Initial dsymutil tool commit.

The goal of this tool is to replicate Darwin's dsymutil functionality
based on LLVM. dsymutil is a DWARF linker. Darwin's linker (ld64) does
not link the debug information, it leaves it in the object files in
relocatable form, but embbeds a `debug map` into the executable that
describes where to find the debug information and how to relocate it.
When releasing/archiving a binary, dsymutil is called to link all the DWARF
information into a `dsym bundle` that can distributed/stored along with
the binary.

With this commit, the LLVM based dsymutil is just able to parse the STABS
debug maps embedded by ld64 in linked binaries (and not all of them, for
example archives aren't supported yet).

Note that the tool directory is called dsymutil, but the executable is
currently called llvm-dsymutil. This discrepancy will disappear once the
tool will be feature complete. At this point the executable will be renamed
to dsymutil, but until then you do not want it to override the system one.

    Differential Revision: http://reviews.llvm.org/D6242

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@224134 91177308-0d34-0410-b5e6-96231b3b80d8

test/CMakeLists.txt

@@ -30,6 +30,7 @@ set(LLVM_TEST_DEPENDS
           llvm-cov
           llvm-diff
           llvm-dis
+          llvm-dsymutil
           llvm-dwarfdump
           llvm-extract
           llvm-link

test/lit.cfg

@@ -229,6 +229,7 @@ for pattern in [r"\bbugpoint\b(?!-)",
                 r"\bllvm-cov\b",
                 r"\bllvm-diff\b",
                 r"\bllvm-dis\b",
+                r"\bllvm-dsymutil\b",
                 r"\bllvm-dwarfdump\b",
                 r"\bllvm-extract\b",
                 r"\bllvm-go\b",

test/tools/dsymutil/Inputs/basic1.c

@@ -0,0 +1,25 @@
+/* This is the main file used to produce the basic* objects that are
+   used for the dsymutil tests.
+
+   These are compiled in a couple of different ways (always on a
+   Darwin system):
+   Basic compilation:
+      for FILE in basic1.c basic2.c basic3.c; do
+         clang -g -c $FILE -o ${FILE%.c}.macho.x86_64.o
+      done
+      clang basic1.macho.x86_64.o basic2.macho.x86_64.o basic3.macho.x86_64.o -o basic.macho.x86_64 -Wl,-dead_strip
+
+   LTO compilation:
+      for FILE in basic1.c basic2.c basic3.c; do
+         clang -g -c -flto $FILE -o ${FILE%.c}-lto.o
+      done
+      clang basic1-lto.o basic2-lto.o basic3-lto.o -o basic-lto.macho.x86_64 -Wl,-object_path_lto,$PWD/basic-lto.macho.x86_64.o -Wl,-dead_strip
+      rm basic1-lto.o basic2-lto.o basic3-lto.o
+
+*/
+
+int foo(int);
+
+int main(int argc, const char *argv[]) {
+  return foo(argc);
+}

test/tools/dsymutil/Inputs/basic2.c

@@ -0,0 +1,22 @@
+/* For compilation instructions see basic1.c. */
+
+static int baz = 42;
+static int private_int;
+extern volatile int val;
+int unused_data = 1;
+
+int bar(int);
+
+void unused1() {
+  bar(baz);
+}
+
+static int inc() {
+  return ++private_int;
+}
+
+__attribute__((noinline))
+int foo(int arg) {
+  return bar(arg+val) + inc() + baz++;
+}
+

test/tools/dsymutil/Inputs/basic3.c

@@ -0,0 +1,20 @@
+/* For compilation instructions see basic1.c. */
+
+volatile int val;
+
+extern int foo(int);
+
+int unused2() {
+  return foo(val);
+}
+
+static int inc() {
+  return ++val;
+}
+
+__attribute__((noinline))
+int bar(int arg) {
+  if (arg > 42)
+    return inc();
+  return foo(val + arg);
+}

test/tools/dsymutil/debug-map-parsing.test

@@ -0,0 +1,48 @@
+RUN: llvm-dsymutil -v -parse-only -oso-prepend-path=%p %p/Inputs/basic.macho.x86_64 | FileCheck %s
+RUN: llvm-dsymutil -v -parse-only -oso-prepend-path=%p %p/Inputs/basic-lto.macho.x86_64 | FileCheck %s --check-prefix=CHECK-LTO
+RUN: llvm-dsymutil -v -parse-only %p/Inputs/basic.macho.x86_64 2>&1 | FileCheck %s --check-prefix=NOT-FOUND
+RUN: not llvm-dsymutil -v -parse-only %p/Inputs/inexistant 2>&1 | FileCheck %s --check-prefix=NO-EXECUTABLE
+Check that We can parse the debug map of the basic executable.
+
+CHECK-NOT: error
+CHECK: DEBUG MAP:
+CHECK: /Inputs/basic1.macho.x86_64.o:
+CHECK: 	0000000000000000 => 0000000100000ea0	_main
+CHECK: /Inputs/basic2.macho.x86_64.o:
+CHECK: 	0000000000000310 => 0000000100001000	_baz
+CHECK: 	0000000000000020 => 0000000100000ed0	_foo
+CHECK: 	0000000000000070 => 0000000100000f20	_inc
+CHECK: 	0000000000000560 => 0000000100001008	_private_int
+CHECK: /Inputs/basic3.macho.x86_64.o:
+CHECK: 	0000000000000020 => 0000000100000f40	_bar
+CHECK: 	0000000000000070 => 0000000100000f90	_inc
+CHECK: 	0000000000000004 => 0000000100001004	_val
+CHECK: END DEBUG MAP
+
+
+Check that we can parse the debug-map of the basic-lto executable
+
+CHECK-LTO-NOT: error
+CHECK-LTO: DEBUG MAP:
+CHECK-LTO: /Inputs/basic-lto.macho.x86_64.o:
+CHECK-LTO: 	0000000000000050 => 0000000100000f90	_bar
+CHECK-LTO: 	0000000000000658 => 0000000100001000	_baz
+CHECK-LTO: 	0000000000000010 => 0000000100000f50	_foo
+CHECK-LTO: 	0000000000000000 => 0000000100000f40	_main
+CHECK-LTO: 	00000000000008e8 => 0000000100001008	_private_int
+CHECK-LTO: 	00000000000008ec => 0000000100001004	_val
+CHECK-LTO: END DEBUG MAP
+
+Check that we warn about missing object files (this presumes that the files aren't
+present in the machine's /Inputs/ folder, which should be a pretty safe bet).
+
+NOT-FOUND: cannot open{{.*}}"/Inputs/basic1.macho.x86_64.o": No such file
+NOT-FOUND: cannot open{{.*}}"/Inputs/basic2.macho.x86_64.o": No such file
+NOT-FOUND: cannot open{{.*}}"/Inputs/basic3.macho.x86_64.o": No such file
+NOT-FOUND: DEBUG MAP:
+NOT-FOUND-NEXT: END DEBUG MAP
+
+Check that we correctly error out on invalid executatble.
+
+NO-EXECUTABLE: cannot parse{{.*}}/inexistant": No such file
+NO-EXECUTABLE-NOT: DEBUG MAP

tools/CMakeLists.txt

@@ -36,6 +36,7 @@ add_llvm_tool_subdirectory(llvm-objdump)
 add_llvm_tool_subdirectory(llvm-readobj)
 add_llvm_tool_subdirectory(llvm-rtdyld)
 add_llvm_tool_subdirectory(llvm-dwarfdump)
+add_llvm_tool_subdirectory(dsymutil)
 add_llvm_tool_subdirectory(llvm-vtabledump)
 if( LLVM_USE_INTEL_JITEVENTS )
   add_llvm_tool_subdirectory(llvm-jitlistener)

tools/LLVMBuild.txt

@@ -16,7 +16,7 @@
 ;===------------------------------------------------------------------------===;
 
 [common]
-subdirectories = bugpoint llc lli llvm-ar llvm-as llvm-bcanalyzer llvm-cov llvm-diff llvm-dis llvm-dwarfdump llvm-extract llvm-jitlistener llvm-link llvm-lto llvm-mc llvm-nm llvm-objdump llvm-profdata llvm-rtdyld llvm-size macho-dump opt llvm-mcmarkup verify-uselistorder
+subdirectories = bugpoint llc lli llvm-ar llvm-as llvm-bcanalyzer llvm-cov llvm-diff llvm-dis llvm-dwarfdump llvm-extract llvm-jitlistener llvm-link llvm-lto llvm-mc llvm-nm llvm-objdump llvm-profdata llvm-rtdyld llvm-size macho-dump opt llvm-mcmarkup verify-uselistorder dsymutil
 
 [component_0]
 type = Group

tools/Makefile

@@ -33,7 +33,7 @@ PARALLEL_DIRS := opt llvm-as llvm-dis llc llvm-ar llvm-nm llvm-link \
                  macho-dump llvm-objdump llvm-readobj llvm-rtdyld \
                  llvm-dwarfdump llvm-cov llvm-size llvm-stress llvm-mcmarkup \
                  llvm-profdata llvm-symbolizer obj2yaml yaml2obj llvm-c-test \
-                 llvm-vtabledump verify-uselistorder
+                 llvm-vtabledump verify-uselistorder dsymutil
 
 # If Intel JIT Events support is configured, build an extra tool to test it.
 ifeq ($(USE_INTEL_JITEVENTS), 1)

tools/dsymutil/CMakeLists.txt

@@ -0,0 +1,12 @@
+set(LLVM_LINK_COMPONENTS
+  Object
+  Support
+  )
+
+add_llvm_tool(llvm-dsymutil
+  dsymutil.cpp
+  DebugMap.cpp
+  DwarfLinker.cpp
+  MachODebugMapParser.cpp
+  )
+

tools/dsymutil/DebugMap.cpp

@@ -0,0 +1,81 @@
+//===- tools/dsymutil/DebugMap.cpp - Generic debug map representation -----===//
+//
+//                             The LLVM Linker
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+#include "DebugMap.h"
+
+#include "llvm/ADT/iterator_range.h"
+#include "llvm/ADT/STLExtras.h"
+#include "llvm/Support/DataTypes.h"
+#include "llvm/Support/Format.h"
+#include "llvm/Support/raw_ostream.h"
+#include <algorithm>
+
+namespace llvm {
+namespace dsymutil {
+
+using namespace llvm::object;
+
+DebugMapObject::DebugMapObject(StringRef ObjectFilename)
+    : Filename(ObjectFilename) {}
+
+bool DebugMapObject::addSymbol(StringRef Name, uint64_t ObjectAddress,
+                               uint64_t LinkedAddress) {
+  auto InsertResult = Symbols.insert(
+      std::make_pair(Name, SymbolMapping(ObjectAddress, LinkedAddress)));
+  return InsertResult.second;
+}
+
+void DebugMapObject::print(raw_ostream &OS) const {
+  OS << getObjectFilename() << ":\n";
+  // Sort the symbols in alphabetical order, like llvm-nm (and to get
+  // deterministic output for testing).
+  typedef std::pair<StringRef, SymbolMapping> Entry;
+  std::vector<Entry> Entries;
+  Entries.reserve(Symbols.getNumItems());
+  for (const auto &Sym : make_range(Symbols.begin(), Symbols.end()))
+    Entries.push_back(std::make_pair(Sym.getKey(), Sym.getValue()));
+  std::sort(
+      Entries.begin(), Entries.end(),
+      [](const Entry &LHS, const Entry &RHS) { return LHS.first < RHS.first; });
+  for (const auto &Sym : Entries) {
+    OS << format("\t%016" PRIx64 " => %016" PRIx64 "\t%s\n",
+                 Sym.second.ObjectAddress, Sym.second.BinaryAddress,
+                 Sym.first.data());
+  }
+  OS << '\n';
+}
+
+#ifndef NDEBUG
+void DebugMapObject::dump() const { print(errs()); }
+#endif
+
+DebugMapObject &DebugMap::addDebugMapObject(StringRef ObjectFilePath) {
+  Objects.emplace_back(new DebugMapObject(ObjectFilePath));
+  return *Objects.back();
+}
+
+const DebugMapObject::SymbolMapping *
+DebugMapObject::lookupSymbol(StringRef SymbolName) const {
+  StringMap<SymbolMapping>::const_iterator Sym = Symbols.find(SymbolName);
+  if (Sym == Symbols.end())
+    return nullptr;
+  return &Sym->getValue();
+}
+
+void DebugMap::print(raw_ostream &OS) const {
+  OS << "DEBUG MAP:   object addr =>  executable addr\tsymbol name\n";
+  for (const auto &Obj : objects())
+    Obj->print(OS);
+  OS << "END DEBUG MAP\n";
+}
+
+#ifndef NDEBUG
+void DebugMap::dump() const { print(errs()); }
+#endif
+}
+}

tools/dsymutil/DebugMap.h

@@ -0,0 +1,128 @@
+//===- tools/dsymutil/DebugMap.h - Generic debug map representation -------===//
+//
+//                             The LLVM Linker
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+///
+/// \file
+///
+/// This file contains the class declaration of the DebugMap
+/// entity. A DebugMap lists all the object files linked together to
+/// produce an executable along with the linked address of all the
+/// atoms used in these object files.
+/// The DebugMap is an input to the DwarfLinker class that will
+/// extract the Dwarf debug information from the referenced object
+/// files and link their usefull debug info together.
+///
+//===----------------------------------------------------------------------===//
+#ifndef LLVM_TOOLS_DSYMUTIL_DEBUGMAP_H
+#define LLVM_TOOLS_DSYMUTIL_DEBUGMAP_H
+
+#include "llvm/ADT/StringMap.h"
+#include "llvm/Object/ObjectFile.h"
+#include "llvm/Support/ErrorOr.h"
+#include "llvm/Support/Format.h"
+#include "llvm/ADT/iterator_range.h"
+#include <vector>
+
+namespace llvm {
+class raw_ostream;
+
+namespace dsymutil {
+class DebugMapObject;
+
+/// \brief The DebugMap object stores the list of object files to
+/// query for debug information along with the mapping between the
+/// symbols' addresses in the object file to their linked address in
+/// the linked binary.
+///
+/// A DebugMap producer could look like this:
+/// DebugMap *DM = new DebugMap();
+/// for (const auto &Obj: LinkedObjects) {
+///     DebugMapObject &DMO = DM->addDebugMapObject(Obj.getPath());
+///     for (const auto &Sym: Obj.getLinkedSymbols())
+///         DMO.addSymbol(Sym.getName(), Sym.getObjectFileAddress(),
+///                       Sym.getBinaryAddress());
+/// }
+///
+/// A DebugMap consumer can then use the map to link the debug
+/// information. For example something along the lines of:
+/// for (const auto &DMO: DM->objects()) {
+///     auto Obj = createBinary(DMO.getObjectFilename());
+///     for (auto &DIE: Obj.getDwarfDIEs()) {
+///         if (SymbolMapping *Sym = DMO.lookup(DIE.getName()))
+///             DIE.relocate(Sym->ObjectAddress, Sym->BinaryAddress);
+///         else
+///             DIE.discardSubtree();
+///     }
+/// }
+class DebugMap {
+  typedef std::vector<std::unique_ptr<DebugMapObject>> ObjectContainer;
+  ObjectContainer Objects;
+
+public:
+  typedef ObjectContainer::const_iterator const_iterator;
+
+  iterator_range<const_iterator> objects() const {
+    return make_range(begin(), end());
+  }
+
+  const_iterator begin() const { return Objects.begin(); }
+
+  const_iterator end() const { return Objects.end(); }
+
+  /// This function adds an DebugMapObject to the list owned by this
+  /// debug map.
+  DebugMapObject &addDebugMapObject(StringRef ObjectFilePath);
+
+  void print(raw_ostream &OS) const;
+
+#ifndef NDEBUG
+  void dump() const;
+#endif
+};
+
+/// \brief The DebugMapObject represents one object file described by
+/// the DebugMap. It contains a list of mappings between addresses in
+/// the object file and in the linked binary for all the linked atoms
+/// in this object file.
+class DebugMapObject {
+public:
+  struct SymbolMapping {
+    uint64_t ObjectAddress;
+    uint64_t BinaryAddress;
+    SymbolMapping(uint64_t ObjectAddress, uint64_t BinaryAddress)
+        : ObjectAddress(ObjectAddress), BinaryAddress(BinaryAddress) {}
+  };
+
+  /// \brief Adds a symbol mapping to this DebugMapObject.
+  /// \returns false if the symbol was already registered. The request
+  /// is discarded in this case.
+  bool addSymbol(llvm::StringRef SymName, uint64_t ObjectAddress,
+                 uint64_t LinkedAddress);
+
+  /// \bried Lookup a symbol mapping.
+  /// \returns null if the symbol isn't found.
+  const SymbolMapping *lookupSymbol(StringRef SymbolName) const;
+
+  llvm::StringRef getObjectFilename() const { return Filename; }
+
+  void print(raw_ostream &OS) const;
+#ifndef NDEBUG
+  void dump() const;
+#endif
+private:
+  friend class DebugMap;
+  /// DebugMapObjects can only be constructed by the owning DebugMap.
+  DebugMapObject(StringRef ObjectFilename);
+
+  std::string Filename;
+  StringMap<SymbolMapping> Symbols;
+};
+}
+}
+
+#endif // LLVM_TOOLS_DSYMUTIL_DEBUGMAP_H

tools/dsymutil/DwarfLinker.cpp

@@ -0,0 +1,20 @@
+//===- tools/dsymutil/DwarfLinker.cpp - Dwarf debug info linker -----------===//
+//
+//                             The LLVM Linker
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+#include "DebugMap.h"
+#include "dsymutil.h"
+
+namespace llvm {
+namespace dsymutil {
+
+bool linkDwarf(StringRef OutputFilename, const DebugMap &DM) {
+  // Do nothing for now.
+  return true;
+}
+}
+}

tools/dsymutil/LLVMBuild.txt

@@ -0,0 +1,22 @@
+;===- ./tools/dsymutil/LLVMBuild.txt ---------------------*- Conf -*--===;
+;
+;                     The LLVM Compiler Infrastructure
+;
+; This file is distributed under the University of Illinois Open Source
+; License. See LICENSE.TXT for details.
+;
+;===------------------------------------------------------------------------===;
+;
+; This is an LLVMBuild description file for the components in this subdirectory.
+;
+; For more information on the LLVMBuild system, please see:
+;
+;   http://llvm.org/docs/LLVMBuild.html
+;
+;===------------------------------------------------------------------------===;
+
+[component_0]
+type = Tool
+name = llvm-dsymutil
+parent = Tools
+required_libraries = Object Support

tools/dsymutil/MachODebugMapParser.cpp

@@ -0,0 +1,247 @@
+//===- tools/dsymutil/MachODebugMapParser.cpp - Parse STABS debug maps ----===//
+//
+//                             The LLVM Linker
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "DebugMap.h"
+#include "dsymutil.h"
+#include "llvm/Object/MachO.h"
+#include "llvm/Support/Path.h"
+#include "llvm/Support/raw_ostream.h"
+
+namespace {
+using namespace llvm;
+using namespace llvm::dsymutil;
+using namespace llvm::object;
+
+class MachODebugMapParser {
+public:
+  MachODebugMapParser(StringRef BinaryPath, StringRef PathPrefix = "")
+      : BinaryPath(BinaryPath), PathPrefix(PathPrefix) {}
+
+  /// \brief Parses and returns the DebugMap of the input binary.
+  /// \returns an error in case the provided BinaryPath doesn't exist
+  /// or isn't of a supported type.
+  ErrorOr<std::unique_ptr<DebugMap>> parse();
+
+private:
+  std::string BinaryPath;
+  std::string PathPrefix;
+
+  /// OwningBinary constructed from the BinaryPath.
+  object::OwningBinary<object::MachOObjectFile> MainOwningBinary;
+  /// Map of the binary symbol addresses.
+  StringMap<uint64_t> MainBinarySymbolAddresses;
+  /// The constructed DebugMap.
+  std::unique_ptr<DebugMap> Result;
+
+  /// Handle to the currently processed object file.
+  object::OwningBinary<object::MachOObjectFile> CurrentObjectFile;
+  /// Map of the currently processed object file symbol addresses.
+  StringMap<uint64_t> CurrentObjectAddresses;
+  /// Element of the debug map corresponfing to the current object file.
+  DebugMapObject *CurrentDebugMapObject;
+
+  void switchToNewDebugMapObject(StringRef Filename);
+  void resetParserState();
+  uint64_t getMainBinarySymbolAddress(StringRef Name);
+  void loadMainBinarySymbols();
+  void loadCurrentObjectFileSymbols();
+  void handleStabSymbolTableEntry(uint32_t StringIndex, uint8_t Type,
+                                  uint8_t SectionIndex, uint16_t Flags,
+                                  uint64_t Value);
+
+  template <typename STEType> void handleStabDebugMapEntry(const STEType &STE) {
+    handleStabSymbolTableEntry(STE.n_strx, STE.n_type, STE.n_sect, STE.n_desc,
+                               STE.n_value);
+  }
+};
+
+static void Warning(const Twine &Msg) { errs() << "warning: " + Msg + "\n"; }
+}
+
+static ErrorOr<OwningBinary<MachOObjectFile>>
+createMachOBinary(StringRef File) {
+  auto MemBufOrErr = MemoryBuffer::getFile(File);
+  if (auto Error = MemBufOrErr.getError())
+    return Error;
+
+  MemoryBufferRef BufRef = (*MemBufOrErr)->getMemBufferRef();
+  auto MachOOrErr = ObjectFile::createMachOObjectFile(BufRef);
+  if (auto Error = MachOOrErr.getError())
+    return Error;
+
+  return OwningBinary<MachOObjectFile>(std::move(*MachOOrErr),
+                                       std::move(*MemBufOrErr));
+}
+
+/// Reset the parser state coresponding to the current object
+/// file. This is to be called after an object file is finished
+/// processing.
+void MachODebugMapParser::resetParserState() {
+  CurrentObjectFile = OwningBinary<object::MachOObjectFile>();
+  CurrentObjectAddresses.clear();
+  CurrentDebugMapObject = nullptr;
+}
+
+/// Create a new DebugMapObject. This function resets the state of the
+/// parser that was referring to the last object file and sets
+/// everything up to add symbols to the new one.
+void MachODebugMapParser::switchToNewDebugMapObject(StringRef Filename) {
+  resetParserState();
+
+  SmallString<80> Path(PathPrefix);
+  sys::path::append(Path, Filename);
+
+  auto MachOOrError = createMachOBinary(Path);
+  if (auto Error = MachOOrError.getError()) {
+    Warning(Twine("cannot open debug object \"") + Path.str() + "\": " +
+            Error.message() + "\n");
+    return;
+  }
+
+  CurrentObjectFile = std::move(*MachOOrError);
+  loadCurrentObjectFileSymbols();
+  CurrentDebugMapObject = &Result->addDebugMapObject(Path);
+}
+
+/// This main parsing routine tries to open the main binary and if
+/// successful iterates over the STAB entries. The real parsing is
+/// done in handleStabSymbolTableEntry.
+ErrorOr<std::unique_ptr<DebugMap>> MachODebugMapParser::parse() {
+  auto MainBinaryOrError = createMachOBinary(BinaryPath);
+  if (auto Error = MainBinaryOrError.getError())
+    return Error;
+
+  MainOwningBinary = std::move(*MainBinaryOrError);
+  loadMainBinarySymbols();
+  Result = make_unique<DebugMap>();
+  const auto &MainBinary = *MainOwningBinary.getBinary();
+  for (const SymbolRef &Symbol : MainBinary.symbols()) {
+    const DataRefImpl &DRI = Symbol.getRawDataRefImpl();
+    if (MainBinary.is64Bit())
+      handleStabDebugMapEntry(MainBinary.getSymbol64TableEntry(DRI));
+    else
+      handleStabDebugMapEntry(MainBinary.getSymbolTableEntry(DRI));
+  }
+
+  resetParserState();
+  return std::move(Result);
+}
+
+/// Interpret the STAB entries to fill the DebugMap.
+void MachODebugMapParser::handleStabSymbolTableEntry(uint32_t StringIndex,
+                                                     uint8_t Type,
+                                                     uint8_t SectionIndex,
+                                                     uint16_t Flags,
+                                                     uint64_t Value) {
+  if (!(Type & MachO::N_STAB))
+    return;
+
+  const MachOObjectFile &MachOBinary = *MainOwningBinary.getBinary();
+  const char *Name = &MachOBinary.getStringTableData().data()[StringIndex];
+
+  // An N_OSO entry represents the start of a new object file description.
+  if (Type == MachO::N_OSO)
+    return switchToNewDebugMapObject(Name);
+
+  // If the last N_OSO object file wasn't found,
+  // CurrentDebugMapObject will be null. Do not update anything
+  // until we find the next valid N_OSO entry.
+  if (!CurrentDebugMapObject)
+    return;
+
+  switch (Type) {
+  case MachO::N_GSYM:
+    // This is a global variable. We need to query the main binary
+    // symbol table to find its address as it might not be in the
+    // debug map (for common symbols).
+    Value = getMainBinarySymbolAddress(Name);
+    if (Value == UnknownAddressOrSize)
+      return;
+    break;
+  case MachO::N_FUN:
+    // Functions are scopes in STABS. They have an end marker that we
+    // need to ignore.
+    if (Name[0] == '\0')
+      return;
+    break;
+  case MachO::N_STSYM:
+    break;
+  default:
+    return;
+  }
+
+  auto ObjectSymIt = CurrentObjectAddresses.find(Name);
+  if (ObjectSymIt == CurrentObjectAddresses.end())
+    return Warning("could not find object file symbol for symbol " +
+                   Twine(Name));
+  if (!CurrentDebugMapObject->addSymbol(Name, ObjectSymIt->getValue(), Value))
+    return Warning(Twine("failed to insert symbol '") + Name +
+                   "' in the debug map.");
+}
+
+/// Load the current object file symbols into CurrentObjectAddresses.
+void MachODebugMapParser::loadCurrentObjectFileSymbols() {
+  CurrentObjectAddresses.clear();
+  const auto &Binary = *CurrentObjectFile.getBinary();
+
+  for (auto Sym : Binary.symbols()) {
+    StringRef Name;
+    uint64_t Addr;
+    if (Sym.getAddress(Addr) || Addr == UnknownAddressOrSize ||
+        Sym.getName(Name))
+      continue;
+    CurrentObjectAddresses[Name] = Addr;
+  }
+}
+
+/// Lookup a symbol address in the main binary symbol table. The
+/// parser only needs to query common symbols, thus not every symbol's
+/// address is available through this function.
+uint64_t MachODebugMapParser::getMainBinarySymbolAddress(StringRef Name) {
+  auto Sym = MainBinarySymbolAddresses.find(Name);
+  if (Sym == MainBinarySymbolAddresses.end())
+    return UnknownAddressOrSize;
+  return Sym->second;
+}
+
+/// Load the interesting main binary symbols' addresses into
+/// MainBinarySymbolAddresses.
+void MachODebugMapParser::loadMainBinarySymbols() {
+  const MachOObjectFile &Binary = *MainOwningBinary.getBinary();
+  section_iterator Section = Binary.section_end();
+  for (const auto &Sym : Binary.symbols()) {
+    SymbolRef::Type Type;
+    // Skip undefined and STAB entries.
+    if (Sym.getType(Type) || (Type & SymbolRef::ST_Debug) ||
+        (Type & SymbolRef::ST_Unknown))
+      continue;
+    StringRef Name;
+    uint64_t Addr;
+    // The only symbols of interest are the global variables. These
+    // are the only ones that need to be queried because the address
+    // of common data won't be described in the debug map. All other
+    // addresses should be fetched for the debug map.
+    if (Sym.getAddress(Addr) || Addr == UnknownAddressOrSize ||
+        !(Sym.getFlags() & SymbolRef::SF_Global) || Sym.getSection(Section) ||
+        Section->isText() || Sym.getName(Name) || Name.size() == 0 ||
+        Name[0] == '\0')
+      continue;
+    MainBinarySymbolAddresses[Name] = Addr;
+  }
+}
+
+namespace llvm {
+namespace dsymutil {
+llvm::ErrorOr<std::unique_ptr<DebugMap>> parseDebugMap(StringRef InputFile,
+                                                       StringRef PrependPath) {
+  MachODebugMapParser Parser(InputFile, PrependPath);
+  return Parser.parse();
+}
+}
+}

tools/dsymutil/Makefile

@@ -0,0 +1,17 @@
+##===- tools/dsymutil/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-dsymutil
+LINK_COMPONENTS := Object Support
+
+# This tool has no plugins, optimize startup time.
+TOOL_NO_EXPORTS := 1
+
+include $(LEVEL)/Makefile.common

tools/dsymutil/dsymutil.cpp

@@ -0,0 +1,73 @@
+//===-- dsymutil.cpp - Debug info 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 aims to be a dropin replacement for
+// Darwin's dsymutil.
+//
+//===----------------------------------------------------------------------===//
+
+#include "DebugMap.h"
+#include "dsymutil.h"
+
+#include "llvm/Support/ManagedStatic.h"
+#include "llvm/Support/PrettyStackTrace.h"
+#include "llvm/Support/Options.h"
+#include "llvm/Support/raw_ostream.h"
+#include "llvm/Support/Signals.h"
+
+#include <string>
+
+using namespace llvm::dsymutil;
+
+namespace {
+using namespace llvm::cl;
+
+static opt<std::string> InputFile(Positional, desc("<input file>"),
+                                  init("a.out"));
+
+static opt<std::string> OsoPrependPath("oso-prepend-path",
+                                       desc("Specify a directory to prepend "
+                                            "to the paths of object files."),
+                                       value_desc("path"));
+
+static opt<bool> Verbose("v", desc("Verbosity level"), init(false));
+
+static opt<bool>
+    ParseOnly("parse-only",
+              desc("Only parse the debug map, do not actaully link "
+                   "the DWARF."),
+              init(false));
+}
+
+int main(int argc, char **argv) {
+  llvm::sys::PrintStackTraceOnErrorSignal();
+  llvm::PrettyStackTraceProgram StackPrinter(argc, argv);
+  llvm::llvm_shutdown_obj Shutdown;
+
+  llvm::cl::ParseCommandLineOptions(argc, argv, "llvm dsymutil\n");
+  auto DebugMapPtrOrErr = parseDebugMap(InputFile, OsoPrependPath);
+
+  if (auto EC = DebugMapPtrOrErr.getError()) {
+    llvm::errs() << "error: cannot parse the debug map for \"" << InputFile
+                 << "\": " << EC.message() << '\n';
+    return 1;
+  }
+
+  if (Verbose)
+    (*DebugMapPtrOrErr)->print(llvm::outs());
+
+  if (ParseOnly)
+    return 0;
+
+  std::string OutputBasename(InputFile);
+  if (OutputBasename == "-")
+    OutputBasename = "a.out";
+
+  return !linkDwarf(OutputBasename + ".dwarf", **DebugMapPtrOrErr);
+}

tools/dsymutil/dsymutil.h

@@ -0,0 +1,37 @@
+//===- tools/dsymutil/dsymutil.h - dsymutil high-level functionality ------===//
+//
+//                             The LLVM Linker
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+///
+/// \file
+///
+/// This file contains the class declaration for the code that parses STABS
+/// debug maps that are embedded in the binaries symbol tables.
+///
+//===----------------------------------------------------------------------===//
+#ifndef LLVM_TOOLS_DSYMUTIL_DSYMUTIL_H
+#define LLVM_TOOLS_DSYMUTIL_DSYMUTIL_H
+
+#include "DebugMap.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/Support/ErrorOr.h"
+#include <memory>
+
+namespace llvm {
+namespace dsymutil {
+/// \brief Extract the DebugMap from the given file.
+/// The file has to be a MachO object file.
+llvm::ErrorOr<std::unique_ptr<DebugMap>>
+parseDebugMap(StringRef InputFile, StringRef PrependPath = "");
+
+/// \brief Link the Dwarf debuginfo as directed by the passed DebugMap
+/// \p DM into a DwarfFile named \p OutputFilename.
+/// \returns false if the link failed.
+bool linkDwarf(StringRef OutputFilename, const DebugMap &DM);
+}
+}
+#endif // LLVM_TOOLS_DSYMUTIL_DSYMUTIL_H