symbol-elf.c 40.0 KB
Newer Older
1 2 3 4 5 6 7 8
#include <fcntl.h>
#include <stdio.h>
#include <errno.h>
#include <string.h>
#include <unistd.h>
#include <inttypes.h>

#include "symbol.h"
9
#include "machine.h"
10
#include "vdso.h"
11
#include <symbol/kallsyms.h>
12 13
#include "debug.h"

14 15 16 17 18
#ifndef EM_AARCH64
#define EM_AARCH64	183  /* ARM 64 bit */
#endif


19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39
#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
extern char *cplus_demangle(const char *, int);

static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i)
{
	return cplus_demangle(c, i);
}
#else
#ifdef NO_DEMANGLE
static inline char *bfd_demangle(void __maybe_unused *v,
				 const char __maybe_unused *c,
				 int __maybe_unused i)
{
	return NULL;
}
#else
#define PACKAGE 'perf'
#include <bfd.h>
#endif
#endif

40
#ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
41
int elf_getphdrnum(Elf *elf, size_t *dst)
42 43 44 45 46 47 48 49 50 51 52 53 54 55
{
	GElf_Ehdr gehdr;
	GElf_Ehdr *ehdr;

	ehdr = gelf_getehdr(elf, &gehdr);
	if (!ehdr)
		return -1;

	*dst = ehdr->e_phnum;

	return 0;
}
#endif

56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76
#ifndef NT_GNU_BUILD_ID
#define NT_GNU_BUILD_ID 3
#endif

/**
 * elf_symtab__for_each_symbol - iterate thru all the symbols
 *
 * @syms: struct elf_symtab instance to iterate
 * @idx: uint32_t idx
 * @sym: GElf_Sym iterator
 */
#define elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) \
	for (idx = 0, gelf_getsym(syms, idx, &sym);\
	     idx < nr_syms; \
	     idx++, gelf_getsym(syms, idx, &sym))

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

77 78 79 80
#ifndef STT_GNU_IFUNC
#define STT_GNU_IFUNC 10
#endif

81 82
static inline int elf_sym__is_function(const GElf_Sym *sym)
{
83 84
	return (elf_sym__type(sym) == STT_FUNC ||
		elf_sym__type(sym) == STT_GNU_IFUNC) &&
85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171
	       sym->st_name != 0 &&
	       sym->st_shndx != SHN_UNDEF;
}

static inline bool elf_sym__is_object(const GElf_Sym *sym)
{
	return elf_sym__type(sym) == STT_OBJECT &&
		sym->st_name != 0 &&
		sym->st_shndx != SHN_UNDEF;
}

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 bool elf_sym__is_a(GElf_Sym *sym, enum map_type type)
{
	switch (type) {
	case MAP__FUNCTION:
		return elf_sym__is_function(sym);
	case MAP__VARIABLE:
		return elf_sym__is_object(sym);
	default:
		return false;
	}
}

static inline const char *elf_sym__name(const GElf_Sym *sym,
					const Elf_Data *symstrs)
{
	return symstrs->d_buf + sym->st_name;
}

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;
}

static inline bool elf_sec__is_data(const GElf_Shdr *shdr,
				    const Elf_Data *secstrs)
{
	return strstr(elf_sec__name(shdr, secstrs), "data") != NULL;
}

static bool elf_sec__is_a(GElf_Shdr *shdr, Elf_Data *secstrs,
			  enum map_type type)
{
	switch (type) {
	case MAP__FUNCTION:
		return elf_sec__is_text(shdr, secstrs);
	case MAP__VARIABLE:
		return elf_sec__is_data(shdr, secstrs);
	default:
		return false;
	}
}

static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
{
	Elf_Scn *sec = NULL;
	GElf_Shdr shdr;
	size_t cnt = 1;

	while ((sec = elf_nextscn(elf, sec)) != NULL) {
		gelf_getshdr(sec, &shdr);

		if ((addr >= shdr.sh_addr) &&
		    (addr < (shdr.sh_addr + shdr.sh_size)))
			return cnt;

		++cnt;
	}

	return -1;
}

172 173
Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
			     GElf_Shdr *shp, const char *name, size_t *idx)
174 175 176 177
{
	Elf_Scn *sec = NULL;
	size_t cnt = 1;

178 179 180 181
	/* Elf is corrupted/truncated, avoid calling elf_strptr. */
	if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL))
		return NULL;

182 183 184 185 186
	while ((sec = elf_nextscn(elf, sec)) != NULL) {
		char *str;

		gelf_getshdr(sec, shp);
		str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
187
		if (str && !strcmp(name, str)) {
188 189
			if (idx)
				*idx = cnt;
190
			return sec;
191 192 193 194
		}
		++cnt;
	}

195
	return NULL;
196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214
}

#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))

/*
 * 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).
 */
215
int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map,
216 217 218 219 220 221 222 223 224 225 226 227 228 229
				symbol_filter_t filter)
{
	uint32_t nr_rel_entries, idx;
	GElf_Sym sym;
	u64 plt_offset;
	GElf_Shdr shdr_plt;
	struct symbol *f;
	GElf_Shdr shdr_rel_plt, shdr_dynsym;
	Elf_Data *reldata, *syms, *symstrs;
	Elf_Scn *scn_plt_rel, *scn_symstrs, *scn_dynsym;
	size_t dynsym_idx;
	GElf_Ehdr ehdr;
	char sympltname[1024];
	Elf *elf;
230
	int nr = 0, symidx, err = 0;
231

232 233 234
	if (!ss->dynsym)
		return 0;

235 236
	elf = ss->elf;
	ehdr = ss->ehdr;
237

238 239 240
	scn_dynsym = ss->dynsym;
	shdr_dynsym = ss->dynshdr;
	dynsym_idx = ss->dynsym_idx;
241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281

	if (scn_dynsym == NULL)
		goto out_elf_end;

	scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt,
					  ".rela.plt", NULL);
	if (scn_plt_rel == NULL) {
		scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt,
						  ".rel.plt", NULL);
		if (scn_plt_rel == NULL)
			goto out_elf_end;
	}

	err = -1;

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

	if (elf_section_by_name(elf, &ehdr, &shdr_plt, ".plt", NULL) == NULL)
		goto out_elf_end;

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

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

	scn_symstrs = elf_getscn(elf, shdr_dynsym.sh_link);
	if (scn_symstrs == NULL)
		goto out_elf_end;

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

282 283 284
	if (symstrs->d_size == 0)
		goto out_elf_end;

285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522
	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,
					STB_GLOBAL, sympltname);
			if (!f)
				goto out_elf_end;

			if (filter && filter(map, f))
				symbol__delete(f);
			else {
				symbols__insert(&dso->symbols[map->type], 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,
					STB_GLOBAL, sympltname);
			if (!f)
				goto out_elf_end;

			if (filter && filter(map, f))
				symbol__delete(f);
			else {
				symbols__insert(&dso->symbols[map->type], f);
				++nr;
			}
		}
	}

	err = 0;
out_elf_end:
	if (err == 0)
		return nr;
	pr_debug("%s: problems reading %s PLT info.\n",
		 __func__, dso->long_name);
	return 0;
}

/*
 * Align offset to 4 bytes as needed for note name and descriptor data.
 */
#define NOTE_ALIGN(n) (((n) + 3) & -4U)

static int elf_read_build_id(Elf *elf, void *bf, size_t size)
{
	int err = -1;
	GElf_Ehdr ehdr;
	GElf_Shdr shdr;
	Elf_Data *data;
	Elf_Scn *sec;
	Elf_Kind ek;
	void *ptr;

	if (size < BUILD_ID_SIZE)
		goto out;

	ek = elf_kind(elf);
	if (ek != ELF_K_ELF)
		goto out;

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

	/*
	 * Check following sections for notes:
	 *   '.note.gnu.build-id'
	 *   '.notes'
	 *   '.note' (VDSO specific)
	 */
	do {
		sec = elf_section_by_name(elf, &ehdr, &shdr,
					  ".note.gnu.build-id", NULL);
		if (sec)
			break;

		sec = elf_section_by_name(elf, &ehdr, &shdr,
					  ".notes", NULL);
		if (sec)
			break;

		sec = elf_section_by_name(elf, &ehdr, &shdr,
					  ".note", NULL);
		if (sec)
			break;

		return err;

	} while (0);

	data = elf_getdata(sec, NULL);
	if (data == NULL)
		goto out;

	ptr = data->d_buf;
	while (ptr < (data->d_buf + data->d_size)) {
		GElf_Nhdr *nhdr = ptr;
		size_t namesz = NOTE_ALIGN(nhdr->n_namesz),
		       descsz = NOTE_ALIGN(nhdr->n_descsz);
		const char *name;

		ptr += sizeof(*nhdr);
		name = ptr;
		ptr += namesz;
		if (nhdr->n_type == NT_GNU_BUILD_ID &&
		    nhdr->n_namesz == sizeof("GNU")) {
			if (memcmp(name, "GNU", sizeof("GNU")) == 0) {
				size_t sz = min(size, descsz);
				memcpy(bf, ptr, sz);
				memset(bf + sz, 0, size - sz);
				err = descsz;
				break;
			}
		}
		ptr += descsz;
	}

out:
	return err;
}

int filename__read_build_id(const char *filename, void *bf, size_t size)
{
	int fd, err = -1;
	Elf *elf;

	if (size < BUILD_ID_SIZE)
		goto out;

	fd = open(filename, O_RDONLY);
	if (fd < 0)
		goto out;

	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
	if (elf == NULL) {
		pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename);
		goto out_close;
	}

	err = elf_read_build_id(elf, bf, size);

	elf_end(elf);
out_close:
	close(fd);
out:
	return err;
}

int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
{
	int fd, err = -1;

	if (size < BUILD_ID_SIZE)
		goto out;

	fd = open(filename, O_RDONLY);
	if (fd < 0)
		goto out;

	while (1) {
		char bf[BUFSIZ];
		GElf_Nhdr nhdr;
		size_t namesz, descsz;

		if (read(fd, &nhdr, sizeof(nhdr)) != sizeof(nhdr))
			break;

		namesz = NOTE_ALIGN(nhdr.n_namesz);
		descsz = NOTE_ALIGN(nhdr.n_descsz);
		if (nhdr.n_type == NT_GNU_BUILD_ID &&
		    nhdr.n_namesz == sizeof("GNU")) {
			if (read(fd, bf, namesz) != (ssize_t)namesz)
				break;
			if (memcmp(bf, "GNU", sizeof("GNU")) == 0) {
				size_t sz = min(descsz, size);
				if (read(fd, build_id, sz) == (ssize_t)sz) {
					memset(build_id + sz, 0, size - sz);
					err = 0;
					break;
				}
			} else if (read(fd, bf, descsz) != (ssize_t)descsz)
				break;
		} else {
			int n = namesz + descsz;
			if (read(fd, bf, n) != n)
				break;
		}
	}
	close(fd);
out:
	return err;
}

int filename__read_debuglink(const char *filename, char *debuglink,
			     size_t size)
{
	int fd, err = -1;
	Elf *elf;
	GElf_Ehdr ehdr;
	GElf_Shdr shdr;
	Elf_Data *data;
	Elf_Scn *sec;
	Elf_Kind ek;

	fd = open(filename, O_RDONLY);
	if (fd < 0)
		goto out;

	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
	if (elf == NULL) {
		pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename);
		goto out_close;
	}

	ek = elf_kind(elf);
	if (ek != ELF_K_ELF)
523
		goto out_elf_end;
524 525 526

	if (gelf_getehdr(elf, &ehdr) == NULL) {
		pr_err("%s: cannot get elf header.\n", __func__);
527
		goto out_elf_end;
528 529 530 531 532
	}

	sec = elf_section_by_name(elf, &ehdr, &shdr,
				  ".gnu_debuglink", NULL);
	if (sec == NULL)
533
		goto out_elf_end;
534 535 536

	data = elf_getdata(sec, NULL);
	if (data == NULL)
537
		goto out_elf_end;
538 539 540 541

	/* the start of this section is a zero-terminated string */
	strncpy(debuglink, data->d_buf, size);

542 543
	err = 0;

544
out_elf_end:
545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578
	elf_end(elf);
out_close:
	close(fd);
out:
	return err;
}

static int dso__swap_init(struct dso *dso, unsigned char eidata)
{
	static unsigned int const endian = 1;

	dso->needs_swap = DSO_SWAP__NO;

	switch (eidata) {
	case ELFDATA2LSB:
		/* We are big endian, DSO is little endian. */
		if (*(unsigned char const *)&endian != 1)
			dso->needs_swap = DSO_SWAP__YES;
		break;

	case ELFDATA2MSB:
		/* We are little endian, DSO is big endian. */
		if (*(unsigned char const *)&endian != 0)
			dso->needs_swap = DSO_SWAP__YES;
		break;

	default:
		pr_err("unrecognized DSO data encoding %d\n", eidata);
		return -EINVAL;
	}

	return 0;
}

579 580 581
static int decompress_kmodule(struct dso *dso, const char *name,
			      enum dso_binary_type type)
{
582
	int fd = -1;
583
	char tmpbuf[] = "/tmp/perf-kmod-XXXXXX";
584
	struct kmod_path m;
585

586 587 588
	if (type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP &&
	    type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP &&
	    type != DSO_BINARY_TYPE__BUILD_ID_CACHE)
589 590
		return -1;

591 592 593 594 595
	if (type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
		name = dso->long_name;

	if (kmod_path__parse_ext(&m, name) || !m.comp)
		return -1;
596 597

	fd = mkstemp(tmpbuf);
598 599
	if (fd < 0) {
		dso->load_errno = errno;
600
		goto out;
601
	}
602

603
	if (!decompress_to_file(m.ext, name, fd)) {
604
		dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
605 606 607 608 609 610
		close(fd);
		fd = -1;
	}

	unlink(tmpbuf);

611 612
out:
	free(m.ext);
613 614 615
	return fd;
}

616 617 618 619 620
bool symsrc__possibly_runtime(struct symsrc *ss)
{
	return ss->dynsym || ss->opdsec;
}

621 622 623 624
bool symsrc__has_symtab(struct symsrc *ss)
{
	return ss->symtab != NULL;
}
625 626 627

void symsrc__destroy(struct symsrc *ss)
{
628
	zfree(&ss->name);
629 630 631 632
	elf_end(ss->elf);
	close(ss->fd);
}

633 634 635 636 637
bool __weak elf__needs_adjust_symbols(GElf_Ehdr ehdr)
{
	return ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL;
}

638 639
int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
		 enum dso_binary_type type)
640 641 642 643
{
	int err = -1;
	GElf_Ehdr ehdr;
	Elf *elf;
644 645
	int fd;

646
	if (dso__needs_decompress(dso)) {
647
		fd = decompress_kmodule(dso, name, type);
648 649 650
		if (fd < 0)
			return -1;
	} else {
651
		fd = open(name, O_RDONLY);
652 653 654 655 656
		if (fd < 0) {
			dso->load_errno = errno;
			return -1;
		}
	}
657 658 659 660

	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
	if (elf == NULL) {
		pr_debug("%s: cannot read %s ELF file.\n", __func__, name);
661
		dso->load_errno = DSO_LOAD_ERRNO__INVALID_ELF;
662 663 664 665
		goto out_close;
	}

	if (gelf_getehdr(elf, &ehdr) == NULL) {
666
		dso->load_errno = DSO_LOAD_ERRNO__INVALID_ELF;
667 668 669 670
		pr_debug("%s: cannot get elf header.\n", __func__);
		goto out_elf_end;
	}

671 672
	if (dso__swap_init(dso, ehdr.e_ident[EI_DATA])) {
		dso->load_errno = DSO_LOAD_ERRNO__INTERNAL_ERROR;
673
		goto out_elf_end;
674
	}
675 676 677 678 679

	/* Always reject images with a mismatched build-id: */
	if (dso->has_build_id) {
		u8 build_id[BUILD_ID_SIZE];

680 681
		if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0) {
			dso->load_errno = DSO_LOAD_ERRNO__CANNOT_READ_BUILDID;
682
			goto out_elf_end;
683
		}
684

685
		if (!dso__build_id_equal(dso, build_id)) {
686
			pr_debug("%s: build id mismatch for %s.\n", __func__, name);
687
			dso->load_errno = DSO_LOAD_ERRNO__MISMATCHING_BUILDID;
688
			goto out_elf_end;
689
		}
690 691
	}

692 693
	ss->is_64_bit = (gelf_getclass(elf) == ELFCLASS64);

694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713
	ss->symtab = elf_section_by_name(elf, &ehdr, &ss->symshdr, ".symtab",
			NULL);
	if (ss->symshdr.sh_type != SHT_SYMTAB)
		ss->symtab = NULL;

	ss->dynsym_idx = 0;
	ss->dynsym = elf_section_by_name(elf, &ehdr, &ss->dynshdr, ".dynsym",
			&ss->dynsym_idx);
	if (ss->dynshdr.sh_type != SHT_DYNSYM)
		ss->dynsym = NULL;

	ss->opdidx = 0;
	ss->opdsec = elf_section_by_name(elf, &ehdr, &ss->opdshdr, ".opd",
			&ss->opdidx);
	if (ss->opdshdr.sh_type != SHT_PROGBITS)
		ss->opdsec = NULL;

	if (dso->kernel == DSO_TYPE_USER) {
		GElf_Shdr shdr;
		ss->adjust_symbols = (ehdr.e_type == ET_EXEC ||
714
				ehdr.e_type == ET_REL ||
715
				dso__is_vdso(dso) ||
716 717 718 719
				elf_section_by_name(elf, &ehdr, &shdr,
						     ".gnu.prelink_undo",
						     NULL) != NULL);
	} else {
720
		ss->adjust_symbols = elf__needs_adjust_symbols(ehdr);
721 722 723
	}

	ss->name   = strdup(name);
724 725
	if (!ss->name) {
		dso->load_errno = errno;
726
		goto out_elf_end;
727
	}
728 729 730 731 732 733 734 735 736 737 738 739 740 741 742

	ss->elf    = elf;
	ss->fd     = fd;
	ss->ehdr   = ehdr;
	ss->type   = type;

	return 0;

out_elf_end:
	elf_end(elf);
out_close:
	close(fd);
	return err;
}

743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773
/**
 * ref_reloc_sym_not_found - has kernel relocation symbol been found.
 * @kmap: kernel maps and relocation reference symbol
 *
 * This function returns %true if we are dealing with the kernel maps and the
 * relocation reference symbol has not yet been found.  Otherwise %false is
 * returned.
 */
static bool ref_reloc_sym_not_found(struct kmap *kmap)
{
	return kmap && kmap->ref_reloc_sym && kmap->ref_reloc_sym->name &&
	       !kmap->ref_reloc_sym->unrelocated_addr;
}

/**
 * ref_reloc - kernel relocation offset.
 * @kmap: kernel maps and relocation reference symbol
 *
 * This function returns the offset of kernel addresses as determined by using
 * the relocation reference symbol i.e. if the kernel has not been relocated
 * then the return value is zero.
 */
static u64 ref_reloc(struct kmap *kmap)
{
	if (kmap && kmap->ref_reloc_sym &&
	    kmap->ref_reloc_sym->unrelocated_addr)
		return kmap->ref_reloc_sym->addr -
		       kmap->ref_reloc_sym->unrelocated_addr;
	return 0;
}

774 775 776 777 778
static bool want_demangle(bool is_kernel_sym)
{
	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
}

779 780
void __weak arch__elf_sym_adjust(GElf_Sym *sym __maybe_unused) { }

781 782
int dso__load_sym(struct dso *dso, struct map *map,
		  struct symsrc *syms_ss, struct symsrc *runtime_ss,
783
		  symbol_filter_t filter, int kmodule)
784 785
{
	struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL;
786
	struct map_groups *kmaps = kmap ? map__kmaps(map) : NULL;
787 788 789 790 791 792 793
	struct map *curr_map = map;
	struct dso *curr_dso = dso;
	Elf_Data *symstrs, *secstrs;
	uint32_t nr_syms;
	int err = -1;
	uint32_t idx;
	GElf_Ehdr ehdr;
794
	GElf_Shdr shdr;
795 796
	Elf_Data *syms, *opddata = NULL;
	GElf_Sym sym;
797
	Elf_Scn *sec, *sec_strndx;
798 799
	Elf *elf;
	int nr = 0;
800
	bool remap_kernel = false, adjust_kernel_syms = false;
801

802 803 804
	if (kmap && !kmaps)
		return -1;

805
	dso->symtab_type = syms_ss->type;
806
	dso->is_64_bit = syms_ss->is_64_bit;
807 808 809 810 811 812 813 814
	dso->rel = syms_ss->ehdr.e_type == ET_REL;

	/*
	 * Modules may already have symbols from kallsyms, but those symbols
	 * have the wrong values for the dso maps, so remove them.
	 */
	if (kmodule && syms_ss->symtab)
		symbols__delete(&dso->symbols[map->type]);
815

816
	if (!syms_ss->symtab) {
817 818 819 820 821 822 823 824
		/*
		 * If the vmlinux is stripped, fail so we will fall back
		 * to using kallsyms. The vmlinux runtime symbols aren't
		 * of much use.
		 */
		if (dso->kernel)
			goto out_elf_end;

825 826
		syms_ss->symtab  = syms_ss->dynsym;
		syms_ss->symshdr = syms_ss->dynshdr;
827 828
	}

829 830 831 832
	elf = syms_ss->elf;
	ehdr = syms_ss->ehdr;
	sec = syms_ss->symtab;
	shdr = syms_ss->symshdr;
833

834 835
	if (runtime_ss->opdsec)
		opddata = elf_rawdata(runtime_ss->opdsec, NULL);
836 837 838 839 840 841 842 843 844 845 846 847 848

	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;

849
	sec_strndx = elf_getscn(runtime_ss->elf, runtime_ss->ehdr.e_shstrndx);
850 851 852 853 854 855 856 857 858 859
	if (sec_strndx == NULL)
		goto out_elf_end;

	secstrs = elf_getdata(sec_strndx, NULL);
	if (secstrs == NULL)
		goto out_elf_end;

	nr_syms = shdr.sh_size / shdr.sh_entsize;

	memset(&sym, 0, sizeof(sym));
860 861 862 863 864 865 866 867 868 869 870 871

	/*
	 * The kernel relocation symbol is needed in advance in order to adjust
	 * kernel maps correctly.
	 */
	if (ref_reloc_sym_not_found(kmap)) {
		elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
			const char *elf_name = elf_sym__name(&sym, symstrs);

			if (strcmp(elf_name, kmap->ref_reloc_sym->name))
				continue;
			kmap->ref_reloc_sym->unrelocated_addr = sym.st_value;
872 873
			map->reloc = kmap->ref_reloc_sym->addr -
				     kmap->ref_reloc_sym->unrelocated_addr;
874 875 876 877
			break;
		}
	}

878 879 880 881 882 883 884 885 886 887 888
	/*
	 * Handle any relocation of vdso necessary because older kernels
	 * attempted to prelink vdso to its virtual address.
	 */
	if (dso__is_vdso(dso)) {
		GElf_Shdr tshdr;

		if (elf_section_by_name(elf, &ehdr, &tshdr, ".text", NULL))
			map->reloc = map->start - tshdr.sh_addr + tshdr.sh_offset;
	}

889 890 891 892 893 894 895 896 897
	dso->adjust_symbols = runtime_ss->adjust_symbols || ref_reloc(kmap);
	/*
	 * Initial kernel and module mappings do not map to the dso.  For
	 * function mappings, flag the fixups.
	 */
	if (map->type == MAP__FUNCTION && (dso->kernel || kmodule)) {
		remap_kernel = true;
		adjust_kernel_syms = dso->adjust_symbols;
	}
898 899 900 901 902 903
	elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
		struct symbol *f;
		const char *elf_name = elf_sym__name(&sym, symstrs);
		char *demangled = NULL;
		int is_label = elf_sym__is_label(&sym);
		const char *section_name;
904
		bool used_opd = false;
905 906 907 908 909 910 911

		if (!is_label && !elf_sym__is_a(&sym, map->type))
			continue;

		/* Reject ARM ELF "mapping symbols": these aren't unique and
		 * don't identify functions, so will confuse the profile
		 * output: */
912 913 914
		if (ehdr.e_machine == EM_ARM || ehdr.e_machine == EM_AARCH64) {
			if (elf_name[0] == '$' && strchr("adtx", elf_name[1])
			    && (elf_name[2] == '\0' || elf_name[2] == '.'))
915 916 917
				continue;
		}

918 919
		if (runtime_ss->opdsec && sym.st_shndx == runtime_ss->opdidx) {
			u32 offset = sym.st_value - syms_ss->opdshdr.sh_addr;
920 921
			u64 *opd = opddata->d_buf + offset;
			sym.st_value = DSO__SWAP(dso, u64, *opd);
922 923 924
			sym.st_shndx = elf_addr_to_index(runtime_ss->elf,
					sym.st_value);
			used_opd = true;
925
		}
926 927 928 929 930 931 932 933 934 935 936
		/*
		 * When loading symbols in a data mapping, ABS symbols (which
		 * has a value of SHN_ABS in its st_shndx) failed at
		 * elf_getscn().  And it marks the loading as a failure so
		 * already loaded symbols cannot be fixed up.
		 *
		 * I'm not sure what should be done. Just ignore them for now.
		 * - Namhyung Kim
		 */
		if (sym.st_shndx == SHN_ABS)
			continue;
937

938
		sec = elf_getscn(runtime_ss->elf, sym.st_shndx);
939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955
		if (!sec)
			goto out_elf_end;

		gelf_getshdr(sec, &shdr);

		if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type))
			continue;

		section_name = elf_sec__name(&shdr, secstrs);

		/* On ARM, symbols for thumb functions have 1 added to
		 * the symbol address as a flag - remove it */
		if ((ehdr.e_machine == EM_ARM) &&
		    (map->type == MAP__FUNCTION) &&
		    (sym.st_value & 1))
			--sym.st_value;

956 957
		arch__elf_sym_adjust(&sym);

958
		if (dso->kernel || kmodule) {
959 960
			char dso_name[PATH_MAX];

961 962 963 964
			/* Adjust symbol to map to file offset */
			if (adjust_kernel_syms)
				sym.st_value -= shdr.sh_addr - shdr.sh_offset;

965 966 967 968 969 970
			if (strcmp(section_name,
				   (curr_dso->short_name +
				    dso->short_name_len)) == 0)
				goto new_symbol;

			if (strcmp(section_name, ".text") == 0) {
971 972 973 974 975 976 977 978 979 980 981 982 983 984
				/*
				 * The initial kernel mapping is based on
				 * kallsyms and identity maps.  Overwrite it to
				 * map to the kernel dso.
				 */
				if (remap_kernel && dso->kernel) {
					remap_kernel = false;
					map->start = shdr.sh_addr +
						     ref_reloc(kmap);
					map->end = map->start + shdr.sh_size;
					map->pgoff = shdr.sh_offset;
					map->map_ip = map__map_ip;
					map->unmap_ip = map__unmap_ip;
					/* Ensure maps are correctly ordered */
985
					if (kmaps) {
986
						map__get(map);
987 988
						map_groups__remove(kmaps, map);
						map_groups__insert(kmaps, map);
989
						map__put(map);
990
					}
991 992
				}

993 994 995 996 997 998 999 1000 1001 1002
				/*
				 * The initial module mapping is based on
				 * /proc/modules mapped to offset zero.
				 * Overwrite it to map to the module dso.
				 */
				if (remap_kernel && kmodule) {
					remap_kernel = false;
					map->pgoff = shdr.sh_offset;
				}

1003 1004 1005 1006 1007
				curr_map = map;
				curr_dso = dso;
				goto new_symbol;
			}

1008 1009 1010
			if (!kmap)
				goto new_symbol;

1011 1012 1013
			snprintf(dso_name, sizeof(dso_name),
				 "%s%s", dso->short_name, section_name);

1014
			curr_map = map_groups__find_by_name(kmaps, map->type, dso_name);
1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029
			if (curr_map == NULL) {
				u64 start = sym.st_value;

				if (kmodule)
					start += map->start + shdr.sh_offset;

				curr_dso = dso__new(dso_name);
				if (curr_dso == NULL)
					goto out_elf_end;
				curr_dso->kernel = dso->kernel;
				curr_dso->long_name = dso->long_name;
				curr_dso->long_name_len = dso->long_name_len;
				curr_map = map__new2(start, curr_dso,
						     map->type);
				if (curr_map == NULL) {
1030
					dso__put(curr_dso);
1031 1032
					goto out_elf_end;
				}
1033 1034 1035 1036 1037 1038 1039 1040 1041 1042
				if (adjust_kernel_syms) {
					curr_map->start = shdr.sh_addr +
							  ref_reloc(kmap);
					curr_map->end = curr_map->start +
							shdr.sh_size;
					curr_map->pgoff = shdr.sh_offset;
				} else {
					curr_map->map_ip = identity__map_ip;
					curr_map->unmap_ip = identity__map_ip;
				}
1043
				curr_dso->symtab_type = dso->symtab_type;
1044
				map_groups__insert(kmaps, curr_map);
1045
				dsos__add(&map->groups->machine->dsos, curr_dso);
1046 1047 1048 1049 1050 1051 1052
				dso__set_loaded(curr_dso, map->type);
			} else
				curr_dso = curr_map->dso;

			goto new_symbol;
		}

1053 1054
		if ((used_opd && runtime_ss->adjust_symbols)
				|| (!used_opd && syms_ss->adjust_symbols)) {
1055 1056 1057 1058 1059 1060
			pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
				  "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__,
				  (u64)sym.st_value, (u64)shdr.sh_addr,
				  (u64)shdr.sh_offset);
			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
		}
1061
new_symbol:
1062 1063 1064 1065 1066
		/*
		 * 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...
		 */
1067
		if (want_demangle(dso->kernel || kmodule)) {
1068 1069 1070 1071 1072
			int demangle_flags = DMGL_NO_OPTS;
			if (verbose)
				demangle_flags = DMGL_PARAMS | DMGL_ANSI;

			demangled = bfd_demangle(NULL, elf_name, demangle_flags);
1073 1074 1075
			if (demangled != NULL)
				elf_name = demangled;
		}
1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093
		f = symbol__new(sym.st_value, sym.st_size,
				GELF_ST_BIND(sym.st_info), elf_name);
		free(demangled);
		if (!f)
			goto out_elf_end;

		if (filter && filter(curr_map, f))
			symbol__delete(f);
		else {
			symbols__insert(&curr_dso->symbols[curr_map->type], f);
			nr++;
		}
	}

	/*
	 * For misannotated, zeroed, ASM function sizes.
	 */
	if (nr > 0) {
1094 1095
		if (!symbol_conf.allow_aliases)
			symbols__fixup_duplicate(&dso->symbols[map->type]);
1096 1097 1098 1099 1100 1101
		symbols__fixup_end(&dso->symbols[map->type]);
		if (kmap) {
			/*
			 * We need to fixup this here too because we create new
			 * maps here, for things like vsyscall sections.
			 */
1102
			__map_groups__fixup_end(kmaps, map->type);
1103 1104 1105 1106 1107 1108 1109
		}
	}
	err = nr;
out_elf_end:
	return err;
}

1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160
static int elf_read_maps(Elf *elf, bool exe, mapfn_t mapfn, void *data)
{
	GElf_Phdr phdr;
	size_t i, phdrnum;
	int err;
	u64 sz;

	if (elf_getphdrnum(elf, &phdrnum))
		return -1;

	for (i = 0; i < phdrnum; i++) {
		if (gelf_getphdr(elf, i, &phdr) == NULL)
			return -1;
		if (phdr.p_type != PT_LOAD)
			continue;
		if (exe) {
			if (!(phdr.p_flags & PF_X))
				continue;
		} else {
			if (!(phdr.p_flags & PF_R))
				continue;
		}
		sz = min(phdr.p_memsz, phdr.p_filesz);
		if (!sz)
			continue;
		err = mapfn(phdr.p_vaddr, sz, phdr.p_offset, data);
		if (err)
			return err;
	}
	return 0;
}

int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
		    bool *is_64_bit)
{
	int err;
	Elf *elf;

	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
	if (elf == NULL)
		return -1;

	if (is_64_bit)
		*is_64_bit = (gelf_getclass(elf) == ELFCLASS64);

	err = elf_read_maps(elf, exe, mapfn, data);

	elf_end(elf);
	return err;
}

A
Adrian Hunter 已提交
1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193
enum dso_type dso__type_fd(int fd)
{
	enum dso_type dso_type = DSO__TYPE_UNKNOWN;
	GElf_Ehdr ehdr;
	Elf_Kind ek;
	Elf *elf;

	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
	if (elf == NULL)
		goto out;

	ek = elf_kind(elf);
	if (ek != ELF_K_ELF)
		goto out_end;

	if (gelf_getclass(elf) == ELFCLASS64) {
		dso_type = DSO__TYPE_64BIT;
		goto out_end;
	}

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

	if (ehdr.e_machine == EM_X86_64)
		dso_type = DSO__TYPE_X32BIT;
	else
		dso_type = DSO__TYPE_32BIT;
out_end:
	elf_end(elf);
out:
	return dso_type;
}

1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 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
static int copy_bytes(int from, off_t from_offs, int to, off_t to_offs, u64 len)
{
	ssize_t r;
	size_t n;
	int err = -1;
	char *buf = malloc(page_size);

	if (buf == NULL)
		return -1;

	if (lseek(to, to_offs, SEEK_SET) != to_offs)
		goto out;

	if (lseek(from, from_offs, SEEK_SET) != from_offs)
		goto out;

	while (len) {
		n = page_size;
		if (len < n)
			n = len;
		/* Use read because mmap won't work on proc files */
		r = read(from, buf, n);
		if (r < 0)
			goto out;
		if (!r)
			break;
		n = r;
		r = write(to, buf, n);
		if (r < 0)
			goto out;
		if ((size_t)r != n)
			goto out;
		len -= n;
	}

	err = 0;
out:
	free(buf);
	return err;
}

struct kcore {
	int fd;
	int elfclass;
	Elf *elf;
	GElf_Ehdr ehdr;
};

static int kcore__open(struct kcore *kcore, const char *filename)
{
	GElf_Ehdr *ehdr;

	kcore->fd = open(filename, O_RDONLY);
	if (kcore->fd == -1)
		return -1;

	kcore->elf = elf_begin(kcore->fd, ELF_C_READ, NULL);
	if (!kcore->elf)
		goto out_close;

	kcore->elfclass = gelf_getclass(kcore->elf);
	if (kcore->elfclass == ELFCLASSNONE)
		goto out_end;

	ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr);
	if (!ehdr)
		goto out_end;

	return 0;

out_end:
	elf_end(kcore->elf);
out_close:
	close(kcore->fd);
	return -1;
}

static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
		       bool temp)
{
	GElf_Ehdr *ehdr;

	kcore->elfclass = elfclass;

	if (temp)
		kcore->fd = mkstemp(filename);
	else
		kcore->fd = open(filename, O_WRONLY | O_CREAT | O_EXCL, 0400);
	if (kcore->fd == -1)
		return -1;

	kcore->elf = elf_begin(kcore->fd, ELF_C_WRITE, NULL);
	if (!kcore->elf)
		goto out_close;

	if (!gelf_newehdr(kcore->elf, elfclass))
		goto out_end;

	ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr);
	if (!ehdr)
		goto out_end;

	return 0;

out_end:
	elf_end(kcore->elf);
out_close:
	close(kcore->fd);
	unlink(filename);
	return -1;
}

static void kcore__close(struct kcore *kcore)
{
	elf_end(kcore->elf);
	close(kcore->fd);
}

static int kcore__copy_hdr(struct kcore *from, struct kcore *to, size_t count)
{
	GElf_Ehdr *ehdr = &to->ehdr;
	GElf_Ehdr *kehdr = &from->ehdr;

	memcpy(ehdr->e_ident, kehdr->e_ident, EI_NIDENT);
	ehdr->e_type      = kehdr->e_type;
	ehdr->e_machine   = kehdr->e_machine;
	ehdr->e_version   = kehdr->e_version;
	ehdr->e_entry     = 0;
	ehdr->e_shoff     = 0;
	ehdr->e_flags     = kehdr->e_flags;
	ehdr->e_phnum     = count;
	ehdr->e_shentsize = 0;
	ehdr->e_shnum     = 0;
	ehdr->e_shstrndx  = 0;

	if (from->elfclass == ELFCLASS32) {
		ehdr->e_phoff     = sizeof(Elf32_Ehdr);
		ehdr->e_ehsize    = sizeof(Elf32_Ehdr);
		ehdr->e_phentsize = sizeof(Elf32_Phdr);
	} else {
		ehdr->e_phoff     = sizeof(Elf64_Ehdr);
		ehdr->e_ehsize    = sizeof(Elf64_Ehdr);
		ehdr->e_phentsize = sizeof(Elf64_Phdr);
	}

	if (!gelf_update_ehdr(to->elf, ehdr))
		return -1;

	if (!gelf_newphdr(to->elf, count))
		return -1;

	return 0;
}

static int kcore__add_phdr(struct kcore *kcore, int idx, off_t offset,
			   u64 addr, u64 len)
{
	GElf_Phdr gphdr;
	GElf_Phdr *phdr;

	phdr = gelf_getphdr(kcore->elf, idx, &gphdr);
	if (!phdr)
		return -1;

	phdr->p_type	= PT_LOAD;
	phdr->p_flags	= PF_R | PF_W | PF_X;
	phdr->p_offset	= offset;
	phdr->p_vaddr	= addr;
	phdr->p_paddr	= 0;
	phdr->p_filesz	= len;
	phdr->p_memsz	= len;
	phdr->p_align	= page_size;

	if (!gelf_update_phdr(kcore->elf, idx, phdr))
		return -1;

	return 0;
}

static off_t kcore__write(struct kcore *kcore)
{
	return elf_update(kcore->elf, ELF_C_WRITE);
}

1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 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 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 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 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743
struct phdr_data {
	off_t offset;
	u64 addr;
	u64 len;
};

struct kcore_copy_info {
	u64 stext;
	u64 etext;
	u64 first_symbol;
	u64 last_symbol;
	u64 first_module;
	u64 last_module_symbol;
	struct phdr_data kernel_map;
	struct phdr_data modules_map;
};

static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
					u64 start)
{
	struct kcore_copy_info *kci = arg;

	if (!symbol_type__is_a(type, MAP__FUNCTION))
		return 0;

	if (strchr(name, '[')) {
		if (start > kci->last_module_symbol)
			kci->last_module_symbol = start;
		return 0;
	}

	if (!kci->first_symbol || start < kci->first_symbol)
		kci->first_symbol = start;

	if (!kci->last_symbol || start > kci->last_symbol)
		kci->last_symbol = start;

	if (!strcmp(name, "_stext")) {
		kci->stext = start;
		return 0;
	}

	if (!strcmp(name, "_etext")) {
		kci->etext = start;
		return 0;
	}

	return 0;
}

static int kcore_copy__parse_kallsyms(struct kcore_copy_info *kci,
				      const char *dir)
{
	char kallsyms_filename[PATH_MAX];

	scnprintf(kallsyms_filename, PATH_MAX, "%s/kallsyms", dir);

	if (symbol__restricted_filename(kallsyms_filename, "/proc/kallsyms"))
		return -1;

	if (kallsyms__parse(kallsyms_filename, kci,
			    kcore_copy__process_kallsyms) < 0)
		return -1;

	return 0;
}

static int kcore_copy__process_modules(void *arg,
				       const char *name __maybe_unused,
				       u64 start)
{
	struct kcore_copy_info *kci = arg;

	if (!kci->first_module || start < kci->first_module)
		kci->first_module = start;

	return 0;
}

static int kcore_copy__parse_modules(struct kcore_copy_info *kci,
				     const char *dir)
{
	char modules_filename[PATH_MAX];

	scnprintf(modules_filename, PATH_MAX, "%s/modules", dir);

	if (symbol__restricted_filename(modules_filename, "/proc/modules"))
		return -1;

	if (modules__parse(modules_filename, kci,
			   kcore_copy__process_modules) < 0)
		return -1;

	return 0;
}

static void kcore_copy__map(struct phdr_data *p, u64 start, u64 end, u64 pgoff,
			    u64 s, u64 e)
{
	if (p->addr || s < start || s >= end)
		return;

	p->addr = s;
	p->offset = (s - start) + pgoff;
	p->len = e < end ? e - s : end - s;
}

static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data)
{
	struct kcore_copy_info *kci = data;
	u64 end = start + len;

	kcore_copy__map(&kci->kernel_map, start, end, pgoff, kci->stext,
			kci->etext);

	kcore_copy__map(&kci->modules_map, start, end, pgoff, kci->first_module,
			kci->last_module_symbol);

	return 0;
}

static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf)
{
	if (elf_read_maps(elf, true, kcore_copy__read_map, kci) < 0)
		return -1;

	return 0;
}

static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
				 Elf *elf)
{
	if (kcore_copy__parse_kallsyms(kci, dir))
		return -1;

	if (kcore_copy__parse_modules(kci, dir))
		return -1;

	if (kci->stext)
		kci->stext = round_down(kci->stext, page_size);
	else
		kci->stext = round_down(kci->first_symbol, page_size);

	if (kci->etext) {
		kci->etext = round_up(kci->etext, page_size);
	} else if (kci->last_symbol) {
		kci->etext = round_up(kci->last_symbol, page_size);
		kci->etext += page_size;
	}

	kci->first_module = round_down(kci->first_module, page_size);

	if (kci->last_module_symbol) {
		kci->last_module_symbol = round_up(kci->last_module_symbol,
						   page_size);
		kci->last_module_symbol += page_size;
	}

	if (!kci->stext || !kci->etext)
		return -1;

	if (kci->first_module && !kci->last_module_symbol)
		return -1;

	return kcore_copy__read_maps(kci, elf);
}

static int kcore_copy__copy_file(const char *from_dir, const char *to_dir,
				 const char *name)
{
	char from_filename[PATH_MAX];
	char to_filename[PATH_MAX];

	scnprintf(from_filename, PATH_MAX, "%s/%s", from_dir, name);
	scnprintf(to_filename, PATH_MAX, "%s/%s", to_dir, name);

	return copyfile_mode(from_filename, to_filename, 0400);
}

static int kcore_copy__unlink(const char *dir, const char *name)
{
	char filename[PATH_MAX];

	scnprintf(filename, PATH_MAX, "%s/%s", dir, name);

	return unlink(filename);
}

static int kcore_copy__compare_fds(int from, int to)
{
	char *buf_from;
	char *buf_to;
	ssize_t ret;
	size_t len;
	int err = -1;

	buf_from = malloc(page_size);
	buf_to = malloc(page_size);
	if (!buf_from || !buf_to)
		goto out;

	while (1) {
		/* Use read because mmap won't work on proc files */
		ret = read(from, buf_from, page_size);
		if (ret < 0)
			goto out;

		if (!ret)
			break;

		len = ret;

		if (readn(to, buf_to, len) != (int)len)
			goto out;

		if (memcmp(buf_from, buf_to, len))
			goto out;
	}

	err = 0;
out:
	free(buf_to);
	free(buf_from);
	return err;
}

static int kcore_copy__compare_files(const char *from_filename,
				     const char *to_filename)
{
	int from, to, err = -1;

	from = open(from_filename, O_RDONLY);
	if (from < 0)
		return -1;

	to = open(to_filename, O_RDONLY);
	if (to < 0)
		goto out_close_from;

	err = kcore_copy__compare_fds(from, to);

	close(to);
out_close_from:
	close(from);
	return err;
}

static int kcore_copy__compare_file(const char *from_dir, const char *to_dir,
				    const char *name)
{
	char from_filename[PATH_MAX];
	char to_filename[PATH_MAX];

	scnprintf(from_filename, PATH_MAX, "%s/%s", from_dir, name);
	scnprintf(to_filename, PATH_MAX, "%s/%s", to_dir, name);

	return kcore_copy__compare_files(from_filename, to_filename);
}

/**
 * kcore_copy - copy kallsyms, modules and kcore from one directory to another.
 * @from_dir: from directory
 * @to_dir: to directory
 *
 * This function copies kallsyms, modules and kcore files from one directory to
 * another.  kallsyms and modules are copied entirely.  Only code segments are
 * copied from kcore.  It is assumed that two segments suffice: one for the
 * kernel proper and one for all the modules.  The code segments are determined
 * from kallsyms and modules files.  The kernel map starts at _stext or the
 * lowest function symbol, and ends at _etext or the highest function symbol.
 * The module map starts at the lowest module address and ends at the highest
 * module symbol.  Start addresses are rounded down to the nearest page.  End
 * addresses are rounded up to the nearest page.  An extra page is added to the
 * highest kernel symbol and highest module symbol to, hopefully, encompass that
 * symbol too.  Because it contains only code sections, the resulting kcore is
 * unusual.  One significant peculiarity is that the mapping (start -> pgoff)
 * is not the same for the kernel map and the modules map.  That happens because
 * the data is copied adjacently whereas the original kcore has gaps.  Finally,
 * kallsyms and modules files are compared with their copies to check that
 * modules have not been loaded or unloaded while the copies were taking place.
 *
 * Return: %0 on success, %-1 on failure.
 */
int kcore_copy(const char *from_dir, const char *to_dir)
{
	struct kcore kcore;
	struct kcore extract;
	size_t count = 2;
	int idx = 0, err = -1;
	off_t offset = page_size, sz, modules_offset = 0;
	struct kcore_copy_info kci = { .stext = 0, };
	char kcore_filename[PATH_MAX];
	char extract_filename[PATH_MAX];

	if (kcore_copy__copy_file(from_dir, to_dir, "kallsyms"))
		return -1;

	if (kcore_copy__copy_file(from_dir, to_dir, "modules"))
		goto out_unlink_kallsyms;

	scnprintf(kcore_filename, PATH_MAX, "%s/kcore", from_dir);
	scnprintf(extract_filename, PATH_MAX, "%s/kcore", to_dir);

	if (kcore__open(&kcore, kcore_filename))
		goto out_unlink_modules;

	if (kcore_copy__calc_maps(&kci, from_dir, kcore.elf))
		goto out_kcore_close;

	if (kcore__init(&extract, extract_filename, kcore.elfclass, false))
		goto out_kcore_close;

	if (!kci.modules_map.addr)
		count -= 1;

	if (kcore__copy_hdr(&kcore, &extract, count))
		goto out_extract_close;

	if (kcore__add_phdr(&extract, idx++, offset, kci.kernel_map.addr,
			    kci.kernel_map.len))
		goto out_extract_close;

	if (kci.modules_map.addr) {
		modules_offset = offset + kci.kernel_map.len;
		if (kcore__add_phdr(&extract, idx, modules_offset,
				    kci.modules_map.addr, kci.modules_map.len))
			goto out_extract_close;
	}

	sz = kcore__write(&extract);
	if (sz < 0 || sz > offset)
		goto out_extract_close;

	if (copy_bytes(kcore.fd, kci.kernel_map.offset, extract.fd, offset,
		       kci.kernel_map.len))
		goto out_extract_close;

	if (modules_offset && copy_bytes(kcore.fd, kci.modules_map.offset,
					 extract.fd, modules_offset,
					 kci.modules_map.len))
		goto out_extract_close;

	if (kcore_copy__compare_file(from_dir, to_dir, "modules"))
		goto out_extract_close;

	if (kcore_copy__compare_file(from_dir, to_dir, "kallsyms"))
		goto out_extract_close;

	err = 0;

out_extract_close:
	kcore__close(&extract);
	if (err)
		unlink(extract_filename);
out_kcore_close:
	kcore__close(&kcore);
out_unlink_modules:
	if (err)
		kcore_copy__unlink(to_dir, "modules");
out_unlink_kallsyms:
	if (err)
		kcore_copy__unlink(to_dir, "kallsyms");

	return err;
}

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 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788
int kcore_extract__create(struct kcore_extract *kce)
{
	struct kcore kcore;
	struct kcore extract;
	size_t count = 1;
	int idx = 0, err = -1;
	off_t offset = page_size, sz;

	if (kcore__open(&kcore, kce->kcore_filename))
		return -1;

	strcpy(kce->extract_filename, PERF_KCORE_EXTRACT);
	if (kcore__init(&extract, kce->extract_filename, kcore.elfclass, true))
		goto out_kcore_close;

	if (kcore__copy_hdr(&kcore, &extract, count))
		goto out_extract_close;

	if (kcore__add_phdr(&extract, idx, offset, kce->addr, kce->len))
		goto out_extract_close;

	sz = kcore__write(&extract);
	if (sz < 0 || sz > offset)
		goto out_extract_close;

	if (copy_bytes(kcore.fd, kce->offs, extract.fd, offset, kce->len))
		goto out_extract_close;

	err = 0;

out_extract_close:
	kcore__close(&extract);
	if (err)
		unlink(kce->extract_filename);
out_kcore_close:
	kcore__close(&kcore);

	return err;
}

void kcore_extract__delete(struct kcore_extract *kce)
{
	unlink(kce->extract_filename);
}

1789 1790 1791 1792
void symbol__elf_init(void)
{
	elf_version(EV_CURRENT);
}