[AVR] Add the machine code emitter

[dylanmckay]

Register the machine code emitter

[kparzysz]

lib/Target/AVR/MCTargetDesc/AVRMCCodeEmitter.cpp

160

Line too long.

191

No else after return.

254

No else after return, here and below.

[dylanmckay]

Code review from Krzysztof

• Don't go over 80 columns
• No returns in else blocks

lib/Target/AVR/MCTargetDesc/AVRMCCodeEmitter.h

+//===-- AVRMCCodeEmitter.h - Convert AVR Code to Machine Code -------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines the AVRMCCodeEmitter class.
+//
+//===----------------------------------------------------------------------===//
+//
+
+#ifndef LLVM_AVR_CODE_EMITTER_H
+#define LLVM_AVR_CODE_EMITTER_H
+
+#include "AVRFixupKinds.h"
+
+#include "llvm/MC/MCCodeEmitter.h"
+#include "llvm/Support/DataTypes.h"
+
+#define GET_INSTRINFO_OPERAND_TYPES_ENUM
+#include "AVRGenInstrInfo.inc"
+
+namespace llvm {
+
+class MCContext;
+class MCExpr;
+class MCFixup;
+class MCInst;
+class MCInstrInfo;
+class MCOperand;
+class MCSubtargetInfo;
+class raw_ostream;
+
+/// Writes AVR machine code to a stream.
+class AVRMCCodeEmitter : public MCCodeEmitter {
+public:
+  AVRMCCodeEmitter(const MCInstrInfo &MCII, MCContext &Ctx)
+      : MCII(MCII), Ctx(Ctx) {}
+
+private:
+  /// Finishes up encoding an LD/ST instruction.
+  /// The purpose of this function is to set an bit in the instruction
+  /// which follows no logical pattern. See the implementation for details.
+  unsigned loadStorePostEncoder(const MCInst &MI, unsigned EncodedValue,
+                                const MCSubtargetInfo &STI) const;
+
+  /// Gets the encoding for a conditional branch target.
+  template <AVR::Fixups Fixup>
+  unsigned encodeRelCondBrTarget(const MCInst &MI, unsigned OpNo,
+                                 SmallVectorImpl<MCFixup> &Fixups,
+                                 const MCSubtargetInfo &STI) const;
+
+  /// Encodes the `PTRREGS` operand to a load or store instruction.
+  unsigned encodeLDSTPtrReg(const MCInst &MI, unsigned OpNo,
+                            SmallVectorImpl<MCFixup> &Fixups,
+                            const MCSubtargetInfo &STI) const;
+
+  /// Encodes a `register+immediate` operand for `LDD`/`STD`.
+  unsigned encodeMemri(const MCInst &MI, unsigned OpNo,
+                       SmallVectorImpl<MCFixup> &Fixups,
+                       const MCSubtargetInfo &STI) const;
+
+  /// Takes the compliment of a number (~0 - val).
+  unsigned encodeComplement(const MCInst &MI, unsigned OpNo,
+                            SmallVectorImpl<MCFixup> &Fixups,
+                            const MCSubtargetInfo &STI) const;
+
+  /// Encodes an immediate value with a given fixup.
+  template <AVR::Fixups Fixup>
+  unsigned encodeImm(const MCInst &MI, unsigned OpNo,
+                     SmallVectorImpl<MCFixup> &Fixups,
+                     const MCSubtargetInfo &STI) const;
+
+  /// Gets the encoding of the target for the `CALL k` instruction.
+  unsigned encodeCallTarget(const MCInst &MI, unsigned OpNo,
+                            SmallVectorImpl<MCFixup> &Fixups,
+                            const MCSubtargetInfo &STI) const;
+
+  /// TableGen'ed function to get the binary encoding for an instruction.
+  uint64_t getBinaryCodeForInstr(const MCInst &MI,
+                                 SmallVectorImpl<MCFixup> &Fixups,
+                                 const MCSubtargetInfo &STI) const;
+
+  unsigned getExprOpValue(const MCExpr *Expr, SmallVectorImpl<MCFixup> &Fixups,
+                          const MCSubtargetInfo &STI) const;
+
+  /// Returns the binary encoding of operand.
+  ///
+  /// If the machine operand requires relocation, the relocation is recorded
+  /// and zero is returned.
+  unsigned getMachineOpValue(const MCInst &MI, const MCOperand &MO,
+                             SmallVectorImpl<MCFixup> &Fixups,
+                             const MCSubtargetInfo &STI) const;
+
+  void emitInstruction(uint64_t Val, unsigned Size, const MCSubtargetInfo &STI,
+                       raw_ostream &OS) const;
+
+  void encodeInstruction(const MCInst &MI, raw_ostream &OS,
+                         SmallVectorImpl<MCFixup> &Fixups,
+                         const MCSubtargetInfo &STI) const override;
+
+  AVRMCCodeEmitter(const AVRMCCodeEmitter &) = delete;
+  void operator=(const AVRMCCodeEmitter &) = delete;
+
+  const MCInstrInfo &MCII;
+  MCContext &Ctx;
+};
+
+} // end namespace of llvm.
+
+#endif // LLVM_AVR_CODE_EMITTER_H
+

lib/Target/AVR/MCTargetDesc/AVRMCCodeEmitter.cpp

+//===-- AVRMCCodeEmitter.cpp - Convert AVR Code to Machine Code -----------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the AVRMCCodeEmitter class.
+//
+//===----------------------------------------------------------------------===//
+
+#include "AVRMCCodeEmitter.h"
+
+#include "MCTargetDesc/AVRMCExpr.h"
+#include "MCTargetDesc/AVRMCTargetDesc.h"
+
+#include "llvm/ADT/APFloat.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/MC/MCContext.h"
+#include "llvm/MC/MCExpr.h"
+#include "llvm/MC/MCFixup.h"
+#include "llvm/MC/MCInst.h"
+#include "llvm/MC/MCInstrInfo.h"
+#include "llvm/MC/MCRegisterInfo.h"
+#include "llvm/MC/MCSubtargetInfo.h"
+#include "llvm/Support/raw_ostream.h"
+
+#define DEBUG_TYPE "mccodeemitter"
+
+#define GET_INSTRMAP_INFO
+#include "AVRGenInstrInfo.inc"
+#undef GET_INSTRMAP_INFO
+
+namespace llvm {
+
+/// Performs a post-encoding step on a `LD` or `ST` instruction.
+///
+/// The encoding of the LD/ST family of instructions is inconsistent w.r.t
+/// the pointer register and the addressing mode.
+///
+/// The permutations of the format are as followed:
+/// ld Rd, X    `1001 000d dddd 1100`
+/// ld Rd, X+   `1001 000d dddd 1101`
+/// ld Rd, -X   `1001 000d dddd 1110`
+///
+/// ld Rd, Y    `1000 000d dddd 1000`
+/// ld Rd, Y+   `1001 000d dddd 1001`
+/// ld Rd, -Y   `1001 000d dddd 1010`
+///
+/// ld Rd, Z    `1000 000d dddd 0000`
+/// ld Rd, Z+   `1001 000d dddd 0001`
+/// ld Rd, -Z   `1001 000d dddd 0010`
+///                 ^
+///                 |
+/// Note this one inconsistent bit - it is 1 sometimes and 0 at other times.
+/// There is no logical pattern. Looking at a truth table, the following
+/// formula can be derived to fit the pattern:
+//
+/// ```
+/// inconsistent_bit = is_predec OR is_postinc OR is_reg_x
+/// ```
+//
+/// We manually set this bit in this post encoder method.
+unsigned
+AVRMCCodeEmitter::loadStorePostEncoder(const MCInst &MI, unsigned EncodedValue,
+                                       const MCSubtargetInfo &STI) const {
+
+  assert(MI.getOperand(0).isReg() && MI.getOperand(1).isReg() &&
+         "the load/store operands must be registers");
+
+  unsigned Opcode = MI.getOpcode();
+
+  // check whether either of the registers are the X pointer register.
+  bool IsRegX = MI.getOperand(0).getReg() == AVR::R27R26 ||
+                  MI.getOperand(1).getReg() == AVR::R27R26;
+
+  bool IsPredec = Opcode == AVR::LDRdPtrPd || Opcode == AVR::STPtrPdRr;
+  bool IsPostinc = Opcode == AVR::LDRdPtrPi || Opcode == AVR::STPtrPiRr;
+
+  // Check if we need to set the inconsistent bit
+  if (IsRegX || IsPredec || IsPostinc) {
+    EncodedValue |= (1 << 12);
+  }
+
+  return EncodedValue;
+}
+
+template <AVR::Fixups Fixup>
+unsigned
+AVRMCCodeEmitter::encodeRelCondBrTarget(const MCInst &MI, unsigned OpNo,
+                                        SmallVectorImpl<MCFixup> &Fixups,
+                                        const MCSubtargetInfo &STI) const {
+  const MCOperand &MO = MI.getOperand(OpNo);
+
+  if (MO.isExpr()) {
+    Fixups.push_back(MCFixup::create(0, MO.getExpr(),
+                     MCFixupKind(Fixup), MI.getLoc()));
+    return 0;
+  }
+
+  assert(MO.isImm());
+
+  // Take the size of the current instruction away.
+  // With labels, this is implicitly done.
+  auto target = MO.getImm();
+  AVR::fixups::adjustBranchTarget(target);
+  return target;
+}
+
+unsigned AVRMCCodeEmitter::encodeLDSTPtrReg(const MCInst &MI, unsigned OpNo,
+                                            SmallVectorImpl<MCFixup> &Fixups,
+                                            const MCSubtargetInfo &STI) const {
+  auto MO = MI.getOperand(OpNo);
+
+  // The operand should be a pointer register.
+  assert(MO.isReg());
+
+  switch (MO.getReg()) {
+  case AVR::R27R26: return 0x03; // X: 0b11
+  case AVR::R29R28: return 0x02; // Y: 0b10
+  case AVR::R31R30: return 0x00; // Z: 0b00
+  default:
+    llvm_unreachable("invalid pointer register");
+  }
+}
+
+/// Encodes a `memri` operand.
+/// The operand is 7-bits.
+/// * The lower 6 bits is the immediate
+/// * The upper bit is the pointer register bit (Z=0,Y=1)
+unsigned AVRMCCodeEmitter::encodeMemri(const MCInst &MI, unsigned OpNo,
+                                       SmallVectorImpl<MCFixup> &Fixups,
+                                       const MCSubtargetInfo &STI) const {
+  auto RegOp = MI.getOperand(OpNo);
+  auto OffsetOp = MI.getOperand(OpNo + 1);
+
+  assert(RegOp.isReg() && "Expected register operand");
+
+  uint8_t RegBit = 0;
+
+  switch (RegOp.getReg()) {
+  default:
+    llvm_unreachable("Expected either Y or Z register");
+  case AVR::R31R30:
+    RegBit = 0;
+    break; // Z register
+  case AVR::R29R28:
+    RegBit = 1;
+    break; // Y register
+  }
+
+  int8_t OffsetBits;
+
+  if (OffsetOp.isImm()) {
+    OffsetBits = OffsetOp.getImm();
+  } else if (OffsetOp.isExpr()) {
+    OffsetBits = 0;
+    Fixups.push_back(MCFixup::create(0, OffsetOp.getExpr(), MCFixupKind(AVR::fixup_6), MI.getLoc()));
+  } else {
+    llvm_unreachable("invalid value for offset");
+  }
+
+  return (RegBit << 6) | OffsetBits;
+}
+
+unsigned AVRMCCodeEmitter::encodeComplement(const MCInst &MI, unsigned OpNo,
+                                            SmallVectorImpl<MCFixup> &Fixups,
+                                            const MCSubtargetInfo &STI) const {
+  // The operand should be an immediate.
+  assert(MI.getOperand(OpNo).isImm());
+
+  auto Imm = MI.getOperand(OpNo).getImm();
+  return (~0) - Imm;
+}
+
+template <AVR::Fixups Fixup>
+unsigned AVRMCCodeEmitter::encodeImm(const MCInst &MI, unsigned OpNo,
+                                     SmallVectorImpl<MCFixup> &Fixups,
+                                     const MCSubtargetInfo &STI) const {
+  auto MO = MI.getOperand(OpNo);
+
+  if (MO.isExpr()) {
+    if (isa<AVRMCExpr>(MO.getExpr())) {
+      // If the expression is already an AVRMCExpr (i.e. a lo8(symbol),
+      // we shouldn't perform any more fixups. Without this check, we would
+      // instead create a fixup to the symbol named 'lo8(symbol)' which
+      // is not correct.
+      return getExprOpValue(MO.getExpr(), Fixups, STI);
+    } else {
+      MCFixupKind FixupKind = static_cast<MCFixupKind>(Fixup);
+      Fixups.push_back(MCFixup::create(0, MO.getExpr(), FixupKind, MI.getLoc()));
+
+      return 0;
+    }
+  }
+
+  assert(MO.isImm());
+  return MO.getImm();
+}
+
+unsigned AVRMCCodeEmitter::encodeCallTarget(const MCInst &MI, unsigned OpNo,
+                                            SmallVectorImpl<MCFixup> &Fixups,
+                                            const MCSubtargetInfo &STI) const {
+  auto MO = MI.getOperand(OpNo);
+
+  if (MO.isExpr()) {
+    MCFixupKind FixupKind = static_cast<MCFixupKind>(AVR::fixup_call);
+    Fixups.push_back(MCFixup::create(0, MO.getExpr(), FixupKind, MI.getLoc()));
+    return 0;
+  }
+
+  assert(MO.isImm());
+
+  auto Target = MO.getImm();
+  AVR::fixups::adjustBranchTarget(Target);
+  return Target;
+}
+
+unsigned AVRMCCodeEmitter::getExprOpValue(const MCExpr *Expr,
+                                          SmallVectorImpl<MCFixup> &Fixups,
+                                          const MCSubtargetInfo &STI) const {
+
+  MCExpr::ExprKind Kind = Expr->getKind();
+
+  if (Kind == MCExpr::Binary) {
+    Expr = static_cast<const MCBinaryExpr *>(Expr)->getLHS();
+    Kind = Expr->getKind();
+  }
+
+  if (Kind == MCExpr::Target) {
+    AVRMCExpr const *AVRExpr = cast<AVRMCExpr>(Expr);
+    int64_t Result;
+    if (AVRExpr->evaluateAsConstant(Result)) {
+      return Result;
+    }
+
+    MCFixupKind FixupKind = static_cast<MCFixupKind>(AVRExpr->getFixupKind());
+    Fixups.push_back(MCFixup::create(0, AVRExpr, FixupKind));
+    return 0;
+  }
+
+  assert(Kind == MCExpr::SymbolRef);
+  return 0;
+}
+
+unsigned AVRMCCodeEmitter::getMachineOpValue(const MCInst &MI,
+                                             const MCOperand &MO,
+                                             SmallVectorImpl<MCFixup> &Fixups,
+                                             const MCSubtargetInfo &STI) const {
+  if (MO.isReg()) {
+    return Ctx.getRegisterInfo()->getEncodingValue(MO.getReg());
+  } else if (MO.isImm()) {
+    return static_cast<unsigned>(MO.getImm());
+  } else if (MO.isFPImm()) {
+    return static_cast<unsigned>(APFloat(MO.getFPImm())
+                                     .bitcastToAPInt()
+                                     .getHiBits(32)
+                                     .getLimitedValue());
+  }
+
+  // MO must be an Expr.
+  assert(MO.isExpr());
+
+  return getExprOpValue(MO.getExpr(), Fixups, STI);
+}
+
+void AVRMCCodeEmitter::emitInstruction(uint64_t Val, unsigned Size,
+                                       const MCSubtargetInfo &STI,
+                                       raw_ostream &OS) const {
+  const uint16_t *Words = reinterpret_cast<uint16_t const *>(&Val);
+  size_t WordCount = Size / 2;
+
+  for (int64_t i = WordCount - 1; i >= 0; --i) {
+    uint16_t Word = Words[i];
+
+    OS << (uint8_t) ((Word & 0x00ff) >> 0);
+    OS << (uint8_t) ((Word & 0xff00) >> 8);
+  }
+}
+
+void AVRMCCodeEmitter::encodeInstruction(const MCInst &MI, raw_ostream &OS,
+                                         SmallVectorImpl<MCFixup> &Fixups,
+                                         const MCSubtargetInfo &STI) const {
+  const MCInstrDesc &Desc = MCII.get(MI.getOpcode());
+
+  // Get byte count of instruction
+  unsigned Size = Desc.getSize();
+
+  assert(Size > 0 && "Instruction size cannot be zero");
+
+  uint64_t BinaryOpCode = getBinaryCodeForInstr(MI, Fixups, STI);
+  emitInstruction(BinaryOpCode, Size, STI, OS);
+}
+
+MCCodeEmitter *createAVRMCCodeEmitter(const MCInstrInfo &MCII,
+                                      const MCRegisterInfo &MRI,
+                                      MCContext &Ctx) {
+  return new AVRMCCodeEmitter(MCII, Ctx);
+}
+
+#include "AVRGenMCCodeEmitter.inc"
+
+} // end of namespace llvm

lib/Target/AVR/MCTargetDesc/AVRMCTargetDesc.cpp

extern "C" void LLVMInitializeAVRTargetMC() {
 
   // Register the MC subtarget info.
   TargetRegistry::RegisterMCSubtargetInfo(TheAVRTarget,
                                           createAVRMCSubtargetInfo);
 
   // Register the MCInstPrinter.
   TargetRegistry::RegisterMCInstPrinter(TheAVRTarget, createAVRMCInstPrinter);
 
+  // Register the MC Code Emitter
+  TargetRegistry::RegisterMCCodeEmitter(TheAVRTarget, createAVRMCCodeEmitter);
+
   // Register the ELF streamer
   TargetRegistry::RegisterELFStreamer(TheAVRTarget, createMCStreamer);
 
   // Register the obj target streamer.
   TargetRegistry::RegisterObjectTargetStreamer(TheAVRTarget,
                                                createAVRObjectTargetStreamer);
 
   // Register the asm target streamer.
   TargetRegistry::RegisterAsmTargetStreamer(TheAVRTarget,
                                             createMCAsmTargetStreamer);
 
   // Register the asm backend (as little endian).
   TargetRegistry::RegisterMCAsmBackend(TheAVRTarget, createAVRAsmBackend);
 }
 

lib/Target/AVR/MCTargetDesc/CMakeLists.txt

 add_llvm_library(LLVMAVRDesc
   AVRAsmBackend.cpp
   AVRELFObjectWriter.cpp
   AVRELFStreamer.cpp
   AVRMCAsmInfo.cpp
+  AVRMCCodeEmitter.cpp
   AVRMCExpr.cpp
   AVRMCTargetDesc.cpp
   AVRTargetStreamer.cpp
 )
 
 add_dependencies(LLVMAVRDesc AVRCommonTableGen)