[WebAssembly] Implementation of global.get/set for reftypes in LLVM IR

Reland of 31859f8.

This change implements new DAG notes GLOBAL_GET/GLOBAL_SET, and
lowering methods for load and stores of reference types from IR
globals. Once the lowering creates the new nodes, tablegen pattern
matches those and converts them to Wasm global.get/set.

Reviewed By: tlively

Differential Revision: https://reviews.llvm.org/D104797

Author: pmatos

clang/lib/Basic/Targets/WebAssembly.h

@@ -150,9 +150,9 @@ class LLVM_LIBRARY_VISIBILITY WebAssembly32TargetInfo
                                    const TargetOptions &Opts)
       : WebAssemblyTargetInfo(T, Opts) {
     if (T.isOSEmscripten())
-      resetDataLayout("e-m:e-p:32:32-i64:64-f128:64-n32:64-S128-ni:1");
+      resetDataLayout("e-m:e-p:32:32-i64:64-f128:64-n32:64-S128-ni:1:10:20");
     else
-      resetDataLayout("e-m:e-p:32:32-i64:64-n32:64-S128-ni:1");
+      resetDataLayout("e-m:e-p:32:32-i64:64-n32:64-S128-ni:1:10:20");
   }
 
 protected:
@@ -172,9 +172,9 @@ class LLVM_LIBRARY_VISIBILITY WebAssembly64TargetInfo
     PtrDiffType = SignedLong;
     IntPtrType = SignedLong;
     if (T.isOSEmscripten())
-      resetDataLayout("e-m:e-p:64:64-i64:64-f128:64-n32:64-S128-ni:1");
+      resetDataLayout("e-m:e-p:64:64-i64:64-f128:64-n32:64-S128-ni:1:10:20");
     else
-      resetDataLayout("e-m:e-p:64:64-i64:64-n32:64-S128-ni:1");
+      resetDataLayout("e-m:e-p:64:64-i64:64-n32:64-S128-ni:1:10:20");
   }
 
 protected:

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-ni:1"
+// WEBASSEMBLY32: target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128-ni:1:10:20"
 
 // 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-ni:1"
+// WEBASSEMBLY64: target datalayout = "e-m:e-p:64:64-i64:64-n32:64-S128-ni:1:10:20"
 
 // RUN: %clang_cc1 -triple lanai-unknown-unknown -o - -emit-llvm %s | \
 // RUN: FileCheck %s -check-prefix=LANAI

llvm/include/llvm/CodeGen/TargetLowering.h

@@ -349,7 +349,7 @@ class TargetLoweringBase {
   /// 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));
   }
 

llvm/include/llvm/CodeGen/ValueTypes.h

@@ -120,6 +120,12 @@ namespace llvm {
       return changeExtendedTypeToInteger();
     }
 
+    /// Test if the given EVT has zero size, this will fail if called on a
+    /// scalable type
+    bool isZeroSized() const {
+      return !isScalableVector() && 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 +213,9 @@ namespace llvm {
     }
 
     /// 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 {

llvm/lib/CodeGen/CodeGenPrepare.cpp

@@ -6465,6 +6465,10 @@ bool CodeGenPrepare::optimizeLoadExt(LoadInst *Load) {
 
   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);
 

llvm/lib/CodeGen/MachineOperand.cpp

@@ -1180,7 +1180,7 @@ void MachineMemOperand::print(raw_ostream &OS, ModuleSlotTracker &MST,
        << "unknown-address";
   }
   MachineOperand::printOperandOffset(OS, getOffset());
-  if (getAlign() != getSize())
+  if (getSize() > 0 && getAlign() != getSize())
     OS << ", align " << getAlign().value();
   if (getAlign() != getBaseAlign())
     OS << ", basealign " << getBaseAlign().value();

llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp

@@ -23243,6 +23243,10 @@ bool DAGCombiner::parallelizeChainedStores(StoreSDNode *St) {
   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.

llvm/lib/CodeGen/TargetLoweringBase.cpp

@@ -1710,7 +1710,7 @@ bool TargetLoweringBase::allowsMemoryAccessForAlignment(
   // 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;

llvm/lib/CodeGen/ValueTypes.cpp

@@ -198,6 +198,10 @@ Type *EVT::getTypeForEVT(LLVMContext &Context) const {
   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:

llvm/lib/Target/WebAssembly/Utils/WebAssemblyUtilities.cpp

@@ -116,6 +116,31 @@ MCSymbolWasm *WebAssembly::getOrCreateFunctionTableSymbol(
   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));
+
+    // Setting Weak ensure only one table is left after linking when multiple
+    // modules define the table.
+    Sym->setWeak(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());