Add a parameter for getLazyBitcodeModule to lazily load Metadata.

We only defer loading metadata inside ParseModule when ShouldLazyLoadMetadata
is true and we have not loaded any Metadata block yet.

This commit implements all-or-nothing loading of Metadata. If there is a
request to load any metadata block, we will load all deferred metadata blocks.

We make sure the deferred metadata blocks are loaded before we materialize any
function or a module.

The default value of the added parameter ShouldLazyLoadMetadata for
getLazyBitcodeModule is false, so the default behavior stays the same.

We only set the parameter to true when creating LTOModule in local contexts.
These can only really be used for parsing symbols, so it's unnecessary to ever
load the metadata blocks.

If we are going to enable lazy-loading of Metadata for other usages of
getLazyBitcodeModule, where deferred metadata blocks need to be loaded, we can
expose BitcodeReader::materializeMetadata to Module, similar to
Module::materialize.

rdar://19804575


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@232198 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Bitcode/ReaderWriter.h

@@ -29,12 +29,14 @@ namespace llvm {
   class raw_ostream;
 
   /// Read the header of the specified bitcode buffer and prepare for lazy
-  /// deserialization of function bodies.  If successful, this moves Buffer. On
+  /// deserialization of function bodies. If ShouldLazyLoadMetadata is true,
+  /// lazily load metadata as well. If successful, this moves Buffer. On
   /// error, this *does not* move Buffer.
   ErrorOr<Module *>
   getLazyBitcodeModule(std::unique_ptr<MemoryBuffer> &&Buffer,
                        LLVMContext &Context,
-                       DiagnosticHandlerFunction DiagnosticHandler = nullptr);
+                       DiagnosticHandlerFunction DiagnosticHandler = nullptr,
+                       bool ShouldLazyLoadMetadata = false);
 
   /// Read the header of the specified stream and prepare for lazy
   /// deserialization and streaming of function bodies.

lib/Bitcode/Reader/BitcodeReader.cpp

@@ -82,7 +82,7 @@ BitcodeReader::BitcodeReader(MemoryBuffer *buffer, LLVMContext &C,
       TheModule(nullptr), Buffer(buffer), LazyStreamer(nullptr),
       NextUnreadBit(0), SeenValueSymbolTable(false), ValueList(C),
       MDValueList(C), SeenFirstFunctionBody(false), UseRelativeIDs(false),
-      WillMaterializeAllForwardRefs(false) {}
+      WillMaterializeAllForwardRefs(false), IsMetadataMaterialized(false) {}
 
 BitcodeReader::BitcodeReader(DataStreamer *streamer, LLVMContext &C,
                              DiagnosticHandlerFunction DiagnosticHandler)
@@ -90,7 +90,7 @@ BitcodeReader::BitcodeReader(DataStreamer *streamer, LLVMContext &C,
       TheModule(nullptr), Buffer(nullptr), LazyStreamer(streamer),
       NextUnreadBit(0), SeenValueSymbolTable(false), ValueList(C),
       MDValueList(C), SeenFirstFunctionBody(false), UseRelativeIDs(false),
-      WillMaterializeAllForwardRefs(false) {}
+      WillMaterializeAllForwardRefs(false), IsMetadataMaterialized(false) {}
 
 std::error_code BitcodeReader::materializeForwardReferencedFunctions() {
   if (WillMaterializeAllForwardRefs)
@@ -136,6 +136,7 @@ void BitcodeReader::FreeState() {
   std::vector<BasicBlock*>().swap(FunctionBBs);
   std::vector<Function*>().swap(FunctionsWithBodies);
   DeferredFunctionInfo.clear();
+  DeferredMetadataInfo.clear();
   MDKindMap.clear();
 
   assert(BasicBlockFwdRefs.empty() && "Unresolved blockaddress fwd references");
@@ -1199,6 +1200,7 @@ std::error_code BitcodeReader::ParseValueSymbolTable() {
 static int64_t unrotateSign(uint64_t U) { return U & 1 ? ~(U >> 1) : U >> 1; }
 
 std::error_code BitcodeReader::ParseMetadata() {
+  IsMetadataMaterialized = true;
   unsigned NextMDValueNo = MDValueList.size();
 
   if (Stream.EnterSubBlock(bitc::METADATA_BLOCK_ID))
@@ -2235,6 +2237,30 @@ std::error_code BitcodeReader::ParseUseLists() {
   }
 }
 
+/// When we see the block for metadata, remember where it is and then skip it.
+/// This lets us lazily deserialize the metadata.
+std::error_code BitcodeReader::rememberAndSkipMetadata() {
+  // Save the current stream state.
+  uint64_t CurBit = Stream.GetCurrentBitNo();
+  DeferredMetadataInfo.push_back(CurBit);
+
+  // Skip over the block for now.
+  if (Stream.SkipBlock())
+    return Error("Invalid record");
+  return std::error_code();
+}
+
+std::error_code BitcodeReader::materializeMetadata() {
+  for (uint64_t BitPos : DeferredMetadataInfo) {
+    // Move the bit stream to the saved position.
+    Stream.JumpToBit(BitPos);
+    if (std::error_code EC = ParseMetadata())
+      return EC;
+  }
+  DeferredMetadataInfo.clear();
+  return std::error_code();
+}
+
 /// RememberAndSkipFunctionBody - When we see the block for a function body,
 /// remember where it is and then skip it.  This lets us lazily deserialize the
 /// functions.
@@ -2285,7 +2311,8 @@ std::error_code BitcodeReader::GlobalCleanup() {
   return std::error_code();
 }
 
-std::error_code BitcodeReader::ParseModule(bool Resume) {
+std::error_code BitcodeReader::ParseModule(bool Resume,
+                                           bool ShouldLazyLoadMetadata) {
   if (Resume)
     Stream.JumpToBit(NextUnreadBit);
   else if (Stream.EnterSubBlock(bitc::MODULE_BLOCK_ID))
@@ -2339,6 +2366,12 @@ std::error_code BitcodeReader::ParseModule(bool Resume) {
           return EC;
         break;
       case bitc::METADATA_BLOCK_ID:
+        if (ShouldLazyLoadMetadata && !IsMetadataMaterialized) {
+          if (std::error_code EC = rememberAndSkipMetadata())
+            return EC;
+          break;
+        }
+        assert(DeferredMetadataInfo.empty() && "Unexpected deferred metadata");
         if (std::error_code EC = ParseMetadata())
           return EC;
         break;
@@ -2653,7 +2686,8 @@ std::error_code BitcodeReader::ParseModule(bool Resume) {
   }
 }
 
-std::error_code BitcodeReader::ParseBitcodeInto(Module *M) {
+std::error_code BitcodeReader::ParseBitcodeInto(Module *M,
+                                                bool ShouldLazyLoadMetadata) {
   TheModule = nullptr;
 
   if (std::error_code EC = InitStream())
@@ -2694,7 +2728,7 @@ std::error_code BitcodeReader::ParseBitcodeInto(Module *M) {
         if (TheModule)
           return Error("Invalid multiple blocks");
         TheModule = M;
-        if (std::error_code EC = ParseModule(false))
+        if (std::error_code EC = ParseModule(false, ShouldLazyLoadMetadata))
           return EC;
         if (LazyStreamer)
           return std::error_code();
@@ -3894,6 +3928,9 @@ std::error_code BitcodeReader::FindFunctionInStream(
 void BitcodeReader::releaseBuffer() { Buffer.release(); }
 
 std::error_code BitcodeReader::materialize(GlobalValue *GV) {
+  if (std::error_code EC = materializeMetadata())
+    return EC;
+
   Function *F = dyn_cast<Function>(GV);
   // If it's not a function or is already material, ignore the request.
   if (!F || !F->isMaterializable())
@@ -3961,6 +3998,9 @@ std::error_code BitcodeReader::MaterializeModule(Module *M) {
   assert(M == TheModule &&
          "Can only Materialize the Module this BitcodeReader is attached to.");
 
+  if (std::error_code EC = materializeMetadata())
+    return EC;
+
   // Promise to materialize all forward references.
   WillMaterializeAllForwardRefs = true;
 
@@ -4101,7 +4141,8 @@ const std::error_category &llvm::BitcodeErrorCategory() {
 static ErrorOr<Module *>
 getLazyBitcodeModuleImpl(std::unique_ptr<MemoryBuffer> &&Buffer,
                          LLVMContext &Context, bool WillMaterializeAll,
-                         DiagnosticHandlerFunction DiagnosticHandler) {
+                         DiagnosticHandlerFunction DiagnosticHandler,
+                         bool ShouldLazyLoadMetadata = false) {
   Module *M = new Module(Buffer->getBufferIdentifier(), Context);
   BitcodeReader *R =
       new BitcodeReader(Buffer.get(), Context, DiagnosticHandler);
@@ -4113,7 +4154,8 @@ getLazyBitcodeModuleImpl(std::unique_ptr<MemoryBuffer> &&Buffer,
     return EC;
   };
 
-  if (std::error_code EC = R->ParseBitcodeInto(M))
+  // Delay parsing Metadata if ShouldLazyLoadMetadata is true.
+  if (std::error_code EC = R->ParseBitcodeInto(M, ShouldLazyLoadMetadata))
     return cleanupOnError(EC);
 
   if (!WillMaterializeAll)
@@ -4128,9 +4170,10 @@ getLazyBitcodeModuleImpl(std::unique_ptr<MemoryBuffer> &&Buffer,
 ErrorOr<Module *>
 llvm::getLazyBitcodeModule(std::unique_ptr<MemoryBuffer> &&Buffer,
                            LLVMContext &Context,
-                           DiagnosticHandlerFunction DiagnosticHandler) {
+                           DiagnosticHandlerFunction DiagnosticHandler,
+                           bool ShouldLazyLoadMetadata) {
   return getLazyBitcodeModuleImpl(std::move(Buffer), Context, false,
-                                  DiagnosticHandler);
+                                  DiagnosticHandler, ShouldLazyLoadMetadata);
 }
 
 ErrorOr<std::unique_ptr<Module>>

lib/Bitcode/Reader/BitcodeReader.h

@@ -190,6 +190,11 @@ class BitcodeReader : public GVMaterializer {
   /// stream.
   DenseMap<Function*, uint64_t> DeferredFunctionInfo;
 
+  /// When Metadata block is initially scanned when parsing the module, we may
+  /// choose to defer parsing of the metadata. This vector contains info about
+  /// which Metadata blocks are deferred.
+  std::vector<uint64_t> DeferredMetadataInfo;
+
   /// These are basic blocks forward-referenced by block addresses.  They are
   /// inserted lazily into functions when they're loaded.  The basic block ID is
   /// its index into the vector.
@@ -212,6 +217,9 @@ class BitcodeReader : public GVMaterializer {
   /// Functions that have block addresses taken.  This is usually empty.
   SmallPtrSet<const Function *, 4> BlockAddressesTaken;
 
+  /// True if any Metadata block has been materialized.
+  bool IsMetadataMaterialized;
+
 public:
   std::error_code Error(BitcodeError E, const Twine &Message);
   std::error_code Error(BitcodeError E);
@@ -237,7 +245,8 @@ public:
 
   /// @brief Main interface to parsing a bitcode buffer.
   /// @returns true if an error occurred.
-  std::error_code ParseBitcodeInto(Module *M);
+  std::error_code ParseBitcodeInto(Module *M,
+                                   bool ShouldLazyLoadMetadata = false);
 
   /// @brief Cheap mechanism to just extract module triple
   /// @returns true if an error occurred.
@@ -245,6 +254,9 @@ public:
 
   static uint64_t decodeSignRotatedValue(uint64_t V);
 
+  /// Materialize any deferred Metadata block.
+  std::error_code materializeMetadata();
+
 private:
   std::vector<StructType *> IdentifiedStructTypes;
   StructType *createIdentifiedStructType(LLVMContext &Context, StringRef Name);
@@ -340,7 +352,7 @@ private:
   /// a corresponding error code.
   std::error_code parseAlignmentValue(uint64_t Exponent, unsigned &Alignment);
   std::error_code ParseAttrKind(uint64_t Code, Attribute::AttrKind *Kind);
-  std::error_code ParseModule(bool Resume);
+  std::error_code ParseModule(bool Resume, bool ShouldLazyLoadMetadata = false);
   std::error_code ParseAttributeBlock();
   std::error_code ParseAttributeGroupBlock();
   std::error_code ParseTypeTable();
@@ -349,6 +361,8 @@ private:
   std::error_code ParseValueSymbolTable();
   std::error_code ParseConstants();
   std::error_code RememberAndSkipFunctionBody();
+  /// Save the positions of the Metadata blocks and skip parsing the blocks.
+  std::error_code rememberAndSkipMetadata();
   std::error_code ParseFunctionBody(Function *F);
   std::error_code GlobalCleanup();
   std::error_code ResolveGlobalAndAliasInits();

lib/LTO/LTOModule.cpp

@@ -179,7 +179,8 @@ static Module *parseBitcodeFileImpl(MemoryBufferRef Buffer,
   std::unique_ptr<MemoryBuffer> LightweightBuf =
       MemoryBuffer::getMemBuffer(*MBOrErr, false);
   ErrorOr<Module *> M = getLazyBitcodeModule(std::move(LightweightBuf), Context,
-                                             DiagnosticHandler);
+                                             DiagnosticHandler,
+                                             true/*ShouldLazyLoadMetadata*/);
   if (!M)
     return nullptr;
   return *M;