fix(amd64): correct guard displacements, frameless FP offsets and immediate ranges

Assisted-by: GLM 5.3

asm/encode.go

@@ -117,9 +117,9 @@ func (e *enc) encode(mnem string, ops []Operand) error {
 	case "IMUL", "IMUL3":
 		return e.encodeImul(ops, size)
 	case "PUSH":
-		return e.encodePushPop(ops, true)
+		return e.encodePushPop(ops, size, true)
 	case "POP":
-		return e.encodePushPop(ops, false)
+		return e.encodePushPop(ops, size, false)
 	case "BSF", "BSR", "LZCNT", "TZCNT", "POPCNT":
 		return e.encodeCount(base, ops, size)
 	case "BSWAP":
@@ -345,6 +345,12 @@ func setMem(i *instr, regField int, m Mem) error {
 // a memory operand.  It is shared by the REX (scalar) and VEX (vector) paths.
 func memComponents(regField int, m Mem) (modrm, sib int, disp []byte, xBit, bBit int, err error) {
 	sib = -1
+	// A displacement wider than int32 fits no encoding form; truncating it
+	// would address a different location, and go tool asm reports "offset
+	// too large" for the same operand.
+	if m.Disp < -(1<<31) || m.Disp > (1<<31)-1 {
+		return 0, -1, nil, 0, 0, fmt.Errorf("displacement %d does not fit in 32 bits", m.Disp)
+	}
 	// RIP-relative: neither base nor index.
 	if !m.HasBase && !m.HasIndex {
 		return regField<<3 | 0x05, -1, le32(m.Disp), 0, 0, nil // mod=00, rm=101