

1770 1771 1772 1773 1774 1775 1776 1777
		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;
1778
			obj->has_pseudo_calls = true;
1779 1780 1781
			continue;
		}

1782 1783 1784
		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);
1785
			return -LIBBPF_ERRNO__RELOC;
1786 1787
		}

1788 1789 1790
		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);
1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801
			if (type != LIBBPF_MAP_UNSPEC) {
				if (GELF_ST_BIND(sym.st_info) == STB_GLOBAL) {
					pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n",
						   name, insn_idx, insns[insn_idx].code);
					return -LIBBPF_ERRNO__RELOC;
				}
				if (!obj->caps.global_data) {
					pr_warning("bpf: relocation: kernel does not support global \'%s\' variable access in insns[%d]\n",
						   name, insn_idx);
					return -LIBBPF_ERRNO__RELOC;
				}
1802 1803
			}

1804
			for (map_idx = 0; map_idx < nr_maps; map_idx++) {
1805 1806 1807
				if (maps[map_idx].libbpf_type != type)
					continue;
				if (type != LIBBPF_MAP_UNSPEC ||
1808 1809 1810 1811 1812 1813 1814
				    (maps[map_idx].sec_idx == sym.st_shndx &&
				     maps[map_idx].sec_offset == sym.st_value)) {
					pr_debug("relocation: found map %zd (%s, sec_idx %d, offset %zu) for insn %u\n",
						 map_idx, maps[map_idx].name,
						 maps[map_idx].sec_idx,
						 maps[map_idx].sec_offset,
						 insn_idx);
1815 1816
					break;
				}
1817 1818
			}

1819
			if (map_idx >= nr_maps) {
1820
				pr_warning("bpf relocation: map_idx %d larger than %d\n",
1821 1822 1823
					   (int)map_idx, (int)nr_maps - 1);
				return -LIBBPF_ERRNO__RELOC;
			}
1824

1825 1826
			prog->reloc_desc[i].type = type != LIBBPF_MAP_UNSPEC ?
						   RELO_DATA : RELO_LD64;
1827 1828 1829
			prog->reloc_desc[i].insn_idx = insn_idx;
			prog->reloc_desc[i].map_idx = map_idx;
		}
1830 1831 1832 1833
	}
	return 0;
}

1834
static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
1835 1836
{
	struct bpf_map_def *def = &map->def;
1837
	__u32 key_type_id = 0, value_type_id = 0;
1838
	int ret;
1839

1840 1841 1842 1843
	/* if it's BTF-defined map, we don't need to search for type IDs */
	if (map->sec_idx == obj->efile.btf_maps_shndx)
		return 0;

1844
	if (!bpf_map__is_internal(map)) {
1845
		ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size,
1846 1847 1848 1849 1850 1851 1852
					   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'.
		 */
1853
		ret = btf__find_by_name(obj->btf,
1854 1855 1856
				libbpf_type_to_btf_name[map->libbpf_type]);
	}
	if (ret < 0)
1857
		return ret;
1858

1859
	map->btf_key_type_id = key_type_id;
1860 1861
	map->btf_value_type_id = bpf_map__is_internal(map) ?
				 ret : value_type_id;
1862 1863 1864
	return 0;
}

J
Jakub Kicinski 已提交
1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911
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;
}

1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925
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;
}

1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965
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;
}

1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011
static int
bpf_object__probe_global_data(struct bpf_object *obj)
{
	struct bpf_load_program_attr prg_attr;
	struct bpf_create_map_attr map_attr;
	char *cp, errmsg[STRERR_BUFSIZE];
	struct bpf_insn insns[] = {
		BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16),
		BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
		BPF_MOV64_IMM(BPF_REG_0, 0),
		BPF_EXIT_INSN(),
	};
	int ret, map;

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

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

	insns[0].imm = map;

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

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

	close(map);
	return 0;
}

2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060
static int bpf_object__probe_btf_func(struct bpf_object *obj)
{
	const char strs[] = "\0int\0x\0a";
	/* void x(int a) {} */
	__u32 types[] = {
		/* int */
		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
		/* FUNC_PROTO */                                /* [2] */
		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
		BTF_PARAM_ENC(7, 1),
		/* FUNC x */                                    /* [3] */
		BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2),
	};
	int res;

	res = libbpf__probe_raw_btf((char *)types, sizeof(types),
				    strs, sizeof(strs));
	if (res < 0)
		return res;
	if (res > 0)
		obj->caps.btf_func = 1;
	return 0;
}

static int bpf_object__probe_btf_datasec(struct bpf_object *obj)
{
	const char strs[] = "\0x\0.data";
	/* static int a; */
	__u32 types[] = {
		/* int */
		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
		/* VAR x */                                     /* [2] */
		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
		BTF_VAR_STATIC,
		/* DATASEC val */                               /* [3] */
		BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
		BTF_VAR_SECINFO_ENC(2, 0, 4),
	};
	int res;

	res = libbpf__probe_raw_btf((char *)types, sizeof(types),
				    strs, sizeof(strs));
	if (res < 0)
		return res;
	if (res > 0)
		obj->caps.btf_datasec = 1;
	return 0;
}

2061 2062 2063
static int
bpf_object__probe_caps(struct bpf_object *obj)
{
2064 2065 2066
	int (*probe_fn[])(struct bpf_object *obj) = {
		bpf_object__probe_name,
		bpf_object__probe_global_data,
2067 2068
		bpf_object__probe_btf_func,
		bpf_object__probe_btf_datasec,
2069 2070 2071 2072 2073 2074
	};
	int i, ret;

	for (i = 0; i < ARRAY_SIZE(probe_fn); i++) {
		ret = probe_fn[i](obj);
		if (ret < 0)
2075
			pr_debug("Probe #%d failed with %d.\n", i, ret);
2076 2077 2078
	}

	return 0;
2079 2080
}

2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108
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;
}

2109 2110 2111
static int
bpf_object__create_maps(struct bpf_object *obj)
{
2112
	struct bpf_create_map_attr create_attr = {};
2113
	unsigned int i;
2114
	int err;
2115

2116
	for (i = 0; i < obj->nr_maps; i++) {
2117 2118
		struct bpf_map *map = &obj->maps[i];
		struct bpf_map_def *def = &map->def;
2119
		char *cp, errmsg[STRERR_BUFSIZE];
2120 2121
		int *pfd = &map->fd;

J
Jakub Kicinski 已提交
2122 2123 2124 2125 2126 2127
		if (map->fd >= 0) {
			pr_debug("skip map create (preset) %s: fd=%d\n",
				 map->name, map->fd);
			continue;
		}

2128 2129
		if (obj->caps.name)
			create_attr.name = map->name;
2130
		create_attr.map_ifindex = map->map_ifindex;
2131 2132 2133 2134 2135
		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;
2136
		create_attr.btf_fd = 0;
2137 2138
		create_attr.btf_key_type_id = 0;
		create_attr.btf_value_type_id = 0;
2139 2140 2141
		if (bpf_map_type__is_map_in_map(def->type) &&
		    map->inner_map_fd >= 0)
			create_attr.inner_map_fd = map->inner_map_fd;
2142

2143
		if (obj->btf && !bpf_map_find_btf_info(obj, map)) {
2144
			create_attr.btf_fd = btf__fd(obj->btf);
2145 2146
			create_attr.btf_key_type_id = map->btf_key_type_id;
			create_attr.btf_value_type_id = map->btf_value_type_id;
2147 2148 2149
		}

		*pfd = bpf_create_map_xattr(&create_attr);
2150 2151
		if (*pfd < 0 && (create_attr.btf_key_type_id ||
				 create_attr.btf_value_type_id)) {
2152
			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
2153
			pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
2154
				   map->name, cp, errno);
2155
			create_attr.btf_fd = 0;
2156 2157 2158 2159
			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;
2160 2161 2162
			*pfd = bpf_create_map_xattr(&create_attr);
		}

2163 2164 2165
		if (*pfd < 0) {
			size_t j;

2166
			err = *pfd;
2167
err_out:
2168
			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
E
Eric Leblond 已提交
2169
			pr_warning("failed to create map (name: '%s'): %s\n",
2170
				   map->name, cp);
2171
			for (j = 0; j < i; j++)
2172
				zclose(obj->maps[j].fd);
2173 2174
			return err;
		}
2175 2176 2177 2178 2179 2180 2181 2182 2183

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

2184
		pr_debug("created map %s: fd=%d\n", map->name, *pfd);
2185 2186 2187 2188 2189
	}

	return 0;
}

2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204
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
2205
		 * in the last btf_ext reloc. Must have to error out.
2206 2207 2208 2209 2210 2211
		 */
		pr_warning("Error in relocating %s for sec %s.\n",
			   info_name, prog->section_name);
		return err;
	}

2212
	/* Have problem loading the very first info. Ignore the rest. */
2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242
	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);
	}

2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255
	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);
	}

2256 2257 2258 2259 2260 2261
	if (!insn_offset)
		prog->btf_fd = btf__fd(obj->btf);

	return 0;
}

2262 2263 2264 2265 2266 2267 2268
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;
2269
	int err;
2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286

	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;
2287
		new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn));
2288 2289 2290 2291
		if (!new_insn) {
			pr_warning("oom in prog realloc\n");
			return -ENOMEM;
		}
2292

2293 2294 2295 2296 2297
		if (obj->btf_ext) {
			err = bpf_program_reloc_btf_ext(prog, obj,
							text->section_name,
							prog->insns_cnt);
			if (err)
2298 2299 2300
				return err;
		}

2301 2302 2303 2304 2305
		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;
2306 2307 2308
		pr_debug("added %zd insn from %s to prog %s\n",
			 text->insns_cnt, text->section_name,
			 prog->section_name);
2309 2310 2311 2312 2313 2314
	}
	insn = &prog->insns[relo->insn_idx];
	insn->imm += prog->main_prog_cnt - relo->insn_idx;
	return 0;
}

W
Wang Nan 已提交
2315
static int
2316
bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
W
Wang Nan 已提交
2317
{
2318
	int i, err;
W
Wang Nan 已提交
2319

2320 2321 2322
	if (!prog)
		return 0;

2323 2324 2325 2326
	if (obj->btf_ext) {
		err = bpf_program_reloc_btf_ext(prog, obj,
						prog->section_name, 0);
		if (err)
2327 2328 2329 2330
			return err;
	}

	if (!prog->reloc_desc)
W
Wang Nan 已提交
2331 2332 2333
		return 0;

	for (i = 0; i < prog->nr_reloc; i++) {
2334 2335 2336
		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;
2337 2338
			struct bpf_insn *insns = prog->insns;
			int insn_idx, map_idx;
W
Wang Nan 已提交
2339

2340 2341
			insn_idx = prog->reloc_desc[i].insn_idx;
			map_idx = prog->reloc_desc[i].map_idx;
W
Wang Nan 已提交
2342

2343
			if (insn_idx + 1 >= (int)prog->insns_cnt) {
2344 2345 2346 2347
				pr_warning("relocation out of range: '%s'\n",
					   prog->section_name);
				return -LIBBPF_ERRNO__RELOC;
			}
2348 2349 2350 2351 2352 2353 2354

			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;
			}
2355
			insns[insn_idx].imm = obj->maps[map_idx].fd;
2356
		} else if (prog->reloc_desc[i].type == RELO_CALL) {
2357 2358 2359 2360
			err = bpf_program__reloc_text(prog, obj,
						      &prog->reloc_desc[i]);
			if (err)
				return err;
W
Wang Nan 已提交
2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379
		}
	}

	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];

2380
		err = bpf_program__relocate(prog, obj);
W
Wang Nan 已提交
2381 2382 2383 2384 2385 2386 2387 2388 2389
		if (err) {
			pr_warning("failed to relocate '%s'\n",
				   prog->section_name);
			return err;
		}
	}
	return 0;
}

2390 2391 2392 2393 2394 2395
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");
2396
		return -LIBBPF_ERRNO__INTERNAL;
2397 2398 2399 2400 2401 2402 2403 2404 2405 2406
	}

	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__);
2407
			return -LIBBPF_ERRNO__INTERNAL;
2408 2409 2410 2411
		}

		prog = bpf_object__find_prog_by_idx(obj, idx);
		if (!prog) {
2412
			pr_warning("relocation failed: no section(%d)\n", idx);
2413
			return -LIBBPF_ERRNO__RELOC;
2414 2415
		}

2416
		err = bpf_program__collect_reloc(prog, shdr, data, obj);
2417
		if (err)
2418
			return err;
2419 2420 2421 2422
	}
	return 0;
}

2423
static int
2424
load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
2425
	     char *license, __u32 kern_version, int *pfd)
2426
{
2427
	struct bpf_load_program_attr load_attr;
2428
	char *cp, errmsg[STRERR_BUFSIZE];
2429
	int log_buf_size = BPF_LOG_BUF_SIZE;
2430
	char *log_buf;
2431
	int ret;
2432

2433 2434 2435
	if (!insns || !insns_cnt)
		return -EINVAL;

2436
	memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
2437 2438
	load_attr.prog_type = prog->type;
	load_attr.expected_attach_type = prog->expected_attach_type;
2439 2440
	if (prog->caps->name)
		load_attr.name = prog->name;
2441 2442 2443 2444
	load_attr.insns = insns;
	load_attr.insns_cnt = insns_cnt;
	load_attr.license = license;
	load_attr.kern_version = kern_version;
2445
	load_attr.prog_ifindex = prog->prog_ifindex;
2446
	load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0;
2447 2448
	load_attr.func_info = prog->func_info;
	load_attr.func_info_rec_size = prog->func_info_rec_size;
2449
	load_attr.func_info_cnt = prog->func_info_cnt;
2450 2451 2452
	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;
2453
	load_attr.log_level = prog->log_level;
2454
	load_attr.prog_flags = prog->prog_flags;
2455

2456 2457
retry_load:
	log_buf = malloc(log_buf_size);
2458 2459 2460
	if (!log_buf)
		pr_warning("Alloc log buffer for bpf loader error, continue without log\n");

2461
	ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size);
2462 2463

	if (ret >= 0) {
2464 2465
		if (load_attr.log_level)
			pr_debug("verifier log:\n%s", log_buf);
2466 2467 2468 2469 2470
		*pfd = ret;
		ret = 0;
		goto out;
	}

2471 2472 2473 2474 2475
	if (errno == ENOSPC) {
		log_buf_size <<= 1;
		free(log_buf);
		goto retry_load;
	}
2476
	ret = -LIBBPF_ERRNO__LOAD;
2477
	cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
2478
	pr_warning("load bpf program failed: %s\n", cp);
2479

2480 2481
	if (log_buf && log_buf[0] != '\0') {
		ret = -LIBBPF_ERRNO__VERIFY;
2482 2483 2484
		pr_warning("-- BEGIN DUMP LOG ---\n");
		pr_warning("\n%s\n", log_buf);
		pr_warning("-- END LOG --\n");
2485 2486 2487
	} 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);
2488
		ret = -LIBBPF_ERRNO__PROG2BIG;
2489
	} else {
2490
		/* Wrong program type? */
2491
		if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) {
2492 2493
			int fd;

2494 2495 2496
			load_attr.prog_type = BPF_PROG_TYPE_KPROBE;
			load_attr.expected_attach_type = 0;
			fd = bpf_load_program_xattr(&load_attr, NULL, 0);
2497 2498 2499 2500 2501
			if (fd >= 0) {
				close(fd);
				ret = -LIBBPF_ERRNO__PROGTYPE;
				goto out;
			}
2502
		}
2503 2504 2505

		if (log_buf)
			ret = -LIBBPF_ERRNO__KVER;
2506 2507 2508 2509 2510 2511 2512
	}

out:
	free(log_buf);
	return ret;
}

2513
int
2514
bpf_program__load(struct bpf_program *prog,
2515
		  char *license, __u32 kern_version)
2516
{
2517
	int err = 0, fd, i;
2518

2519 2520 2521 2522 2523 2524
	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;
		}
2525

2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539
		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);
		}
2540
		err = load_program(prog, prog->insns, prog->insns_cnt,
2541
				   license, kern_version, &fd);
2542 2543 2544 2545 2546 2547 2548 2549 2550
		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;

2551
		memset(&result, 0, sizeof(result));
2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568
		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;
		}

2569
		err = load_program(prog, result.new_insn_ptr,
2570
				   result.new_insn_cnt,
2571
				   license, kern_version, &fd);
2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583

		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:
2584 2585 2586 2587 2588 2589 2590 2591
	if (err)
		pr_warning("failed to load program '%s'\n",
			   prog->section_name);
	zfree(&prog->insns);
	prog->insns_cnt = 0;
	return err;
}

2592 2593 2594 2595 2596 2597
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;
}

2598
static int
2599
bpf_object__load_progs(struct bpf_object *obj, int log_level)
2600 2601 2602 2603 2604
{
	size_t i;
	int err;

	for (i = 0; i < obj->nr_programs; i++) {
2605
		if (bpf_program__is_function_storage(&obj->programs[i], obj))
2606
			continue;
2607
		obj->programs[i].log_level |= log_level;
2608 2609 2610 2611 2612 2613 2614 2615 2616
		err = bpf_program__load(&obj->programs[i],
					obj->license,
					obj->kern_version);
		if (err)
			return err;
	}
	return 0;
}

2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628
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:
2629
	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
2630 2631 2632 2633 2634
	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:
2635
	case BPF_PROG_TYPE_LIRC_MODE2:
2636
	case BPF_PROG_TYPE_SK_REUSEPORT:
2637
	case BPF_PROG_TYPE_FLOW_DISSECTOR:
2638 2639 2640
	case BPF_PROG_TYPE_UNSPEC:
	case BPF_PROG_TYPE_TRACEPOINT:
	case BPF_PROG_TYPE_RAW_TRACEPOINT:
M
Matt Mullins 已提交
2641
	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
2642
	case BPF_PROG_TYPE_PERF_EVENT:
A
Andrey Ignatov 已提交
2643
	case BPF_PROG_TYPE_CGROUP_SYSCTL:
2644 2645
		return false;
	case BPF_PROG_TYPE_KPROBE:
2646 2647 2648 2649 2650 2651
	default:
		return true;
	}
}

static int bpf_object__validate(struct bpf_object *obj, bool needs_kver)
2652
{
2653
	if (needs_kver && obj->kern_version == 0) {
2654 2655
		pr_warning("%s doesn't provide kernel version\n",
			   obj->path);
2656
		return -LIBBPF_ERRNO__KVERSION;
2657 2658 2659 2660
	}
	return 0;
}

2661
static struct bpf_object *
2662
__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
2663
		   bool needs_kver, int flags)
2664 2665
{
	struct bpf_object *obj;
2666
	int err;
2667 2668 2669

	if (elf_version(EV_CURRENT) == EV_NONE) {
		pr_warning("failed to init libelf for %s\n", path);
2670
		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
2671 2672
	}

2673
	obj = bpf_object__new(path, obj_buf, obj_buf_sz);
2674 2675
	if (IS_ERR(obj))
		return obj;
2676

2677 2678
	CHECK_ERR(bpf_object__elf_init(obj), err, out);
	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
2679
	CHECK_ERR(bpf_object__probe_caps(obj), err, out);
2680
	CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out);
2681
	CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
2682
	CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out);
2683 2684 2685 2686 2687

	bpf_object__elf_finish(obj);
	return obj;
out:
	bpf_object__close(obj);
2688
	return ERR_PTR(err);
2689 2690
}

2691 2692
struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
					    int flags)
2693 2694
{
	/* param validation */
2695
	if (!attr->file)
2696 2697
		return NULL;

2698 2699 2700
	pr_debug("loading %s\n", attr->file);

	return __bpf_object__open(attr->file, NULL, 0,
2701 2702 2703 2704 2705 2706 2707
				  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);
2708 2709 2710 2711 2712 2713 2714 2715
}

struct bpf_object *bpf_object__open(const char *path)
{
	struct bpf_object_open_attr attr = {
		.file		= path,
		.prog_type	= BPF_PROG_TYPE_UNSPEC,
	};
2716

2717
	return bpf_object__open_xattr(&attr);
2718 2719 2720
}

struct bpf_object *bpf_object__open_buffer(void *obj_buf,
2721 2722
					   size_t obj_buf_sz,
					   const char *name)
2723
{
2724 2725
	char tmp_name[64];

2726 2727 2728 2729
	/* param validation */
	if (!obj_buf || obj_buf_sz <= 0)
		return NULL;

2730 2731 2732 2733 2734 2735
	if (!name) {
		snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx",
			 (unsigned long)obj_buf,
			 (unsigned long)obj_buf_sz);
		name = tmp_name;
	}
2736
	pr_debug("loading object '%s' from buffer\n", name);
2737

2738
	return __bpf_object__open(name, obj_buf, obj_buf_sz, true, true);
2739 2740
}

2741 2742 2743 2744 2745 2746 2747
int bpf_object__unload(struct bpf_object *obj)
{
	size_t i;

	if (!obj)
		return -EINVAL;

2748 2749
	for (i = 0; i < obj->nr_maps; i++)
		zclose(obj->maps[i].fd);
2750

2751 2752 2753
	for (i = 0; i < obj->nr_programs; i++)
		bpf_program__unload(&obj->programs[i]);

2754 2755 2756
	return 0;
}

2757
int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
2758
{
2759
	struct bpf_object *obj;
2760 2761
	int err;

2762 2763 2764
	if (!attr)
		return -EINVAL;
	obj = attr->obj;
2765 2766 2767 2768 2769 2770 2771 2772 2773
	if (!obj)
		return -EINVAL;

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

	obj->loaded = true;
2774 2775 2776

	CHECK_ERR(bpf_object__create_maps(obj), err, out);
	CHECK_ERR(bpf_object__relocate(obj), err, out);
2777
	CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out);
2778 2779 2780 2781 2782

	return 0;
out:
	bpf_object__unload(obj);
	pr_warning("failed to load object '%s'\n", obj->path);
2783
	return err;
2784 2785
}

2786 2787 2788 2789 2790 2791 2792 2793 2794
int bpf_object__load(struct bpf_object *obj)
{
	struct bpf_object_load_attr attr = {
		.obj = obj,
	};

	return bpf_object__load_xattr(&attr);
}

2795 2796
static int check_path(const char *path)
{
2797
	char *cp, errmsg[STRERR_BUFSIZE];
2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810
	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)) {
2811
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
2812
		pr_warning("failed to statfs %s: %s\n", dir, cp);
2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827
		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)
{
2828
	char *cp, errmsg[STRERR_BUFSIZE];
2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846
	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)) {
2847
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
2848
		pr_warning("failed to pin program: %s\n", cp);
2849 2850 2851 2852 2853 2854 2855
		return -errno;
	}
	pr_debug("pinned program '%s'\n", path);

	return 0;
}

2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883
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;
}

2884 2885
static int make_dir(const char *path)
{
2886
	char *cp, errmsg[STRERR_BUFSIZE];
2887 2888 2889 2890 2891
	int err = 0;

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

2892
	if (err) {
2893
		cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
2894 2895
		pr_warning("failed to mkdir %s: %s\n", path, cp);
	}
2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917
	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;
	}

2918 2919 2920 2921 2922
	if (prog->instances.nr == 1) {
		/* don't create subdirs when pinning single instance */
		return bpf_program__pin_instance(prog, path, 0);
	}

2923 2924 2925 2926
	err = make_dir(path);
	if (err)
		return err;

2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982
	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;
2983 2984 2985 2986 2987
	}

	if (prog->instances.nr == 1) {
		/* don't create subdirs when pinning single instance */
		return bpf_program__unpin_instance(prog, path, 0);
2988 2989
	}

2990 2991 2992 2993 2994 2995 2996 2997 2998 2999
	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;

3000
		err = bpf_program__unpin_instance(prog, buf, i);
3001 3002 3003 3004
		if (err)
			return err;
	}

3005 3006 3007 3008
	err = rmdir(path);
	if (err)
		return -errno;

3009 3010 3011
	return 0;
}

J
Joe Stringer 已提交
3012 3013
int bpf_map__pin(struct bpf_map *map, const char *path)
{
3014
	char *cp, errmsg[STRERR_BUFSIZE];
J
Joe Stringer 已提交
3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026
	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)) {
3027
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
3028
		pr_warning("failed to pin map: %s\n", cp);
J
Joe Stringer 已提交
3029 3030 3031 3032
		return -errno;
	}

	pr_debug("pinned map '%s'\n", path);
3033

J
Joe Stringer 已提交
3034 3035 3036
	return 0;
}

3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058
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)
3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074
{
	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;

3075
	bpf_object__for_each_map(map, obj) {
3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121
		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;

3122
	bpf_object__for_each_map(map, obj) {
3123 3124 3125 3126 3127 3128 3129 3130 3131 3132
		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;

3133
		err = bpf_map__unpin(map, buf);
3134 3135 3136 3137
		if (err)
			return err;
	}

3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162
	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
3163
			       prog->pin_name);
3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184
		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
3185
			       prog->pin_name);
3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204
		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;

3205 3206 3207 3208 3209
	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
3210
			       prog->pin_name);
3211 3212 3213 3214 3215
		if (len < 0)
			return -EINVAL;
		else if (len >= PATH_MAX)
			return -ENAMETOOLONG;

3216
		err = bpf_program__unpin(prog, buf);
3217 3218 3219 3220 3221 3222 3223
		if (err)
			return err;
	}

	return 0;
}

3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240
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;
}

3241 3242
void bpf_object__close(struct bpf_object *obj)
{
3243 3244
	size_t i;

3245 3246 3247
	if (!obj)
		return;

3248 3249 3250
	if (obj->clear_priv)
		obj->clear_priv(obj, obj->priv);

3251
	bpf_object__elf_finish(obj);
3252
	bpf_object__unload(obj);
3253
	btf__free(obj->btf);
3254
	btf_ext__free(obj->btf_ext);
3255

3256
	for (i = 0; i < obj->nr_maps; i++) {
3257
		zfree(&obj->maps[i].name);
3258 3259 3260 3261 3262 3263
		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;
	}
3264 3265 3266

	zfree(&obj->sections.rodata);
	zfree(&obj->sections.data);
3267 3268
	zfree(&obj->maps);
	obj->nr_maps = 0;
3269 3270 3271 3272 3273 3274 3275

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

3276
	list_del(&obj->list);
3277 3278
	free(obj);
}
3279

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

3299
const char *bpf_object__name(struct bpf_object *obj)
3300
{
3301
	return obj ? obj->path : ERR_PTR(-EINVAL);
3302 3303
}

3304
unsigned int bpf_object__kversion(struct bpf_object *obj)
3305
{
3306
	return obj ? obj->kern_version : 0;
3307 3308
}

3309 3310 3311 3312 3313
struct btf *bpf_object__btf(struct bpf_object *obj)
{
	return obj ? obj->btf : NULL;
}

3314 3315 3316 3317 3318
int bpf_object__btf_fd(const struct bpf_object *obj)
{
	return obj->btf ? btf__fd(obj->btf) : -1;
}

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

3335
static struct bpf_program *
3336
__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward)
3337
{
3338
	size_t nr_programs = obj->nr_programs;
3339
	ssize_t idx;
3340

3341
	if (!nr_programs)
3342 3343
		return NULL;

3344 3345 3346 3347 3348
	if (!p)
		/* Iter from the beginning */
		return forward ? &obj->programs[0] :
			&obj->programs[nr_programs - 1];

3349
	if (p->obj != obj) {
3350 3351 3352 3353
		pr_warning("error: program handler doesn't match object\n");
		return NULL;
	}

3354
	idx = (p - obj->programs) + (forward ? 1 : -1);
3355
	if (idx >= obj->nr_programs || idx < 0)
3356 3357 3358 3359
		return NULL;
	return &obj->programs[idx];
}

3360 3361 3362 3363 3364 3365
struct bpf_program *
bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
{
	struct bpf_program *prog = prev;

	do {
3366
		prog = __bpf_program__iter(prog, obj, true);
3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377
	} 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 {
3378
		prog = __bpf_program__iter(prog, obj, false);
3379 3380 3381 3382 3383
	} while (prog && bpf_program__is_function_storage(prog, obj));

	return prog;
}

3384 3385
int bpf_program__set_priv(struct bpf_program *prog, void *priv,
			  bpf_program_clear_priv_t clear_priv)
3386 3387 3388 3389 3390 3391 3392 3393 3394
{
	if (prog->priv && prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

3395
void *bpf_program__priv(struct bpf_program *prog)
3396
{
3397
	return prog ? prog->priv : ERR_PTR(-EINVAL);
3398 3399
}

3400 3401 3402 3403 3404
void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex)
{
	prog->prog_ifindex = ifindex;
}

3405
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
3406 3407 3408 3409
{
	const char *title;

	title = prog->section_name;
3410
	if (needs_copy) {
3411 3412 3413
		title = strdup(title);
		if (!title) {
			pr_warning("failed to strdup program title\n");
3414
			return ERR_PTR(-ENOMEM);
3415 3416 3417 3418 3419 3420 3421 3422
		}
	}

	return title;
}

int bpf_program__fd(struct bpf_program *prog)
{
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
	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;

3458 3459 3460
	if (!prog)
		return -EINVAL;

3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474
	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;
3475
}
3476

3477
void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
3478 3479 3480 3481 3482 3483 3484 3485 3486 3487
{
	prog->type = type;
}

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

3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501
#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);	\
}							\

3502
BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
3503
BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
3504 3505
BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
3506
BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
3507
BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT);
3508 3509
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
3510

J
John Fastabend 已提交
3511 3512
void bpf_program__set_expected_attach_type(struct bpf_program *prog,
					   enum bpf_attach_type type)
3513 3514 3515 3516
{
	prog->expected_attach_type = type;
}

3517 3518
#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, atype) \
	{ string, sizeof(string) - 1, ptype, eatype, is_attachable, atype }
3519

3520
/* Programs that can NOT be attached. */
3521
#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0)
3522

3523 3524
/* Programs that can be attached. */
#define BPF_APROG_SEC(string, ptype, atype) \
3525
	BPF_PROG_SEC_IMPL(string, ptype, 0, 1, atype)
3526

3527 3528
/* Programs that must specify expected attach type at load time. */
#define BPF_EAPROG_SEC(string, ptype, eatype) \
3529
	BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, eatype)
3530 3531 3532 3533 3534

/* 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)
3535

3536 3537 3538 3539
static const struct {
	const char *sec;
	size_t len;
	enum bpf_prog_type prog_type;
3540
	enum bpf_attach_type expected_attach_type;
3541
	int is_attachable;
3542
	enum bpf_attach_type attach_type;
3543
} section_names[] = {
3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556
	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),
3557 3558 3559 3560
	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),
3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571
	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),
3572 3573 3574 3575
	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),
3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594
	BPF_APROG_COMPAT("sk_skb",		BPF_PROG_TYPE_SK_SKB),
	BPF_APROG_SEC("sk_msg",			BPF_PROG_TYPE_SK_MSG,
						BPF_SK_MSG_VERDICT),
	BPF_APROG_SEC("lirc_mode2",		BPF_PROG_TYPE_LIRC_MODE2,
						BPF_LIRC_MODE2),
	BPF_APROG_SEC("flow_dissector",		BPF_PROG_TYPE_FLOW_DISSECTOR,
						BPF_FLOW_DISSECTOR),
	BPF_EAPROG_SEC("cgroup/bind4",		BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
						BPF_CGROUP_INET4_BIND),
	BPF_EAPROG_SEC("cgroup/bind6",		BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
						BPF_CGROUP_INET6_BIND),
	BPF_EAPROG_SEC("cgroup/connect4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
						BPF_CGROUP_INET4_CONNECT),
	BPF_EAPROG_SEC("cgroup/connect6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
						BPF_CGROUP_INET6_CONNECT),
	BPF_EAPROG_SEC("cgroup/sendmsg4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
						BPF_CGROUP_UDP4_SENDMSG),
	BPF_EAPROG_SEC("cgroup/sendmsg6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
						BPF_CGROUP_UDP6_SENDMSG),
A
Andrey Ignatov 已提交
3595 3596
	BPF_EAPROG_SEC("cgroup/sysctl",		BPF_PROG_TYPE_CGROUP_SYSCTL,
						BPF_CGROUP_SYSCTL),
3597
};
3598

3599
#undef BPF_PROG_SEC_IMPL
3600
#undef BPF_PROG_SEC
3601 3602 3603
#undef BPF_APROG_SEC
#undef BPF_EAPROG_SEC
#undef BPF_APROG_COMPAT
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
#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;
}

3633 3634
int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
			     enum bpf_attach_type *expected_attach_type)
3635
{
3636
	char *type_names;
3637 3638
	int i;

3639 3640
	if (!name)
		return -EINVAL;
3641

3642 3643 3644 3645 3646 3647 3648
	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;
	}
3649 3650 3651 3652 3653 3654 3655
	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);
	}

3656 3657
	return -EINVAL;
}
3658

3659 3660 3661
int libbpf_attach_type_by_name(const char *name,
			       enum bpf_attach_type *attach_type)
{
3662
	char *type_names;
3663 3664 3665 3666 3667 3668 3669 3670
	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;
3671
		if (!section_names[i].is_attachable)
3672 3673 3674 3675
			return -EINVAL;
		*attach_type = section_names[i].attach_type;
		return 0;
	}
3676 3677 3678 3679 3680 3681 3682
	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);
	}

3683 3684 3685
	return -EINVAL;
}

3686 3687 3688 3689 3690 3691 3692
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);
3693 3694
}

3695
int bpf_map__fd(struct bpf_map *map)
3696
{
3697
	return map ? map->fd : -EINVAL;
3698 3699
}

3700
const struct bpf_map_def *bpf_map__def(struct bpf_map *map)
3701
{
3702
	return map ? &map->def : ERR_PTR(-EINVAL);
3703 3704
}

3705
const char *bpf_map__name(struct bpf_map *map)
3706
{
3707
	return map ? map->name : NULL;
3708 3709
}

3710
__u32 bpf_map__btf_key_type_id(const struct bpf_map *map)
3711
{
3712
	return map ? map->btf_key_type_id : 0;
3713 3714
}

3715
__u32 bpf_map__btf_value_type_id(const struct bpf_map *map)
3716
{
3717
	return map ? map->btf_value_type_id : 0;
3718 3719
}

3720 3721
int bpf_map__set_priv(struct bpf_map *map, void *priv,
		     bpf_map_clear_priv_t clear_priv)
3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735
{
	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;
}

3736
void *bpf_map__priv(struct bpf_map *map)
3737
{
3738
	return map ? map->priv : ERR_PTR(-EINVAL);
3739 3740
}

3741 3742 3743 3744 3745
bool bpf_map__is_offload_neutral(struct bpf_map *map)
{
	return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
}

3746 3747 3748 3749 3750
bool bpf_map__is_internal(struct bpf_map *map)
{
	return map->libbpf_type != LIBBPF_MAP_UNSPEC;
}

3751 3752 3753 3754 3755
void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
{
	map->map_ifindex = ifindex;
}

3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769
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;
}

3770 3771
static struct bpf_map *
__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i)
3772
{
3773
	ssize_t idx;
3774 3775 3776 3777 3778 3779 3780 3781
	struct bpf_map *s, *e;

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

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

3782
	if ((m < s) || (m >= e)) {
3783 3784 3785 3786 3787
		pr_warning("error in %s: map handler doesn't belong to object\n",
			   __func__);
		return NULL;
	}

3788 3789
	idx = (m - obj->maps) + i;
	if (idx >= obj->nr_maps || idx < 0)
3790 3791 3792
		return NULL;
	return &obj->maps[idx];
}
3793

3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814
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);
}

3815
struct bpf_map *
3816
bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
3817 3818 3819
{
	struct bpf_map *pos;

3820
	bpf_object__for_each_map(pos, obj) {
3821
		if (pos->name && !strcmp(pos->name, name))
3822 3823 3824 3825
			return pos;
	}
	return NULL;
}
3826

3827 3828 3829 3830 3831 3832
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));
}

3833 3834 3835
struct bpf_map *
bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset)
{
3836
	return ERR_PTR(-ENOTSUP);
3837
}
3838 3839 3840

long libbpf_get_error(const void *ptr)
{
3841
	return PTR_ERR_OR_ZERO(ptr);
3842
}
3843 3844 3845

int bpf_prog_load(const char *file, enum bpf_prog_type type,
		  struct bpf_object **pobj, int *prog_fd)
3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858
{
	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)
3859
{
3860 3861 3862 3863
	struct bpf_object_open_attr open_attr = {
		.file		= attr->file,
		.prog_type	= attr->prog_type,
	};
3864
	struct bpf_program *prog, *first_prog = NULL;
3865 3866
	enum bpf_attach_type expected_attach_type;
	enum bpf_prog_type prog_type;
3867
	struct bpf_object *obj;
3868
	struct bpf_map *map;
3869 3870
	int err;

3871 3872
	if (!attr)
		return -EINVAL;
3873 3874
	if (!attr->file)
		return -EINVAL;
3875

3876
	obj = bpf_object__open_xattr(&open_attr);
3877
	if (IS_ERR_OR_NULL(obj))
3878 3879
		return -ENOENT;

3880 3881 3882 3883 3884
	bpf_object__for_each_program(prog, obj) {
		/*
		 * If type is not specified, try to guess it based on
		 * section name.
		 */
3885
		prog_type = attr->prog_type;
3886
		prog->prog_ifindex = attr->ifindex;
3887 3888
		expected_attach_type = attr->expected_attach_type;
		if (prog_type == BPF_PROG_TYPE_UNSPEC) {
3889 3890 3891
			err = bpf_program__identify_section(prog, &prog_type,
							    &expected_attach_type);
			if (err < 0) {
3892 3893 3894
				bpf_object__close(obj);
				return -EINVAL;
			}
3895
		}
3896

3897 3898 3899 3900
		bpf_program__set_type(prog, prog_type);
		bpf_program__set_expected_attach_type(prog,
						      expected_attach_type);

3901
		prog->log_level = attr->log_level;
3902
		prog->prog_flags = attr->prog_flags;
3903
		if (!first_prog)
3904 3905 3906
			first_prog = prog;
	}

3907
	bpf_object__for_each_map(map, obj) {
3908 3909
		if (!bpf_map__is_offload_neutral(map))
			map->map_ifindex = attr->ifindex;
3910 3911
	}

3912 3913 3914 3915
	if (!first_prog) {
		pr_warning("object file doesn't contain bpf program\n");
		bpf_object__close(obj);
		return -ENOENT;
3916 3917
	}

3918 3919 3920 3921 3922 3923 3924
	err = bpf_object__load(obj);
	if (err) {
		bpf_object__close(obj);
		return -EINVAL;
	}

	*pobj = obj;
3925
	*prog_fd = bpf_program__fd(first_prog);
3926 3927
	return 0;
}
3928 3929

enum bpf_perf_event_ret
3930 3931 3932
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)
3933
{
3934
	struct perf_event_mmap_page *header = mmap_mem;
3935
	__u64 data_head = ring_buffer_read_head(header);
3936
	__u64 data_tail = header->data_tail;
3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955
	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;
3956 3957 3958
					ret = LIBBPF_PERF_EVENT_ERROR;
					break;
				}
3959
				*copy_size = ehdr_size;
3960 3961
			}

3962 3963 3964
			memcpy(*copy_mem, copy_start, len_first);
			memcpy(*copy_mem + len_first, base, len_secnd);
			ehdr = *copy_mem;
3965 3966
		}

3967 3968
		ret = fn(ehdr, private_data);
		data_tail += ehdr_size;
3969 3970 3971 3972
		if (ret != LIBBPF_PERF_EVENT_CONT)
			break;
	}

3973
	ring_buffer_write_tail(header, data_tail);
3974 3975
	return ret;
}
3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221

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);
	}
}
4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278

int libbpf_num_possible_cpus(void)
{
	static const char *fcpu = "/sys/devices/system/cpu/possible";
	int len = 0, n = 0, il = 0, ir = 0;
	unsigned int start = 0, end = 0;
	static int cpus;
	char buf[128];
	int error = 0;
	int fd = -1;

	if (cpus > 0)
		return cpus;

	fd = open(fcpu, O_RDONLY);
	if (fd < 0) {
		error = errno;
		pr_warning("Failed to open file %s: %s\n",
			   fcpu, strerror(error));
		return -error;
	}
	len = read(fd, buf, sizeof(buf));
	close(fd);
	if (len <= 0) {
		error = len ? errno : EINVAL;
		pr_warning("Failed to read # of possible cpus from %s: %s\n",
			   fcpu, strerror(error));
		return -error;
	}
	if (len == sizeof(buf)) {
		pr_warning("File %s size overflow\n", fcpu);
		return -EOVERFLOW;
	}
	buf[len] = '\0';

	for (ir = 0, cpus = 0; ir <= len; ir++) {
		/* Each sub string separated by ',' has format \d+-\d+ or \d+ */
		if (buf[ir] == ',' || buf[ir] == '\0') {
			buf[ir] = '\0';
			n = sscanf(&buf[il], "%u-%u", &start, &end);
			if (n <= 0) {
				pr_warning("Failed to get # CPUs from %s\n",
					   &buf[il]);
				return -EINVAL;
			} else if (n == 1) {
				end = start;
			}
			cpus += end - start + 1;
			il = ir + 1;
		}
	}
	if (cpus <= 0) {
		pr_warning("Invalid #CPUs %d from %s\n", cpus, fcpu);
		return -EINVAL;
	}
	return cpus;
}