Index: lib/CodeGen/CGAtomic.cpp
===================================================================
--- lib/CodeGen/CGAtomic.cpp
+++ lib/CodeGen/CGAtomic.cpp
@@ -1160,7 +1160,7 @@
     if (UseOptimizedLibcall && Res.getScalarVal()) {
       llvm::Value *ResVal = Res.getScalarVal();
       if (PostOp) {
-        llvm::Value *LoadVal1 = Args[1].RV.getScalarVal();
+        llvm::Value *LoadVal1 = Args[1].getRValue(*this).getScalarVal();
         ResVal = Builder.CreateBinOp(PostOp, ResVal, LoadVal1);
       }
       if (E->getOp() == AtomicExpr::AO__atomic_nand_fetch)
Index: lib/CodeGen/CGCall.h
===================================================================
--- lib/CodeGen/CGCall.h
+++ lib/CodeGen/CGCall.h
@@ -213,12 +213,41 @@
   };
 
   struct CallArg {
-    RValue RV;
+  private:
+    union {
+      RValue RV;
+      LValue LV; /// The l-value from which the argument is derived.
+    };
+    bool HasLV;
+
+  public:
     QualType Ty;
-    bool NeedsCopy;
-    CallArg(RValue rv, QualType ty, bool needscopy)
-    : RV(rv), Ty(ty), NeedsCopy(needscopy)
-    { }
+    CallArg(RValue rv, QualType ty) : RV(rv), HasLV(false), Ty(ty) {}
+    CallArg(LValue _LV, QualType ty) : LV(_LV), HasLV(true), Ty(ty) {}
+    bool hasLValue() const { return HasLV; }
+    QualType getType() const { return Ty; }
+
+    /// \returns an independent RValue. If the CallArg contains an LValue,
+    /// a temporary copy is returned.
+    RValue getRValue(CodeGenFunction &CGF) const;
+
+    LValue getLValue() const {
+      assert(HasLV);
+      return LV;
+    }
+    void setRValue(RValue _RV) {
+      assert(!HasLV);
+      RV = _RV;
+    }
+
+    bool isAggregate() const { return HasLV || RV.isAggregate(); }
+
+    Address getAggregateAddress() const {
+      assert(isAggregate());
+      return HasLV ? LV.getAddress() : RV.getAggregateAddress();
+    }
+
+    void copyInto(CodeGenFunction &CGF, Address A) const;
   };
 
   /// CallArgList - Type for representing both the value and type of
@@ -248,8 +277,10 @@
       llvm::Instruction *IsActiveIP;
     };
 
-    void add(RValue rvalue, QualType type, bool needscopy = false) {
-      push_back(CallArg(rvalue, type, needscopy));
+    void add(RValue rvalue, QualType type) { push_back(CallArg(rvalue, type)); }
+
+    void addUncopiedAggregate(LValue LV, QualType type) {
+      push_back(CallArg(LV, type));
     }
 
     /// Add all the arguments from another CallArgList to this one. After doing
Index: lib/CodeGen/CGCall.cpp
===================================================================
--- lib/CodeGen/CGCall.cpp
+++ lib/CodeGen/CGCall.cpp
@@ -1040,42 +1040,47 @@
 }
 
 void CodeGenFunction::ExpandTypeToArgs(
-    QualType Ty, RValue RV, llvm::FunctionType *IRFuncTy,
+    QualType Ty, CallArg Arg, llvm::FunctionType *IRFuncTy,
     SmallVectorImpl<llvm::Value *> &IRCallArgs, unsigned &IRCallArgPos) {
   auto Exp = getTypeExpansion(Ty, getContext());
   if (auto CAExp = dyn_cast<ConstantArrayExpansion>(Exp.get())) {
-    forConstantArrayExpansion(*this, CAExp, RV.getAggregateAddress(),
-                              [&](Address EltAddr) {
-      RValue EltRV =
-          convertTempToRValue(EltAddr, CAExp->EltTy, SourceLocation());
-      ExpandTypeToArgs(CAExp->EltTy, EltRV, IRFuncTy, IRCallArgs, IRCallArgPos);
-    });
+    forConstantArrayExpansion(
+        *this, CAExp, Arg.getAggregateAddress(), [&](Address EltAddr) {
+          CallArg EltArg = CallArg(
+              convertTempToRValue(EltAddr, CAExp->EltTy, SourceLocation()),
+              CAExp->EltTy);
+          ExpandTypeToArgs(CAExp->EltTy, EltArg, IRFuncTy, IRCallArgs,
+                           IRCallArgPos);
+        });
   } else if (auto RExp = dyn_cast<RecordExpansion>(Exp.get())) {
-    Address This = RV.getAggregateAddress();
+    Address This = Arg.getAggregateAddress();
     for (const CXXBaseSpecifier *BS : RExp->Bases) {
       // Perform a single step derived-to-base conversion.
       Address Base =
           GetAddressOfBaseClass(This, Ty->getAsCXXRecordDecl(), &BS, &BS + 1,
                                 /*NullCheckValue=*/false, SourceLocation());
-      RValue BaseRV = RValue::getAggregate(Base);
+      CallArg BaseArg = CallArg(RValue::getAggregate(Base), BS->getType());
 
       // Recurse onto bases.
-      ExpandTypeToArgs(BS->getType(), BaseRV, IRFuncTy, IRCallArgs,
+      ExpandTypeToArgs(BS->getType(), BaseArg, IRFuncTy, IRCallArgs,
                        IRCallArgPos);
     }
 
     LValue LV = MakeAddrLValue(This, Ty);
     for (auto FD : RExp->Fields) {
-      RValue FldRV = EmitRValueForField(LV, FD, SourceLocation());
-      ExpandTypeToArgs(FD->getType(), FldRV, IRFuncTy, IRCallArgs,
+      CallArg FldArg =
+          CallArg(EmitRValueForField(LV, FD, SourceLocation()), FD->getType());
+      ExpandTypeToArgs(FD->getType(), FldArg, IRFuncTy, IRCallArgs,
                        IRCallArgPos);
     }
   } else if (isa<ComplexExpansion>(Exp.get())) {
-    ComplexPairTy CV = RV.getComplexVal();
+    ComplexPairTy CV = Arg.getRValue(*this).getComplexVal();
     IRCallArgs[IRCallArgPos++] = CV.first;
     IRCallArgs[IRCallArgPos++] = CV.second;
   } else {
     assert(isa<NoExpansion>(Exp.get()));
+    assert(!Arg.hasLValue());
+    auto RV = Arg.getRValue(*this);
     assert(RV.isScalar() &&
            "Unexpected non-scalar rvalue during struct expansion.");
 
@@ -3417,13 +3422,15 @@
     assert(InitialArgSize + 1 == Args.size() &&
            "The code below depends on only adding one arg per EmitCallArg");
     (void)InitialArgSize;
-    RValue RVArg = Args.back().RV;
-    EmitNonNullArgCheck(RVArg, ArgTypes[Idx], (*Arg)->getExprLoc(), AC,
-                        ParamsToSkip + Idx);
-    // @llvm.objectsize should never have side-effects and shouldn't need
-    // destruction/cleanups, so we can safely "emit" it after its arg,
-    // regardless of right-to-leftness
-    MaybeEmitImplicitObjectSize(Idx, *Arg, RVArg);
+    if (!Args.back().hasLValue()) {
+      RValue RVArg = Args.back().getRValue(*this);
+      EmitNonNullArgCheck(RVArg, ArgTypes[Idx], (*Arg)->getExprLoc(), AC,
+                          ParamsToSkip + Idx);
+      // @llvm.objectsize should never have side-effects and shouldn't need
+      // destruction/cleanups, so we can safely "emit" it after its arg,
+      // regardless of right-to-leftness
+      MaybeEmitImplicitObjectSize(Idx, *Arg, RVArg);
+    }
   }
 
   if (!LeftToRight) {
@@ -3470,6 +3477,28 @@
 
 } // end anonymous namespace
 
+RValue CallArg::getRValue(CodeGenFunction &CGF) const {
+  if (!HasLV)
+    return RV;
+  LValue Copy = CGF.MakeAddrLValue(CGF.CreateMemTemp(Ty), Ty);
+  CGF.EmitAggregateCopy(Copy, LV, Ty, LV.isVolatile());
+  return RValue::getAggregate(Copy.getAddress());
+}
+
+void CallArg::copyInto(CodeGenFunction &CGF, Address Addr) const {
+  LValue Dst = CGF.MakeAddrLValue(Addr, Ty);
+  if (!HasLV && RV.isScalar())
+    CGF.EmitStoreOfScalar(RV.getScalarVal(), Dst, /*init=*/true);
+  else if (!HasLV && RV.isComplex())
+    CGF.EmitStoreOfComplex(RV.getComplexVal(), Dst, /*init=*/true);
+  else {
+    LValue SrcLV = CGF.MakeAddrLValue(getAggregateAddress(), Ty);
+    CGF.EmitAggregateCopy(Dst, SrcLV, Ty,
+                          HasLV ? LV.isVolatileQualified()
+                                : RV.isVolatileQualified());
+  }
+}
+
 void CodeGenFunction::EmitCallArg(CallArgList &args, const Expr *E,
                                   QualType type) {
   DisableDebugLocationUpdates Dis(*this, E);
@@ -3535,15 +3564,7 @@
       cast<CastExpr>(E)->getCastKind() == CK_LValueToRValue) {
     LValue L = EmitLValue(cast<CastExpr>(E)->getSubExpr());
     assert(L.isSimple());
-    if (L.getAlignment() >= getContext().getTypeAlignInChars(type)) {
-      args.add(L.asAggregateRValue(), type, /*NeedsCopy*/true);
-    } else {
-      // We can't represent a misaligned lvalue in the CallArgList, so copy
-      // to an aligned temporary now.
-      LValue Dest = MakeAddrLValue(CreateMemTemp(type), type);
-      EmitAggregateCopy(Dest, L, type, L.isVolatile());
-      args.add(RValue::getAggregate(Dest.getAddress()), type);
-    }
+    args.addUncopiedAggregate(L, type);
     return;
   }
 
@@ -3701,16 +3722,6 @@
   return llvm::CallSite(Inst);
 }
 
-/// \brief Store a non-aggregate value to an address to initialize it.  For
-/// initialization, a non-atomic store will be used.
-static void EmitInitStoreOfNonAggregate(CodeGenFunction &CGF, RValue Src,
-                                        LValue Dst) {
-  if (Src.isScalar())
-    CGF.EmitStoreOfScalar(Src.getScalarVal(), Dst, /*init=*/true);
-  else
-    CGF.EmitStoreOfComplex(Src.getComplexVal(), Dst, /*init=*/true);
-}
-
 void CodeGenFunction::deferPlaceholderReplacement(llvm::Instruction *Old,
                                                   llvm::Value *New) {
   DeferredReplacements.push_back(std::make_pair(Old, New));
@@ -3803,7 +3814,6 @@
   for (CallArgList::const_iterator I = CallArgs.begin(), E = CallArgs.end();
        I != E; ++I, ++info_it, ++ArgNo) {
     const ABIArgInfo &ArgInfo = info_it->info;
-    RValue RV = I->RV;
 
     // Insert a padding argument to ensure proper alignment.
     if (IRFunctionArgs.hasPaddingArg(ArgNo))
@@ -3817,10 +3827,10 @@
     case ABIArgInfo::InAlloca: {
       assert(NumIRArgs == 0);
       assert(getTarget().getTriple().getArch() == llvm::Triple::x86);
-      if (RV.isAggregate()) {
+      if (I->isAggregate()) {
         // Replace the placeholder with the appropriate argument slot GEP.
         llvm::Instruction *Placeholder =
-            cast<llvm::Instruction>(RV.getAggregatePointer());
+            cast<llvm::Instruction>(I->getAggregateAddress().getPointer());
         CGBuilderTy::InsertPoint IP = Builder.saveIP();
         Builder.SetInsertPoint(Placeholder);
         Address Addr = createInAllocaStructGEP(ArgInfo.getInAllocaFieldIndex());
@@ -3836,22 +3846,20 @@
         // from {}* to (%struct.foo*)*.
         if (Addr.getType() != MemType)
           Addr = Builder.CreateBitCast(Addr, MemType);
-        LValue argLV = MakeAddrLValue(Addr, I->Ty);
-        EmitInitStoreOfNonAggregate(*this, RV, argLV);
+        I->copyInto(*this, Addr);
       }
       break;
     }
 
     case ABIArgInfo::Indirect: {
       assert(NumIRArgs == 1);
-      if (RV.isScalar() || RV.isComplex()) {
+      if (!I->isAggregate()) {
         // Make a temporary alloca to pass the argument.
         Address Addr = CreateMemTemp(I->Ty, ArgInfo.getIndirectAlign(),
                                      "indirect-arg-temp", false);
         IRCallArgs[FirstIRArg] = Addr.getPointer();
 
-        LValue argLV = MakeAddrLValue(Addr, I->Ty);
-        EmitInitStoreOfNonAggregate(*this, RV, argLV);
+        I->copyInto(*this, Addr);
       } else {
         // We want to avoid creating an unnecessary temporary+copy here;
         // however, we need one in three cases:
@@ -3859,32 +3867,49 @@
         //    source.  (This case doesn't occur on any common architecture.)
         // 2. If the argument is byval, RV is not sufficiently aligned, and
         //    we cannot force it to be sufficiently aligned.
-        // 3. If the argument is byval, but RV is located in an address space
-        //    different than that of the argument (0).
-        Address Addr = RV.getAggregateAddress();
+        // 3. If the argument is byval, but RV is not located in default
+        //    or alloca address space.
+        Address Addr = I->getAggregateAddress();
+        llvm::Value *V = Addr.getPointer();
         CharUnits Align = ArgInfo.getIndirectAlign();
         const llvm::DataLayout *TD = &CGM.getDataLayout();
-        const unsigned RVAddrSpace = Addr.getType()->getAddressSpace();
-        const unsigned ArgAddrSpace =
-            (FirstIRArg < IRFuncTy->getNumParams()
-                 ? IRFuncTy->getParamType(FirstIRArg)->getPointerAddressSpace()
-                 : 0);
-        if ((!ArgInfo.getIndirectByVal() && I->NeedsCopy) ||
-            (ArgInfo.getIndirectByVal() && Addr.getAlignment() < Align &&
-             llvm::getOrEnforceKnownAlignment(Addr.getPointer(),
-                                              Align.getQuantity(), *TD)
-               < Align.getQuantity()) ||
-            (ArgInfo.getIndirectByVal() && (RVAddrSpace != ArgAddrSpace))) {
+
+        assert((FirstIRArg >= IRFuncTy->getNumParams() ||
+                IRFuncTy->getParamType(FirstIRArg)->getPointerAddressSpace() ==
+                    TD->getAllocaAddrSpace()) &&
+               "indirect argument must be in alloca address space");
+
+        bool NeedCopy = false;
+
+        if (Addr.getAlignment() < Align &&
+            llvm::getOrEnforceKnownAlignment(V, Align.getQuantity(), *TD) <
+                Align.getQuantity()) {
+          NeedCopy = true;
+        } else if (I->hasLValue()) {
+          auto LV = I->getLValue();
+          auto AS = LV.getAddressSpace();
+          if ((!ArgInfo.getIndirectByVal() &&
+               (LV.getAlignment() >=
+                getContext().getTypeAlignInChars(I->Ty))) ||
+              (ArgInfo.getIndirectByVal() &&
+               ((AS != LangAS::Default && AS != LangAS::opencl_private &&
+                 AS != CGM.getASTAllocaAddressSpace())))) {
+            NeedCopy = true;
+          }
+        }
+        if (NeedCopy) {
           // Create an aligned temporary, and copy to it.
           Address AI = CreateMemTemp(I->Ty, ArgInfo.getIndirectAlign(),
                                      "byval-temp", false);
           IRCallArgs[FirstIRArg] = AI.getPointer();
-          LValue Dest = MakeAddrLValue(AI, I->Ty);
-          LValue Src = MakeAddrLValue(Addr, I->Ty);
-          EmitAggregateCopy(Dest, Src, I->Ty, RV.isVolatileQualified());
+          I->copyInto(*this, AI);
         } else {
           // Skip the extra memcpy call.
-          IRCallArgs[FirstIRArg] = Addr.getPointer();
+          auto *T = V->getType()->getPointerElementType()->getPointerTo(
+              CGM.getDataLayout().getAllocaAddrSpace());
+          IRCallArgs[FirstIRArg] = getTargetHooks().performAddrSpaceCast(
+              *this, V, LangAS::Default, CGM.getASTAllocaAddressSpace(), T,
+              true);
         }
       }
       break;
@@ -3901,10 +3926,10 @@
           ArgInfo.getDirectOffset() == 0) {
         assert(NumIRArgs == 1);
         llvm::Value *V;
-        if (RV.isScalar())
-          V = RV.getScalarVal();
+        if (!I->isAggregate())
+          V = I->getRValue(*this).getScalarVal();
         else
-          V = Builder.CreateLoad(RV.getAggregateAddress());
+          V = Builder.CreateLoad(I->getAggregateAddress());
 
         // Implement swifterror by copying into a new swifterror argument.
         // We'll write back in the normal path out of the call.
@@ -3942,12 +3967,11 @@
 
       // FIXME: Avoid the conversion through memory if possible.
       Address Src = Address::invalid();
-      if (RV.isScalar() || RV.isComplex()) {
+      if (!I->isAggregate()) {
         Src = CreateMemTemp(I->Ty, "coerce");
-        LValue SrcLV = MakeAddrLValue(Src, I->Ty);
-        EmitInitStoreOfNonAggregate(*this, RV, SrcLV);
+        I->copyInto(*this, Src);
       } else {
-        Src = RV.getAggregateAddress();
+        Src = I->getAggregateAddress();
       }
 
       // If the value is offset in memory, apply the offset now.
@@ -4001,9 +4025,10 @@
 
       llvm::Value *tempSize = nullptr;
       Address addr = Address::invalid();
-      if (RV.isAggregate()) {
-        addr = RV.getAggregateAddress();
+      if (I->isAggregate()) {
+        addr = I->getAggregateAddress();
       } else {
+        RValue RV = I->getRValue(*this);
         assert(RV.isScalar()); // complex should always just be direct
 
         llvm::Type *scalarType = RV.getScalarVal()->getType();
@@ -4042,7 +4067,7 @@
 
     case ABIArgInfo::Expand:
       unsigned IRArgPos = FirstIRArg;
-      ExpandTypeToArgs(I->Ty, RV, IRFuncTy, IRCallArgs, IRArgPos);
+      ExpandTypeToArgs(I->Ty, *I, IRFuncTy, IRCallArgs, IRArgPos);
       assert(IRArgPos == FirstIRArg + NumIRArgs);
       break;
     }
@@ -4393,8 +4418,9 @@
       EmitAlignmentAssumption(Ret.getScalarVal(), AlignmentCI->getZExtValue(),
                               OffsetValue);
     } else if (const auto *AA = TargetDecl->getAttr<AllocAlignAttr>()) {
-      llvm::Value *ParamVal =
-          CallArgs[AA->paramIndex().getLLVMIndex()].RV.getScalarVal();
+      llvm::Value *ParamVal = CallArgs[AA->paramIndex().getLLVMIndex()]
+                                  .getRValue(*this)
+                                  .getScalarVal();
       EmitAlignmentAssumption(Ret.getScalarVal(), ParamVal);
     }
   }
Index: lib/CodeGen/CGClass.cpp
===================================================================
--- lib/CodeGen/CGClass.cpp
+++ lib/CodeGen/CGClass.cpp
@@ -2077,7 +2077,8 @@
     assert(Args.size() == 2 && "unexpected argcount for trivial ctor");
 
     QualType SrcTy = D->getParamDecl(0)->getType().getNonReferenceType();
-    Address Src(Args[1].RV.getScalarVal(), getNaturalTypeAlignment(SrcTy));
+    Address Src(Args[1].getRValue(*this).getScalarVal(),
+                getNaturalTypeAlignment(SrcTy));
     LValue SrcLVal = MakeAddrLValue(Src, SrcTy);
     QualType DestTy = getContext().getTypeDeclType(ClassDecl);
     LValue DestLVal = MakeAddrLValue(This, DestTy);
@@ -2131,8 +2132,7 @@
     const CXXConstructorDecl *D, bool ForVirtualBase, Address This,
     bool InheritedFromVBase, const CXXInheritedCtorInitExpr *E) {
   CallArgList Args;
-  CallArg ThisArg(RValue::get(This.getPointer()), D->getThisType(getContext()),
-                  /*NeedsCopy=*/false);
+  CallArg ThisArg(RValue::get(This.getPointer()), D->getThisType(getContext()));
 
   // Forward the parameters.
   if (InheritedFromVBase &&
@@ -2196,7 +2196,7 @@
   assert(Args.size() >= Params.size() && "too few arguments for call");
   for (unsigned I = 0, N = Args.size(); I != N; ++I) {
     if (I < Params.size() && isa<ImplicitParamDecl>(Params[I])) {
-      const RValue &RV = Args[I].RV;
+      const RValue &RV = Args[I].getRValue(*this);
       assert(!RV.isComplex() && "complex indirect params not supported");
       ParamValue Val = RV.isScalar()
                            ? ParamValue::forDirect(RV.getScalarVal())
Index: lib/CodeGen/CGDecl.cpp
===================================================================
--- lib/CodeGen/CGDecl.cpp
+++ lib/CodeGen/CGDecl.cpp
@@ -1882,6 +1882,22 @@
     llvm::Type *IRTy = ConvertTypeForMem(Ty)->getPointerTo(AS);
     if (DeclPtr.getType() != IRTy)
       DeclPtr = Builder.CreateBitCast(DeclPtr, IRTy, D.getName());
+    // Indirect argument is in alloca address space, which may be different
+    // from the default address space.
+    auto AllocaAS = CGM.getASTAllocaAddressSpace();
+    auto *V = DeclPtr.getPointer();
+    auto SrcLangAS = getLangOpts().OpenCL ? LangAS::opencl_private : AllocaAS;
+    auto DestLangAS =
+        getLangOpts().OpenCL ? LangAS::opencl_private : LangAS::Default;
+    if (SrcLangAS != DestLangAS) {
+      assert(getContext().getTargetAddressSpace(SrcLangAS) ==
+             CGM.getDataLayout().getAllocaAddrSpace());
+      auto DestAS = getContext().getTargetAddressSpace(DestLangAS);
+      auto *T = V->getType()->getPointerElementType()->getPointerTo(DestAS);
+      DeclPtr = Address(getTargetHooks().performAddrSpaceCast(
+                            *this, V, SrcLangAS, DestLangAS, T, true),
+                        DeclPtr.getAlignment());
+    }
 
     // Push a destructor cleanup for this parameter if the ABI requires it.
     // Don't push a cleanup in a thunk for a method that will also emit a
Index: lib/CodeGen/CGExprCXX.cpp
===================================================================
--- lib/CodeGen/CGExprCXX.cpp
+++ lib/CodeGen/CGExprCXX.cpp
@@ -265,7 +265,7 @@
         // when it isn't necessary; just produce the proper effect here.
         LValue RHS = isa<CXXOperatorCallExpr>(CE)
                          ? MakeNaturalAlignAddrLValue(
-                               (*RtlArgs)[0].RV.getScalarVal(),
+                               (*RtlArgs)[0].getRValue(*this).getScalarVal(),
                                (*(CE->arg_begin() + 1))->getType())
                          : EmitLValue(*CE->arg_begin());
         EmitAggregateAssign(This, RHS, CE->getType());
@@ -1490,7 +1490,7 @@
                                            AllocAlign);
     for (unsigned I = 0, N = E->getNumPlacementArgs(); I != N; ++I) {
       auto &Arg = NewArgs[I + NumNonPlacementArgs];
-      Cleanup->setPlacementArg(I, Arg.RV, Arg.Ty);
+      Cleanup->setPlacementArg(I, Arg.getRValue(CGF), Arg.Ty);
     }
 
     return;
@@ -1521,8 +1521,8 @@
                                               AllocAlign);
   for (unsigned I = 0, N = E->getNumPlacementArgs(); I != N; ++I) {
     auto &Arg = NewArgs[I + NumNonPlacementArgs];
-    Cleanup->setPlacementArg(I, DominatingValue<RValue>::save(CGF, Arg.RV),
-                             Arg.Ty);
+    Cleanup->setPlacementArg(
+        I, DominatingValue<RValue>::save(CGF, Arg.getRValue(CGF)), Arg.Ty);
   }
 
   CGF.initFullExprCleanup();
Index: lib/CodeGen/CGGPUBuiltin.cpp
===================================================================
--- lib/CodeGen/CGGPUBuiltin.cpp
+++ lib/CodeGen/CGGPUBuiltin.cpp
@@ -83,8 +83,9 @@
                /* ParamsToSkip = */ 0);
 
   // We don't know how to emit non-scalar varargs.
-  if (std::any_of(Args.begin() + 1, Args.end(),
-                  [](const CallArg &A) { return !A.RV.isScalar(); })) {
+  if (std::any_of(Args.begin() + 1, Args.end(), [&](const CallArg &A) {
+        return !A.getRValue(*this).isScalar();
+      })) {
     CGM.ErrorUnsupported(E, "non-scalar arg to printf");
     return RValue::get(llvm::ConstantInt::get(IntTy, 0));
   }
@@ -97,7 +98,7 @@
   } else {
     llvm::SmallVector<llvm::Type *, 8> ArgTypes;
     for (unsigned I = 1, NumArgs = Args.size(); I < NumArgs; ++I)
-      ArgTypes.push_back(Args[I].RV.getScalarVal()->getType());
+      ArgTypes.push_back(Args[I].getRValue(*this).getScalarVal()->getType());
 
     // Using llvm::StructType is correct only because printf doesn't accept
     // aggregates.  If we had to handle aggregates here, we'd have to manually
@@ -109,7 +110,7 @@
 
     for (unsigned I = 1, NumArgs = Args.size(); I < NumArgs; ++I) {
       llvm::Value *P = Builder.CreateStructGEP(AllocaTy, Alloca, I - 1);
-      llvm::Value *Arg = Args[I].RV.getScalarVal();
+      llvm::Value *Arg = Args[I].getRValue(*this).getScalarVal();
       Builder.CreateAlignedStore(Arg, P, DL.getPrefTypeAlignment(Arg->getType()));
     }
     BufferPtr = Builder.CreatePointerCast(Alloca, llvm::Type::getInt8PtrTy(Ctx));
@@ -117,6 +118,6 @@
 
   // Invoke vprintf and return.
   llvm::Function* VprintfFunc = GetVprintfDeclaration(CGM.getModule());
-  return RValue::get(
-      Builder.CreateCall(VprintfFunc, {Args[0].RV.getScalarVal(), BufferPtr}));
+  return RValue::get(Builder.CreateCall(
+      VprintfFunc, {Args[0].getRValue(*this).getScalarVal(), BufferPtr}));
 }
Index: lib/CodeGen/CGObjCGNU.cpp
===================================================================
--- lib/CodeGen/CGObjCGNU.cpp
+++ lib/CodeGen/CGObjCGNU.cpp
@@ -1441,7 +1441,7 @@
   }
 
   // Reset the receiver in case the lookup modified it
-  ActualArgs[0] = CallArg(RValue::get(Receiver), ASTIdTy, false);
+  ActualArgs[0] = CallArg(RValue::get(Receiver), ASTIdTy);
 
   imp = EnforceType(Builder, imp, MSI.MessengerType);
 
Index: lib/CodeGen/CGObjCMac.cpp
===================================================================
--- lib/CodeGen/CGObjCMac.cpp
+++ lib/CodeGen/CGObjCMac.cpp
@@ -1708,7 +1708,7 @@
            e = Method->param_end(); i != e; ++i, ++I) {
         const ParmVarDecl *ParamDecl = (*i);
         if (ParamDecl->hasAttr<NSConsumedAttr>()) {
-          RValue RV = I->RV;
+          RValue RV = I->getRValue(CGF);
           assert(RV.isScalar() && 
                  "NullReturnState::complete - arg not on object");
           CGF.EmitARCRelease(RV.getScalarVal(), ARCImpreciseLifetime);
@@ -7071,7 +7071,7 @@
             CGF.getPointerAlign());
 
   // Update the message ref argument.
-  args[1].RV = RValue::get(mref.getPointer());
+  args[1].setRValue(RValue::get(mref.getPointer()));
 
   // Load the function to call from the message ref table.
   Address calleeAddr =
Index: lib/CodeGen/CodeGenFunction.h
===================================================================
--- lib/CodeGen/CodeGenFunction.h
+++ lib/CodeGen/CodeGenFunction.h
@@ -3873,10 +3873,10 @@
   void ExpandTypeFromArgs(QualType Ty, LValue Dst,
                           SmallVectorImpl<llvm::Value *>::iterator &AI);
 
-  /// ExpandTypeToArgs - Expand an RValue \arg RV, with the LLVM type for \arg
+  /// ExpandTypeToArgs - Expand an CallArg \arg Arg, with the LLVM type for \arg
   /// Ty, into individual arguments on the provided vector \arg IRCallArgs,
   /// starting at index \arg IRCallArgPos. See ABIArgInfo::Expand.
-  void ExpandTypeToArgs(QualType Ty, RValue RV, llvm::FunctionType *IRFuncTy,
+  void ExpandTypeToArgs(QualType Ty, CallArg Arg, llvm::FunctionType *IRFuncTy,
                         SmallVectorImpl<llvm::Value *> &IRCallArgs,
                         unsigned &IRCallArgPos);
 
Index: lib/CodeGen/ItaniumCXXABI.cpp
===================================================================
--- lib/CodeGen/ItaniumCXXABI.cpp
+++ lib/CodeGen/ItaniumCXXABI.cpp
@@ -1474,8 +1474,7 @@
   llvm::Value *VTT =
       CGF.GetVTTParameter(GlobalDecl(D, Type), ForVirtualBase, Delegating);
   QualType VTTTy = getContext().getPointerType(getContext().VoidPtrTy);
-  Args.insert(Args.begin() + 1,
-              CallArg(RValue::get(VTT), VTTTy, /*needscopy=*/false));
+  Args.insert(Args.begin() + 1, CallArg(RValue::get(VTT), VTTTy));
   return AddedStructorArgs::prefix(1);  // Added one arg.
 }
 
Index: lib/CodeGen/MicrosoftCXXABI.cpp
===================================================================
--- lib/CodeGen/MicrosoftCXXABI.cpp
+++ lib/CodeGen/MicrosoftCXXABI.cpp
@@ -1537,8 +1537,7 @@
   }
   RValue RV = RValue::get(MostDerivedArg);
   if (FPT->isVariadic()) {
-    Args.insert(Args.begin() + 1,
-                CallArg(RV, getContext().IntTy, /*needscopy=*/false));
+    Args.insert(Args.begin() + 1, CallArg(RV, getContext().IntTy));
     return AddedStructorArgs::prefix(1);
   }
   Args.add(RV, getContext().IntTy);
Index: test/CodeGenCXX/amdgcn-func-arg.cpp
===================================================================
--- /dev/null
+++ test/CodeGenCXX/amdgcn-func-arg.cpp
@@ -0,0 +1,94 @@
+// RUN: %clang_cc1 -O0 -triple amdgcn---amdgiz -emit-llvm %s -o - | FileCheck %s
+
+class A {
+public:
+  int x;
+  A():x(0) {}
+  ~A() {}
+};
+
+class B {
+int x[100];
+};
+
+A g_a;
+B g_b;
+
+void func_with_ref_arg(A &a);
+void func_with_ref_arg(B &b);
+
+// CHECK-LABEL: define void @_Z22func_with_indirect_arg1A(%class.A addrspace(5)* %a)
+// CHECK:  %p = alloca %class.A*, align 8, addrspace(5)
+// CHECK:  %[[r1:.+]] = addrspacecast %class.A* addrspace(5)* %p to %class.A**
+// CHECK:  %[[r0:.+]] = addrspacecast %class.A addrspace(5)* %a to %class.A*
+// CHECK:  store %class.A* %[[r0]], %class.A** %[[r1]], align 8
+void func_with_indirect_arg(A a) {
+  A *p = &a;
+}
+
+// CHECK-LABEL: define void @_Z22test_indirect_arg_autov()
+// CHECK:  %a = alloca %class.A, align 4, addrspace(5)
+// CHECK:  %[[r0:.+]] = addrspacecast %class.A addrspace(5)* %a to %class.A*
+// CHECK:  %agg.tmp = alloca %class.A, align 4, addrspace(5)
+// CHECK:  %[[r1:.+]] = addrspacecast %class.A addrspace(5)* %agg.tmp to %class.A*
+// CHECK:  call void @_ZN1AC1Ev(%class.A* %[[r0]])
+// CHECK:  call void @llvm.memcpy.p0i8.p0i8.i64
+// CHECK:  %[[r4:.+]] = addrspacecast %class.A* %[[r1]] to %class.A addrspace(5)*
+// CHECK:  call void @_Z22func_with_indirect_arg1A(%class.A addrspace(5)* %[[r4]])
+// CHECK:  call void @_ZN1AD1Ev(%class.A* %[[r1]])
+// CHECK:  call void @_Z17func_with_ref_argR1A(%class.A* dereferenceable(4) %[[r0]])
+// CHECK:  call void @_ZN1AD1Ev(%class.A* %[[r0]])
+void test_indirect_arg_auto() {
+  A a;
+  func_with_indirect_arg(a);
+  func_with_ref_arg(a);
+}
+
+// CHECK: define void @_Z24test_indirect_arg_globalv()
+// CHECK:  %agg.tmp = alloca %class.A, align 4, addrspace(5)
+// CHECK:  %[[r0:.+]] = addrspacecast %class.A addrspace(5)* %agg.tmp to %class.A*
+// CHECK:  call void @llvm.memcpy.p0i8.p0i8.i64
+// CHECK:  %[[r2:.+]] = addrspacecast %class.A* %[[r0]] to %class.A addrspace(5)*
+// CHECK:  call void @_Z22func_with_indirect_arg1A(%class.A addrspace(5)* %[[r2]])
+// CHECK:  call void @_ZN1AD1Ev(%class.A* %[[r0]])
+// CHECK:  call void @_Z17func_with_ref_argR1A(%class.A* dereferenceable(4) addrspacecast (%class.A addrspace(1)* @g_a to %class.A*))
+void test_indirect_arg_global() {
+  func_with_indirect_arg(g_a);
+  func_with_ref_arg(g_a);
+}
+
+// CHECK-LABEL: define void @_Z19func_with_byval_arg1B(%class.B addrspace(5)* byval align 4 %b)
+// CHECK:  %p = alloca %class.B*, align 8, addrspace(5)
+// CHECK:  %[[r1:.+]] = addrspacecast %class.B* addrspace(5)* %p to %class.B**
+// CHECK:  %[[r0:.+]] = addrspacecast %class.B addrspace(5)* %b to %class.B*
+// CHECK:  store %class.B* %[[r0]], %class.B** %[[r1]], align 8
+void func_with_byval_arg(B b) {
+  B *p = &b;
+}
+
+// CHECK-LABEL: define void @_Z19test_byval_arg_autov()
+// CHECK:  %b = alloca %class.B, align 4, addrspace(5)
+// CHECK:  %[[r0:.+]] = addrspacecast %class.B addrspace(5)* %b to %class.B*
+// CHECK:  %agg.tmp = alloca %class.B, align 4, addrspace(5)
+// CHECK:  %[[r1:.+]] = addrspacecast %class.B addrspace(5)* %agg.tmp to %class.B*
+// CHECK:  call void @llvm.memcpy.p0i8.p0i8.i64
+// CHECK:  %[[r4:.+]] = addrspacecast %class.B* %[[r1]] to %class.B addrspace(5)*
+// CHECK:  call void @_Z19func_with_byval_arg1B(%class.B addrspace(5)* byval align 4 %[[r4]])
+// CHECK:  call void @_Z17func_with_ref_argR1B(%class.B* dereferenceable(400) %[[r0]])
+void test_byval_arg_auto() {
+  B b;
+  func_with_byval_arg(b);
+  func_with_ref_arg(b);
+}
+
+// CHECK-LABEL: define void @_Z21test_byval_arg_globalv()
+// CHECK:  %agg.tmp = alloca %class.B, align 4, addrspace(5)
+// CHECK:  %[[r0:.+]] = addrspacecast %class.B addrspace(5)* %agg.tmp to %class.B*
+// CHECK:  call void @llvm.memcpy.p0i8.p0i8.i64
+// CHECK:  %[[r2:.+]] = addrspacecast %class.B* %[[r0]] to %class.B addrspace(5)*
+// CHECK:  call void @_Z19func_with_byval_arg1B(%class.B addrspace(5)* byval align 4 %[[r2]])
+// CHECK:  call void @_Z17func_with_ref_argR1B(%class.B* dereferenceable(400) addrspacecast (%class.B addrspace(1)* @g_b to %class.B*))
+void test_byval_arg_global() {
+  func_with_byval_arg(g_b);
+  func_with_ref_arg(g_b);
+}
Index: test/CodeGenOpenCL/addr-space-struct-arg.cl
===================================================================
--- test/CodeGenOpenCL/addr-space-struct-arg.cl
+++ test/CodeGenOpenCL/addr-space-struct-arg.cl
@@ -1,5 +1,6 @@
 // RUN: %clang_cc1 %s -emit-llvm -o - -O0 -finclude-default-header -ffake-address-space-map -triple i686-pc-darwin | FileCheck -enable-var-scope -check-prefixes=COM,X86 %s
 // RUN: %clang_cc1 %s -emit-llvm -o - -O0 -finclude-default-header -triple amdgcn-amdhsa-amd | FileCheck -enable-var-scope -check-prefixes=COM,AMDGCN %s
+// RUN: %clang_cc1 %s -emit-llvm -o - -cl-std=CL2.0 -O0 -finclude-default-header -triple amdgcn-amdhsa-amd | FileCheck -enable-var-scope -check-prefixes=COM,AMDGCN,AMDGCN20 %s
 
 typedef struct {
   int cells[9];
@@ -35,6 +36,9 @@
   int2 y[20];
 };
 
+#if __OPENCL_C_VERSION__ >= 200
+struct LargeStructOneMember g_s;
+#endif
 
 // X86-LABEL: define void @foo(%struct.Mat4X4* noalias sret %agg.result, %struct.Mat3X3* byval align 4 %in)
 // AMDGCN-LABEL: define %struct.Mat4X4 @foo([9 x i32] %in.coerce)
@@ -80,10 +84,42 @@
 }
 
 // AMDGCN-LABEL: define void @FuncOneLargeMember(%struct.LargeStructOneMember addrspace(5)* byval align 8 %u)
+// AMDGCN-NOT: addrspacecast
+// AMDGCN:   store <2 x i32> %{{.*}}, <2 x i32> addrspace(5)*
 void FuncOneLargeMember(struct LargeStructOneMember u) {
   u.x[0] = (int2)(0, 0);
 }
 
+// AMDGCN20-LABEL: define void @test_indirect_arg_globl()
+// AMDGCN20:  %[[byval_temp:.*]] = alloca %struct.LargeStructOneMember, align 8, addrspace(5)
+// AMDGCN20:  %[[r0:.*]] = bitcast %struct.LargeStructOneMember addrspace(5)* %[[byval_temp]] to i8 addrspace(5)*
+// AMDGCN20:  call void @llvm.memcpy.p5i8.p1i8.i64(i8 addrspace(5)* align 8 %[[r0]], i8 addrspace(1)* align 8 bitcast (%struct.LargeStructOneMember addrspace(1)* @g_s to i8 addrspace(1)*), i64 800, i1 false)
+// AMDGCN20:  call void @FuncOneLargeMember(%struct.LargeStructOneMember addrspace(5)* byval align 8 %[[byval_temp]])
+#if __OPENCL_C_VERSION__ >= 200
+void test_indirect_arg_globl(void) {
+  FuncOneLargeMember(g_s);
+}
+#endif
+
+// AMDGCN-LABEL: define amdgpu_kernel void @test_indirect_arg_local()
+// AMDGCN: %[[byval_temp:.*]] = alloca %struct.LargeStructOneMember, align 8, addrspace(5)
+// AMDGCN: %[[r0:.*]] = bitcast %struct.LargeStructOneMember addrspace(5)* %[[byval_temp]] to i8 addrspace(5)*
+// AMDGCN: call void @llvm.memcpy.p5i8.p3i8.i64(i8 addrspace(5)* align 8 %[[r0]], i8 addrspace(3)* align 8 bitcast (%struct.LargeStructOneMember addrspace(3)* @test_indirect_arg_local.l_s to i8 addrspace(3)*), i64 800, i1 false)
+// AMDGCN: call void @FuncOneLargeMember(%struct.LargeStructOneMember addrspace(5)* byval align 8 %[[byval_temp]])
+kernel void test_indirect_arg_local(void) {
+  local struct LargeStructOneMember l_s;
+  FuncOneLargeMember(l_s);
+}
+
+// AMDGCN-LABEL: define void @test_indirect_arg_private()
+// AMDGCN: %[[p_s:.*]] = alloca %struct.LargeStructOneMember, align 8, addrspace(5)
+// AMDGCN-NOT: @llvm.memcpy
+// AMDGCN-NEXT: call void @FuncOneLargeMember(%struct.LargeStructOneMember addrspace(5)* byval align 8 %[[p_s]])
+void test_indirect_arg_private(void) {
+  struct LargeStructOneMember p_s;
+  FuncOneLargeMember(p_s);
+}
+
 // AMDGCN-LABEL: define amdgpu_kernel void @KernelOneMember
 // AMDGCN-SAME:  (<2 x i32> %[[u_coerce:.*]])
 // AMDGCN:  %[[u:.*]] = alloca %struct.StructOneMember, align 8, addrspace(5)
@@ -112,7 +148,6 @@
   u.y[0] = (int2)(0, 0);
 }
 
-
 // AMDGCN-LABEL: define amdgpu_kernel void @KernelTwoMember
 // AMDGCN-SAME:  (%struct.StructTwoMember %[[u_coerce:.*]])
 // AMDGCN:  %[[u:.*]] = alloca %struct.StructTwoMember, align 8, addrspace(5)
Index: test/CodeGenOpenCL/byval.cl
===================================================================
--- test/CodeGenOpenCL/byval.cl
+++ test/CodeGenOpenCL/byval.cl
@@ -1,5 +1,4 @@
 // RUN: %clang_cc1 -emit-llvm -o - -triple amdgcn %s | FileCheck %s
-// RUN: %clang_cc1 -emit-llvm -o - -triple amdgcn---opencl %s | FileCheck %s
 
 struct A {
   int x[100];