Bitcode: Introduce a BitcodeFileContents data type. NFCI.

[pcc]

Summary

This data type includes the contents of a bitcode file.
Right now a bitcode file can only contain modules, but
a later change will add a symbol table.

[eugenis]

LGTM with a nit

llvm/include/llvm/Object/IRObjectFile.h

23

why is this necessary?

[pcc]

llvm/include/llvm/Object/IRObjectFile.h

23

This header was previously relying on the forward declaration of BitcodeModule in IRSymtab.h. Because I have removed that declaration I need to add it here.

[tejohnson]

llvm/include/llvm/Bitcode/BitcodeReader.h

106

Suggest moving the struct def above the function declaration.

llvm/include/llvm/Object/IRObjectFile.h

73

Should this use the new type?

[pcc]

llvm/include/llvm/Bitcode/BitcodeReader.h

106

Will do

llvm/include/llvm/Object/IRObjectFile.h

73

Yes, I'll do the obvious search and replace on these patches when I commit them.

llvm/include/llvm/Bitcode/BitcodeReader.h

namespace llvm {
 
   template <typename T>
   ErrorOr<T> expectedToErrorOrAndEmitErrors(LLVMContext &Ctx, Expected<T> Val) {
     if (!Val)
       return errorToErrorCodeAndEmitErrors(Ctx, Val.takeError());
     return std::move(*Val);
   }
 
+  struct BitcodeFileContents;
+
   /// Represents a module in a bitcode file.
   class BitcodeModule {
     // This covers the identification (if present) and module blocks.
     ArrayRef<uint8_t> Buffer;
     StringRef ModuleIdentifier;
 
     // The string table used to interpret this module.
     StringRef Strtab;
 
     // The bitstream location of the IDENTIFICATION_BLOCK.
     uint64_t IdentificationBit;
 
     // The bitstream location of this module's MODULE_BLOCK.
     uint64_t ModuleBit;
 
     BitcodeModule(ArrayRef<uint8_t> Buffer, StringRef ModuleIdentifier,
                   uint64_t IdentificationBit, uint64_t ModuleBit)
         : Buffer(Buffer), ModuleIdentifier(ModuleIdentifier),
           IdentificationBit(IdentificationBit), ModuleBit(ModuleBit) {}
 
     // Calls the ctor.
-    friend Expected<std::vector<BitcodeModule>>
-    getBitcodeModuleList(MemoryBufferRef Buffer);
+    friend Expected<BitcodeFileContents>
+    getBitcodeFileContents(MemoryBufferRef Buffer);
 
     Expected<std::unique_ptr<Module>> getModuleImpl(LLVMContext &Context,
                                                     bool MaterializeAll,
                                                     bool ShouldLazyLoadMetadata,
                                                     bool IsImporting);
 
   public:
     StringRef getBuffer() const {
public:
     /// Parse the specified bitcode buffer, returning the module summary index.
     Expected<std::unique_ptr<ModuleSummaryIndex>> getSummary();
 
     /// Parse the specified bitcode buffer and merge its module summary index
     /// into CombinedIndex.
     Error readSummary(ModuleSummaryIndex &CombinedIndex, unsigned ModuleId);
   };
 
+  /// Returns the contents of a bitcode file.
+  Expected<BitcodeFileContents> getBitcodeFileContents(MemoryBufferRef Buffer);
+  struct BitcodeFileContents {
+    std::vector<BitcodeModule> Mods;
+  };
+
   /// Returns a list of modules in the specified bitcode buffer.
   Expected<std::vector<BitcodeModule>>
   getBitcodeModuleList(MemoryBufferRef Buffer);
 
   /// Read the header of the specified bitcode buffer and prepare for lazy
   /// deserialization of function bodies. If ShouldLazyLoadMetadata is true,
   /// lazily load metadata as well. If IsImporting is true, this module is
   /// being parsed for ThinLTO importing into another module.

llvm/include/llvm/Object/IRObjectFile.h

 #define LLVM_OBJECT_IROBJECTFILE_H
 
 #include "llvm/ADT/PointerUnion.h"
 #include "llvm/Object/IRSymtab.h"
 #include "llvm/Object/ModuleSymbolTable.h"
 #include "llvm/Object/SymbolicFile.h"
 
 namespace llvm {
+class BitcodeModule;
 class Mangler;
 class Module;
 class GlobalValue;
 class Triple;
 
 namespace object {
 class ObjectFile;
 

 };
 }
 
 namespace irsymtab {
 
 /// The contents of a bitcode file and its irsymtab. Any underlying data
 /// for the irsymtab are owned by Symtab and Strtab.
 struct File {
   std::vector<BitcodeModule> Mods;
   SmallVector<char, 0> Symtab, Strtab;
   Reader TheReader;
 };
 
 /// Reads a bitcode file, creating its irsymtab if necessary.
 Expected<File> read(MemoryBufferRef MBRef);
 
 }
 
 }
 
 #endif

llvm/include/llvm/Object/IRSymtab.h

 #include "llvm/Support/Endian.h"
 #include "llvm/Support/Error.h"
 #include <cassert>
 #include <cstdint>
 #include <vector>
 
 namespace llvm {
 
-class BitcodeModule;
+struct BitcodeFileContents;
 
 namespace irsymtab {
 
 namespace storage {
 
 // The data structures in this namespace define the low-level serialization
 // format. Clients that just want to read a symbol table should use the
 // irsymtab::Reader class.

 /// The contents of a bitcode file and its irsymtab. Any underlying data
 /// for the irsymtab are owned by Symtab and Strtab.
 struct FileContents {
   SmallVector<char, 0> Symtab, Strtab;
   Reader TheReader;
 };
 
 /// Reads the contents of a bitcode file, creating its irsymtab if necessary.
-Expected<FileContents> readBitcode(ArrayRef<BitcodeModule> Mods);
+Expected<FileContents> readBitcode(const BitcodeFileContents &BFC);
 
 } // end namespace irsymtab
 } // end namespace llvm
 
 #endif // LLVM_OBJECT_IRSYMTAB_H

llvm/lib/Bitcode/Reader/BitcodeReader.cpp

 }
 
 //===----------------------------------------------------------------------===//
 // External interface
 //===----------------------------------------------------------------------===//
 
 Expected<std::vector<BitcodeModule>>
 llvm::getBitcodeModuleList(MemoryBufferRef Buffer) {
+  auto FOrErr = getBitcodeFileContents(Buffer);
+  if (!FOrErr)
+    return FOrErr.takeError();
+  return std::move(FOrErr->Mods);
+}
+
+Expected<BitcodeFileContents>
+llvm::getBitcodeFileContents(MemoryBufferRef Buffer) {
   Expected<BitstreamCursor> StreamOrErr = initStream(Buffer);
   if (!StreamOrErr)
     return StreamOrErr.takeError();
   BitstreamCursor &Stream = *StreamOrErr;
 
-  std::vector<BitcodeModule> Modules;
+  BitcodeFileContents F;
   while (true) {
     uint64_t BCBegin = Stream.getCurrentByteNo();
 
     // We may be consuming bitcode from a client that leaves garbage at the end
     // of the bitcode stream (e.g. Apple's ar tool). If we are close enough to
     // the end that there cannot possibly be another module, stop looking.
     if (BCBegin + 8 >= Stream.getBitcodeBytes().size())
-      return Modules;
+      return F;
 
     BitstreamEntry Entry = Stream.advance();
     switch (Entry.Kind) {
     case BitstreamEntry::EndBlock:
     case BitstreamEntry::Error:
       return error("Malformed block");
 
     case BitstreamEntry::SubBlock: {
case BitstreamEntry::SubBlock: {
           return error("Malformed block");
       }
 
       if (Entry.ID == bitc::MODULE_BLOCK_ID) {
         uint64_t ModuleBit = Stream.GetCurrentBitNo() - BCBegin * 8;
         if (Stream.SkipBlock())
           return error("Malformed block");
 
-        Modules.push_back({Stream.getBitcodeBytes().slice(
-                               BCBegin, Stream.getCurrentByteNo() - BCBegin),
-                           Buffer.getBufferIdentifier(), IdentificationBit,
-                           ModuleBit});
+        F.Mods.push_back({Stream.getBitcodeBytes().slice(
         continue;
       }
 
       if (Entry.ID == bitc::STRTAB_BLOCK_ID) {
         Expected<StringRef> Strtab = readStrtab(Stream);
         if (!Strtab)
           return Strtab.takeError();
         // This string table is used by every preceding bitcode module that does
         // not have its own string table. A bitcode file may have multiple
         // string tables if it was created by binary concatenation, for example
         // with "llvm-cat -b".
-        for (auto I = Modules.rbegin(), E = Modules.rend(); I != E; ++I) {
+        for (auto I = F.Mods.rbegin(), E = F.Mods.rend(); I != E; ++I) {
           if (!I->Strtab.empty())
             break;
           I->Strtab = *Strtab;
         }
         continue;
       }
 
       if (Stream.SkipBlock())

llvm/lib/Object/IRObjectFile.cpp

 
 Expected<irsymtab::File> irsymtab::read(MemoryBufferRef MBRef) {
   File F;
   ErrorOr<MemoryBufferRef> BCOrErr =
       object::IRObjectFile::findBitcodeInMemBuffer(MBRef);
   if (!BCOrErr)
     return errorCodeToError(BCOrErr.getError());
 
-  Expected<std::vector<BitcodeModule>> BMsOrErr =
-      getBitcodeModuleList(*BCOrErr);
-  if (!BMsOrErr)
-    return BMsOrErr.takeError();
+  Expected<BitcodeFileContents> BFCOrErr = getBitcodeFileContents(*BCOrErr);
+  if (!BFCOrErr)
+    return BFCOrErr.takeError();
 
-  Expected<FileContents> FCOrErr = readBitcode(*BMsOrErr);
+  Expected<FileContents> FCOrErr = readBitcode(*BFCOrErr);
   if (!FCOrErr)
     return FCOrErr.takeError();
 
-  F.Mods = std::move(*BMsOrErr);
+  F.Mods = std::move(BFCOrErr->Mods);
   F.Symtab = std::move(FCOrErr->Symtab);
   F.Strtab = std::move(FCOrErr->Strtab);
   F.TheReader = std::move(FCOrErr->TheReader);
   return std::move(F);
 }

llvm/lib/Object/IRSymtab.cpp

 
 } // end anonymous namespace
 
 Error irsymtab::build(ArrayRef<Module *> Mods, SmallVector<char, 0> &Symtab,
                       SmallVector<char, 0> &Strtab) {
   return Builder(Symtab, Strtab).build(Mods);
 }
 
-Expected<FileContents> irsymtab::readBitcode(ArrayRef<BitcodeModule> BMs) {
+// Upgrade a vector of bitcode modules created by an old version of LLVM by
+// creating an irsymtab for them in the current format.
+static Expected<FileContents> upgrade(ArrayRef<BitcodeModule> BMs) {
   FileContents FC;
-  if (BMs.empty())
-    return make_error<StringError>("Bitcode file does not contain any modules",
-                                   inconvertibleErrorCode());
 
   LLVMContext Ctx;
   std::vector<Module *> Mods;
   std::vector<std::unique_ptr<Module>> OwnedMods;
   for (auto BM : BMs) {
     Expected<std::unique_ptr<Module>> MOrErr =
         BM.getLazyModule(Ctx, /*ShouldLazyLoadMetadata*/ true,
                          /*IsImporting*/ false);
static Expected<FileContents> upgrade(ArrayRef<BitcodeModule> BMs) {
 
   if (Error E = build(Mods, FC.Symtab, FC.Strtab))
     return std::move(E);
 
   FC.TheReader = {{FC.Symtab.data(), FC.Symtab.size()},
                   {FC.Strtab.data(), FC.Strtab.size()}};
   return std::move(FC);
 }
+
+Expected<FileContents> irsymtab::readBitcode(const BitcodeFileContents &BFC) {
+  if (BFC.Mods.empty())
+    return make_error<StringError>("Bitcode file does not contain any modules",
+                                   inconvertibleErrorCode());
+
+  // Right now we have no on-disk representation of symbol tables, so we always
+  // upgrade.
+  return upgrade(BFC.Mods);
+}