Add a disassembler to the PowerPC backend

The tests for the disassembler were adapted from the encoder tests, and for the
most part, the output from the disassembler matches that encoder-test inputs.
There are some places where more-informative mnemonics could be produced
(notably for the branch instructions), and those cases are noted in the tests
with FIXMEs.

Future work includes:

 - Generating more-informative mnemonics when possible (this may also be done
   in the printer).

 - Remove the dependence on positional "numbered" operand-to-variable mapping
   (for both encoding and decoding).

 - Internally using 64-bit instruction variants in 64-bit mode (if this turns
   out to matter).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@197693 91177308-0d34-0410-b5e6-96231b3b80d8

4 files changed, 335 insertions, 0 deletions

diff --git a/lib/Target/PowerPC/Disassembler/CMakeLists.txt b/lib/Target/PowerPC/Disassembler/CMakeLists.txt
new file mode 100644
index 0000000000..ca457df88d
--- /dev/null
+++ b/lib/Target/PowerPC/Disassembler/CMakeLists.txt
@@ -0,0 +1,3 @@
+add_llvm_library(LLVMPowerPCDisassembler
+  PPCDisassembler.cpp
+  )
diff --git a/lib/Target/PowerPC/Disassembler/LLVMBuild.txt b/lib/Target/PowerPC/Disassembler/LLVMBuild.txt
new file mode 100644
index 0000000000..7f29040eb6
--- /dev/null
+++ b/lib/Target/PowerPC/Disassembler/LLVMBuild.txt
@@ -0,0 +1,23 @@
+;===-- ./lib/Target/PowerPC/Disassembler/LLVMBuild.txt ---------*- Conf -*--===;
+;
+;                     The LLVM Compiler Infrastructure
+;
+; This file is distributed under the University of Illinois Open Source
+; License. See LICENSE.TXT for details.
+;
+;===------------------------------------------------------------------------===;
+;
+; This is an LLVMBuild description file for the components in this subdirectory.
+;
+; For more information on the LLVMBuild system, please see:
+;
+;   http://llvm.org/docs/LLVMBuild.html
+;
+;===------------------------------------------------------------------------===;
+
+[component_0]
+type = Library
+name = PowerPCDisassembler
+parent = PowerPC
+required_libraries = MC Support PowerPCDesc PowerPCInfo
+add_to_library_groups = PowerPC
diff --git a/lib/Target/PowerPC/Disassembler/Makefile b/lib/Target/PowerPC/Disassembler/Makefile
new file mode 100644
index 0000000000..86e3b47522
--- /dev/null
+++ b/lib/Target/PowerPC/Disassembler/Makefile
@@ -0,0 +1,16 @@
+##===-- lib/Target/PowerPC/Disassembler/Makefile -----------*- Makefile -*-===##
+#
+#                     The LLVM Compiler Infrastructure
+#
+# This file is distributed under the University of Illinois Open Source
+# License. See LICENSE.TXT for details.
+#
+##===----------------------------------------------------------------------===##
+
+LEVEL = ../../../..
+LIBRARYNAME = LLVMPowerPCDisassembler
+
+# Hack: we need to include 'main' PPC target directory to grab private headers
+CPP.Flags += -I$(PROJ_OBJ_DIR)/.. -I$(PROJ_SRC_DIR)/..
+
+include $(LEVEL)/Makefile.common
diff --git a/lib/Target/PowerPC/Disassembler/PPCDisassembler.cpp b/lib/Target/PowerPC/Disassembler/PPCDisassembler.cpp
new file mode 100644
index 0000000000..1dab14b2ca
--- /dev/null
+++ b/lib/Target/PowerPC/Disassembler/PPCDisassembler.cpp
@@ -0,0 +1,293 @@
+//===------ PPCDisassembler.cpp - Disassembler for PowerPC ------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "PPC.h"
+#include "llvm/MC/MCDisassembler.h"
+#include "llvm/MC/MCFixedLenDisassembler.h"
+#include "llvm/MC/MCInst.h"
+#include "llvm/MC/MCSubtargetInfo.h"
+#include "llvm/Support/MemoryObject.h"
+#include "llvm/Support/TargetRegistry.h"
+
+using namespace llvm;
+
+typedef MCDisassembler::DecodeStatus DecodeStatus;
+
+namespace {
+class PPCDisassembler : public MCDisassembler {
+public:
+  PPCDisassembler(const MCSubtargetInfo &STI)
+    : MCDisassembler(STI) {}
+  virtual ~PPCDisassembler() {}
+
+  // Override MCDisassembler.
+  virtual DecodeStatus getInstruction(MCInst &instr,
+                                      uint64_t &size,
+                                      const MemoryObject &region,
+                                      uint64_t address,
+                                      raw_ostream &vStream,
+                                      raw_ostream &cStream) const LLVM_OVERRIDE;
+};
+} // end anonymous namespace
+
+static MCDisassembler *createPPCDisassembler(const Target &T,
+                                             const MCSubtargetInfo &STI) {
+  return new PPCDisassembler(STI);
+}
+
+extern "C" void LLVMInitializePowerPCDisassembler() {
+  // Register the disassembler for each target.
+  TargetRegistry::RegisterMCDisassembler(ThePPC32Target,
+                                         createPPCDisassembler);
+  TargetRegistry::RegisterMCDisassembler(ThePPC64Target,
+                                         createPPCDisassembler);
+  TargetRegistry::RegisterMCDisassembler(ThePPC64LETarget,
+                                         createPPCDisassembler);
+}
+
+// FIXME: These can be generated by TableGen from the existing register
+// encoding values!
+
+static const unsigned CRRegs[] = {
+  PPC::CR0, PPC::CR1, PPC::CR2, PPC::CR3,
+  PPC::CR4, PPC::CR5, PPC::CR6, PPC::CR7
+};
+
+static const unsigned CRBITRegs[] = {
+  PPC::CR0LT, PPC::CR0GT, PPC::CR0EQ, PPC::CR0UN,
+  PPC::CR1LT, PPC::CR1GT, PPC::CR1EQ, PPC::CR1UN,
+  PPC::CR2LT, PPC::CR2GT, PPC::CR2EQ, PPC::CR2UN,
+  PPC::CR3LT, PPC::CR3GT, PPC::CR3EQ, PPC::CR3UN,
+  PPC::CR4LT, PPC::CR4GT, PPC::CR4EQ, PPC::CR4UN,
+  PPC::CR5LT, PPC::CR5GT, PPC::CR5EQ, PPC::CR5UN,
+  PPC::CR6LT, PPC::CR6GT, PPC::CR6EQ, PPC::CR6UN,
+  PPC::CR7LT, PPC::CR7GT, PPC::CR7EQ, PPC::CR7UN
+};
+
+static const unsigned FRegs[] = {
+  PPC::F0, PPC::F1, PPC::F2, PPC::F3,
+  PPC::F4, PPC::F5, PPC::F6, PPC::F7,
+  PPC::F8, PPC::F9, PPC::F10, PPC::F11,
+  PPC::F12, PPC::F13, PPC::F14, PPC::F15,
+  PPC::F16, PPC::F17, PPC::F18, PPC::F19,
+  PPC::F20, PPC::F21, PPC::F22, PPC::F23,
+  PPC::F24, PPC::F25, PPC::F26, PPC::F27,
+  PPC::F28, PPC::F29, PPC::F30, PPC::F31
+};
+
+static const unsigned VRegs[] = {
+  PPC::V0, PPC::V1, PPC::V2, PPC::V3,
+  PPC::V4, PPC::V5, PPC::V6, PPC::V7,
+  PPC::V8, PPC::V9, PPC::V10, PPC::V11,
+  PPC::V12, PPC::V13, PPC::V14, PPC::V15,
+  PPC::V16, PPC::V17, PPC::V18, PPC::V19,
+  PPC::V20, PPC::V21, PPC::V22, PPC::V23,
+  PPC::V24, PPC::V25, PPC::V26, PPC::V27,
+  PPC::V28, PPC::V29, PPC::V30, PPC::V31
+};
+
+static const unsigned GPRegs[] = {
+  PPC::R0, PPC::R1, PPC::R2, PPC::R3,
+  PPC::R4, PPC::R5, PPC::R6, PPC::R7,
+  PPC::R8, PPC::R9, PPC::R10, PPC::R11,
+  PPC::R12, PPC::R13, PPC::R14, PPC::R15,
+  PPC::R16, PPC::R17, PPC::R18, PPC::R19,
+  PPC::R20, PPC::R21, PPC::R22, PPC::R23,
+  PPC::R24, PPC::R25, PPC::R26, PPC::R27,
+  PPC::R28, PPC::R29, PPC::R30, PPC::R31
+};
+
+static const unsigned GP0Regs[] = {
+  PPC::ZERO, PPC::R1, PPC::R2, PPC::R3,
+  PPC::R4, PPC::R5, PPC::R6, PPC::R7,
+  PPC::R8, PPC::R9, PPC::R10, PPC::R11,
+  PPC::R12, PPC::R13, PPC::R14, PPC::R15,
+  PPC::R16, PPC::R17, PPC::R18, PPC::R19,
+  PPC::R20, PPC::R21, PPC::R22, PPC::R23,
+  PPC::R24, PPC::R25, PPC::R26, PPC::R27,
+  PPC::R28, PPC::R29, PPC::R30, PPC::R31
+};
+
+static const unsigned G8Regs[] = {
+  PPC::X0, PPC::X1, PPC::X2, PPC::X3,
+  PPC::X4, PPC::X5, PPC::X6, PPC::X7,
+  PPC::X8, PPC::X9, PPC::X10, PPC::X11,
+  PPC::X12, PPC::X13, PPC::X14, PPC::X15,
+  PPC::X16, PPC::X17, PPC::X18, PPC::X19,
+  PPC::X20, PPC::X21, PPC::X22, PPC::X23,
+  PPC::X24, PPC::X25, PPC::X26, PPC::X27,
+  PPC::X28, PPC::X29, PPC::X30, PPC::X31
+};
+
+template <std::size_t N>
+static DecodeStatus decodeRegisterClass(MCInst &Inst, uint64_t RegNo,
+                                        const unsigned (&Regs)[N]) {
+  assert(RegNo < N && "Invalid register number");
+  Inst.addOperand(MCOperand::CreateReg(Regs[RegNo]));
+  return MCDisassembler::Success;
+}
+
+static DecodeStatus DecodeCRRCRegisterClass(MCInst &Inst, uint64_t RegNo,
+                                            uint64_t Address,
+                                            const void *Decoder) {
+  return decodeRegisterClass(Inst, RegNo, CRRegs);
+}
+
+static DecodeStatus DecodeCRBITRCRegisterClass(MCInst &Inst, uint64_t RegNo,
+                                            uint64_t Address,
+                                            const void *Decoder) {
+  return decodeRegisterClass(Inst, RegNo, CRBITRegs);
+}
+
+static DecodeStatus DecodeF4RCRegisterClass(MCInst &Inst, uint64_t RegNo,
+                                            uint64_t Address,
+                                            const void *Decoder) {
+  return decodeRegisterClass(Inst, RegNo, FRegs);
+}
+
+static DecodeStatus DecodeF8RCRegisterClass(MCInst &Inst, uint64_t RegNo,
+                                            uint64_t Address,
+                                            const void *Decoder) {
+  return decodeRegisterClass(Inst, RegNo, FRegs);
+}
+
+static DecodeStatus DecodeVRRCRegisterClass(MCInst &Inst, uint64_t RegNo,
+                                            uint64_t Address,
+                                            const void *Decoder) {
+  return decodeRegisterClass(Inst, RegNo, VRegs);
+}
+
+static DecodeStatus DecodeGPRCRegisterClass(MCInst &Inst, uint64_t RegNo,
+                                            uint64_t Address,
+                                            const void *Decoder) {
+  return decodeRegisterClass(Inst, RegNo, GPRegs);
+}
+
+static DecodeStatus DecodeGPRC_NOR0RegisterClass(MCInst &Inst, uint64_t RegNo,
+                                            uint64_t Address,
+                                            const void *Decoder) {
+  return decodeRegisterClass(Inst, RegNo, GP0Regs);
+}
+
+static DecodeStatus DecodeG8RCRegisterClass(MCInst &Inst, uint64_t RegNo,
+                                            uint64_t Address,
+                                            const void *Decoder) {
+  return decodeRegisterClass(Inst, RegNo, G8Regs);
+}
+
+#define DecodePointerLikeRegClass0 DecodeGPRCRegisterClass
+#define DecodePointerLikeRegClass1 DecodeGPRC_NOR0RegisterClass
+
+template<unsigned N>
+static DecodeStatus decodeUImmOperand(MCInst &Inst, uint64_t Imm,
+                                      int64_t Address, const void *Decoder) {
+  assert(isUInt<N>(Imm) && "Invalid immediate");
+  Inst.addOperand(MCOperand::CreateImm(Imm));
+  return MCDisassembler::Success;
+}
+
+template<unsigned N>
+static DecodeStatus decodeSImmOperand(MCInst &Inst, uint64_t Imm,
+                                      int64_t Address, const void *Decoder) {
+  assert(isUInt<N>(Imm) && "Invalid immediate");
+  Inst.addOperand(MCOperand::CreateImm(SignExtend64<N>(Imm)));
+  return MCDisassembler::Success;
+}
+
+static DecodeStatus decodeMemRIOperands(MCInst &Inst, uint64_t Imm,
+                                        int64_t Address, const void *Decoder) {
+  // Decode the memri field (imm, reg), which has the low 16-bits as the
+  // displacement and the next 5 bits as the register #.
+
+  uint64_t Base = Imm >> 16;
+  uint64_t Disp = Imm & 0xFFFF;
+
+  assert(Base < 32 && "Invalid base register");
+
+  switch (Inst.getOpcode()) {
+  default: break;
+  case PPC::LBZU:
+  case PPC::LHAU:
+  case PPC::LHZU:
+  case PPC::LWZU:
+  case PPC::LFSU:
+  case PPC::LFDU:
+    // Add the tied output operand.
+    Inst.addOperand(MCOperand::CreateReg(GP0Regs[Base]));
+    break;
+  case PPC::STBU:
+  case PPC::STHU:
+  case PPC::STWU:
+  case PPC::STFSU:
+  case PPC::STFDU:
+    Inst.insert(Inst.begin(), MCOperand::CreateReg(GP0Regs[Base]));
+    break;
+  }
+
+  Inst.addOperand(MCOperand::CreateImm(SignExtend64<16>(Disp)));
+  Inst.addOperand(MCOperand::CreateReg(GP0Regs[Base]));
+  return MCDisassembler::Success;
+}
+
+static DecodeStatus decodeMemRIXOperands(MCInst &Inst, uint64_t Imm,
+                                         int64_t Address, const void *Decoder) {
+  // Decode the memrix field (imm, reg), which has the low 14-bits as the
+  // displacement and the next 5 bits as the register #.
+
+  uint64_t Base = Imm >> 14;
+  uint64_t Disp = Imm & 0x3FFF;
+
+  assert(Base < 32 && "Invalid base register");
+
+  if (Inst.getOpcode() == PPC::LDU)
+    // Add the tied output operand.
+    Inst.addOperand(MCOperand::CreateReg(GP0Regs[Base]));
+  else if (Inst.getOpcode() == PPC::STDU)
+    Inst.insert(Inst.begin(), MCOperand::CreateReg(GP0Regs[Base]));
+
+  Inst.addOperand(MCOperand::CreateImm(SignExtend64<16>(Disp << 2)));
+  Inst.addOperand(MCOperand::CreateReg(GP0Regs[Base]));
+  return MCDisassembler::Success;
+}
+
+static DecodeStatus decodeCRBitMOperand(MCInst &Inst, uint64_t Imm,
+                                        int64_t Address, const void *Decoder) {
+  // The cr bit encoding is 0x80 >> cr_reg_num.
+
+  unsigned Zeros = countTrailingZeros(Imm);
+  assert(Zeros < 8 && "Invalid CR bit value");
+
+  Inst.addOperand(MCOperand::CreateReg(CRRegs[7 - Zeros]));
+  return MCDisassembler::Success;
+}
+
+#include "PPCGenDisassemblerTables.inc"
+
+DecodeStatus PPCDisassembler::getInstruction(MCInst &MI, uint64_t &Size,
+                                                 const MemoryObject &Region,
+                                                 uint64_t Address,
+                                                 raw_ostream &os,
+                                                 raw_ostream &cs) const {
+  // Get the four bytes of the instruction.
+  uint8_t Bytes[4];
+  Size = 4;
+  if (Region.readBytes(Address, Size, Bytes) == -1) {
+    Size = 0;
+    return MCDisassembler::Fail;
+  }
+
+  // The instruction is big-endian encoded.
+  uint32_t Inst = (Bytes[0] << 24) |
+                  (Bytes[1] << 16) |
+                  (Bytes[2] <<  8) |
+                  (Bytes[3] <<  0);
+
+  return decodeInstruction(DecoderTable32, MI, Inst, Address, this, STI);
+}
+