diff --git a/clang/lib/Basic/Targets/WebAssembly.h b/clang/lib/Basic/Targets/WebAssembly.h
--- a/clang/lib/Basic/Targets/WebAssembly.h
+++ b/clang/lib/Basic/Targets/WebAssembly.h
@@ -147,7 +147,7 @@
   explicit WebAssembly32TargetInfo(const llvm::Triple &T,
                                    const TargetOptions &Opts)
       : WebAssemblyTargetInfo(T, Opts) {
-    resetDataLayout("e-m:e-p:32:32-i64:64-n32:64-S128");
+    resetDataLayout("e-m:e-p:32:32-i64:64-n32:64-S128-ni:1");
   }
 
 protected:
@@ -166,7 +166,7 @@
     SizeType = UnsignedLong;
     PtrDiffType = SignedLong;
     IntPtrType = SignedLong;
-    resetDataLayout("e-m:e-p:64:64-i64:64-n32:64-S128");
+    resetDataLayout("e-m:e-p:64:64-i64:64-n32:64-S128-ni:1");
   }
 
 protected:
diff --git a/clang/lib/Basic/Targets/WebAssembly.cpp b/clang/lib/Basic/Targets/WebAssembly.cpp
--- a/clang/lib/Basic/Targets/WebAssembly.cpp
+++ b/clang/lib/Basic/Targets/WebAssembly.cpp
@@ -214,6 +214,8 @@
       continue;
     }
     if (Feature == "+reference-types") {
+      // FIXME: Ensure address spaces 10 and 20 are marked as non-integral in
+      // the datalayout string.
       HasReferenceTypes = true;
       continue;
     }
diff --git a/clang/test/CodeGen/target-data.c b/clang/test/CodeGen/target-data.c
--- a/clang/test/CodeGen/target-data.c
+++ b/clang/test/CodeGen/target-data.c
@@ -108,11 +108,11 @@
 
 // RUN: %clang_cc1 -triple wasm32-unknown-unknown -o - -emit-llvm %s | \
 // RUN: FileCheck %s -check-prefix=WEBASSEMBLY32
-// WEBASSEMBLY32: target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
+// WEBASSEMBLY32: target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128-ni:1"
 
 // RUN: %clang_cc1 -triple wasm64-unknown-unknown -o - -emit-llvm %s | \
 // RUN: FileCheck %s -check-prefix=WEBASSEMBLY64
-// WEBASSEMBLY64: target datalayout = "e-m:e-p:64:64-i64:64-n32:64-S128"
+// WEBASSEMBLY64: target datalayout = "e-m:e-p:64:64-i64:64-n32:64-S128-ni:1"
 
 // RUN: %clang_cc1 -triple lanai-unknown-unknown -o - -emit-llvm %s | \
 // RUN: FileCheck %s -check-prefix=LANAI
diff --git a/llvm/include/llvm/CodeGen/TargetLowering.h b/llvm/include/llvm/CodeGen/TargetLowering.h
--- a/llvm/include/llvm/CodeGen/TargetLowering.h
+++ b/llvm/include/llvm/CodeGen/TargetLowering.h
@@ -347,7 +347,7 @@
   /// Return the in-memory pointer type for the given address space, defaults to
   /// the pointer type from the data layout.  FIXME: The default needs to be
   /// removed once all the code is updated.
-  MVT getPointerMemTy(const DataLayout &DL, uint32_t AS = 0) const {
+  virtual MVT getPointerMemTy(const DataLayout &DL, uint32_t AS = 0) const {
     return MVT::getIntegerVT(DL.getPointerSizeInBits(AS));
   }
 
diff --git a/llvm/include/llvm/CodeGen/ValueTypes.h b/llvm/include/llvm/CodeGen/ValueTypes.h
--- a/llvm/include/llvm/CodeGen/ValueTypes.h
+++ b/llvm/include/llvm/CodeGen/ValueTypes.h
@@ -120,6 +120,9 @@
       return changeExtendedTypeToInteger();
     }
 
+    /// Test if the given EVT has zero size
+    bool isZeroSized() const { return getSizeInBits() == 0; }
+
     /// Test if the given EVT is simple (as opposed to being extended).
     bool isSimple() const {
       return V.SimpleTy != MVT::INVALID_SIMPLE_VALUE_TYPE;
@@ -207,7 +210,9 @@
     }
 
     /// Return true if the bit size is a multiple of 8.
-    bool isByteSized() const { return getSizeInBits().isKnownMultipleOf(8); }
+    bool isByteSized() const {
+      return !isZeroSized() && getSizeInBits().isKnownMultipleOf(8);
+    }
 
     /// Return true if the size is a power-of-two number of bytes.
     bool isRound() const {
diff --git a/llvm/include/llvm/Support/MachineValueType.h b/llvm/include/llvm/Support/MachineValueType.h
--- a/llvm/include/llvm/Support/MachineValueType.h
+++ b/llvm/include/llvm/Support/MachineValueType.h
@@ -995,6 +995,11 @@
       }
     }
 
+    /// Test if the given MVT has zero size
+    bool isZeroSized() const {
+      return !getSizeInBits().isScalable() && getFixedSizeInBits() == 0;
+    }
+
     /// Return the size of the specified fixed width value type in bits. The
     /// function will assert if the type is scalable.
     uint64_t getFixedSizeInBits() const {
diff --git a/llvm/lib/CodeGen/CodeGenPrepare.cpp b/llvm/lib/CodeGen/CodeGenPrepare.cpp
--- a/llvm/lib/CodeGen/CodeGenPrepare.cpp
+++ b/llvm/lib/CodeGen/CodeGenPrepare.cpp
@@ -6451,6 +6451,10 @@
 
   EVT LoadResultVT = TLI->getValueType(*DL, Load->getType());
   unsigned BitWidth = LoadResultVT.getSizeInBits();
+  // If the BitWidth is 0, do not try to optimize the type
+  if (BitWidth == 0)
+    return false;
+
   APInt DemandBits(BitWidth, 0);
   APInt WidestAndBits(BitWidth, 0);
 
diff --git a/llvm/lib/CodeGen/MachineOperand.cpp b/llvm/lib/CodeGen/MachineOperand.cpp
--- a/llvm/lib/CodeGen/MachineOperand.cpp
+++ b/llvm/lib/CodeGen/MachineOperand.cpp
@@ -1167,8 +1167,11 @@
        << "unknown-address";
   }
   MachineOperand::printOperandOffset(OS, getOffset());
-  if (getAlign() != getSize())
-    OS << ", align " << getAlign().value();
+  if (getSize() > 0) {
+    if (getAlign() != getSize())
+      OS << ", align " << getAlign().value();
+  } else
+    OS << ", opaque ";
   if (getAlign() != getBaseAlign())
     OS << ", basealign " << getBaseAlign().value();
   auto AAInfo = getAAInfo();
diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -23038,6 +23038,10 @@
   if (BasePtr.getBase().isUndef())
     return false;
 
+  // Do not handle stores to opaque types
+  if (St->getMemoryVT().isZeroSized())
+    return false;
+
   // BaseIndexOffset assumes that offsets are fixed-size, which
   // is not valid for scalable vectors where the offsets are
   // scaled by `vscale`, so bail out early.
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -4089,6 +4089,7 @@
   SmallVector<SDValue, 4> Values(NumValues);
   SmallVector<SDValue, 4> Chains(std::min(MaxParallelChains, NumValues));
   EVT PtrVT = Ptr.getValueType();
+  EVT EltVT = PtrVT.getScalarType();
 
   MachineMemOperand::Flags MMOFlags
     = TLI.getLoadMemOperandFlags(I, DAG.getDataLayout());
@@ -4108,17 +4109,21 @@
       Root = Chain;
       ChainI = 0;
     }
-    SDValue A = DAG.getNode(ISD::ADD, dl,
-                            PtrVT, Ptr,
-                            DAG.getConstant(Offsets[i], dl, PtrVT),
-                            Flags);
+    SDValue A;
+
+    if (EltVT.isZeroSized())
+      A = Ptr;
+    else
+      A = DAG.getNode(ISD::ADD, dl, PtrVT, Ptr,
+                      DAG.getConstant(Offsets[i], dl, PtrVT), Flags);
 
     SDValue L = DAG.getLoad(MemVTs[i], dl, Root, A,
                             MachinePointerInfo(SV, Offsets[i]), Alignment,
                             MMOFlags, AAInfo, Ranges);
     Chains[ChainI] = L.getValue(1);
 
-    if (MemVTs[i] != ValueVTs[i])
+    // Skip ZExt or Trunc if a ValueVT is zero sized
+    if (!ValueVTs[i].isZeroSized() && MemVTs[i] != ValueVTs[i])
       L = DAG.getZExtOrTrunc(L, dl, ValueVTs[i]);
 
     Values[i] = L;
@@ -4257,7 +4262,8 @@
     SDValue Add =
         DAG.getMemBasePlusOffset(Ptr, TypeSize::Fixed(Offsets[i]), dl, Flags);
     SDValue Val = SDValue(Src.getNode(), Src.getResNo() + i);
-    if (MemVTs[i] != ValueVTs[i])
+    // Skip ZExt or Trunc if a ValueVT is zero sized
+    if (!ValueVTs[i].isZeroSized() && MemVTs[i] != ValueVTs[i])
       Val = DAG.getPtrExtOrTrunc(Val, dl, MemVTs[i]);
     SDValue St =
         DAG.getStore(Root, dl, Val, Add, MachinePointerInfo(PtrV, Offsets[i]),
diff --git a/llvm/lib/CodeGen/TargetLoweringBase.cpp b/llvm/lib/CodeGen/TargetLoweringBase.cpp
--- a/llvm/lib/CodeGen/TargetLoweringBase.cpp
+++ b/llvm/lib/CodeGen/TargetLoweringBase.cpp
@@ -1681,7 +1681,7 @@
   // For example, the ABI alignment may change based on software platform while
   // this function should only be affected by hardware implementation.
   Type *Ty = VT.getTypeForEVT(Context);
-  if (Alignment >= DL.getABITypeAlign(Ty)) {
+  if (!VT.isZeroSized() && Alignment >= DL.getABITypeAlign(Ty)) {
     // Assume that an access that meets the ABI-specified alignment is fast.
     if (Fast != nullptr)
       *Fast = true;
diff --git a/llvm/lib/CodeGen/ValueTypes.cpp b/llvm/lib/CodeGen/ValueTypes.cpp
--- a/llvm/lib/CodeGen/ValueTypes.cpp
+++ b/llvm/lib/CodeGen/ValueTypes.cpp
@@ -199,6 +199,10 @@
   case MVT::ppcf128: return Type::getPPC_FP128Ty(Context);
   case MVT::x86mmx:  return Type::getX86_MMXTy(Context);
   case MVT::x86amx:  return Type::getX86_AMXTy(Context);
+  case MVT::externref:
+    return PointerType::get(StructType::create(Context), 10);
+  case MVT::funcref:
+    return PointerType::get(StructType::create(Context), 20);
   case MVT::v1i1:
     return FixedVectorType::get(Type::getInt1Ty(Context), 1);
   case MVT::v2i1:
diff --git a/llvm/lib/Target/WebAssembly/Utils/WebAssemblyUtilities.h b/llvm/lib/Target/WebAssembly/Utils/WebAssemblyUtilities.h
--- a/llvm/lib/Target/WebAssembly/Utils/WebAssemblyUtilities.h
+++ b/llvm/lib/Target/WebAssembly/Utils/WebAssemblyUtilities.h
@@ -48,6 +48,12 @@
 getOrCreateFunctionTableSymbol(MCContext &Ctx,
                                const WebAssemblySubtarget *Subtarget);
 
+/// Returns the __funcref_call_table, for use in funcref calls when lowered to
+/// table.set + call_indirect.
+MCSymbolWasm *
+getOrCreateFuncrefCallTableSymbol(MCContext &Ctx,
+                                  const WebAssemblySubtarget *Subtarget);
+
 /// Find a catch instruction from an EH pad. Returns null if no catch
 /// instruction found or the catch is in an invalid location.
 MachineInstr *findCatch(MachineBasicBlock *EHPad);
diff --git a/llvm/lib/Target/WebAssembly/Utils/WebAssemblyUtilities.cpp b/llvm/lib/Target/WebAssembly/Utils/WebAssemblyUtilities.cpp
--- a/llvm/lib/Target/WebAssembly/Utils/WebAssemblyUtilities.cpp
+++ b/llvm/lib/Target/WebAssembly/Utils/WebAssemblyUtilities.cpp
@@ -116,6 +116,34 @@
   return Sym;
 }
 
+MCSymbolWasm *WebAssembly::getOrCreateFuncrefCallTableSymbol(
+    MCContext &Ctx, const WebAssemblySubtarget *Subtarget) {
+  StringRef Name = "__funcref_call_table";
+  MCSymbolWasm *Sym = cast_or_null<MCSymbolWasm>(Ctx.lookupSymbol(Name));
+  if (Sym) {
+    if (!Sym->isFunctionTable())
+      Ctx.reportError(SMLoc(), "symbol is not a wasm funcref table");
+  } else {
+    Sym = cast<MCSymbolWasm>(Ctx.getOrCreateSymbol(Name));
+
+    // The default function table is synthesized by the linker.
+    Sym->setUndefined();
+
+    // Setting Comdat ensure only one table is left after linking when multiple
+    // modules define the table.
+    Sym->setComdat(true);
+
+    wasm::WasmLimits Limits = {0, 1, 1};
+    wasm::WasmTableType TableType = {wasm::WASM_TYPE_FUNCREF, Limits};
+    Sym->setType(wasm::WASM_SYMBOL_TYPE_TABLE);
+    Sym->setTableType(TableType);
+  }
+  // MVP object files can't have symtab entries for tables.
+  if (!(Subtarget && Subtarget->hasReferenceTypes()))
+    Sym->setOmitFromLinkingSection();
+  return Sym;
+}
+
 // Find a catch instruction from an EH pad.
 MachineInstr *WebAssembly::findCatch(MachineBasicBlock *EHPad) {
   assert(EHPad->isEHPad());
diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyFastISel.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyFastISel.cpp
--- a/llvm/lib/Target/WebAssembly/WebAssemblyFastISel.cpp
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyFastISel.cpp
@@ -130,9 +130,12 @@
     case MVT::i64:
     case MVT::f32:
     case MVT::f64:
+      return VT;
     case MVT::funcref:
     case MVT::externref:
-      return VT;
+      if (Subtarget->hasReferenceTypes())
+        return VT;
+      break;
     case MVT::f16:
       return MVT::f32;
     case MVT::v16i8:
diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyISD.def b/llvm/lib/Target/WebAssembly/WebAssemblyISD.def
--- a/llvm/lib/Target/WebAssembly/WebAssemblyISD.def
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyISD.def
@@ -19,7 +19,7 @@
 HANDLE_NODETYPE(ARGUMENT)
 // A wrapper node for TargetExternalSymbol, TargetGlobalAddress, and MCSymbol
 HANDLE_NODETYPE(Wrapper)
-// A special wapper used in PIC code for __memory_base/__table_base relcative
+// A special wapper used in PIC code for __memory_base/__table_base relative
 // access.
 HANDLE_NODETYPE(WrapperPIC)
 HANDLE_NODETYPE(BR_IF)
@@ -44,3 +44,8 @@
 
 // Memory intrinsics
 HANDLE_MEM_NODETYPE(LOAD_SPLAT)
+
+// Reference Types
+HANDLE_MEM_NODETYPE(GLOBAL_GET)
+HANDLE_MEM_NODETYPE(GLOBAL_SET)
+HANDLE_MEM_NODETYPE(TABLE_SET)
diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyISelDAGToDAG.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyISelDAGToDAG.cpp
--- a/llvm/lib/Target/WebAssembly/WebAssemblyISelDAGToDAG.cpp
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyISelDAGToDAG.cpp
@@ -60,6 +60,7 @@
 
   bool SelectInlineAsmMemoryOperand(const SDValue &Op, unsigned ConstraintID,
                                     std::vector<SDValue> &OutOps) override;
+  bool SelectExternRefAddr(const SDValue &Addr, const SDValue &Base);
 
 // Include the pieces autogenerated from the target description.
 #include "WebAssemblyGenDAGISel.inc"
diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.h b/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.h
--- a/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.h
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.h
@@ -45,6 +45,33 @@
   WebAssemblyTargetLowering(const TargetMachine &TM,
                             const WebAssemblySubtarget &STI);
 
+  enum WasmAddressSpace : unsigned {
+    // WebAssembly uses the following address spaces:
+    // AS 0 : is the default address space for values in linear memory
+    DEFAULT = 0,
+    // AS 1 : is a non-integral address space for global variables
+    GLOBAL = 1,
+    // AS 10 : is a non-integral address space for externref values
+    EXTERNREF = 10,
+    // AS 20 : is a non-integral address space for funcref values
+    FUNCREF = 20,
+  };
+
+  MVT getPointerTy(const DataLayout &DL, uint32_t AS = 0) const override {
+    if (AS == WasmAddressSpace::EXTERNREF)
+      return MVT::externref;
+    else if (AS == WasmAddressSpace::FUNCREF)
+      return MVT::funcref;
+    return TargetLowering::getPointerTy(DL, AS);
+  }
+  MVT getPointerMemTy(const DataLayout &DL, uint32_t AS = 0) const override {
+    if (AS == WasmAddressSpace::EXTERNREF)
+      return MVT::externref;
+    else if (AS == WasmAddressSpace::FUNCREF)
+      return MVT::funcref;
+    return TargetLowering::getPointerMemTy(DL, AS);
+  }
+
 private:
   /// Keep a pointer to the WebAssemblySubtarget around so that we can make the
   /// right decision when generating code for different targets.
@@ -66,6 +93,7 @@
   bool isLegalAddressingMode(const DataLayout &DL, const AddrMode &AM, Type *Ty,
                              unsigned AS,
                              Instruction *I = nullptr) const override;
+  bool isFuncref(const Value *Op) const;
   bool allowsMisalignedMemoryAccesses(EVT, unsigned AddrSpace, Align Alignment,
                                       MachineMemOperand::Flags Flags,
                                       bool *Fast) const override;
@@ -100,6 +128,11 @@
     report_fatal_error("llvm.clear_cache is not supported on wasm");
   }
 
+  bool splitValueIntoRegisterParts(SelectionDAG &DAG, const SDLoc &DL,
+                                   SDValue Val, SDValue *Parts,
+                                   unsigned NumParts, MVT PartVT,
+                                   Optional<CallingConv::ID> CC) const override;
+
   // Custom lowering hooks.
   SDValue LowerOperation(SDValue Op, SelectionDAG &DAG) const override;
   SDValue LowerFrameIndex(SDValue Op, SelectionDAG &DAG) const;
@@ -120,6 +153,8 @@
   SDValue LowerAccessVectorElement(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerShift(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerFP_TO_INT_SAT(SDValue Op, SelectionDAG &DAG) const;
+  SDValue LowerLoad(SDValue Op, SelectionDAG &DAG) const;
+  SDValue LowerStore(SDValue Op, SelectionDAG &DAG) const;
 
   // Custom DAG combine hooks
   SDValue
diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
--- a/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
@@ -14,6 +14,7 @@
 #include "WebAssemblyISelLowering.h"
 #include "MCTargetDesc/WebAssemblyMCTargetDesc.h"
 #include "Utils/WebAssemblyUtilities.h"
+#include "Utils/WebAssemblyTypeUtilities.h"
 #include "WebAssemblyMachineFunctionInfo.h"
 #include "WebAssemblySubtarget.h"
 #include "WebAssemblyTargetMachine.h"
@@ -24,6 +25,7 @@
 #include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
 #include "llvm/CodeGen/SelectionDAG.h"
+#include "llvm/CodeGen/SelectionDAGNodes.h"
 #include "llvm/CodeGen/WasmEHFuncInfo.h"
 #include "llvm/IR/DiagnosticInfo.h"
 #include "llvm/IR/DiagnosticPrinter.h"
@@ -66,9 +68,33 @@
     addRegisterClass(MVT::v2i64, &WebAssembly::V128RegClass);
     addRegisterClass(MVT::v2f64, &WebAssembly::V128RegClass);
   }
+  if (Subtarget->hasReferenceTypes()) {
+    addRegisterClass(MVT::externref, &WebAssembly::EXTERNREFRegClass);
+    addRegisterClass(MVT::funcref, &WebAssembly::FUNCREFRegClass);
+  }
   // Compute derived properties from the register classes.
   computeRegisterProperties(Subtarget->getRegisterInfo());
 
+  // Transform loads and stores to pointers in address space 1 to loads and
+  // stores to WebAssembly global variables, outside linear memory.
+  for (auto T : {MVT::i32, MVT::i64, MVT::f32, MVT::f64}) {
+    setOperationAction(ISD::LOAD, T, Custom);
+    setOperationAction(ISD::STORE, T, Custom);
+  }
+  if (Subtarget->hasSIMD128()) {
+    for (auto T : {MVT::v16i8, MVT::v8i16, MVT::v4i32, MVT::v4f32, MVT::v2i64,
+                   MVT::v2f64}) {
+      setOperationAction(ISD::LOAD, T, Custom);
+      setOperationAction(ISD::STORE, T, Custom);
+    }
+  }
+  if (Subtarget->hasReferenceTypes()) {
+    for (auto T : {MVT::externref, MVT::funcref}) {
+      setOperationAction(ISD::LOAD, T, Custom);
+      setOperationAction(ISD::STORE, T, Custom);
+    }
+  }
+
   setOperationAction(ISD::GlobalAddress, MVTPtr, Custom);
   setOperationAction(ISD::GlobalTLSAddress, MVTPtr, Custom);
   setOperationAction(ISD::ExternalSymbol, MVTPtr, Custom);
@@ -454,6 +480,16 @@
   bool IsIndirect = CallParams.getOperand(0).isReg();
   bool IsRetCall = CallResults.getOpcode() == WebAssembly::RET_CALL_RESULTS;
 
+  bool IsFuncrefCall = false;
+  if (IsIndirect) {
+    Register Reg = CallParams.getOperand(0).getReg();
+    const MachineFunction *MF = BB->getParent();
+    const MachineRegisterInfo &MRI = MF->getRegInfo();
+    const TargetRegisterClass *TRC = MRI.getRegClass(Reg);
+    IsFuncrefCall = (TRC == &WebAssembly::FUNCREFRegClass);
+    assert(!IsFuncrefCall || Subtarget->hasReferenceTypes());
+  }
+
   unsigned CallOp;
   if (IsIndirect && IsRetCall) {
     CallOp = WebAssembly::RET_CALL_INDIRECT;
@@ -497,8 +533,11 @@
     // Placeholder for the type index.
     MIB.addImm(0);
     // The table into which this call_indirect indexes.
-    MCSymbolWasm *Table =
-        WebAssembly::getOrCreateFunctionTableSymbol(MF.getContext(), Subtarget);
+    MCSymbolWasm *Table = IsFuncrefCall
+                              ? WebAssembly::getOrCreateFuncrefCallTableSymbol(
+                                    MF.getContext(), Subtarget)
+                              : WebAssembly::getOrCreateFunctionTableSymbol(
+                                    MF.getContext(), Subtarget);
     if (Subtarget->hasReferenceTypes()) {
       MIB.addSym(Table);
     } else {
@@ -517,6 +556,27 @@
   CallParams.eraseFromParent();
   CallResults.eraseFromParent();
 
+  // If this is a funcref call, to avoid hidden GC roots, we need to clear the table
+  // slot with ref.null upon call_indirect return.
+  if (IsIndirect && IsFuncrefCall) {
+    MCSymbolWasm *Table = WebAssembly::getOrCreateFuncrefCallTableSymbol(MF.getContext(), Subtarget);
+    Register RegZero =
+        MF.getRegInfo().createVirtualRegister(&WebAssembly::I32RegClass);
+    MachineInstr *Const0 = BuildMI(MF, DL, TII.get(WebAssembly::CONST_I32), RegZero)
+      .addImm(0);
+    BB->insertAfter(MIB.getInstr()->getIterator(), Const0);
+    
+    Register RegFuncref =
+        MF.getRegInfo().createVirtualRegister(&WebAssembly::FUNCREFRegClass);
+    MachineInstr *RefNull = BuildMI(MF, DL, TII.get(WebAssembly::REF_NULL_FUNCREF), RegFuncref)
+      .addImm(static_cast<int32_t>(WebAssembly::HeapType::Funcref));
+    BB->insertAfter(Const0->getIterator(), RefNull);
+
+    MachineInstr *TableSet = BuildMI(MF, DL, TII.get(WebAssembly::TABLE_SET_FUNCREF))
+      .addSym(Table).addReg(RegZero).addReg(RegFuncref);
+    BB->insertAfter(RefNull->getIterator(), TableSet);
+  }
+    
   return BB;
 }
 
@@ -1045,6 +1105,33 @@
     InTys.push_back(In.VT);
   }
 
+  // Lastly, if this is a call to a funcref we need to add an instruction
+  // table.set to the chain and transform the call.
+  if (CLI.CB && isFuncref(CLI.CB->getCalledOperand())) {
+    // In the absence of function references proposal where a funcref call is
+    // lowered to call_ref, using reference types we generate a table.set to set
+    // the funcref to a special table used solely for this purpose, followed by
+    // a call_indirect. Here we just generate the table set, and return the
+    // SDValue of the table.set so that LowerCall can finalize the lowering by
+    // generating the call_indirect.
+    SDValue Chain = Ops[0];
+
+    MCSymbolWasm *Table = WebAssembly::getOrCreateFuncrefCallTableSymbol(
+        MF.getContext(), Subtarget);
+    SDValue Sym = DAG.getMCSymbol(Table, PtrVT);
+    SDValue TableSlot = DAG.getConstant(0, DL, MVT::i32);
+    SDValue TableSetOps[] = {Chain, Sym, TableSlot, Callee};
+    SDValue TableSet = DAG.getMemIntrinsicNode(
+        WebAssemblyISD::TABLE_SET, DL, DAG.getVTList(MVT::Other), TableSetOps,
+        MVT::funcref,
+        // Machine Mem Operand args
+        MachinePointerInfo(WasmAddressSpace::FUNCREF),
+        CLI.CB->getCalledOperand()->getPointerAlignment(DAG.getDataLayout()),
+        MachineMemOperand::MOStore);
+
+    Ops[0] = TableSet; // The new chain is the TableSet itself
+  }
+
   if (CLI.IsTailCall) {
     // ret_calls do not return values to the current frame
     SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Glue);
@@ -1253,7 +1340,70 @@
   case ISD::FP_TO_SINT_SAT:
   case ISD::FP_TO_UINT_SAT:
     return LowerFP_TO_INT_SAT(Op, DAG);
+  case ISD::LOAD:
+    return LowerLoad(Op, DAG);
+  case ISD::STORE:
+    return LowerStore(Op, DAG);
+  }
+}
+
+static bool IsWebAssemblyGlobal(SDValue Op) {
+  if (const GlobalAddressSDNode *GA = dyn_cast<GlobalAddressSDNode>(Op))
+    return GA->getAddressSpace() ==
+           WebAssemblyTargetLowering::WasmAddressSpace::GLOBAL;
+
+  return false;
+}
+
+bool WebAssemblyTargetLowering::isFuncref(const Value *Op) const {
+  const Type *Ty = Op->getType();
+
+  return isa<PointerType>(Ty) &&
+         Ty->getPointerAddressSpace() == WasmAddressSpace::FUNCREF;
+}
+
+SDValue WebAssemblyTargetLowering::LowerStore(SDValue Op,
+                                              SelectionDAG &DAG) const {
+  SDLoc DL(Op);
+  StoreSDNode *SN = cast<StoreSDNode>(Op.getNode());
+  const SDValue &Value = SN->getValue();
+  const SDValue &Offset = SN->getOffset();
+  const SDValue &Base = SN->getBasePtr();
+
+  if (IsWebAssemblyGlobal(Base)) {
+    if (!Offset->isUndef())
+      report_fatal_error("unexpected offset when storing to webassembly global",
+                         false);
+
+    SDVTList Tys = DAG.getVTList(MVT::Other);
+    SDValue Ops[] = {SN->getChain(), Value, Base};
+    return DAG.getMemIntrinsicNode(WebAssemblyISD::GLOBAL_SET, DL, Tys, Ops,
+                                   SN->getMemoryVT(), SN->getMemOperand());
   }
+
+  return Op;
+}
+
+SDValue WebAssemblyTargetLowering::LowerLoad(SDValue Op,
+                                             SelectionDAG &DAG) const {
+  SDLoc DL(Op);
+  LoadSDNode *LN = cast<LoadSDNode>(Op.getNode());
+  const SDValue &Base = LN->getBasePtr();
+  const SDValue &Offset = LN->getOffset();
+
+  if (IsWebAssemblyGlobal(Base)) {
+    if (!Offset->isUndef())
+      report_fatal_error(
+          "unexpected offset when loading from webassembly global", false);
+
+    EVT VT = LN->getValueType(0);
+    SDValue GlobalGet = DAG.getMemIntrinsicNode(
+        WebAssemblyISD::GLOBAL_GET, DL, DAG.getVTList(VT),
+        {LN->getChain(), Base}, LN->getMemoryVT(), LN->getMemOperand());
+    return DAG.getMergeValues({GlobalGet, LN->getChain()}, DL);
+  }
+
+  return Op;
 }
 
 SDValue WebAssemblyTargetLowering::LowerCopyToReg(SDValue Op,
@@ -1374,8 +1524,6 @@
   EVT VT = Op.getValueType();
   assert(GA->getTargetFlags() == 0 &&
          "Unexpected target flags on generic GlobalAddressSDNode");
-  if (GA->getAddressSpace() != 0)
-    fail(DL, DAG, "WebAssembly only expects the 0 address space");
 
   unsigned OperandFlags = 0;
   if (isPositionIndependent()) {
@@ -2186,3 +2334,13 @@
     return performVectorTruncSatLowCombine(N, DCI);
   }
 }
+
+bool WebAssemblyTargetLowering::splitValueIntoRegisterParts(
+    SelectionDAG &DAG, const SDLoc &DL, SDValue Val, SDValue *Parts,
+    unsigned NumParts, MVT PartVT, Optional<CallingConv::ID> CC) const {
+  if (PartVT.isZeroSized()) {
+    Parts[0] = Val;
+    return true;
+  }
+  return false;
+}
diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyInstrInfo.td b/llvm/lib/Target/WebAssembly/WebAssemblyInstrInfo.td
--- a/llvm/lib/Target/WebAssembly/WebAssemblyInstrInfo.td
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyInstrInfo.td
@@ -79,6 +79,8 @@
                                                      SDTCisPtrTy<0>]>;
 def SDT_WebAssemblyThrow      : SDTypeProfile<0, -1, []>;
 def SDT_WebAssemblyCatch      : SDTypeProfile<1, 1, [SDTCisPtrTy<0>]>;
+def SDT_WebAssemblyGlobalGet  : SDTypeProfile<1, 1, [SDTCisPtrTy<1>]>;
+def SDT_WebAssemblyGlobalSet  : SDTypeProfile<0, 2, [SDTCisPtrTy<1>]>;
 
 //===----------------------------------------------------------------------===//
 // WebAssembly-specific DAG Nodes.
@@ -106,6 +108,12 @@
                               [SDNPHasChain, SDNPVariadic]>;
 def WebAssemblycatch : SDNode<"WebAssemblyISD::CATCH", SDT_WebAssemblyCatch,
                               [SDNPHasChain, SDNPSideEffect]>;
+def WebAssemblyglobal_get :
+    SDNode<"WebAssemblyISD::GLOBAL_GET", SDT_WebAssemblyGlobalGet,
+           [SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>;
+def WebAssemblyglobal_set :
+    SDNode<"WebAssemblyISD::GLOBAL_SET", SDT_WebAssemblyGlobalSet,
+           [SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;
 
 //===----------------------------------------------------------------------===//
 // WebAssembly-specific Operands.
@@ -257,7 +265,7 @@
 
 // local.get and local.set are not generated by instruction selection; they
 // are implied by virtual register uses and defs.
-multiclass LOCAL<WebAssemblyRegClass vt, Operand global_op> {
+multiclass LOCAL<WebAssemblyRegClass reg, Operand global_op> {
   let hasSideEffects = 0 in {
   // COPY is not an actual instruction in wasm, but since we allow local.get and
   // local.set to be implicit during most of codegen, we can have a COPY which
@@ -265,58 +273,66 @@
   // and local.set. COPYs are eliminated (and replaced with
   // local.get/local.set) in the ExplicitLocals pass.
   let isAsCheapAsAMove = 1, isCodeGenOnly = 1 in
-  defm COPY_#vt : I<(outs vt:$res), (ins vt:$src), (outs), (ins), [],
-                    "local.copy\t$res, $src", "local.copy">;
+  defm COPY_#reg : I<(outs reg:$res), (ins reg:$src), (outs), (ins), [],
+                     "local.copy\t$res, $src", "local.copy">;
 
   // TEE is similar to COPY, but writes two copies of its result. Typically
   // this would be used to stackify one result and write the other result to a
   // local.
   let isAsCheapAsAMove = 1, isCodeGenOnly = 1 in
-  defm TEE_#vt : I<(outs vt:$res, vt:$also), (ins vt:$src), (outs), (ins), [],
-                   "local.tee\t$res, $also, $src", "local.tee">;
+  defm TEE_#reg : I<(outs reg:$res, reg:$also), (ins reg:$src), (outs), (ins), [],
+                    "local.tee\t$res, $also, $src", "local.tee">;
 
   // This is the actual local.get instruction in wasm. These are made explicit
   // by the ExplicitLocals pass. It has mayLoad because it reads from a wasm
   // local, which is a side effect not otherwise modeled in LLVM.
   let mayLoad = 1, isAsCheapAsAMove = 1 in
-  defm LOCAL_GET_#vt : I<(outs vt:$res), (ins local_op:$local),
-                         (outs), (ins local_op:$local), [],
-                         "local.get\t$res, $local", "local.get\t$local", 0x20>;
+  defm LOCAL_GET_#reg : I<(outs reg:$res), (ins local_op:$local),
+                          (outs), (ins local_op:$local), [],
+                          "local.get\t$res, $local", "local.get\t$local", 0x20>;
 
   // This is the actual local.set instruction in wasm. These are made explicit
   // by the ExplicitLocals pass. It has mayStore because it writes to a wasm
   // local, which is a side effect not otherwise modeled in LLVM.
   let mayStore = 1, isAsCheapAsAMove = 1 in
-  defm LOCAL_SET_#vt : I<(outs), (ins local_op:$local, vt:$src),
-                         (outs), (ins local_op:$local), [],
-                         "local.set\t$local, $src", "local.set\t$local", 0x21>;
+  defm LOCAL_SET_#reg : I<(outs), (ins local_op:$local, reg:$src),
+                          (outs), (ins local_op:$local), [],
+                          "local.set\t$local, $src", "local.set\t$local", 0x21>;
 
   // This is the actual local.tee instruction in wasm. TEEs are turned into
   // LOCAL_TEEs by the ExplicitLocals pass. It has mayStore for the same reason
   // as LOCAL_SET.
   let mayStore = 1, isAsCheapAsAMove = 1 in
-  defm LOCAL_TEE_#vt : I<(outs vt:$res), (ins local_op:$local, vt:$src),
-                         (outs), (ins local_op:$local), [],
-                         "local.tee\t$res, $local, $src", "local.tee\t$local",
-                         0x22>;
+  defm LOCAL_TEE_#reg : I<(outs reg:$res), (ins local_op:$local, reg:$src),
+                          (outs), (ins local_op:$local), [],
+                          "local.tee\t$res, $local, $src", "local.tee\t$local",
+                          0x22>;
 
   // Unused values must be dropped in some contexts.
-  defm DROP_#vt : I<(outs), (ins vt:$src), (outs), (ins), [],
-                    "drop\t$src", "drop", 0x1a>;
+  defm DROP_#reg : I<(outs), (ins reg:$src), (outs), (ins), [],
+                     "drop\t$src", "drop", 0x1a>;
 
   let mayLoad = 1 in
-  defm GLOBAL_GET_#vt : I<(outs vt:$res), (ins global_op:$local),
-                          (outs), (ins global_op:$local), [],
-                          "global.get\t$res, $local", "global.get\t$local",
-                          0x23>;
+  defm GLOBAL_GET_#reg : I<(outs reg:$res), (ins global_op:$addr),
+                           (outs), (ins global_op:$addr), [],
+                            "global.get\t$res, $addr", "global.get\t$addr",
+                           0x23>;
 
   let mayStore = 1 in
-  defm GLOBAL_SET_#vt : I<(outs), (ins global_op:$local, vt:$src),
-                          (outs), (ins global_op:$local), [],
-                          "global.set\t$local, $src", "global.set\t$local",
-                          0x24>;
-
-} // hasSideEffects = 0
+  defm GLOBAL_SET_#reg : I<(outs), (ins global_op:$addr, reg:$src),
+                           (outs), (ins global_op:$addr), [],
+                           "global.set\t$addr, $src", "global.set\t$addr",
+                           0x24>;
+
+  } // hasSideEffects = 0
+  foreach vt = reg.RegTypes in {
+    def : Pat<(vt (WebAssemblyglobal_get
+                   (WebAssemblywrapper tglobaladdr:$addr))),
+              (!cast<NI>("GLOBAL_GET_" # reg) tglobaladdr:$addr)>;
+    def : Pat<(WebAssemblyglobal_set
+               vt:$src, (WebAssemblywrapper tglobaladdr:$addr)),
+              (!cast<NI>("GLOBAL_SET_" # reg) tglobaladdr:$addr, vt:$src)>;
+  }
 }
 defm "" : LOCAL<I32, global_op32>;
 defm "" : LOCAL<I64, global_op64>;  // 64-bit only needed for pointers.
diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyInstrTable.td b/llvm/lib/Target/WebAssembly/WebAssemblyInstrTable.td
--- a/llvm/lib/Target/WebAssembly/WebAssemblyInstrTable.td
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyInstrTable.td
@@ -11,8 +11,8 @@
 /// Instructions that handle tables
 //===----------------------------------------------------------------------===//
 
-
 multiclass TABLE<WebAssemblyRegClass rt> {
+  let mayLoad = 1 in
   defm TABLE_GET_#rt : I<(outs rt:$res), (ins table32_op:$table),
                          (outs), (ins table32_op:$table),
                          [],
@@ -20,6 +20,7 @@
                          "table.get\t$table",
                          0x25>;
 
+  let mayStore = 1 in
   defm TABLE_SET_#rt : I<(outs), (ins table32_op:$table, rt:$val, I32:$i),
                          (outs), (ins table32_op:$table),
                          [],
@@ -46,6 +47,17 @@
 defm "" : TABLE<FUNCREF>, Requires<[HasReferenceTypes]>;
 defm "" : TABLE<EXTERNREF>, Requires<[HasReferenceTypes]>;
 
+def wasm_table_set_t : SDTypeProfile<0, 3, []>;
+def wasm_table_set : SDNode<"WebAssemblyISD::TABLE_SET", wasm_table_set_t,
+                            [SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;
+
+def : Pat<(wasm_table_set i32:$table, i32:$idx, funcref:$r),
+          (TABLE_SET_FUNCREF i32:$table, i32:$idx, funcref:$r)>,
+          Requires<[HasReferenceTypes]>;
+def : Pat<(wasm_table_set i32:$table, i32:$idx, externref:$r),
+          (TABLE_SET_EXTERNREF i32:$table, i32:$idx, externref:$r)>,
+          Requires<[HasReferenceTypes]>;
+
 defm TABLE_SIZE : I<(outs I32:$sz), (ins table32_op:$table),
                     (outs), (ins table32_op:$table),
                     [],
diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyMCInstLower.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyMCInstLower.cpp
--- a/llvm/lib/Target/WebAssembly/WebAssemblyMCInstLower.cpp
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyMCInstLower.cpp
@@ -198,6 +198,10 @@
     return wasm::ValType::F64;
   if (RC == &WebAssembly::V128RegClass)
     return wasm::ValType::V128;
+  if (RC == &WebAssembly::EXTERNREFRegClass)
+    return wasm::ValType::EXTERNREF;
+  if (RC == &WebAssembly::FUNCREFRegClass)
+    return wasm::ValType::FUNCREF;
   llvm_unreachable("Unexpected register class");
 }
 
diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyTargetMachine.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyTargetMachine.cpp
--- a/llvm/lib/Target/WebAssembly/WebAssemblyTargetMachine.cpp
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyTargetMachine.cpp
@@ -112,6 +112,12 @@
   return *RM;
 }
 
+// Check for reference types in Feature String, in order to extend target
+// description string
+static bool hasReferenceTypes(const StringRef &FS) {
+  return FS.find("+reference-types") != StringRef::npos;
+}
+
 /// Create an WebAssembly architecture model.
 ///
 WebAssemblyTargetMachine::WebAssemblyTargetMachine(
@@ -119,8 +125,13 @@
     const TargetOptions &Options, Optional<Reloc::Model> RM,
     Optional<CodeModel::Model> CM, CodeGenOpt::Level OL, bool JIT)
     : LLVMTargetMachine(T,
-                        TT.isArch64Bit() ? "e-m:e-p:64:64-i64:64-n32:64-S128"
-                                         : "e-m:e-p:32:32-i64:64-n32:64-S128",
+                        TT.isArch64Bit()
+                            ? (hasReferenceTypes(FS)
+                                   ? "e-m:e-p:64:64-i64:64-n32:64-S128-ni:1:10:20"
+                                   : "e-m:e-p:64:64-i64:64-n32:64-S128-ni:1")
+                            : (hasReferenceTypes(FS)
+                                   ? "e-m:e-p:32:32-i64:64-n32:64-S128-ni:1:10:20"
+                                   : "e-m:e-p:32:32-i64:64-n32:64-S128-ni:1"),
                         TT, CPU, FS, Options, getEffectiveRelocModel(RM, TT),
                         getEffectiveCodeModel(CM, CodeModel::Large), OL),
       TLOF(new WebAssemblyTargetObjectFile()) {
diff --git a/llvm/test/CodeGen/WebAssembly/externref-globalget.ll b/llvm/test/CodeGen/WebAssembly/externref-globalget.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/WebAssembly/externref-globalget.ll
@@ -0,0 +1,19 @@
+; RUN: llc < %s --mtriple=wasm32-unknown-unknown -asm-verbose=false -mattr=+reference-types | FileCheck %s
+
+%extern = type opaque
+%externref = type %extern addrspace(10)* ;; addrspace 10 is nonintegral
+
+@externref_global = local_unnamed_addr addrspace(1) global %externref undef
+
+define %externref @return_externref_global() {
+  ;; this generates a global.get of @externref_global
+  %ref = load %externref, %externref addrspace(1)* @externref_global
+  ret %externref %ref
+}
+
+; CHECK-LABEL: return_externref_global:
+; CHECK-NEXT: functype       return_externref_global () -> (externref)
+; CHECK-NEXT: global.get externref_global
+; CHECK-NEXT: end_function
+
+; CHECK: .globl externref_global
diff --git a/llvm/test/CodeGen/WebAssembly/externref-globalset.ll b/llvm/test/CodeGen/WebAssembly/externref-globalset.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/WebAssembly/externref-globalset.ll
@@ -0,0 +1,20 @@
+; RUN: llc --mtriple=wasm32-unknown-unknown -asm-verbose=false -mattr=+reference-types < %s | FileCheck %s
+
+%extern = type opaque
+%externref = type %extern addrspace(10)* ;; addrspace 1 is nonintegral
+
+@externref_global = local_unnamed_addr addrspace(1) global %externref undef
+
+define void @set_externref_global(%externref %g) {
+  ;; this generates a global.set of @externref.global
+  store %externref %g, %externref addrspace(1)* @externref_global
+  ret void
+}
+
+; CHECK-LABEL: set_externref_global:
+; CHECK-NEXT: functype       set_externref_global (externref) -> ()
+; CHECK-NEXT: local.get      0
+; CHECK-NEXT: global.set     externref_global
+; CHECK-NEXT: end_function
+
+; CHECK: .globl externref_global
diff --git a/llvm/test/CodeGen/WebAssembly/externref-inttoptr.ll b/llvm/test/CodeGen/WebAssembly/externref-inttoptr.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/WebAssembly/externref-inttoptr.ll
@@ -0,0 +1,11 @@
+; RUN: not llc --mtriple=wasm32-unknown-unknown -asm-verbose=false -mattr=+reference-types < %s 2>&1 | FileCheck %s --check-prefix=CHECK-ERROR
+
+%extern = type opaque
+%externref = type %extern addrspace(10)*
+
+define %externref @int_to_externref(i32 %i) {
+  %ref = inttoptr i32 %i to %externref
+  ret %externref %ref
+}
+
+; CHECK-ERROR: inttoptr not supported for non-integral pointers
diff --git a/llvm/test/CodeGen/WebAssembly/externref-ptrtoint.ll b/llvm/test/CodeGen/WebAssembly/externref-ptrtoint.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/WebAssembly/externref-ptrtoint.ll
@@ -0,0 +1,11 @@
+; RUN: not llc --mtriple=wasm32-unknown-unknown -asm-verbose=false -mattr=+reference-types < %s 2>&1 | FileCheck %s --check-prefix=CHECK-ERROR
+
+%extern = type opaque
+%externref = type %extern addrspace(10)*
+
+define i32 @externref_to_int(%externref %ref) {
+  %i = ptrtoint %externref %ref to i32
+  ret i32 %i
+}
+
+; CHECK-ERROR: ptrtoint not supported for non-integral pointers
diff --git a/llvm/test/CodeGen/WebAssembly/externref-undef.ll b/llvm/test/CodeGen/WebAssembly/externref-undef.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/WebAssembly/externref-undef.ll
@@ -0,0 +1,17 @@
+; RUN: llc < %s --mtriple=wasm32-unknown-unknown -asm-verbose=false -mattr=+reference-types | FileCheck %s
+
+%extern = type opaque
+%externref = type %extern addrspace(10)* ;; addrspace 1 is nonintegral
+
+@externref_global = local_unnamed_addr addrspace(1) global %externref undef
+
+define %extern @return_extern_undef() {
+  ret %extern undef
+}
+
+; CHECK-LABEL: return_extern_undef:
+; CHECK-NEXT: functype       return_extern_undef () -> ()
+; CHECK-NEXT: end_function
+
+; CHECK: .globl externref_global
+
diff --git a/llvm/test/CodeGen/WebAssembly/externref-unsized-load.ll b/llvm/test/CodeGen/WebAssembly/externref-unsized-load.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/WebAssembly/externref-unsized-load.ll
@@ -0,0 +1,11 @@
+; RUN: not llc --mtriple=wasm32-unknown-unknown -asm-verbose=false -mattr=+reference-types < %s 2>&1 | FileCheck %s --check-prefix=CHECK-ERROR
+
+%extern = type opaque
+%externref = type %extern addrspace(10)*
+
+define void @load_extern(%externref %ref) {
+  %e = load %extern, %externref %ref
+  ret void
+}
+
+; CHECK-ERROR: error: loading unsized types is not allowed
diff --git a/llvm/test/CodeGen/WebAssembly/externref-unsized-store.ll b/llvm/test/CodeGen/WebAssembly/externref-unsized-store.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/WebAssembly/externref-unsized-store.ll
@@ -0,0 +1,11 @@
+; RUN: not llc --mtriple=wasm32-unknown-unknown -asm-verbose=false -mattr=+reference-types < %s 2>&1 | FileCheck %s --check-prefix=CHECK-ERROR
+
+%extern = type opaque
+%externref = type %extern addrspace(10)*
+
+define void @store_extern(%externref %ref) {
+  store %extern undef, %externref %ref
+  ret void
+}
+
+; CHECK-ERROR: error: storing unsized types is not allowed
diff --git a/llvm/test/CodeGen/WebAssembly/funcref-call.ll b/llvm/test/CodeGen/WebAssembly/funcref-call.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/WebAssembly/funcref-call.ll
@@ -0,0 +1,23 @@
+; RUN: llc < %s --mtriple=wasm32-unknown-unknown -asm-verbose=false -mattr=+reference-types | FileCheck %s
+
+%func = type void ()
+%funcref = type %func addrspace(20)* ;; addrspace 20 is nonintegral
+
+define void @call_funcref(%funcref %ref) {
+  call addrspace(20) void %ref() 
+  ret void
+}
+
+; CHECK-LABEL: call_funcref:
+; CHECK-NEXT: functype       call_funcref (funcref) -> ()
+; CHECK-NEXT: i32.const 0
+; CHECK-NEXT: local.get 0
+; CHECK-NEXT: table.set __funcref_call_table
+; CHECK-NEXT: local.get 0
+; CHECK-NEXT: call_indirect __funcref_call_table, () -> ()
+; CHECK-NEXT: i32.const 0
+; CHECK-NEXT: ref.null func
+; CHECK-NEXT: table.set __funcref_call_table
+; CHECK-NEXT: end_function
+
+; CHECK: .tabletype __funcref_call_table, funcref
diff --git a/llvm/test/CodeGen/WebAssembly/funcref-globalget.ll b/llvm/test/CodeGen/WebAssembly/funcref-globalget.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/WebAssembly/funcref-globalget.ll
@@ -0,0 +1,19 @@
+; RUN: llc < %s --mtriple=wasm32-unknown-unknown -asm-verbose=false -mattr=+reference-types | FileCheck %s
+
+%func = type opaque
+%funcref = type %func addrspace(20)* ;; addrspace 20 is nonintegral
+
+@funcref_global = local_unnamed_addr addrspace(1) global %funcref undef
+
+define %funcref @return_funcref_global() {
+  ;; this generates a global.get of @funcref_global
+  %ref = load %funcref, %funcref addrspace(1)* @funcref_global
+  ret %funcref %ref
+}
+
+; CHECK-LABEL: return_funcref_global:
+; CHECK-NEXT: .functype       return_funcref_global () -> (funcref)
+; CHECK-NEXT: global.get funcref_global
+; CHECK-NEXT: end_function
+
+; CHECK: .globl funcref_global
diff --git a/llvm/test/CodeGen/WebAssembly/funcref-globalset.ll b/llvm/test/CodeGen/WebAssembly/funcref-globalset.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/WebAssembly/funcref-globalset.ll
@@ -0,0 +1,20 @@
+; RUN: llc < %s --mtriple=wasm32-unknown-unknown -asm-verbose=false -mattr=+reference-types | FileCheck %s
+
+%func = type opaque
+%funcref = type %func addrspace(20)* ;; addrspace 20 is nonintegral
+
+@funcref_global = local_unnamed_addr addrspace(1) global %funcref undef
+
+define void @set_funcref_global(%funcref %g) {
+  ;; this generates a global.set of @funcref_global
+  store %funcref %g, %funcref addrspace(1)* @funcref_global
+  ret void
+}
+
+; CHECK-LABEL: set_funcref_global:
+; CHECK-NEXT: functype       set_funcref_global (funcref) -> ()
+; CHECK-NEXT: local.get      0
+; CHECK-NEXT: global.set     funcref_global
+; CHECK-NEXT: end_function
+
+; CHECK: .globl funcref_global
diff --git a/llvm/test/CodeGen/WebAssembly/global-get.ll b/llvm/test/CodeGen/WebAssembly/global-get.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/WebAssembly/global-get.ll
@@ -0,0 +1,54 @@
+; RUN: llc < %s --mtriple=wasm32-unknown-unknown -asm-verbose=false | FileCheck %s
+
+@i32_global = local_unnamed_addr addrspace(1) global i32 undef
+@i64_global = local_unnamed_addr addrspace(1) global i64 undef
+@f32_global = local_unnamed_addr addrspace(1) global float undef
+@f64_global = local_unnamed_addr addrspace(1) global double undef
+
+define i32 @return_i32_global() {
+; CHECK-LABEL: return_i32_global:
+; CHECK-NEXT: functype       return_i32_global () -> (i32)
+; CHECK-NEXT: global.get i32_global
+; CHECK-NEXT: end_function
+  %v = load i32, i32 addrspace(1)* @i32_global
+  ret i32 %v
+}
+
+define i64 @return_i64_global() {
+; CHECK-LABEL: return_i64_global:
+; CHECK-NEXT: functype       return_i64_global () -> (i64)
+; CHECK-NEXT: global.get i64_global
+; CHECK-NEXT: end_function
+  %v = load i64, i64 addrspace(1)* @i64_global
+  ret i64 %v
+}
+
+define float @return_f32_global() {
+; CHECK-LABEL: return_f32_global:
+; CHECK-NEXT: functype       return_f32_global () -> (f32)
+; CHECK-NEXT: global.get f32_global
+; CHECK-NEXT: end_function
+  %v = load float, float addrspace(1)* @f32_global
+  ret float %v
+}
+
+define double @return_f64_global() {
+; CHECK-LABEL: return_f64_global:
+; CHECK-NEXT: functype       return_f64_global () -> (f64)
+; CHECK-NEXT: global.get f64_global
+; CHECK-NEXT: end_function
+  %v = load double, double addrspace(1)* @f64_global
+  ret double %v
+}
+
+
+;; LLVM doesn't yet declare proper WebAssembly globals for these values,
+;; instead placing them in linear memory.  To fix in a followup.
+; FIXME-CHECK: .globl i32_global
+; FIXME-CHECK: .globaltype i32_global, i32
+; FIXME-CHECK: .globl i64_global
+; FIXME-CHECK: .globaltype i64_global, i64
+; FIXME-CHECK: .globl f32_global
+; FIXME-CHECK: .globaltype f32_global, f32
+; FIXME-CHECK: .globl f64_global
+; FIXME-CHECK: .globaltype f64_global, f64
diff --git a/llvm/test/CodeGen/WebAssembly/global-set.ll b/llvm/test/CodeGen/WebAssembly/global-set.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/WebAssembly/global-set.ll
@@ -0,0 +1,57 @@
+; RUN: llc --mtriple=wasm32-unknown-unknown -asm-verbose=false < %s | FileCheck %s
+
+@i32_global = local_unnamed_addr addrspace(1) global i32 undef
+@i64_global = local_unnamed_addr addrspace(1) global i64 undef
+@f32_global = local_unnamed_addr addrspace(1) global float undef
+@f64_global = local_unnamed_addr addrspace(1) global double undef
+
+define void @set_i32_global(i32 %v) {
+; CHECK-LABEL: set_i32_global:
+; CHECK-NEXT: functype       set_i32_global (i32) -> ()
+; CHECK-NEXT: local.get 0
+; CHECK-NEXT: global.set i32_global
+; CHECK-NEXT: end_function
+  store i32 %v, i32 addrspace(1)* @i32_global
+  ret void
+}
+
+define void @set_i64_global(i64 %v) {
+; CHECK-LABEL: set_i64_global:
+; CHECK-NEXT: functype       set_i64_global (i64) -> ()
+; CHECK-NEXT: local.get 0
+; CHECK-NEXT: global.set i64_global
+; CHECK-NEXT: end_function
+  store i64 %v, i64 addrspace(1)* @i64_global
+  ret void
+}
+
+define void @set_f32_global(float %v) {
+; CHECK-LABEL: set_f32_global:
+; CHECK-NEXT: functype       set_f32_global (f32) -> ()
+; CHECK-NEXT: local.get 0
+; CHECK-NEXT: global.set f32_global
+; CHECK-NEXT: end_function
+  store float %v, float addrspace(1)* @f32_global
+  ret void
+}
+
+define void @set_f64_global(double %v) {
+; CHECK-LABEL: set_f64_global:
+; CHECK-NEXT: functype       set_f64_global (f64) -> ()
+; CHECK-NEXT: local.get 0
+; CHECK-NEXT: global.set f64_global
+; CHECK-NEXT: end_function
+  store double %v, double addrspace(1)* @f64_global
+  ret void
+}
+
+;; LLVM doesn't yet declare proper WebAssembly globals for these values,
+;; instead placing them in linear memory.  To fix in a followup.
+; FIXME-CHECK: .globl i32_global
+; FIXME-CHECK: .globaltype i32_global, i32
+; FIXME-CHECK: .globl i64_global
+; FIXME-CHECK: .globaltype i64_global, i64
+; FIXME-CHECK: .globl f32_global
+; FIXME-CHECK: .globaltype f32_global, f32
+; FIXME-CHECK: .globl f64_global
+; FIXME-CHECK: .globaltype f64_global, f64