C++ GetElementPtrInst::getNumOperands方法代码示例

/// If the argument is a GEP, then returns the operand identified by
/// getGEPInductionOperand. However, if there is some other non-loop-invariant
/// operand, it returns that instead.
Value *llvm::stripGetElementPtr(Value *Ptr, ScalarEvolution *SE, Loop *Lp) {
  GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(Ptr);
  if (!GEP)
    return Ptr;

  unsigned InductionOperand = getGEPInductionOperand(GEP);

  // Check that all of the gep indices are uniform except for our induction
  // operand.
  for (unsigned i = 0, e = GEP->getNumOperands(); i != e; ++i)
    if (i != InductionOperand &&
        !SE->isLoopInvariant(SE->getSCEV(GEP->getOperand(i)), Lp))
      return Ptr;
  return GEP->getOperand(InductionOperand);
}

// FIXME: Merge with llvm::isConsecutiveAccess
bool Vectorizer::isConsecutiveAccess(Value *A, Value *B) {
  Value *PtrA = getPointerOperand(A);
  Value *PtrB = getPointerOperand(B);
  unsigned ASA = getPointerAddressSpace(A);
  unsigned ASB = getPointerAddressSpace(B);

  // Check that the address spaces match and that the pointers are valid.
  if (!PtrA || !PtrB || (ASA != ASB))
    return false;

  // Make sure that A and B are different pointers of the same size type.
  unsigned PtrBitWidth = DL.getPointerSizeInBits(ASA);
  Type *PtrATy = PtrA->getType()->getPointerElementType();
  Type *PtrBTy = PtrB->getType()->getPointerElementType();
  if (PtrA == PtrB ||
      DL.getTypeStoreSize(PtrATy) != DL.getTypeStoreSize(PtrBTy) ||
      DL.getTypeStoreSize(PtrATy->getScalarType()) !=
          DL.getTypeStoreSize(PtrBTy->getScalarType()))
    return false;

  APInt Size(PtrBitWidth, DL.getTypeStoreSize(PtrATy));

  unsigned IdxWidth = DL.getIndexSizeInBits(ASA);
  APInt OffsetA(IdxWidth, 0), OffsetB(IdxWidth, 0);
  PtrA = PtrA->stripAndAccumulateInBoundsConstantOffsets(DL, OffsetA);
  PtrB = PtrB->stripAndAccumulateInBoundsConstantOffsets(DL, OffsetB);

  APInt OffsetDelta = OffsetB - OffsetA;

  // Check if they are based on the same pointer. That makes the offsets
  // sufficient.
  if (PtrA == PtrB)
    return OffsetDelta == Size;

  // Compute the necessary base pointer delta to have the necessary final delta
  // equal to the size.
  APInt BaseDelta = Size - OffsetDelta;

  // Compute the distance with SCEV between the base pointers.
  const SCEV *PtrSCEVA = SE.getSCEV(PtrA);
  const SCEV *PtrSCEVB = SE.getSCEV(PtrB);
  const SCEV *C = SE.getConstant(BaseDelta);
  const SCEV *X = SE.getAddExpr(PtrSCEVA, C);
  if (X == PtrSCEVB)
    return true;

  // Sometimes even this doesn't work, because SCEV can't always see through
  // patterns that look like (gep (ext (add (shl X, C1), C2))). Try checking
  // things the hard way.

  // Look through GEPs after checking they're the same except for the last
  // index.
  GetElementPtrInst *GEPA = getSourceGEP(A);
  GetElementPtrInst *GEPB = getSourceGEP(B);
  if (!GEPA || !GEPB || GEPA->getNumOperands() != GEPB->getNumOperands())
    return false;
  unsigned FinalIndex = GEPA->getNumOperands() - 1;
  for (unsigned i = 0; i < FinalIndex; i++)
    if (GEPA->getOperand(i) != GEPB->getOperand(i))
      return false;

  Instruction *OpA = dyn_cast<Instruction>(GEPA->getOperand(FinalIndex));
  Instruction *OpB = dyn_cast<Instruction>(GEPB->getOperand(FinalIndex));
  if (!OpA || !OpB || OpA->getOpcode() != OpB->getOpcode() ||
      OpA->getType() != OpB->getType())
    return false;

  // Only look through a ZExt/SExt.
  if (!isa<SExtInst>(OpA) && !isa<ZExtInst>(OpA))
    return false;

  bool Signed = isa<SExtInst>(OpA);

  OpA = dyn_cast<Instruction>(OpA->getOperand(0));
  OpB = dyn_cast<Instruction>(OpB->getOperand(0));
  if (!OpA || !OpB || OpA->getType() != OpB->getType())
    return false;

  // Now we need to prove that adding 1 to OpA won't overflow.
  bool Safe = false;
  // First attempt: if OpB is an add with NSW/NUW, and OpB is 1 added to OpA,
  // we're okay.
  if (OpB->getOpcode() == Instruction::Add &&
      isa<ConstantInt>(OpB->getOperand(1)) &&
      cast<ConstantInt>(OpB->getOperand(1))->getSExtValue() > 0) {
    if (Signed)
      Safe = cast<BinaryOperator>(OpB)->hasNoSignedWrap();
    else
      Safe = cast<BinaryOperator>(OpB)->hasNoUnsignedWrap();
  }

  unsigned BitWidth = OpA->getType()->getScalarSizeInBits();

  // Second attempt:
  // If any bits are known to be zero other than the sign bit in OpA, we can
  // add 1 to it while guaranteeing no overflow of any sort.
  if (!Safe) {
    KnownBits Known(BitWidth);
    computeKnownBits(OpA, Known, DL, 0, nullptr, OpA, &DT);
//.........这里部分代码省略.........

//
// Method: runOnModule()
//
// Description:
//  Entry point for this LLVM pass.
//  Find all GEPs, and simplify them.
//
// Inputs:
//  M - A reference to the LLVM module to transform
//
// Outputs:
//  M - The transformed LLVM module.
//
// Return value:
//  true  - The module was modified.
//  false - The module was not modified.
//
bool SimplifyGEP::runOnModule(Module& M) {
  TD = &getAnalysis<TargetData>();
  preprocess(M);
  for (Module::iterator F = M.begin(); F != M.end(); ++F){
    for (Function::iterator B = F->begin(), FE = F->end(); B != FE; ++B) {      
      for (BasicBlock::iterator I = B->begin(), BE = B->end(); I != BE; I++) {
        if(!(isa<GetElementPtrInst>(I)))
          continue;
        GetElementPtrInst *GEP = cast<GetElementPtrInst>(I);
        Value *PtrOp = GEP->getOperand(0);
        Value *StrippedPtr = PtrOp->stripPointerCasts();
        // Check if the GEP base pointer is enclosed in a cast
        if (StrippedPtr != PtrOp) {
          const PointerType *StrippedPtrTy =cast<PointerType>(StrippedPtr->getType());
          bool HasZeroPointerIndex = false;
          if (ConstantInt *C = dyn_cast<ConstantInt>(GEP->getOperand(1)))
            HasZeroPointerIndex = C->isZero();
          // Transform: GEP (bitcast [10 x i8]* X to [0 x i8]*), i32 0, ...
          // into     : GEP [10 x i8]* X, i32 0, ...
          //
          // Likewise, transform: GEP (bitcast i8* X to [0 x i8]*), i32 0, ...
          //           into     : GEP i8* X, ...
          // 
          // This occurs when the program declares an array extern like "int X[];"
          if (HasZeroPointerIndex) {
            const PointerType *CPTy = cast<PointerType>(PtrOp->getType());
            if (const ArrayType *CATy =
                dyn_cast<ArrayType>(CPTy->getElementType())) {
              // GEP (bitcast i8* X to [0 x i8]*), i32 0, ... ?
              if (CATy->getElementType() == StrippedPtrTy->getElementType()) {
                // -> GEP i8* X, ...
                SmallVector<Value*, 8> Idx(GEP->idx_begin()+1, GEP->idx_end());
                GetElementPtrInst *Res =
                  GetElementPtrInst::Create(StrippedPtr, Idx, GEP->getName(), GEP);
                Res->setIsInBounds(GEP->isInBounds());
                GEP->replaceAllUsesWith(Res);
                continue;
              }

              if (const ArrayType *XATy =
                  dyn_cast<ArrayType>(StrippedPtrTy->getElementType())){
                // GEP (bitcast [10 x i8]* X to [0 x i8]*), i32 0, ... ?
                if (CATy->getElementType() == XATy->getElementType()) {
                  // -> GEP [10 x i8]* X, i32 0, ...
                  // At this point, we know that the cast source type is a pointer
                  // to an array of the same type as the destination pointer
                  // array.  Because the array type is never stepped over (there
                  // is a leading zero) we can fold the cast into this GEP.
                  GEP->setOperand(0, StrippedPtr);
                  continue;
                }
              }
            }   
          } else if (GEP->getNumOperands() == 2) {
            // Transform things like:
            // %t = getelementptr i32* bitcast ([2 x i32]* %str to i32*), i32 %V
            // into:  %t1 = getelementptr [2 x i32]* %str, i32 0, i32 %V; bitcast
            Type *SrcElTy = StrippedPtrTy->getElementType();
            Type *ResElTy=cast<PointerType>(PtrOp->getType())->getElementType();
            if (TD && SrcElTy->isArrayTy() &&
                TD->getTypeAllocSize(cast<ArrayType>(SrcElTy)->getElementType()) ==
                TD->getTypeAllocSize(ResElTy)) {
              Value *Idx[2];
              Idx[0] = Constant::getNullValue(Type::getInt32Ty(GEP->getContext()));
              Idx[1] = GEP->getOperand(1);
              Value *NewGEP = GetElementPtrInst::Create(StrippedPtr, Idx,
                                                        GEP->getName(), GEP);
              // V and GEP are both pointer types --> BitCast
              GEP->replaceAllUsesWith(new BitCastInst(NewGEP, GEP->getType(), GEP->getName(), GEP));
              continue;
            }

            // Transform things like:
            // getelementptr i8* bitcast ([100 x double]* X to i8*), i32 %tmp
            //   (where tmp = 8*tmp2) into:
            // getelementptr [100 x double]* %arr, i32 0, i32 %tmp2; bitcast

            if (TD && SrcElTy->isArrayTy() && ResElTy->isIntegerTy(8)) {
              uint64_t ArrayEltSize =
                TD->getTypeAllocSize(cast<ArrayType>(SrcElTy)->getElementType());

              // Check to see if "tmp" is a scale by a multiple of ArrayEltSize.  We
              // allow either a mul, shift, or constant here.
//.........这里部分代码省略.........

string esp::parseName(Value *value){
  // has existed
  if(names.find(value) != names.end())
    return names[value];

  string name = "";
  Value *current = value;

  /*
  bool continueFlag = true;
  do{
    if(isa<Instruction > (current)){
      Instruction* inst = dyn_cast<Instruction>(current);
      unsigned op = inst->getOpcode();
      switch(op){
      case Instruction::Ret :{
        break;
      }

      case Instruction::Br :{
        break;
      }

      case Instruction::Switch :{
        break;
      }

      case Instruction::Call :{
        CallInst *callinst = (CallInst*) current;

        if (((CallInst*) current)->getCalledFunction() != NULL) {
            name += string("@")+((CallInst*) current)->getCalledFunction()->getNameStr() + "(";
        } else {
            name += string("@[funcPTR](");
            name += ((CallInst*) current)->getCalledValue()->getNameStr();
        }

        for (unsigned i = 1; i < callinst->getNumOperands(); i++) {
            name += esp::parseName(callinst->getOperand(i));
        }

        name += string(")");
        continueFlag = false;
        break;
      }

      case Instruction::PHI :{
        name += string("PHI[");
        name += current->getNameStr();
        PHINode *phi = (PHINode*) current;
        for (unsigned i = 0; i < phi->getNumIncomingValues(); i++) {
            Value *incoming = phi->getIncomingValue(i);
            if (i != 0) name += ",";
            if (!hasLoop(incoming)) {
                if (!incoming->hasName()) {
                    name += esp::parseName(incoming);
                } else {
                    name += incoming->getNameStr();
                }

            }
        }

        name += std::string("]");
        continueFlag = false;
        break;
      }

      case Instruction::Select :{
        break;
      }

      case Instruction::Add :{
        name += "+";
        name += parseBinaryOpName(inst);
        break;
      }

      case Instruction::Sub :{
        name += "-";
        name += parseBinaryOpName(inst);
        break;
      }

      case Instruction::Mul :{
        name += "*";
        name += parseBinaryOpName(inst);
        break;
      }

      case Instruction::UDiv :{
        name += "/";
        name += parseBinaryOpName(inst);
        break;
      }

      case Instruction::SDiv :{
        name += "//";
        name += parseBinaryOpName(inst);
        break;
//.........这里部分代码省略.........

void ArrayObfs::ArrObfuscate ( Function *F )
{

	// Iterate the whole Function
	Function *f = F;
	for ( Function::iterator bb = f->begin(); bb != f->end(); ++bb )
	{
		for ( BasicBlock::iterator inst = bb->begin(); inst != bb->end(); )
		{
			if ( inst->getOpcode() == 29 )		// getelementptr
			{
				//errs() << "INST : " << *inst << "\n";

				GetElementPtrInst *Ary = dyn_cast<GetElementPtrInst>(&*inst);
				Value *ptrVal = Ary->getOperand(0);
				Type *type = ptrVal->getType();

				unsigned numOfOprand = Ary->getNumOperands();
				unsigned lastOprand = numOfOprand - 1;

				// Check Type Array

				if ( PointerType *ptrType = dyn_cast<PointerType>( type ) )
				{
					Type *elementType = ptrType->getElementType();
					if ( elementType->isArrayTy() )
					{
						// Skip if Index is a Variable
						if ( dyn_cast<ConstantInt>( Ary->getOperand( lastOprand ) ) )
						{

				//////////////////////////////////////////////////////////////////////////////

				// Do Real Stuff
				Value *oprand = Ary->getOperand( lastOprand );
				Value *basePtr = Ary->getOperand( 0 );
				APInt offset = dyn_cast<ConstantInt>(oprand)->getValue();
				Value *prevPtr = basePtr;

				// Enter a Loop to Perform Random Obfuscation
				unsigned cnt = 100;

				// Prelog : Clone the Original Inst
				unsigned ObfsIdx =  cryptoutils->get_uint64_t() & 0xffff;
				Value *newOprand = ConstantInt::get( oprand->getType(), ObfsIdx );
				Instruction *gep = inst->clone();
				gep->setOperand( lastOprand, newOprand );
				gep->setOperand( 0, prevPtr );
				gep->insertBefore( inst );
				prevPtr = gep;
				offset = offset - ObfsIdx;

				// Create a Global Variable to Avoid Optimization
				Module *M = f->getParent();
				Constant *initGV = ConstantInt::get( prevPtr->getType(), 0 );
				GlobalVariable *gv = new GlobalVariable( *M, prevPtr->getType(), false, GlobalValue::CommonLinkage, initGV );

				while ( cnt-- )
				{
					// Iteratively Generate Obfuscated Code
					switch( cryptoutils->get_uint64_t() & 7 )
					{
					// Random Indexing Obfuscation
					case 0 :
					case 1 :
					case 2 :
						{
						//errs() << "=> Random Index \n";

						// Create New Instruction
						//   Create Obfuscated New Oprand in ConstantInt Type
						unsigned ObfsIdx =  cryptoutils->get_uint64_t() & 0xffff;
						Value *newOprand = ConstantInt::get( oprand->getType(), ObfsIdx );

						//   Create GetElementPtrInst Instruction
						GetElementPtrInst *gep = GetElementPtrInst::Create( prevPtr, newOprand, "", inst );

						//Set prevPtr
						prevPtr = gep;

						//errs() << "Created : " << *prevPtr << "\n";

						offset = offset - ObfsIdx;
						break;
						}

					// Ptr Dereference
					case 3 :
					case 4 :
						{
						//errs() << "=> Ptr Dereference \n";

						Module *M = f->getParent();
						Value *ONE = ConstantInt::get( Type::getInt32Ty( M->getContext() ), 1 );
						Value *tmp = new AllocaInst( prevPtr->getType(), ONE, "", inst );

						new StoreInst( prevPtr, tmp, inst );

						prevPtr = new LoadInst( tmp, "", inst );

//.........这里部分代码省略.........

Value *llvm::ConvertExpressionToType(Value *V, const Type *Ty, 
                                     ValueMapCache &VMC, const TargetData &TD) {
  if (V->getType() == Ty) return V;  // Already where we need to be?

  ValueMapCache::ExprMapTy::iterator VMCI = VMC.ExprMap.find(V);
  if (VMCI != VMC.ExprMap.end()) {
    const Value *GV = VMCI->second;
    const Type *GTy = VMCI->second->getType();
    assert(VMCI->second->getType() == Ty);

    if (Instruction *I = dyn_cast<Instruction>(V))
      ValueHandle IHandle(VMC, I);  // Remove I if it is unused now!

    return VMCI->second;
  }

  DEBUG(std::cerr << "CETT: " << (void*)V << " " << *V);

  Instruction *I = dyn_cast<Instruction>(V);
  if (I == 0) {
    Constant *CPV = cast<Constant>(V);
    // Constants are converted by constant folding the cast that is required.
    // We assume here that all casts are implemented for constant prop.
    Value *Result = ConstantExpr::getCast(CPV, Ty);
    // Add the instruction to the expression map
    //VMC.ExprMap[V] = Result;
    return Result;
  }


  BasicBlock *BB = I->getParent();
  std::string Name = I->getName();  if (!Name.empty()) I->setName("");
  Instruction *Res;     // Result of conversion

  ValueHandle IHandle(VMC, I);  // Prevent I from being removed!
  
  Constant *Dummy = Constant::getNullValue(Ty);

  switch (I->getOpcode()) {
  case Instruction::Cast:
    assert(VMC.NewCasts.count(ValueHandle(VMC, I)) == 0);
    Res = new CastInst(I->getOperand(0), Ty, Name);
    VMC.NewCasts.insert(ValueHandle(VMC, Res));
    break;
    
  case Instruction::Add:
  case Instruction::Sub:
    Res = BinaryOperator::create(cast<BinaryOperator>(I)->getOpcode(),
                                 Dummy, Dummy, Name);
    VMC.ExprMap[I] = Res;   // Add node to expression eagerly

    Res->setOperand(0, ConvertExpressionToType(I->getOperand(0), Ty, VMC, TD));
    Res->setOperand(1, ConvertExpressionToType(I->getOperand(1), Ty, VMC, TD));
    break;

  case Instruction::Shl:
  case Instruction::Shr:
    Res = new ShiftInst(cast<ShiftInst>(I)->getOpcode(), Dummy,
                        I->getOperand(1), Name);
    VMC.ExprMap[I] = Res;
    Res->setOperand(0, ConvertExpressionToType(I->getOperand(0), Ty, VMC, TD));
    break;

  case Instruction::Load: {
    LoadInst *LI = cast<LoadInst>(I);

    Res = new LoadInst(Constant::getNullValue(PointerType::get(Ty)), Name);
    VMC.ExprMap[I] = Res;
    Res->setOperand(0, ConvertExpressionToType(LI->getPointerOperand(),
                                               PointerType::get(Ty), VMC, TD));
    assert(Res->getOperand(0)->getType() == PointerType::get(Ty));
    assert(Ty == Res->getType());
    assert(Res->getType()->isFirstClassType() && "Load of structure or array!");
    break;
  }

  case Instruction::PHI: {
    PHINode *OldPN = cast<PHINode>(I);
    PHINode *NewPN = new PHINode(Ty, Name);

    VMC.ExprMap[I] = NewPN;   // Add node to expression eagerly
    while (OldPN->getNumOperands()) {
      BasicBlock *BB = OldPN->getIncomingBlock(0);
      Value *OldVal = OldPN->getIncomingValue(0);
      ValueHandle OldValHandle(VMC, OldVal);
      OldPN->removeIncomingValue(BB, false);
      Value *V = ConvertExpressionToType(OldVal, Ty, VMC, TD);
      NewPN->addIncoming(V, BB);
    }
    Res = NewPN;
    break;
  }

  case Instruction::Malloc: {
    Res = ConvertMallocToType(cast<MallocInst>(I), Ty, Name, VMC, TD);
    break;
  }

  case Instruction::GetElementPtr: {
    // GetElementPtr's are directly convertible to a pointer type if they have
//.........这里部分代码省略.........

//.........这里部分代码省略.........
    //   %t1 = getelementptr %Hosp * %hosp, ubyte 4, ubyte 0  ; <%List **>
    //   %t2 = cast %List * * %t1 to %List *
    // into
    //   %t2 = getelementptr %Hosp * %hosp, ubyte 4           ; <%List *>
    // 
    GetElementPtrInst *GEP = cast<GetElementPtrInst>(I);
    const PointerType *PTy = dyn_cast<PointerType>(Ty);
    if (!PTy) return false;  // GEP must always return a pointer...
    const Type *PVTy = PTy->getElementType();

    // Check to see if there are zero elements that we can remove from the
    // index array.  If there are, check to see if removing them causes us to
    // get to the right type...
    //
    std::vector<Value*> Indices(GEP->idx_begin(), GEP->idx_end());
    const Type *BaseType = GEP->getPointerOperand()->getType();
    const Type *ElTy = 0;

    while (!Indices.empty() &&
           Indices.back() == Constant::getNullValue(Indices.back()->getType())){
      Indices.pop_back();
      ElTy = GetElementPtrInst::getIndexedType(BaseType, Indices, true);
      if (ElTy == PVTy)
        break;  // Found a match!!
      ElTy = 0;
    }

    if (ElTy) break;   // Found a number of zeros we can strip off!

    // Otherwise, we can convert a GEP from one form to the other iff the
    // current gep is of the form 'getelementptr sbyte*, long N
    // and we could convert this to an appropriate GEP for the new type.
    //
    if (GEP->getNumOperands() == 2 &&
        GEP->getType() == PointerType::get(Type::SByteTy)) {

      // Do not Check to see if our incoming pointer can be converted
      // to be a ptr to an array of the right type... because in more cases than
      // not, it is simply not analyzable because of pointer/array
      // discrepancies.  To fix this, we will insert a cast before the GEP.
      //

      // Check to see if 'N' is an expression that can be converted to
      // the appropriate size... if so, allow it.
      //
      std::vector<Value*> Indices;
      const Type *ElTy = ConvertibleToGEP(PTy, I->getOperand(1), Indices, TD);
      if (ElTy == PVTy) {
        if (!ExpressionConvertibleToType(I->getOperand(0),
                                         PointerType::get(ElTy), CTMap, TD))
          return false;  // Can't continue, ExConToTy might have polluted set!
        break;
      }
    }

    // Otherwise, it could be that we have something like this:
    //     getelementptr [[sbyte] *] * %reg115, long %reg138    ; [sbyte]**
    // and want to convert it into something like this:
    //     getelemenptr [[int] *] * %reg115, long %reg138      ; [int]**
    //
    if (GEP->getNumOperands() == 2 && 
        PTy->getElementType()->isSized() &&
        TD.getTypeSize(PTy->getElementType()) == 
        TD.getTypeSize(GEP->getType()->getElementType())) {
      const PointerType *NewSrcTy = PointerType::get(PVTy);
      if (!ExpressionConvertibleToType(I->getOperand(0), NewSrcTy, CTMap, TD))