libbpf.c 29.4 KB
Newer Older
1 2 3 4 5 6 7 8 9
/*
 * 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.
 */

#include <stdlib.h>
10 11
#include <stdio.h>
#include <stdarg.h>
12
#include <inttypes.h>
13
#include <string.h>
14
#include <unistd.h>
15 16
#include <fcntl.h>
#include <errno.h>
17
#include <asm/unistd.h>
18
#include <linux/kernel.h>
19
#include <linux/bpf.h>
20
#include <linux/list.h>
21 22
#include <libelf.h>
#include <gelf.h>
23 24

#include "libbpf.h"
25
#include "bpf.h"
26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62

#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;
}
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 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117
#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",
	[ERRCODE_OFFSET(ENDIAN)]	= "Endian missmatch",
	[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",
};

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)


118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137
/* 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

138 139 140 141 142 143 144 145 146 147
/*
 * 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;
	char *section_name;
	struct bpf_insn *insns;
	size_t insns_cnt;
148 149 150 151 152 153

	struct {
		int insn_idx;
		int map_idx;
	} *reloc_desc;
	int nr_reloc;
154

155 156 157 158 159
	struct {
		int nr;
		int *fds;
	} instances;
	bpf_program_prep_t preprocessor;
160 161 162 163

	struct bpf_object *obj;
	void *priv;
	bpf_program_clear_priv_t clear_priv;
164 165
};

166 167
struct bpf_map {
	int fd;
168
	char *name;
169 170 171 172 173
	struct bpf_map_def def;
	void *priv;
	bpf_map_clear_priv_t clear_priv;
};

174 175
static LIST_HEAD(bpf_objects_list);

176
struct bpf_object {
177 178
	char license[64];
	u32 kern_version;
179

180 181
	struct bpf_program *programs;
	size_t nr_programs;
182 183 184
	struct bpf_map *maps;
	size_t nr_maps;

185
	bool loaded;
186

187 188 189 190 191 192
	/*
	 * Information when doing elf related work. Only valid if fd
	 * is valid.
	 */
	struct {
		int fd;
193 194
		void *obj_buf;
		size_t obj_buf_sz;
195 196
		Elf *elf;
		GElf_Ehdr ehdr;
197
		Elf_Data *symbols;
198
		size_t strtabidx;
199 200 201 202 203
		struct {
			GElf_Shdr shdr;
			Elf_Data *data;
		} *reloc;
		int nr_reloc;
204
	} efile;
205 206 207 208 209 210
	/*
	 * 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;
211 212 213 214
	char path[];
};
#define obj_elf_valid(o)	((o)->efile.elf)

215 216
static void bpf_program__unload(struct bpf_program *prog)
{
217 218
	int i;

219 220 221
	if (!prog)
		return;

222 223 224 225 226 227 228 229 230 231 232 233 234 235
	/*
	 * 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);
236 237
}

238 239 240 241 242
static void bpf_program__exit(struct bpf_program *prog)
{
	if (!prog)
		return;

243 244 245 246 247 248
	if (prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

249
	bpf_program__unload(prog);
250 251
	zfree(&prog->section_name);
	zfree(&prog->insns);
252 253 254
	zfree(&prog->reloc_desc);

	prog->nr_reloc = 0;
255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285
	prog->insns_cnt = 0;
	prog->idx = -1;
}

static int
bpf_program__init(void *data, size_t size, char *name, int idx,
		    struct bpf_program *prog)
{
	if (size < sizeof(struct bpf_insn)) {
		pr_warning("corrupted section '%s'\n", name);
		return -EINVAL;
	}

	bzero(prog, sizeof(*prog));

	prog->section_name = strdup(name);
	if (!prog->section_name) {
		pr_warning("failed to alloc name for prog %s\n",
			   name);
		goto errout;
	}

	prog->insns = malloc(size);
	if (!prog->insns) {
		pr_warning("failed to alloc insns for %s\n", name);
		goto errout;
	}
	prog->insns_cnt = size / sizeof(struct bpf_insn);
	memcpy(prog->insns, data,
	       prog->insns_cnt * sizeof(struct bpf_insn));
	prog->idx = idx;
286 287
	prog->instances.fds = NULL;
	prog->instances.nr = -1;
288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324

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

static int
bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
			char *name, int idx)
{
	struct bpf_program prog, *progs;
	int nr_progs, err;

	err = bpf_program__init(data, size, name, idx, &prog);
	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().
		 */
		pr_warning("failed to alloc a new program '%s'\n",
			   name);
		bpf_program__exit(&prog);
		return -ENOMEM;
	}

	pr_debug("found program %s\n", prog.section_name);
	obj->programs = progs;
	obj->nr_programs = nr_progs + 1;
325
	prog.obj = obj;
326 327 328 329
	progs[nr_progs] = prog;
	return 0;
}

330 331 332
static struct bpf_object *bpf_object__new(const char *path,
					  void *obj_buf,
					  size_t obj_buf_sz)
333 334 335 336 337 338
{
	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);
339
		return ERR_PTR(-ENOMEM);
340 341 342 343
	}

	strcpy(obj->path, path);
	obj->efile.fd = -1;
344 345 346 347 348 349 350 351 352 353

	/*
	 * 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;

354
	obj->loaded = false;
355 356 357

	INIT_LIST_HEAD(&obj->list);
	list_add(&obj->list, &bpf_objects_list);
358 359 360 361 362 363 364 365 366 367 368 369
	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;
	}
370
	obj->efile.symbols = NULL;
371 372 373

	zfree(&obj->efile.reloc);
	obj->efile.nr_reloc = 0;
374
	zclose(obj->efile.fd);
375 376
	obj->efile.obj_buf = NULL;
	obj->efile.obj_buf_sz = 0;
377 378 379 380 381 382 383 384 385
}

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");
386
		return -LIBBPF_ERRNO__LIBELF;
387 388
	}

389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406
	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);
407 408 409 410 411
	}

	if (!obj->efile.elf) {
		pr_warning("failed to open %s as ELF file\n",
				obj->path);
412
		err = -LIBBPF_ERRNO__LIBELF;
413 414 415 416 417 418
		goto errout;
	}

	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
		pr_warning("failed to get EHDR from %s\n",
				obj->path);
419
		err = -LIBBPF_ERRNO__FORMAT;
420 421 422 423 424 425 426
		goto errout;
	}
	ep = &obj->efile.ehdr;

	if ((ep->e_type != ET_REL) || (ep->e_machine != 0)) {
		pr_warning("%s is not an eBPF object file\n",
			obj->path);
427
		err = -LIBBPF_ERRNO__FORMAT;
428 429 430 431 432 433 434 435 436
		goto errout;
	}

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

437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454
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:
455
		return -LIBBPF_ERRNO__ENDIAN;
456 457 458 459 460 461
	}

	return 0;

mismatch:
	pr_warning("Error: endianness mismatch.\n");
462
	return -LIBBPF_ERRNO__ENDIAN;
463 464
}

465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482
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);
483
		return -LIBBPF_ERRNO__FORMAT;
484 485 486 487 488 489 490 491
	}
	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;
}

492 493 494 495
static int
bpf_object__init_maps(struct bpf_object *obj, void *data,
		      size_t size)
{
496 497 498 499 500
	size_t nr_maps;
	int i;

	nr_maps = size / sizeof(struct bpf_map_def);
	if (!data || !nr_maps) {
501 502 503 504 505
		pr_debug("%s doesn't need map definition\n",
			 obj->path);
		return 0;
	}

506 507 508 509 510
	pr_debug("maps in %s: %zd bytes\n", obj->path, size);

	obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
	if (!obj->maps) {
		pr_warning("alloc maps for object failed\n");
511 512
		return -ENOMEM;
	}
513 514 515 516
	obj->nr_maps = nr_maps;

	for (i = 0; i < nr_maps; i++) {
		struct bpf_map_def *def = &obj->maps[i].def;
517

518 519 520 521 522 523 524 525 526 527
		/*
		 * fill all fd with -1 so won't close incorrect
		 * fd (fd=0 is stdin) when failure (zclose won't close
		 * negative fd)).
		 */
		obj->maps[i].fd = -1;

		/* Save map definition into obj->maps */
		*def = ((struct bpf_map_def *)data)[i];
	}
528 529 530
	return 0;
}

531
static int
532 533 534 535 536 537
bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx)
{
	int i;
	Elf_Data *symbols = obj->efile.symbols;

	if (!symbols || maps_shndx < 0)
538
		return -EINVAL;
539 540 541 542 543 544 545 546 547 548 549 550

	for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
		GElf_Sym sym;
		size_t map_idx;
		const char *map_name;

		if (!gelf_getsym(symbols, i, &sym))
			continue;
		if (sym.st_shndx != maps_shndx)
			continue;

		map_name = elf_strptr(obj->efile.elf,
551
				      obj->efile.strtabidx,
552 553 554 555 556 557 558 559
				      sym.st_name);
		map_idx = sym.st_value / sizeof(struct bpf_map_def);
		if (map_idx >= obj->nr_maps) {
			pr_warning("index of map \"%s\" is buggy: %zu > %zu\n",
				   map_name, map_idx, obj->nr_maps);
			continue;
		}
		obj->maps[map_idx].name = strdup(map_name);
560 561 562 563
		if (!obj->maps[map_idx].name) {
			pr_warning("failed to alloc map name\n");
			return -ENOMEM;
		}
564 565 566
		pr_debug("map %zu is \"%s\"\n", map_idx,
			 obj->maps[map_idx].name);
	}
567
	return 0;
568 569
}

570 571 572 573 574
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;
575
	int idx = 0, err = 0, maps_shndx = -1;
576 577 578 579 580

	/* 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);
581
		return -LIBBPF_ERRNO__FORMAT;
582 583 584 585 586 587 588 589 590 591 592
	}

	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);
593
			err = -LIBBPF_ERRNO__FORMAT;
594 595 596 597 598 599 600
			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);
601
			err = -LIBBPF_ERRNO__FORMAT;
602 603 604 605 606 607 608
			goto out;
		}

		data = elf_getdata(scn, 0);
		if (!data) {
			pr_warning("failed to get section data from %s(%s)\n",
				   name, obj->path);
609
			err = -LIBBPF_ERRNO__FORMAT;
610 611 612 613 614 615
			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);
616 617 618 619 620 621 622 623 624

		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);
625
		else if (strcmp(name, "maps") == 0) {
626 627
			err = bpf_object__init_maps(obj, data->d_buf,
						    data->d_size);
628 629
			maps_shndx = idx;
		} else if (sh.sh_type == SHT_SYMTAB) {
630 631 632
			if (obj->efile.symbols) {
				pr_warning("bpf: multiple SYMTAB in %s\n",
					   obj->path);
633
				err = -LIBBPF_ERRNO__FORMAT;
634
			} else {
635
				obj->efile.symbols = data;
636 637
				obj->efile.strtabidx = sh.sh_link;
			}
638 639 640 641 642 643
		} else if ((sh.sh_type == SHT_PROGBITS) &&
			   (sh.sh_flags & SHF_EXECINSTR) &&
			   (data->d_size > 0)) {
			err = bpf_object__add_program(obj, data->d_buf,
						      data->d_size, name, idx);
			if (err) {
644 645
				char errmsg[STRERR_BUFSIZE];

646 647 648 649
				strerror_r(-err, errmsg, sizeof(errmsg));
				pr_warning("failed to alloc program %s (%s): %s",
					   name, obj->path, errmsg);
			}
650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667
		} 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;
			}
668
		}
669 670
		if (err)
			goto out;
671
	}
672

673 674 675 676
	if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
		pr_warning("Corrupted ELF file: index of strtab invalid\n");
		return LIBBPF_ERRNO__FORMAT;
	}
677
	if (maps_shndx >= 0)
678
		err = bpf_object__init_maps_name(obj, maps_shndx);
679 680 681 682
out:
	return err;
}

683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723
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
bpf_program__collect_reloc(struct bpf_program *prog,
			   size_t nr_maps, GElf_Shdr *shdr,
			   Elf_Data *data, Elf_Data *symbols)
{
	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);
724
			return -LIBBPF_ERRNO__FORMAT;
725 726 727 728 729 730 731 732 733 734
		}

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

		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));
735
			return -LIBBPF_ERRNO__FORMAT;
736 737 738 739 740
		}

		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);
741
			return -LIBBPF_ERRNO__RELOC;
742 743 744 745 746 747
		}

		map_idx = sym.st_value / sizeof(struct bpf_map_def);
		if (map_idx >= nr_maps) {
			pr_warning("bpf relocation: map_idx %d large than %d\n",
				   (int)map_idx, (int)nr_maps - 1);
748
			return -LIBBPF_ERRNO__RELOC;
749 750 751 752 753 754 755 756
		}

		prog->reloc_desc[i].insn_idx = insn_idx;
		prog->reloc_desc[i].map_idx = map_idx;
	}
	return 0;
}

757 758 759 760 761
static int
bpf_object__create_maps(struct bpf_object *obj)
{
	unsigned int i;

762 763 764
	for (i = 0; i < obj->nr_maps; i++) {
		struct bpf_map_def *def = &obj->maps[i].def;
		int *pfd = &obj->maps[i].fd;
765

766 767 768 769
		*pfd = bpf_create_map(def->type,
				      def->key_size,
				      def->value_size,
				      def->max_entries);
770 771 772 773 774 775 776
		if (*pfd < 0) {
			size_t j;
			int err = *pfd;

			pr_warning("failed to create map: %s\n",
				   strerror(errno));
			for (j = 0; j < i; j++)
777
				zclose(obj->maps[j].fd);
778 779 780 781 782 783 784 785
			return err;
		}
		pr_debug("create map: fd=%d\n", *pfd);
	}

	return 0;
}

W
Wang Nan 已提交
786
static int
787
bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
W
Wang Nan 已提交
788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803
{
	int i;

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

	for (i = 0; i < prog->nr_reloc; i++) {
		int insn_idx, map_idx;
		struct bpf_insn *insns = prog->insns;

		insn_idx = prog->reloc_desc[i].insn_idx;
		map_idx = prog->reloc_desc[i].map_idx;

		if (insn_idx >= (int)prog->insns_cnt) {
			pr_warning("relocation out of range: '%s'\n",
				   prog->section_name);
804
			return -LIBBPF_ERRNO__RELOC;
W
Wang Nan 已提交
805 806
		}
		insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
807
		insns[insn_idx].imm = obj->maps[map_idx].fd;
W
Wang Nan 已提交
808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825
	}

	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];

826
		err = bpf_program__relocate(prog, obj);
W
Wang Nan 已提交
827 828 829 830 831 832 833 834 835
		if (err) {
			pr_warning("failed to relocate '%s'\n",
				   prog->section_name);
			return err;
		}
	}
	return 0;
}

836 837 838 839 840 841
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");
842
		return -LIBBPF_ERRNO__INTERNAL;
843 844 845 846 847 848 849
	}

	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;
850
		size_t nr_maps = obj->nr_maps;
851 852 853

		if (shdr->sh_type != SHT_REL) {
			pr_warning("internal error at %d\n", __LINE__);
854
			return -LIBBPF_ERRNO__INTERNAL;
855 856 857 858 859 860
		}

		prog = bpf_object__find_prog_by_idx(obj, idx);
		if (!prog) {
			pr_warning("relocation failed: no %d section\n",
				   idx);
861
			return -LIBBPF_ERRNO__RELOC;
862 863 864 865 866 867
		}

		err = bpf_program__collect_reloc(prog, nr_maps,
						 shdr, data,
						 obj->efile.symbols);
		if (err)
868
			return err;
869 870 871 872
	}
	return 0;
}

873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896
static int
load_program(struct bpf_insn *insns, int insns_cnt,
	     char *license, u32 kern_version, int *pfd)
{
	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");

	ret = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns,
			       insns_cnt, license, kern_version,
			       log_buf, BPF_LOG_BUF_SIZE);

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

897
	ret = -LIBBPF_ERRNO__LOAD;
898 899
	pr_warning("load bpf program failed: %s\n", strerror(errno));

900 901
	if (log_buf && log_buf[0] != '\0') {
		ret = -LIBBPF_ERRNO__VERIFY;
902 903 904
		pr_warning("-- BEGIN DUMP LOG ---\n");
		pr_warning("\n%s\n", log_buf);
		pr_warning("-- END LOG --\n");
905 906 907 908 909 910 911 912 913
	} 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;
		} else if (log_buf) {
			pr_warning("log buffer is empty\n");
			ret = -LIBBPF_ERRNO__KVER;
		}
914 915 916 917 918 919 920 921 922 923 924
	}

out:
	free(log_buf);
	return ret;
}

static int
bpf_program__load(struct bpf_program *prog,
		  char *license, u32 kern_version)
{
925
	int err = 0, fd, i;
926

927 928 929 930 931 932
	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;
		}
933

934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991
		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);
		}
		err = load_program(prog->insns, prog->insns_cnt,
				   license, kern_version, &fd);
		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;
		}

		err = load_program(result.new_insn_ptr,
				   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:
992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015
	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++) {
		err = bpf_program__load(&obj->programs[i],
					obj->license,
					obj->kern_version);
		if (err)
			return err;
	}
	return 0;
}

1016 1017 1018 1019 1020
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);
1021
		return -LIBBPF_ERRNO__KVERSION;
1022 1023 1024 1025
	}
	return 0;
}

1026
static struct bpf_object *
1027
__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz)
1028 1029
{
	struct bpf_object *obj;
1030
	int err;
1031 1032 1033

	if (elf_version(EV_CURRENT) == EV_NONE) {
		pr_warning("failed to init libelf for %s\n", path);
1034
		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
1035 1036
	}

1037
	obj = bpf_object__new(path, obj_buf, obj_buf_sz);
1038 1039
	if (IS_ERR(obj))
		return obj;
1040

1041 1042 1043 1044 1045
	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);
1046 1047 1048 1049 1050

	bpf_object__elf_finish(obj);
	return obj;
out:
	bpf_object__close(obj);
1051
	return ERR_PTR(err);
1052 1053 1054 1055 1056 1057 1058 1059 1060 1061
}

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

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

1062 1063 1064 1065
	return __bpf_object__open(path, NULL, 0);
}

struct bpf_object *bpf_object__open_buffer(void *obj_buf,
1066 1067
					   size_t obj_buf_sz,
					   const char *name)
1068
{
1069 1070
	char tmp_name[64];

1071 1072 1073 1074
	/* param validation */
	if (!obj_buf || obj_buf_sz <= 0)
		return NULL;

1075 1076 1077 1078 1079 1080 1081 1082 1083
	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);
1084

1085
	return __bpf_object__open(name, obj_buf, obj_buf_sz);
1086 1087
}

1088 1089 1090 1091 1092 1093 1094
int bpf_object__unload(struct bpf_object *obj)
{
	size_t i;

	if (!obj)
		return -EINVAL;

1095 1096
	for (i = 0; i < obj->nr_maps; i++)
		zclose(obj->maps[i].fd);
1097

1098 1099 1100
	for (i = 0; i < obj->nr_programs; i++)
		bpf_program__unload(&obj->programs[i]);

1101 1102 1103 1104 1105
	return 0;
}

int bpf_object__load(struct bpf_object *obj)
{
1106 1107
	int err;

1108 1109 1110 1111 1112 1113 1114 1115 1116
	if (!obj)
		return -EINVAL;

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

	obj->loaded = true;
1117 1118 1119 1120

	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);
1121 1122 1123 1124 1125

	return 0;
out:
	bpf_object__unload(obj);
	pr_warning("failed to load object '%s'\n", obj->path);
1126
	return err;
1127 1128
}

1129 1130
void bpf_object__close(struct bpf_object *obj)
{
1131 1132
	size_t i;

1133 1134 1135 1136
	if (!obj)
		return;

	bpf_object__elf_finish(obj);
1137
	bpf_object__unload(obj);
1138

1139
	for (i = 0; i < obj->nr_maps; i++) {
1140
		zfree(&obj->maps[i].name);
1141 1142 1143 1144 1145 1146 1147 1148
		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;
1149 1150 1151 1152 1153 1154 1155

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

1156
	list_del(&obj->list);
1157 1158
	free(obj);
}
1159

1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178
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;
}

1179 1180 1181 1182
const char *
bpf_object__get_name(struct bpf_object *obj)
{
	if (!obj)
1183
		return ERR_PTR(-EINVAL);
1184 1185 1186
	return obj->path;
}

1187 1188 1189 1190 1191 1192 1193 1194
unsigned int
bpf_object__get_kversion(struct bpf_object *obj)
{
	if (!obj)
		return 0;
	return obj->kern_version;
}

1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234
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];
}

int bpf_program__set_private(struct bpf_program *prog,
			     void *priv,
			     bpf_program_clear_priv_t clear_priv)
{
	if (prog->priv && prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

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

int bpf_program__get_private(struct bpf_program *prog, void **ppriv)
{
	*ppriv = prog->priv;
	return 0;
}

1235
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
1236 1237 1238 1239
{
	const char *title;

	title = prog->section_name;
1240
	if (needs_copy) {
1241 1242 1243
		title = strdup(title);
		if (!title) {
			pr_warning("failed to strdup program title\n");
1244
			return ERR_PTR(-ENOMEM);
1245 1246 1247 1248 1249 1250 1251 1252
		}
	}

	return title;
}

int bpf_program__fd(struct bpf_program *prog)
{
1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301
	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;
1302
}
1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320

int bpf_map__get_fd(struct bpf_map *map)
{
	if (!map)
		return -EINVAL;

	return map->fd;
}

int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef)
{
	if (!map || !pdef)
		return -EINVAL;

	*pdef = map->def;
	return 0;
}

1321 1322 1323 1324 1325 1326 1327
const char *bpf_map__get_name(struct bpf_map *map)
{
	if (!map)
		return NULL;
	return map->name;
}

1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379
int bpf_map__set_private(struct bpf_map *map, void *priv,
			 bpf_map_clear_priv_t clear_priv)
{
	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;
}

int bpf_map__get_private(struct bpf_map *map, void **ppriv)
{
	if (!map)
		return -EINVAL;

	if (ppriv)
		*ppriv = map->priv;
	return 0;
}

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];
}
1380 1381 1382 1383 1384 1385 1386

struct bpf_map *
bpf_object__get_map_by_name(struct bpf_object *obj, const char *name)
{
	struct bpf_map *pos;

	bpf_map__for_each(pos, obj) {
1387
		if (pos->name && !strcmp(pos->name, name))
1388 1389 1390 1391
			return pos;
	}
	return NULL;
}