perf annotate-data: Handle array style accesses

On x86, instructions for array access often looks like below.

  mov  0x1234(%rax,%rbx,8), %rcx

Usually the first register holds the type information and the second one
has the index.  And the current code only looks up a variable for the
first register.  But it's possible to be in the other way around so it
needs to check the second register if the first one failed.

The stat changed like this.

  Annotate data type stats:
  total 294, ok 148 (50.3%), bad 146 (49.7%)
  -----------------------------------------------------------
          30 : no_sym
          32 : no_mem_ops
          66 : no_var
          10 : no_typeinfo
           8 : bad_offset

Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lore.kernel.org/r/20240117062657.985479-4-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

1 files changed, 34 insertions, 9 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 0ec42e85ca5c..3cdcdd449c86 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -3563,8 +3563,22 @@ static int extract_reg_offset(struct arch *arch, const char *str,
 	if (regname == NULL)
 		return -1;
 
-	op_loc->reg = get_dwarf_regnum(regname, 0);
+	op_loc->reg1 = get_dwarf_regnum(regname, 0);
 	free(regname);
+
+	/* Get the second register */
+	if (op_loc->multi_regs) {
+		p = strchr(p + 1, arch->objdump.register_char);
+		if (p == NULL)
+			return -1;
+
+		regname = strdup(p);
+		if (regname == NULL)
+			return -1;
+
+		op_loc->reg2 = get_dwarf_regnum(regname, 0);
+		free(regname);
+	}
 	return 0;
 }
 
@@ -3577,14 +3591,20 @@ static int extract_reg_offset(struct arch *arch, const char *str,
  * Get detailed location info (register and offset) in the instruction.
  * It needs both source and target operand and whether it accesses a
  * memory location.  The offset field is meaningful only when the
- * corresponding mem flag is set.
+ * corresponding mem flag is set.  The reg2 field is meaningful only
+ * when multi_regs flag is set.
  *
  * Some examples on x86:
  *
- *   mov  (%rax), %rcx   # src_reg = rax, src_mem = 1, src_offset = 0
- *                       # dst_reg = rcx, dst_mem = 0
+ *   mov  (%rax), %rcx   # src_reg1 = rax, src_mem = 1, src_offset = 0
+ *                       # dst_reg1 = rcx, dst_mem = 0
  *
- *   mov  0x18, %r8      # src_reg = -1, dst_reg = r8
+ *   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
+ *                              # dst_reg1 = rbx, dst_reg2 = rcx, dst_mem = 1
+ *                              # dst_multi_regs = 1, dst_offset = 8
  */
 int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
 			       struct annotated_insn_loc *loc)
@@ -3605,24 +3625,29 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
 
 	for_each_insn_op_loc(loc, i, op_loc) {
 		const char *insn_str = ops->source.raw;
+		bool multi_regs = ops->source.multi_regs;
 
-		if (i == INSN_OP_TARGET)
+		if (i == INSN_OP_TARGET) {
 			insn_str = ops->target.raw;
+			multi_regs = ops->target.multi_regs;
+		}
 
 		/* Invalidate the register by default */
-		op_loc->reg = -1;
+		op_loc->reg1 = -1;
+		op_loc->reg2 = -1;
 
 		if (insn_str == NULL)
 			continue;
 
 		if (strchr(insn_str, arch->objdump.memory_ref_char)) {
 			op_loc->mem_ref = true;
+			op_loc->multi_regs = multi_regs;
 			extract_reg_offset(arch, insn_str, op_loc);
 		} else {
 			char *s = strdup(insn_str);
 
 			if (s) {
-				op_loc->reg = get_dwarf_regnum(s, 0);
+				op_loc->reg1 = get_dwarf_regnum(s, 0);
 				free(s);
 			}
 		}
@@ -3771,7 +3796,7 @@ retry:
 		/* Recalculate IP because of LOCK prefix or insn fusion */
 		ip = ms->sym->start + dl->al.offset;
 
-		mem_type = find_data_type(ms, ip, op_loc->reg, op_loc->offset);
+		mem_type = find_data_type(ms, ip, op_loc);
 		if (mem_type)
 			istat->good++;
 		else