feat(asm): the immediate multiply and arm64 indirect branches GOROOT writes

Assisted-by: GLM 5.3 Flash

CHANGELOG.md

@@ -19,12 +19,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   access pair assembles as the toolchain's one-instruction form (the
   bare `MOVQ TLS, r` load nops out and `off(r)(TLS*1)` folds to the
   segment-prefixed absolute whose disp32 carries the R_TLSLE
-  relocation, per-GOOS); and `gasm asm` predefines the `GOARCH_<arch>`
+  relocation, per-GOOS); arm64 accepts the bare-register indirect branch
+  (`BL R9` beside `BL (R9)`, both BLR) and the zero-immediate store
+  (`MOVD $0, mem` through the zero register, rejecting non-zero immediates
+  as the toolchain does); and `gasm asm` predefines the `GOARCH_<arch>`
   and `GOOS_<goos>` macros the go command passes to `go tool asm`, so
   GOROOT headers' `#ifdef GOARCH_amd64` platform blocks (`go_tls.h`'s
   `get_tls` and friends) select as intended.  The GOROOT corpus measure
-  moves to 267 of 353 files assembling for every target architecture
-  (75.6 %), 89.4 % of the real-code corpus, from 70.8 % and 82.2 %.
+  moves to 276 of 353 files assembling for every target architecture
+  (78.2 %), 91.4 % of the real-code corpus (280 of 303), from 70.8 %
+  and 82.2 %.
 
 ### Added
 

asm/arm64_assemble.go

@@ -637,6 +637,20 @@ func encodeARM64Branch(mnem string, ops []*ast.Operand, pc int, offsets map[stri
 		return a64wordLE(a64UncondBranch(opc, uint32(rn), 0)), nil
 	}
 
+	// The bare spelling BL R9 is the same indirect branch: the parser reads
+	// a bare identifier as a symbol, and one named for a register is an
+	// indirect branch through it, which the toolchain accepts alongside the
+	// parenthesised form (BL (R3) and BL R3 both encode BLR R3).
+	if op.Addr.Sym != nil && op.Addr.Sym.Pseudo == "" && op.Addr.Base == "" && op.Addr.Index == "" {
+		if rn := arm64RegNum(op.Addr.Sym.Name); rn >= 0 {
+			opc := uint32(0) // BR
+			if link {
+				opc = 1 // BLR
+			}
+			return a64wordLE(a64UncondBranch(opc, uint32(rn), 0)), nil
+		}
+	}
+
 	// Symbol reference: BL sym(SB), or B sym(SB) for a tail call, against a
 	// relocation (R_CALLARM64 either way).
 	if op.Addr.Sym != nil && op.Addr.Sym.Pseudo == "SB" {
@@ -1454,6 +1468,15 @@ func encodeARM64Mov(instr *ast.Instr, mnem string, wb string, fi arm64FrameInfo,
 			}
 			return encodeARM64SBAddr(src.Imm.Sym, rd, relocs), nil
 		}
+		// Immediate → memory: only storing zero is encodable (the ZR
+		// register); the toolchain rejects any other immediate-to-memory
+		// combination ("illegal combination").
+		if isMemOperand(dst) {
+			if arm64Imm64(src) != 0 {
+				return nil, fmt.Errorf("%s: illegal combination: an immediate store must be zero", mnem)
+			}
+			return encodeARM64MemOp(mnem, dst, 31, false, fi, "")
+		}
 		rd := arm64RegNum(operandRegName(dst))
 		if rd < 0 {
 			return nil, fmt.Errorf("%s $imm: invalid destination register", mnem)

asm/instrs.go

@@ -640,7 +640,16 @@ func (e *enc) encodeDoubleShift(base string, ops []Operand, size int) error {
 func (e *enc) encodeImul(ops []Operand, size int) error {
 	switch len(ops) {
 	case 2:
-		// IMUL r, r/m: 0x0F 0xAF.
+		// Two shapes. The leading-immediate spelling IMUL $imm, r multiplies
+		// r in place (dst = rm = r): the shape GOROOT's clock code writes.
+		// Otherwise IMUL r, r/m: 0x0F 0xAF.
+		if imm, ok := ops[0].(Imm); ok {
+			dstReg, isReg := ops[1].(Reg)
+			if !isReg {
+				return fmt.Errorf("IMUL: destination must be a register")
+			}
+			return e.encodeImulImm(imm, dstReg, dstReg, size)
+		}
 		dstReg, ok := ops[1].(Reg)
 		if !ok {
 			return fmt.Errorf("IMUL: destination must be a register")
@@ -660,17 +669,26 @@ func (e *enc) encodeImul(ops []Operand, size int) error {
 		if !ok {
 			return fmt.Errorf("IMUL: immediate operand expected first")
 		}
-		// Plan 9 order: IMUL $imm, src, dst.
+		// Plan 9 order: IMUL $imm, src, dst; the source stays a general
+		// r/m operand (setRM takes registers and memory alike).
+		return e.encodeImulImm(imm, ops[1], dstReg, size)
+	}
+	return fmt.Errorf("IMUL expects 2 or 3 operands, got %d", len(ops))
+}
+
+// encodeImulImm emits the immediate multiply: 0x6B with a sign-extended imm8
+// when the value fits, 0x69 with a 32-bit immediate otherwise.
+func (e *enc) encodeImulImm(imm Imm, rm Operand, dst Reg, size int) error {
 	if fits8(int64(imm)) {
 		i := newInstr(size, []byte{0x6B})
-			if err := setRM(i, dstReg, ops[1], size); err != nil {
+		if err := setRM(i, dst, rm, size); err != nil {
 			return err
 		}
 		i.imm = []byte{byte(int8(imm))}
 		return e.emit(i)
 	}
 	i := newInstr(size, []byte{0x69})
-		if err := setRM(i, dstReg, ops[1], size); err != nil {
+	if err := setRM(i, dst, rm, size); err != nil {
 		return err
 	}
 	immBytes, err := immediate(int64(imm), size, false)
@@ -680,8 +698,6 @@ func (e *enc) encodeImul(ops []Operand, size int) error {
 	i.imm = immBytes
 	return e.emit(i)
 }
-	return fmt.Errorf("IMUL expects 2 or 3 operands, got %d", len(ops))
-}
 
 // --- PUSH / POP -------------------------------------------------------------