[asan] Removed unused cast in the IR by moving AddrLong init after optimized callback section.

[kstoimenov]

Update after rebase.

[vitalybuka]

llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp

1781

no tests needs to be updated?

[vitalybuka]

llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp

1780

ClOptimizeCallbacks does not exist in the HEAD,
I guess some parent patches are missing

[kstoimenov]

llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp

1780

D'oh! I have to push the flag patch first of course.

1781

I stated working on tests in the parent patch an this is how I found this inefficiency. I will them accordingly.

[kstoimenov]

Decided to merge that with the previous change.

llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp

AddressSanitizer(Module &M, const GlobalsMetadata *GlobalsMD,
         Recover(ClRecover.getNumOccurrences() > 0 ? ClRecover : Recover),
         UseAfterScope(UseAfterScope || ClUseAfterScope),
         UseAfterReturn(ClUseAfterReturn.getNumOccurrences() ? ClUseAfterReturn
                                                             : UseAfterReturn),
         GlobalsMD(*GlobalsMD) {
     C = &(M.getContext());
     LongSize = M.getDataLayout().getPointerSizeInBits();
     IntptrTy = Type::getIntNTy(*C, LongSize);
+    Int8PtrTy = Type::getInt8PtrTy(*C);
+    Int32Ty = Type::getInt32Ty(*C);
     TargetTriple = Triple(M.getTargetTriple());
 
     Mapping = getShadowMapping(TargetTriple, LongSize, this->CompileKernel);
 
     assert(this->UseAfterReturn != AsanDetectStackUseAfterReturnMode::Invalid);
   }
 
   uint64_t getAllocaSizeInBytes(const AllocaInst &AI) const {
private:
   LLVMContext *C;
   Triple TargetTriple;
   int LongSize;
   bool CompileKernel;
   bool Recover;
   bool UseAfterScope;
   AsanDetectStackUseAfterReturnMode UseAfterReturn;
   Type *IntptrTy;
+  Type *Int8PtrTy;
+  Type *Int32Ty;
   ShadowMapping Mapping;
   FunctionCallee AsanHandleNoReturnFunc;
   FunctionCallee AsanPtrCmpFunction, AsanPtrSubFunction;
   Constant *AsanShadowGlobal;
 
   // These arrays is indexed by AccessIsWrite, Experiment and log2(AccessSize).
   FunctionCallee AsanErrorCallback[2][2][kNumberOfAccessSizes];
   FunctionCallee AsanMemoryAccessCallback[2][2][kNumberOfAccessSizes];
void AddressSanitizer::instrumentAddress(Instruction *OrigIns,
   if (TargetTriple.isAMDGPU()) {
     InsertBefore = instrumentAMDGPUAddress(OrigIns, InsertBefore, Addr,
                                            TypeSize, IsWrite, SizeArgument);
     if (!InsertBefore)
       return;
   }
 
   IRBuilder<> IRB(InsertBefore);
-  Value *AddrLong = IRB.CreatePointerCast(Addr, IntptrTy);
   size_t AccessSizeIndex = TypeSizeToSizeIndex(TypeSize);
   const ASanAccessInfo AccessInfo(IsWrite, CompileKernel, AccessSizeIndex);
 
+  if (UseCalls && ClOptimizeCallbacks) {
+    const ASanAccessInfo AccessInfo(IsWrite, CompileKernel, AccessSizeIndex);
+    Module *M = IRB.GetInsertBlock()->getParent()->getParent();
+    IRB.CreateCall(
+        Intrinsic::getDeclaration(M, Intrinsic::asan_check_memaccess),
+        {IRB.CreatePointerCast(Addr, Int8PtrTy),
+         ConstantInt::get(Int32Ty, AccessInfo.Packed)});
+    return;
+  }
+
+  Value *AddrLong = IRB.CreatePointerCast(Addr, IntptrTy);
   if (UseCalls) {
     if (ClOptimizeCallbacks) {
       Value *Ptr8 = IRB.CreatePointerCast(Addr, Int8PtrTy);
       Module *M = IRB.GetInsertBlock()->getParent()->getParent();
       IRB.CreateCall(
           Intrinsic::getDeclaration(M, Intrinsic::asan_check_memaccess),
           {Ptr8, ConstantInt::get(IRB.getInt32Ty(), AccessInfo.Packed)});
     } else {