[AMDGPU] Disassembler: print label names in branch instructions

[SamWot]

Summary

Add AMDGPUSymbolizer for finding names for labels from ELF symbol table.

[artem.tamazov]

Good, thanks.

[vpykhtin]

LGTM.

[SamWot]

Change was reverted due to bug found by buildbot.

[SamWot]

MCContext was trying to read uninitialized variable (MCObjectFileInfo *) in createSymbolImpl().
I fixed this by setting MCObjectFileInfo * to nullptr. In that case createSymbolImpl() does not try to read this variable and no problems occur.

[artem.tamazov]

OK for now.

[SamWot]

Initialize MCObjectFileInfo with some default values instead of nullptr.

[vpykhtin]

LGTM.

lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.h

 //
 //===----------------------------------------------------------------------===//
 
 #ifndef LLVM_LIB_TARGET_AMDGPU_DISASSEMBLER_AMDGPUDISASSEMBLER_H
 #define LLVM_LIB_TARGET_AMDGPU_DISASSEMBLER_AMDGPUDISASSEMBLER_H
 
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/MC/MCDisassembler/MCDisassembler.h"
+#include "llvm/MC/MCDisassembler/MCSymbolizer.h"
 
 namespace llvm {
 
-  class MCContext;
-  class MCInst;
-  class MCOperand;
-  class MCSubtargetInfo;
-  class Twine;
 
-  class AMDGPUDisassembler : public MCDisassembler {
-  private:
-    mutable ArrayRef<uint8_t> Bytes;
+//===----------------------------------------------------------------------===//
+// AMDGPUDisassembler
+//===----------------------------------------------------------------------===//
+
 
-  public:
-    AMDGPUDisassembler(const MCSubtargetInfo &STI, MCContext &Ctx) :
-      MCDisassembler(STI, Ctx) {}
 
-    ~AMDGPUDisassembler() {}
 
-    DecodeStatus getInstruction(MCInst &MI, uint64_t &Size,
-                                ArrayRef<uint8_t> Bytes, uint64_t Address,
-                                raw_ostream &WS, raw_ostream &CS) const override;
 
-    const char* getRegClassName(unsigned RegClassID) const;
 
-    MCOperand createRegOperand(unsigned int RegId) const;
-    MCOperand createRegOperand(unsigned RegClassID, unsigned Val) const;
-    MCOperand createSRegOperand(unsigned SRegClassID, unsigned Val) const;
 
-    MCOperand errOperand(unsigned V, const llvm::Twine& ErrMsg) const;
 
-    DecodeStatus tryDecodeInst(const uint8_t* Table,
-                               MCInst &MI,
-                               uint64_t Inst,
-                               uint64_t Address) const;
 
-    MCOperand decodeOperand_VGPR_32(unsigned Val) const;
-    MCOperand decodeOperand_VS_32(unsigned Val) const;
-    MCOperand decodeOperand_VS_64(unsigned Val) const;
 
-    MCOperand decodeOperand_VReg_64(unsigned Val) const;
-    MCOperand decodeOperand_VReg_96(unsigned Val) const;
-    MCOperand decodeOperand_VReg_128(unsigned Val) const;
 
-    MCOperand decodeOperand_SReg_32(unsigned Val) const;
-    MCOperand decodeOperand_SReg_32_XM0(unsigned Val) const;
-    MCOperand decodeOperand_SReg_64(unsigned Val) const;
-    MCOperand decodeOperand_SReg_128(unsigned Val) const;
-    MCOperand decodeOperand_SReg_256(unsigned Val) const;
-    MCOperand decodeOperand_SReg_512(unsigned Val) const;
 
-    enum OpWidthTy {
-      OPW32,
-      OPW64,
-      OPW128,
-      OPW_LAST_,
-      OPW_FIRST_ = OPW32
-    };
-    unsigned getVgprClassId(const OpWidthTy Width) const;
-    unsigned getSgprClassId(const OpWidthTy Width) const;
-    unsigned getTtmpClassId(const OpWidthTy Width) const;
 
-    static MCOperand decodeIntImmed(unsigned Imm);
-    static MCOperand decodeFPImmed(bool Is32, unsigned Imm);
-    MCOperand decodeLiteralConstant() const;
 
-    MCOperand decodeSrcOp(const OpWidthTy Width, unsigned Val) const;
-    MCOperand decodeSpecialReg32(unsigned Val) const;
-    MCOperand decodeSpecialReg64(unsigned Val) const;
-  };
+
+//===----------------------------------------------------------------------===//
+// AMDGPUSymbolizer
+//===----------------------------------------------------------------------===//
+
+class AMDGPUSymbolizer : public MCSymbolizer {
+private:
+  void *DisInfo;
+
+public:
+  AMDGPUSymbolizer(MCContext &Ctx, std::unique_ptr<MCRelocationInfo> &&RelInfo,
+                   void *disInfo) 
+                   : MCSymbolizer(Ctx, std::move(RelInfo)), DisInfo(disInfo) {}
+
+  bool tryAddingSymbolicOperand(MCInst &Inst, raw_ostream &cStream,
+                                int64_t Value, uint64_t Address,
+                                bool IsBranch, uint64_t Offset,
+                                uint64_t InstSize) override;
+
+  void tryAddingPcLoadReferenceComment(raw_ostream &cStream,
+                                       int64_t Value,
+                                       uint64_t Address) override {
+    assert(false && "Implement if needed");
+  }
+};
+
 } // namespace llvm
 
 #endif //LLVM_LIB_TARGET_AMDGPU_DISASSEMBLER_AMDGPUDISASSEMBLER_H

lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.cpp

 #include "SIDefines.h"
 #include "Utils/AMDGPUBaseInfo.h"
 
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCFixedLenDisassembler.h"
 #include "llvm/MC/MCInst.h"
 #include "llvm/MC/MCInstrDesc.h"
 #include "llvm/MC/MCSubtargetInfo.h"
+#include "llvm/Support/ELF.h"
 #include "llvm/Support/Endian.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/TargetRegistry.h"
 
 
 using namespace llvm;
 
 #define DEBUG_TYPE "amdgpu-disassembler"
 
 typedef llvm::MCDisassembler::DecodeStatus DecodeStatus;
 
 
 inline static MCDisassembler::DecodeStatus
 addOperand(MCInst &Inst, const MCOperand& Opnd) {
   Inst.addOperand(Opnd);
   return Opnd.isValid() ?
     MCDisassembler::Success :
     MCDisassembler::SoftFail;
 }
 
+static DecodeStatus decodeSoppBrTarget(MCInst &Inst, unsigned Imm,
+                                       uint64_t Addr, const void *Decoder) {
+  auto DAsm = static_cast<const AMDGPUDisassembler*>(Decoder);
+
+  APInt SignedOffset(18, Imm * 4, true);
+  int64_t Offset = (SignedOffset.sext(64) + 4 + Addr).getSExtValue();
+
+  if (DAsm->tryAddingSymbolicOperand(Inst, Offset, Addr, true, 2, 2))
+    return MCDisassembler::Success;
+  return addOperand(Inst, MCOperand::createImm(Imm)); 
+}
+
 #define DECODE_OPERAND2(RegClass, DecName) \
 static DecodeStatus Decode##RegClass##RegisterClass(MCInst &Inst, \
                                                     unsigned Imm, \
                                                     uint64_t /*Addr*/, \
                                                     const void *Decoder) { \
   auto DAsm = static_cast<const AMDGPUDisassembler*>(Decoder); \
   return addOperand(Inst, DAsm->decodeOperand_##DecName(Imm)); \
 }
MCOperand AMDGPUDisassembler::decodeSpecialReg64(unsigned Val) const {
   case 108: return createRegOperand(TBA);
   case 110: return createRegOperand(TMA);
   case 126: return createRegOperand(EXEC);
   default: break;
   }
   return errOperand(Val, "unknown operand encoding " + Twine(Val));
 }
 
+//===----------------------------------------------------------------------===//
+// AMDGPUSymbolizer
+//===----------------------------------------------------------------------===//
+  
+// Try to find symbol name for specified label
+bool AMDGPUSymbolizer::tryAddingSymbolicOperand(MCInst &Inst,
+                                raw_ostream &/*cStream*/, int64_t Value,
+                                uint64_t /*Address*/, bool IsBranch,
+                                uint64_t /*Offset*/, uint64_t /*InstSize*/) {
+  typedef std::tuple<uint64_t, StringRef, uint8_t> SymbolInfoTy;
+  typedef std::vector<SymbolInfoTy> SectionSymbolsTy;
+
+  if (!IsBranch) {
+    return false;
+  }
+
+  auto *Symbols = static_cast<SectionSymbolsTy *>(DisInfo);
+  auto Result = std::find_if(Symbols->begin(), Symbols->end(),
+                             [Value](const SymbolInfoTy& Val) {
+                                return std::get<0>(Val) == static_cast<uint64_t>(Value)
+                                    && std::get<2>(Val) == ELF::STT_NOTYPE;
+                             });
+  if (Result != Symbols->end()) {
+    auto *Sym = Ctx.getOrCreateSymbol(std::get<1>(*Result));
+    const auto *Add = MCSymbolRefExpr::create(Sym, Ctx);
+    Inst.addOperand(MCOperand::createExpr(Add));
+    return true;
+  }
+  return false;
+}
+
+//===----------------------------------------------------------------------===//
+// Initialization
+//===----------------------------------------------------------------------===//
+
+static MCSymbolizer *createAMDGPUSymbolizer(const Triple &/*TT*/,
+                              LLVMOpInfoCallback /*GetOpInfo*/,
+                              LLVMSymbolLookupCallback /*SymbolLookUp*/,
+                              void *DisInfo, 
+                              MCContext *Ctx,
+                              std::unique_ptr<MCRelocationInfo> &&RelInfo) {
+  return new AMDGPUSymbolizer(*Ctx, std::move(RelInfo), DisInfo);
+}
+
 static MCDisassembler *createAMDGPUDisassembler(const Target &T,
                                                 const MCSubtargetInfo &STI,
                                                 MCContext &Ctx) {
   return new AMDGPUDisassembler(STI, Ctx);
 }
 
 extern "C" void LLVMInitializeAMDGPUDisassembler() {
   TargetRegistry::RegisterMCDisassembler(TheGCNTarget, createAMDGPUDisassembler);
+  TargetRegistry::RegisterMCSymbolizer(TheGCNTarget, createAMDGPUSymbolizer);
 }

lib/Target/AMDGPU/SIInstrInfo.td

 
 def SoppBrTarget : AsmOperandClass {
   let Name = "SoppBrTarget";
   let ParserMethod = "parseSOppBrTarget";
 }
 
 def sopp_brtarget : Operand<OtherVT> {
   let EncoderMethod = "getSOPPBrEncoding";
+  let DecoderMethod = "decodeSoppBrTarget";
   let OperandType = "OPERAND_PCREL";
   let ParserMatchClass = SoppBrTarget;
 }
 
 def si_ga : Operand<iPTR>;
 
 def InterpSlot : Operand<i32> {
   let PrintMethod = "printInterpSlot";

test/MC/AMDGPU/labels-branch.s

 // RUN: llvm-mc -arch=amdgcn -mcpu=fiji -show-encoding %s | FileCheck %s --check-prefix=VI
 // RUN: llvm-mc -arch=amdgcn -mcpu=fiji -filetype=obj %s | llvm-objdump -disassemble -mcpu=fiji - | FileCheck %s --check-prefix=BIN
 
 loop_start:
 s_branch loop_start
 // VI: s_branch loop_start ; encoding: [A,A,0x82,0xbf]
 // VI-NEXT: ;   fixup A - offset: 0, value: loop_start, kind: fixup_si_sopp_br
 // BIN: loop_start:
-// BIN-NEXT: BF82FFFF
+// BIN-NEXT: s_branch loop_start // 000000000000: BF82FFFF
 
 s_branch loop_end
 // VI: s_branch loop_end ; encoding: [A,A,0x82,0xbf]
 // VI-NEXT: ;   fixup A - offset: 0, value: loop_end, kind: fixup_si_sopp_br
-// BIN: BF820000
+// BIN: s_branch loop_end // 000000000004: BF820000
 // BIN: loop_end:
 loop_end:
 
 s_branch gds
 // VI: s_branch gds ; encoding: [A,A,0x82,0xbf]
 // VI-NEXT: ;   fixup A - offset: 0, value: gds, kind: fixup_si_sopp_br
-// BIN: BF820000
+// BIN: s_branch gds // 000000000008: BF820000
 // BIN: gds:
 gds:
   s_nop 0

tools/llvm-objdump/llvm-objdump.cpp

if (!AsmInfo)
     report_fatal_error("error: no assembly info for target " + TripleName);
   std::unique_ptr<const MCSubtargetInfo> STI(
       TheTarget->createMCSubtargetInfo(TripleName, MCPU, Features.getString()));
   if (!STI)
     report_fatal_error("error: no subtarget info for target " + TripleName);
   std::unique_ptr<const MCInstrInfo> MII(TheTarget->createMCInstrInfo());
   if (!MII)
     report_fatal_error("error: no instruction info for target " + TripleName);
-  std::unique_ptr<const MCObjectFileInfo> MOFI(new MCObjectFileInfo);
-  MCContext Ctx(AsmInfo.get(), MRI.get(), MOFI.get());
+  MCContext Ctx(AsmInfo.get(), MRI.get(), nullptr);
 
   std::unique_ptr<MCDisassembler> DisAsm(
     TheTarget->createMCDisassembler(*STI, Ctx));
   if (!DisAsm)
     report_fatal_error("error: no disassembler for target " + TripleName);
 
   std::unique_ptr<const MCInstrAnalysis> MIA(
       TheTarget->createMCInstrAnalysis(MII.get()));
if (isArmElf(Obj)) {
         if (Name.startswith("$t"))
           TextMappingSymsAddr.push_back(Address - SectionAddr);
       }
     }
 
     std::sort(DataMappingSymsAddr.begin(), DataMappingSymsAddr.end());
     std::sort(TextMappingSymsAddr.begin(), TextMappingSymsAddr.end());
 
+    if (Obj->isELF() && Obj->getArch() == Triple::amdgcn) {
+      // AMDGPU disassembler uses symbolizer for printing labels
+      std::unique_ptr<MCRelocationInfo> RelInfo(
+        TheTarget->createMCRelocationInfo(TripleName, Ctx));
+      if (RelInfo) {
+        std::unique_ptr<MCSymbolizer> Symbolizer(
+          TheTarget->createMCSymbolizer(
+            TripleName, nullptr, nullptr, &Symbols, &Ctx, std::move(RelInfo)));
+        DisAsm->setSymbolizer(std::move(Symbolizer));
+      }
+    }
+
     // Make a list of all the relocations for this section.
     std::vector<RelocationRef> Rels;
     if (InlineRelocs) {
       for (const SectionRef &RelocSec : SectionRelocMap[Section]) {
         for (const RelocationRef &Reloc : RelocSec.relocations()) {
           Rels.push_back(Reloc);
         }
       }