IR, Bitcode: Change bitcode reader to no longer own its memory buffer.

Unique ownership is just one possible ownership pattern for the memory buffer
underlying the bitcode reader. In practice, as this patch shows, ownership can
often reside at a higher level. With the upcoming change to allow multiple
modules in a single bitcode file, it will no longer be appropriate for
modules to generally have unique ownership of their memory buffer.

The C API exposes the ownership relation via the LLVMGetBitcodeModuleInContext
and LLVMGetBitcodeModuleInContext2 functions, so we still need some way for
the module to own the memory buffer. This patch does so by adding an owned
memory buffer field to Module, and using it in a few other places where it
is convenient.

Differential Revision: https://reviews.llvm.org/D26384

llvm-svn: 286214

2 files changed, 55 insertions, 114 deletions

diff --git a/llvm/lib/Bitcode/Reader/BitReader.cpp b/llvm/lib/Bitcode/Reader/BitReader.cpp
index 9ac3cb95d08..8527bcf7c3b 100644
--- a/llvm/lib/Bitcode/Reader/BitReader.cpp
+++ b/llvm/lib/Bitcode/Reader/BitReader.cpp
@@ -101,7 +101,7 @@ LLVMBool LLVMGetBitcodeModuleInContext(LLVMContextRef ContextRef,
   std::unique_ptr<MemoryBuffer> Owner(unwrap(MemBuf));
 
   ErrorOr<std::unique_ptr<Module>> ModuleOrErr =
-      getLazyBitcodeModule(std::move(Owner), Ctx);
+      getOwningLazyBitcodeModule(std::move(Owner), Ctx);
   Owner.release();
   Ctx.setDiagnosticHandler(OldDiagnosticHandler, OldDiagnosticContext, true);
 
@@ -124,7 +124,7 @@ LLVMBool LLVMGetBitcodeModuleInContext2(LLVMContextRef ContextRef,
   std::unique_ptr<MemoryBuffer> Owner(unwrap(MemBuf));
 
   ErrorOr<std::unique_ptr<Module>> ModuleOrErr =
-      getLazyBitcodeModule(std::move(Owner), Ctx);
+      getOwningLazyBitcodeModule(std::move(Owner), Ctx);
   Owner.release();
 
   if (ModuleOrErr.getError()) {
diff --git a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
index a5f040bfa36..e5c48120950 100644
--- a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
+++ b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -230,9 +230,9 @@ private:
 
 class BitcodeReaderBase {
 protected:
-  BitcodeReaderBase(MemoryBuffer *Buffer) : Buffer(Buffer) {}
+  BitcodeReaderBase(MemoryBufferRef Buffer) : Buffer(Buffer) {}
 
-  std::unique_ptr<MemoryBuffer> Buffer;
+  MemoryBufferRef Buffer;
   BitstreamBlockInfo BlockInfo;
   BitstreamCursor Stream;
 
@@ -244,10 +244,10 @@ protected:
 };
 
 std::error_code BitcodeReaderBase::initStream() {
-  const unsigned char *BufPtr = (const unsigned char*)Buffer->getBufferStart();
-  const unsigned char *BufEnd = BufPtr+Buffer->getBufferSize();
+  const unsigned char *BufPtr = (const unsigned char*)Buffer.getBufferStart();
+  const unsigned char *BufEnd = BufPtr+Buffer.getBufferSize();
 
-  if (Buffer->getBufferSize() & 3)
+  if (Buffer.getBufferSize() & 3)
     return error("Invalid bitcode signature");
 
   // If we have a wrapper header, parse it and ignore the non-bc file contents.
@@ -360,15 +360,10 @@ public:
   std::error_code error(BitcodeError E, const Twine &Message);
   std::error_code error(const Twine &Message) override;
 
-  BitcodeReader(MemoryBuffer *Buffer, LLVMContext &Context);
-  ~BitcodeReader() override { freeState(); }
+  BitcodeReader(MemoryBufferRef Buffer, LLVMContext &Context);
 
   std::error_code materializeForwardReferencedFunctions();
 
-  void freeState();
-
-  void releaseBuffer();
-
   std::error_code materialize(GlobalValue *GV) override;
   std::error_code materializeModule() override;
   std::vector<StructType *> getIdentifiedStructTypes() const override;
@@ -585,13 +580,8 @@ public:
   std::error_code error(const Twine &Message);
 
   ModuleSummaryIndexBitcodeReader(
-      MemoryBuffer *Buffer, DiagnosticHandlerFunction DiagnosticHandler,
+      MemoryBufferRef Buffer, DiagnosticHandlerFunction DiagnosticHandler,
       bool CheckGlobalValSummaryPresenceOnly = false);
-  ~ModuleSummaryIndexBitcodeReader() { freeState(); }
-
-  void freeState();
-
-  void releaseBuffer();
 
   /// Check if the parser has encountered a summary section.
   bool foundGlobalValSummary() { return SeenGlobalValSummary; }
@@ -661,7 +651,7 @@ std::error_code BitcodeReader::error(const Twine &Message) {
                  Message);
 }
 
-BitcodeReader::BitcodeReader(MemoryBuffer *Buffer, LLVMContext &Context)
+BitcodeReader::BitcodeReader(MemoryBufferRef Buffer, LLVMContext &Context)
     : BitcodeReaderBase(Buffer), Context(Context), ValueList(Context),
       MetadataList(Context) {}
 
@@ -698,24 +688,6 @@ std::error_code BitcodeReader::materializeForwardReferencedFunctions() {
   return std::error_code();
 }
 
-void BitcodeReader::freeState() {
-  Buffer = nullptr;
-  std::vector<Type*>().swap(TypeList);
-  ValueList.clear();
-  MetadataList.clear();
-  std::vector<Comdat *>().swap(ComdatList);
-
-  std::vector<AttributeSet>().swap(MAttributes);
-  std::vector<BasicBlock*>().swap(FunctionBBs);
-  std::vector<Function*>().swap(FunctionsWithBodies);
-  DeferredFunctionInfo.clear();
-  DeferredMetadataInfo.clear();
-  MDKindMap.clear();
-
-  assert(BasicBlockFwdRefs.empty() && "Unresolved blockaddress fwd references");
-  BasicBlockFwdRefQueue.clear();
-}
-
 //===----------------------------------------------------------------------===//
 //  Helper functions to implement forward reference resolution, etc.
 //===----------------------------------------------------------------------===//
@@ -5887,8 +5859,6 @@ std::error_code BitcodeReader::findFunctionInStream(
 // GVMaterializer implementation
 //===----------------------------------------------------------------------===//
 
-void BitcodeReader::releaseBuffer() { Buffer.release(); }
-
 std::error_code BitcodeReader::materialize(GlobalValue *GV) {
   Function *F = dyn_cast<Function>(GV);
   // If it's not a function or is already material, ignore the request.
@@ -6006,16 +5976,12 @@ std::error_code ModuleSummaryIndexBitcodeReader::error(const Twine &Message) {
 }
 
 ModuleSummaryIndexBitcodeReader::ModuleSummaryIndexBitcodeReader(
-    MemoryBuffer *Buffer, DiagnosticHandlerFunction DiagnosticHandler,
+    MemoryBufferRef Buffer, DiagnosticHandlerFunction DiagnosticHandler,
     bool CheckGlobalValSummaryPresenceOnly)
     : BitcodeReaderBase(Buffer),
       DiagnosticHandler(std::move(DiagnosticHandler)),
       CheckGlobalValSummaryPresenceOnly(CheckGlobalValSummaryPresenceOnly) {}
 
-void ModuleSummaryIndexBitcodeReader::freeState() { Buffer = nullptr; }
-
-void ModuleSummaryIndexBitcodeReader::releaseBuffer() { Buffer.release(); }
-
 std::pair<GlobalValue::GUID, GlobalValue::GUID>
 ModuleSummaryIndexBitcodeReader::getGUIDFromValueId(unsigned ValueId) {
   auto VGI = ValueIdToCallGraphGUIDMap.find(ValueId);
@@ -6219,7 +6185,7 @@ std::error_code ModuleSummaryIndexBitcodeReader::parseModule() {
             break;
           if (TheIndex->modulePaths().empty())
             // We always seed the index with the module.
-            TheIndex->addModulePath(Buffer->getBufferIdentifier(), 0);
+            TheIndex->addModulePath(Buffer.getBufferIdentifier(), 0);
           if (TheIndex->modulePaths().size() != 1)
             return error("Don't expect multiple modules defined?");
           auto &Hash = TheIndex->modulePaths().begin()->second.second;
@@ -6359,7 +6325,7 @@ std::error_code ModuleSummaryIndexBitcodeReader::parseEntireSummary() {
       // module path string table entry with an empty (0) ID to take
       // ownership.
       FS->setModulePath(
-          TheIndex->addModulePath(Buffer->getBufferIdentifier(), 0)->first());
+          TheIndex->addModulePath(Buffer.getBufferIdentifier(), 0)->first());
       static int RefListStartIndex = 4;
       int CallGraphEdgeStartIndex = RefListStartIndex + NumRefs;
       assert(Record.size() >= RefListStartIndex + NumRefs &&
@@ -6398,7 +6364,7 @@ std::error_code ModuleSummaryIndexBitcodeReader::parseEntireSummary() {
       // module path string table entry with an empty (0) ID to take
       // ownership.
       AS->setModulePath(
-          TheIndex->addModulePath(Buffer->getBufferIdentifier(), 0)->first());
+          TheIndex->addModulePath(Buffer.getBufferIdentifier(), 0)->first());
 
       GlobalValue::GUID AliaseeGUID = getGUIDFromValueId(AliaseeID).first;
       auto *AliaseeSummary = TheIndex->getGlobalValueSummary(AliaseeGUID);
@@ -6419,7 +6385,7 @@ std::error_code ModuleSummaryIndexBitcodeReader::parseEntireSummary() {
       std::unique_ptr<GlobalVarSummary> FS =
           llvm::make_unique<GlobalVarSummary>(Flags);
       FS->setModulePath(
-          TheIndex->addModulePath(Buffer->getBufferIdentifier(), 0)->first());
+          TheIndex->addModulePath(Buffer.getBufferIdentifier(), 0)->first());
       for (unsigned I = 2, E = Record.size(); I != E; ++I) {
         unsigned RefValueId = Record[I];
         GlobalValue::GUID RefGUID = getGUIDFromValueId(RefValueId).first;
@@ -6677,77 +6643,68 @@ const std::error_category &llvm::BitcodeErrorCategory() {
 // External interface
 //===----------------------------------------------------------------------===//
 
+/// \brief Get a lazy one-at-time loading module from bitcode.
+///
+/// This isn't always used in a lazy context.  In particular, it's also used by
+/// \a parseBitcodeFile().  If this is truly lazy, then we need to eagerly pull
+/// in forward-referenced functions from block address references.
+///
+/// \param[in] MaterializeAll Set to \c true if we should materialize
+/// everything.
 static ErrorOr<std::unique_ptr<Module>>
-getBitcodeModuleImpl(StringRef Name, BitcodeReader *R, LLVMContext &Context,
-                     bool MaterializeAll, bool ShouldLazyLoadMetadata) {
-  std::unique_ptr<Module> M = llvm::make_unique<Module>(Name, Context);
-  M->setMaterializer(R);
+getLazyBitcodeModuleImpl(MemoryBufferRef Buffer, LLVMContext &Context,
+                         bool MaterializeAll,
+                         bool ShouldLazyLoadMetadata = false) {
+  BitcodeReader *R = new BitcodeReader(Buffer, Context);
 
-  auto cleanupOnError = [&](std::error_code EC) {
-    R->releaseBuffer(); // Never take ownership on error.
-    return EC;
-  };
+  std::unique_ptr<Module> M =
+      llvm::make_unique<Module>(Buffer.getBufferIdentifier(), Context);
+  M->setMaterializer(R);
 
   // Delay parsing Metadata if ShouldLazyLoadMetadata is true.
   if (std::error_code EC = R->parseBitcodeInto(M.get(), ShouldLazyLoadMetadata))
-    return cleanupOnError(EC);
+    return EC;
 
   if (MaterializeAll) {
     // Read in the entire module, and destroy the BitcodeReader.
     if (std::error_code EC = M->materializeAll())
-      return cleanupOnError(EC);
+      return EC;
   } else {
     // Resolve forward references from blockaddresses.
     if (std::error_code EC = R->materializeForwardReferencedFunctions())
-      return cleanupOnError(EC);
+      return EC;
   }
   return std::move(M);
 }
 
-/// \brief Get a lazy one-at-time loading module from bitcode.
-///
-/// This isn't always used in a lazy context.  In particular, it's also used by
-/// \a parseBitcodeFile().  If this is truly lazy, then we need to eagerly pull
-/// in forward-referenced functions from block address references.
-///
-/// \param[in] MaterializeAll Set to \c true if we should materialize
-/// everything.
-static ErrorOr<std::unique_ptr<Module>>
-getLazyBitcodeModuleImpl(std::unique_ptr<MemoryBuffer> &&Buffer,
-                         LLVMContext &Context, bool MaterializeAll,
-                         bool ShouldLazyLoadMetadata = false) {
-  BitcodeReader *R = new BitcodeReader(Buffer.get(), Context);
-
-  ErrorOr<std::unique_ptr<Module>> Ret =
-      getBitcodeModuleImpl(Buffer->getBufferIdentifier(), R, Context,
-                           MaterializeAll, ShouldLazyLoadMetadata);
-  if (!Ret)
-    return Ret;
-
-  Buffer.release(); // The BitcodeReader owns it now.
-  return Ret;
-}
-
 ErrorOr<std::unique_ptr<Module>>
-llvm::getLazyBitcodeModule(std::unique_ptr<MemoryBuffer> &&Buffer,
+llvm::getLazyBitcodeModule(MemoryBufferRef Buffer,
                            LLVMContext &Context, bool ShouldLazyLoadMetadata) {
-  return getLazyBitcodeModuleImpl(std::move(Buffer), Context, false,
+  return getLazyBitcodeModuleImpl(Buffer, Context, false,
                                   ShouldLazyLoadMetadata);
 }
 
+ErrorOr<std::unique_ptr<Module>>
+llvm::getOwningLazyBitcodeModule(std::unique_ptr<MemoryBuffer> &&Buffer,
+                                 LLVMContext &Context,
+                                 bool ShouldLazyLoadMetadata) {
+  auto MOrErr = getLazyBitcodeModule(*Buffer, Context, ShouldLazyLoadMetadata);
+  if (MOrErr)
+    (*MOrErr)->setOwnedMemoryBuffer(std::move(Buffer));
+  return MOrErr;
+}
+
 ErrorOr<std::unique_ptr<Module>> llvm::parseBitcodeFile(MemoryBufferRef Buffer,
                                                         LLVMContext &Context) {
-  std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false);
-  return getLazyBitcodeModuleImpl(std::move(Buf), Context, true);
+  return getLazyBitcodeModuleImpl(Buffer, Context, true);
   // TODO: Restore the use-lists to the in-memory state when the bitcode was
   // written.  We must defer until the Module has been fully materialized.
 }
 
 std::string llvm::getBitcodeTargetTriple(MemoryBufferRef Buffer,
                                          LLVMContext &Context) {
-  std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false);
-  auto R = llvm::make_unique<BitcodeReader>(Buf.release(), Context);
-  ErrorOr<std::string> Triple = R->parseTriple();
+  BitcodeReader R(Buffer, Context);
+  ErrorOr<std::string> Triple = R.parseTriple();
   if (Triple.getError())
     return "";
   return Triple.get();
@@ -6755,9 +6712,8 @@ std::string llvm::getBitcodeTargetTriple(MemoryBufferRef Buffer,
 
 bool llvm::isBitcodeContainingObjCCategory(MemoryBufferRef Buffer,
                                            LLVMContext &Context) {
-  std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false);
-  auto R = llvm::make_unique<BitcodeReader>(Buf.release(), Context);
-  ErrorOr<bool> hasObjCCategory = R->hasObjCCategory();
+  BitcodeReader R(Buffer, Context);
+  ErrorOr<bool> hasObjCCategory = R.hasObjCCategory();
   if (hasObjCCategory.getError())
     return false;
   return hasObjCCategory.get();
@@ -6765,8 +6721,7 @@ bool llvm::isBitcodeContainingObjCCategory(MemoryBufferRef Buffer,
 
 std::string llvm::getBitcodeProducerString(MemoryBufferRef Buffer,
                                            LLVMContext &Context) {
-  std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false);
-  BitcodeReader R(Buf.release(), Context);
+  BitcodeReader R(Buffer, Context);
   ErrorOr<std::string> ProducerString = R.parseIdentificationBlock();
   if (ProducerString.getError())
     return "";
@@ -6777,20 +6732,13 @@ std::string llvm::getBitcodeProducerString(MemoryBufferRef Buffer,
 ErrorOr<std::unique_ptr<ModuleSummaryIndex>> llvm::getModuleSummaryIndex(
     MemoryBufferRef Buffer,
     const DiagnosticHandlerFunction &DiagnosticHandler) {
-  std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false);
-  ModuleSummaryIndexBitcodeReader R(Buf.get(), DiagnosticHandler);
+  ModuleSummaryIndexBitcodeReader R(Buffer, DiagnosticHandler);
 
   auto Index = llvm::make_unique<ModuleSummaryIndex>();
 
-  auto cleanupOnError = [&](std::error_code EC) {
-    R.releaseBuffer(); // Never take ownership on error.
-    return EC;
-  };
-
   if (std::error_code EC = R.parseSummaryIndexInto(Index.get()))
-    return cleanupOnError(EC);
+    return EC;
 
-  Buf.release(); // The ModuleSummaryIndexBitcodeReader owns it now.
   return std::move(Index);
 }
 
@@ -6798,17 +6746,10 @@ ErrorOr<std::unique_ptr<ModuleSummaryIndex>> llvm::getModuleSummaryIndex(
 bool llvm::hasGlobalValueSummary(
     MemoryBufferRef Buffer,
     const DiagnosticHandlerFunction &DiagnosticHandler) {
-  std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false);
-  ModuleSummaryIndexBitcodeReader R(Buf.get(), DiagnosticHandler, true);
+  ModuleSummaryIndexBitcodeReader R(Buffer, DiagnosticHandler, true);
 
-  auto cleanupOnError = [&](std::error_code EC) {
-    R.releaseBuffer(); // Never take ownership on error.
+  if (R.parseSummaryIndexInto(nullptr))
     return false;
-  };
-
-  if (std::error_code EC = R.parseSummaryIndexInto(nullptr))
-    return cleanupOnError(EC);
 
-  Buf.release(); // The ModuleSummaryIndexBitcodeReader owns it now.
   return R.foundGlobalValSummary();
 }