[IRMover] Implement name based structure type mapping

[evgeny777]

Summary

This patch was separated from D43077 after discussion with @tejohnson. It implements name based structure type mapping to
avoid mapping to wrong type which is isomorphic to one we're about to import.

Not sure whom to add for review.

[tejohnson]

+rafael who is a bit more familiar with this part of the IR linker.

[evgeny777]

Rebased + added @dblaikie

[evgeny777]

Addressed review comments in the mailing list:

• added --initial-module flag to llvm-link
• test cases now use llvm-link instead of llvm-lto

[evgeny777]

Approved in the mailing list

llvm/trunk/include/llvm/Linker/IRMover.h

class IRMover {
   /// Type of the Metadata map in \a ValueToValueMapTy.
   typedef DenseMap<const Metadata *, TrackingMDRef> MDMapT;
 
 public:
   class IdentifiedStructTypeSet {
     // The set of opaque types is the composite module.
     DenseSet<StructType *> OpaqueStructTypes;
 
-    // The set of identified but non opaque structures in the composite module.
-    DenseSet<StructType *, StructTypeKeyInfo> NonOpaqueStructTypes;
-
-  public:
-    void addNonOpaque(StructType *Ty);
-    void switchToNonOpaque(StructType *Ty);
-    void addOpaque(StructType *Ty);
-    StructType *findNonOpaque(ArrayRef<Type *> ETypes, bool IsPacked);
-    bool hasType(StructType *Ty);
-  };
-
+    // The set of identified but non opaque structures in the composite module.
+    DenseSet<StructType *, StructTypeKeyInfo> NonOpaqueStructTypes;
+
+    // Map between structure type name and instance. Used in findNonOpaque
+    // to correctly map imported global variable type during ThinLTO import
+    // phase.
+    DenseMap<StringRef, StructType *> NonOpaqueStructNameMap;
+
+  public:
+    void addNonOpaque(StructType *Ty);
+    void switchToNonOpaque(StructType *Ty);
+    void addOpaque(StructType *Ty);
+    StructType *findNonOpaque(ArrayRef<Type *> ETypes, bool IsPacked,
+                              StringRef Name);
+    bool hasType(StructType *Ty);
+  };
+
   IRMover(Module &M);
 
   typedef std::function<void(GlobalValue &)> ValueAdder;
 
   /// Move in the provide values in \p ValuesToLink from \p Src.
   ///
   /// - \p AddLazyFor is a call back that the IRMover will call when a global
   ///   value is referenced by one of the ValuesToLink (transitively) but was

llvm/trunk/lib/Linker/IRMover.cpp

if (IsUniqued)
       return *Entry = StructType::get(Ty->getContext(), ElementTypes, IsPacked);
 
     // If the type is opaque, we can just use it directly.
     if (STy->isOpaque()) {
       DstStructTypesSet.addOpaque(STy);
       return *Entry = Ty;
     }
 
-    if (StructType *OldT =
-            DstStructTypesSet.findNonOpaque(ElementTypes, IsPacked)) {
+    if (StructType *OldT = DstStructTypesSet.findNonOpaque(
+            ElementTypes, IsPacked, STy->getName())) {
       STy->setName("");
       return *Entry = OldT;
     }
 
     if (!AnyChange) {
       DstStructTypesSet.addNonOpaque(STy);
       return *Entry = Ty;
     }
AddLazyFor(SGV, [this, &LazilyAdded](GlobalValue &GV) {
     LazilyAdded = true;
   });
   return LazilyAdded;
 }
 
 Expected<Constant *> IRLinker::linkGlobalValueProto(GlobalValue *SGV,
                                                     bool ForAlias) {
   GlobalValue *DGV = getLinkedToGlobal(SGV);
-
   bool ShouldLink = shouldLink(DGV, *SGV);
 
   // just missing from map
   if (ShouldLink) {
     auto I = ValueMap.find(SGV);
     if (I != ValueMap.end())
       return cast<Constant>(I->second);
 
bool IRMover::StructTypeKeyInfo::isEqual(const StructType *LHS,
                                          const StructType *RHS) {
   if (RHS == getEmptyKey() || RHS == getTombstoneKey())
     return LHS == RHS;
   return KeyTy(LHS) == KeyTy(RHS);
 }
 
 void IRMover::IdentifiedStructTypeSet::addNonOpaque(StructType *Ty) {
   assert(!Ty->isOpaque());
+  if (Ty->hasName())
+    NonOpaqueStructNameMap.insert({getTypeNamePrefix(Ty->getName()), Ty});
+
   NonOpaqueStructTypes.insert(Ty);
 }
 
 void IRMover::IdentifiedStructTypeSet::switchToNonOpaque(StructType *Ty) {
-  assert(!Ty->isOpaque());
-  NonOpaqueStructTypes.insert(Ty);
+  addNonOpaque(Ty);
   bool Removed = OpaqueStructTypes.erase(Ty);
   (void)Removed;
   assert(Removed);
 }
 
 void IRMover::IdentifiedStructTypeSet::addOpaque(StructType *Ty) {
   assert(Ty->isOpaque());
   OpaqueStructTypes.insert(Ty);
 }
 
 StructType *
 IRMover::IdentifiedStructTypeSet::findNonOpaque(ArrayRef<Type *> ETypes,
-                                                bool IsPacked) {
+                                                bool IsPacked, StringRef Name) {
   IRMover::StructTypeKeyInfo::KeyTy Key(ETypes, IsPacked);
   auto I = NonOpaqueStructTypes.find_as(Key);
-  return I == NonOpaqueStructTypes.end() ? nullptr : *I;
+  if (I == NonOpaqueStructTypes.end())
+    return nullptr;
+  auto NI = NonOpaqueStructNameMap.find(getTypeNamePrefix(Name));
+  if (NI != NonOpaqueStructNameMap.end() &&
+      IRMover::StructTypeKeyInfo::KeyTy((*NI).second) == Key)
+    return (*NI).second;
+  return *I;
 }
 
 bool IRMover::IdentifiedStructTypeSet::hasType(StructType *Ty) {
   if (Ty->isOpaque())
     return OpaqueStructTypes.count(Ty);
   auto I = NonOpaqueStructTypes.find(Ty);
   return I == NonOpaqueStructTypes.end() ? false : *I == Ty;
 }

llvm/trunk/test/Linker/Inputs/struct-mapping.ll

+%struct.Baz = type { i64, i64, %struct.Foo }
+%struct.Foo = type { i64, i64 }
+
+@baz = global %struct.Baz zeroinitializer

llvm/trunk/test/Linker/struct-mapping.ll

+; RUN: llvm-link --initial-module=%s %p/Inputs/struct-mapping.ll -S -o - | FileCheck %s
+
+; Here we check that new type mapping algorithm correctly mapped type of internal
+; member of struct.Baz to struct.Foo. Without it we'd map that type to struct.Bar, because
+; it is recursively isomorphic to struct.Foo and is defined first in source file.
+; CHECK: %struct.Baz = type { i64, i64, %struct.Foo }
+
+%struct.Bar = type { i64, i64 }
+%struct.Foo = type { i64, i64 }
+
+@bar = global %struct.Bar zeroinitializer
+@foo = global %struct.Foo zeroinitializer

llvm/trunk/tools/llvm-link/llvm-link.cpp

 static cl::opt<std::string>
     SummaryIndex("summary-index", cl::desc("Module summary index filename"),
                  cl::init(""), cl::value_desc("filename"));
 
 static cl::opt<std::string>
 OutputFilename("o", cl::desc("Override output filename"), cl::init("-"),
                cl::value_desc("filename"));
 
+static cl::opt<std::string>
+    InitialModule("initial-module",
+                  cl::desc("Link to existing destination module"), cl::init(""),
+                  cl::value_desc("filename"));
+
 static cl::opt<bool>
 Internalize("internalize", cl::desc("Internalize linked symbols"));
 
 static cl::opt<bool>
     DisableDITypeMap("disable-debug-info-type-map",
                      cl::desc("Don't use a uniquing type map for debug info"));
 
 static cl::opt<bool>
int main(int argc, char **argv) {
   Context.setDiagnosticHandler(
     llvm::make_unique<LLVMLinkDiagnosticHandler>(), true);
   llvm_shutdown_obj Y;  // Call llvm_shutdown() on exit.
   cl::ParseCommandLineOptions(argc, argv, "llvm linker\n");
 
   if (!DisableDITypeMap)
     Context.enableDebugTypeODRUniquing();
 
-  auto Composite = make_unique<Module>("llvm-link", Context);
+  auto Composite = InitialModule.empty()
+                       ? make_unique<Module>("llvm-link", Context)
+                       : loadFile(argv[0], InitialModule, Context);
   Linker L(*Composite);
 
   unsigned Flags = Linker::Flags::None;
   if (OnlyNeeded)
     Flags |= Linker::Flags::LinkOnlyNeeded;
 
   // First add all the regular input files
   if (!linkFiles(argv[0], Context, L, InputFilenames, Flags))