[PATCH 3/3] perf disasm & annotate x86: Track C++ vptr and resolve virtual function calls

[Yanbo Zhao <yzhao62@ncsu.edu>]

Implement disassembler and x86 type profiling support for C++ virtual
dispatch and indirect call resolution:
- In call__parse() for indirect calls, duplicate and store ops->raw into
  ops->target.raw so instruction location extraction can retrieve target
  operand registers and offsets.
- In extract_reg_offset(), skip any leading '*' prefix (e.g. *%rax).
- Add TSR_KIND_VTABLE_PTR to enum type_state_kind and handle it in
  pr_debug_type_name().
- In update_insn_state_x86() for mov instructions, inspect member
  name and identify '_vptr' access, setting register kind to
  TSR_KIND_VTABLE_PTR via die_is_vptr_member() helper.
- For call instructions targeting virtual function tables, look up
  the virtual function DIE via die_find_virtual_func() before
  register state invalidation.  Only the primary vtable is handled
  for now (TODO: multiple inheritance).
- Update the receiver ('this' pointer) register to the C++ class DIE
  upon virtual call resolution when CU is C++.  The register number
  comes from the new type_state::arg0_reg field initialized per arch
  like ret_reg, instead of being hardcoded.
- Move caller-saved register invalidation after reading target
  operands to prevent losing state required for virtual call
  resolution.

Signed-off-by: Yanbo Zhao <yzhao62@ncsu.edu>
---
 tools/perf/util/annotate-arch/annotate-x86.c | 103 ++++++++++++++++---
 tools/perf/util/annotate-data.c              |   7 ++
 tools/perf/util/annotate-data.h              |   3 +
 tools/perf/util/annotate.c                   |   4 +
 tools/perf/util/disasm.c                     |   1 +
 5 files changed, 105 insertions(+), 13 deletions(-)

diff --git a/tools/perf/util/annotate-arch/annotate-x86.c b/tools/perf/util/annotate-arch/annotate-x86.c
index 7e6136536393..cfb37a6130ba 100644
--- a/tools/perf/util/annotate-arch/annotate-x86.c
+++ b/tools/perf/util/annotate-arch/annotate-x86.c
@@ -11,6 +11,8 @@
 #include "../map.h"
 #include "../string2.h" // strstarts
 #include "../symbol.h"
+#include "../hist.h"
+#include "../dwarf-aux.h"
 
 /*
  * x86 instruction nmemonic table to parse disasm lines for annotate.
@@ -234,6 +236,11 @@ static void update_insn_state_x86(struct type_state *state,
 		struct symbol *func = dl->ops.target.sym;
 		const char *call_name;
 		u64 call_addr;
+		Dwarf_Die target_func_die;
+		bool resolved_statically = false;
+		Dwarf_Die class_die;
+		bool has_class_die = false;
+		struct annotated_op_loc *target_op;
 
 		/* Try to resolve the call target name */
 		if (func)
@@ -245,12 +252,42 @@ static void update_insn_state_x86(struct type_state *state,
 		if (call_name && !strcmp(call_name, "__fentry__"))
 			return;
 
+		/*
+		 * 1. Resolve target statically (virtual call fallback) FIRST
+		 * (before invalidation)
+		 */
+		target_op = &loc.ops[INSN_OP_TARGET];
+
+		if (target_op->mem_ref && has_reg_type(state, target_op->reg1)) {
+			struct type_state_reg *reg = &state->regs[target_op->reg1];
+
+			if (reg->ok && reg->kind == TSR_KIND_VTABLE_PTR) {
+				/* TODO: handle multiple inheritance (non-primary vtables) */
+				int vtable_index = target_op->offset / 8;
+				Dwarf_Die target_class_die = reg->type;
+
+				if (die_find_virtual_func(&target_class_die, vtable_index,
+							  &target_func_die) &&
+				    die_get_type(&target_func_die, &type_die)) {
+					resolved_statically = true;
+					class_die = target_class_die;
+					has_class_die = true;
+				}
+			}
+		}
+
+		/* Fallback to name-based resolution for direct calls */
+		if (!resolved_statically && call_name) {
+			if (die_find_func_rettype(cu_die, call_name, &type_die))
+				resolved_statically = true;
+		}
+
 		if (call_name)
 			pr_debug_dtp("call [%x] %s\n", insn_offset, call_name);
 		else
 			pr_debug_dtp("call [%x] <unknown>\n", insn_offset);
 
-		/* Invalidate caller-saved registers after call */
+		/* 2. Invalidate caller-saved registers after we read them for resolution */
 		call_addr = map__rip_2objdump(dloc->ms->map,
 					      dloc->ms->sym->start + dl->al.offset);
 		for (unsigned i = 0; i < ARRAY_SIZE(state->regs); i++) {
@@ -264,8 +301,8 @@ static void update_insn_state_x86(struct type_state *state,
 			invalidate_reg_state(reg);
 		}
 
-		/* Update register with the return type (if any) */
-		if (call_name && die_find_func_rettype(cu_die, call_name, &type_die)) {
+		/* 3. Apply resolved types to registers */
+		if (resolved_statically) {
 			tsr = &state->regs[state->ret_reg];
 			tsr->type = type_die;
 			tsr->kind = TSR_KIND_TYPE;
@@ -275,6 +312,20 @@ static void update_insn_state_x86(struct type_state *state,
 			pr_debug_dtp("call [%x] return -> reg%d",
 				     insn_offset, state->ret_reg);
 			pr_debug_type_name(&type_die, tsr->kind);
+
+			/* Update receiver ('this' pointer) register if C++ */
+			if (has_class_die && cu_is_cplusplus(cu_die)) {
+				struct type_state_reg *recv_tsr = &state->regs[state->arg0_reg];
+
+				if (recv_tsr->ok &&
+				    (recv_tsr->kind == TSR_KIND_TYPE ||
+				     recv_tsr->kind == TSR_KIND_POINTER)) {
+					recv_tsr->type = class_die;
+					pr_debug_dtp("call [%x] update receiver reg%d to C++ class",
+						     insn_offset, state->arg0_reg);
+					pr_debug_type_name(&class_die, recv_tsr->kind);
+				}
+			}
 		}
 		return;
 	}
@@ -622,17 +673,43 @@ static void update_insn_state_x86(struct type_state *state,
 		}
 		/* 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 + state->regs[sreg].offset, &type_die)) {
-			tsr->type = type_die;
-			tsr->kind = TSR_KIND_TYPE;
-			tsr->offset = 0;
-			tsr->ok = true;
+			 state->regs[sreg].kind == TSR_KIND_TYPE) {
+			Dwarf_Die class_type;
+			Dwarf_Die member;
+			int total_offset = src->offset + state->regs[sreg].offset;
+			bool is_vptr = false;
+
+			if (die_get_real_type(&state->regs[sreg].type, &class_type) &&
+			    die_is_compound_type(&class_type) &&
+			    die_find_member_by_offset(&class_type, total_offset, &member) &&
+			    die_is_vptr_member(&member)) {
+				tsr->type = class_type;
+				tsr->kind = TSR_KIND_VTABLE_PTR;
+				tsr->offset = 0;
+				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);
+				pr_debug_dtp("mov [%x] %#x(reg%d) -> reg%d (vptr)",
+					     insn_offset, src->offset,
+					     sreg, dst->reg1);
+				pr_debug_type_name(&class_type, tsr->kind);
+				is_vptr = true;
+			}
+
+			if (!is_vptr) {
+				if (die_deref_ptr_type(&state->regs[sreg].type,
+						       total_offset, &type_die)) {
+					tsr->type = type_die;
+					tsr->kind = TSR_KIND_TYPE;
+					tsr->offset = 0;
+					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);
+				} else {
+					invalidate_reg_state(tsr);
+				}
+			}
 		}
 		/* Handle dereference of TSR_KIND_POINTER registers */
 		else if (has_reg_type(state, sreg) && state->regs[sreg].ok &&
diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index ee6bd2d0012d..875e5ba2fe9f 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -28,6 +28,8 @@
 
 /* register number of the stack pointer */
 #define X86_REG_SP 7
+/* register number of the first integer argument (%rdi) */
+#define X86_REG_DI 5
 
 static void delete_var_types(struct die_var_type *var_types);
 
@@ -66,6 +68,10 @@ void pr_debug_type_name(Dwarf_Die *die, enum type_state_kind kind)
 		pr_info(" pointer");
 		/* it also prints the type info */
 		break;
+	case TSR_KIND_VTABLE_PTR:
+		pr_info(" C++ vtable pointer");
+		/* it also prints the type info */
+		break;
 	case TSR_KIND_CANARY:
 		pr_info(" stack canary\n");
 		return;
@@ -177,6 +183,7 @@ static void init_type_state(struct type_state *state, const struct arch *arch)
 		state->regs[10].caller_saved = true;
 		state->regs[11].caller_saved = true;
 		state->ret_reg = 0;
+		state->arg0_reg = X86_REG_DI;
 		state->stack_reg = X86_REG_SP;
 	}
 }
diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
index c26130744260..785e1d1777ce 100644
--- a/tools/perf/util/annotate-data.h
+++ b/tools/perf/util/annotate-data.h
@@ -36,6 +36,7 @@ enum type_state_kind {
 	TSR_KIND_CONST,
 	TSR_KIND_PERCPU_POINTER,
 	TSR_KIND_POINTER,
+	TSR_KIND_VTABLE_PTR,
 	TSR_KIND_CANARY,
 };
 
@@ -224,6 +225,8 @@ struct type_state {
 	struct list_head stack_vars;
 	/* return value register */
 	int ret_reg;
+	/* first integer argument register (holds 'this' for C++ methods) */
+	int arg0_reg;
 	/* stack pointer register */
 	int stack_reg;
 };
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index df70e95a8470..b4c6b45b4da3 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2509,6 +2509,10 @@ static int extract_reg_offset(const struct arch *arch, const char *str,
 	if (arch->objdump.register_char == 0)
 		return -1;
 
+	/* Skip leading '*' for indirect call/jmp operands (e.g. *%rax) */
+	if (*str == '*')
+		str++;
+
 	/*
 	 * It should start from offset, but it's possible to skip 0
 	 * in the asm.  So 0(%rax) should be same as (%rax).
diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index 6cfdbabbb8c7..01266eeddbb4 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -279,6 +279,7 @@ static int call__parse(const struct arch *arch, struct ins_operands *ops, struct
 	return 0;
 
 indirect_call:
+	ops->target.raw = strdup(ops->raw);
 	tok = strchr(endptr, '*');
 	if (tok != NULL) {
 		endptr++;
-- 
2.25.1