perf annotate-data: Add update_insn_state()

The update_insn_state() function is to update the type state table after
processing each instruction.  For now, it handles MOV (on x86) insn
to transfer type info from the source location to the target.

The location can be a register or a stack slot.  Check carefully when
memory reference happens and fetch the type correctly.  It basically
ignores write to a memory since it doesn't change the type info.  One
exception is writes to (new) stack slots for register spilling.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20240319055115.4063940-11-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 158 insertions, 3 deletions

diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index 8eaa06f1cee5..592437b6c097 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -71,7 +71,9 @@ struct type_state_stack {
  * 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;
 };
 
@@ -85,6 +87,8 @@ void init_type_state(struct type_state *state, struct arch *arch __maybe_unused)
 void exit_type_state(struct type_state *state);
 void update_var_state(struct type_state *state, struct data_loc_info *dloc,
 		      u64 addr, u64 insn_offset, struct die_var_type *var_types);
+void update_insn_state(struct type_state *state, struct data_loc_info *dloc,
+		       struct disasm_line *dl);
 
 void init_type_state(struct type_state *state, struct arch *arch __maybe_unused)
 {
@@ -412,13 +416,13 @@ void update_var_state(struct type_state *state, struct data_loc_info *dloc,
 		if (var->reg == DWARF_REG_FB) {
 			findnew_stack_state(state, var->offset, &mem_die);
 
-			pr_debug_dtp("var [%"PRIx64"] -%#x(stack) type=",
+			pr_debug_dtp("var [%"PRIx64"] -%#x(stack)",
 				     insn_offset, -var->offset);
 			pr_debug_type_name(&mem_die);
 		} else if (var->reg == fbreg) {
 			findnew_stack_state(state, var->offset - fb_offset, &mem_die);
 
-			pr_debug_dtp("var [%"PRIx64"] -%#x(stack) type=",
+			pr_debug_dtp("var [%"PRIx64"] -%#x(stack)",
 				     insn_offset, -var->offset + fb_offset);
 			pr_debug_type_name(&mem_die);
 		} else if (has_reg_type(state, var->reg) && var->offset == 0) {
@@ -428,13 +432,164 @@ void update_var_state(struct type_state *state, struct data_loc_info *dloc,
 			reg->type = mem_die;
 			reg->ok = true;
 
-			pr_debug_dtp("var [%"PRIx64"] reg%d type=",
+			pr_debug_dtp("var [%"PRIx64"] reg%d",
 				     insn_offset, var->reg);
 			pr_debug_type_name(&mem_die);
 		}
 	}
 }
 
+static void update_insn_state_x86(struct type_state *state,
+				  struct data_loc_info *dloc,
+				  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 (strncmp(dl->ins.name, "mov", 3))
+		return;
+
+	if (dloc->fb_cfa) {
+		u64 ip = dloc->ms->sym->start + dl->al.offset;
+		u64 pc = map__rip_2objdump(dloc->ms->map, ip);
+
+		if (die_get_cfa(dloc->di->dbg, pc, &fbreg, &fboff) < 0)
+			fbreg = -1;
+	}
+
+	/* Case 1. register to register transfers */
+	if (!src->mem_ref && !dst->mem_ref) {
+		if (!has_reg_type(state, dst->reg1))
+			return;
+
+		tsr = &state->regs[dst->reg1];
+		if (!has_reg_type(state, src->reg1) ||
+		    !state->regs[src->reg1].ok) {
+			tsr->ok = false;
+			return;
+		}
+
+		tsr->type = state->regs[src->reg1].type;
+		tsr->ok = true;
+
+		pr_debug_dtp("mov [%x] reg%d -> reg%d",
+			     insn_offset, src->reg1, dst->reg1);
+		pr_debug_type_name(&tsr->type);
+	}
+	/* Case 2. memory to register transers */
+	if (src->mem_ref && !dst->mem_ref) {
+		int sreg = src->reg1;
+
+		if (!has_reg_type(state, dst->reg1))
+			return;
+
+		tsr = &state->regs[dst->reg1];
+
+retry:
+		/* Check stack variables with offset */
+		if (sreg == fbreg) {
+			struct type_state_stack *stack;
+			int offset = src->offset - fboff;
+
+			stack = find_stack_state(state, offset);
+			if (stack == NULL) {
+				tsr->ok = false;
+				return;
+			} else if (!stack->compound) {
+				tsr->type = stack->type;
+				tsr->ok = true;
+			} else if (die_get_member_type(&stack->type,
+						       offset - stack->offset,
+						       &type_die)) {
+				tsr->type = type_die;
+				tsr->ok = true;
+			} else {
+				tsr->ok = false;
+				return;
+			}
+
+			pr_debug_dtp("mov [%x] -%#x(stack) -> reg%d",
+				     insn_offset, -offset, dst->reg1);
+			pr_debug_type_name(&tsr->type);
+		}
+		/* And then dereference the pointer if it has one */
+		else if (has_reg_type(state, sreg) && state->regs[sreg].ok &&
+			 die_deref_ptr_type(&state->regs[sreg].type,
+					    src->offset, &type_die)) {
+			tsr->type = type_die;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] %#x(reg%d) -> reg%d",
+				     insn_offset, src->offset, sreg, dst->reg1);
+			pr_debug_type_name(&tsr->type);
+		}
+		/* Or try another register if any */
+		else if (src->multi_regs && sreg == src->reg1 &&
+			 src->reg1 != src->reg2) {
+			sreg = src->reg2;
+			goto retry;
+		}
+		/* It failed to get a type info, mark it as invalid */
+		else {
+			tsr->ok = false;
+		}
+	}
+	/* Case 3. register to memory transfers */
+	if (!src->mem_ref && dst->mem_ref) {
+		if (!has_reg_type(state, src->reg1) ||
+		    !state->regs[src->reg1].ok)
+			return;
+
+		/* Check stack variables with offset */
+		if (dst->reg1 == fbreg) {
+			struct type_state_stack *stack;
+			int offset = dst->offset - fboff;
+
+			stack = find_stack_state(state, offset);
+			if (stack) {
+				/*
+				 * The source register is likely to hold a type
+				 * of member if it's a compound type.  Do not
+				 * update the stack variable type since we can
+				 * get the member type later by using the
+				 * die_get_member_type().
+				 */
+				if (!stack->compound)
+					set_stack_state(stack, offset,
+							&state->regs[src->reg1].type);
+			} else {
+				findnew_stack_state(state, offset,
+						    &state->regs[src->reg1].type);
+			}
+
+			pr_debug_dtp("mov [%x] reg%d -> -%#x(stack)",
+				     insn_offset, src->reg1, -offset);
+			pr_debug_type_name(&state->regs[src->reg1].type);
+		}
+		/*
+		 * Ignore other transfers since it'd set a value in a struct
+		 * and won't change the type.
+		 */
+	}
+	/* Case 4. memory to memory transfers (not handled for now) */
+}
+
+void update_insn_state(struct type_state *state, struct data_loc_info *dloc,
+		       struct disasm_line *dl)
+{
+	if (arch__is(dloc->arch, "x86"))
+		update_insn_state_x86(state, dloc, dl);
+}
+
 /* The result will be saved in @type_die */
 static int find_data_type_die(struct data_loc_info *dloc, Dwarf_Die *type_die)
 {