libbpf.c 43.8 KB
Newer Older
1 2 3 4 5 6
/*
 * 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.
7
 * Copyright (C) 2017 Nicira, Inc.
W
Wang Nan 已提交
8 9 10 11 12 13 14 15 16 17 18 19 20
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation;
 * version 2.1 of the License (not later!)
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this program; if not,  see <http://www.gnu.org/licenses>
21 22 23
 */

#include <stdlib.h>
24 25
#include <stdio.h>
#include <stdarg.h>
26
#include <libgen.h>
27
#include <inttypes.h>
28
#include <string.h>
29
#include <unistd.h>
30 31
#include <fcntl.h>
#include <errno.h>
32
#include <asm/unistd.h>
33
#include <linux/err.h>
34
#include <linux/kernel.h>
35
#include <linux/bpf.h>
36
#include <linux/list.h>
37 38 39 40
#include <linux/limits.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/vfs.h>
41 42
#include <libelf.h>
#include <gelf.h>
43 44

#include "libbpf.h"
45
#include "bpf.h"
46

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

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

55 56 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 88 89 90
#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;
}
91

92 93 94 95 96 97 98 99 100 101
#define STRERR_BUFSIZE  128

#define ERRNO_OFFSET(e)		((e) - __LIBBPF_ERRNO__START)
#define ERRCODE_OFFSET(c)	ERRNO_OFFSET(LIBBPF_ERRNO__##c)
#define NR_ERRNO	(__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)

static const char *libbpf_strerror_table[NR_ERRNO] = {
	[ERRCODE_OFFSET(LIBELF)]	= "Something wrong in libelf",
	[ERRCODE_OFFSET(FORMAT)]	= "BPF object format invalid",
	[ERRCODE_OFFSET(KVERSION)]	= "'version' section incorrect or lost",
102
	[ERRCODE_OFFSET(ENDIAN)]	= "Endian mismatch",
103 104 105 106 107
	[ERRCODE_OFFSET(INTERNAL)]	= "Internal error in libbpf",
	[ERRCODE_OFFSET(RELOC)]		= "Relocation failed",
	[ERRCODE_OFFSET(VERIFY)]	= "Kernel verifier blocks program loading",
	[ERRCODE_OFFSET(PROG2BIG)]	= "Program too big",
	[ERRCODE_OFFSET(KVER)]		= "Incorrect kernel version",
108
	[ERRCODE_OFFSET(PROGTYPE)]	= "Kernel doesn't support this program type",
109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146
};

int libbpf_strerror(int err, char *buf, size_t size)
{
	if (!buf || !size)
		return -1;

	err = err > 0 ? err : -err;

	if (err < __LIBBPF_ERRNO__START) {
		int ret;

		ret = strerror_r(err, buf, size);
		buf[size - 1] = '\0';
		return ret;
	}

	if (err < __LIBBPF_ERRNO__END) {
		const char *msg;

		msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
		snprintf(buf, size, "%s", msg);
		buf[size - 1] = '\0';
		return 0;
	}

	snprintf(buf, size, "Unknown libbpf error %d", err);
	buf[size - 1] = '\0';
	return -1;
}

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


147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166
/* 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

167 168 169 170 171 172 173
/*
 * 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;
174
	char *name;
175 176
	char *section_name;
	struct bpf_insn *insns;
177
	size_t insns_cnt, main_prog_cnt;
178
	enum bpf_prog_type type;
179

180 181 182 183 184
	struct reloc_desc {
		enum {
			RELO_LD64,
			RELO_CALL,
		} type;
185
		int insn_idx;
186 187 188 189
		union {
			int map_idx;
			int text_off;
		};
190 191
	} *reloc_desc;
	int nr_reloc;
192

193 194 195 196 197
	struct {
		int nr;
		int *fds;
	} instances;
	bpf_program_prep_t preprocessor;
198 199 200 201

	struct bpf_object *obj;
	void *priv;
	bpf_program_clear_priv_t clear_priv;
202 203
};

204 205
struct bpf_map {
	int fd;
206
	char *name;
E
Eric Leblond 已提交
207
	size_t offset;
208 209 210 211 212
	struct bpf_map_def def;
	void *priv;
	bpf_map_clear_priv_t clear_priv;
};

213 214
static LIST_HEAD(bpf_objects_list);

215
struct bpf_object {
216 217
	char license[64];
	u32 kern_version;
218

219 220
	struct bpf_program *programs;
	size_t nr_programs;
221 222 223
	struct bpf_map *maps;
	size_t nr_maps;

224
	bool loaded;
225

226 227 228 229 230 231
	/*
	 * Information when doing elf related work. Only valid if fd
	 * is valid.
	 */
	struct {
		int fd;
232 233
		void *obj_buf;
		size_t obj_buf_sz;
234 235
		Elf *elf;
		GElf_Ehdr ehdr;
236
		Elf_Data *symbols;
237
		size_t strtabidx;
238 239 240 241 242
		struct {
			GElf_Shdr shdr;
			Elf_Data *data;
		} *reloc;
		int nr_reloc;
243
		int maps_shndx;
244
		int text_shndx;
245
	} efile;
246 247 248 249 250 251
	/*
	 * 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;
252 253 254 255

	void *priv;
	bpf_object_clear_priv_t clear_priv;

256 257 258 259
	char path[];
};
#define obj_elf_valid(o)	((o)->efile.elf)

260 261
static void bpf_program__unload(struct bpf_program *prog)
{
262 263
	int i;

264 265 266
	if (!prog)
		return;

267 268 269 270 271 272 273 274 275 276 277 278 279 280
	/*
	 * 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);
281 282
}

283 284 285 286 287
static void bpf_program__exit(struct bpf_program *prog)
{
	if (!prog)
		return;

288 289 290 291 292 293
	if (prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

294
	bpf_program__unload(prog);
295
	zfree(&prog->name);
296 297
	zfree(&prog->section_name);
	zfree(&prog->insns);
298 299 300
	zfree(&prog->reloc_desc);

	prog->nr_reloc = 0;
301 302 303 304 305
	prog->insns_cnt = 0;
	prog->idx = -1;
}

static int
306 307
bpf_program__init(void *data, size_t size, char *section_name, int idx,
		  struct bpf_program *prog)
308 309
{
	if (size < sizeof(struct bpf_insn)) {
310
		pr_warning("corrupted section '%s'\n", section_name);
311 312 313 314 315
		return -EINVAL;
	}

	bzero(prog, sizeof(*prog));

316
	prog->section_name = strdup(section_name);
317
	if (!prog->section_name) {
318 319
		pr_warning("failed to alloc name for prog under section %s\n",
			   section_name);
320 321 322 323 324
		goto errout;
	}

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

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

static int
bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
345
			char *section_name, int idx)
346 347 348 349
{
	struct bpf_program prog, *progs;
	int nr_progs, err;

350
	err = bpf_program__init(data, size, section_name, idx, &prog);
351 352 353 354 355 356 357 358 359 360 361 362 363
	if (err)
		return err;

	progs = obj->programs;
	nr_progs = obj->nr_programs;

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

	pr_debug("found program %s\n", prog.section_name);
	obj->programs = progs;
	obj->nr_programs = nr_progs + 1;
373
	prog.obj = obj;
374 375 376 377
	progs[nr_progs] = prog;
	return 0;
}

378 379 380 381 382 383 384 385
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++) {
386
		const char *name = NULL;
387 388

		prog = &obj->programs[pi];
389 390 391 392
		if (prog->idx == obj->efile.text_shndx) {
			name = ".text";
			goto skip_search;
		}
393 394 395 396 397 398 399 400 401

		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;
402 403
			if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL)
				continue;
404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419

			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;
			}
		}

		if (!name) {
			pr_warning("failed to find sym for prog %s\n",
				   prog->section_name);
			return -EINVAL;
		}
420
skip_search:
421 422 423 424 425 426 427 428 429 430 431
		prog->name = strdup(name);
		if (!prog->name) {
			pr_warning("failed to allocate memory for prog sym %s\n",
				   name);
			return -ENOMEM;
		}
	}

	return 0;
}

432 433 434
static struct bpf_object *bpf_object__new(const char *path,
					  void *obj_buf,
					  size_t obj_buf_sz)
435 436 437 438 439 440
{
	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);
441
		return ERR_PTR(-ENOMEM);
442 443 444 445
	}

	strcpy(obj->path, path);
	obj->efile.fd = -1;
446 447 448 449 450 451 452 453 454

	/*
	 * 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;
455
	obj->efile.maps_shndx = -1;
456

457
	obj->loaded = false;
458 459 460

	INIT_LIST_HEAD(&obj->list);
	list_add(&obj->list, &bpf_objects_list);
461 462 463 464 465 466 467 468 469 470 471 472
	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;
	}
473
	obj->efile.symbols = NULL;
474 475 476

	zfree(&obj->efile.reloc);
	obj->efile.nr_reloc = 0;
477
	zclose(obj->efile.fd);
478 479
	obj->efile.obj_buf = NULL;
	obj->efile.obj_buf_sz = 0;
480 481 482 483 484 485 486 487 488
}

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");
489
		return -LIBBPF_ERRNO__LIBELF;
490 491
	}

492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509
	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) {
			pr_warning("failed to open %s: %s\n", obj->path,
					strerror(errno));
			return -errno;
		}

		obj->efile.elf = elf_begin(obj->efile.fd,
				LIBBPF_ELF_C_READ_MMAP,
				NULL);
510 511 512 513 514
	}

	if (!obj->efile.elf) {
		pr_warning("failed to open %s as ELF file\n",
				obj->path);
515
		err = -LIBBPF_ERRNO__LIBELF;
516 517 518 519 520 521
		goto errout;
	}

	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
		pr_warning("failed to get EHDR from %s\n",
				obj->path);
522
		err = -LIBBPF_ERRNO__FORMAT;
523 524 525 526
		goto errout;
	}
	ep = &obj->efile.ehdr;

527 528
	/* Old LLVM set e_machine to EM_NONE */
	if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) {
529 530
		pr_warning("%s is not an eBPF object file\n",
			obj->path);
531
		err = -LIBBPF_ERRNO__FORMAT;
532 533 534 535 536 537 538 539 540
		goto errout;
	}

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

541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558
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:
559
		return -LIBBPF_ERRNO__ENDIAN;
560 561 562 563 564 565
	}

	return 0;

mismatch:
	pr_warning("Error: endianness mismatch.\n");
566
	return -LIBBPF_ERRNO__ENDIAN;
567 568
}

569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586
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)
{
	u32 kver;

	if (size != sizeof(kver)) {
		pr_warning("invalid kver section in %s\n", obj->path);
587
		return -LIBBPF_ERRNO__FORMAT;
588 589 590 591 592 593 594 595
	}
	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
596 597 598 599
static int compare_bpf_map(const void *_a, const void *_b)
{
	const struct bpf_map *a = _a;
	const struct bpf_map *b = _b;
600

E
Eric Leblond 已提交
601
	return a->offset - b->offset;
602 603
}

604
static int
E
Eric Leblond 已提交
605
bpf_object__init_maps(struct bpf_object *obj)
606
{
607
	int i, map_idx, map_def_sz, nr_maps = 0;
E
Eric Leblond 已提交
608 609
	Elf_Scn *scn;
	Elf_Data *data;
610 611
	Elf_Data *symbols = obj->efile.symbols;

E
Eric Leblond 已提交
612 613 614 615 616 617 618 619 620 621 622
	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);
623
		return -EINVAL;
E
Eric Leblond 已提交
624
	}
625

E
Eric Leblond 已提交
626 627 628 629 630 631 632
	/*
	 * 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.
	 */
633 634
	for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
		GElf_Sym sym;
E
Eric Leblond 已提交
635 636 637 638 639 640 641 642 643 644 645 646 647 648 649

		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;

650 651 652 653 654 655 656 657 658
	/* 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
659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678
	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;

	/*
	 * 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 = 0; i < nr_maps; i++)
		obj->maps[i].fd = -1;

	/*
	 * 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;
679
		const char *map_name;
E
Eric Leblond 已提交
680
		struct bpf_map_def *def;
681 682 683

		if (!gelf_getsym(symbols, i, &sym))
			continue;
684
		if (sym.st_shndx != obj->efile.maps_shndx)
685 686 687
			continue;

		map_name = elf_strptr(obj->efile.elf,
688
				      obj->efile.strtabidx,
689
				      sym.st_name);
E
Eric Leblond 已提交
690
		obj->maps[map_idx].offset = sym.st_value;
691
		if (sym.st_value + map_def_sz > data->d_size) {
E
Eric Leblond 已提交
692 693 694
			pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
				   obj->path, map_name);
			return -EINVAL;
695
		}
E
Eric Leblond 已提交
696

697
		obj->maps[map_idx].name = strdup(map_name);
698 699 700 701
		if (!obj->maps[map_idx].name) {
			pr_warning("failed to alloc map name\n");
			return -ENOMEM;
		}
E
Eric Leblond 已提交
702
		pr_debug("map %d is \"%s\"\n", map_idx,
703
			 obj->maps[map_idx].name);
E
Eric Leblond 已提交
704
		def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
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
		/*
		 * 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);
					return -EINVAL;
				}
			}
			memcpy(&obj->maps[map_idx].def, def,
			       sizeof(struct bpf_map_def));
		}
E
Eric Leblond 已提交
734
		map_idx++;
735
	}
E
Eric Leblond 已提交
736 737

	qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map);
738
	return 0;
739 740
}

741 742 743 744 745
static int bpf_object__elf_collect(struct bpf_object *obj)
{
	Elf *elf = obj->efile.elf;
	GElf_Ehdr *ep = &obj->efile.ehdr;
	Elf_Scn *scn = NULL;
746
	int idx = 0, err = 0;
747 748 749 750 751

	/* 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);
752
		return -LIBBPF_ERRNO__FORMAT;
753 754 755 756 757 758 759 760 761 762 763
	}

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

		idx++;
		if (gelf_getshdr(scn, &sh) != &sh) {
			pr_warning("failed to get section header from %s\n",
				   obj->path);
764
			err = -LIBBPF_ERRNO__FORMAT;
765 766 767 768 769 770 771
			goto out;
		}

		name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
		if (!name) {
			pr_warning("failed to get section name from %s\n",
				   obj->path);
772
			err = -LIBBPF_ERRNO__FORMAT;
773 774 775 776 777 778 779
			goto out;
		}

		data = elf_getdata(scn, 0);
		if (!data) {
			pr_warning("failed to get section data from %s(%s)\n",
				   name, obj->path);
780
			err = -LIBBPF_ERRNO__FORMAT;
781 782 783 784 785 786
			goto out;
		}
		pr_debug("section %s, size %ld, link %d, flags %lx, type=%d\n",
			 name, (unsigned long)data->d_size,
			 (int)sh.sh_link, (unsigned long)sh.sh_flags,
			 (int)sh.sh_type);
787 788 789 790 791 792 793 794 795

		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
796
		else if (strcmp(name, "maps") == 0)
797
			obj->efile.maps_shndx = idx;
E
Eric Leblond 已提交
798
		else if (sh.sh_type == SHT_SYMTAB) {
799 800 801
			if (obj->efile.symbols) {
				pr_warning("bpf: multiple SYMTAB in %s\n",
					   obj->path);
802
				err = -LIBBPF_ERRNO__FORMAT;
803
			} else {
804
				obj->efile.symbols = data;
805 806
				obj->efile.strtabidx = sh.sh_link;
			}
807 808 809
		} else if ((sh.sh_type == SHT_PROGBITS) &&
			   (sh.sh_flags & SHF_EXECINSTR) &&
			   (data->d_size > 0)) {
810 811
			if (strcmp(name, ".text") == 0)
				obj->efile.text_shndx = idx;
812 813 814
			err = bpf_object__add_program(obj, data->d_buf,
						      data->d_size, name, idx);
			if (err) {
815 816
				char errmsg[STRERR_BUFSIZE];

817 818 819 820
				strerror_r(-err, errmsg, sizeof(errmsg));
				pr_warning("failed to alloc program %s (%s): %s",
					   name, obj->path, errmsg);
			}
821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838
		} else if (sh.sh_type == SHT_REL) {
			void *reloc = obj->efile.reloc;
			int nr_reloc = obj->efile.nr_reloc + 1;

			reloc = realloc(reloc,
					sizeof(*obj->efile.reloc) * nr_reloc);
			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;
			}
839
		}
840 841
		if (err)
			goto out;
842
	}
843

844 845 846 847
	if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
		pr_warning("Corrupted ELF file: index of strtab invalid\n");
		return LIBBPF_ERRNO__FORMAT;
	}
848
	if (obj->efile.maps_shndx >= 0) {
E
Eric Leblond 已提交
849
		err = bpf_object__init_maps(obj);
850 851 852 853
		if (err)
			goto out;
	}
	err = bpf_object__init_prog_names(obj);
854 855 856 857
out:
	return err;
}

858 859 860 861 862 863 864 865 866 867 868 869 870 871 872
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;
}

static int
873 874
bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
			   Elf_Data *data, struct bpf_object *obj)
875
{
876 877 878 879 880
	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;
881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902
	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);
903
			return -LIBBPF_ERRNO__FORMAT;
904 905 906 907 908 909 910
		}

		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));
911
			return -LIBBPF_ERRNO__FORMAT;
912
		}
D
David Miller 已提交
913 914 915
		pr_debug("relo for %lld value %lld name %d\n",
			 (long long) (rel.r_info >> 32),
			 (long long) sym.st_value, sym.st_name);
916

917
		if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) {
918 919 920 921 922 923 924 925
			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);

926 927 928 929 930 931 932 933 934 935 936
		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;
			continue;
		}

937 938 939
		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);
940
			return -LIBBPF_ERRNO__RELOC;
941 942
		}

943 944 945 946 947 948 949 950 951
		/* 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;
			}
		}

952 953 954
		if (map_idx >= nr_maps) {
			pr_warning("bpf relocation: map_idx %d large than %d\n",
				   (int)map_idx, (int)nr_maps - 1);
955
			return -LIBBPF_ERRNO__RELOC;
956 957
		}

958
		prog->reloc_desc[i].type = RELO_LD64;
959 960 961 962 963 964
		prog->reloc_desc[i].insn_idx = insn_idx;
		prog->reloc_desc[i].map_idx = map_idx;
	}
	return 0;
}

965 966 967 968 969
static int
bpf_object__create_maps(struct bpf_object *obj)
{
	unsigned int i;

970 971 972
	for (i = 0; i < obj->nr_maps; i++) {
		struct bpf_map_def *def = &obj->maps[i].def;
		int *pfd = &obj->maps[i].fd;
973

974 975 976 977 978
		*pfd = bpf_create_map_name(def->type,
					   obj->maps[i].name,
					   def->key_size,
					   def->value_size,
					   def->max_entries,
979
					   def->map_flags);
980 981 982 983
		if (*pfd < 0) {
			size_t j;
			int err = *pfd;

E
Eric Leblond 已提交
984 985
			pr_warning("failed to create map (name: '%s'): %s\n",
				   obj->maps[i].name,
986 987
				   strerror(errno));
			for (j = 0; j < i; j++)
988
				zclose(obj->maps[j].fd);
989 990
			return err;
		}
E
Eric Leblond 已提交
991
		pr_debug("create map %s: fd=%d\n", obj->maps[i].name, *pfd);
992 993 994 995 996
	}

	return 0;
}

997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 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
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;

	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;
		new_insn = realloc(prog->insns, new_cnt * sizeof(*insn));
		if (!new_insn) {
			pr_warning("oom in prog realloc\n");
			return -ENOMEM;
		}
		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;
	}
	insn = &prog->insns[relo->insn_idx];
	insn->imm += prog->main_prog_cnt - relo->insn_idx;
	pr_debug("added %zd insn from %s to prog %s\n",
		 text->insns_cnt, text->section_name, prog->section_name);
	return 0;
}

W
Wang Nan 已提交
1039
static int
1040
bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
W
Wang Nan 已提交
1041
{
1042
	int i, err;
W
Wang Nan 已提交
1043 1044 1045 1046 1047

	if (!prog || !prog->reloc_desc)
		return 0;

	for (i = 0; i < prog->nr_reloc; i++) {
1048 1049 1050
		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
1051

1052 1053
			insn_idx = prog->reloc_desc[i].insn_idx;
			map_idx = prog->reloc_desc[i].map_idx;
W
Wang Nan 已提交
1054

1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066
			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
1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085
		}
	}

	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];

1086
		err = bpf_program__relocate(prog, obj);
W
Wang Nan 已提交
1087 1088 1089 1090 1091 1092 1093 1094 1095
		if (err) {
			pr_warning("failed to relocate '%s'\n",
				   prog->section_name);
			return err;
		}
	}
	return 0;
}

1096 1097 1098 1099 1100 1101
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");
1102
		return -LIBBPF_ERRNO__INTERNAL;
1103 1104 1105 1106 1107 1108 1109 1110 1111 1112
	}

	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__);
1113
			return -LIBBPF_ERRNO__INTERNAL;
1114 1115 1116 1117 1118 1119
		}

		prog = bpf_object__find_prog_by_idx(obj, idx);
		if (!prog) {
			pr_warning("relocation failed: no %d section\n",
				   idx);
1120
			return -LIBBPF_ERRNO__RELOC;
1121 1122
		}

1123
		err = bpf_program__collect_reloc(prog,
1124
						 shdr, data,
1125
						 obj);
1126
		if (err)
1127
			return err;
1128 1129 1130 1131
	}
	return 0;
}

1132
static int
1133
load_program(enum bpf_prog_type type, const char *name, struct bpf_insn *insns,
1134
	     int insns_cnt, char *license, u32 kern_version, int *pfd)
1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145
{
	int ret;
	char *log_buf;

	if (!insns || !insns_cnt)
		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");

1146 1147
	ret = bpf_load_program_name(type, name, insns, insns_cnt, license,
				    kern_version, log_buf, BPF_LOG_BUF_SIZE);
1148 1149 1150 1151 1152 1153 1154

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

1155
	ret = -LIBBPF_ERRNO__LOAD;
1156 1157
	pr_warning("load bpf program failed: %s\n", strerror(errno));

1158 1159
	if (log_buf && log_buf[0] != '\0') {
		ret = -LIBBPF_ERRNO__VERIFY;
1160 1161 1162
		pr_warning("-- BEGIN DUMP LOG ---\n");
		pr_warning("\n%s\n", log_buf);
		pr_warning("-- END LOG --\n");
1163 1164 1165 1166
	} else if (insns_cnt >= BPF_MAXINSNS) {
		pr_warning("Program too large (%d insns), at most %d insns\n",
			   insns_cnt, BPF_MAXINSNS);
		ret = -LIBBPF_ERRNO__PROG2BIG;
1167
	} else {
1168 1169 1170 1171
		/* Wrong program type? */
		if (type != BPF_PROG_TYPE_KPROBE) {
			int fd;

1172 1173 1174
			fd = bpf_load_program_name(BPF_PROG_TYPE_KPROBE, name,
						   insns, insns_cnt, license,
						   kern_version, NULL, 0);
1175 1176 1177 1178 1179
			if (fd >= 0) {
				close(fd);
				ret = -LIBBPF_ERRNO__PROGTYPE;
				goto out;
			}
1180
		}
1181 1182 1183

		if (log_buf)
			ret = -LIBBPF_ERRNO__KVER;
1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194
	}

out:
	free(log_buf);
	return ret;
}

static int
bpf_program__load(struct bpf_program *prog,
		  char *license, u32 kern_version)
{
1195
	int err = 0, fd, i;
1196

1197 1198 1199 1200 1201 1202
	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;
		}
1203

1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217
		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);
		}
1218 1219
		err = load_program(prog->type, prog->name, prog->insns,
				   prog->insns_cnt, license, kern_version, &fd);
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
		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;
		}

1247 1248
		err = load_program(prog->type, prog->name,
				   result.new_insn_ptr,
1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262
				   result.new_insn_cnt,
				   license, kern_version, &fd);

		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:
1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277
	if (err)
		pr_warning("failed to load program '%s'\n",
			   prog->section_name);
	zfree(&prog->insns);
	prog->insns_cnt = 0;
	return err;
}

static int
bpf_object__load_progs(struct bpf_object *obj)
{
	size_t i;
	int err;

	for (i = 0; i < obj->nr_programs; i++) {
1278 1279
		if (obj->programs[i].idx == obj->efile.text_shndx)
			continue;
1280 1281 1282 1283 1284 1285 1286 1287 1288
		err = bpf_program__load(&obj->programs[i],
					obj->license,
					obj->kern_version);
		if (err)
			return err;
	}
	return 0;
}

1289 1290 1291 1292 1293
static int bpf_object__validate(struct bpf_object *obj)
{
	if (obj->kern_version == 0) {
		pr_warning("%s doesn't provide kernel version\n",
			   obj->path);
1294
		return -LIBBPF_ERRNO__KVERSION;
1295 1296 1297 1298
	}
	return 0;
}

1299
static struct bpf_object *
1300
__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz)
1301 1302
{
	struct bpf_object *obj;
1303
	int err;
1304 1305 1306

	if (elf_version(EV_CURRENT) == EV_NONE) {
		pr_warning("failed to init libelf for %s\n", path);
1307
		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
1308 1309
	}

1310
	obj = bpf_object__new(path, obj_buf, obj_buf_sz);
1311 1312
	if (IS_ERR(obj))
		return obj;
1313

1314 1315 1316 1317 1318
	CHECK_ERR(bpf_object__elf_init(obj), err, out);
	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
	CHECK_ERR(bpf_object__elf_collect(obj), err, out);
	CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
	CHECK_ERR(bpf_object__validate(obj), err, out);
1319 1320 1321 1322 1323

	bpf_object__elf_finish(obj);
	return obj;
out:
	bpf_object__close(obj);
1324
	return ERR_PTR(err);
1325 1326 1327 1328 1329 1330 1331 1332 1333 1334
}

struct bpf_object *bpf_object__open(const char *path)
{
	/* param validation */
	if (!path)
		return NULL;

	pr_debug("loading %s\n", path);

1335 1336 1337 1338
	return __bpf_object__open(path, NULL, 0);
}

struct bpf_object *bpf_object__open_buffer(void *obj_buf,
1339 1340
					   size_t obj_buf_sz,
					   const char *name)
1341
{
1342 1343
	char tmp_name[64];

1344 1345 1346 1347
	/* param validation */
	if (!obj_buf || obj_buf_sz <= 0)
		return NULL;

1348 1349 1350 1351 1352 1353 1354 1355 1356
	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);
1357

1358
	return __bpf_object__open(name, obj_buf, obj_buf_sz);
1359 1360
}

1361 1362 1363 1364 1365 1366 1367
int bpf_object__unload(struct bpf_object *obj)
{
	size_t i;

	if (!obj)
		return -EINVAL;

1368 1369
	for (i = 0; i < obj->nr_maps; i++)
		zclose(obj->maps[i].fd);
1370

1371 1372 1373
	for (i = 0; i < obj->nr_programs; i++)
		bpf_program__unload(&obj->programs[i]);

1374 1375 1376 1377 1378
	return 0;
}

int bpf_object__load(struct bpf_object *obj)
{
1379 1380
	int err;

1381 1382 1383 1384 1385 1386 1387 1388 1389
	if (!obj)
		return -EINVAL;

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

	obj->loaded = true;
1390 1391 1392 1393

	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);
1394 1395 1396 1397 1398

	return 0;
out:
	bpf_object__unload(obj);
	pr_warning("failed to load object '%s'\n", obj->path);
1399
	return err;
1400 1401
}

1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 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 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511
static int check_path(const char *path)
{
	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)) {
		pr_warning("failed to statfs %s: %s\n", dir, strerror(errno));
		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)
{
	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)) {
		pr_warning("failed to pin program: %s\n", strerror(errno));
		return -errno;
	}
	pr_debug("pinned program '%s'\n", path);

	return 0;
}

static int make_dir(const char *path)
{
	int err = 0;

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

	if (err)
		pr_warning("failed to mkdir %s: %s\n", path, strerror(-err));
	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;
	}

	err = make_dir(path);
	if (err)
		return err;

	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;

		err = bpf_program__pin_instance(prog, buf, i);
		if (err)
			return err;
	}

	return 0;
}

J
Joe Stringer 已提交
1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533
int bpf_map__pin(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;
	}

	if (bpf_obj_pin(map->fd, path)) {
		pr_warning("failed to pin map: %s\n", strerror(errno));
		return -errno;
	}

	pr_debug("pinned map '%s'\n", path);
	return 0;
}

1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586
int bpf_object__pin(struct bpf_object *obj, const char *path)
{
	struct bpf_program *prog;
	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;

	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;

		err = bpf_map__pin(map, buf);
		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,
			       prog->section_name);
		if (len < 0)
			return -EINVAL;
		else if (len >= PATH_MAX)
			return -ENAMETOOLONG;

		err = bpf_program__pin(prog, buf);
		if (err)
			return err;
	}

	return 0;
}

1587 1588
void bpf_object__close(struct bpf_object *obj)
{
1589 1590
	size_t i;

1591 1592 1593
	if (!obj)
		return;

1594 1595 1596
	if (obj->clear_priv)
		obj->clear_priv(obj, obj->priv);

1597
	bpf_object__elf_finish(obj);
1598
	bpf_object__unload(obj);
1599

1600
	for (i = 0; i < obj->nr_maps; i++) {
1601
		zfree(&obj->maps[i].name);
1602 1603 1604 1605 1606 1607 1608 1609
		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;
1610 1611 1612 1613 1614 1615 1616

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

1617
	list_del(&obj->list);
1618 1619
	free(obj);
}
1620

1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639
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;
}

1640
const char *bpf_object__name(struct bpf_object *obj)
1641
{
1642
	return obj ? obj->path : ERR_PTR(-EINVAL);
1643 1644
}

1645
unsigned int bpf_object__kversion(struct bpf_object *obj)
1646
{
1647
	return obj ? obj->kern_version : 0;
1648 1649
}

1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665
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);
}

1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687
struct bpf_program *
bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
{
	size_t idx;

	if (!obj->programs)
		return NULL;
	/* First handler */
	if (prev == NULL)
		return &obj->programs[0];

	if (prev->obj != obj) {
		pr_warning("error: program handler doesn't match object\n");
		return NULL;
	}

	idx = (prev - obj->programs) + 1;
	if (idx >= obj->nr_programs)
		return NULL;
	return &obj->programs[idx];
}

1688 1689
int bpf_program__set_priv(struct bpf_program *prog, void *priv,
			  bpf_program_clear_priv_t clear_priv)
1690 1691 1692 1693 1694 1695 1696 1697 1698
{
	if (prog->priv && prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

1699
void *bpf_program__priv(struct bpf_program *prog)
1700
{
1701
	return prog ? prog->priv : ERR_PTR(-EINVAL);
1702 1703
}

1704
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
1705 1706 1707 1708
{
	const char *title;

	title = prog->section_name;
1709
	if (needs_copy) {
1710 1711 1712
		title = strdup(title);
		if (!title) {
			pr_warning("failed to strdup program title\n");
1713
			return ERR_PTR(-ENOMEM);
1714 1715 1716 1717 1718 1719 1720 1721
		}
	}

	return title;
}

int bpf_program__fd(struct bpf_program *prog)
{
1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770
	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;

	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;
1771
}
1772

1773
void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
1774 1775 1776 1777 1778 1779 1780 1781 1782 1783
{
	prog->type = type;
}

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

1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797
#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);	\
}							\

1798
BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
1799
BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
1800 1801
BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
1802
BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
1803 1804
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
1805

1806
#define BPF_PROG_SEC(string, type) { string, sizeof(string) - 1, type }
1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844
static const struct {
	const char *sec;
	size_t len;
	enum bpf_prog_type prog_type;
} section_names[] = {
	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("tracepoint/",	BPF_PROG_TYPE_TRACEPOINT),
	BPF_PROG_SEC("xdp",		BPF_PROG_TYPE_XDP),
	BPF_PROG_SEC("perf_event",	BPF_PROG_TYPE_PERF_EVENT),
	BPF_PROG_SEC("cgroup/skb",	BPF_PROG_TYPE_CGROUP_SKB),
	BPF_PROG_SEC("cgroup/sock",	BPF_PROG_TYPE_CGROUP_SOCK),
	BPF_PROG_SEC("cgroup/dev",	BPF_PROG_TYPE_CGROUP_DEVICE),
	BPF_PROG_SEC("sockops",		BPF_PROG_TYPE_SOCK_OPS),
	BPF_PROG_SEC("sk_skb",		BPF_PROG_TYPE_SK_SKB),
};
#undef BPF_PROG_SEC

static enum bpf_prog_type bpf_program__guess_type(struct bpf_program *prog)
{
	int i;

	if (!prog->section_name)
		goto err;

	for (i = 0; i < ARRAY_SIZE(section_names); i++)
		if (strncmp(prog->section_name, section_names[i].sec,
			    section_names[i].len) == 0)
			return section_names[i].prog_type;

err:
	pr_warning("failed to guess program type based on section name %s\n",
		   prog->section_name);

	return BPF_PROG_TYPE_UNSPEC;
}

1845
int bpf_map__fd(struct bpf_map *map)
1846
{
1847
	return map ? map->fd : -EINVAL;
1848 1849
}

1850
const struct bpf_map_def *bpf_map__def(struct bpf_map *map)
1851
{
1852
	return map ? &map->def : ERR_PTR(-EINVAL);
1853 1854
}

1855
const char *bpf_map__name(struct bpf_map *map)
1856
{
1857
	return map ? map->name : NULL;
1858 1859
}

1860 1861
int bpf_map__set_priv(struct bpf_map *map, void *priv,
		     bpf_map_clear_priv_t clear_priv)
1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875
{
	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;
}

1876
void *bpf_map__priv(struct bpf_map *map)
1877
{
1878
	return map ? map->priv : ERR_PTR(-EINVAL);
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
}

struct bpf_map *
bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
{
	size_t idx;
	struct bpf_map *s, *e;

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

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

	if (prev == NULL)
		return s;

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

	idx = (prev - obj->maps) + 1;
	if (idx >= obj->nr_maps)
		return NULL;
	return &obj->maps[idx];
}
1907 1908

struct bpf_map *
1909
bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
1910 1911 1912 1913
{
	struct bpf_map *pos;

	bpf_map__for_each(pos, obj) {
1914
		if (pos->name && !strcmp(pos->name, name))
1915 1916 1917 1918
			return pos;
	}
	return NULL;
}
1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930

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);
}
1931 1932 1933 1934 1935 1936 1937

long libbpf_get_error(const void *ptr)
{
	if (IS_ERR(ptr))
		return PTR_ERR(ptr);
	return 0;
}
1938 1939 1940 1941

int bpf_prog_load(const char *file, enum bpf_prog_type type,
		  struct bpf_object **pobj, int *prog_fd)
{
1942
	struct bpf_program *prog, *first_prog = NULL;
1943 1944 1945 1946 1947 1948 1949
	struct bpf_object *obj;
	int err;

	obj = bpf_object__open(file);
	if (IS_ERR(obj))
		return -ENOENT;

1950 1951 1952 1953 1954
	bpf_object__for_each_program(prog, obj) {
		/*
		 * If type is not specified, try to guess it based on
		 * section name.
		 */
1955
		if (type == BPF_PROG_TYPE_UNSPEC) {
1956 1957 1958 1959 1960
			type = bpf_program__guess_type(prog);
			if (type == BPF_PROG_TYPE_UNSPEC) {
				bpf_object__close(obj);
				return -EINVAL;
			}
1961
		}
1962 1963 1964 1965 1966 1967 1968 1969 1970 1971

		bpf_program__set_type(prog, type);
		if (prog->idx != obj->efile.text_shndx && !first_prog)
			first_prog = prog;
	}

	if (!first_prog) {
		pr_warning("object file doesn't contain bpf program\n");
		bpf_object__close(obj);
		return -ENOENT;
1972 1973
	}

1974 1975 1976 1977 1978 1979 1980
	err = bpf_object__load(obj);
	if (err) {
		bpf_object__close(obj);
		return -EINVAL;
	}

	*pobj = obj;
1981
	*prog_fd = bpf_program__fd(first_prog);
1982 1983
	return 0;
}