libbpf.c 65.8 KB
Newer Older
1
// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
2

3 4 5 6 7 8
/*
 * Common eBPF ELF object loading operations.
 *
 * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
 * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
 * Copyright (C) 2015 Huawei Inc.
9
 * Copyright (C) 2017 Nicira, Inc.
10 11
 */

12
#define _GNU_SOURCE
13
#include <stdlib.h>
14 15
#include <stdio.h>
#include <stdarg.h>
16
#include <libgen.h>
17
#include <inttypes.h>
18
#include <string.h>
19
#include <unistd.h>
20 21
#include <fcntl.h>
#include <errno.h>
22
#include <asm/unistd.h>
23
#include <linux/err.h>
24
#include <linux/kernel.h>
25
#include <linux/bpf.h>
26
#include <linux/btf.h>
27
#include <linux/filter.h>
28
#include <linux/list.h>
29
#include <linux/limits.h>
30
#include <linux/perf_event.h>
31
#include <linux/ring_buffer.h>
32 33 34
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/vfs.h>
35
#include <tools/libc_compat.h>
36 37
#include <libelf.h>
#include <gelf.h>
38 39

#include "libbpf.h"
40
#include "bpf.h"
41
#include "btf.h"
42
#include "str_error.h"
43

44 45 46 47
#ifndef EM_BPF
#define EM_BPF 247
#endif

48 49 50 51
#ifndef BPF_FS_MAGIC
#define BPF_FS_MAGIC		0xcafe4a11
#endif

52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87
#define __printf(a, b)	__attribute__((format(printf, a, b)))

__printf(1, 2)
static int __base_pr(const char *format, ...)
{
	va_list args;
	int err;

	va_start(args, format);
	err = vfprintf(stderr, format, args);
	va_end(args);
	return err;
}

static __printf(1, 2) libbpf_print_fn_t __pr_warning = __base_pr;
static __printf(1, 2) libbpf_print_fn_t __pr_info = __base_pr;
static __printf(1, 2) libbpf_print_fn_t __pr_debug;

#define __pr(func, fmt, ...)	\
do {				\
	if ((func))		\
		(func)("libbpf: " fmt, ##__VA_ARGS__); \
} while (0)

#define pr_warning(fmt, ...)	__pr(__pr_warning, fmt, ##__VA_ARGS__)
#define pr_info(fmt, ...)	__pr(__pr_info, fmt, ##__VA_ARGS__)
#define pr_debug(fmt, ...)	__pr(__pr_debug, fmt, ##__VA_ARGS__)

void libbpf_set_print(libbpf_print_fn_t warn,
		      libbpf_print_fn_t info,
		      libbpf_print_fn_t debug)
{
	__pr_warning = warn;
	__pr_info = info;
	__pr_debug = debug;
}
88

89 90 91 92 93 94 95 96 97
#define STRERR_BUFSIZE  128

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


98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117
/* 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

118 119 120 121 122
struct bpf_capabilities {
	/* v4.14: kernel support for program & map names. */
	__u32 name:1;
};

123 124 125 126 127 128 129
/*
 * 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;
130
	char *name;
131
	int prog_ifindex;
132
	char *section_name;
S
Stanislav Fomichev 已提交
133 134 135 136
	/* section_name with / replaced by _; makes recursive pinning
	 * in bpf_object__pin_programs easier
	 */
	char *pin_name;
137
	struct bpf_insn *insns;
138
	size_t insns_cnt, main_prog_cnt;
139
	enum bpf_prog_type type;
140

141 142 143 144 145
	struct reloc_desc {
		enum {
			RELO_LD64,
			RELO_CALL,
		} type;
146
		int insn_idx;
147 148 149 150
		union {
			int map_idx;
			int text_off;
		};
151 152
	} *reloc_desc;
	int nr_reloc;
153

154 155 156 157 158
	struct {
		int nr;
		int *fds;
	} instances;
	bpf_program_prep_t preprocessor;
159 160 161 162

	struct bpf_object *obj;
	void *priv;
	bpf_program_clear_priv_t clear_priv;
163 164

	enum bpf_attach_type expected_attach_type;
165 166 167 168
	int btf_fd;
	void *func_info;
	__u32 func_info_rec_size;
	__u32 func_info_len;
169 170

	struct bpf_capabilities *caps;
171 172
};

173 174
struct bpf_map {
	int fd;
175
	char *name;
E
Eric Leblond 已提交
176
	size_t offset;
177
	int map_ifindex;
178
	int inner_map_fd;
179
	struct bpf_map_def def;
180 181
	__u32 btf_key_type_id;
	__u32 btf_value_type_id;
182 183 184 185
	void *priv;
	bpf_map_clear_priv_t clear_priv;
};

186 187
static LIST_HEAD(bpf_objects_list);

188
struct bpf_object {
189
	char license[64];
190
	__u32 kern_version;
191

192 193
	struct bpf_program *programs;
	size_t nr_programs;
194 195 196
	struct bpf_map *maps;
	size_t nr_maps;

197
	bool loaded;
198
	bool has_pseudo_calls;
199

200 201 202 203 204 205
	/*
	 * Information when doing elf related work. Only valid if fd
	 * is valid.
	 */
	struct {
		int fd;
206 207
		void *obj_buf;
		size_t obj_buf_sz;
208 209
		Elf *elf;
		GElf_Ehdr ehdr;
210
		Elf_Data *symbols;
211
		size_t strtabidx;
212 213 214 215 216
		struct {
			GElf_Shdr shdr;
			Elf_Data *data;
		} *reloc;
		int nr_reloc;
217
		int maps_shndx;
218
		int text_shndx;
219
	} efile;
220 221 222 223 224 225
	/*
	 * 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;
226

227
	struct btf *btf;
228
	struct btf_ext *btf_ext;
229

230 231 232
	void *priv;
	bpf_object_clear_priv_t clear_priv;

233 234
	struct bpf_capabilities caps;

235 236 237 238
	char path[];
};
#define obj_elf_valid(o)	((o)->efile.elf)

239
void bpf_program__unload(struct bpf_program *prog)
240
{
241 242
	int i;

243 244 245
	if (!prog)
		return;

246 247 248 249 250 251 252 253 254 255 256 257 258 259
	/*
	 * 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);
260 261 262

	zclose(prog->btf_fd);
	zfree(&prog->func_info);
263 264
}

265 266 267 268 269
static void bpf_program__exit(struct bpf_program *prog)
{
	if (!prog)
		return;

270 271 272 273 274 275
	if (prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

276
	bpf_program__unload(prog);
277
	zfree(&prog->name);
278
	zfree(&prog->section_name);
S
Stanislav Fomichev 已提交
279
	zfree(&prog->pin_name);
280
	zfree(&prog->insns);
281 282 283
	zfree(&prog->reloc_desc);

	prog->nr_reloc = 0;
284 285 286 287
	prog->insns_cnt = 0;
	prog->idx = -1;
}

S
Stanislav Fomichev 已提交
288 289 290 291 292 293 294 295 296 297 298
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;
}

299
static int
300 301
bpf_program__init(void *data, size_t size, char *section_name, int idx,
		  struct bpf_program *prog)
302 303
{
	if (size < sizeof(struct bpf_insn)) {
304
		pr_warning("corrupted section '%s'\n", section_name);
305 306 307 308 309
		return -EINVAL;
	}

	bzero(prog, sizeof(*prog));

310
	prog->section_name = strdup(section_name);
311
	if (!prog->section_name) {
312 313
		pr_warning("failed to alloc name for prog under section(%d) %s\n",
			   idx, section_name);
314 315 316
		goto errout;
	}

S
Stanislav Fomichev 已提交
317 318 319 320 321 322 323
	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;
	}

324 325
	prog->insns = malloc(size);
	if (!prog->insns) {
326 327
		pr_warning("failed to alloc insns for prog under section %s\n",
			   section_name);
328 329 330 331 332 333
		goto errout;
	}
	prog->insns_cnt = size / sizeof(struct bpf_insn);
	memcpy(prog->insns, data,
	       prog->insns_cnt * sizeof(struct bpf_insn));
	prog->idx = idx;
334 335
	prog->instances.fds = NULL;
	prog->instances.nr = -1;
336
	prog->type = BPF_PROG_TYPE_KPROBE;
337
	prog->btf_fd = -1;
338 339 340 341 342 343 344 345 346

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

static int
bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
347
			char *section_name, int idx)
348 349 350 351
{
	struct bpf_program prog, *progs;
	int nr_progs, err;

352
	err = bpf_program__init(data, size, section_name, idx, &prog);
353 354 355
	if (err)
		return err;

356
	prog.caps = &obj->caps;
357 358 359
	progs = obj->programs;
	nr_progs = obj->nr_programs;

360
	progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
361 362 363 364 365 366
	if (!progs) {
		/*
		 * In this case the original obj->programs
		 * is still valid, so don't need special treat for
		 * bpf_close_object().
		 */
367 368
		pr_warning("failed to alloc a new program under section '%s'\n",
			   section_name);
369 370 371 372 373 374 375
		bpf_program__exit(&prog);
		return -ENOMEM;
	}

	pr_debug("found program %s\n", prog.section_name);
	obj->programs = progs;
	obj->nr_programs = nr_progs + 1;
376
	prog.obj = obj;
377 378 379 380
	progs[nr_progs] = prog;
	return 0;
}

381 382 383 384 385 386 387 388
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++) {
389
		const char *name = NULL;
390 391 392 393 394 395 396 397 398 399 400

		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;
401 402
			if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL)
				continue;
403 404 405 406 407 408 409 410 411 412 413

			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;
			}
		}

414 415 416
		if (!name && prog->idx == obj->efile.text_shndx)
			name = ".text";

417 418 419 420 421
		if (!name) {
			pr_warning("failed to find sym for prog %s\n",
				   prog->section_name);
			return -EINVAL;
		}
422

423 424 425 426 427 428 429 430 431 432 433
		prog->name = strdup(name);
		if (!prog->name) {
			pr_warning("failed to allocate memory for prog sym %s\n",
				   name);
			return -ENOMEM;
		}
	}

	return 0;
}

434 435 436
static struct bpf_object *bpf_object__new(const char *path,
					  void *obj_buf,
					  size_t obj_buf_sz)
437 438 439 440 441 442
{
	struct bpf_object *obj;

	obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1);
	if (!obj) {
		pr_warning("alloc memory failed for %s\n", path);
443
		return ERR_PTR(-ENOMEM);
444 445 446 447
	}

	strcpy(obj->path, path);
	obj->efile.fd = -1;
448 449 450 451 452 453 454 455 456

	/*
	 * Caller of this function should also calls
	 * bpf_object__elf_finish() after data collection to return
	 * obj_buf to user. If not, we should duplicate the buffer to
	 * avoid user freeing them before elf finish.
	 */
	obj->efile.obj_buf = obj_buf;
	obj->efile.obj_buf_sz = obj_buf_sz;
457
	obj->efile.maps_shndx = -1;
458

459
	obj->loaded = false;
460 461 462

	INIT_LIST_HEAD(&obj->list);
	list_add(&obj->list, &bpf_objects_list);
463 464 465 466 467 468 469 470 471 472 473 474
	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;
	}
475
	obj->efile.symbols = NULL;
476 477 478

	zfree(&obj->efile.reloc);
	obj->efile.nr_reloc = 0;
479
	zclose(obj->efile.fd);
480 481
	obj->efile.obj_buf = NULL;
	obj->efile.obj_buf_sz = 0;
482 483 484 485 486 487 488 489 490
}

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");
491
		return -LIBBPF_ERRNO__LIBELF;
492 493
	}

494 495 496 497 498 499 500 501 502 503
	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) {
504
			char errmsg[STRERR_BUFSIZE];
505 506
			char *cp = libbpf_strerror_r(errno, errmsg,
						     sizeof(errmsg));
507 508

			pr_warning("failed to open %s: %s\n", obj->path, cp);
509 510 511 512 513 514
			return -errno;
		}

		obj->efile.elf = elf_begin(obj->efile.fd,
				LIBBPF_ELF_C_READ_MMAP,
				NULL);
515 516 517 518 519
	}

	if (!obj->efile.elf) {
		pr_warning("failed to open %s as ELF file\n",
				obj->path);
520
		err = -LIBBPF_ERRNO__LIBELF;
521 522 523 524 525 526
		goto errout;
	}

	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
		pr_warning("failed to get EHDR from %s\n",
				obj->path);
527
		err = -LIBBPF_ERRNO__FORMAT;
528 529 530 531
		goto errout;
	}
	ep = &obj->efile.ehdr;

532 533
	/* Old LLVM set e_machine to EM_NONE */
	if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) {
534 535
		pr_warning("%s is not an eBPF object file\n",
			obj->path);
536
		err = -LIBBPF_ERRNO__FORMAT;
537 538 539 540 541 542 543 544 545
		goto errout;
	}

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

546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563
static int
bpf_object__check_endianness(struct bpf_object *obj)
{
	static unsigned int const endian = 1;

	switch (obj->efile.ehdr.e_ident[EI_DATA]) {
	case ELFDATA2LSB:
		/* We are big endian, BPF obj is little endian. */
		if (*(unsigned char const *)&endian != 1)
			goto mismatch;
		break;

	case ELFDATA2MSB:
		/* We are little endian, BPF obj is big endian. */
		if (*(unsigned char const *)&endian != 0)
			goto mismatch;
		break;
	default:
564
		return -LIBBPF_ERRNO__ENDIAN;
565 566 567 568 569 570
	}

	return 0;

mismatch:
	pr_warning("Error: endianness mismatch.\n");
571
	return -LIBBPF_ERRNO__ENDIAN;
572 573
}

574 575 576 577 578 579 580 581 582 583 584 585 586 587
static int
bpf_object__init_license(struct bpf_object *obj,
			 void *data, size_t size)
{
	memcpy(obj->license, data,
	       min(size, sizeof(obj->license) - 1));
	pr_debug("license of %s is %s\n", obj->path, obj->license);
	return 0;
}

static int
bpf_object__init_kversion(struct bpf_object *obj,
			  void *data, size_t size)
{
588
	__u32 kver;
589 590 591

	if (size != sizeof(kver)) {
		pr_warning("invalid kver section in %s\n", obj->path);
592
		return -LIBBPF_ERRNO__FORMAT;
593 594 595 596 597 598 599 600
	}
	memcpy(&kver, data, sizeof(kver));
	obj->kern_version = kver;
	pr_debug("kernel version of %s is %x\n", obj->path,
		 obj->kern_version);
	return 0;
}

E
Eric Leblond 已提交
601 602 603 604
static int compare_bpf_map(const void *_a, const void *_b)
{
	const struct bpf_map *a = _a;
	const struct bpf_map *b = _b;
605

E
Eric Leblond 已提交
606
	return a->offset - b->offset;
607 608
}

609 610 611 612 613 614 615 616
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;
}

617
static int
618
bpf_object__init_maps(struct bpf_object *obj, int flags)
619
{
620
	bool strict = !(flags & MAPS_RELAX_COMPAT);
621
	int i, map_idx, map_def_sz, nr_maps = 0;
E
Eric Leblond 已提交
622 623
	Elf_Scn *scn;
	Elf_Data *data;
624 625
	Elf_Data *symbols = obj->efile.symbols;

E
Eric Leblond 已提交
626 627 628 629 630 631 632 633 634 635 636
	if (obj->efile.maps_shndx < 0)
		return -EINVAL;
	if (!symbols)
		return -EINVAL;

	scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx);
	if (scn)
		data = elf_getdata(scn, NULL);
	if (!scn || !data) {
		pr_warning("failed to get Elf_Data from map section %d\n",
			   obj->efile.maps_shndx);
637
		return -EINVAL;
E
Eric Leblond 已提交
638
	}
639

E
Eric Leblond 已提交
640 641 642 643 644 645 646
	/*
	 * 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.
	 */
647 648
	for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
		GElf_Sym sym;
E
Eric Leblond 已提交
649 650 651 652 653 654 655 656 657 658 659 660 661 662 663

		if (!gelf_getsym(symbols, i, &sym))
			continue;
		if (sym.st_shndx != obj->efile.maps_shndx)
			continue;
		nr_maps++;
	}

	/* Alloc obj->maps and fill nr_maps. */
	pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path,
		 nr_maps, data->d_size);

	if (!nr_maps)
		return 0;

664 665 666 667 668 669 670 671 672
	/* Assume equally sized map definitions */
	map_def_sz = data->d_size / nr_maps;
	if (!data->d_size || (data->d_size % nr_maps) != 0) {
		pr_warning("unable to determine map definition size "
			   "section %s, %d maps in %zd bytes\n",
			   obj->path, nr_maps, data->d_size);
		return -EINVAL;
	}

E
Eric Leblond 已提交
673 674 675 676 677 678 679
	obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
	if (!obj->maps) {
		pr_warning("alloc maps for object failed\n");
		return -ENOMEM;
	}
	obj->nr_maps = nr_maps;

680 681 682 683 684 685
	for (i = 0; i < nr_maps; i++) {
		/*
		 * fill all fd with -1 so won't close incorrect
		 * fd (fd=0 is stdin) when failure (zclose won't close
		 * negative fd)).
		 */
E
Eric Leblond 已提交
686
		obj->maps[i].fd = -1;
687 688
		obj->maps[i].inner_map_fd = -1;
	}
E
Eric Leblond 已提交
689 690 691 692 693 694

	/*
	 * Fill obj->maps using data in "maps" section.
	 */
	for (i = 0, map_idx = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
		GElf_Sym sym;
695
		const char *map_name;
E
Eric Leblond 已提交
696
		struct bpf_map_def *def;
697 698 699

		if (!gelf_getsym(symbols, i, &sym))
			continue;
700
		if (sym.st_shndx != obj->efile.maps_shndx)
701 702 703
			continue;

		map_name = elf_strptr(obj->efile.elf,
704
				      obj->efile.strtabidx,
705
				      sym.st_name);
E
Eric Leblond 已提交
706
		obj->maps[map_idx].offset = sym.st_value;
707
		if (sym.st_value + map_def_sz > data->d_size) {
E
Eric Leblond 已提交
708 709 710
			pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
				   obj->path, map_name);
			return -EINVAL;
711
		}
E
Eric Leblond 已提交
712

713
		obj->maps[map_idx].name = strdup(map_name);
714 715 716 717
		if (!obj->maps[map_idx].name) {
			pr_warning("failed to alloc map name\n");
			return -ENOMEM;
		}
E
Eric Leblond 已提交
718
		pr_debug("map %d is \"%s\"\n", map_idx,
719
			 obj->maps[map_idx].name);
E
Eric Leblond 已提交
720
		def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743
		/*
		 * If the definition of the map in the object file fits in
		 * bpf_map_def, copy it.  Any extra fields in our version
		 * of bpf_map_def will default to zero as a result of the
		 * calloc above.
		 */
		if (map_def_sz <= sizeof(struct bpf_map_def)) {
			memcpy(&obj->maps[map_idx].def, def, map_def_sz);
		} else {
			/*
			 * Here the map structure being read is bigger than what
			 * we expect, truncate if the excess bits are all zero.
			 * If they are not zero, reject this map as
			 * incompatible.
			 */
			char *b;
			for (b = ((char *)def) + sizeof(struct bpf_map_def);
			     b < ((char *)def) + map_def_sz; b++) {
				if (*b != 0) {
					pr_warning("maps section in %s: \"%s\" "
						   "has unrecognized, non-zero "
						   "options\n",
						   obj->path, map_name);
744 745
					if (strict)
						return -EINVAL;
746 747 748 749 750
				}
			}
			memcpy(&obj->maps[map_idx].def, def,
			       sizeof(struct bpf_map_def));
		}
E
Eric Leblond 已提交
751
		map_idx++;
752
	}
E
Eric Leblond 已提交
753 754

	qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map);
755
	return 0;
756 757
}

758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775
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;
}

776
static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
777 778 779 780
{
	Elf *elf = obj->efile.elf;
	GElf_Ehdr *ep = &obj->efile.ehdr;
	Elf_Scn *scn = NULL;
781
	int idx = 0, err = 0;
782 783 784 785 786

	/* Elf is corrupted/truncated, avoid calling elf_strptr. */
	if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
		pr_warning("failed to get e_shstrndx from %s\n",
			   obj->path);
787
		return -LIBBPF_ERRNO__FORMAT;
788 789 790 791 792 793 794 795 796
	}

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

		idx++;
		if (gelf_getshdr(scn, &sh) != &sh) {
797 798
			pr_warning("failed to get section(%d) header from %s\n",
				   idx, obj->path);
799
			err = -LIBBPF_ERRNO__FORMAT;
800 801 802 803 804
			goto out;
		}

		name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
		if (!name) {
805 806
			pr_warning("failed to get section(%d) name from %s\n",
				   idx, obj->path);
807
			err = -LIBBPF_ERRNO__FORMAT;
808 809 810 811 812
			goto out;
		}

		data = elf_getdata(scn, 0);
		if (!data) {
813 814
			pr_warning("failed to get section(%d) data from %s(%s)\n",
				   idx, name, obj->path);
815
			err = -LIBBPF_ERRNO__FORMAT;
816 817
			goto out;
		}
818 819
		pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n",
			 idx, name, (unsigned long)data->d_size,
820 821
			 (int)sh.sh_link, (unsigned long)sh.sh_flags,
			 (int)sh.sh_type);
822 823 824 825 826 827 828 829 830

		if (strcmp(name, "license") == 0)
			err = bpf_object__init_license(obj,
						       data->d_buf,
						       data->d_size);
		else if (strcmp(name, "version") == 0)
			err = bpf_object__init_kversion(obj,
							data->d_buf,
							data->d_size);
E
Eric Leblond 已提交
831
		else if (strcmp(name, "maps") == 0)
832
			obj->efile.maps_shndx = idx;
833 834 835 836 837 838 839 840
		else if (strcmp(name, BTF_ELF_SEC) == 0) {
			obj->btf = btf__new(data->d_buf, data->d_size,
					    __pr_debug);
			if (IS_ERR(obj->btf)) {
				pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
					   BTF_ELF_SEC, PTR_ERR(obj->btf));
				obj->btf = NULL;
			}
841 842 843 844 845 846 847 848 849
		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
			obj->btf_ext = btf_ext__new(data->d_buf, data->d_size,
						    __pr_debug);
			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;
			}
850
		} else if (sh.sh_type == SHT_SYMTAB) {
851 852 853
			if (obj->efile.symbols) {
				pr_warning("bpf: multiple SYMTAB in %s\n",
					   obj->path);
854
				err = -LIBBPF_ERRNO__FORMAT;
855
			} else {
856
				obj->efile.symbols = data;
857 858
				obj->efile.strtabidx = sh.sh_link;
			}
859 860 861
		} else if ((sh.sh_type == SHT_PROGBITS) &&
			   (sh.sh_flags & SHF_EXECINSTR) &&
			   (data->d_size > 0)) {
862 863
			if (strcmp(name, ".text") == 0)
				obj->efile.text_shndx = idx;
864 865 866
			err = bpf_object__add_program(obj, data->d_buf,
						      data->d_size, name, idx);
			if (err) {
867
				char errmsg[STRERR_BUFSIZE];
868 869
				char *cp = libbpf_strerror_r(-err, errmsg,
							     sizeof(errmsg));
870

871
				pr_warning("failed to alloc program %s (%s): %s",
872
					   name, obj->path, cp);
873
			}
874 875 876
		} else if (sh.sh_type == SHT_REL) {
			void *reloc = obj->efile.reloc;
			int nr_reloc = obj->efile.nr_reloc + 1;
877 878 879 880 881 882 883 884
			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;
			}
885

886 887
			reloc = reallocarray(reloc, nr_reloc,
					     sizeof(*obj->efile.reloc));
888 889 890 891 892 893 894 895 896 897 898 899
			if (!reloc) {
				pr_warning("realloc failed\n");
				err = -ENOMEM;
			} else {
				int n = nr_reloc - 1;

				obj->efile.reloc = reloc;
				obj->efile.nr_reloc = nr_reloc;

				obj->efile.reloc[n].shdr = sh;
				obj->efile.reloc[n].data = data;
			}
900 901
		} else {
			pr_debug("skip section(%d) %s\n", idx, name);
902
		}
903 904
		if (err)
			goto out;
905
	}
906

907 908 909 910
	if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
		pr_warning("Corrupted ELF file: index of strtab invalid\n");
		return LIBBPF_ERRNO__FORMAT;
	}
911
	if (obj->efile.maps_shndx >= 0) {
912
		err = bpf_object__init_maps(obj, flags);
913 914 915 916
		if (err)
			goto out;
	}
	err = bpf_object__init_prog_names(obj);
917 918 919 920
out:
	return err;
}

921 922 923 924 925 926 927 928 929 930 931 932 933 934
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;
}

935 936 937 938 939 940 941 942 943 944 945 946
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;
}

947
static int
948 949
bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
			   Elf_Data *data, struct bpf_object *obj)
950
{
951 952 953 954 955
	Elf_Data *symbols = obj->efile.symbols;
	int text_shndx = obj->efile.text_shndx;
	int maps_shndx = obj->efile.maps_shndx;
	struct bpf_map *maps = obj->maps;
	size_t nr_maps = obj->nr_maps;
956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977
	int i, nrels;

	pr_debug("collecting relocating info for: '%s'\n",
		 prog->section_name);
	nrels = shdr->sh_size / shdr->sh_entsize;

	prog->reloc_desc = malloc(sizeof(*prog->reloc_desc) * nrels);
	if (!prog->reloc_desc) {
		pr_warning("failed to alloc memory in relocation\n");
		return -ENOMEM;
	}
	prog->nr_reloc = nrels;

	for (i = 0; i < nrels; i++) {
		GElf_Sym sym;
		GElf_Rel rel;
		unsigned int insn_idx;
		struct bpf_insn *insns = prog->insns;
		size_t map_idx;

		if (!gelf_getrel(data, i, &rel)) {
			pr_warning("relocation: failed to get %d reloc\n", i);
978
			return -LIBBPF_ERRNO__FORMAT;
979 980 981 982 983 984 985
		}

		if (!gelf_getsym(symbols,
				 GELF_R_SYM(rel.r_info),
				 &sym)) {
			pr_warning("relocation: symbol %"PRIx64" not found\n",
				   GELF_R_SYM(rel.r_info));
986
			return -LIBBPF_ERRNO__FORMAT;
987
		}
D
David Miller 已提交
988 989 990
		pr_debug("relo for %lld value %lld name %d\n",
			 (long long) (rel.r_info >> 32),
			 (long long) sym.st_value, sym.st_name);
991

992
		if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) {
993 994 995 996 997 998 999 1000
			pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n",
				   prog->section_name, sym.st_shndx);
			return -LIBBPF_ERRNO__RELOC;
		}

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

1001 1002 1003 1004 1005 1006 1007 1008
		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;
1009
			obj->has_pseudo_calls = true;
1010 1011 1012
			continue;
		}

1013 1014 1015
		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);
1016
			return -LIBBPF_ERRNO__RELOC;
1017 1018
		}

1019 1020 1021 1022 1023 1024 1025 1026 1027
		/* TODO: 'maps' is sorted. We can use bsearch to make it faster. */
		for (map_idx = 0; map_idx < nr_maps; map_idx++) {
			if (maps[map_idx].offset == sym.st_value) {
				pr_debug("relocation: find map %zd (%s) for insn %u\n",
					 map_idx, maps[map_idx].name, insn_idx);
				break;
			}
		}

1028 1029 1030
		if (map_idx >= nr_maps) {
			pr_warning("bpf relocation: map_idx %d large than %d\n",
				   (int)map_idx, (int)nr_maps - 1);
1031
			return -LIBBPF_ERRNO__RELOC;
1032 1033
		}

1034
		prog->reloc_desc[i].type = RELO_LD64;
1035 1036 1037 1038 1039 1040
		prog->reloc_desc[i].insn_idx = insn_idx;
		prog->reloc_desc[i].map_idx = map_idx;
	}
	return 0;
}

1041 1042
static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
{
1043 1044
	const struct btf_type *container_type;
	const struct btf_member *key, *value;
1045 1046
	struct bpf_map_def *def = &map->def;
	const size_t max_name = 256;
1047
	char container_name[max_name];
1048
	__s64 key_size, value_size;
1049
	__s32 container_id;
1050

1051 1052 1053
	if (snprintf(container_name, max_name, "____btf_map_%s", map->name) ==
	    max_name) {
		pr_warning("map:%s length of '____btf_map_%s' is too long\n",
1054 1055 1056 1057
			   map->name, map->name);
		return -EINVAL;
	}

1058 1059 1060 1061 1062
	container_id = btf__find_by_name(btf, container_name);
	if (container_id < 0) {
		pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n",
			 map->name, container_name);
		return container_id;
1063 1064
	}

1065 1066 1067 1068 1069
	container_type = btf__type_by_id(btf, container_id);
	if (!container_type) {
		pr_warning("map:%s cannot find BTF type for container_id:%u\n",
			   map->name, container_id);
		return -EINVAL;
1070 1071
	}

1072 1073 1074 1075
	if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT ||
	    BTF_INFO_VLEN(container_type->info) < 2) {
		pr_warning("map:%s container_name:%s is an invalid container struct\n",
			   map->name, container_name);
1076 1077 1078
		return -EINVAL;
	}

1079 1080 1081 1082 1083 1084 1085 1086
	key = (struct btf_member *)(container_type + 1);
	value = key + 1;

	key_size = btf__resolve_size(btf, key->type);
	if (key_size < 0) {
		pr_warning("map:%s invalid BTF key_type_size\n",
			   map->name);
		return key_size;
1087 1088
	}

1089 1090 1091 1092
	if (def->key_size != key_size) {
		pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n",
			   map->name, (__u32)key_size, def->key_size);
		return -EINVAL;
1093 1094
	}

1095
	value_size = btf__resolve_size(btf, value->type);
1096
	if (value_size < 0) {
1097
		pr_warning("map:%s invalid BTF value_type_size\n", map->name);
1098 1099 1100 1101
		return value_size;
	}

	if (def->value_size != value_size) {
1102 1103
		pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n",
			   map->name, (__u32)value_size, def->value_size);
1104 1105 1106
		return -EINVAL;
	}

1107 1108
	map->btf_key_type_id = key->type;
	map->btf_value_type_id = value->type;
1109 1110 1111 1112

	return 0;
}

J
Jakub Kicinski 已提交
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
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;
}

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
static int
bpf_object__probe_name(struct bpf_object *obj)
{
	struct bpf_load_program_attr attr;
	char *cp, errmsg[STRERR_BUFSIZE];
	struct bpf_insn insns[] = {
		BPF_MOV64_IMM(BPF_REG_0, 0),
		BPF_EXIT_INSN(),
	};
	int ret;

	/* make sure basic loading works */

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

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

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

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

	return 0;
}

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

1206 1207 1208
static int
bpf_object__create_maps(struct bpf_object *obj)
{
1209
	struct bpf_create_map_attr create_attr = {};
1210
	unsigned int i;
1211
	int err;
1212

1213
	for (i = 0; i < obj->nr_maps; i++) {
1214 1215
		struct bpf_map *map = &obj->maps[i];
		struct bpf_map_def *def = &map->def;
1216
		char *cp, errmsg[STRERR_BUFSIZE];
1217 1218
		int *pfd = &map->fd;

J
Jakub Kicinski 已提交
1219 1220 1221 1222 1223 1224
		if (map->fd >= 0) {
			pr_debug("skip map create (preset) %s: fd=%d\n",
				 map->name, map->fd);
			continue;
		}

1225 1226
		if (obj->caps.name)
			create_attr.name = map->name;
1227
		create_attr.map_ifindex = map->map_ifindex;
1228 1229 1230 1231 1232 1233
		create_attr.map_type = def->type;
		create_attr.map_flags = def->map_flags;
		create_attr.key_size = def->key_size;
		create_attr.value_size = def->value_size;
		create_attr.max_entries = def->max_entries;
		create_attr.btf_fd = 0;
1234 1235
		create_attr.btf_key_type_id = 0;
		create_attr.btf_value_type_id = 0;
1236 1237 1238
		if (bpf_map_type__is_map_in_map(def->type) &&
		    map->inner_map_fd >= 0)
			create_attr.inner_map_fd = map->inner_map_fd;
1239 1240 1241

		if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) {
			create_attr.btf_fd = btf__fd(obj->btf);
1242 1243
			create_attr.btf_key_type_id = map->btf_key_type_id;
			create_attr.btf_value_type_id = map->btf_value_type_id;
1244 1245 1246
		}

		*pfd = bpf_create_map_xattr(&create_attr);
1247
		if (*pfd < 0 && create_attr.btf_key_type_id) {
1248
			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1249
			pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
1250
				   map->name, cp, errno);
1251
			create_attr.btf_fd = 0;
1252 1253 1254 1255
			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;
1256 1257 1258
			*pfd = bpf_create_map_xattr(&create_attr);
		}

1259 1260 1261
		if (*pfd < 0) {
			size_t j;

1262
			err = *pfd;
1263
			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
E
Eric Leblond 已提交
1264
			pr_warning("failed to create map (name: '%s'): %s\n",
1265
				   map->name, cp);
1266
			for (j = 0; j < i; j++)
1267
				zclose(obj->maps[j].fd);
1268 1269
			return err;
		}
1270
		pr_debug("create map %s: fd=%d\n", map->name, *pfd);
1271 1272 1273 1274 1275
	}

	return 0;
}

1276 1277 1278 1279 1280 1281 1282
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;
1283
	int err;
1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300

	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;
1301
		new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn));
1302 1303 1304 1305
		if (!new_insn) {
			pr_warning("oom in prog realloc\n");
			return -ENOMEM;
		}
1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319

		if (obj->btf && obj->btf_ext) {
			err = btf_ext__reloc(obj->btf, obj->btf_ext,
					     text->section_name,
					     prog->insns_cnt,
					     &prog->func_info,
					     &prog->func_info_len);
			if (err) {
				pr_warning("error in btf_ext__reloc for sec %s\n",
					   text->section_name);
				return err;
			}
		}

1320 1321 1322 1323 1324
		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;
1325 1326 1327
		pr_debug("added %zd insn from %s to prog %s\n",
			 text->insns_cnt, text->section_name,
			 prog->section_name);
1328 1329 1330 1331 1332 1333
	}
	insn = &prog->insns[relo->insn_idx];
	insn->imm += prog->main_prog_cnt - relo->insn_idx;
	return 0;
}

W
Wang Nan 已提交
1334
static int
1335
bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
W
Wang Nan 已提交
1336
{
1337
	int i, err;
W
Wang Nan 已提交
1338

1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356
	if (!prog)
		return 0;

	if (obj->btf && obj->btf_ext) {
		err = btf_ext__reloc_init(obj->btf, obj->btf_ext,
					  prog->section_name,
					  &prog->func_info,
					  &prog->func_info_rec_size,
					  &prog->func_info_len);
		if (err) {
			pr_warning("err in btf_ext__reloc_init for sec %s\n",
				   prog->section_name);
			return err;
		}
		prog->btf_fd = btf__fd(obj->btf);
	}

	if (!prog->reloc_desc)
W
Wang Nan 已提交
1357 1358 1359
		return 0;

	for (i = 0; i < prog->nr_reloc; i++) {
1360 1361 1362
		if (prog->reloc_desc[i].type == RELO_LD64) {
			struct bpf_insn *insns = prog->insns;
			int insn_idx, map_idx;
W
Wang Nan 已提交
1363

1364 1365
			insn_idx = prog->reloc_desc[i].insn_idx;
			map_idx = prog->reloc_desc[i].map_idx;
W
Wang Nan 已提交
1366

1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378
			if (insn_idx >= (int)prog->insns_cnt) {
				pr_warning("relocation out of range: '%s'\n",
					   prog->section_name);
				return -LIBBPF_ERRNO__RELOC;
			}
			insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
			insns[insn_idx].imm = obj->maps[map_idx].fd;
		} else {
			err = bpf_program__reloc_text(prog, obj,
						      &prog->reloc_desc[i]);
			if (err)
				return err;
W
Wang Nan 已提交
1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397
		}
	}

	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];

1398
		err = bpf_program__relocate(prog, obj);
W
Wang Nan 已提交
1399 1400 1401 1402 1403 1404 1405 1406 1407
		if (err) {
			pr_warning("failed to relocate '%s'\n",
				   prog->section_name);
			return err;
		}
	}
	return 0;
}

1408 1409 1410 1411 1412 1413
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");
1414
		return -LIBBPF_ERRNO__INTERNAL;
1415 1416 1417 1418 1419 1420 1421 1422 1423 1424
	}

	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__);
1425
			return -LIBBPF_ERRNO__INTERNAL;
1426 1427 1428 1429
		}

		prog = bpf_object__find_prog_by_idx(obj, idx);
		if (!prog) {
1430
			pr_warning("relocation failed: no section(%d)\n", idx);
1431
			return -LIBBPF_ERRNO__RELOC;
1432 1433
		}

1434
		err = bpf_program__collect_reloc(prog,
1435
						 shdr, data,
1436
						 obj);
1437
		if (err)
1438
			return err;
1439 1440 1441 1442
	}
	return 0;
}

1443
static int
1444 1445 1446
load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
	     char *license, __u32 kern_version, int *pfd,
	     __u32 func_info_cnt)
1447
{
1448
	struct bpf_load_program_attr load_attr;
1449
	char *cp, errmsg[STRERR_BUFSIZE];
1450
	char *log_buf;
1451
	int ret;
1452

1453
	memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
1454 1455
	load_attr.prog_type = prog->type;
	load_attr.expected_attach_type = prog->expected_attach_type;
1456 1457
	if (prog->caps->name)
		load_attr.name = prog->name;
1458 1459 1460 1461
	load_attr.insns = insns;
	load_attr.insns_cnt = insns_cnt;
	load_attr.license = license;
	load_attr.kern_version = kern_version;
1462
	load_attr.prog_ifindex = prog->prog_ifindex;
Y
Yonghong Song 已提交
1463
	load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0;
1464 1465 1466
	load_attr.func_info = prog->func_info;
	load_attr.func_info_rec_size = prog->func_info_rec_size;
	load_attr.func_info_cnt = func_info_cnt;
1467 1468

	if (!load_attr.insns || !load_attr.insns_cnt)
1469 1470 1471 1472 1473 1474
		return -EINVAL;

	log_buf = malloc(BPF_LOG_BUF_SIZE);
	if (!log_buf)
		pr_warning("Alloc log buffer for bpf loader error, continue without log\n");

1475
	ret = bpf_load_program_xattr(&load_attr, log_buf, BPF_LOG_BUF_SIZE);
1476 1477 1478 1479 1480 1481 1482

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

1483
	ret = -LIBBPF_ERRNO__LOAD;
1484
	cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1485
	pr_warning("load bpf program failed: %s\n", cp);
1486

1487 1488
	if (log_buf && log_buf[0] != '\0') {
		ret = -LIBBPF_ERRNO__VERIFY;
1489 1490 1491
		pr_warning("-- BEGIN DUMP LOG ---\n");
		pr_warning("\n%s\n", log_buf);
		pr_warning("-- END LOG --\n");
1492 1493 1494
	} 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);
1495
		ret = -LIBBPF_ERRNO__PROG2BIG;
1496
	} else {
1497
		/* Wrong program type? */
1498
		if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) {
1499 1500
			int fd;

1501 1502 1503
			load_attr.prog_type = BPF_PROG_TYPE_KPROBE;
			load_attr.expected_attach_type = 0;
			fd = bpf_load_program_xattr(&load_attr, NULL, 0);
1504 1505 1506 1507 1508
			if (fd >= 0) {
				close(fd);
				ret = -LIBBPF_ERRNO__PROGTYPE;
				goto out;
			}
1509
		}
1510 1511 1512

		if (log_buf)
			ret = -LIBBPF_ERRNO__KVER;
1513 1514 1515 1516 1517 1518 1519
	}

out:
	free(log_buf);
	return ret;
}

1520
int
1521
bpf_program__load(struct bpf_program *prog,
1522
		  char *license, __u32 kern_version)
1523
{
1524
	__u32 func_info_cnt;
1525
	int err = 0, fd, i;
1526

1527 1528 1529 1530 1531
	if (prog->func_info_len == 0)
		func_info_cnt = 0;
	else
		func_info_cnt = prog->func_info_len / prog->func_info_rec_size;

1532 1533 1534 1535 1536 1537
	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;
		}
1538

1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552
		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);
		}
1553
		err = load_program(prog, prog->insns, prog->insns_cnt,
1554
				   license, kern_version, &fd,
1555
				   func_info_cnt);
1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582
		if (!err)
			prog->instances.fds[0] = fd;
		goto out;
	}

	for (i = 0; i < prog->instances.nr; i++) {
		struct bpf_prog_prep_result result;
		bpf_program_prep_t preprocessor = prog->preprocessor;

		bzero(&result, sizeof(result));
		err = preprocessor(prog, i, prog->insns,
				   prog->insns_cnt, &result);
		if (err) {
			pr_warning("Preprocessing the %dth instance of program '%s' failed\n",
				   i, prog->section_name);
			goto out;
		}

		if (!result.new_insn_ptr || !result.new_insn_cnt) {
			pr_debug("Skip loading the %dth instance of program '%s'\n",
				 i, prog->section_name);
			prog->instances.fds[i] = -1;
			if (result.pfd)
				*result.pfd = -1;
			continue;
		}

1583
		err = load_program(prog, result.new_insn_ptr,
1584
				   result.new_insn_cnt,
1585
				   license, kern_version, &fd,
1586
				   func_info_cnt);
1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598

		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:
1599 1600 1601 1602 1603 1604 1605 1606
	if (err)
		pr_warning("failed to load program '%s'\n",
			   prog->section_name);
	zfree(&prog->insns);
	prog->insns_cnt = 0;
	return err;
}

1607 1608 1609 1610 1611 1612
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;
}

1613 1614 1615 1616 1617 1618 1619
static int
bpf_object__load_progs(struct bpf_object *obj)
{
	size_t i;
	int err;

	for (i = 0; i < obj->nr_programs; i++) {
1620
		if (bpf_program__is_function_storage(&obj->programs[i], obj))
1621
			continue;
1622 1623 1624 1625 1626 1627 1628 1629 1630
		err = bpf_program__load(&obj->programs[i],
					obj->license,
					obj->kern_version);
		if (err)
			return err;
	}
	return 0;
}

1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642
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:
1643
	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
1644 1645 1646 1647 1648
	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:
1649
	case BPF_PROG_TYPE_LIRC_MODE2:
1650
	case BPF_PROG_TYPE_SK_REUSEPORT:
1651
	case BPF_PROG_TYPE_FLOW_DISSECTOR:
1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663
		return false;
	case BPF_PROG_TYPE_UNSPEC:
	case BPF_PROG_TYPE_KPROBE:
	case BPF_PROG_TYPE_TRACEPOINT:
	case BPF_PROG_TYPE_PERF_EVENT:
	case BPF_PROG_TYPE_RAW_TRACEPOINT:
	default:
		return true;
	}
}

static int bpf_object__validate(struct bpf_object *obj, bool needs_kver)
1664
{
1665
	if (needs_kver && obj->kern_version == 0) {
1666 1667
		pr_warning("%s doesn't provide kernel version\n",
			   obj->path);
1668
		return -LIBBPF_ERRNO__KVERSION;
1669 1670 1671 1672
	}
	return 0;
}

1673
static struct bpf_object *
1674
__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
1675
		   bool needs_kver, int flags)
1676 1677
{
	struct bpf_object *obj;
1678
	int err;
1679 1680 1681

	if (elf_version(EV_CURRENT) == EV_NONE) {
		pr_warning("failed to init libelf for %s\n", path);
1682
		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
1683 1684
	}

1685
	obj = bpf_object__new(path, obj_buf, obj_buf_sz);
1686 1687
	if (IS_ERR(obj))
		return obj;
1688

1689 1690
	CHECK_ERR(bpf_object__elf_init(obj), err, out);
	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
1691
	CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out);
1692
	CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
1693
	CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out);
1694 1695 1696 1697 1698

	bpf_object__elf_finish(obj);
	return obj;
out:
	bpf_object__close(obj);
1699
	return ERR_PTR(err);
1700 1701
}

1702 1703
struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
					    int flags)
1704 1705
{
	/* param validation */
1706
	if (!attr->file)
1707 1708
		return NULL;

1709 1710 1711
	pr_debug("loading %s\n", attr->file);

	return __bpf_object__open(attr->file, NULL, 0,
1712 1713 1714 1715 1716 1717 1718
				  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);
1719 1720 1721 1722 1723 1724 1725 1726
}

struct bpf_object *bpf_object__open(const char *path)
{
	struct bpf_object_open_attr attr = {
		.file		= path,
		.prog_type	= BPF_PROG_TYPE_UNSPEC,
	};
1727

1728
	return bpf_object__open_xattr(&attr);
1729 1730 1731
}

struct bpf_object *bpf_object__open_buffer(void *obj_buf,
1732 1733
					   size_t obj_buf_sz,
					   const char *name)
1734
{
1735 1736
	char tmp_name[64];

1737 1738 1739 1740
	/* param validation */
	if (!obj_buf || obj_buf_sz <= 0)
		return NULL;

1741 1742 1743 1744 1745 1746 1747 1748 1749
	if (!name) {
		snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx",
			 (unsigned long)obj_buf,
			 (unsigned long)obj_buf_sz);
		tmp_name[sizeof(tmp_name) - 1] = '\0';
		name = tmp_name;
	}
	pr_debug("loading object '%s' from buffer\n",
		 name);
1750

1751
	return __bpf_object__open(name, obj_buf, obj_buf_sz, true, true);
1752 1753
}

1754 1755 1756 1757 1758 1759 1760
int bpf_object__unload(struct bpf_object *obj)
{
	size_t i;

	if (!obj)
		return -EINVAL;

1761 1762
	for (i = 0; i < obj->nr_maps; i++)
		zclose(obj->maps[i].fd);
1763

1764 1765 1766
	for (i = 0; i < obj->nr_programs; i++)
		bpf_program__unload(&obj->programs[i]);

1767 1768 1769 1770 1771
	return 0;
}

int bpf_object__load(struct bpf_object *obj)
{
1772 1773
	int err;

1774 1775 1776 1777 1778 1779 1780 1781 1782
	if (!obj)
		return -EINVAL;

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

	obj->loaded = true;
1783

1784
	CHECK_ERR(bpf_object__probe_caps(obj), err, out);
1785 1786 1787
	CHECK_ERR(bpf_object__create_maps(obj), err, out);
	CHECK_ERR(bpf_object__relocate(obj), err, out);
	CHECK_ERR(bpf_object__load_progs(obj), err, out);
1788 1789 1790 1791 1792

	return 0;
out:
	bpf_object__unload(obj);
	pr_warning("failed to load object '%s'\n", obj->path);
1793
	return err;
1794 1795
}

1796 1797
static int check_path(const char *path)
{
1798
	char *cp, errmsg[STRERR_BUFSIZE];
1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811
	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)) {
1812
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1813
		pr_warning("failed to statfs %s: %s\n", dir, cp);
1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828
		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)
{
1829
	char *cp, errmsg[STRERR_BUFSIZE];
1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847
	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)) {
1848
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
1849
		pr_warning("failed to pin program: %s\n", cp);
1850 1851 1852 1853 1854 1855 1856
		return -errno;
	}
	pr_debug("pinned program '%s'\n", path);

	return 0;
}

1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884
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;
}

1885 1886
static int make_dir(const char *path)
{
1887
	char *cp, errmsg[STRERR_BUFSIZE];
1888 1889 1890 1891 1892
	int err = 0;

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

1893
	if (err) {
1894
		cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
1895 1896
		pr_warning("failed to mkdir %s: %s\n", path, cp);
	}
1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918
	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;
	}

1919 1920 1921 1922 1923
	if (prog->instances.nr == 1) {
		/* don't create subdirs when pinning single instance */
		return bpf_program__pin_instance(prog, path, 0);
	}

1924 1925 1926 1927
	err = make_dir(path);
	if (err)
		return err;

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 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983
	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;
1984 1985 1986 1987 1988
	}

	if (prog->instances.nr == 1) {
		/* don't create subdirs when pinning single instance */
		return bpf_program__unpin_instance(prog, path, 0);
1989 1990
	}

1991 1992 1993 1994 1995 1996 1997 1998 1999 2000
	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;

2001
		err = bpf_program__unpin_instance(prog, buf, i);
2002 2003 2004 2005
		if (err)
			return err;
	}

2006 2007 2008 2009
	err = rmdir(path);
	if (err)
		return -errno;

2010 2011 2012
	return 0;
}

J
Joe Stringer 已提交
2013 2014
int bpf_map__pin(struct bpf_map *map, const char *path)
{
2015
	char *cp, errmsg[STRERR_BUFSIZE];
J
Joe Stringer 已提交
2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027
	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)) {
2028
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
2029
		pr_warning("failed to pin map: %s\n", cp);
J
Joe Stringer 已提交
2030 2031 2032 2033
		return -errno;
	}

	pr_debug("pinned map '%s'\n", path);
2034

J
Joe Stringer 已提交
2035 2036 2037
	return 0;
}

2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059
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)
2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075
{
	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;

2076 2077 2078 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 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122
	bpf_map__for_each(map, obj) {
		char buf[PATH_MAX];
		int len;

		len = snprintf(buf, PATH_MAX, "%s/%s", path,
			       bpf_map__name(map));
		if (len < 0) {
			err = -EINVAL;
			goto err_unpin_maps;
		} else if (len >= PATH_MAX) {
			err = -ENAMETOOLONG;
			goto err_unpin_maps;
		}

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

	return 0;

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

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

		bpf_map__unpin(map, buf);
	}

	return err;
}

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

	if (!obj)
		return -ENOENT;

2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133
	bpf_map__for_each(map, obj) {
		char buf[PATH_MAX];
		int len;

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

2134
		err = bpf_map__unpin(map, buf);
2135 2136 2137 2138
		if (err)
			return err;
	}

2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163
	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
2164
			       prog->pin_name);
2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185
		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
2186
			       prog->pin_name);
2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205
		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;

2206 2207 2208 2209 2210
	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
2211
			       prog->pin_name);
2212 2213 2214 2215 2216
		if (len < 0)
			return -EINVAL;
		else if (len >= PATH_MAX)
			return -ENAMETOOLONG;

2217
		err = bpf_program__unpin(prog, buf);
2218 2219 2220 2221 2222 2223 2224
		if (err)
			return err;
	}

	return 0;
}

2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241
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;
}

2242 2243
void bpf_object__close(struct bpf_object *obj)
{
2244 2245
	size_t i;

2246 2247 2248
	if (!obj)
		return;

2249 2250 2251
	if (obj->clear_priv)
		obj->clear_priv(obj, obj->priv);

2252
	bpf_object__elf_finish(obj);
2253
	bpf_object__unload(obj);
2254
	btf__free(obj->btf);
2255
	btf_ext__free(obj->btf_ext);
2256

2257
	for (i = 0; i < obj->nr_maps; i++) {
2258
		zfree(&obj->maps[i].name);
2259 2260 2261 2262 2263 2264 2265 2266
		if (obj->maps[i].clear_priv)
			obj->maps[i].clear_priv(&obj->maps[i],
						obj->maps[i].priv);
		obj->maps[i].priv = NULL;
		obj->maps[i].clear_priv = NULL;
	}
	zfree(&obj->maps);
	obj->nr_maps = 0;
2267 2268 2269 2270 2271 2272 2273

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

2274
	list_del(&obj->list);
2275 2276
	free(obj);
}
2277

2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296
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;
}

2297
const char *bpf_object__name(struct bpf_object *obj)
2298
{
2299
	return obj ? obj->path : ERR_PTR(-EINVAL);
2300 2301
}

2302
unsigned int bpf_object__kversion(struct bpf_object *obj)
2303
{
2304
	return obj ? obj->kern_version : 0;
2305 2306
}

2307 2308 2309 2310 2311
int bpf_object__btf_fd(const struct bpf_object *obj)
{
	return obj->btf ? btf__fd(obj->btf) : -1;
}

2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327
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);
}

2328
static struct bpf_program *
2329
__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward)
2330
{
2331
	size_t nr_programs = obj->nr_programs;
2332
	ssize_t idx;
2333

2334
	if (!nr_programs)
2335 2336
		return NULL;

2337 2338 2339 2340 2341
	if (!p)
		/* Iter from the beginning */
		return forward ? &obj->programs[0] :
			&obj->programs[nr_programs - 1];

2342
	if (p->obj != obj) {
2343 2344 2345 2346
		pr_warning("error: program handler doesn't match object\n");
		return NULL;
	}

2347
	idx = (p - obj->programs) + (forward ? 1 : -1);
2348
	if (idx >= obj->nr_programs || idx < 0)
2349 2350 2351 2352
		return NULL;
	return &obj->programs[idx];
}

2353 2354 2355 2356 2357 2358
struct bpf_program *
bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
{
	struct bpf_program *prog = prev;

	do {
2359
		prog = __bpf_program__iter(prog, obj, true);
2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370
	} 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 {
2371
		prog = __bpf_program__iter(prog, obj, false);
2372 2373 2374 2375 2376
	} while (prog && bpf_program__is_function_storage(prog, obj));

	return prog;
}

2377 2378
int bpf_program__set_priv(struct bpf_program *prog, void *priv,
			  bpf_program_clear_priv_t clear_priv)
2379 2380 2381 2382 2383 2384 2385 2386 2387
{
	if (prog->priv && prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

2388
void *bpf_program__priv(struct bpf_program *prog)
2389
{
2390
	return prog ? prog->priv : ERR_PTR(-EINVAL);
2391 2392
}

2393 2394 2395 2396 2397
void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex)
{
	prog->prog_ifindex = ifindex;
}

2398
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
2399 2400 2401 2402
{
	const char *title;

	title = prog->section_name;
2403
	if (needs_copy) {
2404 2405 2406
		title = strdup(title);
		if (!title) {
			pr_warning("failed to strdup program title\n");
2407
			return ERR_PTR(-ENOMEM);
2408 2409 2410 2411 2412 2413 2414 2415
		}
	}

	return title;
}

int bpf_program__fd(struct bpf_program *prog)
{
2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450
	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;

2451 2452 2453
	if (!prog)
		return -EINVAL;

2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467
	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;
2468
}
2469

2470
void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
2471 2472 2473 2474 2475 2476 2477 2478 2479 2480
{
	prog->type = type;
}

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

2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494
#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);	\
}							\

2495
BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
2496
BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
2497 2498
BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
2499
BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
2500
BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT);
2501 2502
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
2503

J
John Fastabend 已提交
2504 2505
void bpf_program__set_expected_attach_type(struct bpf_program *prog,
					   enum bpf_attach_type type)
2506 2507 2508 2509
{
	prog->expected_attach_type = type;
}

2510 2511
#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, atype) \
	{ string, sizeof(string) - 1, ptype, eatype, is_attachable, atype }
2512

2513
/* Programs that can NOT be attached. */
2514
#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0)
2515

2516 2517
/* Programs that can be attached. */
#define BPF_APROG_SEC(string, ptype, atype) \
2518
	BPF_PROG_SEC_IMPL(string, ptype, 0, 1, atype)
2519

2520 2521
/* Programs that must specify expected attach type at load time. */
#define BPF_EAPROG_SEC(string, ptype, eatype) \
2522
	BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, eatype)
2523 2524 2525 2526 2527

/* 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)
2528

2529 2530 2531 2532
static const struct {
	const char *sec;
	size_t len;
	enum bpf_prog_type prog_type;
2533
	enum bpf_attach_type expected_attach_type;
2534
	int is_attachable;
2535
	enum bpf_attach_type attach_type;
2536
} section_names[] = {
2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549
	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),
2550 2551 2552 2553
	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),
2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564
	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),
2565 2566 2567 2568
	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),
2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587
	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),
2588
};
2589

2590
#undef BPF_PROG_SEC_IMPL
2591
#undef BPF_PROG_SEC
2592 2593 2594
#undef BPF_APROG_SEC
#undef BPF_EAPROG_SEC
#undef BPF_APROG_COMPAT
2595

2596 2597
int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
			     enum bpf_attach_type *expected_attach_type)
2598 2599 2600
{
	int i;

2601 2602
	if (!name)
		return -EINVAL;
2603

2604 2605 2606 2607 2608 2609 2610 2611 2612
	for (i = 0; i < ARRAY_SIZE(section_names); i++) {
		if (strncmp(name, section_names[i].sec, section_names[i].len))
			continue;
		*prog_type = section_names[i].prog_type;
		*expected_attach_type = section_names[i].expected_attach_type;
		return 0;
	}
	return -EINVAL;
}
2613

2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624
int libbpf_attach_type_by_name(const char *name,
			       enum bpf_attach_type *attach_type)
{
	int i;

	if (!name)
		return -EINVAL;

	for (i = 0; i < ARRAY_SIZE(section_names); i++) {
		if (strncmp(name, section_names[i].sec, section_names[i].len))
			continue;
2625
		if (!section_names[i].is_attachable)
2626 2627 2628 2629 2630 2631 2632
			return -EINVAL;
		*attach_type = section_names[i].attach_type;
		return 0;
	}
	return -EINVAL;
}

2633 2634 2635 2636 2637 2638 2639
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);
2640 2641
}

2642
int bpf_map__fd(struct bpf_map *map)
2643
{
2644
	return map ? map->fd : -EINVAL;
2645 2646
}

2647
const struct bpf_map_def *bpf_map__def(struct bpf_map *map)
2648
{
2649
	return map ? &map->def : ERR_PTR(-EINVAL);
2650 2651
}

2652
const char *bpf_map__name(struct bpf_map *map)
2653
{
2654
	return map ? map->name : NULL;
2655 2656
}

2657
__u32 bpf_map__btf_key_type_id(const struct bpf_map *map)
2658
{
2659
	return map ? map->btf_key_type_id : 0;
2660 2661
}

2662
__u32 bpf_map__btf_value_type_id(const struct bpf_map *map)
2663
{
2664
	return map ? map->btf_value_type_id : 0;
2665 2666
}

2667 2668
int bpf_map__set_priv(struct bpf_map *map, void *priv,
		     bpf_map_clear_priv_t clear_priv)
2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682
{
	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;
}

2683
void *bpf_map__priv(struct bpf_map *map)
2684
{
2685
	return map ? map->priv : ERR_PTR(-EINVAL);
2686 2687
}

2688 2689 2690 2691 2692
bool bpf_map__is_offload_neutral(struct bpf_map *map)
{
	return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
}

2693 2694 2695 2696 2697
void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
{
	map->map_ifindex = ifindex;
}

2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711
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;
}

2712 2713
static struct bpf_map *
__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i)
2714
{
2715
	ssize_t idx;
2716 2717 2718 2719 2720 2721 2722 2723
	struct bpf_map *s, *e;

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

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

2724
	if ((m < s) || (m >= e)) {
2725 2726 2727 2728 2729
		pr_warning("error in %s: map handler doesn't belong to object\n",
			   __func__);
		return NULL;
	}

2730 2731
	idx = (m - obj->maps) + i;
	if (idx >= obj->nr_maps || idx < 0)
2732 2733 2734
		return NULL;
	return &obj->maps[idx];
}
2735

2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756
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);
}

2757
struct bpf_map *
2758
bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
2759 2760 2761 2762
{
	struct bpf_map *pos;

	bpf_map__for_each(pos, obj) {
2763
		if (pos->name && !strcmp(pos->name, name))
2764 2765 2766 2767
			return pos;
	}
	return NULL;
}
2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779

struct bpf_map *
bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset)
{
	int i;

	for (i = 0; i < obj->nr_maps; i++) {
		if (obj->maps[i].offset == offset)
			return &obj->maps[i];
	}
	return ERR_PTR(-ENOENT);
}
2780 2781 2782 2783 2784 2785 2786

long libbpf_get_error(const void *ptr)
{
	if (IS_ERR(ptr))
		return PTR_ERR(ptr);
	return 0;
}
2787 2788 2789

int bpf_prog_load(const char *file, enum bpf_prog_type type,
		  struct bpf_object **pobj, int *prog_fd)
2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802
{
	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)
2803
{
2804 2805 2806 2807
	struct bpf_object_open_attr open_attr = {
		.file		= attr->file,
		.prog_type	= attr->prog_type,
	};
2808
	struct bpf_program *prog, *first_prog = NULL;
2809 2810
	enum bpf_attach_type expected_attach_type;
	enum bpf_prog_type prog_type;
2811
	struct bpf_object *obj;
2812
	struct bpf_map *map;
2813 2814
	int err;

2815 2816
	if (!attr)
		return -EINVAL;
2817 2818
	if (!attr->file)
		return -EINVAL;
2819

2820
	obj = bpf_object__open_xattr(&open_attr);
2821
	if (IS_ERR_OR_NULL(obj))
2822 2823
		return -ENOENT;

2824 2825 2826 2827 2828
	bpf_object__for_each_program(prog, obj) {
		/*
		 * If type is not specified, try to guess it based on
		 * section name.
		 */
2829
		prog_type = attr->prog_type;
2830
		prog->prog_ifindex = attr->ifindex;
2831 2832
		expected_attach_type = attr->expected_attach_type;
		if (prog_type == BPF_PROG_TYPE_UNSPEC) {
2833 2834 2835 2836 2837
			err = bpf_program__identify_section(prog, &prog_type,
							    &expected_attach_type);
			if (err < 0) {
				pr_warning("failed to guess program type based on section name %s\n",
					   prog->section_name);
2838 2839 2840
				bpf_object__close(obj);
				return -EINVAL;
			}
2841
		}
2842

2843 2844 2845 2846
		bpf_program__set_type(prog, prog_type);
		bpf_program__set_expected_attach_type(prog,
						      expected_attach_type);

2847
		if (!first_prog)
2848 2849 2850
			first_prog = prog;
	}

2851
	bpf_map__for_each(map, obj) {
2852 2853
		if (!bpf_map__is_offload_neutral(map))
			map->map_ifindex = attr->ifindex;
2854 2855
	}

2856 2857 2858 2859
	if (!first_prog) {
		pr_warning("object file doesn't contain bpf program\n");
		bpf_object__close(obj);
		return -ENOENT;
2860 2861
	}

2862 2863 2864 2865 2866 2867 2868
	err = bpf_object__load(obj);
	if (err) {
		bpf_object__close(obj);
		return -EINVAL;
	}

	*pobj = obj;
2869
	*prog_fd = bpf_program__fd(first_prog);
2870 2871
	return 0;
}
2872 2873

enum bpf_perf_event_ret
2874 2875 2876
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)
2877
{
2878
	struct perf_event_mmap_page *header = mmap_mem;
2879
	__u64 data_head = ring_buffer_read_head(header);
2880
	__u64 data_tail = header->data_tail;
2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899
	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;
2900 2901 2902
					ret = LIBBPF_PERF_EVENT_ERROR;
					break;
				}
2903
				*copy_size = ehdr_size;
2904 2905
			}

2906 2907 2908
			memcpy(*copy_mem, copy_start, len_first);
			memcpy(*copy_mem + len_first, base, len_secnd);
			ehdr = *copy_mem;
2909 2910
		}

2911 2912
		ret = fn(ehdr, private_data);
		data_tail += ehdr_size;
2913 2914 2915 2916
		if (ret != LIBBPF_PERF_EVENT_CONT)
			break;
	}

2917
	ring_buffer_write_tail(header, data_tail);
2918 2919
	return ret;
}