[PATCH v2 12/16] perf annotate-arm64: Support 'mov' instruction tracking

[Tengda Wu]

Extend update_insn_state() for arm64 to handle register-to-register
'mov' instructions.

When a 'mov' instruction occurs between two registers, the data type
information (DWARF type, kind, and offset) needs to be propagated from
the source register to the destination register. This ensures that if
a pointer or a structure was previously identified in one register,
the tracker continues to recognize it after it is moved.

A real-world example is shown below:

  ffff8000803eebf8 <get_vma_policy>:
  ffff8000803eec20:  mov  x21, x0  // x0 (struct vm_area_struct*) -> x21
  ffff8000803eec28:  ldr  x2, [x0, #112]
  ffff8000803eec2c:  cbz  x2, ffff8000803eec94 <get_vma_policy+0x9c>
  ffff8000803eec94:  ldr  x0, [x21, #152]  // PMU sample

Before this commit, the type of x21 was unknown, causing the subsequent
inference to fail:

  var [0] reg0 offset 0 type='struct vm_area_struct*' size=0x8
  chk [9c] reg21 offset=0x98 ok=0 kind=0 cfa : no type information
  final result: no type information

After this commit, the type of x21 is correctly inferred as 'vm_area_struct':

  var [0] reg0 offset 0 type='struct vm_area_struct*' size=0x8
  mov [28] reg0 -> reg21 type='struct vm_area_struct*' size=0x8
  chk [9c] reg21 offset=0x98 ok=1 kind=1 (struct vm_area_struct*) : Good!
  found by insn track: 0x98(reg21) type-offset=0x98
  final result:  type='struct vm_area_struct' size=0xb0

Signed-off-by: Tengda Wu <wutengda@xxxxxxxxxxxxxxx>
---
 .../perf/util/annotate-arch/annotate-arm64.c  | 28 +++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/tools/perf/util/annotate-arch/annotate-arm64.c b/tools/perf/util/annotate-arch/annotate-arm64.c
index f9100230c2f6..013b673f4861 100644
--- a/tools/perf/util/annotate-arch/annotate-arm64.c
+++ b/tools/perf/util/annotate-arch/annotate-arm64.c
@@ -308,6 +308,34 @@ static void update_insn_state_arm64(struct type_state *state,
 	sreg = src->reg1;
 	dreg = dst->reg1;
 
+	/* Register to register transfers */
+	if (!strcmp(dl->ins.name, "mov")) {
+		if (!has_reg_type(state, sreg))
+			return;
+
+		tsr = &state->regs[sreg];
+		tsr->copied_from = -1;
+
+		if (!has_reg_type(state, dreg) ||
+		    !state->regs[dreg].ok) {
+			tsr->ok = false;
+			return;
+		}
+
+		tsr->type = state->regs[dreg].type;
+		tsr->kind = state->regs[dreg].kind;
+		tsr->offset = state->regs[dreg].offset;
+		tsr->ok = true;
+
+		if (tsr->kind == TSR_KIND_TYPE || tsr->kind == TSR_KIND_POINTER)
+			tsr->copied_from = dreg;
+
+		pr_debug_dtp("mov [%x] reg%d -> reg%d",
+			     insn_offset, dreg, sreg);
+		pr_debug_type_name(&tsr->type, tsr->kind);
+		return;
+	}
+
 	if (dloc->fb_cfa) {
 		u64 ip = dloc->ms->sym->start + dl->al.offset;
 		u64 pc = map__rip_2objdump(dloc->ms->map, ip);
-- 
2.34.1