summaryrefslogtreecommitdiffstats
path: root/contrib/llvm/tools/llvm-objdump
diff options
context:
space:
mode:
Diffstat (limited to 'contrib/llvm/tools/llvm-objdump')
-rw-r--r--contrib/llvm/tools/llvm-objdump/MCFunction.cpp138
-rw-r--r--contrib/llvm/tools/llvm-objdump/MCFunction.h100
-rw-r--r--contrib/llvm/tools/llvm-objdump/MachODump.cpp664
-rw-r--r--contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp656
-rw-r--r--contrib/llvm/tools/llvm-objdump/llvm-objdump.h46
5 files changed, 1604 insertions, 0 deletions
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..1feea42
--- /dev/null
+++ b/contrib/llvm/tools/llvm-objdump/MachODump.cpp
@@ -0,0 +1,664 @@
+//===-- 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/MachO.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/MCRegisterInfo.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.
+ if (TripleName.empty()) {
+ 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 SymbolSorter {
+ bool operator()(const SymbolRef &A, const SymbolRef &B) {
+ SymbolRef::Type AType, BType;
+ A.getType(AType);
+ B.getType(BType);
+
+ uint64_t AAddr, BAddr;
+ if (AType != SymbolRef::ST_Function)
+ AAddr = 0;
+ else
+ A.getAddress(AAddr);
+ if (BType != SymbolRef::ST_Function)
+ BAddr = 0;
+ else
+ B.getAddress(BAddr);
+ return AAddr < BAddr;
+ }
+};
+
+// Print additional information about an address, if available.
+static void DumpAddress(uint64_t Address, ArrayRef<SectionRef> Sections,
+ MachOObject *MachOObj, raw_ostream &OS) {
+ for (unsigned i = 0; i != Sections.size(); ++i) {
+ uint64_t SectAddr = 0, SectSize = 0;
+ Sections[i].getAddress(SectAddr);
+ Sections[i].getSize(SectSize);
+ uint64_t addr = SectAddr;
+ if (SectAddr <= Address &&
+ SectAddr + SectSize > Address) {
+ StringRef bytes, name;
+ Sections[i].getContents(bytes);
+ Sections[i].getName(name);
+ // Print constant strings.
+ if (!name.compare("__cstring"))
+ OS << '"' << bytes.substr(addr, bytes.find('\0', addr)) << '"';
+ // Print constant CFStrings.
+ if (!name.compare("__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,
+ MachOObjectFile *MachOObj,
+ InMemoryStruct<macho::SymtabLoadCommand> *SymtabLC,
+ std::vector<SectionRef> &Sections,
+ std::vector<SymbolRef> &Symbols,
+ SmallVectorImpl<uint64_t> &FoundFns) {
+ error_code ec;
+ for (symbol_iterator SI = MachOObj->begin_symbols(),
+ SE = MachOObj->end_symbols(); SI != SE; SI.increment(ec))
+ Symbols.push_back(*SI);
+
+ for (section_iterator SI = MachOObj->begin_sections(),
+ SE = MachOObj->end_sections(); SI != SE; SI.increment(ec)) {
+ SectionRef SR = *SI;
+ StringRef SectName;
+ SR.getName(SectName);
+ Sections.push_back(*SI);
+ }
+
+ for (unsigned i = 0; i != Header.NumLoadCommands; ++i) {
+ const MachOObject::LoadCommandInfo &LCI =
+ MachOObj->getObject()->getLoadCommandInfo(i);
+ if (LCI.Command.Type == macho::LCT_FunctionStarts) {
+ // We found a function starts segment, parse the addresses for later
+ // consumption.
+ InMemoryStruct<macho::LinkeditDataLoadCommand> LLC;
+ MachOObj->getObject()->ReadLinkeditDataLoadCommand(LCI, LLC);
+
+ MachOObj->getObject()->ReadULEB128s(LLC->DataOffset, FoundFns);
+ }
+ }
+}
+
+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<MachOObjectFile> MachOOF(static_cast<MachOObjectFile*>(
+ ObjectFile::createMachOObjectFile(Buff.take())));
+ MachOObject *MachOObj = MachOOF->getObject();
+
+ const Target *TheTarget = GetTarget(MachOObj);
+ 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));
+ OwningPtr<const MCRegisterInfo> MRI(TheTarget->createMCRegInfo(TripleName));
+ int AsmPrinterVariant = AsmInfo->getAssemblerDialect();
+ OwningPtr<MCInstPrinter>
+ IP(TheTarget->createMCInstPrinter(AsmPrinterVariant, *AsmInfo, *InstrInfo,
+ *MRI, *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;
+ if (SymtabLCI) {
+ MachOObj->ReadSymtabLoadCommand(*SymtabLCI, SymtabLC);
+ MachOObj->RegisterStringTable(*SymtabLC);
+ }
+
+ std::vector<SectionRef> Sections;
+ std::vector<SymbolRef> Symbols;
+ SmallVector<uint64_t, 8> FoundFns;
+
+ getSectionsAndSymbols(Header, MachOOF.get(), &SymtabLC, Sections, Symbols,
+ FoundFns);
+
+ // Make a copy of the unsorted symbol list. FIXME: duplication
+ std::vector<SymbolRef> UnsortedSymbols(Symbols);
+ // Sort the symbols by address, just in case they didn't come in that way.
+ std::sort(Symbols.begin(), Symbols.end(), SymbolSorter());
+
+#ifndef NDEBUG
+ raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls();
+#else
+ raw_ostream &DebugOut = nulls();
+#endif
+
+ StringRef DebugAbbrevSection, DebugInfoSection, DebugArangesSection,
+ DebugLineSection, DebugStrSection;
+ OwningPtr<DIContext> diContext;
+ OwningPtr<MachOObjectFile> DSYMObj;
+ MachOObject *DbgInfoObj = MachOObj;
+ // Try to find debug info and set up the DIContext for it.
+ if (UseDbg) {
+ ArrayRef<SectionRef> DebugSections = Sections;
+ std::vector<SectionRef> 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(static_cast<MachOObjectFile*>(
+ ObjectFile::createMachOObjectFile(Buf.take())));
+ const macho::Header &Header = DSYMObj->getObject()->getHeader();
+
+ std::vector<SymbolRef> Symbols;
+ SmallVector<uint64_t, 8> FoundFns;
+ getSectionsAndSymbols(Header, DSYMObj.get(), 0, DSYMSections, Symbols,
+ FoundFns);
+ DebugSections = DSYMSections;
+ DbgInfoObj = DSYMObj.get()->getObject();
+ }
+
+ // Find the named debug info sections.
+ for (unsigned SectIdx = 0; SectIdx != DebugSections.size(); SectIdx++) {
+ StringRef SectName;
+ if (!DebugSections[SectIdx].getName(SectName)) {
+ if (SectName.equals("__DWARF,__debug_abbrev"))
+ DebugSections[SectIdx].getContents(DebugAbbrevSection);
+ else if (SectName.equals("__DWARF,__debug_info"))
+ DebugSections[SectIdx].getContents(DebugInfoSection);
+ else if (SectName.equals("__DWARF,__debug_aranges"))
+ DebugSections[SectIdx].getContents(DebugArangesSection);
+ else if (SectName.equals("__DWARF,__debug_line"))
+ DebugSections[SectIdx].getContents(DebugLineSection);
+ else if (SectName.equals("__DWARF,__debug_str"))
+ DebugSections[SectIdx].getContents(DebugStrSection);
+ }
+ }
+
+ // 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++) {
+ StringRef SectName;
+ if (Sections[SectIdx].getName(SectName) ||
+ SectName.compare("__TEXT,__text"))
+ continue; // Skip non-text sections
+
+ // Insert the functions from the function starts segment into our map.
+ uint64_t VMAddr;
+ Sections[SectIdx].getAddress(VMAddr);
+ for (unsigned i = 0, e = FoundFns.size(); i != e; ++i) {
+ StringRef SectBegin;
+ Sections[SectIdx].getContents(SectBegin);
+ uint64_t Offset = (uint64_t)SectBegin.data();
+ FunctionMap.insert(std::make_pair(VMAddr + FoundFns[i]-Offset,
+ (MCFunction*)0));
+ }
+
+ StringRef Bytes;
+ Sections[SectIdx].getContents(Bytes);
+ StringRefMemoryObject memoryObject(Bytes);
+ bool symbolTableWorked = false;
+
+ // Parse relocations.
+ std::vector<std::pair<uint64_t, SymbolRef> > Relocs;
+ error_code ec;
+ for (relocation_iterator RI = Sections[SectIdx].begin_relocations(),
+ RE = Sections[SectIdx].end_relocations(); RI != RE; RI.increment(ec)) {
+ uint64_t RelocOffset, SectionAddress;
+ RI->getAddress(RelocOffset);
+ Sections[SectIdx].getAddress(SectionAddress);
+ RelocOffset -= SectionAddress;
+
+ SymbolRef RelocSym;
+ RI->getSymbol(RelocSym);
+
+ Relocs.push_back(std::make_pair(RelocOffset, RelocSym));
+ }
+ array_pod_sort(Relocs.begin(), Relocs.end());
+
+ // Disassemble symbol by symbol.
+ for (unsigned SymIdx = 0; SymIdx != Symbols.size(); SymIdx++) {
+ StringRef SymName;
+ Symbols[SymIdx].getName(SymName);
+
+ SymbolRef::Type ST;
+ Symbols[SymIdx].getType(ST);
+ if (ST != SymbolRef::ST_Function)
+ continue;
+
+ // Make sure the symbol is defined in this section.
+ bool containsSym = false;
+ Sections[SectIdx].containsSymbol(Symbols[SymIdx], containsSym);
+ if (!containsSym)
+ continue;
+
+ // Start at the address of the symbol relative to the section's address.
+ uint64_t SectionAddress = 0;
+ uint64_t Start = 0;
+ Sections[SectIdx].getAddress(SectionAddress);
+ Symbols[SymIdx].getAddress(Start);
+ Start -= SectionAddress;
+
+ // Stop disassembling either at the beginning of the next symbol or at
+ // the end of the section.
+ bool containsNextSym = false;
+ uint64_t NextSym = 0;
+ uint64_t NextSymIdx = SymIdx+1;
+ while (Symbols.size() > NextSymIdx) {
+ SymbolRef::Type NextSymType;
+ Symbols[NextSymIdx].getType(NextSymType);
+ if (NextSymType == SymbolRef::ST_Function) {
+ Sections[SectIdx].containsSymbol(Symbols[NextSymIdx],
+ containsNextSym);
+ Symbols[NextSymIdx].getAddress(NextSym);
+ NextSym -= SectionAddress;
+ break;
+ }
+ ++NextSymIdx;
+ }
+
+ uint64_t SectSize;
+ Sections[SectIdx].getSize(SectSize);
+ uint64_t End = containsNextSym ? NextSym : SectSize;
+ uint64_t Size;
+
+ symbolTableWorked = true;
+
+ if (!CFG) {
+ // Normal disassembly, print addresses, bytes and mnemonic form.
+ StringRef SymName;
+ Symbols[SymIdx].getName(SymName);
+
+ outs() << SymName << ":\n";
+ DILineInfo lastLine;
+ for (uint64_t Index = Start; Index < End; Index += Size) {
+ MCInst Inst;
+
+ if (DisAsm->getInstruction(Inst, Size, memoryObject, Index,
+ DebugOut, nulls())) {
+ uint64_t SectAddress = 0;
+ Sections[SectIdx].getAddress(SectAddress);
+ outs() << format("%8" PRIx64 ":\t", SectAddress + Index);
+
+ DumpBytes(StringRef(Bytes.data() + Index, Size));
+ IP->printInst(&Inst, outs(), "");
+
+ // Print debug info.
+ if (diContext) {
+ DILineInfo dli =
+ diContext->getLineInfoForAddress(SectAddress + 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.
+ StringRef SymName;
+ Symbols[SymIdx].getName(SymName);
+ createMCFunctionAndSaveCalls(
+ SymName, DisAsm.get(), memoryObject, Start, End,
+ InstrAnalysis.get(), Start, DebugOut, FunctionMap, Functions);
+ }
+ }
+ if (!CFG && !symbolTableWorked) {
+ // Reading the symbol table didn't work, disassemble the whole section.
+ uint64_t SectAddress;
+ Sections[SectIdx].getAddress(SectAddress);
+ uint64_t SectSize;
+ Sections[SectIdx].getSize(SectSize);
+ uint64_t InstSize;
+ for (uint64_t Index = 0; Index < SectSize; Index += InstSize) {
+ MCInst Inst;
+
+ if (DisAsm->getInstruction(Inst, InstSize, memoryObject, Index,
+ DebugOut, nulls())) {
+ outs() << format("%8" PRIx64 ":\t", SectAddress + Index);
+ DumpBytes(StringRef(Bytes.data() + Index, InstSize));
+ IP->printInst(&Inst, outs(), "");
+ outs() << "\n";
+ } else {
+ errs() << "llvm-objdump: warning: invalid instruction encoding\n";
+ if (InstSize == 0)
+ InstSize = 1; // skip illegible bytes
+ }
+ }
+ }
+
+ if (CFG) {
+ if (!symbolTableWorked) {
+ // Reading the symbol table didn't work, create a big __TEXT symbol.
+ uint64_t SectSize = 0, SectAddress = 0;
+ Sections[SectIdx].getSize(SectSize);
+ Sections[SectIdx].getAddress(SectAddress);
+ createMCFunctionAndSaveCalls("__TEXT", DisAsm.get(), memoryObject,
+ 0, SectSize,
+ InstrAnalysis.get(),
+ SectAddress, 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.
+ uint64_t SectSize = 0;
+ Sections[SectIdx].getSize(SectSize);
+
+ SmallVector<uint64_t, 16> Calls;
+ MCFunction f =
+ MCFunction::createFunctionFromMC("unknown", DisAsm.get(),
+ memoryObject, mi->first,
+ SectSize,
+ 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;
+ }
+
+ uint64_t SectSize = 0, SectAddress;
+ Sections[SectIdx].getSize(SectSize);
+ Sections[SectIdx].getAddress(SectAddress);
+
+ // No predecessors, this is a data block. Print as .byte directives.
+ if (!hasPreds) {
+ uint64_t End = llvm::next(fi) == fe ? SectSize :
+ llvm::next(fi)->first;
+ outs() << "# " << End-fi->first << " bytes of data:\n";
+ for (unsigned pos = fi->first; pos != End; ++pos) {
+ outs() << format("%8x:\t", SectAddress + 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(SectAddress + Inst.Address) !=
+ FunctionMap.end())
+ outs() << FunctionMap[SectAddress + Inst.Address]-> getName()
+ << ":\n";
+
+ outs() << format("%8" PRIx64 ":\t", SectAddress + 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 >= SectAddress + Inst.Address &&
+ Relocs[j].first < SectAddress + Inst.Address + Inst.Size) {
+ StringRef SymName;
+ uint64_t Addr;
+ Relocs[j].second.getAddress(Addr);
+ Relocs[j].second.getName(SymName);
+
+ outs() << "\t# " << SymName << ' ';
+ DumpAddress(Addr, Sections, MachOObj, 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, outs());
+
+ // Print debug info.
+ if (diContext) {
+ DILineInfo dli =
+ diContext->getLineInfoForAddress(SectAddress + 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/llvm-objdump.cpp b/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp
new file mode 100644
index 0000000..b431c76
--- /dev/null
+++ b/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp
@@ -0,0 +1,656 @@
+//===-- 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/COFF.h"
+#include "llvm/Object/ObjectFile.h"
+#include "llvm/ADT/OwningPtr.h"
+#include "llvm/ADT/StringExtras.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/MCInstrInfo.h"
+#include "llvm/MC/MCRegisterInfo.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 <cctype>
+#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>
+SectionContents("s", cl::desc("Display the content of each section"));
+
+static cl::opt<bool>
+SymbolTable("t", cl::desc("Display the symbol table"));
+
+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 TheTriple("unknown-unknown-unknown");
+ if (TripleName.empty()) {
+ if (Obj)
+ TheTriple.setArch(Triple::ArchType(Obj->getArch()));
+ } else
+ TheTriple.setTriple(Triple::normalize(TripleName));
+
+ // Get the target specific parser.
+ std::string Error;
+ const Target *TheTarget = TargetRegistry::lookupTarget(ArchName, TheTriple,
+ Error);
+ if (!TheTarget) {
+ errs() << ToolName << ": " << Error;
+ return 0;
+ }
+
+ // Update the triple name and return the found target.
+ TripleName = TheTriple.getTriple();
+ return TheTarget;
+}
+
+void llvm::StringRefMemoryObject::anchor() { }
+
+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);
+ // getTarget() will have already issued a diagnostic if necessary, so
+ // just bail here if it failed.
+ if (!TheTarget)
+ return;
+
+ 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->getAddress(Address))) break;
+ Address -= SectionAddr;
+
+ 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;
+ }
+
+ OwningPtr<const MCRegisterInfo> MRI(TheTarget->createMCRegInfo(TripleName));
+ if (!MRI) {
+ errs() << "error: no register info for target " << TripleName << "\n";
+ return;
+ }
+
+ OwningPtr<const MCInstrInfo> MII(TheTarget->createMCInstrInfo());
+ if (!MII) {
+ errs() << "error: no instruction info for target " << TripleName << "\n";
+ return;
+ }
+
+ int AsmPrinterVariant = AsmInfo->getAssemblerDialect();
+ OwningPtr<MCInstPrinter> IP(TheTarget->createMCInstPrinter(
+ AsmPrinterVariant, *AsmInfo, *MII, *MRI, *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) {
+ bool hidden = false;
+ uint64_t addr;
+ SmallString<16> name;
+ SmallString<32> val;
+
+ // If this relocation is hidden, skip it.
+ if (error(rel_cur->getHidden(hidden))) goto skip_print_rel;
+ if (hidden) goto skip_print_rel;
+
+ 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;
+
+ bool hidden;
+ uint64_t address;
+ SmallString<32> relocname;
+ SmallString<32> valuestr;
+ if (error(ri->getHidden(hidden))) continue;
+ if (hidden) continue;
+ 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 PrintSectionContents(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;
+ StringRef Name;
+ StringRef Contents;
+ uint64_t BaseAddr;
+ if (error(si->getName(Name))) continue;
+ if (error(si->getContents(Contents))) continue;
+ if (error(si->getAddress(BaseAddr))) continue;
+
+ outs() << "Contents of section " << Name << ":\n";
+
+ // Dump out the content as hex and printable ascii characters.
+ for (std::size_t addr = 0, end = Contents.size(); addr < end; addr += 16) {
+ outs() << format(" %04" PRIx64 " ", BaseAddr + addr);
+ // Dump line of hex.
+ for (std::size_t i = 0; i < 16; ++i) {
+ if (i != 0 && i % 4 == 0)
+ outs() << ' ';
+ if (addr + i < end)
+ outs() << hexdigit((Contents[addr + i] >> 4) & 0xF, true)
+ << hexdigit(Contents[addr + i] & 0xF, true);
+ else
+ outs() << " ";
+ }
+ // Print ascii.
+ outs() << " ";
+ for (std::size_t i = 0; i < 16 && addr + i < end; ++i) {
+ if (std::isprint(Contents[addr + i] & 0xFF))
+ outs() << Contents[addr + i];
+ else
+ outs() << ".";
+ }
+ outs() << "\n";
+ }
+ }
+}
+
+static void PrintCOFFSymbolTable(const COFFObjectFile *coff) {
+ const coff_file_header *header;
+ if (error(coff->getHeader(header))) return;
+ int aux_count = 0;
+ const coff_symbol *symbol = 0;
+ for (int i = 0, e = header->NumberOfSymbols; i != e; ++i) {
+ if (aux_count--) {
+ // Figure out which type of aux this is.
+ if (symbol->StorageClass == COFF::IMAGE_SYM_CLASS_STATIC
+ && symbol->Value == 0) { // Section definition.
+ const coff_aux_section_definition *asd;
+ if (error(coff->getAuxSymbol<coff_aux_section_definition>(i, asd)))
+ return;
+ outs() << "AUX "
+ << format("scnlen 0x%x nreloc %d nlnno %d checksum 0x%x "
+ , unsigned(asd->Length)
+ , unsigned(asd->NumberOfRelocations)
+ , unsigned(asd->NumberOfLinenumbers)
+ , unsigned(asd->CheckSum))
+ << format("assoc %d comdat %d\n"
+ , unsigned(asd->Number)
+ , unsigned(asd->Selection));
+ } else
+ outs() << "AUX Unknown\n";
+ } else {
+ StringRef name;
+ if (error(coff->getSymbol(i, symbol))) return;
+ if (error(coff->getSymbolName(symbol, name))) return;
+ outs() << "[" << format("%2d", i) << "]"
+ << "(sec " << format("%2d", int(symbol->SectionNumber)) << ")"
+ << "(fl 0x00)" // Flag bits, which COFF doesn't have.
+ << "(ty " << format("%3x", unsigned(symbol->Type)) << ")"
+ << "(scl " << format("%3x", unsigned(symbol->StorageClass)) << ") "
+ << "(nx " << unsigned(symbol->NumberOfAuxSymbols) << ") "
+ << "0x" << format("%08x", unsigned(symbol->Value)) << " "
+ << name << "\n";
+ aux_count = symbol->NumberOfAuxSymbols;
+ }
+ }
+}
+
+static void PrintSymbolTable(const ObjectFile *o) {
+ outs() << "SYMBOL TABLE:\n";
+
+ if (const COFFObjectFile *coff = dyn_cast<const COFFObjectFile>(o))
+ PrintCOFFSymbolTable(coff);
+ else {
+ error_code ec;
+ for (symbol_iterator si = o->begin_symbols(),
+ se = o->end_symbols(); si != se; si.increment(ec)) {
+ if (error(ec)) return;
+ StringRef Name;
+ uint64_t Address;
+ SymbolRef::Type Type;
+ uint64_t Size;
+ uint32_t Flags;
+ section_iterator Section = o->end_sections();
+ if (error(si->getName(Name))) continue;
+ if (error(si->getAddress(Address))) continue;
+ if (error(si->getFlags(Flags))) continue;
+ if (error(si->getType(Type))) continue;
+ if (error(si->getSize(Size))) continue;
+ if (error(si->getSection(Section))) continue;
+
+ bool Global = Flags & SymbolRef::SF_Global;
+ bool Weak = Flags & SymbolRef::SF_Weak;
+ bool Absolute = Flags & SymbolRef::SF_Absolute;
+
+ if (Address == UnknownAddressOrSize)
+ Address = 0;
+ if (Size == UnknownAddressOrSize)
+ Size = 0;
+ char GlobLoc = ' ';
+ if (Type != SymbolRef::ST_Unknown)
+ GlobLoc = Global ? 'g' : 'l';
+ char Debug = (Type == SymbolRef::ST_Debug || Type == SymbolRef::ST_File)
+ ? 'd' : ' ';
+ char FileFunc = ' ';
+ if (Type == SymbolRef::ST_File)
+ FileFunc = 'f';
+ else if (Type == SymbolRef::ST_Function)
+ FileFunc = 'F';
+
+ outs() << format("%08" PRIx64, Address) << " "
+ << GlobLoc // Local -> 'l', Global -> 'g', Neither -> ' '
+ << (Weak ? 'w' : ' ') // Weak?
+ << ' ' // Constructor. Not supported yet.
+ << ' ' // Warning. Not supported yet.
+ << ' ' // Indirect reference to another symbol.
+ << Debug // Debugging (d) or dynamic (D) symbol.
+ << FileFunc // Name of function (F), file (f) or object (O).
+ << ' ';
+ if (Absolute)
+ outs() << "*ABS*";
+ else if (Section == o->end_sections())
+ outs() << "*UND*";
+ else {
+ StringRef SectionName;
+ if (error(Section->getName(SectionName)))
+ SectionName = "";
+ outs() << SectionName;
+ }
+ outs() << '\t'
+ << format("%08" PRIx64 " ", Size)
+ << Name
+ << '\n';
+ }
+ }
+}
+
+static void DumpObject(const ObjectFile *o) {
+ outs() << '\n';
+ outs() << o->getFileName()
+ << ":\tfile format " << o->getFileFormatName() << "\n\n";
+
+ if (Disassemble)
+ DisassembleObject(o, Relocations);
+ if (Relocations && !Disassemble)
+ PrintRelocations(o);
+ if (SectionHeaders)
+ PrintSectionHeaders(o);
+ if (SectionContents)
+ PrintSectionContents(o);
+ if (SymbolTable)
+ PrintSymbolTable(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)) {
+ // Ignore non-object files.
+ if (ec != object_error::invalid_file_type)
+ 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();
+
+ // Register the target printer for --version.
+ cl::AddExtraVersionPrinter(TargetRegistry::printRegisteredTargetsForVersion);
+
+ 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
+ && !SectionContents
+ && !SymbolTable) {
+ 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..aa71b77
--- /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 {
+ virtual void anchor();
+ 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
OpenPOWER on IntegriCloud