Adding upstream version 6.10.3.upstream/6.10.3

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

98 files changed, 7765 insertions, 4118 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index e0a723e245..da64efd871 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -12,6 +12,7 @@ perf-y += config.o
 perf-y += copyfile.o
 perf-y += ctype.o
 perf-y += db-export.o
+perf-y += disasm.o
 perf-y += env.o
 perf-y += event.o
 perf-y += evlist.o
@@ -140,6 +141,7 @@ perf-y += term.o
 perf-y += help-unknown-cmd.o
 perf-y += dlfilter.o
 perf-y += mem-events.o
+perf-y += mem-info.o
 perf-y += vsprintf.o
 perf-y += units.o
 perf-y += time-utils.o
@@ -388,3 +390,17 @@ $(OUTPUT)util/vsprintf.o: ../lib/vsprintf.c FORCE
 $(OUTPUT)util/list_sort.o: ../lib/list_sort.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
+
+ifdef SHELLCHECK
+  SHELL_TESTS := generate-cmdlist.sh
+  TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log)
+else
+  SHELL_TESTS :=
+  TEST_LOGS :=
+endif
+
+$(OUTPUT)%.shellcheck_log: %
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,test)shellcheck -a -S warning "$<" > $@ || (cat $@ && rm $@ && false)
+
+perf-y += $(TEST_LOGS)
diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index 30c4d19fcf..965da6c0b5 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -8,6 +8,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <inttypes.h>
+#include <linux/zalloc.h>
 
 #include "annotate.h"
 #include "annotate-data.h"
@@ -19,9 +20,202 @@
 #include "evlist.h"
 #include "map.h"
 #include "map_symbol.h"
+#include "sort.h"
 #include "strbuf.h"
 #include "symbol.h"
 #include "symbol_conf.h"
+#include "thread.h"
+
+/* register number of the stack pointer */
+#define X86_REG_SP 7
+
+static void delete_var_types(struct die_var_type *var_types);
+
+enum type_state_kind {
+	TSR_KIND_INVALID = 0,
+	TSR_KIND_TYPE,
+	TSR_KIND_PERCPU_BASE,
+	TSR_KIND_CONST,
+	TSR_KIND_POINTER,
+	TSR_KIND_CANARY,
+};
+
+#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, enum type_state_kind kind)
+{
+	struct strbuf sb;
+	char *str;
+	Dwarf_Word size = 0;
+
+	if (!debug_type_profile && verbose < 3)
+		return;
+
+	switch (kind) {
+	case TSR_KIND_INVALID:
+		pr_info("\n");
+		return;
+	case TSR_KIND_PERCPU_BASE:
+		pr_info(" percpu base\n");
+		return;
+	case TSR_KIND_CONST:
+		pr_info(" constant\n");
+		return;
+	case TSR_KIND_POINTER:
+		pr_info(" pointer");
+		/* it also prints the type info */
+		break;
+	case TSR_KIND_CANARY:
+		pr_info(" stack canary\n");
+		return;
+	case TSR_KIND_TYPE:
+	default:
+		break;
+	}
+
+	dwarf_aggregate_size(die, &size);
+
+	strbuf_init(&sb, 32);
+	die_get_typename_from_type(die, &sb);
+	str = strbuf_detach(&sb, NULL);
+	pr_info(" type='%s' size=%#lx (die:%#lx)\n",
+		str, (long)size, (long)dwarf_dieoffset(die));
+	free(str);
+}
+
+static void pr_debug_location(Dwarf_Die *die, u64 pc, int reg)
+{
+	ptrdiff_t off = 0;
+	Dwarf_Attribute attr;
+	Dwarf_Addr base, start, end;
+	Dwarf_Op *ops;
+	size_t nops;
+
+	if (!debug_type_profile && verbose < 3)
+		return;
+
+	if (dwarf_attr(die, DW_AT_location, &attr) == NULL)
+		return;
+
+	while ((off = dwarf_getlocations(&attr, off, &base, &start, &end, &ops, &nops)) > 0) {
+		if (reg != DWARF_REG_PC && end < pc)
+			continue;
+		if (reg != DWARF_REG_PC && start > pc)
+			break;
+
+		pr_info(" variable location: ");
+		switch (ops->atom) {
+		case DW_OP_reg0 ...DW_OP_reg31:
+			pr_info("reg%d\n", ops->atom - DW_OP_reg0);
+			break;
+		case DW_OP_breg0 ...DW_OP_breg31:
+			pr_info("base=reg%d, offset=%#lx\n",
+				ops->atom - DW_OP_breg0, (long)ops->number);
+			break;
+		case DW_OP_regx:
+			pr_info("reg%ld\n", (long)ops->number);
+			break;
+		case DW_OP_bregx:
+			pr_info("base=reg%ld, offset=%#lx\n",
+				(long)ops->number, (long)ops->number2);
+			break;
+		case DW_OP_fbreg:
+			pr_info("use frame base, offset=%#lx\n", (long)ops->number);
+			break;
+		case DW_OP_addr:
+			pr_info("address=%#lx\n", (long)ops->number);
+			break;
+		default:
+			pr_info("unknown: code=%#x, number=%#lx\n",
+				ops->atom, (long)ops->number);
+			break;
+		}
+		break;
+	}
+}
+
+/*
+ * 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;
+	u32 imm_value;
+	bool ok;
+	bool caller_saved;
+	u8 kind;
+};
+
+/* 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;
+	u8 kind;
+};
+
+/* 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;
+	/* stack pointer register */
+	int stack_reg;
+};
+
+static bool has_reg_type(struct type_state *state, int reg)
+{
+	return (unsigned)reg < ARRAY_SIZE(state->regs);
+}
+
+static 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;
+		state->stack_reg = X86_REG_SP;
+	}
+}
+
+static 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.
@@ -118,8 +312,8 @@ static void delete_members(struct annotated_member *member)
 	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);
+		zfree(&child->type_name);
+		zfree(&child->var_name);
 		free(child);
 	}
 }
@@ -143,7 +337,7 @@ static struct annotated_data_type *dso__findnew_data_type(struct dso *dso,
 	/* 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);
+	node = rb_find(&key, dso__data_types(dso), data_type_cmp);
 	if (node) {
 		result = rb_entry(node, struct annotated_data_type, node);
 		free(type_name);
@@ -164,7 +358,7 @@ static struct annotated_data_type *dso__findnew_data_type(struct dso *dso,
 	if (symbol_conf.annotate_data_member)
 		add_member_types(result, type_die);
 
-	rb_add(&result->node, &dso->data_types, data_type_less);
+	rb_add(&result->node, dso__data_types(dso), data_type_less);
 	return result;
 }
 
@@ -194,14 +388,22 @@ static bool find_cu_die(struct debuginfo *di, u64 pc, Dwarf_Die *cu_die)
 }
 
 /* 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)
+static int check_variable(struct data_loc_info *dloc, Dwarf_Die *var_die,
+			  Dwarf_Die *type_die, int reg, int offset, bool is_fbreg)
 {
 	Dwarf_Word size;
+	bool is_pointer = true;
+
+	if (reg == DWARF_REG_PC)
+		is_pointer = false;
+	else if (reg == dloc->fbreg || is_fbreg)
+		is_pointer = false;
+	else if (arch__is(dloc->arch, "x86") && reg == X86_REG_SP)
+		is_pointer = false;
 
 	/* Get the type of the variable */
 	if (die_get_real_type(var_die, type_die) == NULL) {
-		pr_debug("variable has no type\n");
+		pr_debug_dtp("variable has no type\n");
 		ann_data_stat.no_typeinfo++;
 		return -1;
 	}
@@ -215,7 +417,7 @@ static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset,
 		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("no pointer or no type\n");
+			pr_debug_dtp("no pointer or no type\n");
 			ann_data_stat.no_typeinfo++;
 			return -1;
 		}
@@ -223,14 +425,15 @@ static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset,
 
 	/* Get the size of the actual type */
 	if (dwarf_aggregate_size(type_die, &size) < 0) {
-		pr_debug("type size is unknown\n");
+		pr_debug_dtp("type size is unknown\n");
 		ann_data_stat.invalid_size++;
 		return -1;
 	}
 
 	/* Minimal sanity check */
 	if ((unsigned)offset >= size) {
-		pr_debug("offset: %d is bigger than size: %" PRIu64 "\n", offset, size);
+		pr_debug_dtp("offset: %d is bigger than size: %"PRIu64"\n",
+			     offset, size);
 		ann_data_stat.bad_offset++;
 		return -1;
 	}
@@ -238,23 +441,1191 @@ static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset,
 	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, u8 kind,
+			    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;
+	stack->kind = kind;
+
+	switch (tag) {
+	case DW_TAG_structure_type:
+	case DW_TAG_union_type:
+		stack->compound = (kind != TSR_KIND_POINTER);
+		break;
+	default:
+		stack->compound = false;
+		break;
+	}
+}
+
+static struct type_state_stack *findnew_stack_state(struct type_state *state,
+						    int offset, u8 kind,
+						    Dwarf_Die *type_die)
+{
+	struct type_state_stack *stack = find_stack_state(state, offset);
+
+	if (stack) {
+		set_stack_state(stack, offset, kind, type_die);
+		return stack;
+	}
+
+	stack = malloc(sizeof(*stack));
+	if (stack) {
+		set_stack_state(stack, offset, kind, type_die);
+		list_add(&stack->list, &state->stack_vars);
+	}
+	return stack;
+}
+
+/* Maintain a cache for quick global variable lookup */
+struct global_var_entry {
+	struct rb_node node;
+	char *name;
+	u64 start;
+	u64 end;
+	u64 die_offset;
+};
+
+static int global_var_cmp(const void *_key, const struct rb_node *node)
+{
+	const u64 addr = (uintptr_t)_key;
+	struct global_var_entry *gvar;
+
+	gvar = rb_entry(node, struct global_var_entry, node);
+
+	if (gvar->start <= addr && addr < gvar->end)
+		return 0;
+	return gvar->start > addr ? -1 : 1;
+}
+
+static bool global_var_less(struct rb_node *node_a, const struct rb_node *node_b)
+{
+	struct global_var_entry *gvar_a, *gvar_b;
+
+	gvar_a = rb_entry(node_a, struct global_var_entry, node);
+	gvar_b = rb_entry(node_b, struct global_var_entry, node);
+
+	return gvar_a->start < gvar_b->start;
+}
+
+static struct global_var_entry *global_var__find(struct data_loc_info *dloc, u64 addr)
+{
+	struct dso *dso = map__dso(dloc->ms->map);
+	struct rb_node *node;
+
+	node = rb_find((void *)(uintptr_t)addr, dso__global_vars(dso), global_var_cmp);
+	if (node == NULL)
+		return NULL;
+
+	return rb_entry(node, struct global_var_entry, node);
+}
+
+static bool global_var__add(struct data_loc_info *dloc, u64 addr,
+			    const char *name, Dwarf_Die *type_die)
+{
+	struct dso *dso = map__dso(dloc->ms->map);
+	struct global_var_entry *gvar;
+	Dwarf_Word size;
+
+	if (dwarf_aggregate_size(type_die, &size) < 0)
+		return false;
+
+	gvar = malloc(sizeof(*gvar));
+	if (gvar == NULL)
+		return false;
+
+	gvar->name = name ? strdup(name) : NULL;
+	if (name && gvar->name == NULL) {
+		free(gvar);
+		return false;
+	}
+
+	gvar->start = addr;
+	gvar->end = addr + size;
+	gvar->die_offset = dwarf_dieoffset(type_die);
+
+	rb_add(&gvar->node, dso__global_vars(dso), global_var_less);
+	return true;
+}
+
+void global_var_type__tree_delete(struct rb_root *root)
+{
+	struct global_var_entry *gvar;
+
+	while (!RB_EMPTY_ROOT(root)) {
+		struct rb_node *node = rb_first(root);
+
+		rb_erase(node, root);
+		gvar = rb_entry(node, struct global_var_entry, node);
+		zfree(&gvar->name);
+		free(gvar);
+	}
+}
+
+static bool get_global_var_info(struct data_loc_info *dloc, u64 addr,
+				const char **var_name, int *var_offset)
+{
+	struct addr_location al;
+	struct symbol *sym;
+	u64 mem_addr;
+
+	/* Kernel symbols might be relocated */
+	mem_addr = 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);
+	} else {
+		*var_name = NULL;
+	}
+	addr_location__exit(&al);
+	if (*var_name == NULL)
+		return false;
+
+	return true;
+}
+
+static void global_var__collect(struct data_loc_info *dloc)
+{
+	Dwarf *dwarf = dloc->di->dbg;
+	Dwarf_Off off, next_off;
+	Dwarf_Die cu_die, type_die;
+	size_t header_size;
+
+	/* Iterate all CU and collect global variables that have no location in a register. */
+	off = 0;
+	while (dwarf_nextcu(dwarf, off, &next_off, &header_size,
+			    NULL, NULL, NULL) == 0) {
+		struct die_var_type *var_types = NULL;
+		struct die_var_type *pos;
+
+		if (dwarf_offdie(dwarf, off + header_size, &cu_die) == NULL) {
+			off = next_off;
+			continue;
+		}
+
+		die_collect_global_vars(&cu_die, &var_types);
+
+		for (pos = var_types; pos; pos = pos->next) {
+			const char *var_name = NULL;
+			int var_offset = 0;
+
+			if (pos->reg != -1)
+				continue;
+
+			if (!dwarf_offdie(dwarf, pos->die_off, &type_die))
+				continue;
+
+			if (!get_global_var_info(dloc, pos->addr, &var_name,
+						 &var_offset))
+				continue;
+
+			if (var_offset != 0)
+				continue;
+
+			global_var__add(dloc, pos->addr, var_name, &type_die);
+		}
+
+		delete_var_types(var_types);
+
+		off = next_off;
+	}
+}
+
+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;
+	int offset;
+	const char *var_name = NULL;
+	struct global_var_entry *gvar;
+	struct dso *dso = map__dso(dloc->ms->map);
+	Dwarf_Die var_die;
+
+	if (RB_EMPTY_ROOT(dso__global_vars(dso)))
+		global_var__collect(dloc);
+
+	gvar = global_var__find(dloc, var_addr);
+	if (gvar) {
+		if (!dwarf_offdie(dloc->di->dbg, gvar->die_offset, type_die))
+			return false;
+
+		*var_offset = var_addr - gvar->start;
+		return true;
+	}
+
+	/* Try to get the variable by address first */
+	if (die_find_variable_by_addr(cu_die, var_addr, &var_die, &offset) &&
+	    check_variable(dloc, &var_die, type_die, DWARF_REG_PC, offset,
+			   /*is_fbreg=*/false) == 0) {
+		var_name = dwarf_diename(&var_die);
+		*var_offset = offset;
+		goto ok;
+	}
+
+	if (!get_global_var_info(dloc, var_addr, &var_name, var_offset))
+		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(dloc, &var_die, type_die, DWARF_REG_PC, *var_offset,
+			   /*is_fbreg=*/false) == 0)
+		goto ok;
+
+	return false;
+
+ok:
+	/* The address should point to the start of the variable */
+	global_var__add(dloc, var_addr - *var_offset, var_name, type_die);
+	return true;
+}
+
+/**
+ * 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.
+ */
+static 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, TSR_KIND_TYPE,
+					    &mem_die);
+
+			pr_debug_dtp("var [%"PRIx64"] -%#x(stack)",
+				     insn_offset, -var->offset);
+			pr_debug_type_name(&mem_die, TSR_KIND_TYPE);
+		} else if (var->reg == fbreg) {
+			findnew_stack_state(state, var->offset - fb_offset,
+					    TSR_KIND_TYPE, &mem_die);
+
+			pr_debug_dtp("var [%"PRIx64"] -%#x(stack)",
+				     insn_offset, -var->offset + fb_offset);
+			pr_debug_type_name(&mem_die, TSR_KIND_TYPE);
+		} 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->kind = TSR_KIND_TYPE;
+			reg->ok = true;
+
+			pr_debug_dtp("var [%"PRIx64"] reg%d",
+				     insn_offset, var->reg);
+			pr_debug_type_name(&mem_die, TSR_KIND_TYPE);
+		}
+	}
+}
+
+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->kind = TSR_KIND_TYPE;
+			tsr->ok = true;
+
+			pr_debug_dtp("call [%x] return -> reg%d",
+				     insn_offset, state->ret_reg);
+			pr_debug_type_name(&type_die, tsr->kind);
+		}
+		return;
+	}
+
+	if (!strncmp(dl->ins.name, "add", 3)) {
+		u64 imm_value = -1ULL;
+		int offset;
+		const char *var_name = NULL;
+		struct map_symbol *ms = dloc->ms;
+		u64 ip = ms->sym->start + dl->al.offset;
+
+		if (!has_reg_type(state, dst->reg1))
+			return;
+
+		tsr = &state->regs[dst->reg1];
+
+		if (src->imm)
+			imm_value = src->offset;
+		else if (has_reg_type(state, src->reg1) &&
+			 state->regs[src->reg1].kind == TSR_KIND_CONST)
+			imm_value = state->regs[src->reg1].imm_value;
+		else if (src->reg1 == DWARF_REG_PC) {
+			u64 var_addr = annotate_calc_pcrel(dloc->ms, ip,
+							   src->offset, dl);
+
+			if (get_global_var_info(dloc, var_addr,
+						&var_name, &offset) &&
+			    !strcmp(var_name, "this_cpu_off") &&
+			    tsr->kind == TSR_KIND_CONST) {
+				tsr->kind = TSR_KIND_PERCPU_BASE;
+				imm_value = tsr->imm_value;
+			}
+		}
+		else
+			return;
+
+		if (tsr->kind != TSR_KIND_PERCPU_BASE)
+			return;
+
+		if (get_global_var_type(cu_die, dloc, ip, imm_value, &offset,
+					&type_die) && offset == 0) {
+			/*
+			 * This is not a pointer type, but it should be treated
+			 * as a pointer.
+			 */
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_POINTER;
+			tsr->ok = true;
+
+			pr_debug_dtp("add [%x] percpu %#"PRIx64" -> reg%d",
+				     insn_offset, imm_value, dst->reg1);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+		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 or segment:offset to register transfers */
+	if (!src->mem_ref && !dst->mem_ref) {
+		if (!has_reg_type(state, dst->reg1))
+			return;
+
+		tsr = &state->regs[dst->reg1];
+		if (dso__kernel(map__dso(dloc->ms->map)) &&
+		    src->segment == INSN_SEG_X86_GS && src->imm) {
+			u64 ip = dloc->ms->sym->start + dl->al.offset;
+			u64 var_addr;
+			int offset;
+
+			/*
+			 * In kernel, %gs points to a per-cpu region for the
+			 * current CPU.  Access with a constant offset should
+			 * be treated as a global variable access.
+			 */
+			var_addr = src->offset;
+
+			if (var_addr == 40) {
+				tsr->kind = TSR_KIND_CANARY;
+				tsr->ok = true;
+
+				pr_debug_dtp("mov [%x] stack canary -> reg%d\n",
+					     insn_offset, dst->reg1);
+				return;
+			}
+
+			if (!get_global_var_type(cu_die, dloc, ip, var_addr,
+						 &offset, &type_die) ||
+			    !die_get_member_type(&type_die, offset, &type_die)) {
+				tsr->ok = false;
+				return;
+			}
+
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_TYPE;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] this-cpu addr=%#"PRIx64" -> reg%d",
+				     insn_offset, var_addr, dst->reg1);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+			return;
+		}
+
+		if (src->imm) {
+			tsr->kind = TSR_KIND_CONST;
+			tsr->imm_value = src->offset;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] imm=%#x -> reg%d\n",
+				     insn_offset, tsr->imm_value, dst->reg1);
+			return;
+		}
+
+		if (!has_reg_type(state, src->reg1) ||
+		    !state->regs[src->reg1].ok) {
+			tsr->ok = false;
+			return;
+		}
+
+		tsr->type = state->regs[src->reg1].type;
+		tsr->kind = state->regs[src->reg1].kind;
+		tsr->ok = true;
+
+		pr_debug_dtp("mov [%x] reg%d -> reg%d",
+			     insn_offset, src->reg1, dst->reg1);
+		pr_debug_type_name(&tsr->type, tsr->kind);
+	}
+	/* 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->kind = stack->kind;
+				tsr->ok = true;
+			} else if (die_get_member_type(&stack->type,
+						       offset - stack->offset,
+						       &type_die)) {
+				tsr->type = type_die;
+				tsr->kind = TSR_KIND_TYPE;
+				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, tsr->kind);
+		}
+		/* And then dereference the pointer if it has one */
+		else if (has_reg_type(state, sreg) && state->regs[sreg].ok &&
+			 state->regs[sreg].kind == TSR_KIND_TYPE &&
+			 die_deref_ptr_type(&state->regs[sreg].type,
+					    src->offset, &type_die)) {
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_TYPE;
+			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, tsr->kind);
+		}
+		/* 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->kind = TSR_KIND_TYPE;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] global addr=%"PRIx64" -> reg%d",
+				     insn_offset, addr, dst->reg1);
+			pr_debug_type_name(&type_die, tsr->kind);
+		}
+		/* And check percpu access with base register */
+		else if (has_reg_type(state, sreg) &&
+			 state->regs[sreg].kind == TSR_KIND_PERCPU_BASE) {
+			u64 ip = dloc->ms->sym->start + dl->al.offset;
+			u64 var_addr = src->offset;
+			int offset;
+
+			if (src->multi_regs) {
+				int reg2 = (sreg == src->reg1) ? src->reg2 : src->reg1;
+
+				if (has_reg_type(state, reg2) && state->regs[reg2].ok &&
+				    state->regs[reg2].kind == TSR_KIND_CONST)
+					var_addr += state->regs[reg2].imm_value;
+			}
+
+			/*
+			 * In kernel, %gs points to a per-cpu region for the
+			 * current CPU.  Access with a constant offset should
+			 * be treated as a global variable access.
+			 */
+			if (get_global_var_type(cu_die, dloc, ip, var_addr,
+						&offset, &type_die) &&
+			    die_get_member_type(&type_die, offset, &type_die)) {
+				tsr->type = type_die;
+				tsr->kind = TSR_KIND_TYPE;
+				tsr->ok = true;
+
+				if (src->multi_regs) {
+					pr_debug_dtp("mov [%x] percpu %#x(reg%d,reg%d) -> reg%d",
+						     insn_offset, src->offset, src->reg1,
+						     src->reg2, dst->reg1);
+				} else {
+					pr_debug_dtp("mov [%x] percpu %#x(reg%d) -> reg%d",
+						     insn_offset, src->offset, sreg, dst->reg1);
+				}
+				pr_debug_type_name(&tsr->type, tsr->kind);
+			} else {
+				tsr->ok = false;
+			}
+		}
+		/* And then dereference the calculated pointer if it has one */
+		else if (has_reg_type(state, sreg) && state->regs[sreg].ok &&
+			 state->regs[sreg].kind == TSR_KIND_POINTER &&
+			 die_get_member_type(&state->regs[sreg].type,
+					     src->offset, &type_die)) {
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_TYPE;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] pointer %#x(reg%d) -> reg%d",
+				     insn_offset, src->offset, sreg, dst->reg1);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+		/* Or try another register if any */
+		else if (src->multi_regs && sreg == src->reg1 &&
+			 src->reg1 != src->reg2) {
+			sreg = src->reg2;
+			goto retry;
+		}
+		else {
+			int offset;
+			const char *var_name = NULL;
+
+			/* it might be per-cpu variable (in kernel) access */
+			if (src->offset < 0) {
+				if (get_global_var_info(dloc, (s64)src->offset,
+							&var_name, &offset) &&
+				    !strcmp(var_name, "__per_cpu_offset")) {
+					tsr->kind = TSR_KIND_PERCPU_BASE;
+
+					pr_debug_dtp("mov [%x] percpu base reg%d\n",
+						     insn_offset, dst->reg1);
+				}
+			}
+
+			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;
+
+			tsr = &state->regs[src->reg1];
+
+			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, tsr->kind,
+							&tsr->type);
+			} else {
+				findnew_stack_state(state, offset, tsr->kind,
+						    &tsr->type);
+			}
+
+			pr_debug_dtp("mov [%x] reg%d -> -%#x(stack)",
+				     insn_offset, src->reg1, -offset);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+		/*
+		 * 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.
+ */
+static 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);
+}
+
+/*
+ * Prepend this_blocks (from the outer scope) to full_blocks, removing
+ * duplicate disasm line.
+ */
+static void prepend_basic_blocks(struct list_head *this_blocks,
+				 struct list_head *full_blocks)
+{
+	struct annotated_basic_block *first_bb, *last_bb;
+
+	last_bb = list_last_entry(this_blocks, typeof(*last_bb), list);
+	first_bb = list_first_entry(full_blocks, typeof(*first_bb), list);
+
+	if (list_empty(full_blocks))
+		goto out;
+
+	/* Last insn in this_blocks should be same as first insn in full_blocks */
+	if (last_bb->end != first_bb->begin) {
+		pr_debug("prepend basic blocks: mismatched disasm line %"PRIx64" -> %"PRIx64"\n",
+			 last_bb->end->al.offset, first_bb->begin->al.offset);
+		goto out;
+	}
+
+	/* Is the basic block have only one disasm_line? */
+	if (last_bb->begin == last_bb->end) {
+		list_del(&last_bb->list);
+		free(last_bb);
+		goto out;
+	}
+
+	/* Point to the insn before the last when adding this block to full_blocks */
+	last_bb->end = list_prev_entry(last_bb->end, al.node);
+
+out:
+	list_splice(this_blocks, full_blocks);
+}
+
+static void delete_basic_blocks(struct list_head *basic_blocks)
+{
+	struct annotated_basic_block *bb, *tmp;
+
+	list_for_each_entry_safe(bb, tmp, basic_blocks, list) {
+		list_del(&bb->list);
+		free(bb);
+	}
+}
+
+/* Make sure all variables have a valid start address */
+static void fixup_var_address(struct die_var_type *var_types, u64 addr)
+{
+	while (var_types) {
+		/*
+		 * Some variables have no address range meaning it's always
+		 * available in the whole scope.  Let's adjust the start
+		 * address to the start of the scope.
+		 */
+		if (var_types->addr == 0)
+			var_types->addr = addr;
+
+		var_types = var_types->next;
+	}
+}
+
+static void delete_var_types(struct die_var_type *var_types)
+{
+	while (var_types) {
+		struct die_var_type *next = var_types->next;
+
+		free(var_types);
+		var_types = next;
+	}
+}
+
+/* should match to is_stack_canary() in util/annotate.c */
+static void setup_stack_canary(struct data_loc_info *dloc)
+{
+	if (arch__is(dloc->arch, "x86")) {
+		dloc->op->segment = INSN_SEG_X86_GS;
+		dloc->op->imm = true;
+		dloc->op->offset = 40;
+	}
+}
+
+/*
+ * It's at the target address, check if it has a matching type.
+ * It returns 1 if found, 0 if not or -1 if not found but no need to
+ * repeat the search.  The last case is for per-cpu variables which
+ * are similar to global variables and no additional info is needed.
+ */
+static int check_matching_type(struct type_state *state,
+			       struct data_loc_info *dloc,
+			       Dwarf_Die *cu_die, Dwarf_Die *type_die)
+{
+	Dwarf_Word size;
+	u32 insn_offset = dloc->ip - dloc->ms->sym->start;
+	int reg = dloc->op->reg1;
+
+	pr_debug_dtp("chk [%x] reg%d offset=%#x ok=%d kind=%d",
+		     insn_offset, reg, dloc->op->offset,
+		     state->regs[reg].ok, state->regs[reg].kind);
+
+	if (state->regs[reg].ok && state->regs[reg].kind == TSR_KIND_TYPE) {
+		int tag = dwarf_tag(&state->regs[reg].type);
+
+		/*
+		 * Normal registers should hold a pointer (or array) to
+		 * dereference a memory location.
+		 */
+		if (tag != DW_TAG_pointer_type && tag != DW_TAG_array_type) {
+			if (dloc->op->offset < 0 && reg != state->stack_reg)
+				goto check_kernel;
+
+			pr_debug_dtp("\n");
+			return -1;
+		}
+
+		pr_debug_dtp("\n");
+
+		/* Remove the pointer and get the target type */
+		if (die_get_real_type(&state->regs[reg].type, type_die) == NULL)
+			return -1;
+
+		dloc->type_offset = dloc->op->offset;
+
+		/* Get the size of the actual type */
+		if (dwarf_aggregate_size(type_die, &size) < 0 ||
+		    (unsigned)dloc->type_offset >= size)
+			return -1;
+
+		return 1;
+	}
+
+	if (reg == dloc->fbreg) {
+		struct type_state_stack *stack;
+
+		pr_debug_dtp(" fbreg\n");
+
+		stack = find_stack_state(state, dloc->type_offset);
+		if (stack == NULL)
+			return 0;
+
+		if (stack->kind == TSR_KIND_CANARY) {
+			setup_stack_canary(dloc);
+			return -1;
+		}
+
+		if (stack->kind != TSR_KIND_TYPE)
+			return 0;
+
+		*type_die = stack->type;
+		/* Update the type offset from the start of slot */
+		dloc->type_offset -= stack->offset;
+
+		return 1;
+	}
+
+	if (dloc->fb_cfa) {
+		struct type_state_stack *stack;
+		u64 pc = map__rip_2objdump(dloc->ms->map, dloc->ip);
+		int fbreg, fboff;
+
+		pr_debug_dtp(" cfa\n");
+
+		if (die_get_cfa(dloc->di->dbg, pc, &fbreg, &fboff) < 0)
+			fbreg = -1;
+
+		if (reg != fbreg)
+			return 0;
+
+		stack = find_stack_state(state, dloc->type_offset - fboff);
+		if (stack == NULL)
+			return 0;
+
+		if (stack->kind == TSR_KIND_CANARY) {
+			setup_stack_canary(dloc);
+			return -1;
+		}
+
+		if (stack->kind != TSR_KIND_TYPE)
+			return 0;
+
+		*type_die = stack->type;
+		/* Update the type offset from the start of slot */
+		dloc->type_offset -= fboff + stack->offset;
+
+		return 1;
+	}
+
+	if (state->regs[reg].kind == TSR_KIND_PERCPU_BASE) {
+		u64 var_addr = dloc->op->offset;
+		int var_offset;
+
+		pr_debug_dtp(" percpu var\n");
+
+		if (dloc->op->multi_regs) {
+			int reg2 = dloc->op->reg2;
+
+			if (dloc->op->reg2 == reg)
+				reg2 = dloc->op->reg1;
+
+			if (has_reg_type(state, reg2) && state->regs[reg2].ok &&
+			    state->regs[reg2].kind == TSR_KIND_CONST)
+				var_addr += state->regs[reg2].imm_value;
+		}
+
+		if (get_global_var_type(cu_die, dloc, dloc->ip, var_addr,
+					&var_offset, type_die)) {
+			dloc->type_offset = var_offset;
+			return 1;
+		}
+		/* No need to retry per-cpu (global) variables */
+		return -1;
+	}
+
+	if (state->regs[reg].ok && state->regs[reg].kind == TSR_KIND_POINTER) {
+		pr_debug_dtp(" percpu ptr\n");
+
+		/*
+		 * It's actaully pointer but the address was calculated using
+		 * some arithmetic.  So it points to the actual type already.
+		 */
+		*type_die = state->regs[reg].type;
+
+		dloc->type_offset = dloc->op->offset;
+
+		/* Get the size of the actual type */
+		if (dwarf_aggregate_size(type_die, &size) < 0 ||
+		    (unsigned)dloc->type_offset >= size)
+			return -1;
+
+		return 1;
+	}
+
+	if (state->regs[reg].ok && state->regs[reg].kind == TSR_KIND_CANARY) {
+		pr_debug_dtp(" stack canary\n");
+
+		/*
+		 * This is a saved value of the stack canary which will be handled
+		 * in the outer logic when it returns failure here.  Pretend it's
+		 * from the stack canary directly.
+		 */
+		setup_stack_canary(dloc);
+
+		return -1;
+	}
+
+check_kernel:
+	if (dso__kernel(map__dso(dloc->ms->map))) {
+		u64 addr;
+		int offset;
+
+		/* Direct this-cpu access like "%gs:0x34740" */
+		if (dloc->op->segment == INSN_SEG_X86_GS && dloc->op->imm &&
+		    arch__is(dloc->arch, "x86")) {
+			pr_debug_dtp(" this-cpu var\n");
+
+			addr = dloc->op->offset;
+
+			if (get_global_var_type(cu_die, dloc, dloc->ip, addr,
+						&offset, type_die)) {
+				dloc->type_offset = offset;
+				return 1;
+			}
+			return -1;
+		}
+
+		/* Access to global variable like "-0x7dcf0500(,%rdx,8)" */
+		if (dloc->op->offset < 0 && reg != state->stack_reg) {
+			addr = (s64) dloc->op->offset;
+
+			if (get_global_var_type(cu_die, dloc, dloc->ip, addr,
+						&offset, type_die)) {
+				pr_debug_dtp(" global var\n");
+
+				dloc->type_offset = offset;
+				return 1;
+			}
+			pr_debug_dtp(" negative offset\n");
+			return -1;
+		}
+	}
+
+	pr_debug_dtp("\n");
+	return 0;
+}
+
+/* Iterate instructions in basic blocks and update type table */
+static int find_data_type_insn(struct data_loc_info *dloc,
+			       struct list_head *basic_blocks,
+			       struct die_var_type *var_types,
+			       Dwarf_Die *cu_die, Dwarf_Die *type_die)
+{
+	struct type_state state;
+	struct symbol *sym = dloc->ms->sym;
+	struct annotation *notes = symbol__annotation(sym);
+	struct annotated_basic_block *bb;
+	int ret = 0;
+
+	init_type_state(&state, dloc->arch);
+
+	list_for_each_entry(bb, basic_blocks, list) {
+		struct disasm_line *dl = bb->begin;
+
+		BUG_ON(bb->begin->al.offset == -1 || bb->end->al.offset == -1);
+
+		pr_debug_dtp("bb: [%"PRIx64" - %"PRIx64"]\n",
+			     bb->begin->al.offset, bb->end->al.offset);
+
+		list_for_each_entry_from(dl, &notes->src->source, al.node) {
+			u64 this_ip = sym->start + dl->al.offset;
+			u64 addr = map__rip_2objdump(dloc->ms->map, this_ip);
+
+			/* Skip comment or debug info lines */
+			if (dl->al.offset == -1)
+				continue;
+
+			/* Update variable type at this address */
+			update_var_state(&state, dloc, addr, dl->al.offset, var_types);
+
+			if (this_ip == dloc->ip) {
+				ret = check_matching_type(&state, dloc,
+							  cu_die, type_die);
+				goto out;
+			}
+
+			/* Update type table after processing the instruction */
+			update_insn_state(&state, dloc, cu_die, dl);
+			if (dl == bb->end)
+				break;
+		}
+	}
+
+out:
+	exit_type_state(&state);
+	return ret;
+}
+
+/*
+ * Construct a list of basic blocks for each scope with variables and try to find
+ * the data type by updating a type state table through instructions.
+ */
+static int find_data_type_block(struct data_loc_info *dloc,
+				Dwarf_Die *cu_die, Dwarf_Die *scopes,
+				int nr_scopes, Dwarf_Die *type_die)
+{
+	LIST_HEAD(basic_blocks);
+	struct die_var_type *var_types = NULL;
+	u64 src_ip, dst_ip, prev_dst_ip;
+	int ret = -1;
+
+	/* TODO: other architecture support */
+	if (!arch__is(dloc->arch, "x86"))
+		return -1;
+
+	prev_dst_ip = dst_ip = dloc->ip;
+	for (int i = nr_scopes - 1; i >= 0; i--) {
+		Dwarf_Addr base, start, end;
+		LIST_HEAD(this_blocks);
+		int found;
+
+		if (dwarf_ranges(&scopes[i], 0, &base, &start, &end) < 0)
+			break;
+
+		pr_debug_dtp("scope: [%d/%d] (die:%lx)\n",
+			     i + 1, nr_scopes, (long)dwarf_dieoffset(&scopes[i]));
+		src_ip = map__objdump_2rip(dloc->ms->map, start);
+
+again:
+		/* Get basic blocks for this scope */
+		if (annotate_get_basic_blocks(dloc->ms->sym, src_ip, dst_ip,
+					      &this_blocks) < 0) {
+			/* Try previous block if they are not connected */
+			if (prev_dst_ip != dst_ip) {
+				dst_ip = prev_dst_ip;
+				goto again;
+			}
+
+			pr_debug_dtp("cannot find a basic block from %"PRIx64" to %"PRIx64"\n",
+				     src_ip - dloc->ms->sym->start,
+				     dst_ip - dloc->ms->sym->start);
+			continue;
+		}
+		prepend_basic_blocks(&this_blocks, &basic_blocks);
+
+		/* Get variable info for this scope and add to var_types list */
+		die_collect_vars(&scopes[i], &var_types);
+		fixup_var_address(var_types, start);
+
+		/* Find from start of this scope to the target instruction */
+		found = find_data_type_insn(dloc, &basic_blocks, var_types,
+					    cu_die, type_die);
+		if (found > 0) {
+			char buf[64];
+
+			if (dloc->op->multi_regs)
+				snprintf(buf, sizeof(buf), "reg%d, reg%d",
+					 dloc->op->reg1, dloc->op->reg2);
+			else
+				snprintf(buf, sizeof(buf), "reg%d", dloc->op->reg1);
+
+			pr_debug_dtp("found by insn track: %#x(%s) type-offset=%#x\n",
+				     dloc->op->offset, buf, dloc->type_offset);
+			pr_debug_type_name(type_die, TSR_KIND_TYPE);
+			ret = 0;
+			break;
+		}
+
+		if (found < 0)
+			break;
+
+		/* Go up to the next scope and find blocks to the start */
+		prev_dst_ip = dst_ip;
+		dst_ip = src_ip;
+	}
+
+	delete_basic_blocks(&basic_blocks);
+	delete_var_types(var_types);
+	return ret;
+}
+
 /* The result will be saved in @type_die */
-static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
-			      const char *var_name, struct annotated_op_loc *loc,
-			      Dwarf_Die *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;
-	bool is_fbreg = false;
 	int fb_offset = 0;
+	bool is_fbreg = false;
+	u64 pc;
+	char buf[64];
+
+	if (dloc->op->multi_regs)
+		snprintf(buf, sizeof(buf), "reg%d, reg%d", dloc->op->reg1, dloc->op->reg2);
+	else if (dloc->op->reg1 == DWARF_REG_PC)
+		snprintf(buf, sizeof(buf), "PC");
+	else
+		snprintf(buf, sizeof(buf), "reg%d", dloc->op->reg1);
+
+	pr_debug_dtp("-----------------------------------------------------------\n");
+	pr_debug_dtp("find data type for %#x(%s) at %s+%#"PRIx64"\n",
+		     dloc->op->offset, buf, dloc->ms->sym->name,
+		     dloc->ip - dloc->ms->sym->start);
+
+	/*
+	 * 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(di, pc, &cu_die)) {
-		pr_debug("cannot find CU for address %" PRIx64 "\n", pc);
+	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;
 	}
@@ -262,19 +1633,18 @@ static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
 	reg = loc->reg1;
 	offset = loc->offset;
 
-	if (reg == DWARF_REG_PC) {
-		if (die_find_variable_by_addr(&cu_die, pc, addr, &var_die, &offset)) {
-			ret = check_variable(&var_die, type_die, offset,
-					     /*is_pointer=*/false);
-			loc->offset = offset;
-			goto out;
-		}
+	pr_debug_dtp("CU for %s (die:%#lx)\n",
+		     dwarf_diename(&cu_die), (long)dwarf_dieoffset(&cu_die));
 
-		if (var_name && die_find_variable_at(&cu_die, var_name, pc,
-						     &var_die)) {
-			ret = check_variable(&var_die, type_die, 0,
-					     /*is_pointer=*/false);
-			/* loc->offset will be updated by the caller */
+	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 by addr=%#"PRIx64" type_offset=%#x\n",
+				     dloc->var_addr, offset);
+			pr_debug_type_name(type_die, TSR_KIND_TYPE);
+			ret = 0;
 			goto out;
 		}
 	}
@@ -291,16 +1661,20 @@ static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
 		    dwarf_formblock(&attr, &block) == 0 && block.length == 1) {
 			switch (*block.data) {
 			case DW_OP_reg0 ... DW_OP_reg31:
-				fbreg = *block.data - DW_OP_reg0;
+				fbreg = dloc->fbreg = *block.data - DW_OP_reg0;
 				break;
 			case DW_OP_call_frame_cfa:
-				if (die_get_cfa(di->dbg, pc, &fbreg,
+				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);
 		}
 	}
 
@@ -312,7 +1686,7 @@ retry:
 	/* 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], pc, addr,
+			if (!die_find_variable_by_addr(&scopes[i], dloc->var_addr,
 						       &var_die, &offset))
 				continue;
 		} else {
@@ -323,9 +1697,30 @@ retry:
 		}
 
 		/* Found a variable, see if it's correct */
-		ret = check_variable(&var_die, type_die, offset,
-				     reg != DWARF_REG_PC && !is_fbreg);
-		loc->offset = offset;
+		ret = check_variable(dloc, &var_die, type_die, reg, offset, 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("addr=%#"PRIx64" type_offset=%#x\n",
+					     dloc->var_addr, offset);
+			} else if (reg == DWARF_REG_FB || is_fbreg) {
+				pr_debug_dtp("stack_offset=%#x type_offset=%#x\n",
+					     fb_offset, offset);
+			} else {
+				pr_debug_dtp("type_offset=%#x\n", offset);
+			}
+			pr_debug_location(&var_die, pc, reg);
+			pr_debug_type_name(type_die, TSR_KIND_TYPE);
+		} else {
+			pr_debug_dtp("check variable \"%s\" failed (die: %#lx)\n",
+				     dwarf_diename(&var_die),
+				     (long)dwarf_dieoffset(&var_die));
+			pr_debug_location(&var_die, pc, reg);
+			pr_debug_type_name(type_die, TSR_KIND_TYPE);
+		}
+		dloc->type_offset = offset;
 		goto out;
 	}
 
@@ -334,8 +1729,19 @@ retry:
 		goto retry;
 	}
 
-	if (ret < 0)
+	if (reg != DWARF_REG_PC) {
+		ret = find_data_type_block(dloc, &cu_die, scopes,
+					   nr_scopes, type_die);
+		if (ret == 0) {
+			ann_data_stat.insn_track++;
+			goto out;
+		}
+	}
+
+	if (ret < 0) {
+		pr_debug_dtp("no variable found\n");
 		ann_data_stat.no_var++;
+	}
 
 out:
 	free(scopes);
@@ -344,50 +1750,45 @@ out:
 
 /**
  * find_data_type - Return a data type at the location
- * @ms: map and symbol at the location
- * @ip: instruction address of the memory access
- * @loc: instruction operand location
- * @addr: data address of the memory access
- * @var_name: global variable name
+ * @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 @loc->offset after finding the start of the variable.
- * If it cannot find a global variable by address, it tried to fine a declaration
- * of the variable using @var_name.  In that case, @loc->offset won't be updated.
+ * 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 map_symbol *ms, u64 ip,
-					   struct annotated_op_loc *loc, u64 addr,
-					   const char *var_name)
+struct annotated_data_type *find_data_type(struct data_loc_info *dloc)
 {
 	struct annotated_data_type *result = NULL;
-	struct dso *dso = map__dso(ms->map);
-	struct debuginfo *di;
+	struct dso *dso = map__dso(dloc->ms->map);
 	Dwarf_Die type_die;
-	u64 pc;
 
-	di = debuginfo__new(dso->long_name);
-	if (di == NULL) {
-		pr_debug("cannot get the debug info\n");
+	dloc->di = debuginfo__new(dso__long_name(dso));
+	if (dloc->di == NULL) {
+		pr_debug_dtp("cannot get the debug info\n");
 		return NULL;
 	}
 
 	/*
-	 * 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.
+	 * The type offset is the same as instruction offset by default.
+	 * But when finding a global variable, the offset won't be valid.
 	 */
-	pc = map__rip_2objdump(ms->map, ip);
-	if (find_data_type_die(di, pc, addr, var_name, loc, &type_die) < 0)
+	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(di);
+	debuginfo__delete(dloc->di);
 	return result;
 }
 
@@ -399,7 +1800,6 @@ static int alloc_data_type_histograms(struct annotated_data_type *adt, int nr_en
 	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;
@@ -413,20 +1813,24 @@ static int alloc_data_type_histograms(struct annotated_data_type *adt, int nr_en
 		if (adt->histograms[i] == NULL)
 			goto err;
 	}
+
+	adt->nr_histograms = nr_entries;
 	return 0;
 
 err:
 	while (--i >= 0)
-		free(adt->histograms[i]);
-	free(adt->histograms);
+		zfree(&(adt->histograms[i]));
+	zfree(&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);
+		zfree(&(adt->histograms[i]));
+
+	zfree(&adt->histograms);
+	adt->nr_histograms = 0;
 }
 
 void annotated_data_type__tree_delete(struct rb_root *root)
@@ -440,7 +1844,7 @@ void annotated_data_type__tree_delete(struct rb_root *root)
 		pos = rb_entry(node, struct annotated_data_type, node);
 		delete_members(&pos->self);
 		delete_data_type_histograms(pos);
-		free(pos->self.type_name);
+		zfree(&pos->self.type_name);
 		free(pos);
 	}
 }
@@ -484,3 +1888,115 @@ int annotated_data_type__update_samples(struct annotated_data_type *adt,
 	h->addr[offset].period += period;
 	return 0;
 }
+
+static void print_annotated_data_header(struct hist_entry *he, struct evsel *evsel)
+{
+	struct dso *dso = map__dso(he->ms.map);
+	int nr_members = 1;
+	int nr_samples = he->stat.nr_events;
+	int width = 7;
+	const char *val_hdr = "Percent";
+
+	if (evsel__is_group_event(evsel)) {
+		struct hist_entry *pair;
+
+		list_for_each_entry(pair, &he->pairs.head, pairs.node)
+			nr_samples += pair->stat.nr_events;
+	}
+
+	printf("Annotate type: '%s' in %s (%d samples):\n",
+	       he->mem_type->self.type_name, dso__name(dso), nr_samples);
+
+	if (evsel__is_group_event(evsel)) {
+		struct evsel *pos;
+		int i = 0;
+
+		for_each_group_evsel(pos, evsel)
+			printf(" event[%d] = %s\n", i++, pos->name);
+
+		nr_members = evsel->core.nr_members;
+	}
+
+	if (symbol_conf.show_total_period) {
+		width = 11;
+		val_hdr = "Period";
+	} else if (symbol_conf.show_nr_samples) {
+		width = 7;
+		val_hdr = "Samples";
+	}
+
+	printf("============================================================================\n");
+	printf("%*s %10s %10s  %s\n", (width + 1) * nr_members, val_hdr,
+	       "offset", "size", "field");
+}
+
+static void print_annotated_data_value(struct type_hist *h, u64 period, int nr_samples)
+{
+	double percent = h->period ? (100.0 * period / h->period) : 0;
+	const char *color = get_percent_color(percent);
+
+	if (symbol_conf.show_total_period)
+		color_fprintf(stdout, color, " %11" PRIu64, period);
+	else if (symbol_conf.show_nr_samples)
+		color_fprintf(stdout, color, " %7d", nr_samples);
+	else
+		color_fprintf(stdout, color, " %7.2f", percent);
+}
+
+static void print_annotated_data_type(struct annotated_data_type *mem_type,
+				      struct annotated_member *member,
+				      struct evsel *evsel, int indent)
+{
+	struct annotated_member *child;
+	struct type_hist *h = mem_type->histograms[evsel->core.idx];
+	int i, nr_events = 1, samples = 0;
+	u64 period = 0;
+	int width = symbol_conf.show_total_period ? 11 : 7;
+
+	for (i = 0; i < member->size; i++) {
+		samples += h->addr[member->offset + i].nr_samples;
+		period += h->addr[member->offset + i].period;
+	}
+	print_annotated_data_value(h, period, samples);
+
+	if (evsel__is_group_event(evsel)) {
+		struct evsel *pos;
+
+		for_each_group_member(pos, evsel) {
+			h = mem_type->histograms[pos->core.idx];
+
+			samples = 0;
+			period = 0;
+			for (i = 0; i < member->size; i++) {
+				samples += h->addr[member->offset + i].nr_samples;
+				period += h->addr[member->offset + i].period;
+			}
+			print_annotated_data_value(h, period, samples);
+		}
+		nr_events = evsel->core.nr_members;
+	}
+
+	printf(" %10d %10d  %*s%s\t%s",
+	       member->offset, member->size, indent, "", member->type_name,
+	       member->var_name ?: "");
+
+	if (!list_empty(&member->children))
+		printf(" {\n");
+
+	list_for_each_entry(child, &member->children, node)
+		print_annotated_data_type(mem_type, child, evsel, indent + 4);
+
+	if (!list_empty(&member->children))
+		printf("%*s}", (width + 1) * nr_events + 24 + indent, "");
+	printf(";\n");
+}
+
+int hist_entry__annotate_data_tty(struct hist_entry *he, struct evsel *evsel)
+{
+	print_annotated_data_header(he, evsel);
+	print_annotated_data_type(he->mem_type, &he->mem_type->self, evsel, 0);
+	printf("\n");
+
+	/* move to the next entry */
+	return '>';
+}
diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
index 1b0db8e8c4..0a57d9f5ee 100644
--- a/tools/perf/util/annotate-data.h
+++ b/tools/perf/util/annotate-data.h
@@ -8,8 +8,12 @@
 #include <linux/types.h>
 
 struct annotated_op_loc;
+struct debuginfo;
 struct evsel;
+struct hist_browser_timer;
+struct hist_entry;
 struct map_symbol;
+struct thread;
 
 /**
  * struct annotated_member - Type of member field
@@ -71,6 +75,40 @@ struct annotated_data_type {
 
 extern struct annotated_data_type unknown_type;
 extern struct annotated_data_type stackop_type;
+extern struct annotated_data_type canary_type;
+
+/**
+ * struct data_loc_info - Data location information
+ * @arch: CPU architecture info
+ * @thread: Thread info
+ * @ms: Map and Symbol info
+ * @ip: Instruction address
+ * @var_addr: Data address (for global variables)
+ * @cpumode: CPU execution mode
+ * @op: Instruction operand location (regs and offset)
+ * @di: Debug info
+ * @fbreg: Frame base register
+ * @fb_cfa: Whether the frame needs to check CFA
+ * @type_offset: Final offset in the type
+ */
+struct data_loc_info {
+	/* These are input field, should be filled by caller */
+	struct arch *arch;
+	struct thread *thread;
+	struct map_symbol *ms;
+	u64 ip;
+	u64 var_addr;
+	u8 cpumode;
+	struct annotated_op_loc *op;
+
+	/* These are used internally */
+	struct debuginfo *di;
+	int fbreg;
+	bool fb_cfa;
+
+	/* This is for the result */
+	int type_offset;
+};
 
 /**
  * struct annotated_data_stat - Debug statistics
@@ -100,15 +138,14 @@ struct annotated_data_stat {
 	int no_typeinfo;
 	int invalid_size;
 	int bad_offset;
+	int insn_track;
 };
 extern struct annotated_data_stat ann_data_stat;
 
 #ifdef HAVE_DWARF_SUPPORT
 
 /* Returns data type at the location (ip, reg, offset) */
-struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
-					   struct annotated_op_loc *loc, u64 addr,
-					   const char *var_name);
+struct annotated_data_type *find_data_type(struct data_loc_info *dloc);
 
 /* Update type access histogram at the given offset */
 int annotated_data_type__update_samples(struct annotated_data_type *adt,
@@ -118,12 +155,15 @@ int annotated_data_type__update_samples(struct annotated_data_type *adt,
 /* Release all data type information in the tree */
 void annotated_data_type__tree_delete(struct rb_root *root);
 
+/* Release all global variable information in the tree */
+void global_var_type__tree_delete(struct rb_root *root);
+
+int hist_entry__annotate_data_tty(struct hist_entry *he, struct evsel *evsel);
+
 #else /* HAVE_DWARF_SUPPORT */
 
 static inline struct annotated_data_type *
-find_data_type(struct map_symbol *ms __maybe_unused, u64 ip __maybe_unused,
-	       struct annotated_op_loc *loc __maybe_unused,
-	       u64 addr __maybe_unused, const char *var_name __maybe_unused)
+find_data_type(struct data_loc_info *dloc __maybe_unused)
 {
 	return NULL;
 }
@@ -142,6 +182,28 @@ static inline void annotated_data_type__tree_delete(struct rb_root *root __maybe
 {
 }
 
+static inline void global_var_type__tree_delete(struct rb_root *root __maybe_unused)
+{
+}
+
+static inline int hist_entry__annotate_data_tty(struct hist_entry *he __maybe_unused,
+						struct evsel *evsel __maybe_unused)
+{
+	return -1;
+}
+
 #endif /* HAVE_DWARF_SUPPORT */
 
+#ifdef HAVE_SLANG_SUPPORT
+int hist_entry__annotate_data_tui(struct hist_entry *he, struct evsel *evsel,
+				  struct hist_browser_timer *hbt);
+#else
+static inline int hist_entry__annotate_data_tui(struct hist_entry *he __maybe_unused,
+						struct evsel *evsel __maybe_unused,
+						struct hist_browser_timer *hbt __maybe_unused)
+{
+	return -1;
+}
+#endif /* HAVE_SLANG_SUPPORT */
+
 #endif /* _PERF_ANNOTATE_DATA_H */
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 79d082155c..1451caf25e 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -16,6 +16,7 @@
 #include "build-id.h"
 #include "color.h"
 #include "config.h"
+#include "disasm.h"
 #include "dso.h"
 #include "env.h"
 #include "map.h"
@@ -64,47 +65,6 @@
 /* global annotation options */
 struct annotation_options annotate_opts;
 
-static regex_t	 file_lineno;
-
-static struct ins_ops *ins__find(struct arch *arch, const char *name);
-static void ins__sort(struct arch *arch);
-static int disasm_line__parse(char *line, const char **namep, char **rawp);
-static int call__scnprintf(struct ins *ins, char *bf, size_t size,
-			  struct ins_operands *ops, int max_ins_name);
-static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
-			  struct ins_operands *ops, int max_ins_name);
-
-struct arch {
-	const char	*name;
-	struct ins	*instructions;
-	size_t		nr_instructions;
-	size_t		nr_instructions_allocated;
-	struct ins_ops  *(*associate_instruction_ops)(struct arch *arch, const char *name);
-	bool		sorted_instructions;
-	bool		initialized;
-	const char	*insn_suffix;
-	void		*priv;
-	unsigned int	model;
-	unsigned int	family;
-	int		(*init)(struct arch *arch, char *cpuid);
-	bool		(*ins_is_fused)(struct arch *arch, const char *ins1,
-					const char *ins2);
-	struct		{
-		char comment_char;
-		char skip_functions_char;
-		char register_char;
-		char memory_ref_char;
-	} objdump;
-};
-
-static struct ins_ops call_ops;
-static struct ins_ops dec_ops;
-static struct ins_ops jump_ops;
-static struct ins_ops mov_ops;
-static struct ins_ops nop_ops;
-static struct ins_ops lock_ops;
-static struct ins_ops ret_ops;
-
 /* Data type collection debug statistics */
 struct annotated_data_stat ann_data_stat;
 LIST_HEAD(ann_insn_stat);
@@ -117,753 +77,13 @@ struct annotated_data_type stackop_type = {
 	},
 };
 
-static int arch__grow_instructions(struct arch *arch)
-{
-	struct ins *new_instructions;
-	size_t new_nr_allocated;
-
-	if (arch->nr_instructions_allocated == 0 && arch->instructions)
-		goto grow_from_non_allocated_table;
-
-	new_nr_allocated = arch->nr_instructions_allocated + 128;
-	new_instructions = realloc(arch->instructions, new_nr_allocated * sizeof(struct ins));
-	if (new_instructions == NULL)
-		return -1;
-
-out_update_instructions:
-	arch->instructions = new_instructions;
-	arch->nr_instructions_allocated = new_nr_allocated;
-	return 0;
-
-grow_from_non_allocated_table:
-	new_nr_allocated = arch->nr_instructions + 128;
-	new_instructions = calloc(new_nr_allocated, sizeof(struct ins));
-	if (new_instructions == NULL)
-		return -1;
-
-	memcpy(new_instructions, arch->instructions, arch->nr_instructions);
-	goto out_update_instructions;
-}
-
-static int arch__associate_ins_ops(struct arch* arch, const char *name, struct ins_ops *ops)
-{
-	struct ins *ins;
-
-	if (arch->nr_instructions == arch->nr_instructions_allocated &&
-	    arch__grow_instructions(arch))
-		return -1;
-
-	ins = &arch->instructions[arch->nr_instructions];
-	ins->name = strdup(name);
-	if (!ins->name)
-		return -1;
-
-	ins->ops  = ops;
-	arch->nr_instructions++;
-
-	ins__sort(arch);
-	return 0;
-}
-
-#include "arch/arc/annotate/instructions.c"
-#include "arch/arm/annotate/instructions.c"
-#include "arch/arm64/annotate/instructions.c"
-#include "arch/csky/annotate/instructions.c"
-#include "arch/loongarch/annotate/instructions.c"
-#include "arch/mips/annotate/instructions.c"
-#include "arch/x86/annotate/instructions.c"
-#include "arch/powerpc/annotate/instructions.c"
-#include "arch/riscv64/annotate/instructions.c"
-#include "arch/s390/annotate/instructions.c"
-#include "arch/sparc/annotate/instructions.c"
-
-static struct arch architectures[] = {
-	{
-		.name = "arc",
-		.init = arc__annotate_init,
-	},
-	{
-		.name = "arm",
-		.init = arm__annotate_init,
-	},
-	{
-		.name = "arm64",
-		.init = arm64__annotate_init,
-	},
-	{
-		.name = "csky",
-		.init = csky__annotate_init,
-	},
-	{
-		.name = "mips",
-		.init = mips__annotate_init,
-		.objdump = {
-			.comment_char = '#',
-		},
-	},
-	{
-		.name = "x86",
-		.init = x86__annotate_init,
-		.instructions = x86__instructions,
-		.nr_instructions = ARRAY_SIZE(x86__instructions),
-		.insn_suffix = "bwlq",
-		.objdump =  {
-			.comment_char = '#',
-			.register_char = '%',
-			.memory_ref_char = '(',
-		},
-	},
-	{
-		.name = "powerpc",
-		.init = powerpc__annotate_init,
-	},
-	{
-		.name = "riscv64",
-		.init = riscv64__annotate_init,
-	},
-	{
-		.name = "s390",
-		.init = s390__annotate_init,
-		.objdump =  {
-			.comment_char = '#',
-		},
-	},
-	{
-		.name = "sparc",
-		.init = sparc__annotate_init,
-		.objdump = {
-			.comment_char = '#',
-		},
-	},
-	{
-		.name = "loongarch",
-		.init = loongarch__annotate_init,
-		.objdump = {
-			.comment_char = '#',
-		},
+struct annotated_data_type canary_type = {
+	.self = {
+		.type_name = (char *)"(stack canary)",
+		.children = LIST_HEAD_INIT(canary_type.self.children),
 	},
 };
 
-static void ins__delete(struct ins_operands *ops)
-{
-	if (ops == NULL)
-		return;
-	zfree(&ops->source.raw);
-	zfree(&ops->source.name);
-	zfree(&ops->target.raw);
-	zfree(&ops->target.name);
-}
-
-static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
-			      struct ins_operands *ops, int max_ins_name)
-{
-	return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->raw);
-}
-
-int ins__scnprintf(struct ins *ins, char *bf, size_t size,
-		   struct ins_operands *ops, int max_ins_name)
-{
-	if (ins->ops->scnprintf)
-		return ins->ops->scnprintf(ins, bf, size, ops, max_ins_name);
-
-	return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
-}
-
-bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2)
-{
-	if (!arch || !arch->ins_is_fused)
-		return false;
-
-	return arch->ins_is_fused(arch, ins1, ins2);
-}
-
-static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
-{
-	char *endptr, *tok, *name;
-	struct map *map = ms->map;
-	struct addr_map_symbol target = {
-		.ms = { .map = map, },
-	};
-
-	ops->target.addr = strtoull(ops->raw, &endptr, 16);
-
-	name = strchr(endptr, '<');
-	if (name == NULL)
-		goto indirect_call;
-
-	name++;
-
-	if (arch->objdump.skip_functions_char &&
-	    strchr(name, arch->objdump.skip_functions_char))
-		return -1;
-
-	tok = strchr(name, '>');
-	if (tok == NULL)
-		return -1;
-
-	*tok = '\0';
-	ops->target.name = strdup(name);
-	*tok = '>';
-
-	if (ops->target.name == NULL)
-		return -1;
-find_target:
-	target.addr = map__objdump_2mem(map, ops->target.addr);
-
-	if (maps__find_ams(ms->maps, &target) == 0 &&
-	    map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
-		ops->target.sym = target.ms.sym;
-
-	return 0;
-
-indirect_call:
-	tok = strchr(endptr, '*');
-	if (tok != NULL) {
-		endptr++;
-
-		/* Indirect call can use a non-rip register and offset: callq  *0x8(%rbx).
-		 * Do not parse such instruction.  */
-		if (strstr(endptr, "(%r") == NULL)
-			ops->target.addr = strtoull(endptr, NULL, 16);
-	}
-	goto find_target;
-}
-
-static int call__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops, int max_ins_name)
-{
-	if (ops->target.sym)
-		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
-
-	if (ops->target.addr == 0)
-		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
-
-	if (ops->target.name)
-		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.name);
-
-	return scnprintf(bf, size, "%-*s *%" PRIx64, max_ins_name, ins->name, ops->target.addr);
-}
-
-static struct ins_ops call_ops = {
-	.parse	   = call__parse,
-	.scnprintf = call__scnprintf,
-};
-
-bool ins__is_call(const struct ins *ins)
-{
-	return ins->ops == &call_ops || ins->ops == &s390_call_ops || ins->ops == &loongarch_call_ops;
-}
-
-/*
- * Prevents from matching commas in the comment section, e.g.:
- * ffff200008446e70:       b.cs    ffff2000084470f4 <generic_exec_single+0x314>  // b.hs, b.nlast
- *
- * and skip comma as part of function arguments, e.g.:
- * 1d8b4ac <linemap_lookup(line_maps const*, unsigned int)+0xcc>
- */
-static inline const char *validate_comma(const char *c, struct ins_operands *ops)
-{
-	if (ops->jump.raw_comment && c > ops->jump.raw_comment)
-		return NULL;
-
-	if (ops->jump.raw_func_start && c > ops->jump.raw_func_start)
-		return NULL;
-
-	return c;
-}
-
-static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
-{
-	struct map *map = ms->map;
-	struct symbol *sym = ms->sym;
-	struct addr_map_symbol target = {
-		.ms = { .map = map, },
-	};
-	const char *c = strchr(ops->raw, ',');
-	u64 start, end;
-
-	ops->jump.raw_comment = strchr(ops->raw, arch->objdump.comment_char);
-	ops->jump.raw_func_start = strchr(ops->raw, '<');
-
-	c = validate_comma(c, ops);
-
-	/*
-	 * Examples of lines to parse for the _cpp_lex_token@@Base
-	 * function:
-	 *
-	 * 1159e6c: jne    115aa32 <_cpp_lex_token@@Base+0xf92>
-	 * 1159e8b: jne    c469be <cpp_named_operator2name@@Base+0xa72>
-	 *
-	 * The first is a jump to an offset inside the same function,
-	 * the second is to another function, i.e. that 0xa72 is an
-	 * offset in the cpp_named_operator2name@@base function.
-	 */
-	/*
-	 * skip over possible up to 2 operands to get to address, e.g.:
-	 * tbnz	 w0, #26, ffff0000083cd190 <security_file_permission+0xd0>
-	 */
-	if (c++ != NULL) {
-		ops->target.addr = strtoull(c, NULL, 16);
-		if (!ops->target.addr) {
-			c = strchr(c, ',');
-			c = validate_comma(c, ops);
-			if (c++ != NULL)
-				ops->target.addr = strtoull(c, NULL, 16);
-		}
-	} else {
-		ops->target.addr = strtoull(ops->raw, NULL, 16);
-	}
-
-	target.addr = map__objdump_2mem(map, ops->target.addr);
-	start = map__unmap_ip(map, sym->start);
-	end = map__unmap_ip(map, sym->end);
-
-	ops->target.outside = target.addr < start || target.addr > end;
-
-	/*
-	 * FIXME: things like this in _cpp_lex_token (gcc's cc1 program):
-
-		cpp_named_operator2name@@Base+0xa72
-
-	 * Point to a place that is after the cpp_named_operator2name
-	 * boundaries, i.e.  in the ELF symbol table for cc1
-	 * cpp_named_operator2name is marked as being 32-bytes long, but it in
-	 * fact is much larger than that, so we seem to need a symbols__find()
-	 * routine that looks for >= current->start and  < next_symbol->start,
-	 * possibly just for C++ objects?
-	 *
-	 * For now lets just make some progress by marking jumps to outside the
-	 * current function as call like.
-	 *
-	 * Actual navigation will come next, with further understanding of how
-	 * the symbol searching and disassembly should be done.
-	 */
-	if (maps__find_ams(ms->maps, &target) == 0 &&
-	    map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
-		ops->target.sym = target.ms.sym;
-
-	if (!ops->target.outside) {
-		ops->target.offset = target.addr - start;
-		ops->target.offset_avail = true;
-	} else {
-		ops->target.offset_avail = false;
-	}
-
-	return 0;
-}
-
-static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops, int max_ins_name)
-{
-	const char *c;
-
-	if (!ops->target.addr || ops->target.offset < 0)
-		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
-
-	if (ops->target.outside && ops->target.sym != NULL)
-		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
-
-	c = strchr(ops->raw, ',');
-	c = validate_comma(c, ops);
-
-	if (c != NULL) {
-		const char *c2 = strchr(c + 1, ',');
-
-		c2 = validate_comma(c2, ops);
-		/* check for 3-op insn */
-		if (c2 != NULL)
-			c = c2;
-		c++;
-
-		/* mirror arch objdump's space-after-comma style */
-		if (*c == ' ')
-			c++;
-	}
-
-	return scnprintf(bf, size, "%-*s %.*s%" PRIx64, max_ins_name,
-			 ins->name, c ? c - ops->raw : 0, ops->raw,
-			 ops->target.offset);
-}
-
-static void jump__delete(struct ins_operands *ops __maybe_unused)
-{
-	/*
-	 * The ops->jump.raw_comment and ops->jump.raw_func_start belong to the
-	 * raw string, don't free them.
-	 */
-}
-
-static struct ins_ops jump_ops = {
-	.free	   = jump__delete,
-	.parse	   = jump__parse,
-	.scnprintf = jump__scnprintf,
-};
-
-bool ins__is_jump(const struct ins *ins)
-{
-	return ins->ops == &jump_ops || ins->ops == &loongarch_jump_ops;
-}
-
-static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep)
-{
-	char *endptr, *name, *t;
-
-	if (strstr(raw, "(%rip)") == NULL)
-		return 0;
-
-	*addrp = strtoull(comment, &endptr, 16);
-	if (endptr == comment)
-		return 0;
-	name = strchr(endptr, '<');
-	if (name == NULL)
-		return -1;
-
-	name++;
-
-	t = strchr(name, '>');
-	if (t == NULL)
-		return 0;
-
-	*t = '\0';
-	*namep = strdup(name);
-	*t = '>';
-
-	return 0;
-}
-
-static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
-{
-	ops->locked.ops = zalloc(sizeof(*ops->locked.ops));
-	if (ops->locked.ops == NULL)
-		return 0;
-
-	if (disasm_line__parse(ops->raw, &ops->locked.ins.name, &ops->locked.ops->raw) < 0)
-		goto out_free_ops;
-
-	ops->locked.ins.ops = ins__find(arch, ops->locked.ins.name);
-
-	if (ops->locked.ins.ops == NULL)
-		goto out_free_ops;
-
-	if (ops->locked.ins.ops->parse &&
-	    ops->locked.ins.ops->parse(arch, ops->locked.ops, ms) < 0)
-		goto out_free_ops;
-
-	return 0;
-
-out_free_ops:
-	zfree(&ops->locked.ops);
-	return 0;
-}
-
-static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops, int max_ins_name)
-{
-	int printed;
-
-	if (ops->locked.ins.ops == NULL)
-		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
-
-	printed = scnprintf(bf, size, "%-*s ", max_ins_name, ins->name);
-	return printed + ins__scnprintf(&ops->locked.ins, bf + printed,
-					size - printed, ops->locked.ops, max_ins_name);
-}
-
-static void lock__delete(struct ins_operands *ops)
-{
-	struct ins *ins = &ops->locked.ins;
-
-	if (ins->ops && ins->ops->free)
-		ins->ops->free(ops->locked.ops);
-	else
-		ins__delete(ops->locked.ops);
-
-	zfree(&ops->locked.ops);
-	zfree(&ops->target.raw);
-	zfree(&ops->target.name);
-}
-
-static struct ins_ops lock_ops = {
-	.free	   = lock__delete,
-	.parse	   = lock__parse,
-	.scnprintf = lock__scnprintf,
-};
-
-/*
- * Check if the operand has more than one registers like x86 SIB addressing:
- *   0x1234(%rax, %rbx, 8)
- *
- * But it doesn't care segment selectors like %gs:0x5678(%rcx), so just check
- * the input string after 'memory_ref_char' if exists.
- */
-static bool check_multi_regs(struct arch *arch, const char *op)
-{
-	int count = 0;
-
-	if (arch->objdump.register_char == 0)
-		return false;
-
-	if (arch->objdump.memory_ref_char) {
-		op = strchr(op, arch->objdump.memory_ref_char);
-		if (op == NULL)
-			return false;
-	}
-
-	while ((op = strchr(op, arch->objdump.register_char)) != NULL) {
-		count++;
-		op++;
-	}
-
-	return count > 1;
-}
-
-static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
-{
-	char *s = strchr(ops->raw, ','), *target, *comment, prev;
-
-	if (s == NULL)
-		return -1;
-
-	*s = '\0';
-
-	/*
-	 * x86 SIB addressing has something like 0x8(%rax, %rcx, 1)
-	 * then it needs to have the closing parenthesis.
-	 */
-	if (strchr(ops->raw, '(')) {
-		*s = ',';
-		s = strchr(ops->raw, ')');
-		if (s == NULL || s[1] != ',')
-			return -1;
-		*++s = '\0';
-	}
-
-	ops->source.raw = strdup(ops->raw);
-	*s = ',';
-
-	if (ops->source.raw == NULL)
-		return -1;
-
-	ops->source.multi_regs = check_multi_regs(arch, ops->source.raw);
-
-	target = skip_spaces(++s);
-	comment = strchr(s, arch->objdump.comment_char);
-
-	if (comment != NULL)
-		s = comment - 1;
-	else
-		s = strchr(s, '\0') - 1;
-
-	while (s > target && isspace(s[0]))
-		--s;
-	s++;
-	prev = *s;
-	*s = '\0';
-
-	ops->target.raw = strdup(target);
-	*s = prev;
-
-	if (ops->target.raw == NULL)
-		goto out_free_source;
-
-	ops->target.multi_regs = check_multi_regs(arch, ops->target.raw);
-
-	if (comment == NULL)
-		return 0;
-
-	comment = skip_spaces(comment);
-	comment__symbol(ops->source.raw, comment + 1, &ops->source.addr, &ops->source.name);
-	comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
-
-	return 0;
-
-out_free_source:
-	zfree(&ops->source.raw);
-	return -1;
-}
-
-static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops, int max_ins_name)
-{
-	return scnprintf(bf, size, "%-*s %s,%s", max_ins_name, ins->name,
-			 ops->source.name ?: ops->source.raw,
-			 ops->target.name ?: ops->target.raw);
-}
-
-static struct ins_ops mov_ops = {
-	.parse	   = mov__parse,
-	.scnprintf = mov__scnprintf,
-};
-
-static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
-{
-	char *target, *comment, *s, prev;
-
-	target = s = ops->raw;
-
-	while (s[0] != '\0' && !isspace(s[0]))
-		++s;
-	prev = *s;
-	*s = '\0';
-
-	ops->target.raw = strdup(target);
-	*s = prev;
-
-	if (ops->target.raw == NULL)
-		return -1;
-
-	comment = strchr(s, arch->objdump.comment_char);
-	if (comment == NULL)
-		return 0;
-
-	comment = skip_spaces(comment);
-	comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
-
-	return 0;
-}
-
-static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops, int max_ins_name)
-{
-	return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name,
-			 ops->target.name ?: ops->target.raw);
-}
-
-static struct ins_ops dec_ops = {
-	.parse	   = dec__parse,
-	.scnprintf = dec__scnprintf,
-};
-
-static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
-			  struct ins_operands *ops __maybe_unused, int max_ins_name)
-{
-	return scnprintf(bf, size, "%-*s", max_ins_name, "nop");
-}
-
-static struct ins_ops nop_ops = {
-	.scnprintf = nop__scnprintf,
-};
-
-static struct ins_ops ret_ops = {
-	.scnprintf = ins__raw_scnprintf,
-};
-
-bool ins__is_ret(const struct ins *ins)
-{
-	return ins->ops == &ret_ops;
-}
-
-bool ins__is_lock(const struct ins *ins)
-{
-	return ins->ops == &lock_ops;
-}
-
-static int ins__key_cmp(const void *name, const void *insp)
-{
-	const struct ins *ins = insp;
-
-	return strcmp(name, ins->name);
-}
-
-static int ins__cmp(const void *a, const void *b)
-{
-	const struct ins *ia = a;
-	const struct ins *ib = b;
-
-	return strcmp(ia->name, ib->name);
-}
-
-static void ins__sort(struct arch *arch)
-{
-	const int nmemb = arch->nr_instructions;
-
-	qsort(arch->instructions, nmemb, sizeof(struct ins), ins__cmp);
-}
-
-static struct ins_ops *__ins__find(struct arch *arch, const char *name)
-{
-	struct ins *ins;
-	const int nmemb = arch->nr_instructions;
-
-	if (!arch->sorted_instructions) {
-		ins__sort(arch);
-		arch->sorted_instructions = true;
-	}
-
-	ins = bsearch(name, arch->instructions, nmemb, sizeof(struct ins), ins__key_cmp);
-	if (ins)
-		return ins->ops;
-
-	if (arch->insn_suffix) {
-		char tmp[32];
-		char suffix;
-		size_t len = strlen(name);
-
-		if (len == 0 || len >= sizeof(tmp))
-			return NULL;
-
-		suffix = name[len - 1];
-		if (strchr(arch->insn_suffix, suffix) == NULL)
-			return NULL;
-
-		strcpy(tmp, name);
-		tmp[len - 1] = '\0'; /* remove the suffix and check again */
-
-		ins = bsearch(tmp, arch->instructions, nmemb, sizeof(struct ins), ins__key_cmp);
-	}
-	return ins ? ins->ops : NULL;
-}
-
-static struct ins_ops *ins__find(struct arch *arch, const char *name)
-{
-	struct ins_ops *ops = __ins__find(arch, name);
-
-	if (!ops && arch->associate_instruction_ops)
-		ops = arch->associate_instruction_ops(arch, name);
-
-	return ops;
-}
-
-static int arch__key_cmp(const void *name, const void *archp)
-{
-	const struct arch *arch = archp;
-
-	return strcmp(name, arch->name);
-}
-
-static int arch__cmp(const void *a, const void *b)
-{
-	const struct arch *aa = a;
-	const struct arch *ab = b;
-
-	return strcmp(aa->name, ab->name);
-}
-
-static void arch__sort(void)
-{
-	const int nmemb = ARRAY_SIZE(architectures);
-
-	qsort(architectures, nmemb, sizeof(struct arch), arch__cmp);
-}
-
-static struct arch *arch__find(const char *name)
-{
-	const int nmemb = ARRAY_SIZE(architectures);
-	static bool sorted;
-
-	if (!sorted) {
-		arch__sort();
-		sorted = true;
-	}
-
-	return bsearch(name, architectures, nmemb, sizeof(struct arch), arch__key_cmp);
-}
-
-bool arch__is(struct arch *arch, const char *name)
-{
-	return !strcmp(arch->name, name);
-}
-
 /* symbol histogram: key = offset << 16 | evsel->core.idx */
 static size_t sym_hist_hash(long key, void *ctx __maybe_unused)
 {
@@ -1156,14 +376,33 @@ int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
 	return err;
 }
 
+struct annotation_line *annotated_source__get_line(struct annotated_source *src,
+						   s64 offset)
+{
+	struct annotation_line *al;
+
+	list_for_each_entry(al, &src->source, node) {
+		if (al->offset == offset)
+			return al;
+	}
+	return NULL;
+}
+
 static unsigned annotation__count_insn(struct annotation *notes, u64 start, u64 end)
 {
+	struct annotation_line *al;
 	unsigned n_insn = 0;
-	u64 offset;
 
-	for (offset = start; offset <= end; offset++) {
-		if (notes->src->offsets[offset])
-			n_insn++;
+	al = annotated_source__get_line(notes->src, start);
+	if (al == NULL)
+		return 0;
+
+	list_for_each_entry_from(al, &notes->src->source, node) {
+		if (al->offset == -1)
+			continue;
+		if ((u64)al->offset > end)
+			break;
+		n_insn++;
 	}
 	return n_insn;
 }
@@ -1180,10 +419,10 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 {
 	unsigned n_insn;
 	unsigned int cover_insn = 0;
-	u64 offset;
 
 	n_insn = annotation__count_insn(notes, start, end);
 	if (n_insn && ch->num && ch->cycles) {
+		struct annotation_line *al;
 		struct annotated_branch *branch;
 		float ipc = n_insn / ((double)ch->cycles / (double)ch->num);
 
@@ -1191,10 +430,16 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 		if (ch->reset >= 0x7fff)
 			return;
 
-		for (offset = start; offset <= end; offset++) {
-			struct annotation_line *al = notes->src->offsets[offset];
+		al = annotated_source__get_line(notes->src, start);
+		if (al == NULL)
+			return;
 
-			if (al && al->cycles && al->cycles->ipc == 0.0) {
+		list_for_each_entry_from(al, &notes->src->source, node) {
+			if (al->offset == -1)
+				continue;
+			if ((u64)al->offset > end)
+				break;
+			if (al->cycles && al->cycles->ipc == 0.0) {
 				al->cycles->ipc = ipc;
 				cover_insn++;
 			}
@@ -1230,7 +475,7 @@ static int annotation__compute_ipc(struct annotation *notes, size_t size)
 		if (ch && ch->cycles) {
 			struct annotation_line *al;
 
-			al = notes->src->offsets[offset];
+			al = annotated_source__get_line(notes->src, offset);
 			if (al && al->cycles == NULL) {
 				al->cycles = zalloc(sizeof(*al->cycles));
 				if (al->cycles == NULL) {
@@ -1253,7 +498,9 @@ static int annotation__compute_ipc(struct annotation *notes, size_t size)
 			struct cyc_hist *ch = &notes->branch->cycles_hist[offset];
 
 			if (ch && ch->cycles) {
-				struct annotation_line *al = notes->src->offsets[offset];
+				struct annotation_line *al;
+
+				al = annotated_source__get_line(notes->src, offset);
 				if (al)
 					zfree(&al->cycles);
 			}
@@ -1276,142 +523,6 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *samp
 	return symbol__inc_addr_samples(&he->ms, evsel, ip, sample);
 }
 
-static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map_symbol *ms)
-{
-	dl->ins.ops = ins__find(arch, dl->ins.name);
-
-	if (!dl->ins.ops)
-		return;
-
-	if (dl->ins.ops->parse && dl->ins.ops->parse(arch, &dl->ops, ms) < 0)
-		dl->ins.ops = NULL;
-}
-
-static int disasm_line__parse(char *line, const char **namep, char **rawp)
-{
-	char tmp, *name = skip_spaces(line);
-
-	if (name[0] == '\0')
-		return -1;
-
-	*rawp = name + 1;
-
-	while ((*rawp)[0] != '\0' && !isspace((*rawp)[0]))
-		++*rawp;
-
-	tmp = (*rawp)[0];
-	(*rawp)[0] = '\0';
-	*namep = strdup(name);
-
-	if (*namep == NULL)
-		goto out;
-
-	(*rawp)[0] = tmp;
-	*rawp = strim(*rawp);
-
-	return 0;
-
-out:
-	return -1;
-}
-
-struct annotate_args {
-	struct arch		  *arch;
-	struct map_symbol	  ms;
-	struct evsel		  *evsel;
-	struct annotation_options *options;
-	s64			  offset;
-	char			  *line;
-	int			  line_nr;
-	char			  *fileloc;
-};
-
-static void annotation_line__init(struct annotation_line *al,
-				  struct annotate_args *args,
-				  int nr)
-{
-	al->offset = args->offset;
-	al->line = strdup(args->line);
-	al->line_nr = args->line_nr;
-	al->fileloc = args->fileloc;
-	al->data_nr = nr;
-}
-
-static void annotation_line__exit(struct annotation_line *al)
-{
-	zfree_srcline(&al->path);
-	zfree(&al->line);
-	zfree(&al->cycles);
-}
-
-static size_t disasm_line_size(int nr)
-{
-	struct annotation_line *al;
-
-	return (sizeof(struct disasm_line) + (sizeof(al->data[0]) * nr));
-}
-
-/*
- * Allocating the disasm annotation line data with
- * following structure:
- *
- *    -------------------------------------------
- *    struct disasm_line | struct annotation_line
- *    -------------------------------------------
- *
- * We have 'struct annotation_line' member as last member
- * of 'struct disasm_line' to have an easy access.
- */
-static struct disasm_line *disasm_line__new(struct annotate_args *args)
-{
-	struct disasm_line *dl = NULL;
-	int nr = 1;
-
-	if (evsel__is_group_event(args->evsel))
-		nr = args->evsel->core.nr_members;
-
-	dl = zalloc(disasm_line_size(nr));
-	if (!dl)
-		return NULL;
-
-	annotation_line__init(&dl->al, args, nr);
-	if (dl->al.line == NULL)
-		goto out_delete;
-
-	if (args->offset != -1) {
-		if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
-			goto out_free_line;
-
-		disasm_line__init_ins(dl, args->arch, &args->ms);
-	}
-
-	return dl;
-
-out_free_line:
-	zfree(&dl->al.line);
-out_delete:
-	free(dl);
-	return NULL;
-}
-
-void disasm_line__free(struct disasm_line *dl)
-{
-	if (dl->ins.ops && dl->ins.ops->free)
-		dl->ins.ops->free(&dl->ops);
-	else
-		ins__delete(&dl->ops);
-	zfree(&dl->ins.name);
-	annotation_line__exit(&dl->al);
-	free(dl);
-}
-
-int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name)
-{
-	if (raw || !dl->ins.ops)
-		return scnprintf(bf, size, "%-*s %s", max_ins_name, dl->ins.name, dl->ops.raw);
-
-	return ins__scnprintf(&dl->ins, bf, size, &dl->ops, max_ins_name);
-}
 
 void annotation__exit(struct annotation *notes)
 {
@@ -1471,8 +582,7 @@ bool annotation__trylock(struct annotation *notes)
 	return mutex_trylock(mutex);
 }
 
-
-static void annotation_line__add(struct annotation_line *al, struct list_head *head)
+void annotation_line__add(struct annotation_line *al, struct list_head *head)
 {
 	list_add_tail(&al->node, head);
 }
@@ -1682,673 +792,6 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
 	return 0;
 }
 
-/*
- * symbol__parse_objdump_line() parses objdump output (with -d --no-show-raw)
- * which looks like following
- *
- *  0000000000415500 <_init>:
- *    415500:       sub    $0x8,%rsp
- *    415504:       mov    0x2f5ad5(%rip),%rax        # 70afe0 <_DYNAMIC+0x2f8>
- *    41550b:       test   %rax,%rax
- *    41550e:       je     415515 <_init+0x15>
- *    415510:       callq  416e70 <__gmon_start__@plt>
- *    415515:       add    $0x8,%rsp
- *    415519:       retq
- *
- * it will be parsed and saved into struct disasm_line as
- *  <offset>       <name>  <ops.raw>
- *
- * The offset will be a relative offset from the start of the symbol and -1
- * means that it's not a disassembly line so should be treated differently.
- * The ops.raw part will be parsed further according to type of the instruction.
- */
-static int symbol__parse_objdump_line(struct symbol *sym,
-				      struct annotate_args *args,
-				      char *parsed_line, int *line_nr, char **fileloc)
-{
-	struct map *map = args->ms.map;
-	struct annotation *notes = symbol__annotation(sym);
-	struct disasm_line *dl;
-	char *tmp;
-	s64 line_ip, offset = -1;
-	regmatch_t match[2];
-
-	/* /filename:linenr ? Save line number and ignore. */
-	if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) {
-		*line_nr = atoi(parsed_line + match[1].rm_so);
-		free(*fileloc);
-		*fileloc = strdup(parsed_line);
-		return 0;
-	}
-
-	/* Process hex address followed by ':'. */
-	line_ip = strtoull(parsed_line, &tmp, 16);
-	if (parsed_line != tmp && tmp[0] == ':' && tmp[1] != '\0') {
-		u64 start = map__rip_2objdump(map, sym->start),
-		    end = map__rip_2objdump(map, sym->end);
-
-		offset = line_ip - start;
-		if ((u64)line_ip < start || (u64)line_ip >= end)
-			offset = -1;
-		else
-			parsed_line = tmp + 1;
-	}
-
-	args->offset  = offset;
-	args->line    = parsed_line;
-	args->line_nr = *line_nr;
-	args->fileloc = *fileloc;
-	args->ms.sym  = sym;
-
-	dl = disasm_line__new(args);
-	(*line_nr)++;
-
-	if (dl == NULL)
-		return -1;
-
-	if (!disasm_line__has_local_offset(dl)) {
-		dl->ops.target.offset = dl->ops.target.addr -
-					map__rip_2objdump(map, sym->start);
-		dl->ops.target.offset_avail = true;
-	}
-
-	/* kcore has no symbols, so add the call target symbol */
-	if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.sym) {
-		struct addr_map_symbol target = {
-			.addr = dl->ops.target.addr,
-			.ms = { .map = map, },
-		};
-
-		if (!maps__find_ams(args->ms.maps, &target) &&
-		    target.ms.sym->start == target.al_addr)
-			dl->ops.target.sym = target.ms.sym;
-	}
-
-	annotation_line__add(&dl->al, &notes->src->source);
-	return 0;
-}
-
-static __attribute__((constructor)) void symbol__init_regexpr(void)
-{
-	regcomp(&file_lineno, "^/[^:]+:([0-9]+)", REG_EXTENDED);
-}
-
-static void delete_last_nop(struct symbol *sym)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	struct list_head *list = &notes->src->source;
-	struct disasm_line *dl;
-
-	while (!list_empty(list)) {
-		dl = list_entry(list->prev, struct disasm_line, al.node);
-
-		if (dl->ins.ops) {
-			if (dl->ins.ops != &nop_ops)
-				return;
-		} else {
-			if (!strstr(dl->al.line, " nop ") &&
-			    !strstr(dl->al.line, " nopl ") &&
-			    !strstr(dl->al.line, " nopw "))
-				return;
-		}
-
-		list_del_init(&dl->al.node);
-		disasm_line__free(dl);
-	}
-}
-
-int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen)
-{
-	struct dso *dso = map__dso(ms->map);
-
-	BUG_ON(buflen == 0);
-
-	if (errnum >= 0) {
-		str_error_r(errnum, buf, buflen);
-		return 0;
-	}
-
-	switch (errnum) {
-	case SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX: {
-		char bf[SBUILD_ID_SIZE + 15] = " with build id ";
-		char *build_id_msg = NULL;
-
-		if (dso->has_build_id) {
-			build_id__sprintf(&dso->bid, bf + 15);
-			build_id_msg = bf;
-		}
-		scnprintf(buf, buflen,
-			  "No vmlinux file%s\nwas found in the path.\n\n"
-			  "Note that annotation using /proc/kcore requires CAP_SYS_RAWIO capability.\n\n"
-			  "Please use:\n\n"
-			  "  perf buildid-cache -vu vmlinux\n\n"
-			  "or:\n\n"
-			  "  --vmlinux vmlinux\n", build_id_msg ?: "");
-	}
-		break;
-	case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF:
-		scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation");
-		break;
-	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP:
-		scnprintf(buf, buflen, "Problems with arch specific instruction name regular expressions.");
-		break;
-	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING:
-		scnprintf(buf, buflen, "Problems while parsing the CPUID in the arch specific initialization.");
-		break;
-	case SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE:
-		scnprintf(buf, buflen, "Invalid BPF file: %s.", dso->long_name);
-		break;
-	case SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF:
-		scnprintf(buf, buflen, "The %s BPF file has no BTF section, compile with -g or use pahole -J.",
-			  dso->long_name);
-		break;
-	default:
-		scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum);
-		break;
-	}
-
-	return 0;
-}
-
-static int dso__disassemble_filename(struct dso *dso, char *filename, size_t filename_size)
-{
-	char linkname[PATH_MAX];
-	char *build_id_filename;
-	char *build_id_path = NULL;
-	char *pos;
-	int len;
-
-	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
-	    !dso__is_kcore(dso))
-		return SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX;
-
-	build_id_filename = dso__build_id_filename(dso, NULL, 0, false);
-	if (build_id_filename) {
-		__symbol__join_symfs(filename, filename_size, build_id_filename);
-		free(build_id_filename);
-	} else {
-		if (dso->has_build_id)
-			return ENOMEM;
-		goto fallback;
-	}
-
-	build_id_path = strdup(filename);
-	if (!build_id_path)
-		return ENOMEM;
-
-	/*
-	 * old style build-id cache has name of XX/XXXXXXX.. while
-	 * new style has XX/XXXXXXX../{elf,kallsyms,vdso}.
-	 * extract the build-id part of dirname in the new style only.
-	 */
-	pos = strrchr(build_id_path, '/');
-	if (pos && strlen(pos) < SBUILD_ID_SIZE - 2)
-		dirname(build_id_path);
-
-	if (dso__is_kcore(dso))
-		goto fallback;
-
-	len = readlink(build_id_path, linkname, sizeof(linkname) - 1);
-	if (len < 0)
-		goto fallback;
-
-	linkname[len] = '\0';
-	if (strstr(linkname, DSO__NAME_KALLSYMS) ||
-		access(filename, R_OK)) {
-fallback:
-		/*
-		 * If we don't have build-ids or the build-id file isn't in the
-		 * cache, or is just a kallsyms file, well, lets hope that this
-		 * DSO is the same as when 'perf record' ran.
-		 */
-		if (dso->kernel && dso->long_name[0] == '/')
-			snprintf(filename, filename_size, "%s", dso->long_name);
-		else
-			__symbol__join_symfs(filename, filename_size, dso->long_name);
-
-		mutex_lock(&dso->lock);
-		if (access(filename, R_OK) && errno == ENOENT && dso->nsinfo) {
-			char *new_name = dso__filename_with_chroot(dso, filename);
-			if (new_name) {
-				strlcpy(filename, new_name, filename_size);
-				free(new_name);
-			}
-		}
-		mutex_unlock(&dso->lock);
-	}
-
-	free(build_id_path);
-	return 0;
-}
-
-#if defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
-#define PACKAGE "perf"
-#include <bfd.h>
-#include <dis-asm.h>
-#include <bpf/bpf.h>
-#include <bpf/btf.h>
-#include <bpf/libbpf.h>
-#include <linux/btf.h>
-#include <tools/dis-asm-compat.h>
-
-static int symbol__disassemble_bpf(struct symbol *sym,
-				   struct annotate_args *args)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	struct bpf_prog_linfo *prog_linfo = NULL;
-	struct bpf_prog_info_node *info_node;
-	int len = sym->end - sym->start;
-	disassembler_ftype disassemble;
-	struct map *map = args->ms.map;
-	struct perf_bpil *info_linear;
-	struct disassemble_info info;
-	struct dso *dso = map__dso(map);
-	int pc = 0, count, sub_id;
-	struct btf *btf = NULL;
-	char tpath[PATH_MAX];
-	size_t buf_size;
-	int nr_skip = 0;
-	char *buf;
-	bfd *bfdf;
-	int ret;
-	FILE *s;
-
-	if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
-		return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE;
-
-	pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
-		  sym->name, sym->start, sym->end - sym->start);
-
-	memset(tpath, 0, sizeof(tpath));
-	perf_exe(tpath, sizeof(tpath));
-
-	bfdf = bfd_openr(tpath, NULL);
-	if (bfdf == NULL)
-		abort();
-
-	if (!bfd_check_format(bfdf, bfd_object))
-		abort();
-
-	s = open_memstream(&buf, &buf_size);
-	if (!s) {
-		ret = errno;
-		goto out;
-	}
-	init_disassemble_info_compat(&info, s,
-				     (fprintf_ftype) fprintf,
-				     fprintf_styled);
-	info.arch = bfd_get_arch(bfdf);
-	info.mach = bfd_get_mach(bfdf);
-
-	info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env,
-						 dso->bpf_prog.id);
-	if (!info_node) {
-		ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF;
-		goto out;
-	}
-	info_linear = info_node->info_linear;
-	sub_id = dso->bpf_prog.sub_id;
-
-	info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns);
-	info.buffer_length = info_linear->info.jited_prog_len;
-
-	if (info_linear->info.nr_line_info)
-		prog_linfo = bpf_prog_linfo__new(&info_linear->info);
-
-	if (info_linear->info.btf_id) {
-		struct btf_node *node;
-
-		node = perf_env__find_btf(dso->bpf_prog.env,
-					  info_linear->info.btf_id);
-		if (node)
-			btf = btf__new((__u8 *)(node->data),
-				       node->data_size);
-	}
-
-	disassemble_init_for_target(&info);
-
-#ifdef DISASM_FOUR_ARGS_SIGNATURE
-	disassemble = disassembler(info.arch,
-				   bfd_big_endian(bfdf),
-				   info.mach,
-				   bfdf);
-#else
-	disassemble = disassembler(bfdf);
-#endif
-	if (disassemble == NULL)
-		abort();
-
-	fflush(s);
-	do {
-		const struct bpf_line_info *linfo = NULL;
-		struct disasm_line *dl;
-		size_t prev_buf_size;
-		const char *srcline;
-		u64 addr;
-
-		addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id];
-		count = disassemble(pc, &info);
-
-		if (prog_linfo)
-			linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo,
-								addr, sub_id,
-								nr_skip);
-
-		if (linfo && btf) {
-			srcline = btf__name_by_offset(btf, linfo->line_off);
-			nr_skip++;
-		} else
-			srcline = NULL;
-
-		fprintf(s, "\n");
-		prev_buf_size = buf_size;
-		fflush(s);
-
-		if (!annotate_opts.hide_src_code && srcline) {
-			args->offset = -1;
-			args->line = strdup(srcline);
-			args->line_nr = 0;
-			args->fileloc = NULL;
-			args->ms.sym  = sym;
-			dl = disasm_line__new(args);
-			if (dl) {
-				annotation_line__add(&dl->al,
-						     &notes->src->source);
-			}
-		}
-
-		args->offset = pc;
-		args->line = buf + prev_buf_size;
-		args->line_nr = 0;
-		args->fileloc = NULL;
-		args->ms.sym  = sym;
-		dl = disasm_line__new(args);
-		if (dl)
-			annotation_line__add(&dl->al, &notes->src->source);
-
-		pc += count;
-	} while (count > 0 && pc < len);
-
-	ret = 0;
-out:
-	free(prog_linfo);
-	btf__free(btf);
-	fclose(s);
-	bfd_close(bfdf);
-	return ret;
-}
-#else // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
-static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused,
-				   struct annotate_args *args __maybe_unused)
-{
-	return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF;
-}
-#endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
-
-static int
-symbol__disassemble_bpf_image(struct symbol *sym,
-			      struct annotate_args *args)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	struct disasm_line *dl;
-
-	args->offset = -1;
-	args->line = strdup("to be implemented");
-	args->line_nr = 0;
-	args->fileloc = NULL;
-	dl = disasm_line__new(args);
-	if (dl)
-		annotation_line__add(&dl->al, &notes->src->source);
-
-	zfree(&args->line);
-	return 0;
-}
-
-/*
- * Possibly create a new version of line with tabs expanded. Returns the
- * existing or new line, storage is updated if a new line is allocated. If
- * allocation fails then NULL is returned.
- */
-static char *expand_tabs(char *line, char **storage, size_t *storage_len)
-{
-	size_t i, src, dst, len, new_storage_len, num_tabs;
-	char *new_line;
-	size_t line_len = strlen(line);
-
-	for (num_tabs = 0, i = 0; i < line_len; i++)
-		if (line[i] == '\t')
-			num_tabs++;
-
-	if (num_tabs == 0)
-		return line;
-
-	/*
-	 * Space for the line and '\0', less the leading and trailing
-	 * spaces. Each tab may introduce 7 additional spaces.
-	 */
-	new_storage_len = line_len + 1 + (num_tabs * 7);
-
-	new_line = malloc(new_storage_len);
-	if (new_line == NULL) {
-		pr_err("Failure allocating memory for tab expansion\n");
-		return NULL;
-	}
-
-	/*
-	 * Copy regions starting at src and expand tabs. If there are two
-	 * adjacent tabs then 'src == i', the memcpy is of size 0 and the spaces
-	 * are inserted.
-	 */
-	for (i = 0, src = 0, dst = 0; i < line_len && num_tabs; i++) {
-		if (line[i] == '\t') {
-			len = i - src;
-			memcpy(&new_line[dst], &line[src], len);
-			dst += len;
-			new_line[dst++] = ' ';
-			while (dst % 8 != 0)
-				new_line[dst++] = ' ';
-			src = i + 1;
-			num_tabs--;
-		}
-	}
-
-	/* Expand the last region. */
-	len = line_len - src;
-	memcpy(&new_line[dst], &line[src], len);
-	dst += len;
-	new_line[dst] = '\0';
-
-	free(*storage);
-	*storage = new_line;
-	*storage_len = new_storage_len;
-	return new_line;
-
-}
-
-static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
-{
-	struct annotation_options *opts = &annotate_opts;
-	struct map *map = args->ms.map;
-	struct dso *dso = map__dso(map);
-	char *command;
-	FILE *file;
-	char symfs_filename[PATH_MAX];
-	struct kcore_extract kce;
-	bool delete_extract = false;
-	bool decomp = false;
-	int lineno = 0;
-	char *fileloc = NULL;
-	int nline;
-	char *line;
-	size_t line_len;
-	const char *objdump_argv[] = {
-		"/bin/sh",
-		"-c",
-		NULL, /* Will be the objdump command to run. */
-		"--",
-		NULL, /* Will be the symfs path. */
-		NULL,
-	};
-	struct child_process objdump_process;
-	int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename));
-
-	if (err)
-		return err;
-
-	pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
-		 symfs_filename, sym->name, map__unmap_ip(map, sym->start),
-		 map__unmap_ip(map, sym->end));
-
-	pr_debug("annotating [%p] %30s : [%p] %30s\n",
-		 dso, dso->long_name, sym, sym->name);
-
-	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) {
-		return symbol__disassemble_bpf(sym, args);
-	} else if (dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE) {
-		return symbol__disassemble_bpf_image(sym, args);
-	} else if (dso__is_kcore(dso)) {
-		kce.kcore_filename = symfs_filename;
-		kce.addr = map__rip_2objdump(map, sym->start);
-		kce.offs = sym->start;
-		kce.len = sym->end - sym->start;
-		if (!kcore_extract__create(&kce)) {
-			delete_extract = true;
-			strlcpy(symfs_filename, kce.extract_filename,
-				sizeof(symfs_filename));
-		}
-	} else if (dso__needs_decompress(dso)) {
-		char tmp[KMOD_DECOMP_LEN];
-
-		if (dso__decompress_kmodule_path(dso, symfs_filename,
-						 tmp, sizeof(tmp)) < 0)
-			return -1;
-
-		decomp = true;
-		strcpy(symfs_filename, tmp);
-	}
-
-	err = asprintf(&command,
-		 "%s %s%s --start-address=0x%016" PRIx64
-		 " --stop-address=0x%016" PRIx64
-		 " %s -d %s %s %s %c%s%c %s%s -C \"$1\"",
-		 opts->objdump_path ?: "objdump",
-		 opts->disassembler_style ? "-M " : "",
-		 opts->disassembler_style ?: "",
-		 map__rip_2objdump(map, sym->start),
-		 map__rip_2objdump(map, sym->end),
-		 opts->show_linenr ? "-l" : "",
-		 opts->show_asm_raw ? "" : "--no-show-raw-insn",
-		 opts->annotate_src ? "-S" : "",
-		 opts->prefix ? "--prefix " : "",
-		 opts->prefix ? '"' : ' ',
-		 opts->prefix ?: "",
-		 opts->prefix ? '"' : ' ',
-		 opts->prefix_strip ? "--prefix-strip=" : "",
-		 opts->prefix_strip ?: "");
-
-	if (err < 0) {
-		pr_err("Failure allocating memory for the command to run\n");
-		goto out_remove_tmp;
-	}
-
-	pr_debug("Executing: %s\n", command);
-
-	objdump_argv[2] = command;
-	objdump_argv[4] = symfs_filename;
-
-	/* Create a pipe to read from for stdout */
-	memset(&objdump_process, 0, sizeof(objdump_process));
-	objdump_process.argv = objdump_argv;
-	objdump_process.out = -1;
-	objdump_process.err = -1;
-	objdump_process.no_stderr = 1;
-	if (start_command(&objdump_process)) {
-		pr_err("Failure starting to run %s\n", command);
-		err = -1;
-		goto out_free_command;
-	}
-
-	file = fdopen(objdump_process.out, "r");
-	if (!file) {
-		pr_err("Failure creating FILE stream for %s\n", command);
-		/*
-		 * If we were using debug info should retry with
-		 * original binary.
-		 */
-		err = -1;
-		goto out_close_stdout;
-	}
-
-	/* Storage for getline. */
-	line = NULL;
-	line_len = 0;
-
-	nline = 0;
-	while (!feof(file)) {
-		const char *match;
-		char *expanded_line;
-
-		if (getline(&line, &line_len, file) < 0 || !line)
-			break;
-
-		/* Skip lines containing "filename:" */
-		match = strstr(line, symfs_filename);
-		if (match && match[strlen(symfs_filename)] == ':')
-			continue;
-
-		expanded_line = strim(line);
-		expanded_line = expand_tabs(expanded_line, &line, &line_len);
-		if (!expanded_line)
-			break;
-
-		/*
-		 * The source code line number (lineno) needs to be kept in
-		 * across calls to symbol__parse_objdump_line(), so that it
-		 * can associate it with the instructions till the next one.
-		 * See disasm_line__new() and struct disasm_line::line_nr.
-		 */
-		if (symbol__parse_objdump_line(sym, args, expanded_line,
-					       &lineno, &fileloc) < 0)
-			break;
-		nline++;
-	}
-	free(line);
-	free(fileloc);
-
-	err = finish_command(&objdump_process);
-	if (err)
-		pr_err("Error running %s\n", command);
-
-	if (nline == 0) {
-		err = -1;
-		pr_err("No output from %s\n", command);
-	}
-
-	/*
-	 * kallsyms does not have symbol sizes so there may a nop at the end.
-	 * Remove it.
-	 */
-	if (dso__is_kcore(dso))
-		delete_last_nop(sym);
-
-	fclose(file);
-
-out_close_stdout:
-	close(objdump_process.out);
-
-out_free_command:
-	free(command);
-
-out_remove_tmp:
-	if (decomp)
-		unlink(symfs_filename);
-
-	if (delete_extract)
-		kcore_extract__delete(&kce);
-
-	return err;
-}
-
 static void calc_percent(struct annotation *notes,
 			 struct evsel *evsel,
 			 struct annotation_data *data,
@@ -2429,8 +872,10 @@ static int evsel__get_arch(struct evsel *evsel, struct arch **parch)
 	struct arch *arch;
 	int err;
 
-	if (!arch_name)
+	if (!arch_name) {
+		*parch = NULL;
 		return errno;
+	}
 
 	*parch = arch = arch__find(arch_name);
 	if (arch == NULL) {
@@ -2468,15 +913,22 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 	if (parch)
 		*parch = arch;
 
-	if (!list_empty(&notes->src->source))
+	if (notes->src && !list_empty(&notes->src->source))
 		return 0;
 
 	args.arch = arch;
 	args.ms = *ms;
+
+	if (notes->src == NULL) {
+		notes->src = annotated_source__new();
+		if (notes->src == NULL)
+			return -1;
+	}
+
 	if (annotate_opts.full_addr)
-		notes->start = map__objdump_2mem(ms->map, ms->sym->start);
+		notes->src->start = map__objdump_2mem(ms->map, ms->sym->start);
 	else
-		notes->start = map__rip_2objdump(ms->map, ms->sym->start);
+		notes->src->start = map__rip_2objdump(ms->map, ms->sym->start);
 
 	return symbol__disassemble(sym, &args);
 }
@@ -2658,7 +1110,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel)
 	int graph_dotted_len;
 	char buf[512];
 
-	filename = strdup(dso->long_name);
+	filename = strdup(dso__long_name(dso));
 	if (!filename)
 		return -ENOMEM;
 
@@ -2823,7 +1275,7 @@ int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel)
 	}
 
 	fprintf(fp, "%s() %s\nEvent: %s\n\n",
-		ms->sym->name, map__dso(ms->map)->long_name, ev_name);
+		ms->sym->name, dso__long_name(map__dso(ms->map)), ev_name);
 	symbol__annotate_fprintf2(ms->sym, fp);
 
 	fclose(fp);
@@ -2845,13 +1297,16 @@ void symbol__annotate_decay_histogram(struct symbol *sym, int evidx)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	struct sym_hist *h = annotation__histogram(notes, evidx);
-	int len = symbol__size(sym), offset;
+	struct annotation_line *al;
 
 	h->nr_samples = 0;
-	for (offset = 0; offset < len; ++offset) {
+	list_for_each_entry(al, &notes->src->source, node) {
 		struct sym_hist_entry *entry;
 
-		entry = annotated_source__hist_entry(notes->src, evidx, offset);
+		if (al->offset == -1)
+			continue;
+
+		entry = annotated_source__hist_entry(notes->src, evidx, al->offset);
 		if (entry == NULL)
 			continue;
 
@@ -2908,64 +1363,56 @@ bool disasm_line__is_valid_local_jump(struct disasm_line *dl, struct symbol *sym
 	return true;
 }
 
-void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
+static void
+annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
 {
-	u64 offset, size = symbol__size(sym);
+	struct annotation_line *al;
 
 	/* PLT symbols contain external offsets */
 	if (strstr(sym->name, "@plt"))
 		return;
 
-	for (offset = 0; offset < size; ++offset) {
-		struct annotation_line *al = notes->src->offsets[offset];
+	list_for_each_entry(al, &notes->src->source, node) {
 		struct disasm_line *dl;
+		struct annotation_line *target;
 
 		dl = disasm_line(al);
 
 		if (!disasm_line__is_valid_local_jump(dl, sym))
 			continue;
 
-		al = notes->src->offsets[dl->ops.target.offset];
-
+		target = annotated_source__get_line(notes->src,
+						    dl->ops.target.offset);
 		/*
 		 * FIXME: Oops, no jump target? Buggy disassembler? Or do we
 		 * have to adjust to the previous offset?
 		 */
-		if (al == NULL)
+		if (target == NULL)
 			continue;
 
-		if (++al->jump_sources > notes->max_jump_sources)
-			notes->max_jump_sources = al->jump_sources;
+		if (++target->jump_sources > notes->src->max_jump_sources)
+			notes->src->max_jump_sources = target->jump_sources;
 	}
 }
 
-void annotation__set_offsets(struct annotation *notes, s64 size)
+static void annotation__set_index(struct annotation *notes)
 {
 	struct annotation_line *al;
 	struct annotated_source *src = notes->src;
 
-	src->max_line_len = 0;
+	src->widths.max_line_len = 0;
 	src->nr_entries = 0;
 	src->nr_asm_entries = 0;
 
 	list_for_each_entry(al, &src->source, node) {
 		size_t line_len = strlen(al->line);
 
-		if (src->max_line_len < line_len)
-			src->max_line_len = line_len;
+		if (src->widths.max_line_len < line_len)
+			src->widths.max_line_len = line_len;
 		al->idx = src->nr_entries++;
-		if (al->offset != -1) {
+		if (al->offset != -1)
 			al->idx_asm = src->nr_asm_entries++;
-			/*
-			 * FIXME: short term bandaid to cope with assembly
-			 * routines that comes with labels in the same column
-			 * as the address in objdump, sigh.
-			 *
-			 * E.g. copy_user_generic_unrolled
- 			 */
-			if (al->offset < size)
-				notes->src->offsets[al->offset] = al;
-		} else
+		else
 			al->idx_asm = -1;
 	}
 }
@@ -2996,28 +1443,29 @@ static int annotation__max_ins_name(struct annotation *notes)
 	return max_name;
 }
 
-void annotation__init_column_widths(struct annotation *notes, struct symbol *sym)
+static void
+annotation__init_column_widths(struct annotation *notes, struct symbol *sym)
 {
-	notes->widths.addr = notes->widths.target =
-		notes->widths.min_addr = hex_width(symbol__size(sym));
-	notes->widths.max_addr = hex_width(sym->end);
-	notes->widths.jumps = width_jumps(notes->max_jump_sources);
-	notes->widths.max_ins_name = annotation__max_ins_name(notes);
+	notes->src->widths.addr = notes->src->widths.target =
+		notes->src->widths.min_addr = hex_width(symbol__size(sym));
+	notes->src->widths.max_addr = hex_width(sym->end);
+	notes->src->widths.jumps = width_jumps(notes->src->max_jump_sources);
+	notes->src->widths.max_ins_name = annotation__max_ins_name(notes);
 }
 
 void annotation__update_column_widths(struct annotation *notes)
 {
 	if (annotate_opts.use_offset)
-		notes->widths.target = notes->widths.min_addr;
+		notes->src->widths.target = notes->src->widths.min_addr;
 	else if (annotate_opts.full_addr)
-		notes->widths.target = BITS_PER_LONG / 4;
+		notes->src->widths.target = BITS_PER_LONG / 4;
 	else
-		notes->widths.target = notes->widths.max_addr;
+		notes->src->widths.target = notes->src->widths.max_addr;
 
-	notes->widths.addr = notes->widths.target;
+	notes->src->widths.addr = notes->src->widths.target;
 
 	if (annotate_opts.show_nr_jumps)
-		notes->widths.addr += notes->widths.jumps + 1;
+		notes->src->widths.addr += notes->src->widths.jumps + 1;
 }
 
 void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *ms)
@@ -3025,9 +1473,9 @@ void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *m
 	annotate_opts.full_addr = !annotate_opts.full_addr;
 
 	if (annotate_opts.full_addr)
-		notes->start = map__objdump_2mem(ms->map, ms->sym->start);
+		notes->src->start = map__objdump_2mem(ms->map, ms->sym->start);
 	else
-		notes->start = map__rip_2objdump(ms->map, ms->sym->start);
+		notes->src->start = map__rip_2objdump(ms->map, ms->sym->start);
 
 	annotation__update_column_widths(notes);
 }
@@ -3085,7 +1533,7 @@ int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel)
 	if (err) {
 		char msg[BUFSIZ];
 
-		dso->annotate_warned = true;
+		dso__set_annotate_warned(dso);
 		symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
 		ui__error("Couldn't annotate %s:\n%s", sym->name, msg);
 		return -1;
@@ -3094,13 +1542,12 @@ int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel)
 	if (annotate_opts.print_lines) {
 		srcline_full_filename = annotate_opts.full_path;
 		symbol__calc_lines(ms, &source_line);
-		print_summary(&source_line, dso->long_name);
+		print_summary(&source_line, dso__long_name(dso));
 	}
 
 	hists__scnprintf_title(hists, buf, sizeof(buf));
 	fprintf(stdout, "%s, [percent: %s]\n%s() %s\n",
-		buf, percent_type_str(annotate_opts.percent_type), sym->name,
-		dso->long_name);
+		buf, percent_type_str(annotate_opts.percent_type), sym->name, dso__long_name(dso));
 	symbol__annotate_fprintf2(sym, stdout);
 
 	annotated_source__purge(symbol__annotation(sym)->src);
@@ -3119,7 +1566,7 @@ int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel)
 	if (err) {
 		char msg[BUFSIZ];
 
-		dso->annotate_warned = true;
+		dso__set_annotate_warned(dso);
 		symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
 		ui__error("Couldn't annotate %s:\n%s", sym->name, msg);
 		return -1;
@@ -3130,7 +1577,7 @@ int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel)
 	if (annotate_opts.print_lines) {
 		srcline_full_filename = annotate_opts.full_path;
 		symbol__calc_lines(ms, &source_line);
-		print_summary(&source_line, dso->long_name);
+		print_summary(&source_line, dso__long_name(dso));
 	}
 
 	symbol__annotate_printf(ms, evsel);
@@ -3153,7 +1600,7 @@ static double annotation_line__max_percent(struct annotation_line *al,
 	double percent_max = 0.0;
 	int i;
 
-	for (i = 0; i < notes->nr_events; i++) {
+	for (i = 0; i < notes->src->nr_events; i++) {
 		double percent;
 
 		percent = annotation_data__percent(&al->data[i],
@@ -3194,7 +1641,8 @@ call_like:
 		obj__printf(obj, "  ");
 	}
 
-	disasm_line__scnprintf(dl, bf, size, !annotate_opts.use_offset, notes->widths.max_ins_name);
+	disasm_line__scnprintf(dl, bf, size, !annotate_opts.use_offset,
+			       notes->src->widths.max_ins_name);
 }
 
 static void ipc_coverage_string(char *bf, int size, struct annotation *notes)
@@ -3242,7 +1690,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 	if (al->offset != -1 && percent_max != 0.0) {
 		int i;
 
-		for (i = 0; i < notes->nr_events; i++) {
+		for (i = 0; i < notes->src->nr_events; i++) {
 			double percent;
 
 			percent = annotation_data__percent(&al->data[i], percent_type);
@@ -3322,9 +1770,11 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		obj__printf(obj, "%-*s", width - pcnt_width - cycles_width, " ");
 	else if (al->offset == -1) {
 		if (al->line_nr && annotate_opts.show_linenr)
-			printed = scnprintf(bf, sizeof(bf), "%-*d ", notes->widths.addr + 1, al->line_nr);
+			printed = scnprintf(bf, sizeof(bf), "%-*d ",
+					    notes->src->widths.addr + 1, al->line_nr);
 		else
-			printed = scnprintf(bf, sizeof(bf), "%-*s  ", notes->widths.addr, " ");
+			printed = scnprintf(bf, sizeof(bf), "%-*s  ",
+					    notes->src->widths.addr, " ");
 		obj__printf(obj, bf);
 		obj__printf(obj, "%-*s", width - printed - pcnt_width - cycles_width + 1, al->line);
 	} else {
@@ -3332,7 +1782,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		int color = -1;
 
 		if (!annotate_opts.use_offset)
-			addr += notes->start;
+			addr += notes->src->start;
 
 		if (!annotate_opts.use_offset) {
 			printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
@@ -3342,7 +1792,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 				if (annotate_opts.show_nr_jumps) {
 					int prev;
 					printed = scnprintf(bf, sizeof(bf), "%*d ",
-							    notes->widths.jumps,
+							    notes->src->widths.jumps,
 							    al->jump_sources);
 					prev = obj__set_jumps_percent_color(obj, al->jump_sources,
 									    current_entry);
@@ -3351,7 +1801,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 				}
 print_addr:
 				printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ",
-						    notes->widths.target, addr);
+						    notes->src->widths.target, addr);
 			} else if (ins__is_call(&disasm_line(al)->ins) &&
 				   annotate_opts.offset_level >= ANNOTATION__OFFSET_CALL) {
 				goto print_addr;
@@ -3359,7 +1809,7 @@ print_addr:
 				goto print_addr;
 			} else {
 				printed = scnprintf(bf, sizeof(bf), "%-*s  ",
-						    notes->widths.addr, " ");
+						    notes->src->widths.addr, " ");
 			}
 		}
 
@@ -3395,37 +1845,29 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	size_t size = symbol__size(sym);
 	int nr_pcnt = 1, err;
 
-	notes->src->offsets = zalloc(size * sizeof(struct annotation_line *));
-	if (notes->src->offsets == NULL)
-		return ENOMEM;
-
 	if (evsel__is_group_event(evsel))
 		nr_pcnt = evsel->core.nr_members;
 
 	err = symbol__annotate(ms, evsel, parch);
 	if (err)
-		goto out_free_offsets;
+		return err;
 
 	symbol__calc_percent(sym, evsel);
 
-	annotation__set_offsets(notes, size);
+	annotation__set_index(notes);
 	annotation__mark_jump_targets(notes, sym);
 
 	err = annotation__compute_ipc(notes, size);
 	if (err)
-		goto out_free_offsets;
+		return err;
 
 	annotation__init_column_widths(notes, sym);
-	notes->nr_events = nr_pcnt;
+	notes->src->nr_events = nr_pcnt;
 
 	annotation__update_column_widths(notes);
 	sym->annotate2 = 1;
 
 	return 0;
-
-out_free_offsets:
-	zfree(&notes->src->offsets);
-	return err;
 }
 
 static int annotation__config(const char *var, const char *value, void *data)
@@ -3597,6 +2039,12 @@ static int extract_reg_offset(struct arch *arch, const char *str,
 	 * %gs:0x18(%rbx).  In that case it should skip the part.
 	 */
 	if (*str == arch->objdump.register_char) {
+		if (arch__is(arch, "x86")) {
+			/* FIXME: Handle other segment registers */
+			if (!strncmp(str, "%gs:", 4))
+				op_loc->segment = INSN_SEG_X86_GS;
+		}
+
 		while (*str && !isdigit(*str) &&
 		       *str != arch->objdump.memory_ref_char)
 			str++;
@@ -3651,7 +2099,7 @@ static int extract_reg_offset(struct arch *arch, const char *str,
  *   mov  0x18, %r8      # src_reg1 = -1, src_mem = 0
  *                       # dst_reg1 = r8, dst_mem = 0
  *
- *   mov  %rsi, 8(%rbx,%rcx,4)  # src_reg1 = rsi, src_mem = 0, dst_multi_regs = 0
+ *   mov  %rsi, 8(%rbx,%rcx,4)  # src_reg1 = rsi, src_mem = 0, src_multi_regs = 0
  *                              # dst_reg1 = rbx, dst_reg2 = rcx, dst_mem = 1
  *                              # dst_multi_regs = 1, dst_offset = 8
  */
@@ -3662,7 +2110,7 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
 	struct annotated_op_loc *op_loc;
 	int i;
 
-	if (!strcmp(dl->ins.name, "lock"))
+	if (ins__is_lock(&dl->ins))
 		ops = dl->ops.locked.ops;
 	else
 		ops = &dl->ops;
@@ -3693,40 +2141,40 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
 			op_loc->multi_regs = multi_regs;
 			extract_reg_offset(arch, insn_str, op_loc);
 		} else {
-			char *s = strdup(insn_str);
+			char *s, *p = NULL;
+
+			if (arch__is(arch, "x86")) {
+				/* FIXME: Handle other segment registers */
+				if (!strncmp(insn_str, "%gs:", 4)) {
+					op_loc->segment = INSN_SEG_X86_GS;
+					op_loc->offset = strtol(insn_str + 4,
+								&p, 0);
+					if (p && p != insn_str + 4)
+						op_loc->imm = true;
+					continue;
+				}
+			}
+
+			s = strdup(insn_str);
+			if (s == NULL)
+				return -1;
 
-			if (s) {
+			if (*s == arch->objdump.register_char)
 				op_loc->reg1 = get_dwarf_regnum(s, 0);
-				free(s);
+			else if (*s == arch->objdump.imm_char) {
+				op_loc->offset = strtol(s + 1, &p, 0);
+				if (p && p != s + 1)
+					op_loc->imm = true;
 			}
+			free(s);
 		}
 	}
 
 	return 0;
 }
 
-static void symbol__ensure_annotate(struct map_symbol *ms, struct evsel *evsel)
-{
-	struct disasm_line *dl, *tmp_dl;
-	struct annotation *notes;
-
-	notes = symbol__annotation(ms->sym);
-	if (!list_empty(&notes->src->source))
-		return;
-
-	if (symbol__annotate(ms, evsel, NULL) < 0)
-		return;
-
-	/* remove non-insn disasm lines for simplicity */
-	list_for_each_entry_safe(dl, tmp_dl, &notes->src->source, al.node) {
-		if (dl->al.offset == -1) {
-			list_del(&dl->al.node);
-			free(dl);
-		}
-	}
-}
-
-static struct disasm_line *find_disasm_line(struct symbol *sym, u64 ip)
+static struct disasm_line *find_disasm_line(struct symbol *sym, u64 ip,
+					    bool allow_update)
 {
 	struct disasm_line *dl;
 	struct annotation *notes;
@@ -3734,12 +2182,16 @@ static struct disasm_line *find_disasm_line(struct symbol *sym, u64 ip)
 	notes = symbol__annotation(sym);
 
 	list_for_each_entry(dl, &notes->src->source, al.node) {
+		if (dl->al.offset == -1)
+			continue;
+
 		if (sym->start + dl->al.offset == ip) {
 			/*
 			 * llvm-objdump places "lock" in a separate line and
 			 * in that case, we want to get the next line.
 			 */
-			if (!strcmp(dl->ins.name, "lock") && *dl->ops.raw == '\0') {
+			if (ins__is_lock(&dl->ins) &&
+			    *dl->ops.raw == '\0' && allow_update) {
 				ip++;
 				continue;
 			}
@@ -3785,6 +2237,58 @@ static bool is_stack_operation(struct arch *arch, struct disasm_line *dl)
 	return false;
 }
 
+static bool is_stack_canary(struct arch *arch, struct annotated_op_loc *loc)
+{
+	/* On x86_64, %gs:40 is used for stack canary */
+	if (arch__is(arch, "x86")) {
+		if (loc->segment == INSN_SEG_X86_GS && loc->imm &&
+		    loc->offset == 40)
+			return true;
+	}
+
+	return false;
+}
+
+static struct disasm_line *
+annotation__prev_asm_line(struct annotation *notes, struct disasm_line *curr)
+{
+	struct list_head *sources = &notes->src->source;
+	struct disasm_line *prev;
+
+	if (curr == list_first_entry(sources, struct disasm_line, al.node))
+		return NULL;
+
+	prev = list_prev_entry(curr, al.node);
+	while (prev->al.offset == -1 &&
+	       prev != list_first_entry(sources, struct disasm_line, al.node))
+		prev = list_prev_entry(prev, al.node);
+
+	if (prev->al.offset == -1)
+		return NULL;
+
+	return prev;
+}
+
+static struct disasm_line *
+annotation__next_asm_line(struct annotation *notes, struct disasm_line *curr)
+{
+	struct list_head *sources = &notes->src->source;
+	struct disasm_line *next;
+
+	if (curr == list_last_entry(sources, struct disasm_line, al.node))
+		return NULL;
+
+	next = list_next_entry(curr, al.node);
+	while (next->al.offset == -1 &&
+	       next != list_last_entry(sources, struct disasm_line, al.node))
+		next = list_next_entry(next, al.node);
+
+	if (next->al.offset == -1)
+		return NULL;
+
+	return next;
+}
+
 u64 annotate_calc_pcrel(struct map_symbol *ms, u64 ip, int offset,
 			struct disasm_line *dl)
 {
@@ -3800,12 +2304,12 @@ u64 annotate_calc_pcrel(struct map_symbol *ms, u64 ip, int offset,
 	 * disasm_line.  If it's the last one, we can use symbol's end
 	 * address directly.
 	 */
-	if (&dl->al.node == notes->src->source.prev)
+	next = annotation__next_asm_line(notes, dl);
+	if (next == NULL)
 		addr = ms->sym->end + offset;
-	else {
-		next = list_next_entry(dl, al.node);
+	else
 		addr = ip + (next->al.offset - dl->al.offset) + offset;
-	}
+
 	return map__rip_2objdump(ms->map, addr);
 }
 
@@ -3828,9 +2332,7 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 	struct annotated_op_loc *op_loc;
 	struct annotated_data_type *mem_type;
 	struct annotated_item_stat *istat;
-	u64 ip = he->ip, addr = 0;
-	const char *var_name = NULL;
-	int var_offset;
+	u64 ip = he->ip;
 	int i;
 
 	ann_data_stat.total++;
@@ -3845,19 +2347,17 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 		return NULL;
 	}
 
-	if (evsel__get_arch(evsel, &arch) < 0) {
+	/* Make sure it has the disasm of the function */
+	if (symbol__annotate(ms, evsel, &arch) < 0) {
 		ann_data_stat.no_insn++;
 		return NULL;
 	}
 
-	/* Make sure it runs objdump to get disasm of the function */
-	symbol__ensure_annotate(ms, evsel);
-
 	/*
 	 * Get a disasm to extract the location from the insn.
 	 * This is too slow...
 	 */
-	dl = find_disasm_line(ms->sym, ip);
+	dl = find_disasm_line(ms->sym, ip, /*allow_update=*/true);
 	if (dl == NULL) {
 		ann_data_stat.no_insn++;
 		return NULL;
@@ -3883,51 +2383,55 @@ retry:
 	}
 
 	for_each_insn_op_loc(&loc, i, op_loc) {
-		if (!op_loc->mem_ref)
+		struct data_loc_info dloc = {
+			.arch = arch,
+			.thread = he->thread,
+			.ms = ms,
+			/* Recalculate IP for LOCK prefix or insn fusion */
+			.ip = ms->sym->start + dl->al.offset,
+			.cpumode = he->cpumode,
+			.op = op_loc,
+		};
+
+		if (!op_loc->mem_ref && op_loc->segment == INSN_SEG_NONE)
 			continue;
 
 		/* Recalculate IP because of LOCK prefix or insn fusion */
 		ip = ms->sym->start + dl->al.offset;
 
-		var_offset = op_loc->offset;
-
 		/* PC-relative addressing */
 		if (op_loc->reg1 == DWARF_REG_PC) {
-			struct addr_location al;
-			struct symbol *var;
-			u64 map_addr;
-
-			addr = annotate_calc_pcrel(ms, ip, op_loc->offset, dl);
-			/* Kernel symbols might be relocated */
-			map_addr = addr + map__reloc(ms->map);
-
-			addr_location__init(&al);
-			var = thread__find_symbol_fb(he->thread, he->cpumode,
-						     map_addr, &al);
-			if (var) {
-				var_name = var->name;
-				/* Calculate type offset from the start of variable */
-				var_offset = map_addr - map__unmap_ip(al.map, var->start);
-			}
-			addr_location__exit(&al);
+			dloc.var_addr = annotate_calc_pcrel(ms, dloc.ip,
+							    op_loc->offset, dl);
+		}
+
+		/* This CPU access in kernel - pretend PC-relative addressing */
+		if (dso__kernel(map__dso(ms->map)) && arch__is(arch, "x86") &&
+		    op_loc->segment == INSN_SEG_X86_GS && op_loc->imm) {
+			dloc.var_addr = op_loc->offset;
+			op_loc->reg1 = DWARF_REG_PC;
+		}
+
+		mem_type = find_data_type(&dloc);
+
+		if (mem_type == NULL && is_stack_canary(arch, op_loc)) {
+			istat->good++;
+			he->mem_type_off = 0;
+			return &canary_type;
 		}
 
-		mem_type = find_data_type(ms, ip, op_loc, addr, var_name);
 		if (mem_type)
 			istat->good++;
 		else
 			istat->bad++;
 
-		if (mem_type && var_name)
-			op_loc->offset = var_offset;
-
 		if (symbol_conf.annotate_data_sample) {
 			annotated_data_type__update_samples(mem_type, evsel,
-							    op_loc->offset,
+							    dloc.type_offset,
 							    he->stat.nr_events,
 							    he->stat.period);
 		}
-		he->mem_type_off = op_loc->offset;
+		he->mem_type_off = dloc.type_offset;
 		return mem_type;
 	}
 
@@ -3936,10 +2440,13 @@ retry:
 	 * from the previous instruction.
 	 */
 	if (dl->al.offset > 0) {
+		struct annotation *notes;
 		struct disasm_line *prev_dl;
 
-		prev_dl = list_prev_entry(dl, al.node);
-		if (ins__is_fused(arch, prev_dl->ins.name, dl->ins.name)) {
+		notes = symbol__annotation(ms->sym);
+		prev_dl = annotation__prev_asm_line(notes, dl);
+
+		if (prev_dl && ins__is_fused(arch, prev_dl->ins.name, dl->ins.name)) {
 			dl = prev_dl;
 			goto retry;
 		}
@@ -3949,3 +2456,227 @@ retry:
 	istat->bad++;
 	return NULL;
 }
+
+/* Basic block traversal (BFS) data structure */
+struct basic_block_data {
+	struct list_head queue;
+	struct list_head visited;
+};
+
+/*
+ * During the traversal, it needs to know the parent block where the current
+ * block block started from.  Note that single basic block can be parent of
+ * two child basic blocks (in case of condition jump).
+ */
+struct basic_block_link {
+	struct list_head node;
+	struct basic_block_link *parent;
+	struct annotated_basic_block *bb;
+};
+
+/* Check any of basic block in the list already has the offset */
+static bool basic_block_has_offset(struct list_head *head, s64 offset)
+{
+	struct basic_block_link *link;
+
+	list_for_each_entry(link, head, node) {
+		s64 begin_offset = link->bb->begin->al.offset;
+		s64 end_offset = link->bb->end->al.offset;
+
+		if (begin_offset <= offset && offset <= end_offset)
+			return true;
+	}
+	return false;
+}
+
+static bool is_new_basic_block(struct basic_block_data *bb_data,
+			       struct disasm_line *dl)
+{
+	s64 offset = dl->al.offset;
+
+	if (basic_block_has_offset(&bb_data->visited, offset))
+		return false;
+	if (basic_block_has_offset(&bb_data->queue, offset))
+		return false;
+	return true;
+}
+
+/* Add a basic block starting from dl and link it to the parent */
+static int add_basic_block(struct basic_block_data *bb_data,
+			   struct basic_block_link *parent,
+			   struct disasm_line *dl)
+{
+	struct annotated_basic_block *bb;
+	struct basic_block_link *link;
+
+	if (dl == NULL)
+		return -1;
+
+	if (!is_new_basic_block(bb_data, dl))
+		return 0;
+
+	bb = zalloc(sizeof(*bb));
+	if (bb == NULL)
+		return -1;
+
+	bb->begin = dl;
+	bb->end = dl;
+	INIT_LIST_HEAD(&bb->list);
+
+	link = malloc(sizeof(*link));
+	if (link == NULL) {
+		free(bb);
+		return -1;
+	}
+
+	link->bb = bb;
+	link->parent = parent;
+	list_add_tail(&link->node, &bb_data->queue);
+	return 0;
+}
+
+/* Returns true when it finds the target in the current basic block */
+static bool process_basic_block(struct basic_block_data *bb_data,
+				struct basic_block_link *link,
+				struct symbol *sym, u64 target)
+{
+	struct disasm_line *dl, *next_dl, *last_dl;
+	struct annotation *notes = symbol__annotation(sym);
+	bool found = false;
+
+	dl = link->bb->begin;
+	/* Check if it's already visited */
+	if (basic_block_has_offset(&bb_data->visited, dl->al.offset))
+		return false;
+
+	last_dl = list_last_entry(&notes->src->source,
+				  struct disasm_line, al.node);
+	if (last_dl->al.offset == -1)
+		last_dl = annotation__prev_asm_line(notes, last_dl);
+
+	if (last_dl == NULL)
+		return false;
+
+	list_for_each_entry_from(dl, &notes->src->source, al.node) {
+		/* Skip comment or debug info line */
+		if (dl->al.offset == -1)
+			continue;
+		/* Found the target instruction */
+		if (sym->start + dl->al.offset == target) {
+			found = true;
+			break;
+		}
+		/* End of the function, finish the block */
+		if (dl == last_dl)
+			break;
+		/* 'return' instruction finishes the block */
+		if (ins__is_ret(&dl->ins))
+			break;
+		/* normal instructions are part of the basic block */
+		if (!ins__is_jump(&dl->ins))
+			continue;
+		/* jump to a different function, tail call or return */
+		if (dl->ops.target.outside)
+			break;
+		/* jump instruction creates new basic block(s) */
+		next_dl = find_disasm_line(sym, sym->start + dl->ops.target.offset,
+					   /*allow_update=*/false);
+		if (next_dl)
+			add_basic_block(bb_data, link, next_dl);
+
+		/*
+		 * FIXME: determine conditional jumps properly.
+		 * Conditional jumps create another basic block with the
+		 * next disasm line.
+		 */
+		if (!strstr(dl->ins.name, "jmp")) {
+			next_dl = annotation__next_asm_line(notes, dl);
+			if (next_dl)
+				add_basic_block(bb_data, link, next_dl);
+		}
+		break;
+
+	}
+	link->bb->end = dl;
+	return found;
+}
+
+/*
+ * It founds a target basic block, build a proper linked list of basic blocks
+ * by following the link recursively.
+ */
+static void link_found_basic_blocks(struct basic_block_link *link,
+				    struct list_head *head)
+{
+	while (link) {
+		struct basic_block_link *parent = link->parent;
+
+		list_move(&link->bb->list, head);
+		list_del(&link->node);
+		free(link);
+
+		link = parent;
+	}
+}
+
+static void delete_basic_blocks(struct basic_block_data *bb_data)
+{
+	struct basic_block_link *link, *tmp;
+
+	list_for_each_entry_safe(link, tmp, &bb_data->queue, node) {
+		list_del(&link->node);
+		zfree(&link->bb);
+		free(link);
+	}
+
+	list_for_each_entry_safe(link, tmp, &bb_data->visited, node) {
+		list_del(&link->node);
+		zfree(&link->bb);
+		free(link);
+	}
+}
+
+/**
+ * annotate_get_basic_blocks - Get basic blocks for given address range
+ * @sym: symbol to annotate
+ * @src: source address
+ * @dst: destination address
+ * @head: list head to save basic blocks
+ *
+ * This function traverses disasm_lines from @src to @dst and save them in a
+ * list of annotated_basic_block to @head.  It uses BFS to find the shortest
+ * path between two.  The basic_block_link is to maintain parent links so
+ * that it can build a list of blocks from the start.
+ */
+int annotate_get_basic_blocks(struct symbol *sym, s64 src, s64 dst,
+			      struct list_head *head)
+{
+	struct basic_block_data bb_data = {
+		.queue = LIST_HEAD_INIT(bb_data.queue),
+		.visited = LIST_HEAD_INIT(bb_data.visited),
+	};
+	struct basic_block_link *link;
+	struct disasm_line *dl;
+	int ret = -1;
+
+	dl = find_disasm_line(sym, src, /*allow_update=*/false);
+	if (dl == NULL)
+		return -1;
+
+	if (add_basic_block(&bb_data, /*parent=*/NULL, dl) < 0)
+		return -1;
+
+	/* Find shortest path from src to dst using BFS */
+	while (!list_empty(&bb_data.queue)) {
+		link = list_first_entry(&bb_data.queue, struct basic_block_link, node);
+
+		if (process_basic_block(&bb_data, link, sym, dst)) {
+			link_found_basic_blocks(link, head);
+			ret = 0;
+			break;
+		}
+		list_move(&link->node, &bb_data.visited);
+	}
+	delete_basic_blocks(&bb_data);
+	return ret;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 13cc659e50..d5c821c22f 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -13,10 +13,10 @@
 #include "mutex.h"
 #include "spark.h"
 #include "hashmap.h"
+#include "disasm.h"
 
 struct hist_browser_timer;
 struct hist_entry;
-struct ins_ops;
 struct map;
 struct map_symbol;
 struct addr_map_symbol;
@@ -26,59 +26,6 @@ struct evsel;
 struct symbol;
 struct annotated_data_type;
 
-struct ins {
-	const char     *name;
-	struct ins_ops *ops;
-};
-
-struct ins_operands {
-	char	*raw;
-	struct {
-		char	*raw;
-		char	*name;
-		struct symbol *sym;
-		u64	addr;
-		s64	offset;
-		bool	offset_avail;
-		bool	outside;
-		bool	multi_regs;
-	} target;
-	union {
-		struct {
-			char	*raw;
-			char	*name;
-			u64	addr;
-			bool	multi_regs;
-		} source;
-		struct {
-			struct ins	    ins;
-			struct ins_operands *ops;
-		} locked;
-		struct {
-			char	*raw_comment;
-			char	*raw_func_start;
-		} jump;
-	};
-};
-
-struct arch;
-
-bool arch__is(struct arch *arch, const char *name);
-
-struct ins_ops {
-	void (*free)(struct ins_operands *ops);
-	int (*parse)(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms);
-	int (*scnprintf)(struct ins *ins, char *bf, size_t size,
-			 struct ins_operands *ops, int max_ins_name);
-};
-
-bool ins__is_jump(const struct ins *ins);
-bool ins__is_call(const struct ins *ins);
-bool ins__is_ret(const struct ins *ins);
-bool ins__is_lock(const struct ins *ins);
-int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops, int max_ins_name);
-bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
-
 #define ANNOTATION__IPC_WIDTH 6
 #define ANNOTATION__CYCLES_WIDTH 6
 #define ANNOTATION__MINMAX_CYCLES_WIDTH 19
@@ -171,6 +118,8 @@ struct disasm_line {
 	struct annotation_line	 al;
 };
 
+void annotation_line__add(struct annotation_line *al, struct list_head *head);
+
 static inline double annotation_data__percent(struct annotation_data *data,
 					      unsigned int which)
 {
@@ -212,7 +161,6 @@ static inline bool disasm_line__has_local_offset(const struct disasm_line *dl)
  */
 bool disasm_line__is_valid_local_jump(struct disasm_line *dl, struct symbol *sym);
 
-void disasm_line__free(struct disasm_line *dl);
 struct annotation_line *
 annotation_line__next(struct annotation_line *pos, struct list_head *head);
 
@@ -235,7 +183,6 @@ int __annotation__scnprintf_samples_period(struct annotation *notes,
 					   struct evsel *evsel,
 					   bool show_freq);
 
-int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
 void symbol__calc_percent(struct symbol *sym, struct evsel *evsel);
 
@@ -299,12 +246,14 @@ struct cyc_hist {
  * 		  we have more than a group in a evlist, where we will want
  * 		  to see each group separately, that is why symbol__annotate2()
  * 		  sets src->nr_histograms to evsel->nr_members.
- * @offsets: Array of annotation_line to be accessed by offset.
  * @samples: Hash map of sym_hist_entry.  Keyed by event index and offset in symbol.
+ * @nr_events: Number of events in the current output.
  * @nr_entries: Number of annotated_line in the source list.
  * @nr_asm_entries: Number of annotated_line with actual asm instruction in the
  * 		    source list.
- * @max_line_len: Maximum length of objdump output in an annotated_line.
+ * @max_jump_sources: Maximum number of jump instructions targeting to the same
+ * 		      instruction.
+ * @widths: Precalculated width of each column in the TUI output.
  *
  * disasm_lines are allocated, percentages calculated and all sorted by percentage
  * when the annotation is about to be presented, so the percentages are for
@@ -315,14 +264,27 @@ struct cyc_hist {
 struct annotated_source {
 	struct list_head	source;
 	struct sym_hist		*histograms;
-	struct annotation_line	**offsets;
 	struct hashmap	   	*samples;
 	int    			nr_histograms;
+	int    			nr_events;
 	int			nr_entries;
 	int			nr_asm_entries;
-	u16			max_line_len;
+	int			max_jump_sources;
+	u64			start;
+	struct {
+		u8		addr;
+		u8		jumps;
+		u8		target;
+		u8		min_addr;
+		u8		max_addr;
+		u8		max_ins_name;
+		u16		max_line_len;
+	} widths;
 };
 
+struct annotation_line *annotated_source__get_line(struct annotated_source *src,
+						   s64 offset);
+
 /**
  * struct annotated_branch - basic block and IPC information for a symbol.
  *
@@ -351,17 +313,6 @@ struct annotated_branch {
 };
 
 struct LOCKABLE annotation {
-	u64			start;
-	int			nr_events;
-	int			max_jump_sources;
-	struct {
-		u8		addr;
-		u8		jumps;
-		u8		target;
-		u8		min_addr;
-		u8		max_addr;
-		u8		max_ins_name;
-	} widths;
 	struct annotated_source *src;
 	struct annotated_branch *branch;
 };
@@ -385,7 +336,7 @@ static inline int annotation__cycles_width(struct annotation *notes)
 
 static inline int annotation__pcnt_width(struct annotation *notes)
 {
-	return (symbol_conf.show_total_period ? 12 : 7) * notes->nr_events;
+	return (symbol_conf.show_total_period ? 12 : 7) * notes->src->nr_events;
 }
 
 static inline bool annotation_line__filter(struct annotation_line *al)
@@ -393,10 +344,7 @@ static inline bool annotation_line__filter(struct annotation_line *al)
 	return annotate_opts.hide_src_code && al->offset == -1;
 }
 
-void annotation__set_offsets(struct annotation *notes, s64 size);
-void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym);
 void annotation__update_column_widths(struct annotation *notes);
-void annotation__init_column_widths(struct annotation *notes, struct symbol *sym);
 void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *ms);
 
 static inline struct sym_hist *annotated_source__histogram(struct annotated_source *src, int idx)
@@ -511,15 +459,19 @@ int annotate_check_args(void);
  * @reg1: First register in the operand
  * @reg2: Second register in the operand
  * @offset: Memory access offset in the operand
+ * @segment: Segment selector register
  * @mem_ref: Whether the operand accesses memory
  * @multi_regs: Whether the second register is used
+ * @imm: Whether the operand is an immediate value (in offset)
  */
 struct annotated_op_loc {
 	int reg1;
 	int reg2;
 	int offset;
+	u8 segment;
 	bool mem_ref;
 	bool multi_regs;
+	bool imm;
 };
 
 enum annotated_insn_ops {
@@ -529,6 +481,17 @@ enum annotated_insn_ops {
 	INSN_OP_MAX,
 };
 
+enum annotated_x86_segment {
+	INSN_SEG_NONE = 0,
+
+	INSN_SEG_X86_CS,
+	INSN_SEG_X86_DS,
+	INSN_SEG_X86_ES,
+	INSN_SEG_X86_FS,
+	INSN_SEG_X86_GS,
+	INSN_SEG_X86_SS,
+};
+
 /**
  * struct annotated_insn_loc - Location info of instruction
  * @ops: Array of location info for source and target operands
@@ -561,4 +524,20 @@ extern struct list_head ann_insn_stat;
 u64 annotate_calc_pcrel(struct map_symbol *ms, u64 ip, int offset,
 			struct disasm_line *dl);
 
+/**
+ * struct annotated_basic_block - Basic block of instructions
+ * @list: List node
+ * @begin: start instruction in the block
+ * @end: end instruction in the block
+ */
+struct annotated_basic_block {
+	struct list_head list;
+	struct disasm_line *begin;
+	struct disasm_line *end;
+};
+
+/* Get a list of basic blocks from src to dst addresses */
+int annotate_get_basic_blocks(struct symbol *sym, s64 src, s64 dst,
+			      struct list_head *head);
+
 #endif	/* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index ef314a5797..e2f317063e 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -174,7 +174,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 				   struct evlist *evlist,
 				   struct evsel *evsel, int idx)
 {
-	bool per_cpu = !perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus);
+	bool per_cpu = !perf_cpu_map__has_any_cpu(evlist->core.user_requested_cpus);
 
 	mp->mmap_needed = evsel->needs_auxtrace_mmap;
 
@@ -218,15 +218,20 @@ static struct auxtrace_queue *auxtrace_alloc_queue_array(unsigned int nr_queues)
 	return queue_array;
 }
 
-int auxtrace_queues__init(struct auxtrace_queues *queues)
+int auxtrace_queues__init_nr(struct auxtrace_queues *queues, int nr_queues)
 {
-	queues->nr_queues = AUXTRACE_INIT_NR_QUEUES;
+	queues->nr_queues = nr_queues;
 	queues->queue_array = auxtrace_alloc_queue_array(queues->nr_queues);
 	if (!queues->queue_array)
 		return -ENOMEM;
 	return 0;
 }
 
+int auxtrace_queues__init(struct auxtrace_queues *queues)
+{
+	return auxtrace_queues__init_nr(queues, AUXTRACE_INIT_NR_QUEUES);
+}
+
 static int auxtrace_queues__grow(struct auxtrace_queues *queues,
 				 unsigned int new_nr_queues)
 {
@@ -648,7 +653,7 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 
 static int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx)
 {
-	bool per_cpu_mmaps = !perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus);
+	bool per_cpu_mmaps = !perf_cpu_map__has_any_cpu(evlist->core.user_requested_cpus);
 
 	if (per_cpu_mmaps) {
 		struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->core.all_cpus, idx);
@@ -2654,7 +2659,7 @@ static int addr_filter__entire_dso(struct addr_filter *filt, struct dso *dso)
 	}
 
 	filt->addr = 0;
-	filt->size = dso->data.file_size;
+	filt->size = dso__data(dso)->file_size;
 
 	return 0;
 }
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 55702215a8..8a6ec95658 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -521,6 +521,7 @@ int auxtrace_mmap__read_snapshot(struct mmap *map,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 size_t snapshot_size);
 
+int auxtrace_queues__init_nr(struct auxtrace_queues *queues, int nr_queues);
 int auxtrace_queues__init(struct auxtrace_queues *queues);
 int auxtrace_queues__add_event(struct auxtrace_queues *queues,
 			       struct perf_session *session,
diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c
index dec9109897..04068d4868 100644
--- a/tools/perf/util/block-info.c
+++ b/tools/perf/util/block-info.c
@@ -43,26 +43,14 @@ static struct block_header_column {
 	}
 };
 
-struct block_info *block_info__get(struct block_info *bi)
-{
-	if (bi)
-		refcount_inc(&bi->refcnt);
-	return bi;
-}
-
-void block_info__put(struct block_info *bi)
+struct block_info *block_info__new(void)
 {
-	if (bi && refcount_dec_and_test(&bi->refcnt))
-		free(bi);
+	return zalloc(sizeof(struct block_info));
 }
 
-struct block_info *block_info__new(void)
+void block_info__delete(struct block_info *bi)
 {
-	struct block_info *bi = zalloc(sizeof(*bi));
-
-	if (bi)
-		refcount_set(&bi->refcnt, 1);
-	return bi;
+	free(bi);
 }
 
 int64_t __block_info__cmp(struct hist_entry *left, struct hist_entry *right)
@@ -148,7 +136,7 @@ int block_info__process_sym(struct hist_entry *he, struct block_hist *bh,
 			he_block = hists__add_entry_block(&bh->block_hists,
 							  &al, bi);
 			if (!he_block) {
-				block_info__put(bi);
+				block_info__delete(bi);
 				return -1;
 			}
 		}
@@ -319,7 +307,7 @@ static int block_dso_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 
 	if (map && map__dso(map)) {
 		return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width,
-				 map__dso(map)->short_name);
+				 dso__short_name(map__dso(map)));
 	}
 
 	return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width,
diff --git a/tools/perf/util/block-info.h b/tools/perf/util/block-info.h
index 96f53e8979..0b9e1aad4c 100644
--- a/tools/perf/util/block-info.h
+++ b/tools/perf/util/block-info.h
@@ -3,7 +3,6 @@
 #define __PERF_BLOCK_H
 
 #include <linux/types.h>
-#include <linux/refcount.h>
 #include "hist.h"
 #include "symbol.h"
 #include "sort.h"
@@ -19,7 +18,6 @@ struct block_info {
 	u64			total_cycles;
 	int			num;
 	int			num_aggr;
-	refcount_t		refcnt;
 };
 
 struct block_fmt {
@@ -48,19 +46,8 @@ struct block_report {
 	int			nr_fmts;
 };
 
-struct block_hist;
-
 struct block_info *block_info__new(void);
-struct block_info *block_info__get(struct block_info *bi);
-void   block_info__put(struct block_info *bi);
-
-static inline void __block_info__zput(struct block_info **bi)
-{
-	block_info__put(*bi);
-	*bi = NULL;
-}
-
-#define block_info__zput(bi) __block_info__zput(&bi)
+void block_info__delete(struct block_info *bi);
 
 int64_t __block_info__cmp(struct hist_entry *left, struct hist_entry *right);
 
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 83709146a4..827695cd04 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -59,10 +59,10 @@ static int machine__process_bpf_event_load(struct machine *machine,
 		if (map) {
 			struct dso *dso = map__dso(map);
 
-			dso->binary_type = DSO_BINARY_TYPE__BPF_PROG_INFO;
-			dso->bpf_prog.id = id;
-			dso->bpf_prog.sub_id = i;
-			dso->bpf_prog.env = env;
+			dso__set_binary_type(dso, DSO_BINARY_TYPE__BPF_PROG_INFO);
+			dso__bpf_prog(dso)->id = id;
+			dso__bpf_prog(dso)->sub_id = i;
+			dso__bpf_prog(dso)->env = env;
 			map__put(map);
 		}
 	}
diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c
index 1c82377ed7..ea29c372f3 100644
--- a/tools/perf/util/bpf_counter_cgroup.c
+++ b/tools/perf/util/bpf_counter_cgroup.c
@@ -136,9 +136,8 @@ static int bperf_load_program(struct evlist *evlist)
 		cgrp = evsel->cgrp;
 
 		if (read_cgroup_id(cgrp) < 0) {
-			pr_err("Failed to get cgroup id\n");
-			err = -1;
-			goto out;
+			pr_debug("Failed to get cgroup id for %s\n", cgrp->name);
+			cgrp->id = 0;
 		}
 
 		map_fd = bpf_map__fd(skel->maps.cgrp_idx);
diff --git a/tools/perf/util/bpf_kwork.c b/tools/perf/util/bpf_kwork.c
index 6eb2c78fd7..44f0f708a1 100644
--- a/tools/perf/util/bpf_kwork.c
+++ b/tools/perf/util/bpf_kwork.c
@@ -147,12 +147,12 @@ static bool valid_kwork_class_type(enum kwork_class_type type)
 
 static int setup_filters(struct perf_kwork *kwork)
 {
-	u8 val = 1;
-	int i, nr_cpus, key, fd;
-	struct perf_cpu_map *map;
-
 	if (kwork->cpu_list != NULL) {
-		fd = bpf_map__fd(skel->maps.perf_kwork_cpu_filter);
+		int idx, nr_cpus;
+		struct perf_cpu_map *map;
+		struct perf_cpu cpu;
+		int fd = bpf_map__fd(skel->maps.perf_kwork_cpu_filter);
+
 		if (fd < 0) {
 			pr_debug("Invalid cpu filter fd\n");
 			return -1;
@@ -165,8 +165,8 @@ static int setup_filters(struct perf_kwork *kwork)
 		}
 
 		nr_cpus = libbpf_num_possible_cpus();
-		for (i = 0; i < perf_cpu_map__nr(map); i++) {
-			struct perf_cpu cpu = perf_cpu_map__cpu(map, i);
+		perf_cpu_map__for_each_cpu(cpu, idx, map) {
+			u8 val = 1;
 
 			if (cpu.cpu >= nr_cpus) {
 				perf_cpu_map__put(map);
@@ -181,6 +181,8 @@ static int setup_filters(struct perf_kwork *kwork)
 	}
 
 	if (kwork->profile_name != NULL) {
+		int key, fd;
+
 		if (strlen(kwork->profile_name) >= MAX_KWORKNAME) {
 			pr_err("Requested name filter %s too large, limit to %d\n",
 			       kwork->profile_name, MAX_KWORKNAME - 1);
diff --git a/tools/perf/util/bpf_kwork_top.c b/tools/perf/util/bpf_kwork_top.c
index 035e022727..22a3b00a1e 100644
--- a/tools/perf/util/bpf_kwork_top.c
+++ b/tools/perf/util/bpf_kwork_top.c
@@ -122,11 +122,11 @@ static bool valid_kwork_class_type(enum kwork_class_type type)
 
 static int setup_filters(struct perf_kwork *kwork)
 {
-	u8 val = 1;
-	int i, nr_cpus, fd;
-	struct perf_cpu_map *map;
-
 	if (kwork->cpu_list) {
+		int idx, nr_cpus, fd;
+		struct perf_cpu_map *map;
+		struct perf_cpu cpu;
+
 		fd = bpf_map__fd(skel->maps.kwork_top_cpu_filter);
 		if (fd < 0) {
 			pr_debug("Invalid cpu filter fd\n");
@@ -140,8 +140,8 @@ static int setup_filters(struct perf_kwork *kwork)
 		}
 
 		nr_cpus = libbpf_num_possible_cpus();
-		for (i = 0; i < perf_cpu_map__nr(map); i++) {
-			struct perf_cpu cpu = perf_cpu_map__cpu(map, i);
+		perf_cpu_map__for_each_cpu(cpu, idx, map) {
+			u8 val = 1;
 
 			if (cpu.cpu >= nr_cpus) {
 				perf_cpu_map__put(map);
diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
index 2872f9bc07..0acbd74e8c 100644
--- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
+++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
@@ -341,6 +341,27 @@ failure:
 	return 1; /* Failure: don't filter */
 }
 
+SEC("tp/syscalls/sys_enter_nanosleep")
+int sys_enter_nanosleep(struct syscall_enter_args *args)
+{
+	struct augmented_args_payload *augmented_args = augmented_args_payload();
+	const void *req_arg = (const void *)args->args[0];
+	unsigned int len = sizeof(augmented_args->args);
+	__u32 size = sizeof(struct timespec64);
+
+        if (augmented_args == NULL)
+		goto failure;
+
+	if (size > sizeof(augmented_args->__data))
+                goto failure;
+
+	bpf_probe_read_user(&augmented_args->__data, size, req_arg);
+
+	return augmented__output(args, augmented_args, len + size);
+failure:
+	return 1; /* Failure: don't filter */
+}
+
 static pid_t getpid(void)
 {
 	return bpf_get_current_pid_tgid();
diff --git a/tools/perf/util/bpf_skel/bench_uprobe.bpf.c b/tools/perf/util/bpf_skel/bench_uprobe.bpf.c
index 2c55896bb3..a01c7f791f 100644
--- a/tools/perf/util/bpf_skel/bench_uprobe.bpf.c
+++ b/tools/perf/util/bpf_skel/bench_uprobe.bpf.c
@@ -4,6 +4,7 @@
 #include <bpf/bpf_tracing.h>
 
 unsigned int nr_uprobes;
+unsigned int nr_uretprobes;
 
 SEC("uprobe")
 int BPF_UPROBE(empty)
@@ -20,4 +21,19 @@ int BPF_UPROBE(trace_printk)
 	return 0;
 }
 
+SEC("uretprobe")
+int BPF_URETPROBE(empty_ret)
+{
+	return 0;
+}
+
+SEC("uretprobe")
+int BPF_URETPROBE(trace_printk_ret)
+{
+	char fmt[] = "perf bench uretprobe %u";
+
+	bpf_trace_printk(fmt, sizeof(fmt), ++nr_uretprobes);
+	return 0;
+}
+
 char LICENSE[] SEC("license") = "Dual BSD/GPL";
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 03c64b8538..83a1581e8c 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -60,7 +60,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 
 	addr_location__init(&al);
 	if (thread__find_map(thread, sample->cpumode, sample->ip, &al))
-		map__dso(al.map)->hit = 1;
+		dso__set_hit(map__dso(al.map));
 
 	addr_location__exit(&al);
 	thread__put(thread);
@@ -272,10 +272,10 @@ char *__dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
 	bool alloc = (bf == NULL);
 	int ret;
 
-	if (!dso->has_build_id)
+	if (!dso__has_build_id(dso))
 		return NULL;
 
-	build_id__sprintf(&dso->bid, sbuild_id);
+	build_id__sprintf(dso__bid_const(dso), sbuild_id);
 	linkname = build_id_cache__linkname(sbuild_id, NULL, 0);
 	if (!linkname)
 		return NULL;
@@ -327,48 +327,56 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid
 	return write_padded(fd, name, name_len + 1, len);
 }
 
-static int machine__write_buildid_table(struct machine *machine,
-					struct feat_fd *fd)
+struct machine__write_buildid_table_cb_args {
+	struct machine *machine;
+	struct feat_fd *fd;
+	u16 kmisc, umisc;
+};
+
+static int machine__write_buildid_table_cb(struct dso *dso, void *data)
 {
-	int err = 0;
-	struct dso *pos;
-	u16 kmisc = PERF_RECORD_MISC_KERNEL,
-	    umisc = PERF_RECORD_MISC_USER;
+	struct machine__write_buildid_table_cb_args *args = data;
+	const char *name;
+	size_t name_len;
+	bool in_kernel = false;
 
-	if (!machine__is_host(machine)) {
-		kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
-		umisc = PERF_RECORD_MISC_GUEST_USER;
-	}
+	if (!dso__has_build_id(dso))
+		return 0;
 
-	dsos__for_each_with_build_id(pos, &machine->dsos.head) {
-		const char *name;
-		size_t name_len;
-		bool in_kernel = false;
+	if (!dso__hit(dso) && !dso__is_vdso(dso))
+		return 0;
 
-		if (!pos->hit && !dso__is_vdso(pos))
-			continue;
+	if (dso__is_vdso(dso)) {
+		name = dso__short_name(dso);
+		name_len = dso__short_name_len(dso);
+	} else if (dso__is_kcore(dso)) {
+		name = args->machine->mmap_name;
+		name_len = strlen(name);
+	} else {
+		name = dso__long_name(dso);
+		name_len = dso__long_name_len(dso);
+	}
 
-		if (dso__is_vdso(pos)) {
-			name = pos->short_name;
-			name_len = pos->short_name_len;
-		} else if (dso__is_kcore(pos)) {
-			name = machine->mmap_name;
-			name_len = strlen(name);
-		} else {
-			name = pos->long_name;
-			name_len = pos->long_name_len;
-		}
+	in_kernel = dso__kernel(dso) || is_kernel_module(name, PERF_RECORD_MISC_CPUMODE_UNKNOWN);
+	return write_buildid(name, name_len, dso__bid(dso), args->machine->pid,
+			     in_kernel ? args->kmisc : args->umisc, args->fd);
+}
 
-		in_kernel = pos->kernel ||
-				is_kernel_module(name,
-					PERF_RECORD_MISC_CPUMODE_UNKNOWN);
-		err = write_buildid(name, name_len, &pos->bid, machine->pid,
-				    in_kernel ? kmisc : umisc, fd);
-		if (err)
-			break;
+static int machine__write_buildid_table(struct machine *machine, struct feat_fd *fd)
+{
+	struct machine__write_buildid_table_cb_args args = {
+		.machine = machine,
+		.fd = fd,
+		.kmisc = PERF_RECORD_MISC_KERNEL,
+		.umisc = PERF_RECORD_MISC_USER,
+	};
+
+	if (!machine__is_host(machine)) {
+		args.kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
+		args.umisc = PERF_RECORD_MISC_GUEST_USER;
 	}
 
-	return err;
+	return dsos__for_each_dso(&machine->dsos, machine__write_buildid_table_cb, &args);
 }
 
 int perf_session__write_buildid_table(struct perf_session *session,
@@ -390,42 +398,6 @@ int perf_session__write_buildid_table(struct perf_session *session,
 	return err;
 }
 
-static int __dsos__hit_all(struct list_head *head)
-{
-	struct dso *pos;
-
-	list_for_each_entry(pos, head, node)
-		pos->hit = true;
-
-	return 0;
-}
-
-static int machine__hit_all_dsos(struct machine *machine)
-{
-	return __dsos__hit_all(&machine->dsos.head);
-}
-
-int dsos__hit_all(struct perf_session *session)
-{
-	struct rb_node *nd;
-	int err;
-
-	err = machine__hit_all_dsos(&session->machines.host);
-	if (err)
-		return err;
-
-	for (nd = rb_first_cached(&session->machines.guests); nd;
-	     nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-
-		err = machine__hit_all_dsos(pos);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
 void disable_buildid_cache(void)
 {
 	no_buildid_cache = true;
@@ -904,11 +876,11 @@ static bool dso__build_id_mismatch(struct dso *dso, const char *name)
 	struct build_id bid;
 	bool ret = false;
 
-	mutex_lock(&dso->lock);
-	if (filename__read_build_id_ns(name, &bid, dso->nsinfo) >= 0)
+	mutex_lock(dso__lock(dso));
+	if (filename__read_build_id_ns(name, &bid, dso__nsinfo(dso)) >= 0)
 		ret = !dso__build_id_equal(dso, &bid);
 
-	mutex_unlock(&dso->lock);
+	mutex_unlock(dso__lock(dso));
 
 	return ret;
 }
@@ -918,13 +890,13 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine,
 {
 	bool is_kallsyms = dso__is_kallsyms(dso);
 	bool is_vdso = dso__is_vdso(dso);
-	const char *name = dso->long_name;
+	const char *name = dso__long_name(dso);
 	const char *proper_name = NULL;
 	const char *root_dir = NULL;
 	char *allocated_name = NULL;
 	int ret = 0;
 
-	if (!dso->has_build_id)
+	if (!dso__has_build_id(dso))
 		return 0;
 
 	if (dso__is_kcore(dso)) {
@@ -949,10 +921,10 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine,
 	if (!is_kallsyms && dso__build_id_mismatch(dso, name))
 		goto out_free;
 
-	mutex_lock(&dso->lock);
-	ret = build_id_cache__add_b(&dso->bid, name, dso->nsinfo,
+	mutex_lock(dso__lock(dso));
+	ret = build_id_cache__add_b(dso__bid(dso), name, dso__nsinfo(dso),
 				    is_kallsyms, is_vdso, proper_name, root_dir);
-	mutex_unlock(&dso->lock);
+	mutex_unlock(dso__lock(dso));
 out_free:
 	free(allocated_name);
 	return ret;
@@ -992,7 +964,7 @@ int perf_session__cache_build_ids(struct perf_session *session)
 
 static bool machine__read_build_ids(struct machine *machine, bool with_hits)
 {
-	return __dsos__read_build_ids(&machine->dsos.head, with_hits);
+	return dsos__read_build_ids(&machine->dsos, with_hits);
 }
 
 bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 4e3a116937..3fa8bffb07 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -39,8 +39,6 @@ int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct evsel *evsel,
 			   struct machine *machine);
 
-int dsos__hit_all(struct perf_session *session);
-
 int perf_event__inject_buildid(struct perf_tool *tool, union perf_event *event,
 			       struct perf_sample *sample, struct evsel *evsel,
 			       struct machine *machine);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 7517d16c02..1730b852a9 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -606,7 +606,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 					call->brtype_stat = zalloc(sizeof(*call->brtype_stat));
 					if (!call->brtype_stat) {
 						perror("not enough memory for the code path branch statistics");
-						free(call->brtype_stat);
+						zfree(&call->brtype_stat);
 						return -ENOMEM;
 					}
 				}
@@ -1205,7 +1205,7 @@ char *callchain_list__sym_name(struct callchain_list *cl,
 	if (show_dso)
 		scnprintf(bf + printed, bfsize - printed, " %s",
 			  cl->ms.map ?
-			  map__dso(cl->ms.map)->short_name :
+			  dso__short_name(map__dso(cl->ms.map)) :
 			  "unknown");
 
 	return bf;
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index fcb5090584..0f759dd96d 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -465,9 +465,11 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str,
 		name = cn->name + prefix_len;
 		if (name[0] == '/' && name[1])
 			name++;
+
+		/* the cgroup can go away in the meantime */
 		cgrp = cgroup__new(name, open_cgroup);
 		if (cgrp == NULL)
-			goto out_err;
+			continue;
 
 		leader = NULL;
 		evlist__for_each_entry(orig_list, pos) {
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index afb8d4fd26..49b79cf0c5 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -1,108 +1,188 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "comm.h"
 #include <errno.h>
-#include <stdlib.h>
-#include <stdio.h>
 #include <string.h>
+#include <internal/rc_check.h>
 #include <linux/refcount.h>
-#include <linux/rbtree.h>
 #include <linux/zalloc.h>
 #include "rwsem.h"
 
-struct comm_str {
-	char *str;
-	struct rb_node rb_node;
+DECLARE_RC_STRUCT(comm_str) {
 	refcount_t refcnt;
+	char str[];
 };
 
-/* Should perhaps be moved to struct machine */
-static struct rb_root comm_str_root;
-static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,};
+static struct comm_strs {
+	struct rw_semaphore lock;
+	struct comm_str **strs;
+	int num_strs;
+	int capacity;
+} _comm_strs;
+
+static void comm_strs__remove_if_last(struct comm_str *cs);
+
+static void comm_strs__init(void)
+{
+	init_rwsem(&_comm_strs.lock);
+	_comm_strs.capacity = 16;
+	_comm_strs.num_strs = 0;
+	_comm_strs.strs = calloc(16, sizeof(*_comm_strs.strs));
+}
+
+static struct comm_strs *comm_strs__get(void)
+{
+	static pthread_once_t comm_strs_type_once = PTHREAD_ONCE_INIT;
+
+	pthread_once(&comm_strs_type_once, comm_strs__init);
+
+	return &_comm_strs;
+}
+
+static refcount_t *comm_str__refcnt(struct comm_str *cs)
+{
+	return &RC_CHK_ACCESS(cs)->refcnt;
+}
+
+static const char *comm_str__str(const struct comm_str *cs)
+{
+	return &RC_CHK_ACCESS(cs)->str[0];
+}
 
 static struct comm_str *comm_str__get(struct comm_str *cs)
 {
-	if (cs && refcount_inc_not_zero(&cs->refcnt))
-		return cs;
+	struct comm_str *result;
 
-	return NULL;
+	if (RC_CHK_GET(result, cs))
+		refcount_inc_not_zero(comm_str__refcnt(cs));
+
+	return result;
 }
 
 static void comm_str__put(struct comm_str *cs)
 {
-	if (cs && refcount_dec_and_test(&cs->refcnt)) {
-		down_write(&comm_str_lock);
-		rb_erase(&cs->rb_node, &comm_str_root);
-		up_write(&comm_str_lock);
-		zfree(&cs->str);
-		free(cs);
+	if (!cs)
+		return;
+
+	if (refcount_dec_and_test(comm_str__refcnt(cs))) {
+		RC_CHK_FREE(cs);
+	} else {
+		if (refcount_read(comm_str__refcnt(cs)) == 1)
+			comm_strs__remove_if_last(cs);
+
+		RC_CHK_PUT(cs);
 	}
 }
 
-static struct comm_str *comm_str__alloc(const char *str)
+static struct comm_str *comm_str__new(const char *str)
 {
-	struct comm_str *cs;
-
-	cs = zalloc(sizeof(*cs));
-	if (!cs)
-		return NULL;
+	struct comm_str *result = NULL;
+	RC_STRUCT(comm_str) *cs;
 
-	cs->str = strdup(str);
-	if (!cs->str) {
-		free(cs);
-		return NULL;
+	cs = malloc(sizeof(*cs) + strlen(str) + 1);
+	if (ADD_RC_CHK(result, cs)) {
+		refcount_set(comm_str__refcnt(result), 1);
+		strcpy(&cs->str[0], str);
 	}
+	return result;
+}
 
-	refcount_set(&cs->refcnt, 1);
+static int comm_str__search(const void *_key, const void *_member)
+{
+	const char *key = _key;
+	const struct comm_str *member = *(const struct comm_str * const *)_member;
 
-	return cs;
+	return strcmp(key, comm_str__str(member));
 }
 
-static
-struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root)
+static void comm_strs__remove_if_last(struct comm_str *cs)
 {
-	struct rb_node **p = &root->rb_node;
-	struct rb_node *parent = NULL;
-	struct comm_str *iter, *new;
-	int cmp;
-
-	while (*p != NULL) {
-		parent = *p;
-		iter = rb_entry(parent, struct comm_str, rb_node);
-
-		/*
-		 * If we race with comm_str__put, iter->refcnt is 0
-		 * and it will be removed within comm_str__put call
-		 * shortly, ignore it in this search.
-		 */
-		cmp = strcmp(str, iter->str);
-		if (!cmp && comm_str__get(iter))
-			return iter;
-
-		if (cmp < 0)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
+	struct comm_strs *comm_strs = comm_strs__get();
+
+	down_write(&comm_strs->lock);
+	/*
+	 * Are there only references from the array, if so remove the array
+	 * reference under the write lock so that we don't race with findnew.
+	 */
+	if (refcount_read(comm_str__refcnt(cs)) == 1) {
+		struct comm_str **entry;
+
+		entry = bsearch(comm_str__str(cs), comm_strs->strs, comm_strs->num_strs,
+				sizeof(struct comm_str *), comm_str__search);
+		comm_str__put(*entry);
+		for (int i = entry - comm_strs->strs; i < comm_strs->num_strs - 1; i++)
+			comm_strs->strs[i] = comm_strs->strs[i + 1];
+		comm_strs->num_strs--;
 	}
+	up_write(&comm_strs->lock);
+}
 
-	new = comm_str__alloc(str);
-	if (!new)
-		return NULL;
+static struct comm_str *__comm_strs__find(struct comm_strs *comm_strs, const char *str)
+{
+	struct comm_str **result;
 
-	rb_link_node(&new->rb_node, parent, p);
-	rb_insert_color(&new->rb_node, root);
+	result = bsearch(str, comm_strs->strs, comm_strs->num_strs, sizeof(struct comm_str *),
+			 comm_str__search);
 
-	return new;
+	if (!result)
+		return NULL;
+
+	return comm_str__get(*result);
 }
 
-static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
+static struct comm_str *comm_strs__findnew(const char *str)
 {
-	struct comm_str *cs;
+	struct comm_strs *comm_strs = comm_strs__get();
+	struct comm_str *result;
 
-	down_write(&comm_str_lock);
-	cs = __comm_str__findnew(str, root);
-	up_write(&comm_str_lock);
+	if (!comm_strs)
+		return NULL;
 
-	return cs;
+	down_read(&comm_strs->lock);
+	result = __comm_strs__find(comm_strs, str);
+	up_read(&comm_strs->lock);
+	if (result)
+		return result;
+
+	down_write(&comm_strs->lock);
+	result = __comm_strs__find(comm_strs, str);
+	if (!result) {
+		if (comm_strs->num_strs == comm_strs->capacity) {
+			struct comm_str **tmp;
+
+			tmp = reallocarray(comm_strs->strs,
+					   comm_strs->capacity + 16,
+					   sizeof(*comm_strs->strs));
+			if (!tmp) {
+				up_write(&comm_strs->lock);
+				return NULL;
+			}
+			comm_strs->strs = tmp;
+			comm_strs->capacity += 16;
+		}
+		result = comm_str__new(str);
+		if (result) {
+			int low = 0, high = comm_strs->num_strs - 1;
+			int insert = comm_strs->num_strs; /* Default to inserting at the end. */
+
+			while (low <= high) {
+				int mid = low + (high - low) / 2;
+				int cmp = strcmp(comm_str__str(comm_strs->strs[mid]), str);
+
+				if (cmp < 0) {
+					low = mid + 1;
+				} else {
+					high = mid - 1;
+					insert = mid;
+				}
+			}
+			memmove(&comm_strs->strs[insert + 1], &comm_strs->strs[insert],
+				(comm_strs->num_strs - insert) * sizeof(struct comm_str *));
+			comm_strs->num_strs++;
+			comm_strs->strs[insert] = result;
+		}
+	}
+	up_write(&comm_strs->lock);
+	return comm_str__get(result);
 }
 
 struct comm *comm__new(const char *str, u64 timestamp, bool exec)
@@ -115,7 +195,7 @@ struct comm *comm__new(const char *str, u64 timestamp, bool exec)
 	comm->start = timestamp;
 	comm->exec = exec;
 
-	comm->comm_str = comm_str__findnew(str, &comm_str_root);
+	comm->comm_str = comm_strs__findnew(str);
 	if (!comm->comm_str) {
 		free(comm);
 		return NULL;
@@ -128,7 +208,7 @@ int comm__override(struct comm *comm, const char *str, u64 timestamp, bool exec)
 {
 	struct comm_str *new, *old = comm->comm_str;
 
-	new = comm_str__findnew(str, &comm_str_root);
+	new = comm_strs__findnew(str);
 	if (!new)
 		return -ENOMEM;
 
@@ -149,5 +229,5 @@ void comm__free(struct comm *comm)
 
 const char *comm__str(const struct comm *comm)
 {
-	return comm->comm_str->str;
+	return comm_str__str(comm->comm_str);
 }
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 356e30c42c..27094211ed 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -180,8 +180,6 @@ struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr)
 		cpus->nr = nr;
 		for (i = 0; i < nr; i++)
 			cpus->map[i] = aggr_cpu_id__empty();
-
-		refcount_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -655,10 +653,10 @@ static char hex_char(unsigned char val)
 
 size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size)
 {
-	int i, cpu;
+	int idx;
 	char *ptr = buf;
 	unsigned char *bitmap;
-	struct perf_cpu last_cpu = perf_cpu_map__cpu(map, perf_cpu_map__nr(map) - 1);
+	struct perf_cpu c, last_cpu = perf_cpu_map__max(map);
 
 	if (buf == NULL)
 		return 0;
@@ -669,12 +667,10 @@ size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size)
 		return 0;
 	}
 
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		cpu = perf_cpu_map__cpu(map, i).cpu;
-		bitmap[cpu / 8] |= 1 << (cpu % 8);
-	}
+	perf_cpu_map__for_each_cpu(c, idx, map)
+		bitmap[c.cpu / 8] |= 1 << (c.cpu % 8);
 
-	for (cpu = last_cpu.cpu / 4 * 4; cpu >= 0; cpu -= 4) {
+	for (int cpu = last_cpu.cpu / 4 * 4; cpu >= 0; cpu -= 4) {
 		unsigned char bits = bitmap[cpu / 8];
 
 		if (cpu % 8)
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 26cf76c693..ee0f6139b0 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -5,7 +5,6 @@
 #include <stdbool.h>
 #include <stdio.h>
 #include <perf/cpumap.h>
-#include <linux/refcount.h>
 
 /** Identify where counts are aggregated, -1 implies not to aggregate. */
 struct aggr_cpu_id {
@@ -37,7 +36,6 @@ struct aggr_cpu_id {
 
 /** A collection of aggr_cpu_id values, the "built" version is sorted and uniqued. */
 struct cpu_aggr_map {
-	refcount_t refcnt;
 	/** Number of valid entries. */
 	int nr;
 	/** The entries. */
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index d65d748588..5e9fbcfad7 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -335,8 +335,11 @@ static int cs_etm__process_aux_output_hw_id(struct perf_session *session,
 	trace_chan_id = FIELD_GET(CS_AUX_HW_ID_TRACE_ID_MASK, hw_id);
 
 	/* check that we can handle this version */
-	if (version > CS_AUX_HW_ID_CURR_VERSION)
+	if (version > CS_AUX_HW_ID_CURR_VERSION) {
+		pr_err("CS ETM Trace: PERF_RECORD_AUX_OUTPUT_HW_ID version %d not supported. Please update Perf.\n",
+		       version);
 		return -EINVAL;
+	}
 
 	/* get access to the etm metadata */
 	etm = container_of(session->auxtrace, struct cs_etm_auxtrace, auxtrace);
@@ -1010,7 +1013,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id,
 	if (!dso)
 		goto out;
 
-	if (dso->data.status == DSO_DATA_STATUS_ERROR &&
+	if (dso__data(dso)->status == DSO_DATA_STATUS_ERROR &&
 	    dso__data_status_seen(dso, DSO_DATA_STATUS_SEEN_ITRACE))
 		goto out;
 
@@ -1024,11 +1027,11 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id,
 	if (len <= 0) {
 		ui__warning_once("CS ETM Trace: Missing DSO. Use 'perf archive' or debuginfod to export data from the traced system.\n"
 				 "              Enable CONFIG_PROC_KCORE or use option '-k /path/to/vmlinux' for kernel symbols.\n");
-		if (!dso->auxtrace_warned) {
+		if (!dso__auxtrace_warned(dso)) {
 			pr_err("CS ETM Trace: Debug data not found for address %#"PRIx64" in %s\n",
-				    address,
-				    dso->long_name ? dso->long_name : "Unknown");
-			dso->auxtrace_warned = true;
+				address,
+				dso__long_name(dso) ? dso__long_name(dso) : "Unknown");
+			dso__set_auxtrace_warned(dso);
 		}
 		goto out;
 	}
diff --git a/tools/perf/util/data-convert-json.c b/tools/perf/util/data-convert-json.c
index 09d57efd2d..3cf64f5b23 100644
--- a/tools/perf/util/data-convert-json.c
+++ b/tools/perf/util/data-convert-json.c
@@ -134,7 +134,7 @@ static void output_sample_callchain_entry(struct perf_tool *tool,
 		output_json_key_string(out, false, 5, "symbol", al->sym->name);
 
 		if (dso) {
-			const char *dso_name = dso->short_name;
+			const char *dso_name = dso__short_name(dso);
 
 			if (dso_name && strlen(dso_name) > 0) {
 				fputc(',', out);
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 106429155c..50f916374d 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -146,10 +146,10 @@ int db_export__comm_thread(struct db_export *dbe, struct comm *comm,
 int db_export__dso(struct db_export *dbe, struct dso *dso,
 		   struct machine *machine)
 {
-	if (dso->db_id)
+	if (dso__db_id(dso))
 		return 0;
 
-	dso->db_id = ++dbe->dso_last_db_id;
+	dso__set_db_id(dso, ++dbe->dso_last_db_id);
 
 	if (dbe->export_dso)
 		return dbe->export_dso(dbe, dso, machine);
@@ -184,7 +184,7 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
 		err = db_export__dso(dbe, dso, maps__machine(al->maps));
 		if (err)
 			return err;
-		*dso_db_id = dso->db_id;
+		*dso_db_id = dso__db_id(dso);
 
 		if (!al->sym) {
 			al->sym = symbol__new(al->addr, 0, 0, 0, "unknown");
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index c39ee0fcb8..d633d15329 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -41,6 +41,7 @@ static int redirect_to_stderr;
 int debug_data_convert;
 static FILE *_debug_file;
 bool debug_display_time;
+int debug_type_profile;
 
 FILE *debug_file(void)
 {
@@ -231,6 +232,7 @@ static struct sublevel_option debug_opts[] = {
 	{ .name = "data-convert",	.value_ptr = &debug_data_convert },
 	{ .name = "perf-event-open",	.value_ptr = &debug_peo_args },
 	{ .name = "kmaps",		.value_ptr = &debug_kmaps },
+	{ .name = "type-profile",	.value_ptr = &debug_type_profile },
 	{ .name = NULL, }
 };
 
@@ -270,6 +272,7 @@ int perf_quiet_option(void)
 	redirect_to_stderr = 0;
 	debug_peo_args = 0;
 	debug_kmaps = 0;
+	debug_type_profile = 0;
 
 	return 0;
 }
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 35a7a5ae76..a4026d1fd6 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -14,6 +14,7 @@ extern int debug_peo_args;
 extern bool quiet, dump_trace;
 extern int debug_ordered_events;
 extern int debug_data_convert;
+extern int debug_type_profile;
 
 #ifndef pr_fmt
 #define pr_fmt(fmt) fmt
diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
new file mode 100644
index 0000000000..e10558b795
--- /dev/null
+++ b/tools/perf/util/disasm.c
@@ -0,0 +1,1837 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <ctype.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <libgen.h>
+#include <regex.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <linux/string.h>
+#include <subcmd/run-command.h>
+
+#include "annotate.h"
+#include "build-id.h"
+#include "debug.h"
+#include "disasm.h"
+#include "dso.h"
+#include "env.h"
+#include "evsel.h"
+#include "map.h"
+#include "maps.h"
+#include "namespaces.h"
+#include "srcline.h"
+#include "symbol.h"
+#include "util.h"
+
+static regex_t	 file_lineno;
+
+/* These can be referred from the arch-dependent code */
+static struct ins_ops call_ops;
+static struct ins_ops dec_ops;
+static struct ins_ops jump_ops;
+static struct ins_ops mov_ops;
+static struct ins_ops nop_ops;
+static struct ins_ops lock_ops;
+static struct ins_ops ret_ops;
+
+static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops, int max_ins_name);
+static int call__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops, int max_ins_name);
+
+static void ins__sort(struct arch *arch);
+static int disasm_line__parse(char *line, const char **namep, char **rawp);
+
+static __attribute__((constructor)) void symbol__init_regexpr(void)
+{
+	regcomp(&file_lineno, "^/[^:]+:([0-9]+)", REG_EXTENDED);
+}
+
+static int arch__grow_instructions(struct arch *arch)
+{
+	struct ins *new_instructions;
+	size_t new_nr_allocated;
+
+	if (arch->nr_instructions_allocated == 0 && arch->instructions)
+		goto grow_from_non_allocated_table;
+
+	new_nr_allocated = arch->nr_instructions_allocated + 128;
+	new_instructions = realloc(arch->instructions, new_nr_allocated * sizeof(struct ins));
+	if (new_instructions == NULL)
+		return -1;
+
+out_update_instructions:
+	arch->instructions = new_instructions;
+	arch->nr_instructions_allocated = new_nr_allocated;
+	return 0;
+
+grow_from_non_allocated_table:
+	new_nr_allocated = arch->nr_instructions + 128;
+	new_instructions = calloc(new_nr_allocated, sizeof(struct ins));
+	if (new_instructions == NULL)
+		return -1;
+
+	memcpy(new_instructions, arch->instructions, arch->nr_instructions);
+	goto out_update_instructions;
+}
+
+static int arch__associate_ins_ops(struct arch* arch, const char *name, struct ins_ops *ops)
+{
+	struct ins *ins;
+
+	if (arch->nr_instructions == arch->nr_instructions_allocated &&
+	    arch__grow_instructions(arch))
+		return -1;
+
+	ins = &arch->instructions[arch->nr_instructions];
+	ins->name = strdup(name);
+	if (!ins->name)
+		return -1;
+
+	ins->ops  = ops;
+	arch->nr_instructions++;
+
+	ins__sort(arch);
+	return 0;
+}
+
+#include "arch/arc/annotate/instructions.c"
+#include "arch/arm/annotate/instructions.c"
+#include "arch/arm64/annotate/instructions.c"
+#include "arch/csky/annotate/instructions.c"
+#include "arch/loongarch/annotate/instructions.c"
+#include "arch/mips/annotate/instructions.c"
+#include "arch/x86/annotate/instructions.c"
+#include "arch/powerpc/annotate/instructions.c"
+#include "arch/riscv64/annotate/instructions.c"
+#include "arch/s390/annotate/instructions.c"
+#include "arch/sparc/annotate/instructions.c"
+
+static struct arch architectures[] = {
+	{
+		.name = "arc",
+		.init = arc__annotate_init,
+	},
+	{
+		.name = "arm",
+		.init = arm__annotate_init,
+	},
+	{
+		.name = "arm64",
+		.init = arm64__annotate_init,
+	},
+	{
+		.name = "csky",
+		.init = csky__annotate_init,
+	},
+	{
+		.name = "mips",
+		.init = mips__annotate_init,
+		.objdump = {
+			.comment_char = '#',
+		},
+	},
+	{
+		.name = "x86",
+		.init = x86__annotate_init,
+		.instructions = x86__instructions,
+		.nr_instructions = ARRAY_SIZE(x86__instructions),
+		.insn_suffix = "bwlq",
+		.objdump =  {
+			.comment_char = '#',
+			.register_char = '%',
+			.memory_ref_char = '(',
+			.imm_char = '$',
+		},
+	},
+	{
+		.name = "powerpc",
+		.init = powerpc__annotate_init,
+	},
+	{
+		.name = "riscv64",
+		.init = riscv64__annotate_init,
+	},
+	{
+		.name = "s390",
+		.init = s390__annotate_init,
+		.objdump =  {
+			.comment_char = '#',
+		},
+	},
+	{
+		.name = "sparc",
+		.init = sparc__annotate_init,
+		.objdump = {
+			.comment_char = '#',
+		},
+	},
+	{
+		.name = "loongarch",
+		.init = loongarch__annotate_init,
+		.objdump = {
+			.comment_char = '#',
+		},
+	},
+};
+
+static int arch__key_cmp(const void *name, const void *archp)
+{
+	const struct arch *arch = archp;
+
+	return strcmp(name, arch->name);
+}
+
+static int arch__cmp(const void *a, const void *b)
+{
+	const struct arch *aa = a;
+	const struct arch *ab = b;
+
+	return strcmp(aa->name, ab->name);
+}
+
+static void arch__sort(void)
+{
+	const int nmemb = ARRAY_SIZE(architectures);
+
+	qsort(architectures, nmemb, sizeof(struct arch), arch__cmp);
+}
+
+struct arch *arch__find(const char *name)
+{
+	const int nmemb = ARRAY_SIZE(architectures);
+	static bool sorted;
+
+	if (!sorted) {
+		arch__sort();
+		sorted = true;
+	}
+
+	return bsearch(name, architectures, nmemb, sizeof(struct arch), arch__key_cmp);
+}
+
+bool arch__is(struct arch *arch, const char *name)
+{
+	return !strcmp(arch->name, name);
+}
+
+static void ins_ops__delete(struct ins_operands *ops)
+{
+	if (ops == NULL)
+		return;
+	zfree(&ops->source.raw);
+	zfree(&ops->source.name);
+	zfree(&ops->target.raw);
+	zfree(&ops->target.name);
+}
+
+static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
+			      struct ins_operands *ops, int max_ins_name)
+{
+	return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->raw);
+}
+
+int ins__scnprintf(struct ins *ins, char *bf, size_t size,
+		   struct ins_operands *ops, int max_ins_name)
+{
+	if (ins->ops->scnprintf)
+		return ins->ops->scnprintf(ins, bf, size, ops, max_ins_name);
+
+	return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
+}
+
+bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2)
+{
+	if (!arch || !arch->ins_is_fused)
+		return false;
+
+	return arch->ins_is_fused(arch, ins1, ins2);
+}
+
+static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
+{
+	char *endptr, *tok, *name;
+	struct map *map = ms->map;
+	struct addr_map_symbol target = {
+		.ms = { .map = map, },
+	};
+
+	ops->target.addr = strtoull(ops->raw, &endptr, 16);
+
+	name = strchr(endptr, '<');
+	if (name == NULL)
+		goto indirect_call;
+
+	name++;
+
+	if (arch->objdump.skip_functions_char &&
+	    strchr(name, arch->objdump.skip_functions_char))
+		return -1;
+
+	tok = strchr(name, '>');
+	if (tok == NULL)
+		return -1;
+
+	*tok = '\0';
+	ops->target.name = strdup(name);
+	*tok = '>';
+
+	if (ops->target.name == NULL)
+		return -1;
+find_target:
+	target.addr = map__objdump_2mem(map, ops->target.addr);
+
+	if (maps__find_ams(ms->maps, &target) == 0 &&
+	    map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
+		ops->target.sym = target.ms.sym;
+
+	return 0;
+
+indirect_call:
+	tok = strchr(endptr, '*');
+	if (tok != NULL) {
+		endptr++;
+
+		/* Indirect call can use a non-rip register and offset: callq  *0x8(%rbx).
+		 * Do not parse such instruction.  */
+		if (strstr(endptr, "(%r") == NULL)
+			ops->target.addr = strtoull(endptr, NULL, 16);
+	}
+	goto find_target;
+}
+
+static int call__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops, int max_ins_name)
+{
+	if (ops->target.sym)
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
+
+	if (ops->target.addr == 0)
+		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
+
+	if (ops->target.name)
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.name);
+
+	return scnprintf(bf, size, "%-*s *%" PRIx64, max_ins_name, ins->name, ops->target.addr);
+}
+
+static struct ins_ops call_ops = {
+	.parse	   = call__parse,
+	.scnprintf = call__scnprintf,
+};
+
+bool ins__is_call(const struct ins *ins)
+{
+	return ins->ops == &call_ops || ins->ops == &s390_call_ops || ins->ops == &loongarch_call_ops;
+}
+
+/*
+ * Prevents from matching commas in the comment section, e.g.:
+ * ffff200008446e70:       b.cs    ffff2000084470f4 <generic_exec_single+0x314>  // b.hs, b.nlast
+ *
+ * and skip comma as part of function arguments, e.g.:
+ * 1d8b4ac <linemap_lookup(line_maps const*, unsigned int)+0xcc>
+ */
+static inline const char *validate_comma(const char *c, struct ins_operands *ops)
+{
+	if (ops->jump.raw_comment && c > ops->jump.raw_comment)
+		return NULL;
+
+	if (ops->jump.raw_func_start && c > ops->jump.raw_func_start)
+		return NULL;
+
+	return c;
+}
+
+static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
+{
+	struct map *map = ms->map;
+	struct symbol *sym = ms->sym;
+	struct addr_map_symbol target = {
+		.ms = { .map = map, },
+	};
+	const char *c = strchr(ops->raw, ',');
+	u64 start, end;
+
+	ops->jump.raw_comment = strchr(ops->raw, arch->objdump.comment_char);
+	ops->jump.raw_func_start = strchr(ops->raw, '<');
+
+	c = validate_comma(c, ops);
+
+	/*
+	 * Examples of lines to parse for the _cpp_lex_token@@Base
+	 * function:
+	 *
+	 * 1159e6c: jne    115aa32 <_cpp_lex_token@@Base+0xf92>
+	 * 1159e8b: jne    c469be <cpp_named_operator2name@@Base+0xa72>
+	 *
+	 * The first is a jump to an offset inside the same function,
+	 * the second is to another function, i.e. that 0xa72 is an
+	 * offset in the cpp_named_operator2name@@base function.
+	 */
+	/*
+	 * skip over possible up to 2 operands to get to address, e.g.:
+	 * tbnz	 w0, #26, ffff0000083cd190 <security_file_permission+0xd0>
+	 */
+	if (c++ != NULL) {
+		ops->target.addr = strtoull(c, NULL, 16);
+		if (!ops->target.addr) {
+			c = strchr(c, ',');
+			c = validate_comma(c, ops);
+			if (c++ != NULL)
+				ops->target.addr = strtoull(c, NULL, 16);
+		}
+	} else {
+		ops->target.addr = strtoull(ops->raw, NULL, 16);
+	}
+
+	target.addr = map__objdump_2mem(map, ops->target.addr);
+	start = map__unmap_ip(map, sym->start);
+	end = map__unmap_ip(map, sym->end);
+
+	ops->target.outside = target.addr < start || target.addr > end;
+
+	/*
+	 * FIXME: things like this in _cpp_lex_token (gcc's cc1 program):
+
+		cpp_named_operator2name@@Base+0xa72
+
+	 * Point to a place that is after the cpp_named_operator2name
+	 * boundaries, i.e.  in the ELF symbol table for cc1
+	 * cpp_named_operator2name is marked as being 32-bytes long, but it in
+	 * fact is much larger than that, so we seem to need a symbols__find()
+	 * routine that looks for >= current->start and  < next_symbol->start,
+	 * possibly just for C++ objects?
+	 *
+	 * For now lets just make some progress by marking jumps to outside the
+	 * current function as call like.
+	 *
+	 * Actual navigation will come next, with further understanding of how
+	 * the symbol searching and disassembly should be done.
+	 */
+	if (maps__find_ams(ms->maps, &target) == 0 &&
+	    map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
+		ops->target.sym = target.ms.sym;
+
+	if (!ops->target.outside) {
+		ops->target.offset = target.addr - start;
+		ops->target.offset_avail = true;
+	} else {
+		ops->target.offset_avail = false;
+	}
+
+	return 0;
+}
+
+static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops, int max_ins_name)
+{
+	const char *c;
+
+	if (!ops->target.addr || ops->target.offset < 0)
+		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
+
+	if (ops->target.outside && ops->target.sym != NULL)
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
+
+	c = strchr(ops->raw, ',');
+	c = validate_comma(c, ops);
+
+	if (c != NULL) {
+		const char *c2 = strchr(c + 1, ',');
+
+		c2 = validate_comma(c2, ops);
+		/* check for 3-op insn */
+		if (c2 != NULL)
+			c = c2;
+		c++;
+
+		/* mirror arch objdump's space-after-comma style */
+		if (*c == ' ')
+			c++;
+	}
+
+	return scnprintf(bf, size, "%-*s %.*s%" PRIx64, max_ins_name,
+			 ins->name, c ? c - ops->raw : 0, ops->raw,
+			 ops->target.offset);
+}
+
+static void jump__delete(struct ins_operands *ops __maybe_unused)
+{
+	/*
+	 * The ops->jump.raw_comment and ops->jump.raw_func_start belong to the
+	 * raw string, don't free them.
+	 */
+}
+
+static struct ins_ops jump_ops = {
+	.free	   = jump__delete,
+	.parse	   = jump__parse,
+	.scnprintf = jump__scnprintf,
+};
+
+bool ins__is_jump(const struct ins *ins)
+{
+	return ins->ops == &jump_ops || ins->ops == &loongarch_jump_ops;
+}
+
+static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep)
+{
+	char *endptr, *name, *t;
+
+	if (strstr(raw, "(%rip)") == NULL)
+		return 0;
+
+	*addrp = strtoull(comment, &endptr, 16);
+	if (endptr == comment)
+		return 0;
+	name = strchr(endptr, '<');
+	if (name == NULL)
+		return -1;
+
+	name++;
+
+	t = strchr(name, '>');
+	if (t == NULL)
+		return 0;
+
+	*t = '\0';
+	*namep = strdup(name);
+	*t = '>';
+
+	return 0;
+}
+
+static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
+{
+	ops->locked.ops = zalloc(sizeof(*ops->locked.ops));
+	if (ops->locked.ops == NULL)
+		return 0;
+
+	if (disasm_line__parse(ops->raw, &ops->locked.ins.name, &ops->locked.ops->raw) < 0)
+		goto out_free_ops;
+
+	ops->locked.ins.ops = ins__find(arch, ops->locked.ins.name);
+
+	if (ops->locked.ins.ops == NULL)
+		goto out_free_ops;
+
+	if (ops->locked.ins.ops->parse &&
+	    ops->locked.ins.ops->parse(arch, ops->locked.ops, ms) < 0)
+		goto out_free_ops;
+
+	return 0;
+
+out_free_ops:
+	zfree(&ops->locked.ops);
+	return 0;
+}
+
+static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops, int max_ins_name)
+{
+	int printed;
+
+	if (ops->locked.ins.ops == NULL)
+		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
+
+	printed = scnprintf(bf, size, "%-*s ", max_ins_name, ins->name);
+	return printed + ins__scnprintf(&ops->locked.ins, bf + printed,
+					size - printed, ops->locked.ops, max_ins_name);
+}
+
+static void lock__delete(struct ins_operands *ops)
+{
+	struct ins *ins = &ops->locked.ins;
+
+	if (ins->ops && ins->ops->free)
+		ins->ops->free(ops->locked.ops);
+	else
+		ins_ops__delete(ops->locked.ops);
+
+	zfree(&ops->locked.ops);
+	zfree(&ops->target.raw);
+	zfree(&ops->target.name);
+}
+
+static struct ins_ops lock_ops = {
+	.free	   = lock__delete,
+	.parse	   = lock__parse,
+	.scnprintf = lock__scnprintf,
+};
+
+/*
+ * Check if the operand has more than one registers like x86 SIB addressing:
+ *   0x1234(%rax, %rbx, 8)
+ *
+ * But it doesn't care segment selectors like %gs:0x5678(%rcx), so just check
+ * the input string after 'memory_ref_char' if exists.
+ */
+static bool check_multi_regs(struct arch *arch, const char *op)
+{
+	int count = 0;
+
+	if (arch->objdump.register_char == 0)
+		return false;
+
+	if (arch->objdump.memory_ref_char) {
+		op = strchr(op, arch->objdump.memory_ref_char);
+		if (op == NULL)
+			return false;
+	}
+
+	while ((op = strchr(op, arch->objdump.register_char)) != NULL) {
+		count++;
+		op++;
+	}
+
+	return count > 1;
+}
+
+static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
+{
+	char *s = strchr(ops->raw, ','), *target, *comment, prev;
+
+	if (s == NULL)
+		return -1;
+
+	*s = '\0';
+
+	/*
+	 * x86 SIB addressing has something like 0x8(%rax, %rcx, 1)
+	 * then it needs to have the closing parenthesis.
+	 */
+	if (strchr(ops->raw, '(')) {
+		*s = ',';
+		s = strchr(ops->raw, ')');
+		if (s == NULL || s[1] != ',')
+			return -1;
+		*++s = '\0';
+	}
+
+	ops->source.raw = strdup(ops->raw);
+	*s = ',';
+
+	if (ops->source.raw == NULL)
+		return -1;
+
+	ops->source.multi_regs = check_multi_regs(arch, ops->source.raw);
+
+	target = skip_spaces(++s);
+	comment = strchr(s, arch->objdump.comment_char);
+
+	if (comment != NULL)
+		s = comment - 1;
+	else
+		s = strchr(s, '\0') - 1;
+
+	while (s > target && isspace(s[0]))
+		--s;
+	s++;
+	prev = *s;
+	*s = '\0';
+
+	ops->target.raw = strdup(target);
+	*s = prev;
+
+	if (ops->target.raw == NULL)
+		goto out_free_source;
+
+	ops->target.multi_regs = check_multi_regs(arch, ops->target.raw);
+
+	if (comment == NULL)
+		return 0;
+
+	comment = skip_spaces(comment);
+	comment__symbol(ops->source.raw, comment + 1, &ops->source.addr, &ops->source.name);
+	comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
+
+	return 0;
+
+out_free_source:
+	zfree(&ops->source.raw);
+	return -1;
+}
+
+static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops, int max_ins_name)
+{
+	return scnprintf(bf, size, "%-*s %s,%s", max_ins_name, ins->name,
+			 ops->source.name ?: ops->source.raw,
+			 ops->target.name ?: ops->target.raw);
+}
+
+static struct ins_ops mov_ops = {
+	.parse	   = mov__parse,
+	.scnprintf = mov__scnprintf,
+};
+
+static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
+{
+	char *target, *comment, *s, prev;
+
+	target = s = ops->raw;
+
+	while (s[0] != '\0' && !isspace(s[0]))
+		++s;
+	prev = *s;
+	*s = '\0';
+
+	ops->target.raw = strdup(target);
+	*s = prev;
+
+	if (ops->target.raw == NULL)
+		return -1;
+
+	comment = strchr(s, arch->objdump.comment_char);
+	if (comment == NULL)
+		return 0;
+
+	comment = skip_spaces(comment);
+	comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
+
+	return 0;
+}
+
+static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops, int max_ins_name)
+{
+	return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name,
+			 ops->target.name ?: ops->target.raw);
+}
+
+static struct ins_ops dec_ops = {
+	.parse	   = dec__parse,
+	.scnprintf = dec__scnprintf,
+};
+
+static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
+			  struct ins_operands *ops __maybe_unused, int max_ins_name)
+{
+	return scnprintf(bf, size, "%-*s", max_ins_name, "nop");
+}
+
+static struct ins_ops nop_ops = {
+	.scnprintf = nop__scnprintf,
+};
+
+static struct ins_ops ret_ops = {
+	.scnprintf = ins__raw_scnprintf,
+};
+
+bool ins__is_nop(const struct ins *ins)
+{
+	return ins->ops == &nop_ops;
+}
+
+bool ins__is_ret(const struct ins *ins)
+{
+	return ins->ops == &ret_ops;
+}
+
+bool ins__is_lock(const struct ins *ins)
+{
+	return ins->ops == &lock_ops;
+}
+
+static int ins__key_cmp(const void *name, const void *insp)
+{
+	const struct ins *ins = insp;
+
+	return strcmp(name, ins->name);
+}
+
+static int ins__cmp(const void *a, const void *b)
+{
+	const struct ins *ia = a;
+	const struct ins *ib = b;
+
+	return strcmp(ia->name, ib->name);
+}
+
+static void ins__sort(struct arch *arch)
+{
+	const int nmemb = arch->nr_instructions;
+
+	qsort(arch->instructions, nmemb, sizeof(struct ins), ins__cmp);
+}
+
+static struct ins_ops *__ins__find(struct arch *arch, const char *name)
+{
+	struct ins *ins;
+	const int nmemb = arch->nr_instructions;
+
+	if (!arch->sorted_instructions) {
+		ins__sort(arch);
+		arch->sorted_instructions = true;
+	}
+
+	ins = bsearch(name, arch->instructions, nmemb, sizeof(struct ins), ins__key_cmp);
+	if (ins)
+		return ins->ops;
+
+	if (arch->insn_suffix) {
+		char tmp[32];
+		char suffix;
+		size_t len = strlen(name);
+
+		if (len == 0 || len >= sizeof(tmp))
+			return NULL;
+
+		suffix = name[len - 1];
+		if (strchr(arch->insn_suffix, suffix) == NULL)
+			return NULL;
+
+		strcpy(tmp, name);
+		tmp[len - 1] = '\0'; /* remove the suffix and check again */
+
+		ins = bsearch(tmp, arch->instructions, nmemb, sizeof(struct ins), ins__key_cmp);
+	}
+	return ins ? ins->ops : NULL;
+}
+
+struct ins_ops *ins__find(struct arch *arch, const char *name)
+{
+	struct ins_ops *ops = __ins__find(arch, name);
+
+	if (!ops && arch->associate_instruction_ops)
+		ops = arch->associate_instruction_ops(arch, name);
+
+	return ops;
+}
+
+static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map_symbol *ms)
+{
+	dl->ins.ops = ins__find(arch, dl->ins.name);
+
+	if (!dl->ins.ops)
+		return;
+
+	if (dl->ins.ops->parse && dl->ins.ops->parse(arch, &dl->ops, ms) < 0)
+		dl->ins.ops = NULL;
+}
+
+static int disasm_line__parse(char *line, const char **namep, char **rawp)
+{
+	char tmp, *name = skip_spaces(line);
+
+	if (name[0] == '\0')
+		return -1;
+
+	*rawp = name + 1;
+
+	while ((*rawp)[0] != '\0' && !isspace((*rawp)[0]))
+		++*rawp;
+
+	tmp = (*rawp)[0];
+	(*rawp)[0] = '\0';
+	*namep = strdup(name);
+
+	if (*namep == NULL)
+		goto out;
+
+	(*rawp)[0] = tmp;
+	*rawp = strim(*rawp);
+
+	return 0;
+
+out:
+	return -1;
+}
+
+static void annotation_line__init(struct annotation_line *al,
+				  struct annotate_args *args,
+				  int nr)
+{
+	al->offset = args->offset;
+	al->line = strdup(args->line);
+	al->line_nr = args->line_nr;
+	al->fileloc = args->fileloc;
+	al->data_nr = nr;
+}
+
+static void annotation_line__exit(struct annotation_line *al)
+{
+	zfree_srcline(&al->path);
+	zfree(&al->line);
+	zfree(&al->cycles);
+}
+
+static size_t disasm_line_size(int nr)
+{
+	struct annotation_line *al;
+
+	return (sizeof(struct disasm_line) + (sizeof(al->data[0]) * nr));
+}
+
+/*
+ * Allocating the disasm annotation line data with
+ * following structure:
+ *
+ *    -------------------------------------------
+ *    struct disasm_line | struct annotation_line
+ *    -------------------------------------------
+ *
+ * We have 'struct annotation_line' member as last member
+ * of 'struct disasm_line' to have an easy access.
+ */
+struct disasm_line *disasm_line__new(struct annotate_args *args)
+{
+	struct disasm_line *dl = NULL;
+	int nr = 1;
+
+	if (evsel__is_group_event(args->evsel))
+		nr = args->evsel->core.nr_members;
+
+	dl = zalloc(disasm_line_size(nr));
+	if (!dl)
+		return NULL;
+
+	annotation_line__init(&dl->al, args, nr);
+	if (dl->al.line == NULL)
+		goto out_delete;
+
+	if (args->offset != -1) {
+		if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
+			goto out_free_line;
+
+		disasm_line__init_ins(dl, args->arch, &args->ms);
+	}
+
+	return dl;
+
+out_free_line:
+	zfree(&dl->al.line);
+out_delete:
+	free(dl);
+	return NULL;
+}
+
+void disasm_line__free(struct disasm_line *dl)
+{
+	if (dl->ins.ops && dl->ins.ops->free)
+		dl->ins.ops->free(&dl->ops);
+	else
+		ins_ops__delete(&dl->ops);
+	zfree(&dl->ins.name);
+	annotation_line__exit(&dl->al);
+	free(dl);
+}
+
+int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name)
+{
+	if (raw || !dl->ins.ops)
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, dl->ins.name, dl->ops.raw);
+
+	return ins__scnprintf(&dl->ins, bf, size, &dl->ops, max_ins_name);
+}
+
+/*
+ * symbol__parse_objdump_line() parses objdump output (with -d --no-show-raw)
+ * which looks like following
+ *
+ *  0000000000415500 <_init>:
+ *    415500:       sub    $0x8,%rsp
+ *    415504:       mov    0x2f5ad5(%rip),%rax        # 70afe0 <_DYNAMIC+0x2f8>
+ *    41550b:       test   %rax,%rax
+ *    41550e:       je     415515 <_init+0x15>
+ *    415510:       callq  416e70 <__gmon_start__@plt>
+ *    415515:       add    $0x8,%rsp
+ *    415519:       retq
+ *
+ * it will be parsed and saved into struct disasm_line as
+ *  <offset>       <name>  <ops.raw>
+ *
+ * The offset will be a relative offset from the start of the symbol and -1
+ * means that it's not a disassembly line so should be treated differently.
+ * The ops.raw part will be parsed further according to type of the instruction.
+ */
+static int symbol__parse_objdump_line(struct symbol *sym,
+				      struct annotate_args *args,
+				      char *parsed_line, int *line_nr, char **fileloc)
+{
+	struct map *map = args->ms.map;
+	struct annotation *notes = symbol__annotation(sym);
+	struct disasm_line *dl;
+	char *tmp;
+	s64 line_ip, offset = -1;
+	regmatch_t match[2];
+
+	/* /filename:linenr ? Save line number and ignore. */
+	if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) {
+		*line_nr = atoi(parsed_line + match[1].rm_so);
+		free(*fileloc);
+		*fileloc = strdup(parsed_line);
+		return 0;
+	}
+
+	/* Process hex address followed by ':'. */
+	line_ip = strtoull(parsed_line, &tmp, 16);
+	if (parsed_line != tmp && tmp[0] == ':' && tmp[1] != '\0') {
+		u64 start = map__rip_2objdump(map, sym->start),
+		    end = map__rip_2objdump(map, sym->end);
+
+		offset = line_ip - start;
+		if ((u64)line_ip < start || (u64)line_ip >= end)
+			offset = -1;
+		else
+			parsed_line = tmp + 1;
+	}
+
+	args->offset  = offset;
+	args->line    = parsed_line;
+	args->line_nr = *line_nr;
+	args->fileloc = *fileloc;
+	args->ms.sym  = sym;
+
+	dl = disasm_line__new(args);
+	(*line_nr)++;
+
+	if (dl == NULL)
+		return -1;
+
+	if (!disasm_line__has_local_offset(dl)) {
+		dl->ops.target.offset = dl->ops.target.addr -
+					map__rip_2objdump(map, sym->start);
+		dl->ops.target.offset_avail = true;
+	}
+
+	/* kcore has no symbols, so add the call target symbol */
+	if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.sym) {
+		struct addr_map_symbol target = {
+			.addr = dl->ops.target.addr,
+			.ms = { .map = map, },
+		};
+
+		if (!maps__find_ams(args->ms.maps, &target) &&
+		    target.ms.sym->start == target.al_addr)
+			dl->ops.target.sym = target.ms.sym;
+	}
+
+	annotation_line__add(&dl->al, &notes->src->source);
+	return 0;
+}
+
+static void delete_last_nop(struct symbol *sym)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct list_head *list = &notes->src->source;
+	struct disasm_line *dl;
+
+	while (!list_empty(list)) {
+		dl = list_entry(list->prev, struct disasm_line, al.node);
+
+		if (dl->ins.ops) {
+			if (!ins__is_nop(&dl->ins))
+				return;
+		} else {
+			if (!strstr(dl->al.line, " nop ") &&
+			    !strstr(dl->al.line, " nopl ") &&
+			    !strstr(dl->al.line, " nopw "))
+				return;
+		}
+
+		list_del_init(&dl->al.node);
+		disasm_line__free(dl);
+	}
+}
+
+int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen)
+{
+	struct dso *dso = map__dso(ms->map);
+
+	BUG_ON(buflen == 0);
+
+	if (errnum >= 0) {
+		str_error_r(errnum, buf, buflen);
+		return 0;
+	}
+
+	switch (errnum) {
+	case SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX: {
+		char bf[SBUILD_ID_SIZE + 15] = " with build id ";
+		char *build_id_msg = NULL;
+
+		if (dso__has_build_id(dso)) {
+			build_id__sprintf(dso__bid(dso), bf + 15);
+			build_id_msg = bf;
+		}
+		scnprintf(buf, buflen,
+			  "No vmlinux file%s\nwas found in the path.\n\n"
+			  "Note that annotation using /proc/kcore requires CAP_SYS_RAWIO capability.\n\n"
+			  "Please use:\n\n"
+			  "  perf buildid-cache -vu vmlinux\n\n"
+			  "or:\n\n"
+			  "  --vmlinux vmlinux\n", build_id_msg ?: "");
+	}
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF:
+		scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation");
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP:
+		scnprintf(buf, buflen, "Problems with arch specific instruction name regular expressions.");
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING:
+		scnprintf(buf, buflen, "Problems while parsing the CPUID in the arch specific initialization.");
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE:
+		scnprintf(buf, buflen, "Invalid BPF file: %s.", dso__long_name(dso));
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF:
+		scnprintf(buf, buflen, "The %s BPF file has no BTF section, compile with -g or use pahole -J.",
+			  dso__long_name(dso));
+		break;
+	default:
+		scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum);
+		break;
+	}
+
+	return 0;
+}
+
+static int dso__disassemble_filename(struct dso *dso, char *filename, size_t filename_size)
+{
+	char linkname[PATH_MAX];
+	char *build_id_filename;
+	char *build_id_path = NULL;
+	char *pos;
+	int len;
+
+	if (dso__symtab_type(dso) == DSO_BINARY_TYPE__KALLSYMS &&
+	    !dso__is_kcore(dso))
+		return SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX;
+
+	build_id_filename = dso__build_id_filename(dso, NULL, 0, false);
+	if (build_id_filename) {
+		__symbol__join_symfs(filename, filename_size, build_id_filename);
+		free(build_id_filename);
+	} else {
+		if (dso__has_build_id(dso))
+			return ENOMEM;
+		goto fallback;
+	}
+
+	build_id_path = strdup(filename);
+	if (!build_id_path)
+		return ENOMEM;
+
+	/*
+	 * old style build-id cache has name of XX/XXXXXXX.. while
+	 * new style has XX/XXXXXXX../{elf,kallsyms,vdso}.
+	 * extract the build-id part of dirname in the new style only.
+	 */
+	pos = strrchr(build_id_path, '/');
+	if (pos && strlen(pos) < SBUILD_ID_SIZE - 2)
+		dirname(build_id_path);
+
+	if (dso__is_kcore(dso))
+		goto fallback;
+
+	len = readlink(build_id_path, linkname, sizeof(linkname) - 1);
+	if (len < 0)
+		goto fallback;
+
+	linkname[len] = '\0';
+	if (strstr(linkname, DSO__NAME_KALLSYMS) ||
+		access(filename, R_OK)) {
+fallback:
+		/*
+		 * If we don't have build-ids or the build-id file isn't in the
+		 * cache, or is just a kallsyms file, well, lets hope that this
+		 * DSO is the same as when 'perf record' ran.
+		 */
+		if (dso__kernel(dso) && dso__long_name(dso)[0] == '/')
+			snprintf(filename, filename_size, "%s", dso__long_name(dso));
+		else
+			__symbol__join_symfs(filename, filename_size, dso__long_name(dso));
+
+		mutex_lock(dso__lock(dso));
+		if (access(filename, R_OK) && errno == ENOENT && dso__nsinfo(dso)) {
+			char *new_name = dso__filename_with_chroot(dso, filename);
+			if (new_name) {
+				strlcpy(filename, new_name, filename_size);
+				free(new_name);
+			}
+		}
+		mutex_unlock(dso__lock(dso));
+	} else if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND) {
+		dso__set_binary_type(dso, DSO_BINARY_TYPE__BUILD_ID_CACHE);
+	}
+
+	free(build_id_path);
+	return 0;
+}
+
+#if defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+#define PACKAGE "perf"
+#include <bfd.h>
+#include <dis-asm.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
+#include <linux/btf.h>
+#include <tools/dis-asm-compat.h>
+
+#include "bpf-event.h"
+#include "bpf-utils.h"
+
+static int symbol__disassemble_bpf(struct symbol *sym,
+				   struct annotate_args *args)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct bpf_prog_linfo *prog_linfo = NULL;
+	struct bpf_prog_info_node *info_node;
+	int len = sym->end - sym->start;
+	disassembler_ftype disassemble;
+	struct map *map = args->ms.map;
+	struct perf_bpil *info_linear;
+	struct disassemble_info info;
+	struct dso *dso = map__dso(map);
+	int pc = 0, count, sub_id;
+	struct btf *btf = NULL;
+	char tpath[PATH_MAX];
+	size_t buf_size;
+	int nr_skip = 0;
+	char *buf;
+	bfd *bfdf;
+	int ret;
+	FILE *s;
+
+	if (dso__binary_type(dso) != DSO_BINARY_TYPE__BPF_PROG_INFO)
+		return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE;
+
+	pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
+		  sym->name, sym->start, sym->end - sym->start);
+
+	memset(tpath, 0, sizeof(tpath));
+	perf_exe(tpath, sizeof(tpath));
+
+	bfdf = bfd_openr(tpath, NULL);
+	if (bfdf == NULL)
+		abort();
+
+	if (!bfd_check_format(bfdf, bfd_object))
+		abort();
+
+	s = open_memstream(&buf, &buf_size);
+	if (!s) {
+		ret = errno;
+		goto out;
+	}
+	init_disassemble_info_compat(&info, s,
+				     (fprintf_ftype) fprintf,
+				     fprintf_styled);
+	info.arch = bfd_get_arch(bfdf);
+	info.mach = bfd_get_mach(bfdf);
+
+	info_node = perf_env__find_bpf_prog_info(dso__bpf_prog(dso)->env,
+						 dso__bpf_prog(dso)->id);
+	if (!info_node) {
+		ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF;
+		goto out;
+	}
+	info_linear = info_node->info_linear;
+	sub_id = dso__bpf_prog(dso)->sub_id;
+
+	info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns);
+	info.buffer_length = info_linear->info.jited_prog_len;
+
+	if (info_linear->info.nr_line_info)
+		prog_linfo = bpf_prog_linfo__new(&info_linear->info);
+
+	if (info_linear->info.btf_id) {
+		struct btf_node *node;
+
+		node = perf_env__find_btf(dso__bpf_prog(dso)->env,
+					  info_linear->info.btf_id);
+		if (node)
+			btf = btf__new((__u8 *)(node->data),
+				       node->data_size);
+	}
+
+	disassemble_init_for_target(&info);
+
+#ifdef DISASM_FOUR_ARGS_SIGNATURE
+	disassemble = disassembler(info.arch,
+				   bfd_big_endian(bfdf),
+				   info.mach,
+				   bfdf);
+#else
+	disassemble = disassembler(bfdf);
+#endif
+	if (disassemble == NULL)
+		abort();
+
+	fflush(s);
+	do {
+		const struct bpf_line_info *linfo = NULL;
+		struct disasm_line *dl;
+		size_t prev_buf_size;
+		const char *srcline;
+		u64 addr;
+
+		addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id];
+		count = disassemble(pc, &info);
+
+		if (prog_linfo)
+			linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo,
+								addr, sub_id,
+								nr_skip);
+
+		if (linfo && btf) {
+			srcline = btf__name_by_offset(btf, linfo->line_off);
+			nr_skip++;
+		} else
+			srcline = NULL;
+
+		fprintf(s, "\n");
+		prev_buf_size = buf_size;
+		fflush(s);
+
+		if (!annotate_opts.hide_src_code && srcline) {
+			args->offset = -1;
+			args->line = strdup(srcline);
+			args->line_nr = 0;
+			args->fileloc = NULL;
+			args->ms.sym  = sym;
+			dl = disasm_line__new(args);
+			if (dl) {
+				annotation_line__add(&dl->al,
+						     &notes->src->source);
+			}
+		}
+
+		args->offset = pc;
+		args->line = buf + prev_buf_size;
+		args->line_nr = 0;
+		args->fileloc = NULL;
+		args->ms.sym  = sym;
+		dl = disasm_line__new(args);
+		if (dl)
+			annotation_line__add(&dl->al, &notes->src->source);
+
+		pc += count;
+	} while (count > 0 && pc < len);
+
+	ret = 0;
+out:
+	free(prog_linfo);
+	btf__free(btf);
+	fclose(s);
+	bfd_close(bfdf);
+	return ret;
+}
+#else // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused,
+				   struct annotate_args *args __maybe_unused)
+{
+	return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF;
+}
+#endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+
+static int
+symbol__disassemble_bpf_image(struct symbol *sym,
+			      struct annotate_args *args)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct disasm_line *dl;
+
+	args->offset = -1;
+	args->line = strdup("to be implemented");
+	args->line_nr = 0;
+	args->fileloc = NULL;
+	dl = disasm_line__new(args);
+	if (dl)
+		annotation_line__add(&dl->al, &notes->src->source);
+
+	zfree(&args->line);
+	return 0;
+}
+
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
+#include <capstone/capstone.h>
+
+static int open_capstone_handle(struct annotate_args *args, bool is_64bit,
+				csh *handle)
+{
+	struct annotation_options *opt = args->options;
+	cs_mode mode = is_64bit ? CS_MODE_64 : CS_MODE_32;
+
+	/* TODO: support more architectures */
+	if (!arch__is(args->arch, "x86"))
+		return -1;
+
+	if (cs_open(CS_ARCH_X86, mode, handle) != CS_ERR_OK)
+		return -1;
+
+	if (!opt->disassembler_style ||
+	    !strcmp(opt->disassembler_style, "att"))
+		cs_option(*handle, CS_OPT_SYNTAX, CS_OPT_SYNTAX_ATT);
+
+	/*
+	 * Resolving address operands to symbols is implemented
+	 * on x86 by investigating instruction details.
+	 */
+	cs_option(*handle, CS_OPT_DETAIL, CS_OPT_ON);
+
+	return 0;
+}
+
+struct find_file_offset_data {
+	u64 ip;
+	u64 offset;
+};
+
+/* This will be called for each PHDR in an ELF binary */
+static int find_file_offset(u64 start, u64 len, u64 pgoff, void *arg)
+{
+	struct find_file_offset_data *data = arg;
+
+	if (start <= data->ip && data->ip < start + len) {
+		data->offset = pgoff + data->ip - start;
+		return 1;
+	}
+	return 0;
+}
+
+static void print_capstone_detail(cs_insn *insn, char *buf, size_t len,
+				  struct annotate_args *args, u64 addr)
+{
+	int i;
+	struct map *map = args->ms.map;
+	struct symbol *sym;
+
+	/* TODO: support more architectures */
+	if (!arch__is(args->arch, "x86"))
+		return;
+
+	if (insn->detail == NULL)
+		return;
+
+	for (i = 0; i < insn->detail->x86.op_count; i++) {
+		cs_x86_op *op = &insn->detail->x86.operands[i];
+		u64 orig_addr;
+
+		if (op->type != X86_OP_MEM)
+			continue;
+
+		/* only print RIP-based global symbols for now */
+		if (op->mem.base != X86_REG_RIP)
+			continue;
+
+		/* get the target address */
+		orig_addr = addr + insn->size + op->mem.disp;
+		addr = map__objdump_2mem(map, orig_addr);
+
+		if (dso__kernel(map__dso(map))) {
+			/*
+			 * The kernel maps can be splitted into sections,
+			 * let's find the map first and the search the symbol.
+			 */
+			map = maps__find(map__kmaps(map), addr);
+			if (map == NULL)
+				continue;
+		}
+
+		/* convert it to map-relative address for search */
+		addr = map__map_ip(map, addr);
+
+		sym = map__find_symbol(map, addr);
+		if (sym == NULL)
+			continue;
+
+		if (addr == sym->start) {
+			scnprintf(buf, len, "\t# %"PRIx64" <%s>",
+				  orig_addr, sym->name);
+		} else {
+			scnprintf(buf, len, "\t# %"PRIx64" <%s+%#"PRIx64">",
+				  orig_addr, sym->name, addr - sym->start);
+		}
+		break;
+	}
+}
+
+static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
+					struct annotate_args *args)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct map *map = args->ms.map;
+	struct dso *dso = map__dso(map);
+	struct nscookie nsc;
+	u64 start = map__rip_2objdump(map, sym->start);
+	u64 end = map__rip_2objdump(map, sym->end);
+	u64 len = end - start;
+	u64 offset;
+	int i, fd, count;
+	bool is_64bit = false;
+	bool needs_cs_close = false;
+	u8 *buf = NULL;
+	struct find_file_offset_data data = {
+		.ip = start,
+	};
+	csh handle;
+	cs_insn *insn;
+	char disasm_buf[512];
+	struct disasm_line *dl;
+
+	if (args->options->objdump_path)
+		return -1;
+
+	nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
+	fd = open(filename, O_RDONLY);
+	nsinfo__mountns_exit(&nsc);
+	if (fd < 0)
+		return -1;
+
+	if (file__read_maps(fd, /*exe=*/true, find_file_offset, &data,
+			    &is_64bit) == 0)
+		goto err;
+
+	if (open_capstone_handle(args, is_64bit, &handle) < 0)
+		goto err;
+
+	needs_cs_close = true;
+
+	buf = malloc(len);
+	if (buf == NULL)
+		goto err;
+
+	count = pread(fd, buf, len, data.offset);
+	close(fd);
+	fd = -1;
+
+	if ((u64)count != len)
+		goto err;
+
+	/* add the function address and name */
+	scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:",
+		  start, sym->name);
+
+	args->offset = -1;
+	args->line = disasm_buf;
+	args->line_nr = 0;
+	args->fileloc = NULL;
+	args->ms.sym = sym;
+
+	dl = disasm_line__new(args);
+	if (dl == NULL)
+		goto err;
+
+	annotation_line__add(&dl->al, &notes->src->source);
+
+	count = cs_disasm(handle, buf, len, start, len, &insn);
+	for (i = 0, offset = 0; i < count; i++) {
+		int printed;
+
+		printed = scnprintf(disasm_buf, sizeof(disasm_buf),
+				    "       %-7s %s",
+				    insn[i].mnemonic, insn[i].op_str);
+		print_capstone_detail(&insn[i], disasm_buf + printed,
+				      sizeof(disasm_buf) - printed, args,
+				      start + offset);
+
+		args->offset = offset;
+		args->line = disasm_buf;
+
+		dl = disasm_line__new(args);
+		if (dl == NULL)
+			goto err;
+
+		annotation_line__add(&dl->al, &notes->src->source);
+
+		offset += insn[i].size;
+	}
+
+	/* It failed in the middle: probably due to unknown instructions */
+	if (offset != len) {
+		struct list_head *list = &notes->src->source;
+
+		/* Discard all lines and fallback to objdump */
+		while (!list_empty(list)) {
+			dl = list_first_entry(list, struct disasm_line, al.node);
+
+			list_del_init(&dl->al.node);
+			disasm_line__free(dl);
+		}
+		count = -1;
+	}
+
+out:
+	if (needs_cs_close)
+		cs_close(&handle);
+	free(buf);
+	return count < 0 ? count : 0;
+
+err:
+	if (fd >= 0)
+		close(fd);
+	if (needs_cs_close) {
+		struct disasm_line *tmp;
+
+		/*
+		 * It probably failed in the middle of the above loop.
+		 * Release any resources it might add.
+		 */
+		list_for_each_entry_safe(dl, tmp, &notes->src->source, al.node) {
+			list_del(&dl->al.node);
+			free(dl);
+		}
+	}
+	count = -1;
+	goto out;
+}
+#endif
+
+/*
+ * Possibly create a new version of line with tabs expanded. Returns the
+ * existing or new line, storage is updated if a new line is allocated. If
+ * allocation fails then NULL is returned.
+ */
+static char *expand_tabs(char *line, char **storage, size_t *storage_len)
+{
+	size_t i, src, dst, len, new_storage_len, num_tabs;
+	char *new_line;
+	size_t line_len = strlen(line);
+
+	for (num_tabs = 0, i = 0; i < line_len; i++)
+		if (line[i] == '\t')
+			num_tabs++;
+
+	if (num_tabs == 0)
+		return line;
+
+	/*
+	 * Space for the line and '\0', less the leading and trailing
+	 * spaces. Each tab may introduce 7 additional spaces.
+	 */
+	new_storage_len = line_len + 1 + (num_tabs * 7);
+
+	new_line = malloc(new_storage_len);
+	if (new_line == NULL) {
+		pr_err("Failure allocating memory for tab expansion\n");
+		return NULL;
+	}
+
+	/*
+	 * Copy regions starting at src and expand tabs. If there are two
+	 * adjacent tabs then 'src == i', the memcpy is of size 0 and the spaces
+	 * are inserted.
+	 */
+	for (i = 0, src = 0, dst = 0; i < line_len && num_tabs; i++) {
+		if (line[i] == '\t') {
+			len = i - src;
+			memcpy(&new_line[dst], &line[src], len);
+			dst += len;
+			new_line[dst++] = ' ';
+			while (dst % 8 != 0)
+				new_line[dst++] = ' ';
+			src = i + 1;
+			num_tabs--;
+		}
+	}
+
+	/* Expand the last region. */
+	len = line_len - src;
+	memcpy(&new_line[dst], &line[src], len);
+	dst += len;
+	new_line[dst] = '\0';
+
+	free(*storage);
+	*storage = new_line;
+	*storage_len = new_storage_len;
+	return new_line;
+}
+
+int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
+{
+	struct annotation_options *opts = &annotate_opts;
+	struct map *map = args->ms.map;
+	struct dso *dso = map__dso(map);
+	char *command;
+	FILE *file;
+	char symfs_filename[PATH_MAX];
+	struct kcore_extract kce;
+	bool delete_extract = false;
+	bool decomp = false;
+	int lineno = 0;
+	char *fileloc = NULL;
+	int nline;
+	char *line;
+	size_t line_len;
+	const char *objdump_argv[] = {
+		"/bin/sh",
+		"-c",
+		NULL, /* Will be the objdump command to run. */
+		"--",
+		NULL, /* Will be the symfs path. */
+		NULL,
+	};
+	struct child_process objdump_process;
+	int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename));
+
+	if (err)
+		return err;
+
+	pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
+		 symfs_filename, sym->name, map__unmap_ip(map, sym->start),
+		 map__unmap_ip(map, sym->end));
+
+	pr_debug("annotating [%p] %30s : [%p] %30s\n",
+		 dso, dso__long_name(dso), sym, sym->name);
+
+	if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_PROG_INFO) {
+		return symbol__disassemble_bpf(sym, args);
+	} else if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_IMAGE) {
+		return symbol__disassemble_bpf_image(sym, args);
+	} else if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND) {
+		return -1;
+	} else if (dso__is_kcore(dso)) {
+		kce.kcore_filename = symfs_filename;
+		kce.addr = map__rip_2objdump(map, sym->start);
+		kce.offs = sym->start;
+		kce.len = sym->end - sym->start;
+		if (!kcore_extract__create(&kce)) {
+			delete_extract = true;
+			strlcpy(symfs_filename, kce.extract_filename,
+				sizeof(symfs_filename));
+		}
+	} else if (dso__needs_decompress(dso)) {
+		char tmp[KMOD_DECOMP_LEN];
+
+		if (dso__decompress_kmodule_path(dso, symfs_filename,
+						 tmp, sizeof(tmp)) < 0)
+			return -1;
+
+		decomp = true;
+		strcpy(symfs_filename, tmp);
+	}
+
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
+	err = symbol__disassemble_capstone(symfs_filename, sym, args);
+	if (err == 0)
+		goto out_remove_tmp;
+#endif
+
+	err = asprintf(&command,
+		 "%s %s%s --start-address=0x%016" PRIx64
+		 " --stop-address=0x%016" PRIx64
+		 " %s -d %s %s %s %c%s%c %s%s -C \"$1\"",
+		 opts->objdump_path ?: "objdump",
+		 opts->disassembler_style ? "-M " : "",
+		 opts->disassembler_style ?: "",
+		 map__rip_2objdump(map, sym->start),
+		 map__rip_2objdump(map, sym->end),
+		 opts->show_linenr ? "-l" : "",
+		 opts->show_asm_raw ? "" : "--no-show-raw-insn",
+		 opts->annotate_src ? "-S" : "",
+		 opts->prefix ? "--prefix " : "",
+		 opts->prefix ? '"' : ' ',
+		 opts->prefix ?: "",
+		 opts->prefix ? '"' : ' ',
+		 opts->prefix_strip ? "--prefix-strip=" : "",
+		 opts->prefix_strip ?: "");
+
+	if (err < 0) {
+		pr_err("Failure allocating memory for the command to run\n");
+		goto out_remove_tmp;
+	}
+
+	pr_debug("Executing: %s\n", command);
+
+	objdump_argv[2] = command;
+	objdump_argv[4] = symfs_filename;
+
+	/* Create a pipe to read from for stdout */
+	memset(&objdump_process, 0, sizeof(objdump_process));
+	objdump_process.argv = objdump_argv;
+	objdump_process.out = -1;
+	objdump_process.err = -1;
+	objdump_process.no_stderr = 1;
+	if (start_command(&objdump_process)) {
+		pr_err("Failure starting to run %s\n", command);
+		err = -1;
+		goto out_free_command;
+	}
+
+	file = fdopen(objdump_process.out, "r");
+	if (!file) {
+		pr_err("Failure creating FILE stream for %s\n", command);
+		/*
+		 * If we were using debug info should retry with
+		 * original binary.
+		 */
+		err = -1;
+		goto out_close_stdout;
+	}
+
+	/* Storage for getline. */
+	line = NULL;
+	line_len = 0;
+
+	nline = 0;
+	while (!feof(file)) {
+		const char *match;
+		char *expanded_line;
+
+		if (getline(&line, &line_len, file) < 0 || !line)
+			break;
+
+		/* Skip lines containing "filename:" */
+		match = strstr(line, symfs_filename);
+		if (match && match[strlen(symfs_filename)] == ':')
+			continue;
+
+		expanded_line = strim(line);
+		expanded_line = expand_tabs(expanded_line, &line, &line_len);
+		if (!expanded_line)
+			break;
+
+		/*
+		 * The source code line number (lineno) needs to be kept in
+		 * across calls to symbol__parse_objdump_line(), so that it
+		 * can associate it with the instructions till the next one.
+		 * See disasm_line__new() and struct disasm_line::line_nr.
+		 */
+		if (symbol__parse_objdump_line(sym, args, expanded_line,
+					       &lineno, &fileloc) < 0)
+			break;
+		nline++;
+	}
+	free(line);
+	free(fileloc);
+
+	err = finish_command(&objdump_process);
+	if (err)
+		pr_err("Error running %s\n", command);
+
+	if (nline == 0) {
+		err = -1;
+		pr_err("No output from %s\n", command);
+	}
+
+	/*
+	 * kallsyms does not have symbol sizes so there may a nop at the end.
+	 * Remove it.
+	 */
+	if (dso__is_kcore(dso))
+		delete_last_nop(sym);
+
+	fclose(file);
+
+out_close_stdout:
+	close(objdump_process.out);
+
+out_free_command:
+	free(command);
+
+out_remove_tmp:
+	if (decomp)
+		unlink(symfs_filename);
+
+	if (delete_extract)
+		kcore_extract__delete(&kce);
+
+	return err;
+}
diff --git a/tools/perf/util/disasm.h b/tools/perf/util/disasm.h
new file mode 100644
index 0000000000..3d381a0435
--- /dev/null
+++ b/tools/perf/util/disasm.h
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __PERF_UTIL_DISASM_H
+#define __PERF_UTIL_DISASM_H
+
+#include "map_symbol.h"
+
+struct annotation_options;
+struct disasm_line;
+struct ins;
+struct evsel;
+struct symbol;
+
+struct arch {
+	const char	*name;
+	struct ins	*instructions;
+	size_t		nr_instructions;
+	size_t		nr_instructions_allocated;
+	struct ins_ops  *(*associate_instruction_ops)(struct arch *arch, const char *name);
+	bool		sorted_instructions;
+	bool		initialized;
+	const char	*insn_suffix;
+	void		*priv;
+	unsigned int	model;
+	unsigned int	family;
+	int		(*init)(struct arch *arch, char *cpuid);
+	bool		(*ins_is_fused)(struct arch *arch, const char *ins1,
+					const char *ins2);
+	struct		{
+		char comment_char;
+		char skip_functions_char;
+		char register_char;
+		char memory_ref_char;
+		char imm_char;
+	} objdump;
+};
+
+struct ins {
+	const char     *name;
+	struct ins_ops *ops;
+};
+
+struct ins_operands {
+	char	*raw;
+	struct {
+		char	*raw;
+		char	*name;
+		struct symbol *sym;
+		u64	addr;
+		s64	offset;
+		bool	offset_avail;
+		bool	outside;
+		bool	multi_regs;
+	} target;
+	union {
+		struct {
+			char	*raw;
+			char	*name;
+			u64	addr;
+			bool	multi_regs;
+		} source;
+		struct {
+			struct ins	    ins;
+			struct ins_operands *ops;
+		} locked;
+		struct {
+			char	*raw_comment;
+			char	*raw_func_start;
+		} jump;
+	};
+};
+
+struct ins_ops {
+	void (*free)(struct ins_operands *ops);
+	int (*parse)(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms);
+	int (*scnprintf)(struct ins *ins, char *bf, size_t size,
+			 struct ins_operands *ops, int max_ins_name);
+};
+
+struct annotate_args {
+	struct arch		  *arch;
+	struct map_symbol	  ms;
+	struct evsel		  *evsel;
+	struct annotation_options *options;
+	s64			  offset;
+	char			  *line;
+	int			  line_nr;
+	char			  *fileloc;
+};
+
+struct arch *arch__find(const char *name);
+bool arch__is(struct arch *arch, const char *name);
+
+struct ins_ops *ins__find(struct arch *arch, const char *name);
+int ins__scnprintf(struct ins *ins, char *bf, size_t size,
+		   struct ins_operands *ops, int max_ins_name);
+
+bool ins__is_call(const struct ins *ins);
+bool ins__is_jump(const struct ins *ins);
+bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
+bool ins__is_nop(const struct ins *ins);
+bool ins__is_ret(const struct ins *ins);
+bool ins__is_lock(const struct ins *ins);
+
+struct disasm_line *disasm_line__new(struct annotate_args *args);
+void disasm_line__free(struct disasm_line *dl);
+
+int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size,
+			   bool raw, int max_ins_name);
+
+int symbol__disassemble(struct symbol *sym, struct annotate_args *args);
+
+#endif /* __PERF_UTIL_DISASM_H */
diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c
index 908e168137..7d180bdaed 100644
--- a/tools/perf/util/dlfilter.c
+++ b/tools/perf/util/dlfilter.c
@@ -33,13 +33,13 @@ static void al_to_d_al(struct addr_location *al, struct perf_dlfilter_al *d_al)
 	if (al->map) {
 		struct dso *dso = map__dso(al->map);
 
-		if (symbol_conf.show_kernel_path && dso->long_name)
-			d_al->dso = dso->long_name;
+		if (symbol_conf.show_kernel_path && dso__long_name(dso))
+			d_al->dso = dso__long_name(dso);
 		else
-			d_al->dso = dso->name;
-		d_al->is_64_bit = dso->is_64_bit;
-		d_al->buildid_size = dso->bid.size;
-		d_al->buildid = dso->bid.data;
+			d_al->dso = dso__name(dso);
+		d_al->is_64_bit = dso__is_64_bit(dso);
+		d_al->buildid_size = dso__bid(dso)->size;
+		d_al->buildid = dso__bid(dso)->data;
 	} else {
 		d_al->dso = NULL;
 		d_al->is_64_bit = 0;
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 22fd5fa806..67414944f2 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -40,6 +40,12 @@ static const char * const debuglink_paths[] = {
 	"/usr/lib/debug%s/%s"
 };
 
+void dso__set_nsinfo(struct dso *dso, struct nsinfo *nsi)
+{
+	nsinfo__put(RC_CHK_ACCESS(dso)->nsinfo);
+	RC_CHK_ACCESS(dso)->nsinfo = nsi;
+}
+
 char dso__symtab_origin(const struct dso *dso)
 {
 	static const char origin[] = {
@@ -63,14 +69,14 @@ char dso__symtab_origin(const struct dso *dso)
 		[DSO_BINARY_TYPE__GUEST_VMLINUX]		= 'V',
 	};
 
-	if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND)
+	if (dso == NULL || dso__symtab_type(dso) == DSO_BINARY_TYPE__NOT_FOUND)
 		return '!';
-	return origin[dso->symtab_type];
+	return origin[dso__symtab_type(dso)];
 }
 
 bool dso__is_object_file(const struct dso *dso)
 {
-	switch (dso->binary_type) {
+	switch (dso__binary_type(dso)) {
 	case DSO_BINARY_TYPE__KALLSYMS:
 	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
 	case DSO_BINARY_TYPE__JAVA_JIT:
@@ -117,7 +123,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		char symfile[PATH_MAX];
 		unsigned int i;
 
-		len = __symbol__join_symfs(filename, size, dso->long_name);
+		len = __symbol__join_symfs(filename, size, dso__long_name(dso));
 		last_slash = filename + len;
 		while (last_slash != filename && *last_slash != '/')
 			last_slash--;
@@ -159,12 +165,12 @@ int dso__read_binary_type_filename(const struct dso *dso,
 
 	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
 		len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
-		snprintf(filename + len, size - len, "%s.debug", dso->long_name);
+		snprintf(filename + len, size - len, "%s.debug", dso__long_name(dso));
 		break;
 
 	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
 		len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
-		snprintf(filename + len, size - len, "%s", dso->long_name);
+		snprintf(filename + len, size - len, "%s", dso__long_name(dso));
 		break;
 
 	case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO:
@@ -173,13 +179,13 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		 * /usr/lib/debug/lib when it is expected to be in
 		 * /usr/lib/debug/usr/lib
 		 */
-		if (strlen(dso->long_name) < 9 ||
-		    strncmp(dso->long_name, "/usr/lib/", 9)) {
+		if (strlen(dso__long_name(dso)) < 9 ||
+		    strncmp(dso__long_name(dso), "/usr/lib/", 9)) {
 			ret = -1;
 			break;
 		}
 		len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
-		snprintf(filename + len, size - len, "%s", dso->long_name + 4);
+		snprintf(filename + len, size - len, "%s", dso__long_name(dso) + 4);
 		break;
 
 	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
@@ -187,29 +193,29 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		const char *last_slash;
 		size_t dir_size;
 
-		last_slash = dso->long_name + dso->long_name_len;
-		while (last_slash != dso->long_name && *last_slash != '/')
+		last_slash = dso__long_name(dso) + dso__long_name_len(dso);
+		while (last_slash != dso__long_name(dso) && *last_slash != '/')
 			last_slash--;
 
 		len = __symbol__join_symfs(filename, size, "");
-		dir_size = last_slash - dso->long_name + 2;
+		dir_size = last_slash - dso__long_name(dso) + 2;
 		if (dir_size > (size - len)) {
 			ret = -1;
 			break;
 		}
-		len += scnprintf(filename + len, dir_size, "%s",  dso->long_name);
+		len += scnprintf(filename + len, dir_size, "%s",  dso__long_name(dso));
 		len += scnprintf(filename + len , size - len, ".debug%s",
 								last_slash);
 		break;
 	}
 
 	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
-		if (!dso->has_build_id) {
+		if (!dso__has_build_id(dso)) {
 			ret = -1;
 			break;
 		}
 
-		build_id__sprintf(&dso->bid, build_id_hex);
+		build_id__sprintf(dso__bid_const(dso), build_id_hex);
 		len = __symbol__join_symfs(filename, size, "/usr/lib/debug/.build-id/");
 		snprintf(filename + len, size - len, "%.2s/%s.debug",
 			 build_id_hex, build_id_hex + 2);
@@ -218,23 +224,23 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	case DSO_BINARY_TYPE__VMLINUX:
 	case DSO_BINARY_TYPE__GUEST_VMLINUX:
 	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
-		__symbol__join_symfs(filename, size, dso->long_name);
+		__symbol__join_symfs(filename, size, dso__long_name(dso));
 		break;
 
 	case DSO_BINARY_TYPE__GUEST_KMODULE:
 	case DSO_BINARY_TYPE__GUEST_KMODULE_COMP:
 		path__join3(filename, size, symbol_conf.symfs,
-			    root_dir, dso->long_name);
+			    root_dir, dso__long_name(dso));
 		break;
 
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
-		__symbol__join_symfs(filename, size, dso->long_name);
+		__symbol__join_symfs(filename, size, dso__long_name(dso));
 		break;
 
 	case DSO_BINARY_TYPE__KCORE:
 	case DSO_BINARY_TYPE__GUEST_KCORE:
-		snprintf(filename, size, "%s", dso->long_name);
+		snprintf(filename, size, "%s", dso__long_name(dso));
 		break;
 
 	default:
@@ -310,8 +316,8 @@ bool is_kernel_module(const char *pathname, int cpumode)
 
 bool dso__needs_decompress(struct dso *dso)
 {
-	return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
-		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
+	return dso__symtab_type(dso) == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
+		dso__symtab_type(dso) == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
 }
 
 int filename__decompress(const char *name, char *pathname,
@@ -363,11 +369,10 @@ static int decompress_kmodule(struct dso *dso, const char *name,
 	if (!dso__needs_decompress(dso))
 		return -1;
 
-	if (dso->comp == COMP_ID__NONE)
+	if (dso__comp(dso) == COMP_ID__NONE)
 		return -1;
 
-	return filename__decompress(name, pathname, len, dso->comp,
-				    &dso->load_errno);
+	return filename__decompress(name, pathname, len, dso__comp(dso), dso__load_errno(dso));
 }
 
 int dso__decompress_kmodule_fd(struct dso *dso, const char *name)
@@ -468,17 +473,17 @@ void dso__set_module_info(struct dso *dso, struct kmod_path *m,
 			  struct machine *machine)
 {
 	if (machine__is_host(machine))
-		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
+		dso__set_symtab_type(dso, DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE);
 	else
-		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
+		dso__set_symtab_type(dso, DSO_BINARY_TYPE__GUEST_KMODULE);
 
 	/* _KMODULE_COMP should be next to _KMODULE */
 	if (m->kmod && m->comp) {
-		dso->symtab_type++;
-		dso->comp = m->comp;
+		dso__set_symtab_type(dso, dso__symtab_type(dso) + 1);
+		dso__set_comp(dso, m->comp);
 	}
 
-	dso->is_kmod = 1;
+	dso__set_is_kmod(dso);
 	dso__set_short_name(dso, strdup(m->name), true);
 }
 
@@ -491,13 +496,21 @@ static pthread_mutex_t dso__data_open_lock = PTHREAD_MUTEX_INITIALIZER;
 
 static void dso__list_add(struct dso *dso)
 {
-	list_add_tail(&dso->data.open_entry, &dso__data_open);
+	list_add_tail(&dso__data(dso)->open_entry, &dso__data_open);
+#ifdef REFCNT_CHECKING
+	dso__data(dso)->dso = dso__get(dso);
+#endif
+	/* Assume the dso is part of dsos, hence the optional reference count above. */
+	assert(dso__dsos(dso));
 	dso__data_open_cnt++;
 }
 
 static void dso__list_del(struct dso *dso)
 {
-	list_del_init(&dso->data.open_entry);
+	list_del_init(&dso__data(dso)->open_entry);
+#ifdef REFCNT_CHECKING
+	dso__put(dso__data(dso)->dso);
+#endif
 	WARN_ONCE(dso__data_open_cnt <= 0,
 		  "DSO data fd counter out of bounds.");
 	dso__data_open_cnt--;
@@ -528,7 +541,7 @@ static int do_open(char *name)
 
 char *dso__filename_with_chroot(const struct dso *dso, const char *filename)
 {
-	return filename_with_chroot(nsinfo__pid(dso->nsinfo), filename);
+	return filename_with_chroot(nsinfo__pid(dso__nsinfo_const(dso)), filename);
 }
 
 static int __open_dso(struct dso *dso, struct machine *machine)
@@ -541,18 +554,18 @@ static int __open_dso(struct dso *dso, struct machine *machine)
 	if (!name)
 		return -ENOMEM;
 
-	mutex_lock(&dso->lock);
+	mutex_lock(dso__lock(dso));
 	if (machine)
 		root_dir = machine->root_dir;
 
-	if (dso__read_binary_type_filename(dso, dso->binary_type,
+	if (dso__read_binary_type_filename(dso, dso__binary_type(dso),
 					    root_dir, name, PATH_MAX))
 		goto out;
 
 	if (!is_regular_file(name)) {
 		char *new_name;
 
-		if (errno != ENOENT || dso->nsinfo == NULL)
+		if (errno != ENOENT || dso__nsinfo(dso) == NULL)
 			goto out;
 
 		new_name = dso__filename_with_chroot(dso, name);
@@ -568,7 +581,7 @@ static int __open_dso(struct dso *dso, struct machine *machine)
 		size_t len = sizeof(newpath);
 
 		if (dso__decompress_kmodule_path(dso, name, newpath, len) < 0) {
-			fd = -dso->load_errno;
+			fd = -(*dso__load_errno(dso));
 			goto out;
 		}
 
@@ -582,7 +595,7 @@ static int __open_dso(struct dso *dso, struct machine *machine)
 		unlink(name);
 
 out:
-	mutex_unlock(&dso->lock);
+	mutex_unlock(dso__lock(dso));
 	free(name);
 	return fd;
 }
@@ -601,13 +614,13 @@ static int open_dso(struct dso *dso, struct machine *machine)
 	int fd;
 	struct nscookie nsc;
 
-	if (dso->binary_type != DSO_BINARY_TYPE__BUILD_ID_CACHE) {
-		mutex_lock(&dso->lock);
-		nsinfo__mountns_enter(dso->nsinfo, &nsc);
-		mutex_unlock(&dso->lock);
+	if (dso__binary_type(dso) != DSO_BINARY_TYPE__BUILD_ID_CACHE) {
+		mutex_lock(dso__lock(dso));
+		nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
+		mutex_unlock(dso__lock(dso));
 	}
 	fd = __open_dso(dso, machine);
-	if (dso->binary_type != DSO_BINARY_TYPE__BUILD_ID_CACHE)
+	if (dso__binary_type(dso) != DSO_BINARY_TYPE__BUILD_ID_CACHE)
 		nsinfo__mountns_exit(&nsc);
 
 	if (fd >= 0) {
@@ -624,10 +637,10 @@ static int open_dso(struct dso *dso, struct machine *machine)
 
 static void close_data_fd(struct dso *dso)
 {
-	if (dso->data.fd >= 0) {
-		close(dso->data.fd);
-		dso->data.fd = -1;
-		dso->data.file_size = 0;
+	if (dso__data(dso)->fd >= 0) {
+		close(dso__data(dso)->fd);
+		dso__data(dso)->fd = -1;
+		dso__data(dso)->file_size = 0;
 		dso__list_del(dso);
 	}
 }
@@ -646,9 +659,15 @@ static void close_dso(struct dso *dso)
 
 static void close_first_dso(void)
 {
+	struct dso_data *dso_data;
 	struct dso *dso;
 
-	dso = list_first_entry(&dso__data_open, struct dso, data.open_entry);
+	dso_data = list_first_entry(&dso__data_open, struct dso_data, open_entry);
+#ifdef REFCNT_CHECKING
+	dso = dso_data->dso;
+#else
+	dso = container_of(dso_data, struct dso, data);
+#endif
 	close_dso(dso);
 }
 
@@ -728,28 +747,29 @@ static void try_to_open_dso(struct dso *dso, struct machine *machine)
 		DSO_BINARY_TYPE__NOT_FOUND,
 	};
 	int i = 0;
+	struct dso_data *dso_data = dso__data(dso);
 
-	if (dso->data.fd >= 0)
+	if (dso_data->fd >= 0)
 		return;
 
-	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
-		dso->data.fd = open_dso(dso, machine);
+	if (dso__binary_type(dso) != DSO_BINARY_TYPE__NOT_FOUND) {
+		dso_data->fd = open_dso(dso, machine);
 		goto out;
 	}
 
 	do {
-		dso->binary_type = binary_type_data[i++];
+		dso__set_binary_type(dso, binary_type_data[i++]);
 
-		dso->data.fd = open_dso(dso, machine);
-		if (dso->data.fd >= 0)
+		dso_data->fd = open_dso(dso, machine);
+		if (dso_data->fd >= 0)
 			goto out;
 
-	} while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
+	} while (dso__binary_type(dso) != DSO_BINARY_TYPE__NOT_FOUND);
 out:
-	if (dso->data.fd >= 0)
-		dso->data.status = DSO_DATA_STATUS_OK;
+	if (dso_data->fd >= 0)
+		dso_data->status = DSO_DATA_STATUS_OK;
 	else
-		dso->data.status = DSO_DATA_STATUS_ERROR;
+		dso_data->status = DSO_DATA_STATUS_ERROR;
 }
 
 /**
@@ -763,7 +783,7 @@ out:
  */
 int dso__data_get_fd(struct dso *dso, struct machine *machine)
 {
-	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+	if (dso__data(dso)->status == DSO_DATA_STATUS_ERROR)
 		return -1;
 
 	if (pthread_mutex_lock(&dso__data_open_lock) < 0)
@@ -771,10 +791,10 @@ int dso__data_get_fd(struct dso *dso, struct machine *machine)
 
 	try_to_open_dso(dso, machine);
 
-	if (dso->data.fd < 0)
+	if (dso__data(dso)->fd < 0)
 		pthread_mutex_unlock(&dso__data_open_lock);
 
-	return dso->data.fd;
+	return dso__data(dso)->fd;
 }
 
 void dso__data_put_fd(struct dso *dso __maybe_unused)
@@ -786,10 +806,10 @@ bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
 {
 	u32 flag = 1 << by;
 
-	if (dso->data.status_seen & flag)
+	if (dso__data(dso)->status_seen & flag)
 		return true;
 
-	dso->data.status_seen |= flag;
+	dso__data(dso)->status_seen |= flag;
 
 	return false;
 }
@@ -799,12 +819,13 @@ static ssize_t bpf_read(struct dso *dso, u64 offset, char *data)
 {
 	struct bpf_prog_info_node *node;
 	ssize_t size = DSO__DATA_CACHE_SIZE;
+	struct dso_bpf_prog *dso_bpf_prog = dso__bpf_prog(dso);
 	u64 len;
 	u8 *buf;
 
-	node = perf_env__find_bpf_prog_info(dso->bpf_prog.env, dso->bpf_prog.id);
+	node = perf_env__find_bpf_prog_info(dso_bpf_prog->env, dso_bpf_prog->id);
 	if (!node || !node->info_linear) {
-		dso->data.status = DSO_DATA_STATUS_ERROR;
+		dso__data(dso)->status = DSO_DATA_STATUS_ERROR;
 		return -1;
 	}
 
@@ -822,14 +843,15 @@ static ssize_t bpf_read(struct dso *dso, u64 offset, char *data)
 static int bpf_size(struct dso *dso)
 {
 	struct bpf_prog_info_node *node;
+	struct dso_bpf_prog *dso_bpf_prog = dso__bpf_prog(dso);
 
-	node = perf_env__find_bpf_prog_info(dso->bpf_prog.env, dso->bpf_prog.id);
+	node = perf_env__find_bpf_prog_info(dso_bpf_prog->env, dso_bpf_prog->id);
 	if (!node || !node->info_linear) {
-		dso->data.status = DSO_DATA_STATUS_ERROR;
+		dso__data(dso)->status = DSO_DATA_STATUS_ERROR;
 		return -1;
 	}
 
-	dso->data.file_size = node->info_linear->info.jited_prog_len;
+	dso__data(dso)->file_size = node->info_linear->info.jited_prog_len;
 	return 0;
 }
 #endif // HAVE_LIBBPF_SUPPORT
@@ -837,10 +859,10 @@ static int bpf_size(struct dso *dso)
 static void
 dso_cache__free(struct dso *dso)
 {
-	struct rb_root *root = &dso->data.cache;
+	struct rb_root *root = &dso__data(dso)->cache;
 	struct rb_node *next = rb_first(root);
 
-	mutex_lock(&dso->lock);
+	mutex_lock(dso__lock(dso));
 	while (next) {
 		struct dso_cache *cache;
 
@@ -849,12 +871,12 @@ dso_cache__free(struct dso *dso)
 		rb_erase(&cache->rb_node, root);
 		free(cache);
 	}
-	mutex_unlock(&dso->lock);
+	mutex_unlock(dso__lock(dso));
 }
 
 static struct dso_cache *__dso_cache__find(struct dso *dso, u64 offset)
 {
-	const struct rb_root *root = &dso->data.cache;
+	const struct rb_root *root = &dso__data(dso)->cache;
 	struct rb_node * const *p = &root->rb_node;
 	const struct rb_node *parent = NULL;
 	struct dso_cache *cache;
@@ -880,13 +902,13 @@ static struct dso_cache *__dso_cache__find(struct dso *dso, u64 offset)
 static struct dso_cache *
 dso_cache__insert(struct dso *dso, struct dso_cache *new)
 {
-	struct rb_root *root = &dso->data.cache;
+	struct rb_root *root = &dso__data(dso)->cache;
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	struct dso_cache *cache;
 	u64 offset = new->offset;
 
-	mutex_lock(&dso->lock);
+	mutex_lock(dso__lock(dso));
 	while (*p != NULL) {
 		u64 end;
 
@@ -907,7 +929,7 @@ dso_cache__insert(struct dso *dso, struct dso_cache *new)
 
 	cache = NULL;
 out:
-	mutex_unlock(&dso->lock);
+	mutex_unlock(dso__lock(dso));
 	return cache;
 }
 
@@ -932,18 +954,18 @@ static ssize_t file_read(struct dso *dso, struct machine *machine,
 	pthread_mutex_lock(&dso__data_open_lock);
 
 	/*
-	 * dso->data.fd might be closed if other thread opened another
+	 * dso__data(dso)->fd might be closed if other thread opened another
 	 * file (dso) due to open file limit (RLIMIT_NOFILE).
 	 */
 	try_to_open_dso(dso, machine);
 
-	if (dso->data.fd < 0) {
-		dso->data.status = DSO_DATA_STATUS_ERROR;
+	if (dso__data(dso)->fd < 0) {
+		dso__data(dso)->status = DSO_DATA_STATUS_ERROR;
 		ret = -errno;
 		goto out;
 	}
 
-	ret = pread(dso->data.fd, data, DSO__DATA_CACHE_SIZE, offset);
+	ret = pread(dso__data(dso)->fd, data, DSO__DATA_CACHE_SIZE, offset);
 out:
 	pthread_mutex_unlock(&dso__data_open_lock);
 	return ret;
@@ -963,11 +985,11 @@ static struct dso_cache *dso_cache__populate(struct dso *dso,
 		return NULL;
 	}
 #ifdef HAVE_LIBBPF_SUPPORT
-	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
+	if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_PROG_INFO)
 		*ret = bpf_read(dso, cache_offset, cache->data);
 	else
 #endif
-	if (dso->binary_type == DSO_BINARY_TYPE__OOL)
+	if (dso__binary_type(dso) == DSO_BINARY_TYPE__OOL)
 		*ret = DSO__DATA_CACHE_SIZE;
 	else
 		*ret = file_read(dso, machine, cache_offset, cache->data);
@@ -1056,25 +1078,25 @@ static int file_size(struct dso *dso, struct machine *machine)
 	pthread_mutex_lock(&dso__data_open_lock);
 
 	/*
-	 * dso->data.fd might be closed if other thread opened another
+	 * dso__data(dso)->fd might be closed if other thread opened another
 	 * file (dso) due to open file limit (RLIMIT_NOFILE).
 	 */
 	try_to_open_dso(dso, machine);
 
-	if (dso->data.fd < 0) {
+	if (dso__data(dso)->fd < 0) {
 		ret = -errno;
-		dso->data.status = DSO_DATA_STATUS_ERROR;
+		dso__data(dso)->status = DSO_DATA_STATUS_ERROR;
 		goto out;
 	}
 
-	if (fstat(dso->data.fd, &st) < 0) {
+	if (fstat(dso__data(dso)->fd, &st) < 0) {
 		ret = -errno;
 		pr_err("dso cache fstat failed: %s\n",
 		       str_error_r(errno, sbuf, sizeof(sbuf)));
-		dso->data.status = DSO_DATA_STATUS_ERROR;
+		dso__data(dso)->status = DSO_DATA_STATUS_ERROR;
 		goto out;
 	}
-	dso->data.file_size = st.st_size;
+	dso__data(dso)->file_size = st.st_size;
 
 out:
 	pthread_mutex_unlock(&dso__data_open_lock);
@@ -1083,13 +1105,13 @@ out:
 
 int dso__data_file_size(struct dso *dso, struct machine *machine)
 {
-	if (dso->data.file_size)
+	if (dso__data(dso)->file_size)
 		return 0;
 
-	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+	if (dso__data(dso)->status == DSO_DATA_STATUS_ERROR)
 		return -1;
 #ifdef HAVE_LIBBPF_SUPPORT
-	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
+	if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_PROG_INFO)
 		return bpf_size(dso);
 #endif
 	return file_size(dso, machine);
@@ -1108,7 +1130,7 @@ off_t dso__data_size(struct dso *dso, struct machine *machine)
 		return -1;
 
 	/* For now just estimate dso data size is close to file size */
-	return dso->data.file_size;
+	return dso__data(dso)->file_size;
 }
 
 static ssize_t data_read_write_offset(struct dso *dso, struct machine *machine,
@@ -1119,7 +1141,7 @@ static ssize_t data_read_write_offset(struct dso *dso, struct machine *machine,
 		return -1;
 
 	/* Check the offset sanity. */
-	if (offset > dso->data.file_size)
+	if (offset > dso__data(dso)->file_size)
 		return -1;
 
 	if (offset + size < offset)
@@ -1142,7 +1164,7 @@ static ssize_t data_read_write_offset(struct dso *dso, struct machine *machine,
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 			      u64 offset, u8 *data, ssize_t size)
 {
-	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+	if (dso__data(dso)->status == DSO_DATA_STATUS_ERROR)
 		return -1;
 
 	return data_read_write_offset(dso, machine, offset, data, size, true);
@@ -1182,7 +1204,7 @@ ssize_t dso__data_write_cache_offs(struct dso *dso, struct machine *machine,
 {
 	u8 *data = (u8 *)data_in; /* cast away const to use same fns for r/w */
 
-	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+	if (dso__data(dso)->status == DSO_DATA_STATUS_ERROR)
 		return -1;
 
 	return data_read_write_offset(dso, machine, offset, data, size, false);
@@ -1235,56 +1257,139 @@ struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
 	 */
 	if (dso != NULL) {
 		dso__set_short_name(dso, short_name, false);
-		dso->kernel = dso_type;
+		dso__set_kernel(dso, dso_type);
 	}
 
 	return dso;
 }
 
-static void dso__set_long_name_id(struct dso *dso, const char *name, struct dso_id *id, bool name_allocated)
+static void dso__set_long_name_id(struct dso *dso, const char *name, bool name_allocated)
 {
-	struct rb_root *root = dso->root;
+	struct dsos *dsos = dso__dsos(dso);
 
 	if (name == NULL)
 		return;
 
-	if (dso->long_name_allocated)
-		free((char *)dso->long_name);
-
-	if (root) {
-		rb_erase(&dso->rb_node, root);
+	if (dsos) {
 		/*
-		 * __dsos__findnew_link_by_longname_id() isn't guaranteed to
-		 * add it back, so a clean removal is required here.
+		 * Need to avoid re-sorting the dsos breaking by non-atomically
+		 * renaming the dso.
 		 */
-		RB_CLEAR_NODE(&dso->rb_node);
-		dso->root = NULL;
+		down_write(&dsos->lock);
+	}
+
+	if (dso__long_name_allocated(dso))
+		free((char *)dso__long_name(dso));
+
+	RC_CHK_ACCESS(dso)->long_name = name;
+	RC_CHK_ACCESS(dso)->long_name_len = strlen(name);
+	dso__set_long_name_allocated(dso, name_allocated);
+
+	if (dsos) {
+		dsos->sorted = false;
+		up_write(&dsos->lock);
+	}
+}
+
+static int __dso_id__cmp(const struct dso_id *a, const struct dso_id *b)
+{
+	if (a->maj > b->maj) return -1;
+	if (a->maj < b->maj) return 1;
+
+	if (a->min > b->min) return -1;
+	if (a->min < b->min) return 1;
+
+	if (a->ino > b->ino) return -1;
+	if (a->ino < b->ino) return 1;
+
+	/*
+	 * Synthesized MMAP events have zero ino_generation, avoid comparing
+	 * them with MMAP events with actual ino_generation.
+	 *
+	 * I found it harmful because the mismatch resulted in a new
+	 * dso that did not have a build ID whereas the original dso did have a
+	 * build ID. The build ID was essential because the object was not found
+	 * otherwise. - Adrian
+	 */
+	if (a->ino_generation && b->ino_generation) {
+		if (a->ino_generation > b->ino_generation) return -1;
+		if (a->ino_generation < b->ino_generation) return 1;
 	}
 
-	dso->long_name		 = name;
-	dso->long_name_len	 = strlen(name);
-	dso->long_name_allocated = name_allocated;
+	return 0;
+}
+
+bool dso_id__empty(const struct dso_id *id)
+{
+	if (!id)
+		return true;
+
+	return !id->maj && !id->min && !id->ino && !id->ino_generation;
+}
+
+void __dso__inject_id(struct dso *dso, struct dso_id *id)
+{
+	struct dsos *dsos = dso__dsos(dso);
+	struct dso_id *dso_id = dso__id(dso);
+
+	/* dsos write lock held by caller. */
+
+	dso_id->maj = id->maj;
+	dso_id->min = id->min;
+	dso_id->ino = id->ino;
+	dso_id->ino_generation = id->ino_generation;
+
+	if (dsos)
+		dsos->sorted = false;
+}
 
-	if (root)
-		__dsos__findnew_link_by_longname_id(root, dso, NULL, id);
+int dso_id__cmp(const struct dso_id *a, const struct dso_id *b)
+{
+	/*
+	 * The second is always dso->id, so zeroes if not set, assume passing
+	 * NULL for a means a zeroed id
+	 */
+	if (dso_id__empty(a) || dso_id__empty(b))
+		return 0;
+
+	return __dso_id__cmp(a, b);
+}
+
+int dso__cmp_id(struct dso *a, struct dso *b)
+{
+	return __dso_id__cmp(dso__id(a), dso__id(b));
 }
 
 void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
 {
-	dso__set_long_name_id(dso, name, NULL, name_allocated);
+	dso__set_long_name_id(dso, name, name_allocated);
 }
 
 void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
 {
+	struct dsos *dsos = dso__dsos(dso);
+
 	if (name == NULL)
 		return;
 
-	if (dso->short_name_allocated)
-		free((char *)dso->short_name);
+	if (dsos) {
+		/*
+		 * Need to avoid re-sorting the dsos breaking by non-atomically
+		 * renaming the dso.
+		 */
+		down_write(&dsos->lock);
+	}
+	if (dso__short_name_allocated(dso))
+		free((char *)dso__short_name(dso));
+
+	RC_CHK_ACCESS(dso)->short_name		  = name;
+	RC_CHK_ACCESS(dso)->short_name_len	  = strlen(name);
+	dso__set_short_name_allocated(dso, name_allocated);
 
-	dso->short_name		  = name;
-	dso->short_name_len	  = strlen(name);
-	dso->short_name_allocated = name_allocated;
+	if (dsos) {
+		dsos->sorted = false;
+		up_write(&dsos->lock);
+	}
 }
 
 int dso__name_len(const struct dso *dso)
@@ -1292,43 +1397,48 @@ int dso__name_len(const struct dso *dso)
 	if (!dso)
 		return strlen("[unknown]");
 	if (verbose > 0)
-		return dso->long_name_len;
+		return dso__long_name_len(dso);
 
-	return dso->short_name_len;
+	return dso__short_name_len(dso);
 }
 
 bool dso__loaded(const struct dso *dso)
 {
-	return dso->loaded;
+	return RC_CHK_ACCESS(dso)->loaded;
 }
 
 bool dso__sorted_by_name(const struct dso *dso)
 {
-	return dso->sorted_by_name;
+	return RC_CHK_ACCESS(dso)->sorted_by_name;
 }
 
 void dso__set_sorted_by_name(struct dso *dso)
 {
-	dso->sorted_by_name = true;
+	RC_CHK_ACCESS(dso)->sorted_by_name = true;
 }
 
 struct dso *dso__new_id(const char *name, struct dso_id *id)
 {
-	struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1);
+	RC_STRUCT(dso) *dso = zalloc(sizeof(*dso) + strlen(name) + 1);
+	struct dso *res;
+	struct dso_data *data;
 
-	if (dso != NULL) {
+	if (!dso)
+		return NULL;
+
+	if (ADD_RC_CHK(res, dso)) {
 		strcpy(dso->name, name);
 		if (id)
 			dso->id = *id;
-		dso__set_long_name_id(dso, dso->name, id, false);
-		dso__set_short_name(dso, dso->name, false);
+		dso__set_long_name_id(res, dso->name, false);
+		dso__set_short_name(res, dso->name, false);
 		dso->symbols = RB_ROOT_CACHED;
 		dso->symbol_names = NULL;
 		dso->symbol_names_len = 0;
-		dso->data.cache = RB_ROOT;
 		dso->inlined_nodes = RB_ROOT_CACHED;
 		dso->srclines = RB_ROOT_CACHED;
 		dso->data_types = RB_ROOT;
+		dso->global_vars = RB_ROOT;
 		dso->data.fd = -1;
 		dso->data.status = DSO_DATA_STATUS_UNKNOWN;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
@@ -1344,15 +1454,18 @@ struct dso *dso__new_id(const char *name, struct dso_id *id)
 		dso->is_kmod = 0;
 		dso->needs_swap = DSO_SWAP__UNSET;
 		dso->comp = COMP_ID__NONE;
-		RB_CLEAR_NODE(&dso->rb_node);
-		dso->root = NULL;
-		INIT_LIST_HEAD(&dso->node);
-		INIT_LIST_HEAD(&dso->data.open_entry);
 		mutex_init(&dso->lock);
 		refcount_set(&dso->refcnt, 1);
+		data = &dso->data;
+		data->cache = RB_ROOT;
+		data->fd = -1;
+		data->status = DSO_DATA_STATUS_UNKNOWN;
+		INIT_LIST_HEAD(&data->open_entry);
+#ifdef REFCNT_CHECKING
+		data->dso = NULL; /* Set when on the open_entry list. */
+#endif
 	}
-
-	return dso;
+	return res;
 }
 
 struct dso *dso__new(const char *name)
@@ -1362,71 +1475,78 @@ struct dso *dso__new(const char *name)
 
 void dso__delete(struct dso *dso)
 {
-	if (!RB_EMPTY_NODE(&dso->rb_node))
-		pr_err("DSO %s is still in rbtree when being deleted!\n",
-		       dso->long_name);
+	if (dso__dsos(dso))
+		pr_err("DSO %s is still in rbtree when being deleted!\n", dso__long_name(dso));
 
 	/* free inlines first, as they reference symbols */
-	inlines__tree_delete(&dso->inlined_nodes);
-	srcline__tree_delete(&dso->srclines);
-	symbols__delete(&dso->symbols);
-	dso->symbol_names_len = 0;
-	zfree(&dso->symbol_names);
-	annotated_data_type__tree_delete(&dso->data_types);
-
-	if (dso->short_name_allocated) {
-		zfree((char **)&dso->short_name);
-		dso->short_name_allocated = false;
+	inlines__tree_delete(&RC_CHK_ACCESS(dso)->inlined_nodes);
+	srcline__tree_delete(&RC_CHK_ACCESS(dso)->srclines);
+	symbols__delete(&RC_CHK_ACCESS(dso)->symbols);
+	RC_CHK_ACCESS(dso)->symbol_names_len = 0;
+	zfree(&RC_CHK_ACCESS(dso)->symbol_names);
+	annotated_data_type__tree_delete(dso__data_types(dso));
+	global_var_type__tree_delete(dso__global_vars(dso));
+
+	if (RC_CHK_ACCESS(dso)->short_name_allocated) {
+		zfree((char **)&RC_CHK_ACCESS(dso)->short_name);
+		RC_CHK_ACCESS(dso)->short_name_allocated = false;
 	}
 
-	if (dso->long_name_allocated) {
-		zfree((char **)&dso->long_name);
-		dso->long_name_allocated = false;
+	if (RC_CHK_ACCESS(dso)->long_name_allocated) {
+		zfree((char **)&RC_CHK_ACCESS(dso)->long_name);
+		RC_CHK_ACCESS(dso)->long_name_allocated = false;
 	}
 
 	dso__data_close(dso);
-	auxtrace_cache__free(dso->auxtrace_cache);
+	auxtrace_cache__free(RC_CHK_ACCESS(dso)->auxtrace_cache);
 	dso_cache__free(dso);
 	dso__free_a2l(dso);
-	zfree(&dso->symsrc_filename);
-	nsinfo__zput(dso->nsinfo);
-	mutex_destroy(&dso->lock);
-	free(dso);
+	dso__free_symsrc_filename(dso);
+	nsinfo__zput(RC_CHK_ACCESS(dso)->nsinfo);
+	mutex_destroy(dso__lock(dso));
+	RC_CHK_FREE(dso);
 }
 
 struct dso *dso__get(struct dso *dso)
 {
-	if (dso)
-		refcount_inc(&dso->refcnt);
-	return dso;
+	struct dso *result;
+
+	if (RC_CHK_GET(result, dso))
+		refcount_inc(&RC_CHK_ACCESS(dso)->refcnt);
+
+	return result;
 }
 
 void dso__put(struct dso *dso)
 {
-	if (dso && refcount_dec_and_test(&dso->refcnt))
+	if (dso && refcount_dec_and_test(&RC_CHK_ACCESS(dso)->refcnt))
 		dso__delete(dso);
+	else
+		RC_CHK_PUT(dso);
 }
 
 void dso__set_build_id(struct dso *dso, struct build_id *bid)
 {
-	dso->bid = *bid;
-	dso->has_build_id = 1;
+	RC_CHK_ACCESS(dso)->bid = *bid;
+	RC_CHK_ACCESS(dso)->has_build_id = 1;
 }
 
 bool dso__build_id_equal(const struct dso *dso, struct build_id *bid)
 {
-	if (dso->bid.size > bid->size && dso->bid.size == BUILD_ID_SIZE) {
+	const struct build_id *dso_bid = dso__bid_const(dso);
+
+	if (dso_bid->size > bid->size && dso_bid->size == BUILD_ID_SIZE) {
 		/*
 		 * For the backward compatibility, it allows a build-id has
 		 * trailing zeros.
 		 */
-		return !memcmp(dso->bid.data, bid->data, bid->size) &&
-			!memchr_inv(&dso->bid.data[bid->size], 0,
-				    dso->bid.size - bid->size);
+		return !memcmp(dso_bid->data, bid->data, bid->size) &&
+			!memchr_inv(&dso_bid->data[bid->size], 0,
+				    dso_bid->size - bid->size);
 	}
 
-	return dso->bid.size == bid->size &&
-	       memcmp(dso->bid.data, bid->data, dso->bid.size) == 0;
+	return dso_bid->size == bid->size &&
+	       memcmp(dso_bid->data, bid->data, dso_bid->size) == 0;
 }
 
 void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine)
@@ -1436,8 +1556,8 @@ void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine)
 	if (machine__is_default_guest(machine))
 		return;
 	sprintf(path, "%s/sys/kernel/notes", machine->root_dir);
-	if (sysfs__read_build_id(path, &dso->bid) == 0)
-		dso->has_build_id = true;
+	if (sysfs__read_build_id(path, dso__bid(dso)) == 0)
+		dso__set_has_build_id(dso);
 }
 
 int dso__kernel_module_get_build_id(struct dso *dso,
@@ -1448,14 +1568,14 @@ int dso__kernel_module_get_build_id(struct dso *dso,
 	 * kernel module short names are of the form "[module]" and
 	 * we need just "module" here.
 	 */
-	const char *name = dso->short_name + 1;
+	const char *name = dso__short_name(dso) + 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->bid) == 0)
-		dso->has_build_id = true;
+	if (sysfs__read_build_id(filename, dso__bid(dso)) == 0)
+		dso__set_has_build_id(dso);
 
 	return 0;
 }
@@ -1464,21 +1584,21 @@ static size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
 {
 	char sbuild_id[SBUILD_ID_SIZE];
 
-	build_id__sprintf(&dso->bid, sbuild_id);
+	build_id__sprintf(dso__bid(dso), sbuild_id);
 	return fprintf(fp, "%s", sbuild_id);
 }
 
 size_t dso__fprintf(struct dso *dso, FILE *fp)
 {
 	struct rb_node *nd;
-	size_t ret = fprintf(fp, "dso: %s (", dso->short_name);
+	size_t ret = fprintf(fp, "dso: %s (", dso__short_name(dso));
 
-	if (dso->short_name != dso->long_name)
-		ret += fprintf(fp, "%s, ", dso->long_name);
+	if (dso__short_name(dso) != dso__long_name(dso))
+		ret += fprintf(fp, "%s, ", dso__long_name(dso));
 	ret += fprintf(fp, "%sloaded, ", dso__loaded(dso) ? "" : "NOT ");
 	ret += dso__fprintf_buildid(dso, fp);
 	ret += fprintf(fp, ")\n");
-	for (nd = rb_first_cached(&dso->symbols); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(dso__symbols(dso)); nd; nd = rb_next(nd)) {
 		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
 		ret += symbol__fprintf(pos, fp);
 	}
@@ -1502,7 +1622,7 @@ enum dso_type dso__type(struct dso *dso, struct machine *machine)
 
 int dso__strerror_load(struct dso *dso, char *buf, size_t buflen)
 {
-	int idx, errnum = dso->load_errno;
+	int idx, errnum = *dso__load_errno(dso);
 	/*
 	 * This must have a same ordering as the enum dso_load_errno.
 	 */
@@ -1532,3 +1652,15 @@ int dso__strerror_load(struct dso *dso, char *buf, size_t buflen)
 	scnprintf(buf, buflen, "%s", dso_load__error_str[idx]);
 	return 0;
 }
+
+bool perf_pid_map_tid(const char *dso_name, int *tid)
+{
+	return sscanf(dso_name, "/tmp/perf-%d.map", tid) == 1;
+}
+
+bool is_perf_pid_map_name(const char *dso_name)
+{
+	int tid;
+
+	return perf_pid_map_tid(dso_name, &tid);
+}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index ce9f3849a7..ed0068251c 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -11,6 +11,7 @@
 #include <linux/bitops.h>
 #include "build-id.h"
 #include "mutex.h"
+#include <internal/rc_check.h>
 
 struct machine;
 struct map;
@@ -100,26 +101,27 @@ enum dso_load_errno {
 	__DSO_LOAD_ERRNO__END,
 };
 
-#define DSO__SWAP(dso, type, val)			\
-({							\
-	type ____r = val;				\
-	BUG_ON(dso->needs_swap == DSO_SWAP__UNSET);	\
-	if (dso->needs_swap == DSO_SWAP__YES) {		\
-		switch (sizeof(____r)) {		\
-		case 2:					\
-			____r = bswap_16(val);		\
-			break;				\
-		case 4:					\
-			____r = bswap_32(val);		\
-			break;				\
-		case 8:					\
-			____r = bswap_64(val);		\
-			break;				\
-		default:				\
-			BUG_ON(1);			\
-		}					\
-	}						\
-	____r;						\
+#define DSO__SWAP(dso, type, val)				\
+({								\
+	type ____r = val;					\
+	enum dso_swap_type ___dst = dso__needs_swap(dso);	\
+	BUG_ON(___dst == DSO_SWAP__UNSET);			\
+	if (___dst == DSO_SWAP__YES) {				\
+		switch (sizeof(____r)) {			\
+		case 2:						\
+			____r = bswap_16(val);			\
+			break;					\
+		case 4:						\
+			____r = bswap_32(val);			\
+			break;					\
+		case 8:						\
+			____r = bswap_64(val);			\
+			break;					\
+		default:					\
+			BUG_ON(1);				\
+		}						\
+	}							\
+	____r;							\
 })
 
 #define DSO__DATA_CACHE_SIZE 4096
@@ -142,33 +144,77 @@ struct dso_cache {
 	char data[];
 };
 
+struct dso_data {
+	struct rb_root	 cache;
+	struct list_head open_entry;
+#ifdef REFCNT_CHECKING
+	struct dso	 *dso;
+#endif
+	int		 fd;
+	int		 status;
+	u32		 status_seen;
+	u64		 file_size;
+	u64		 elf_base_addr;
+	u64		 debug_frame_offset;
+	u64		 eh_frame_hdr_addr;
+	u64		 eh_frame_hdr_offset;
+};
+
+struct dso_bpf_prog {
+	u32		id;
+	u32		sub_id;
+	struct perf_env	*env;
+};
+
 struct auxtrace_cache;
 
-struct dso {
+DECLARE_RC_STRUCT(dso) {
 	struct mutex	 lock;
-	struct list_head node;
-	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
-	struct rb_root	 *root;		/* root of rbtree that rb_node is in */
+	struct dsos	 *dsos;
 	struct rb_root_cached symbols;
 	struct symbol	 **symbol_names;
 	size_t		 symbol_names_len;
 	struct rb_root_cached inlined_nodes;
 	struct rb_root_cached srclines;
-	struct rb_root	data_types;
+	struct rb_root	 data_types;
+	struct rb_root	 global_vars;
 
 	struct {
 		u64		addr;
 		struct symbol	*symbol;
 	} last_find_result;
+	struct build_id	 bid;
+	u64		 text_offset;
+	u64		 text_end;
+	const char	 *short_name;
+	const char	 *long_name;
 	void		 *a2l;
 	char		 *symsrc_filename;
+#if defined(__powerpc__)
+	void		*dwfl;			/* DWARF debug info */
+#endif
+	struct nsinfo	*nsinfo;
+	struct auxtrace_cache *auxtrace_cache;
+	union { /* Tool specific area */
+		void	 *priv;
+		u64	 db_id;
+	};
+	/* bpf prog information */
+	struct dso_bpf_prog bpf_prog;
+	/* dso data file */
+	struct dso_data	 data;
+	struct dso_id	 id;
 	unsigned int	 a2l_fails;
-	enum dso_space_type	kernel;
-	bool			is_kmod;
-	enum dso_swap_type	needs_swap;
-	enum dso_binary_type	symtab_type;
-	enum dso_binary_type	binary_type;
+	int		 comp;
+	refcount_t	 refcnt;
 	enum dso_load_errno	load_errno;
+	u16		 long_name_len;
+	u16		 short_name_len;
+	enum dso_binary_type	symtab_type:8;
+	enum dso_binary_type	binary_type:8;
+	enum dso_space_type	kernel:2;
+	enum dso_swap_type	needs_swap:2;
+	bool			is_kmod:1;
 	u8		 adjust_symbols:1;
 	u8		 has_build_id:1;
 	u8		 header_build_id:1;
@@ -182,44 +228,6 @@ struct dso {
 	bool		 sorted_by_name;
 	bool		 loaded;
 	u8		 rel;
-	struct build_id	 bid;
-	u64		 text_offset;
-	u64		 text_end;
-	const char	 *short_name;
-	const char	 *long_name;
-	u16		 long_name_len;
-	u16		 short_name_len;
-	void		*dwfl;			/* DWARF debug info */
-	struct auxtrace_cache *auxtrace_cache;
-	int		 comp;
-
-	/* dso data file */
-	struct {
-		struct rb_root	 cache;
-		int		 fd;
-		int		 status;
-		u32		 status_seen;
-		u64		 file_size;
-		struct list_head open_entry;
-		u64		 elf_base_addr;
-		u64		 debug_frame_offset;
-		u64		 eh_frame_hdr_addr;
-		u64		 eh_frame_hdr_offset;
-	} data;
-	/* bpf prog information */
-	struct {
-		u32		id;
-		u32		sub_id;
-		struct perf_env	*env;
-	} bpf_prog;
-
-	union { /* Tool specific area */
-		void	 *priv;
-		u64	 db_id;
-	};
-	struct nsinfo	*nsinfo;
-	struct dso_id	 id;
-	refcount_t	 refcnt;
 	char		 name[];
 };
 
@@ -230,19 +238,408 @@ struct dso {
  * @n: the 'struct rb_node *' to use as a temporary storage
  */
 #define dso__for_each_symbol(dso, pos, n)	\
-	symbols__for_each_entry(&(dso)->symbols, pos, n)
+	symbols__for_each_entry(dso__symbols(dso), pos, n)
+
+static inline void *dso__a2l(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->a2l;
+}
+
+static inline void dso__set_a2l(struct dso *dso, void *val)
+{
+	RC_CHK_ACCESS(dso)->a2l = val;
+}
+
+static inline unsigned int dso__a2l_fails(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->a2l_fails;
+}
+
+static inline void dso__set_a2l_fails(struct dso *dso, unsigned int val)
+{
+	RC_CHK_ACCESS(dso)->a2l_fails = val;
+}
+
+static inline bool dso__adjust_symbols(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->adjust_symbols;
+}
+
+static inline void dso__set_adjust_symbols(struct dso *dso, bool val)
+{
+	RC_CHK_ACCESS(dso)->adjust_symbols = val;
+}
+
+static inline bool dso__annotate_warned(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->annotate_warned;
+}
+
+static inline void dso__set_annotate_warned(struct dso *dso)
+{
+	RC_CHK_ACCESS(dso)->annotate_warned = 1;
+}
+
+static inline bool dso__auxtrace_warned(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->auxtrace_warned;
+}
 
-#define dsos__for_each_with_build_id(pos, head)	\
-	list_for_each_entry(pos, head, node)	\
-		if (!pos->has_build_id)		\
-			continue;		\
-		else
+static inline void dso__set_auxtrace_warned(struct dso *dso)
+{
+	RC_CHK_ACCESS(dso)->auxtrace_warned = 1;
+}
+
+static inline struct auxtrace_cache *dso__auxtrace_cache(struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->auxtrace_cache;
+}
+
+static inline void dso__set_auxtrace_cache(struct dso *dso, struct auxtrace_cache *cache)
+{
+	RC_CHK_ACCESS(dso)->auxtrace_cache = cache;
+}
+
+static inline struct build_id *dso__bid(struct dso *dso)
+{
+	return &RC_CHK_ACCESS(dso)->bid;
+}
+
+static inline const struct build_id *dso__bid_const(const struct dso *dso)
+{
+	return &RC_CHK_ACCESS(dso)->bid;
+}
+
+static inline struct dso_bpf_prog *dso__bpf_prog(struct dso *dso)
+{
+	return &RC_CHK_ACCESS(dso)->bpf_prog;
+}
+
+static inline bool dso__has_build_id(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->has_build_id;
+}
+
+static inline void dso__set_has_build_id(struct dso *dso)
+{
+	RC_CHK_ACCESS(dso)->has_build_id = true;
+}
+
+static inline bool dso__has_srcline(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->has_srcline;
+}
+
+static inline void dso__set_has_srcline(struct dso *dso, bool val)
+{
+	RC_CHK_ACCESS(dso)->has_srcline = val;
+}
+
+static inline int dso__comp(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->comp;
+}
+
+static inline void dso__set_comp(struct dso *dso, int comp)
+{
+	RC_CHK_ACCESS(dso)->comp = comp;
+}
+
+static inline struct dso_data *dso__data(struct dso *dso)
+{
+	return &RC_CHK_ACCESS(dso)->data;
+}
+
+static inline u64 dso__db_id(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->db_id;
+}
+
+static inline void dso__set_db_id(struct dso *dso, u64 db_id)
+{
+	RC_CHK_ACCESS(dso)->db_id = db_id;
+}
+
+static inline struct dsos *dso__dsos(struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->dsos;
+}
+
+static inline void dso__set_dsos(struct dso *dso, struct dsos *dsos)
+{
+	RC_CHK_ACCESS(dso)->dsos = dsos;
+}
+
+static inline bool dso__header_build_id(struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->header_build_id;
+}
+
+static inline void dso__set_header_build_id(struct dso *dso, bool val)
+{
+	RC_CHK_ACCESS(dso)->header_build_id = val;
+}
+
+static inline bool dso__hit(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->hit;
+}
+
+static inline void dso__set_hit(struct dso *dso)
+{
+	RC_CHK_ACCESS(dso)->hit = 1;
+}
+
+static inline struct dso_id *dso__id(struct dso *dso)
+{
+	return &RC_CHK_ACCESS(dso)->id;
+}
+
+static inline const struct dso_id *dso__id_const(const struct dso *dso)
+{
+	return &RC_CHK_ACCESS(dso)->id;
+}
+
+static inline struct rb_root_cached *dso__inlined_nodes(struct dso *dso)
+{
+	return &RC_CHK_ACCESS(dso)->inlined_nodes;
+}
+
+static inline bool dso__is_64_bit(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->is_64_bit;
+}
+
+static inline void dso__set_is_64_bit(struct dso *dso, bool is)
+{
+	RC_CHK_ACCESS(dso)->is_64_bit = is;
+}
+
+static inline bool dso__is_kmod(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->is_kmod;
+}
+
+static inline void dso__set_is_kmod(struct dso *dso)
+{
+	RC_CHK_ACCESS(dso)->is_kmod = 1;
+}
+
+static inline enum dso_space_type dso__kernel(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->kernel;
+}
+
+static inline void dso__set_kernel(struct dso *dso, enum dso_space_type kernel)
+{
+	RC_CHK_ACCESS(dso)->kernel = kernel;
+}
+
+static inline u64 dso__last_find_result_addr(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->last_find_result.addr;
+}
+
+static inline void dso__set_last_find_result_addr(struct dso *dso, u64 addr)
+{
+	RC_CHK_ACCESS(dso)->last_find_result.addr = addr;
+}
+
+static inline struct symbol *dso__last_find_result_symbol(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->last_find_result.symbol;
+}
+
+static inline void dso__set_last_find_result_symbol(struct dso *dso, struct symbol *symbol)
+{
+	RC_CHK_ACCESS(dso)->last_find_result.symbol = symbol;
+}
+
+static inline enum dso_load_errno *dso__load_errno(struct dso *dso)
+{
+	return &RC_CHK_ACCESS(dso)->load_errno;
+}
 
 static inline void dso__set_loaded(struct dso *dso)
 {
-	dso->loaded = true;
+	RC_CHK_ACCESS(dso)->loaded = true;
+}
+
+static inline struct mutex *dso__lock(struct dso *dso)
+{
+	return &RC_CHK_ACCESS(dso)->lock;
+}
+
+static inline const char *dso__long_name(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->long_name;
 }
 
+static inline bool dso__long_name_allocated(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->long_name_allocated;
+}
+
+static inline void dso__set_long_name_allocated(struct dso *dso, bool allocated)
+{
+	RC_CHK_ACCESS(dso)->long_name_allocated = allocated;
+}
+
+static inline u16 dso__long_name_len(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->long_name_len;
+}
+
+static inline const char *dso__name(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->name;
+}
+
+static inline enum dso_swap_type dso__needs_swap(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->needs_swap;
+}
+
+static inline void dso__set_needs_swap(struct dso *dso, enum dso_swap_type type)
+{
+	RC_CHK_ACCESS(dso)->needs_swap = type;
+}
+
+static inline struct nsinfo *dso__nsinfo(struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->nsinfo;
+}
+
+static inline const struct nsinfo *dso__nsinfo_const(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->nsinfo;
+}
+
+static inline struct nsinfo **dso__nsinfo_ptr(struct dso *dso)
+{
+	return &RC_CHK_ACCESS(dso)->nsinfo;
+}
+
+void dso__set_nsinfo(struct dso *dso, struct nsinfo *nsi);
+
+static inline u8 dso__rel(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->rel;
+}
+
+static inline void dso__set_rel(struct dso *dso, u8 rel)
+{
+	RC_CHK_ACCESS(dso)->rel = rel;
+}
+
+static inline const char *dso__short_name(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->short_name;
+}
+
+static inline bool dso__short_name_allocated(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->short_name_allocated;
+}
+
+static inline void dso__set_short_name_allocated(struct dso *dso, bool allocated)
+{
+	RC_CHK_ACCESS(dso)->short_name_allocated = allocated;
+}
+
+static inline u16 dso__short_name_len(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->short_name_len;
+}
+
+static inline struct rb_root_cached *dso__srclines(struct dso *dso)
+{
+	return &RC_CHK_ACCESS(dso)->srclines;
+}
+
+static inline struct rb_root *dso__data_types(struct dso *dso)
+{
+	return &RC_CHK_ACCESS(dso)->data_types;
+}
+
+static inline struct rb_root *dso__global_vars(struct dso *dso)
+{
+	return &RC_CHK_ACCESS(dso)->global_vars;
+}
+
+static inline struct rb_root_cached *dso__symbols(struct dso *dso)
+{
+	return &RC_CHK_ACCESS(dso)->symbols;
+}
+
+static inline struct symbol **dso__symbol_names(struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->symbol_names;
+}
+
+static inline void dso__set_symbol_names(struct dso *dso, struct symbol **names)
+{
+	RC_CHK_ACCESS(dso)->symbol_names = names;
+}
+
+static inline size_t dso__symbol_names_len(struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->symbol_names_len;
+}
+
+static inline void dso__set_symbol_names_len(struct dso *dso, size_t len)
+{
+	RC_CHK_ACCESS(dso)->symbol_names_len = len;
+}
+
+static inline const char *dso__symsrc_filename(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->symsrc_filename;
+}
+
+static inline void dso__set_symsrc_filename(struct dso *dso, char *val)
+{
+	RC_CHK_ACCESS(dso)->symsrc_filename = val;
+}
+
+static inline void dso__free_symsrc_filename(struct dso *dso)
+{
+	zfree(&RC_CHK_ACCESS(dso)->symsrc_filename);
+}
+
+static inline enum dso_binary_type dso__symtab_type(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->symtab_type;
+}
+
+static inline void dso__set_symtab_type(struct dso *dso, enum dso_binary_type bt)
+{
+	RC_CHK_ACCESS(dso)->symtab_type = bt;
+}
+
+static inline u64 dso__text_end(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->text_end;
+}
+
+static inline void dso__set_text_end(struct dso *dso, u64 val)
+{
+	RC_CHK_ACCESS(dso)->text_end = val;
+}
+
+static inline u64 dso__text_offset(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->text_offset;
+}
+
+static inline void dso__set_text_offset(struct dso *dso, u64 val)
+{
+	RC_CHK_ACCESS(dso)->text_offset = val;
+}
+
+int dso_id__cmp(const struct dso_id *a, const struct dso_id *b);
+bool dso_id__empty(const struct dso_id *id);
+
 struct dso *dso__new_id(const char *name, struct dso_id *id);
 struct dso *dso__new(const char *name);
 void dso__delete(struct dso *dso);
@@ -250,6 +647,7 @@ void dso__delete(struct dso *dso);
 int dso__cmp_id(struct dso *a, struct dso *b);
 void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated);
 void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated);
+void __dso__inject_id(struct dso *dso, struct dso_id *id);
 
 int dso__name_len(const struct dso *dso);
 
@@ -268,7 +666,7 @@ bool dso__loaded(const struct dso *dso);
 
 static inline bool dso__has_symbols(const struct dso *dso)
 {
-	return !RB_EMPTY_ROOT(&dso->symbols.rb_root);
+	return !RB_EMPTY_ROOT(&RC_CHK_ACCESS(dso)->symbols.rb_root);
 }
 
 char *dso__filename_with_chroot(const struct dso *dso, const char *filename);
@@ -384,21 +782,33 @@ void dso__reset_find_symbol_cache(struct dso *dso);
 size_t dso__fprintf_symbols_by_name(struct dso *dso, FILE *fp);
 size_t dso__fprintf(struct dso *dso, FILE *fp);
 
+static inline enum dso_binary_type dso__binary_type(const struct dso *dso)
+{
+	return RC_CHK_ACCESS(dso)->binary_type;
+}
+
+static inline void dso__set_binary_type(struct dso *dso, enum dso_binary_type bt)
+{
+	RC_CHK_ACCESS(dso)->binary_type = bt;
+}
+
 static inline bool dso__is_vmlinux(const struct dso *dso)
 {
-	return dso->binary_type == DSO_BINARY_TYPE__VMLINUX ||
-	       dso->binary_type == DSO_BINARY_TYPE__GUEST_VMLINUX;
+	enum dso_binary_type bt = dso__binary_type(dso);
+
+	return bt == DSO_BINARY_TYPE__VMLINUX || bt == DSO_BINARY_TYPE__GUEST_VMLINUX;
 }
 
 static inline bool dso__is_kcore(const struct dso *dso)
 {
-	return dso->binary_type == DSO_BINARY_TYPE__KCORE ||
-	       dso->binary_type == DSO_BINARY_TYPE__GUEST_KCORE;
+	enum dso_binary_type bt = dso__binary_type(dso);
+
+	return bt == DSO_BINARY_TYPE__KCORE || bt == DSO_BINARY_TYPE__GUEST_KCORE;
 }
 
 static inline bool dso__is_kallsyms(const struct dso *dso)
 {
-	return dso->kernel && dso->long_name[0] != '/';
+	return RC_CHK_ACCESS(dso)->kernel && RC_CHK_ACCESS(dso)->long_name[0] != '/';
 }
 
 bool dso__is_object_file(const struct dso *dso);
@@ -411,4 +821,11 @@ int dso__strerror_load(struct dso *dso, char *buf, size_t buflen);
 
 void reset_fd_limit(void);
 
+u64 dso__find_global_type(struct dso *dso, u64 addr);
+u64 dso__findnew_global_type(struct dso *dso, u64 addr, u64 offset);
+
+/* Check if dso name is of format "/tmp/perf-%d.map" */
+bool perf_pid_map_tid(const char *dso_name, int *tid);
+bool is_perf_pid_map_name(const char *dso_name);
+
 #endif /* __PERF_DSO */
diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c
index cf80aa42dd..a69a9c6612 100644
--- a/tools/perf/util/dsos.c
+++ b/tools/perf/util/dsos.c
@@ -12,115 +12,140 @@
 #include <symbol.h> // filename__read_build_id
 #include <unistd.h>
 
-static int __dso_id__cmp(struct dso_id *a, struct dso_id *b)
+void dsos__init(struct dsos *dsos)
 {
-	if (a->maj > b->maj) return -1;
-	if (a->maj < b->maj) return 1;
+	init_rwsem(&dsos->lock);
 
-	if (a->min > b->min) return -1;
-	if (a->min < b->min) return 1;
+	dsos->cnt = 0;
+	dsos->allocated = 0;
+	dsos->dsos = NULL;
+	dsos->sorted = true;
+}
 
-	if (a->ino > b->ino) return -1;
-	if (a->ino < b->ino) return 1;
+static void dsos__purge(struct dsos *dsos)
+{
+	down_write(&dsos->lock);
 
-	/*
-	 * Synthesized MMAP events have zero ino_generation, avoid comparing
-	 * them with MMAP events with actual ino_generation.
-	 *
-	 * I found it harmful because the mismatch resulted in a new
-	 * dso that did not have a build ID whereas the original dso did have a
-	 * build ID. The build ID was essential because the object was not found
-	 * otherwise. - Adrian
-	 */
-	if (a->ino_generation && b->ino_generation) {
-		if (a->ino_generation > b->ino_generation) return -1;
-		if (a->ino_generation < b->ino_generation) return 1;
-	}
+	for (unsigned int i = 0; i < dsos->cnt; i++) {
+		struct dso *dso = dsos->dsos[i];
 
-	return 0;
-}
+		dso__set_dsos(dso, NULL);
+		dso__put(dso);
+	}
 
-static bool dso_id__empty(struct dso_id *id)
-{
-	if (!id)
-		return true;
+	zfree(&dsos->dsos);
+	dsos->cnt = 0;
+	dsos->allocated = 0;
+	dsos->sorted = true;
 
-	return !id->maj && !id->min && !id->ino && !id->ino_generation;
+	up_write(&dsos->lock);
 }
 
-static void dso__inject_id(struct dso *dso, struct dso_id *id)
+void dsos__exit(struct dsos *dsos)
 {
-	dso->id.maj = id->maj;
-	dso->id.min = id->min;
-	dso->id.ino = id->ino;
-	dso->id.ino_generation = id->ino_generation;
+	dsos__purge(dsos);
+	exit_rwsem(&dsos->lock);
 }
 
-static int dso_id__cmp(struct dso_id *a, struct dso_id *b)
+
+static int __dsos__for_each_dso(struct dsos *dsos,
+				int (*cb)(struct dso *dso, void *data),
+				void *data)
 {
-	/*
-	 * The second is always dso->id, so zeroes if not set, assume passing
-	 * NULL for a means a zeroed id
-	 */
-	if (dso_id__empty(a) || dso_id__empty(b))
-		return 0;
+	for (unsigned int i = 0; i < dsos->cnt; i++) {
+		struct dso *dso = dsos->dsos[i];
+		int err;
 
-	return __dso_id__cmp(a, b);
+		err = cb(dso, data);
+		if (err)
+			return err;
+	}
+	return 0;
 }
 
-int dso__cmp_id(struct dso *a, struct dso *b)
-{
-	return __dso_id__cmp(&a->id, &b->id);
-}
+struct dsos__read_build_ids_cb_args {
+	bool with_hits;
+	bool have_build_id;
+};
 
-bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
+static int dsos__read_build_ids_cb(struct dso *dso, void *data)
 {
-	bool have_build_id = false;
-	struct dso *pos;
+	struct dsos__read_build_ids_cb_args *args = data;
 	struct nscookie nsc;
 
-	list_for_each_entry(pos, head, node) {
-		if (with_hits && !pos->hit && !dso__is_vdso(pos))
-			continue;
-		if (pos->has_build_id) {
-			have_build_id = true;
-			continue;
-		}
-		nsinfo__mountns_enter(pos->nsinfo, &nsc);
-		if (filename__read_build_id(pos->long_name, &pos->bid) > 0) {
-			have_build_id	  = true;
-			pos->has_build_id = true;
-		} else if (errno == ENOENT && pos->nsinfo) {
-			char *new_name = dso__filename_with_chroot(pos, pos->long_name);
-
-			if (new_name && filename__read_build_id(new_name,
-								&pos->bid) > 0) {
-				have_build_id = true;
-				pos->has_build_id = true;
-			}
-			free(new_name);
+	if (args->with_hits && !dso__hit(dso) && !dso__is_vdso(dso))
+		return 0;
+	if (dso__has_build_id(dso)) {
+		args->have_build_id = true;
+		return 0;
+	}
+	nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
+	if (filename__read_build_id(dso__long_name(dso), dso__bid(dso)) > 0) {
+		args->have_build_id = true;
+		dso__set_has_build_id(dso);
+	} else if (errno == ENOENT && dso__nsinfo(dso)) {
+		char *new_name = dso__filename_with_chroot(dso, dso__long_name(dso));
+
+		if (new_name && filename__read_build_id(new_name, dso__bid(dso)) > 0) {
+			args->have_build_id = true;
+			dso__set_has_build_id(dso);
 		}
-		nsinfo__mountns_exit(&nsc);
+		free(new_name);
 	}
+	nsinfo__mountns_exit(&nsc);
+	return 0;
+}
 
-	return have_build_id;
+bool dsos__read_build_ids(struct dsos *dsos, bool with_hits)
+{
+	struct dsos__read_build_ids_cb_args args = {
+		.with_hits = with_hits,
+		.have_build_id = false,
+	};
+
+	dsos__for_each_dso(dsos, dsos__read_build_ids_cb, &args);
+	return args.have_build_id;
 }
 
-static int __dso__cmp_long_name(const char *long_name, struct dso_id *id, struct dso *b)
+static int __dso__cmp_long_name(const char *long_name, const struct dso_id *id,
+				const struct dso *b)
 {
-	int rc = strcmp(long_name, b->long_name);
-	return rc ?: dso_id__cmp(id, &b->id);
+	int rc = strcmp(long_name, dso__long_name(b));
+	return rc ?: dso_id__cmp(id, dso__id_const(b));
 }
 
-static int __dso__cmp_short_name(const char *short_name, struct dso_id *id, struct dso *b)
+static int __dso__cmp_short_name(const char *short_name, const struct dso_id *id,
+				 const struct dso *b)
 {
-	int rc = strcmp(short_name, b->short_name);
-	return rc ?: dso_id__cmp(id, &b->id);
+	int rc = strcmp(short_name, dso__short_name(b));
+	return rc ?: dso_id__cmp(id, dso__id_const(b));
 }
 
-static int dso__cmp_short_name(struct dso *a, struct dso *b)
+static int dsos__cmp_long_name_id_short_name(const void *va, const void *vb)
 {
-	return __dso__cmp_short_name(a->short_name, &a->id, b);
+	const struct dso *a = *((const struct dso **)va);
+	const struct dso *b = *((const struct dso **)vb);
+	int rc = strcmp(dso__long_name(a), dso__long_name(b));
+
+	if (!rc) {
+		rc = dso_id__cmp(dso__id_const(a), dso__id_const(b));
+		if (!rc)
+			rc = strcmp(dso__short_name(a), dso__short_name(b));
+	}
+	return rc;
+}
+
+struct dsos__key {
+	const char *long_name;
+	const struct dso_id *id;
+};
+
+static int dsos__cmp_key_long_name_id(const void *vkey, const void *vdso)
+{
+	const struct dsos__key *key = vkey;
+	const struct dso *dso = *((const struct dso **)vdso);
+
+	return __dso__cmp_long_name(key->long_name, key->id, dso);
 }
 
 /*
@@ -128,110 +153,137 @@ static int dso__cmp_short_name(struct dso *a, struct dso *b)
  * Either one of the dso or name parameter must be non-NULL or the
  * function will not work.
  */
-struct dso *__dsos__findnew_link_by_longname_id(struct rb_root *root, struct dso *dso,
-						const char *name, struct dso_id *id)
+static struct dso *__dsos__find_by_longname_id(struct dsos *dsos,
+					       const char *name,
+					       struct dso_id *id,
+					       bool write_locked)
 {
-	struct rb_node **p = &root->rb_node;
-	struct rb_node  *parent = NULL;
-
-	if (!name)
-		name = dso->long_name;
-	/*
-	 * Find node with the matching name
-	 */
-	while (*p) {
-		struct dso *this = rb_entry(*p, struct dso, rb_node);
-		int rc = __dso__cmp_long_name(name, id, this);
-
-		parent = *p;
-		if (rc == 0) {
-			/*
-			 * In case the new DSO is a duplicate of an existing
-			 * one, print a one-time warning & put the new entry
-			 * at the end of the list of duplicates.
-			 */
-			if (!dso || (dso == this))
-				return this;	/* Find matching dso */
-			/*
-			 * The core kernel DSOs may have duplicated long name.
-			 * In this case, the short name should be different.
-			 * Comparing the short names to differentiate the DSOs.
-			 */
-			rc = dso__cmp_short_name(dso, this);
-			if (rc == 0) {
-				pr_err("Duplicated dso name: %s\n", name);
-				return NULL;
-			}
+	struct dsos__key key = {
+		.long_name = name,
+		.id = id,
+	};
+	struct dso **res;
+
+	if (!dsos->sorted) {
+		if (!write_locked) {
+			struct dso *dso;
+
+			up_read(&dsos->lock);
+			down_write(&dsos->lock);
+			dso = __dsos__find_by_longname_id(dsos, name, id,
+							  /*write_locked=*/true);
+			up_write(&dsos->lock);
+			down_read(&dsos->lock);
+			return dso;
 		}
-		if (rc < 0)
-			p = &parent->rb_left;
-		else
-			p = &parent->rb_right;
+		qsort(dsos->dsos, dsos->cnt, sizeof(struct dso *),
+		      dsos__cmp_long_name_id_short_name);
+		dsos->sorted = true;
 	}
-	if (dso) {
-		/* Add new node and rebalance tree */
-		rb_link_node(&dso->rb_node, parent, p);
-		rb_insert_color(&dso->rb_node, root);
-		dso->root = root;
-	}
-	return NULL;
+
+	res = bsearch(&key, dsos->dsos, dsos->cnt, sizeof(struct dso *),
+		      dsos__cmp_key_long_name_id);
+	if (!res)
+		return NULL;
+
+	return dso__get(*res);
 }
 
-void __dsos__add(struct dsos *dsos, struct dso *dso)
+int __dsos__add(struct dsos *dsos, struct dso *dso)
 {
-	list_add_tail(&dso->node, &dsos->head);
-	__dsos__findnew_link_by_longname_id(&dsos->root, dso, NULL, &dso->id);
-	/*
-	 * It is now in the linked list, grab a reference, then garbage collect
-	 * this when needing memory, by looking at LRU dso instances in the
-	 * list with atomic_read(&dso->refcnt) == 1, i.e. no references
-	 * anywhere besides the one for the list, do, under a lock for the
-	 * list: remove it from the list, then a dso__put(), that probably will
-	 * be the last and will then call dso__delete(), end of life.
-	 *
-	 * That, or at the end of the 'struct machine' lifetime, when all
-	 * 'struct dso' instances will be removed from the list, in
-	 * dsos__exit(), if they have no other reference from some other data
-	 * structure.
-	 *
-	 * E.g.: after processing a 'perf.data' file and storing references
-	 * to objects instantiated while processing events, we will have
-	 * references to the 'thread', 'map', 'dso' structs all from 'struct
-	 * hist_entry' instances, but we may not need anything not referenced,
-	 * so we might as well call machines__exit()/machines__delete() and
-	 * garbage collect it.
-	 */
-	dso__get(dso);
+	if (dsos->cnt == dsos->allocated) {
+		unsigned int to_allocate = 2;
+		struct dso **temp;
+
+		if (dsos->allocated > 0)
+			to_allocate = dsos->allocated * 2;
+		temp = realloc(dsos->dsos, sizeof(struct dso *) * to_allocate);
+		if (!temp)
+			return -ENOMEM;
+		dsos->dsos = temp;
+		dsos->allocated = to_allocate;
+	}
+	if (!dsos->sorted) {
+		dsos->dsos[dsos->cnt++] = dso__get(dso);
+	} else {
+		int low = 0, high = dsos->cnt - 1;
+		int insert = dsos->cnt; /* Default to inserting at the end. */
+
+		while (low <= high) {
+			int mid = low + (high - low) / 2;
+			int cmp = dsos__cmp_long_name_id_short_name(&dsos->dsos[mid], &dso);
+
+			if (cmp < 0) {
+				low = mid + 1;
+			} else {
+				high = mid - 1;
+				insert = mid;
+			}
+		}
+		memmove(&dsos->dsos[insert + 1], &dsos->dsos[insert],
+			(dsos->cnt - insert) * sizeof(struct dso *));
+		dsos->cnt++;
+		dsos->dsos[insert] = dso__get(dso);
+	}
+	dso__set_dsos(dso, dsos);
+	return 0;
 }
 
-void dsos__add(struct dsos *dsos, struct dso *dso)
+int dsos__add(struct dsos *dsos, struct dso *dso)
 {
+	int ret;
+
 	down_write(&dsos->lock);
-	__dsos__add(dsos, dso);
+	ret = __dsos__add(dsos, dso);
 	up_write(&dsos->lock);
+	return ret;
 }
 
-static struct dso *__dsos__findnew_by_longname_id(struct rb_root *root, const char *name, struct dso_id *id)
+struct dsos__find_id_cb_args {
+	const char *name;
+	struct dso_id *id;
+	struct dso *res;
+};
+
+static int dsos__find_id_cb(struct dso *dso, void *data)
 {
-	return __dsos__findnew_link_by_longname_id(root, NULL, name, id);
+	struct dsos__find_id_cb_args *args = data;
+
+	if (__dso__cmp_short_name(args->name, args->id, dso) == 0) {
+		args->res = dso__get(dso);
+		return 1;
+	}
+	return 0;
+
 }
 
-static struct dso *__dsos__find_id(struct dsos *dsos, const char *name, struct dso_id *id, bool cmp_short)
+static struct dso *__dsos__find_id(struct dsos *dsos, const char *name, struct dso_id *id,
+				   bool cmp_short, bool write_locked)
 {
-	struct dso *pos;
+	struct dso *res;
 
 	if (cmp_short) {
-		list_for_each_entry(pos, &dsos->head, node)
-			if (__dso__cmp_short_name(name, id, pos) == 0)
-				return pos;
-		return NULL;
+		struct dsos__find_id_cb_args args = {
+			.name = name,
+			.id = id,
+			.res = NULL,
+		};
+
+		__dsos__for_each_dso(dsos, dsos__find_id_cb, &args);
+		return args.res;
 	}
-	return __dsos__findnew_by_longname_id(&dsos->root, name, id);
+	res = __dsos__find_by_longname_id(dsos, name, id, write_locked);
+	return res;
 }
 
-struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
 {
-	return __dsos__find_id(dsos, name, NULL, cmp_short);
+	struct dso *res;
+
+	down_read(&dsos->lock);
+	res = __dsos__find_id(dsos, name, NULL, cmp_short, /*write_locked=*/false);
+	up_read(&dsos->lock);
+	return res;
 }
 
 static void dso__set_basename(struct dso *dso)
@@ -239,7 +291,7 @@ static void dso__set_basename(struct dso *dso)
 	char *base, *lname;
 	int tid;
 
-	if (sscanf(dso->long_name, "/tmp/perf-%d.map", &tid) == 1) {
+	if (sscanf(dso__long_name(dso), "/tmp/perf-%d.map", &tid) == 1) {
 		if (asprintf(&base, "[JIT] tid %d", tid) < 0)
 			return;
 	} else {
@@ -247,7 +299,7 @@ static void dso__set_basename(struct dso *dso)
 	       * basename() may modify path buffer, so we must pass
                * a copy.
                */
-		lname = strdup(dso->long_name);
+		lname = strdup(dso__long_name(dso));
 		if (!lname)
 			return;
 
@@ -271,25 +323,23 @@ static struct dso *__dsos__addnew_id(struct dsos *dsos, const char *name, struct
 	struct dso *dso = dso__new_id(name, id);
 
 	if (dso != NULL) {
-		__dsos__add(dsos, dso);
+		/*
+		 * The dsos lock is held on entry, so rename the dso before
+		 * adding it to avoid needing to take the dsos lock again to say
+		 * the array isn't sorted.
+		 */
 		dso__set_basename(dso);
-		/* Put dso here because __dsos_add already got it */
-		dso__put(dso);
+		__dsos__add(dsos, dso);
 	}
 	return dso;
 }
 
-struct dso *__dsos__addnew(struct dsos *dsos, const char *name)
-{
-	return __dsos__addnew_id(dsos, name, NULL);
-}
-
 static struct dso *__dsos__findnew_id(struct dsos *dsos, const char *name, struct dso_id *id)
 {
-	struct dso *dso = __dsos__find_id(dsos, name, id, false);
+	struct dso *dso = __dsos__find_id(dsos, name, id, false, /*write_locked=*/true);
 
-	if (dso && dso_id__empty(&dso->id) && !dso_id__empty(id))
-		dso__inject_id(dso, id);
+	if (dso && dso_id__empty(dso__id(dso)) && !dso_id__empty(id))
+		__dso__inject_id(dso, id);
 
 	return dso ? dso : __dsos__addnew_id(dsos, name, id);
 }
@@ -298,36 +348,151 @@ struct dso *dsos__findnew_id(struct dsos *dsos, const char *name, struct dso_id
 {
 	struct dso *dso;
 	down_write(&dsos->lock);
-	dso = dso__get(__dsos__findnew_id(dsos, name, id));
+	dso = __dsos__findnew_id(dsos, name, id);
 	up_write(&dsos->lock);
 	return dso;
 }
 
-size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
-			       bool (skip)(struct dso *dso, int parm), int parm)
+struct dsos__fprintf_buildid_cb_args {
+	FILE *fp;
+	bool (*skip)(struct dso *dso, int parm);
+	int parm;
+	size_t ret;
+};
+
+static int dsos__fprintf_buildid_cb(struct dso *dso, void *data)
 {
-	struct dso *pos;
-	size_t ret = 0;
+	struct dsos__fprintf_buildid_cb_args *args = data;
+	char sbuild_id[SBUILD_ID_SIZE];
 
-	list_for_each_entry(pos, head, node) {
-		char sbuild_id[SBUILD_ID_SIZE];
+	if (args->skip && args->skip(dso, args->parm))
+		return 0;
+	build_id__sprintf(dso__bid(dso), sbuild_id);
+	args->ret += fprintf(args->fp, "%-40s %s\n", sbuild_id, dso__long_name(dso));
+	return 0;
+}
 
-		if (skip && skip(pos, parm))
-			continue;
-		build_id__sprintf(&pos->bid, sbuild_id);
-		ret += fprintf(fp, "%-40s %s\n", sbuild_id, pos->long_name);
-	}
-	return ret;
+size_t dsos__fprintf_buildid(struct dsos *dsos, FILE *fp,
+			       bool (*skip)(struct dso *dso, int parm), int parm)
+{
+	struct dsos__fprintf_buildid_cb_args args = {
+		.fp = fp,
+		.skip = skip,
+		.parm = parm,
+		.ret = 0,
+	};
+
+	dsos__for_each_dso(dsos, dsos__fprintf_buildid_cb, &args);
+	return args.ret;
+}
+
+struct dsos__fprintf_cb_args {
+	FILE *fp;
+	size_t ret;
+};
+
+static int dsos__fprintf_cb(struct dso *dso, void *data)
+{
+	struct dsos__fprintf_cb_args *args = data;
+
+	args->ret += dso__fprintf(dso, args->fp);
+	return 0;
+}
+
+size_t dsos__fprintf(struct dsos *dsos, FILE *fp)
+{
+	struct dsos__fprintf_cb_args args = {
+		.fp = fp,
+		.ret = 0,
+	};
+
+	dsos__for_each_dso(dsos, dsos__fprintf_cb, &args);
+	return args.ret;
+}
+
+static int dsos__hit_all_cb(struct dso *dso, void *data __maybe_unused)
+{
+	dso__set_hit(dso);
+	return 0;
 }
 
-size_t __dsos__fprintf(struct list_head *head, FILE *fp)
+int dsos__hit_all(struct dsos *dsos)
 {
-	struct dso *pos;
-	size_t ret = 0;
+	return dsos__for_each_dso(dsos, dsos__hit_all_cb, NULL);
+}
 
-	list_for_each_entry(pos, head, node) {
-		ret += dso__fprintf(pos, fp);
+struct dso *dsos__findnew_module_dso(struct dsos *dsos,
+				     struct machine *machine,
+				     struct kmod_path *m,
+				     const char *filename)
+{
+	struct dso *dso;
+
+	down_write(&dsos->lock);
+
+	dso = __dsos__find_id(dsos, m->name, NULL, /*cmp_short=*/true, /*write_locked=*/true);
+	if (dso) {
+		up_write(&dsos->lock);
+		return dso;
+	}
+	/*
+	 * Failed to find the dso so create it. Change the name before adding it
+	 * to the array, to avoid unnecessary sorts and potential locking
+	 * issues.
+	 */
+	dso = dso__new_id(m->name, /*id=*/NULL);
+	if (!dso) {
+		up_write(&dsos->lock);
+		return NULL;
 	}
+	dso__set_basename(dso);
+	dso__set_module_info(dso, m, machine);
+	dso__set_long_name(dso,	strdup(filename), true);
+	dso__set_kernel(dso, DSO_SPACE__KERNEL);
+	__dsos__add(dsos, dso);
 
-	return ret;
+	up_write(&dsos->lock);
+	return dso;
+}
+
+static int dsos__find_kernel_dso_cb(struct dso *dso, void *data)
+{
+	struct dso **res = data;
+	/*
+	 * The cpumode passed to is_kernel_module is not the cpumode of *this*
+	 * event. If we insist on passing correct cpumode to is_kernel_module,
+	 * we should record the cpumode when we adding this dso to the linked
+	 * list.
+	 *
+	 * However we don't really need passing correct cpumode.  We know the
+	 * correct cpumode must be kernel mode (if not, we should not link it
+	 * onto kernel_dsos list).
+	 *
+	 * Therefore, we pass PERF_RECORD_MISC_CPUMODE_UNKNOWN.
+	 * is_kernel_module() treats it as a kernel cpumode.
+	 */
+	if (!dso__kernel(dso) ||
+	    is_kernel_module(dso__long_name(dso), PERF_RECORD_MISC_CPUMODE_UNKNOWN))
+		return 0;
+
+	*res = dso__get(dso);
+	return 1;
+}
+
+struct dso *dsos__find_kernel_dso(struct dsos *dsos)
+{
+	struct dso *res = NULL;
+
+	dsos__for_each_dso(dsos, dsos__find_kernel_dso_cb, &res);
+	return res;
+}
+
+int dsos__for_each_dso(struct dsos *dsos, int (*cb)(struct dso *dso, void *data), void *data)
+{
+	int err;
+
+	down_read(&dsos->lock);
+	err = __dsos__for_each_dso(dsos, cb, data);
+	up_read(&dsos->lock);
+	return err;
 }
diff --git a/tools/perf/util/dsos.h b/tools/perf/util/dsos.h
index 5dbec2bc69..6c13b65648 100644
--- a/tools/perf/util/dsos.h
+++ b/tools/perf/util/dsos.h
@@ -10,31 +10,43 @@
 
 struct dso;
 struct dso_id;
+struct kmod_path;
+struct machine;
 
 /*
- * DSOs are put into both a list for fast iteration and rbtree for fast
- * long name lookup.
+ * Collection of DSOs as an array for iteration speed, but sorted for O(n)
+ * lookup.
  */
 struct dsos {
-	struct list_head    head;
-	struct rb_root	    root;	/* rbtree root sorted by long name */
 	struct rw_semaphore lock;
+	struct dso **dsos;
+	unsigned int cnt;
+	unsigned int allocated;
+	bool sorted;
 };
 
-void __dsos__add(struct dsos *dsos, struct dso *dso);
-void dsos__add(struct dsos *dsos, struct dso *dso);
-struct dso *__dsos__addnew(struct dsos *dsos, const char *name);
-struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
+void dsos__init(struct dsos *dsos);
+void dsos__exit(struct dsos *dsos);
+
+int __dsos__add(struct dsos *dsos, struct dso *dso);
+int dsos__add(struct dsos *dsos, struct dso *dso);
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
 
 struct dso *dsos__findnew_id(struct dsos *dsos, const char *name, struct dso_id *id);
  
-struct dso *__dsos__findnew_link_by_longname_id(struct rb_root *root, struct dso *dso,
-						const char *name, struct dso_id *id);
-
-bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
+bool dsos__read_build_ids(struct dsos *dsos, bool with_hits);
 
-size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
+size_t dsos__fprintf_buildid(struct dsos *dsos, FILE *fp,
 			       bool (skip)(struct dso *dso, int parm), int parm);
-size_t __dsos__fprintf(struct list_head *head, FILE *fp);
+size_t dsos__fprintf(struct dsos *dsos, FILE *fp);
+
+int dsos__hit_all(struct dsos *dsos);
+
+struct dso *dsos__findnew_module_dso(struct dsos *dsos, struct machine *machine,
+				     struct kmod_path *m, const char *filename);
+
+struct dso *dsos__find_kernel_dso(struct dsos *dsos);
+
+int dsos__for_each_dso(struct dsos *dsos, int (*cb)(struct dso *dso, void *data), void *data);
 
 #endif /* __PERF_DSOS */
diff --git a/tools/perf/util/dump-insn.h b/tools/perf/util/dump-insn.h
index 6501250615..4a7797dd6d 100644
--- a/tools/perf/util/dump-insn.h
+++ b/tools/perf/util/dump-insn.h
@@ -11,6 +11,7 @@ struct thread;
 struct perf_insn {
 	/* Initialized by callers: */
 	struct thread *thread;
+	struct machine *machine;
 	u8	      cpumode;
 	bool	      is64bit;
 	int	      cpu;
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index f93e57e2fc..44ef968a7a 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -9,6 +9,7 @@
 #include <stdlib.h>
 #include "debug.h"
 #include "dwarf-aux.h"
+#include "dwarf-regs.h"
 #include "strbuf.h"
 #include "string2.h"
 
@@ -696,6 +697,49 @@ Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 	return die_mem;
 }
 
+static int __die_find_func_rettype_cb(Dwarf_Die *die_mem, void *data)
+{
+	const char *func_name;
+
+	if (dwarf_tag(die_mem) != DW_TAG_subprogram)
+		return DIE_FIND_CB_SIBLING;
+
+	func_name = dwarf_diename(die_mem);
+	if (func_name && !strcmp(func_name, data))
+		return DIE_FIND_CB_END;
+
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_find_func_rettype - Search a return type of function
+ * @cu_die: a CU DIE
+ * @name: target function name
+ * @die_mem: a buffer for result DIE
+ *
+ * Search a non-inlined function which matches to @name and stores the
+ * return type of the function to @die_mem and returns it if found.
+ * Returns NULL if failed.  Note that it doesn't needs to find a
+ * definition of the function, so it doesn't match with address.
+ * Most likely, it can find a declaration at the top level.  Thus the
+ * callback function continues to sibling entries only.
+ */
+Dwarf_Die *die_find_func_rettype(Dwarf_Die *cu_die, const char *name,
+				 Dwarf_Die *die_mem)
+{
+	Dwarf_Die tmp_die;
+
+	cu_die = die_find_child(cu_die, __die_find_func_rettype_cb,
+				(void *)name, &tmp_die);
+	if (!cu_die)
+		return NULL;
+
+	if (die_get_real_type(&tmp_die, die_mem) == NULL)
+		return NULL;
+
+	return die_mem;
+}
+
 struct __instance_walk_param {
 	void    *addr;
 	int	(*callback)(Dwarf_Die *, void *);
@@ -1066,8 +1110,10 @@ int die_get_typename_from_type(Dwarf_Die *type_die, struct strbuf *buf)
 	const char *tmp = "";
 
 	tag = dwarf_tag(type_die);
-	if (tag == DW_TAG_array_type || tag == DW_TAG_pointer_type)
+	if (tag == DW_TAG_pointer_type)
 		tmp = "*";
+	else if (tag == DW_TAG_array_type)
+		tmp = "[]";
 	else if (tag == DW_TAG_subroutine_type) {
 		/* Function pointer */
 		return strbuf_add(buf, "(function_type)", 15);
@@ -1147,6 +1193,8 @@ static int reg_from_dwarf_op(Dwarf_Op *op)
 	case DW_OP_regx:
 	case DW_OP_bregx:
 		return op->number;
+	case DW_OP_fbreg:
+		return DWARF_REG_FB;
 	default:
 		break;
 	}
@@ -1160,6 +1208,7 @@ static int offset_from_dwarf_op(Dwarf_Op *op)
 	case DW_OP_regx:
 		return 0;
 	case DW_OP_breg0 ... DW_OP_breg31:
+	case DW_OP_fbreg:
 		return op->number;
 	case DW_OP_bregx:
 		return op->number2;
@@ -1353,6 +1402,9 @@ static bool match_var_offset(Dwarf_Die *die_mem, struct find_var_data *data,
 		return true;
 	}
 
+	if (addr_offset < addr_type)
+		return false;
+
 	if (die_get_real_type(die_mem, &type_die) == NULL)
 		return false;
 
@@ -1399,7 +1451,6 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
 
 		/* Local variables accessed using frame base register */
 		if (data->is_fbreg && ops->atom == DW_OP_fbreg &&
-		    data->offset >= (int)ops->number &&
 		    check_allowed_ops(ops, nops) &&
 		    match_var_offset(die_mem, data, data->offset, ops->number,
 				     /*is_pointer=*/false))
@@ -1490,9 +1541,6 @@ static int __die_find_var_addr_cb(Dwarf_Die *die_mem, void *arg)
 		if (ops->atom != DW_OP_addr)
 			continue;
 
-		if (data->addr < ops->number)
-			continue;
-
 		if (check_allowed_ops(ops, nops) &&
 		    match_var_offset(die_mem, data, data->addr, ops->number,
 				     /*is_pointer=*/false))
@@ -1504,7 +1552,6 @@ static int __die_find_var_addr_cb(Dwarf_Die *die_mem, void *arg)
 /**
  * die_find_variable_by_addr - Find variable located at given address
  * @sc_die: a scope DIE
- * @pc: the program address to find
  * @addr: the data address to find
  * @die_mem: a buffer to save the resulting DIE
  * @offset: the offset in the resulting type
@@ -1512,12 +1559,10 @@ static int __die_find_var_addr_cb(Dwarf_Die *die_mem, void *arg)
  * Find the variable DIE located at the given address (in PC-relative mode).
  * This is usually for global variables.
  */
-Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc,
-				     Dwarf_Addr addr, Dwarf_Die *die_mem,
-				     int *offset)
+Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr addr,
+				     Dwarf_Die *die_mem, int *offset)
 {
 	struct find_var_data data = {
-		.pc = pc,
 		.addr = addr,
 	};
 	Dwarf_Die *result;
@@ -1587,6 +1632,68 @@ void die_collect_vars(Dwarf_Die *sc_die, struct die_var_type **var_types)
 
 	die_find_child(sc_die, __die_collect_vars_cb, (void *)var_types, &die_mem);
 }
+
+static int __die_collect_global_vars_cb(Dwarf_Die *die_mem, void *arg)
+{
+	struct die_var_type **var_types = arg;
+	Dwarf_Die type_die;
+	int tag = dwarf_tag(die_mem);
+	Dwarf_Attribute attr;
+	Dwarf_Addr base, start, end;
+	Dwarf_Op *ops;
+	size_t nops;
+	struct die_var_type *vt;
+
+	if (tag != DW_TAG_variable)
+		return DIE_FIND_CB_SIBLING;
+
+	if (dwarf_attr(die_mem, DW_AT_location, &attr) == NULL)
+		return DIE_FIND_CB_SIBLING;
+
+	/* Only collect the location with an absolute address. */
+	if (dwarf_getlocations(&attr, 0, &base, &start, &end, &ops, &nops) <= 0)
+		return DIE_FIND_CB_SIBLING;
+
+	if (ops->atom != DW_OP_addr)
+		return DIE_FIND_CB_SIBLING;
+
+	if (!check_allowed_ops(ops, nops))
+		return DIE_FIND_CB_SIBLING;
+
+	if (die_get_real_type(die_mem, &type_die) == NULL)
+		return DIE_FIND_CB_SIBLING;
+
+	vt = malloc(sizeof(*vt));
+	if (vt == NULL)
+		return DIE_FIND_CB_END;
+
+	vt->die_off = dwarf_dieoffset(&type_die);
+	vt->addr = ops->number;
+	vt->reg = -1;
+	vt->offset = 0;
+	vt->next = *var_types;
+	*var_types = vt;
+
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_collect_global_vars - Save all global variables
+ * @cu_die: a CU DIE
+ * @var_types: a pointer to save the resulting list
+ *
+ * Save all global variables in the @cu_die and save them to @var_types.
+ * The @var_types is a singly-linked list containing type and location info.
+ * Actual type can be retrieved using dwarf_offdie() with 'die_off' later.
+ *
+ * Callers should free @var_types.
+ */
+void die_collect_global_vars(Dwarf_Die *cu_die, struct die_var_type **var_types)
+{
+	Dwarf_Die die_mem;
+
+	die_find_child(cu_die, __die_collect_global_vars_cb, (void *)var_types, &die_mem);
+}
 #endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
 #ifdef HAVE_DWARF_CFI_SUPPORT
@@ -1855,3 +1962,116 @@ int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes)
 	*scopes = data.scopes;
 	return data.nr;
 }
+
+static int __die_find_member_offset_cb(Dwarf_Die *die_mem, void *arg)
+{
+	Dwarf_Die type_die;
+	Dwarf_Word size, loc;
+	Dwarf_Word offset = (long)arg;
+	int tag = dwarf_tag(die_mem);
+
+	if (tag != DW_TAG_member)
+		return DIE_FIND_CB_SIBLING;
+
+	/* Unions might not have location */
+	if (die_get_data_member_location(die_mem, &loc) < 0)
+		loc = 0;
+
+	if (offset == loc)
+		return DIE_FIND_CB_END;
+
+	if (die_get_real_type(die_mem, &type_die) == NULL) {
+		// TODO: add a pr_debug_dtp() later for this unlikely failure
+		return DIE_FIND_CB_SIBLING;
+	}
+
+	if (dwarf_aggregate_size(&type_die, &size) < 0)
+		size = 0;
+
+	if (loc < offset && offset < (loc + size))
+		return DIE_FIND_CB_END;
+
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_get_member_type - Return type info of struct member
+ * @type_die: a type DIE
+ * @offset: offset in the type
+ * @die_mem: a buffer to save the resulting DIE
+ *
+ * This function returns a type of a member in @type_die where it's located at
+ * @offset if it's a struct.  For now, it just returns the first matching
+ * member in a union.  For other types, it'd return the given type directly
+ * if it's within the size of the type or NULL otherwise.
+ */
+Dwarf_Die *die_get_member_type(Dwarf_Die *type_die, int offset,
+			       Dwarf_Die *die_mem)
+{
+	Dwarf_Die *member;
+	Dwarf_Die mb_type;
+	int tag;
+
+	tag = dwarf_tag(type_die);
+	/* If it's not a compound type, return the type directly */
+	if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) {
+		Dwarf_Word size;
+
+		if (dwarf_aggregate_size(type_die, &size) < 0)
+			size = 0;
+
+		if ((unsigned)offset >= size)
+			return NULL;
+
+		*die_mem = *type_die;
+		return die_mem;
+	}
+
+	mb_type = *type_die;
+	/* TODO: Handle union types better? */
+	while (tag == DW_TAG_structure_type || tag == DW_TAG_union_type) {
+		member = die_find_child(&mb_type, __die_find_member_offset_cb,
+					(void *)(long)offset, die_mem);
+		if (member == NULL)
+			return NULL;
+
+		if (die_get_real_type(member, &mb_type) == NULL)
+			return NULL;
+
+		tag = dwarf_tag(&mb_type);
+
+		if (tag == DW_TAG_structure_type || tag == DW_TAG_union_type) {
+			Dwarf_Word loc;
+
+			/* Update offset for the start of the member struct */
+			if (die_get_data_member_location(member, &loc) == 0)
+				offset -= loc;
+		}
+	}
+	*die_mem = mb_type;
+	return die_mem;
+}
+
+/**
+ * die_deref_ptr_type - Return type info for pointer access
+ * @ptr_die: a pointer type DIE
+ * @offset: access offset for the pointer
+ * @die_mem: a buffer to save the resulting DIE
+ *
+ * This function follows the pointer in @ptr_die with given @offset
+ * and saves the resulting type in @die_mem.  If the pointer points
+ * a struct type, actual member at the offset would be returned.
+ */
+Dwarf_Die *die_deref_ptr_type(Dwarf_Die *ptr_die, int offset,
+			      Dwarf_Die *die_mem)
+{
+	Dwarf_Die type_die;
+
+	if (dwarf_tag(ptr_die) != DW_TAG_pointer_type)
+		return NULL;
+
+	if (die_get_real_type(ptr_die, &type_die) == NULL)
+		return NULL;
+
+	return die_get_member_type(&type_die, offset, die_mem);
+}
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index efafd3a1f5..24446412b8 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -94,6 +94,10 @@ Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 			       Dwarf_Die *die_mem);
 
+/* Search a non-inlined function by name and returns its return type */
+Dwarf_Die *die_find_func_rettype(Dwarf_Die *sp_die, const char *name,
+				 Dwarf_Die *die_mem);
+
 /* Walk on the instances of given DIE */
 int die_walk_instances(Dwarf_Die *in_die,
 		       int (*callback)(Dwarf_Die *, void *), void *data);
@@ -144,6 +148,12 @@ struct die_var_type {
 	int offset;
 };
 
+/* Return type info of a member at offset */
+Dwarf_Die *die_get_member_type(Dwarf_Die *type_die, int offset, Dwarf_Die *die_mem);
+
+/* Return type info where the pointer and offset point to */
+Dwarf_Die *die_deref_ptr_type(Dwarf_Die *ptr_die, int offset, Dwarf_Die *die_mem);
+
 #ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
 
 /* Get byte offset range of given variable DIE */
@@ -155,13 +165,15 @@ Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg,
 				    Dwarf_Die *die_mem);
 
 /* Find a (global) variable located in the 'addr' */
-Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc,
-				     Dwarf_Addr addr, Dwarf_Die *die_mem,
-				     int *offset);
+Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr addr,
+				     Dwarf_Die *die_mem, int *offset);
 
 /* Save all variables and parameters in this scope */
 void die_collect_vars(Dwarf_Die *sc_die, struct die_var_type **var_types);
 
+/* Save all global variables in this CU */
+void die_collect_global_vars(Dwarf_Die *cu_die, struct die_var_type **var_types);
+
 #else /*  HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
 static inline int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
@@ -182,7 +194,6 @@ static inline Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die __maybe_unus
 }
 
 static inline Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die __maybe_unused,
-						   Dwarf_Addr pc __maybe_unused,
 						   Dwarf_Addr addr __maybe_unused,
 						   Dwarf_Die *die_mem __maybe_unused,
 						   int *offset __maybe_unused)
@@ -195,6 +206,11 @@ static inline void die_collect_vars(Dwarf_Die *sc_die __maybe_unused,
 {
 }
 
+static inline void die_collect_global_vars(Dwarf_Die *cu_die __maybe_unused,
+					   struct die_var_type **var_types __maybe_unused)
+{
+}
+
 #endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
 #ifdef HAVE_DWARF_CFI_SUPPORT
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 198903157f..f32f9abf63 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -726,7 +726,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
 	dso = al->map ? map__dso(al->map) : NULL;
 	dump_printf(" ...... dso: %s\n",
 		dso
-		? dso->long_name
+		? dso__long_name(dso)
 		: (al->level == 'H' ? "[hypervisor]" : "<not found>"));
 
 	if (thread__is_filtered(thread))
@@ -750,10 +750,10 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
 	if (al->map) {
 		if (symbol_conf.dso_list &&
 		    (!dso || !(strlist__has_entry(symbol_conf.dso_list,
-						  dso->short_name) ||
-			       (dso->short_name != dso->long_name &&
+						  dso__short_name(dso)) ||
+			       (dso__short_name(dso) != dso__long_name(dso) &&
 				strlist__has_entry(symbol_conf.dso_list,
-						   dso->long_name))))) {
+						   dso__long_name(dso)))))) {
 			al->filtered |= (1 << HIST_FILTER__DSO);
 		}
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 55a300a097..3a719edafc 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -298,7 +298,8 @@ struct evsel *evlist__add_aux_dummy(struct evlist *evlist, bool system_wide)
 #ifdef HAVE_LIBTRACEEVENT
 struct evsel *evlist__add_sched_switch(struct evlist *evlist, bool system_wide)
 {
-	struct evsel *evsel = evsel__newtp_idx("sched", "sched_switch", 0);
+	struct evsel *evsel = evsel__newtp_idx("sched", "sched_switch", 0,
+					       /*format=*/true);
 
 	if (IS_ERR(evsel))
 		return evsel;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 3536404e94..4f818ab6b6 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -452,7 +452,7 @@ out_err:
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
 #ifdef HAVE_LIBTRACEEVENT
-struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx)
+struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx, bool format)
 {
 	struct evsel *evsel = zalloc(perf_evsel__object.size);
 	int err = -ENOMEM;
@@ -469,14 +469,20 @@ struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx)
 		if (asprintf(&evsel->name, "%s:%s", sys, name) < 0)
 			goto out_free;
 
-		evsel->tp_format = trace_event__tp_format(sys, name);
-		if (IS_ERR(evsel->tp_format)) {
-			err = PTR_ERR(evsel->tp_format);
-			goto out_free;
+		event_attr_init(&attr);
+
+		if (format) {
+			evsel->tp_format = trace_event__tp_format(sys, name);
+			if (IS_ERR(evsel->tp_format)) {
+				err = PTR_ERR(evsel->tp_format);
+				goto out_free;
+			}
+			attr.config = evsel->tp_format->id;
+		} else {
+			attr.config = (__u64) -1;
 		}
 
-		event_attr_init(&attr);
-		attr.config = evsel->tp_format->id;
+
 		attr.sample_period = 1;
 		evsel__init(evsel, &attr, idx);
 	}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 517cff431d..375a38e15c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -234,14 +234,14 @@ void free_config_terms(struct list_head *config_terms);
 
 
 #ifdef HAVE_LIBTRACEEVENT
-struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx);
+struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx, bool format);
 
 /*
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
 static inline struct evsel *evsel__newtp(const char *sys, const char *name)
 {
-	return evsel__newtp_idx(sys, name, 0);
+	return evsel__newtp_idx(sys, name, 0, true);
 }
 #endif
 
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index 5f18d20ea9..4e2e4f40e1 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -43,6 +43,9 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
 #elif defined(__riscv) && __riscv_xlen == 64
 #define GEN_ELF_ARCH	EM_RISCV
 #define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__riscv) && __riscv_xlen == 32
+#define GEN_ELF_ARCH	EM_RISCV
+#define GEN_ELF_CLASS	ELFCLASS32
 #elif defined(__loongarch__)
 #define GEN_ELF_ARCH	EM_LOONGARCH
 #define GEN_ELF_CLASS	ELFCLASS64
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 3fe28edc3d..55e9553861 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2308,7 +2308,7 @@ static int __event_process_build_id(struct perf_record_header_build_id *bev,
 
 		build_id__init(&bid, bev->data, size);
 		dso__set_build_id(dso, &bid);
-		dso->header_build_id = 1;
+		dso__set_header_build_id(dso, true);
 
 		if (dso_space != DSO_SPACE__USER) {
 			struct kmod_path m = { .name = NULL, };
@@ -2316,13 +2316,13 @@ static int __event_process_build_id(struct perf_record_header_build_id *bev,
 			if (!kmod_path__parse_name(&m, filename) && m.kmod)
 				dso__set_module_info(dso, &m, machine);
 
-			dso->kernel = dso_space;
+			dso__set_kernel(dso, dso_space);
 			free(m.name);
 		}
 
-		build_id__sprintf(&dso->bid, sbuild_id);
+		build_id__sprintf(dso__bid(dso), sbuild_id);
 		pr_debug("build id event received for %s: %s [%zu]\n",
-			 dso->long_name, sbuild_id, size);
+			 dso__long_name(dso), sbuild_id, size);
 		dso__put(dso);
 	}
 
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index eab99ea6ac..a0a46e34f8 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -52,46 +52,48 @@ static int add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
 	return 0;
 }
 
-const char *help_unknown_cmd(const char *cmd)
+const char *help_unknown_cmd(const char *cmd, struct cmdnames *main_cmds)
 {
 	unsigned int i, n = 0, best_similarity = 0;
-	struct cmdnames main_cmds, other_cmds;
+	struct cmdnames other_cmds;
 
-	memset(&main_cmds, 0, sizeof(main_cmds));
-	memset(&other_cmds, 0, sizeof(main_cmds));
+	memset(&other_cmds, 0, sizeof(other_cmds));
 
 	perf_config(perf_unknown_cmd_config, NULL);
 
-	load_command_list("perf-", &main_cmds, &other_cmds);
+	load_command_list("perf-", main_cmds, &other_cmds);
 
-	if (add_cmd_list(&main_cmds, &other_cmds) < 0) {
+	if (add_cmd_list(main_cmds, &other_cmds) < 0) {
 		fprintf(stderr, "ERROR: Failed to allocate command list for unknown command.\n");
 		goto end;
 	}
-	qsort(main_cmds.names, main_cmds.cnt,
-	      sizeof(main_cmds.names), cmdname_compare);
-	uniq(&main_cmds);
+	qsort(main_cmds->names, main_cmds->cnt,
+	      sizeof(main_cmds->names), cmdname_compare);
+	uniq(main_cmds);
 
-	if (main_cmds.cnt) {
+	if (main_cmds->cnt) {
 		/* This reuses cmdname->len for similarity index */
-		for (i = 0; i < main_cmds.cnt; ++i)
-			main_cmds.names[i]->len =
-				levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4);
-
-		qsort(main_cmds.names, main_cmds.cnt,
-		      sizeof(*main_cmds.names), levenshtein_compare);
+		for (i = 0; i < main_cmds->cnt; ++i) {
+			main_cmds->names[i]->len =
+				levenshtein(cmd, main_cmds->names[i]->name,
+					/*swap_penalty=*/0,
+					/*substition_penality=*/2,
+					/*insertion_penality=*/1,
+					/*deletion_penalty=*/1);
+		}
+		qsort(main_cmds->names, main_cmds->cnt,
+		      sizeof(*main_cmds->names), levenshtein_compare);
 
-		best_similarity = main_cmds.names[0]->len;
+		best_similarity = main_cmds->names[0]->len;
 		n = 1;
-		while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len)
+		while (n < main_cmds->cnt && best_similarity == main_cmds->names[n]->len)
 			++n;
 	}
 
 	if (autocorrect && n == 1) {
-		const char *assumed = main_cmds.names[0]->name;
+		const char *assumed = main_cmds->names[0]->name;
 
-		main_cmds.names[0] = NULL;
-		clean_cmdnames(&main_cmds);
+		main_cmds->names[0] = NULL;
 		clean_cmdnames(&other_cmds);
 		fprintf(stderr, "WARNING: You called a perf program named '%s', "
 			"which does not exist.\n"
@@ -107,15 +109,14 @@ const char *help_unknown_cmd(const char *cmd)
 
 	fprintf(stderr, "perf: '%s' is not a perf-command. See 'perf --help'.\n", cmd);
 
-	if (main_cmds.cnt && best_similarity < 6) {
+	if (main_cmds->cnt && best_similarity < 6) {
 		fprintf(stderr, "\nDid you mean %s?\n",
 			n < 2 ? "this": "one of these");
 
 		for (i = 0; i < n; i++)
-			fprintf(stderr, "\t%s\n", main_cmds.names[i]->name);
+			fprintf(stderr, "\t%s\n", main_cmds->names[i]->name);
 	}
 end:
-	clean_cmdnames(&main_cmds);
 	clean_cmdnames(&other_cmds);
-	exit(1);
+	return NULL;
 }
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index fa359180eb..2e9e193179 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -9,6 +9,7 @@
 #include "map_symbol.h"
 #include "branch.h"
 #include "mem-events.h"
+#include "mem-info.h"
 #include "session.h"
 #include "namespaces.h"
 #include "cgroup.h"
@@ -153,8 +154,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	}
 
 	if (h->mem_info) {
-		if (h->mem_info->daddr.ms.sym) {
-			symlen = (int)h->mem_info->daddr.ms.sym->namelen + 4
+		if (mem_info__daddr(h->mem_info)->ms.sym) {
+			symlen = (int)mem_info__daddr(h->mem_info)->ms.sym->namelen + 4
 			       + unresolved_col_width + 2;
 			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
 					   symlen);
@@ -168,8 +169,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 					   symlen);
 		}
 
-		if (h->mem_info->iaddr.ms.sym) {
-			symlen = (int)h->mem_info->iaddr.ms.sym->namelen + 4
+		if (mem_info__iaddr(h->mem_info)->ms.sym) {
+			symlen = (int)mem_info__iaddr(h->mem_info)->ms.sym->namelen + 4
 			       + unresolved_col_width + 2;
 			hists__new_col_len(hists, HISTC_MEM_IADDR_SYMBOL,
 					   symlen);
@@ -179,8 +180,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 					   symlen);
 		}
 
-		if (h->mem_info->daddr.ms.map) {
-			symlen = dso__name_len(map__dso(h->mem_info->daddr.ms.map));
+		if (mem_info__daddr(h->mem_info)->ms.map) {
+			symlen = dso__name_len(map__dso(mem_info__daddr(h->mem_info)->ms.map));
 			hists__new_col_len(hists, HISTC_MEM_DADDR_DSO,
 					   symlen);
 		} else {
@@ -308,6 +309,9 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
 	dest->period_us		+= src->period_us;
 	dest->period_guest_sys	+= src->period_guest_sys;
 	dest->period_guest_us	+= src->period_guest_us;
+	dest->weight1		+= src->weight1;
+	dest->weight2		+= src->weight2;
+	dest->weight3		+= src->weight3;
 	dest->nr_events		+= src->nr_events;
 }
 
@@ -315,7 +319,9 @@ static void he_stat__decay(struct he_stat *he_stat)
 {
 	he_stat->period = (he_stat->period * 7) / 8;
 	he_stat->nr_events = (he_stat->nr_events * 7) / 8;
-	/* XXX need decay for weight too? */
+	he_stat->weight1 = (he_stat->weight1 * 7) / 8;
+	he_stat->weight2 = (he_stat->weight2 * 7) / 8;
+	he_stat->weight3 = (he_stat->weight3 * 7) / 8;
 }
 
 static void hists__delete_entry(struct hists *hists, struct hist_entry *he);
@@ -470,11 +476,6 @@ static int hist_entry__init(struct hist_entry *he,
 		he->branch_info->to.ms.map = map__get(he->branch_info->to.ms.map);
 	}
 
-	if (he->mem_info) {
-		he->mem_info->iaddr.ms.map = map__get(he->mem_info->iaddr.ms.map);
-		he->mem_info->daddr.ms.map = map__get(he->mem_info->daddr.ms.map);
-	}
-
 	if (hist_entry__has_callchains(he) && symbol_conf.use_callchain)
 		callchain_init(he->callchain);
 
@@ -520,8 +521,8 @@ err_infos:
 		zfree(&he->branch_info);
 	}
 	if (he->mem_info) {
-		map_symbol__exit(&he->mem_info->iaddr.ms);
-		map_symbol__exit(&he->mem_info->daddr.ms);
+		map_symbol__exit(&mem_info__iaddr(he->mem_info)->ms);
+		map_symbol__exit(&mem_info__daddr(he->mem_info)->ms);
 	}
 err:
 	map_symbol__exit(&he->ms);
@@ -566,7 +567,6 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 			he = NULL;
 		}
 	}
-
 	return he;
 }
 
@@ -614,7 +614,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 		cmp = hist_entry__cmp(he, entry);
 		if (!cmp) {
 			if (sample_self) {
-				he_stat__add_period(&he->stat, period);
+				he_stat__add_stat(&he->stat, &entry->stat);
 				hist_entry__add_callchain_period(he, period);
 			}
 			if (symbol_conf.cumulate_callchain)
@@ -626,7 +626,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 			 */
 			mem_info__zput(entry->mem_info);
 
-			block_info__zput(entry->block_info);
+			block_info__delete(entry->block_info);
 
 			kvm_info__zput(entry->kvm_info);
 
@@ -731,12 +731,15 @@ __hists__add_entry(struct hists *hists,
 		.stat = {
 			.nr_events = 1,
 			.period	= sample->period,
+			.weight1 = sample->weight,
+			.weight2 = sample->ins_lat,
+			.weight3 = sample->p_stage_cyc,
 		},
 		.parent = sym_parent,
 		.filtered = symbol__parent_filter(sym_parent) | al->filtered,
 		.hists	= hists,
 		.branch_info = bi,
-		.mem_info = mi,
+		.mem_info = mem_info__get(mi),
 		.kvm_info = ki,
 		.block_info = block_info,
 		.transaction = sample->transaction,
@@ -825,7 +828,7 @@ iter_prepare_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
 	if (mi == NULL)
 		return -ENOMEM;
 
-	iter->priv = mi;
+	iter->mi = mi;
 	return 0;
 }
 
@@ -833,7 +836,7 @@ static int
 iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
 {
 	u64 cost;
-	struct mem_info *mi = iter->priv;
+	struct mem_info *mi = iter->mi;
 	struct hists *hists = evsel__hists(iter->evsel);
 	struct perf_sample *sample = iter->sample;
 	struct hist_entry *he;
@@ -880,12 +883,7 @@ iter_finish_mem_entry(struct hist_entry_iter *iter,
 	err = hist_entry__append_callchain(he, iter->sample);
 
 out:
-	/*
-	 * We don't need to free iter->priv (mem_info) here since the mem info
-	 * was either already freed in hists__findnew_entry() or passed to a
-	 * new hist entry by hist_entry__new().
-	 */
-	iter->priv = NULL;
+	mem_info__zput(iter->mi);
 
 	iter->he = NULL;
 	return err;
@@ -904,7 +902,7 @@ iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al
 	iter->curr = 0;
 	iter->total = sample->branch_stack->nr;
 
-	iter->priv = bi;
+	iter->bi = bi;
 	return 0;
 }
 
@@ -918,7 +916,7 @@ iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
 static int
 iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
 {
-	struct branch_info *bi = iter->priv;
+	struct branch_info *bi = iter->bi;
 	int i = iter->curr;
 
 	if (bi == NULL)
@@ -947,7 +945,7 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
 	int i = iter->curr;
 	int err = 0;
 
-	bi = iter->priv;
+	bi = iter->bi;
 
 	if (iter->hide_unresolved && !(bi[i].from.ms.sym && bi[i].to.ms.sym))
 		goto out;
@@ -976,7 +974,7 @@ static int
 iter_finish_branch_entry(struct hist_entry_iter *iter,
 			 struct addr_location *al __maybe_unused)
 {
-	zfree(&iter->priv);
+	zfree(&iter->bi);
 	iter->he = NULL;
 
 	return iter->curr >= iter->total ? 0 : -1;
@@ -1044,7 +1042,7 @@ iter_prepare_cumulative_entry(struct hist_entry_iter *iter,
 	if (he_cache == NULL)
 		return -ENOMEM;
 
-	iter->priv = he_cache;
+	iter->he_cache = he_cache;
 	iter->curr = 0;
 
 	return 0;
@@ -1057,7 +1055,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
 	struct evsel *evsel = iter->evsel;
 	struct hists *hists = evsel__hists(evsel);
 	struct perf_sample *sample = iter->sample;
-	struct hist_entry **he_cache = iter->priv;
+	struct hist_entry **he_cache = iter->he_cache;
 	struct hist_entry *he;
 	int err = 0;
 
@@ -1115,7 +1113,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 {
 	struct evsel *evsel = iter->evsel;
 	struct perf_sample *sample = iter->sample;
-	struct hist_entry **he_cache = iter->priv;
+	struct hist_entry **he_cache = iter->he_cache;
 	struct hist_entry *he;
 	struct hist_entry he_tmp = {
 		.hists = evsel__hists(evsel),
@@ -1181,7 +1179,9 @@ static int
 iter_finish_cumulative_entry(struct hist_entry_iter *iter,
 			     struct addr_location *al __maybe_unused)
 {
-	zfree(&iter->priv);
+	mem_info__zput(iter->mi);
+	zfree(&iter->bi);
+	zfree(&iter->he_cache);
 	iter->he = NULL;
 
 	return 0;
@@ -1327,13 +1327,13 @@ void hist_entry__delete(struct hist_entry *he)
 	}
 
 	if (he->mem_info) {
-		map_symbol__exit(&he->mem_info->iaddr.ms);
-		map_symbol__exit(&he->mem_info->daddr.ms);
+		map_symbol__exit(&mem_info__iaddr(he->mem_info)->ms);
+		map_symbol__exit(&mem_info__daddr(he->mem_info)->ms);
 		mem_info__zput(he->mem_info);
 	}
 
 	if (he->block_info)
-		block_info__zput(he->block_info);
+		block_info__delete(he->block_info);
 
 	if (he->kvm_info)
 		kvm_info__zput(he->kvm_info);
@@ -2128,7 +2128,7 @@ static bool hists__filter_entry_by_dso(struct hists *hists,
 				       struct hist_entry *he)
 {
 	if (hists->dso_filter != NULL &&
-	    (he->ms.map == NULL || map__dso(he->ms.map) != hists->dso_filter)) {
+	    (he->ms.map == NULL || !RC_CHK_EQUAL(map__dso(he->ms.map), hists->dso_filter))) {
 		he->filtered |= (1 << HIST_FILTER__DSO);
 		return true;
 	}
@@ -2808,7 +2808,7 @@ int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool sh
 	}
 	if (dso)
 		printed += scnprintf(bf + printed, size - printed,
-				    ", DSO: %s", dso->short_name);
+				     ", DSO: %s", dso__short_name(dso));
 	if (socket_id > -1)
 		printed += scnprintf(bf + printed, size - printed,
 				    ", Processor Socket: %d", socket_id);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 4a0aea0c9e..8fb3bdd291 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -4,21 +4,22 @@
 
 #include <linux/rbtree.h>
 #include <linux/types.h>
-#include "evsel.h"
+#include "callchain.h"
 #include "color.h"
 #include "events_stats.h"
+#include "evsel.h"
+#include "map_symbol.h"
 #include "mutex.h"
+#include "sample.h"
+#include "spark.h"
+#include "stat.h"
 
-struct hist_entry;
-struct hist_entry_ops;
 struct addr_location;
-struct map_symbol;
 struct mem_info;
 struct kvm_info;
 struct branch_info;
 struct branch_stack;
 struct block_info;
-struct symbol;
 struct ui_progress;
 
 enum hist_filter {
@@ -131,18 +132,20 @@ struct hist_entry_iter {
 	int total;
 	int curr;
 
-	bool hide_unresolved;
-
 	struct evsel *evsel;
 	struct perf_sample *sample;
 	struct hist_entry *he;
 	struct symbol *parent;
-	void *priv;
+
+	struct mem_info *mi;
+	struct branch_info *bi;
+	struct hist_entry **he_cache;
 
 	const struct hist_iter_ops *ops;
 	/* user-defined callback function (optional) */
 	int (*add_entry_cb)(struct hist_entry_iter *iter,
 			    struct addr_location *al, bool single, void *arg);
+	bool hide_unresolved;
 };
 
 extern const struct hist_iter_ops hist_iter_normal;
@@ -150,6 +153,162 @@ extern const struct hist_iter_ops hist_iter_branch;
 extern const struct hist_iter_ops hist_iter_mem;
 extern const struct hist_iter_ops hist_iter_cumulative;
 
+struct res_sample {
+	u64 time;
+	int cpu;
+	int tid;
+};
+
+struct he_stat {
+	u64			period;
+	u64			period_sys;
+	u64			period_us;
+	u64			period_guest_sys;
+	u64			period_guest_us;
+	u64			weight1;
+	u64			weight2;
+	u64			weight3;
+	u32			nr_events;
+};
+
+struct namespace_id {
+	u64			dev;
+	u64			ino;
+};
+
+struct hist_entry_diff {
+	bool	computed;
+	union {
+		/* PERF_HPP__DELTA */
+		double	period_ratio_delta;
+
+		/* PERF_HPP__RATIO */
+		double	period_ratio;
+
+		/* HISTC_WEIGHTED_DIFF */
+		s64	wdiff;
+
+		/* PERF_HPP_DIFF__CYCLES */
+		s64	cycles;
+	};
+	struct stats	stats;
+	unsigned long	svals[NUM_SPARKS];
+};
+
+struct hist_entry_ops {
+	void	*(*new)(size_t size);
+	void	(*free)(void *ptr);
+};
+
+/**
+ * struct hist_entry - histogram entry
+ *
+ * @row_offset - offset from the first callchain expanded to appear on screen
+ * @nr_rows - rows expanded in callchain, recalculated on folding/unfolding
+ */
+struct hist_entry {
+	struct rb_node		rb_node_in;
+	struct rb_node		rb_node;
+	union {
+		struct list_head node;
+		struct list_head head;
+	} pairs;
+	struct he_stat		stat;
+	struct he_stat		*stat_acc;
+	struct map_symbol	ms;
+	struct thread		*thread;
+	struct comm		*comm;
+	struct namespace_id	cgroup_id;
+	u64			cgroup;
+	u64			ip;
+	u64			transaction;
+	s32			socket;
+	s32			cpu;
+	u64			code_page_size;
+	u64			weight;
+	u64			ins_lat;
+	u64			p_stage_cyc;
+	u8			cpumode;
+	u8			depth;
+	int			mem_type_off;
+	struct simd_flags	simd_flags;
+
+	/* We are added by hists__add_dummy_entry. */
+	bool			dummy;
+	bool			leaf;
+
+	char			level;
+	u8			filtered;
+
+	u16			callchain_size;
+	union {
+		/*
+		 * Since perf diff only supports the stdio output, TUI
+		 * fields are only accessed from perf report (or perf
+		 * top).  So make it a union to reduce memory usage.
+		 */
+		struct hist_entry_diff	diff;
+		struct /* for TUI */ {
+			u16	row_offset;
+			u16	nr_rows;
+			bool	init_have_children;
+			bool	unfolded;
+			bool	has_children;
+			bool	has_no_entry;
+		};
+	};
+	char			*srcline;
+	char			*srcfile;
+	struct symbol		*parent;
+	struct branch_info	*branch_info;
+	long			time;
+	struct hists		*hists;
+	struct mem_info		*mem_info;
+	struct block_info	*block_info;
+	struct kvm_info		*kvm_info;
+	void			*raw_data;
+	u32			raw_size;
+	int			num_res;
+	struct res_sample	*res_samples;
+	void			*trace_output;
+	struct perf_hpp_list	*hpp_list;
+	struct hist_entry	*parent_he;
+	struct hist_entry_ops	*ops;
+	struct annotated_data_type *mem_type;
+	union {
+		/* this is for hierarchical entry structure */
+		struct {
+			struct rb_root_cached	hroot_in;
+			struct rb_root_cached   hroot_out;
+		};				/* non-leaf entries */
+		struct rb_root	sorted_chain;	/* leaf entry has callchains */
+	};
+	struct callchain_root	callchain[0]; /* must be last member */
+};
+
+static __pure inline bool hist_entry__has_callchains(struct hist_entry *he)
+{
+	return he->callchain_size != 0;
+}
+
+static inline bool hist_entry__has_pairs(struct hist_entry *he)
+{
+	return !list_empty(&he->pairs.node);
+}
+
+static inline struct hist_entry *hist_entry__next_pair(struct hist_entry *he)
+{
+	if (hist_entry__has_pairs(he))
+		return list_entry(he->pairs.node.next, struct hist_entry, pairs.node);
+	return NULL;
+}
+
+static inline void hist_entry__add_pair(struct hist_entry *pair,
+					struct hist_entry *he)
+{
+	list_add_tail(&pair->pairs.node, &he->pairs.head);
+}
+
 struct hist_entry *hists__add_entry(struct hists *hists,
 				    struct addr_location *al,
 				    struct symbol *parent,
@@ -186,6 +345,8 @@ int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size,
 			      struct hists *hists);
 int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
 				   struct perf_hpp_fmt *fmt, int printed);
+int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size,
+			     unsigned int width);
 void hist_entry__delete(struct hist_entry *he);
 
 typedef int (*hists__resort_cb_t)(struct hist_entry *he, void *arg);
@@ -238,6 +399,20 @@ void hists__match(struct hists *leader, struct hists *other);
 int hists__link(struct hists *leader, struct hists *other);
 int hists__unlink(struct hists *hists);
 
+static inline float hist_entry__get_percent_limit(struct hist_entry *he)
+{
+	u64 period = he->stat.period;
+	u64 total_period = hists__total_period(he->hists);
+
+	if (unlikely(total_period == 0))
+		return 0;
+
+	if (symbol_conf.cumulate_callchain)
+		period = he->stat_acc->period;
+
+	return period * 100.0 / total_period;
+}
+
 struct hists_evsel {
 	struct evsel evsel;
 	struct hists	  hists;
@@ -377,6 +552,9 @@ enum {
 	PERF_HPP__OVERHEAD_ACC,
 	PERF_HPP__SAMPLES,
 	PERF_HPP__PERIOD,
+	PERF_HPP__WEIGHT1,
+	PERF_HPP__WEIGHT2,
+	PERF_HPP__WEIGHT3,
 
 	PERF_HPP__MAX_INDEX
 };
@@ -423,16 +601,24 @@ void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists);
 void perf_hpp__set_user_width(const char *width_list_str);
 void hists__reset_column_width(struct hists *hists);
 
+enum perf_hpp_fmt_type {
+	PERF_HPP_FMT_TYPE__RAW,
+	PERF_HPP_FMT_TYPE__PERCENT,
+	PERF_HPP_FMT_TYPE__AVERAGE,
+};
+
 typedef u64 (*hpp_field_fn)(struct hist_entry *he);
 typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front);
 typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
 
 int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	     struct hist_entry *he, hpp_field_fn get_field,
-	     const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
+	     const char *fmtstr, hpp_snprint_fn print_fn,
+	     enum perf_hpp_fmt_type fmtype);
 int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		 struct hist_entry *he, hpp_field_fn get_field,
-		 const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
+		 const char *fmtstr, hpp_snprint_fn print_fn,
+		 enum perf_hpp_fmt_type fmtype);
 
 static inline void advance_hpp(struct perf_hpp *hpp, int inc)
 {
@@ -460,15 +646,20 @@ struct hist_browser_timer {
 	int refresh;
 };
 
-struct res_sample;
-
 enum rstype {
 	A_NORMAL,
 	A_ASM,
 	A_SOURCE
 };
 
-struct block_hist;
+struct block_hist {
+	struct hists		block_hists;
+	struct perf_hpp_list	block_list;
+	struct perf_hpp_fmt	block_fmt;
+	int			block_idx;
+	bool			valid;
+	struct hist_entry	he;
+};
 
 #ifdef HAVE_SLANG_SUPPORT
 #include "../ui/keysyms.h"
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 4db9a098f5..d6d7b75125 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -598,15 +598,15 @@ static struct auxtrace_cache *intel_pt_cache(struct dso *dso,
 	struct auxtrace_cache *c;
 	unsigned int bits;
 
-	if (dso->auxtrace_cache)
-		return dso->auxtrace_cache;
+	if (dso__auxtrace_cache(dso))
+		return dso__auxtrace_cache(dso);
 
 	bits = intel_pt_cache_size(dso, machine);
 
 	/* Ignoring cache creation failure */
 	c = auxtrace_cache__new(bits, sizeof(struct intel_pt_cache_entry), 200);
 
-	dso->auxtrace_cache = c;
+	dso__set_auxtrace_cache(dso, c);
 
 	return c;
 }
@@ -650,7 +650,7 @@ intel_pt_cache_lookup(struct dso *dso, struct machine *machine, u64 offset)
 	if (!c)
 		return NULL;
 
-	return auxtrace_cache__lookup(dso->auxtrace_cache, offset);
+	return auxtrace_cache__lookup(dso__auxtrace_cache(dso), offset);
 }
 
 static void intel_pt_cache_invalidate(struct dso *dso, struct machine *machine,
@@ -661,7 +661,7 @@ static void intel_pt_cache_invalidate(struct dso *dso, struct machine *machine,
 	if (!c)
 		return;
 
-	auxtrace_cache__remove(dso->auxtrace_cache, offset);
+	auxtrace_cache__remove(dso__auxtrace_cache(dso), offset);
 }
 
 static inline bool intel_pt_guest_kernel_ip(uint64_t ip)
@@ -821,8 +821,8 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 		}
 		dso = map__dso(al.map);
 
-		if (dso->data.status == DSO_DATA_STATUS_ERROR &&
-			dso__data_status_seen(dso, DSO_DATA_STATUS_SEEN_ITRACE)) {
+		if (dso__data(dso)->status == DSO_DATA_STATUS_ERROR &&
+		    dso__data_status_seen(dso, DSO_DATA_STATUS_SEEN_ITRACE)) {
 			ret = -ENOENT;
 			goto out_ret;
 		}
@@ -855,7 +855,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 		/* Load maps to ensure dso->is_64_bit has been updated */
 		map__load(al.map);
 
-		x86_64 = dso->is_64_bit;
+		x86_64 = dso__is_64_bit(dso);
 
 		while (1) {
 			len = dso__data_read_offset(dso, machine,
@@ -1010,7 +1010,7 @@ static int __intel_pt_pgd_ip(uint64_t ip, void *data)
 
 	offset = map__map_ip(al.map, ip);
 
-	res = intel_pt_match_pgd_ip(ptq->pt, ip, offset, map__dso(al.map)->long_name);
+	res = intel_pt_match_pgd_ip(ptq->pt, ip, offset, dso__long_name(map__dso(al.map)));
 	addr_location__exit(&al);
 	return res;
 }
@@ -3418,7 +3418,7 @@ static int intel_pt_text_poke(struct intel_pt *pt, union perf_event *event)
 		}
 
 		dso = map__dso(al.map);
-		if (!dso || !dso->auxtrace_cache)
+		if (!dso || !dso__auxtrace_cache(dso))
 			continue;
 
 		offset = map__map_ip(al.map, addr);
@@ -3438,7 +3438,7 @@ static int intel_pt_text_poke(struct intel_pt *pt, union perf_event *event)
 		} else {
 			intel_pt_cache_invalidate(dso, machine, offset);
 			intel_pt_log("Invalidated instruction cache for %s at %#"PRIx64"\n",
-				     dso->long_name, addr);
+				     dso__long_name(dso), addr);
 		}
 	}
 out:
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 07c22f765f..8477edefc2 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -16,6 +16,7 @@
 #include "map_symbol.h"
 #include "branch.h"
 #include "mem-events.h"
+#include "mem-info.h"
 #include "path.h"
 #include "srcline.h"
 #include "symbol.h"
@@ -48,13 +49,6 @@ static struct dso *machine__kernel_dso(struct machine *machine)
 	return map__dso(machine->vmlinux_map);
 }
 
-static void dsos__init(struct dsos *dsos)
-{
-	INIT_LIST_HEAD(&dsos->head);
-	dsos->root = RB_ROOT;
-	init_rwsem(&dsos->lock);
-}
-
 static int machine__set_mmap_name(struct machine *machine)
 {
 	if (machine__is_host(machine))
@@ -165,28 +159,6 @@ struct machine *machine__new_kallsyms(void)
 	return machine;
 }
 
-static void dsos__purge(struct dsos *dsos)
-{
-	struct dso *pos, *n;
-
-	down_write(&dsos->lock);
-
-	list_for_each_entry_safe(pos, n, &dsos->head, node) {
-		RB_CLEAR_NODE(&pos->rb_node);
-		pos->root = NULL;
-		list_del_init(&pos->node);
-		dso__put(pos);
-	}
-
-	up_write(&dsos->lock);
-}
-
-static void dsos__exit(struct dsos *dsos)
-{
-	dsos__purge(dsos);
-	exit_rwsem(&dsos->lock);
-}
-
 void machine__delete_threads(struct machine *machine)
 {
 	threads__remove_all_threads(&machine->threads);
@@ -675,31 +647,6 @@ int machine__process_lost_samples_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
-static struct dso *machine__findnew_module_dso(struct machine *machine,
-					       struct kmod_path *m,
-					       const char *filename)
-{
-	struct dso *dso;
-
-	down_write(&machine->dsos.lock);
-
-	dso = __dsos__find(&machine->dsos, m->name, true);
-	if (!dso) {
-		dso = __dsos__addnew(&machine->dsos, m->name);
-		if (dso == NULL)
-			goto out_unlock;
-
-		dso__set_module_info(dso, m, machine);
-		dso__set_long_name(dso, strdup(filename), true);
-		dso->kernel = DSO_SPACE__KERNEL;
-	}
-
-	dso__get(dso);
-out_unlock:
-	up_write(&machine->dsos.lock);
-	return dso;
-}
-
 int machine__process_aux_event(struct machine *machine __maybe_unused,
 			       union perf_event *event)
 {
@@ -737,7 +684,7 @@ static int machine__process_ksymbol_register(struct machine *machine,
 					     struct perf_sample *sample __maybe_unused)
 {
 	struct symbol *sym;
-	struct dso *dso;
+	struct dso *dso = NULL;
 	struct map *map = maps__find(machine__kernel_maps(machine), event->ksymbol.addr);
 	int err = 0;
 
@@ -748,16 +695,15 @@ static int machine__process_ksymbol_register(struct machine *machine,
 			err = -ENOMEM;
 			goto out;
 		}
-		dso->kernel = DSO_SPACE__KERNEL;
+		dso__set_kernel(dso, DSO_SPACE__KERNEL);
 		map = map__new2(0, dso);
-		dso__put(dso);
 		if (!map) {
 			err = -ENOMEM;
 			goto out;
 		}
 		if (event->ksymbol.ksym_type == PERF_RECORD_KSYMBOL_TYPE_OOL) {
-			dso->binary_type = DSO_BINARY_TYPE__OOL;
-			dso->data.file_size = event->ksymbol.len;
+			dso__set_binary_type(dso, DSO_BINARY_TYPE__OOL);
+			dso__data(dso)->file_size = event->ksymbol.len;
 			dso__set_loaded(dso);
 		}
 
@@ -772,11 +718,11 @@ static int machine__process_ksymbol_register(struct machine *machine,
 		dso__set_loaded(dso);
 
 		if (is_bpf_image(event->ksymbol.name)) {
-			dso->binary_type = DSO_BINARY_TYPE__BPF_IMAGE;
+			dso__set_binary_type(dso, DSO_BINARY_TYPE__BPF_IMAGE);
 			dso__set_long_name(dso, "", false);
 		}
 	} else {
-		dso = map__dso(map);
+		dso = dso__get(map__dso(map));
 	}
 
 	sym = symbol__new(map__map_ip(map, map__start(map)),
@@ -789,6 +735,7 @@ static int machine__process_ksymbol_register(struct machine *machine,
 	dso__insert_symbol(dso, sym);
 out:
 	map__put(map);
+	dso__put(dso);
 	return err;
 }
 
@@ -883,7 +830,7 @@ static struct map *machine__addnew_module_map(struct machine *machine, u64 start
 	if (kmod_path__parse_name(&m, filename))
 		return NULL;
 
-	dso = machine__findnew_module_dso(machine, &m, filename);
+	dso = dsos__findnew_module_dso(&machine->dsos, machine, &m, filename);
 	if (dso == NULL)
 		goto out;
 
@@ -907,11 +854,11 @@ out:
 size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
 {
 	struct rb_node *nd;
-	size_t ret = __dsos__fprintf(&machines->host.dsos.head, fp);
+	size_t ret = dsos__fprintf(&machines->host.dsos, fp);
 
 	for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret += __dsos__fprintf(&pos->dsos.head, fp);
+		ret += dsos__fprintf(&pos->dsos, fp);
 	}
 
 	return ret;
@@ -920,7 +867,7 @@ size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
 size_t machine__fprintf_dsos_buildid(struct machine *m, FILE *fp,
 				     bool (skip)(struct dso *dso, int parm), int parm)
 {
-	return __dsos__fprintf_buildid(&m->dsos.head, fp, skip, parm);
+	return dsos__fprintf_buildid(&m->dsos, fp, skip, parm);
 }
 
 size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
@@ -942,17 +889,17 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
 	size_t printed = 0;
 	struct dso *kdso = machine__kernel_dso(machine);
 
-	if (kdso->has_build_id) {
+	if (dso__has_build_id(kdso)) {
 		char filename[PATH_MAX];
-		if (dso__build_id_filename(kdso, filename, sizeof(filename),
-					   false))
+
+		if (dso__build_id_filename(kdso, filename, sizeof(filename), false))
 			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]);
-
+	for (i = 0; i < vmlinux_path__nr_entries; ++i) {
+		printed += fprintf(fp, "[%d] %s\n", i + dso__has_build_id(kdso),
+				   vmlinux_path[i]);
+	}
 	return printed;
 }
 
@@ -1002,7 +949,7 @@ static struct dso *machine__get_kernel(struct machine *machine)
 						 DSO_SPACE__KERNEL_GUEST);
 	}
 
-	if (kernel != NULL && (!kernel->has_build_id))
+	if (kernel != NULL && (!dso__has_build_id(kernel)))
 		dso__read_running_kernel_build_id(kernel, machine);
 
 	return kernel;
@@ -1367,8 +1314,8 @@ static char *get_kernel_version(const char *root_dir)
 
 static bool is_kmod_dso(struct dso *dso)
 {
-	return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
-	       dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE;
+	return dso__symtab_type(dso) == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
+	       dso__symtab_type(dso) == DSO_BINARY_TYPE__GUEST_KMODULE;
 }
 
 static int maps__set_module_path(struct maps *maps, const char *path, struct kmod_path *m)
@@ -1395,8 +1342,8 @@ static int maps__set_module_path(struct maps *maps, const char *path, struct kmo
 	 * we need to update the symtab_type if needed.
 	 */
 	if (m->comp && is_kmod_dso(dso)) {
-		dso->symtab_type++;
-		dso->comp = m->comp;
+		dso__set_symtab_type(dso, dso__symtab_type(dso));
+		dso__set_comp(dso, m->comp);
 	}
 	map__put(map);
 	return 0;
@@ -1616,16 +1563,14 @@ out_put:
 	return ret;
 }
 
-static bool machine__uses_kcore(struct machine *machine)
+static int machine__uses_kcore_cb(struct dso *dso, void *data __maybe_unused)
 {
-	struct dso *dso;
-
-	list_for_each_entry(dso, &machine->dsos.head, node) {
-		if (dso__is_kcore(dso))
-			return true;
-	}
+	return dso__is_kcore(dso) ? 1 : 0;
+}
 
-	return false;
+static bool machine__uses_kcore(struct machine *machine)
+{
+	return dsos__for_each_dso(&machine->dsos, machine__uses_kcore_cb, NULL) != 0 ? true : false;
 }
 
 static bool perf_event__is_extra_kernel_mmap(struct machine *machine,
@@ -1692,53 +1637,20 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		 * Should be there already, from the build-id table in
 		 * the header.
 		 */
-		struct dso *kernel = NULL;
-		struct dso *dso;
-
-		down_read(&machine->dsos.lock);
-
-		list_for_each_entry(dso, &machine->dsos.head, node) {
-
-			/*
-			 * The cpumode passed to is_kernel_module is not the
-			 * cpumode of *this* event. If we insist on passing
-			 * correct cpumode to is_kernel_module, we should
-			 * record the cpumode when we adding this dso to the
-			 * linked list.
-			 *
-			 * However we don't really need passing correct
-			 * cpumode.  We know the correct cpumode must be kernel
-			 * mode (if not, we should not link it onto kernel_dsos
-			 * list).
-			 *
-			 * Therefore, we pass PERF_RECORD_MISC_CPUMODE_UNKNOWN.
-			 * is_kernel_module() treats it as a kernel cpumode.
-			 */
-
-			if (!dso->kernel ||
-			    is_kernel_module(dso->long_name,
-					     PERF_RECORD_MISC_CPUMODE_UNKNOWN))
-				continue;
-
-
-			kernel = dso__get(dso);
-			break;
-		}
-
-		up_read(&machine->dsos.lock);
+		struct dso *kernel = dsos__find_kernel_dso(&machine->dsos);
 
 		if (kernel == NULL)
 			kernel = machine__findnew_dso(machine, machine->mmap_name);
 		if (kernel == NULL)
 			goto out_problem;
 
-		kernel->kernel = dso_space;
+		dso__set_kernel(kernel, dso_space);
 		if (__machine__create_kernel_maps(machine, kernel) < 0) {
 			dso__put(kernel);
 			goto out_problem;
 		}
 
-		if (strstr(kernel->long_name, "vmlinux"))
+		if (strstr(dso__long_name(kernel), "vmlinux"))
 			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
 
 		if (machine__update_kernel_mmap(machine, xm->start, xm->end) < 0) {
@@ -2101,11 +2013,11 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 	if (!mi)
 		return NULL;
 
-	ip__resolve_ams(al->thread, &mi->iaddr, sample->ip);
-	ip__resolve_data(al->thread, al->cpumode, &mi->daddr,
+	ip__resolve_ams(al->thread, mem_info__iaddr(mi), sample->ip);
+	ip__resolve_data(al->thread, al->cpumode, mem_info__daddr(mi),
 			 sample->addr, sample->phys_addr,
 			 sample->data_page_size);
-	mi->data_src.val = sample->data_src;
+	mem_info__data_src(mi)->val = sample->data_src;
 
 	return mi;
 }
@@ -2120,14 +2032,14 @@ static char *callchain_srcline(struct map_symbol *ms, u64 ip)
 		return srcline;
 
 	dso = map__dso(map);
-	srcline = srcline__tree_find(&dso->srclines, ip);
+	srcline = srcline__tree_find(dso__srclines(dso), ip);
 	if (!srcline) {
 		bool show_sym = false;
 		bool show_addr = callchain_param.key == CCKEY_ADDRESS;
 
 		srcline = get_srcline(dso, map__rip_2objdump(map, ip),
 				      ms->sym, show_sym, show_addr, ip);
-		srcline__tree_insert(&dso->srclines, ip, srcline);
+		srcline__tree_insert(dso__srclines(dso), ip, srcline);
 	}
 
 	return srcline;
@@ -2925,12 +2837,12 @@ static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms
 	addr = map__rip_2objdump(map, addr);
 	dso = map__dso(map);
 
-	inline_node = inlines__tree_find(&dso->inlined_nodes, addr);
+	inline_node = inlines__tree_find(dso__inlined_nodes(dso), addr);
 	if (!inline_node) {
 		inline_node = dso__parse_addr_inlines(dso, addr, sym);
 		if (!inline_node)
 			return ret;
-		inlines__tree_insert(&dso->inlined_nodes, inline_node);
+		inlines__tree_insert(dso__inlined_nodes(dso), inline_node);
 	}
 
 	ilist_ms = (struct map_symbol) {
@@ -3219,21 +3131,33 @@ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, ch
 	if (sym == NULL)
 		return NULL;
 
-	*modp = __map__is_kmodule(map) ? (char *)map__dso(map)->short_name : NULL;
+	*modp = __map__is_kmodule(map) ? (char *)dso__short_name(map__dso(map)) : NULL;
 	*addrp = map__unmap_ip(map, sym->start);
 	return sym->name;
 }
 
+struct machine__for_each_dso_cb_args {
+	struct machine *machine;
+	machine__dso_t fn;
+	void *priv;
+};
+
+static int machine__for_each_dso_cb(struct dso *dso, void *data)
+{
+	struct machine__for_each_dso_cb_args *args = data;
+
+	return args->fn(dso, args->machine, args->priv);
+}
+
 int machine__for_each_dso(struct machine *machine, machine__dso_t fn, void *priv)
 {
-	struct dso *pos;
-	int err = 0;
+	struct machine__for_each_dso_cb_args args = {
+		.machine = machine,
+		.fn = fn,
+		.priv = priv,
+	};
 
-	list_for_each_entry(pos, &machine->dsos.head, node) {
-		if (fn(pos, machine, priv))
-			err = -1;
-	}
-	return err;
+	return dsos__for_each_dso(&machine->dsos, machine__for_each_dso_cb, &args);
 }
 
 int machine__for_each_kernel_map(struct machine *machine, machine__map_t fn, void *priv)
@@ -3266,6 +3190,17 @@ bool machine__is_lock_function(struct machine *machine, u64 addr)
 
 		sym = machine__find_kernel_symbol_by_name(machine, "__lock_text_end", &kmap);
 		machine->lock.text_end = map__unmap_ip(kmap, sym->start);
+
+		sym = machine__find_kernel_symbol_by_name(machine, "__traceiter_contention_begin", &kmap);
+		if (sym) {
+			machine->traceiter.text_start = map__unmap_ip(kmap, sym->start);
+			machine->traceiter.text_end = map__unmap_ip(kmap, sym->end);
+		}
+		sym = machine__find_kernel_symbol_by_name(machine, "trace_contention_begin", &kmap);
+		if (sym) {
+			machine->trace.text_start = map__unmap_ip(kmap, sym->start);
+			machine->trace.text_end = map__unmap_ip(kmap, sym->end);
+		}
 	}
 
 	/* failed to get kernel symbols */
@@ -3280,5 +3215,23 @@ bool machine__is_lock_function(struct machine *machine, u64 addr)
 	if (machine->lock.text_start <= addr && addr < machine->lock.text_end)
 		return true;
 
+	/* traceiter functions currently don't have their own section
+	 * but we consider them lock functions
+	 */
+	if (machine->traceiter.text_start != 0) {
+		if (machine->traceiter.text_start <= addr && addr < machine->traceiter.text_end)
+			return true;
+	}
+
+	if (machine->trace.text_start != 0) {
+		if (machine->trace.text_start <= addr && addr < machine->trace.text_end)
+			return true;
+	}
+
 	return false;
 }
+
+int machine__hit_all_dsos(struct machine *machine)
+{
+	return dsos__hit_all(&machine->dsos);
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index e28c787616..82a47bac80 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -49,7 +49,7 @@ struct machine {
 	struct {
 		u64	  text_start;
 		u64	  text_end;
-	} sched, lock;
+	} sched, lock, traceiter, trace;
 	pid_t		  *current_tid;
 	size_t		  current_tid_sz;
 	union { /* Tool specific area */
@@ -306,4 +306,6 @@ int machine__map_x86_64_entry_trampolines(struct machine *machine,
 int machine__resolve(struct machine *machine, struct addr_location *al,
 		     struct perf_sample *sample);
 
+int machine__hit_all_dsos(struct machine *machine);
+
 #endif /* __PERF_MACHINE_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 14a5ea70d8..e1d14936a6 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -168,7 +168,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 		if (dso == NULL)
 			goto out_delete;
 
-		assert(!dso->kernel);
+		assert(!dso__kernel(dso));
 		map__init(result, start, start + len, pgoff, dso);
 
 		if (anon || no_dso) {
@@ -182,10 +182,9 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 			if (!(prot & PROT_EXEC))
 				dso__set_loaded(dso);
 		}
-		mutex_lock(&dso->lock);
-		nsinfo__put(dso->nsinfo);
-		dso->nsinfo = nsi;
-		mutex_unlock(&dso->lock);
+		mutex_lock(dso__lock(dso));
+		dso__set_nsinfo(dso, nsi);
+		mutex_unlock(dso__lock(dso));
 
 		if (build_id__is_defined(bid)) {
 			dso__set_build_id(dso, bid);
@@ -196,13 +195,12 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 			 * reading the header will have the build ID set and all future mmaps will
 			 * have it missing.
 			 */
-			down_read(&machine->dsos.lock);
-			header_bid_dso = __dsos__find(&machine->dsos, filename, false);
-			up_read(&machine->dsos.lock);
-			if (header_bid_dso && header_bid_dso->header_build_id) {
-				dso__set_build_id(dso, &header_bid_dso->bid);
-				dso->header_build_id = 1;
+			header_bid_dso = dsos__find(&machine->dsos, filename, false);
+			if (header_bid_dso && dso__header_build_id(header_bid_dso)) {
+				dso__set_build_id(dso, dso__bid(header_bid_dso));
+				dso__set_header_build_id(dso, 1);
 			}
+			dso__put(header_bid_dso);
 		}
 		dso__put(dso);
 	}
@@ -223,7 +221,7 @@ struct map *map__new2(u64 start, struct dso *dso)
 	struct map *result;
 	RC_STRUCT(map) *map;
 
-	map = calloc(1, sizeof(*map) + (dso->kernel ? sizeof(struct kmap) : 0));
+	map = calloc(1, sizeof(*map) + (dso__kernel(dso) ? sizeof(struct kmap) : 0));
 	if (ADD_RC_CHK(result, map)) {
 		/*
 		 * ->end will be filled after we load all the symbols
@@ -236,7 +234,7 @@ struct map *map__new2(u64 start, struct dso *dso)
 
 bool __map__is_kernel(const struct map *map)
 {
-	if (!map__dso(map)->kernel)
+	if (!dso__kernel(map__dso(map)))
 		return false;
 	return machine__kernel_map(maps__machine(map__kmaps((struct map *)map))) == map;
 }
@@ -253,7 +251,7 @@ bool __map__is_bpf_prog(const struct map *map)
 	const char *name;
 	struct dso *dso = map__dso(map);
 
-	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
+	if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_PROG_INFO)
 		return true;
 
 	/*
@@ -261,7 +259,7 @@ bool __map__is_bpf_prog(const struct map *map)
 	 * type of DSO_BINARY_TYPE__BPF_PROG_INFO. In such cases, we can
 	 * guess the type based on name.
 	 */
-	name = dso->short_name;
+	name = dso__short_name(dso);
 	return name && (strstr(name, "bpf_prog_") == name);
 }
 
@@ -270,7 +268,7 @@ bool __map__is_bpf_image(const struct map *map)
 	const char *name;
 	struct dso *dso = map__dso(map);
 
-	if (dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE)
+	if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_IMAGE)
 		return true;
 
 	/*
@@ -278,7 +276,7 @@ bool __map__is_bpf_image(const struct map *map)
 	 * type of DSO_BINARY_TYPE__BPF_IMAGE. In such cases, we can
 	 * guess the type based on name.
 	 */
-	name = dso->short_name;
+	name = dso__short_name(dso);
 	return name && is_bpf_image(name);
 }
 
@@ -286,7 +284,7 @@ bool __map__is_ool(const struct map *map)
 {
 	const struct dso *dso = map__dso(map);
 
-	return dso && dso->binary_type == DSO_BINARY_TYPE__OOL;
+	return dso && dso__binary_type(dso) == DSO_BINARY_TYPE__OOL;
 }
 
 bool map__has_symbols(const struct map *map)
@@ -317,7 +315,7 @@ void map__put(struct map *map)
 void map__fixup_start(struct map *map)
 {
 	struct dso *dso = map__dso(map);
-	struct rb_root_cached *symbols = &dso->symbols;
+	struct rb_root_cached *symbols = dso__symbols(dso);
 	struct rb_node *nd = rb_first_cached(symbols);
 
 	if (nd != NULL) {
@@ -330,7 +328,7 @@ void map__fixup_start(struct map *map)
 void map__fixup_end(struct map *map)
 {
 	struct dso *dso = map__dso(map);
-	struct rb_root_cached *symbols = &dso->symbols;
+	struct rb_root_cached *symbols = dso__symbols(dso);
 	struct rb_node *nd = rb_last(&symbols->rb_root);
 
 	if (nd != NULL) {
@@ -344,7 +342,7 @@ void map__fixup_end(struct map *map)
 int map__load(struct map *map)
 {
 	struct dso *dso = map__dso(map);
-	const char *name = dso->long_name;
+	const char *name = dso__long_name(dso);
 	int nr;
 
 	if (dso__loaded(dso))
@@ -352,10 +350,10 @@ int map__load(struct map *map)
 
 	nr = dso__load(dso, map);
 	if (nr < 0) {
-		if (dso->has_build_id) {
+		if (dso__has_build_id(dso)) {
 			char sbuild_id[SBUILD_ID_SIZE];
 
-			build_id__sprintf(&dso->bid, sbuild_id);
+			build_id__sprintf(dso__bid(dso), sbuild_id);
 			pr_debug("%s with build id %s not found", name, sbuild_id);
 		} else
 			pr_debug("Failed to open %s", name);
@@ -417,7 +415,7 @@ struct map *map__clone(struct map *from)
 	size_t size = sizeof(RC_STRUCT(map));
 	struct dso *dso = map__dso(from);
 
-	if (dso && dso->kernel)
+	if (dso && dso__kernel(dso))
 		size += sizeof(struct kmap);
 
 	map = memdup(RC_CHK_ACCESS(from), size);
@@ -434,14 +432,14 @@ size_t map__fprintf(struct map *map, FILE *fp)
 	const struct dso *dso = map__dso(map);
 
 	return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n",
-		       map__start(map), map__end(map), map__pgoff(map), dso->name);
+		       map__start(map), map__end(map), map__pgoff(map), dso__name(dso));
 }
 
 static bool prefer_dso_long_name(const struct dso *dso, bool print_off)
 {
-	return dso->long_name &&
+	return dso__long_name(dso) &&
 	       (symbol_conf.show_kernel_path ||
-		(print_off && (dso->name[0] == '[' || dso__is_kcore(dso))));
+		(print_off && (dso__name(dso)[0] == '[' || dso__is_kcore(dso))));
 }
 
 static size_t __map__fprintf_dsoname(struct map *map, bool print_off, FILE *fp)
@@ -452,9 +450,9 @@ static size_t __map__fprintf_dsoname(struct map *map, bool print_off, FILE *fp)
 
 	if (dso) {
 		if (prefer_dso_long_name(dso, print_off))
-			dsoname = dso->long_name;
+			dsoname = dso__long_name(dso);
 		else
-			dsoname = dso->name;
+			dsoname = dso__name(dso);
 	}
 
 	if (symbol_conf.pad_output_len_dso) {
@@ -547,14 +545,14 @@ u64 map__rip_2objdump(struct map *map, u64 rip)
 		}
 	}
 
-	if (!dso->adjust_symbols)
+	if (!dso__adjust_symbols(dso))
 		return rip;
 
-	if (dso->rel)
+	if (dso__rel(dso))
 		return rip - map__pgoff(map);
 
-	if (dso->kernel == DSO_SPACE__USER)
-		return rip + dso->text_offset;
+	if (dso__kernel(dso) == DSO_SPACE__USER)
+		return rip + dso__text_offset(dso);
 
 	return map__unmap_ip(map, rip) - map__reloc(map);
 }
@@ -575,18 +573,35 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 {
 	const struct dso *dso = map__dso(map);
 
-	if (!dso->adjust_symbols)
+	if (!dso__adjust_symbols(dso))
 		return map__unmap_ip(map, ip);
 
-	if (dso->rel)
+	if (dso__rel(dso))
 		return map__unmap_ip(map, ip + map__pgoff(map));
 
-	if (dso->kernel == DSO_SPACE__USER)
-		return map__unmap_ip(map, ip - dso->text_offset);
+	if (dso__kernel(dso) == DSO_SPACE__USER)
+		return map__unmap_ip(map, ip - dso__text_offset(dso));
 
 	return ip + map__reloc(map);
 }
 
+/* convert objdump address to relative address.  (To be removed) */
+u64 map__objdump_2rip(struct map *map, u64 ip)
+{
+	const struct dso *dso = map__dso(map);
+
+	if (!dso__adjust_symbols(dso))
+		return ip;
+
+	if (dso__rel(dso))
+		return ip + map__pgoff(map);
+
+	if (dso__kernel(dso) == DSO_SPACE__USER)
+		return ip - dso__text_offset(dso);
+
+	return map__map_ip(map, ip + map__reloc(map));
+}
+
 bool map__contains_symbol(const struct map *map, const struct symbol *sym)
 {
 	u64 ip = map__unmap_ip(map, sym->start);
@@ -598,7 +613,7 @@ struct kmap *__map__kmap(struct map *map)
 {
 	const struct dso *dso = map__dso(map);
 
-	if (!dso || !dso->kernel)
+	if (!dso || !dso__kernel(dso))
 		return NULL;
 	return (struct kmap *)(&RC_CHK_ACCESS(map)[1]);
 }
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 49756716cb..65e2609fa1 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -132,6 +132,9 @@ u64 map__rip_2objdump(struct map *map, u64 rip);
 /* objdump address -> memory address */
 u64 map__objdump_2mem(struct map *map, u64 ip);
 
+/* objdump address -> rip */
+u64 map__objdump_2rip(struct map *map, u64 ip);
+
 struct symbol;
 struct thread;
 
diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index ce13145a9f..eaada3e0f5 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -76,7 +76,7 @@ static void check_invariants(const struct maps *maps __maybe_unused)
 		/* Expect at least 1 reference count. */
 		assert(refcount_read(map__refcnt(map)) > 0);
 
-		if (map__dso(map) && map__dso(map)->kernel)
+		if (map__dso(map) && dso__kernel(map__dso(map)))
 			assert(RC_CHK_EQUAL(map__kmap(map)->kmaps, maps));
 
 		if (i > 0) {
@@ -124,11 +124,6 @@ static void maps__set_maps_by_address(struct maps *maps, struct map **new)
 
 }
 
-static struct map ***maps__maps_by_name_addr(struct maps *maps)
-{
-	return &RC_CHK_ACCESS(maps)->maps_by_name;
-}
-
 static void maps__set_nr_maps_allocated(struct maps *maps, unsigned int nr_maps_allocated)
 {
 	RC_CHK_ACCESS(maps)->nr_maps_allocated = nr_maps_allocated;
@@ -211,11 +206,6 @@ void maps__set_unwind_libunwind_ops(struct maps *maps, const struct unwind_libun
 
 static struct rw_semaphore *maps__lock(struct maps *maps)
 {
-	/*
-	 * When the lock is acquired or released the maps invariants should
-	 * hold.
-	 */
-	check_invariants(maps);
 	return &RC_CHK_ACCESS(maps)->lock;
 }
 
@@ -289,6 +279,9 @@ void maps__put(struct maps *maps)
 
 static void __maps__free_maps_by_name(struct maps *maps)
 {
+	if (!maps__maps_by_name(maps))
+		return;
+
 	/*
 	 * Free everything to try to do it from the rbtree in the next search
 	 */
@@ -296,6 +289,9 @@ static void __maps__free_maps_by_name(struct maps *maps)
 		map__put(maps__maps_by_name(maps)[i]);
 
 	zfree(&RC_CHK_ACCESS(maps)->maps_by_name);
+
+	/* Consistent with maps__init(). When maps_by_name == NULL, maps_by_name_sorted == false */
+	maps__set_maps_by_name_sorted(maps, false);
 }
 
 static int map__start_cmp(const void *a, const void *b)
@@ -346,7 +342,7 @@ static int map__strcmp(const void *a, const void *b)
 	const struct map *map_b = *(const struct map * const *)b;
 	const struct dso *dso_a = map__dso(map_a);
 	const struct dso *dso_b = map__dso(map_b);
-	int ret = strcmp(dso_a->short_name, dso_b->short_name);
+	int ret = strcmp(dso__short_name(dso_a), dso__short_name(dso_b));
 
 	if (ret == 0 && RC_CHK_ACCESS(map_a) != RC_CHK_ACCESS(map_b)) {
 		/* Ensure distinct but name equal maps have an order. */
@@ -358,6 +354,7 @@ static int map__strcmp(const void *a, const void *b)
 static int maps__sort_by_name(struct maps *maps)
 {
 	int err = 0;
+
 	down_write(maps__lock(maps));
 	if (!maps__maps_by_name_sorted(maps)) {
 		struct map **maps_by_name = maps__maps_by_name(maps);
@@ -384,6 +381,7 @@ static int maps__sort_by_name(struct maps *maps)
 			maps__set_maps_by_name_sorted(maps, true);
 		}
 	}
+	check_invariants(maps);
 	up_write(maps__lock(maps));
 	return err;
 }
@@ -485,7 +483,7 @@ static int __maps__insert(struct maps *maps, struct map *new)
 	}
 	if (map__end(new) < map__start(new))
 		RC_CHK_ACCESS(maps)->ends_broken = true;
-	if (dso && dso->kernel) {
+	if (dso && dso__kernel(dso)) {
 		struct kmap *kmap = map__kmap(new);
 
 		if (kmap)
@@ -502,6 +500,7 @@ int maps__insert(struct maps *maps, struct map *map)
 
 	down_write(maps__lock(maps));
 	ret = __maps__insert(maps, map);
+	check_invariants(maps);
 	up_write(maps__lock(maps));
 	return ret;
 }
@@ -536,6 +535,7 @@ void maps__remove(struct maps *maps, struct map *map)
 {
 	down_write(maps__lock(maps));
 	__maps__remove(maps, map);
+	check_invariants(maps);
 	up_write(maps__lock(maps));
 }
 
@@ -602,6 +602,7 @@ void maps__remove_maps(struct maps *maps, bool (*cb)(struct map *map, void *data
 		else
 			i++;
 	}
+	check_invariants(maps);
 	up_write(maps__lock(maps));
 }
 
@@ -740,7 +741,6 @@ static unsigned int first_ending_after(struct maps *maps, const struct map *map)
  */
 static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new)
 {
-	struct map **maps_by_address;
 	int err = 0;
 	FILE *fp = debug_file();
 
@@ -748,12 +748,12 @@ sort_again:
 	if (!maps__maps_by_address_sorted(maps))
 		__maps__sort_by_address(maps);
 
-	maps_by_address = maps__maps_by_address(maps);
 	/*
 	 * Iterate through entries where the end of the existing entry is
 	 * greater-than the new map's start.
 	 */
 	for (unsigned int i = first_ending_after(maps, new); i < maps__nr_maps(maps); ) {
+		struct map **maps_by_address = maps__maps_by_address(maps);
 		struct map *pos = maps_by_address[i];
 		struct map *before = NULL, *after = NULL;
 
@@ -766,7 +766,7 @@ sort_again:
 
 		if (use_browser) {
 			pr_debug("overlapping maps in %s (disable tui for more info)\n",
-				map__dso(new)->name);
+				dso__name(map__dso(new)));
 		} else if (verbose >= 2) {
 			pr_debug("overlapping maps:\n");
 			map__fprintf(new, fp);
@@ -820,8 +820,10 @@ sort_again:
 			/* Maps are still ordered, go to next one. */
 			i++;
 			if (after) {
-				__maps__insert(maps, after);
+				err = __maps__insert(maps, after);
 				map__put(after);
+				if (err)
+					goto out_err;
 				if (!maps__maps_by_address_sorted(maps)) {
 					/*
 					 * Sorting broken so invariants don't
@@ -850,7 +852,7 @@ sort_again:
 		check_invariants(maps);
 	}
 	/* Add the map. */
-	__maps__insert(maps, new);
+	err = __maps__insert(maps, new);
 out_err:
 	return err;
 }
@@ -942,6 +944,8 @@ int maps__copy_from(struct maps *dest, struct maps *parent)
 			map__put(new);
 		}
 	}
+	check_invariants(dest);
+
 	up_read(maps__lock(parent));
 	up_write(maps__lock(dest));
 	return err;
@@ -987,7 +991,7 @@ static int map__strcmp_name(const void *name, const void *b)
 {
 	const struct dso *dso = map__dso(*(const struct map **)b);
 
-	return strcmp(name, dso->short_name);
+	return strcmp(name, dso__short_name(dso));
 }
 
 struct map *maps__find_by_name(struct maps *maps, const char *name)
@@ -1006,7 +1010,7 @@ struct map *maps__find_by_name(struct maps *maps, const char *name)
 		if (i < maps__nr_maps(maps) && maps__maps_by_name(maps)) {
 			struct dso *dso = map__dso(maps__maps_by_name(maps)[i]);
 
-			if (dso && strcmp(dso->short_name, name) == 0) {
+			if (dso && strcmp(dso__short_name(dso), name) == 0) {
 				result = map__get(maps__maps_by_name(maps)[i]);
 				done = true;
 			}
@@ -1043,7 +1047,7 @@ struct map *maps__find_by_name(struct maps *maps, const char *name)
 					struct map *pos = maps_by_address[i];
 					struct dso *dso = map__dso(pos);
 
-					if (dso && strcmp(dso->short_name, name) == 0) {
+					if (dso && strcmp(dso__short_name(dso), name) == 0) {
 						result = map__get(pos);
 						break;
 					}
@@ -1097,6 +1101,7 @@ void maps__fixup_end(struct maps *maps)
 		map__set_end(maps_by_address[n - 1], ~0ULL);
 
 	RC_CHK_ACCESS(maps)->ends_broken = false;
+	check_invariants(maps);
 
 	up_write(maps__lock(maps));
 }
@@ -1147,6 +1152,8 @@ int maps__merge_in(struct maps *kmaps, struct map *new_map)
 	    map__start(kmaps_maps_by_address[first_after_]) >= map__end(new_map)) {
 		/* No overlap so regular insert suffices. */
 		int ret = __maps__insert(kmaps, new_map);
+
+		check_invariants(kmaps);
 		up_write(maps__lock(kmaps));
 		return ret;
 	}
@@ -1162,8 +1169,7 @@ int maps__merge_in(struct maps *kmaps, struct map *new_map)
 	}
 	maps__set_maps_by_address(kmaps, merged_maps_by_address);
 	maps__set_maps_by_address_sorted(kmaps, true);
-	zfree(maps__maps_by_name_addr(kmaps));
-	maps__set_maps_by_name_sorted(kmaps, true);
+	__maps__free_maps_by_name(kmaps);
 	maps__set_nr_maps_allocated(kmaps, merged_nr_maps_allocated);
 
 	/* Copy entries before the new_map that can't overlap. */
@@ -1184,6 +1190,7 @@ int maps__merge_in(struct maps *kmaps, struct map *new_map)
 		map__zput(kmaps_maps_by_address[i]);
 
 	free(kmaps_maps_by_address);
+	check_invariants(kmaps);
 	up_write(maps__lock(kmaps));
 	return 0;
 }
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 637cbd4a7b..6dda47bb77 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -10,7 +10,9 @@
 #include <linux/kernel.h>
 #include "map_symbol.h"
 #include "mem-events.h"
+#include "mem-info.h"
 #include "debug.h"
+#include "evsel.h"
 #include "symbol.h"
 #include "pmu.h"
 #include "pmus.h"
@@ -281,7 +283,7 @@ static const char * const tlb_access[] = {
 	"Fault",
 };
 
-int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+int perf_mem__tlb_scnprintf(char *out, size_t sz, const struct mem_info *mem_info)
 {
 	size_t l = 0, i;
 	u64 m = PERF_MEM_TLB_NA;
@@ -291,7 +293,7 @@ int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 	out[0] = '\0';
 
 	if (mem_info)
-		m = mem_info->data_src.mem_dtlb;
+		m = mem_info__const_data_src(mem_info)->mem_dtlb;
 
 	hit = m & PERF_MEM_TLB_HIT;
 	miss = m & PERF_MEM_TLB_MISS;
@@ -359,13 +361,13 @@ static const char * const mem_hops[] = {
 	"board",
 };
 
-static int perf_mem__op_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+static int perf_mem__op_scnprintf(char *out, size_t sz, const struct mem_info *mem_info)
 {
 	u64 op = PERF_MEM_LOCK_NA;
 	int l;
 
 	if (mem_info)
-		op = mem_info->data_src.mem_op;
+		op = mem_info__const_data_src(mem_info)->mem_op;
 
 	if (op & PERF_MEM_OP_NA)
 		l = scnprintf(out, sz, "N/A");
@@ -383,7 +385,7 @@ static int perf_mem__op_scnprintf(char *out, size_t sz, struct mem_info *mem_inf
 	return l;
 }
 
-int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+int perf_mem__lvl_scnprintf(char *out, size_t sz, const struct mem_info *mem_info)
 {
 	union perf_mem_data_src data_src;
 	int printed = 0;
@@ -398,7 +400,7 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 	if (!mem_info)
 		goto na;
 
-	data_src = mem_info->data_src;
+	data_src = *mem_info__const_data_src(mem_info);
 
 	if (data_src.mem_lvl & PERF_MEM_LVL_HIT)
 		memcpy(hit_miss, "hit", 3);
@@ -465,7 +467,7 @@ static const char * const snoopx_access[] = {
 	"Peer",
 };
 
-int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+int perf_mem__snp_scnprintf(char *out, size_t sz, const struct mem_info *mem_info)
 {
 	size_t i, l = 0;
 	u64 m = PERF_MEM_SNOOP_NA;
@@ -474,7 +476,7 @@ int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 	out[0] = '\0';
 
 	if (mem_info)
-		m = mem_info->data_src.mem_snoop;
+		m = mem_info__const_data_src(mem_info)->mem_snoop;
 
 	for (i = 0; m && i < ARRAY_SIZE(snoop_access); i++, m >>= 1) {
 		if (!(m & 0x1))
@@ -488,7 +490,7 @@ int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 
 	m = 0;
 	if (mem_info)
-		m = mem_info->data_src.mem_snoopx;
+		m = mem_info__const_data_src(mem_info)->mem_snoopx;
 
 	for (i = 0; m && i < ARRAY_SIZE(snoopx_access); i++, m >>= 1) {
 		if (!(m & 0x1))
@@ -507,13 +509,13 @@ int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 	return l;
 }
 
-int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+int perf_mem__lck_scnprintf(char *out, size_t sz, const struct mem_info *mem_info)
 {
 	u64 mask = PERF_MEM_LOCK_NA;
 	int l;
 
 	if (mem_info)
-		mask = mem_info->data_src.mem_lock;
+		mask = mem_info__const_data_src(mem_info)->mem_lock;
 
 	if (mask & PERF_MEM_LOCK_NA)
 		l = scnprintf(out, sz, "N/A");
@@ -525,7 +527,7 @@ int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 	return l;
 }
 
-int perf_mem__blk_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+int perf_mem__blk_scnprintf(char *out, size_t sz, const struct mem_info *mem_info)
 {
 	size_t l = 0;
 	u64 mask = PERF_MEM_BLK_NA;
@@ -534,7 +536,7 @@ int perf_mem__blk_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 	out[0] = '\0';
 
 	if (mem_info)
-		mask = mem_info->data_src.mem_blk;
+		mask = mem_info__const_data_src(mem_info)->mem_blk;
 
 	if (!mask || (mask & PERF_MEM_BLK_NA)) {
 		l += scnprintf(out + l, sz - l, " N/A");
@@ -548,7 +550,7 @@ int perf_mem__blk_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 	return l;
 }
 
-int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+int perf_script__meminfo_scnprintf(char *out, size_t sz, const struct mem_info *mem_info)
 {
 	int i = 0;
 
@@ -570,8 +572,8 @@ int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_in
 
 int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
 {
-	union perf_mem_data_src *data_src = &mi->data_src;
-	u64 daddr  = mi->daddr.addr;
+	union perf_mem_data_src *data_src = mem_info__data_src(mi);
+	u64 daddr  = mem_info__daddr(mi)->addr;
 	u64 op     = data_src->mem_op;
 	u64 lvl    = data_src->mem_lvl;
 	u64 snoop  = data_src->mem_snoop;
@@ -698,7 +700,7 @@ do {				\
 		return -1;
 	}
 
-	if (!mi->daddr.ms.map || !mi->iaddr.ms.map) {
+	if (!mem_info__daddr(mi)->ms.map || !mem_info__iaddr(mi)->ms.map) {
 		stats->nomap++;
 		return -1;
 	}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 15d5f0320d..ca31014d79 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -3,13 +3,7 @@
 #define __PERF_MEM_EVENTS_H
 
 #include <stdbool.h>
-#include <stdint.h>
-#include <stdio.h>
 #include <linux/types.h>
-#include <linux/refcount.h>
-#include <linux/perf_event.h>
-#include "stat.h"
-#include "evsel.h"
 
 struct perf_mem_event {
 	bool		record;
@@ -21,13 +15,6 @@ struct perf_mem_event {
 	const char	*event_name;
 };
 
-struct mem_info {
-	struct addr_map_symbol	iaddr;
-	struct addr_map_symbol	daddr;
-	union perf_mem_data_src	data_src;
-	refcount_t		refcnt;
-};
-
 enum {
 	PERF_MEM_EVENTS__LOAD,
 	PERF_MEM_EVENTS__STORE,
@@ -35,6 +22,10 @@ enum {
 	PERF_MEM_EVENTS__MAX,
 };
 
+struct evsel;
+struct mem_info;
+struct perf_pmu;
+
 extern unsigned int perf_mem_events__loads_ldlat;
 extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
 
@@ -49,13 +40,13 @@ bool is_mem_loads_aux_event(struct evsel *leader);
 void perf_pmu__mem_events_list(struct perf_pmu *pmu);
 int perf_mem_events__record_args(const char **rec_argv, int *argv_nr);
 
-int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
-int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
-int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
-int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
-int perf_mem__blk_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__tlb_scnprintf(char *out, size_t sz, const struct mem_info *mem_info);
+int perf_mem__lvl_scnprintf(char *out, size_t sz, const struct mem_info *mem_info);
+int perf_mem__snp_scnprintf(char *out, size_t sz, const struct mem_info *mem_info);
+int perf_mem__lck_scnprintf(char *out, size_t sz, const struct mem_info *mem_info);
+int perf_mem__blk_scnprintf(char *out, size_t sz, const struct mem_info *mem_info);
 
-int perf_script__meminfo_scnprintf(char *bf, size_t size, struct mem_info *mem_info);
+int perf_script__meminfo_scnprintf(char *bf, size_t size, const struct mem_info *mem_info);
 
 struct c2c_stats {
 	u32	nr_entries;
diff --git a/tools/perf/util/mem-info.c b/tools/perf/util/mem-info.c
new file mode 100644
index 0000000000..27d67721a6
--- /dev/null
+++ b/tools/perf/util/mem-info.c
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/zalloc.h>
+#include "mem-info.h"
+
+struct mem_info *mem_info__get(struct mem_info *mi)
+{
+	struct mem_info *result;
+
+	if (RC_CHK_GET(result, mi))
+		refcount_inc(mem_info__refcnt(mi));
+
+	return result;
+}
+
+void mem_info__put(struct mem_info *mi)
+{
+	if (mi && refcount_dec_and_test(mem_info__refcnt(mi))) {
+		addr_map_symbol__exit(mem_info__iaddr(mi));
+		addr_map_symbol__exit(mem_info__daddr(mi));
+		RC_CHK_FREE(mi);
+	} else {
+		RC_CHK_PUT(mi);
+	}
+}
+
+struct mem_info *mem_info__new(void)
+{
+	struct mem_info *result = NULL;
+	RC_STRUCT(mem_info) *mi = zalloc(sizeof(*mi));
+
+	if (ADD_RC_CHK(result, mi))
+		refcount_set(mem_info__refcnt(result), 1);
+
+	return result;
+}
diff --git a/tools/perf/util/mem-info.h b/tools/perf/util/mem-info.h
new file mode 100644
index 0000000000..0f68e29f31
--- /dev/null
+++ b/tools/perf/util/mem-info.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_MEM_INFO_H
+#define __PERF_MEM_INFO_H
+
+#include <linux/refcount.h>
+#include <linux/perf_event.h>
+#include <internal/rc_check.h>
+#include "map_symbol.h"
+
+DECLARE_RC_STRUCT(mem_info) {
+	struct addr_map_symbol	iaddr;
+	struct addr_map_symbol	daddr;
+	union perf_mem_data_src	data_src;
+	refcount_t		refcnt;
+};
+
+struct mem_info *mem_info__new(void);
+struct mem_info *mem_info__get(struct mem_info *mi);
+void   mem_info__put(struct mem_info *mi);
+
+static inline void __mem_info__zput(struct mem_info **mi)
+{
+	mem_info__put(*mi);
+	*mi = NULL;
+}
+
+#define mem_info__zput(mi) __mem_info__zput(&mi)
+
+static inline struct addr_map_symbol *mem_info__iaddr(struct mem_info *mi)
+{
+	return &RC_CHK_ACCESS(mi)->iaddr;
+}
+
+static inline struct addr_map_symbol *mem_info__daddr(struct mem_info *mi)
+{
+	return &RC_CHK_ACCESS(mi)->daddr;
+}
+
+static inline union perf_mem_data_src *mem_info__data_src(struct mem_info *mi)
+{
+	return &RC_CHK_ACCESS(mi)->data_src;
+}
+
+static inline const union perf_mem_data_src *mem_info__const_data_src(const struct mem_info *mi)
+{
+	return &RC_CHK_ACCESS(mi)->data_src;
+}
+
+static inline refcount_t *mem_info__refcnt(struct mem_info *mi)
+{
+	return &RC_CHK_ACCESS(mi)->refcnt;
+}
+
+#endif /* __PERF_MEM_INFO_H */
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 79ef6095ab..69f6a46402 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -455,7 +455,7 @@ static int metricgroup__add_to_mep_groups(const struct pmu_metric *pm,
 	const char *g;
 	char *omg, *mg;
 
-	mg = strdup(pm->metric_group ?: "No_group");
+	mg = strdup(pm->metric_group ?: pm->metric_name);
 	if (!mg)
 		return -ENOMEM;
 	omg = mg;
@@ -466,7 +466,7 @@ static int metricgroup__add_to_mep_groups(const struct pmu_metric *pm,
 		if (strlen(g))
 			me = mep_lookup(groups, g, pm->metric_name);
 		else
-			me = mep_lookup(groups, "No_group", pm->metric_name);
+			me = mep_lookup(groups, pm->metric_name, pm->metric_name);
 
 		if (me) {
 			me->metric_desc = pm->desc;
@@ -1502,7 +1502,8 @@ static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu,
 	pr_debug("Parsing metric events '%s'\n", events.buf);
 	parse_events_error__init(&parse_error);
 	ret = __parse_events(parsed_evlist, events.buf, /*pmu_filter=*/NULL,
-			     &parse_error, fake_pmu, /*warn_if_reordered=*/false);
+			     &parse_error, fake_pmu, /*warn_if_reordered=*/false,
+			     /*fake_tp=*/false);
 	if (ret) {
 		parse_events_error__print(&parse_error, events.buf);
 		goto err_out;
@@ -1690,12 +1691,15 @@ int metricgroup__parse_groups(struct evlist *perf_evlist,
 			      bool metric_no_threshold,
 			      const char *user_requested_cpu_list,
 			      bool system_wide,
+			      bool hardware_aware_grouping,
 			      struct rblist *metric_events)
 {
 	const struct pmu_metrics_table *table = pmu_metrics_table__find();
 
 	if (!table)
 		return -EINVAL;
+	if (hardware_aware_grouping)
+		pr_debug("Use hardware aware grouping instead of traditional metric grouping method\n");
 
 	return parse_groups(perf_evlist, pmu, str, metric_no_group, metric_no_merge,
 			    metric_no_threshold, user_requested_cpu_list, system_wide,
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index d5325c6ec8..779f6ede1b 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -77,6 +77,7 @@ int metricgroup__parse_groups(struct evlist *perf_evlist,
 			      bool metric_no_threshold,
 			      const char *user_requested_cpu_list,
 			      bool system_wide,
+			      bool hardware_aware_grouping,
 			      struct rblist *metric_events);
 int metricgroup__parse_groups_test(struct evlist *evlist,
 				   const struct pmu_metrics_table *table,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 6f8b0fa176..6ed0f9c558 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -34,11 +34,12 @@
 #ifdef PARSER_DEBUG
 extern int parse_events_debug;
 #endif
-static int get_config_terms(struct parse_events_terms *head_config, struct list_head *head_terms);
+static int get_config_terms(const struct parse_events_terms *head_config,
+			    struct list_head *head_terms);
 static int parse_events_terms__copy(const struct parse_events_terms *src,
 				    struct parse_events_terms *dest);
 
-struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
+const struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_CPU_CYCLES] = {
 		.symbol = "cpu-cycles",
 		.alias  = "cycles",
@@ -81,7 +82,7 @@ struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
 	},
 };
 
-struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
+const struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 	[PERF_COUNT_SW_CPU_CLOCK] = {
 		.symbol = "cpu-clock",
 		.alias  = "",
@@ -154,7 +155,7 @@ const char *event_type(int type)
 	return "unknown";
 }
 
-static char *get_config_str(struct parse_events_terms *head_terms,
+static char *get_config_str(const struct parse_events_terms *head_terms,
 			    enum parse_events__term_type type_term)
 {
 	struct parse_events_term *term;
@@ -169,12 +170,12 @@ static char *get_config_str(struct parse_events_terms *head_terms,
 	return NULL;
 }
 
-static char *get_config_metric_id(struct parse_events_terms *head_terms)
+static char *get_config_metric_id(const struct parse_events_terms *head_terms)
 {
 	return get_config_str(head_terms, PARSE_EVENTS__TERM_TYPE_METRIC_ID);
 }
 
-static char *get_config_name(struct parse_events_terms *head_terms)
+static char *get_config_name(const struct parse_events_terms *head_terms)
 {
 	return get_config_str(head_terms, PARSE_EVENTS__TERM_TYPE_NAME);
 }
@@ -358,7 +359,7 @@ static int config_term_common(struct perf_event_attr *attr,
 			      struct parse_events_term *term,
 			      struct parse_events_error *err);
 static int config_attr(struct perf_event_attr *attr,
-		       struct parse_events_terms *head,
+		       const struct parse_events_terms *head,
 		       struct parse_events_error *err,
 		       config_term_func_t config_term);
 
@@ -442,17 +443,21 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
 	return strcmp(parse_state->pmu_filter, pmu->name) != 0;
 }
 
+static int parse_events_add_pmu(struct parse_events_state *parse_state,
+				struct list_head *list, struct perf_pmu *pmu,
+				const struct parse_events_terms *const_parsed_terms,
+				bool auto_merge_stats);
+
 int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 			   struct parse_events_state *parse_state,
-			   struct parse_events_terms *head_config)
+			   struct parse_events_terms *parsed_terms)
 {
 	struct perf_pmu *pmu = NULL;
 	bool found_supported = false;
-	const char *config_name = get_config_name(head_config);
-	const char *metric_id = get_config_metric_id(head_config);
+	const char *config_name = get_config_name(parsed_terms);
+	const char *metric_id = get_config_metric_id(parsed_terms);
 
-	/* Legacy cache events are only supported by core PMUs. */
-	while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
+	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
 		LIST_HEAD(config_terms);
 		struct perf_event_attr attr;
 		int ret;
@@ -460,6 +465,24 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 		if (parse_events__filter_pmu(parse_state, pmu))
 			continue;
 
+		if (perf_pmu__have_event(pmu, name)) {
+			/*
+			 * The PMU has the event so add as not a legacy cache
+			 * event.
+			 */
+			ret = parse_events_add_pmu(parse_state, list, pmu,
+						   parsed_terms,
+						   perf_pmu__auto_merge_stats(pmu));
+			if (ret)
+				return ret;
+			continue;
+		}
+
+		if (!pmu->is_core) {
+			/* Legacy cache events are only supported by core PMUs. */
+			continue;
+		}
+
 		memset(&attr, 0, sizeof(attr));
 		attr.type = PERF_TYPE_HW_CACHE;
 
@@ -469,11 +492,12 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 
 		found_supported = true;
 
-		if (head_config) {
-			if (config_attr(&attr, head_config, parse_state->error, config_term_common))
+		if (parsed_terms) {
+			if (config_attr(&attr, parsed_terms, parse_state->error,
+					config_term_common))
 				return -EINVAL;
 
-			if (get_config_terms(head_config, &config_terms))
+			if (get_config_terms(parsed_terms, &config_terms))
 				return -ENOMEM;
 		}
 
@@ -519,13 +543,15 @@ static void tracepoint_error(struct parse_events_error *e, int err,
 	parse_events_error__handle(e, column, strdup(str), strdup(help));
 }
 
-static int add_tracepoint(struct list_head *list, int *idx,
+static int add_tracepoint(struct parse_events_state *parse_state,
+			  struct list_head *list,
 			  const char *sys_name, const char *evt_name,
 			  struct parse_events_error *err,
 			  struct parse_events_terms *head_config, void *loc_)
 {
 	YYLTYPE *loc = loc_;
-	struct evsel *evsel = evsel__newtp_idx(sys_name, evt_name, (*idx)++);
+	struct evsel *evsel = evsel__newtp_idx(sys_name, evt_name, parse_state->idx++,
+					       !parse_state->fake_tp);
 
 	if (IS_ERR(evsel)) {
 		tracepoint_error(err, PTR_ERR(evsel), sys_name, evt_name, loc->first_column);
@@ -544,7 +570,8 @@ static int add_tracepoint(struct list_head *list, int *idx,
 	return 0;
 }
 
-static int add_tracepoint_multi_event(struct list_head *list, int *idx,
+static int add_tracepoint_multi_event(struct parse_events_state *parse_state,
+				      struct list_head *list,
 				      const char *sys_name, const char *evt_name,
 				      struct parse_events_error *err,
 				      struct parse_events_terms *head_config, YYLTYPE *loc)
@@ -578,7 +605,7 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 
 		found++;
 
-		ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name,
+		ret = add_tracepoint(parse_state, list, sys_name, evt_ent->d_name,
 				     err, head_config, loc);
 	}
 
@@ -592,19 +619,21 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 	return ret;
 }
 
-static int add_tracepoint_event(struct list_head *list, int *idx,
+static int add_tracepoint_event(struct parse_events_state *parse_state,
+				struct list_head *list,
 				const char *sys_name, const char *evt_name,
 				struct parse_events_error *err,
 				struct parse_events_terms *head_config, YYLTYPE *loc)
 {
 	return strpbrk(evt_name, "*?") ?
-		add_tracepoint_multi_event(list, idx, sys_name, evt_name,
+		add_tracepoint_multi_event(parse_state, list, sys_name, evt_name,
 					   err, head_config, loc) :
-		add_tracepoint(list, idx, sys_name, evt_name,
+		add_tracepoint(parse_state, list, sys_name, evt_name,
 			       err, head_config, loc);
 }
 
-static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
+static int add_tracepoint_multi_sys(struct parse_events_state *parse_state,
+				    struct list_head *list,
 				    const char *sys_name, const char *evt_name,
 				    struct parse_events_error *err,
 				    struct parse_events_terms *head_config, YYLTYPE *loc)
@@ -630,7 +659,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 		if (!strglobmatch(events_ent->d_name, sys_name))
 			continue;
 
-		ret = add_tracepoint_event(list, idx, events_ent->d_name,
+		ret = add_tracepoint_event(parse_state, list, events_ent->d_name,
 					   evt_name, err, head_config, loc);
 	}
 
@@ -1085,7 +1114,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 #endif
 
 static int config_attr(struct perf_event_attr *attr,
-		       struct parse_events_terms *head,
+		       const struct parse_events_terms *head,
 		       struct parse_events_error *err,
 		       config_term_func_t config_term)
 {
@@ -1098,7 +1127,8 @@ static int config_attr(struct perf_event_attr *attr,
 	return 0;
 }
 
-static int get_config_terms(struct parse_events_terms *head_config, struct list_head *head_terms)
+static int get_config_terms(const struct parse_events_terms *head_config,
+			    struct list_head *head_terms)
 {
 #define ADD_CONFIG_TERM(__type, __weak)				\
 	struct evsel_config_term *__t;			\
@@ -1266,7 +1296,8 @@ static int get_config_chgs(struct perf_pmu *pmu, struct parse_events_terms *head
 	return 0;
 }
 
-int parse_events_add_tracepoint(struct list_head *list, int *idx,
+int parse_events_add_tracepoint(struct parse_events_state *parse_state,
+				struct list_head *list,
 				const char *sys, const char *event,
 				struct parse_events_error *err,
 				struct parse_events_terms *head_config, void *loc_)
@@ -1282,14 +1313,14 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 	}
 
 	if (strpbrk(sys, "*?"))
-		return add_tracepoint_multi_sys(list, idx, sys, event,
+		return add_tracepoint_multi_sys(parse_state, list, sys, event,
 						err, head_config, loc);
 	else
-		return add_tracepoint_event(list, idx, sys, event,
+		return add_tracepoint_event(parse_state, list, sys, event,
 					    err, head_config, loc);
 #else
+	(void)parse_state;
 	(void)list;
-	(void)idx;
 	(void)sys;
 	(void)event;
 	(void)head_config;
@@ -1302,7 +1333,7 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 static int __parse_events_add_numeric(struct parse_events_state *parse_state,
 				struct list_head *list,
 				struct perf_pmu *pmu, u32 type, u32 extended_type,
-				u64 config, struct parse_events_terms *head_config)
+				u64 config, const struct parse_events_terms *head_config)
 {
 	struct perf_event_attr attr;
 	LIST_HEAD(config_terms);
@@ -1338,7 +1369,7 @@ static int __parse_events_add_numeric(struct parse_events_state *parse_state,
 int parse_events_add_numeric(struct parse_events_state *parse_state,
 			     struct list_head *list,
 			     u32 type, u64 config,
-			     struct parse_events_terms *head_config,
+			     const struct parse_events_terms *head_config,
 			     bool wildcard)
 {
 	struct perf_pmu *pmu = NULL;
@@ -1385,56 +1416,34 @@ static bool config_term_percore(struct list_head *config_terms)
 	return false;
 }
 
-int parse_events_add_pmu(struct parse_events_state *parse_state,
-			 struct list_head *list, const char *name,
-			 const struct parse_events_terms *const_parsed_terms,
-			 bool auto_merge_stats, void *loc_)
+static int parse_events_add_pmu(struct parse_events_state *parse_state,
+				struct list_head *list, struct perf_pmu *pmu,
+				const struct parse_events_terms *const_parsed_terms,
+				bool auto_merge_stats)
 {
 	struct perf_event_attr attr;
 	struct perf_pmu_info info;
-	struct perf_pmu *pmu;
 	struct evsel *evsel;
 	struct parse_events_error *err = parse_state->error;
-	YYLTYPE *loc = loc_;
 	LIST_HEAD(config_terms);
 	struct parse_events_terms parsed_terms;
 	bool alias_rewrote_terms = false;
 
-	pmu = parse_state->fake_pmu ?: perf_pmus__find(name);
-
-	if (!pmu) {
-		char *err_str;
-
-		if (asprintf(&err_str,
-				"Cannot find PMU `%s'. Missing kernel support?",
-				name) >= 0)
-			parse_events_error__handle(err, loc->first_column, err_str, NULL);
-		return -EINVAL;
-	}
-
-	parse_events_terms__init(&parsed_terms);
-	if (const_parsed_terms) {
-		int ret = parse_events_terms__copy(const_parsed_terms, &parsed_terms);
-
-		if (ret)
-			return ret;
-	}
-
 	if (verbose > 1) {
 		struct strbuf sb;
 
 		strbuf_init(&sb, /*hint=*/ 0);
-		if (pmu->selectable && list_empty(&parsed_terms.terms)) {
-			strbuf_addf(&sb, "%s//", name);
+		if (pmu->selectable && const_parsed_terms &&
+		    list_empty(&const_parsed_terms->terms)) {
+			strbuf_addf(&sb, "%s//", pmu->name);
 		} else {
-			strbuf_addf(&sb, "%s/", name);
-			parse_events_terms__to_strbuf(&parsed_terms, &sb);
+			strbuf_addf(&sb, "%s/", pmu->name);
+			parse_events_terms__to_strbuf(const_parsed_terms, &sb);
 			strbuf_addch(&sb, '/');
 		}
 		fprintf(stderr, "Attempt to add: %s\n", sb.buf);
 		strbuf_release(&sb);
 	}
-	fix_raw(&parsed_terms, pmu);
 
 	memset(&attr, 0, sizeof(attr));
 	if (pmu->perf_event_attr_init_default)
@@ -1442,7 +1451,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	attr.type = pmu->type;
 
-	if (list_empty(&parsed_terms.terms)) {
+	if (!const_parsed_terms || list_empty(&const_parsed_terms->terms)) {
 		evsel = __add_event(list, &parse_state->idx, &attr,
 				    /*init_attr=*/true, /*name=*/NULL,
 				    /*metric_id=*/NULL, pmu,
@@ -1451,6 +1460,15 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		return evsel ? 0 : -ENOMEM;
 	}
 
+	parse_events_terms__init(&parsed_terms);
+	if (const_parsed_terms) {
+		int ret = parse_events_terms__copy(const_parsed_terms, &parsed_terms);
+
+		if (ret)
+			return ret;
+	}
+	fix_raw(&parsed_terms, pmu);
+
 	/* Configure attr/terms with a known PMU, this will set hardcoded terms. */
 	if (config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) {
 		parse_events_terms__exit(&parsed_terms);
@@ -1469,7 +1487,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 
 		strbuf_init(&sb, /*hint=*/ 0);
 		parse_events_terms__to_strbuf(&parsed_terms, &sb);
-		fprintf(stderr, "..after resolving event: %s/%s/\n", name, sb.buf);
+		fprintf(stderr, "..after resolving event: %s/%s/\n", pmu->name, sb.buf);
 		strbuf_release(&sb);
 	}
 
@@ -1583,8 +1601,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			continue;
 
 		auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
-		if (!parse_events_add_pmu(parse_state, list, pmu->name,
-					  &parsed_terms, auto_merge_stats, loc)) {
+		if (!parse_events_add_pmu(parse_state, list, pmu,
+					  &parsed_terms, auto_merge_stats)) {
 			struct strbuf sb;
 
 			strbuf_init(&sb, /*hint=*/ 0);
@@ -1596,8 +1614,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 	}
 
 	if (parse_state->fake_pmu) {
-		if (!parse_events_add_pmu(parse_state, list, event_name, &parsed_terms,
-					  /*auto_merge_stats=*/true, loc)) {
+		if (!parse_events_add_pmu(parse_state, list, parse_state->fake_pmu, &parsed_terms,
+					  /*auto_merge_stats=*/true)) {
 			struct strbuf sb;
 
 			strbuf_init(&sb, /*hint=*/ 0);
@@ -1618,10 +1636,59 @@ out_err:
 	return ok ? 0 : -1;
 }
 
-int parse_events__modifier_group(struct list_head *list,
-				 char *event_mod)
+int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state,
+					const char *event_or_pmu,
+					const struct parse_events_terms *const_parsed_terms,
+					struct list_head **listp,
+					void *loc_)
 {
-	return parse_events__modifier_event(list, event_mod, true);
+	YYLTYPE *loc = loc_;
+	struct perf_pmu *pmu;
+	int ok = 0;
+	char *help;
+
+	*listp = malloc(sizeof(**listp));
+	if (!*listp)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(*listp);
+
+	/* Attempt to add to list assuming event_or_pmu is a PMU name. */
+	pmu = parse_state->fake_pmu ?: perf_pmus__find(event_or_pmu);
+	if (pmu && !parse_events_add_pmu(parse_state, *listp, pmu, const_parsed_terms,
+					/*auto_merge_stats=*/false))
+		return 0;
+
+	pmu = NULL;
+	/* Failed to add, try wildcard expansion of event_or_pmu as a PMU name. */
+	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
+		if (!parse_events__filter_pmu(parse_state, pmu) &&
+		    perf_pmu__match(pmu, event_or_pmu)) {
+			bool auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
+
+			if (!parse_events_add_pmu(parse_state, *listp, pmu,
+						  const_parsed_terms,
+						  auto_merge_stats)) {
+				ok++;
+				parse_state->wild_card_pmus = true;
+			}
+		}
+	}
+	if (ok)
+		return 0;
+
+	/* Failure to add, assume event_or_pmu is an event name. */
+	zfree(listp);
+	if (!parse_events_multi_pmu_add(parse_state, event_or_pmu, const_parsed_terms, listp, loc))
+		return 0;
+
+	if (asprintf(&help, "Unable to find PMU or event on a PMU of '%s'", event_or_pmu) < 0)
+		help = NULL;
+	parse_events_error__handle(parse_state->error, loc->first_column,
+				strdup("Bad event or PMU"),
+				help);
+	zfree(listp);
+	return -EINVAL;
 }
 
 void parse_events__set_leader(char *name, struct list_head *list)
@@ -1635,213 +1702,146 @@ void parse_events__set_leader(char *name, struct list_head *list)
 
 	leader = list_first_entry(list, struct evsel, core.node);
 	__perf_evlist__set_leader(list, &leader->core);
+	zfree(&leader->group_name);
 	leader->group_name = name;
 }
 
-/* list_event is assumed to point to malloc'ed memory */
-void parse_events_update_lists(struct list_head *list_event,
-			       struct list_head *list_all)
+static int parse_events__modifier_list(struct parse_events_state *parse_state,
+				       YYLTYPE *loc,
+				       struct list_head *list,
+				       struct parse_events_modifier mod,
+				       bool group)
 {
-	/*
-	 * Called for single event definition. Update the
-	 * 'all event' list, and reinit the 'single event'
-	 * list, for next event definition.
-	 */
-	list_splice_tail(list_event, list_all);
-	free(list_event);
-}
-
-struct event_modifier {
-	int eu;
-	int ek;
-	int eh;
-	int eH;
-	int eG;
-	int eI;
-	int precise;
-	int precise_max;
-	int exclude_GH;
-	int sample_read;
-	int pinned;
-	int weak;
-	int exclusive;
-	int bpf_counter;
-};
+	struct evsel *evsel;
+
+	if (!group && mod.weak) {
+		parse_events_error__handle(parse_state->error, loc->first_column,
+					   strdup("Weak modifier is for use with groups"), NULL);
+		return -EINVAL;
+	}
 
-static int get_event_modifier(struct event_modifier *mod, char *str,
-			       struct evsel *evsel)
-{
-	int eu = evsel ? evsel->core.attr.exclude_user : 0;
-	int ek = evsel ? evsel->core.attr.exclude_kernel : 0;
-	int eh = evsel ? evsel->core.attr.exclude_hv : 0;
-	int eH = evsel ? evsel->core.attr.exclude_host : 0;
-	int eG = evsel ? evsel->core.attr.exclude_guest : 0;
-	int eI = evsel ? evsel->core.attr.exclude_idle : 0;
-	int precise = evsel ? evsel->core.attr.precise_ip : 0;
-	int precise_max = 0;
-	int sample_read = 0;
-	int pinned = evsel ? evsel->core.attr.pinned : 0;
-	int exclusive = evsel ? evsel->core.attr.exclusive : 0;
-
-	int exclude = eu | ek | eh;
-	int exclude_GH = evsel ? evsel->exclude_GH : 0;
-	int weak = 0;
-	int bpf_counter = 0;
-
-	memset(mod, 0, sizeof(*mod));
-
-	while (*str) {
-		if (*str == 'u') {
+	__evlist__for_each_entry(list, evsel) {
+		/* Translate modifiers into the equivalent evsel excludes. */
+		int eu = group ? evsel->core.attr.exclude_user : 0;
+		int ek = group ? evsel->core.attr.exclude_kernel : 0;
+		int eh = group ? evsel->core.attr.exclude_hv : 0;
+		int eH = group ? evsel->core.attr.exclude_host : 0;
+		int eG = group ? evsel->core.attr.exclude_guest : 0;
+		int exclude = eu | ek | eh;
+		int exclude_GH = group ? evsel->exclude_GH : 0;
+
+		if (mod.precise) {
+			/* use of precise requires exclude_guest */
+			eG = 1;
+		}
+		if (mod.user) {
 			if (!exclude)
 				exclude = eu = ek = eh = 1;
 			if (!exclude_GH && !perf_guest)
 				eG = 1;
 			eu = 0;
-		} else if (*str == 'k') {
+		}
+		if (mod.kernel) {
 			if (!exclude)
 				exclude = eu = ek = eh = 1;
 			ek = 0;
-		} else if (*str == 'h') {
+		}
+		if (mod.hypervisor) {
 			if (!exclude)
 				exclude = eu = ek = eh = 1;
 			eh = 0;
-		} else if (*str == 'G') {
+		}
+		if (mod.guest) {
 			if (!exclude_GH)
 				exclude_GH = eG = eH = 1;
 			eG = 0;
-		} else if (*str == 'H') {
+		}
+		if (mod.host) {
 			if (!exclude_GH)
 				exclude_GH = eG = eH = 1;
 			eH = 0;
-		} else if (*str == 'I') {
-			eI = 1;
-		} else if (*str == 'p') {
-			precise++;
-			/* use of precise requires exclude_guest */
-			if (!exclude_GH)
-				eG = 1;
-		} else if (*str == 'P') {
-			precise_max = 1;
-		} else if (*str == 'S') {
-			sample_read = 1;
-		} else if (*str == 'D') {
-			pinned = 1;
-		} else if (*str == 'e') {
-			exclusive = 1;
-		} else if (*str == 'W') {
-			weak = 1;
-		} else if (*str == 'b') {
-			bpf_counter = 1;
-		} else
-			break;
-
-		++str;
+		}
+		evsel->core.attr.exclude_user   = eu;
+		evsel->core.attr.exclude_kernel = ek;
+		evsel->core.attr.exclude_hv     = eh;
+		evsel->core.attr.exclude_host   = eH;
+		evsel->core.attr.exclude_guest  = eG;
+		evsel->exclude_GH               = exclude_GH;
+
+		/* Simple modifiers copied to the evsel. */
+		if (mod.precise) {
+			u8 precise = evsel->core.attr.precise_ip + mod.precise;
+			/*
+			 * precise ip:
+			 *
+			 *  0 - SAMPLE_IP can have arbitrary skid
+			 *  1 - SAMPLE_IP must have constant skid
+			 *  2 - SAMPLE_IP requested to have 0 skid
+			 *  3 - SAMPLE_IP must have 0 skid
+			 *
+			 *  See also PERF_RECORD_MISC_EXACT_IP
+			 */
+			if (precise > 3) {
+				char *help;
+
+				if (asprintf(&help,
+					     "Maximum combined precise value is 3, adding precision to \"%s\"",
+					     evsel__name(evsel)) > 0) {
+					parse_events_error__handle(parse_state->error,
+								   loc->first_column,
+								   help, NULL);
+				}
+				return -EINVAL;
+			}
+			evsel->core.attr.precise_ip = precise;
+		}
+		if (mod.precise_max)
+			evsel->precise_max = 1;
+		if (mod.non_idle)
+			evsel->core.attr.exclude_idle = 1;
+		if (mod.sample_read)
+			evsel->sample_read = 1;
+		if (mod.pinned && evsel__is_group_leader(evsel))
+			evsel->core.attr.pinned = 1;
+		if (mod.exclusive && evsel__is_group_leader(evsel))
+			evsel->core.attr.exclusive = 1;
+		if (mod.weak)
+			evsel->weak_group = true;
+		if (mod.bpf)
+			evsel->bpf_counter = true;
 	}
-
-	/*
-	 * precise ip:
-	 *
-	 *  0 - SAMPLE_IP can have arbitrary skid
-	 *  1 - SAMPLE_IP must have constant skid
-	 *  2 - SAMPLE_IP requested to have 0 skid
-	 *  3 - SAMPLE_IP must have 0 skid
-	 *
-	 *  See also PERF_RECORD_MISC_EXACT_IP
-	 */
-	if (precise > 3)
-		return -EINVAL;
-
-	mod->eu = eu;
-	mod->ek = ek;
-	mod->eh = eh;
-	mod->eH = eH;
-	mod->eG = eG;
-	mod->eI = eI;
-	mod->precise = precise;
-	mod->precise_max = precise_max;
-	mod->exclude_GH = exclude_GH;
-	mod->sample_read = sample_read;
-	mod->pinned = pinned;
-	mod->weak = weak;
-	mod->bpf_counter = bpf_counter;
-	mod->exclusive = exclusive;
-
 	return 0;
 }
 
-/*
- * Basic modifier sanity check to validate it contains only one
- * instance of any modifier (apart from 'p') present.
- */
-static int check_modifier(char *str)
+int parse_events__modifier_group(struct parse_events_state *parse_state, void *loc,
+				 struct list_head *list,
+				 struct parse_events_modifier mod)
 {
-	char *p = str;
-
-	/* The sizeof includes 0 byte as well. */
-	if (strlen(str) > (sizeof("ukhGHpppPSDIWeb") - 1))
-		return -1;
-
-	while (*p) {
-		if (*p != 'p' && strchr(p + 1, *p))
-			return -1;
-		p++;
-	}
-
-	return 0;
+	return parse_events__modifier_list(parse_state, loc, list, mod, /*group=*/true);
 }
 
-int parse_events__modifier_event(struct list_head *list, char *str, bool add)
+int parse_events__modifier_event(struct parse_events_state *parse_state, void *loc,
+				 struct list_head *list,
+				 struct parse_events_modifier mod)
 {
-	struct evsel *evsel;
-	struct event_modifier mod;
-
-	if (str == NULL)
-		return 0;
-
-	if (check_modifier(str))
-		return -EINVAL;
-
-	if (!add && get_event_modifier(&mod, str, NULL))
-		return -EINVAL;
-
-	__evlist__for_each_entry(list, evsel) {
-		if (add && get_event_modifier(&mod, str, evsel))
-			return -EINVAL;
-
-		evsel->core.attr.exclude_user   = mod.eu;
-		evsel->core.attr.exclude_kernel = mod.ek;
-		evsel->core.attr.exclude_hv     = mod.eh;
-		evsel->core.attr.precise_ip     = mod.precise;
-		evsel->core.attr.exclude_host   = mod.eH;
-		evsel->core.attr.exclude_guest  = mod.eG;
-		evsel->core.attr.exclude_idle   = mod.eI;
-		evsel->exclude_GH          = mod.exclude_GH;
-		evsel->sample_read         = mod.sample_read;
-		evsel->precise_max         = mod.precise_max;
-		evsel->weak_group	   = mod.weak;
-		evsel->bpf_counter	   = mod.bpf_counter;
-
-		if (evsel__is_group_leader(evsel)) {
-			evsel->core.attr.pinned = mod.pinned;
-			evsel->core.attr.exclusive = mod.exclusive;
-		}
-	}
-
-	return 0;
+	return parse_events__modifier_list(parse_state, loc, list, mod, /*group=*/false);
 }
 
-int parse_events_name(struct list_head *list, const char *name)
+int parse_events__set_default_name(struct list_head *list, char *name)
 {
 	struct evsel *evsel;
+	bool used_name = false;
 
 	__evlist__for_each_entry(list, evsel) {
 		if (!evsel->name) {
-			evsel->name = strdup(name);
+			evsel->name = used_name ? strdup(name) : name;
+			used_name = true;
 			if (!evsel->name)
 				return -ENOMEM;
 		}
 	}
-
+	if (!used_name)
+		free(name);
 	return 0;
 }
 
@@ -2121,7 +2121,7 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list)
 
 int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filter,
 		   struct parse_events_error *err, struct perf_pmu *fake_pmu,
-		   bool warn_if_reordered)
+		   bool warn_if_reordered, bool fake_tp)
 {
 	struct parse_events_state parse_state = {
 		.list	  = LIST_HEAD_INIT(parse_state.list),
@@ -2129,6 +2129,7 @@ int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filte
 		.error	  = err,
 		.stoken	  = PE_START_EVENTS,
 		.fake_pmu = fake_pmu,
+		.fake_tp  = fake_tp,
 		.pmu_filter = pmu_filter,
 		.match_legacy_cache_terms = true,
 	};
@@ -2338,7 +2339,8 @@ int parse_events_option(const struct option *opt, const char *str,
 
 	parse_events_error__init(&err);
 	ret = __parse_events(*args->evlistp, str, args->pmu_filter, &err,
-			     /*fake_pmu=*/NULL, /*warn_if_reordered=*/true);
+			     /*fake_pmu=*/NULL, /*warn_if_reordered=*/true,
+			     /*fake_tp=*/false);
 
 	if (ret) {
 		parse_events_error__print(&err, str);
@@ -2576,7 +2578,7 @@ int parse_events_term__term(struct parse_events_term **term,
 }
 
 int parse_events_term__clone(struct parse_events_term **new,
-			     struct parse_events_term *term)
+			     const struct parse_events_term *term)
 {
 	char *str;
 	struct parse_events_term temp = *term;
@@ -2691,15 +2693,6 @@ int parse_events_terms__to_strbuf(const struct parse_events_terms *terms, struct
 	return 0;
 }
 
-void parse_events_evlist_error(struct parse_events_state *parse_state,
-			       int idx, const char *str)
-{
-	if (!parse_state->error)
-		return;
-
-	parse_events_error__handle(parse_state->error, idx, strdup(str), NULL);
-}
-
 static void config_terms_list(char *buf, size_t buf_sz)
 {
 	int i;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 809359e854..e13de2c8b7 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -32,14 +32,14 @@ int parse_events_option_new_evlist(const struct option *opt, const char *str, in
 __attribute__((nonnull(1, 2, 4)))
 int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filter,
 		   struct parse_events_error *error, struct perf_pmu *fake_pmu,
-		   bool warn_if_reordered);
+		   bool warn_if_reordered, bool fake_tp);
 
 __attribute__((nonnull(1, 2, 3)))
 static inline int parse_events(struct evlist *evlist, const char *str,
 			       struct parse_events_error *err)
 {
 	return __parse_events(evlist, str, /*pmu_filter=*/NULL, err, /*fake_pmu=*/NULL,
-			      /*warn_if_reordered=*/true);
+			      /*warn_if_reordered=*/true, /*fake_tp=*/false);
 }
 
 int parse_event(struct evlist *evlist, const char *str);
@@ -152,6 +152,8 @@ struct parse_events_state {
 	int			   stoken;
 	/* Special fake PMU marker for testing. */
 	struct perf_pmu		  *fake_pmu;
+	/* Skip actual tracepoint processing for testing. */
+	bool			   fake_tp;
 	/* If non-null, when wildcard matching only match the given PMU. */
 	const char		  *pmu_filter;
 	/* Should PE_LEGACY_NAME tokens be generated for config terms? */
@@ -178,7 +180,7 @@ int parse_events_term__term(struct parse_events_term **term,
 			    enum parse_events__term_type term_rhs,
 			    void *loc_term, void *loc_val);
 int parse_events_term__clone(struct parse_events_term **new,
-			     struct parse_events_term *term);
+			     const struct parse_events_term *term);
 void parse_events_term__delete(struct parse_events_term *term);
 
 void parse_events_terms__delete(struct parse_events_terms *terms);
@@ -186,33 +188,49 @@ void parse_events_terms__init(struct parse_events_terms *terms);
 void parse_events_terms__exit(struct parse_events_terms *terms);
 int parse_events_terms(struct parse_events_terms *terms, const char *str, FILE *input);
 int parse_events_terms__to_strbuf(const struct parse_events_terms *terms, struct strbuf *sb);
-int parse_events__modifier_event(struct list_head *list, char *str, bool add);
-int parse_events__modifier_group(struct list_head *list, char *event_mod);
-int parse_events_name(struct list_head *list, const char *name);
-int parse_events_add_tracepoint(struct list_head *list, int *idx,
+
+struct parse_events_modifier {
+	u8 precise;	/* Number of repeated 'p' for precision. */
+	bool precise_max : 1;	/* 'P' */
+	bool non_idle : 1;	/* 'I' */
+	bool sample_read : 1;	/* 'S' */
+	bool pinned : 1;	/* 'D' */
+	bool exclusive : 1;	/* 'e' */
+	bool weak : 1;		/* 'W' */
+	bool bpf : 1;		/* 'b' */
+	bool user : 1;		/* 'u' */
+	bool kernel : 1;	/* 'k' */
+	bool hypervisor : 1;	/* 'h' */
+	bool guest : 1;		/* 'G' */
+	bool host : 1;		/* 'H' */
+};
+
+int parse_events__modifier_event(struct parse_events_state *parse_state, void *loc,
+				 struct list_head *list, struct parse_events_modifier mod);
+int parse_events__modifier_group(struct parse_events_state *parse_state, void *loc,
+				 struct list_head *list, struct parse_events_modifier mod);
+int parse_events__set_default_name(struct list_head *list, char *name);
+int parse_events_add_tracepoint(struct parse_events_state *parse_state,
+				struct list_head *list,
 				const char *sys, const char *event,
 				struct parse_events_error *error,
 				struct parse_events_terms *head_config, void *loc);
 int parse_events_add_numeric(struct parse_events_state *parse_state,
 			     struct list_head *list,
 			     u32 type, u64 config,
-			     struct parse_events_terms *head_config,
+			     const struct parse_events_terms *head_config,
 			     bool wildcard);
 int parse_events_add_tool(struct parse_events_state *parse_state,
 			  struct list_head *list,
 			  int tool_event);
 int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 			   struct parse_events_state *parse_state,
-			   struct parse_events_terms *head_config);
+			   struct parse_events_terms *parsed_terms);
 int parse_events__decode_legacy_cache(const char *name, int pmu_type, __u64 *config);
 int parse_events_add_breakpoint(struct parse_events_state *parse_state,
 				struct list_head *list,
 				u64 addr, char *type, u64 len,
 				struct parse_events_terms *head_config);
-int parse_events_add_pmu(struct parse_events_state *parse_state,
-			 struct list_head *list, const char *name,
-			 const struct parse_events_terms *const_parsed_terms,
-			bool auto_merge_stats, void *loc);
 
 struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr,
 				      const char *name, const char *metric_id,
@@ -223,18 +241,20 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			       const struct parse_events_terms *const_parsed_terms,
 			       struct list_head **listp, void *loc);
 
+int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state,
+					const char *event_or_pmu,
+					const struct parse_events_terms *const_parsed_terms,
+					struct list_head **listp,
+					void *loc_);
+
 void parse_events__set_leader(char *name, struct list_head *list);
-void parse_events_update_lists(struct list_head *list_event,
-			       struct list_head *list_all);
-void parse_events_evlist_error(struct parse_events_state *parse_state,
-			       int idx, const char *str);
 
 struct event_symbol {
 	const char	*symbol;
 	const char	*alias;
 };
-extern struct event_symbol event_symbols_hw[];
-extern struct event_symbol event_symbols_sw[];
+extern const struct event_symbol event_symbols_hw[];
+extern const struct event_symbol event_symbols_sw[];
 
 char *parse_events_formats_error_string(char *additional_terms);
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index e86c45675e..16045c383a 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -18,26 +18,34 @@
 
 char *parse_events_get_text(yyscan_t yyscanner);
 YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
+int parse_events_get_column(yyscan_t yyscanner);
+int parse_events_get_leng(yyscan_t yyscanner);
 
-static int __value(YYSTYPE *yylval, char *str, int base, int token)
+static int get_column(yyscan_t scanner)
 {
-	u64 num;
-
-	errno = 0;
-	num = strtoull(str, NULL, base);
-	if (errno)
-		return PE_ERROR;
-
-	yylval->num = num;
-	return token;
+	return parse_events_get_column(scanner) - parse_events_get_leng(scanner);
 }
 
-static int value(yyscan_t scanner, int base)
+static int value(struct parse_events_state *parse_state, yyscan_t scanner, int base)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
 	char *text = parse_events_get_text(scanner);
+	u64 num;
 
-	return __value(yylval, text, base, PE_VALUE);
+	errno = 0;
+	num = strtoull(text, NULL, base);
+	if (errno) {
+		struct parse_events_error *error = parse_state->error;
+		char *help = NULL;
+
+		if (asprintf(&help, "Bad base %d number \"%s\"", base, text) > 0)
+			parse_events_error__handle(error, get_column(scanner), help , NULL);
+
+		return PE_ERROR;
+	}
+
+	yylval->num = num;
+	return PE_VALUE;
 }
 
 static int str(yyscan_t scanner, int token)
@@ -88,6 +96,11 @@ static int drv_str(yyscan_t scanner, int token)
 	return token;
 }
 
+/*
+ * Use yyless to return all the characaters to the input. Update the column for
+ * location debugging. If __alloc is non-zero set yylval to the text for the
+ * returned token's value.
+ */
 #define REWIND(__alloc)				\
 do {								\
 	YYSTYPE *__yylval = parse_events_get_lval(yyscanner);	\
@@ -134,6 +147,77 @@ static int hw_term(yyscan_t scanner, int config)
 	return PE_TERM_HW;
 }
 
+static void modifiers_error(struct parse_events_state *parse_state, yyscan_t scanner,
+			    int pos, char mod_char, const char *mod_name)
+{
+	struct parse_events_error *error = parse_state->error;
+	char *help = NULL;
+
+	if (asprintf(&help, "Duplicate modifier '%c' (%s)", mod_char, mod_name) > 0)
+		parse_events_error__handle(error, get_column(scanner) + pos, help , NULL);
+}
+
+static int modifiers(struct parse_events_state *parse_state, yyscan_t scanner)
+{
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+	char *text = parse_events_get_text(scanner);
+	struct parse_events_modifier mod = { .precise = 0, };
+
+	for (size_t i = 0, n = strlen(text); i < n; i++) {
+#define CASE(c, field)							\
+		case c:							\
+			if (mod.field) {				\
+				modifiers_error(parse_state, scanner, i, c, #field); \
+				return PE_ERROR;			\
+			}						\
+			mod.field = true;				\
+			break
+
+		switch (text[i]) {
+		CASE('u', user);
+		CASE('k', kernel);
+		CASE('h', hypervisor);
+		CASE('I', non_idle);
+		CASE('G', guest);
+		CASE('H', host);
+		case 'p':
+			mod.precise++;
+			/*
+			 * precise ip:
+			 *
+			 *  0 - SAMPLE_IP can have arbitrary skid
+			 *  1 - SAMPLE_IP must have constant skid
+			 *  2 - SAMPLE_IP requested to have 0 skid
+			 *  3 - SAMPLE_IP must have 0 skid
+			 *
+			 *  See also PERF_RECORD_MISC_EXACT_IP
+			 */
+			if (mod.precise > 3) {
+				struct parse_events_error *error = parse_state->error;
+				char *help = strdup("Maximum precise value is 3");
+
+				if (help) {
+					parse_events_error__handle(error, get_column(scanner) + i,
+								   help , NULL);
+				}
+				return PE_ERROR;
+			}
+			break;
+		CASE('P', precise_max);
+		CASE('S', sample_read);
+		CASE('D', pinned);
+		CASE('W', weak);
+		CASE('e', exclusive);
+		CASE('b', bpf);
+		default:
+			return PE_ERROR;
+		}
+#undef CASE
+	}
+	yylval->mod = mod;
+	return PE_MODIFIER_EVENT;
+}
+
 #define YY_USER_ACTION					\
 do {							\
 	yylloc->last_column  = yylloc->first_column;	\
@@ -158,15 +242,15 @@ event		[^,{}/]+
 num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]{1,16}
 num_raw_hex	[a-fA-F0-9]{1,16}
-name		[a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]!\-]*
-name_tag	[\'][a-zA-Z_*?\[\]][a-zA-Z0-9_*?\-,\.\[\]:=]*[\']
+name		[a-zA-Z0-9_*?\[\]][a-zA-Z0-9_*?.\[\]!\-]*
+name_tag	[\'][a-zA-Z0-9_*?\[\]][a-zA-Z0-9_*?\-,\.\[\]:=]*[\']
 name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
 drv_cfg_term	[a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
 /*
  * If you add a modifier you need to update check_modifier().
  * Also, the letters in modifier_event must not be in modifier_bp.
  */
-modifier_event	[ukhpPGHSDIWeb]+
+modifier_event	[ukhpPGHSDIWeb]{1,15}
 modifier_bp	[rwx]{1,3}
 lc_type 	(L1-dcache|l1-d|l1d|L1-data|L1-icache|l1-i|l1i|L1-instruction|LLC|L2|dTLB|d-tlb|Data-TLB|iTLB|i-tlb|Instruction-TLB|branch|branches|bpu|btb|bpc|node)
 lc_op_result	(load|loads|read|store|stores|write|prefetch|prefetches|speculative-read|speculative-load|refs|Reference|ops|access|misses|miss)
@@ -283,8 +367,8 @@ r0x{num_raw_hex}	{ return str(yyscanner, PE_RAW); }
 	 */
 "/"/{digit}		{ return PE_BP_SLASH; }
 "/"/{non_digit}		{ BEGIN(config); return '/'; }
-{num_dec}		{ return value(yyscanner, 10); }
-{num_hex}		{ return value(yyscanner, 16); }
+{num_dec}		{ return value(_parse_state, yyscanner, 10); }
+{num_hex}		{ return value(_parse_state, yyscanner, 16); }
 	/*
 	 * We need to separate 'mem:' scanner part, in order to get specific
 	 * modifier bits parsed out. Otherwise we would need to handle PE_NAME
@@ -330,10 +414,10 @@ cgroup-switches					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CG
 {lc_type}-{lc_op_result}-{lc_op_result}	{ return str(yyscanner, PE_LEGACY_CACHE); }
 mem:			{ BEGIN(mem); return PE_PREFIX_MEM; }
 r{num_raw_hex}		{ return str(yyscanner, PE_RAW); }
-{num_dec}		{ return value(yyscanner, 10); }
-{num_hex}		{ return value(yyscanner, 16); }
+{num_dec}		{ return value(_parse_state, yyscanner, 10); }
+{num_hex}		{ return value(_parse_state, yyscanner, 16); }
 
-{modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
+{modifier_event}	{ return modifiers(_parse_state, yyscanner); }
 {name}			{ return str(yyscanner, PE_NAME); }
 {name_tag}		{ return str(yyscanner, PE_NAME); }
 "/"			{ BEGIN(config); return '/'; }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index d70f5d84af..b3c51f06cb 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -69,12 +69,12 @@ static void free_list_evsel(struct list_head* list_evsel)
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
 %type <num> PE_VALUE_SYM_TOOL
+%type <mod> PE_MODIFIER_EVENT
 %type <term_type> PE_TERM
 %type <num> value_sym
 %type <str> PE_RAW
 %type <str> PE_NAME
 %type <str> PE_LEGACY_CACHE
-%type <str> PE_MODIFIER_EVENT
 %type <str> PE_MODIFIER_BP
 %type <str> PE_EVENT_NAME
 %type <str> PE_DRV_CFG_TERM
@@ -111,6 +111,7 @@ static void free_list_evsel(struct list_head* list_evsel)
 {
 	char *str;
 	u64 num;
+	struct parse_events_modifier mod;
 	enum parse_events__term_type term_type;
 	struct list_head *list_evsel;
 	struct parse_events_terms *list_terms;
@@ -126,6 +127,10 @@ static void free_list_evsel(struct list_head* list_evsel)
 }
 %%
 
+ /*
+  * Entry points. We are either parsing events or terminals. Just terminal
+  * parsing is used for parsing events in sysfs.
+  */
 start:
 PE_START_EVENTS start_events
 |
@@ -133,31 +138,36 @@ PE_START_TERMS  start_terms
 
 start_events: groups
 {
+	/* Take the parsed events, groups.. and place into parse_state. */
+	struct list_head *groups  = $1;
 	struct parse_events_state *parse_state = _parse_state;
 
-	/* frees $1 */
-	parse_events_update_lists($1, &parse_state->list);
+	list_splice_tail(groups, &parse_state->list);
+	free(groups);
 }
 
-groups:
+groups: /* A list of groups or events. */
 groups ',' group
 {
-	struct list_head *list  = $1;
-	struct list_head *group = $3;
+	/* Merge group into the list of events/groups. */
+	struct list_head *groups  = $1;
+	struct list_head *group  = $3;
 
-	/* frees $3 */
-	parse_events_update_lists(group, list);
-	$$ = list;
+	list_splice_tail(group, groups);
+	free(group);
+	$$ = groups;
 }
 |
 groups ',' event
 {
-	struct list_head *list  = $1;
+	/* Merge event into the list of events/groups. */
+	struct list_head *groups  = $1;
 	struct list_head *event = $3;
 
-	/* frees $3 */
-	parse_events_update_lists(event, list);
-	$$ = list;
+
+	list_splice_tail(event, groups);
+	free(event);
+	$$ = groups;
 }
 |
 group
@@ -167,20 +177,13 @@ event
 group:
 group_def ':' PE_MODIFIER_EVENT
 {
+	/* Apply the modifier to the events in the group_def. */
 	struct list_head *list = $1;
 	int err;
 
-	err = parse_events__modifier_group(list, $3);
-	free($3);
-	if (err) {
-		struct parse_events_state *parse_state = _parse_state;
-		struct parse_events_error *error = parse_state->error;
-
-		parse_events_error__handle(error, @3.first_column,
-					   strdup("Bad modifier"), NULL);
-		free_list_evsel(list);
+	err = parse_events__modifier_group(_parse_state, &@3, list, $3);
+	if (err)
 		YYABORT;
-	}
 	$$ = list;
 }
 |
@@ -191,7 +194,10 @@ PE_NAME '{' events '}'
 {
 	struct list_head *list = $3;
 
-	/* Takes ownership of $1. */
+	/*
+	 * Set the first entry of list to be the leader. Set the group name on
+	 * the leader to $1 taking ownership.
+	 */
 	parse_events__set_leader($1, list);
 	$$ = list;
 }
@@ -200,6 +206,7 @@ PE_NAME '{' events '}'
 {
 	struct list_head *list = $2;
 
+	/* Set the first entry of list to be the leader clearing the group name. */
 	parse_events__set_leader(NULL, list);
 	$$ = list;
 }
@@ -207,12 +214,12 @@ PE_NAME '{' events '}'
 events:
 events ',' event
 {
+	struct list_head *events  = $1;
 	struct list_head *event = $3;
-	struct list_head *list  = $1;
 
-	/* frees $3 */
-	parse_events_update_lists(event, list);
-	$$ = list;
+	list_splice_tail(event, events);
+	free(event);
+	$$ = events;
 }
 |
 event
@@ -230,17 +237,9 @@ event_name PE_MODIFIER_EVENT
 	 * (there could be more events added for multiple tracepoint
 	 * definitions via '*?'.
 	 */
-	err = parse_events__modifier_event(list, $2, false);
-	free($2);
-	if (err) {
-		struct parse_events_state *parse_state = _parse_state;
-		struct parse_events_error *error = parse_state->error;
-
-		parse_events_error__handle(error, @2.first_column,
-					   strdup("Bad modifier"), NULL);
-		free_list_evsel(list);
+	err = parse_events__modifier_event(_parse_state, &@2, list, $2);
+	if (err)
 		YYABORT;
-	}
 	$$ = list;
 }
 |
@@ -249,10 +248,14 @@ event_name
 event_name:
 PE_EVENT_NAME event_def
 {
-	int err;
+	/*
+	 * When an event is parsed the text is rewound and the entire text of
+	 * the event is set to the str of PE_EVENT_NAME token matched here. If
+	 * no name was on an event via a term, set the name to the entire text
+	 * taking ownership of the allocation.
+	 */
+	int err = parse_events__set_default_name($2, $1);
 
-	err = parse_events_name($2, $1);
-	free($1);
 	if (err) {
 		free_list_evsel($2);
 		YYNOMEM;
@@ -273,78 +276,15 @@ event_def: event_pmu |
 event_pmu:
 PE_NAME opt_pmu_config
 {
-	struct parse_events_state *parse_state = _parse_state;
 	/* List of created evsels. */
 	struct list_head *list = NULL;
-	char *pattern = NULL;
+	int err = parse_events_multi_pmu_add_or_add_pmu(_parse_state, $1, $2, &list, &@1);
 
-#define CLEANUP						\
-	do {						\
-		parse_events_terms__delete($2);		\
-		free(list);				\
-		free($1);				\
-		free(pattern);				\
-	} while(0)
-
-	list = alloc_list();
-	if (!list) {
-		CLEANUP;
-		YYNOMEM;
-	}
-	/* Attempt to add to list assuming $1 is a PMU name. */
-	if (parse_events_add_pmu(parse_state, list, $1, $2, /*auto_merge_stats=*/false, &@1)) {
-		struct perf_pmu *pmu = NULL;
-		int ok = 0;
-
-		/* Failure to add, try wildcard expansion of $1 as a PMU name. */
-		if (asprintf(&pattern, "%s*", $1) < 0) {
-			CLEANUP;
-			YYNOMEM;
-		}
-
-		while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-			const char *name = pmu->name;
-
-			if (parse_events__filter_pmu(parse_state, pmu))
-				continue;
-
-			if (!strncmp(name, "uncore_", 7) &&
-			    strncmp($1, "uncore_", 7))
-				name += 7;
-			if (!perf_pmu__match(pattern, name, $1) ||
-			    !perf_pmu__match(pattern, pmu->alias_name, $1)) {
-				bool auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
-
-				if (!parse_events_add_pmu(parse_state, list, pmu->name, $2,
-							  auto_merge_stats, &@1)) {
-					ok++;
-					parse_state->wild_card_pmus = true;
-				}
-			}
-		}
-
-		if (!ok) {
-			/* Failure to add, assume $1 is an event name. */
-			zfree(&list);
-			ok = !parse_events_multi_pmu_add(parse_state, $1, $2, &list, &@1);
-		}
-		if (!ok) {
-			struct parse_events_error *error = parse_state->error;
-			char *help;
-
-			if (asprintf(&help, "Unable to find PMU or event on a PMU of '%s'", $1) < 0)
-				help = NULL;
-			parse_events_error__handle(error, @1.first_column,
-						   strdup("Bad event or PMU"),
-						   help);
-			CLEANUP;
-			YYABORT;
-		}
-	}
+	parse_events_terms__delete($2);
+	free($1);
+	if (err)
+		PE_ABORT(err);
 	$$ = list;
-	list = NULL;
-	CLEANUP;
-#undef CLEANUP
 }
 |
 PE_NAME sep_dc
@@ -537,7 +477,7 @@ tracepoint_name opt_event_config
 	if (!list)
 		YYNOMEM;
 
-	err = parse_events_add_tracepoint(list, &parse_state->idx, $1.sys, $1.event,
+	err = parse_events_add_tracepoint(parse_state, list, $1.sys, $1.event,
 					error, $2, &@1);
 
 	parse_events_terms__delete($2);
@@ -666,6 +606,11 @@ event_term
 }
 
 name_or_raw: PE_RAW | PE_NAME | PE_LEGACY_CACHE
+|
+PE_TERM_HW
+{
+	$$ = $1.str;
+}
 
 event_term:
 PE_RAW
@@ -707,20 +652,6 @@ name_or_raw '=' PE_VALUE
 	$$ = term;
 }
 |
-name_or_raw '=' PE_TERM_HW
-{
-	struct parse_events_term *term;
-	int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					 $1, $3.str, &@1, &@3);
-
-	if (err) {
-		free($1);
-		free($3.str);
-		PE_ABORT(err);
-	}
-	$$ = term;
-}
-|
 PE_LEGACY_CACHE
 {
 	struct parse_events_term *term;
@@ -773,18 +704,6 @@ PE_TERM '=' name_or_raw
 	$$ = term;
 }
 |
-PE_TERM '=' PE_TERM_HW
-{
-	struct parse_events_term *term;
-	int err = parse_events_term__str(&term, $1, /*config=*/NULL, $3.str, &@1, &@3);
-
-	if (err) {
-		free($3.str);
-		PE_ABORT(err);
-	}
-	$$ = term;
-}
-|
 PE_TERM '=' PE_TERM
 {
 	struct parse_events_term *term;
@@ -845,9 +764,15 @@ sep_slash_slash_dc: '/' '/' | ':' |
 
 %%
 
-void parse_events_error(YYLTYPE *loc, void *parse_state,
+void parse_events_error(YYLTYPE *loc, void *_parse_state,
 			void *scanner __maybe_unused,
 			char const *msg __maybe_unused)
 {
-	parse_events_evlist_error(parse_state, loc->last_column, "parser error");
+	struct parse_events_state *parse_state = _parse_state;
+
+	if (!parse_state->error || !list_empty(&parse_state->error->list))
+		return;
+
+	parse_events_error__handle(parse_state->error, loc->last_column,
+				   strdup("Unrecognized input"), NULL);
 }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index cc349d9cb0..888ce99122 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -194,7 +194,7 @@ static void perf_pmu_format__load(const struct perf_pmu *pmu, struct perf_pmu_fo
  * Parse & process all the sysfs attributes located under
  * the directory specified in 'dir' parameter.
  */
-int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load)
+static int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load)
 {
 	struct dirent *evt_ent;
 	DIR *format_dir;
@@ -244,7 +244,7 @@ int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load)
  * located at:
  * /sys/bus/event_source/devices/<dev>/format as sysfs group attributes.
  */
-static int pmu_format(struct perf_pmu *pmu, int dirfd, const char *name)
+static int pmu_format(struct perf_pmu *pmu, int dirfd, const char *name, bool eager_load)
 {
 	int fd;
 
@@ -253,7 +253,7 @@ static int pmu_format(struct perf_pmu *pmu, int dirfd, const char *name)
 		return 0;
 
 	/* it'll close the fd */
-	if (perf_pmu__format_parse(pmu, fd, /*eager_load=*/false))
+	if (perf_pmu__format_parse(pmu, fd, eager_load))
 		return -1;
 
 	return 0;
@@ -551,7 +551,8 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 		unit = pe->unit;
 		perpkg = pe->perpkg;
 		deprecated = pe->deprecated;
-		pmu_name = pe->pmu;
+		if (pe->pmu && strcmp(pe->pmu, "default_core"))
+			pmu_name = pe->pmu;
 	}
 
 	alias = zalloc(sizeof(*alias));
@@ -634,33 +635,18 @@ static inline bool pmu_alias_info_file(const char *name)
  * Reading the pmu event aliases definition, which should be located at:
  * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes.
  */
-static int pmu_aliases_parse(struct perf_pmu *pmu)
+static int __pmu_aliases_parse(struct perf_pmu *pmu, int events_dir_fd)
 {
-	char path[PATH_MAX];
 	struct dirent *evt_ent;
 	DIR *event_dir;
-	size_t len;
-	int fd, dir_fd;
-
-	len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path));
-	if (!len)
-		return 0;
-	scnprintf(path + len, sizeof(path) - len, "%s/events", pmu->name);
-
-	dir_fd = open(path, O_DIRECTORY);
-	if (dir_fd == -1) {
-		pmu->sysfs_aliases_loaded = true;
-		return 0;
-	}
 
-	event_dir = fdopendir(dir_fd);
-	if (!event_dir){
-		close (dir_fd);
+	event_dir = fdopendir(events_dir_fd);
+	if (!event_dir)
 		return -EINVAL;
-	}
 
 	while ((evt_ent = readdir(event_dir))) {
 		char *name = evt_ent->d_name;
+		int fd;
 		FILE *file;
 
 		if (!strcmp(name, ".") || !strcmp(name, ".."))
@@ -672,7 +658,7 @@ static int pmu_aliases_parse(struct perf_pmu *pmu)
 		if (pmu_alias_info_file(name))
 			continue;
 
-		fd = openat(dir_fd, name, O_RDONLY);
+		fd = openat(events_dir_fd, name, O_RDONLY);
 		if (fd == -1) {
 			pr_debug("Cannot open %s\n", name);
 			continue;
@@ -691,11 +677,50 @@ static int pmu_aliases_parse(struct perf_pmu *pmu)
 	}
 
 	closedir(event_dir);
-	close (dir_fd);
 	pmu->sysfs_aliases_loaded = true;
 	return 0;
 }
 
+static int pmu_aliases_parse(struct perf_pmu *pmu)
+{
+	char path[PATH_MAX];
+	size_t len;
+	int events_dir_fd, ret;
+
+	if (pmu->sysfs_aliases_loaded)
+		return 0;
+
+	len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path));
+	if (!len)
+		return 0;
+	scnprintf(path + len, sizeof(path) - len, "%s/events", pmu->name);
+
+	events_dir_fd = open(path, O_DIRECTORY);
+	if (events_dir_fd == -1) {
+		pmu->sysfs_aliases_loaded = true;
+		return 0;
+	}
+	ret = __pmu_aliases_parse(pmu, events_dir_fd);
+	close(events_dir_fd);
+	return ret;
+}
+
+static int pmu_aliases_parse_eager(struct perf_pmu *pmu, int sysfs_fd)
+{
+	char path[FILENAME_MAX + 7];
+	int ret, events_dir_fd;
+
+	scnprintf(path, sizeof(path), "%s/events", pmu->name);
+	events_dir_fd = openat(sysfs_fd, path, O_DIRECTORY, 0);
+	if (events_dir_fd == -1) {
+		pmu->sysfs_aliases_loaded = true;
+		return 0;
+	}
+	ret = __pmu_aliases_parse(pmu, events_dir_fd);
+	close(events_dir_fd);
+	return ret;
+}
+
 static int pmu_alias_terms(struct perf_pmu_alias *alias, int err_loc, struct list_head *terms)
 {
 	struct parse_events_term *term, *cloned;
@@ -1034,7 +1059,8 @@ perf_pmu__arch_init(struct perf_pmu *pmu)
 		pmu->mem_events = perf_mem_events;
 }
 
-struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *name)
+struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *name,
+				  bool eager_load)
 {
 	struct perf_pmu *pmu;
 	__u32 type;
@@ -1063,7 +1089,7 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 	 * type value and format definitions. Load both right
 	 * now.
 	 */
-	if (pmu_format(pmu, dirfd, name))
+	if (pmu_format(pmu, dirfd, name, eager_load))
 		goto err;
 
 	pmu->is_core = is_pmu_core(name);
@@ -1087,6 +1113,9 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 
 	perf_pmu__arch_init(pmu);
 
+	if (eager_load)
+		pmu_aliases_parse_eager(pmu, dirfd);
+
 	return pmu;
 err:
 	zfree(&pmu->name);
@@ -1649,6 +1678,62 @@ bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name)
 	return false;
 }
 
+int perf_pmu__for_each_format(struct perf_pmu *pmu, void *state, pmu_format_callback cb)
+{
+	static const char *const terms[] = {
+		"config=0..0xffffffffffffffff",
+		"config1=0..0xffffffffffffffff",
+		"config2=0..0xffffffffffffffff",
+		"config3=0..0xffffffffffffffff",
+		"name=string",
+		"period=number",
+		"freq=number",
+		"branch_type=(u|k|hv|any|...)",
+		"time",
+		"call-graph=(fp|dwarf|lbr)",
+		"stack-size=number",
+		"max-stack=number",
+		"nr=number",
+		"inherit",
+		"no-inherit",
+		"overwrite",
+		"no-overwrite",
+		"percore",
+		"aux-output",
+		"aux-sample-size=number",
+	};
+	struct perf_pmu_format *format;
+	int ret;
+
+	/*
+	 * max-events and driver-config are missing above as are the internal
+	 * types user, metric-id, raw, legacy cache and hardware. Assert against
+	 * the enum parse_events__term_type so they are kept in sync.
+	 */
+	_Static_assert(ARRAY_SIZE(terms) == __PARSE_EVENTS__TERM_TYPE_NR - 6,
+		       "perf_pmu__for_each_format()'s terms must be kept in sync with enum parse_events__term_type");
+	list_for_each_entry(format, &pmu->format, list) {
+		perf_pmu_format__load(pmu, format);
+		ret = cb(state, format->name, (int)format->value, format->bits);
+		if (ret)
+			return ret;
+	}
+	if (!pmu->is_core)
+		return 0;
+
+	for (size_t i = 0; i < ARRAY_SIZE(terms); i++) {
+		int config = PERF_PMU_FORMAT_VALUE_CONFIG;
+
+		if (i < PERF_PMU_FORMAT_VALUE_CONFIG_END)
+			config = i;
+
+		ret = cb(state, terms[i], config, /*bits=*/NULL);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
 bool is_pmu_core(const char *name)
 {
 	return !strcmp(name, "cpu") || !strcmp(name, "cpum_cf") || is_sysfs_pmu_core(name);
@@ -1744,8 +1829,12 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
 	pmu_add_cpu_aliases(pmu);
 	list_for_each_entry(event, &pmu->aliases, list) {
 		size_t buf_used;
+		int pmu_name_len;
 
 		info.pmu_name = event->pmu_name ?: pmu->name;
+		pmu_name_len = skip_duplicate_pmus
+			? pmu_name_len_no_suffix(info.pmu_name, /*num=*/NULL)
+			: (int)strlen(info.pmu_name);
 		info.alias = NULL;
 		if (event->desc) {
 			info.name = event->name;
@@ -1770,7 +1859,7 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
 		info.encoding_desc = buf + buf_used;
 		parse_events_terms__to_strbuf(&event->terms, &sb);
 		buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used,
-				"%s/%s/", info.pmu_name, sb.buf) + 1;
+				"%.*s/%s/", pmu_name_len, info.pmu_name, sb.buf) + 1;
 		info.topic = event->topic;
 		info.str = sb.buf;
 		info.deprecated = event->deprecated;
@@ -2051,18 +2140,29 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
 		   name ?: "N/A", buf, config_name, config);
 }
 
-int perf_pmu__match(const char *pattern, const char *name, const char *tok)
+bool perf_pmu__match(const struct perf_pmu *pmu, const char *tok)
 {
-	if (!name)
-		return -1;
+	const char *name = pmu->name;
+	bool need_fnmatch = strchr(tok, '*') != NULL;
 
-	if (fnmatch(pattern, name, 0))
-		return -1;
+	if (!strncmp(tok, "uncore_", 7))
+		tok += 7;
+	if (!strncmp(name, "uncore_", 7))
+		name += 7;
 
-	if (tok && !perf_pmu__match_ignoring_suffix(name, tok))
-		return -1;
+	if (perf_pmu__match_ignoring_suffix(name, tok) ||
+	    (need_fnmatch && !fnmatch(tok, name, 0)))
+		return true;
 
-	return 0;
+	name = pmu->alias_name;
+	if (!name)
+		return false;
+
+	if (!strncmp(name, "uncore_", 7))
+		name += 7;
+
+	return perf_pmu__match_ignoring_suffix(name, tok) ||
+		(need_fnmatch && !fnmatch(tok, name, 0));
 }
 
 double __weak perf_pmu__cpu_slots_per_cycle(void)
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 77c59ebc05..b2d3fd291f 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -198,6 +198,8 @@ struct pmu_event_info {
 };
 
 typedef int (*pmu_event_callback)(void *state, struct pmu_event_info *info);
+typedef int (*pmu_format_callback)(void *state, const char *name, int config,
+				   const unsigned long *bits);
 
 void pmu_add_sys_aliases(struct perf_pmu *pmu);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
@@ -214,9 +216,9 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_
 			  struct parse_events_error *err);
 int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, pmu_event_callback cb);
 
-int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load);
 void perf_pmu_format__set_value(void *format, int config, unsigned long *bits);
 bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name);
+int perf_pmu__for_each_format(struct perf_pmu *pmu, void *state, pmu_format_callback cb);
 
 bool is_pmu_core(const char *name);
 bool perf_pmu__supports_legacy_cache(const struct perf_pmu *pmu);
@@ -262,7 +264,7 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
 				   const char *config_name);
 void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu);
 
-int perf_pmu__match(const char *pattern, const char *name, const char *tok);
+bool perf_pmu__match(const struct perf_pmu *pmu, const char *tok);
 
 double perf_pmu__cpu_slots_per_cycle(void);
 int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size);
@@ -271,7 +273,8 @@ int perf_pmu__pathname_scnprintf(char *buf, size_t size,
 int perf_pmu__event_source_devices_fd(void);
 int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, int flags);
 
-struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name);
+struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name,
+				  bool eager_load);
 struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus);
 void perf_pmu__delete(struct perf_pmu *pmu);
 struct perf_pmu *perf_pmus__find_core_pmu(void);
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index 16505071d3..6907e3e7fb 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -16,6 +16,7 @@
 #include "pmus.h"
 #include "pmu.h"
 #include "print-events.h"
+#include "strbuf.h"
 
 /*
  * core_pmus:  A PMU belongs to core_pmus if it's name is "cpu" or it's sysfs
@@ -123,7 +124,8 @@ struct perf_pmu *perf_pmus__find(const char *name)
 		return NULL;
 
 	dirfd = perf_pmu__event_source_devices_fd();
-	pmu = perf_pmu__lookup(core_pmu ? &core_pmus : &other_pmus, dirfd, name);
+	pmu = perf_pmu__lookup(core_pmu ? &core_pmus : &other_pmus, dirfd, name,
+			       /*eager_load=*/false);
 	close(dirfd);
 
 	if (!pmu) {
@@ -158,7 +160,8 @@ static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name)
 	if (core_pmu && read_sysfs_core_pmus)
 		return NULL;
 
-	return perf_pmu__lookup(core_pmu ? &core_pmus : &other_pmus, dirfd, name);
+	return perf_pmu__lookup(core_pmu ? &core_pmus : &other_pmus, dirfd, name,
+				/*eager_load=*/false);
 }
 
 static int pmus_cmp(void *priv __maybe_unused,
@@ -474,8 +477,8 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p
 	qsort(aliases, len, sizeof(struct sevent), cmp_sevent);
 	for (int j = 0; j < len; j++) {
 		/* Skip duplicates */
-		if (j > 0 && pmu_alias_is_duplicate(&aliases[j], &aliases[j - 1]))
-			continue;
+		if (j < len - 1 && pmu_alias_is_duplicate(&aliases[j], &aliases[j + 1]))
+			goto free;
 
 		print_cb->print_event(print_state,
 				aliases[j].pmu_name,
@@ -488,6 +491,7 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p
 				aliases[j].desc,
 				aliases[j].long_desc,
 				aliases[j].encoding_desc);
+free:
 		zfree(&aliases[j].name);
 		zfree(&aliases[j].alias);
 		zfree(&aliases[j].scale_unit);
@@ -503,6 +507,99 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p
 	zfree(&aliases);
 }
 
+struct build_format_string_args {
+	struct strbuf short_string;
+	struct strbuf long_string;
+	int num_formats;
+};
+
+static int build_format_string(void *state, const char *name, int config,
+			       const unsigned long *bits)
+{
+	struct build_format_string_args *args = state;
+	unsigned int num_bits;
+	int ret1, ret2 = 0;
+
+	(void)config;
+	args->num_formats++;
+	if (args->num_formats > 1) {
+		strbuf_addch(&args->long_string, ',');
+		if (args->num_formats < 4)
+			strbuf_addch(&args->short_string, ',');
+	}
+	num_bits = bits ? bitmap_weight(bits, PERF_PMU_FORMAT_BITS) : 0;
+	if (num_bits <= 1) {
+		ret1 = strbuf_addf(&args->long_string, "%s", name);
+		if (args->num_formats < 4)
+			ret2 = strbuf_addf(&args->short_string, "%s", name);
+	} else if (num_bits > 8) {
+		ret1 = strbuf_addf(&args->long_string, "%s=0..0x%llx", name,
+				   ULLONG_MAX >> (64 - num_bits));
+		if (args->num_formats < 4) {
+			ret2 = strbuf_addf(&args->short_string, "%s=0..0x%llx", name,
+					   ULLONG_MAX >> (64 - num_bits));
+		}
+	} else {
+		ret1 = strbuf_addf(&args->long_string, "%s=0..%llu", name,
+				  ULLONG_MAX >> (64 - num_bits));
+		if (args->num_formats < 4) {
+			ret2 = strbuf_addf(&args->short_string, "%s=0..%llu", name,
+					   ULLONG_MAX >> (64 - num_bits));
+		}
+	}
+	return ret1 < 0 ? ret1 : (ret2 < 0 ? ret2 : 0);
+}
+
+void perf_pmus__print_raw_pmu_events(const struct print_callbacks *print_cb, void *print_state)
+{
+	bool skip_duplicate_pmus = print_cb->skip_duplicate_pmus(print_state);
+	struct perf_pmu *(*scan_fn)(struct perf_pmu *);
+	struct perf_pmu *pmu = NULL;
+
+	if (skip_duplicate_pmus)
+		scan_fn = perf_pmus__scan_skip_duplicates;
+	else
+		scan_fn = perf_pmus__scan;
+
+	while ((pmu = scan_fn(pmu)) != NULL) {
+		struct build_format_string_args format_args = {
+			.short_string = STRBUF_INIT,
+			.long_string = STRBUF_INIT,
+			.num_formats = 0,
+		};
+		int len = pmu_name_len_no_suffix(pmu->name, /*num=*/NULL);
+		const char *desc = "(see 'man perf-list' or 'man perf-record' on how to encode it)";
+
+		if (!pmu->is_core)
+			desc = NULL;
+
+		strbuf_addf(&format_args.short_string, "%.*s/", len, pmu->name);
+		strbuf_addf(&format_args.long_string, "%.*s/", len, pmu->name);
+		perf_pmu__for_each_format(pmu, &format_args, build_format_string);
+
+		if (format_args.num_formats > 3)
+			strbuf_addf(&format_args.short_string, ",.../modifier");
+		else
+			strbuf_addf(&format_args.short_string, "/modifier");
+
+		strbuf_addf(&format_args.long_string, "/modifier");
+		print_cb->print_event(print_state,
+				/*topic=*/NULL,
+				/*pmu_name=*/NULL,
+				format_args.short_string.buf,
+				/*event_alias=*/NULL,
+				/*scale_unit=*/NULL,
+				/*deprecated=*/false,
+				"Raw event descriptor",
+				desc,
+				/*long_desc=*/NULL,
+				format_args.long_string.buf);
+
+		strbuf_release(&format_args.short_string);
+		strbuf_release(&format_args.long_string);
+	}
+}
+
 bool perf_pmus__have_event(const char *pname, const char *name)
 {
 	struct perf_pmu *pmu = perf_pmus__find(pname);
@@ -602,3 +699,13 @@ struct perf_pmu *perf_pmus__find_core_pmu(void)
 {
 	return perf_pmus__scan_core(NULL);
 }
+
+struct perf_pmu *perf_pmus__add_test_pmu(int test_sysfs_dirfd, const char *name)
+{
+	/*
+	 * Some PMU functions read from the sysfs mount point, so care is
+	 * needed, hence passing the eager_load flag to load things like the
+	 * format files.
+	 */
+	return perf_pmu__lookup(&other_pmus, test_sysfs_dirfd, name, /*eager_load=*/true);
+}
diff --git a/tools/perf/util/pmus.h b/tools/perf/util/pmus.h
index 94d2a08d89..9d4ded80b8 100644
--- a/tools/perf/util/pmus.h
+++ b/tools/perf/util/pmus.h
@@ -18,9 +18,12 @@ struct perf_pmu *perf_pmus__scan_core(struct perf_pmu *pmu);
 const struct perf_pmu *perf_pmus__pmu_for_pmu_filter(const char *str);
 
 void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *print_state);
+void perf_pmus__print_raw_pmu_events(const struct print_callbacks *print_cb, void *print_state);
 bool perf_pmus__have_event(const char *pname, const char *name);
 int perf_pmus__num_core_pmus(void);
 bool perf_pmus__supports_extended_type(void);
 char *perf_pmus__default_pmu_name(void);
 
+struct perf_pmu *perf_pmus__add_test_pmu(int test_sysfs_dirfd, const char *name);
+
 #endif /* __PMUS_H */
diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index 7b54e93854..3f38c27f01 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -9,6 +9,7 @@
 #include <unistd.h>
 
 #include <api/fs/tracing_path.h>
+#include <api/io.h>
 #include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <linux/zalloc.h>
@@ -38,7 +39,7 @@ static const char * const event_type_descriptors[] = {
 	"Software event",
 	"Tracepoint event",
 	"Hardware cache event",
-	"Raw hardware event descriptor",
+	"Raw event descriptor",
 	"Hardware breakpoint",
 };
 
@@ -92,34 +93,48 @@ void print_tracepoint_events(const struct print_callbacks *print_cb __maybe_unus
 
 		evt_items = scandirat(events_fd, sys_dirent->d_name, &evt_namelist, NULL, alphasort);
 		for (int j = 0; j < evt_items; j++) {
+			/*
+			 * Buffer sized at twice the max filename length + 1
+			 * separator + 1 \0 terminator.
+			 */
+			char buf[NAME_MAX * 2 + 2];
+			/* 16 possible hex digits and 22 other characters and \0. */
+			char encoding[16 + 22];
 			struct dirent *evt_dirent = evt_namelist[j];
-			char evt_path[MAXPATHLEN];
-			int evt_fd;
+			struct io id;
+			__u64 config;
 
 			if (evt_dirent->d_type != DT_DIR ||
 			    !strcmp(evt_dirent->d_name, ".") ||
 			    !strcmp(evt_dirent->d_name, ".."))
 				goto next_evt;
 
-			snprintf(evt_path, sizeof(evt_path), "%s/id", evt_dirent->d_name);
-			evt_fd = openat(dir_fd, evt_path, O_RDONLY);
-			if (evt_fd < 0)
+			snprintf(buf, sizeof(buf), "%s/id", evt_dirent->d_name);
+			io__init(&id, openat(dir_fd, buf, O_RDONLY), buf, sizeof(buf));
+
+			if (id.fd < 0)
+				goto next_evt;
+
+			if (io__get_dec(&id, &config) < 0) {
+				close(id.fd);
 				goto next_evt;
-			close(evt_fd);
+			}
+			close(id.fd);
 
-			snprintf(evt_path, MAXPATHLEN, "%s:%s",
+			snprintf(buf, sizeof(buf), "%s:%s",
 				 sys_dirent->d_name, evt_dirent->d_name);
+			snprintf(encoding, sizeof(encoding), "tracepoint/config=0x%llx/", config);
 			print_cb->print_event(print_state,
 					/*topic=*/NULL,
-					/*pmu_name=*/NULL,
-					evt_path,
+					/*pmu_name=*/NULL, /* really "tracepoint" */
+					/*event_name=*/buf,
 					/*event_alias=*/NULL,
 					/*scale_unit=*/NULL,
 					/*deprecated=*/false,
 					"Tracepoint event",
 					/*desc=*/NULL,
 					/*long_desc=*/NULL,
-					/*encoding_desc=*/NULL);
+					encoding);
 next_evt:
 			free(evt_namelist[j]);
 		}
@@ -401,8 +416,6 @@ void print_symbol_events(const struct print_callbacks *print_cb, void *print_sta
  */
 void print_events(const struct print_callbacks *print_cb, void *print_state)
 {
-	char *tmp;
-
 	print_symbol_events(print_cb, print_state, PERF_TYPE_HARDWARE,
 			event_symbols_hw, PERF_COUNT_HW_MAX);
 	print_symbol_events(print_cb, print_state, PERF_TYPE_SOFTWARE,
@@ -426,21 +439,7 @@ void print_events(const struct print_callbacks *print_cb, void *print_state)
 			/*long_desc=*/NULL,
 			/*encoding_desc=*/NULL);
 
-	if (asprintf(&tmp, "%s/t1=v1[,t2=v2,t3 ...]/modifier",
-		     perf_pmus__scan_core(/*pmu=*/NULL)->name) > 0) {
-		print_cb->print_event(print_state,
-				/*topic=*/NULL,
-				/*pmu_name=*/NULL,
-				tmp,
-				/*event_alias=*/NULL,
-				/*scale_unit=*/NULL,
-				/*deprecated=*/false,
-				event_type_descriptors[PERF_TYPE_RAW],
-				"(see 'man perf-list' on how to encode it)",
-				/*long_desc=*/NULL,
-				/*encoding_desc=*/NULL);
-		free(tmp);
-	}
+	perf_pmus__print_raw_pmu_events(print_cb, print_state);
 
 	print_cb->print_event(print_state,
 			/*topic=*/NULL,
diff --git a/tools/perf/util/print_insn.c b/tools/perf/util/print_insn.c
index 459e0e93d7..a950e9157d 100644
--- a/tools/perf/util/print_insn.c
+++ b/tools/perf/util/print_insn.c
@@ -4,6 +4,7 @@
  *
  * Author(s): Changbin Du <changbin.du@huawei.com>
  */
+#include <inttypes.h>
 #include <string.h>
 #include <stdbool.h>
 #include "debug.h"
@@ -12,6 +13,9 @@
 #include "machine.h"
 #include "thread.h"
 #include "print_insn.h"
+#include "dump-insn.h"
+#include "map.h"
+#include "dso.h"
 
 size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp)
 {
@@ -28,12 +32,12 @@ size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp)
 #ifdef HAVE_LIBCAPSTONE_SUPPORT
 #include <capstone/capstone.h>
 
-static int capstone_init(struct machine *machine, csh *cs_handle)
+static int capstone_init(struct machine *machine, csh *cs_handle, bool is64)
 {
 	cs_arch arch;
 	cs_mode mode;
 
-	if (machine__is(machine, "x86_64")) {
+	if (machine__is(machine, "x86_64") && is64) {
 		arch = CS_ARCH_X86;
 		mode = CS_MODE_64;
 	} else if (machine__normalized_is(machine, "x86")) {
@@ -69,8 +73,8 @@ static int capstone_init(struct machine *machine, csh *cs_handle)
 	return 0;
 }
 
-static size_t print_insn_x86(struct perf_sample *sample, struct thread *thread,
-			     cs_insn *insn, FILE *fp)
+static size_t print_insn_x86(struct thread *thread, u8 cpumode, cs_insn *insn,
+			     int print_opts, FILE *fp)
 {
 	struct addr_location al;
 	size_t printed = 0;
@@ -80,9 +84,11 @@ static size_t print_insn_x86(struct perf_sample *sample, struct thread *thread,
 
 		addr_location__init(&al);
 		if (op->type == X86_OP_IMM &&
-		    thread__find_symbol(thread, sample->cpumode, op->imm, &al)) {
+		    thread__find_symbol(thread, cpumode, op->imm, &al)) {
 			printed += fprintf(fp, "%s ", insn[0].mnemonic);
 			printed += symbol__fprintf_symname_offs(al.sym, &al, fp);
+			if (print_opts & PRINT_INSN_IMM_HEX)
+				printed += fprintf(fp, " [%#" PRIx64 "]", op->imm);
 			addr_location__exit(&al);
 			return printed;
 		}
@@ -93,42 +99,71 @@ static size_t print_insn_x86(struct perf_sample *sample, struct thread *thread,
 	return printed;
 }
 
-size_t sample__fprintf_insn_asm(struct perf_sample *sample, struct thread *thread,
-				struct machine *machine, FILE *fp)
+static bool is64bitip(struct machine *machine, struct addr_location *al)
 {
-	csh cs_handle;
+	const struct dso *dso = al->map ? map__dso(al->map) : NULL;
+
+	if (dso)
+		return dso__is_64_bit(dso);
+
+	return machine__is(machine, "x86_64") ||
+		machine__normalized_is(machine, "arm64") ||
+		machine__normalized_is(machine, "s390");
+}
+
+ssize_t fprintf_insn_asm(struct machine *machine, struct thread *thread, u8 cpumode,
+			 bool is64bit, const uint8_t *code, size_t code_size,
+			 uint64_t ip, int *lenp, int print_opts, FILE *fp)
+{
+	size_t printed;
 	cs_insn *insn;
+	csh cs_handle;
 	size_t count;
-	size_t printed = 0;
 	int ret;
 
 	/* TODO: Try to initiate capstone only once but need a proper place. */
-	ret = capstone_init(machine, &cs_handle);
-	if (ret < 0) {
-		/* fallback */
-		return sample__fprintf_insn_raw(sample, fp);
-	}
+	ret = capstone_init(machine, &cs_handle, is64bit);
+	if (ret < 0)
+		return ret;
 
-	count = cs_disasm(cs_handle, (uint8_t *)sample->insn, sample->insn_len,
-			  sample->ip, 1, &insn);
+	count = cs_disasm(cs_handle, code, code_size, ip, 1, &insn);
 	if (count > 0) {
 		if (machine__normalized_is(machine, "x86"))
-			printed += print_insn_x86(sample, thread, &insn[0], fp);
+			printed = print_insn_x86(thread, cpumode, &insn[0], print_opts, fp);
 		else
-			printed += fprintf(fp, "%s %s", insn[0].mnemonic, insn[0].op_str);
+			printed = fprintf(fp, "%s %s", insn[0].mnemonic, insn[0].op_str);
+		if (lenp)
+			*lenp = insn->size;
 		cs_free(insn, count);
 	} else {
-		printed += fprintf(fp, "illegal instruction");
+		printed = -1;
 	}
 
 	cs_close(&cs_handle);
 	return printed;
 }
+
+size_t sample__fprintf_insn_asm(struct perf_sample *sample, struct thread *thread,
+				struct machine *machine, FILE *fp,
+				struct addr_location *al)
+{
+	bool is64bit = is64bitip(machine, al);
+	ssize_t printed;
+
+	printed = fprintf_insn_asm(machine, thread, sample->cpumode, is64bit,
+				   (uint8_t *)sample->insn, sample->insn_len,
+				   sample->ip, NULL, 0, fp);
+	if (printed < 0)
+		return sample__fprintf_insn_raw(sample, fp);
+
+	return printed;
+}
 #else
 size_t sample__fprintf_insn_asm(struct perf_sample *sample __maybe_unused,
 				struct thread *thread __maybe_unused,
 				struct machine *machine __maybe_unused,
-				FILE *fp __maybe_unused)
+				FILE *fp __maybe_unused,
+				struct addr_location *al __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/print_insn.h b/tools/perf/util/print_insn.h
index 465bdcfcc2..07d11af3fc 100644
--- a/tools/perf/util/print_insn.h
+++ b/tools/perf/util/print_insn.h
@@ -8,9 +8,15 @@
 struct perf_sample;
 struct thread;
 struct machine;
+struct perf_insn;
+
+#define PRINT_INSN_IMM_HEX		(1<<0)
 
 size_t sample__fprintf_insn_asm(struct perf_sample *sample, struct thread *thread,
-				struct machine *machine, FILE *fp);
+				struct machine *machine, FILE *fp, struct addr_location *al);
 size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp);
+ssize_t fprintf_insn_asm(struct machine *machine, struct thread *thread, u8 cpumode,
+			 bool is64bit, const uint8_t *code, size_t code_size,
+			 uint64_t ip, int *lenp, int print_opts, FILE *fp);
 
 #endif /* PERF_PRINT_INSN_H */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 5c12459e97..a17c9b8a7a 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -159,8 +159,8 @@ static int kernel_get_module_map_cb(struct map *map, void *data)
 {
 	struct kernel_get_module_map_cb_args *args = data;
 	struct dso *dso = map__dso(map);
-	const char *short_name = dso->short_name; /* short_name is "[module]" */
-	u16 short_name_len =  dso->short_name_len;
+	const char *short_name = dso__short_name(dso);
+	u16 short_name_len =  dso__short_name_len(dso);
 
 	if (strncmp(short_name + 1, args->module, short_name_len - 2) == 0 &&
 	    args->module[short_name_len - 2] == '\0') {
@@ -202,10 +202,9 @@ struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user)
 		map = dso__new_map(target);
 		dso = map ? map__dso(map) : NULL;
 		if (dso) {
-			mutex_lock(&dso->lock);
-			nsinfo__put(dso->nsinfo);
-			dso->nsinfo = nsinfo__get(nsi);
-			mutex_unlock(&dso->lock);
+			mutex_lock(dso__lock(dso));
+			dso__set_nsinfo(dso, nsinfo__get(nsi));
+			mutex_unlock(dso__lock(dso));
 		}
 		return map;
 	} else {
@@ -236,7 +235,7 @@ static int convert_exec_to_group(const char *exec, char **result)
 		}
 	}
 
-	ret = e_snprintf(buf, 64, "%s_%s", PERFPROBE_GROUP, ptr1);
+	ret = e_snprintf(buf, sizeof(buf), "%s_%s", PERFPROBE_GROUP, ptr1);
 	if (ret < 0)
 		goto out;
 
@@ -368,11 +367,11 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso)
 
 	map = machine__kernel_map(host_machine);
 	dso = map__dso(map);
-	if (!dso->has_build_id)
+	if (!dso__has_build_id(dso))
 		dso__read_running_kernel_build_id(dso, host_machine);
 
 	vmlinux_name = symbol_conf.vmlinux_name;
-	dso->load_errno = 0;
+	*dso__load_errno(dso) = 0;
 	if (vmlinux_name)
 		ret = dso__load_vmlinux(dso, map, vmlinux_name, false);
 	else
@@ -499,7 +498,7 @@ static struct debuginfo *open_from_debuginfod(struct dso *dso, struct nsinfo *ns
 	if (!c)
 		return NULL;
 
-	build_id__sprintf(&dso->bid, sbuild_id);
+	build_id__sprintf(dso__bid(dso), sbuild_id);
 	fd = debuginfod_find_debuginfo(c, (const unsigned char *)sbuild_id,
 					0, &path);
 	if (fd >= 0)
@@ -542,7 +541,7 @@ static struct debuginfo *open_debuginfo(const char *module, struct nsinfo *nsi,
 	if (!module || !strchr(module, '/')) {
 		err = kernel_get_module_dso(module, &dso);
 		if (err < 0) {
-			if (!dso || dso->load_errno == 0) {
+			if (!dso || *dso__load_errno(dso) == 0) {
 				if (!str_error_r(-err, reason, STRERR_BUFSIZE))
 					strcpy(reason, "(unknown)");
 			} else
@@ -559,7 +558,7 @@ static struct debuginfo *open_debuginfo(const char *module, struct nsinfo *nsi,
 			}
 			return NULL;
 		}
-		path = dso->long_name;
+		path = dso__long_name(dso);
 	}
 	nsinfo__mountns_enter(nsi, &nsc);
 	ret = debuginfo__new(path);
@@ -2758,7 +2757,7 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 	/* Try no suffix number */
 	ret = e_snprintf(buf, len, "%s%s", nbase, ret_event ? "__return" : "");
 	if (ret < 0) {
-		pr_debug("snprintf() failed: %d\n", ret);
+		pr_warning("snprintf() failed: %d; the event name nbase='%s' is too long\n", ret, nbase);
 		goto out;
 	}
 	if (!strlist__has_entry(namelist, buf))
@@ -2867,7 +2866,7 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
 		group = PERFPROBE_GROUP;
 
 	/* Get an unused new event name */
-	ret = get_new_event_name(buf, 64, event, namelist,
+	ret = get_new_event_name(buf, sizeof(buf), event, namelist,
 				 tev->point.retprobe, allow_suffix);
 	if (ret < 0)
 		return ret;
@@ -3795,8 +3794,8 @@ int show_available_funcs(const char *target, struct nsinfo *nsi,
 	/* Show all (filtered) symbols */
 	setup_pager();
 
-	for (size_t i = 0; i < dso->symbol_names_len; i++) {
-		struct symbol *pos = dso->symbol_names[i];
+	for (size_t i = 0; i < dso__symbol_names_len(dso); i++) {
+		struct symbol *pos = dso__symbol_names(dso)[i];
 
 		if (strfilter__compare(_filter, pos->name))
 			printf("%s\n", pos->name);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index c8923375e3..630e16c54e 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -186,8 +186,6 @@ static_var:
 	return ret2;
 }
 
-#define BYTES_TO_BITS(nb)	((nb) * BITS_PER_LONG / sizeof(long))
-
 static int convert_variable_type(Dwarf_Die *vr_die,
 				 struct probe_trace_arg *tvar,
 				 const char *cast, bool user_access)
@@ -217,7 +215,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 		total = dwarf_bytesize(vr_die);
 		if (boffs < 0 || total < 0)
 			return -ENOENT;
-		ret = snprintf(buf, 16, "b%d@%d/%zd", bsize, boffs,
+		ret = snprintf(buf, 16, "b%d@%d/%d", bsize, boffs,
 				BYTES_TO_BITS(total));
 		goto formatted;
 	}
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 87e817b3cf..e867de8dda 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -237,7 +237,7 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str)
 
 	evsel = evlist__last(temp_evlist);
 
-	if (!evlist || perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus)) {
+	if (!evlist || perf_cpu_map__is_any_cpu_or_is_empty(evlist->core.user_requested_cpus)) {
 		struct perf_cpu_map *cpus = perf_cpu_map__new_online_cpus();
 
 		if (cpus)
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b072ac5d3b..e16257d5ab 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -320,10 +320,10 @@ static SV *perl_process_callchain(struct perf_sample *sample,
 			const char *dsoname = "[unknown]";
 
 			if (dso) {
-				if (symbol_conf.show_kernel_path && dso->long_name)
-					dsoname = dso->long_name;
+				if (symbol_conf.show_kernel_path && dso__long_name(dso))
+					dsoname = dso__long_name(dso);
 				else
-					dsoname = dso->name;
+					dsoname = dso__name(dso);
 			}
 			if (!hv_stores(elem, "dso", newSVpv(dsoname,0))) {
 				hv_undef(elem);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index b4f0f60e60..fb00f3ad68 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -45,6 +45,7 @@
 #include "../thread.h"
 #include "../comm.h"
 #include "../machine.h"
+#include "../mem-info.h"
 #include "../db-export.h"
 #include "../thread-stack.h"
 #include "../trace-event.h"
@@ -393,10 +394,10 @@ static const char *get_dsoname(struct map *map)
 	struct dso *dso = map ? map__dso(map) : NULL;
 
 	if (dso) {
-		if (symbol_conf.show_kernel_path && dso->long_name)
-			dsoname = dso->long_name;
+		if (symbol_conf.show_kernel_path && dso__long_name(dso))
+			dsoname = dso__long_name(dso);
 		else
-			dsoname = dso->name;
+			dsoname = dso__name(dso);
 	}
 
 	return dsoname;
@@ -720,15 +721,20 @@ static void set_sample_read_in_dict(PyObject *dict_sample,
 }
 
 static void set_sample_datasrc_in_dict(PyObject *dict,
-				       struct perf_sample *sample)
+				      struct perf_sample *sample)
 {
-	struct mem_info mi = { .data_src.val = sample->data_src };
+	struct mem_info *mi = mem_info__new();
 	char decode[100];
 
+	if (!mi)
+		Py_FatalError("couldn't create mem-info");
+
 	pydict_set_item_string_decref(dict, "datasrc",
 			PyLong_FromUnsignedLongLong(sample->data_src));
 
-	perf_script__meminfo_scnprintf(decode, 100, &mi);
+	mem_info__data_src(mi)->val = sample->data_src;
+	perf_script__meminfo_scnprintf(decode, 100, mi);
+	mem_info__put(mi);
 
 	pydict_set_item_string_decref(dict, "datasrc_decode",
 			_PyUnicode_FromString(decode));
@@ -799,8 +805,9 @@ static void set_sym_in_dict(PyObject *dict, struct addr_location *al,
 	if (al->map) {
 		struct dso *dso = map__dso(al->map);
 
-		pydict_set_item_string_decref(dict, dso_field, _PyUnicode_FromString(dso->name));
-		build_id__sprintf(&dso->bid, sbuild_id);
+		pydict_set_item_string_decref(dict, dso_field,
+					      _PyUnicode_FromString(dso__name(dso)));
+		build_id__sprintf(dso__bid(dso), sbuild_id);
 		pydict_set_item_string_decref(dict, dso_bid_field,
 			_PyUnicode_FromString(sbuild_id));
 		pydict_set_item_string_decref(dict, dso_map_start,
@@ -1246,14 +1253,14 @@ static int python_export_dso(struct db_export *dbe, struct dso *dso,
 	char sbuild_id[SBUILD_ID_SIZE];
 	PyObject *t;
 
-	build_id__sprintf(&dso->bid, sbuild_id);
+	build_id__sprintf(dso__bid(dso), sbuild_id);
 
 	t = tuple_new(5);
 
-	tuple_set_d64(t, 0, dso->db_id);
+	tuple_set_d64(t, 0, dso__db_id(dso));
 	tuple_set_d64(t, 1, machine->db_id);
-	tuple_set_string(t, 2, dso->short_name);
-	tuple_set_string(t, 3, dso->long_name);
+	tuple_set_string(t, 2, dso__short_name(dso));
+	tuple_set_string(t, 3, dso__long_name(dso));
 	tuple_set_string(t, 4, sbuild_id);
 
 	call_object(tables->dso_handler, t, "dso_table");
@@ -1273,7 +1280,7 @@ static int python_export_symbol(struct db_export *dbe, struct symbol *sym,
 	t = tuple_new(6);
 
 	tuple_set_d64(t, 0, *sym_db_id);
-	tuple_set_d64(t, 1, dso->db_id);
+	tuple_set_d64(t, 1, dso__db_id(dso));
 	tuple_set_d64(t, 2, sym->start);
 	tuple_set_d64(t, 3, sym->end);
 	tuple_set_s32(t, 4, sym->binding);
@@ -1699,13 +1706,15 @@ static void python_process_stat(struct perf_stat_config *config,
 {
 	struct perf_thread_map *threads = counter->core.threads;
 	struct perf_cpu_map *cpus = counter->core.cpus;
-	int cpu, thread;
 
-	for (thread = 0; thread < perf_thread_map__nr(threads); thread++) {
-		for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
-			process_stat(counter, perf_cpu_map__cpu(cpus, cpu),
+	for (int thread = 0; thread < perf_thread_map__nr(threads); thread++) {
+		int idx;
+		struct perf_cpu cpu;
+
+		perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+			process_stat(counter, cpu,
 				     perf_thread_map__pid(threads, thread), tstamp,
-				     perf_counts(counter->counts, cpu, thread));
+				     perf_counts(counter->counts, idx, thread));
 		}
 	}
 }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 06d0bd7fb4..a10343b9dc 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -2749,6 +2749,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 	int i, err = -1;
 	struct perf_cpu_map *map;
 	int nr_cpus = min(session->header.env.nr_cpus_avail, MAX_NR_CPUS);
+	struct perf_cpu cpu;
 
 	for (i = 0; i < PERF_TYPE_MAX; ++i) {
 		struct evsel *evsel;
@@ -2770,9 +2771,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 		return -1;
 	}
 
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		struct perf_cpu cpu = perf_cpu_map__cpu(map, i);
-
+	perf_cpu_map__for_each_cpu(cpu, i, map) {
 		if (cpu.cpu >= nr_cpus) {
 			pr_err("Requested CPU %d too large. "
 			       "Consider raising MAX_NR_CPUS\n", cpu.cpu);
@@ -2917,3 +2916,24 @@ int perf_event__process_id_index(struct perf_session *session,
 	}
 	return 0;
 }
+
+int perf_session__dsos_hit_all(struct perf_session *session)
+{
+	struct rb_node *nd;
+	int err;
+
+	err = machine__hit_all_dsos(&session->machines.host);
+	if (err)
+		return err;
+
+	for (nd = rb_first_cached(&session->machines.guests); nd;
+	     nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+
+		err = machine__hit_all_dsos(pos);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 5064c6ec11..3b0256e977 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -156,6 +156,8 @@ int perf_session__deliver_synth_event(struct perf_session *session,
 				      union perf_event *event,
 				      struct perf_sample *sample);
 
+int perf_session__dsos_hit_all(struct perf_session *session);
+
 int perf_event__process_id_index(struct perf_session *session,
 				 union perf_event *event);
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 92a1bd695e..ab7c7ff35f 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -23,6 +23,7 @@
 #include "strlist.h"
 #include "strbuf.h"
 #include "mem-events.h"
+#include "mem-info.h"
 #include "annotate.h"
 #include "annotate-data.h"
 #include "event.h"
@@ -239,11 +240,11 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r)
 		return cmp_null(dso_r, dso_l);
 
 	if (verbose > 0) {
-		dso_name_l = dso_l->long_name;
-		dso_name_r = dso_r->long_name;
+		dso_name_l = dso__long_name(dso_l);
+		dso_name_r = dso__long_name(dso_r);
 	} else {
-		dso_name_l = dso_l->short_name;
-		dso_name_r = dso_r->short_name;
+		dso_name_l = dso__short_name(dso_l);
+		dso_name_r = dso__short_name(dso_r);
 	}
 
 	return strcmp(dso_name_l, dso_name_r);
@@ -262,7 +263,7 @@ static int _hist_entry__dso_snprintf(struct map *map, char *bf,
 	const char *dso_name = "[unknown]";
 
 	if (dso)
-		dso_name = verbose > 0 ? dso->long_name : dso->short_name;
+		dso_name = verbose > 0 ? dso__long_name(dso) : dso__short_name(dso);
 
 	return repsep_snprintf(bf, size, "%-*.*s", width, width, dso_name);
 }
@@ -333,7 +334,7 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
 	 * comparing symbol address alone is not enough since it's a
 	 * relative address within a dso.
 	 */
-	if (!hists__has(left->hists, dso) || hists__has(right->hists, dso)) {
+	if (!hists__has(left->hists, dso)) {
 		ret = sort__dso_cmp(left, right);
 		if (ret != 0)
 			return ret;
@@ -364,7 +365,7 @@ static int _hist_entry__sym_snprintf(struct map_symbol *ms,
 		char o = dso ? dso__symtab_origin(dso) : '!';
 		u64 rip = ip;
 
-		if (dso && dso->kernel && dso->adjust_symbols)
+		if (dso && dso__kernel(dso) && dso__adjust_symbols(dso))
 			rip = map__unmap_ip(map, ip);
 
 		ret += repsep_snprintf(bf, size, "%-#*llx %c ",
@@ -1364,9 +1365,9 @@ sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right)
 	uint64_t l = 0, r = 0;
 
 	if (left->mem_info)
-		l = left->mem_info->daddr.addr;
+		l = mem_info__daddr(left->mem_info)->addr;
 	if (right->mem_info)
-		r = right->mem_info->daddr.addr;
+		r = mem_info__daddr(right->mem_info)->addr;
 
 	return (int64_t)(r - l);
 }
@@ -1378,8 +1379,8 @@ static int hist_entry__daddr_snprintf(struct hist_entry *he, char *bf,
 	struct map_symbol *ms = NULL;
 
 	if (he->mem_info) {
-		addr = he->mem_info->daddr.addr;
-		ms = &he->mem_info->daddr.ms;
+		addr = mem_info__daddr(he->mem_info)->addr;
+		ms = &mem_info__daddr(he->mem_info)->ms;
 	}
 	return _hist_entry__sym_snprintf(ms, addr, he->level, bf, size, width);
 }
@@ -1390,9 +1391,9 @@ sort__iaddr_cmp(struct hist_entry *left, struct hist_entry *right)
 	uint64_t l = 0, r = 0;
 
 	if (left->mem_info)
-		l = left->mem_info->iaddr.addr;
+		l = mem_info__iaddr(left->mem_info)->addr;
 	if (right->mem_info)
-		r = right->mem_info->iaddr.addr;
+		r = mem_info__iaddr(right->mem_info)->addr;
 
 	return (int64_t)(r - l);
 }
@@ -1404,8 +1405,8 @@ static int hist_entry__iaddr_snprintf(struct hist_entry *he, char *bf,
 	struct map_symbol *ms = NULL;
 
 	if (he->mem_info) {
-		addr = he->mem_info->iaddr.addr;
-		ms   = &he->mem_info->iaddr.ms;
+		addr = mem_info__iaddr(he->mem_info)->addr;
+		ms   = &mem_info__iaddr(he->mem_info)->ms;
 	}
 	return _hist_entry__sym_snprintf(ms, addr, he->level, bf, size, width);
 }
@@ -1417,9 +1418,9 @@ sort__dso_daddr_cmp(struct hist_entry *left, struct hist_entry *right)
 	struct map *map_r = NULL;
 
 	if (left->mem_info)
-		map_l = left->mem_info->daddr.ms.map;
+		map_l = mem_info__daddr(left->mem_info)->ms.map;
 	if (right->mem_info)
-		map_r = right->mem_info->daddr.ms.map;
+		map_r = mem_info__daddr(right->mem_info)->ms.map;
 
 	return _sort__dso_cmp(map_l, map_r);
 }
@@ -1430,7 +1431,7 @@ static int hist_entry__dso_daddr_snprintf(struct hist_entry *he, char *bf,
 	struct map *map = NULL;
 
 	if (he->mem_info)
-		map = he->mem_info->daddr.ms.map;
+		map = mem_info__daddr(he->mem_info)->ms.map;
 
 	return _hist_entry__dso_snprintf(map, bf, size, width);
 }
@@ -1442,12 +1443,12 @@ sort__locked_cmp(struct hist_entry *left, struct hist_entry *right)
 	union perf_mem_data_src data_src_r;
 
 	if (left->mem_info)
-		data_src_l = left->mem_info->data_src;
+		data_src_l = *mem_info__data_src(left->mem_info);
 	else
 		data_src_l.mem_lock = PERF_MEM_LOCK_NA;
 
 	if (right->mem_info)
-		data_src_r = right->mem_info->data_src;
+		data_src_r = *mem_info__data_src(right->mem_info);
 	else
 		data_src_r.mem_lock = PERF_MEM_LOCK_NA;
 
@@ -1470,12 +1471,12 @@ sort__tlb_cmp(struct hist_entry *left, struct hist_entry *right)
 	union perf_mem_data_src data_src_r;
 
 	if (left->mem_info)
-		data_src_l = left->mem_info->data_src;
+		data_src_l = *mem_info__data_src(left->mem_info);
 	else
 		data_src_l.mem_dtlb = PERF_MEM_TLB_NA;
 
 	if (right->mem_info)
-		data_src_r = right->mem_info->data_src;
+		data_src_r = *mem_info__data_src(right->mem_info);
 	else
 		data_src_r.mem_dtlb = PERF_MEM_TLB_NA;
 
@@ -1498,12 +1499,12 @@ sort__lvl_cmp(struct hist_entry *left, struct hist_entry *right)
 	union perf_mem_data_src data_src_r;
 
 	if (left->mem_info)
-		data_src_l = left->mem_info->data_src;
+		data_src_l = *mem_info__data_src(left->mem_info);
 	else
 		data_src_l.mem_lvl = PERF_MEM_LVL_NA;
 
 	if (right->mem_info)
-		data_src_r = right->mem_info->data_src;
+		data_src_r = *mem_info__data_src(right->mem_info);
 	else
 		data_src_r.mem_lvl = PERF_MEM_LVL_NA;
 
@@ -1526,12 +1527,12 @@ sort__snoop_cmp(struct hist_entry *left, struct hist_entry *right)
 	union perf_mem_data_src data_src_r;
 
 	if (left->mem_info)
-		data_src_l = left->mem_info->data_src;
+		data_src_l = *mem_info__data_src(left->mem_info);
 	else
 		data_src_l.mem_snoop = PERF_MEM_SNOOP_NA;
 
 	if (right->mem_info)
-		data_src_r = right->mem_info->data_src;
+		data_src_r = *mem_info__data_src(right->mem_info);
 	else
 		data_src_r.mem_snoop = PERF_MEM_SNOOP_NA;
 
@@ -1562,8 +1563,8 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
 	if (left->cpumode > right->cpumode) return -1;
 	if (left->cpumode < right->cpumode) return 1;
 
-	l_map = left->mem_info->daddr.ms.map;
-	r_map = right->mem_info->daddr.ms.map;
+	l_map = mem_info__daddr(left->mem_info)->ms.map;
+	r_map = mem_info__daddr(right->mem_info)->ms.map;
 
 	/* if both are NULL, jump to sort on al_addr instead */
 	if (!l_map && !r_map)
@@ -1586,8 +1587,8 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
 	 */
 
 	if ((left->cpumode != PERF_RECORD_MISC_KERNEL) &&
-	    (!(map__flags(l_map) & MAP_SHARED)) && !l_dso->id.maj && !l_dso->id.min &&
-	    !l_dso->id.ino && !l_dso->id.ino_generation) {
+	    (!(map__flags(l_map) & MAP_SHARED)) && !dso__id(l_dso)->maj && !dso__id(l_dso)->min &&
+	     !dso__id(l_dso)->ino && !dso__id(l_dso)->ino_generation) {
 		/* userspace anonymous */
 
 		if (thread__pid(left->thread) > thread__pid(right->thread))
@@ -1598,8 +1599,8 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
 
 addr:
 	/* al_addr does all the right addr - start + offset calculations */
-	l = cl_address(left->mem_info->daddr.al_addr, chk_double_cl);
-	r = cl_address(right->mem_info->daddr.al_addr, chk_double_cl);
+	l = cl_address(mem_info__daddr(left->mem_info)->al_addr, chk_double_cl);
+	r = cl_address(mem_info__daddr(right->mem_info)->al_addr, chk_double_cl);
 
 	if (l > r) return -1;
 	if (l < r) return 1;
@@ -1616,17 +1617,18 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf,
 	char level = he->level;
 
 	if (he->mem_info) {
-		struct map *map = he->mem_info->daddr.ms.map;
+		struct map *map = mem_info__daddr(he->mem_info)->ms.map;
 		struct dso *dso = map ? map__dso(map) : NULL;
 
-		addr = cl_address(he->mem_info->daddr.al_addr, chk_double_cl);
-		ms = &he->mem_info->daddr.ms;
+		addr = cl_address(mem_info__daddr(he->mem_info)->al_addr, chk_double_cl);
+		ms = &mem_info__daddr(he->mem_info)->ms;
 
 		/* print [s] for shared data mmaps */
 		if ((he->cpumode != PERF_RECORD_MISC_KERNEL) &&
 		     map && !(map__prot(map) & PROT_EXEC) &&
 		     (map__flags(map) & MAP_SHARED) &&
-		    (dso->id.maj || dso->id.min || dso->id.ino || dso->id.ino_generation))
+		     (dso__id(dso)->maj || dso__id(dso)->min || dso__id(dso)->ino ||
+		      dso__id(dso)->ino_generation))
 			level = 's';
 		else if (!map)
 			level = 'X';
@@ -1804,12 +1806,12 @@ sort__blocked_cmp(struct hist_entry *left, struct hist_entry *right)
 	union perf_mem_data_src data_src_r;
 
 	if (left->mem_info)
-		data_src_l = left->mem_info->data_src;
+		data_src_l = *mem_info__data_src(left->mem_info);
 	else
 		data_src_l.mem_blk = PERF_MEM_BLK_NA;
 
 	if (right->mem_info)
-		data_src_r = right->mem_info->data_src;
+		data_src_r = *mem_info__data_src(right->mem_info);
 	else
 		data_src_r.mem_blk = PERF_MEM_BLK_NA;
 
@@ -1838,9 +1840,9 @@ sort__phys_daddr_cmp(struct hist_entry *left, struct hist_entry *right)
 	uint64_t l = 0, r = 0;
 
 	if (left->mem_info)
-		l = left->mem_info->daddr.phys_addr;
+		l = mem_info__daddr(left->mem_info)->phys_addr;
 	if (right->mem_info)
-		r = right->mem_info->daddr.phys_addr;
+		r = mem_info__daddr(right->mem_info)->phys_addr;
 
 	return (int64_t)(r - l);
 }
@@ -1852,7 +1854,7 @@ static int hist_entry__phys_daddr_snprintf(struct hist_entry *he, char *bf,
 	size_t ret = 0;
 	size_t len = BITS_PER_LONG / 4;
 
-	addr = he->mem_info->daddr.phys_addr;
+	addr = mem_info__daddr(he->mem_info)->phys_addr;
 
 	ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", he->level);
 
@@ -1879,9 +1881,9 @@ sort__data_page_size_cmp(struct hist_entry *left, struct hist_entry *right)
 	uint64_t l = 0, r = 0;
 
 	if (left->mem_info)
-		l = left->mem_info->daddr.data_page_size;
+		l = mem_info__daddr(left->mem_info)->data_page_size;
 	if (right->mem_info)
-		r = right->mem_info->daddr.data_page_size;
+		r = mem_info__daddr(right->mem_info)->data_page_size;
 
 	return (int64_t)(r - l);
 }
@@ -1892,7 +1894,7 @@ static int hist_entry__data_page_size_snprintf(struct hist_entry *he, char *bf,
 	char str[PAGE_SIZE_NAME_LEN];
 
 	return repsep_snprintf(bf, size, "%-*s", width,
-			       get_page_size_name(he->mem_info->daddr.data_page_size, str));
+			get_page_size_name(mem_info__daddr(he->mem_info)->data_page_size, str));
 }
 
 struct sort_entry sort_mem_data_page_size = {
@@ -2441,6 +2443,13 @@ static struct hpp_dimension hpp_sort_dimensions[] = {
 	DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"),
 	DIM(PERF_HPP__SAMPLES, "sample"),
 	DIM(PERF_HPP__PERIOD, "period"),
+	DIM(PERF_HPP__WEIGHT1, "weight1"),
+	DIM(PERF_HPP__WEIGHT2, "weight2"),
+	DIM(PERF_HPP__WEIGHT3, "weight3"),
+	/* aliases for weight_struct */
+	DIM(PERF_HPP__WEIGHT2, "ins_lat"),
+	DIM(PERF_HPP__WEIGHT3, "retire_lat"),
+	DIM(PERF_HPP__WEIGHT3, "p_stage_cyc"),
 };
 
 #undef DIM
@@ -3743,26 +3752,29 @@ void sort__setup_elide(FILE *output)
 	}
 }
 
-int output_field_add(struct perf_hpp_list *list, char *tok)
+int output_field_add(struct perf_hpp_list *list, const char *tok)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) {
-		struct sort_dimension *sd = &common_sort_dimensions[i];
+	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
+		struct hpp_dimension *hd = &hpp_sort_dimensions[i];
 
-		if (!sd->name || strncasecmp(tok, sd->name, strlen(tok)))
+		if (strncasecmp(tok, hd->name, strlen(tok)))
 			continue;
 
-		return __sort_dimension__add_output(list, sd);
+		if (!strcasecmp(tok, "weight"))
+			ui__warning("--fields weight shows the average value unlike in the --sort key.\n");
+
+		return __hpp_dimension__add_output(list, hd);
 	}
 
-	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
-		struct hpp_dimension *hd = &hpp_sort_dimensions[i];
+	for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) {
+		struct sort_dimension *sd = &common_sort_dimensions[i];
 
-		if (strncasecmp(tok, hd->name, strlen(tok)))
+		if (!sd->name || strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		return __hpp_dimension__add_output(list, hd);
+		return __sort_dimension__add_output(list, sd);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 6f6b4189a3..0bd0ee3ae7 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -3,19 +3,9 @@
 #define __PERF_SORT_H
 #include <regex.h>
 #include <stdbool.h>
-#include <linux/list.h>
-#include <linux/rbtree.h>
-#include "map_symbol.h"
-#include "symbol_conf.h"
-#include "callchain.h"
-#include "values.h"
 #include "hist.h"
-#include "stat.h"
-#include "spark.h"
 
 struct option;
-struct thread;
-struct annotated_data_type;
 
 extern regex_t parent_regex;
 extern const char *sort_order;
@@ -39,175 +29,6 @@ extern struct sort_entry sort_type;
 extern const char default_mem_sort_order[];
 extern bool chk_double_cl;
 
-struct res_sample {
-	u64 time;
-	int cpu;
-	int tid;
-};
-
-struct he_stat {
-	u64			period;
-	u64			period_sys;
-	u64			period_us;
-	u64			period_guest_sys;
-	u64			period_guest_us;
-	u32			nr_events;
-};
-
-struct namespace_id {
-	u64			dev;
-	u64			ino;
-};
-
-struct hist_entry_diff {
-	bool	computed;
-	union {
-		/* PERF_HPP__DELTA */
-		double	period_ratio_delta;
-
-		/* PERF_HPP__RATIO */
-		double	period_ratio;
-
-		/* HISTC_WEIGHTED_DIFF */
-		s64	wdiff;
-
-		/* PERF_HPP_DIFF__CYCLES */
-		s64	cycles;
-	};
-	struct stats	stats;
-	unsigned long	svals[NUM_SPARKS];
-};
-
-struct hist_entry_ops {
-	void	*(*new)(size_t size);
-	void	(*free)(void *ptr);
-};
-
-/**
- * struct hist_entry - histogram entry
- *
- * @row_offset - offset from the first callchain expanded to appear on screen
- * @nr_rows - rows expanded in callchain, recalculated on folding/unfolding
- */
-struct hist_entry {
-	struct rb_node		rb_node_in;
-	struct rb_node		rb_node;
-	union {
-		struct list_head node;
-		struct list_head head;
-	} pairs;
-	struct he_stat		stat;
-	struct he_stat		*stat_acc;
-	struct map_symbol	ms;
-	struct thread		*thread;
-	struct comm		*comm;
-	struct namespace_id	cgroup_id;
-	u64			cgroup;
-	u64			ip;
-	u64			transaction;
-	s32			socket;
-	s32			cpu;
-	u64			code_page_size;
-	u64			weight;
-	u64			ins_lat;
-	u64			p_stage_cyc;
-	u8			cpumode;
-	u8			depth;
-	int			mem_type_off;
-	struct simd_flags	simd_flags;
-
-	/* We are added by hists__add_dummy_entry. */
-	bool			dummy;
-	bool			leaf;
-
-	char			level;
-	u8			filtered;
-
-	u16			callchain_size;
-	union {
-		/*
-		 * Since perf diff only supports the stdio output, TUI
-		 * fields are only accessed from perf report (or perf
-		 * top).  So make it a union to reduce memory usage.
-		 */
-		struct hist_entry_diff	diff;
-		struct /* for TUI */ {
-			u16	row_offset;
-			u16	nr_rows;
-			bool	init_have_children;
-			bool	unfolded;
-			bool	has_children;
-			bool	has_no_entry;
-		};
-	};
-	char			*srcline;
-	char			*srcfile;
-	struct symbol		*parent;
-	struct branch_info	*branch_info;
-	long			time;
-	struct hists		*hists;
-	struct mem_info		*mem_info;
-	struct block_info	*block_info;
-	struct kvm_info		*kvm_info;
-	void			*raw_data;
-	u32			raw_size;
-	int			num_res;
-	struct res_sample	*res_samples;
-	void			*trace_output;
-	struct perf_hpp_list	*hpp_list;
-	struct hist_entry	*parent_he;
-	struct hist_entry_ops	*ops;
-	struct annotated_data_type *mem_type;
-	union {
-		/* this is for hierarchical entry structure */
-		struct {
-			struct rb_root_cached	hroot_in;
-			struct rb_root_cached   hroot_out;
-		};				/* non-leaf entries */
-		struct rb_root	sorted_chain;	/* leaf entry has callchains */
-	};
-	struct callchain_root	callchain[0]; /* must be last member */
-};
-
-static __pure inline bool hist_entry__has_callchains(struct hist_entry *he)
-{
-	return he->callchain_size != 0;
-}
-
-int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width);
-
-static inline bool hist_entry__has_pairs(struct hist_entry *he)
-{
-	return !list_empty(&he->pairs.node);
-}
-
-static inline struct hist_entry *hist_entry__next_pair(struct hist_entry *he)
-{
-	if (hist_entry__has_pairs(he))
-		return list_entry(he->pairs.node.next, struct hist_entry, pairs.node);
-	return NULL;
-}
-
-static inline void hist_entry__add_pair(struct hist_entry *pair,
-					struct hist_entry *he)
-{
-	list_add_tail(&pair->pairs.node, &he->pairs.head);
-}
-
-static inline float hist_entry__get_percent_limit(struct hist_entry *he)
-{
-	u64 period = he->stat.period;
-	u64 total_period = hists__total_period(he->hists);
-
-	if (unlikely(total_period == 0))
-		return 0;
-
-	if (symbol_conf.cumulate_callchain)
-		period = he->stat_acc->period;
-
-	return period * 100.0 / total_period;
-}
-
 enum sort_mode {
 	SORT_MODE__NORMAL,
 	SORT_MODE__BRANCH,
@@ -299,15 +120,6 @@ struct sort_entry {
 	u8	se_width_idx;
 };
 
-struct block_hist {
-	struct hists		block_hists;
-	struct perf_hpp_list	block_list;
-	struct perf_hpp_fmt	block_fmt;
-	int			block_idx;
-	bool			valid;
-	struct hist_entry	he;
-};
-
 extern struct sort_entry sort_thread;
 
 struct evlist;
@@ -329,7 +141,7 @@ void reset_dimensions(void);
 int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 			struct evlist *evlist,
 			int level);
-int output_field_add(struct perf_hpp_list *list, char *tok);
+int output_field_add(struct perf_hpp_list *list, const char *tok);
 int64_t
 sort__iaddr_cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 7addc34afc..4d67c1e095 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -27,14 +27,14 @@ bool srcline_full_filename;
 
 char *srcline__unknown = (char *)"??:0";
 
-static const char *dso__name(struct dso *dso)
+static const char *srcline_dso_name(struct dso *dso)
 {
 	const char *dso_name;
 
-	if (dso->symsrc_filename)
-		dso_name = dso->symsrc_filename;
+	if (dso__symsrc_filename(dso))
+		dso_name = dso__symsrc_filename(dso);
 	else
-		dso_name = dso->long_name;
+		dso_name = dso__long_name(dso);
 
 	if (dso_name[0] == '[')
 		return NULL;
@@ -288,7 +288,7 @@ static int inline_list__append_dso_a2l(struct dso *dso,
 				       struct inline_node *node,
 				       struct symbol *sym)
 {
-	struct a2l_data *a2l = dso->a2l;
+	struct a2l_data *a2l = dso__a2l(dso);
 	struct symbol *inline_sym = new_inline_sym(dso, sym, a2l->funcname);
 	char *srcline = NULL;
 
@@ -304,11 +304,11 @@ static int addr2line(const char *dso_name, u64 addr,
 		     struct symbol *sym)
 {
 	int ret = 0;
-	struct a2l_data *a2l = dso->a2l;
+	struct a2l_data *a2l = dso__a2l(dso);
 
 	if (!a2l) {
-		dso->a2l = addr2line_init(dso_name);
-		a2l = dso->a2l;
+		a2l = addr2line_init(dso_name);
+		dso__set_a2l(dso, a2l);
 	}
 
 	if (a2l == NULL) {
@@ -360,14 +360,14 @@ static int addr2line(const char *dso_name, u64 addr,
 
 void dso__free_a2l(struct dso *dso)
 {
-	struct a2l_data *a2l = dso->a2l;
+	struct a2l_data *a2l = dso__a2l(dso);
 
 	if (!a2l)
 		return;
 
 	addr2line_cleanup(a2l);
 
-	dso->a2l = NULL;
+	dso__set_a2l(dso, NULL);
 }
 
 #else /* HAVE_LIBBFD_SUPPORT */
@@ -638,7 +638,7 @@ static int addr2line(const char *dso_name, u64 addr,
 		     struct inline_node *node,
 		     struct symbol *sym __maybe_unused)
 {
-	struct child_process *a2l = dso->a2l;
+	struct child_process *a2l = dso__a2l(dso);
 	char *record_function = NULL;
 	char *record_filename = NULL;
 	unsigned int record_line_nr = 0;
@@ -655,8 +655,9 @@ static int addr2line(const char *dso_name, u64 addr,
 		if (!filename__has_section(dso_name, ".debug_line"))
 			goto out;
 
-		dso->a2l = addr2line_subprocess_init(symbol_conf.addr2line_path, dso_name);
-		a2l = dso->a2l;
+		dso__set_a2l(dso,
+			     addr2line_subprocess_init(symbol_conf.addr2line_path, dso_name));
+		a2l = dso__a2l(dso);
 	}
 
 	if (a2l == NULL) {
@@ -770,7 +771,7 @@ out:
 	free(record_function);
 	free(record_filename);
 	if (io.eof) {
-		dso->a2l = NULL;
+		dso__set_a2l(dso, NULL);
 		addr2line_subprocess_cleanup(a2l);
 	}
 	return ret;
@@ -778,14 +779,14 @@ out:
 
 void dso__free_a2l(struct dso *dso)
 {
-	struct child_process *a2l = dso->a2l;
+	struct child_process *a2l = dso__a2l(dso);
 
 	if (!a2l)
 		return;
 
 	addr2line_subprocess_cleanup(a2l);
 
-	dso->a2l = NULL;
+	dso__set_a2l(dso, NULL);
 }
 
 #endif /* HAVE_LIBBFD_SUPPORT */
@@ -823,33 +824,34 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 	char *srcline;
 	const char *dso_name;
 
-	if (!dso->has_srcline)
+	if (!dso__has_srcline(dso))
 		goto out;
 
-	dso_name = dso__name(dso);
+	dso_name = srcline_dso_name(dso);
 	if (dso_name == NULL)
-		goto out;
+		goto out_err;
 
 	if (!addr2line(dso_name, addr, &file, &line, dso,
 		       unwind_inlines, NULL, sym))
-		goto out;
+		goto out_err;
 
 	srcline = srcline_from_fileline(file, line);
 	free(file);
 
 	if (!srcline)
-		goto out;
+		goto out_err;
 
-	dso->a2l_fails = 0;
+	dso__set_a2l_fails(dso, 0);
 
 	return srcline;
 
-out:
-	if (dso->a2l_fails && ++dso->a2l_fails > A2L_FAIL_LIMIT) {
-		dso->has_srcline = 0;
+out_err:
+	dso__set_a2l_fails(dso, dso__a2l_fails(dso) + 1);
+	if (dso__a2l_fails(dso) > A2L_FAIL_LIMIT) {
+		dso__set_has_srcline(dso, false);
 		dso__free_a2l(dso);
 	}
-
+out:
 	if (!show_addr)
 		return (show_sym && sym) ?
 			    strndup(sym->name, sym->namelen) : SRCLINE_UNKNOWN;
@@ -858,7 +860,7 @@ out:
 		if (asprintf(&srcline, "%s+%" PRIu64, show_sym ? sym->name : "",
 					ip - sym->start) < 0)
 			return SRCLINE_UNKNOWN;
-	} else if (asprintf(&srcline, "%s[%" PRIx64 "]", dso->short_name, addr) < 0)
+	} else if (asprintf(&srcline, "%s[%" PRIx64 "]", dso__short_name(dso), addr) < 0)
 		return SRCLINE_UNKNOWN;
 	return srcline;
 }
@@ -869,22 +871,23 @@ char *get_srcline_split(struct dso *dso, u64 addr, unsigned *line)
 	char *file = NULL;
 	const char *dso_name;
 
-	if (!dso->has_srcline)
-		goto out;
+	if (!dso__has_srcline(dso))
+		return NULL;
 
-	dso_name = dso__name(dso);
+	dso_name = srcline_dso_name(dso);
 	if (dso_name == NULL)
-		goto out;
+		goto out_err;
 
 	if (!addr2line(dso_name, addr, &file, line, dso, true, NULL, NULL))
-		goto out;
+		goto out_err;
 
-	dso->a2l_fails = 0;
+	dso__set_a2l_fails(dso, 0);
 	return file;
 
-out:
-	if (dso->a2l_fails && ++dso->a2l_fails > A2L_FAIL_LIMIT) {
-		dso->has_srcline = 0;
+out_err:
+	dso__set_a2l_fails(dso, dso__a2l_fails(dso) + 1);
+	if (dso__a2l_fails(dso) > A2L_FAIL_LIMIT) {
+		dso__set_has_srcline(dso, false);
 		dso__free_a2l(dso);
 	}
 
@@ -982,7 +985,7 @@ struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr,
 {
 	const char *dso_name;
 
-	dso_name = dso__name(dso);
+	dso_name = srcline_dso_name(dso);
 	if (dso_name == NULL)
 		return NULL;
 
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 91d2f7f65d..186305fd2d 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -38,6 +38,7 @@
 static int aggr_header_lens[] = {
 	[AGGR_CORE] 	= 18,
 	[AGGR_CACHE]	= 22,
+	[AGGR_CLUSTER]	= 20,
 	[AGGR_DIE] 	= 12,
 	[AGGR_SOCKET] 	= 6,
 	[AGGR_NODE] 	= 6,
@@ -49,6 +50,7 @@ static int aggr_header_lens[] = {
 static const char *aggr_header_csv[] = {
 	[AGGR_CORE] 	= 	"core,cpus,",
 	[AGGR_CACHE]	= 	"cache,cpus,",
+	[AGGR_CLUSTER]	= 	"cluster,cpus,",
 	[AGGR_DIE] 	= 	"die,cpus,",
 	[AGGR_SOCKET] 	= 	"socket,cpus,",
 	[AGGR_NONE] 	= 	"cpu,",
@@ -60,6 +62,7 @@ static const char *aggr_header_csv[] = {
 static const char *aggr_header_std[] = {
 	[AGGR_CORE] 	= 	"core",
 	[AGGR_CACHE] 	= 	"cache",
+	[AGGR_CLUSTER]	= 	"cluster",
 	[AGGR_DIE] 	= 	"die",
 	[AGGR_SOCKET] 	= 	"socket",
 	[AGGR_NONE] 	= 	"cpu",
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 3466aa9524..6bb975e46d 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -176,6 +176,13 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type
 		if (type != evsel__stat_type(cur))
 			continue;
 
+		/*
+		 * Except the SW CLOCK events,
+		 * ignore if not the PMU we're looking for.
+		 */
+		if ((type != STAT_NSECS) && (evsel->pmu != cur->pmu))
+			continue;
+
 		aggr = &cur->stats->aggr[aggr_idx];
 		if (type == STAT_NSECS)
 			return aggr->counts.val;
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index b0bcf92f0f..0bd5467389 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -315,7 +315,7 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals,
 	if (!counter->per_pkg)
 		return 0;
 
-	if (perf_cpu_map__has_any_cpu_or_is_empty(cpus))
+	if (perf_cpu_map__is_any_cpu_or_is_empty(cpus))
 		return 0;
 
 	if (!mask) {
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index d6e5c8787b..fd7a187551 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -87,6 +87,7 @@ struct perf_stat_config {
 	bool			 metric_no_group;
 	bool			 metric_no_merge;
 	bool			 metric_no_threshold;
+	bool			 hardware_aware_grouping;
 	bool			 stop_read_counter;
 	bool			 iostat_run;
 	char			 *user_requested_cpu_list;
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 1892e9b6aa..2b04f47f4d 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -725,26 +725,24 @@ static void scan_core_topology(int *map, struct topology *t, int nr_cpus)
 
 static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus)
 {
-	int i;
-	int ret = 0;
-	struct perf_cpu_map *m;
-	struct perf_cpu c;
+	int idx, ret = 0;
+	struct perf_cpu_map *map;
+	struct perf_cpu cpu;
 
-	m = perf_cpu_map__new(s);
-	if (!m)
+	map = perf_cpu_map__new(s);
+	if (!map)
 		return -1;
 
-	for (i = 0; i < perf_cpu_map__nr(m); i++) {
-		c = perf_cpu_map__cpu(m, i);
-		if (c.cpu >= nr_cpus) {
+	perf_cpu_map__for_each_cpu(cpu, idx, map) {
+		if (cpu.cpu >= nr_cpus) {
 			ret = -1;
 			break;
 		}
 
-		__set_bit(c.cpu, cpumask_bits(b));
+		__set_bit(cpu.cpu, cpumask_bits(b));
 	}
 
-	perf_cpu_map__put(m);
+	perf_cpu_map__put(map);
 
 	return ret;
 }
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 0b91f813c4..e398abfd13 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -174,7 +174,7 @@ static inline bool elf_sec__is_data(const GElf_Shdr *shdr,
 
 static bool elf_sec__filter(GElf_Shdr *shdr, Elf_Data *secstrs)
 {
-	return elf_sec__is_text(shdr, secstrs) || 
+	return elf_sec__is_text(shdr, secstrs) ||
 	       elf_sec__is_data(shdr, secstrs);
 }
 
@@ -312,8 +312,8 @@ static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
 	 * DWARF DW_compile_unit has this, but we don't always have access
 	 * to it...
 	 */
-	if (!want_demangle(dso->kernel || kmodule))
-	    return demangled;
+	if (!want_demangle(dso__kernel(dso) || kmodule))
+		return demangled;
 
 	demangled = cxx_demangle_sym(elf_name, verbose > 0, verbose > 0);
 	if (demangled == NULL) {
@@ -470,7 +470,7 @@ static bool get_plt_sizes(struct dso *dso, GElf_Ehdr *ehdr, GElf_Shdr *shdr_plt,
 	}
 	if (*plt_entry_size)
 		return true;
-	pr_debug("Missing PLT entry size for %s\n", dso->long_name);
+	pr_debug("Missing PLT entry size for %s\n", dso__long_name(dso));
 	return false;
 }
 
@@ -654,7 +654,7 @@ static int dso__synthesize_plt_got_symbols(struct dso *dso, Elf *elf,
 		sym = symbol__new(shdr.sh_offset + i, shdr.sh_entsize, STB_GLOBAL, STT_FUNC, buf);
 		if (!sym)
 			goto out;
-		symbols__insert(&dso->symbols, sym);
+		symbols__insert(dso__symbols(dso), sym);
 	}
 	err = 0;
 out:
@@ -708,7 +708,7 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss)
 	plt_sym = symbol__new(shdr_plt.sh_offset, plt_header_size, STB_GLOBAL, STT_FUNC, ".plt");
 	if (!plt_sym)
 		goto out_elf_end;
-	symbols__insert(&dso->symbols, plt_sym);
+	symbols__insert(dso__symbols(dso), plt_sym);
 
 	/* Only x86 has .plt.got */
 	if (machine_is_x86(ehdr.e_machine) &&
@@ -830,7 +830,7 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss)
 			goto out_elf_end;
 
 		plt_offset += plt_entry_size;
-		symbols__insert(&dso->symbols, f);
+		symbols__insert(dso__symbols(dso), f);
 		++nr;
 	}
 
@@ -840,7 +840,7 @@ out_elf_end:
 	if (err == 0)
 		return nr;
 	pr_debug("%s: problems reading %s PLT info.\n",
-		 __func__, dso->long_name);
+		 __func__, dso__long_name(dso));
 	return 0;
 }
 
@@ -1175,19 +1175,19 @@ static int dso__swap_init(struct dso *dso, unsigned char eidata)
 {
 	static unsigned int const endian = 1;
 
-	dso->needs_swap = DSO_SWAP__NO;
+	dso__set_needs_swap(dso, 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;
+			dso__set_needs_swap(dso, 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;
+			dso__set_needs_swap(dso, DSO_SWAP__YES);
 		break;
 
 	default:
@@ -1238,11 +1238,11 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 		if (fd < 0)
 			return -1;
 
-		type = dso->symtab_type;
+		type = dso__symtab_type(dso);
 	} else {
 		fd = open(name, O_RDONLY);
 		if (fd < 0) {
-			dso->load_errno = errno;
+			*dso__load_errno(dso) = errno;
 			return -1;
 		}
 	}
@@ -1250,37 +1250,37 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
 	if (elf == NULL) {
 		pr_debug("%s: cannot read %s ELF file.\n", __func__, name);
-		dso->load_errno = DSO_LOAD_ERRNO__INVALID_ELF;
+		*dso__load_errno(dso) = DSO_LOAD_ERRNO__INVALID_ELF;
 		goto out_close;
 	}
 
 	if (gelf_getehdr(elf, &ehdr) == NULL) {
-		dso->load_errno = DSO_LOAD_ERRNO__INVALID_ELF;
+		*dso__load_errno(dso) = DSO_LOAD_ERRNO__INVALID_ELF;
 		pr_debug("%s: cannot get elf header.\n", __func__);
 		goto out_elf_end;
 	}
 
 	if (dso__swap_init(dso, ehdr.e_ident[EI_DATA])) {
-		dso->load_errno = DSO_LOAD_ERRNO__INTERNAL_ERROR;
+		*dso__load_errno(dso) = DSO_LOAD_ERRNO__INTERNAL_ERROR;
 		goto out_elf_end;
 	}
 
 	/* Always reject images with a mismatched build-id: */
-	if (dso->has_build_id && !symbol_conf.ignore_vmlinux_buildid) {
+	if (dso__has_build_id(dso) && !symbol_conf.ignore_vmlinux_buildid) {
 		u8 build_id[BUILD_ID_SIZE];
 		struct build_id bid;
 		int size;
 
 		size = elf_read_build_id(elf, build_id, BUILD_ID_SIZE);
 		if (size <= 0) {
-			dso->load_errno = DSO_LOAD_ERRNO__CANNOT_READ_BUILDID;
+			*dso__load_errno(dso) = DSO_LOAD_ERRNO__CANNOT_READ_BUILDID;
 			goto out_elf_end;
 		}
 
 		build_id__init(&bid, build_id, size);
 		if (!dso__build_id_equal(dso, &bid)) {
 			pr_debug("%s: build id mismatch for %s.\n", __func__, name);
-			dso->load_errno = DSO_LOAD_ERRNO__MISMATCHING_BUILDID;
+			*dso__load_errno(dso) = DSO_LOAD_ERRNO__MISMATCHING_BUILDID;
 			goto out_elf_end;
 		}
 	}
@@ -1305,14 +1305,14 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 	if (ss->opdshdr.sh_type != SHT_PROGBITS)
 		ss->opdsec = NULL;
 
-	if (dso->kernel == DSO_SPACE__USER)
+	if (dso__kernel(dso) == DSO_SPACE__USER)
 		ss->adjust_symbols = true;
 	else
 		ss->adjust_symbols = elf__needs_adjust_symbols(ehdr);
 
 	ss->name   = strdup(name);
 	if (!ss->name) {
-		dso->load_errno = errno;
+		*dso__load_errno(dso) = errno;
 		goto out_elf_end;
 	}
 
@@ -1419,7 +1419,7 @@ void __weak arch__sym_update(struct symbol *s __maybe_unused,
 static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 				      GElf_Sym *sym, GElf_Shdr *shdr,
 				      struct maps *kmaps, struct kmap *kmap,
-				      struct dso **curr_dsop, struct map **curr_mapp,
+				      struct dso **curr_dsop,
 				      const char *section_name,
 				      bool adjust_kernel_syms, bool kmodule, bool *remap_kernel,
 				      u64 max_text_sh_offset)
@@ -1432,7 +1432,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 	if (adjust_kernel_syms)
 		sym->st_value -= shdr->sh_addr - shdr->sh_offset;
 
-	if (strcmp(section_name, (curr_dso->short_name + dso->short_name_len)) == 0)
+	if (strcmp(section_name, (dso__short_name(curr_dso) + dso__short_name_len(dso))) == 0)
 		return 0;
 
 	if (strcmp(section_name, ".text") == 0) {
@@ -1441,7 +1441,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 		 * kallsyms and identity maps.  Overwrite it to
 		 * map to the kernel dso.
 		 */
-		if (*remap_kernel && dso->kernel && !kmodule) {
+		if (*remap_kernel && dso__kernel(dso) && !kmodule) {
 			*remap_kernel = false;
 			map__set_start(map, shdr->sh_addr + ref_reloc(kmap));
 			map__set_end(map, map__start(map) + shdr->sh_size);
@@ -1470,8 +1470,8 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 			map__set_pgoff(map, shdr->sh_offset);
 		}
 
-		*curr_mapp = map;
-		*curr_dsop = dso;
+		dso__put(*curr_dsop);
+		*curr_dsop = dso__get(dso);
 		return 0;
 	}
 
@@ -1484,12 +1484,12 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 	 */
 	if (kmodule && adjust_kernel_syms && is_exe_text(shdr->sh_flags) &&
 	    shdr->sh_offset <= max_text_sh_offset) {
-		*curr_mapp = map;
-		*curr_dsop = dso;
+		dso__put(*curr_dsop);
+		*curr_dsop = dso__get(dso);
 		return 0;
 	}
 
-	snprintf(dso_name, sizeof(dso_name), "%s%s", dso->short_name, section_name);
+	snprintf(dso_name, sizeof(dso_name), "%s%s", dso__short_name(dso), section_name);
 
 	curr_map = maps__find_by_name(kmaps, dso_name);
 	if (curr_map == NULL) {
@@ -1501,17 +1501,17 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 		curr_dso = dso__new(dso_name);
 		if (curr_dso == NULL)
 			return -1;
-		curr_dso->kernel = dso->kernel;
-		curr_dso->long_name = dso->long_name;
-		curr_dso->long_name_len = dso->long_name_len;
-		curr_dso->binary_type = dso->binary_type;
-		curr_dso->adjust_symbols = dso->adjust_symbols;
+		dso__set_kernel(curr_dso, dso__kernel(dso));
+		RC_CHK_ACCESS(curr_dso)->long_name = dso__long_name(dso);
+		RC_CHK_ACCESS(curr_dso)->long_name_len = dso__long_name_len(dso);
+		dso__set_binary_type(curr_dso, dso__binary_type(dso));
+		dso__set_adjust_symbols(curr_dso, dso__adjust_symbols(dso));
 		curr_map = map__new2(start, curr_dso);
-		dso__put(curr_dso);
-		if (curr_map == NULL)
+		if (curr_map == NULL) {
+			dso__put(curr_dso);
 			return -1;
-
-		if (curr_dso->kernel)
+		}
+		if (dso__kernel(curr_dso))
 			map__kmap(curr_map)->kmaps = kmaps;
 
 		if (adjust_kernel_syms) {
@@ -1521,24 +1521,18 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 		} else {
 			map__set_mapping_type(curr_map, MAPPING_TYPE__IDENTITY);
 		}
-		curr_dso->symtab_type = dso->symtab_type;
+		dso__set_symtab_type(curr_dso, dso__symtab_type(dso));
 		if (maps__insert(kmaps, curr_map))
 			return -1;
-		/*
-		 * Add it before we drop the reference to curr_map, i.e. while
-		 * we still are sure to have a reference to this DSO via
-		 * *curr_map->dso.
-		 */
 		dsos__add(&maps__machine(kmaps)->dsos, curr_dso);
-		/* kmaps already got it */
-		map__put(curr_map);
 		dso__set_loaded(curr_dso);
-		*curr_mapp = curr_map;
+		dso__put(*curr_dsop);
 		*curr_dsop = curr_dso;
 	} else {
-		*curr_dsop = map__dso(curr_map);
-		map__put(curr_map);
+		dso__put(*curr_dsop);
+		*curr_dsop = dso__get(map__dso(curr_map));
 	}
+	map__put(curr_map);
 
 	return 0;
 }
@@ -1547,13 +1541,11 @@ static int
 dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		       struct symsrc *runtime_ss, int kmodule, int dynsym)
 {
-	struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL;
+	struct kmap *kmap = dso__kernel(dso) ? map__kmap(map) : NULL;
 	struct maps *kmaps = kmap ? map__kmaps(map) : NULL;
-	struct map *curr_map = map;
-	struct dso *curr_dso = dso;
+	struct dso *curr_dso = NULL;
 	Elf_Data *symstrs, *secstrs, *secstrs_run, *secstrs_sym;
 	uint32_t nr_syms;
-	int err = -1;
 	uint32_t idx;
 	GElf_Ehdr ehdr;
 	GElf_Shdr shdr;
@@ -1581,8 +1573,8 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 
 	if (elf_section_by_name(runtime_ss->elf, &runtime_ss->ehdr, &tshdr,
 				".text", NULL)) {
-		dso->text_offset = tshdr.sh_addr - tshdr.sh_offset;
-		dso->text_end = tshdr.sh_offset + tshdr.sh_size;
+		dso__set_text_offset(dso, tshdr.sh_addr - tshdr.sh_offset);
+		dso__set_text_end(dso, tshdr.sh_offset + tshdr.sh_size);
 	}
 
 	if (runtime_ss->opdsec)
@@ -1641,21 +1633,22 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 	 * attempted to prelink vdso to its virtual address.
 	 */
 	if (dso__is_vdso(dso))
-		map__set_reloc(map, map__start(map) - dso->text_offset);
+		map__set_reloc(map, map__start(map) - dso__text_offset(dso));
 
-	dso->adjust_symbols = runtime_ss->adjust_symbols || ref_reloc(kmap);
+	dso__set_adjust_symbols(dso, runtime_ss->adjust_symbols || ref_reloc(kmap));
 	/*
 	 * Initial kernel and module mappings do not map to the dso.
 	 * Flag the fixups.
 	 */
-	if (dso->kernel) {
+	if (dso__kernel(dso)) {
 		remap_kernel = true;
-		adjust_kernel_syms = dso->adjust_symbols;
+		adjust_kernel_syms = dso__adjust_symbols(dso);
 	}
 
 	if (kmodule && adjust_kernel_syms)
 		max_text_sh_offset = max_text_section(runtime_ss->elf, &runtime_ss->ehdr);
 
+	curr_dso = dso__get(dso);
 	elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
 		struct symbol *f;
 		const char *elf_name = elf_sym__name(&sym, symstrs);
@@ -1743,10 +1736,14 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		    (sym.st_value & 1))
 			--sym.st_value;
 
-		if (dso->kernel) {
-			if (dso__process_kernel_symbol(dso, map, &sym, &shdr, kmaps, kmap, &curr_dso, &curr_map,
-						       section_name, adjust_kernel_syms, kmodule,
-						       &remap_kernel, max_text_sh_offset))
+		if (dso__kernel(dso)) {
+			if (dso__process_kernel_symbol(dso, map, &sym, &shdr,
+						       kmaps, kmap, &curr_dso,
+						       section_name,
+						       adjust_kernel_syms,
+						       kmodule,
+						       &remap_kernel,
+						       max_text_sh_offset))
 				goto out_elf_end;
 		} else if ((used_opd && runtime_ss->adjust_symbols) ||
 			   (!used_opd && syms_ss->adjust_symbols)) {
@@ -1792,16 +1789,17 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 
 		arch__sym_update(f, &sym);
 
-		__symbols__insert(&curr_dso->symbols, f, dso->kernel);
+		__symbols__insert(dso__symbols(curr_dso), f, dso__kernel(dso));
 		nr++;
 	}
+	dso__put(curr_dso);
 
 	/*
 	 * For misannotated, zeroed, ASM function sizes.
 	 */
 	if (nr > 0) {
-		symbols__fixup_end(&dso->symbols, false);
-		symbols__fixup_duplicate(&dso->symbols);
+		symbols__fixup_end(dso__symbols(dso), false);
+		symbols__fixup_duplicate(dso__symbols(dso));
 		if (kmap) {
 			/*
 			 * We need to fixup this here too because we create new
@@ -1810,9 +1808,10 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 			maps__fixup_end(kmaps);
 		}
 	}
-	err = nr;
+	return nr;
 out_elf_end:
-	return err;
+	dso__put(curr_dso);
+	return -1;
 }
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
@@ -1821,16 +1820,16 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 	int nr = 0;
 	int err = -1;
 
-	dso->symtab_type = syms_ss->type;
-	dso->is_64_bit = syms_ss->is_64_bit;
-	dso->rel = syms_ss->ehdr.e_type == ET_REL;
+	dso__set_symtab_type(dso, syms_ss->type);
+	dso__set_is_64_bit(dso, syms_ss->is_64_bit);
+	dso__set_rel(dso, 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);
+		symbols__delete(dso__symbols(dso));
 
 	if (!syms_ss->symtab) {
 		/*
@@ -1838,7 +1837,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		 * to using kallsyms. The vmlinux runtime symbols aren't
 		 * of much use.
 		 */
-		if (dso->kernel)
+		if (dso__kernel(dso))
 			return err;
 	} else  {
 		err = dso__load_sym_internal(dso, map, syms_ss, runtime_ss,
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 1da8b71350..c6f369b5d8 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -273,7 +273,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 out_close:
 	close(fd);
 out_errno:
-	dso->load_errno = errno;
+	RC_CHK_ACCESS(dso)->load_errno = errno;
 	return -1;
 }
 
@@ -348,7 +348,7 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
 
 	ret = fd__is_64_bit(ss->fd);
 	if (ret >= 0)
-		dso->is_64_bit = ret;
+		RC_CHK_ACCESS(dso)->is_64_bit = ret;
 
 	if (filename__read_build_id(ss->name, &bid) > 0)
 		dso__set_build_id(dso, &bid);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 68dbeae8d2..22646f0cca 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -27,6 +27,7 @@
 #include "symbol.h"
 #include "map_symbol.h"
 #include "mem-events.h"
+#include "mem-info.h"
 #include "symsrc.h"
 #include "strlist.h"
 #include "intlist.h"
@@ -532,52 +533,52 @@ static struct symbol *symbols__find_by_name(struct symbol *symbols[],
 
 void dso__reset_find_symbol_cache(struct dso *dso)
 {
-	dso->last_find_result.addr   = 0;
-	dso->last_find_result.symbol = NULL;
+	dso__set_last_find_result_addr(dso, 0);
+	dso__set_last_find_result_symbol(dso, NULL);
 }
 
 void dso__insert_symbol(struct dso *dso, struct symbol *sym)
 {
-	__symbols__insert(&dso->symbols, sym, dso->kernel);
+	__symbols__insert(dso__symbols(dso), sym, dso__kernel(dso));
 
 	/* update the symbol cache if necessary */
-	if (dso->last_find_result.addr >= sym->start &&
-	    (dso->last_find_result.addr < sym->end ||
+	if (dso__last_find_result_addr(dso) >= sym->start &&
+	    (dso__last_find_result_addr(dso) < sym->end ||
 	    sym->start == sym->end)) {
-		dso->last_find_result.symbol = sym;
+		dso__set_last_find_result_symbol(dso, sym);
 	}
 }
 
 void dso__delete_symbol(struct dso *dso, struct symbol *sym)
 {
-	rb_erase_cached(&sym->rb_node, &dso->symbols);
+	rb_erase_cached(&sym->rb_node, dso__symbols(dso));
 	symbol__delete(sym);
 	dso__reset_find_symbol_cache(dso);
 }
 
 struct symbol *dso__find_symbol(struct dso *dso, u64 addr)
 {
-	if (dso->last_find_result.addr != addr || dso->last_find_result.symbol == NULL) {
-		dso->last_find_result.addr   = addr;
-		dso->last_find_result.symbol = symbols__find(&dso->symbols, addr);
+	if (dso__last_find_result_addr(dso) != addr || dso__last_find_result_symbol(dso) == NULL) {
+		dso__set_last_find_result_addr(dso, addr);
+		dso__set_last_find_result_symbol(dso, symbols__find(dso__symbols(dso), addr));
 	}
 
-	return dso->last_find_result.symbol;
+	return dso__last_find_result_symbol(dso);
 }
 
 struct symbol *dso__find_symbol_nocache(struct dso *dso, u64 addr)
 {
-	return symbols__find(&dso->symbols, addr);
+	return symbols__find(dso__symbols(dso), addr);
 }
 
 struct symbol *dso__first_symbol(struct dso *dso)
 {
-	return symbols__first(&dso->symbols);
+	return symbols__first(dso__symbols(dso));
 }
 
 struct symbol *dso__last_symbol(struct dso *dso)
 {
-	return symbols__last(&dso->symbols);
+	return symbols__last(dso__symbols(dso));
 }
 
 struct symbol *dso__next_symbol(struct symbol *sym)
@@ -587,11 +588,11 @@ struct symbol *dso__next_symbol(struct symbol *sym)
 
 struct symbol *dso__next_symbol_by_name(struct dso *dso, size_t *idx)
 {
-	if (*idx + 1 >= dso->symbol_names_len)
+	if (*idx + 1 >= dso__symbol_names_len(dso))
 		return NULL;
 
 	++*idx;
-	return dso->symbol_names[*idx];
+	return dso__symbol_names(dso)[*idx];
 }
 
  /*
@@ -599,27 +600,29 @@ struct symbol *dso__next_symbol_by_name(struct dso *dso, size_t *idx)
   */
 struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name, size_t *idx)
 {
-	struct symbol *s = symbols__find_by_name(dso->symbol_names, dso->symbol_names_len,
-						name, SYMBOL_TAG_INCLUDE__NONE, idx);
-	if (!s)
-		s = symbols__find_by_name(dso->symbol_names, dso->symbol_names_len,
-					name, SYMBOL_TAG_INCLUDE__DEFAULT_ONLY, idx);
+	struct symbol *s = symbols__find_by_name(dso__symbol_names(dso),
+						 dso__symbol_names_len(dso),
+						 name, SYMBOL_TAG_INCLUDE__NONE, idx);
+	if (!s) {
+		s = symbols__find_by_name(dso__symbol_names(dso), dso__symbol_names_len(dso),
+					  name, SYMBOL_TAG_INCLUDE__DEFAULT_ONLY, idx);
+	}
 	return s;
 }
 
 void dso__sort_by_name(struct dso *dso)
 {
-	mutex_lock(&dso->lock);
+	mutex_lock(dso__lock(dso));
 	if (!dso__sorted_by_name(dso)) {
 		size_t len;
 
-		dso->symbol_names = symbols__sort_by_name(&dso->symbols, &len);
-		if (dso->symbol_names) {
-			dso->symbol_names_len = len;
+		dso__set_symbol_names(dso, symbols__sort_by_name(dso__symbols(dso), &len));
+		if (dso__symbol_names(dso)) {
+			dso__set_symbol_names_len(dso, len);
 			dso__set_sorted_by_name(dso);
 		}
 	}
-	mutex_unlock(&dso->lock);
+	mutex_unlock(dso__lock(dso));
 }
 
 /*
@@ -746,7 +749,7 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
 {
 	struct symbol *sym;
 	struct dso *dso = arg;
-	struct rb_root_cached *root = &dso->symbols;
+	struct rb_root_cached *root = dso__symbols(dso);
 
 	if (!symbol_type__filter(type))
 		return 0;
@@ -786,8 +789,8 @@ static int maps__split_kallsyms_for_kcore(struct maps *kmaps, struct dso *dso)
 {
 	struct symbol *pos;
 	int count = 0;
-	struct rb_root_cached old_root = dso->symbols;
-	struct rb_root_cached *root = &dso->symbols;
+	struct rb_root_cached *root = dso__symbols(dso);
+	struct rb_root_cached old_root = *root;
 	struct rb_node *next = rb_first_cached(root);
 
 	if (!kmaps)
@@ -821,13 +824,13 @@ static int maps__split_kallsyms_for_kcore(struct maps *kmaps, struct dso *dso)
 			pos->end = map__end(curr_map);
 		if (pos->end)
 			pos->end -= map__start(curr_map) - map__pgoff(curr_map);
-		symbols__insert(&curr_map_dso->symbols, pos);
+		symbols__insert(dso__symbols(curr_map_dso), pos);
 		++count;
 		map__put(curr_map);
 	}
 
 	/* Symbols have been adjusted */
-	dso->adjust_symbols = 1;
+	dso__set_adjust_symbols(dso, true);
 
 	return count;
 }
@@ -844,7 +847,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
 	struct map *curr_map = map__get(initial_map);
 	struct symbol *pos;
 	int count = 0, moved = 0;
-	struct rb_root_cached *root = &dso->symbols;
+	struct rb_root_cached *root = dso__symbols(dso);
 	struct rb_node *next = rb_first_cached(root);
 	int kernel_range = 0;
 	bool x86_64;
@@ -871,9 +874,9 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
 
 			*module++ = '\0';
 			curr_map_dso = map__dso(curr_map);
-			if (strcmp(curr_map_dso->short_name, module)) {
+			if (strcmp(dso__short_name(curr_map_dso), module)) {
 				if (!RC_CHK_EQUAL(curr_map, initial_map) &&
-				    dso->kernel == DSO_SPACE__KERNEL_GUEST &&
+				    dso__kernel(dso) == DSO_SPACE__KERNEL_GUEST &&
 				    machine__is_default_guest(machine)) {
 					/*
 					 * We assume all symbols of a module are
@@ -896,7 +899,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
 					goto discard_symbol;
 				}
 				curr_map_dso = map__dso(curr_map);
-				if (curr_map_dso->loaded &&
+				if (dso__loaded(curr_map_dso) &&
 				    !machine__is_default_guest(machine))
 					goto discard_symbol;
 			}
@@ -932,7 +935,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
 				goto add_symbol;
 			}
 
-			if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
+			if (dso__kernel(dso) == DSO_SPACE__KERNEL_GUEST)
 				snprintf(dso_name, sizeof(dso_name),
 					"[guest.kernel].%d",
 					kernel_range++);
@@ -946,7 +949,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
 			if (ndso == NULL)
 				return -1;
 
-			ndso->kernel = dso->kernel;
+			dso__set_kernel(ndso, dso__kernel(dso));
 
 			curr_map = map__new2(pos->start, ndso);
 			if (curr_map == NULL) {
@@ -971,7 +974,7 @@ add_symbol:
 			struct dso *curr_map_dso = map__dso(curr_map);
 
 			rb_erase_cached(&pos->rb_node, root);
-			symbols__insert(&curr_map_dso->symbols, pos);
+			symbols__insert(dso__symbols(curr_map_dso), pos);
 			++moved;
 		} else
 			++count;
@@ -983,7 +986,7 @@ discard_symbol:
 	}
 
 	if (!RC_CHK_EQUAL(curr_map, initial_map) &&
-	    dso->kernel == DSO_SPACE__KERNEL_GUEST &&
+	    dso__kernel(dso) == DSO_SPACE__KERNEL_GUEST &&
 	    machine__is_default_guest(maps__machine(kmaps))) {
 		dso__set_loaded(map__dso(curr_map));
 	}
@@ -1157,7 +1160,7 @@ static int do_validate_kcore_modules_cb(struct map *old_map, void *data)
 
 	dso = map__dso(old_map);
 	/* Module must be in memory at the same address */
-	mi = find_module(dso->short_name, modules);
+	mi = find_module(dso__short_name(dso), modules);
 	if (!mi || mi->start != map__start(old_map))
 		return -EINVAL;
 
@@ -1326,7 +1329,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 			      &is_64_bit);
 	if (err)
 		goto out_err;
-	dso->is_64_bit = is_64_bit;
+	dso__set_is_64_bit(dso, is_64_bit);
 
 	if (list_empty(&md.maps)) {
 		err = -EINVAL;
@@ -1422,10 +1425,10 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	 * Set the data type and long name so that kcore can be read via
 	 * dso__data_read_addr().
 	 */
-	if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
-		dso->binary_type = DSO_BINARY_TYPE__GUEST_KCORE;
+	if (dso__kernel(dso) == DSO_SPACE__KERNEL_GUEST)
+		dso__set_binary_type(dso, DSO_BINARY_TYPE__GUEST_KCORE);
 	else
-		dso->binary_type = DSO_BINARY_TYPE__KCORE;
+		dso__set_binary_type(dso, DSO_BINARY_TYPE__KCORE);
 	dso__set_long_name(dso, strdup(kcore_filename), true);
 
 	close(fd);
@@ -1486,13 +1489,13 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename,
 	if (kallsyms__delta(kmap, filename, &delta))
 		return -1;
 
-	symbols__fixup_end(&dso->symbols, true);
-	symbols__fixup_duplicate(&dso->symbols);
+	symbols__fixup_end(dso__symbols(dso), true);
+	symbols__fixup_duplicate(dso__symbols(dso));
 
-	if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
-		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
+	if (dso__kernel(dso) == DSO_SPACE__KERNEL_GUEST)
+		dso__set_symtab_type(dso, DSO_BINARY_TYPE__GUEST_KALLSYMS);
 	else
-		dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;
+		dso__set_symtab_type(dso, DSO_BINARY_TYPE__KALLSYMS);
 
 	if (!no_kcore && !dso__load_kcore(dso, map, filename))
 		return maps__split_kallsyms_for_kcore(kmap->kmaps, dso);
@@ -1548,7 +1551,7 @@ static int dso__load_perf_map(const char *map_path, struct dso *dso)
 		if (sym == NULL)
 			goto out_delete_line;
 
-		symbols__insert(&dso->symbols, sym);
+		symbols__insert(dso__symbols(dso), sym);
 		nr_syms++;
 	}
 
@@ -1604,7 +1607,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile)
 
 	if (!bfd_check_format(abfd, bfd_object)) {
 		pr_debug2("%s: cannot read %s bfd file.\n", __func__,
-			  dso->long_name);
+			  dso__long_name(dso));
 		goto out_close;
 	}
 
@@ -1637,12 +1640,13 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile)
 		}
 		if (i < symbols_count) {
 			/* PE symbols can only have 4 bytes, so use .text high bits */
-			dso->text_offset = section->vma - (u32)section->vma;
-			dso->text_offset += (u32)bfd_asymbol_value(symbols[i]);
-			dso->text_end = (section->vma - dso->text_offset) + section->size;
+			u64 text_offset = (section->vma - (u32)section->vma)
+				+ (u32)bfd_asymbol_value(symbols[i]);
+			dso__set_text_offset(dso, text_offset);
+			dso__set_text_end(dso, (section->vma - text_offset) + section->size);
 		} else {
-			dso->text_offset = section->vma - section->filepos;
-			dso->text_end = section->filepos + section->size;
+			dso__set_text_offset(dso, section->vma - section->filepos);
+			dso__set_text_end(dso, section->filepos + section->size);
 		}
 	}
 
@@ -1668,21 +1672,21 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile)
 		else
 			len = section->size - sym->value;
 
-		start = bfd_asymbol_value(sym) - dso->text_offset;
+		start = bfd_asymbol_value(sym) - dso__text_offset(dso);
 		symbol = symbol__new(start, len, bfd2elf_binding(sym), STT_FUNC,
 				     bfd_asymbol_name(sym));
 		if (!symbol)
 			goto out_free;
 
-		symbols__insert(&dso->symbols, symbol);
+		symbols__insert(dso__symbols(dso), symbol);
 	}
 #ifdef bfd_get_section
 #undef bfd_asymbol_section
 #endif
 
-	symbols__fixup_end(&dso->symbols, false);
-	symbols__fixup_duplicate(&dso->symbols);
-	dso->adjust_symbols = 1;
+	symbols__fixup_end(dso__symbols(dso), false);
+	symbols__fixup_duplicate(dso__symbols(dso));
+	dso__set_adjust_symbols(dso, true);
 
 	err = 0;
 out_free:
@@ -1705,17 +1709,17 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
 	case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO:
 	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
 	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
-		return !kmod && dso->kernel == DSO_SPACE__USER;
+		return !kmod && dso__kernel(dso) == DSO_SPACE__USER;
 
 	case DSO_BINARY_TYPE__KALLSYMS:
 	case DSO_BINARY_TYPE__VMLINUX:
 	case DSO_BINARY_TYPE__KCORE:
-		return dso->kernel == DSO_SPACE__KERNEL;
+		return dso__kernel(dso) == DSO_SPACE__KERNEL;
 
 	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
 	case DSO_BINARY_TYPE__GUEST_VMLINUX:
 	case DSO_BINARY_TYPE__GUEST_KCORE:
-		return dso->kernel == DSO_SPACE__KERNEL_GUEST;
+		return dso__kernel(dso) == DSO_SPACE__KERNEL_GUEST;
 
 	case DSO_BINARY_TYPE__GUEST_KMODULE:
 	case DSO_BINARY_TYPE__GUEST_KMODULE_COMP:
@@ -1725,7 +1729,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
 		 * kernel modules know their symtab type - it's set when
 		 * creating a module dso in machine__addnew_module_map().
 		 */
-		return kmod && dso->symtab_type == type;
+		return kmod && dso__symtab_type(dso) == type;
 
 	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
 	case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO:
@@ -1793,18 +1797,20 @@ int dso__load(struct dso *dso, struct map *map)
 	struct build_id bid;
 	struct nscookie nsc;
 	char newmapname[PATH_MAX];
-	const char *map_path = dso->long_name;
+	const char *map_path = dso__long_name(dso);
+
+	mutex_lock(dso__lock(dso));
+	perfmap = is_perf_pid_map_name(map_path);
 
-	mutex_lock(&dso->lock);
-	perfmap = strncmp(dso->name, "/tmp/perf-", 10) == 0;
 	if (perfmap) {
-		if (dso->nsinfo && (dso__find_perf_map(newmapname,
-		    sizeof(newmapname), &dso->nsinfo) == 0)) {
+		if (dso__nsinfo(dso) &&
+		    (dso__find_perf_map(newmapname, sizeof(newmapname),
+					dso__nsinfo_ptr(dso)) == 0)) {
 			map_path = newmapname;
 		}
 	}
 
-	nsinfo__mountns_enter(dso->nsinfo, &nsc);
+	nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
 
 	/* check again under the dso->lock */
 	if (dso__loaded(dso)) {
@@ -1812,15 +1818,15 @@ int dso__load(struct dso *dso, struct map *map)
 		goto out;
 	}
 
-	kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
-		dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
-		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE ||
-		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
+	kmod = dso__symtab_type(dso) == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
+		dso__symtab_type(dso) == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
+		dso__symtab_type(dso) == DSO_BINARY_TYPE__GUEST_KMODULE ||
+		dso__symtab_type(dso) == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
 
-	if (dso->kernel && !kmod) {
-		if (dso->kernel == DSO_SPACE__KERNEL)
+	if (dso__kernel(dso) && !kmod) {
+		if (dso__kernel(dso) == DSO_SPACE__KERNEL)
 			ret = dso__load_kernel_sym(dso, map);
-		else if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
+		else if (dso__kernel(dso) == DSO_SPACE__KERNEL_GUEST)
 			ret = dso__load_guest_kernel_sym(dso, map);
 
 		machine = maps__machine(map__kmaps(map));
@@ -1829,12 +1835,13 @@ int dso__load(struct dso *dso, struct map *map)
 		goto out;
 	}
 
-	dso->adjust_symbols = 0;
+	dso__set_adjust_symbols(dso, false);
 
 	if (perfmap) {
 		ret = dso__load_perf_map(map_path, dso);
-		dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
-					     DSO_BINARY_TYPE__NOT_FOUND;
+		dso__set_symtab_type(dso, ret > 0
+				? DSO_BINARY_TYPE__JAVA_JIT
+				: DSO_BINARY_TYPE__NOT_FOUND);
 		goto out;
 	}
 
@@ -1849,9 +1856,9 @@ int dso__load(struct dso *dso, struct map *map)
 	 * Read the build id if possible. This is required for
 	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
 	 */
-	if (!dso->has_build_id &&
-	    is_regular_file(dso->long_name)) {
-	    __symbol__join_symfs(name, PATH_MAX, dso->long_name);
+	if (!dso__has_build_id(dso) &&
+	    is_regular_file(dso__long_name(dso))) {
+		__symbol__join_symfs(name, PATH_MAX, dso__long_name(dso));
 		if (filename__read_build_id(name, &bid) > 0)
 			dso__set_build_id(dso, &bid);
 	}
@@ -1885,7 +1892,7 @@ int dso__load(struct dso *dso, struct map *map)
 			nsinfo__mountns_exit(&nsc);
 
 		is_reg = is_regular_file(name);
-		if (!is_reg && errno == ENOENT && dso->nsinfo) {
+		if (!is_reg && errno == ENOENT && dso__nsinfo(dso)) {
 			char *new_name = dso__filename_with_chroot(dso, name);
 			if (new_name) {
 				is_reg = is_regular_file(new_name);
@@ -1902,7 +1909,7 @@ int dso__load(struct dso *dso, struct map *map)
 			sirc = symsrc__init(ss, dso, name, symtab_type);
 
 		if (nsexit)
-			nsinfo__mountns_enter(dso->nsinfo, &nsc);
+			nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
 
 		if (bfdrc == 0) {
 			ret = 0;
@@ -1915,8 +1922,8 @@ int dso__load(struct dso *dso, struct map *map)
 		if (!syms_ss && symsrc__has_symtab(ss)) {
 			syms_ss = ss;
 			next_slot = true;
-			if (!dso->symsrc_filename)
-				dso->symsrc_filename = strdup(name);
+			if (!dso__symsrc_filename(dso))
+				dso__set_symsrc_filename(dso, strdup(name));
 		}
 
 		if (!runtime_ss && symsrc__possibly_runtime(ss)) {
@@ -1963,11 +1970,11 @@ int dso__load(struct dso *dso, struct map *map)
 		symsrc__destroy(&ss_[ss_pos - 1]);
 out_free:
 	free(name);
-	if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
+	if (ret < 0 && strstr(dso__name(dso), " (deleted)") != NULL)
 		ret = 0;
 out:
 	dso__set_loaded(dso);
-	mutex_unlock(&dso->lock);
+	mutex_unlock(dso__lock(dso));
 	nsinfo__mountns_exit(&nsc);
 
 	return ret;
@@ -1990,7 +1997,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 	else
 		symbol__join_symfs(symfs_vmlinux, vmlinux);
 
-	if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
+	if (dso__kernel(dso) == DSO_SPACE__KERNEL_GUEST)
 		symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
 	else
 		symtab_type = DSO_BINARY_TYPE__VMLINUX;
@@ -2006,10 +2013,10 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 	 * an incorrect long name unless we set it here first.
 	 */
 	dso__set_long_name(dso, vmlinux, vmlinux_allocated);
-	if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
-		dso->binary_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
+	if (dso__kernel(dso) == DSO_SPACE__KERNEL_GUEST)
+		dso__set_binary_type(dso, DSO_BINARY_TYPE__GUEST_VMLINUX);
 	else
-		dso->binary_type = DSO_BINARY_TYPE__VMLINUX;
+		dso__set_binary_type(dso, DSO_BINARY_TYPE__VMLINUX);
 
 	err = dso__load_sym(dso, map, &ss, &ss, 0);
 	symsrc__destroy(&ss);
@@ -2101,7 +2108,7 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 	bool is_host = false;
 	char path[PATH_MAX];
 
-	if (!dso->has_build_id) {
+	if (!dso__has_build_id(dso)) {
 		/*
 		 * Last resort, if we don't have a build-id and couldn't find
 		 * any vmlinux file, try the running kernel kallsyms table.
@@ -2126,7 +2133,7 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 			goto proc_kallsyms;
 	}
 
-	build_id__sprintf(&dso->bid, sbuild_id);
+	build_id__sprintf(dso__bid(dso), sbuild_id);
 
 	/* Find kallsyms in build-id cache with kcore */
 	scnprintf(path, sizeof(path), "%s/%s/%s",
@@ -2218,7 +2225,7 @@ do_kallsyms:
 	free(kallsyms_allocated_filename);
 
 	if (err > 0 && !dso__is_kcore(dso)) {
-		dso->binary_type = DSO_BINARY_TYPE__KALLSYMS;
+		dso__set_binary_type(dso, DSO_BINARY_TYPE__KALLSYMS);
 		dso__set_long_name(dso, DSO__NAME_KALLSYMS, false);
 		map__fixup_start(map);
 		map__fixup_end(map);
@@ -2261,7 +2268,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map)
 	if (err > 0)
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 	if (err > 0 && !dso__is_kcore(dso)) {
-		dso->binary_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
+		dso__set_binary_type(dso, DSO_BINARY_TYPE__GUEST_KALLSYMS);
 		dso__set_long_name(dso, machine->mmap_name, false);
 		map__fixup_start(map);
 		map__fixup_end(map);
@@ -2575,31 +2582,6 @@ int symbol__config_symfs(const struct option *opt __maybe_unused,
 	return 0;
 }
 
-struct mem_info *mem_info__get(struct mem_info *mi)
-{
-	if (mi)
-		refcount_inc(&mi->refcnt);
-	return mi;
-}
-
-void mem_info__put(struct mem_info *mi)
-{
-	if (mi && refcount_dec_and_test(&mi->refcnt)) {
-		addr_map_symbol__exit(&mi->iaddr);
-		addr_map_symbol__exit(&mi->daddr);
-		free(mi);
-	}
-}
-
-struct mem_info *mem_info__new(void)
-{
-	struct mem_info *mi = zalloc(sizeof(*mi));
-
-	if (mi)
-		refcount_set(&mi->refcnt, 1);
-	return mi;
-}
-
 /*
  * Checks that user supplied symbol kernel files are accessible because
  * the default mechanism for accessing elf files fails silently. i.e. if
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 071837ddce..3fb5d146d9 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -268,18 +268,6 @@ enum {
 	SDT_NOTE_IDX_REFCTR,
 };
 
-struct mem_info *mem_info__new(void);
-struct mem_info *mem_info__get(struct mem_info *mi);
-void   mem_info__put(struct mem_info *mi);
-
-static inline void __mem_info__zput(struct mem_info **mi)
-{
-	mem_info__put(*mi);
-	*mi = NULL;
-}
-
-#define mem_info__zput(mi) __mem_info__zput(&mi)
-
 int symbol__validate_sym_arguments(void);
 
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c
index 088f4abf23..53e1af4ed9 100644
--- a/tools/perf/util/symbol_fprintf.c
+++ b/tools/perf/util/symbol_fprintf.c
@@ -64,8 +64,8 @@ size_t dso__fprintf_symbols_by_name(struct dso *dso,
 {
 	size_t ret = 0;
 
-	for (size_t i = 0; i < dso->symbol_names_len; i++) {
-		struct symbol *pos = dso->symbol_names[i];
+	for (size_t i = 0; i < dso__symbol_names_len(dso); i++) {
+		struct symbol *pos = dso__symbol_names(dso)[i];
 
 		ret += fprintf(fp, "%s\n", pos->name);
 	}
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 2a0289c149..5498048f56 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -385,8 +385,8 @@ static void perf_record_mmap2__read_build_id(struct perf_record_mmap2 *event,
 	id.ino_generation = event->ino_generation;
 
 	dso = dsos__findnew_id(&machine->dsos, event->filename, &id);
-	if (dso && dso->has_build_id) {
-		bid = dso->bid;
+	if (dso && dso__has_build_id(dso)) {
+		bid = *dso__bid(dso);
 		rc = 0;
 		goto out;
 	}
@@ -407,7 +407,7 @@ out:
 		event->__reserved_1 = 0;
 		event->__reserved_2 = 0;
 
-		if (dso && !dso->has_build_id)
+		if (dso && !dso__has_build_id(dso))
 			dso__set_build_id(dso, &bid);
 	} else {
 		if (event->filename[0] == '/') {
@@ -684,7 +684,7 @@ static int perf_event__synthesize_modules_maps_cb(struct map *map, void *data)
 
 	dso = map__dso(map);
 	if (symbol_conf.buildid_mmap2) {
-		size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64));
+		size = PERF_ALIGN(dso__long_name_len(dso) + 1, sizeof(u64));
 		event->mmap2.header.type = PERF_RECORD_MMAP2;
 		event->mmap2.header.size = (sizeof(event->mmap2) -
 					(sizeof(event->mmap2.filename) - size));
@@ -694,11 +694,11 @@ static int perf_event__synthesize_modules_maps_cb(struct map *map, void *data)
 		event->mmap2.len   = map__size(map);
 		event->mmap2.pid   = args->machine->pid;
 
-		memcpy(event->mmap2.filename, dso->long_name, dso->long_name_len + 1);
+		memcpy(event->mmap2.filename, dso__long_name(dso), dso__long_name_len(dso) + 1);
 
 		perf_record_mmap2__read_build_id(&event->mmap2, args->machine, false);
 	} else {
-		size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64));
+		size = PERF_ALIGN(dso__long_name_len(dso) + 1, sizeof(u64));
 		event->mmap.header.type = PERF_RECORD_MMAP;
 		event->mmap.header.size = (sizeof(event->mmap) -
 					(sizeof(event->mmap.filename) - size));
@@ -708,7 +708,7 @@ static int perf_event__synthesize_modules_maps_cb(struct map *map, void *data)
 		event->mmap.len   = map__size(map);
 		event->mmap.pid   = args->machine->pid;
 
-		memcpy(event->mmap.filename, dso->long_name, dso->long_name_len + 1);
+		memcpy(event->mmap.filename, dso__long_name(dso), dso__long_name_len(dso) + 1);
 	}
 
 	if (perf_tool__process_synth_event(args->tool, event, args->machine, args->process) != 0)
@@ -2231,20 +2231,20 @@ int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16
 	union perf_event ev;
 	size_t len;
 
-	if (!pos->hit)
+	if (!dso__hit(pos))
 		return 0;
 
 	memset(&ev, 0, sizeof(ev));
 
-	len = pos->long_name_len + 1;
+	len = dso__long_name_len(pos) + 1;
 	len = PERF_ALIGN(len, NAME_ALIGN);
-	ev.build_id.size = min(pos->bid.size, sizeof(pos->bid.data));
-	memcpy(&ev.build_id.build_id, pos->bid.data, ev.build_id.size);
+	ev.build_id.size = min(dso__bid(pos)->size, sizeof(dso__bid(pos)->data));
+	memcpy(&ev.build_id.build_id, dso__bid(pos)->data, ev.build_id.size);
 	ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID;
 	ev.build_id.header.misc = misc | PERF_RECORD_MISC_BUILD_ID_SIZE;
 	ev.build_id.pid = machine->pid;
 	ev.build_id.header.size = sizeof(ev.build_id) + len;
-	memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len);
+	memcpy(&ev.build_id.filename, dso__long_name(pos), dso__long_name_len(pos));
 
 	return process(tool, &ev, NULL, machine);
 }
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 515726489e..87c59aa9fe 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -453,14 +453,14 @@ int thread__memcpy(struct thread *thread, struct machine *machine,
 
 	dso = map__dso(al.map);
 
-	if (!dso || dso->data.status == DSO_DATA_STATUS_ERROR || map__load(al.map) < 0) {
+	if (!dso || dso__data(dso)->status == DSO_DATA_STATUS_ERROR || map__load(al.map) < 0) {
 		addr_location__exit(&al);
 		return -1;
 	}
 
 	offset = map__map_ip(al.map, ip);
 	if (is64bit)
-		*is64bit = dso->is_64_bit;
+		*is64bit = dso__is_64_bit(dso);
 
 	addr_location__exit(&al);
 
diff --git a/tools/perf/util/tracepoint.c b/tools/perf/util/tracepoint.c
index 92dd8b455b..95377ed5d8 100644
--- a/tools/perf/util/tracepoint.c
+++ b/tools/perf/util/tracepoint.c
@@ -4,10 +4,12 @@
 #include <errno.h>
 #include <fcntl.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <sys/param.h>
 #include <unistd.h>
 
 #include <api/fs/tracing_path.h>
+#include "fncache.h"
 
 int tp_event_has_id(const char *dir_path, struct dirent *evt_dir)
 {
@@ -26,39 +28,25 @@ int tp_event_has_id(const char *dir_path, struct dirent *evt_dir)
 /*
  * Check whether event is in <debugfs_mount_point>/tracing/events
  */
-int is_valid_tracepoint(const char *event_string)
+bool is_valid_tracepoint(const char *event_string)
 {
-	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_dirent, *evt_dirent;
-	char evt_path[MAXPATHLEN];
-	char *dir_path;
-
-	sys_dir = tracing_events__opendir();
-	if (!sys_dir)
-		return 0;
-
-	for_each_subsystem(sys_dir, sys_dirent) {
-		dir_path = get_events_file(sys_dirent->d_name);
-		if (!dir_path)
-			continue;
-		evt_dir = opendir(dir_path);
-		if (!evt_dir)
-			goto next;
-
-		for_each_event(dir_path, evt_dir, evt_dirent) {
-			snprintf(evt_path, MAXPATHLEN, "%s:%s",
-				 sys_dirent->d_name, evt_dirent->d_name);
-			if (!strcmp(evt_path, event_string)) {
-				closedir(evt_dir);
-				put_events_file(dir_path);
-				closedir(sys_dir);
-				return 1;
-			}
-		}
-		closedir(evt_dir);
-next:
-		put_events_file(dir_path);
-	}
-	closedir(sys_dir);
-	return 0;
+	char *dst, *path = malloc(strlen(event_string) + 4); /* Space for "/id\0". */
+	bool have_file = false; /* Conservatively return false if memory allocation failed. */
+	const char *src;
+
+	if (!path)
+		return false;
+
+	/* Copy event_string replacing the ':' with '/'. */
+	for (src = event_string, dst = path; *src; src++, dst++)
+		*dst = (*src == ':') ? '/' : *src;
+	/* Add "/id\0". */
+	memcpy(dst, "/id", 4);
+
+	dst = get_events_file(path);
+	if (dst)
+		have_file = file_available(dst);
+	free(dst);
+	free(path);
+	return have_file;
 }
diff --git a/tools/perf/util/tracepoint.h b/tools/perf/util/tracepoint.h
index c4a110fe87..65ccb01fc3 100644
--- a/tools/perf/util/tracepoint.h
+++ b/tools/perf/util/tracepoint.h
@@ -4,6 +4,7 @@
 
 #include <dirent.h>
 #include <string.h>
+#include <stdbool.h>
 
 int tp_event_has_id(const char *dir_path, struct dirent *evt_dir);
 
@@ -20,6 +21,6 @@ int tp_event_has_id(const char *dir_path, struct dirent *evt_dir);
 		    (strcmp(sys_dirent->d_name, ".")) &&	\
 		    (strcmp(sys_dirent->d_name, "..")))
 
-int is_valid_tracepoint(const char *event_string);
+bool is_valid_tracepoint(const char *event_string);
 
 #endif /* __PERF_TRACEPOINT_H */
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index b38d322734..bde216e630 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -29,8 +29,8 @@ static int __find_debuginfo(Dwfl_Module *mod __maybe_unused, void **userdata,
 	const struct dso *dso = *userdata;
 
 	assert(dso);
-	if (dso->symsrc_filename && strcmp (file_name, dso->symsrc_filename))
-		*debuginfo_file_name = strdup(dso->symsrc_filename);
+	if (dso__symsrc_filename(dso) && strcmp(file_name, dso__symsrc_filename(dso)))
+		*debuginfo_file_name = strdup(dso__symsrc_filename(dso));
 	return -1;
 }
 
@@ -66,7 +66,7 @@ static int __report_module(struct addr_location *al, u64 ip,
 	 * a different code in another DSO.  So just use the map->start
 	 * directly to pick the correct one.
 	 */
-	if (!strncmp(dso->long_name, "/tmp/jitted-", 12))
+	if (!strncmp(dso__long_name(dso), "/tmp/jitted-", 12))
 		base = map__start(al->map);
 	else
 		base = map__start(al->map) - map__pgoff(al->map);
@@ -83,15 +83,15 @@ static int __report_module(struct addr_location *al, u64 ip,
 	if (!mod) {
 		char filename[PATH_MAX];
 
-		__symbol__join_symfs(filename, sizeof(filename), dso->long_name);
-		mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
+		__symbol__join_symfs(filename, sizeof(filename), dso__long_name(dso));
+		mod = dwfl_report_elf(ui->dwfl, dso__short_name(dso), filename, -1,
 				      base, false);
 	}
 	if (!mod) {
 		char filename[PATH_MAX];
 
 		if (dso__build_id_filename(dso, filename, sizeof(filename), false))
-			mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
+			mod = dwfl_report_elf(ui->dwfl, dso__short_name(dso), filename, -1,
 					      base, false);
 	}
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 6a5ac0faa6..7460bb96bd 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -329,27 +329,27 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui,
 	};
 	int ret, fd;
 
-	if (dso->data.eh_frame_hdr_offset == 0) {
+	if (dso__data(dso)->eh_frame_hdr_offset == 0) {
 		fd = dso__data_get_fd(dso, ui->machine);
 		if (fd < 0)
 			return -EINVAL;
 
 		/* Check the .eh_frame section for unwinding info */
 		ret = elf_section_address_and_offset(fd, ".eh_frame_hdr",
-						     &dso->data.eh_frame_hdr_addr,
-						     &dso->data.eh_frame_hdr_offset);
-		dso->data.elf_base_addr = elf_base_address(fd);
+						     &dso__data(dso)->eh_frame_hdr_addr,
+						     &dso__data(dso)->eh_frame_hdr_offset);
+		dso__data(dso)->elf_base_addr = elf_base_address(fd);
 		dso__data_put_fd(dso);
-		if (ret || dso->data.eh_frame_hdr_offset == 0)
+		if (ret || dso__data(dso)->eh_frame_hdr_offset == 0)
 			return -EINVAL;
 	}
 
 	maps__for_each_map(thread__maps(ui->thread), read_unwind_spec_eh_frame_maps_cb, &args);
 
-	args.base_addr -= dso->data.elf_base_addr;
+	args.base_addr -= dso__data(dso)->elf_base_addr;
 	/* Address of .eh_frame_hdr */
-	*segbase = args.base_addr + dso->data.eh_frame_hdr_addr;
-	ret = unwind_spec_ehframe(dso, ui->machine, dso->data.eh_frame_hdr_offset,
+	*segbase = args.base_addr + dso__data(dso)->eh_frame_hdr_addr;
+	ret = unwind_spec_ehframe(dso, ui->machine, dso__data(dso)->eh_frame_hdr_offset,
 				   table_data, fde_count);
 	if (ret)
 		return ret;
@@ -363,7 +363,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 					struct machine *machine, u64 *offset)
 {
 	int fd;
-	u64 ofs = dso->data.debug_frame_offset;
+	u64 ofs = dso__data(dso)->debug_frame_offset;
 
 	/* debug_frame can reside in:
 	 *  - dso
@@ -379,7 +379,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 		}
 
 		if (ofs <= 0) {
-			fd = open(dso->symsrc_filename, O_RDONLY);
+			fd = open(dso__symsrc_filename(dso), O_RDONLY);
 			if (fd >= 0) {
 				ofs = elf_section_offset(fd, ".debug_frame");
 				close(fd);
@@ -402,21 +402,21 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 				}
 			}
 			if (ofs > 0) {
-				if (dso->symsrc_filename != NULL) {
+				if (dso__symsrc_filename(dso) != NULL) {
 					pr_warning(
 						"%s: overwrite symsrc(%s,%s)\n",
 							__func__,
-							dso->symsrc_filename,
+							dso__symsrc_filename(dso),
 							debuglink);
-					zfree(&dso->symsrc_filename);
+					dso__free_symsrc_filename(dso);
 				}
-				dso->symsrc_filename = debuglink;
+				dso__set_symsrc_filename(dso, debuglink);
 			} else {
 				free(debuglink);
 			}
 		}
 
-		dso->data.debug_frame_offset = ofs;
+		dso__data(dso)->debug_frame_offset = ofs;
 	}
 
 	*offset = ofs;
@@ -460,7 +460,7 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
 		return -EINVAL;
 	}
 
-	pr_debug("unwind: find_proc_info dso %s\n", dso->name);
+	pr_debug("unwind: find_proc_info dso %s\n", dso__name(dso));
 
 	/* Check the .eh_frame section for unwinding info */
 	if (!read_unwind_spec_eh_frame(dso, ui, &table_data, &segbase, &fde_count)) {
@@ -481,7 +481,7 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
 	if (ret < 0 &&
 	    !read_unwind_spec_debug_frame(dso, ui->machine, &segbase)) {
 		int fd = dso__data_get_fd(dso, ui->machine);
-		int is_exec = elf_is_exec(fd, dso->name);
+		int is_exec = elf_is_exec(fd, dso__name(dso));
 		u64 start = map__start(map);
 		unw_word_t base = is_exec ? 0 : start;
 		const char *symfile;
@@ -489,7 +489,7 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
 		if (fd >= 0)
 			dso__data_put_fd(dso);
 
-		symfile = dso->symsrc_filename ?: dso->name;
+		symfile = dso__symsrc_filename(dso) ?: dso__name(dso);
 
 		memset(&di, 0, sizeof(di));
 		if (dwarf_find_debug_frame(0, &di, ip, base, symfile, start, map__end(map)))
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 2728eb4f13..cb8be6acfb 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -25,7 +25,7 @@ int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized
 		return 0;
 
 	if (maps__addr_space(maps)) {
-		pr_debug("unwind: thread map already set, dso=%s\n", dso->name);
+		pr_debug("unwind: thread map already set, dso=%s\n", dso__name(dso));
 		if (initialized)
 			*initialized = true;
 		return 0;
diff --git a/tools/perf/util/values.h b/tools/perf/util/values.h
index 8c41f22f42..791c1ad606 100644
--- a/tools/perf/util/values.h
+++ b/tools/perf/util/values.h
@@ -2,6 +2,7 @@
 #ifndef __PERF_VALUES_H
 #define __PERF_VALUES_H
 
+#include <stdio.h>
 #include <linux/types.h>
 
 struct perf_read_values {
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index df89637961..1b6f8f6db7 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -133,8 +133,6 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s
 	if (dso != NULL) {
 		__dsos__add(&machine->dsos, dso);
 		dso__set_long_name(dso, long_name, false);
-		/* Put dso here because __dsos_add already got it */
-		dso__put(dso);
 	}
 
 	return dso;
@@ -150,7 +148,7 @@ static int machine__thread_dso_type_maps_cb(struct map *map, void *data)
 	struct machine__thread_dso_type_maps_cb_args *args = data;
 	struct dso *dso = map__dso(map);
 
-	if (!dso || dso->long_name[0] != '/')
+	if (!dso || dso__long_name(dso)[0] != '/')
 		return 0;
 
 	args->dso_type = dso__type(dso, args->machine);
@@ -252,17 +250,15 @@ static struct dso *__machine__findnew_compat(struct machine *machine,
 	const char *file_name;
 	struct dso *dso;
 
-	dso = __dsos__find(&machine->dsos, vdso_file->dso_name, true);
+	dso = dsos__find(&machine->dsos, vdso_file->dso_name, true);
 	if (dso)
-		goto out;
+		return dso;
 
 	file_name = vdso__get_compat_file(vdso_file);
 	if (!file_name)
-		goto out;
+		return NULL;
 
-	dso = __machine__addnew_vdso(machine, vdso_file->dso_name, file_name);
-out:
-	return dso;
+	return __machine__addnew_vdso(machine, vdso_file->dso_name, file_name);
 }
 
 static int __machine__findnew_vdso_compat(struct machine *machine,
@@ -308,21 +304,21 @@ static struct dso *machine__find_vdso(struct machine *machine,
 	dso_type = machine__thread_dso_type(machine, thread);
 	switch (dso_type) {
 	case DSO__TYPE_32BIT:
-		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO32, true);
+		dso = dsos__find(&machine->dsos, DSO__NAME_VDSO32, true);
 		if (!dso) {
-			dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO,
-					   true);
+			dso = dsos__find(&machine->dsos, DSO__NAME_VDSO,
+					 true);
 			if (dso && dso_type != dso__type(dso, machine))
 				dso = NULL;
 		}
 		break;
 	case DSO__TYPE_X32BIT:
-		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSOX32, true);
+		dso = dsos__find(&machine->dsos, DSO__NAME_VDSOX32, true);
 		break;
 	case DSO__TYPE_64BIT:
 	case DSO__TYPE_UNKNOWN:
 	default:
-		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
+		dso = dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
 		break;
 	}
 
@@ -334,42 +330,38 @@ struct dso *machine__findnew_vdso(struct machine *machine,
 {
 	struct vdso_info *vdso_info;
 	struct dso *dso = NULL;
+	char *file;
 
-	down_write(&machine->dsos.lock);
 	if (!machine->vdso_info)
 		machine->vdso_info = vdso_info__new();
 
 	vdso_info = machine->vdso_info;
 	if (!vdso_info)
-		goto out_unlock;
+		return NULL;
 
 	dso = machine__find_vdso(machine, thread);
 	if (dso)
-		goto out_unlock;
+		return dso;
 
 #if BITS_PER_LONG == 64
 	if (__machine__findnew_vdso_compat(machine, thread, vdso_info, &dso))
-		goto out_unlock;
+		return dso;
 #endif
 
-	dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
-	if (!dso) {
-		char *file;
+	dso = dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
+	if (dso)
+		return dso;
 
-		file = get_file(&vdso_info->vdso);
-		if (file)
-			dso = __machine__addnew_vdso(machine, DSO__NAME_VDSO, file);
-	}
+	file = get_file(&vdso_info->vdso);
+	if (!file)
+		return NULL;
 
-out_unlock:
-	dso__get(dso);
-	up_write(&machine->dsos.lock);
-	return dso;
+	return __machine__addnew_vdso(machine, DSO__NAME_VDSO, file);
 }
 
 bool dso__is_vdso(struct dso *dso)
 {
-	return !strcmp(dso->short_name, DSO__NAME_VDSO) ||
-	       !strcmp(dso->short_name, DSO__NAME_VDSO32) ||
-	       !strcmp(dso->short_name, DSO__NAME_VDSOX32);
+	return !strcmp(dso__short_name(dso), DSO__NAME_VDSO) ||
+	       !strcmp(dso__short_name(dso), DSO__NAME_VDSO32) ||
+	       !strcmp(dso__short_name(dso), DSO__NAME_VDSOX32);
 }