fix(arm64): encode shifts, divides and multiplies and align sizes with emission

Assisted-by: GLM 5.3

asm/guard_test.go

@@ -152,6 +152,45 @@ func TestStackGuardBytesARM64(t *testing.T) {
 	}
 }
 
+// TestStackGuardBranchTargetsARM64 checks the class-2 guard's branch
+// positions for a frame whose guard constant needs two MOV words: the
+// displacements must be computed from byte offsets (8+4*ml and 16+4*ml), so
+// both branches land on the morestack block rather than inside the body.
+// The frame size makes the toolchain switch its own prologue decomposition,
+// so the assertion is on the branch targets, not pinned bytes.
+func TestStackGuardBranchTargetsARM64(t *testing.T) {
+	f, errs := parser.Parse("g_arm64.s", "TEXT \u00b7f(SB), $65664-0\n\tCALL \u00b7other(SB)\n\tRET\nTEXT \u00b7other(SB), NOSPLIT, $0\n\tRET\n")
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	img, err := AssembleFileARM64(f)
+	if err != nil {
+		t.Fatalf("assemble: %v", err)
+	}
+	fn := img.Funcs[0]
+	code := img.Code[fn.Offset : fn.Offset+fn.Size]
+	if len(code)%4 != 0 {
+		t.Fatalf("function size %d is not a word multiple", len(code))
+	}
+	// autosize = 65680, so the guard materialises 65552 = MOVZ+MOVK: ml = 2
+	// and the branches sit at bytes 16 and 24 of the guard prefix.
+	const morestackBlock = 12 // MOVD R30, R3; BL; B back
+	blockStart := len(code) - morestackBlock
+	check := func(name string, off int) {
+		t.Helper()
+		w := leWord(code[off:])
+		imm19 := int32(w>>5) & 0x7FFFF
+		if imm19&(1<<18) != 0 {
+			imm19 -= 1 << 19
+		}
+		if target := off + int(imm19)*4; target != blockStart {
+			t.Errorf("%s at byte %d targets byte %d, want the morestack block at %d", name, off, target, blockStart)
+		}
+	}
+	check("B.LO", 16)
+	check("B.LS", 24)
+}
+
 // The riscv64 stack-split guard, pinned from `go tool asm` (Go 1.27,
 // riscv64): the morestack call sits between the guard and the body, and the
 // guard branches forward over it.  Relocation fields are masked.