[codeview,pdb] Try really hard to conserve memory when reading.

PDBs can be extremely large.  We're already mapping the entire
PDB into the process's address space, but to make matters worse
the blocks of the PDB are not arranged contiguously.  So, when
we have something like an array or a string embedded into the
stream, we have to make a copy.  Since it's convenient to use
traditional data structures to iterate and manipulate these
records, we need the memory to be contiguous.

As a result of this, we were using roughly twice as much memory
as the file size of the PDB, because every stream was copied
out and re-stitched together contiguously.

This patch addresses this by improving the MappedBlockStream
to allocate from a BumpPtrAllocator only when a read requires
a discontiguous read.  Furthermore, it introduces some data
structures backed by a stream which can iterate over both
fixed and variable length records of a PDB.  Since everything
is backed by a stream and not a buffer, we can read almost
everything from the PDB with zero copies.

Differential Revision: http://reviews.llvm.org/D20654
Reviewed By: ruiu

llvm-svn: 270951

2 files changed, 64 insertions, 29 deletions

diff --git a/llvm/lib/DebugInfo/CodeView/ByteStream.cpp b/llvm/lib/DebugInfo/CodeView/ByteStream.cpp
index 879343afbfd..1ea976b6a26 100644
--- a/llvm/lib/DebugInfo/CodeView/ByteStream.cpp
+++ b/llvm/lib/DebugInfo/CodeView/ByteStream.cpp
@@ -17,31 +17,24 @@ using namespace llvm::codeview;
 
 ByteStream::ByteStream() {}
 
-ByteStream::ByteStream(MutableArrayRef<uint8_t> Bytes) { initialize(Bytes); }
+ByteStream::ByteStream(MutableArrayRef<uint8_t> Data) : Data(Data) {}
 
-ByteStream::ByteStream(uint32_t Length) { initialize(Length); }
-
-ByteStream::~ByteStream() { reset(); }
+ByteStream::~ByteStream() {}
 
 void ByteStream::reset() {
   Ownership.reset();
   Data = MutableArrayRef<uint8_t>();
 }
 
-void ByteStream::initialize(MutableArrayRef<uint8_t> Bytes) {
-  reset();
-  Data = Bytes;
-}
-
-void ByteStream::initialize(uint32_t Length) {
+void ByteStream::load(uint32_t Length) {
   reset();
   if (Length > 0)
     Data = MutableArrayRef<uint8_t>(new uint8_t[Length], Length);
   Ownership.reset(Data.data());
 }
 
-Error ByteStream::initialize(StreamReader &Reader, uint32_t Length) {
-  initialize(Length);
+Error ByteStream::load(StreamReader &Reader, uint32_t Length) {
+  load(Length);
   auto EC = Reader.readBytes(Data);
   if (EC)
     reset();
@@ -52,15 +45,15 @@ Error ByteStream::readBytes(uint32_t Offset,
                             MutableArrayRef<uint8_t> Buffer) const {
   if (Data.size() < Buffer.size() + Offset)
     return make_error<CodeViewError>(cv_error_code::insufficient_buffer);
-  ::memcpy(Buffer.data(), Data.data() + Offset, Buffer.size());
+  ::memcpy(Buffer.data() + Offset, Data.data(), Buffer.size());
   return Error::success();
 }
 
-Error ByteStream::getArrayRef(uint32_t Offset, ArrayRef<uint8_t> &Buffer,
-                              uint32_t Length) const {
-  if (Data.size() < Length + Offset)
+Error ByteStream::readBytes(uint32_t Offset, uint32_t Size,
+                            ArrayRef<uint8_t> &Buffer) const {
+  if (Data.size() < Buffer.size() + Offset)
     return make_error<CodeViewError>(cv_error_code::insufficient_buffer);
-  Buffer = Data.slice(Offset, Length);
+  Buffer = Data.slice(Offset, Size);
   return Error::success();
 }
 
diff --git a/llvm/lib/DebugInfo/CodeView/StreamReader.cpp b/llvm/lib/DebugInfo/CodeView/StreamReader.cpp
index 8a2926bc883..64985bfd0e2 100644
--- a/llvm/lib/DebugInfo/CodeView/StreamReader.cpp
+++ b/llvm/lib/DebugInfo/CodeView/StreamReader.cpp
@@ -10,12 +10,20 @@
 #include "llvm/DebugInfo/CodeView/StreamReader.h"
 
 #include "llvm/DebugInfo/CodeView/CodeViewError.h"
+#include "llvm/DebugInfo/CodeView/StreamRef.h"
 
 using namespace llvm;
 using namespace llvm::codeview;
 
 StreamReader::StreamReader(const StreamInterface &S) : Stream(S), Offset(0) {}
 
+Error StreamReader::readBytes(uint32_t Size, ArrayRef<uint8_t> &Buffer) {
+  if (auto EC = Stream.readBytes(Offset, Size, Buffer))
+    return EC;
+  Offset += Size;
+  return Error::success();
+}
+
 Error StreamReader::readBytes(MutableArrayRef<uint8_t> Buffer) {
   if (auto EC = Stream.readBytes(Offset, Buffer))
     return EC;
@@ -23,29 +31,63 @@ Error StreamReader::readBytes(MutableArrayRef<uint8_t> Buffer) {
   return Error::success();
 }
 
+Error StreamReader::readInteger(uint16_t &Dest) {
+  const support::ulittle16_t *P;
+  if (auto EC = readObject(P))
+    return EC;
+  Dest = *P;
+  return Error::success();
+}
+
 Error StreamReader::readInteger(uint32_t &Dest) {
-  support::ulittle32_t P;
-  if (auto EC = readObject(&P))
+  const support::ulittle32_t *P;
+  if (auto EC = readObject(P))
     return EC;
-  Dest = P;
+  Dest = *P;
   return Error::success();
 }
 
-Error StreamReader::readZeroString(std::string &Dest) {
-  Dest.clear();
-  char C;
+Error StreamReader::readZeroString(StringRef &Dest) {
+  uint32_t Length = 0;
+  // First compute the length of the string by reading 1 byte at a time.
+  uint32_t OriginalOffset = getOffset();
+  const char *C;
   do {
-    if (auto EC = readObject(&C))
+    if (auto EC = readObject(C))
       return EC;
-    if (C != '\0')
-      Dest.push_back(C);
-  } while (C != '\0');
+    if (*C != '\0')
+      ++Length;
+  } while (*C != '\0');
+  // Now go back and request a reference for that many bytes.
+  uint32_t NewOffset = getOffset();
+  setOffset(OriginalOffset);
+
+  ArrayRef<uint8_t> Data;
+  if (auto EC = readBytes(Length, Data))
+    return EC;
+  Dest = StringRef(reinterpret_cast<const char *>(Data.begin()), Data.size());
+
+  // Now set the offset back to where it was after we calculated the length.
+  setOffset(NewOffset);
   return Error::success();
 }
 
-Error StreamReader::getArrayRef(ArrayRef<uint8_t> &Array, uint32_t Length) {
-  if (auto EC = Stream.getArrayRef(Offset, Array, Length))
+Error StreamReader::readFixedString(StringRef &Dest, uint32_t Length) {
+  ArrayRef<uint8_t> Bytes;
+  if (auto EC = readBytes(Length, Bytes))
     return EC;
+  Dest = StringRef(reinterpret_cast<const char *>(Bytes.begin()), Bytes.size());
+  return Error::success();
+}
+
+Error StreamReader::readStreamRef(StreamRef &Ref) {
+  return readStreamRef(Ref, bytesRemaining());
+}
+
+Error StreamReader::readStreamRef(StreamRef &Ref, uint32_t Length) {
+  if (bytesRemaining() < Length)
+    return make_error<CodeViewError>(cv_error_code::insufficient_buffer);
+  Ref = StreamRef(Stream, Offset, Length);
   Offset += Length;
   return Error::success();
 }