tools/perf/util/symbol.c

#include <dirent.h>
#include <errno.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/param.h>
#include <fcntl.h>
#include <unistd.h>
#include <inttypes.h>
#include "build-id.h"
#include "util.h"
#include "debug.h"
#include "symbol.h"
#include "strlist.h"

#include <elf.h>
#include <limits.h>
#include <sys/utsname.h>

#ifndef KSYM_NAME_LEN
#define KSYM_NAME_LEN 256
#endif

static void dso_cache__free(struct rb_root *root);
static int dso__load_kernel_sym(struct dso *dso, struct map *map,
				symbol_filter_t filter);
static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
			symbol_filter_t filter);
static int vmlinux_path__nr_entries;
static char **vmlinux_path;

struct symbol_conf symbol_conf = {
	.exclude_other	  = true,
	.use_modules	  = true,
	.try_vmlinux_path = true,
	.annotate_src	  = true,
	.symfs            = "",
};

static enum dso_binary_type binary_type_symtab[] = {
	DSO_BINARY_TYPE__KALLSYMS,
	DSO_BINARY_TYPE__GUEST_KALLSYMS,
	DSO_BINARY_TYPE__JAVA_JIT,
	DSO_BINARY_TYPE__DEBUGLINK,
	DSO_BINARY_TYPE__BUILD_ID_CACHE,
	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
	DSO_BINARY_TYPE__GUEST_KMODULE,
	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
	DSO_BINARY_TYPE__NOT_FOUND,
};

#define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab)

static enum dso_binary_type binary_type_data[] = {
	DSO_BINARY_TYPE__BUILD_ID_CACHE,
	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
	DSO_BINARY_TYPE__NOT_FOUND,
};

#define DSO_BINARY_TYPE__DATA_CNT ARRAY_SIZE(binary_type_data)

int dso__name_len(const struct dso *dso)
{
	if (!dso)
		return strlen("[unknown]");
	if (verbose)
		return dso->long_name_len;

	return dso->short_name_len;
}

bool dso__loaded(const struct dso *dso, enum map_type type)
{
	return dso->loaded & (1 << type);
}

bool dso__sorted_by_name(const struct dso *dso, enum map_type type)
{
	return dso->sorted_by_name & (1 << type);
}

static void dso__set_sorted_by_name(struct dso *dso, enum map_type type)
{
	dso->sorted_by_name |= (1 << type);
}

bool symbol_type__is_a(char symbol_type, enum map_type map_type)
{
	symbol_type = toupper(symbol_type);

	switch (map_type) {
	case MAP__FUNCTION:
		return symbol_type == 'T' || symbol_type == 'W';
	case MAP__VARIABLE:
		return symbol_type == 'D';
	default:
		return false;
	}
}

static int prefix_underscores_count(const char *str)
{
	const char *tail = str;

	while (*tail == '_')
		tail++;

	return tail - str;
}

#define SYMBOL_A 0
#define SYMBOL_B 1

static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
{
	s64 a;
	s64 b;

	/* Prefer a symbol with non zero length */
	a = syma->end - syma->start;
	b = symb->end - symb->start;
	if ((b == 0) && (a > 0))
		return SYMBOL_A;
	else if ((a == 0) && (b > 0))
		return SYMBOL_B;

	/* Prefer a non weak symbol over a weak one */
	a = syma->binding == STB_WEAK;
	b = symb->binding == STB_WEAK;
	if (b && !a)
		return SYMBOL_A;
	if (a && !b)
		return SYMBOL_B;

	/* Prefer a global symbol over a non global one */
	a = syma->binding == STB_GLOBAL;
	b = symb->binding == STB_GLOBAL;
	if (a && !b)
		return SYMBOL_A;
	if (b && !a)
		return SYMBOL_B;

	/* Prefer a symbol with less underscores */
	a = prefix_underscores_count(syma->name);
	b = prefix_underscores_count(symb->name);
	if (b > a)
		return SYMBOL_A;
	else if (a > b)
		return SYMBOL_B;

	/* If all else fails, choose the symbol with the longest name */
	if (strlen(syma->name) >= strlen(symb->name))
		return SYMBOL_A;
	else
		return SYMBOL_B;
}

void symbols__fixup_duplicate(struct rb_root *symbols)
{
	struct rb_node *nd;
	struct symbol *curr, *next;

	nd = rb_first(symbols);

	while (nd) {
		curr = rb_entry(nd, struct symbol, rb_node);
again:
		nd = rb_next(&curr->rb_node);
		next = rb_entry(nd, struct symbol, rb_node);

		if (!nd)
			break;

		if (curr->start != next->start)
			continue;

		if (choose_best_symbol(curr, next) == SYMBOL_A) {
			rb_erase(&next->rb_node, symbols);
			goto again;
		} else {
			nd = rb_next(&curr->rb_node);
			rb_erase(&curr->rb_node, symbols);
		}
	}
}

void symbols__fixup_end(struct rb_root *symbols)
{
	struct rb_node *nd, *prevnd = rb_first(symbols);
	struct symbol *curr, *prev;

	if (prevnd == NULL)
		return;

	curr = rb_entry(prevnd, struct symbol, rb_node);

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

		if (prev->end == prev->start && prev->end != curr->start)
			prev->end = curr->start - 1;
	}

	/* Last entry */
	if (curr->end == curr->start)
		curr->end = roundup(curr->start, 4096);
}

void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
{
	struct map *prev, *curr;
	struct rb_node *nd, *prevnd = rb_first(&mg->maps[type]);

	if (prevnd == NULL)
		return;

	curr = rb_entry(prevnd, struct map, rb_node);

	for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) {
		prev = curr;
		curr = rb_entry(nd, struct map, rb_node);
		prev->end = curr->start - 1;
	}

	/*
	 * We still haven't the actual symbols, so guess the
	 * last map final address.
	 */
	curr->end = ~0ULL;
}

static void map_groups__fixup_end(struct map_groups *mg)
{
	int i;
	for (i = 0; i < MAP__NR_TYPES; ++i)
		__map_groups__fixup_end(mg, i);
}

struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
{
	size_t namelen = strlen(name) + 1;
	struct symbol *sym = calloc(1, (symbol_conf.priv_size +
					sizeof(*sym) + namelen));
	if (sym == NULL)
		return NULL;

	if (symbol_conf.priv_size)
		sym = ((void *)sym) + symbol_conf.priv_size;

	sym->start   = start;
	sym->end     = len ? start + len - 1 : start;
	sym->binding = binding;
	sym->namelen = namelen - 1;

	pr_debug4("%s: %s %#" PRIx64 "-%#" PRIx64 "\n",
		  __func__, name, start, sym->end);
	memcpy(sym->name, name, namelen);

	return sym;
}

void symbol__delete(struct symbol *sym)
{
	free(((void *)sym) - symbol_conf.priv_size);
}

static size_t symbol__fprintf(struct symbol *sym, FILE *fp)
{
	return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %c %s\n",
		       sym->start, sym->end,
		       sym->binding == STB_GLOBAL ? 'g' :
		       sym->binding == STB_LOCAL  ? 'l' : 'w',
		       sym->name);
}

size_t symbol__fprintf_symname_offs(const struct symbol *sym,
				    const struct addr_location *al, FILE *fp)
{
	unsigned long offset;
	size_t length;

	if (sym && sym->name) {
		length = fprintf(fp, "%s", sym->name);
		if (al) {
			offset = al->addr - sym->start;
			length += fprintf(fp, "+0x%lx", offset);
		}
		return length;
	} else
		return fprintf(fp, "[unknown]");
}

size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp)
{
	return symbol__fprintf_symname_offs(sym, NULL, fp);
}

void dso__set_long_name(struct dso *dso, char *name)
{
	if (name == NULL)
		return;
	dso->long_name = name;
	dso->long_name_len = strlen(name);
}

static void dso__set_short_name(struct dso *dso, const char *name)
{
	if (name == NULL)
		return;
	dso->short_name = name;
	dso->short_name_len = strlen(name);
}

static void dso__set_basename(struct dso *dso)
{
	dso__set_short_name(dso, basename(dso->long_name));
}

struct dso *dso__new(const char *name)
{
	struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1);

	if (dso != NULL) {
		int i;
		strcpy(dso->name, name);
		dso__set_long_name(dso, dso->name);
		dso__set_short_name(dso, dso->name);
		for (i = 0; i < MAP__NR_TYPES; ++i)
			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
		dso->cache = RB_ROOT;
		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
		dso->data_type   = DSO_BINARY_TYPE__NOT_FOUND;
		dso->loaded = 0;
		dso->sorted_by_name = 0;
		dso->has_build_id = 0;
		dso->kernel = DSO_TYPE_USER;
		dso->needs_swap = DSO_SWAP__UNSET;
		INIT_LIST_HEAD(&dso->node);
	}

	return dso;
}

static void symbols__delete(struct rb_root *symbols)
{
	struct symbol *pos;
	struct rb_node *next = rb_first(symbols);

	while (next) {
		pos = rb_entry(next, struct symbol, rb_node);
		next = rb_next(&pos->rb_node);
		rb_erase(&pos->rb_node, symbols);
		symbol__delete(pos);
	}
}

void dso__delete(struct dso *dso)
{
	int i;
	for (i = 0; i < MAP__NR_TYPES; ++i)
		symbols__delete(&dso->symbols[i]);
	if (dso->sname_alloc)
		free((char *)dso->short_name);
	if (dso->lname_alloc)
		free(dso->long_name);
	dso_cache__free(&dso->cache);
	free(dso);
}

void dso__set_build_id(struct dso *dso, void *build_id)
{
	memcpy(dso->build_id, build_id, sizeof(dso->build_id));
	dso->has_build_id = 1;
}

void symbols__insert(struct rb_root *symbols, struct symbol *sym)
{
	struct rb_node **p = &symbols->rb_node;
	struct rb_node *parent = NULL;
	const u64 ip = sym->start;
	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, symbols);
}

static struct symbol *symbols__find(struct rb_root *symbols, u64 ip)
{
	struct rb_node *n;

	if (symbols == NULL)
		return NULL;

	n = symbols->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;
}

struct symbol_name_rb_node {
	struct rb_node	rb_node;
	struct symbol	sym;
};

static void symbols__insert_by_name(struct rb_root *symbols, struct symbol *sym)
{
	struct rb_node **p = &symbols->rb_node;
	struct rb_node *parent = NULL;
	struct symbol_name_rb_node *symn, *s;

	symn = container_of(sym, struct symbol_name_rb_node, sym);

	while (*p != NULL) {
		parent = *p;
		s = rb_entry(parent, struct symbol_name_rb_node, rb_node);
		if (strcmp(sym->name, s->sym.name) < 0)
			p = &(*p)->rb_left;
		else
			p = &(*p)->rb_right;
	}
	rb_link_node(&symn->rb_node, parent, p);
	rb_insert_color(&symn->rb_node, symbols);
}

static void symbols__sort_by_name(struct rb_root *symbols,
				  struct rb_root *source)
{
	struct rb_node *nd;

	for (nd = rb_first(source); nd; nd = rb_next(nd)) {
		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
		symbols__insert_by_name(symbols, pos);
	}
}

static struct symbol *symbols__find_by_name(struct rb_root *symbols,
					    const char *name)
{
	struct rb_node *n;

	if (symbols == NULL)
		return NULL;

	n = symbols->rb_node;

	while (n) {
		struct symbol_name_rb_node *s;
		int cmp;

		s = rb_entry(n, struct symbol_name_rb_node, rb_node);
		cmp = strcmp(name, s->sym.name);

		if (cmp < 0)
			n = n->rb_left;
		else if (cmp > 0)
			n = n->rb_right;
		else
			return &s->sym;
	}

	return NULL;
}

struct symbol *dso__find_symbol(struct dso *dso,
				enum map_type type, u64 addr)
{
	return symbols__find(&dso->symbols[type], addr);
}

struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
					const char *name)
{
	return symbols__find_by_name(&dso->symbol_names[type], name);
}

void dso__sort_by_name(struct dso *dso, enum map_type type)
{
	dso__set_sorted_by_name(dso, type);
	return symbols__sort_by_name(&dso->symbol_names[type],
				     &dso->symbols[type]);
}

int build_id__sprintf(const u8 *build_id, int len, char *bf)
{
	char *bid = bf;
	const u8 *raw = build_id;
	int i;

	for (i = 0; i < len; ++i) {
		sprintf(bid, "%02x", *raw);
		++raw;
		bid += 2;
	}

	return raw - build_id;
}

size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
{
	char sbuild_id[BUILD_ID_SIZE * 2 + 1];

	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
	return fprintf(fp, "%s", sbuild_id);
}

size_t dso__fprintf_symbols_by_name(struct dso *dso,
				    enum map_type type, FILE *fp)
{
	size_t ret = 0;
	struct rb_node *nd;
	struct symbol_name_rb_node *pos;

	for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) {
		pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
		fprintf(fp, "%s\n", pos->sym.name);
	}

	return ret;
}

size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
{
	struct rb_node *nd;
	size_t ret = fprintf(fp, "dso: %s (", dso->short_name);

	if (dso->short_name != dso->long_name)
		ret += fprintf(fp, "%s, ", dso->long_name);
	ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type],
		       dso->loaded ? "" : "NOT ");
	ret += dso__fprintf_buildid(dso, fp);
	ret += fprintf(fp, ")\n");
	for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) {
		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
		ret += symbol__fprintf(pos, fp);
	}

	return ret;
}

int kallsyms__parse(const char *filename, void *arg,
		    int (*process_symbol)(void *arg, const char *name,
					  char type, u64 start))
{
	char *line = NULL;
	size_t n;
	int err = -1;
	FILE *file = fopen(filename, "r");

	if (file == NULL)
		goto out_failure;

	err = 0;

	while (!feof(file)) {
		u64 start;
		int line_len, len;
		char symbol_type;
		char *symbol_name;

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

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

		len = hex2u64(line, &start);

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

		symbol_type = line[len];
		len += 2;
		symbol_name = line + len;
		len = line_len - len;

		if (len >= KSYM_NAME_LEN) {
			err = -1;
			break;
		}

		err = process_symbol(arg, symbol_name,
				     symbol_type, start);
		if (err)
			break;
	}

	free(line);
	fclose(file);
	return err;

out_failure:
	return -1;
}

struct process_kallsyms_args {
	struct map *map;
	struct dso *dso;
};

static u8 kallsyms2elf_type(char type)
{
	if (type == 'W')
		return STB_WEAK;

	return isupper(type) ? STB_GLOBAL : STB_LOCAL;
}

static int map__process_kallsym_symbol(void *arg, const char *name,
				       char type, u64 start)
{
	struct symbol *sym;
	struct process_kallsyms_args *a = arg;
	struct rb_root *root = &a->dso->symbols[a->map->type];

	if (!symbol_type__is_a(type, a->map->type))
		return 0;

	/*
	 * module symbols are not sorted so we add all
	 * symbols, setting length to 0, and rely on
	 * symbols__fixup_end() to fix it up.
	 */
	sym = symbol__new(start, 0, kallsyms2elf_type(type), name);
	if (sym == NULL)
		return -ENOMEM;
	/*
	 * We will pass the symbols to the filter later, in
	 * map__split_kallsyms, when we have split the maps per module
	 */
	symbols__insert(root, sym);

	return 0;
}

/*
 * Loads the function entries in /proc/kallsyms into kernel_map->dso,
 * so that we can in the next step set the symbol ->end address and then
 * call kernel_maps__split_kallsyms.
 */
static int dso__load_all_kallsyms(struct dso *dso, const char *filename,
				  struct map *map)
{
	struct process_kallsyms_args args = { .map = map, .dso = dso, };
	return kallsyms__parse(filename, &args, map__process_kallsym_symbol);
}

/*
 * Split the symbols into maps, making sure there are no overlaps, i.e. the
 * kernel range is broken in several maps, named [kernel].N, as we don't have
 * the original ELF section names vmlinux have.
 */
static int dso__split_kallsyms(struct dso *dso, struct map *map,
			       symbol_filter_t filter)
{
	struct map_groups *kmaps = map__kmap(map)->kmaps;
	struct machine *machine = kmaps->machine;
	struct map *curr_map = map;
	struct symbol *pos;
	int count = 0, moved = 0;	
	struct rb_root *root = &dso->symbols[map->type];
	struct rb_node *next = rb_first(root);
	int kernel_range = 0;

	while (next) {
		char *module;

		pos = rb_entry(next, struct symbol, rb_node);
		next = rb_next(&pos->rb_node);

		module = strchr(pos->name, '\t');
		if (module) {
			if (!symbol_conf.use_modules)
				goto discard_symbol;

			*module++ = '\0';

			if (strcmp(curr_map->dso->short_name, module)) {
				if (curr_map != map &&
				    dso->kernel == DSO_TYPE_GUEST_KERNEL &&
				    machine__is_default_guest(machine)) {
					/*
					 * We assume all symbols of a module are
					 * continuous in * kallsyms, so curr_map
					 * points to a module and all its
					 * symbols are in its kmap. Mark it as
					 * loaded.
					 */
					dso__set_loaded(curr_map->dso,
							curr_map->type);
				}

				curr_map = map_groups__find_by_name(kmaps,
							map->type, module);
				if (curr_map == NULL) {
					pr_debug("%s/proc/{kallsyms,modules} "
					         "inconsistency while looking "
						 "for \"%s\" module!\n",
						 machine->root_dir, module);
					curr_map = map;
					goto discard_symbol;
				}

				if (curr_map->dso->loaded &&
				    !machine__is_default_guest(machine))
					goto discard_symbol;
			}
			/*
			 * So that we look just like we get from .ko files,
			 * i.e. not prelinked, relative to map->start.
			 */
			pos->start = curr_map->map_ip(curr_map, pos->start);
			pos->end   = curr_map->map_ip(curr_map, pos->end);
		} else if (curr_map != map) {
			char dso_name[PATH_MAX];
			struct dso *ndso;

			if (count == 0) {
				curr_map = map;
				goto filter_symbol;
			}

			if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
				snprintf(dso_name, sizeof(dso_name),
					"[guest.kernel].%d",
					kernel_range++);
			else
				snprintf(dso_name, sizeof(dso_name),
					"[kernel].%d",
					kernel_range++);

			ndso = dso__new(dso_name);
			if (ndso == NULL)
				return -1;

			ndso->kernel = dso->kernel;

			curr_map = map__new2(pos->start, ndso, map->type);
			if (curr_map == NULL) {
				dso__delete(ndso);
				return -1;
			}

			curr_map->map_ip = curr_map->unmap_ip = identity__map_ip;
			map_groups__insert(kmaps, curr_map);
			++kernel_range;
		}
filter_symbol:
		if (filter && filter(curr_map, pos)) {
discard_symbol:		rb_erase(&pos->rb_node, root);
			symbol__delete(pos);
		} else {
			if (curr_map != map) {
				rb_erase(&pos->rb_node, root);
				symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
				++moved;
			} else
				++count;
		}
	}

	if (curr_map != map &&
	    dso->kernel == DSO_TYPE_GUEST_KERNEL &&
	    machine__is_default_guest(kmaps->machine)) {
		dso__set_loaded(curr_map->dso, curr_map->type);
	}

	return count + moved;
}

static bool symbol__restricted_filename(const char *filename,
					const char *restricted_filename)
{
	bool restricted = false;

	if (symbol_conf.kptr_restrict) {
		char *r = realpath(filename, NULL);

		if (r != NULL) {
			restricted = strcmp(r, restricted_filename) == 0;
			free(r);
			return restricted;
		}
	}

	return restricted;
}

int dso__load_kallsyms(struct dso *dso, const char *filename,
		       struct map *map, symbol_filter_t filter)
{
	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
		return -1;

	if (dso__load_all_kallsyms(dso, filename, map) < 0)
		return -1;

	symbols__fixup_duplicate(&dso->symbols[map->type]);
	symbols__fixup_end(&dso->symbols[map->type]);

	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
	else
		dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;

	return dso__split_kallsyms(dso, map, filter);
}

static int dso__load_perf_map(struct dso *dso, struct map *map,
			      symbol_filter_t filter)
{
	char *line = NULL;
	size_t n;
	FILE *file;
	int nr_syms = 0;

	file = fopen(dso->long_name, "r");
	if (file == NULL)
		goto out_failure;

	while (!feof(file)) {
		u64 start, size;
		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, STB_GLOBAL, line + len);

		if (sym == NULL)
			goto out_delete_line;

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

	free(line);
	fclose(file);

	return nr_syms;

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

bool dso__build_id_equal(const struct dso *dso, u8 *build_id)
{
	return memcmp(dso->build_id, build_id, sizeof(dso->build_id)) == 0;
}

bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
{
	bool have_build_id = false;
	struct dso *pos;

	list_for_each_entry(pos, head, node) {
		if (with_hits && !pos->hit)
			continue;
		if (pos->has_build_id) {
			have_build_id = true;
			continue;
		}
		if (filename__read_build_id(pos->long_name, pos->build_id,
					    sizeof(pos->build_id)) > 0) {
			have_build_id	  = true;
			pos->has_build_id = true;
		}
	}

	return have_build_id;
}

char dso__symtab_origin(const struct dso *dso)
{
	static const char origin[] = {
		[DSO_BINARY_TYPE__KALLSYMS]		= 'k',
		[DSO_BINARY_TYPE__VMLINUX]		= 'v',
		[DSO_BINARY_TYPE__JAVA_JIT]		= 'j',
		[DSO_BINARY_TYPE__DEBUGLINK]		= 'l',
		[DSO_BINARY_TYPE__BUILD_ID_CACHE]	= 'B',
		[DSO_BINARY_TYPE__FEDORA_DEBUGINFO]	= 'f',
		[DSO_BINARY_TYPE__UBUNTU_DEBUGINFO]	= 'u',
		[DSO_BINARY_TYPE__BUILDID_DEBUGINFO]	= 'b',
		[DSO_BINARY_TYPE__SYSTEM_PATH_DSO]	= 'd',
		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE]	= 'K',
		[DSO_BINARY_TYPE__GUEST_KALLSYMS]	= 'g',
		[DSO_BINARY_TYPE__GUEST_KMODULE]	= 'G',
		[DSO_BINARY_TYPE__GUEST_VMLINUX]	= 'V',
	};

	if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND)
		return '!';
	return origin[dso->symtab_type];
}

int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
			  char *root_dir, char *file, size_t size)
{
	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
	int ret = 0;

	switch (type) {
	case DSO_BINARY_TYPE__DEBUGLINK: {
		char *debuglink;

		strncpy(file, dso->long_name, size);
		debuglink = file + dso->long_name_len;
		while (debuglink != file && *debuglink != '/')
			debuglink--;
		if (*debuglink == '/')
			debuglink++;
		filename__read_debuglink(dso->long_name, debuglink,
					 size - (debuglink - file));
		}
		break;
	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
		/* skip the locally configured cache if a symfs is given */
		if (symbol_conf.symfs[0] ||
		    (dso__build_id_filename(dso, file, size) == NULL))
			ret = -1;
		break;

	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
		snprintf(file, size, "%s/usr/lib/debug%s.debug",
			 symbol_conf.symfs, dso->long_name);
		break;

	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
		snprintf(file, size, "%s/usr/lib/debug%s",
			 symbol_conf.symfs, dso->long_name);
		break;

	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
		if (!dso->has_build_id) {
			ret = -1;
			break;
		}

		build_id__sprintf(dso->build_id,
				  sizeof(dso->build_id),
				  build_id_hex);
		snprintf(file, size,
			 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
			 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
		break;

	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
		snprintf(file, size, "%s%s",
			 symbol_conf.symfs, dso->long_name);
		break;

	case DSO_BINARY_TYPE__GUEST_KMODULE:
		snprintf(file, size, "%s%s%s", symbol_conf.symfs,
			 root_dir, dso->long_name);
		break;

	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
		snprintf(file, size, "%s%s", symbol_conf.symfs,
			 dso->long_name);
		break;

	default:
	case DSO_BINARY_TYPE__KALLSYMS:
	case DSO_BINARY_TYPE__VMLINUX:
	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
	case DSO_BINARY_TYPE__GUEST_VMLINUX:
	case DSO_BINARY_TYPE__JAVA_JIT:
	case DSO_BINARY_TYPE__NOT_FOUND:
		ret = -1;
		break;
	}

	return ret;
}

int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
{
	char *name;
	int ret = -1;
	u_int i;
	struct machine *machine;
	char *root_dir = (char *) "";
	int ss_pos = 0;
	struct symsrc ss_[2];
	struct symsrc *syms_ss = NULL, *runtime_ss = NULL;

	dso__set_loaded(dso, map->type);

	if (dso->kernel == DSO_TYPE_KERNEL)
		return dso__load_kernel_sym(dso, map, filter);
	else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
		return dso__load_guest_kernel_sym(dso, map, filter);

	if (map->groups && map->groups->machine)
		machine = map->groups->machine;
	else
		machine = NULL;

	name = malloc(PATH_MAX);
	if (!name)
		return -1;

	dso->adjust_symbols = 0;

	if (strncmp(dso->name, "/tmp/perf-", 10) == 0) {
		struct stat st;

		if (lstat(dso->name, &st) < 0)
			return -1;

		if (st.st_uid && (st.st_uid != geteuid())) {
			pr_warning("File %s not owned by current user or root, "
				"ignoring it.\n", dso->name);
			return -1;
		}

		ret = dso__load_perf_map(dso, map, filter);
		dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
					     DSO_BINARY_TYPE__NOT_FOUND;
		return ret;
	}

	if (machine)
		root_dir = machine->root_dir;

	/* Iterate over candidate debug images.
	 * Keep track of "interesting" ones (those which have a symtab, dynsym,
	 * and/or opd section) for processing.
	 */
	for (i = 0; i < DSO_BINARY_TYPE__SYMTAB_CNT; i++) {
		struct symsrc *ss = &ss_[ss_pos];
		bool next_slot = false;

		enum dso_binary_type symtab_type = binary_type_symtab[i];

		if (dso__binary_type_file(dso, symtab_type,
					  root_dir, name, PATH_MAX))
			continue;

		/* Name is now the name of the next image to try */
		if (symsrc__init(ss, dso, name, symtab_type) < 0)
			continue;

		if (!syms_ss && symsrc__has_symtab(ss)) {
			syms_ss = ss;
			next_slot = true;
		}

		if (!runtime_ss && symsrc__possibly_runtime(ss)) {
			runtime_ss = ss;
			next_slot = true;
		}

		if (next_slot) {
			ss_pos++;

			if (syms_ss && runtime_ss)
				break;
		}

	}

	if (!runtime_ss && !syms_ss)
		goto out_free;

	if (runtime_ss && !syms_ss) {
		syms_ss = runtime_ss;
	}

	/* We'll have to hope for the best */
	if (!runtime_ss && syms_ss)
		runtime_ss = syms_ss;

	if (syms_ss)
		ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, 0);
	else
		ret = -1;

	if (ret > 0) {
		int nr_plt;

		nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss, map, filter);
		if (nr_plt > 0)
			ret += nr_plt;
	}

	for (; ss_pos > 0; ss_pos--)
		symsrc__destroy(&ss_[ss_pos - 1]);
out_free:
	free(name);
	if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
		return 0;
	return ret;
}

struct map *map_groups__find_by_name(struct map_groups *mg,
				     enum map_type type, const char *name)
{
	struct rb_node *nd;

	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
		struct map *map = rb_entry(nd, struct map, rb_node);

		if (map->dso && strcmp(map->dso->short_name, name) == 0)
			return map;
	}

	return NULL;
}

static int dso__kernel_module_get_build_id(struct dso *dso,
					   const char *root_dir)
{
	char filename[PATH_MAX];
	/*
	 * kernel module short names are of the form "[module]" and
	 * we need just "module" here.
	 */
	const char *name = dso->short_name + 1;

	snprintf(filename, sizeof(filename),
		 "%s/sys/module/%.*s/notes/.note.gnu.build-id",
		 root_dir, (int)strlen(name) - 1, name);

	if (sysfs__read_build_id(filename, dso->build_id,
				 sizeof(dso->build_id)) == 0)
		dso->has_build_id = true;

	return 0;
}

static int map_groups__set_modules_path_dir(struct map_groups *mg,
				const char *dir_name)
{
	struct dirent *dent;
	DIR *dir = opendir(dir_name);
	int ret = 0;

	if (!dir) {
		pr_debug("%s: cannot open %s dir\n", __func__, dir_name);
		return -1;
	}

	while ((dent = readdir(dir)) != NULL) {
		char path[PATH_MAX];
		struct stat st;

		/*sshfs might return bad dent->d_type, so we have to stat*/
		snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name);
		if (stat(path, &st))
			continue;

		if (S_ISDIR(st.st_mode)) {
			if (!strcmp(dent->d_name, ".") ||
			    !strcmp(dent->d_name, ".."))
				continue;

			ret = map_groups__set_modules_path_dir(mg, path);
			if (ret < 0)
				goto out;
		} else {
			char *dot = strrchr(dent->d_name, '.'),
			     dso_name[PATH_MAX];
			struct map *map;
			char *long_name;

			if (dot == NULL || strcmp(dot, ".ko"))
				continue;
			snprintf(dso_name, sizeof(dso_name), "[%.*s]",
				 (int)(dot - dent->d_name), dent->d_name);

			strxfrchar(dso_name, '-', '_');
			map = map_groups__find_by_name(mg, MAP__FUNCTION,
						       dso_name);
			if (map == NULL)
				continue;

			long_name = strdup(path);
			if (long_name == NULL) {
				ret = -1;
				goto out;
			}
			dso__set_long_name(map->dso, long_name);
			map->dso->lname_alloc = 1;
			dso__kernel_module_get_build_id(map->dso, "");
		}
	}

out:
	closedir(dir);
	return ret;
}

static char *get_kernel_version(const char *root_dir)
{
	char version[PATH_MAX];
	FILE *file;
	char *name, *tmp;
	const char *prefix = "Linux version ";

	sprintf(version, "%s/proc/version", root_dir);
	file = fopen(version, "r");
	if (!file)
		return NULL;

	version[0] = '\0';
	tmp = fgets(version, sizeof(version), file);
	fclose(file);

	name = strstr(version, prefix);
	if (!name)
		return NULL;
	name += strlen(prefix);
	tmp = strchr(name, ' ');
	if (tmp)
		*tmp = '\0';

	return strdup(name);
}

static int machine__set_modules_path(struct machine *machine)
{
	char *version;
	char modules_path[PATH_MAX];

	version = get_kernel_version(machine->root_dir);
	if (!version)
		return -1;

	snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel",
		 machine->root_dir, version);
	free(version);

	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path);
}

struct map *machine__new_module(struct machine *machine, u64 start,
				const char *filename)
{
	struct map *map;
	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename);

	if (dso == NULL)
		return NULL;

	map = map__new2(start, dso, MAP__FUNCTION);
	if (map == NULL)
		return NULL;

	if (machine__is_host(machine))
		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
	else
		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
	map_groups__insert(&machine->kmaps, map);
	return map;
}

static int machine__create_modules(struct machine *machine)
{
	char *line = NULL;
	size_t n;
	FILE *file;
	struct map *map;
	const char *modules;
	char path[PATH_MAX];

	if (machine__is_default_guest(machine))
		modules = symbol_conf.default_guest_modules;
	else {
		sprintf(path, "%s/proc/modules", machine->root_dir);
		modules = path;
	}

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

	file = fopen(modules, "r");
	if (file == NULL)
		return -1;

	while (!feof(file)) {
		char name[PATH_MAX];
		u64 start;
		char *sep;
		int line_len;

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

		if (!line)
			goto out_failure;

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

		sep = strrchr(line, 'x');
		if (sep == NULL)
			continue;

		hex2u64(sep + 1, &start);

		sep = strchr(line, ' ');
		if (sep == NULL)
			continue;

		*sep = '\0';

		snprintf(name, sizeof(name), "[%s]", line);
		map = machine__new_module(machine, start, name);
		if (map == NULL)
			goto out_delete_line;
		dso__kernel_module_get_build_id(map->dso, machine->root_dir);
	}

	free(line);
	fclose(file);

	return machine__set_modules_path(machine);

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

int dso__load_vmlinux(struct dso *dso, struct map *map,
		      const char *vmlinux, symbol_filter_t filter)
{
	int err = -1;
	struct symsrc ss;
	char symfs_vmlinux[PATH_MAX];
	enum dso_binary_type symtab_type;

	snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s",
		 symbol_conf.symfs, vmlinux);

	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
		symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
	else
		symtab_type = DSO_BINARY_TYPE__VMLINUX;

	if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type))
		return -1;

	err = dso__load_sym(dso, map, &ss, &ss, filter, 0);
	symsrc__destroy(&ss);

	if (err > 0) {
		dso__set_long_name(dso, (char *)vmlinux);
		dso__set_loaded(dso, map->type);
		pr_debug("Using %s for symbols\n", symfs_vmlinux);
	}

	return err;
}

int dso__load_vmlinux_path(struct dso *dso, struct map *map,
			   symbol_filter_t filter)
{
	int i, err = 0;
	char *filename;

	pr_debug("Looking at the vmlinux_path (%d entries long)\n",
		 vmlinux_path__nr_entries + 1);

	filename = dso__build_id_filename(dso, NULL, 0);
	if (filename != NULL) {
		err = dso__load_vmlinux(dso, map, filename, filter);
		if (err > 0)
			goto out;
		free(filename);
	}

	for (i = 0; i < vmlinux_path__nr_entries; ++i) {
		err = dso__load_vmlinux(dso, map, vmlinux_path[i], filter);
		if (err > 0) {
			dso__set_long_name(dso, strdup(vmlinux_path[i]));
			break;
		}
	}
out:
	return err;
}

static int dso__load_kernel_sym(struct dso *dso, struct map *map,
				symbol_filter_t filter)
{
	int err;
	const char *kallsyms_filename = NULL;
	char *kallsyms_allocated_filename = NULL;
	/*
	 * Step 1: if the user specified a kallsyms or vmlinux filename, use
	 * it and only it, reporting errors to the user if it cannot be used.
	 *
	 * For instance, try to analyse an ARM perf.data file _without_ a
	 * build-id, or if the user specifies the wrong path to the right
	 * vmlinux file, obviously we can't fallback to another vmlinux (a
	 * x86_86 one, on the machine where analysis is being performed, say),
	 * or worse, /proc/kallsyms.
	 *
	 * If the specified file _has_ a build-id and there is a build-id
	 * section in the perf.data file, we will still do the expected
	 * validation in dso__load_vmlinux and will bail out if they don't
	 * match.
	 */
	if (symbol_conf.kallsyms_name != NULL) {
		kallsyms_filename = symbol_conf.kallsyms_name;
		goto do_kallsyms;
	}

	if (symbol_conf.vmlinux_name != NULL) {
		err = dso__load_vmlinux(dso, map,
					symbol_conf.vmlinux_name, filter);
		if (err > 0) {
			dso__set_long_name(dso,
					   strdup(symbol_conf.vmlinux_name));
			goto out_fixup;
		}
		return err;
	}

	if (vmlinux_path != NULL) {
		err = dso__load_vmlinux_path(dso, map, filter);
		if (err > 0)
			goto out_fixup;
	}

	/* do not try local files if a symfs was given */
	if (symbol_conf.symfs[0] != 0)
		return -1;

	/*
	 * Say the kernel DSO was created when processing the build-id header table,
	 * we have a build-id, so check if it is the same as the running kernel,
	 * using it if it is.
	 */
	if (dso->has_build_id) {
		u8 kallsyms_build_id[BUILD_ID_SIZE];
		char sbuild_id[BUILD_ID_SIZE * 2 + 1];

		if (sysfs__read_build_id("/sys/kernel/notes", kallsyms_build_id,
					 sizeof(kallsyms_build_id)) == 0) {
			if (dso__build_id_equal(dso, kallsyms_build_id)) {
				kallsyms_filename = "/proc/kallsyms";
				goto do_kallsyms;
			}
		}
		/*
		 * Now look if we have it on the build-id cache in
		 * $HOME/.debug/[kernel.kallsyms].
		 */
		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
				  sbuild_id);

		if (asprintf(&kallsyms_allocated_filename,
			     "%s/.debug/[kernel.kallsyms]/%s",
			     getenv("HOME"), sbuild_id) == -1) {
			pr_err("Not enough memory for kallsyms file lookup\n");
			return -1;
		}

		kallsyms_filename = kallsyms_allocated_filename;

		if (access(kallsyms_filename, F_OK)) {
			pr_err("No kallsyms or vmlinux with build-id %s "
			       "was found\n", sbuild_id);
			free(kallsyms_allocated_filename);
			return -1;
		}
	} else {
		/*
		 * Last resort, if we don't have a build-id and couldn't find
		 * any vmlinux file, try the running kernel kallsyms table.
		 */
		kallsyms_filename = "/proc/kallsyms";
	}

do_kallsyms:
	err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
	if (err > 0)
		pr_debug("Using %s for symbols\n", kallsyms_filename);
	free(kallsyms_allocated_filename);

	if (err > 0) {
		dso__set_long_name(dso, strdup("[kernel.kallsyms]"));
out_fixup:
		map__fixup_start(map);
		map__fixup_end(map);
	}

	return err;
}

static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
				      symbol_filter_t filter)
{
	int err;
	const char *kallsyms_filename = NULL;
	struct machine *machine;
	char path[PATH_MAX];

	if (!map->groups) {
		pr_debug("Guest kernel map hasn't the point to groups\n");
		return -1;
	}
	machine = map->groups->machine;

	if (machine__is_default_guest(machine)) {
		/*
		 * if the user specified a vmlinux filename, use it and only
		 * it, reporting errors to the user if it cannot be used.
		 * Or use file guest_kallsyms inputted by user on commandline
		 */
		if (symbol_conf.default_guest_vmlinux_name != NULL) {
			err = dso__load_vmlinux(dso, map,
				symbol_conf.default_guest_vmlinux_name, filter);
			goto out_try_fixup;
		}

		kallsyms_filename = symbol_conf.default_guest_kallsyms;
		if (!kallsyms_filename)
			return -1;
	} else {
		sprintf(path, "%s/proc/kallsyms", machine->root_dir);
		kallsyms_filename = path;
	}

	err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
	if (err > 0)
		pr_debug("Using %s for symbols\n", kallsyms_filename);

out_try_fixup:
	if (err > 0) {
		if (kallsyms_filename != NULL) {
			machine__mmap_name(machine, path, sizeof(path));
			dso__set_long_name(dso, strdup(path));
		}
		map__fixup_start(map);
		map__fixup_end(map);
	}

	return err;
}

void dsos__add(struct list_head *head, struct dso *dso)
{
	list_add_tail(&dso->node, head);
}

struct dso *dsos__find(struct list_head *head, const char *name)
{
	struct dso *pos;

	list_for_each_entry(pos, head, node)
		if (strcmp(pos->long_name, name) == 0)
			return pos;
	return NULL;
}

struct dso *__dsos__findnew(struct list_head *head, const char *name)
{
	struct dso *dso = dsos__find(head, name);

	if (!dso) {
		dso = dso__new(name);
		if (dso != NULL) {
			dsos__add(head, dso);
			dso__set_basename(dso);
		}
	}

	return dso;
}

size_t __dsos__fprintf(struct list_head *head, FILE *fp)
{
	struct dso *pos;
	size_t ret = 0;

	list_for_each_entry(pos, head, node) {
		int i;
		for (i = 0; i < MAP__NR_TYPES; ++i)
			ret += dso__fprintf(pos, i, fp);
	}

	return ret;
}

size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp)
{
	struct rb_node *nd;
	size_t ret = 0;

	for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
		struct machine *pos = rb_entry(nd, struct machine, rb_node);
		ret += __dsos__fprintf(&pos->kernel_dsos, fp);
		ret += __dsos__fprintf(&pos->user_dsos, fp);
	}

	return ret;
}

static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
				      bool with_hits)
{
	struct dso *pos;
	size_t ret = 0;

	list_for_each_entry(pos, head, node) {
		if (with_hits && !pos->hit)
			continue;
		ret += dso__fprintf_buildid(pos, fp);
		ret += fprintf(fp, " %s\n", pos->long_name);
	}
	return ret;
}

size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
				     bool with_hits)
{
	return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, with_hits) +
	       __dsos__fprintf_buildid(&machine->user_dsos, fp, with_hits);
}

size_t machines__fprintf_dsos_buildid(struct rb_root *machines,
				      FILE *fp, bool with_hits)
{
	struct rb_node *nd;
	size_t ret = 0;

	for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
		struct machine *pos = rb_entry(nd, struct machine, rb_node);
		ret += machine__fprintf_dsos_buildid(pos, fp, with_hits);
	}
	return ret;
}

static struct dso*
dso__kernel_findnew(struct machine *machine, const char *name,
		    const char *short_name, int dso_type)
{
	/*
	 * The kernel dso could be created by build_id processing.
	 */
	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, name);

	/*
	 * We need to run this in all cases, since during the build_id
	 * processing we had no idea this was the kernel dso.
	 */
	if (dso != NULL) {
		dso__set_short_name(dso, short_name);
		dso->kernel = dso_type;
	}

	return dso;
}

void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine)
{
	char path[PATH_MAX];

	if (machine__is_default_guest(machine))
		return;
	sprintf(path, "%s/sys/kernel/notes", machine->root_dir);
	if (sysfs__read_build_id(path, dso->build_id,
				 sizeof(dso->build_id)) == 0)
		dso->has_build_id = true;
}

static struct dso *machine__get_kernel(struct machine *machine)
{
	const char *vmlinux_name = NULL;
	struct dso *kernel;

	if (machine__is_host(machine)) {
		vmlinux_name = symbol_conf.vmlinux_name;
		if (!vmlinux_name)
			vmlinux_name = "[kernel.kallsyms]";

		kernel = dso__kernel_findnew(machine, vmlinux_name,
					     "[kernel]",
					     DSO_TYPE_KERNEL);
	} else {
		char bf[PATH_MAX];

		if (machine__is_default_guest(machine))
			vmlinux_name = symbol_conf.default_guest_vmlinux_name;
		if (!vmlinux_name)
			vmlinux_name = machine__mmap_name(machine, bf,
							  sizeof(bf));

		kernel = dso__kernel_findnew(machine, vmlinux_name,
					     "[guest.kernel]",
					     DSO_TYPE_GUEST_KERNEL);
	}

	if (kernel != NULL && (!kernel->has_build_id))
		dso__read_running_kernel_build_id(kernel, machine);

	return kernel;
}

struct process_args {
	u64 start;
};

static int symbol__in_kernel(void *arg, const char *name,
			     char type __maybe_unused, u64 start)
{
	struct process_args *args = arg;

	if (strchr(name, '['))
		return 0;

	args->start = start;
	return 1;
}

/* Figure out the start address of kernel map from /proc/kallsyms */
static u64 machine__get_kernel_start_addr(struct machine *machine)
{
	const char *filename;
	char path[PATH_MAX];
	struct process_args args;

	if (machine__is_host(machine)) {
		filename = "/proc/kallsyms";
	} else {
		if (machine__is_default_guest(machine))
			filename = (char *)symbol_conf.default_guest_kallsyms;
		else {
			sprintf(path, "%s/proc/kallsyms", machine->root_dir);
			filename = path;
		}
	}

	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
		return 0;

	if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
		return 0;

	return args.start;
}

int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
{
	enum map_type type;
	u64 start = machine__get_kernel_start_addr(machine);

	for (type = 0; type < MAP__NR_TYPES; ++type) {
		struct kmap *kmap;

		machine->vmlinux_maps[type] = map__new2(start, kernel, type);
		if (machine->vmlinux_maps[type] == NULL)
			return -1;

		machine->vmlinux_maps[type]->map_ip =
			machine->vmlinux_maps[type]->unmap_ip =
				identity__map_ip;
		kmap = map__kmap(machine->vmlinux_maps[type]);
		kmap->kmaps = &machine->kmaps;
		map_groups__insert(&machine->kmaps,
				   machine->vmlinux_maps[type]);
	}

	return 0;
}

void machine__destroy_kernel_maps(struct machine *machine)
{
	enum map_type type;

	for (type = 0; type < MAP__NR_TYPES; ++type) {
		struct kmap *kmap;

		if (machine->vmlinux_maps[type] == NULL)
			continue;

		kmap = map__kmap(machine->vmlinux_maps[type]);
		map_groups__remove(&machine->kmaps,
				   machine->vmlinux_maps[type]);
		if (kmap->ref_reloc_sym) {
			/*
			 * ref_reloc_sym is shared among all maps, so free just
			 * on one of them.
			 */
			if (type == MAP__FUNCTION) {
				free((char *)kmap->ref_reloc_sym->name);
				kmap->ref_reloc_sym->name = NULL;
				free(kmap->ref_reloc_sym);
			}
			kmap->ref_reloc_sym = NULL;
		}

		map__delete(machine->vmlinux_maps[type]);
		machine->vmlinux_maps[type] = NULL;
	}
}

int machine__create_kernel_maps(struct machine *machine)
{
	struct dso *kernel = machine__get_kernel(machine);

	if (kernel == NULL ||
	    __machine__create_kernel_maps(machine, kernel) < 0)
		return -1;

	if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
		if (machine__is_host(machine))
			pr_debug("Problems creating module maps, "
				 "continuing anyway...\n");
		else
			pr_debug("Problems creating module maps for guest %d, "
				 "continuing anyway...\n", machine->pid);
	}

	/*
	 * Now that we have all the maps created, just set the ->end of them:
	 */
	map_groups__fixup_end(&machine->kmaps);
	return 0;
}

static void vmlinux_path__exit(void)
{
	while (--vmlinux_path__nr_entries >= 0) {
		free(vmlinux_path[vmlinux_path__nr_entries]);
		vmlinux_path[vmlinux_path__nr_entries] = NULL;
	}

	free(vmlinux_path);
	vmlinux_path = NULL;
}

static int vmlinux_path__init(void)
{
	struct utsname uts;
	char bf[PATH_MAX];

	vmlinux_path = malloc(sizeof(char *) * 5);
	if (vmlinux_path == NULL)
		return -1;

	vmlinux_path[vmlinux_path__nr_entries] = strdup("vmlinux");
	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
		goto out_fail;
	++vmlinux_path__nr_entries;
	vmlinux_path[vmlinux_path__nr_entries] = strdup("/boot/vmlinux");
	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
		goto out_fail;
	++vmlinux_path__nr_entries;

	/* only try running kernel version if no symfs was given */
	if (symbol_conf.symfs[0] != 0)
		return 0;

	if (uname(&uts) < 0)
		return -1;

	snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", uts.release);
	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
		goto out_fail;
	++vmlinux_path__nr_entries;
	snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", uts.release);
	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
		goto out_fail;
	++vmlinux_path__nr_entries;
	snprintf(bf, sizeof(bf), "/usr/lib/debug/lib/modules/%s/vmlinux",
		 uts.release);
	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
		goto out_fail;
	++vmlinux_path__nr_entries;

	return 0;

out_fail:
	vmlinux_path__exit();
	return -1;
}

size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
{
	int i;
	size_t printed = 0;
	struct dso *kdso = machine->vmlinux_maps[MAP__FUNCTION]->dso;

	if (kdso->has_build_id) {
		char filename[PATH_MAX];
		if (dso__build_id_filename(kdso, filename, sizeof(filename)))
			printed += fprintf(fp, "[0] %s\n", filename);
	}

	for (i = 0; i < vmlinux_path__nr_entries; ++i)
		printed += fprintf(fp, "[%d] %s\n",
				   i + kdso->has_build_id, vmlinux_path[i]);

	return printed;
}

static int setup_list(struct strlist **list, const char *list_str,
		      const char *list_name)
{
	if (list_str == NULL)
		return 0;

	*list = strlist__new(true, list_str);
	if (!*list) {
		pr_err("problems parsing %s list\n", list_name);
		return -1;
	}
	return 0;
}

static bool symbol__read_kptr_restrict(void)
{
	bool value = false;

	if (geteuid() != 0) {
		FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r");
		if (fp != NULL) {
			char line[8];

			if (fgets(line, sizeof(line), fp) != NULL)
				value = atoi(line) != 0;

			fclose(fp);
		}
	}

	return value;
}

int symbol__init(void)
{
	const char *symfs;

	if (symbol_conf.initialized)
		return 0;

	symbol_conf.priv_size = PERF_ALIGN(symbol_conf.priv_size, sizeof(u64));

	symbol__elf_init();

	if (symbol_conf.sort_by_name)
		symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -
					  sizeof(struct symbol));

	if (symbol_conf.try_vmlinux_path && vmlinux_path__init() < 0)
		return -1;

	if (symbol_conf.field_sep && *symbol_conf.field_sep == '.') {
		pr_err("'.' is the only non valid --field-separator argument\n");
		return -1;
	}

	if (setup_list(&symbol_conf.dso_list,
		       symbol_conf.dso_list_str, "dso") < 0)
		return -1;

	if (setup_list(&symbol_conf.comm_list,
		       symbol_conf.comm_list_str, "comm") < 0)
		goto out_free_dso_list;

	if (setup_list(&symbol_conf.sym_list,
		       symbol_conf.sym_list_str, "symbol") < 0)
		goto out_free_comm_list;

	/*
	 * A path to symbols of "/" is identical to ""
	 * reset here for simplicity.
	 */
	symfs = realpath(symbol_conf.symfs, NULL);
	if (symfs == NULL)
		symfs = symbol_conf.symfs;
	if (strcmp(symfs, "/") == 0)
		symbol_conf.symfs = "";
	if (symfs != symbol_conf.symfs)
		free((void *)symfs);

	symbol_conf.kptr_restrict = symbol__read_kptr_restrict();

	symbol_conf.initialized = true;
	return 0;

out_free_comm_list:
	strlist__delete(symbol_conf.comm_list);
out_free_dso_list:
	strlist__delete(symbol_conf.dso_list);
	return -1;
}

void symbol__exit(void)
{
	if (!symbol_conf.initialized)
		return;
	strlist__delete(symbol_conf.sym_list);
	strlist__delete(symbol_conf.dso_list);
	strlist__delete(symbol_conf.comm_list);
	vmlinux_path__exit();
	symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL;
	symbol_conf.initialized = false;
}

int machines__create_kernel_maps(struct rb_root *machines, pid_t pid)
{
	struct machine *machine = machines__findnew(machines, pid);

	if (machine == NULL)
		return -1;

	return machine__create_kernel_maps(machine);
}

static int hex(char ch)
{
	if ((ch >= '0') && (ch <= '9'))
		return ch - '0';
	if ((ch >= 'a') && (ch <= 'f'))
		return ch - 'a' + 10;
	if ((ch >= 'A') && (ch <= 'F'))
		return ch - 'A' + 10;
	return -1;
}

/*
 * While we find nice hex chars, build a long_val.
 * Return number of chars processed.
 */
int hex2u64(const char *ptr, u64 *long_val)
{
	const char *p = ptr;
	*long_val = 0;

	while (*p) {
		const int hex_val = hex(*p);

		if (hex_val < 0)
			break;

		*long_val = (*long_val << 4) | hex_val;
		p++;
	}

	return p - ptr;
}

char *strxfrchar(char *s, char from, char to)
{
	char *p = s;

	while ((p = strchr(p, from)) != NULL)
		*p++ = to;

	return s;
}

int machines__create_guest_kernel_maps(struct rb_root *machines)
{
	int ret = 0;
	struct dirent **namelist = NULL;
	int i, items = 0;
	char path[PATH_MAX];
	pid_t pid;
	char *endp;

	if (symbol_conf.default_guest_vmlinux_name ||
	    symbol_conf.default_guest_modules ||
	    symbol_conf.default_guest_kallsyms) {
		machines__create_kernel_maps(machines, DEFAULT_GUEST_KERNEL_ID);
	}

	if (symbol_conf.guestmount) {
		items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL);
		if (items <= 0)
			return -ENOENT;
		for (i = 0; i < items; i++) {
			if (!isdigit(namelist[i]->d_name[0])) {
				/* Filter out . and .. */
				continue;
			}
			pid = (pid_t)strtol(namelist[i]->d_name, &endp, 10);
			if ((*endp != '\0') ||
			    (endp == namelist[i]->d_name) ||
			    (errno == ERANGE)) {
				pr_debug("invalid directory (%s). Skipping.\n",
					 namelist[i]->d_name);
				continue;
			}
			sprintf(path, "%s/%s/proc/kallsyms",
				symbol_conf.guestmount,
				namelist[i]->d_name);
			ret = access(path, R_OK);
			if (ret) {
				pr_debug("Can't access file %s\n", path);
				goto failure;
			}
			machines__create_kernel_maps(machines, pid);
		}
failure:
		free(namelist);
	}

	return ret;
}

void machines__destroy_guest_kernel_maps(struct rb_root *machines)
{
	struct rb_node *next = rb_first(machines);

	while (next) {
		struct machine *pos = rb_entry(next, struct machine, rb_node);

		next = rb_next(&pos->rb_node);
		rb_erase(&pos->rb_node, machines);
		machine__delete(pos);
	}
}

int machine__load_kallsyms(struct machine *machine, const char *filename,
			   enum map_type type, symbol_filter_t filter)
{
	struct map *map = machine->vmlinux_maps[type];
	int ret = dso__load_kallsyms(map->dso, filename, map, filter);

	if (ret > 0) {
		dso__set_loaded(map->dso, type);
		/*
		 * Since /proc/kallsyms will have multiple sessions for the
		 * kernel, with modules between them, fixup the end of all
		 * sections.
		 */
		__map_groups__fixup_end(&machine->kmaps, type);
	}

	return ret;
}

int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
			       symbol_filter_t filter)
{
	struct map *map = machine->vmlinux_maps[type];
	int ret = dso__load_vmlinux_path(map->dso, map, filter);

	if (ret > 0) {
		dso__set_loaded(map->dso, type);
		map__reloc_vmlinux(map);
	}

	return ret;
}

struct map *dso__new_map(const char *name)
{
	struct map *map = NULL;
	struct dso *dso = dso__new(name);

	if (dso)
		map = map__new2(0, dso, MAP__FUNCTION);

	return map;
}

static int open_dso(struct dso *dso, struct machine *machine)
{
	char *root_dir = (char *) "";
	char *name;
	int fd;

	name = malloc(PATH_MAX);
	if (!name)
		return -ENOMEM;

	if (machine)
		root_dir = machine->root_dir;

	if (dso__binary_type_file(dso, dso->data_type,
				  root_dir, name, PATH_MAX)) {
		free(name);
		return -EINVAL;
	}

	fd = open(name, O_RDONLY);
	free(name);
	return fd;
}

int dso__data_fd(struct dso *dso, struct machine *machine)
{
	int i = 0;

	if (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND)
		return open_dso(dso, machine);

	do {
		int fd;

		dso->data_type = binary_type_data[i++];

		fd = open_dso(dso, machine);
		if (fd >= 0)
			return fd;

	} while (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND);

	return -EINVAL;
}

static void
dso_cache__free(struct rb_root *root)
{
	struct rb_node *next = rb_first(root);

	while (next) {
		struct dso_cache *cache;

		cache = rb_entry(next, struct dso_cache, rb_node);
		next = rb_next(&cache->rb_node);
		rb_erase(&cache->rb_node, root);
		free(cache);
	}
}

static struct dso_cache*
dso_cache__find(struct rb_root *root, u64 offset)
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct dso_cache *cache;

	while (*p != NULL) {
		u64 end;

		parent = *p;
		cache = rb_entry(parent, struct dso_cache, rb_node);
		end = cache->offset + DSO__DATA_CACHE_SIZE;

		if (offset < cache->offset)
			p = &(*p)->rb_left;
		else if (offset >= end)
			p = &(*p)->rb_right;
		else
			return cache;
	}
	return NULL;
}

static void
dso_cache__insert(struct rb_root *root, struct dso_cache *new)
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct dso_cache *cache;
	u64 offset = new->offset;

	while (*p != NULL) {
		u64 end;

		parent = *p;
		cache = rb_entry(parent, struct dso_cache, rb_node);
		end = cache->offset + DSO__DATA_CACHE_SIZE;

		if (offset < cache->offset)
			p = &(*p)->rb_left;
		else if (offset >= end)
			p = &(*p)->rb_right;
	}

	rb_link_node(&new->rb_node, parent, p);
	rb_insert_color(&new->rb_node, root);
}

static ssize_t
dso_cache__memcpy(struct dso_cache *cache, u64 offset,
		  u8 *data, u64 size)
{
	u64 cache_offset = offset - cache->offset;
	u64 cache_size   = min(cache->size - cache_offset, size);

	memcpy(data, cache->data + cache_offset, cache_size);
	return cache_size;
}

static ssize_t
dso_cache__read(struct dso *dso, struct machine *machine,
		 u64 offset, u8 *data, ssize_t size)
{
	struct dso_cache *cache;
	ssize_t ret;
	int fd;

	fd = dso__data_fd(dso, machine);
	if (fd < 0)
		return -1;

	do {
		u64 cache_offset;

		ret = -ENOMEM;

		cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
		if (!cache)
			break;

		cache_offset = offset & DSO__DATA_CACHE_MASK;
		ret = -EINVAL;

		if (-1 == lseek(fd, cache_offset, SEEK_SET))
			break;

		ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE);
		if (ret <= 0)
			break;

		cache->offset = cache_offset;
		cache->size   = ret;
		dso_cache__insert(&dso->cache, cache);

		ret = dso_cache__memcpy(cache, offset, data, size);

	} while (0);

	if (ret <= 0)
		free(cache);

	close(fd);
	return ret;
}

static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
			      u64 offset, u8 *data, ssize_t size)
{
	struct dso_cache *cache;

	cache = dso_cache__find(&dso->cache, offset);
	if (cache)
		return dso_cache__memcpy(cache, offset, data, size);
	else
		return dso_cache__read(dso, machine, offset, data, size);
}

ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
			      u64 offset, u8 *data, ssize_t size)
{
	ssize_t r = 0;
	u8 *p = data;

	do {
		ssize_t ret;

		ret = dso_cache_read(dso, machine, offset, p, size);
		if (ret < 0)
			return ret;

		/* Reached EOF, return what we have. */
		if (!ret)
			break;

		BUG_ON(ret > size);

		r      += ret;
		p      += ret;
		offset += ret;
		size   -= ret;

	} while (size);

	return r;
}

ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
			    struct machine *machine, u64 addr,
			    u8 *data, ssize_t size)
{
	u64 offset = map->map_ip(map, addr);
	return dso__data_read_offset(dso, machine, offset, data, size);
}