diff options
author | dim <dim@FreeBSD.org> | 2012-02-05 23:56:22 +0000 |
---|---|---|
committer | dim <dim@FreeBSD.org> | 2012-02-05 23:56:22 +0000 |
commit | eb8951e7f7015d193e6640deb0ebde32f01b72d8 (patch) | |
tree | 8052b8010f619e8d40e5e3b37482591f537e0ca0 /contrib/llvm/tools/llvm-objdump | |
parent | 4de4d315e465f872a81f448b1788cc017f2d2033 (diff) | |
parent | 07637c87f826cdf411f0673595e9bc92ebd793f2 (diff) | |
download | FreeBSD-src-eb8951e7f7015d193e6640deb0ebde32f01b72d8.zip FreeBSD-src-eb8951e7f7015d193e6640deb0ebde32f01b72d8.tar.gz |
Add a WITH_CLANG_EXTRAS option for src.conf(5), disabled by default,
that builds the following additional llvm/clang tools:
- bugpoint
- llc
- lli
- llvm-ar
- llvm-as
- llvm-bcanalyzer
- llvm-diff
- llvm-dis
- llvm-extract
- llvm-ld
- llvm-link
- llvm-mc
- llvm-nm
- llvm-objdump
- llvm-prof
- llvm-ranlib
- llvm-rtdyld
- llvm-stub
- macho-dump
- opt
These tools are mainly useful for people that want to manipulate llvm
bitcode (.bc) and llvm assembly language (.ll) files, or want to tinker
with llvm and clang themselves.
MFC after: 2 weeks
Diffstat (limited to 'contrib/llvm/tools/llvm-objdump')
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/CMakeLists.txt | 14 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/MCFunction.cpp | 138 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/MCFunction.h | 100 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/MachODump.cpp | 617 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/Makefile | 18 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp | 459 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/llvm-objdump.h | 46 |
7 files changed, 1392 insertions, 0 deletions
diff --git a/contrib/llvm/tools/llvm-objdump/CMakeLists.txt b/contrib/llvm/tools/llvm-objdump/CMakeLists.txt new file mode 100644 index 0000000..f3b2e1f --- /dev/null +++ b/contrib/llvm/tools/llvm-objdump/CMakeLists.txt @@ -0,0 +1,14 @@ +set(LLVM_LINK_COMPONENTS + ${LLVM_TARGETS_TO_BUILD} + DebugInfo + MC + MCParser + MCDisassembler + Object + ) + +add_llvm_tool(llvm-objdump + llvm-objdump.cpp + MachODump.cpp + MCFunction.cpp + ) diff --git a/contrib/llvm/tools/llvm-objdump/MCFunction.cpp b/contrib/llvm/tools/llvm-objdump/MCFunction.cpp new file mode 100644 index 0000000..5c67f1b --- /dev/null +++ b/contrib/llvm/tools/llvm-objdump/MCFunction.cpp @@ -0,0 +1,138 @@ +//===-- MCFunction.cpp ----------------------------------------------------===// +// +// 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 algorithm to break down a region of machine code +// into basic blocks and try to reconstruct a CFG from it. +// +//===----------------------------------------------------------------------===// + +#include "MCFunction.h" +#include "llvm/ADT/STLExtras.h" +#include "llvm/MC/MCDisassembler.h" +#include "llvm/MC/MCInst.h" +#include "llvm/MC/MCInstPrinter.h" +#include "llvm/MC/MCInstrAnalysis.h" +#include "llvm/MC/MCInstrDesc.h" +#include "llvm/MC/MCInstrInfo.h" +#include "llvm/Support/MemoryObject.h" +#include "llvm/Support/raw_ostream.h" +#include "llvm/Support/system_error.h" +#include <set> +using namespace llvm; + +MCFunction +MCFunction::createFunctionFromMC(StringRef Name, const MCDisassembler *DisAsm, + const MemoryObject &Region, uint64_t Start, + uint64_t End, const MCInstrAnalysis *Ana, + raw_ostream &DebugOut, + SmallVectorImpl<uint64_t> &Calls) { + std::vector<MCDecodedInst> Instructions; + std::set<uint64_t> Splits; + Splits.insert(Start); + uint64_t Size; + + MCFunction f(Name); + + { + DenseSet<uint64_t> VisitedInsts; + SmallVector<uint64_t, 16> WorkList; + WorkList.push_back(Start); + // Disassemble code and gather basic block split points. + while (!WorkList.empty()) { + uint64_t Index = WorkList.pop_back_val(); + if (VisitedInsts.find(Index) != VisitedInsts.end()) + continue; // Already visited this location. + + for (;Index < End; Index += Size) { + VisitedInsts.insert(Index); + + MCInst Inst; + if (DisAsm->getInstruction(Inst, Size, Region, Index, DebugOut, nulls())){ + Instructions.push_back(MCDecodedInst(Index, Size, Inst)); + if (Ana->isBranch(Inst)) { + uint64_t targ = Ana->evaluateBranch(Inst, Index, Size); + if (targ != -1ULL && targ == Index+Size) + continue; // Skip nop jumps. + + // If we could determine the branch target, make a note to start a + // new basic block there and add the target to the worklist. + if (targ != -1ULL) { + Splits.insert(targ); + WorkList.push_back(targ); + WorkList.push_back(Index+Size); + } + Splits.insert(Index+Size); + break; + } else if (Ana->isReturn(Inst)) { + // Return instruction. This basic block ends here. + Splits.insert(Index+Size); + break; + } else if (Ana->isCall(Inst)) { + uint64_t targ = Ana->evaluateBranch(Inst, Index, Size); + // Add the call to the call list if the destination is known. + if (targ != -1ULL && targ != Index+Size) + Calls.push_back(targ); + } + } else { + errs().write_hex(Index) << ": warning: invalid instruction encoding\n"; + if (Size == 0) + Size = 1; // skip illegible bytes + } + } + } + } + + // Make sure the instruction list is sorted. + std::sort(Instructions.begin(), Instructions.end()); + + // Create basic blocks. + unsigned ii = 0, ie = Instructions.size(); + for (std::set<uint64_t>::iterator spi = Splits.begin(), + spe = llvm::prior(Splits.end()); spi != spe; ++spi) { + MCBasicBlock BB; + uint64_t BlockEnd = *llvm::next(spi); + // Add instructions to the BB. + for (; ii != ie; ++ii) { + if (Instructions[ii].Address < *spi || + Instructions[ii].Address >= BlockEnd) + break; + BB.addInst(Instructions[ii]); + } + f.addBlock(*spi, BB); + } + + std::sort(f.Blocks.begin(), f.Blocks.end()); + + // Calculate successors of each block. + for (MCFunction::iterator i = f.begin(), e = f.end(); i != e; ++i) { + MCBasicBlock &BB = const_cast<MCBasicBlock&>(i->second); + if (BB.getInsts().empty()) continue; + const MCDecodedInst &Inst = BB.getInsts().back(); + + if (Ana->isBranch(Inst.Inst)) { + uint64_t targ = Ana->evaluateBranch(Inst.Inst, Inst.Address, Inst.Size); + if (targ == -1ULL) { + // Indirect branch. Bail and add all blocks of the function as a + // successor. + for (MCFunction::iterator i = f.begin(), e = f.end(); i != e; ++i) + BB.addSucc(i->first); + } else if (targ != Inst.Address+Inst.Size) + BB.addSucc(targ); + // Conditional branches can also fall through to the next block. + if (Ana->isConditionalBranch(Inst.Inst) && llvm::next(i) != e) + BB.addSucc(llvm::next(i)->first); + } else { + // No branch. Fall through to the next block. + if (!Ana->isReturn(Inst.Inst) && llvm::next(i) != e) + BB.addSucc(llvm::next(i)->first); + } + } + + return f; +} diff --git a/contrib/llvm/tools/llvm-objdump/MCFunction.h b/contrib/llvm/tools/llvm-objdump/MCFunction.h new file mode 100644 index 0000000..6d3a548 --- /dev/null +++ b/contrib/llvm/tools/llvm-objdump/MCFunction.h @@ -0,0 +1,100 @@ +//===-- MCFunction.h ------------------------------------------------------===// +// +// 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 data structures to hold a CFG reconstructed from +// machine code. +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_OBJECTDUMP_MCFUNCTION_H +#define LLVM_OBJECTDUMP_MCFUNCTION_H + +#include "llvm/ADT/ArrayRef.h" +#include "llvm/ADT/DenseSet.h" +#include "llvm/MC/MCInst.h" +#include <map> + +namespace llvm { + +class MCDisassembler; +class MCInstrAnalysis; +class MemoryObject; +class raw_ostream; + +/// MCDecodedInst - Small container to hold an MCInst and associated info like +/// address and size. +struct MCDecodedInst { + uint64_t Address; + uint64_t Size; + MCInst Inst; + + MCDecodedInst() {} + MCDecodedInst(uint64_t Address, uint64_t Size, MCInst Inst) + : Address(Address), Size(Size), Inst(Inst) {} + + bool operator<(const MCDecodedInst &RHS) const { + return Address < RHS.Address; + } +}; + +/// MCBasicBlock - Consists of multiple MCDecodedInsts and a list of successing +/// MCBasicBlocks. +class MCBasicBlock { + std::vector<MCDecodedInst> Insts; + typedef DenseSet<uint64_t> SetTy; + SetTy Succs; +public: + ArrayRef<MCDecodedInst> getInsts() const { return Insts; } + + typedef SetTy::const_iterator succ_iterator; + succ_iterator succ_begin() const { return Succs.begin(); } + succ_iterator succ_end() const { return Succs.end(); } + + bool contains(uint64_t Addr) const { return Succs.count(Addr); } + + void addInst(const MCDecodedInst &Inst) { Insts.push_back(Inst); } + void addSucc(uint64_t Addr) { Succs.insert(Addr); } + + bool operator<(const MCBasicBlock &RHS) const { + return Insts.size() < RHS.Insts.size(); + } +}; + +/// MCFunction - Represents a named function in machine code, containing +/// multiple MCBasicBlocks. +class MCFunction { + const StringRef Name; + // Keep BBs sorted by address. + typedef std::vector<std::pair<uint64_t, MCBasicBlock> > MapTy; + MapTy Blocks; +public: + MCFunction(StringRef Name) : Name(Name) {} + + // Create an MCFunction from a region of binary machine code. + static MCFunction + createFunctionFromMC(StringRef Name, const MCDisassembler *DisAsm, + const MemoryObject &Region, uint64_t Start, uint64_t End, + const MCInstrAnalysis *Ana, raw_ostream &DebugOut, + SmallVectorImpl<uint64_t> &Calls); + + typedef MapTy::const_iterator iterator; + iterator begin() const { return Blocks.begin(); } + iterator end() const { return Blocks.end(); } + + StringRef getName() const { return Name; } + + MCBasicBlock &addBlock(uint64_t Address, const MCBasicBlock &BB) { + Blocks.push_back(std::make_pair(Address, BB)); + return Blocks.back().second; + } +}; + +} + +#endif diff --git a/contrib/llvm/tools/llvm-objdump/MachODump.cpp b/contrib/llvm/tools/llvm-objdump/MachODump.cpp new file mode 100644 index 0000000..3f44b29 --- /dev/null +++ b/contrib/llvm/tools/llvm-objdump/MachODump.cpp @@ -0,0 +1,617 @@ +//===-- MachODump.cpp - Object file dumping utility for llvm --------------===// +// +// 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 MachO-specific dumper for llvm-objdump. +// +//===----------------------------------------------------------------------===// + +#include "llvm-objdump.h" +#include "MCFunction.h" +#include "llvm/Support/MachO.h" +#include "llvm/Object/MachOObject.h" +#include "llvm/ADT/OwningPtr.h" +#include "llvm/ADT/Triple.h" +#include "llvm/ADT/STLExtras.h" +#include "llvm/DebugInfo/DIContext.h" +#include "llvm/MC/MCAsmInfo.h" +#include "llvm/MC/MCDisassembler.h" +#include "llvm/MC/MCInst.h" +#include "llvm/MC/MCInstPrinter.h" +#include "llvm/MC/MCInstrAnalysis.h" +#include "llvm/MC/MCInstrDesc.h" +#include "llvm/MC/MCInstrInfo.h" +#include "llvm/MC/MCSubtargetInfo.h" +#include "llvm/Support/CommandLine.h" +#include "llvm/Support/Debug.h" +#include "llvm/Support/Format.h" +#include "llvm/Support/GraphWriter.h" +#include "llvm/Support/MemoryBuffer.h" +#include "llvm/Support/TargetRegistry.h" +#include "llvm/Support/TargetSelect.h" +#include "llvm/Support/raw_ostream.h" +#include "llvm/Support/system_error.h" +#include <algorithm> +#include <cstring> +using namespace llvm; +using namespace object; + +static cl::opt<bool> + CFG("cfg", cl::desc("Create a CFG for every symbol in the object file and" + "write it to a graphviz file (MachO-only)")); + +static cl::opt<bool> + UseDbg("g", cl::desc("Print line information from debug info if available")); + +static cl::opt<std::string> + DSYMFile("dsym", cl::desc("Use .dSYM file for debug info")); + +static const Target *GetTarget(const MachOObject *MachOObj) { + // Figure out the target triple. + llvm::Triple TT("unknown-unknown-unknown"); + switch (MachOObj->getHeader().CPUType) { + case llvm::MachO::CPUTypeI386: + TT.setArch(Triple::ArchType(Triple::x86)); + break; + case llvm::MachO::CPUTypeX86_64: + TT.setArch(Triple::ArchType(Triple::x86_64)); + break; + case llvm::MachO::CPUTypeARM: + TT.setArch(Triple::ArchType(Triple::arm)); + break; + case llvm::MachO::CPUTypePowerPC: + TT.setArch(Triple::ArchType(Triple::ppc)); + break; + case llvm::MachO::CPUTypePowerPC64: + TT.setArch(Triple::ArchType(Triple::ppc64)); + break; + } + + TripleName = TT.str(); + + // Get the target specific parser. + std::string Error; + const Target *TheTarget = TargetRegistry::lookupTarget(TripleName, Error); + if (TheTarget) + return TheTarget; + + errs() << "llvm-objdump: error: unable to get target for '" << TripleName + << "', see --version and --triple.\n"; + return 0; +} + +struct Section { + char Name[16]; + uint64_t Address; + uint64_t Size; + uint32_t Offset; + uint32_t NumRelocs; + uint64_t RelocTableOffset; +}; + +struct Symbol { + uint64_t Value; + uint32_t StringIndex; + uint8_t SectionIndex; + bool operator<(const Symbol &RHS) const { return Value < RHS.Value; } +}; + +template <typename T> +static Section copySection(const T &Sect) { + Section S; + memcpy(S.Name, Sect->Name, 16); + S.Address = Sect->Address; + S.Size = Sect->Size; + S.Offset = Sect->Offset; + S.NumRelocs = Sect->NumRelocationTableEntries; + S.RelocTableOffset = Sect->RelocationTableOffset; + return S; +} + +template <typename T> +static Symbol copySymbol(const T &STE) { + Symbol S; + S.StringIndex = STE->StringIndex; + S.SectionIndex = STE->SectionIndex; + S.Value = STE->Value; + return S; +} + +// Print additional information about an address, if available. +static void DumpAddress(uint64_t Address, ArrayRef<Section> Sections, + MachOObject *MachOObj, raw_ostream &OS) { + for (unsigned i = 0; i != Sections.size(); ++i) { + uint64_t addr = Address-Sections[i].Address; + if (Sections[i].Address <= Address && + Sections[i].Address + Sections[i].Size > Address) { + StringRef bytes = MachOObj->getData(Sections[i].Offset, + Sections[i].Size); + // Print constant strings. + if (!strcmp(Sections[i].Name, "__cstring")) + OS << '"' << bytes.substr(addr, bytes.find('\0', addr)) << '"'; + // Print constant CFStrings. + if (!strcmp(Sections[i].Name, "__cfstring")) + OS << "@\"" << bytes.substr(addr, bytes.find('\0', addr)) << '"'; + } + } +} + +typedef std::map<uint64_t, MCFunction*> FunctionMapTy; +typedef SmallVector<MCFunction, 16> FunctionListTy; +static void createMCFunctionAndSaveCalls(StringRef Name, + const MCDisassembler *DisAsm, + MemoryObject &Object, uint64_t Start, + uint64_t End, + MCInstrAnalysis *InstrAnalysis, + uint64_t Address, + raw_ostream &DebugOut, + FunctionMapTy &FunctionMap, + FunctionListTy &Functions) { + SmallVector<uint64_t, 16> Calls; + MCFunction f = + MCFunction::createFunctionFromMC(Name, DisAsm, Object, Start, End, + InstrAnalysis, DebugOut, Calls); + Functions.push_back(f); + FunctionMap[Address] = &Functions.back(); + + // Add the gathered callees to the map. + for (unsigned i = 0, e = Calls.size(); i != e; ++i) + FunctionMap.insert(std::make_pair(Calls[i], (MCFunction*)0)); +} + +// Write a graphviz file for the CFG inside an MCFunction. +static void emitDOTFile(const char *FileName, const MCFunction &f, + MCInstPrinter *IP) { + // Start a new dot file. + std::string Error; + raw_fd_ostream Out(FileName, Error); + if (!Error.empty()) { + errs() << "llvm-objdump: warning: " << Error << '\n'; + return; + } + + Out << "digraph " << f.getName() << " {\n"; + Out << "graph [ rankdir = \"LR\" ];\n"; + for (MCFunction::iterator i = f.begin(), e = f.end(); i != e; ++i) { + bool hasPreds = false; + // Only print blocks that have predecessors. + // FIXME: Slow. + for (MCFunction::iterator pi = f.begin(), pe = f.end(); pi != pe; + ++pi) + if (pi->second.contains(i->first)) { + hasPreds = true; + break; + } + + if (!hasPreds && i != f.begin()) + continue; + + Out << '"' << i->first << "\" [ label=\"<a>"; + // Print instructions. + for (unsigned ii = 0, ie = i->second.getInsts().size(); ii != ie; + ++ii) { + // Escape special chars and print the instruction in mnemonic form. + std::string Str; + raw_string_ostream OS(Str); + IP->printInst(&i->second.getInsts()[ii].Inst, OS, ""); + Out << DOT::EscapeString(OS.str()) << '|'; + } + Out << "<o>\" shape=\"record\" ];\n"; + + // Add edges. + for (MCBasicBlock::succ_iterator si = i->second.succ_begin(), + se = i->second.succ_end(); si != se; ++si) + Out << i->first << ":o -> " << *si <<":a\n"; + } + Out << "}\n"; +} + +static void getSectionsAndSymbols(const macho::Header &Header, + MachOObject *MachOObj, + InMemoryStruct<macho::SymtabLoadCommand> *SymtabLC, + std::vector<Section> &Sections, + std::vector<Symbol> &Symbols, + SmallVectorImpl<uint64_t> &FoundFns) { + // Make a list of all symbols in the object file. + for (unsigned i = 0; i != Header.NumLoadCommands; ++i) { + const MachOObject::LoadCommandInfo &LCI = MachOObj->getLoadCommandInfo(i); + if (LCI.Command.Type == macho::LCT_Segment) { + InMemoryStruct<macho::SegmentLoadCommand> SegmentLC; + MachOObj->ReadSegmentLoadCommand(LCI, SegmentLC); + + // Store the sections in this segment. + for (unsigned SectNum = 0; SectNum != SegmentLC->NumSections; ++SectNum) { + InMemoryStruct<macho::Section> Sect; + MachOObj->ReadSection(LCI, SectNum, Sect); + Sections.push_back(copySection(Sect)); + + } + } else if (LCI.Command.Type == macho::LCT_Segment64) { + InMemoryStruct<macho::Segment64LoadCommand> Segment64LC; + MachOObj->ReadSegment64LoadCommand(LCI, Segment64LC); + + // Store the sections in this segment. + for (unsigned SectNum = 0; SectNum != Segment64LC->NumSections; + ++SectNum) { + InMemoryStruct<macho::Section64> Sect64; + MachOObj->ReadSection64(LCI, SectNum, Sect64); + Sections.push_back(copySection(Sect64)); + } + } else if (LCI.Command.Type == macho::LCT_FunctionStarts) { + // We found a function starts segment, parse the addresses for later + // consumption. + InMemoryStruct<macho::LinkeditDataLoadCommand> LLC; + MachOObj->ReadLinkeditDataLoadCommand(LCI, LLC); + + MachOObj->ReadULEB128s(LLC->DataOffset, FoundFns); + } + } + // Store the symbols. + if (SymtabLC) { + for (unsigned i = 0; i != (*SymtabLC)->NumSymbolTableEntries; ++i) { + if (MachOObj->is64Bit()) { + InMemoryStruct<macho::Symbol64TableEntry> STE; + MachOObj->ReadSymbol64TableEntry((*SymtabLC)->SymbolTableOffset, i, + STE); + Symbols.push_back(copySymbol(STE)); + } else { + InMemoryStruct<macho::SymbolTableEntry> STE; + MachOObj->ReadSymbolTableEntry((*SymtabLC)->SymbolTableOffset, i, + STE); + Symbols.push_back(copySymbol(STE)); + } + } + } +} + +void llvm::DisassembleInputMachO(StringRef Filename) { + OwningPtr<MemoryBuffer> Buff; + + if (error_code ec = MemoryBuffer::getFileOrSTDIN(Filename, Buff)) { + errs() << "llvm-objdump: " << Filename << ": " << ec.message() << "\n"; + return; + } + + OwningPtr<MachOObject> MachOObj(MachOObject::LoadFromBuffer(Buff.take())); + + const Target *TheTarget = GetTarget(MachOObj.get()); + if (!TheTarget) { + // GetTarget prints out stuff. + return; + } + OwningPtr<const MCInstrInfo> InstrInfo(TheTarget->createMCInstrInfo()); + OwningPtr<MCInstrAnalysis> + InstrAnalysis(TheTarget->createMCInstrAnalysis(InstrInfo.get())); + + // Set up disassembler. + OwningPtr<const MCAsmInfo> AsmInfo(TheTarget->createMCAsmInfo(TripleName)); + OwningPtr<const MCSubtargetInfo> + STI(TheTarget->createMCSubtargetInfo(TripleName, "", "")); + OwningPtr<const MCDisassembler> DisAsm(TheTarget->createMCDisassembler(*STI)); + int AsmPrinterVariant = AsmInfo->getAssemblerDialect(); + OwningPtr<MCInstPrinter> IP(TheTarget->createMCInstPrinter( + AsmPrinterVariant, *AsmInfo, *STI)); + + if (!InstrAnalysis || !AsmInfo || !STI || !DisAsm || !IP) { + errs() << "error: couldn't initialize disassembler for target " + << TripleName << '\n'; + return; + } + + outs() << '\n' << Filename << ":\n\n"; + + const macho::Header &Header = MachOObj->getHeader(); + + const MachOObject::LoadCommandInfo *SymtabLCI = 0; + // First, find the symbol table segment. + for (unsigned i = 0; i != Header.NumLoadCommands; ++i) { + const MachOObject::LoadCommandInfo &LCI = MachOObj->getLoadCommandInfo(i); + if (LCI.Command.Type == macho::LCT_Symtab) { + SymtabLCI = &LCI; + break; + } + } + + // Read and register the symbol table data. + InMemoryStruct<macho::SymtabLoadCommand> SymtabLC; + MachOObj->ReadSymtabLoadCommand(*SymtabLCI, SymtabLC); + MachOObj->RegisterStringTable(*SymtabLC); + + std::vector<Section> Sections; + std::vector<Symbol> Symbols; + SmallVector<uint64_t, 8> FoundFns; + + getSectionsAndSymbols(Header, MachOObj.get(), &SymtabLC, Sections, Symbols, + FoundFns); + + // Make a copy of the unsorted symbol list. FIXME: duplication + std::vector<Symbol> UnsortedSymbols(Symbols); + // Sort the symbols by address, just in case they didn't come in that way. + array_pod_sort(Symbols.begin(), Symbols.end()); + +#ifndef NDEBUG + raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls(); +#else + raw_ostream &DebugOut = nulls(); +#endif + + StringRef DebugAbbrevSection, DebugInfoSection, DebugArangesSection, + DebugLineSection, DebugStrSection; + OwningPtr<DIContext> diContext; + OwningPtr<MachOObject> DSYMObj; + MachOObject *DbgInfoObj = MachOObj.get(); + // Try to find debug info and set up the DIContext for it. + if (UseDbg) { + ArrayRef<Section> DebugSections = Sections; + std::vector<Section> DSYMSections; + + // A separate DSym file path was specified, parse it as a macho file, + // get the sections and supply it to the section name parsing machinery. + if (!DSYMFile.empty()) { + OwningPtr<MemoryBuffer> Buf; + if (error_code ec = MemoryBuffer::getFileOrSTDIN(DSYMFile.c_str(), Buf)) { + errs() << "llvm-objdump: " << Filename << ": " << ec.message() << '\n'; + return; + } + DSYMObj.reset(MachOObject::LoadFromBuffer(Buf.take())); + const macho::Header &Header = DSYMObj->getHeader(); + + std::vector<Symbol> Symbols; + SmallVector<uint64_t, 8> FoundFns; + getSectionsAndSymbols(Header, DSYMObj.get(), 0, DSYMSections, Symbols, + FoundFns); + DebugSections = DSYMSections; + DbgInfoObj = DSYMObj.get(); + } + + // Find the named debug info sections. + for (unsigned SectIdx = 0; SectIdx != DebugSections.size(); SectIdx++) { + if (!strcmp(DebugSections[SectIdx].Name, "__debug_abbrev")) + DebugAbbrevSection = DbgInfoObj->getData(DebugSections[SectIdx].Offset, + DebugSections[SectIdx].Size); + else if (!strcmp(DebugSections[SectIdx].Name, "__debug_info")) + DebugInfoSection = DbgInfoObj->getData(DebugSections[SectIdx].Offset, + DebugSections[SectIdx].Size); + else if (!strcmp(DebugSections[SectIdx].Name, "__debug_aranges")) + DebugArangesSection = DbgInfoObj->getData(DebugSections[SectIdx].Offset, + DebugSections[SectIdx].Size); + else if (!strcmp(DebugSections[SectIdx].Name, "__debug_line")) + DebugLineSection = DbgInfoObj->getData(DebugSections[SectIdx].Offset, + DebugSections[SectIdx].Size); + else if (!strcmp(DebugSections[SectIdx].Name, "__debug_str")) + DebugStrSection = DbgInfoObj->getData(DebugSections[SectIdx].Offset, + DebugSections[SectIdx].Size); + } + + // Setup the DIContext. + diContext.reset(DIContext::getDWARFContext(DbgInfoObj->isLittleEndian(), + DebugInfoSection, + DebugAbbrevSection, + DebugArangesSection, + DebugLineSection, + DebugStrSection)); + } + + FunctionMapTy FunctionMap; + FunctionListTy Functions; + + for (unsigned SectIdx = 0; SectIdx != Sections.size(); SectIdx++) { + if (strcmp(Sections[SectIdx].Name, "__text")) + continue; // Skip non-text sections + + // Insert the functions from the function starts segment into our map. + uint64_t VMAddr = Sections[SectIdx].Address - Sections[SectIdx].Offset; + for (unsigned i = 0, e = FoundFns.size(); i != e; ++i) + FunctionMap.insert(std::make_pair(FoundFns[i]+VMAddr, (MCFunction*)0)); + + StringRef Bytes = MachOObj->getData(Sections[SectIdx].Offset, + Sections[SectIdx].Size); + StringRefMemoryObject memoryObject(Bytes); + bool symbolTableWorked = false; + + // Parse relocations. + std::vector<std::pair<uint64_t, uint32_t> > Relocs; + for (unsigned j = 0; j != Sections[SectIdx].NumRelocs; ++j) { + InMemoryStruct<macho::RelocationEntry> RE; + MachOObj->ReadRelocationEntry(Sections[SectIdx].RelocTableOffset, j, RE); + Relocs.push_back(std::make_pair(RE->Word0, RE->Word1 & 0xffffff)); + } + array_pod_sort(Relocs.begin(), Relocs.end()); + + // Disassemble symbol by symbol. + for (unsigned SymIdx = 0; SymIdx != Symbols.size(); SymIdx++) { + // Make sure the symbol is defined in this section. + if ((unsigned)Symbols[SymIdx].SectionIndex - 1 != SectIdx) + continue; + + // Start at the address of the symbol relative to the section's address. + uint64_t Start = Symbols[SymIdx].Value - Sections[SectIdx].Address; + // Stop disassembling either at the beginning of the next symbol or at + // the end of the section. + uint64_t End = (SymIdx+1 == Symbols.size() || + Symbols[SymIdx].SectionIndex != Symbols[SymIdx+1].SectionIndex) ? + Sections[SectIdx].Size : + Symbols[SymIdx+1].Value - Sections[SectIdx].Address; + uint64_t Size; + + if (Start >= End) + continue; + + symbolTableWorked = true; + + if (!CFG) { + // Normal disassembly, print addresses, bytes and mnemonic form. + outs() << MachOObj->getStringAtIndex(Symbols[SymIdx].StringIndex) + << ":\n"; + DILineInfo lastLine; + for (uint64_t Index = Start; Index < End; Index += Size) { + MCInst Inst; + + if (DisAsm->getInstruction(Inst, Size, memoryObject, Index, + DebugOut, nulls())) { + outs() << format("%8llx:\t", Sections[SectIdx].Address + Index); + DumpBytes(StringRef(Bytes.data() + Index, Size)); + IP->printInst(&Inst, outs(), ""); + + // Print debug info. + if (diContext) { + DILineInfo dli = + diContext->getLineInfoForAddress(Sections[SectIdx].Address + + Index); + // Print valid line info if it changed. + if (dli != lastLine && dli.getLine() != 0) + outs() << "\t## " << dli.getFileName() << ':' + << dli.getLine() << ':' << dli.getColumn(); + lastLine = dli; + } + outs() << "\n"; + } else { + errs() << "llvm-objdump: warning: invalid instruction encoding\n"; + if (Size == 0) + Size = 1; // skip illegible bytes + } + } + } else { + // Create CFG and use it for disassembly. + createMCFunctionAndSaveCalls( + MachOObj->getStringAtIndex(Symbols[SymIdx].StringIndex), + DisAsm.get(), memoryObject, Start, End, InstrAnalysis.get(), + Start, DebugOut, FunctionMap, Functions); + } + } + + if (CFG) { + if (!symbolTableWorked) { + // Reading the symbol table didn't work, create a big __TEXT symbol. + createMCFunctionAndSaveCalls("__TEXT", DisAsm.get(), memoryObject, + 0, Sections[SectIdx].Size, + InstrAnalysis.get(), + Sections[SectIdx].Offset, DebugOut, + FunctionMap, Functions); + } + for (std::map<uint64_t, MCFunction*>::iterator mi = FunctionMap.begin(), + me = FunctionMap.end(); mi != me; ++mi) + if (mi->second == 0) { + // Create functions for the remaining callees we have gathered, + // but we didn't find a name for them. + SmallVector<uint64_t, 16> Calls; + MCFunction f = + MCFunction::createFunctionFromMC("unknown", DisAsm.get(), + memoryObject, mi->first, + Sections[SectIdx].Size, + InstrAnalysis.get(), DebugOut, + Calls); + Functions.push_back(f); + mi->second = &Functions.back(); + for (unsigned i = 0, e = Calls.size(); i != e; ++i) { + std::pair<uint64_t, MCFunction*> p(Calls[i], (MCFunction*)0); + if (FunctionMap.insert(p).second) + mi = FunctionMap.begin(); + } + } + + DenseSet<uint64_t> PrintedBlocks; + for (unsigned ffi = 0, ffe = Functions.size(); ffi != ffe; ++ffi) { + MCFunction &f = Functions[ffi]; + for (MCFunction::iterator fi = f.begin(), fe = f.end(); fi != fe; ++fi){ + if (!PrintedBlocks.insert(fi->first).second) + continue; // We already printed this block. + + // We assume a block has predecessors when it's the first block after + // a symbol. + bool hasPreds = FunctionMap.find(fi->first) != FunctionMap.end(); + + // See if this block has predecessors. + // FIXME: Slow. + for (MCFunction::iterator pi = f.begin(), pe = f.end(); pi != pe; + ++pi) + if (pi->second.contains(fi->first)) { + hasPreds = true; + break; + } + + // No predecessors, this is a data block. Print as .byte directives. + if (!hasPreds) { + uint64_t End = llvm::next(fi) == fe ? Sections[SectIdx].Size : + llvm::next(fi)->first; + outs() << "# " << End-fi->first << " bytes of data:\n"; + for (unsigned pos = fi->first; pos != End; ++pos) { + outs() << format("%8x:\t", Sections[SectIdx].Address + pos); + DumpBytes(StringRef(Bytes.data() + pos, 1)); + outs() << format("\t.byte 0x%02x\n", (uint8_t)Bytes[pos]); + } + continue; + } + + if (fi->second.contains(fi->first)) // Print a header for simple loops + outs() << "# Loop begin:\n"; + + DILineInfo lastLine; + // Walk over the instructions and print them. + for (unsigned ii = 0, ie = fi->second.getInsts().size(); ii != ie; + ++ii) { + const MCDecodedInst &Inst = fi->second.getInsts()[ii]; + + // If there's a symbol at this address, print its name. + if (FunctionMap.find(Sections[SectIdx].Address + Inst.Address) != + FunctionMap.end()) + outs() << FunctionMap[Sections[SectIdx].Address + Inst.Address]-> + getName() << ":\n"; + + outs() << format("%8llx:\t", Sections[SectIdx].Address + + Inst.Address); + DumpBytes(StringRef(Bytes.data() + Inst.Address, Inst.Size)); + + if (fi->second.contains(fi->first)) // Indent simple loops. + outs() << '\t'; + + IP->printInst(&Inst.Inst, outs(), ""); + + // Look for relocations inside this instructions, if there is one + // print its target and additional information if available. + for (unsigned j = 0; j != Relocs.size(); ++j) + if (Relocs[j].first >= Sections[SectIdx].Address + Inst.Address && + Relocs[j].first < Sections[SectIdx].Address + Inst.Address + + Inst.Size) { + outs() << "\t# " + << MachOObj->getStringAtIndex( + UnsortedSymbols[Relocs[j].second].StringIndex) + << ' '; + DumpAddress(UnsortedSymbols[Relocs[j].second].Value, Sections, + MachOObj.get(), outs()); + } + + // If this instructions contains an address, see if we can evaluate + // it and print additional information. + uint64_t targ = InstrAnalysis->evaluateBranch(Inst.Inst, + Inst.Address, + Inst.Size); + if (targ != -1ULL) + DumpAddress(targ, Sections, MachOObj.get(), outs()); + + // Print debug info. + if (diContext) { + DILineInfo dli = + diContext->getLineInfoForAddress(Sections[SectIdx].Address + + Inst.Address); + // Print valid line info if it changed. + if (dli != lastLine && dli.getLine() != 0) + outs() << "\t## " << dli.getFileName() << ':' + << dli.getLine() << ':' << dli.getColumn(); + lastLine = dli; + } + + outs() << '\n'; + } + } + + emitDOTFile((f.getName().str() + ".dot").c_str(), f, IP.get()); + } + } + } +} diff --git a/contrib/llvm/tools/llvm-objdump/Makefile b/contrib/llvm/tools/llvm-objdump/Makefile new file mode 100644 index 0000000..703bf6c --- /dev/null +++ b/contrib/llvm/tools/llvm-objdump/Makefile @@ -0,0 +1,18 @@ +##===- tools/llvm-objdump/Makefile -------------------------*- Makefile -*-===## +# +# The LLVM Compiler Infrastructure +# +# This file is distributed under the University of Illinois Open Source +# License. See LICENSE.TXT for details. +# +##===----------------------------------------------------------------------===## +LEVEL = ../.. + +TOOLNAME = llvm-objdump +LINK_COMPONENTS = $(TARGETS_TO_BUILD) DebugInfo MC MCParser MCDisassembler \ + Object + +# This tool has no plugins, optimize startup time. +TOOL_NO_EXPORTS = 1 + +include $(LEVEL)/Makefile.common diff --git a/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp b/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp new file mode 100644 index 0000000..40c59bd --- /dev/null +++ b/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp @@ -0,0 +1,459 @@ +//===-- llvm-objdump.cpp - Object file dumping utility for llvm -----------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// This program is a utility that works like binutils "objdump", that is, it +// dumps out a plethora of information about an object file depending on the +// flags. +// +//===----------------------------------------------------------------------===// + +#include "llvm-objdump.h" +#include "MCFunction.h" +#include "llvm/Object/Archive.h" +#include "llvm/Object/ObjectFile.h" +#include "llvm/ADT/OwningPtr.h" +#include "llvm/ADT/Triple.h" +#include "llvm/ADT/STLExtras.h" +#include "llvm/MC/MCAsmInfo.h" +#include "llvm/MC/MCDisassembler.h" +#include "llvm/MC/MCInst.h" +#include "llvm/MC/MCInstPrinter.h" +#include "llvm/MC/MCSubtargetInfo.h" +#include "llvm/Support/Casting.h" +#include "llvm/Support/CommandLine.h" +#include "llvm/Support/Debug.h" +#include "llvm/Support/FileSystem.h" +#include "llvm/Support/Format.h" +#include "llvm/Support/GraphWriter.h" +#include "llvm/Support/Host.h" +#include "llvm/Support/ManagedStatic.h" +#include "llvm/Support/MemoryBuffer.h" +#include "llvm/Support/MemoryObject.h" +#include "llvm/Support/PrettyStackTrace.h" +#include "llvm/Support/Signals.h" +#include "llvm/Support/SourceMgr.h" +#include "llvm/Support/TargetRegistry.h" +#include "llvm/Support/TargetSelect.h" +#include "llvm/Support/raw_ostream.h" +#include "llvm/Support/system_error.h" +#include <algorithm> +#include <cstring> +using namespace llvm; +using namespace object; + +static cl::list<std::string> +InputFilenames(cl::Positional, cl::desc("<input object files>"),cl::ZeroOrMore); + +static cl::opt<bool> +Disassemble("disassemble", + cl::desc("Display assembler mnemonics for the machine instructions")); +static cl::alias +Disassembled("d", cl::desc("Alias for --disassemble"), + cl::aliasopt(Disassemble)); + +static cl::opt<bool> +Relocations("r", cl::desc("Display the relocation entries in the file")); + +static cl::opt<bool> +MachO("macho", cl::desc("Use MachO specific object file parser")); +static cl::alias +MachOm("m", cl::desc("Alias for --macho"), cl::aliasopt(MachO)); + +cl::opt<std::string> +llvm::TripleName("triple", cl::desc("Target triple to disassemble for, " + "see -version for available targets")); + +cl::opt<std::string> +llvm::ArchName("arch", cl::desc("Target arch to disassemble for, " + "see -version for available targets")); + +static cl::opt<bool> +SectionHeaders("section-headers", cl::desc("Display summaries of the headers " + "for each section.")); +static cl::alias +SectionHeadersShort("headers", cl::desc("Alias for --section-headers"), + cl::aliasopt(SectionHeaders)); +static cl::alias +SectionHeadersShorter("h", cl::desc("Alias for --section-headers"), + cl::aliasopt(SectionHeaders)); + +static StringRef ToolName; + +static bool error(error_code ec) { + if (!ec) return false; + + outs() << ToolName << ": error reading file: " << ec.message() << ".\n"; + outs().flush(); + return true; +} + +static const Target *GetTarget(const ObjectFile *Obj = NULL) { + // Figure out the target triple. + llvm::Triple TT("unknown-unknown-unknown"); + if (TripleName.empty()) { + if (Obj) + TT.setArch(Triple::ArchType(Obj->getArch())); + } else + TT.setTriple(Triple::normalize(TripleName)); + + if (!ArchName.empty()) + TT.setArchName(ArchName); + + TripleName = TT.str(); + + // Get the target specific parser. + std::string Error; + const Target *TheTarget = TargetRegistry::lookupTarget(TripleName, Error); + if (TheTarget) + return TheTarget; + + errs() << ToolName << ": error: unable to get target for '" << TripleName + << "', see --version and --triple.\n"; + return 0; +} + +void llvm::DumpBytes(StringRef bytes) { + static const char hex_rep[] = "0123456789abcdef"; + // FIXME: The real way to do this is to figure out the longest instruction + // and align to that size before printing. I'll fix this when I get + // around to outputting relocations. + // 15 is the longest x86 instruction + // 3 is for the hex rep of a byte + a space. + // 1 is for the null terminator. + enum { OutputSize = (15 * 3) + 1 }; + char output[OutputSize]; + + assert(bytes.size() <= 15 + && "DumpBytes only supports instructions of up to 15 bytes"); + memset(output, ' ', sizeof(output)); + unsigned index = 0; + for (StringRef::iterator i = bytes.begin(), + e = bytes.end(); i != e; ++i) { + output[index] = hex_rep[(*i & 0xF0) >> 4]; + output[index + 1] = hex_rep[*i & 0xF]; + index += 3; + } + + output[sizeof(output) - 1] = 0; + outs() << output; +} + +static bool RelocAddressLess(RelocationRef a, RelocationRef b) { + uint64_t a_addr, b_addr; + if (error(a.getAddress(a_addr))) return false; + if (error(b.getAddress(b_addr))) return false; + return a_addr < b_addr; +} + +static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { + const Target *TheTarget = GetTarget(Obj); + if (!TheTarget) { + // GetTarget prints out stuff. + return; + } + + outs() << '\n'; + outs() << Obj->getFileName() + << ":\tfile format " << Obj->getFileFormatName() << "\n\n"; + + error_code ec; + for (section_iterator i = Obj->begin_sections(), + e = Obj->end_sections(); + i != e; i.increment(ec)) { + if (error(ec)) break; + bool text; + if (error(i->isText(text))) break; + if (!text) continue; + + uint64_t SectionAddr; + if (error(i->getAddress(SectionAddr))) break; + + // Make a list of all the symbols in this section. + std::vector<std::pair<uint64_t, StringRef> > Symbols; + for (symbol_iterator si = Obj->begin_symbols(), + se = Obj->end_symbols(); + si != se; si.increment(ec)) { + bool contains; + if (!error(i->containsSymbol(*si, contains)) && contains) { + uint64_t Address; + if (error(si->getOffset(Address))) break; + StringRef Name; + if (error(si->getName(Name))) break; + Symbols.push_back(std::make_pair(Address, Name)); + } + } + + // Sort the symbols by address, just in case they didn't come in that way. + array_pod_sort(Symbols.begin(), Symbols.end()); + + // Make a list of all the relocations for this section. + std::vector<RelocationRef> Rels; + if (InlineRelocs) { + for (relocation_iterator ri = i->begin_relocations(), + re = i->end_relocations(); + ri != re; ri.increment(ec)) { + if (error(ec)) break; + Rels.push_back(*ri); + } + } + + // Sort relocations by address. + std::sort(Rels.begin(), Rels.end(), RelocAddressLess); + + StringRef name; + if (error(i->getName(name))) break; + outs() << "Disassembly of section " << name << ':'; + + // If the section has no symbols just insert a dummy one and disassemble + // the whole section. + if (Symbols.empty()) + Symbols.push_back(std::make_pair(0, name)); + + // Set up disassembler. + OwningPtr<const MCAsmInfo> AsmInfo(TheTarget->createMCAsmInfo(TripleName)); + + if (!AsmInfo) { + errs() << "error: no assembly info for target " << TripleName << "\n"; + return; + } + + OwningPtr<const MCSubtargetInfo> STI( + TheTarget->createMCSubtargetInfo(TripleName, "", "")); + + if (!STI) { + errs() << "error: no subtarget info for target " << TripleName << "\n"; + return; + } + + OwningPtr<const MCDisassembler> DisAsm( + TheTarget->createMCDisassembler(*STI)); + if (!DisAsm) { + errs() << "error: no disassembler for target " << TripleName << "\n"; + return; + } + + int AsmPrinterVariant = AsmInfo->getAssemblerDialect(); + OwningPtr<MCInstPrinter> IP(TheTarget->createMCInstPrinter( + AsmPrinterVariant, *AsmInfo, *STI)); + if (!IP) { + errs() << "error: no instruction printer for target " << TripleName + << '\n'; + return; + } + + StringRef Bytes; + if (error(i->getContents(Bytes))) break; + StringRefMemoryObject memoryObject(Bytes); + uint64_t Size; + uint64_t Index; + uint64_t SectSize; + if (error(i->getSize(SectSize))) break; + + std::vector<RelocationRef>::const_iterator rel_cur = Rels.begin(); + std::vector<RelocationRef>::const_iterator rel_end = Rels.end(); + // Disassemble symbol by symbol. + for (unsigned si = 0, se = Symbols.size(); si != se; ++si) { + uint64_t Start = Symbols[si].first; + uint64_t End; + // The end is either the size of the section or the beginning of the next + // symbol. + if (si == se - 1) + End = SectSize; + // Make sure this symbol takes up space. + else if (Symbols[si + 1].first != Start) + End = Symbols[si + 1].first - 1; + else + // This symbol has the same address as the next symbol. Skip it. + continue; + + outs() << '\n' << Symbols[si].second << ":\n"; + +#ifndef NDEBUG + raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls(); +#else + raw_ostream &DebugOut = nulls(); +#endif + + for (Index = Start; Index < End; Index += Size) { + MCInst Inst; + + if (DisAsm->getInstruction(Inst, Size, memoryObject, Index, + DebugOut, nulls())) { + outs() << format("%8"PRIx64":\t", SectionAddr + Index); + DumpBytes(StringRef(Bytes.data() + Index, Size)); + IP->printInst(&Inst, outs(), ""); + outs() << "\n"; + } else { + errs() << ToolName << ": warning: invalid instruction encoding\n"; + if (Size == 0) + Size = 1; // skip illegible bytes + } + + // Print relocation for instruction. + while (rel_cur != rel_end) { + uint64_t addr; + SmallString<16> name; + SmallString<32> val; + if (error(rel_cur->getAddress(addr))) goto skip_print_rel; + // Stop when rel_cur's address is past the current instruction. + if (addr > Index + Size) break; + if (error(rel_cur->getTypeName(name))) goto skip_print_rel; + if (error(rel_cur->getValueString(val))) goto skip_print_rel; + + outs() << format("\t\t\t%8"PRIx64": ", SectionAddr + addr) << name << "\t" + << val << "\n"; + + skip_print_rel: + ++rel_cur; + } + } + } + } +} + +static void PrintRelocations(const ObjectFile *o) { + error_code ec; + for (section_iterator si = o->begin_sections(), se = o->end_sections(); + si != se; si.increment(ec)){ + if (error(ec)) return; + if (si->begin_relocations() == si->end_relocations()) + continue; + StringRef secname; + if (error(si->getName(secname))) continue; + outs() << "RELOCATION RECORDS FOR [" << secname << "]:\n"; + for (relocation_iterator ri = si->begin_relocations(), + re = si->end_relocations(); + ri != re; ri.increment(ec)) { + if (error(ec)) return; + + uint64_t address; + SmallString<32> relocname; + SmallString<32> valuestr; + if (error(ri->getTypeName(relocname))) continue; + if (error(ri->getAddress(address))) continue; + if (error(ri->getValueString(valuestr))) continue; + outs() << address << " " << relocname << " " << valuestr << "\n"; + } + outs() << "\n"; + } +} + +static void PrintSectionHeaders(const ObjectFile *o) { + outs() << "Sections:\n" + "Idx Name Size Address Type\n"; + error_code ec; + unsigned i = 0; + for (section_iterator si = o->begin_sections(), se = o->end_sections(); + si != se; si.increment(ec)) { + if (error(ec)) return; + StringRef Name; + if (error(si->getName(Name))) return; + uint64_t Address; + if (error(si->getAddress(Address))) return; + uint64_t Size; + if (error(si->getSize(Size))) return; + bool Text, Data, BSS; + if (error(si->isText(Text))) return; + if (error(si->isData(Data))) return; + if (error(si->isBSS(BSS))) return; + std::string Type = (std::string(Text ? "TEXT " : "") + + (Data ? "DATA " : "") + (BSS ? "BSS" : "")); + outs() << format("%3d %-13s %09"PRIx64" %017"PRIx64" %s\n", i, Name.str().c_str(), Size, + Address, Type.c_str()); + ++i; + } +} + +static void DumpObject(const ObjectFile *o) { + if (Disassemble) + DisassembleObject(o, Relocations); + if (Relocations && !Disassemble) + PrintRelocations(o); + if (SectionHeaders) + PrintSectionHeaders(o); +} + +/// @brief Dump each object file in \a a; +static void DumpArchive(const Archive *a) { + for (Archive::child_iterator i = a->begin_children(), + e = a->end_children(); i != e; ++i) { + OwningPtr<Binary> child; + if (error_code ec = i->getAsBinary(child)) { + errs() << ToolName << ": '" << a->getFileName() << "': " << ec.message() + << ".\n"; + continue; + } + if (ObjectFile *o = dyn_cast<ObjectFile>(child.get())) + DumpObject(o); + else + errs() << ToolName << ": '" << a->getFileName() << "': " + << "Unrecognized file type.\n"; + } +} + +/// @brief Open file and figure out how to dump it. +static void DumpInput(StringRef file) { + // If file isn't stdin, check that it exists. + if (file != "-" && !sys::fs::exists(file)) { + errs() << ToolName << ": '" << file << "': " << "No such file\n"; + return; + } + + if (MachO && Disassemble) { + DisassembleInputMachO(file); + return; + } + + // Attempt to open the binary. + OwningPtr<Binary> binary; + if (error_code ec = createBinary(file, binary)) { + errs() << ToolName << ": '" << file << "': " << ec.message() << ".\n"; + return; + } + + if (Archive *a = dyn_cast<Archive>(binary.get())) { + DumpArchive(a); + } else if (ObjectFile *o = dyn_cast<ObjectFile>(binary.get())) { + DumpObject(o); + } else { + errs() << ToolName << ": '" << file << "': " << "Unrecognized file type.\n"; + } +} + +int main(int argc, char **argv) { + // Print a stack trace if we signal out. + sys::PrintStackTraceOnErrorSignal(); + PrettyStackTraceProgram X(argc, argv); + llvm_shutdown_obj Y; // Call llvm_shutdown() on exit. + + // Initialize targets and assembly printers/parsers. + llvm::InitializeAllTargetInfos(); + llvm::InitializeAllTargetMCs(); + llvm::InitializeAllAsmParsers(); + llvm::InitializeAllDisassemblers(); + + cl::ParseCommandLineOptions(argc, argv, "llvm object file dumper\n"); + TripleName = Triple::normalize(TripleName); + + ToolName = argv[0]; + + // Defaults to a.out if no filenames specified. + if (InputFilenames.size() == 0) + InputFilenames.push_back("a.out"); + + if (!Disassemble && !Relocations && !SectionHeaders) { + cl::PrintHelpMessage(); + return 2; + } + + std::for_each(InputFilenames.begin(), InputFilenames.end(), + DumpInput); + + return 0; +} diff --git a/contrib/llvm/tools/llvm-objdump/llvm-objdump.h b/contrib/llvm/tools/llvm-objdump/llvm-objdump.h new file mode 100644 index 0000000..75f852a --- /dev/null +++ b/contrib/llvm/tools/llvm-objdump/llvm-objdump.h @@ -0,0 +1,46 @@ +//===-- llvm-objdump.h ----------------------------------------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_OBJDUMP_H +#define LLVM_OBJDUMP_H + +#include "llvm/ADT/StringRef.h" +#include "llvm/Support/CommandLine.h" +#include "llvm/Support/DataTypes.h" +#include "llvm/Support/MemoryObject.h" + +namespace llvm { + +extern cl::opt<std::string> TripleName; +extern cl::opt<std::string> ArchName; + +// Various helper functions. +void DumpBytes(StringRef bytes); +void DisassembleInputMachO(StringRef Filename); + +class StringRefMemoryObject : public MemoryObject { +private: + StringRef Bytes; +public: + StringRefMemoryObject(StringRef bytes) : Bytes(bytes) {} + + uint64_t getBase() const { return 0; } + uint64_t getExtent() const { return Bytes.size(); } + + int readByte(uint64_t Addr, uint8_t *Byte) const { + if (Addr >= getExtent()) + return -1; + *Byte = Bytes[Addr]; + return 0; + } +}; + +} + +#endif |