Enable streaming of bitcode

This CL delays reading of function bodies from initial parse until
materialization, allowing overlap of compilation with bitcode download.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@149918 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 167 insertions, 77 deletions

diff --git a/lib/Bitcode/Reader/BitcodeReader.cpp b/lib/Bitcode/Reader/BitcodeReader.cpp
index ace3042eb6..899154971b 100644
--- a/lib/Bitcode/Reader/BitcodeReader.cpp
+++ b/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -22,6 +22,7 @@
 #include "llvm/AutoUpgrade.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/ADT/SmallVector.h"
+#include "llvm/Support/DataStream.h"
 #include "llvm/Support/MathExtras.h"
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/OperandTraits.h"
@@ -1409,8 +1410,36 @@ bool BitcodeReader::RememberAndSkipFunctionBody() {
   return false;
 }
 
-bool BitcodeReader::ParseModule() {
-  if (Stream.EnterSubBlock(bitc::MODULE_BLOCK_ID))
+bool BitcodeReader::GlobalCleanup() {
+  // Patch the initializers for globals and aliases up.
+  ResolveGlobalAndAliasInits();
+  if (!GlobalInits.empty() || !AliasInits.empty())
+    return Error("Malformed global initializer set");
+
+  // Look for intrinsic functions which need to be upgraded at some point
+  for (Module::iterator FI = TheModule->begin(), FE = TheModule->end();
+       FI != FE; ++FI) {
+    Function *NewFn;
+    if (UpgradeIntrinsicFunction(FI, NewFn))
+      UpgradedIntrinsics.push_back(std::make_pair(FI, NewFn));
+  }
+
+  // Look for global variables which need to be renamed.
+  for (Module::global_iterator
+         GI = TheModule->global_begin(), GE = TheModule->global_end();
+       GI != GE; ++GI)
+    UpgradeGlobalVariable(GI);
+  // Force deallocation of memory for these vectors to favor the client that
+  // want lazy deserialization.
+  std::vector<std::pair<GlobalVariable*, unsigned> >().swap(GlobalInits);
+  std::vector<std::pair<GlobalAlias*, unsigned> >().swap(AliasInits);
+  return false;
+}
+
+bool BitcodeReader::ParseModule(bool Resume) {
+  if (Resume)
+    Stream.JumpToBit(NextUnreadBit);
+  else if (Stream.EnterSubBlock(bitc::MODULE_BLOCK_ID))
     return Error("Malformed block record");
 
   SmallVector<uint64_t, 64> Record;
@@ -1424,33 +1453,7 @@ bool BitcodeReader::ParseModule() {
       if (Stream.ReadBlockEnd())
         return Error("Error at end of module block");
 
-      // Patch the initializers for globals and aliases up.
-      ResolveGlobalAndAliasInits();
-      if (!GlobalInits.empty() || !AliasInits.empty())
-        return Error("Malformed global initializer set");
-      if (!FunctionsWithBodies.empty())
-        return Error("Too few function bodies found");
-
-      // Look for intrinsic functions which need to be upgraded at some point
-      for (Module::iterator FI = TheModule->begin(), FE = TheModule->end();
-           FI != FE; ++FI) {
-        Function* NewFn;
-        if (UpgradeIntrinsicFunction(FI, NewFn))
-          UpgradedIntrinsics.push_back(std::make_pair(FI, NewFn));
-      }
-
-      // Look for global variables which need to be renamed.
-      for (Module::global_iterator
-             GI = TheModule->global_begin(), GE = TheModule->global_end();
-           GI != GE; ++GI)
-        UpgradeGlobalVariable(GI);
-
-      // Force deallocation of memory for these vectors to favor the client that
-      // want lazy deserialization.
-      std::vector<std::pair<GlobalVariable*, unsigned> >().swap(GlobalInits);
-      std::vector<std::pair<GlobalAlias*, unsigned> >().swap(AliasInits);
-      std::vector<Function*>().swap(FunctionsWithBodies);
-      return false;
+      return GlobalCleanup();
     }
 
     if (Code == bitc::ENTER_SUBBLOCK) {
@@ -1474,6 +1477,7 @@ bool BitcodeReader::ParseModule() {
       case bitc::VALUE_SYMTAB_BLOCK_ID:
         if (ParseValueSymbolTable())
           return true;
+        SeenValueSymbolTable = true;
         break;
       case bitc::CONSTANTS_BLOCK_ID:
         if (ParseConstants() || ResolveGlobalAndAliasInits())
@@ -1486,13 +1490,25 @@ bool BitcodeReader::ParseModule() {
       case bitc::FUNCTION_BLOCK_ID:
         // If this is the first function body we've seen, reverse the
         // FunctionsWithBodies list.
-        if (!HasReversedFunctionsWithBodies) {
+        if (!SeenFirstFunctionBody) {
           std::reverse(FunctionsWithBodies.begin(), FunctionsWithBodies.end());
-          HasReversedFunctionsWithBodies = true;
+          if (GlobalCleanup())
+            return true;
+          SeenFirstFunctionBody = true;
         }
 
         if (RememberAndSkipFunctionBody())
           return true;
+        // For streaming bitcode, suspend parsing when we reach the function
+        // bodies. Subsequent materialization calls will resume it when
+        // necessary. For streaming, the function bodies must be at the end of
+        // the bitcode. If the bitcode file is old, the symbol table will be
+        // at the end instead and will not have been seen yet. In this case,
+        // just finish the parse now.
+        if (LazyStreamer && SeenValueSymbolTable) {
+          NextUnreadBit = Stream.GetCurrentBitNo();
+          return false;
+        }
         break;
       case bitc::USELIST_BLOCK_ID:
         if (ParseUseLists())
@@ -1651,8 +1667,10 @@ bool BitcodeReader::ParseModule() {
 
       // If this is a function with a body, remember the prototype we are
       // creating now, so that we can match up the body with them later.
-      if (!isProto)
+      if (!isProto) {
         FunctionsWithBodies.push_back(Func);
+        if (LazyStreamer) DeferredFunctionInfo[Func] = 0;
+      }
       break;
     }
     // ALIAS: [alias type, aliasee val#, linkage]
@@ -1691,24 +1709,7 @@ bool BitcodeReader::ParseModule() {
 bool BitcodeReader::ParseBitcodeInto(Module *M) {
   TheModule = 0;
 
-  unsigned char *BufPtr = (unsigned char *)Buffer->getBufferStart();
-  unsigned char *BufEnd = BufPtr+Buffer->getBufferSize();
-
-  if (Buffer->getBufferSize() & 3) {
-    if (!isRawBitcode(BufPtr, BufEnd) && !isBitcodeWrapper(BufPtr, BufEnd))
-      return Error("Invalid bitcode signature");
-    else
-      return Error("Bitcode stream should be a multiple of 4 bytes in length");
-  }
-
-  // If we have a wrapper header, parse it and ignore the non-bc file contents.
-  // The magic number is 0x0B17C0DE stored in little endian.
-  if (isBitcodeWrapper(BufPtr, BufEnd))
-    if (SkipBitcodeWrapperHeader(BufPtr, BufEnd))
-      return Error("Invalid bitcode wrapper header");
-
-  StreamFile.init(BufPtr, BufEnd);
-  Stream.init(StreamFile);
+  if (InitStream()) return true;
 
   // Sniff for the signature.
   if (Stream.Read(8) != 'B' ||
@@ -1750,8 +1751,9 @@ bool BitcodeReader::ParseBitcodeInto(Module *M) {
       if (TheModule)
         return Error("Multiple MODULE_BLOCKs in same stream");
       TheModule = M;
-      if (ParseModule())
+      if (ParseModule(false))
         return true;
+      if (LazyStreamer) return false;
       break;
     default:
       if (Stream.SkipBlock())
@@ -1819,20 +1821,7 @@ bool BitcodeReader::ParseModuleTriple(std::string &Triple) {
 }
 
 bool BitcodeReader::ParseTriple(std::string &Triple) {
-  if (Buffer->getBufferSize() & 3)
-    return Error("Bitcode stream should be a multiple of 4 bytes in length");
-
-  unsigned char *BufPtr = (unsigned char *)Buffer->getBufferStart();
-  unsigned char *BufEnd = BufPtr+Buffer->getBufferSize();
-
-  // If we have a wrapper header, parse it and ignore the non-bc file contents.
-  // The magic number is 0x0B17C0DE stored in little endian.
-  if (isBitcodeWrapper(BufPtr, BufEnd))
-    if (SkipBitcodeWrapperHeader(BufPtr, BufEnd))
-      return Error("Invalid bitcode wrapper header");
-
-  StreamFile.init(BufPtr, BufEnd);
-  Stream.init(StreamFile);
+  if (InitStream()) return true;
 
   // Sniff for the signature.
   if (Stream.Read(8) != 'B' ||
@@ -2708,6 +2697,19 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
   return false;
 }
 
+/// FindFunctionInStream - Find the function body in the bitcode stream
+bool BitcodeReader::FindFunctionInStream(Function *F,
+       DenseMap<Function*, uint64_t>::iterator DeferredFunctionInfoIterator) {
+  while (DeferredFunctionInfoIterator->second == 0) {
+    if (Stream.AtEndOfStream())
+      return Error("Could not find Function in stream");
+    // ParseModule will parse the next body in the stream and set its
+    // position in the DeferredFunctionInfo map.
+    if (ParseModule(true)) return true;
+  }
+  return false;
+}
+
 //===----------------------------------------------------------------------===//
 // GVMaterializer implementation
 //===----------------------------------------------------------------------===//
@@ -2728,6 +2730,10 @@ bool BitcodeReader::Materialize(GlobalValue *GV, std::string *ErrInfo) {
 
   DenseMap<Function*, uint64_t>::iterator DFII = DeferredFunctionInfo.find(F);
   assert(DFII != DeferredFunctionInfo.end() && "Deferred function not found!");
+  // If its position is recorded as 0, its body is somewhere in the stream
+  // but we haven't seen it yet.
+  if (DFII->second == 0)
+    if (LazyStreamer && FindFunctionInStream(F, DFII)) return true;
 
   // Move the bit stream to the saved position of the deferred function body.
   Stream.JumpToBit(DFII->second);
@@ -2805,6 +2811,57 @@ bool BitcodeReader::MaterializeModule(Module *M, std::string *ErrInfo) {
   return false;
 }
 
+bool BitcodeReader::InitStream() {
+  if (LazyStreamer) return InitLazyStream();
+  return InitStreamFromBuffer();
+}
+
+bool BitcodeReader::InitStreamFromBuffer() {
+  const unsigned char *BufPtr = (unsigned char *)Buffer->getBufferStart();
+  const unsigned char *BufEnd = BufPtr+Buffer->getBufferSize();
+
+  if (Buffer->getBufferSize() & 3) {
+    if (!isRawBitcode(BufPtr, BufEnd) && !isBitcodeWrapper(BufPtr, BufEnd))
+      return Error("Invalid bitcode signature");
+    else
+      return Error("Bitcode stream should be a multiple of 4 bytes in length");
+  }
+
+  // If we have a wrapper header, parse it and ignore the non-bc file contents.
+  // The magic number is 0x0B17C0DE stored in little endian.
+  if (isBitcodeWrapper(BufPtr, BufEnd))
+    if (SkipBitcodeWrapperHeader(BufPtr, BufEnd, true))
+      return Error("Invalid bitcode wrapper header");
+
+  StreamFile.reset(new BitstreamReader(BufPtr, BufEnd));
+  Stream.init(*StreamFile);
+
+  return false;
+}
+
+bool BitcodeReader::InitLazyStream() {
+  // Check and strip off the bitcode wrapper; BitstreamReader expects never to
+  // see it.
+  StreamingMemoryObject *Bytes = new StreamingMemoryObject(LazyStreamer);
+  StreamFile.reset(new BitstreamReader(Bytes));
+  Stream.init(*StreamFile);
+
+  unsigned char buf[16];
+  if (Bytes->readBytes(0, 16, buf, NULL) == -1)
+    return Error("Bitcode stream must be at least 16 bytes in length");
+
+  if (!isBitcode(buf, buf + 16))
+    return Error("Invalid bitcode signature");
+
+  if (isBitcodeWrapper(buf, buf + 4)) {
+    const unsigned char *bitcodeStart = buf;
+    const unsigned char *bitcodeEnd = buf + 16;
+    SkipBitcodeWrapperHeader(bitcodeStart, bitcodeEnd, false);
+    Bytes->dropLeadingBytes(bitcodeStart - buf);
+    Bytes->setKnownObjectSize(bitcodeEnd - bitcodeStart);
+  }
+  return false;
+}
 
 //===----------------------------------------------------------------------===//
 // External interface
@@ -2833,6 +2890,24 @@ Module *llvm::getLazyBitcodeModule(MemoryBuffer *Buffer,
   return M;
 }
 
+
+Module *llvm::getStreamedBitcodeModule(const std::string &name,
+                                       DataStreamer *streamer,
+                                       LLVMContext &Context,
+                                       std::string *ErrMsg) {
+  Module *M = new Module(name, Context);
+  BitcodeReader *R = new BitcodeReader(streamer, Context);
+  M->setMaterializer(R);
+  if (R->ParseBitcodeInto(M)) {
+    if (ErrMsg)
+      *ErrMsg = R->getErrorString();
+    delete M;  // Also deletes R.
+    return 0;
+  }
+  R->setBufferOwned(false); // no buffer to delete
+  return M;
+}
+
 /// ParseBitcodeFile - Read the specified bitcode file, returning the module.
 /// If an error occurs, return null and fill in *ErrMsg if non-null.
 Module *llvm::ParseBitcodeFile(MemoryBuffer *Buffer, LLVMContext& Context,
diff --git a/lib/Bitcode/Reader/BitcodeReader.h b/lib/Bitcode/Reader/BitcodeReader.h
index 952d645a4c..ad7baa732d 100644
--- a/lib/Bitcode/Reader/BitcodeReader.h
+++ b/lib/Bitcode/Reader/BitcodeReader.h
@@ -126,8 +126,11 @@ class BitcodeReader : public GVMaterializer {
   Module *TheModule;
   MemoryBuffer *Buffer;
   bool BufferOwned;
-  BitstreamReader StreamFile;
+  OwningPtr<BitstreamReader> StreamFile;
   BitstreamCursor Stream;
+  DataStreamer *LazyStreamer;
+  uint64_t NextUnreadBit;
+  bool SeenValueSymbolTable;
   
   const char *ErrorString;
   
@@ -161,9 +164,10 @@ class BitcodeReader : public GVMaterializer {
   // Map the bitcode's custom MDKind ID to the Module's MDKind ID.
   DenseMap<unsigned, unsigned> MDKindMap;
   
-  // After the module header has been read, the FunctionsWithBodies list is 
-  // reversed.  This keeps track of whether we've done this yet.
-  bool HasReversedFunctionsWithBodies;
+  // Several operations happen after the module header has been read, but
+  // before function bodies are processed. This keeps track of whether
+  // we've done this yet.
+  bool SeenFirstFunctionBody;
   
   /// DeferredFunctionInfo - When function bodies are initially scanned, this
   /// map contains info about where to find deferred function body in the
@@ -178,8 +182,13 @@ class BitcodeReader : public GVMaterializer {
 public:
   explicit BitcodeReader(MemoryBuffer *buffer, LLVMContext &C)
     : Context(C), TheModule(0), Buffer(buffer), BufferOwned(false),
-      ErrorString(0), ValueList(C), MDValueList(C) {
-    HasReversedFunctionsWithBodies = false;
+      LazyStreamer(0), SeenValueSymbolTable(false), ErrorString(0),
+      ValueList(C), MDValueList(C), SeenFirstFunctionBody(false) {
+  }
+  explicit BitcodeReader(DataStreamer *streamer, LLVMContext &C)
+    : Context(C), TheModule(0), Buffer(0), BufferOwned(false),
+      LazyStreamer(streamer), SeenValueSymbolTable(false), ErrorString(0),
+      ValueList(C), MDValueList(C), SeenFirstFunctionBody(false) {
   }
   ~BitcodeReader() {
     FreeState();
@@ -258,7 +267,7 @@ private:
   }
 
   
-  bool ParseModule();
+  bool ParseModule(bool Resume);
   bool ParseAttributeBlock();
   bool ParseTypeTable();
   bool ParseTypeTableBody();
@@ -267,11 +276,17 @@ private:
   bool ParseConstants();
   bool RememberAndSkipFunctionBody();
   bool ParseFunctionBody(Function *F);
+  bool GlobalCleanup();
   bool ResolveGlobalAndAliasInits();
   bool ParseMetadata();
   bool ParseMetadataAttachment();
   bool ParseModuleTriple(std::string &Triple);
   bool ParseUseLists();
+  bool InitStream();
+  bool InitStreamFromBuffer();
+  bool InitLazyStream();
+  bool FindFunctionInStream(Function *F,
+         DenseMap<Function*, uint64_t>::iterator DeferredFunctionInfoIterator);
 };
   
 } // End llvm namespace
diff --git a/lib/Bitcode/Writer/BitcodeWriter.cpp b/lib/Bitcode/Writer/BitcodeWriter.cpp
index 0e2f0ec783..0e8d3acfd8 100644
--- a/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ b/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -1738,11 +1738,6 @@ static void WriteModule(const Module *M, BitstreamWriter &Stream) {
   // Emit metadata.
   WriteModuleMetadata(M, VE, Stream);
 
-  // Emit function bodies.
-  for (Module::const_iterator F = M->begin(), E = M->end(); F != E; ++F)
-    if (!F->isDeclaration())
-      WriteFunction(*F, VE, Stream);
-
   // Emit metadata.
   WriteModuleMetadataStore(M, Stream);
 
@@ -1753,6 +1748,11 @@ static void WriteModule(const Module *M, BitstreamWriter &Stream) {
   if (EnablePreserveUseListOrdering)
     WriteModuleUseLists(M, VE, Stream);
 
+  // Emit function bodies.
+  for (Module::const_iterator F = M->begin(), E = M->end(); F != E; ++F)
+    if (!F->isDeclaration())
+      WriteFunction(*F, VE, Stream);
+
   Stream.ExitBlock();
 }