linux/tools/perf/util/annotate-data.c

/* SPDX-License-Identifier: GPL-2.0 */
/*
 * Convert sample address to data type using DWARF debug info.
 *
 * Written by Namhyung Kim <namhyung@kernel.org>
 */

#include <stdio.h>
#include <stdlib.h>
#include <inttypes.h>

#include "annotate.h"
#include "annotate-data.h"
#include "debuginfo.h"
#include "debug.h"
#include "dso.h"
#include "dwarf-regs.h"
#include "evsel.h"
#include "evlist.h"
#include "map.h"
#include "map_symbol.h"
#include "strbuf.h"
#include "symbol.h"
#include "symbol_conf.h"
#include "thread.h"

#define pr_debug_dtp(fmt, ...)					\
do {								\
	if (debug_type_profile)					\
		pr_info(fmt, ##__VA_ARGS__);			\
	else							\
		pr_debug3(fmt, ##__VA_ARGS__);			\
} while (0)

static void pr_debug_type_name(Dwarf_Die *die)
{
	struct strbuf sb;
	char *str;

	if (!debug_type_profile && verbose < 3)
		return;

	strbuf_init(&sb, 32);
	die_get_typename_from_type(die, &sb);
	str = strbuf_detach(&sb, NULL);
	pr_info(" type=%s (die:%lx)\n", str, (long)dwarf_dieoffset(die));
	free(str);
}

/*
 * Type information in a register, valid when @ok is true.
 * The @caller_saved registers are invalidated after a function call.
 */
struct type_state_reg {
	Dwarf_Die type;
	bool ok;
	bool caller_saved;
};

/* Type information in a stack location, dynamically allocated */
struct type_state_stack {
	struct list_head list;
	Dwarf_Die type;
	int offset;
	int size;
	bool compound;
};

/* FIXME: This should be arch-dependent */
#define TYPE_STATE_MAX_REGS  16

/*
 * State table to maintain type info in each register and stack location.
 * It'll be updated when new variable is allocated or type info is moved
 * to a new location (register or stack).  As it'd be used with the
 * shortest path of basic blocks, it only maintains a single table.
 */
struct type_state {
	/* state of general purpose registers */
	struct type_state_reg regs[TYPE_STATE_MAX_REGS];
	/* state of stack location */
	struct list_head stack_vars;
	/* return value register */
	int ret_reg;
};

static bool has_reg_type(struct type_state *state, int reg)
{
	return (unsigned)reg < ARRAY_SIZE(state->regs);
}

/* These declarations will be remove once they are changed to static */
void init_type_state(struct type_state *state, struct arch *arch __maybe_unused);
void exit_type_state(struct type_state *state);
void update_var_state(struct type_state *state, struct data_loc_info *dloc,
		      u64 addr, u64 insn_offset, struct die_var_type *var_types);
void update_insn_state(struct type_state *state, struct data_loc_info *dloc,
		       Dwarf_Die *cu_die, struct disasm_line *dl);

void init_type_state(struct type_state *state, struct arch *arch)
{
	memset(state, 0, sizeof(*state));
	INIT_LIST_HEAD(&state->stack_vars);

	if (arch__is(arch, "x86")) {
		state->regs[0].caller_saved = true;
		state->regs[1].caller_saved = true;
		state->regs[2].caller_saved = true;
		state->regs[4].caller_saved = true;
		state->regs[5].caller_saved = true;
		state->regs[8].caller_saved = true;
		state->regs[9].caller_saved = true;
		state->regs[10].caller_saved = true;
		state->regs[11].caller_saved = true;
		state->ret_reg = 0;
	}
}

void exit_type_state(struct type_state *state)
{
	struct type_state_stack *stack, *tmp;

	list_for_each_entry_safe(stack, tmp, &state->stack_vars, list) {
		list_del(&stack->list);
		free(stack);
	}
}

/*
 * Compare type name and size to maintain them in a tree.
 * I'm not sure if DWARF would have information of a single type in many
 * different places (compilation units).  If not, it could compare the
 * offset of the type entry in the .debug_info section.
 */
static int data_type_cmp(const void *_key, const struct rb_node *node)
{
	const struct annotated_data_type *key = _key;
	struct annotated_data_type *type;

	type = rb_entry(node, struct annotated_data_type, node);

	if (key->self.size != type->self.size)
		return key->self.size - type->self.size;
	return strcmp(key->self.type_name, type->self.type_name);
}

static bool data_type_less(struct rb_node *node_a, const struct rb_node *node_b)
{
	struct annotated_data_type *a, *b;

	a = rb_entry(node_a, struct annotated_data_type, node);
	b = rb_entry(node_b, struct annotated_data_type, node);

	if (a->self.size != b->self.size)
		return a->self.size < b->self.size;
	return strcmp(a->self.type_name, b->self.type_name) < 0;
}

/* Recursively add new members for struct/union */
static int __add_member_cb(Dwarf_Die *die, void *arg)
{
	struct annotated_member *parent = arg;
	struct annotated_member *member;
	Dwarf_Die member_type, die_mem;
	Dwarf_Word size, loc;
	Dwarf_Attribute attr;
	struct strbuf sb;
	int tag;

	if (dwarf_tag(die) != DW_TAG_member)
		return DIE_FIND_CB_SIBLING;

	member = zalloc(sizeof(*member));
	if (member == NULL)
		return DIE_FIND_CB_END;

	strbuf_init(&sb, 32);
	die_get_typename(die, &sb);

	die_get_real_type(die, &member_type);
	if (dwarf_aggregate_size(&member_type, &size) < 0)
		size = 0;

	if (!dwarf_attr_integrate(die, DW_AT_data_member_location, &attr))
		loc = 0;
	else
		dwarf_formudata(&attr, &loc);

	member->type_name = strbuf_detach(&sb, NULL);
	/* member->var_name can be NULL */
	if (dwarf_diename(die))
		member->var_name = strdup(dwarf_diename(die));
	member->size = size;
	member->offset = loc + parent->offset;
	INIT_LIST_HEAD(&member->children);
	list_add_tail(&member->node, &parent->children);

	tag = dwarf_tag(&member_type);
	switch (tag) {
	case DW_TAG_structure_type:
	case DW_TAG_union_type:
		die_find_child(&member_type, __add_member_cb, member, &die_mem);
		break;
	default:
		break;
	}
	return DIE_FIND_CB_SIBLING;
}

static void add_member_types(struct annotated_data_type *parent, Dwarf_Die *type)
{
	Dwarf_Die die_mem;

	die_find_child(type, __add_member_cb, &parent->self, &die_mem);
}

static void delete_members(struct annotated_member *member)
{
	struct annotated_member *child, *tmp;

	list_for_each_entry_safe(child, tmp, &member->children, node) {
		list_del(&child->node);
		delete_members(child);
		free(child->type_name);
		free(child->var_name);
		free(child);
	}
}

static struct annotated_data_type *dso__findnew_data_type(struct dso *dso,
							  Dwarf_Die *type_die)
{
	struct annotated_data_type *result = NULL;
	struct annotated_data_type key;
	struct rb_node *node;
	struct strbuf sb;
	char *type_name;
	Dwarf_Word size;

	strbuf_init(&sb, 32);
	if (die_get_typename_from_type(type_die, &sb) < 0)
		strbuf_add(&sb, "(unknown type)", 14);
	type_name = strbuf_detach(&sb, NULL);
	dwarf_aggregate_size(type_die, &size);

	/* Check existing nodes in dso->data_types tree */
	key.self.type_name = type_name;
	key.self.size = size;
	node = rb_find(&key, &dso->data_types, data_type_cmp);
	if (node) {
		result = rb_entry(node, struct annotated_data_type, node);
		free(type_name);
		return result;
	}

	/* If not, add a new one */
	result = zalloc(sizeof(*result));
	if (result == NULL) {
		free(type_name);
		return NULL;
	}

	result->self.type_name = type_name;
	result->self.size = size;
	INIT_LIST_HEAD(&result->self.children);

	if (symbol_conf.annotate_data_member)
		add_member_types(result, type_die);

	rb_add(&result->node, &dso->data_types, data_type_less);
	return result;
}

static bool find_cu_die(struct debuginfo *di, u64 pc, Dwarf_Die *cu_die)
{
	Dwarf_Off off, next_off;
	size_t header_size;

	if (dwarf_addrdie(di->dbg, pc, cu_die) != NULL)
		return cu_die;

	/*
	 * There are some kernels don't have full aranges and contain only a few
	 * aranges entries.  Fallback to iterate all CU entries in .debug_info
	 * in case it's missing.
	 */
	off = 0;
	while (dwarf_nextcu(di->dbg, off, &next_off, &header_size,
			    NULL, NULL, NULL) == 0) {
		if (dwarf_offdie(di->dbg, off + header_size, cu_die) &&
		    dwarf_haspc(cu_die, pc))
			return true;

		off = next_off;
	}
	return false;
}

/* The type info will be saved in @type_die */
static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset,
			  bool is_pointer)
{
	Dwarf_Word size;

	/* Get the type of the variable */
	if (die_get_real_type(var_die, type_die) == NULL) {
		pr_debug_dtp("variable has no type\n");
		ann_data_stat.no_typeinfo++;
		return -1;
	}

	/*
	 * Usually it expects a pointer type for a memory access.
	 * Convert to a real type it points to.  But global variables
	 * and local variables are accessed directly without a pointer.
	 */
	if (is_pointer) {
		if ((dwarf_tag(type_die) != DW_TAG_pointer_type &&
		     dwarf_tag(type_die) != DW_TAG_array_type) ||
		    die_get_real_type(type_die, type_die) == NULL) {
			pr_debug_dtp("no pointer or no type\n");
			ann_data_stat.no_typeinfo++;
			return -1;
		}
	}

	/* Get the size of the actual type */
	if (dwarf_aggregate_size(type_die, &size) < 0) {
		pr_debug_dtp("type size is unknown\n");
		ann_data_stat.invalid_size++;
		return -1;
	}

	/* Minimal sanity check */
	if ((unsigned)offset >= size) {
		pr_debug_dtp("offset: %d is bigger than size: %"PRIu64"\n",
			     offset, size);
		ann_data_stat.bad_offset++;
		return -1;
	}

	return 0;
}

static struct type_state_stack *find_stack_state(struct type_state *state,
						 int offset)
{
	struct type_state_stack *stack;

	list_for_each_entry(stack, &state->stack_vars, list) {
		if (offset == stack->offset)
			return stack;

		if (stack->compound && stack->offset < offset &&
		    offset < stack->offset + stack->size)
			return stack;
	}
	return NULL;
}

static void set_stack_state(struct type_state_stack *stack, int offset,
			    Dwarf_Die *type_die)
{
	int tag;
	Dwarf_Word size;

	if (dwarf_aggregate_size(type_die, &size) < 0)
		size = 0;

	tag = dwarf_tag(type_die);

	stack->type = *type_die;
	stack->size = size;
	stack->offset = offset;

	switch (tag) {
	case DW_TAG_structure_type:
	case DW_TAG_union_type:
		stack->compound = true;
		break;
	default:
		stack->compound = false;
		break;
	}
}

static struct type_state_stack *findnew_stack_state(struct type_state *state,
						    int offset, Dwarf_Die *type_die)
{
	struct type_state_stack *stack = find_stack_state(state, offset);

	if (stack) {
		set_stack_state(stack, offset, type_die);
		return stack;
	}

	stack = malloc(sizeof(*stack));
	if (stack) {
		set_stack_state(stack, offset, type_die);
		list_add(&stack->list, &state->stack_vars);
	}
	return stack;
}

static bool get_global_var_type(Dwarf_Die *cu_die, struct data_loc_info *dloc,
				u64 ip, u64 var_addr, int *var_offset,
				Dwarf_Die *type_die)
{
	u64 pc, mem_addr;
	int offset;
	bool is_pointer = false;
	const char *var_name = NULL;
	Dwarf_Die var_die;
	struct addr_location al;
	struct symbol *sym;

	/* Try to get the variable by address first */
	if (die_find_variable_by_addr(cu_die, var_addr, &var_die, &offset) &&
	    check_variable(&var_die, type_die, offset, is_pointer) == 0) {
		*var_offset = offset;
		return true;
	}

	/* Kernel symbols might be relocated */
	mem_addr = var_addr + map__reloc(dloc->ms->map);

	addr_location__init(&al);
	sym = thread__find_symbol_fb(dloc->thread, dloc->cpumode,
				     mem_addr, &al);
	if (sym) {
		var_name = sym->name;
		/* Calculate type offset from the start of variable */
		*var_offset = mem_addr - map__unmap_ip(al.map, sym->start);
	}
	addr_location__exit(&al);
	if (var_name == NULL)
		return false;

	pc = map__rip_2objdump(dloc->ms->map, ip);

	/* Try to get the name of global variable */
	if (die_find_variable_at(cu_die, var_name, pc, &var_die) &&
	    check_variable(&var_die, type_die, *var_offset, is_pointer) == 0)
		return true;

	return false;
}

/**
 * update_var_state - Update type state using given variables
 * @state: type state table
 * @dloc: data location info
 * @addr: instruction address to match with variable
 * @insn_offset: instruction offset (for debug)
 * @var_types: list of variables with type info
 *
 * This function fills the @state table using @var_types info.  Each variable
 * is used only at the given location and updates an entry in the table.
 */
void update_var_state(struct type_state *state, struct data_loc_info *dloc,
		      u64 addr, u64 insn_offset, struct die_var_type *var_types)
{
	Dwarf_Die mem_die;
	struct die_var_type *var;
	int fbreg = dloc->fbreg;
	int fb_offset = 0;

	if (dloc->fb_cfa) {
		if (die_get_cfa(dloc->di->dbg, addr, &fbreg, &fb_offset) < 0)
			fbreg = -1;
	}

	for (var = var_types; var != NULL; var = var->next) {
		if (var->addr != addr)
			continue;
		/* Get the type DIE using the offset */
		if (!dwarf_offdie(dloc->di->dbg, var->die_off, &mem_die))
			continue;

		if (var->reg == DWARF_REG_FB) {
			findnew_stack_state(state, var->offset, &mem_die);

			pr_debug_dtp("var [%"PRIx64"] -%#x(stack)",
				     insn_offset, -var->offset);
			pr_debug_type_name(&mem_die);
		} else if (var->reg == fbreg) {
			findnew_stack_state(state, var->offset - fb_offset, &mem_die);

			pr_debug_dtp("var [%"PRIx64"] -%#x(stack)",
				     insn_offset, -var->offset + fb_offset);
			pr_debug_type_name(&mem_die);
		} else if (has_reg_type(state, var->reg) && var->offset == 0) {
			struct type_state_reg *reg;

			reg = &state->regs[var->reg];
			reg->type = mem_die;
			reg->ok = true;

			pr_debug_dtp("var [%"PRIx64"] reg%d",
				     insn_offset, var->reg);
			pr_debug_type_name(&mem_die);
		}
	}
}

static void update_insn_state_x86(struct type_state *state,
				  struct data_loc_info *dloc, Dwarf_Die *cu_die,
				  struct disasm_line *dl)
{
	struct annotated_insn_loc loc;
	struct annotated_op_loc *src = &loc.ops[INSN_OP_SOURCE];
	struct annotated_op_loc *dst = &loc.ops[INSN_OP_TARGET];
	struct type_state_reg *tsr;
	Dwarf_Die type_die;
	u32 insn_offset = dl->al.offset;
	int fbreg = dloc->fbreg;
	int fboff = 0;

	if (annotate_get_insn_location(dloc->arch, dl, &loc) < 0)
		return;

	if (ins__is_call(&dl->ins)) {
		struct symbol *func = dl->ops.target.sym;

		if (func == NULL)
			return;

		/* __fentry__ will preserve all registers */
		if (!strcmp(func->name, "__fentry__"))
			return;

		pr_debug_dtp("call [%x] %s\n", insn_offset, func->name);

		/* Otherwise invalidate caller-saved registers after call */
		for (unsigned i = 0; i < ARRAY_SIZE(state->regs); i++) {
			if (state->regs[i].caller_saved)
				state->regs[i].ok = false;
		}

		/* Update register with the return type (if any) */
		if (die_find_func_rettype(cu_die, func->name, &type_die)) {
			tsr = &state->regs[state->ret_reg];
			tsr->type = type_die;
			tsr->ok = true;

			pr_debug_dtp("call [%x] return -> reg%d",
				     insn_offset, state->ret_reg);
			pr_debug_type_name(&type_die);
		}
		return;
	}

	if (strncmp(dl->ins.name, "mov", 3))
		return;

	if (dloc->fb_cfa) {
		u64 ip = dloc->ms->sym->start + dl->al.offset;
		u64 pc = map__rip_2objdump(dloc->ms->map, ip);

		if (die_get_cfa(dloc->di->dbg, pc, &fbreg, &fboff) < 0)
			fbreg = -1;
	}

	/* Case 1. register to register transfers */
	if (!src->mem_ref && !dst->mem_ref) {
		if (!has_reg_type(state, dst->reg1))
			return;

		tsr = &state->regs[dst->reg1];
		if (!has_reg_type(state, src->reg1) ||
		    !state->regs[src->reg1].ok) {
			tsr->ok = false;
			return;
		}

		tsr->type = state->regs[src->reg1].type;
		tsr->ok = true;

		pr_debug_dtp("mov [%x] reg%d -> reg%d",
			     insn_offset, src->reg1, dst->reg1);
		pr_debug_type_name(&tsr->type);
	}
	/* Case 2. memory to register transers */
	if (src->mem_ref && !dst->mem_ref) {
		int sreg = src->reg1;

		if (!has_reg_type(state, dst->reg1))
			return;

		tsr = &state->regs[dst->reg1];

retry:
		/* Check stack variables with offset */
		if (sreg == fbreg) {
			struct type_state_stack *stack;
			int offset = src->offset - fboff;

			stack = find_stack_state(state, offset);
			if (stack == NULL) {
				tsr->ok = false;
				return;
			} else if (!stack->compound) {
				tsr->type = stack->type;
				tsr->ok = true;
			} else if (die_get_member_type(&stack->type,
						       offset - stack->offset,
						       &type_die)) {
				tsr->type = type_die;
				tsr->ok = true;
			} else {
				tsr->ok = false;
				return;
			}

			pr_debug_dtp("mov [%x] -%#x(stack) -> reg%d",
				     insn_offset, -offset, dst->reg1);
			pr_debug_type_name(&tsr->type);
		}
		/* And then dereference the pointer if it has one */
		else if (has_reg_type(state, sreg) && state->regs[sreg].ok &&
			 die_deref_ptr_type(&state->regs[sreg].type,
					    src->offset, &type_die)) {
			tsr->type = type_die;
			tsr->ok = true;

			pr_debug_dtp("mov [%x] %#x(reg%d) -> reg%d",
				     insn_offset, src->offset, sreg, dst->reg1);
			pr_debug_type_name(&tsr->type);
		}
		/* Or check if it's a global variable */
		else if (sreg == DWARF_REG_PC) {
			struct map_symbol *ms = dloc->ms;
			u64 ip = ms->sym->start + dl->al.offset;
			u64 addr;
			int offset;

			addr = annotate_calc_pcrel(ms, ip, src->offset, dl);

			if (!get_global_var_type(cu_die, dloc, ip, addr, &offset,
						 &type_die) ||
			    !die_get_member_type(&type_die, offset, &type_die)) {
				tsr->ok = false;
				return;
			}

			tsr->type = type_die;
			tsr->ok = true;

			pr_debug_dtp("mov [%x] global addr=%"PRIx64" -> reg%d",
				     insn_offset, addr, dst->reg1);
			pr_debug_type_name(&type_die);
		}
		/* Or try another register if any */
		else if (src->multi_regs && sreg == src->reg1 &&
			 src->reg1 != src->reg2) {
			sreg = src->reg2;
			goto retry;
		}
		/* It failed to get a type info, mark it as invalid */
		else {
			tsr->ok = false;
		}
	}
	/* Case 3. register to memory transfers */
	if (!src->mem_ref && dst->mem_ref) {
		if (!has_reg_type(state, src->reg1) ||
		    !state->regs[src->reg1].ok)
			return;

		/* Check stack variables with offset */
		if (dst->reg1 == fbreg) {
			struct type_state_stack *stack;
			int offset = dst->offset - fboff;

			stack = find_stack_state(state, offset);
			if (stack) {
				/*
				 * The source register is likely to hold a type
				 * of member if it's a compound type.  Do not
				 * update the stack variable type since we can
				 * get the member type later by using the
				 * die_get_member_type().
				 */
				if (!stack->compound)
					set_stack_state(stack, offset,
							&state->regs[src->reg1].type);
			} else {
				findnew_stack_state(state, offset,
						    &state->regs[src->reg1].type);
			}

			pr_debug_dtp("mov [%x] reg%d -> -%#x(stack)",
				     insn_offset, src->reg1, -offset);
			pr_debug_type_name(&state->regs[src->reg1].type);
		}
		/*
		 * Ignore other transfers since it'd set a value in a struct
		 * and won't change the type.
		 */
	}
	/* Case 4. memory to memory transfers (not handled for now) */
}

/**
 * update_insn_state - Update type state for an instruction
 * @state: type state table
 * @dloc: data location info
 * @cu_die: compile unit debug entry
 * @dl: disasm line for the instruction
 *
 * This function updates the @state table for the target operand of the
 * instruction at @dl if it transfers the type like MOV on x86.  Since it
 * tracks the type, it won't care about the values like in arithmetic
 * instructions like ADD/SUB/MUL/DIV and INC/DEC.
 *
 * Note that ops->reg2 is only available when both mem_ref and multi_regs
 * are true.
 */
void update_insn_state(struct type_state *state, struct data_loc_info *dloc,
		       Dwarf_Die *cu_die, struct disasm_line *dl)
{
	if (arch__is(dloc->arch, "x86"))
		update_insn_state_x86(state, dloc, cu_die, dl);
}

/* The result will be saved in @type_die */
static int find_data_type_die(struct data_loc_info *dloc, Dwarf_Die *type_die)
{
	struct annotated_op_loc *loc = dloc->op;
	Dwarf_Die cu_die, var_die;
	Dwarf_Die *scopes = NULL;
	int reg, offset;
	int ret = -1;
	int i, nr_scopes;
	int fbreg = -1;
	int fb_offset = 0;
	bool is_fbreg = false;
	u64 pc;
	char buf[64];

	if (dloc->op->multi_regs)
		snprintf(buf, sizeof(buf), " or reg%d", dloc->op->reg2);
	else if (dloc->op->reg1 == DWARF_REG_PC)
		snprintf(buf, sizeof(buf), " (PC)");
	else
		buf[0] = '\0';

	pr_debug_dtp("-----------------------------------------------------------\n");
	pr_debug_dtp("%s [%"PRIx64"] for reg%d%s offset=%#x in %s\n",
		     __func__, dloc->ip - dloc->ms->sym->start,
		     dloc->op->reg1, buf, dloc->op->offset, dloc->ms->sym->name);

	/*
	 * IP is a relative instruction address from the start of the map, as
	 * it can be randomized/relocated, it needs to translate to PC which is
	 * a file address for DWARF processing.
	 */
	pc = map__rip_2objdump(dloc->ms->map, dloc->ip);

	/* Get a compile_unit for this address */
	if (!find_cu_die(dloc->di, pc, &cu_die)) {
		pr_debug_dtp("cannot find CU for address %"PRIx64"\n", pc);
		ann_data_stat.no_cuinfo++;
		return -1;
	}

	reg = loc->reg1;
	offset = loc->offset;

	pr_debug_dtp("CU die offset: %#lx\n", (long)dwarf_dieoffset(&cu_die));

	if (reg == DWARF_REG_PC) {
		if (get_global_var_type(&cu_die, dloc, dloc->ip, dloc->var_addr,
					&offset, type_die)) {
			dloc->type_offset = offset;

			pr_debug_dtp("found PC-rel by addr=%#"PRIx64" offset=%#x\n",
				     dloc->var_addr, offset);
			goto out;
		}
	}

	/* Get a list of nested scopes - i.e. (inlined) functions and blocks. */
	nr_scopes = die_get_scopes(&cu_die, pc, &scopes);

	if (reg != DWARF_REG_PC && dwarf_hasattr(&scopes[0], DW_AT_frame_base)) {
		Dwarf_Attribute attr;
		Dwarf_Block block;

		/* Check if the 'reg' is assigned as frame base register */
		if (dwarf_attr(&scopes[0], DW_AT_frame_base, &attr) != NULL &&
		    dwarf_formblock(&attr, &block) == 0 && block.length == 1) {
			switch (*block.data) {
			case DW_OP_reg0 ... DW_OP_reg31:
				fbreg = dloc->fbreg = *block.data - DW_OP_reg0;
				break;
			case DW_OP_call_frame_cfa:
				dloc->fb_cfa = true;
				if (die_get_cfa(dloc->di->dbg, pc, &fbreg,
						&fb_offset) < 0)
					fbreg = -1;
				break;
			default:
				break;
			}

			pr_debug_dtp("frame base: cfa=%d fbreg=%d\n",
				     dloc->fb_cfa, fbreg);
		}
	}

retry:
	is_fbreg = (reg == fbreg);
	if (is_fbreg)
		offset = loc->offset - fb_offset;

	/* Search from the inner-most scope to the outer */
	for (i = nr_scopes - 1; i >= 0; i--) {
		if (reg == DWARF_REG_PC) {
			if (!die_find_variable_by_addr(&scopes[i], dloc->var_addr,
						       &var_die, &offset))
				continue;
		} else {
			/* Look up variables/parameters in this scope */
			if (!die_find_variable_by_reg(&scopes[i], pc, reg,
						      &offset, is_fbreg, &var_die))
				continue;
		}

		/* Found a variable, see if it's correct */
		ret = check_variable(&var_die, type_die, offset,
				     reg != DWARF_REG_PC && !is_fbreg);
		if (ret == 0) {
			pr_debug_dtp("found \"%s\" in scope=%d/%d (die: %#lx) ",
				     dwarf_diename(&var_die), i+1, nr_scopes,
				     (long)dwarf_dieoffset(&scopes[i]));
			if (reg == DWARF_REG_PC)
				pr_debug_dtp("%#x(PC) offset=%#x", loc->offset, offset);
			else if (reg == DWARF_REG_FB || is_fbreg)
				pr_debug_dtp("%#x(reg%d) stack fb_offset=%#x offset=%#x",
					     loc->offset, reg, fb_offset, offset);
			else
				pr_debug_dtp("%#x(reg%d)", loc->offset, reg);
			pr_debug_type_name(type_die);
		}
		dloc->type_offset = offset;
		goto out;
	}

	if (loc->multi_regs && reg == loc->reg1 && loc->reg1 != loc->reg2) {
		reg = loc->reg2;
		goto retry;
	}

	if (ret < 0) {
		pr_debug_dtp("no variable found\n");
		ann_data_stat.no_var++;
	}

out:
	free(scopes);
	return ret;
}

/**
 * find_data_type - Return a data type at the location
 * @dloc: data location
 *
 * This functions searches the debug information of the binary to get the data
 * type it accesses.  The exact location is expressed by (ip, reg, offset)
 * for pointer variables or (ip, addr) for global variables.  Note that global
 * variables might update the @dloc->type_offset after finding the start of the
 * variable.  If it cannot find a global variable by address, it tried to find
 * a declaration of the variable using var_name.  In that case, @dloc->offset
 * won't be updated.
 *
 * It return %NULL if not found.
 */
struct annotated_data_type *find_data_type(struct data_loc_info *dloc)
{
	struct annotated_data_type *result = NULL;
	struct dso *dso = map__dso(dloc->ms->map);
	Dwarf_Die type_die;

	dloc->di = debuginfo__new(dso->long_name);
	if (dloc->di == NULL) {
		pr_debug_dtp("cannot get the debug info\n");
		return NULL;
	}

	/*
	 * The type offset is the same as instruction offset by default.
	 * But when finding a global variable, the offset won't be valid.
	 */
	dloc->type_offset = dloc->op->offset;

	dloc->fbreg = -1;

	if (find_data_type_die(dloc, &type_die) < 0)
		goto out;

	result = dso__findnew_data_type(dso, &type_die);

out:
	debuginfo__delete(dloc->di);
	return result;
}

static int alloc_data_type_histograms(struct annotated_data_type *adt, int nr_entries)
{
	int i;
	size_t sz = sizeof(struct type_hist);

	sz += sizeof(struct type_hist_entry) * adt->self.size;

	/* Allocate a table of pointers for each event */
	adt->nr_histograms = nr_entries;
	adt->histograms = calloc(nr_entries, sizeof(*adt->histograms));
	if (adt->histograms == NULL)
		return -ENOMEM;

	/*
	 * Each histogram is allocated for the whole size of the type.
	 * TODO: Probably we can move the histogram to members.
	 */
	for (i = 0; i < nr_entries; i++) {
		adt->histograms[i] = zalloc(sz);
		if (adt->histograms[i] == NULL)
			goto err;
	}
	return 0;

err:
	while (--i >= 0)
		free(adt->histograms[i]);
	free(adt->histograms);
	return -ENOMEM;
}

static void delete_data_type_histograms(struct annotated_data_type *adt)
{
	for (int i = 0; i < adt->nr_histograms; i++)
		free(adt->histograms[i]);
	free(adt->histograms);
}

void annotated_data_type__tree_delete(struct rb_root *root)
{
	struct annotated_data_type *pos;

	while (!RB_EMPTY_ROOT(root)) {
		struct rb_node *node = rb_first(root);

		rb_erase(node, root);
		pos = rb_entry(node, struct annotated_data_type, node);
		delete_members(&pos->self);
		delete_data_type_histograms(pos);
		free(pos->self.type_name);
		free(pos);
	}
}

/**
 * annotated_data_type__update_samples - Update histogram
 * @adt: Data type to update
 * @evsel: Event to update
 * @offset: Offset in the type
 * @nr_samples: Number of samples at this offset
 * @period: Event count at this offset
 *
 * This function updates type histogram at @ofs for @evsel.  Samples are
 * aggregated before calling this function so it can be called with more
 * than one samples at a certain offset.
 */
int annotated_data_type__update_samples(struct annotated_data_type *adt,
					struct evsel *evsel, int offset,
					int nr_samples, u64 period)
{
	struct type_hist *h;

	if (adt == NULL)
		return 0;

	if (adt->histograms == NULL) {
		int nr = evsel->evlist->core.nr_entries;

		if (alloc_data_type_histograms(adt, nr) < 0)
			return -1;
	}

	if (offset < 0 || offset >= adt->self.size)
		return -1;

	h = adt->histograms[evsel->core.idx];

	h->nr_samples += nr_samples;
	h->addr[offset].nr_samples += nr_samples;
	h->period += period;
	h->addr[offset].period += period;
	return 0;
}