symbol.c 20.0 KB
Newer Older
1 2
#include "util.h"
#include "../perf.h"
3
#include "string.h"
4 5 6 7 8
#include "symbol.h"

#include <libelf.h>
#include <gelf.h>
#include <elf.h>
P
Peter Zijlstra 已提交
9 10

#ifndef NO_DEMANGLE
11
#include <bfd.h>
P
Peter Zijlstra 已提交
12 13 14 15 16 17 18
#else
static inline
char *bfd_demangle(void __used *v, const char __used *c, int __used i)
{
	return NULL;
}
#endif
19

20 21
const char *sym_hist_filter;

22 23 24 25 26
#ifndef DMGL_PARAMS
#define DMGL_PARAMS      (1 << 0)       /* Include function args */
#define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
#endif

27 28 29 30 31 32 33 34 35 36
enum dso_origin {
	DSO__ORIG_KERNEL = 0,
	DSO__ORIG_JAVA_JIT,
	DSO__ORIG_FEDORA,
	DSO__ORIG_UBUNTU,
	DSO__ORIG_BUILDID,
	DSO__ORIG_DSO,
	DSO__ORIG_NOT_FOUND,
};

37
static struct symbol *symbol__new(u64 start, u64 len,
38
				  const char *name, unsigned int priv_size,
39
				  u64 obj_start, int verbose)
40
{
41
	size_t namelen = strlen(name) + 1;
42
	struct symbol *self = calloc(1, priv_size + sizeof(*self) + namelen);
43

44 45 46 47 48
	if (!self)
		return NULL;

	if (verbose >= 2)
		printf("new symbol: %016Lx [%08lx]: %s, hist: %p, obj_start: %p\n",
49
			(u64)start, (unsigned long)len, name, self->hist, (void *)(unsigned long)obj_start);
50 51 52 53 54 55

	self->obj_start= obj_start;
	self->hist = NULL;
	self->hist_sum = 0;

	if (sym_hist_filter && !strcmp(name, sym_hist_filter))
56
		self->hist = calloc(sizeof(u64), len);
57 58 59 60

	if (priv_size) {
		memset(self, 0, priv_size);
		self = ((void *)self) + priv_size;
61
	}
62
	self->start = start;
63
	self->end   = len ? start + len - 1 : start;
64
	memcpy(self->name, name, namelen);
65 66 67 68

	return self;
}

69
static void symbol__delete(struct symbol *self, unsigned int priv_size)
70
{
71
	free(((void *)self) - priv_size);
72 73 74 75
}

static size_t symbol__fprintf(struct symbol *self, FILE *fp)
{
76 77
	if (!self->module)
		return fprintf(fp, " %llx-%llx %s\n",
78
		       self->start, self->end, self->name);
79 80 81
	else
		return fprintf(fp, " %llx-%llx %s \t[%s]\n",
		       self->start, self->end, self->name, self->module->name);
82 83
}

84
struct dso *dso__new(const char *name, unsigned int sym_priv_size)
85 86 87 88 89 90
{
	struct dso *self = malloc(sizeof(*self) + strlen(name) + 1);

	if (self != NULL) {
		strcpy(self->name, name);
		self->syms = RB_ROOT;
91
		self->sym_priv_size = sym_priv_size;
P
Peter Zijlstra 已提交
92
		self->find_symbol = dso__find_symbol;
93
		self->slen_calculated = 0;
94
		self->origin = DSO__ORIG_NOT_FOUND;
95 96 97 98 99 100 101 102 103 104 105 106 107
	}

	return self;
}

static void dso__delete_symbols(struct dso *self)
{
	struct symbol *pos;
	struct rb_node *next = rb_first(&self->syms);

	while (next) {
		pos = rb_entry(next, struct symbol, rb_node);
		next = rb_next(&pos->rb_node);
108
		rb_erase(&pos->rb_node, &self->syms);
109
		symbol__delete(pos, self->sym_priv_size);
110 111 112 113 114 115 116 117 118 119 120 121 122
	}
}

void dso__delete(struct dso *self)
{
	dso__delete_symbols(self);
	free(self);
}

static void dso__insert_symbol(struct dso *self, struct symbol *sym)
{
	struct rb_node **p = &self->syms.rb_node;
	struct rb_node *parent = NULL;
123
	const u64 ip = sym->start;
124 125 126 127 128 129 130 131 132 133 134 135 136 137
	struct symbol *s;

	while (*p != NULL) {
		parent = *p;
		s = rb_entry(parent, struct symbol, rb_node);
		if (ip < s->start)
			p = &(*p)->rb_left;
		else
			p = &(*p)->rb_right;
	}
	rb_link_node(&sym->rb_node, parent, p);
	rb_insert_color(&sym->rb_node, &self->syms);
}

138
struct symbol *dso__find_symbol(struct dso *self, u64 ip)
139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173
{
	struct rb_node *n;

	if (self == NULL)
		return NULL;

	n = self->syms.rb_node;

	while (n) {
		struct symbol *s = rb_entry(n, struct symbol, rb_node);

		if (ip < s->start)
			n = n->rb_left;
		else if (ip > s->end)
			n = n->rb_right;
		else
			return s;
	}

	return NULL;
}

size_t dso__fprintf(struct dso *self, FILE *fp)
{
	size_t ret = fprintf(fp, "dso: %s\n", self->name);

	struct rb_node *nd;
	for (nd = rb_first(&self->syms); nd; nd = rb_next(nd)) {
		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
		ret += symbol__fprintf(pos, fp);
	}

	return ret;
}

174
static int dso__load_kallsyms(struct dso *self, symbol_filter_t filter, int verbose)
175 176 177 178 179
{
	struct rb_node *nd, *prevnd;
	char *line = NULL;
	size_t n;
	FILE *file = fopen("/proc/kallsyms", "r");
180
	int count = 0;
181 182 183 184 185

	if (file == NULL)
		goto out_failure;

	while (!feof(file)) {
186
		u64 start;
187 188 189 190 191 192 193 194 195 196 197 198 199
		struct symbol *sym;
		int line_len, len;
		char symbol_type;

		line_len = getline(&line, &n, file);
		if (line_len < 0)
			break;

		if (!line)
			goto out_failure;

		line[--line_len] = '\0'; /* \n */

200
		len = hex2u64(line, &start);
201 202 203 204 205 206 207 208 209 210 211 212 213 214

		len++;
		if (len + 2 >= line_len)
			continue;

		symbol_type = toupper(line[len]);
		/*
		 * We're interested only in code ('T'ext)
		 */
		if (symbol_type != 'T' && symbol_type != 'W')
			continue;
		/*
		 * Well fix up the end later, when we have all sorted.
		 */
215
		sym = symbol__new(start, 0xdead, line + len + 2,
216
				  self->sym_priv_size, 0, verbose);
217 218 219 220

		if (sym == NULL)
			goto out_delete_line;

221 222
		if (filter && filter(self, sym))
			symbol__delete(sym, self->sym_priv_size);
223
		else {
224
			dso__insert_symbol(self, sym);
225 226
			count++;
		}
227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248
	}

	/*
	 * Now that we have all sorted out, just set the ->end of all
	 * symbols
	 */
	prevnd = rb_first(&self->syms);

	if (prevnd == NULL)
		goto out_delete_line;

	for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) {
		struct symbol *prev = rb_entry(prevnd, struct symbol, rb_node),
			      *curr = rb_entry(nd, struct symbol, rb_node);

		prev->end = curr->start - 1;
		prevnd = nd;
	}

	free(line);
	fclose(file);

249
	return count;
250 251 252 253 254 255 256

out_delete_line:
	free(line);
out_failure:
	return -1;
}

257 258 259 260 261 262 263 264 265 266 267 268
static int dso__load_perf_map(struct dso *self, symbol_filter_t filter, int verbose)
{
	char *line = NULL;
	size_t n;
	FILE *file;
	int nr_syms = 0;

	file = fopen(self->name, "r");
	if (file == NULL)
		goto out_failure;

	while (!feof(file)) {
269
		u64 start, size;
270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318
		struct symbol *sym;
		int line_len, len;

		line_len = getline(&line, &n, file);
		if (line_len < 0)
			break;

		if (!line)
			goto out_failure;

		line[--line_len] = '\0'; /* \n */

		len = hex2u64(line, &start);

		len++;
		if (len + 2 >= line_len)
			continue;

		len += hex2u64(line + len, &size);

		len++;
		if (len + 2 >= line_len)
			continue;

		sym = symbol__new(start, size, line + len,
				  self->sym_priv_size, start, verbose);

		if (sym == NULL)
			goto out_delete_line;

		if (filter && filter(self, sym))
			symbol__delete(sym, self->sym_priv_size);
		else {
			dso__insert_symbol(self, sym);
			nr_syms++;
		}
	}

	free(line);
	fclose(file);

	return nr_syms;

out_delete_line:
	free(line);
out_failure:
	return -1;
}

319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343
/**
 * elf_symtab__for_each_symbol - iterate thru all the symbols
 *
 * @self: struct elf_symtab instance to iterate
 * @index: uint32_t index
 * @sym: GElf_Sym iterator
 */
#define elf_symtab__for_each_symbol(syms, nr_syms, index, sym) \
	for (index = 0, gelf_getsym(syms, index, &sym);\
	     index < nr_syms; \
	     index++, gelf_getsym(syms, index, &sym))

static inline uint8_t elf_sym__type(const GElf_Sym *sym)
{
	return GELF_ST_TYPE(sym->st_info);
}

static inline int elf_sym__is_function(const GElf_Sym *sym)
{
	return elf_sym__type(sym) == STT_FUNC &&
	       sym->st_name != 0 &&
	       sym->st_shndx != SHN_UNDEF &&
	       sym->st_size != 0;
}

344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363
static inline int elf_sym__is_label(const GElf_Sym *sym)
{
	return elf_sym__type(sym) == STT_NOTYPE &&
		sym->st_name != 0 &&
		sym->st_shndx != SHN_UNDEF &&
		sym->st_shndx != SHN_ABS;
}

static inline const char *elf_sec__name(const GElf_Shdr *shdr,
					const Elf_Data *secstrs)
{
	return secstrs->d_buf + shdr->sh_name;
}

static inline int elf_sec__is_text(const GElf_Shdr *shdr,
					const Elf_Data *secstrs)
{
	return strstr(elf_sec__name(shdr, secstrs), "text") != NULL;
}

364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392
static inline const char *elf_sym__name(const GElf_Sym *sym,
					const Elf_Data *symstrs)
{
	return symstrs->d_buf + sym->st_name;
}

static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
				    GElf_Shdr *shp, const char *name,
				    size_t *index)
{
	Elf_Scn *sec = NULL;
	size_t cnt = 1;

	while ((sec = elf_nextscn(elf, sec)) != NULL) {
		char *str;

		gelf_getshdr(sec, shp);
		str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
		if (!strcmp(name, str)) {
			if (index)
				*index = cnt;
			break;
		}
		++cnt;
	}

	return sec;
}

393 394 395 396 397 398 399 400 401 402
#define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \
	for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \
	     idx < nr_entries; \
	     ++idx, pos = gelf_getrel(reldata, idx, &pos_mem))

#define elf_section__for_each_rela(reldata, pos, pos_mem, idx, nr_entries) \
	for (idx = 0, pos = gelf_getrela(reldata, 0, &pos_mem); \
	     idx < nr_entries; \
	     ++idx, pos = gelf_getrela(reldata, idx, &pos_mem))

403 404 405 406 407 408 409 410
/*
 * We need to check if we have a .dynsym, so that we can handle the
 * .plt, synthesizing its symbols, that aren't on the symtabs (be it
 * .dynsym or .symtab).
 * And always look at the original dso, not at debuginfo packages, that
 * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS).
 */
static int dso__synthesize_plt_symbols(struct  dso *self, int verbose)
411 412 413
{
	uint32_t nr_rel_entries, idx;
	GElf_Sym sym;
414
	u64 plt_offset;
415 416
	GElf_Shdr shdr_plt;
	struct symbol *f;
417
	GElf_Shdr shdr_rel_plt, shdr_dynsym;
418
	Elf_Data *reldata, *syms, *symstrs;
419 420 421
	Elf_Scn *scn_plt_rel, *scn_symstrs, *scn_dynsym;
	size_t dynsym_idx;
	GElf_Ehdr ehdr;
422
	char sympltname[1024];
423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440
	Elf *elf;
	int nr = 0, symidx, fd, err = 0;

	fd = open(self->name, O_RDONLY);
	if (fd < 0)
		goto out;

	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
	if (elf == NULL)
		goto out_close;

	if (gelf_getehdr(elf, &ehdr) == NULL)
		goto out_elf_end;

	scn_dynsym = elf_section_by_name(elf, &ehdr, &shdr_dynsym,
					 ".dynsym", &dynsym_idx);
	if (scn_dynsym == NULL)
		goto out_elf_end;
441

442
	scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt,
443 444
					  ".rela.plt", NULL);
	if (scn_plt_rel == NULL) {
445
		scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt,
446 447
						  ".rel.plt", NULL);
		if (scn_plt_rel == NULL)
448
			goto out_elf_end;
449 450
	}

451 452
	err = -1;

453
	if (shdr_rel_plt.sh_link != dynsym_idx)
454
		goto out_elf_end;
455

456 457
	if (elf_section_by_name(elf, &ehdr, &shdr_plt, ".plt", NULL) == NULL)
		goto out_elf_end;
458 459 460 461 462 463 464

	/*
	 * Fetch the relocation section to find the indexes to the GOT
	 * and the symbols in the .dynsym they refer to.
	 */
	reldata = elf_getdata(scn_plt_rel, NULL);
	if (reldata == NULL)
465
		goto out_elf_end;
466 467 468

	syms = elf_getdata(scn_dynsym, NULL);
	if (syms == NULL)
469
		goto out_elf_end;
470

471
	scn_symstrs = elf_getscn(elf, shdr_dynsym.sh_link);
472
	if (scn_symstrs == NULL)
473
		goto out_elf_end;
474 475 476

	symstrs = elf_getdata(scn_symstrs, NULL);
	if (symstrs == NULL)
477
		goto out_elf_end;
478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493

	nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize;
	plt_offset = shdr_plt.sh_offset;

	if (shdr_rel_plt.sh_type == SHT_RELA) {
		GElf_Rela pos_mem, *pos;

		elf_section__for_each_rela(reldata, pos, pos_mem, idx,
					   nr_rel_entries) {
			symidx = GELF_R_SYM(pos->r_info);
			plt_offset += shdr_plt.sh_entsize;
			gelf_getsym(syms, symidx, &sym);
			snprintf(sympltname, sizeof(sympltname),
				 "%s@plt", elf_sym__name(&sym, symstrs));

			f = symbol__new(plt_offset, shdr_plt.sh_entsize,
494
					sympltname, self->sym_priv_size, 0, verbose);
495
			if (!f)
496
				goto out_elf_end;
497 498 499 500 501 502 503 504 505 506 507 508 509 510 511

			dso__insert_symbol(self, f);
			++nr;
		}
	} else if (shdr_rel_plt.sh_type == SHT_REL) {
		GElf_Rel pos_mem, *pos;
		elf_section__for_each_rel(reldata, pos, pos_mem, idx,
					  nr_rel_entries) {
			symidx = GELF_R_SYM(pos->r_info);
			plt_offset += shdr_plt.sh_entsize;
			gelf_getsym(syms, symidx, &sym);
			snprintf(sympltname, sizeof(sympltname),
				 "%s@plt", elf_sym__name(&sym, symstrs));

			f = symbol__new(plt_offset, shdr_plt.sh_entsize,
512
					sympltname, self->sym_priv_size, 0, verbose);
513
			if (!f)
514
				goto out_elf_end;
515 516 517 518 519 520

			dso__insert_symbol(self, f);
			++nr;
		}
	}

521 522 523 524 525 526 527 528 529 530 531 532
	err = 0;
out_elf_end:
	elf_end(elf);
out_close:
	close(fd);

	if (err == 0)
		return nr;
out:
	fprintf(stderr, "%s: problems reading %s PLT info.\n",
		__func__, self->name);
	return 0;
533 534
}

535
static int dso__load_sym(struct dso *self, int fd, const char *name,
536
			 symbol_filter_t filter, int verbose, struct module *mod)
537
{
538
	Elf_Data *symstrs, *secstrs;
539 540 541 542 543 544 545
	uint32_t nr_syms;
	int err = -1;
	uint32_t index;
	GElf_Ehdr ehdr;
	GElf_Shdr shdr;
	Elf_Data *syms;
	GElf_Sym sym;
546
	Elf_Scn *sec, *sec_strndx;
547
	Elf *elf;
548
	int nr = 0, kernel = !strcmp("[kernel]", self->name);
549 550 551

	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
	if (elf == NULL) {
552 553 554
		if (verbose)
			fprintf(stderr, "%s: cannot read %s ELF file.\n",
				__func__, name);
555 556 557 558
		goto out_close;
	}

	if (gelf_getehdr(elf, &ehdr) == NULL) {
559 560
		if (verbose)
			fprintf(stderr, "%s: cannot get elf header.\n", __func__);
561 562 563 564
		goto out_elf_end;
	}

	sec = elf_section_by_name(elf, &ehdr, &shdr, ".symtab", NULL);
565
	if (sec == NULL) {
566 567
		sec = elf_section_by_name(elf, &ehdr, &shdr, ".dynsym", NULL);
		if (sec == NULL)
568 569
			goto out_elf_end;
	}
570 571 572 573 574 575 576 577 578 579 580 581 582

	syms = elf_getdata(sec, NULL);
	if (syms == NULL)
		goto out_elf_end;

	sec = elf_getscn(elf, shdr.sh_link);
	if (sec == NULL)
		goto out_elf_end;

	symstrs = elf_getdata(sec, NULL);
	if (symstrs == NULL)
		goto out_elf_end;

583 584 585 586 587
	sec_strndx = elf_getscn(elf, ehdr.e_shstrndx);
	if (sec_strndx == NULL)
		goto out_elf_end;

	secstrs = elf_getdata(sec_strndx, NULL);
S
Stoyan Gaydarov 已提交
588
	if (secstrs == NULL)
589 590
		goto out_elf_end;

591 592
	nr_syms = shdr.sh_size / shdr.sh_entsize;

593
	memset(&sym, 0, sizeof(sym));
594 595
	if (!kernel) {
		self->adjust_symbols = (ehdr.e_type == ET_EXEC ||
596 597 598
				elf_section_by_name(elf, &ehdr, &shdr,
						     ".gnu.prelink_undo",
						     NULL) != NULL);
599 600
	} else self->adjust_symbols = 0;

601 602
	elf_symtab__for_each_symbol(syms, nr_syms, index, sym) {
		struct symbol *f;
603 604
		const char *name;
		char *demangled;
605
		u64 obj_start;
606 607 608
		struct section *section = NULL;
		int is_label = elf_sym__is_label(&sym);
		const char *section_name;
609

610
		if (!is_label && !elf_sym__is_function(&sym))
611 612 613 614 615 616 617
			continue;

		sec = elf_getscn(elf, sym.st_shndx);
		if (!sec)
			goto out_elf_end;

		gelf_getshdr(sec, &shdr);
618 619 620 621 622

		if (is_label && !elf_sec__is_text(&shdr, secstrs))
			continue;

		section_name = elf_sec__name(&shdr, secstrs);
623 624
		obj_start = sym.st_value;

625
		if (self->adjust_symbols) {
626 627 628
			if (verbose >= 2)
				printf("adjusting symbol: st_value: %Lx sh_addr: %Lx sh_offset: %Lx\n",
					(u64)sym.st_value, (u64)shdr.sh_addr, (u64)shdr.sh_offset);
629

630 631
			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
		}
632

633 634 635 636 637 638 639 640 641 642
		if (mod) {
			section = mod->sections->find_section(mod->sections, section_name);
			if (section)
				sym.st_value += section->vma;
			else {
				fprintf(stderr, "dso__load_sym() module %s lookup of %s failed\n",
					mod->name, section_name);
				goto out_elf_end;
			}
		}
643 644 645 646 647 648 649 650 651
		/*
		 * We need to figure out if the object was created from C++ sources
		 * DWARF DW_compile_unit has this, but we don't always have access
		 * to it...
		 */
		name = elf_sym__name(&sym, symstrs);
		demangled = bfd_demangle(NULL, name, DMGL_PARAMS | DMGL_ANSI);
		if (demangled != NULL)
			name = demangled;
652

653
		f = symbol__new(sym.st_value, sym.st_size, name,
654
				self->sym_priv_size, obj_start, verbose);
655
		free(demangled);
656 657 658
		if (!f)
			goto out_elf_end;

659 660 661
		if (filter && filter(self, f))
			symbol__delete(f, self->sym_priv_size);
		else {
662
			f->module = mod;
663 664 665
			dso__insert_symbol(self, f);
			nr++;
		}
666 667 668 669 670 671 672 673 674
	}

	err = nr;
out_elf_end:
	elf_end(elf);
out_close:
	return err;
}

675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723
#define BUILD_ID_SIZE 128

static char *dso__read_build_id(struct dso *self, int verbose)
{
	int i;
	GElf_Ehdr ehdr;
	GElf_Shdr shdr;
	Elf_Data *build_id_data;
	Elf_Scn *sec;
	char *build_id = NULL, *bid;
	unsigned char *raw;
	Elf *elf;
	int fd = open(self->name, O_RDONLY);

	if (fd < 0)
		goto out;

	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
	if (elf == NULL) {
		if (verbose)
			fprintf(stderr, "%s: cannot read %s ELF file.\n",
				__func__, self->name);
		goto out_close;
	}

	if (gelf_getehdr(elf, &ehdr) == NULL) {
		if (verbose)
			fprintf(stderr, "%s: cannot get elf header.\n", __func__);
		goto out_elf_end;
	}

	sec = elf_section_by_name(elf, &ehdr, &shdr, ".note.gnu.build-id", NULL);
	if (sec == NULL)
		goto out_elf_end;

	build_id_data = elf_getdata(sec, NULL);
	if (build_id_data == NULL)
		goto out_elf_end;
	build_id = malloc(BUILD_ID_SIZE);
	if (build_id == NULL)
		goto out_elf_end;
	raw = build_id_data->d_buf + 16;
	bid = build_id;

	for (i = 0; i < 20; ++i) {
		sprintf(bid, "%02x", *raw);
		++raw;
		bid += 2;
	}
724
	if (verbose >= 2)
725 726 727 728 729 730 731 732 733
		printf("%s(%s): %s\n", __func__, self->name, build_id);
out_elf_end:
	elf_end(elf);
out_close:
	close(fd);
out:
	return build_id;
}

734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749
char dso__symtab_origin(const struct dso *self)
{
	static const char origin[] = {
		[DSO__ORIG_KERNEL] =   'k',
		[DSO__ORIG_JAVA_JIT] = 'j',
		[DSO__ORIG_FEDORA] =   'f',
		[DSO__ORIG_UBUNTU] =   'u',
		[DSO__ORIG_BUILDID] =  'b',
		[DSO__ORIG_DSO] =      'd',
	};

	if (self == NULL || self->origin == DSO__ORIG_NOT_FOUND)
		return '!';
	return origin[self->origin];
}

750
int dso__load(struct dso *self, symbol_filter_t filter, int verbose)
751
{
752 753
	int size = PATH_MAX;
	char *name = malloc(size), *build_id = NULL;
754 755 756 757 758 759
	int ret = -1;
	int fd;

	if (!name)
		return -1;

760
	self->adjust_symbols = 0;
761

762 763 764 765 766 767 768 769
	if (strncmp(self->name, "/tmp/perf-", 10) == 0) {
		ret = dso__load_perf_map(self, filter, verbose);
		self->origin = ret > 0 ? DSO__ORIG_JAVA_JIT :
					 DSO__ORIG_NOT_FOUND;
		return ret;
	}

	self->origin = DSO__ORIG_FEDORA - 1;
770

771 772
more:
	do {
773 774 775
		self->origin++;
		switch (self->origin) {
		case DSO__ORIG_FEDORA:
776 777
			snprintf(name, size, "/usr/lib/debug%s.debug", self->name);
			break;
778
		case DSO__ORIG_UBUNTU:
779 780
			snprintf(name, size, "/usr/lib/debug%s", self->name);
			break;
781
		case DSO__ORIG_BUILDID:
782 783 784 785 786 787 788 789
			build_id = dso__read_build_id(self, verbose);
			if (build_id != NULL) {
				snprintf(name, size,
					 "/usr/lib/debug/.build-id/%.2s/%s.debug",
					build_id, build_id + 2);
				free(build_id);
				break;
			}
790
			self->origin++;
791
			/* Fall thru */
792
		case DSO__ORIG_DSO:
793 794 795 796 797 798 799 800 801 802
			snprintf(name, size, "%s", self->name);
			break;

		default:
			goto out;
		}

		fd = open(name, O_RDONLY);
	} while (fd < 0);

803
	ret = dso__load_sym(self, fd, name, filter, verbose, NULL);
804 805 806 807 808 809 810 811
	close(fd);

	/*
	 * Some people seem to have debuginfo files _WITHOUT_ debug info!?!?
	 */
	if (!ret)
		goto more;

812 813 814 815 816
	if (ret > 0) {
		int nr_plt = dso__synthesize_plt_symbols(self, verbose);
		if (nr_plt > 0)
			ret += nr_plt;
	}
817 818 819 820 821
out:
	free(name);
	return ret;
}

822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901
static int dso__load_module(struct dso *self, struct mod_dso *mods, const char *name,
			     symbol_filter_t filter, int verbose)
{
	struct module *mod = mod_dso__find_module(mods, name);
	int err = 0, fd;

	if (mod == NULL || !mod->active)
		return err;

	fd = open(mod->path, O_RDONLY);

	if (fd < 0)
		return err;

	err = dso__load_sym(self, fd, name, filter, verbose, mod);
	close(fd);

	return err;
}

int dso__load_modules(struct dso *self, symbol_filter_t filter, int verbose)
{
	struct mod_dso *mods = mod_dso__new_dso("modules");
	struct module *pos;
	struct rb_node *next;
	int err;

	err = mod_dso__load_modules(mods);

	if (err <= 0)
		return err;

	/*
	 * Iterate over modules, and load active symbols.
	 */
	next = rb_first(&mods->mods);
	while (next) {
		pos = rb_entry(next, struct module, rb_node);
		err = dso__load_module(self, mods, pos->name, filter, verbose);

		if (err < 0)
			break;

		next = rb_next(&pos->rb_node);
	}

	if (err < 0) {
		mod_dso__delete_modules(mods);
		mod_dso__delete_self(mods);
	}

	return err;
}

static inline void dso__fill_symbol_holes(struct dso *self)
{
	struct symbol *prev = NULL;
	struct rb_node *nd;

	for (nd = rb_last(&self->syms); nd; nd = rb_prev(nd)) {
		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);

		if (prev) {
			u64 hole = 0;
			int alias = pos->start == prev->start;

			if (!alias)
				hole = prev->start - pos->end - 1;

			if (hole || alias) {
				if (alias)
					pos->end = prev->end;
				else if (hole)
					pos->end = prev->start - 1;
			}
		}
		prev = pos;
	}
}

902
static int dso__load_vmlinux(struct dso *self, const char *vmlinux,
903
			     symbol_filter_t filter, int verbose)
904 905 906 907 908 909
{
	int err, fd = open(vmlinux, O_RDONLY);

	if (fd < 0)
		return -1;

910 911 912 913 914
	err = dso__load_sym(self, fd, vmlinux, filter, verbose, NULL);

	if (err > 0)
		dso__fill_symbol_holes(self);

915 916 917 918 919
	close(fd);

	return err;
}

920
int dso__load_kernel(struct dso *self, const char *vmlinux,
921
		     symbol_filter_t filter, int verbose, int modules)
922 923 924
{
	int err = -1;

925
	if (vmlinux) {
926
		err = dso__load_vmlinux(self, vmlinux, filter, verbose);
927 928 929
		if (err > 0 && modules)
			err = dso__load_modules(self, filter, verbose);
	}
930

931
	if (err <= 0)
932
		err = dso__load_kallsyms(self, filter, verbose);
933

934 935 936
	if (err > 0)
		self->origin = DSO__ORIG_KERNEL;

937 938 939
	return err;
}

940 941 942 943
void symbol__init(void)
{
	elf_version(EV_CURRENT);
}