[pdb] Use MappedBlockStream to parse the PDB directory.

In order to efficiently write PDBs, we need to be able to make a
StreamWriter class similar to a StreamReader, which can transparently deal
with writing to discontiguous streams, and we need to use this for all
writing, similar to how we use StreamReader for all reading.

Most discontiguous streams are the typical numbered streams that appear in
a PDB file and are described by the directory, but the exception to this,
that until now has been parsed by hand, is the directory itself.
MappedBlockStream works by querying the directory to find out which blocks
a stream occupies and various other things, so naturally the same logic
could not possibly work to describe the blocks that the directory itself
resided on.

To solve this, I've introduced an abstraction IPDBStreamData, which allows
the client to query for the list of blocks occupied by the stream, as well
as the stream length. I provide two implementations of this: one which
queries the directory (for indexed streams), and one which queries the
super block (for the directory stream).

This has the side benefit of vastly simplifying the code to parse the
directory. Whereas before a mini state machine was rolled by hand, now we
simply use FixedStreamArray to read out the stream sizes, then build a
vector of FixedStreamArrays for the stream map, all in just a few lines of
code.

Reviewed By: ruiu
Differential Revision: http://reviews.llvm.org/D21046

llvm-svn: 271982

include/llvm/DebugInfo/CodeView/StreamArray.h

@@ -224,6 +224,8 @@ public:
     return FixedStreamArrayIterator<T>(*this, size());
   }
 
+  StreamRef getUnderlyingStream() const { return Stream; }
+
 private:
   StreamRef Stream;
 };

include/llvm/DebugInfo/CodeView/StreamReader.h

@@ -52,6 +52,20 @@ public:
     return Error::success();
   }
 
+  template <typename T>
+  Error readArray(ArrayRef<T> &Array, uint32_t NumElements) {
+    ArrayRef<uint8_t> Bytes;
+    if (NumElements == 0) {
+      Array = ArrayRef<T>();
+      return Error::success();
+    }
+
+    if (auto EC = readBytes(Bytes, NumElements * sizeof(T)))
+      return EC;
+    Array = ArrayRef<T>(reinterpret_cast<const T *>(Bytes.data()), NumElements);
+    return Error::success();
+  }
+
   template <typename T, typename U>
   Error readArray(VarStreamArray<T, U> &Array, uint32_t Size) {
     StreamRef S;

include/llvm/DebugInfo/PDB/Raw/IPDBFile.h

@@ -12,6 +12,7 @@
 
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/StringRef.h"
+#include "llvm/DebugInfo/CodeView/StreamArray.h"
 #include "llvm/Support/Endian.h"
 
 #include <stdint.h>
@@ -28,7 +29,8 @@ public:
 
   virtual uint32_t getNumStreams() const = 0;
   virtual uint32_t getStreamByteSize(uint32_t StreamIndex) const = 0;
-  virtual ArrayRef<uint32_t> getStreamBlockList(uint32_t StreamIndex) const = 0;
+  virtual ArrayRef<support::ulittle32_t>
+  getStreamBlockList(uint32_t StreamIndex) const = 0;
 
   virtual StringRef getBlockData(uint32_t BlockIndex,
                                  uint32_t NumBytes) const = 0;

include/llvm/DebugInfo/PDB/Raw/IPDBStreamData.h

@@ -0,0 +1,38 @@
+//===- IPDBStreamData.h - Base interface for PDB Stream Data ----*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_DEBUGINFO_PDB_RAW_IPDBSTREAMDATA_H
+#define LLVM_DEBUGINFO_PDB_RAW_IPDBSTREAMDATA_H
+
+#include "llvm/ADT/ArrayRef.h"
+#include "llvm/Support/Endian.h"
+
+namespace llvm {
+namespace pdb {
+/// IPDBStream abstracts the notion of PDB stream data.  Although we already
+/// have another stream abstraction (namely in the form of StreamInterface
+/// and MappedBlockStream), they assume that the stream data is referenced
+/// the same way.  Namely, by looking in the directory to get the list of
+/// stream blocks, and by looking in the array of stream lengths to get the
+/// length.  This breaks down for the directory itself, however, since its
+/// length and list of blocks are stored elsewhere.  By abstracting the
+/// notion of stream data further, we can use a MappedBlockStream to read
+/// from the directory itself, or from an indexed stream which references
+/// the directory.
+class IPDBStreamData {
+public:
+  virtual ~IPDBStreamData() {}
+
+  virtual uint32_t getLength() = 0;
+  virtual ArrayRef<support::ulittle32_t> getStreamBlocks() = 0;
+};
+}
+}
+
+#endif

include/llvm/DebugInfo/PDB/Raw/IndexedStreamData.h

@@ -0,0 +1,34 @@
+//===- IndexedStreamData.h - Standard PDB Stream Data -----------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_DEBUGINFO_PDB_RAW_INDEXEDSTREAMDATA_H
+#define LLVM_DEBUGINFO_PDB_RAW_INDEXEDSTREAMDATA_H
+
+#include "llvm/DebugInfo/PDB/Raw/IPDBStreamData.h"
+
+namespace llvm {
+namespace pdb {
+class IPDBFile;
+
+class IndexedStreamData : public IPDBStreamData {
+public:
+  IndexedStreamData(uint32_t StreamIdx, const IPDBFile &File);
+  virtual ~IndexedStreamData() {}
+
+  uint32_t getLength() override;
+  ArrayRef<support::ulittle32_t> getStreamBlocks() override;
+
+private:
+  uint32_t StreamIdx;
+  const IPDBFile &File;
+};
+}
+}
+
+#endif

include/llvm/DebugInfo/PDB/Raw/InfoStream.h

@@ -24,7 +24,7 @@ namespace pdb {
 class PDBFile;
 class InfoStream {
 public:
-  InfoStream(PDBFile &File);
+  InfoStream(const PDBFile &File);
 
   Error reload();
 
@@ -36,10 +36,7 @@ public:
   uint32_t getNamedStreamIndex(llvm::StringRef Name) const;
   iterator_range<StringMapConstIterator<uint32_t>> named_streams() const;
 
-  PDBFile &getFile() { return Pdb; }
-
 private:
-  PDBFile &Pdb;
   MappedBlockStream Stream;
 
   // PDB file format version.  We only support VC70.  See the enumeration

include/llvm/DebugInfo/PDB/Raw/MappedBlockStream.h

@@ -14,6 +14,7 @@
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/DebugInfo/CodeView/StreamInterface.h"
 #include "llvm/Support/Allocator.h"
+#include "llvm/Support/Endian.h"
 #include "llvm/Support/Error.h"
 #include <cstdint>
 #include <vector>
@@ -22,15 +23,16 @@ namespace llvm {
 namespace pdb {
 
 class IPDBFile;
+class IPDBStreamData;
 
 class MappedBlockStream : public codeview::StreamInterface {
 public:
-  MappedBlockStream(uint32_t StreamIdx, const IPDBFile &File);
+  MappedBlockStream(std::unique_ptr<IPDBStreamData> Data, const IPDBFile &File);
 
   Error readBytes(uint32_t Offset, uint32_t Size,
                   ArrayRef<uint8_t> &Buffer) const override;
 
-  uint32_t getLength() const override { return StreamLength; }
+  uint32_t getLength() const override;
 
   uint32_t getNumBytesCopied() const;
 
@@ -39,11 +41,11 @@ private:
   bool tryReadContiguously(uint32_t Offset, uint32_t Size,
                            ArrayRef<uint8_t> &Buffer) const;
 
-  uint32_t StreamLength;
-  std::vector<uint32_t> BlockList;
+  const IPDBFile &Pdb;
+  std::unique_ptr<IPDBStreamData> Data;
+
   mutable llvm::BumpPtrAllocator Pool;
   mutable DenseMap<uint32_t, uint8_t *> CacheMap;
-  const IPDBFile &Pdb;
 };
 
 } // end namespace pdb

include/llvm/DebugInfo/PDB/Raw/ModStream.h

@@ -26,7 +26,7 @@ class ModInfo;
 
 class ModStream {
 public:
-  ModStream(PDBFile &File, const ModInfo &Module);
+  ModStream(const PDBFile &File, const ModInfo &Module);
   ~ModStream();
 
   Error reload();

include/llvm/DebugInfo/PDB/Raw/PDBFile.h

@@ -11,6 +11,7 @@
 #define LLVM_DEBUGINFO_PDB_RAW_PDBFILE_H
 
 #include "llvm/ADT/DenseMap.h"
+#include "llvm/DebugInfo/CodeView/StreamArray.h"
 #include "llvm/DebugInfo/PDB/Raw/IPDBFile.h"
 #include "llvm/Support/Endian.h"
 #include "llvm/Support/Error.h"
@@ -48,11 +49,12 @@ public:
 
   uint32_t getNumStreams() const override;
   uint32_t getStreamByteSize(uint32_t StreamIndex) const override;
-  ArrayRef<uint32_t> getStreamBlockList(uint32_t StreamIndex) const override;
+  ArrayRef<support::ulittle32_t>
+  getStreamBlockList(uint32_t StreamIndex) const override;
 
   StringRef getBlockData(uint32_t BlockIndex, uint32_t NumBytes) const override;
 
-  ArrayRef<support::ulittle32_t> getDirectoryBlockArray();
+  ArrayRef<support::ulittle32_t> getDirectoryBlockArray() const;
 
   Error parseFileHeaders();
   Error parseStreamData();
@@ -81,6 +83,7 @@ private:
   std::unique_ptr<TpiStream> Ipi;
   std::unique_ptr<PublicsStream> Publics;
   std::unique_ptr<SymbolStream> Symbols;
+  std::unique_ptr<MappedBlockStream> DirectoryStream;
   std::unique_ptr<MappedBlockStream> StringTableStream;
   std::unique_ptr<NameHashTable> StringTable;
 };

include/llvm/DebugInfo/PDB/Raw/SymbolStream.h

@@ -22,7 +22,7 @@ class PDBFile;
 
 class SymbolStream {
 public:
-  SymbolStream(PDBFile &File, uint32_t StreamNum);
+  SymbolStream(const PDBFile &File, uint32_t StreamNum);
   ~SymbolStream();
   Error reload();
 

include/llvm/DebugInfo/PDB/Raw/TpiStream.h

@@ -31,7 +31,7 @@ class TpiStream {
   struct HeaderInfo;
 
 public:
-  TpiStream(PDBFile &File, uint32_t StreamIdx);
+  TpiStream(const PDBFile &File, uint32_t StreamIdx);
   ~TpiStream();
   Error reload();
 
@@ -50,7 +50,7 @@ public:
   iterator_range<codeview::CVTypeArray::Iterator> types(bool *HadError) const;
 
 private:
-  PDBFile &Pdb;
+  const PDBFile &Pdb;
   MappedBlockStream Stream;
   HashFunctionType HashFunction;
 

lib/DebugInfo/PDB/CMakeLists.txt

@@ -30,6 +30,7 @@ endif()
 add_pdb_impl_folder(Raw
   Raw/DbiStream.cpp
   Raw/EnumTables.cpp
+  Raw/IndexedStreamData.cpp
   Raw/InfoStream.cpp
   Raw/MappedBlockStream.cpp
   Raw/ModInfo.cpp

lib/DebugInfo/PDB/Raw/DbiStream.cpp

@@ -12,6 +12,7 @@
 #include "llvm/DebugInfo/CodeView/StreamArray.h"
 #include "llvm/DebugInfo/CodeView/StreamReader.h"
 #include "llvm/DebugInfo/PDB/Raw/ISectionContribVisitor.h"
+#include "llvm/DebugInfo/PDB/Raw/IndexedStreamData.h"
 #include "llvm/DebugInfo/PDB/Raw/InfoStream.h"
 #include "llvm/DebugInfo/PDB/Raw/ModInfo.h"
 #include "llvm/DebugInfo/PDB/Raw/NameHashTable.h"
@@ -93,7 +94,9 @@ Error loadSectionContribs(FixedStreamArray<ContribType> &Output,
 }
 
 DbiStream::DbiStream(PDBFile &File)
-    : Pdb(File), Stream(StreamDBI, File), Header(nullptr) {
+    : Pdb(File),
+      Stream(llvm::make_unique<IndexedStreamData>(StreamDBI, File), File),
+      Header(nullptr) {
   static_assert(sizeof(HeaderInfo) == 64, "Invalid HeaderInfo size!");
 }
 
@@ -290,7 +293,8 @@ Error DbiStream::initializeSectionContributionData() {
 // Initializes this->SectionHeaders.
 Error DbiStream::initializeSectionHeadersData() {
   uint32_t StreamNum = getDebugStreamIndex(DbgHeaderType::SectionHdr);
-  SectionHeaderStream.reset(new MappedBlockStream(StreamNum, Pdb));
+  SectionHeaderStream.reset(new MappedBlockStream(
+      llvm::make_unique<IndexedStreamData>(StreamNum, Pdb), Pdb));
 
   size_t StreamLen = SectionHeaderStream->getLength();
   if (StreamLen % sizeof(object::coff_section))
@@ -308,7 +312,8 @@ Error DbiStream::initializeSectionHeadersData() {
 // Initializes this->Fpos.
 Error DbiStream::initializeFpoRecords() {
   uint32_t StreamNum = getDebugStreamIndex(DbgHeaderType::NewFPO);
-  FpoStream.reset(new MappedBlockStream(StreamNum, Pdb));
+  FpoStream.reset(new MappedBlockStream(
+      llvm::make_unique<IndexedStreamData>(StreamNum, Pdb), Pdb));
 
   size_t StreamLen = FpoStream->getLength();
   if (StreamLen % sizeof(object::FpoData))

lib/DebugInfo/PDB/Raw/IndexedStreamData.cpp

@@ -0,0 +1,25 @@
+//===- IndexedStreamData.cpp - Standard PDB Stream Data ---------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/DebugInfo/PDB/Raw/IndexedStreamData.h"
+#include "llvm/DebugInfo/PDB/Raw/IPDBFile.h"
+
+using namespace llvm;
+using namespace llvm::pdb;
+
+IndexedStreamData::IndexedStreamData(uint32_t StreamIdx, const IPDBFile &File)
+    : StreamIdx(StreamIdx), File(File) {}
+
+uint32_t IndexedStreamData::getLength() {
+  return File.getStreamByteSize(StreamIdx);
+}
+
+ArrayRef<support::ulittle32_t> IndexedStreamData::getStreamBlocks() {
+  return File.getStreamBlockList(StreamIdx);
+}

lib/DebugInfo/PDB/Raw/InfoStream.cpp

@@ -11,6 +11,7 @@
 #include "llvm/ADT/BitVector.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/DebugInfo/CodeView/StreamReader.h"
+#include "llvm/DebugInfo/PDB/Raw/IndexedStreamData.h"
 #include "llvm/DebugInfo/PDB/Raw/PDBFile.h"
 #include "llvm/DebugInfo/PDB/Raw/RawConstants.h"
 #include "llvm/DebugInfo/PDB/Raw/RawError.h"
@@ -18,7 +19,8 @@
 using namespace llvm;
 using namespace llvm::pdb;
 
-InfoStream::InfoStream(PDBFile &File) : Pdb(File), Stream(StreamPDB, File) {}
+InfoStream::InfoStream(const PDBFile &File)
+    : Stream(llvm::make_unique<IndexedStreamData>(StreamPDB, File), File) {}
 
 Error InfoStream::reload() {
   codeview::StreamReader Reader(Stream);

lib/DebugInfo/PDB/Raw/MappedBlockStream.cpp

@@ -8,28 +8,23 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/DebugInfo/PDB/Raw/MappedBlockStream.h"
+#include "llvm/DebugInfo/PDB/Raw/IPDBStreamData.h"
 #include "llvm/DebugInfo/PDB/Raw/PDBFile.h"
 #include "llvm/DebugInfo/PDB/Raw/RawError.h"
 
 using namespace llvm;
 using namespace llvm::pdb;
 
-MappedBlockStream::MappedBlockStream(uint32_t StreamIdx, const IPDBFile &File)
-    : Pdb(File) {
-  if (StreamIdx >= Pdb.getNumStreams()) {
-    StreamLength = 0;
-  } else {
-    StreamLength = Pdb.getStreamByteSize(StreamIdx);
-    BlockList = Pdb.getStreamBlockList(StreamIdx);
-  }
-}
+MappedBlockStream::MappedBlockStream(std::unique_ptr<IPDBStreamData> Data,
+                                     const IPDBFile &Pdb)
+    : Pdb(Pdb), Data(std::move(Data)) {}
 
 Error MappedBlockStream::readBytes(uint32_t Offset, uint32_t Size,
                                    ArrayRef<uint8_t> &Buffer) const {
   // Make sure we aren't trying to read beyond the end of the stream.
-  if (Size > StreamLength)
+  if (Size > Data->getLength())
     return make_error<RawError>(raw_error_code::insufficient_buffer);
-  if (Offset > StreamLength - Size)
+  if (Offset > Data->getLength() - Size)
     return make_error<RawError>(raw_error_code::insufficient_buffer);
 
   if (tryReadContiguously(Offset, Size, Buffer))
@@ -57,6 +52,8 @@ Error MappedBlockStream::readBytes(uint32_t Offset, uint32_t Size,
   return Error::success();
 }
 
+uint32_t MappedBlockStream::getLength() const { return Data->getLength(); }
+
 bool MappedBlockStream::tryReadContiguously(uint32_t Offset, uint32_t Size,
                                             ArrayRef<uint8_t> &Buffer) const {
   // Attempt to fulfill the request with a reference directly into the stream.
@@ -72,6 +69,7 @@ bool MappedBlockStream::tryReadContiguously(uint32_t Offset, uint32_t Size,
       llvm::alignTo(Size - BytesFromFirstBlock, Pdb.getBlockSize()) /
       Pdb.getBlockSize();
 
+  auto BlockList = Data->getStreamBlocks();
   uint32_t RequiredContiguousBlocks = NumAdditionalBlocks + 1;
   uint32_t E = BlockList[BlockNum];
   for (uint32_t I = 0; I < RequiredContiguousBlocks; ++I, ++E) {
@@ -93,14 +91,15 @@ Error MappedBlockStream::readBytes(uint32_t Offset,
   uint32_t OffsetInBlock = Offset % Pdb.getBlockSize();
 
   // Make sure we aren't trying to read beyond the end of the stream.
-  if (Buffer.size() > StreamLength)
+  if (Buffer.size() > Data->getLength())
     return make_error<RawError>(raw_error_code::insufficient_buffer);
-  if (Offset > StreamLength - Buffer.size())
+  if (Offset > Data->getLength() - Buffer.size())
     return make_error<RawError>(raw_error_code::insufficient_buffer);
 
   uint32_t BytesLeft = Buffer.size();
   uint32_t BytesWritten = 0;
   uint8_t *WriteBuffer = Buffer.data();
+  auto BlockList = Data->getStreamBlocks();
   while (BytesLeft > 0) {
     uint32_t StreamBlockAddr = BlockList[BlockNum];
 

lib/DebugInfo/PDB/Raw/ModStream.cpp

@@ -10,6 +10,7 @@
 #include "llvm/DebugInfo/PDB/Raw/ModStream.h"
 
 #include "llvm/DebugInfo/CodeView/StreamReader.h"
+#include "llvm/DebugInfo/PDB/Raw/IndexedStreamData.h"
 #include "llvm/DebugInfo/PDB/Raw/ModInfo.h"
 #include "llvm/DebugInfo/PDB/Raw/PDBFile.h"
 #include "llvm/DebugInfo/PDB/Raw/RawError.h"
@@ -18,8 +19,10 @@
 using namespace llvm;
 using namespace llvm::pdb;
 
-ModStream::ModStream(PDBFile &File, const ModInfo &Module)
-    : Mod(Module), Stream(Module.getModuleStreamIndex(), File) {}
+ModStream::ModStream(const PDBFile &File, const ModInfo &Module)
+    : Mod(Module), Stream(llvm::make_unique<IndexedStreamData>(
+                              Module.getModuleStreamIndex(), File),
+                          File) {}
 
 ModStream::~ModStream() {}
 

lib/DebugInfo/PDB/Raw/PDBFile.cpp

@@ -8,8 +8,12 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/DebugInfo/PDB/Raw/PDBFile.h"
+
 #include "llvm/ADT/ArrayRef.h"
+#include "llvm/DebugInfo/CodeView/StreamArray.h"
+#include "llvm/DebugInfo/CodeView/StreamReader.h"
 #include "llvm/DebugInfo/PDB/Raw/DbiStream.h"
+#include "llvm/DebugInfo/PDB/Raw/IndexedStreamData.h"
 #include "llvm/DebugInfo/PDB/Raw/InfoStream.h"
 #include "llvm/DebugInfo/PDB/Raw/NameHashTable.h"
 #include "llvm/DebugInfo/PDB/Raw/PublicsStream.h"
@@ -49,13 +53,28 @@ struct SuperBlock {
   // This contains the block # of the block map.
   support::ulittle32_t BlockMapAddr;
 };
+
+class DirectoryStreamData : public IPDBStreamData {
+public:
+  DirectoryStreamData(const PDBFile &File) : File(File) {}
+
+  virtual uint32_t getLength() { return File.getNumDirectoryBytes(); }
+  virtual llvm::ArrayRef<llvm::support::ulittle32_t> getStreamBlocks() {
+    return File.getDirectoryBlockArray();
+  }
+
+private:
+  const PDBFile &File;
+};
+
+typedef codeview::FixedStreamArray<support::ulittle32_t> ulittle_array;
 }
 
 struct llvm::pdb::PDBFileContext {
   std::unique_ptr<MemoryBuffer> Buffer;
   const SuperBlock *SB;
-  std::vector<uint32_t> StreamSizes;
-  DenseMap<uint32_t, std::vector<uint32_t>> StreamMap;
+  ArrayRef<support::ulittle32_t> StreamSizes;
+  std::vector<ulittle_array> StreamMap;
 };
 
 static Error checkOffset(MemoryBufferRef M, uintptr_t Addr,
@@ -109,10 +128,14 @@ uint32_t PDBFile::getStreamByteSize(uint32_t StreamIndex) const {
   return Context->StreamSizes[StreamIndex];
 }
 
-llvm::ArrayRef<uint32_t>
+ArrayRef<support::ulittle32_t>
 PDBFile::getStreamBlockList(uint32_t StreamIndex) const {
-  auto &Data = Context->StreamMap[StreamIndex];
-  return llvm::ArrayRef<uint32_t>(Data);
+  auto Result = Context->StreamMap[StreamIndex];
+  codeview::StreamReader Reader(Result.getUnderlyingStream());
+  ArrayRef<support::ulittle32_t> Array;
+  if (auto EC = Reader.readArray(Array, Result.size()))
+    return ArrayRef<support::ulittle32_t>();
+  return Array;
 }
 
 StringRef PDBFile::getBlockData(uint32_t BlockIndex, uint32_t NumBytes) const {
@@ -184,113 +207,44 @@ Error PDBFile::parseFileHeaders() {
 
 Error PDBFile::parseStreamData() {
   assert(Context && Context->SB);
+  if (DirectoryStream)
+    return Error::success();
 
-  bool SeenNumStreams = false;
+  // bool SeenNumStreams = false;
   uint32_t NumStreams = 0;
-  uint32_t StreamIdx = 0;
-  uint64_t DirectoryBytesRead = 0;
+  // uint32_t StreamIdx = 0;
+  // uint64_t DirectoryBytesRead = 0;
 
-  MemoryBufferRef M = *Context->Buffer;
   const SuperBlock *SB = Context->SB;
 
-  auto DirectoryBlocks = getDirectoryBlockArray();
+  // Normally you can't use a MappedBlockStream without having fully parsed the
+  // PDB file, because it accesses the directory and various other things, which
+  // is exactly what we are attempting to parse.  By specifying a custom
+  // subclass of IPDBStreamData which only accesses the fields that have already
+  // been parsed, we can avoid this and reuse MappedBlockStream.
+  auto SD = llvm::make_unique<DirectoryStreamData>(*this);
+  DirectoryStream = llvm::make_unique<MappedBlockStream>(std::move(SD), *this);
+  codeview::StreamReader Reader(*DirectoryStream);
+  if (auto EC = Reader.readInteger(NumStreams))
+    return EC;
 
-  // The structure of the directory is as follows:
-  //    struct PDBDirectory {
-  //      uint32_t NumStreams;
-  //      uint32_t StreamSizes[NumStreams];
-  //      uint32_t StreamMap[NumStreams][];
-  //    };
-  //
-  //  Empty streams don't consume entries in the StreamMap.
-  for (uint32_t DirectoryBlockAddr : DirectoryBlocks) {
-    uint64_t DirectoryBlockOffset =
-        blockToOffset(DirectoryBlockAddr, SB->BlockSize);
-    auto DirectoryBlock =
-        makeArrayRef(reinterpret_cast<const support::ulittle32_t *>(
-                         M.getBufferStart() + DirectoryBlockOffset),
-                     SB->BlockSize / sizeof(support::ulittle32_t));
-    if (auto EC = checkOffset(M, DirectoryBlock))
-      return EC;
-
-    // We read data out of the directory four bytes at a time.  Depending on
-    // where we are in the directory, the contents may be: the number of streams
-    // in the directory, a stream's size, or a block in the stream map.
-    for (uint32_t Data : DirectoryBlock) {
-      // Don't read beyond the end of the directory.
-      if (DirectoryBytesRead == SB->NumDirectoryBytes)
-        break;
-
-      DirectoryBytesRead += sizeof(Data);
-
-      // This data must be the number of streams if we haven't seen it yet.
-      if (!SeenNumStreams) {
-        NumStreams = Data;
-        SeenNumStreams = true;
-        continue;
-      }
-      // This data must be a stream size if we have not seen them all yet.
-      if (Context->StreamSizes.size() < NumStreams) {
-        // It seems like some streams have their set to -1 when their contents
-        // are not present.  Treat them like empty streams for now.
-        if (Data == UINT32_MAX)
-          Context->StreamSizes.push_back(0);
-        else
-          Context->StreamSizes.push_back(Data);
-        continue;
-      }
-
-      // This data must be a stream block number if we have seen all of the
-      // stream sizes.
-      std::vector<uint32_t> *StreamBlocks = nullptr;
-      // Figure out which stream this block number belongs to.
-      while (StreamIdx < NumStreams) {
-        uint64_t NumExpectedStreamBlocks =
-            bytesToBlocks(Context->StreamSizes[StreamIdx], SB->BlockSize);
-        StreamBlocks = &Context->StreamMap[StreamIdx];
-        if (NumExpectedStreamBlocks > StreamBlocks->size())
-          break;
-        ++StreamIdx;
-      }
-      // It seems this block doesn't belong to any stream?  The stream is either
-      // corrupt or something more mysterious is going on.
-      if (StreamIdx == NumStreams)
-        return make_error<RawError>(raw_error_code::corrupt_file,
-                                    "Orphaned block found?");
-
-      uint64_t BlockOffset = blockToOffset(Data, getBlockSize());
-      if (BlockOffset + getBlockSize() < BlockOffset)
-        return make_error<RawError>(raw_error_code::corrupt_file,
-                                    "Bogus stream block number");
-      if (BlockOffset + getBlockSize() > M.getBufferSize())
-        return make_error<RawError>(raw_error_code::corrupt_file,
-                                    "Stream block number is out of bounds");
-
-      StreamBlocks->push_back(Data);
-    }
-  }
-
-  if (Context->StreamSizes.size() != NumStreams)
-    return make_error<RawError>(
-        raw_error_code::corrupt_file,
-        "The directory has fewer streams then expected");
-
-  for (uint32_t I = 0; I != NumStreams; ++I) {
+  if (auto EC = Reader.readArray(Context->StreamSizes, NumStreams))
+    return EC;
+  for (uint32_t I = 0; I < NumStreams; ++I) {
     uint64_t NumExpectedStreamBlocks =
-        bytesToBlocks(getStreamByteSize(I), getBlockSize());
-    size_t NumStreamBlocks = getStreamBlockList(I).size();
-    if (NumExpectedStreamBlocks != NumStreamBlocks)
-      return make_error<RawError>(raw_error_code::corrupt_file,
-                                  "The number of stream blocks is not "
-                                  "sufficient for the size of this stream");
+        bytesToBlocks(getStreamByteSize(I), SB->BlockSize);
+    ulittle_array Blocks;
+    if (auto EC = Reader.readArray(Blocks, NumExpectedStreamBlocks))
+      return EC;
+    Context->StreamMap.push_back(Blocks);
   }
 
   // We should have read exactly SB->NumDirectoryBytes bytes.
-  assert(DirectoryBytesRead == SB->NumDirectoryBytes);
+  assert(Reader.bytesRemaining() == 0);
   return Error::success();
 }
 
-llvm::ArrayRef<support::ulittle32_t> PDBFile::getDirectoryBlockArray() {
+llvm::ArrayRef<support::ulittle32_t> PDBFile::getDirectoryBlockArray() const {
   return makeArrayRef(
       reinterpret_cast<const support::ulittle32_t *>(
           Context->Buffer->getBufferStart() + getBlockMapOffset()),
@@ -371,7 +325,8 @@ Expected<NameHashTable &> PDBFile::getStringTable() {
 
     if (NameStreamIndex == 0)
       return make_error<RawError>(raw_error_code::no_stream);
-    auto S = llvm::make_unique<MappedBlockStream>(NameStreamIndex, *this);
+    auto SD = llvm::make_unique<IndexedStreamData>(NameStreamIndex, *this);
+    auto S = llvm::make_unique<MappedBlockStream>(std::move(SD), *this);
     codeview::StreamReader Reader(*S);
     auto N = llvm::make_unique<NameHashTable>();
     if (auto EC = N->load(Reader))

lib/DebugInfo/PDB/Raw/PublicsStream.cpp

@@ -27,6 +27,7 @@
 #include "llvm/DebugInfo/CodeView/CodeView.h"
 #include "llvm/DebugInfo/CodeView/StreamReader.h"
 #include "llvm/DebugInfo/CodeView/TypeRecord.h"
+#include "llvm/DebugInfo/PDB/Raw/IndexedStreamData.h"
 #include "llvm/DebugInfo/PDB/Raw/MappedBlockStream.h"
 #include "llvm/DebugInfo/PDB/Raw/PDBFile.h"
 #include "llvm/DebugInfo/PDB/Raw/RawConstants.h"
@@ -71,7 +72,8 @@ struct PublicsStream::GSIHashHeader {
 };
 
 PublicsStream::PublicsStream(PDBFile &File, uint32_t StreamNum)
-    : Pdb(File), StreamNum(StreamNum), Stream(StreamNum, File) {}
+    : Pdb(File), StreamNum(StreamNum),
+      Stream(llvm::make_unique<IndexedStreamData>(StreamNum, File), File) {}
 
 PublicsStream::~PublicsStream() {}
 

lib/DebugInfo/PDB/Raw/SymbolStream.cpp

@@ -12,6 +12,7 @@
 #include "llvm/DebugInfo/CodeView/CodeView.h"
 #include "llvm/DebugInfo/CodeView/StreamReader.h"
 #include "llvm/DebugInfo/CodeView/TypeRecord.h"
+#include "llvm/DebugInfo/PDB/Raw/IndexedStreamData.h"
 #include "llvm/DebugInfo/PDB/Raw/MappedBlockStream.h"
 #include "llvm/DebugInfo/PDB/Raw/PDBFile.h"
 #include "llvm/DebugInfo/PDB/Raw/RawConstants.h"
@@ -23,8 +24,9 @@ using namespace llvm;
 using namespace llvm::support;
 using namespace llvm::pdb;
 
-SymbolStream::SymbolStream(PDBFile &File, uint32_t StreamNum)
-    : MappedStream(StreamNum, File) {}
+SymbolStream::SymbolStream(const PDBFile &File, uint32_t StreamNum)
+    : MappedStream(llvm::make_unique<IndexedStreamData>(StreamNum, File),
+                   File) {}
 
 SymbolStream::~SymbolStream() {}
 

lib/DebugInfo/PDB/Raw/TpiStream.cpp

@@ -13,6 +13,7 @@
 #include "llvm/DebugInfo/CodeView/StreamReader.h"
 #include "llvm/DebugInfo/CodeView/TypeIndex.h"
 #include "llvm/DebugInfo/CodeView/TypeRecord.h"
+#include "llvm/DebugInfo/PDB/Raw/IndexedStreamData.h"
 #include "llvm/DebugInfo/PDB/Raw/MappedBlockStream.h"
 #include "llvm/DebugInfo/PDB/Raw/PDBFile.h"
 #include "llvm/DebugInfo/PDB/Raw/RawConstants.h"
@@ -61,8 +62,10 @@ struct TpiStream::HeaderInfo {
   EmbeddedBuf HashAdjBuffer;
 };
 
-TpiStream::TpiStream(PDBFile &File, uint32_t StreamIdx)
-    : Pdb(File), Stream(StreamIdx, File), HashFunction(nullptr) {}
+TpiStream::TpiStream(const PDBFile &File, uint32_t StreamIdx)
+    : Pdb(File),
+      Stream(llvm::make_unique<IndexedStreamData>(StreamIdx, File), File),
+      HashFunction(nullptr) {}
 
 TpiStream::~TpiStream() {}
 
@@ -101,7 +104,8 @@ Error TpiStream::reload() {
     return EC;
 
   // Hash indices, hash values, etc come from the hash stream.
-  HashStream.reset(new MappedBlockStream(Header->HashStreamIndex, Pdb));
+  HashStream.reset(new MappedBlockStream(
+      llvm::make_unique<IndexedStreamData>(Header->HashStreamIndex, Pdb), Pdb));
   codeview::StreamReader HSR(*HashStream);
 
   uint32_t NumHashValues = Header->HashValueBuffer.Length / sizeof(ulittle32_t);

lib/DebugInfo/PDB/Raw/TpiStream.cpp.rej

@@ -0,0 +1,11 @@
+diff a/lib/DebugInfo/PDB/Raw/TpiStream.cpp b/lib/DebugInfo/PDB/Raw/TpiStream.cpp	(rejected hunks)
+@@ -101,7 +104,8 @@
+     return EC;
+ 
+   // Hash indices, hash values, etc come from the hash stream.
+-  HashStream.reset(new MappedBlockStream(Header->HashStreamIndex, Pdb));
++  HashStream.reset(new MappedBlockStream(
++      llvm::make_unique<IndexedStreamData>(Header->HashStreamIndex, Pdb), Pdb));
+   codeview::StreamReader HSR(*HashStream);
+   uint32_t NumHashValues = Header->HashValueBuffer.Length / sizeof(ulittle32_t);
+   HSR.setOffset(Header->HashValueBuffer.Off);

tools/llvm-pdbdump/LLVMOutputStyle.cpp

@@ -17,6 +17,7 @@
 #include "llvm/DebugInfo/PDB/Raw/DbiStream.h"
 #include "llvm/DebugInfo/PDB/Raw/EnumTables.h"
 #include "llvm/DebugInfo/PDB/Raw/ISectionContribVisitor.h"
+#include "llvm/DebugInfo/PDB/Raw/IndexedStreamData.h"
 #include "llvm/DebugInfo/PDB/Raw/InfoStream.h"
 #include "llvm/DebugInfo/PDB/Raw/ModInfo.h"
 #include "llvm/DebugInfo/PDB/Raw/ModStream.h"
@@ -194,7 +195,8 @@ Error LLVMOutputStyle::dumpStreamData() {
       DumpStreamNum >= StreamCount)
     return Error::success();
 
-  MappedBlockStream S(DumpStreamNum, File);
+  MappedBlockStream S(llvm::make_unique<IndexedStreamData>(DumpStreamNum, File),
+                      File);
   codeview::StreamReader R(S);
   while (R.bytesRemaining() > 0) {
     ArrayRef<uint8_t> Data;
@@ -244,7 +246,8 @@ Error LLVMOutputStyle::dumpNamedStream() {
     DictScope D(P, Name);
     P.printNumber("Index", NameStreamIndex);
 
-    MappedBlockStream NameStream(NameStreamIndex, File);
+    MappedBlockStream NameStream(
+        llvm::make_unique<IndexedStreamData>(NameStreamIndex, File), File);
     codeview::StreamReader Reader(NameStream);
 
     NameHashTable NameTable;