Bitcode: Introduce a BitcodeFileContents data type. NFCI.

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.

Differential Revision: https://reviews.llvm.org/D33969

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@305019 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Bitcode/BitcodeReader.h

@@ -40,6 +40,8 @@ namespace llvm {
     return std::move(*Val);
   }
 
+  struct BitcodeFileContents;
+
   /// Represents a module in a bitcode file.
   class BitcodeModule {
     // This covers the identification (if present) and module blocks.
@@ -61,8 +63,8 @@ namespace llvm {
           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,
@@ -99,6 +101,13 @@ namespace llvm {
     Error readSummary(ModuleSummaryIndex &CombinedIndex, unsigned ModuleId);
   };
 
+  struct BitcodeFileContents {
+    std::vector<BitcodeModule> Mods;
+  };
+
+  /// Returns the contents of a bitcode file.
+  Expected<BitcodeFileContents> getBitcodeFileContents(MemoryBufferRef Buffer);
+
   /// Returns a list of modules in the specified bitcode buffer.
   Expected<std::vector<BitcodeModule>>
   getBitcodeModuleList(MemoryBufferRef Buffer);

include/llvm/Object/IRObjectFile.h

@@ -20,6 +20,7 @@
 #include "llvm/Object/SymbolicFile.h"
 
 namespace llvm {
+class BitcodeModule;
 class Mangler;
 class Module;
 class GlobalValue;

include/llvm/Object/IRSymtab.h

@@ -37,7 +37,7 @@
 
 namespace llvm {
 
-class BitcodeModule;
+struct BitcodeFileContents;
 
 namespace irsymtab {
 
@@ -325,7 +325,7 @@ struct FileContents {
 };
 
 /// 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

lib/Bitcode/Reader/BitcodeReader.cpp

@@ -5370,20 +5370,28 @@ static Expected<StringRef> readStrtab(BitstreamCursor &Stream) {
 
 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) {
@@ -5409,10 +5417,10 @@ llvm::getBitcodeModuleList(MemoryBufferRef Buffer) {
         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(
+                              BCBegin, Stream.getCurrentByteNo() - BCBegin),
+                          Buffer.getBufferIdentifier(), IdentificationBit,
+                          ModuleBit});
         continue;
       }
 
@@ -5424,7 +5432,7 @@ llvm::getBitcodeModuleList(MemoryBufferRef Buffer) {
         // 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;

lib/Object/IRObjectFile.cpp

@@ -147,16 +147,15 @@ Expected<IRSymtabFile> object::readIRSymtab(MemoryBufferRef 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<irsymtab::FileContents> FCOrErr = irsymtab::readBitcode(*BMsOrErr);
+  Expected<irsymtab::FileContents> FCOrErr = irsymtab::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);

lib/Object/IRSymtab.cpp

@@ -262,11 +262,10 @@ Error irsymtab::build(ArrayRef<Module *> Mods, SmallVector<char, 0> &Symtab,
   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;
@@ -293,3 +292,13 @@ Expected<FileContents> irsymtab::readBitcode(ArrayRef<BitcodeModule> BMs) {
                   {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);
+}