1 files changed, 576 insertions, 1 deletions

diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index 5cdf457f5cbe..803f9351a3fb 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -202,7 +202,582 @@ static int x86__annotate_init(struct arch *arch, char *cpuid)
 		if (x86__cpuid_parse(arch, cpuid))
 			err = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING;
 	}
-
+	arch->e_machine = EM_X86_64;
+	arch->e_flags = 0;
 	arch->initialized = true;
 	return err;
 }
+
+#ifdef HAVE_LIBDW_SUPPORT
+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->offset = 0;
+			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];
+		tsr->copied_from = -1;
+
+		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;
+				tsr->offset = 0;
+				tsr->ok = true;
+				imm_value = tsr->imm_value;
+			}
+		}
+		else
+			return;
+
+		/* Ignore add to non-pointer or non-const types */
+		if (tsr->kind == TSR_KIND_POINTER ||
+		    (dwarf_tag(&tsr->type) == DW_TAG_pointer_type &&
+		     src->reg1 != DWARF_REG_PC && tsr->kind == TSR_KIND_TYPE && !dst->mem_ref)) {
+			tsr->offset += imm_value;
+			pr_debug_dtp("add [%x] offset %#"PRIx64" to reg%d",
+				     insn_offset, imm_value, dst->reg1);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+
+		if (tsr->kind == TSR_KIND_CONST)
+			tsr->imm_value += imm_value;
+
+		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_PERCPU_POINTER;
+			tsr->offset = 0;
+			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, "sub", 3)) {
+		u64 imm_value = -1ULL;
+
+		if (!has_reg_type(state, dst->reg1))
+			return;
+
+		tsr = &state->regs[dst->reg1];
+		tsr->copied_from = -1;
+
+		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;
+
+		if (tsr->kind == TSR_KIND_POINTER ||
+		    (dwarf_tag(&tsr->type) == DW_TAG_pointer_type &&
+		     src->reg1 != DWARF_REG_PC && tsr->kind == TSR_KIND_TYPE && !dst->mem_ref)) {
+			tsr->offset -= imm_value;
+			pr_debug_dtp("sub [%x] offset %#"PRIx64" to reg%d",
+				     insn_offset, imm_value, dst->reg1);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+
+		if (tsr->kind == TSR_KIND_CONST)
+			tsr->imm_value -= imm_value;
+
+		return;
+	}
+
+	if (!strncmp(dl->ins.name, "lea", 3)) {
+		int sreg = src->reg1;
+		struct type_state_reg src_tsr;
+
+		if (!has_reg_type(state, sreg) ||
+		    !has_reg_type(state, dst->reg1) ||
+		    !src->mem_ref)
+			return;
+
+		src_tsr = state->regs[sreg];
+		tsr = &state->regs[dst->reg1];
+
+		tsr->copied_from = -1;
+		tsr->ok = false;
+
+		/* Case 1: Based on stack pointer or frame pointer */
+		if (sreg == fbreg || sreg == state->stack_reg) {
+			struct type_state_stack *stack;
+			int offset = src->offset - fboff;
+
+			stack = find_stack_state(state, offset);
+			if (!stack)
+				return;
+
+			tsr->type = stack->type;
+			tsr->kind = TSR_KIND_POINTER;
+			tsr->offset = offset - stack->offset;
+			tsr->ok = true;
+
+			if (sreg == fbreg) {
+				pr_debug_dtp("lea [%x] address of -%#x(stack) -> reg%d",
+					     insn_offset, -src->offset, dst->reg1);
+			} else {
+				pr_debug_dtp("lea [%x] address of %#x(reg%d) -> reg%d",
+					     insn_offset, src->offset, sreg, dst->reg1);
+			}
+
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+		/* Case 2: Based on a register holding a typed pointer */
+		else if (src_tsr.ok && (src_tsr.kind == TSR_KIND_POINTER ||
+			 (dwarf_tag(&src_tsr.type) == DW_TAG_pointer_type &&
+			  src_tsr.kind == TSR_KIND_TYPE))) {
+
+			if (src_tsr.kind == TSR_KIND_TYPE &&
+			    __die_get_real_type(&state->regs[sreg].type, &type_die) == NULL)
+				return;
+
+			if (src_tsr.kind == TSR_KIND_POINTER)
+				type_die = state->regs[sreg].type;
+
+			/* Check if the target type has a member at the new offset */
+			if (die_get_member_type(&type_die,
+						src->offset + src_tsr.offset, &type_die) == NULL)
+				return;
+
+			tsr->type = src_tsr.type;
+			tsr->kind = src_tsr.kind;
+			tsr->offset = src->offset + src_tsr.offset;
+			tsr->ok = true;
+
+			pr_debug_dtp("lea [%x] address of %s%#x(reg%d) -> reg%d",
+						insn_offset, src->offset < 0 ? "-" : "",
+						abs(src->offset), sreg, dst->reg1);
+
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+		return;
+	}
+
+	/* Invalidate register states for other ops which may change pointers */
+	if (has_reg_type(state, dst->reg1) && !dst->mem_ref &&
+	    dwarf_tag(&state->regs[dst->reg1].type) == DW_TAG_pointer_type) {
+		if (!strncmp(dl->ins.name, "imul", 4) || !strncmp(dl->ins.name, "mul", 3) ||
+		    !strncmp(dl->ins.name, "idiv", 4) || !strncmp(dl->ins.name, "div", 3) ||
+		    !strncmp(dl->ins.name, "shl", 3)  || !strncmp(dl->ins.name, "shr", 3) ||
+		    !strncmp(dl->ins.name, "sar", 3)  || !strncmp(dl->ins.name, "and", 3) ||
+		    !strncmp(dl->ins.name, "or", 2)   || !strncmp(dl->ins.name, "neg", 3) ||
+		    !strncmp(dl->ins.name, "inc", 3)  || !strncmp(dl->ins.name, "dec", 3)) {
+			pr_debug_dtp("%s [%x] invalidate reg%d\n",
+						dl->ins.name, insn_offset, dst->reg1);
+			state->regs[dst->reg1].ok = false;
+			state->regs[dst->reg1].copied_from = -1;
+			return;
+		}
+
+		if (!strncmp(dl->ins.name, "xor", 3) && dst->reg1 == src->reg1) {
+			/* xor reg, reg clears the register */
+			pr_debug_dtp("xor [%x] clear reg%d\n",
+				     insn_offset, dst->reg1);
+
+			state->regs[dst->reg1].kind = TSR_KIND_CONST;
+			state->regs[dst->reg1].imm_value = 0;
+			state->regs[dst->reg1].ok = true;
+			state->regs[dst->reg1].copied_from = -1;
+			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];
+		tsr->copied_from = -1;
+
+		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->offset = 0;
+				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->offset = 0;
+			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->offset = 0;
+			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->imm_value = state->regs[src->reg1].imm_value;
+		tsr->offset = state->regs[src->reg1].offset;
+		tsr->ok = true;
+
+		/* To copy back the variable type later (hopefully) */
+		if (tsr->kind == TSR_KIND_TYPE || tsr->kind == TSR_KIND_POINTER)
+			tsr->copied_from = src->reg1;
+
+		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];
+		tsr->copied_from = -1;
+
+retry:
+		/* Check stack variables with offset */
+		if (sreg == fbreg || sreg == state->stack_reg) {
+			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->offset = stack->ptr_offset;
+				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->offset = 0;
+				tsr->ok = true;
+			} else {
+				tsr->ok = false;
+				return;
+			}
+
+			if (sreg == fbreg) {
+				pr_debug_dtp("mov [%x] -%#x(stack) -> reg%d",
+					     insn_offset, -offset, dst->reg1);
+			} else {
+				pr_debug_dtp("mov [%x] %#x(reg%d) -> reg%d",
+					     insn_offset, offset, sreg, 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 + state->regs[sreg].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);
+		}
+		/* Handle dereference of TSR_KIND_POINTER registers */
+		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 + state->regs[sreg].offset, &type_die)) {
+			tsr->type = state->regs[sreg].type;
+			tsr->kind = TSR_KIND_TYPE;
+			tsr->offset = src->offset + state->regs[sreg].offset;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] addr %#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->offset = 0;
+			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->offset = 0;
+				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_PERCPU_POINTER &&
+			 die_get_member_type(&state->regs[sreg].type,
+					     src->offset, &type_die)) {
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_TYPE;
+			tsr->offset = 0;
+			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;
+					tsr->offset = 0;
+					tsr->ok = true;
+
+					pr_debug_dtp("mov [%x] percpu base reg%d\n",
+						     insn_offset, dst->reg1);
+					return;
+				}
+			}
+
+			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 || dst->reg1 == state->stack_reg) {
+			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, tsr->offset);
+			} else {
+				findnew_stack_state(state, offset, tsr->kind,
+						    &tsr->type, tsr->offset);
+			}
+
+			if (dst->reg1 == fbreg) {
+				pr_debug_dtp("mov [%x] reg%d -> -%#x(stack)",
+					     insn_offset, src->reg1, -offset);
+			} else {
+				pr_debug_dtp("mov [%x] reg%d -> %#x(reg%d)",
+					     insn_offset, src->reg1, offset, dst->reg1);
+			}
+			if (tsr->offset != 0) {
+				pr_debug_dtp(" reg%d offset %#x ->",
+					src->reg1, tsr->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) */
+}
+#endif