[CodeGen] Introduce generic TBAA access descriptors

[kosarev]

Summary

With this patch we implement a concept of TBAA access descriptors that are capable of representing both scalar and struct-path accesses in a generic way.

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

[rjmccall]

LGTM.

cfe/trunk/lib/CodeGen/CGExpr.cpp

if (DeclRefExpr *DRE = tryToConvertMemberExprToDeclRefExpr(*this, ME))
     return tryEmitAsConstant(DRE);
   return ConstantEmission();
 }
 
 llvm::Value *CodeGenFunction::EmitLoadOfScalar(LValue lvalue,
                                                SourceLocation Loc) {
   return EmitLoadOfScalar(lvalue.getAddress(), lvalue.isVolatile(),
                           lvalue.getType(), Loc, lvalue.getBaseInfo(),
-                          lvalue.getTBAAAccessType(),
-                          lvalue.getTBAABaseType(), lvalue.getTBAAOffset(),
-                          lvalue.isNontemporal());
+                          lvalue.getTBAAInfo(), lvalue.isNontemporal());
 }
 
 static bool hasBooleanRepresentation(QualType Ty) {
   if (Ty->isBooleanType())
     return true;
 
   if (const EnumType *ET = Ty->getAs<EnumType>())
     return ET->getDecl()->getIntegerType()->isBooleanType();
EmitCheck(std::make_pair(Check, Kind), SanitizerHandler::LoadInvalidValue,
             StaticArgs, EmitCheckValue(Value));
   return true;
 }
 
 llvm::Value *CodeGenFunction::EmitLoadOfScalar(Address Addr, bool Volatile,
                                                QualType Ty,
                                                SourceLocation Loc,
                                                LValueBaseInfo BaseInfo,
-                                               llvm::MDNode *TBAAAccessType,
-                                               QualType TBAABaseType,
-                                               uint64_t TBAAOffset,
+                                               TBAAAccessInfo TBAAInfo,
                                                bool isNontemporal) {
   if (!CGM.getCodeGenOpts().PreserveVec3Type) {
     // For better performance, handle vector loads differently.
     if (Ty->isVectorType()) {
       const llvm::Type *EltTy = Addr.getElementType();
 
       const auto *VTy = cast<llvm::VectorType>(EltTy);
 
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, TBAAAccessType);
+      LValue::MakeAddr(Addr, Ty, getContext(), BaseInfo, TBAAInfo.AccessType);
   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 (TBAAAccessType) {
+  if (TBAAInfo.AccessType) {
     bool MayAlias = BaseInfo.getMayAlias();
     llvm::MDNode *TBAA = MayAlias
         ? CGM.getTBAAMayAliasTypeInfo()
-        : CGM.getTBAAStructTagInfo(TBAABaseType, TBAAAccessType, TBAAOffset);
+        : CGM.getTBAAStructTagInfo(TBAAInfo);
     if (TBAA)
       CGM.DecorateInstructionWithTBAA(Load, TBAA, MayAlias);
   }
 
   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)
llvm::Value *CodeGenFunction::EmitFromMemory(llvm::Value *Value, QualType Ty) {
   }
 
   return Value;
 }
 
 void CodeGenFunction::EmitStoreOfScalar(llvm::Value *Value, Address Addr,
                                         bool Volatile, QualType Ty,
                                         LValueBaseInfo BaseInfo,
-                                        llvm::MDNode *TBAAAccessType,
-                                        bool isInit, QualType TBAABaseType,
-                                        uint64_t TBAAOffset,
-                                        bool isNontemporal) {
-
+                                        TBAAAccessInfo TBAAInfo,
+                                        bool isInit, bool isNontemporal) {
   if (!CGM.getCodeGenOpts().PreserveVec3Type) {
     // Handle vectors differently to get better performance.
     if (Ty->isVectorType()) {
       llvm::Type *SrcTy = Value->getType();
       auto *VecTy = dyn_cast<llvm::VectorType>(SrcTy);
       // Handle vec3 special.
       if (VecTy && VecTy->getNumElements() == 3) {
         // Our source is a vec3, do a shuffle vector to make it a vec4.
if (Ty->isVectorType()) {
         Addr = Builder.CreateElementBitCast(Addr, SrcTy, "storetmp");
       }
     }
   }
 
   Value = EmitToMemory(Value, Ty);
 
   LValue AtomicLValue =
-      LValue::MakeAddr(Addr, Ty, getContext(), BaseInfo, TBAAAccessType);
+      LValue::MakeAddr(Addr, Ty, getContext(), BaseInfo, TBAAInfo.AccessType);
   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 (TBAAAccessType) {
+  if (TBAAInfo.AccessType) {
     bool MayAlias = BaseInfo.getMayAlias();
     llvm::MDNode *TBAA = MayAlias
         ? CGM.getTBAAMayAliasTypeInfo()
-        : CGM.getTBAAStructTagInfo(TBAABaseType, TBAAAccessType, TBAAOffset);
+        : CGM.getTBAAStructTagInfo(TBAAInfo);
     if (TBAA)
       CGM.DecorateInstructionWithTBAA(Store, TBAA, MayAlias);
   }
 }
 
 void CodeGenFunction::EmitStoreOfScalar(llvm::Value *value, LValue lvalue,
                                         bool isInit) {
   EmitStoreOfScalar(value, lvalue.getAddress(), lvalue.isVolatile(),
                     lvalue.getType(), lvalue.getBaseInfo(),
-                    lvalue.getTBAAAccessType(), isInit,
-                    lvalue.getTBAABaseType(), lvalue.getTBAAOffset(),
-                    lvalue.isNontemporal());
+                    lvalue.getTBAAInfo(), isInit, lvalue.isNontemporal());
 }
 
 /// EmitLoadOfLValue - Given an expression that represents a value lvalue, this
 /// method emits the address of the lvalue, then loads the result as an rvalue,
 /// returning the rvalue.
 RValue CodeGenFunction::EmitLoadOfLValue(LValue LV, SourceLocation Loc) {
   if (LV.isObjCWeak()) {
     // load of a __weak object.
LValue CodeGenFunction::EmitLValueForField(LValue base,
 
   LValue LV = MakeAddrLValue(addr, type, FieldBaseInfo);
   LV.getQuals().addCVRQualifiers(cvr);
   if (TBAAPath) {
     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.
-    LV.setTBAABaseType(mayAlias ? getContext().CharTy : base.getTBAABaseType());
-    LV.setTBAAOffset(mayAlias ? 0 : base.getTBAAOffset() +
-                     Layout.getFieldOffset(field->getFieldIndex()) /
-                                           getContext().getCharWidth());
+    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);
+    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

cfe/trunk/lib/CodeGen/CGValue.h

 #ifndef LLVM_CLANG_LIB_CODEGEN_CGVALUE_H
 #define LLVM_CLANG_LIB_CODEGEN_CGVALUE_H
 
 #include "clang/AST/ASTContext.h"
 #include "clang/AST/Type.h"
 #include "llvm/IR/Value.h"
 #include "llvm/IR/Type.h"
 #include "Address.h"
+#include "CodeGenTBAA.h"
 
 namespace llvm {
   class Constant;
   class MDNode;
 }
 
 namespace clang {
 namespace CodeGen {
class LValue {
   // Lvalue is a thread local reference
   bool ThreadLocalRef : 1;
 
   // Lvalue has ARC imprecise lifetime.  We store this inverted to try
   // to make the default bitfield pattern all-zeroes.
   bool ImpreciseLifetime : 1;
 
   LValueBaseInfo BaseInfo;
+  TBAAAccessInfo TBAAInfo;
 
   // This flag shows if a nontemporal load/stores should be used when accessing
   // this lvalue.
   bool Nontemporal : 1;
 
   Expr *BaseIvarExp;
 
-  /// TBAABaseType - The base access type used by TBAA.
-  QualType TBAABaseType;
-
-  /// TBAAOffset - Access offset used by TBAA.
-  uint64_t TBAAOffset;
-
-  /// TBAAInfo - The final access type used by TBAA.
-  llvm::MDNode *TBAAAccessType;
-
 private:
   void Initialize(QualType Type, Qualifiers Quals,
                   CharUnits Alignment, LValueBaseInfo BaseInfo,
                   llvm::MDNode *TBAAAccessType = nullptr) {
     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);
 
     // 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;
-
-    // Initialize fields for TBAA.
-    this->TBAABaseType = Type;
-    this->TBAAOffset = 0;
-    this->TBAAAccessType = TBAAAccessType;
   }
 
 public:
   bool isSimple() const { return LVType == Simple; }
   bool isVectorElt() const { return LVType == VectorElt; }
   bool isBitField() const { return LVType == BitField; }
   bool isExtVectorElt() const { return LVType == ExtVectorElt; }
   bool isGlobalReg() const { return LVType == GlobalReg; }
public:
 
   bool isVolatile() const {
     return Quals.hasVolatile();
   }
   
   Expr *getBaseIvarExp() const { return BaseIvarExp; }
   void setBaseIvarExp(Expr *V) { BaseIvarExp = V; }
 
-  QualType getTBAABaseType() const { return TBAABaseType; }
-  void setTBAABaseType(QualType T) { TBAABaseType = T; }
-
-  uint64_t getTBAAOffset() const { return TBAAOffset; }
-  void setTBAAOffset(uint64_t O) { TBAAOffset = O; }
+  TBAAAccessInfo getTBAAInfo() const { return TBAAInfo; }
+  void setTBAAInfo(TBAAAccessInfo Info) { TBAAInfo = Info; }
 
-  llvm::MDNode *getTBAAAccessType() const { return TBAAAccessType; }
-  void setTBAAAccessType(llvm::MDNode *N) { TBAAAccessType = N; }
+  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(); }

cfe/trunk/lib/CodeGen/CodeGenFunction.h

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),
-                                llvm::MDNode *TBAAAccessType = nullptr,
-                                QualType TBAABaseTy = QualType(),
-                                uint64_t TBAAOffset = 0,
+                                TBAAAccessInfo TBAAInfo = TBAAAccessInfo(),
                                 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),
-                         llvm::MDNode *TBAAAccessType = nullptr,
-                         bool isInit = false, QualType TBAABaseTy = QualType(),
-                         uint64_t TBAAOffset = 0, bool isNontemporal = false);
+                         TBAAAccessInfo TBAAInfo = TBAAAccessInfo(),
+                         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/CodeGenModule.h

public:
   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();
   llvm::MDNode *getTBAAStructInfo(QualType QTy);
-  /// Return the path-aware tag for given base type, access node and offset.
-  llvm::MDNode *getTBAAStructTagInfo(QualType BaseTy, llvm::MDNode *AccessN,
-                                     uint64_t O);
+
+  /// Get path-aware TBAA tag for a given memory access.
+  llvm::MDNode *getTBAAStructTagInfo(TBAAAccessInfo Info);
 
   /// getTBAAMayAliasTypeInfo - Get TBAA information that represents
   /// may-alias accesses.
   llvm::MDNode *getTBAAMayAliasTypeInfo();
 
   bool isTypeConstant(QualType QTy, bool ExcludeCtorDtor);
 
   bool isPaddedAtomicType(QualType type);

cfe/trunk/lib/CodeGen/CodeGenModule.cpp

 #include "CGCall.h"
 #include "CGDebugInfo.h"
 #include "CGObjCRuntime.h"
 #include "CGOpenCLRuntime.h"
 #include "CGOpenMPRuntime.h"
 #include "CGOpenMPRuntimeNVPTX.h"
 #include "CodeGenFunction.h"
 #include "CodeGenPGO.h"
-#include "CodeGenTBAA.h"
 #include "ConstantEmitter.h"
 #include "CoverageMappingGen.h"
 #include "TargetInfo.h"
 #include "clang/AST/ASTContext.h"
 #include "clang/AST/CharUnits.h"
 #include "clang/AST/DeclCXX.h"
 #include "clang/AST/DeclObjC.h"
 #include "clang/AST/DeclTemplate.h"

 }
 
 llvm::MDNode *CodeGenModule::getTBAAStructInfo(QualType QTy) {
   if (!TBAA)
     return nullptr;
   return TBAA->getTBAAStructInfo(QTy);
 }
 
-llvm::MDNode *CodeGenModule::getTBAAStructTagInfo(QualType BaseTy,
-                                                  llvm::MDNode *AccessN,
-                                                  uint64_t O) {
+llvm::MDNode *CodeGenModule::getTBAAStructTagInfo(TBAAAccessInfo Info) {
   if (!TBAA)
     return nullptr;
-  return TBAA->getTBAAStructTagInfo(BaseTy, AccessN, O);
+  return TBAA->getTBAAStructTagInfo(Info);
 }
 
 llvm::MDNode *CodeGenModule::getTBAAMayAliasTypeInfo() {
   if (!TBAA)
     return nullptr;
   return TBAA->getMayAliasTypeInfo();
 }
 

cfe/trunk/lib/CodeGen/CodeGenTBAA.h

namespace clang {
   class ASTContext;
   class CodeGenOptions;
   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)
+    : BaseType(BaseType), AccessType(AccessType), Offset(Offset)
+  {}
+
+  explicit TBAAAccessInfo(llvm::MDNode *AccessType)
+    : TBAAAccessInfo(/* BaseType= */ QualType(), 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;
+
+  /// 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;
 
public:
   llvm::MDNode *getTBAAInfoForVTablePtr();
 
   /// 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 the tag MDNode for a given base type, the actual scalar access MDNode
-  /// and offset into the base type.
-  llvm::MDNode *getTBAAStructTagInfo(QualType BaseQType,
-                                     llvm::MDNode *AccessNode, uint64_t Offset);
+
+  /// Get path-aware TBAA tag for a given memory access.
+  llvm::MDNode *getTBAAStructTagInfo(TBAAAccessInfo Info);
 
   /// Get the scalar tag MDNode for a given scalar type.
   llvm::MDNode *getTBAAScalarTagInfo(llvm::MDNode *AccessNode);
 
   /// getMayAliasTypeInfo - Get TBAA information that represents may-alias
   /// accesses.
   llvm::MDNode *getMayAliasTypeInfo();
 };

cfe/trunk/lib/CodeGen/CodeGenTBAA.cpp

if (const RecordType *TTy = QTy->getAs<RecordType>()) {
     // Create the struct type node with a vector of pairs (offset, type).
     return StructTypeMetadataCache[Ty] =
       MDHelper.createTBAAStructTypeNode(OutName, Fields);
   }
 
   return StructMetadataCache[Ty] = nullptr;
 }
 
-/// Return a TBAA tag node for both scalar TBAA and struct-path aware TBAA.
-llvm::MDNode *
-CodeGenTBAA::getTBAAStructTagInfo(QualType BaseQTy, llvm::MDNode *AccessNode,
-                                  uint64_t Offset) {
-  if (!AccessNode)
+llvm::MDNode *CodeGenTBAA::getTBAAStructTagInfo(TBAAAccessInfo Info) {
+  if (!Info.AccessType)
     return nullptr;
 
   if (!CodeGenOpts.StructPathTBAA)
-    return getTBAAScalarTagInfo(AccessNode);
+    return getTBAAScalarTagInfo(Info.AccessType);
 
-  const Type *BTy = Context.getCanonicalType(BaseQTy).getTypePtr();
-  TBAAPathTag PathTag = TBAAPathTag(BTy, AccessNode, Offset);
+  const Type *BTy = Context.getCanonicalType(Info.BaseType).getTypePtr();
+  TBAAPathTag PathTag = TBAAPathTag(BTy, Info.AccessType, Info.Offset);
   if (llvm::MDNode *N = StructTagMetadataCache[PathTag])
     return N;
 
   llvm::MDNode *BNode = nullptr;
-  if (isTBAAPathStruct(BaseQTy))
-    BNode  = getTBAAStructTypeInfo(BaseQTy);
+  if (isTBAAPathStruct(Info.BaseType))
+    BNode = getTBAAStructTypeInfo(Info.BaseType);
   if (!BNode)
     return StructTagMetadataCache[PathTag] =
-       MDHelper.createTBAAStructTagNode(AccessNode, AccessNode, 0);
+       MDHelper.createTBAAStructTagNode(Info.AccessType, Info.AccessType,
+                                        /* Offset= */ 0);
 
   return StructTagMetadataCache[PathTag] =
-    MDHelper.createTBAAStructTagNode(BNode, AccessNode, Offset);
+    MDHelper.createTBAAStructTagNode(BNode, Info.AccessType, Info.Offset);
 }
 
 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);
 }
 
 llvm::MDNode *CodeGenTBAA::getMayAliasTypeInfo() {
   return getChar();
 }