[CodeGen] Unify generation of scalar and struct-path TBAA tags

[kosarev]

Summary

This patch makes it possible to produce access tags in a uniform manner regardless whether the resulting tag will be a scalar or a struct-path one. getAccessTagInfo() now takes care of the actual translation of access descriptors to tags and can handle all kinds of accesses. Facilities that specific to scalar accesses are eliminated.

Some more details:

• DecorateInstructionWithTBAA() is not responsible for conversion of types to access tags anymore. Instead, it takes an access descriptor (TBAAAccessInfo) and generates corresponding access tag from it.
• getTBAAInfoForVTablePtr() reworked to getTBAAVTablePtrAccessInfo() that now returns the virtual-pointer access descriptor and not the virtual-point type metadata.
• Added function getTBAAMayAliasAccessInfo() that returns the descriptor for may-alias accesses.
• getTBAAStructTagInfo() renamed to getTBAAAccessTagInfo() as now it is the only way to generate access tag by a given access descriptor. It is capable of producing both scalar and struct-path tags, depending on options and availability of the base access type. getTBAAScalarTagInfo() and its cache ScalarTagMetadataCache are eliminated.
• Now that we do not need to care about whether the resulting access tag should be a scalar or struct-path one, getTBAAStructTypeInfo() is renamed to getBaseTypeInfo().
• Added function getTBAAAccessInfo() that constructs access descriptor by a given QualType access type.

This is part of D37826 reworked to be a separate patch to simplify review.

[kosarev]

Just in case, please let me know if you think this change should further be broken down into smaller pieces. Thanks.

[rjmccall]

LGTM with one comment fix that I noticed.

lib/CodeGen/CodeGenModule.h

659 ↗

(On Diff #117519)

"an access"

cfe/trunk/lib/CodeGen/CGAtomic.cpp

public:
     /// Project an l-value down to the value field.
     LValue projectValue() const {
       assert(LVal.isSimple());
       Address addr = getAtomicAddress();
       if (hasPadding())
         addr = CGF.Builder.CreateStructGEP(addr, 0, CharUnits());
 
       return LValue::MakeAddr(addr, getValueType(), CGF.getContext(),
-                              LVal.getBaseInfo(), LVal.getTBAAAccessType());
+                              LVal.getBaseInfo(), LVal.getTBAAInfo());
     }
 
     /// \brief Emits atomic load.
     /// \returns Loaded value.
     RValue EmitAtomicLoad(AggValueSlot ResultSlot, SourceLocation Loc,
                           bool AsValue, llvm::AtomicOrdering AO,
                           bool IsVolatile);
 
llvm::Value *AtomicInfo::EmitAtomicLoadOp(llvm::AtomicOrdering AO,
   // Okay, we're doing this natively.
   Address Addr = getAtomicAddressAsAtomicIntPointer();
   llvm::LoadInst *Load = CGF.Builder.CreateLoad(Addr, "atomic-load");
   Load->setAtomic(AO);
 
   // Other decoration.
   if (IsVolatile)
     Load->setVolatile(true);
-  if (LVal.getTBAAAccessType())
-    CGF.CGM.DecorateInstructionWithTBAA(Load, LVal.getTBAAAccessType());
+  CGF.CGM.DecorateInstructionWithTBAA(Load, LVal.getTBAAInfo());
   return Load;
 }
 
 /// An LValue is a candidate for having its loads and stores be made atomic if
 /// we are operating under /volatile:ms *and* the LValue itself is volatile and
 /// performing such an operation can be performed without a libcall.
 bool CodeGenFunction::LValueIsSuitableForInlineAtomic(LValue LV) {
   if (!CGM.getCodeGenOpts().MSVolatile) return false;
if (LVal.isSimple()) {
 
     // Initializations don't need to be atomic.
     if (!isInit)
       store->setAtomic(AO);
 
     // Other decoration.
     if (IsVolatile)
       store->setVolatile(true);
-    if (dest.getTBAAAccessType())
-      CGM.DecorateInstructionWithTBAA(store, dest.getTBAAAccessType());
+    CGM.DecorateInstructionWithTBAA(store, dest.getTBAAInfo());
     return;
   }
 
   // Emit simple atomic update operation.
   atomics.EmitAtomicUpdate(AO, rvalue, IsVolatile);
 }
 
 /// Emit a compare-and-exchange op for atomic type.

cfe/trunk/lib/CodeGen/CGClass.cpp

void CodeGenFunction::InitializeVTablePointer(const VPtr &Vptr) {
   llvm::Type *VTablePtrTy =
       llvm::FunctionType::get(CGM.Int32Ty, /*isVarArg=*/true)
           ->getPointerTo()
           ->getPointerTo();
   VTableField = Builder.CreateBitCast(VTableField, VTablePtrTy->getPointerTo());
   VTableAddressPoint = Builder.CreateBitCast(VTableAddressPoint, VTablePtrTy);
 
   llvm::StoreInst *Store = Builder.CreateStore(VTableAddressPoint, VTableField);
-  CGM.DecorateInstructionWithTBAA(Store, CGM.getTBAAInfoForVTablePtr());
+  CGM.DecorateInstructionWithTBAA(Store, CGM.getTBAAVTablePtrAccessInfo());
   if (CGM.getCodeGenOpts().OptimizationLevel > 0 &&
       CGM.getCodeGenOpts().StrictVTablePointers)
     CGM.DecorateInstructionWithInvariantGroup(Store, Vptr.VTableClass);
 }
 
 CodeGenFunction::VPtrsVector
 CodeGenFunction::getVTablePointers(const CXXRecordDecl *VTableClass) {
   CodeGenFunction::VPtrsVector VPtrsResult;
if (RD->getNumVBases())
     CGM.getCXXABI().initializeHiddenVirtualInheritanceMembers(*this, RD);
 }
 
 llvm::Value *CodeGenFunction::GetVTablePtr(Address This,
                                            llvm::Type *VTableTy,
                                            const CXXRecordDecl *RD) {
   Address VTablePtrSrc = Builder.CreateElementBitCast(This, VTableTy);
   llvm::Instruction *VTable = Builder.CreateLoad(VTablePtrSrc, "vtable");
-  CGM.DecorateInstructionWithTBAA(VTable, CGM.getTBAAInfoForVTablePtr());
+  CGM.DecorateInstructionWithTBAA(VTable, CGM.getTBAAVTablePtrAccessInfo());
 
   if (CGM.getCodeGenOpts().OptimizationLevel > 0 &&
       CGM.getCodeGenOpts().StrictVTablePointers)
     CGM.DecorateInstructionWithInvariantGroup(VTable, RD);
 
   return VTable;
 }
 

cfe/trunk/lib/CodeGen/CGExpr.cpp

case Expr::ExprWithCleanupsClass: {
     RunCleanupsScope Scope(*this);
     LValue LV = EmitLValue(cleanups->getSubExpr());
     if (LV.isSimple()) {
       // Defend against branches out of gnu statement expressions surrounded by
       // cleanups.
       llvm::Value *V = LV.getPointer();
       Scope.ForceCleanup({&V});
       return LValue::MakeAddr(Address(V, LV.getAlignment()), LV.getType(),
-                              getContext(), LV.getBaseInfo(),
-                              LV.getTBAAAccessType());
+                              getContext(), LV.getBaseInfo(), LV.getTBAAInfo());
     }
     // FIXME: Is it possible to create an ExprWithCleanups that produces a
     // bitfield lvalue or some other non-simple lvalue?
     return LV;
   }
 
   case Expr::CXXDefaultArgExprClass:
     return EmitLValue(cast<CXXDefaultArgExpr>(E)->getExpr());
if (Ty->isVectorType()) {
                                         {0, 1, 2}, "extractVec");
         return EmitFromMemory(V, Ty);
       }
     }
   }
 
   // Atomic operations have to be done on integral types.
   LValue AtomicLValue =
-      LValue::MakeAddr(Addr, Ty, getContext(), BaseInfo, TBAAInfo.AccessType);
+      LValue::MakeAddr(Addr, Ty, getContext(), BaseInfo, TBAAInfo);
   if (Ty->isAtomicType() || LValueIsSuitableForInlineAtomic(AtomicLValue)) {
     return EmitAtomicLoad(AtomicLValue, Loc).getScalarVal();
   }
 
   llvm::LoadInst *Load = Builder.CreateLoad(Addr, Volatile);
   if (isNontemporal) {
     llvm::MDNode *Node = llvm::MDNode::get(
         Load->getContext(), llvm::ConstantAsMetadata::get(Builder.getInt32(1)));
     Load->setMetadata(CGM.getModule().getMDKindID("nontemporal"), Node);
   }
-  if (TBAAInfo.AccessType) {
-    bool MayAlias = BaseInfo.getMayAlias();
-    llvm::MDNode *TBAA = MayAlias
-        ? CGM.getTBAAMayAliasTypeInfo()
-        : CGM.getTBAAStructTagInfo(TBAAInfo);
-    if (TBAA)
-      CGM.DecorateInstructionWithTBAA(Load, TBAA, MayAlias);
-  }
+
+  if (BaseInfo.getMayAlias())
+    TBAAInfo = CGM.getTBAAMayAliasAccessInfo();
+  CGM.DecorateInstructionWithTBAA(Load, TBAAInfo);
 
   if (EmitScalarRangeCheck(Load, Ty, Loc)) {
     // In order to prevent the optimizer from throwing away the check, don't
     // attach range metadata to the load.
   } else if (CGM.getCodeGenOpts().OptimizationLevel > 0)
     if (llvm::MDNode *RangeInfo = getRangeForLoadFromType(Ty))
       Load->setMetadata(llvm::LLVMContext::MD_range, RangeInfo);
 
if (Ty->isVectorType()) {
         Addr = Builder.CreateElementBitCast(Addr, SrcTy, "storetmp");
       }
     }
   }
 
   Value = EmitToMemory(Value, Ty);
 
   LValue AtomicLValue =
-      LValue::MakeAddr(Addr, Ty, getContext(), BaseInfo, TBAAInfo.AccessType);
+      LValue::MakeAddr(Addr, Ty, getContext(), BaseInfo, TBAAInfo);
   if (Ty->isAtomicType() ||
       (!isInit && LValueIsSuitableForInlineAtomic(AtomicLValue))) {
     EmitAtomicStore(RValue::get(Value), AtomicLValue, isInit);
     return;
   }
 
   llvm::StoreInst *Store = Builder.CreateStore(Value, Addr, Volatile);
   if (isNontemporal) {
     llvm::MDNode *Node =
         llvm::MDNode::get(Store->getContext(),
                           llvm::ConstantAsMetadata::get(Builder.getInt32(1)));
     Store->setMetadata(CGM.getModule().getMDKindID("nontemporal"), Node);
   }
-  if (TBAAInfo.AccessType) {
-    bool MayAlias = BaseInfo.getMayAlias();
-    llvm::MDNode *TBAA = MayAlias
-        ? CGM.getTBAAMayAliasTypeInfo()
-        : CGM.getTBAAStructTagInfo(TBAAInfo);
-    if (TBAA)
-      CGM.DecorateInstructionWithTBAA(Store, TBAA, MayAlias);
-  }
+
+  if (BaseInfo.getMayAlias())
+    TBAAInfo = CGM.getTBAAMayAliasAccessInfo();
+  CGM.DecorateInstructionWithTBAA(Store, TBAAInfo);
 }
 
 void CodeGenFunction::EmitStoreOfScalar(llvm::Value *value, LValue lvalue,
                                         bool isInit) {
   EmitStoreOfScalar(value, lvalue.getAddress(), lvalue.isVolatile(),
                     lvalue.getType(), lvalue.getBaseInfo(),
                     lvalue.getTBAAInfo(), isInit, lvalue.isNontemporal());
 }
if (rec->isUnion()) {
 
     // If this is a reference field, load the reference right now.
     if (const ReferenceType *refType = type->getAs<ReferenceType>()) {
       llvm::LoadInst *load = Builder.CreateLoad(addr, "ref");
       if (cvr & Qualifiers::Volatile) load->setVolatile(true);
 
       // Loading the reference will disable path-aware TBAA.
       TBAAPath = false;
-      if (CGM.shouldUseTBAA()) {
-        llvm::MDNode *tbaa = mayAlias ? CGM.getTBAAMayAliasTypeInfo() :
-                                        CGM.getTBAATypeInfo(type);
-        if (tbaa)
-          CGM.DecorateInstructionWithTBAA(load, tbaa);
-      }
+      TBAAAccessInfo TBAAInfo = mayAlias ? CGM.getTBAAMayAliasAccessInfo() :
+                                           CGM.getTBAAAccessInfo(type);
+      CGM.DecorateInstructionWithTBAA(load, TBAAInfo);
 
       mayAlias = false;
       type = refType->getPointeeType();
 
       CharUnits alignment =
         getNaturalTypeAlignment(type, &FieldBaseInfo, /*pointee*/ true);
       FieldBaseInfo.setMayAlias(false);
       addr = Address(load, alignment);
addr = Builder.CreateElementBitCast(addr,
                                       CGM.getTypes().ConvertTypeForMem(type),
                                       field->getName());
 
   if (field->hasAttr<AnnotateAttr>())
     addr = EmitFieldAnnotations(field, addr);
 
   LValue LV = MakeAddrLValue(addr, type, FieldBaseInfo);
   LV.getQuals().addCVRQualifiers(cvr);
-  if (TBAAPath) {
+
+  // Fields of may_alias structs act like 'char' for TBAA purposes.
+  // FIXME: this should get propagated down through anonymous structs
+  // and unions.
+  if (mayAlias) {
+    LV.setTBAAInfo(CGM.getTBAAMayAliasAccessInfo());
+  } else if (TBAAPath) {
+    // If no base type been assigned for the base access, then try to generate
+    // one for this base lvalue.
+    TBAAAccessInfo TBAAInfo = base.getTBAAInfo();
+    if (!TBAAInfo.BaseType) {
+        TBAAInfo.BaseType = CGM.getTBAABaseTypeInfo(base.getType());
+        assert(!TBAAInfo.Offset &&
+               "Nonzero offset for an access with no base type!");
+    }
+
+    // Adjust offset to be relative to the base type.
     const ASTRecordLayout &Layout =
         getContext().getASTRecordLayout(field->getParent());
-    // Set the base type to be the base type of the base LValue and
-    // update offset to be relative to the base type.
     unsigned CharWidth = getContext().getCharWidth();
-    TBAAAccessInfo TBAAInfo = mayAlias ?
-      TBAAAccessInfo(CGM.getTBAAMayAliasTypeInfo()) :
-      TBAAAccessInfo(base.getTBAAInfo().BaseType, CGM.getTBAATypeInfo(type),
-                     base.getTBAAInfo().Offset + Layout.getFieldOffset(
-                         field->getFieldIndex()) / CharWidth);
+    if (TBAAInfo.BaseType)
+      TBAAInfo.Offset +=
+          Layout.getFieldOffset(field->getFieldIndex()) / CharWidth;
+
+    // Update the final access type.
+    TBAAInfo.AccessType = LV.getTBAAInfo().AccessType;
+
     LV.setTBAAInfo(TBAAInfo);
   }
 
   // __weak attribute on a field is ignored.
   if (LV.getQuals().getObjCGCAttr() == Qualifiers::Weak)
     LV.getQuals().removeObjCGCAttr();
 
-  // Fields of may_alias structs act like 'char' for TBAA purposes.
-  // FIXME: this should get propagated down through anonymous structs
-  // and unions.
-  if (mayAlias && LV.getTBAAAccessType())
-    LV.setTBAAAccessType(CGM.getTBAAMayAliasTypeInfo());
-
   return LV;
 }
 
 LValue
 CodeGenFunction::EmitLValueForFieldInitialization(LValue Base,
                                                   const FieldDecl *Field) {
   QualType FieldType = Field->getType();
 

cfe/trunk/lib/CodeGen/CGValue.h

class LValue {
   // this lvalue.
   bool Nontemporal : 1;
 
   Expr *BaseIvarExp;
 
 private:
   void Initialize(QualType Type, Qualifiers Quals,
                   CharUnits Alignment, LValueBaseInfo BaseInfo,
-                  llvm::MDNode *TBAAAccessType = nullptr) {
+                  TBAAAccessInfo TBAAInfo = TBAAAccessInfo()) {
     assert((!Alignment.isZero() || Type->isIncompleteType()) &&
            "initializing l-value with zero alignment!");
     this->Type = Type;
     this->Quals = Quals;
     this->Alignment = Alignment.getQuantity();
     assert(this->Alignment == Alignment.getQuantity() &&
            "Alignment exceeds allowed max!");
     this->BaseInfo = BaseInfo;
-    this->TBAAInfo = TBAAAccessInfo(Type, TBAAAccessType, /* Offset= */ 0);
+    this->TBAAInfo = TBAAInfo;
 
     // Initialize Objective-C flags.
     this->Ivar = this->ObjIsArray = this->NonGC = this->GlobalObjCRef = false;
     this->ImpreciseLifetime = false;
     this->Nontemporal = false;
     this->ThreadLocalRef = false;
     this->BaseIvarExp = nullptr;
   }
public:
   }
   
   Expr *getBaseIvarExp() const { return BaseIvarExp; }
   void setBaseIvarExp(Expr *V) { BaseIvarExp = V; }
 
   TBAAAccessInfo getTBAAInfo() const { return TBAAInfo; }
   void setTBAAInfo(TBAAAccessInfo Info) { TBAAInfo = Info; }
 
-  llvm::MDNode *getTBAAAccessType() const { return TBAAInfo.AccessType; }
-  void setTBAAAccessType(llvm::MDNode *N) { TBAAInfo.AccessType = N; }
-
   const Qualifiers &getQuals() const { return Quals; }
   Qualifiers &getQuals() { return Quals; }
 
   unsigned getAddressSpace() const { return Quals.getAddressSpace(); }
 
   CharUnits getAlignment() const { return CharUnits::fromQuantity(Alignment); }
   void setAlignment(CharUnits A) { Alignment = A.getQuantity(); }
 
public:
   const CGBitFieldInfo &getBitFieldInfo() const {
     assert(isBitField());
     return *BitFieldInfo;
   }
 
   // global register lvalue
   llvm::Value *getGlobalReg() const { assert(isGlobalReg()); return V; }
 
-  static LValue MakeAddr(Address address, QualType type,
-                         ASTContext &Context,
-                         LValueBaseInfo BaseInfo,
-                         llvm::MDNode *TBAAAccessType = nullptr) {
+  static LValue MakeAddr(Address address, QualType type, ASTContext &Context,
+                         LValueBaseInfo BaseInfo, TBAAAccessInfo TBAAInfo) {
     Qualifiers qs = type.getQualifiers();
     qs.setObjCGCAttr(Context.getObjCGCAttrKind(type));
 
     LValue R;
     R.LVType = Simple;
     assert(address.getPointer()->getType()->isPointerTy());
     R.V = address.getPointer();
-    R.Initialize(type, qs, address.getAlignment(), BaseInfo, TBAAAccessType);
+    R.Initialize(type, qs, address.getAlignment(), BaseInfo, TBAAInfo);
     return R;
   }
 
   static LValue MakeVectorElt(Address vecAddress, llvm::Value *Idx,
                               QualType type, LValueBaseInfo BaseInfo) {
     LValue R;
     R.LVType = VectorElt;
     R.V = vecAddress.getPointer();

cfe/trunk/lib/CodeGen/CodeGenFunction.h

#endif
   //===--------------------------------------------------------------------===//
   //                                  Helpers
   //===--------------------------------------------------------------------===//
 
   LValue MakeAddrLValue(Address Addr, QualType T,
                         LValueBaseInfo BaseInfo =
                             LValueBaseInfo(AlignmentSource::Type)) {
     return LValue::MakeAddr(Addr, T, getContext(), BaseInfo,
-                            CGM.getTBAATypeInfo(T));
+                            CGM.getTBAAAccessInfo(T));
   }
 
   LValue MakeAddrLValue(llvm::Value *V, QualType T, CharUnits Alignment,
                         LValueBaseInfo BaseInfo =
                             LValueBaseInfo(AlignmentSource::Type)) {
     return LValue::MakeAddr(Address(V, Alignment), T, getContext(),
-                            BaseInfo, CGM.getTBAATypeInfo(T));
+                            BaseInfo, CGM.getTBAAAccessInfo(T));
   }
 
   LValue MakeNaturalAlignPointeeAddrLValue(llvm::Value *V, QualType T);
   LValue MakeNaturalAlignAddrLValue(llvm::Value *V, QualType T);
   CharUnits getNaturalTypeAlignment(QualType T,
                                     LValueBaseInfo *BaseInfo = nullptr,
                                     bool forPointeeType = false);
   CharUnits getNaturalPointeeTypeAlignment(QualType T,
public:
 
   /// EmitLoadOfScalar - Load a scalar value from an address, taking
   /// care to appropriately convert from the memory representation to
   /// the LLVM value representation.
   llvm::Value *EmitLoadOfScalar(Address Addr, bool Volatile, QualType Ty,
                                 SourceLocation Loc,
                                 LValueBaseInfo BaseInfo =
                                     LValueBaseInfo(AlignmentSource::Type),
-                                TBAAAccessInfo TBAAInfo = TBAAAccessInfo(),
+                                bool isNontemporal = false) {
+    return EmitLoadOfScalar(Addr, Volatile, Ty, Loc, BaseInfo,
+                            CGM.getTBAAAccessInfo(Ty), isNontemporal);
+  }
+
+  llvm::Value *EmitLoadOfScalar(Address Addr, bool Volatile, QualType Ty,
+                                SourceLocation Loc, LValueBaseInfo BaseInfo,
+                                TBAAAccessInfo TBAAInfo,
                                 bool isNontemporal = false);
 
   /// EmitLoadOfScalar - Load a scalar value from an address, taking
   /// care to appropriately convert from the memory representation to
   /// the LLVM value representation.  The l-value must be a simple
   /// l-value.
   llvm::Value *EmitLoadOfScalar(LValue lvalue, SourceLocation Loc);
 
   /// EmitStoreOfScalar - Store a scalar value to an address, taking
   /// care to appropriately convert from the memory representation to
   /// the LLVM value representation.
   void EmitStoreOfScalar(llvm::Value *Value, Address Addr,
                          bool Volatile, QualType Ty,
                          LValueBaseInfo BaseInfo =
                              LValueBaseInfo(AlignmentSource::Type),
-                         TBAAAccessInfo TBAAInfo = TBAAAccessInfo(),
+                         bool isInit = false, bool isNontemporal = false) {
+    EmitStoreOfScalar(Value, Addr, Volatile, Ty, BaseInfo,
+                      CGM.getTBAAAccessInfo(Ty), isInit, isNontemporal);
+  }
+
+  void EmitStoreOfScalar(llvm::Value *Value, Address Addr,
+                         bool Volatile, QualType Ty,
+                         LValueBaseInfo BaseInfo, TBAAAccessInfo TBAAInfo,
                          bool isInit = false, bool isNontemporal = false);
 
   /// EmitStoreOfScalar - Store a scalar value to an address, taking
   /// care to appropriately convert from the memory representation to
   /// the LLVM value representation.  The l-value must be a simple
   /// l-value.  The isInit flag indicates whether this is an initialization.
   /// If so, atomic qualifiers are ignored and the store is always non-atomic.
   void EmitStoreOfScalar(llvm::Value *value, LValue lvalue, bool isInit=false);

cfe/trunk/lib/CodeGen/CodeGenFunction.cpp

CharUnits CodeGenFunction::getNaturalTypeAlignment(QualType T,
   }
   return Alignment;
 }
 
 LValue CodeGenFunction::MakeNaturalAlignAddrLValue(llvm::Value *V, QualType T) {
   LValueBaseInfo BaseInfo;
   CharUnits Alignment = getNaturalTypeAlignment(T, &BaseInfo);
   return LValue::MakeAddr(Address(V, Alignment), T, getContext(), BaseInfo,
-                          CGM.getTBAATypeInfo(T));
+                          CGM.getTBAAAccessInfo(T));
 }
 
 /// Given a value of type T* that may not be to a complete object,
 /// construct an l-value with the natural pointee alignment of T.
 LValue
 CodeGenFunction::MakeNaturalAlignPointeeAddrLValue(llvm::Value *V, QualType T) {
   LValueBaseInfo BaseInfo;
   CharUnits Align = getNaturalTypeAlignment(T, &BaseInfo, /*pointee*/ true);

cfe/trunk/lib/CodeGen/CodeGenModule.h

public:
 
   CtorList &getGlobalCtors() { return GlobalCtors; }
   CtorList &getGlobalDtors() { return GlobalDtors; }
 
   /// getTBAATypeInfo - Get metadata used to describe accesses to objects of
   /// the given type.
   llvm::MDNode *getTBAATypeInfo(QualType QTy);
 
-  llvm::MDNode *getTBAAInfoForVTablePtr();
+  /// getTBAAAccessInfo - Get TBAA information that describes an access to
+  /// an object of the given type.
+  TBAAAccessInfo getTBAAAccessInfo(QualType AccessType);
+
+  /// getTBAAVTablePtrAccessInfo - Get the TBAA information that describes an
+  /// access to a virtual table pointer.
+  TBAAAccessInfo getTBAAVTablePtrAccessInfo();
+
   llvm::MDNode *getTBAAStructInfo(QualType QTy);
 
-  /// Get path-aware TBAA tag for a given memory access.
-  llvm::MDNode *getTBAAStructTagInfo(TBAAAccessInfo Info);
+  /// getTBAABaseTypeMetadata - Get metadata that describes the given base
+  /// access type. Return null if the type is not suitable for use in TBAA
+  /// access tags.
+  llvm::MDNode *getTBAABaseTypeInfo(QualType QTy);
+
+  /// getTBAAAccessTagInfo - Get TBAA tag for a given memory access.
+  llvm::MDNode *getTBAAAccessTagInfo(TBAAAccessInfo Info);
 
-  /// getTBAAMayAliasTypeInfo - Get TBAA information that represents
+  /// getTBAAMayAliasAccessInfo - Get TBAA information that represents
   /// may-alias accesses.
-  llvm::MDNode *getTBAAMayAliasTypeInfo();
+  TBAAAccessInfo getTBAAMayAliasAccessInfo();
 
   bool isTypeConstant(QualType QTy, bool ExcludeCtorDtor);
 
   bool isPaddedAtomicType(QualType type);
   bool isPaddedAtomicType(const AtomicType *type);
 
-  /// Decorate the instruction with a TBAA tag. For scalar TBAA, the tag
-  /// is the same as the type. For struct-path aware TBAA, the tag
-  /// is different from the type: base type, access type and offset.
-  /// When ConvertTypeToTag is true, we create a tag based on the scalar type.
+  /// DecorateInstructionWithTBAA - Decorate the instruction with a TBAA tag.
   void DecorateInstructionWithTBAA(llvm::Instruction *Inst,
-                                   llvm::MDNode *TBAAInfo,
-                                   bool ConvertTypeToTag = true);
+                                   TBAAAccessInfo TBAAInfo);
 
   /// Adds !invariant.barrier !tag to instruction
   void DecorateInstructionWithInvariantGroup(llvm::Instruction *I,
                                              const CXXRecordDecl *RD);
 
   /// Emit the given number of characters as a value of type size_t.
   llvm::ConstantInt *getSize(CharUnits numChars);
 

cfe/trunk/lib/CodeGen/CodeGenModule.cpp

 }
 
 llvm::MDNode *CodeGenModule::getTBAATypeInfo(QualType QTy) {
   if (!TBAA)
     return nullptr;
   return TBAA->getTypeInfo(QTy);
 }
 
-llvm::MDNode *CodeGenModule::getTBAAInfoForVTablePtr() {
+TBAAAccessInfo CodeGenModule::getTBAAAccessInfo(QualType AccessType) {
+  return TBAAAccessInfo(getTBAATypeInfo(AccessType));
+}
+
+TBAAAccessInfo CodeGenModule::getTBAAVTablePtrAccessInfo() {
   if (!TBAA)
-    return nullptr;
-  return TBAA->getTBAAInfoForVTablePtr();
+    return TBAAAccessInfo();
+  return TBAA->getVTablePtrAccessInfo();
 }
 
 llvm::MDNode *CodeGenModule::getTBAAStructInfo(QualType QTy) {
   if (!TBAA)
     return nullptr;
   return TBAA->getTBAAStructInfo(QTy);
 }
 
-llvm::MDNode *CodeGenModule::getTBAAStructTagInfo(TBAAAccessInfo Info) {
+llvm::MDNode *CodeGenModule::getTBAABaseTypeInfo(QualType QTy) {
   if (!TBAA)
     return nullptr;
-  return TBAA->getTBAAStructTagInfo(Info);
+  return TBAA->getBaseTypeInfo(QTy);
 }
 
-llvm::MDNode *CodeGenModule::getTBAAMayAliasTypeInfo() {
+llvm::MDNode *CodeGenModule::getTBAAAccessTagInfo(TBAAAccessInfo Info) {
   if (!TBAA)
     return nullptr;
-  return TBAA->getMayAliasTypeInfo();
+  return TBAA->getAccessTagInfo(Info);
+}
+
+TBAAAccessInfo CodeGenModule::getTBAAMayAliasAccessInfo() {
+  if (!TBAA)
+    return TBAAAccessInfo();
+  return TBAA->getMayAliasAccessInfo();
 }
 
-/// Decorate the instruction with a TBAA tag. For both scalar TBAA
-/// and struct-path aware TBAA, the tag has the same format:
-/// base type, access type and offset.
-/// When ConvertTypeToTag is true, we create a tag based on the scalar type.
 void CodeGenModule::DecorateInstructionWithTBAA(llvm::Instruction *Inst,
-                                                llvm::MDNode *TBAAInfo,
-                                                bool ConvertTypeToTag) {
-  if (ConvertTypeToTag && TBAA)
-    Inst->setMetadata(llvm::LLVMContext::MD_tbaa,
-                      TBAA->getTBAAScalarTagInfo(TBAAInfo));
-  else
-    Inst->setMetadata(llvm::LLVMContext::MD_tbaa, TBAAInfo);
+                                                TBAAAccessInfo TBAAInfo) {
+  if (llvm::MDNode *Tag = getTBAAAccessTagInfo(TBAAInfo))
+    Inst->setMetadata(llvm::LLVMContext::MD_tbaa, Tag);
 }
 
 void CodeGenModule::DecorateInstructionWithInvariantGroup(
     llvm::Instruction *I, const CXXRecordDecl *RD) {
   I->setMetadata(llvm::LLVMContext::MD_invariant_group,
                  llvm::MDNode::get(getLLVMContext(), {}));
 }
 

cfe/trunk/lib/CodeGen/CodeGenTBAA.h

namespace clang {
   class LangOptions;
   class MangleContext;
   class QualType;
   class Type;
 
 namespace CodeGen {
 class CGRecordLayout;
 
-struct TBAAPathTag {
-  TBAAPathTag(const Type *B, const llvm::MDNode *A, uint64_t O)
-    : BaseT(B), AccessN(A), Offset(O) {}
-  const Type *BaseT;
-  const llvm::MDNode *AccessN;
-  uint64_t Offset;
-};
-
 // TBAAAccessInfo - Describes a memory access in terms of TBAA.
 struct TBAAAccessInfo {
-  TBAAAccessInfo(QualType BaseType, llvm::MDNode *AccessType, uint64_t Offset)
+  TBAAAccessInfo(llvm::MDNode *BaseType, llvm::MDNode *AccessType,
+                 uint64_t Offset)
     : BaseType(BaseType), AccessType(AccessType), Offset(Offset)
   {}
 
   explicit TBAAAccessInfo(llvm::MDNode *AccessType)
-    : TBAAAccessInfo(/* BaseType= */ QualType(), AccessType, /* Offset= */ 0)
+    : TBAAAccessInfo(/* BaseType= */ nullptr, AccessType, /* Offset= */ 0)
   {}
 
   TBAAAccessInfo()
     : TBAAAccessInfo(/* AccessType= */ nullptr)
   {}
 
   /// BaseType - The base/leading access type. May be null if this access
   /// descriptor represents an access that is not considered to be an access
   /// to an aggregate or union member.
-  QualType BaseType;
+  llvm::MDNode *BaseType;
 
   /// AccessType - The final access type. May be null if there is no TBAA
   /// information available about this access.
   llvm::MDNode *AccessType;
 
   /// Offset - The byte offset of the final access within the base one. Must be
   /// zero if the base access type is not specified.
   uint64_t Offset;
 };
 
 /// CodeGenTBAA - This class organizes the cross-module state that is used
 /// while lowering AST types to LLVM types.
 class CodeGenTBAA {
   ASTContext &Context;
   const CodeGenOptions &CodeGenOpts;
   const LangOptions &Features;
   MangleContext &MContext;
 
   // MDHelper - Helper for creating metadata.
   llvm::MDBuilder MDHelper;
 
   /// MetadataCache - This maps clang::Types to scalar llvm::MDNodes describing
   /// them.
   llvm::DenseMap<const Type *, llvm::MDNode *> MetadataCache;
-  /// This maps clang::Types to a struct node in the type DAG.
-  llvm::DenseMap<const Type *, llvm::MDNode *> StructTypeMetadataCache;
-  /// This maps TBAAPathTags to a tag node.
-  llvm::DenseMap<TBAAPathTag, llvm::MDNode *> StructTagMetadataCache;
-  /// This maps a scalar type to a scalar tag node.
-  llvm::DenseMap<const llvm::MDNode *, llvm::MDNode *> ScalarTagMetadataCache;
+  /// This maps clang::Types to a base access type in the type DAG.
+  llvm::DenseMap<const Type *, llvm::MDNode *> BaseTypeMetadataCache;
+  /// This maps TBAA access descriptors to tag nodes.
+  llvm::DenseMap<TBAAAccessInfo, llvm::MDNode *> AccessTagMetadataCache;
 
   /// StructMetadataCache - This maps clang::Types to llvm::MDNodes describing
   /// them for struct assignments.
   llvm::DenseMap<const Type *, llvm::MDNode *> StructMetadataCache;
 
   llvm::MDNode *Root;
   llvm::MDNode *Char;
 
CodeGenTBAA(ASTContext &Ctx, llvm::LLVMContext &VMContext,
               const LangOptions &Features,
               MangleContext &MContext);
   ~CodeGenTBAA();
 
   /// getTypeInfo - Get metadata used to describe accesses to objects of the
   /// given type.
   llvm::MDNode *getTypeInfo(QualType QTy);
 
-  /// getTBAAInfoForVTablePtr - Get the TBAA MDNode to be used for a
-  /// dereference of a vtable pointer.
-  llvm::MDNode *getTBAAInfoForVTablePtr();
+  /// getVTablePtrAccessInfo - Get the TBAA information that describes an
+  /// access to a virtual table pointer.
+  TBAAAccessInfo getVTablePtrAccessInfo();
 
   /// getTBAAStructInfo - Get the TBAAStruct MDNode to be used for a memcpy of
   /// the given type.
   llvm::MDNode *getTBAAStructInfo(QualType QTy);
 
-  /// Get the MDNode in the type DAG for given struct type QType.
-  llvm::MDNode *getTBAAStructTypeInfo(QualType QType);
-
-  /// Get path-aware TBAA tag for a given memory access.
-  llvm::MDNode *getTBAAStructTagInfo(TBAAAccessInfo Info);
+  /// getTBAABaseTypeMetadata - Get metadata that describes the given base
+  /// access type. Return null if the type is not suitable for use in TBAA
+  /// access tags.
+  llvm::MDNode *getBaseTypeInfo(QualType QTy);
 
-  /// Get the scalar tag MDNode for a given scalar type.
-  llvm::MDNode *getTBAAScalarTagInfo(llvm::MDNode *AccessNode);
+  /// getAccessTagInfo - Get TBAA tag for a given memory access.
+  llvm::MDNode *getAccessTagInfo(TBAAAccessInfo Info);
 
-  /// getMayAliasTypeInfo - Get TBAA information that represents may-alias
+  /// getMayAliasAccessInfo - Get TBAA information that represents may-alias
   /// accesses.
-  llvm::MDNode *getMayAliasTypeInfo();
+  TBAAAccessInfo getMayAliasAccessInfo();
 };
 
 }  // end namespace CodeGen
 }  // end namespace clang
 
 namespace llvm {
 
-template<> struct DenseMapInfo<clang::CodeGen::TBAAPathTag> {
-  static clang::CodeGen::TBAAPathTag getEmptyKey() {
-    return clang::CodeGen::TBAAPathTag(
-      DenseMapInfo<const clang::Type *>::getEmptyKey(),
-      DenseMapInfo<const MDNode *>::getEmptyKey(),
+template<> struct DenseMapInfo<clang::CodeGen::TBAAAccessInfo> {
+  static clang::CodeGen::TBAAAccessInfo getEmptyKey() {
+    return clang::CodeGen::TBAAAccessInfo(
+      DenseMapInfo<MDNode *>::getEmptyKey(),
+      DenseMapInfo<MDNode *>::getEmptyKey(),
       DenseMapInfo<uint64_t>::getEmptyKey());
   }
 
-  static clang::CodeGen::TBAAPathTag getTombstoneKey() {
-    return clang::CodeGen::TBAAPathTag(
-      DenseMapInfo<const clang::Type *>::getTombstoneKey(),
-      DenseMapInfo<const MDNode *>::getTombstoneKey(),
+  static clang::CodeGen::TBAAAccessInfo getTombstoneKey() {
+    return clang::CodeGen::TBAAAccessInfo(
+      DenseMapInfo<MDNode *>::getTombstoneKey(),
+      DenseMapInfo<MDNode *>::getTombstoneKey(),
       DenseMapInfo<uint64_t>::getTombstoneKey());
   }
 
-  static unsigned getHashValue(const clang::CodeGen::TBAAPathTag &Val) {
-    return DenseMapInfo<const clang::Type *>::getHashValue(Val.BaseT) ^
-           DenseMapInfo<const MDNode *>::getHashValue(Val.AccessN) ^
+  static unsigned getHashValue(const clang::CodeGen::TBAAAccessInfo &Val) {
+    return DenseMapInfo<MDNode *>::getHashValue(Val.BaseType) ^
+           DenseMapInfo<MDNode *>::getHashValue(Val.AccessType) ^
            DenseMapInfo<uint64_t>::getHashValue(Val.Offset);
   }
 
-  static bool isEqual(const clang::CodeGen::TBAAPathTag &LHS,
-                      const clang::CodeGen::TBAAPathTag &RHS) {
-    return LHS.BaseT == RHS.BaseT &&
-           LHS.AccessN == RHS.AccessN &&
+  static bool isEqual(const clang::CodeGen::TBAAAccessInfo &LHS,
+                      const clang::CodeGen::TBAAAccessInfo &RHS) {
+    return LHS.BaseType == RHS.BaseType &&
+           LHS.AccessType == RHS.AccessType &&
            LHS.Offset == RHS.Offset;
   }
 };
 
 }  // end namespace llvm
 
 #endif

cfe/trunk/lib/CodeGen/CodeGenTBAA.cpp

if (const EnumType *ETy = dyn_cast<EnumType>(Ty)) {
     MContext.mangleTypeName(QualType(ETy, 0), Out);
     return MetadataCache[Ty] = createTBAAScalarType(OutName, getChar());
   }
 
   // For now, handle any other kind of type conservatively.
   return MetadataCache[Ty] = getChar();
 }
 
-llvm::MDNode *CodeGenTBAA::getTBAAInfoForVTablePtr() {
-  return createTBAAScalarType("vtable pointer", getRoot());
+TBAAAccessInfo CodeGenTBAA::getVTablePtrAccessInfo() {
+  return TBAAAccessInfo(createTBAAScalarType("vtable pointer", getRoot()));
 }
 
 bool
 CodeGenTBAA::CollectFields(uint64_t BaseOffset,
                            QualType QTy,
                            SmallVectorImpl<llvm::MDBuilder::TBAAStructField> &
                              Fields,
                            bool MayAlias) {
for (RecordDecl::field_iterator i = RD->field_begin(),
         return false;
     }
     return true;
   }
 
   /* Otherwise, treat whatever it is as a field. */
   uint64_t Offset = BaseOffset;
   uint64_t Size = Context.getTypeSizeInChars(QTy).getQuantity();
-  llvm::MDNode *TBAAInfo = MayAlias ? getChar() : getTypeInfo(QTy);
-  llvm::MDNode *TBAATag = getTBAAScalarTagInfo(TBAAInfo);
+  llvm::MDNode *TBAAType = MayAlias ? getChar() : getTypeInfo(QTy);
+  llvm::MDNode *TBAATag = getAccessTagInfo(TBAAAccessInfo(TBAAType));
   Fields.push_back(llvm::MDBuilder::TBAAStructField(Offset, Size, TBAATag));
   return true;
 }
 
 llvm::MDNode *
 CodeGenTBAA::getTBAAStructInfo(QualType QTy) {
   const Type *Ty = Context.getCanonicalType(QTy).getTypePtr();
 
   if (llvm::MDNode *N = StructMetadataCache[Ty])
     return N;
 
   SmallVector<llvm::MDBuilder::TBAAStructField, 4> Fields;
   if (CollectFields(0, QTy, Fields, TypeHasMayAlias(QTy)))
     return MDHelper.createTBAAStructNode(Fields);
 
   // For now, handle any other kind of type conservatively.
   return StructMetadataCache[Ty] = nullptr;
 }
 
-/// Check if the given type can be handled by path-aware TBAA.
-static bool isTBAAPathStruct(QualType QTy) {
+/// Check if the given type is a valid base type to be used in access tags.
+static bool isValidBaseType(QualType QTy) {
   if (const RecordType *TTy = QTy->getAs<RecordType>()) {
     const RecordDecl *RD = TTy->getDecl()->getDefinition();
     if (RD->hasFlexibleArrayMember())
       return false;
     // RD can be struct, union, class, interface or enum.
     // For now, we only handle struct and class.
     if (RD->isStruct() || RD->isClass())
       return true;
   }
   return false;
 }
 
-llvm::MDNode *
-CodeGenTBAA::getTBAAStructTypeInfo(QualType QTy) {
-  const Type *Ty = Context.getCanonicalType(QTy).getTypePtr();
-  assert(isTBAAPathStruct(QTy));
+llvm::MDNode *CodeGenTBAA::getBaseTypeInfo(QualType QTy) {
+  if (!isValidBaseType(QTy))
+    return nullptr;
 
-  if (llvm::MDNode *N = StructTypeMetadataCache[Ty])
+  const Type *Ty = Context.getCanonicalType(QTy).getTypePtr();
+  if (llvm::MDNode *N = BaseTypeMetadataCache[Ty])
     return N;
 
   if (const RecordType *TTy = QTy->getAs<RecordType>()) {
     const RecordDecl *RD = TTy->getDecl()->getDefinition();
 
     const ASTRecordLayout &Layout = Context.getASTRecordLayout(RD);
     SmallVector <std::pair<llvm::MDNode*, uint64_t>, 4> Fields;
     unsigned idx = 0;
     for (RecordDecl::field_iterator i = RD->field_begin(),
          e = RD->field_end(); i != e; ++i, ++idx) {
       QualType FieldQTy = i->getType();
-      llvm::MDNode *FieldNode;
-      if (isTBAAPathStruct(FieldQTy))
-        FieldNode = getTBAAStructTypeInfo(FieldQTy);
-      else
-        FieldNode = getTypeInfo(FieldQTy);
+      llvm::MDNode *FieldNode = isValidBaseType(FieldQTy) ?
+          getBaseTypeInfo(FieldQTy) : getTypeInfo(FieldQTy);
       if (!FieldNode)
-        return StructTypeMetadataCache[Ty] = nullptr;
+        return BaseTypeMetadataCache[Ty] = nullptr;
       Fields.push_back(std::make_pair(
           FieldNode, Layout.getFieldOffset(idx) / Context.getCharWidth()));
     }
 
     SmallString<256> OutName;
     if (Features.CPlusPlus) {
       // Don't use the mangler for C code.
       llvm::raw_svector_ostream Out(OutName);
       MContext.mangleTypeName(QualType(Ty, 0), Out);
     } else {
       OutName = RD->getName();
     }
     // Create the struct type node with a vector of pairs (offset, type).
-    return StructTypeMetadataCache[Ty] =
+    return BaseTypeMetadataCache[Ty] =
       MDHelper.createTBAAStructTypeNode(OutName, Fields);
   }
 
-  return StructMetadataCache[Ty] = nullptr;
+  return BaseTypeMetadataCache[Ty] = nullptr;
 }
 
-llvm::MDNode *CodeGenTBAA::getTBAAStructTagInfo(TBAAAccessInfo Info) {
+llvm::MDNode *CodeGenTBAA::getAccessTagInfo(TBAAAccessInfo Info) {
   if (!Info.AccessType)
     return nullptr;
 
   if (!CodeGenOpts.StructPathTBAA)
-    return getTBAAScalarTagInfo(Info.AccessType);
+    Info = TBAAAccessInfo(Info.AccessType);
 
-  const Type *BTy = Context.getCanonicalType(Info.BaseType).getTypePtr();
-  TBAAPathTag PathTag = TBAAPathTag(BTy, Info.AccessType, Info.Offset);
-  if (llvm::MDNode *N = StructTagMetadataCache[PathTag])
+  llvm::MDNode *&N = AccessTagMetadataCache[Info];
+  if (N)
     return N;
 
-  llvm::MDNode *BNode = nullptr;
-  if (isTBAAPathStruct(Info.BaseType))
-    BNode = getTBAAStructTypeInfo(Info.BaseType);
-  if (!BNode)
-    return StructTagMetadataCache[PathTag] =
-       MDHelper.createTBAAStructTagNode(Info.AccessType, Info.AccessType,
-                                        /* Offset= */ 0);
-
-  return StructTagMetadataCache[PathTag] =
-    MDHelper.createTBAAStructTagNode(BNode, Info.AccessType, Info.Offset);
+  if (!Info.BaseType) {
+    Info.BaseType = Info.AccessType;
+    assert(!Info.Offset && "Nonzero offset for an access with no base type!");
   }
-
-llvm::MDNode *
-CodeGenTBAA::getTBAAScalarTagInfo(llvm::MDNode *AccessNode) {
-  if (!AccessNode)
-    return nullptr;
-  if (llvm::MDNode *N = ScalarTagMetadataCache[AccessNode])
-    return N;
-
-  return ScalarTagMetadataCache[AccessNode] =
-    MDHelper.createTBAAStructTagNode(AccessNode, AccessNode, 0);
+  return N = MDHelper.createTBAAStructTagNode(Info.BaseType, Info.AccessType,
+                                              Info.Offset);
 }
 
-llvm::MDNode *CodeGenTBAA::getMayAliasTypeInfo() {
-  return getChar();
+TBAAAccessInfo CodeGenTBAA::getMayAliasAccessInfo() {
+  return TBAAAccessInfo(getChar());
 }