TypeBasedAliasAnalysis.cpp

Go to the documentation of this file.

//===- TypeBasedAliasAnalysis.cpp - Type-Based Alias Analysis -------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file defines the TypeBasedAliasAnalysis pass, which implements
// metadata-based TBAA.
//
// In LLVM IR, memory does not have types, so LLVM's own type system is not
// suitable for doing TBAA. Instead, metadata is added to the IR to describe
// a type system of a higher level language. This can be used to implement
// typical C/C++ TBAA, but it can also be used to implement custom alias
// analysis behavior for other languages.
//
// Scalar type nodes have up to three fields, e.g.:
//   !0 = !{ !"an example type tree" }
//   !1 = !{ !"int", !0 }
//   !2 = !{ !"float", !0 }
//   !3 = !{ !"const float", !2, i64 1 }
//
// The first field is an identity field. It can be any value, usually
// an MDString, which uniquely identifies the type. The most important
// name in the tree is the name of the root node. Two trees with
// different root node names are entirely disjoint, even if they
// have leaves with common names.
//
// The second field identifies the type's parent node in the tree, or
// is null or omitted for a root node. A type is considered to alias
// all of its descendants and all of its ancestors in the tree. Also,
// a type is considered to alias all types in other trees, so that
// bitcode produced from multiple front-ends is handled conservatively.
//
// If the third field is present, it's an integer which if equal to 1
// indicates that the type is "constant" (meaning pointsToConstantMemory
// should return true; see
// http://llvm.org/docs/AliasAnalysis.html#OtherItfs).
//
// The MDNodes attached to an instruction using "!tbaa" are not plain type
// nodes, but path tag nodes.
//
// The path tag node has 4 fields with the last field being optional.
//
// The first field is the base type node, it can be a struct type node
// or a scalar type node. The second field is the access type node, it
// must be a scalar type node. The third field is the offset into the base type.
// The last field has the same meaning as the last field of our scalar TBAA:
// it's an integer which if equal to 1 indicates that the access is "constant".
//
// The struct type node has a name and a list of pairs, one pair for each member
// of the struct. The first element of each pair is a type node (a struct type
// node or a scalar type node), specifying the type of the member, the second
// element of each pair is the offset of the member.
//
// Given an example
// typedef struct {
//   short s;
// } A;
// typedef struct {
//   uint16_t s;
//   A a;
// } B;
//
// For an access to B.a.s, we attach !5 (a path tag node) to the load/store
// instruction. The base type is !4 (struct B), the access type is !2 (scalar
// type short) and the offset is 4.
//
// !0 = !{!"Simple C/C++ TBAA"}
// !1 = !{!"omnipotent char", !0} // Scalar type node
// !2 = !{!"short", !1}           // Scalar type node
// !3 = !{!"A", !2, i64 0}        // Struct type node
// !4 = !{!"B", !2, i64 0, !3, i64 4}
//                                                           // Struct type node
// !5 = !{!4, !2, i64 4}          // Path tag node
//
// The struct type nodes and the scalar type nodes form a type DAG.
//         Root (!0)
//         char (!1)  -- edge to Root
//         short (!2) -- edge to char
//         A (!3) -- edge with offset 0 to short
//         B (!4) -- edge with offset 0 to short and edge with offset 4 to A
//
// To check if two tags (tagX and tagY) can alias, we start from the base type
// of tagX, follow the edge with the correct offset in the type DAG and adjust
// the offset until we reach the base type of tagY or until we reach the Root
// node.
// If we reach the base type of tagY, compare the adjusted offset with
// offset of tagY, return Alias if the offsets are the same, return NoAlias
// otherwise.
// If we reach the Root node, perform the above starting from base type of tagY
// to see if we reach base type of tagX.
//
// If they have different roots, they're part of different potentially
// unrelated type systems, so we return Alias to be conservative.
// If neither node is an ancestor of the other and they have the same root,
// then we say NoAlias.
//
//===----------------------------------------------------------------------===//
 
#include "llvm/Analysis/TypeBasedAliasAnalysis.h"
#include "llvm/ADT/SetVector.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/MemoryLocation.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/InstrTypes.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/Module.h"
#include "llvm/InitializePasses.h"
#include "llvm/Pass.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/CommandLine.h"
#include <cassert>
#include <cstdint>
 
using namespace llvm;
 
// A handy option for disabling TBAA functionality. The same effect can also be
// achieved by stripping the !tbaa tags from IR, but this option is sometimes
// more convenient.
static cl::opt<bool> EnableTBAA("enable-tbaa", cl::init(true), cl::Hidden);
 
namespace {
 
/// isNewFormatTypeNode - Return true iff the given type node is in the new
/// size-aware format.
static bool isNewFormatTypeNode(const MDNode *N) {
  if (N->getNumOperands() < 3)
    return false;
  // In the old format the first operand is a string.
  if (!isa<MDNode>(N->getOperand(0)))
    return false;
  return true;
}
 
/// This is a simple wrapper around an MDNode which provides a higher-level
/// interface by hiding the details of how alias analysis information is encoded
/// in its operands.
class TBAANode {
  const MDNode *Node = nullptr;
 
public:
  TBAANode() = default;
  explicit TBAANode(const MDNode *N) : Node(N) {}
 
  /// getNode - Get the MDNode for this TBAANode.
  const MDNode *getNode() const { return Node; }
 
  /// isNewFormat - Return true iff the wrapped type node is in the new
  /// size-aware format.
  bool isNewFormat() const { return isNewFormatTypeNode(Node); }
 
  /// getParent - Get this TBAANode's Alias tree parent.
  TBAANode getParent() const {
    if (isNewFormat())
      return TBAANode(cast<MDNode>(Node->getOperand(0)));
 
    if (Node->getNumOperands() < 2)
      return TBAANode();
    const MDNode *P = dyn_cast_or_null<MDNode>(Node->getOperand(1));
    if (!P)
      return TBAANode();
    // Ok, this node has a valid parent. Return it.
    return TBAANode(P);
  }
};
 
/// This is a simple wrapper around an MDNode which provides a
/// higher-level interface by hiding the details of how alias analysis
/// information is encoded in its operands.
class TBAAStructTagNode {
  /// This node should be created with createTBAAAccessTag().
  const MDNode *Node;
 
public:
  explicit TBAAStructTagNode(const MDNode *N) : Node(N) {}
 
  /// Get the MDNode for this TBAAStructTagNode.
  const MDNode *getNode() const { return Node; }
 
  /// isNewFormat - Return true iff the wrapped access tag is in the new
  /// size-aware format.
  bool isNewFormat() const {
    if (Node->getNumOperands() < 4)
      return false;
    if (const MDNode *AccessType = getAccessType())
      if (!TBAANode(AccessType).isNewFormat())
        return false;
    return true;
  }
 
  const MDNode *getBaseType() const {
    return dyn_cast_or_null<MDNode>(Node->getOperand(0));
  }
 
  const MDNode *getAccessType() const {
    return dyn_cast_or_null<MDNode>(Node->getOperand(1));
  }
 
  uint64_t getOffset() const {
    return mdconst::extract<ConstantInt>(Node->getOperand(2))->getZExtValue();
  }
 
  uint64_t getSize() const {
    if (!isNewFormat())
      return UINT64_MAX;
    return mdconst::extract<ConstantInt>(Node->getOperand(3))->getZExtValue();
  }
 
  /// Test if this TBAAStructTagNode represents a type for objects
  /// which are not modified (by any means) in the context where this
  /// AliasAnalysis is relevant.
  bool isTypeImmutable() const {
    unsigned OpNo = isNewFormat() ? 4 : 3;
    if (Node->getNumOperands() < OpNo + 1)
      return false;
    ConstantInt *CI = mdconst::dyn_extract<ConstantInt>(Node->getOperand(OpNo));
    if (!CI)
      return false;
    return CI->getValue()[0];
  }
};
 
/// This is a simple wrapper around an MDNode which provides a
/// higher-level interface by hiding the details of how alias analysis
/// information is encoded in its operands.
class TBAAStructTypeNode {
  /// This node should be created with createTBAATypeNode().
  const MDNode *Node = nullptr;
 
public:
  TBAAStructTypeNode() = default;
  explicit TBAAStructTypeNode(const MDNode *N) : Node(N) {}
 
  /// Get the MDNode for this TBAAStructTypeNode.
  const MDNode *getNode() const { return Node; }
 
  /// isNewFormat - Return true iff the wrapped type node is in the new
  /// size-aware format.
  bool isNewFormat() const { return isNewFormatTypeNode(Node); }
 
  bool operator==(const TBAAStructTypeNode &Other) const {
    return getNode() == Other.getNode();
  }
 
  /// getId - Return type identifier.
  Metadata *getId() const {
    return Node->getOperand(isNewFormat() ? 2 : 0);
  }
 
  unsigned getNumFields() const {
    unsigned FirstFieldOpNo = isNewFormat() ? 3 : 1;
    unsigned NumOpsPerField = isNewFormat() ? 3 : 2;
    return (getNode()->getNumOperands() - FirstFieldOpNo) / NumOpsPerField;
  }
 
  TBAAStructTypeNode getFieldType(unsigned FieldIndex) const {
    unsigned FirstFieldOpNo = isNewFormat() ? 3 : 1;
    unsigned NumOpsPerField = isNewFormat() ? 3 : 2;
    unsigned OpIndex = FirstFieldOpNo + FieldIndex * NumOpsPerField;
    auto *TypeNode = cast<MDNode>(getNode()->getOperand(OpIndex));
    return TBAAStructTypeNode(TypeNode);
  }
 
  /// Get this TBAAStructTypeNode's field in the type DAG with
  /// given offset. Update the offset to be relative to the field type.
  TBAAStructTypeNode getField(uint64_t &Offset) const {
    bool NewFormat = isNewFormat();
    const ArrayRef<MDOperand> Operands = Node->operands();
    const unsigned NumOperands = Operands.size();
 
    if (NewFormat) {
      // New-format root and scalar type nodes have no fields.
      if (NumOperands < 6)
        return TBAAStructTypeNode();
    } else {
      // Parent can be omitted for the root node.
      if (NumOperands < 2)
        return TBAAStructTypeNode();
 
      // Fast path for a scalar type node and a struct type node with a single
      // field.
      if (NumOperands <= 3) {
        uint64_t Cur =
            NumOperands == 2
                ? 0
                : mdconst::extract<ConstantInt>(Operands[2])->getZExtValue();
        Offset -= Cur;
        MDNode *P = dyn_cast_or_null<MDNode>(Operands[1]);
        if (!P)
          return TBAAStructTypeNode();
        return TBAAStructTypeNode(P);
      }
    }
 
    // Assume the offsets are in order. We return the previous field if
    // the current offset is bigger than the given offset.
    unsigned FirstFieldOpNo = NewFormat ? 3 : 1;
    unsigned NumOpsPerField = NewFormat ? 3 : 2;
    unsigned TheIdx = 0;
 
    for (unsigned Idx = FirstFieldOpNo; Idx < NumOperands;
         Idx += NumOpsPerField) {
      uint64_t Cur =
          mdconst::extract<ConstantInt>(Operands[Idx + 1])->getZExtValue();
      if (Cur > Offset) {
        assert(Idx >= FirstFieldOpNo + NumOpsPerField &&
               "TBAAStructTypeNode::getField should have an offset match!");
        TheIdx = Idx - NumOpsPerField;
        break;
      }
    }
    // Move along the last field.
    if (TheIdx == 0)
      TheIdx = NumOperands - NumOpsPerField;
    uint64_t Cur =
        mdconst::extract<ConstantInt>(Operands[TheIdx + 1])->getZExtValue();
    Offset -= Cur;
    MDNode *P = dyn_cast_or_null<MDNode>(Operands[TheIdx]);
    if (!P)
      return TBAAStructTypeNode();
    return TBAAStructTypeNode(P);
  }
};
 
} // end anonymous namespace
 
AliasResult TypeBasedAAResult::alias(const MemoryLocation &LocA,
                                     const MemoryLocation &LocB,
                                     AAQueryInfo &AAQI, const Instruction *) {
  if (!shouldUseTBAA())
    return AliasResult::MayAlias;
 
  if (Aliases(LocA.AATags.TBAA, LocB.AATags.TBAA))
    return AliasResult::MayAlias;
 
  // Otherwise return a definitive result.
  return AliasResult::NoAlias;
}
 
AliasResult TypeBasedAAResult::aliasErrno(const MemoryLocation &Loc,
                                          const Instruction *CtxI) {
  if (!shouldUseTBAA())
    return AliasResult::MayAlias;
 
  const auto *N = Loc.AATags.TBAA;
  if (!N)
    return AliasResult::MayAlias;
 
  // There cannot be any alias with errno if TBAA proves the given memory
  // location does not alias errno.
  const auto *ErrnoTBAAMD =
      CtxI->getModule()->getNamedMetadata("llvm.errno.tbaa");
  if (!ErrnoTBAAMD || any_of(ErrnoTBAAMD->operands(), [&](const auto *Node) {
        return Aliases(N, Node);
      }))
    return AliasResult::MayAlias;
  return AliasResult::NoAlias;
}
 
ModRefInfo TypeBasedAAResult::getModRefInfoMask(const MemoryLocation &Loc,
                                                AAQueryInfo &AAQI,
                                                bool IgnoreLocals) {
  if (!shouldUseTBAA())
    return ModRefInfo::ModRef;
 
  const MDNode *M = Loc.AATags.TBAA;
  if (!M)
    return ModRefInfo::ModRef;
 
  // If this is an "immutable" type, we can assume the pointer is pointing
  // to constant memory.
  if (TBAAStructTagNode(M).isTypeImmutable())
    return ModRefInfo::NoModRef;
 
  return ModRefInfo::ModRef;
}
 
MemoryEffects TypeBasedAAResult::getMemoryEffects(const CallBase *Call,
                                                  AAQueryInfo &AAQI) {
  if (!shouldUseTBAA())
    return MemoryEffects::unknown();
 
  // If this is an "immutable" type, the access is not observable.
  if (const MDNode *M = Call->getMetadata(LLVMContext::MD_tbaa))
    if (TBAAStructTagNode(M).isTypeImmutable())
      return MemoryEffects::none();
 
  return MemoryEffects::unknown();
}
 
MemoryEffects TypeBasedAAResult::getMemoryEffects(const Function *F) {
  // Functions don't have metadata.
  return MemoryEffects::unknown();
}
 
ModRefInfo TypeBasedAAResult::getModRefInfo(const CallBase *Call,
                                            const MemoryLocation &Loc,
                                            AAQueryInfo &AAQI) {
  if (!shouldUseTBAA())
    return ModRefInfo::ModRef;
 
  if (const MDNode *L = Loc.AATags.TBAA)
    if (const MDNode *M = Call->getMetadata(LLVMContext::MD_tbaa))
      if (!Aliases(L, M))
        return ModRefInfo::NoModRef;
 
  return ModRefInfo::ModRef;
}
 
ModRefInfo TypeBasedAAResult::getModRefInfo(const CallBase *Call1,
                                            const CallBase *Call2,
                                            AAQueryInfo &AAQI) {
  if (!shouldUseTBAA())
    return ModRefInfo::ModRef;
 
  if (const MDNode *M1 = Call1->getMetadata(LLVMContext::MD_tbaa))
    if (const MDNode *M2 = Call2->getMetadata(LLVMContext::MD_tbaa))
      if (!Aliases(M1, M2))
        return ModRefInfo::NoModRef;
 
  return ModRefInfo::ModRef;
}
 
bool MDNode::isTBAAVtableAccess() const {
  // For struct-path aware TBAA, we use the access type of the tag.
  TBAAStructTagNode Tag(this);
  TBAAStructTypeNode AccessType(Tag.getAccessType());
  if(auto *Id = dyn_cast<MDString>(AccessType.getId()))
    if (Id->getString() == "vtable pointer")
      return true;
  return false;
}
 
static bool matchAccessTags(const MDNode *A, const MDNode *B,
                            const MDNode **GenericTag = nullptr);
 
MDNode *MDNode::getMostGenericTBAA(MDNode *A, MDNode *B) {
  const MDNode *GenericTag;
  matchAccessTags(A, B, &GenericTag);
  return const_cast<MDNode*>(GenericTag);
}
 
static const MDNode *getLeastCommonType(const MDNode *A, const MDNode *B) {
  if (!A || !B)
    return nullptr;
 
  if (A == B)
    return A;
 
  SmallSetVector<const MDNode *, 4> PathA;
  TBAANode TA(A);
  while (TA.getNode()) {
    [[maybe_unused]] bool Inserted = PathA.insert(TA.getNode());
    assert(Inserted && "Cycle found in TBAA metadata.");
    TA = TA.getParent();
  }
 
  SmallSetVector<const MDNode *, 4> PathB;
  TBAANode TB(B);
  while (TB.getNode()) {
    [[maybe_unused]] bool Inserted = PathB.insert(TB.getNode());
    assert(Inserted && "Cycle found in TBAA metadata.");
    TB = TB.getParent();
  }
 
  int IA = PathA.size() - 1;
  int IB = PathB.size() - 1;
 
  const MDNode *Ret = nullptr;
  while (IA >= 0 && IB >= 0) {
    if (PathA[IA] == PathB[IB])
      Ret = PathA[IA];
    else
      break;
    --IA;
    --IB;
  }
 
  return Ret;
}
 
AAMDNodes AAMDNodes::merge(const AAMDNodes &Other) const {
  AAMDNodes Result;
  Result.TBAA = MDNode::getMostGenericTBAA(TBAA, Other.TBAA);
  Result.TBAAStruct = nullptr;
  Result.Scope = MDNode::getMostGenericAliasScope(Scope, Other.Scope);
  Result.NoAlias = MDNode::intersect(NoAlias, Other.NoAlias);
  Result.NoAliasAddrSpace = MDNode::getMostGenericNoaliasAddrspace(
      NoAliasAddrSpace, Other.NoAliasAddrSpace);
  return Result;
}
 
AAMDNodes AAMDNodes::concat(const AAMDNodes &Other) const {
  AAMDNodes Result;
  Result.TBAA = Result.TBAAStruct = nullptr;
  Result.Scope = MDNode::getMostGenericAliasScope(Scope, Other.Scope);
  Result.NoAlias = MDNode::intersect(NoAlias, Other.NoAlias);
  Result.NoAliasAddrSpace = MDNode::getMostGenericNoaliasAddrspace(
      NoAliasAddrSpace, Other.NoAliasAddrSpace);
  return Result;
}
 
static const MDNode *createAccessTag(const MDNode *AccessType) {
  // If there is no access type or the access type is the root node, then
  // we don't have any useful access tag to return.
  if (!AccessType || AccessType->getNumOperands() < 2)
    return nullptr;
 
  Type *Int64 = IntegerType::get(AccessType->getContext(), 64);
  auto *OffsetNode = ConstantAsMetadata::get(ConstantInt::get(Int64, 0));
 
  if (TBAAStructTypeNode(AccessType).isNewFormat()) {
    // TODO: Take access ranges into account when matching access tags and
    // fix this code to generate actual access sizes for generic tags.
    uint64_t AccessSize = UINT64_MAX;
    auto *SizeNode =
        ConstantAsMetadata::get(ConstantInt::get(Int64, AccessSize));
    Metadata *Ops[] = {const_cast<MDNode*>(AccessType),
                       const_cast<MDNode*>(AccessType),
                       OffsetNode, SizeNode};
    return MDNode::get(AccessType->getContext(), Ops);
  }
 
  Metadata *Ops[] = {const_cast<MDNode*>(AccessType),
                     const_cast<MDNode*>(AccessType),
                     OffsetNode};
  return MDNode::get(AccessType->getContext(), Ops);
}
 
static bool hasField(TBAAStructTypeNode BaseType,
                     TBAAStructTypeNode FieldType) {
  for (unsigned I = 0, E = BaseType.getNumFields(); I != E; ++I) {
    TBAAStructTypeNode T = BaseType.getFieldType(I);
    if (T == FieldType || hasField(T, FieldType))
      return true;
  }
  return false;
}
 
/// Return true if for two given accesses, one of the accessed objects may be a
/// subobject of the other. The \p BaseTag and \p SubobjectTag parameters
/// describe the accesses to the base object and the subobject respectively.
/// \p CommonType must be the metadata node describing the common type of the
/// accessed objects. On return, \p MayAlias is set to true iff these accesses
/// may alias and \p Generic, if not null, points to the most generic access
/// tag for the given two.
static bool mayBeAccessToSubobjectOf(TBAAStructTagNode BaseTag,
                                     TBAAStructTagNode SubobjectTag,
                                     const MDNode *CommonType,
                                     const MDNode **GenericTag,
                                     bool &MayAlias) {
  // If the base object is of the least common type, then this may be an access
  // to its subobject.
  if (BaseTag.getAccessType() == BaseTag.getBaseType() &&
      BaseTag.getAccessType() == CommonType) {
    if (GenericTag)
      *GenericTag = createAccessTag(CommonType);
    MayAlias = true;
    return true;
  }
 
  // If the access to the base object is through a field of the subobject's
  // type, then this may be an access to that field. To check for that we start
  // from the base type, follow the edge with the correct offset in the type DAG
  // and adjust the offset until we reach the field type or until we reach the
  // access type.
  bool NewFormat = BaseTag.isNewFormat();
  TBAAStructTypeNode BaseType(BaseTag.getBaseType());
  uint64_t OffsetInBase = BaseTag.getOffset();
 
  for (;;) {
    // In the old format there is no distinction between fields and parent
    // types, so in this case we consider all nodes up to the root.
    if (!BaseType.getNode()) {
      assert(!NewFormat && "Did not see access type in access path!");
      break;
    }
 
    if (BaseType.getNode() == SubobjectTag.getBaseType()) {
      MayAlias = OffsetInBase == SubobjectTag.getOffset() ||
                 BaseType.getNode() == BaseTag.getAccessType() ||
                 SubobjectTag.getBaseType() == SubobjectTag.getAccessType();
      if (GenericTag) {
        if (!MayAlias) {
          *GenericTag = createAccessTag(CommonType);
        } else if (SubobjectTag.isTypeImmutable() &&
                   !BaseTag.isTypeImmutable()) {
          // The generic tag can only be immutable if both accesses are, so
          // drop the flag and keep the rest of the tag.
          const MDNode *Tag = SubobjectTag.getNode();
          unsigned FlagOpNo = SubobjectTag.isNewFormat() ? 4 : 3;
          SmallVector<Metadata *, 4> Ops(Tag->operands().take_front(FlagOpNo));
          *GenericTag = MDNode::get(Tag->getContext(), Ops);
        } else {
          *GenericTag = SubobjectTag.getNode();
        }
      }
      return true;
    }
 
    // With new-format nodes we stop at the access type.
    if (NewFormat && BaseType.getNode() == BaseTag.getAccessType())
      break;
 
    // Follow the edge with the correct offset. Offset will be adjusted to
    // be relative to the field type.
    BaseType = BaseType.getField(OffsetInBase);
  }
 
  // If the base object has a direct or indirect field of the subobject's type,
  // then this may be an access to that field. We need this to check now that
  // we support aggregates as access types.
  if (NewFormat) {
    // TBAAStructTypeNode BaseAccessType(BaseTag.getAccessType());
    TBAAStructTypeNode FieldType(SubobjectTag.getBaseType());
    if (hasField(BaseType, FieldType)) {
      if (GenericTag)
        *GenericTag = createAccessTag(CommonType);
      MayAlias = true;
      return true;
    }
  }
 
  return false;
}
 
/// matchTags - Return true if the given couple of accesses are allowed to
/// overlap. If \arg GenericTag is not null, then on return it points to the
/// most generic access descriptor for the given two.
static bool matchAccessTags(const MDNode *A, const MDNode *B,
                            const MDNode **GenericTag) {
  if (A == B) {
    if (GenericTag)
      *GenericTag = A;
    return true;
  }
 
  // Accesses with no TBAA information may alias with any other accesses.
  if (!A || !B) {
    if (GenericTag)
      *GenericTag = nullptr;
    return true;
  }
 
  TBAAStructTagNode TagA(A), TagB(B);
  const MDNode *CommonType = getLeastCommonType(TagA.getAccessType(),
                                                TagB.getAccessType());
 
  // If the final access types have different roots, they're part of different
  // potentially unrelated type systems, so we must be conservative.
  if (!CommonType) {
    if (GenericTag)
      *GenericTag = nullptr;
    return true;
  }
 
  // If one of the accessed objects may be a subobject of the other, then such
  // accesses may alias.
  bool MayAlias;
  if (mayBeAccessToSubobjectOf(/* BaseTag= */ TagA, /* SubobjectTag= */ TagB,
                               CommonType, GenericTag, MayAlias) ||
      mayBeAccessToSubobjectOf(/* BaseTag= */ TagB, /* SubobjectTag= */ TagA,
                               CommonType, GenericTag, MayAlias))
    return MayAlias;
 
  // Otherwise, we've proved there's no alias.
  if (GenericTag)
    *GenericTag = createAccessTag(CommonType);
  return false;
}
 
/// Aliases - Test whether the access represented by tag A may alias the
/// access represented by tag B.
bool TypeBasedAAResult::Aliases(const MDNode *A, const MDNode *B) const {
  return matchAccessTags(A, B);
}
 
bool TypeBasedAAResult::shouldUseTBAA() const {
  return EnableTBAA && !UsingTypeSanitizer;
}
 
AnalysisKey TypeBasedAA::Key;
 
TypeBasedAAResult TypeBasedAA::run(Function &F, FunctionAnalysisManager &AM) {
  return TypeBasedAAResult(F.hasFnAttribute(Attribute::SanitizeType));
}
 
char TypeBasedAAWrapperPass::ID = 0;
INITIALIZE_PASS(TypeBasedAAWrapperPass, "tbaa", "Type-Based Alias Analysis",
                false, true)
 
ImmutablePass *llvm::createTypeBasedAAWrapperPass() {
  return new TypeBasedAAWrapperPass();
}
 
TypeBasedAAWrapperPass::TypeBasedAAWrapperPass() : ImmutablePass(ID) {}
 
bool TypeBasedAAWrapperPass::doInitialization(Module &M) {
  Result.reset(new TypeBasedAAResult(/*UsingTypeSanitizer=*/false));
  return false;
}
 
bool TypeBasedAAWrapperPass::doFinalization(Module &M) {
  Result.reset();
  return false;
}
 
void TypeBasedAAWrapperPass::getAnalysisUsage(AnalysisUsage &AU) const {
  AU.setPreservesAll();
}
 
MDNode *AAMDNodes::shiftTBAA(MDNode *MD, size_t Offset) {
  // Fast path if there's no offset
  if (Offset == 0)
    return MD;
 
  // The correct behavior here is to add the offset into the TBAA
  // struct node offset. The base type, however may not have defined
  // a type at this additional offset, resulting in errors. Since
  // this method is only used within a given load/store access
  // the offset provided is only used to subdivide the previous load
  // maintaining the validity of the previous TBAA.
  //
  // This, however, should be revisited in the future.
  return MD;
}
 
// Read a !tbaa.struct field entry (an offset or a size) as a 64-bit value.
// Returns std::nullopt if it does not fit in 64 bits.
static std::optional<uint64_t> getTBAAStructFieldAsInt64(const MDOperand &Op) {
  return mdconst::extract<ConstantInt>(Op)->getValue().tryZExtValue();
}
 
static bool isScalarAccessTag(const MDNode *Tag) {
  TBAAStructTagNode T(Tag);
  return T.getAccessType() == T.getBaseType();
}
 
MDNode *AAMDNodes::shiftTBAAStruct(MDNode *MD, size_t Offset) {
  // Fast path if there's no offset
  if (Offset == 0)
    return MD;
  SmallVector<Metadata *, 3> Sub;
  for (size_t i = 0, size = MD->getNumOperands(); i < size; i += 3) {
    ConstantInt *InnerOffset = mdconst::extract<ConstantInt>(MD->getOperand(i));
    ConstantInt *InnerSize =
        mdconst::extract<ConstantInt>(MD->getOperand(i + 1));
    // Don't include any triples that aren't in bounds
    if (InnerOffset->getZExtValue() + InnerSize->getZExtValue() <= Offset)
      continue;
 
    uint64_t NewSize = InnerSize->getZExtValue();
    uint64_t NewOffset = InnerOffset->getZExtValue() - Offset;
    if (InnerOffset->getZExtValue() < Offset) {
      NewOffset = 0;
      NewSize -= Offset - InnerOffset->getZExtValue();
    }
 
    // Shift the offset of the triple
    Sub.push_back(ConstantAsMetadata::get(
        ConstantInt::get(InnerOffset->getType(), NewOffset)));
    Sub.push_back(ConstantAsMetadata::get(
        ConstantInt::get(InnerSize->getType(), NewSize)));
    Sub.push_back(MD->getOperand(i + 2));
  }
  return MDNode::get(MD->getContext(), Sub);
}
 
MDNode *AAMDNodes::extendToTBAA(MDNode *MD, ssize_t Len) {
  // Fast path if 0-length
  if (Len == 0)
    return nullptr;
 
  TBAAStructTagNode Tag(MD);
 
  // Only new format TBAA has a size
  if (!Tag.isNewFormat())
    return MD;
 
  // If unknown size, drop the TBAA.
  if (Len == -1)
    return nullptr;
 
  // Otherwise, create TBAA with the new Len
  ArrayRef<MDOperand> MDOperands = MD->operands();
  SmallVector<Metadata *, 4> NextNodes(MDOperands);
  ConstantInt *PreviousSize = mdconst::extract<ConstantInt>(NextNodes[3]);
 
  // Don't create a new MDNode if it is the same length.
  if (PreviousSize->equalsInt(Len))
    return MD;
 
  NextNodes[3] =
      ConstantAsMetadata::get(ConstantInt::get(PreviousSize->getType(), Len));
  return MDNode::get(MD->getContext(), NextNodes);
}
 
AAMDNodes AAMDNodes::adjustForAccess(unsigned AccessSize) {
  AAMDNodes New = *this;
  MDNode *M = New.TBAAStruct;
 
  // The access may cover several !tbaa.struct fields (e.g. a {int, int} copy
  // widened to an i64 load/store). If those fields share a single tag and tile
  // [0, AccessSize) with no gaps, that tag still describes the whole access.
  New.TBAAStruct = nullptr;
  if (New.TBAA || !M)
    return New;
  MDNode *CommonTag = nullptr;
  uint64_t Offset = 0;
  for (size_t I = 0, E = M->getNumOperands(); I + 2 < E && Offset < AccessSize;
       I += 3) {
    std::optional<uint64_t> FieldOffset =
        getTBAAStructFieldAsInt64(M->getOperand(I));
    std::optional<uint64_t> FieldSize =
        getTBAAStructFieldAsInt64(M->getOperand(I + 1));
    MDNode *FieldTag = dyn_cast_or_null<MDNode>(M->getOperand(I + 2));
    if (!FieldOffset || !FieldSize || !FieldTag ||
        !isScalarAccessTag(FieldTag) || *FieldOffset != Offset ||
        (CommonTag && FieldTag != CommonTag))
      break;
    CommonTag = FieldTag;
    Offset += *FieldSize;
  }
  if (Offset == AccessSize)
    New.TBAA = CommonTag;
  return New;
}
 
AAMDNodes AAMDNodes::adjustForAccess(size_t Offset, Type *AccessTy,
                                     const DataLayout &DL) {
  AAMDNodes New = shift(Offset);
  if (!DL.typeSizeEqualsStoreSize(AccessTy))
    return New;
  TypeSize Size = DL.getTypeStoreSize(AccessTy);
  if (Size.isScalable())
    return New;
 
  return New.adjustForAccess(Size.getKnownMinValue());
}
 
AAMDNodes AAMDNodes::adjustForAccess(size_t Offset, unsigned AccessSize) {
  AAMDNodes New = shift(Offset);
  return New.adjustForAccess(AccessSize);
}