[ThinLTO] Fix ThinLTOCodegenerator to export llvm.used symbols

Summary:
Reapply r357931 with fixes to ThinLTO testcases and llvm-lto tool.

ThinLTOCodeGenerator currently does not preserve llvm.used symbols and
it can internalize them. In order to pass the necessary information to the
legacy ThinLTOCodeGenerator, the input to the code generator is
rewritten to be based on lto::InputFile.

Now ThinLTO using the legacy LTO API will requires data layout in
Module.

"internalize" thinlto action in llvm-lto is updated to run both
"promote" and "internalize" with the same configuration as
ThinLTOCodeGenerator. The old "promote" + "internalize" option does not
produce the same output as ThinLTOCodeGenerator.

This fixes: PR41236
rdar://problem/49293439

Reviewers: tejohnson, pcc, kromanova, dexonsmith

Reviewed By: tejohnson

Subscribers: ormris, bd1976llvm, mehdi_amini, inglorion, eraman, hiraditya, jkorous, dexonsmith, arphaman, dang, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D60421

llvm-svn: 358601

Author: cachemeifyoucan

llvm/include/llvm/LTO/LTO.h

@@ -131,6 +131,7 @@ class InputFile {
     using irsymtab::Symbol::isWeak;
     using irsymtab::Symbol::isIndirect;
     using irsymtab::Symbol::getName;
+    using irsymtab::Symbol::getIRName;
     using irsymtab::Symbol::getVisibility;
     using irsymtab::Symbol::canBeOmittedFromSymbolTable;
     using irsymtab::Symbol::isTLS;
@@ -161,6 +162,9 @@ class InputFile {
   // Returns a table with all the comdats used by this file.
   ArrayRef<StringRef> getComdatTable() const { return ComdatTable; }
 
+  // Returns the only BitcodeModule from InputFile.
+  BitcodeModule &getSingleBitcodeModule();
+
 private:
   ArrayRef<Symbol> module_symbols(unsigned I) const {
     const auto &Indices = ModuleSymIndices[I];

llvm/include/llvm/LTO/legacy/ThinLTOCodeGenerator.h

@@ -19,6 +19,7 @@
 #include "llvm/ADT/StringSet.h"
 #include "llvm/ADT/Triple.h"
 #include "llvm/IR/ModuleSummaryIndex.h"
+#include "llvm/LTO/LTO.h"
 #include "llvm/Support/CachePruning.h"
 #include "llvm/Support/CodeGen.h"
 #include "llvm/Support/MemoryBuffer.h"
@@ -31,23 +32,6 @@ class StringRef;
 class LLVMContext;
 class TargetMachine;
 
-/// Wrapper around MemoryBufferRef, owning the identifier
-class ThinLTOBuffer {
-  std::string OwnedIdentifier;
-  StringRef Buffer;
-
-public:
-  ThinLTOBuffer(StringRef Buffer, StringRef Identifier)
-      : OwnedIdentifier(Identifier), Buffer(Buffer) {}
-
-  MemoryBufferRef getMemBuffer() const {
-    return MemoryBufferRef(Buffer,
-                           {OwnedIdentifier.c_str(), OwnedIdentifier.size()});
-  }
-  StringRef getBuffer() const { return Buffer; }
-  StringRef getBufferIdentifier() const { return OwnedIdentifier; }
-};
-
 /// Helper to gather options relevant to the target machine creation
 struct TargetMachineBuilder {
   Triple TheTriple;
@@ -267,31 +251,36 @@ class ThinLTOCodeGenerator {
    * and additionally resolve weak and linkonce symbols.
    * Index is updated to reflect linkage changes from weak resolution.
    */
-  void promote(Module &Module, ModuleSummaryIndex &Index);
+  void promote(Module &Module, ModuleSummaryIndex &Index,
+               const lto::InputFile &File);
 
   /**
    * Compute and emit the imported files for module at \p ModulePath.
    */
   void emitImports(Module &Module, StringRef OutputName,
-                   ModuleSummaryIndex &Index);
+                   ModuleSummaryIndex &Index,
+                   const lto::InputFile &File);
 
   /**
    * Perform cross-module importing for the module identified by
    * ModuleIdentifier.
    */
-  void crossModuleImport(Module &Module, ModuleSummaryIndex &Index);
+  void crossModuleImport(Module &Module, ModuleSummaryIndex &Index,
+                         const lto::InputFile &File);
 
   /**
    * Compute the list of summaries needed for importing into module.
    */
   void gatherImportedSummariesForModule(
       Module &Module, ModuleSummaryIndex &Index,
-      std::map<std::string, GVSummaryMapTy> &ModuleToSummariesForIndex);
+      std::map<std::string, GVSummaryMapTy> &ModuleToSummariesForIndex,
+      const lto::InputFile &File);
 
   /**
    * Perform internalization. Index is updated to reflect linkage changes.
    */
-  void internalize(Module &Module, ModuleSummaryIndex &Index);
+  void internalize(Module &Module, ModuleSummaryIndex &Index,
+                   const lto::InputFile &File);
 
   /**
    * Perform post-importing ThinLTO optimizations.
@@ -313,7 +302,7 @@ class ThinLTOCodeGenerator {
 
   /// Vector holding the input buffers containing the bitcode modules to
   /// process.
-  std::vector<ThinLTOBuffer> Modules;
+  std::vector<std::unique_ptr<lto::InputFile>> Modules;
 
   /// Set of symbols that need to be preserved outside of the set of bitcode
   /// files.

llvm/lib/LTO/LTO.cpp

@@ -420,6 +420,11 @@ StringRef InputFile::getName() const {
   return Mods[0].getModuleIdentifier();
 }
 
+BitcodeModule &InputFile::getSingleBitcodeModule() {
+  assert(Mods.size() == 1 && "Expect only one bitcode module");
+  return Mods[0];
+}
+
 LTO::RegularLTOState::RegularLTOState(unsigned ParallelCodeGenParallelismLevel,
                                       Config &Conf)
     : ParallelCodeGenParallelismLevel(ParallelCodeGenParallelismLevel),