llvm-project/clang/lib/CodeGen/CodeGenTBAA.h

263 lines
9.4 KiB
C
Raw Normal View History

//===--- CodeGenTBAA.h - TBAA information for LLVM CodeGen ------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This is the code that manages TBAA information and defines the TBAA policy
// for the optimizer to use.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_CLANG_LIB_CODEGEN_CODEGENTBAA_H
#define LLVM_CLANG_LIB_CODEGEN_CODEGENTBAA_H
#include "clang/AST/Type.h"
#include "clang/Basic/LLVM.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/IR/MDBuilder.h"
#include "llvm/IR/Metadata.h"
namespace clang {
class ASTContext;
class CodeGenOptions;
class LangOptions;
class MangleContext;
class QualType;
class Type;
namespace CodeGen {
class CGRecordLayout;
// TBAAAccessKind - A kind of TBAA memory access descriptor.
enum class TBAAAccessKind : unsigned {
[CodeGen] Add initial support for union members in TBAA The basic idea behind this patch is that since in strict aliasing mode all accesses to union members require their outermost enclosing union objects to be specified explicitly, then for a couple given accesses to union members of the form p->a.b.c... q->x.y.z... it is known they can only alias if both p and q point to the same union type and offset ranges of members a.b.c... and x.y.z... overlap. Note that the actual types of the members do not matter. Specifically, in this patch we do the following: * Make unions to be valid TBAA base access types. This enables generation of TBAA type descriptors for unions. * Encode union types as structures with a single member of a special "union member" type. Currently we do not encode information about sizes of types, but conceptually such union members are considered to be of the size of the whole union. * Encode accesses to direct and indirect union members, including member arrays, as accesses to these special members. All accesses to members of a union thus get the same offset, which is the offset of the union they are part of. This means the existing LLVM TBAA machinery is able to handle such accesses with no changes. While this is already an improvement comparing to the current situation, that is, representing all union accesses as may-alias ones, there are further changes planned to complete the support for unions. One of them is storing information about access sizes so we can distinct accesses to non-overlapping union members, including accesses to different elements of member arrays. Another change is encoding type sizes in order to make it possible to compute offsets within constant-indexed array elements. These enhancements will be addressed with separate patches. Differential Revision: https://reviews.llvm.org/D39455 llvm-svn: 319413
2017-11-30 17:26:39 +08:00
Ordinary, // An ordinary memory access.
MayAlias, // An access that may alias with any other accesses.
Incomplete, // Used to designate pointee values of incomplete types.
UnionMember, // An access to a direct or indirect union member.
};
// TBAAAccessInfo - Describes a memory access in terms of TBAA.
struct TBAAAccessInfo {
TBAAAccessInfo(TBAAAccessKind Kind, llvm::MDNode *BaseType,
llvm::MDNode *AccessType, uint64_t Offset, uint64_t Size)
: Kind(Kind), BaseType(BaseType), AccessType(AccessType),
Offset(Offset), Size(Size)
{}
TBAAAccessInfo(llvm::MDNode *BaseType, llvm::MDNode *AccessType,
uint64_t Offset, uint64_t Size)
: TBAAAccessInfo(TBAAAccessKind::Ordinary, BaseType, AccessType,
Offset, Size)
{}
explicit TBAAAccessInfo(llvm::MDNode *AccessType, uint64_t Size)
: TBAAAccessInfo(/* BaseType= */ nullptr, AccessType, /* Offset= */ 0, Size)
{}
TBAAAccessInfo()
: TBAAAccessInfo(/* AccessType= */ nullptr, /* Size= */ 0)
{}
static TBAAAccessInfo getMayAliasInfo() {
return TBAAAccessInfo(TBAAAccessKind::MayAlias,
/* BaseType= */ nullptr, /* AccessType= */ nullptr,
/* Offset= */ 0, /* Size= */ 0);
}
bool isMayAlias() const { return Kind == TBAAAccessKind::MayAlias; }
static TBAAAccessInfo getIncompleteInfo() {
return TBAAAccessInfo(TBAAAccessKind::Incomplete,
/* BaseType= */ nullptr, /* AccessType= */ nullptr,
/* Offset= */ 0, /* Size= */ 0);
}
bool isIncomplete() const { return Kind == TBAAAccessKind::Incomplete; }
[CodeGen] Add initial support for union members in TBAA The basic idea behind this patch is that since in strict aliasing mode all accesses to union members require their outermost enclosing union objects to be specified explicitly, then for a couple given accesses to union members of the form p->a.b.c... q->x.y.z... it is known they can only alias if both p and q point to the same union type and offset ranges of members a.b.c... and x.y.z... overlap. Note that the actual types of the members do not matter. Specifically, in this patch we do the following: * Make unions to be valid TBAA base access types. This enables generation of TBAA type descriptors for unions. * Encode union types as structures with a single member of a special "union member" type. Currently we do not encode information about sizes of types, but conceptually such union members are considered to be of the size of the whole union. * Encode accesses to direct and indirect union members, including member arrays, as accesses to these special members. All accesses to members of a union thus get the same offset, which is the offset of the union they are part of. This means the existing LLVM TBAA machinery is able to handle such accesses with no changes. While this is already an improvement comparing to the current situation, that is, representing all union accesses as may-alias ones, there are further changes planned to complete the support for unions. One of them is storing information about access sizes so we can distinct accesses to non-overlapping union members, including accesses to different elements of member arrays. Another change is encoding type sizes in order to make it possible to compute offsets within constant-indexed array elements. These enhancements will be addressed with separate patches. Differential Revision: https://reviews.llvm.org/D39455 llvm-svn: 319413
2017-11-30 17:26:39 +08:00
static TBAAAccessInfo getUnionMemberInfo(llvm::MDNode *BaseType,
uint64_t Offset, uint64_t Size) {
return TBAAAccessInfo(TBAAAccessKind::UnionMember, BaseType,
/* AccessType= */ nullptr, Offset, Size);
}
bool isUnionMember() const { return Kind == TBAAAccessKind::UnionMember; }
bool operator==(const TBAAAccessInfo &Other) const {
return Kind == Other.Kind &&
BaseType == Other.BaseType &&
AccessType == Other.AccessType &&
Offset == Other.Offset &&
Size == Other.Size;
}
bool operator!=(const TBAAAccessInfo &Other) const {
return !(*this == Other);
}
explicit operator bool() const {
return *this != TBAAAccessInfo();
}
/// Kind - The kind of the access descriptor.
TBAAAccessKind Kind;
/// 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.
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;
/// Size - The size of access, in bytes.
uint64_t Size;
};
/// CodeGenTBAA - This class organizes the cross-module state that is used
/// while lowering AST types to LLVM types.
class CodeGenTBAA {
ASTContext &Context;
llvm::Module &Module;
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 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;
/// getRoot - This is the mdnode for the root of the metadata type graph
/// for this translation unit.
llvm::MDNode *getRoot();
/// getChar - This is the mdnode for "char", which is special, and any types
/// considered to be equivalent to it.
llvm::MDNode *getChar();
[CodeGen] Add initial support for union members in TBAA The basic idea behind this patch is that since in strict aliasing mode all accesses to union members require their outermost enclosing union objects to be specified explicitly, then for a couple given accesses to union members of the form p->a.b.c... q->x.y.z... it is known they can only alias if both p and q point to the same union type and offset ranges of members a.b.c... and x.y.z... overlap. Note that the actual types of the members do not matter. Specifically, in this patch we do the following: * Make unions to be valid TBAA base access types. This enables generation of TBAA type descriptors for unions. * Encode union types as structures with a single member of a special "union member" type. Currently we do not encode information about sizes of types, but conceptually such union members are considered to be of the size of the whole union. * Encode accesses to direct and indirect union members, including member arrays, as accesses to these special members. All accesses to members of a union thus get the same offset, which is the offset of the union they are part of. This means the existing LLVM TBAA machinery is able to handle such accesses with no changes. While this is already an improvement comparing to the current situation, that is, representing all union accesses as may-alias ones, there are further changes planned to complete the support for unions. One of them is storing information about access sizes so we can distinct accesses to non-overlapping union members, including accesses to different elements of member arrays. Another change is encoding type sizes in order to make it possible to compute offsets within constant-indexed array elements. These enhancements will be addressed with separate patches. Differential Revision: https://reviews.llvm.org/D39455 llvm-svn: 319413
2017-11-30 17:26:39 +08:00
/// getUnionMemberType - Get metadata that represents the type of union
/// members.
llvm::MDNode *getUnionMemberType(uint64_t Size);
/// CollectFields - Collect information about the fields of a type for
/// !tbaa.struct metadata formation. Return false for an unsupported type.
bool CollectFields(uint64_t BaseOffset,
QualType Ty,
SmallVectorImpl<llvm::MDBuilder::TBAAStructField> &Fields,
bool MayAlias);
/// createScalarTypeNode - A wrapper function to create a metadata node
/// describing a scalar type.
llvm::MDNode *createScalarTypeNode(StringRef Name, llvm::MDNode *Parent,
uint64_t Size);
/// getTypeInfoHelper - An internal helper function to generate metadata used
/// to describe accesses to objects of the given type.
llvm::MDNode *getTypeInfoHelper(const Type *Ty);
/// getBaseTypeInfoHelper - An internal helper function to generate metadata
/// used to describe accesses to objects of the given base type.
llvm::MDNode *getBaseTypeInfoHelper(const Type *Ty);
public:
CodeGenTBAA(ASTContext &Ctx, llvm::Module &M, const CodeGenOptions &CGO,
const LangOptions &Features, MangleContext &MContext);
~CodeGenTBAA();
/// getTypeInfo - Get metadata used to describe accesses to objects of the
/// given type.
llvm::MDNode *getTypeInfo(QualType QTy);
[CodeGen] Unify generation of scalar and struct-path TBAA tags 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. Differential Revision: https://reviews.llvm.org/D38503 llvm-svn: 314979
2017-10-05 19:08:17 +08:00
/// getVTablePtrAccessInfo - Get the TBAA information that describes an
/// access to a virtual table pointer.
TBAAAccessInfo getVTablePtrAccessInfo(llvm::Type *VTablePtrType);
/// getTBAAStructInfo - Get the TBAAStruct MDNode to be used for a memcpy of
/// the given type.
llvm::MDNode *getTBAAStructInfo(QualType QTy);
/// getBaseTypeInfo - 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);
[CodeGen] Unify generation of scalar and struct-path TBAA tags 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. Differential Revision: https://reviews.llvm.org/D38503 llvm-svn: 314979
2017-10-05 19:08:17 +08:00
/// getAccessTagInfo - Get TBAA tag for a given memory access.
llvm::MDNode *getAccessTagInfo(TBAAAccessInfo Info);
/// mergeTBAAInfoForCast - Get merged TBAA information for the purpose of
/// type casts.
TBAAAccessInfo mergeTBAAInfoForCast(TBAAAccessInfo SourceInfo,
TBAAAccessInfo TargetInfo);
/// mergeTBAAInfoForConditionalOperator - Get merged TBAA information for the
/// purpose of conditional operator.
TBAAAccessInfo mergeTBAAInfoForConditionalOperator(TBAAAccessInfo InfoA,
TBAAAccessInfo InfoB);
};
} // end namespace CodeGen
} // end namespace clang
namespace llvm {
template<> struct DenseMapInfo<clang::CodeGen::TBAAAccessInfo> {
static clang::CodeGen::TBAAAccessInfo getEmptyKey() {
unsigned UnsignedKey = DenseMapInfo<unsigned>::getEmptyKey();
return clang::CodeGen::TBAAAccessInfo(
static_cast<clang::CodeGen::TBAAAccessKind>(UnsignedKey),
DenseMapInfo<MDNode *>::getEmptyKey(),
DenseMapInfo<MDNode *>::getEmptyKey(),
DenseMapInfo<uint64_t>::getEmptyKey(),
DenseMapInfo<uint64_t>::getEmptyKey());
}
static clang::CodeGen::TBAAAccessInfo getTombstoneKey() {
unsigned UnsignedKey = DenseMapInfo<unsigned>::getTombstoneKey();
return clang::CodeGen::TBAAAccessInfo(
static_cast<clang::CodeGen::TBAAAccessKind>(UnsignedKey),
DenseMapInfo<MDNode *>::getTombstoneKey(),
DenseMapInfo<MDNode *>::getTombstoneKey(),
DenseMapInfo<uint64_t>::getTombstoneKey(),
DenseMapInfo<uint64_t>::getTombstoneKey());
}
static unsigned getHashValue(const clang::CodeGen::TBAAAccessInfo &Val) {
auto KindValue = static_cast<unsigned>(Val.Kind);
return DenseMapInfo<unsigned>::getHashValue(KindValue) ^
DenseMapInfo<MDNode *>::getHashValue(Val.BaseType) ^
DenseMapInfo<MDNode *>::getHashValue(Val.AccessType) ^
DenseMapInfo<uint64_t>::getHashValue(Val.Offset) ^
DenseMapInfo<uint64_t>::getHashValue(Val.Size);
}
static bool isEqual(const clang::CodeGen::TBAAAccessInfo &LHS,
const clang::CodeGen::TBAAAccessInfo &RHS) {
return LHS == RHS;
}
};
} // end namespace llvm
#endif