Reapply: IR: add optional type to 'byval' function parameters

When we switch to opaque pointer types we will need some way to describe
how many bytes a 'byval' parameter should occupy on the stack. This adds
a (for now) optional extra type parameter.

If present, the type must match the pointee type of the argument.

The original commit did not remap byval types when linking modules, which broke
LTO. This version fixes that.

Note to front-end maintainers: if this causes test failures, it's probably
because the "byval" attribute is printed after attributes without any parameter
after this change.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@362128 91177308-0d34-0410-b5e6-96231b3b80d8

docs/LangRef.rst

@@ -1017,7 +1017,7 @@ Currently, only the following parameter attributes are defined:
     opposed to memory, though some targets use it to distinguish between
     two different kinds of registers). Use of this attribute is
     target-specific.
-``byval``
+``byval`` or ``byval(<ty>)``
     This indicates that the pointer parameter should really be passed by
     value to the function. The attribute implies that a hidden copy of
     the pointee is made between the caller and the callee, so the callee
@@ -1029,6 +1029,9 @@ Currently, only the following parameter attributes are defined:
     ``byval`` parameters). This is not a valid attribute for return
     values.
 
+    The byval attribute also supports an optional type argument, which must be
+    the same as the pointee type of the argument.
+
     The byval attribute also supports specifying an alignment with the
     align attribute. It indicates the alignment of the stack slot to
     form and the known alignment of the pointer specified to the call

docs/ReleaseNotes.rst

@@ -67,6 +67,11 @@ Changes to the LLVM IR
   type is now mandatory. Specify `i8* null` to migrate from the obsoleted
   2-field form.
 
+* The ``byval`` attribute can now take a type parameter:
+  ``byval(<ty>)``. If present it must be identical to the argument's
+  pointee type. In the next release we intend to make this parameter
+  mandatory in preparation for opaque pointer types.
+
 Changes to the ARM Backend
 --------------------------
 

include/llvm/CodeGen/TargetLowering.h

@@ -188,6 +188,7 @@ public:
     bool IsSwiftSelf : 1;
     bool IsSwiftError : 1;
     uint16_t Alignment = 0;
+    Type *ByValType = nullptr;
 
     ArgListEntry()
         : IsSExt(false), IsZExt(false), IsInReg(false), IsSRet(false),

include/llvm/IR/Argument.h

@@ -78,6 +78,9 @@ public:
   /// If this is a byval or inalloca argument, return its alignment.
   unsigned getParamAlignment() const;
 
+  /// If this is a byval argument, return its type.
+  Type *getParamByValType() const;
+
   /// Return true if this argument has the nest attribute.
   bool hasNestAttr() const;
 

include/llvm/IR/Attributes.h

@@ -90,6 +90,7 @@ public:
   static Attribute get(LLVMContext &Context, AttrKind Kind, uint64_t Val = 0);
   static Attribute get(LLVMContext &Context, StringRef Kind,
                        StringRef Val = StringRef());
+  static Attribute get(LLVMContext &Context, AttrKind Kind, Type *Ty);
 
   /// Return a uniquified Attribute object that has the specific
   /// alignment set.
@@ -102,6 +103,7 @@ public:
   static Attribute getWithAllocSizeArgs(LLVMContext &Context,
                                         unsigned ElemSizeArg,
                                         const Optional<unsigned> &NumElemsArg);
+  static Attribute getWithByValType(LLVMContext &Context, Type *Ty);
 
   //===--------------------------------------------------------------------===//
   // Attribute Accessors
@@ -117,6 +119,9 @@ public:
   /// attribute.
   bool isStringAttribute() const;
 
+  /// Return true if the attribute is a type attribute.
+  bool isTypeAttribute() const;
+
   /// Return true if the attribute is present.
   bool hasAttribute(AttrKind Val) const;
 
@@ -139,6 +144,10 @@ public:
   /// attribute to be a string attribute.
   StringRef getValueAsString() const;
 
+  /// Return the attribute's value as a Type. This requires the attribute to be
+  /// a type attribute.
+  Type *getValueAsType() const;
+
   /// Returns the alignment field of an attribute as a byte alignment
   /// value.
   unsigned getAlignment() const;
@@ -279,6 +288,7 @@ public:
   unsigned getStackAlignment() const;
   uint64_t getDereferenceableBytes() const;
   uint64_t getDereferenceableOrNullBytes() const;
+  Type *getByValType() const;
   std::pair<unsigned, Optional<unsigned>> getAllocSizeArgs() const;
   std::string getAsString(bool InAttrGrp = false) const;
 
@@ -598,6 +608,9 @@ public:
   /// Return the alignment for the specified function parameter.
   unsigned getParamAlignment(unsigned ArgNo) const;
 
+  /// Return the byval type for the specified function parameter.
+  Type *getParamByValType(unsigned ArgNo) const;
+
   /// Get the stack alignment.
   unsigned getStackAlignment(unsigned Index) const;
 
@@ -697,6 +710,7 @@ class AttrBuilder {
   uint64_t DerefBytes = 0;
   uint64_t DerefOrNullBytes = 0;
   uint64_t AllocSizeArgs = 0;
+  Type *ByValType = nullptr;
 
 public:
   AttrBuilder() = default;
@@ -772,6 +786,9 @@ public:
   /// dereferenceable_or_null attribute exists (zero is returned otherwise).
   uint64_t getDereferenceableOrNullBytes() const { return DerefOrNullBytes; }
 
+  /// Retrieve the byval type.
+  Type *getByValType() const { return ByValType; }
+
   /// Retrieve the allocsize args, if the allocsize attribute exists.  If it
   /// doesn't exist, pair(0, 0) is returned.
   std::pair<unsigned, Optional<unsigned>> getAllocSizeArgs() const;
@@ -796,6 +813,9 @@ public:
   AttrBuilder &addAllocSizeAttr(unsigned ElemSizeArg,
                                 const Optional<unsigned> &NumElemsArg);
 
+  /// This turns a byval type into the form used internally in Attribute.
+  AttrBuilder &addByValAttr(Type *Ty);
+
   /// Add an allocsize attribute, using the representation returned by
   /// Attribute.getIntValue().
   AttrBuilder &addAllocSizeAttrFromRawRepr(uint64_t RawAllocSizeRepr);

include/llvm/IR/CallSite.h

@@ -415,6 +415,11 @@ public:
     CALLSITE_DELEGATE_GETTER(getParamAlignment(ArgNo));
   }
 
+  /// Extract the byval type for a call or parameter (nullptr=unknown).
+  Type *getParamByValType(unsigned ArgNo) const {
+    CALLSITE_DELEGATE_GETTER(getParamByValType(ArgNo));
+  }
+
   /// Extract the number of dereferenceable bytes for a call or parameter
   /// (0=unknown).
   uint64_t getDereferenceableBytes(unsigned i) const {

include/llvm/IR/Function.h

@@ -431,6 +431,11 @@ public:
     return AttributeSets.getParamAlignment(ArgNo);
   }
 
+  /// Extract the byval type for a parameter (nullptr=unknown).
+  Type *getParamByValType(unsigned ArgNo) const {
+    return AttributeSets.getParamByValType(ArgNo);
+  }
+
   /// Extract the number of dereferenceable bytes for a call or
   /// parameter (0=unknown).
   /// @param i AttributeList index, referring to a return value or argument.

include/llvm/IR/InstrTypes.h

@@ -1560,6 +1560,11 @@ public:
     return Attrs.getParamAlignment(ArgNo);
   }
 
+  /// Extract the byval type for a call or parameter (nullptr=unknown).
+  Type *getParamByValType(unsigned ArgNo) const {
+    return Attrs.getParamByValType(ArgNo);
+  }
+
   /// Extract the number of dereferenceable bytes for a call or
   /// parameter (0=unknown).
   uint64_t getDereferenceableBytes(unsigned i) const {

lib/AsmParser/LLParser.cpp

@@ -1601,7 +1601,13 @@ bool LLParser::ParseOptionalParamAttrs(AttrBuilder &B) {
       B.addAlignmentAttr(Alignment);
       continue;
     }
-    case lltok::kw_byval:           B.addAttribute(Attribute::ByVal); break;
+    case lltok::kw_byval: {
+      Type *Ty;
+      if (ParseByValWithOptionalType(Ty))
+        return true;
+      B.addByValAttr(Ty);
+      continue;
+    }
     case lltok::kw_dereferenceable: {
       uint64_t Bytes;
       if (ParseOptionalDerefAttrBytes(lltok::kw_dereferenceable, Bytes))
@@ -2454,6 +2460,22 @@ bool LLParser::ParseParameterList(SmallVectorImpl<ParamInfo> &ArgList,
   return false;
 }
 
+/// ParseByValWithOptionalType
+///   ::= byval
+///   ::= byval(<ty>)
+bool LLParser::ParseByValWithOptionalType(Type *&Result) {
+  Result = nullptr;
+  if (!EatIfPresent(lltok::kw_byval))
+    return true;
+  if (!EatIfPresent(lltok::lparen))
+    return false;
+  if (ParseType(Result))
+    return true;
+  if (!EatIfPresent(lltok::rparen))
+    return Error(Lex.getLoc(), "expected ')'");
+  return false;
+}
+
 /// ParseOptionalOperandBundles
 ///    ::= /*empty*/
 ///    ::= '[' OperandBundle [, OperandBundle ]* ']'

lib/AsmParser/LLParser.h

@@ -339,6 +339,7 @@ namespace llvm {
     bool ParseFnAttributeValuePairs(AttrBuilder &B,
                                     std::vector<unsigned> &FwdRefAttrGrps,
                                     bool inAttrGrp, LocTy &BuiltinLoc);
+    bool ParseByValWithOptionalType(Type *&Result);
 
     // Module Summary Index Parsing.
     bool SkipModuleSummaryEntry();

lib/Bitcode/Reader/BitcodeReader.cpp

@@ -638,6 +638,10 @@ private:
     return getFnValueByID(ValNo, Ty);
   }
 
+  /// Upgrades old-style typeless byval attributes by adding the corresponding
+  /// argument's pointee type.
+  void propagateByValTypes(CallBase *CB);
+
   /// Converts alignment exponent (i.e. power of two (or zero)) to the
   /// corresponding alignment to use. If alignment is too large, returns
   /// a corresponding error code.
@@ -1492,6 +1496,12 @@ Error BitcodeReader::parseAttributeGroupBlock() {
           if (Error Err = parseAttrKind(Record[++i], &Kind))
             return Err;
 
+          // Upgrade old-style byval attribute to one with a type, even if it's
+          // nullptr. We will have to insert the real type when we associate
+          // this AttributeList with a function.
+          if (Kind == Attribute::ByVal)
+            B.addByValAttr(nullptr);
+
           B.addAttribute(Kind);
         } else if (Record[i] == 1) { // Integer attribute
           Attribute::AttrKind Kind;
@@ -1507,9 +1517,7 @@ Error BitcodeReader::parseAttributeGroupBlock() {
             B.addDereferenceableOrNullAttr(Record[++i]);
           else if (Kind == Attribute::AllocSize)
             B.addAllocSizeAttrFromRawRepr(Record[++i]);
-        } else {                     // String attribute
-          assert((Record[i] == 3 || Record[i] == 4) &&
-                 "Invalid attribute group entry");
+        } else if (Record[i] == 3 || Record[i] == 4) { // String attribute
           bool HasValue = (Record[i++] == 4);
           SmallString<64> KindStr;
           SmallString<64> ValStr;
@@ -1527,6 +1535,15 @@ Error BitcodeReader::parseAttributeGroupBlock() {
           }
 
           B.addAttribute(KindStr.str(), ValStr.str());
+        } else {
+          assert((Record[i] == 5 || Record[i] == 6) &&
+                 "Invalid attribute group entry");
+          bool HasType = Record[i] == 6;
+          Attribute::AttrKind Kind;
+          if (Error Err = parseAttrKind(Record[++i], &Kind))
+            return Err;
+          if (Kind == Attribute::ByVal)
+            B.addByValAttr(HasType ? getTypeByID(Record[++i]) : nullptr);
         }
       }
 
@@ -3028,6 +3045,17 @@ Error BitcodeReader::parseFunctionRecord(ArrayRef<uint64_t> Record) {
   Func->setLinkage(getDecodedLinkage(RawLinkage));
   Func->setAttributes(getAttributes(Record[4]));
 
+  // Upgrade any old-style byval without a type by propagating the argument's
+  // pointee type. There should be no opaque pointers where the byval type is
+  // implicit.
+  for (auto &Arg : Func->args()) {
+    if (Arg.hasByValAttr() && !Arg.getParamByValType()) {
+      Arg.removeAttr(Attribute::ByVal);
+      Arg.addAttr(Attribute::getWithByValType(
+          Context, Arg.getType()->getPointerElementType()));
+    }
+  }
+
   unsigned Alignment;
   if (Error Err = parseAlignmentValue(Record[5], Alignment))
     return Err;
@@ -3441,6 +3469,19 @@ Error BitcodeReader::typeCheckLoadStoreInst(Type *ValType, Type *PtrType) {
   return Error::success();
 }
 
+void BitcodeReader::propagateByValTypes(CallBase *CB) {
+  for (unsigned i = 0; i < CB->getNumArgOperands(); ++i) {
+    if (CB->paramHasAttr(i, Attribute::ByVal) &&
+        !CB->getAttribute(i, Attribute::ByVal).getValueAsType()) {
+      CB->removeParamAttr(i, Attribute::ByVal);
+      CB->addParamAttr(
+          i, Attribute::getWithByValType(
+                 Context,
+                 CB->getArgOperand(i)->getType()->getPointerElementType()));
+    }
+  }
+}
+
 /// Lazily parse the specified function body block.
 Error BitcodeReader::parseFunctionBody(Function *F) {
   if (Stream.EnterSubBlock(bitc::FUNCTION_BLOCK_ID))
@@ -4256,6 +4297,8 @@ Error BitcodeReader::parseFunctionBody(Function *F) {
       cast<InvokeInst>(I)->setCallingConv(
           static_cast<CallingConv::ID>(CallingConv::MaxID & CCInfo));
       cast<InvokeInst>(I)->setAttributes(PAL);
+      propagateByValTypes(cast<CallBase>(I));
+
       break;
     }
     case bitc::FUNC_CODE_INST_RESUME: { // RESUME: [opval]
@@ -4731,6 +4774,7 @@ Error BitcodeReader::parseFunctionBody(Function *F) {
         TCK = CallInst::TCK_NoTail;
       cast<CallInst>(I)->setTailCallKind(TCK);
       cast<CallInst>(I)->setAttributes(PAL);
+      propagateByValTypes(cast<CallBase>(I));
       if (FMF.any()) {
         if (!isa<FPMathOperator>(I))
           return error("Fast-math-flags specified for call without "

lib/Bitcode/Writer/BitcodeWriter.cpp

@@ -747,7 +747,7 @@ void ModuleBitcodeWriter::writeAttributeGroupTable() {
         Record.push_back(1);
         Record.push_back(getAttrKindEncoding(Attr.getKindAsEnum()));
         Record.push_back(Attr.getValueAsInt());
-      } else {
+      } else if (Attr.isStringAttribute()) {
         StringRef Kind = Attr.getKindAsString();
         StringRef Val = Attr.getValueAsString();
 
@@ -758,6 +758,13 @@ void ModuleBitcodeWriter::writeAttributeGroupTable() {
           Record.append(Val.begin(), Val.end());
           Record.push_back(0);
         }
+      } else {
+        assert(Attr.isTypeAttribute());
+        Type *Ty = Attr.getValueAsType();
+        Record.push_back(Ty ? 6 : 5);
+        Record.push_back(getAttrKindEncoding(Attr.getKindAsEnum()));
+        if (Ty)
+          Record.push_back(VE.getTypeID(Attr.getValueAsType()));
       }
     }
 
@@ -4126,15 +4133,15 @@ void ModuleBitcodeWriter::write() {
   // Emit blockinfo, which defines the standard abbreviations etc.
   writeBlockInfo();
 
+  // Emit information describing all of the types in the module.
+  writeTypeTable();
+
   // Emit information about attribute groups.
   writeAttributeGroupTable();
 
   // Emit information about parameter attributes.
   writeAttributeTable();
 
-  // Emit information describing all of the types in the module.
-  writeTypeTable();
-
   writeComdats();
 
   // Emit top-level description of module, including target triple, inline asm,

lib/Bitcode/Writer/ValueEnumerator.cpp

@@ -949,9 +949,11 @@ void ValueEnumerator::incorporateFunction(const Function &F) {
   incorporateFunctionMetadata(F);
 
   // Adding function arguments to the value table.
-  for (const auto &I : F.args())
+  for (const auto &I : F.args()) {
     EnumerateValue(&I);
-
+    if (I.hasAttribute(Attribute::ByVal) && I.getParamByValType())
+      EnumerateType(I.getParamByValType());
+  }
   FirstFuncConstantID = Values.size();
 
   // Add all function-level constants to the value table.

lib/CodeGen/GlobalISel/CallLowering.cpp

@@ -87,7 +87,10 @@ void CallLowering::setArgFlags(CallLowering::ArgInfo &Arg, unsigned OpIdx,
 
   if (Arg.Flags.isByVal() || Arg.Flags.isInAlloca()) {
     Type *ElementTy = cast<PointerType>(Arg.Ty)->getElementType();
-    Arg.Flags.setByValSize(DL.getTypeAllocSize(ElementTy));
+
+    auto Ty = Attrs.getAttribute(OpIdx, Attribute::ByVal).getValueAsType();
+    Arg.Flags.setByValSize(DL.getTypeAllocSize(Ty ? Ty : ElementTy));
+
     // For ByVal, alignment should be passed from FE.  BE will guess if
     // this info is not there but there are cases it cannot get right.
     unsigned FrameAlign;

lib/CodeGen/SelectionDAG/FastISel.cpp

@@ -1204,9 +1204,11 @@ bool FastISel::lowerCallTo(CallLoweringInfo &CLI) {
     if (Arg.IsByVal || Arg.IsInAlloca) {
       PointerType *Ty = cast<PointerType>(Arg.Ty);
       Type *ElementTy = Ty->getElementType();
-      unsigned FrameSize = DL.getTypeAllocSize(ElementTy);
-      // For ByVal, alignment should come from FE. BE will guess if this info is
-      // not there, but there are cases it cannot get right.
+      unsigned FrameSize =
+          DL.getTypeAllocSize(Arg.ByValType ? Arg.ByValType : ElementTy);
+
+      // For ByVal, alignment should come from FE. BE will guess if this info
+      // is not there, but there are cases it cannot get right.
       unsigned FrameAlign = Arg.Alignment;
       if (!FrameAlign)
         FrameAlign = TLI.getByValTypeAlignment(ElementTy, DL);

lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp

@@ -9076,8 +9076,11 @@ TargetLowering::LowerCallTo(TargetLowering::CallLoweringInfo &CLI) const {
       if (Args[i].IsByVal || Args[i].IsInAlloca) {
         PointerType *Ty = cast<PointerType>(Args[i].Ty);
         Type *ElementTy = Ty->getElementType();
-        Flags.setByValSize(DL.getTypeAllocSize(ElementTy));
-        // For ByVal, alignment should come from FE.  BE will guess if this
+
+        unsigned FrameSize = DL.getTypeAllocSize(
+            Args[i].ByValType ? Args[i].ByValType : ElementTy);
+        Flags.setByValSize(FrameSize);
+
         // info is not there but there are cases it cannot get right.
         unsigned FrameAlign;
         if (Args[i].Alignment)
@@ -9574,9 +9577,14 @@ void SelectionDAGISel::LowerArguments(const Function &F) {
       if (Flags.isByVal() || Flags.isInAlloca()) {
         PointerType *Ty = cast<PointerType>(Arg.getType());
         Type *ElementTy = Ty->getElementType();
-        Flags.setByValSize(DL.getTypeAllocSize(ElementTy));
-        // For ByVal, alignment should be passed from FE.  BE will guess if
-        // this info is not there but there are cases it cannot get right.
+
+        // For ByVal, size and alignment should be passed from FE.  BE will
+        // guess if this info is not there but there are cases it cannot get
+        // right.
+        unsigned FrameSize = DL.getTypeAllocSize(
+            Arg.getParamByValType() ? Arg.getParamByValType() : ElementTy);
+        Flags.setByValSize(FrameSize);
+
         unsigned FrameAlign;
         if (Arg.getParamAlignment())
           FrameAlign = Arg.getParamAlignment();

lib/CodeGen/SelectionDAG/TargetLowering.cpp

@@ -112,6 +112,7 @@ void TargetLoweringBase::ArgListEntry::setAttributes(const CallBase *Call,
   IsSwiftSelf = Call->paramHasAttr(ArgIdx, Attribute::SwiftSelf);
   IsSwiftError = Call->paramHasAttr(ArgIdx, Attribute::SwiftError);
   Alignment = Call->getParamAlignment(ArgIdx);
+  ByValType = Call->getParamByValType(ArgIdx);
 }
 
 /// Generate a libcall taking the given operands as arguments and returning a

lib/IR/AttributeImpl.h

@@ -29,6 +29,7 @@
 namespace llvm {
 
 class LLVMContext;
+class Type;
 
 //===----------------------------------------------------------------------===//
 /// \class
@@ -41,7 +42,8 @@ protected:
   enum AttrEntryKind {
     EnumAttrEntry,
     IntAttrEntry,
-    StringAttrEntry
+    StringAttrEntry,
+    TypeAttrEntry,
   };
 
   AttributeImpl(AttrEntryKind KindID) : KindID(KindID) {}
@@ -56,6 +58,7 @@ public:
   bool isEnumAttribute() const { return KindID == EnumAttrEntry; }
   bool isIntAttribute() const { return KindID == IntAttrEntry; }
   bool isStringAttribute() const { return KindID == StringAttrEntry; }
+  bool isTypeAttribute() const { return KindID == TypeAttrEntry; }
 
   bool hasAttribute(Attribute::AttrKind A) const;
   bool hasAttribute(StringRef Kind) const;
@@ -66,16 +69,20 @@ public:
   StringRef getKindAsString() const;
   StringRef getValueAsString() const;
 
+  Type *getValueAsType() const;
+
   /// Used when sorting the attributes.
   bool operator<(const AttributeImpl &AI) const;
 
   void Profile(FoldingSetNodeID &ID) const {
     if (isEnumAttribute())
-      Profile(ID, getKindAsEnum(), 0);
+      Profile(ID, getKindAsEnum(), static_cast<uint64_t>(0));
     else if (isIntAttribute())
       Profile(ID, getKindAsEnum(), getValueAsInt());
-    else
+    else if (isStringAttribute())
       Profile(ID, getKindAsString(), getValueAsString());
+    else
+      Profile(ID, getKindAsEnum(), getValueAsType());
   }
 
   static void Profile(FoldingSetNodeID &ID, Attribute::AttrKind Kind,
@@ -88,6 +95,12 @@ public:
     ID.AddString(Kind);
     if (!Values.empty()) ID.AddString(Values);
   }
+
+  static void Profile(FoldingSetNodeID &ID, Attribute::AttrKind Kind,
+                      Type *Ty) {
+    ID.AddInteger(Kind);
+    ID.AddPointer(Ty);
+  }
 };
 
 //===----------------------------------------------------------------------===//
@@ -145,6 +158,18 @@ public:
   StringRef getStringValue() const { return Val; }
 };
 
+class TypeAttributeImpl : public EnumAttributeImpl {
+  virtual void anchor();
+
+  Type *Ty;
+
+public:
+  TypeAttributeImpl(Attribute::AttrKind Kind, Type *Ty)
+      : EnumAttributeImpl(TypeAttrEntry, Kind), Ty(Ty) {}
+
+  Type *getTypeValue() const { return Ty; }
+};
+
 //===----------------------------------------------------------------------===//
 /// \class
 /// This class represents a group of attributes that apply to one
@@ -189,6 +214,7 @@ public:
   uint64_t getDereferenceableOrNullBytes() const;
   std::pair<unsigned, Optional<unsigned>> getAllocSizeArgs() const;
   std::string getAsString(bool InAttrGrp) const;
+  Type *getByValType() const;
 
   using iterator = const Attribute *;
 

lib/IR/Attributes.cpp

@@ -121,6 +121,27 @@ Attribute Attribute::get(LLVMContext &Context, StringRef Kind, StringRef Val) {
   return Attribute(PA);
 }
 
+Attribute Attribute::get(LLVMContext &Context, Attribute::AttrKind Kind,
+                         Type *Ty) {
+  LLVMContextImpl *pImpl = Context.pImpl;
+  FoldingSetNodeID ID;
+  ID.AddInteger(Kind);
+  ID.AddPointer(Ty);
+
+  void *InsertPoint;
+  AttributeImpl *PA = pImpl->AttrsSet.FindNodeOrInsertPos(ID, InsertPoint);
+
+  if (!PA) {
+    // If we didn't find any existing attributes of the same shape then create a
+    // new one and insert it.
+    PA = new TypeAttributeImpl(Kind, Ty);
+    pImpl->AttrsSet.InsertNode(PA, InsertPoint);
+  }
+
+  // Return the Attribute that we found or created.
+  return Attribute(PA);
+}
+
 Attribute Attribute::getWithAlignment(LLVMContext &Context, uint64_t Align) {
   assert(isPowerOf2_32(Align) && "Alignment must be a power of two.");
   assert(Align <= 0x40000000 && "Alignment too large.");
@@ -146,6 +167,10 @@ Attribute Attribute::getWithDereferenceableOrNullBytes(LLVMContext &Context,
   return get(Context, DereferenceableOrNull, Bytes);
 }
 
+Attribute Attribute::getWithByValType(LLVMContext &Context, Type *Ty) {
+  return get(Context, ByVal, Ty);
+}
+
 Attribute
 Attribute::getWithAllocSizeArgs(LLVMContext &Context, unsigned ElemSizeArg,
                                 const Optional<unsigned> &NumElemsArg) {
@@ -170,9 +195,13 @@ bool Attribute::isStringAttribute() const {
   return pImpl && pImpl->isStringAttribute();
 }
 
+bool Attribute::isTypeAttribute() const {
+  return pImpl && pImpl->isTypeAttribute();
+}
+
 Attribute::AttrKind Attribute::getKindAsEnum() const {
   if (!pImpl) return None;
-  assert((isEnumAttribute() || isIntAttribute()) &&
+  assert((isEnumAttribute() || isIntAttribute() || isTypeAttribute()) &&
          "Invalid attribute type to get the kind as an enum!");
   return pImpl->getKindAsEnum();
 }
@@ -198,6 +227,14 @@ StringRef Attribute::getValueAsString() const {
   return pImpl->getValueAsString();
 }
 
+Type *Attribute::getValueAsType() const {
+  if (!pImpl) return {};
+  assert(isTypeAttribute() &&
+         "Invalid attribute type to get the value as a type!");
+  return pImpl->getValueAsType();
+}
+
+
 bool Attribute::hasAttribute(AttrKind Kind) const {
   return (pImpl && pImpl->hasAttribute(Kind)) || (!pImpl && Kind == None);
 }
@@ -252,8 +289,6 @@ std::string Attribute::getAsString(bool InAttrGrp) const {
     return "argmemonly";
   if (hasAttribute(Attribute::Builtin))
     return "builtin";
-  if (hasAttribute(Attribute::ByVal))
-    return "byval";
   if (hasAttribute(Attribute::Convergent))
     return "convergent";
   if (hasAttribute(Attribute::SwiftError))
@@ -353,6 +388,19 @@ std::string Attribute::getAsString(bool InAttrGrp) const {
   if (hasAttribute(Attribute::ImmArg))
     return "immarg";
 
+  if (hasAttribute(Attribute::ByVal)) {
+    std::string Result;
+    Result += "byval";
+    if (Type *Ty = getValueAsType()) {
+      raw_string_ostream OS(Result);
+      Result += '(';
+      Ty->print(OS, false, true);
+      OS.flush();
+      Result += ')';
+    }
+    return Result;
+  }
+
   // FIXME: These should be output like this:
   //
   //   align=4
@@ -451,6 +499,8 @@ void IntAttributeImpl::anchor() {}
 
 void StringAttributeImpl::anchor() {}
 
+void TypeAttributeImpl::anchor() {}
+
 bool AttributeImpl::hasAttribute(Attribute::AttrKind A) const {
   if (isStringAttribute()) return false;
   return getKindAsEnum() == A;
@@ -462,7 +512,7 @@ bool AttributeImpl::hasAttribute(StringRef Kind) const {
 }
 
 Attribute::AttrKind AttributeImpl::getKindAsEnum() const {
-  assert(isEnumAttribute() || isIntAttribute());
+  assert(isEnumAttribute() || isIntAttribute() || isTypeAttribute());
   return static_cast<const EnumAttributeImpl *>(this)->getEnumKind();
 }
 
@@ -481,6 +531,11 @@ StringRef AttributeImpl::getValueAsString() const {
   return static_cast<const StringAttributeImpl *>(this)->getStringValue();
 }
 
+Type *AttributeImpl::getValueAsType() const {
+  assert(isTypeAttribute());
+  return static_cast<const TypeAttributeImpl *>(this)->getTypeValue();
+}
+
 bool AttributeImpl::operator<(const AttributeImpl &AI) const {
   // This sorts the attributes with Attribute::AttrKinds coming first (sorted
   // relative to their enum value) and then strings.
@@ -488,10 +543,23 @@ bool AttributeImpl::operator<(const AttributeImpl &AI) const {
     if (AI.isEnumAttribute()) return getKindAsEnum() < AI.getKindAsEnum();
     if (AI.isIntAttribute()) return true;
     if (AI.isStringAttribute()) return true;
+    if (AI.isTypeAttribute()) return true;
+  }
+
+  if (isTypeAttribute()) {
+    if (AI.isEnumAttribute()) return false;
+    if (AI.isTypeAttribute()) {
+      assert(getKindAsEnum() != AI.getKindAsEnum() &&
+             "Comparison of types would be unstable");
+      return getKindAsEnum() < AI.getKindAsEnum();
+    }
+    if (AI.isIntAttribute()) return true;
+    if (AI.isStringAttribute()) return true;
   }
 
   if (isIntAttribute()) {
     if (AI.isEnumAttribute()) return false;
+    if (AI.isTypeAttribute()) return false;
     if (AI.isIntAttribute()) {
       if (getKindAsEnum() == AI.getKindAsEnum())
         return getValueAsInt() < AI.getValueAsInt();
@@ -500,7 +568,9 @@ bool AttributeImpl::operator<(const AttributeImpl &AI) const {
     if (AI.isStringAttribute()) return true;
   }
 
+  assert(isStringAttribute());
   if (AI.isEnumAttribute()) return false;
+  if (AI.isTypeAttribute()) return false;
   if (AI.isIntAttribute()) return false;
   if (getKindAsString() == AI.getKindAsString())
     return getValueAsString() < AI.getValueAsString();
@@ -608,6 +678,10 @@ uint64_t AttributeSet::getDereferenceableOrNullBytes() const {
   return SetNode ? SetNode->getDereferenceableOrNullBytes() : 0;
 }
 
+Type *AttributeSet::getByValType() const {
+  return SetNode ? SetNode->getByValType() : nullptr;
+}
+
 std::pair<unsigned, Optional<unsigned>> AttributeSet::getAllocSizeArgs() const {
   return SetNode ? SetNode->getAllocSizeArgs()
                  : std::pair<unsigned, Optional<unsigned>>(0, 0);
@@ -691,6 +765,9 @@ AttributeSetNode *AttributeSetNode::get(LLVMContext &C, const AttrBuilder &B) {
 
     Attribute Attr;
     switch (Kind) {
+    case Attribute::ByVal:
+      Attr = Attribute::getWithByValType(C, B.getByValType());
+      break;
     case Attribute::Alignment:
       Attr = Attribute::getWithAlignment(C, B.getAlignment());
       break;
@@ -760,6 +837,13 @@ unsigned AttributeSetNode::getStackAlignment() const {
   return 0;
 }
 
+Type *AttributeSetNode::getByValType() const {
+  for (const auto I : *this)
+    if (I.hasAttribute(Attribute::ByVal))
+      return I.getValueAsType();
+  return 0;
+}
+
 uint64_t AttributeSetNode::getDereferenceableBytes() const {
   for (const auto I : *this)
     if (I.hasAttribute(Attribute::Dereferenceable))
@@ -1258,6 +1342,11 @@ unsigned AttributeList::getParamAlignment(unsigned ArgNo) const {
   return getAttributes(ArgNo + FirstArgIndex).getAlignment();
 }
 
+Type *AttributeList::getParamByValType(unsigned Index) const {
+  return getAttributes(Index+FirstArgIndex).getByValType();
+}
+
+
 unsigned AttributeList::getStackAlignment(unsigned Index) const {
   return getAttributes(Index).getStackAlignment();
 }
@@ -1336,6 +1425,7 @@ void AttrBuilder::clear() {
   TargetDepAttrs.clear();
   Alignment = StackAlignment = DerefBytes = DerefOrNullBytes = 0;
   AllocSizeArgs = 0;
+  ByValType = nullptr;
 }
 
 AttrBuilder &AttrBuilder::addAttribute(Attribute::AttrKind Val) {
@@ -1360,6 +1450,8 @@ AttrBuilder &AttrBuilder::addAttribute(Attribute Attr) {
     Alignment = Attr.getAlignment();
   else if (Kind == Attribute::StackAlignment)
     StackAlignment = Attr.getStackAlignment();
+  else if (Kind == Attribute::ByVal)
+    ByValType = Attr.getValueAsType();
   else if (Kind == Attribute::Dereferenceable)
     DerefBytes = Attr.getDereferenceableBytes();
   else if (Kind == Attribute::DereferenceableOrNull)
@@ -1382,6 +1474,8 @@ AttrBuilder &AttrBuilder::removeAttribute(Attribute::AttrKind Val) {
     Alignment = 0;
   else if (Val == Attribute::StackAlignment)
     StackAlignment = 0;
+  else if (Val == Attribute::ByVal)
+    ByValType = nullptr;
   else if (Val == Attribute::Dereferenceable)
     DerefBytes = 0;
   else if (Val == Attribute::DereferenceableOrNull)
@@ -1464,6 +1558,12 @@ AttrBuilder &AttrBuilder::addAllocSizeAttrFromRawRepr(uint64_t RawArgs) {
   return *this;
 }
 
+AttrBuilder &AttrBuilder::addByValAttr(Type *Ty) {
+  Attrs[Attribute::ByVal] = true;
+  ByValType = Ty;
+  return *this;
+}
+
 AttrBuilder &AttrBuilder::merge(const AttrBuilder &B) {
   // FIXME: What if both have alignments, but they don't match?!
   if (!Alignment)
@@ -1481,6 +1581,9 @@ AttrBuilder &AttrBuilder::merge(const AttrBuilder &B) {
   if (!AllocSizeArgs)
     AllocSizeArgs = B.AllocSizeArgs;
 
+  if (!ByValType)
+    ByValType = B.ByValType;
+
   Attrs |= B.Attrs;
 
   for (auto I : B.td_attrs())
@@ -1506,6 +1609,9 @@ AttrBuilder &AttrBuilder::remove(const AttrBuilder &B) {
   if (B.AllocSizeArgs)
     AllocSizeArgs = 0;
 
+  if (B.ByValType)
+    ByValType = nullptr;
+
   Attrs &= ~B.Attrs;
 
   for (auto I : B.td_attrs())
@@ -1565,7 +1671,7 @@ bool AttrBuilder::operator==(const AttrBuilder &B) {
       return false;
 
   return Alignment == B.Alignment && StackAlignment == B.StackAlignment &&
-         DerefBytes == B.DerefBytes;
+         DerefBytes == B.DerefBytes && ByValType == B.ByValType;
 }
 
 //===----------------------------------------------------------------------===//

lib/IR/Function.cpp

@@ -113,6 +113,11 @@ unsigned Argument::getParamAlignment() const {
   return getParent()->getParamAlignment(getArgNo());
 }
 
+Type *Argument::getParamByValType() const {
+  assert(getType()->isPointerTy() && "Only pointers have byval types");
+  return getParent()->getParamByValType(getArgNo());
+}
+
 uint64_t Argument::getDereferenceableBytes() const {
   assert(getType()->isPointerTy() &&
          "Only pointers have dereferenceable bytes");

lib/IR/Verifier.cpp

@@ -1695,6 +1695,11 @@ void Verifier::verifyParameterAttrs(AttributeSet Attrs, Type *Ty,
          "'noinline and alwaysinline' are incompatible!",
          V);
 
+  if (Attrs.hasAttribute(Attribute::ByVal) && Attrs.getByValType()) {
+    Assert(Attrs.getByValType() == cast<PointerType>(Ty)->getElementType(),
+           "Attribute 'byval' type does not match parameter!");
+  }
+
   AttrBuilder IncompatibleAttrs = AttributeFuncs::typeIncompatible(Ty);
   Assert(!AttrBuilder(Attrs).overlaps(IncompatibleAttrs),
          "Wrong types for attribute: " +

lib/Linker/IRMover.cpp

@@ -489,6 +489,10 @@ class IRLinker {
   void linkAliasBody(GlobalAlias &Dst, GlobalAlias &Src);
   Error linkGlobalValueBody(GlobalValue &Dst, GlobalValue &Src);
 
+  /// Replace all types in the source AttributeList with the
+  /// corresponding destination type.
+  AttributeList mapAttributeTypes(LLVMContext &C, AttributeList Attrs);
+
   /// Functions that take care of cloning a specific global value type
   /// into the destination module.
   GlobalVariable *copyGlobalVariableProto(const GlobalVariable *SGVar);
@@ -628,6 +632,21 @@ GlobalVariable *IRLinker::copyGlobalVariableProto(const GlobalVariable *SGVar) {
   return NewDGV;
 }
 
+AttributeList IRLinker::mapAttributeTypes(LLVMContext &C, AttributeList Attrs) {
+  for (unsigned i = 0; i < Attrs.getNumAttrSets(); ++i) {
+    if (Attrs.hasAttribute(i, Attribute::ByVal)) {
+      Type *Ty = Attrs.getAttribute(i, Attribute::ByVal).getValueAsType();
+      if (!Ty)
+        continue;
+
+      Attrs = Attrs.removeAttribute(C, i, Attribute::ByVal);
+      Attrs = Attrs.addAttribute(
+          C, i, Attribute::getWithByValType(C, TypeMap.get(Ty)));
+    }
+  }
+  return Attrs;
+}
+
 /// Link the function in the source module into the destination module if
 /// needed, setting up mapping information.
 Function *IRLinker::copyFunctionProto(const Function *SF) {
@@ -637,6 +656,7 @@ Function *IRLinker::copyFunctionProto(const Function *SF) {
       Function::Create(TypeMap.get(SF->getFunctionType()),
                        GlobalValue::ExternalLinkage, SF->getName(), &DstM);
   F->copyAttributesFrom(SF);
+  F->setAttributes(mapAttributeTypes(F->getContext(), F->getAttributes()));
   return F;
 }
 

lib/Transforms/Utils/ValueMapper.cpp

@@ -913,6 +913,21 @@ void Mapper::remapInstruction(Instruction *I) {
       Tys.push_back(TypeMapper->remapType(Ty));
     CS.mutateFunctionType(FunctionType::get(
         TypeMapper->remapType(I->getType()), Tys, FTy->isVarArg()));
+
+    LLVMContext &C = CS->getContext();
+    AttributeList Attrs = CS.getAttributes();
+    for (unsigned i = 0; i < Attrs.getNumAttrSets(); ++i) {
+      if (Attrs.hasAttribute(i, Attribute::ByVal)) {
+        Type *Ty = Attrs.getAttribute(i, Attribute::ByVal).getValueAsType();
+        if (!Ty)
+          continue;
+
+        Attrs = Attrs.removeAttribute(C, i, Attribute::ByVal);
+        Attrs = Attrs.addAttribute(
+            C, i, Attribute::getWithByValType(C, TypeMapper->remapType(Ty)));
+      }
+    }
+    CS.setAttributes(Attrs);
     return;
   }
   if (auto *AI = dyn_cast<AllocaInst>(I))

test/Assembler/byval-type-attr.ll

@@ -0,0 +1,31 @@
+; RUN: llvm-as < %s | llvm-dis | llvm-as | llvm-dis | FileCheck %s
+
+; CHECK: define void @foo(i32* byval(i32) align 4)
+define void @foo(i32* byval(i32) align 4) {
+  ret void
+}
+
+; CHECK: define void @bar({ i32*, i8 }* byval({ i32*, i8 }) align 4)
+define void @bar({i32*, i8}* byval({i32*, i8}) align 4) {
+  ret void
+}
+
+define void @caller({ i32*, i8 }* %ptr) personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+; CHECK: call void @bar({ i32*, i8 }* byval({ i32*, i8 }) %ptr)
+; CHECK: invoke void @bar({ i32*, i8 }* byval({ i32*, i8 }) %ptr)
+  call void @bar({i32*, i8}* byval %ptr)
+  invoke void @bar({i32*, i8}* byval %ptr) to label %success unwind label %fail
+
+success:
+  ret void
+
+fail:
+  landingpad { i8*, i32 } cleanup
+  ret void
+}
+
+; CHECK: declare void @baz([8 x i8]* byval([8 x i8]))
+%named_type = type [8 x i8]
+declare void @baz(%named_type* byval(%named_type))
+
+declare i32 @__gxx_personality_v0(...)

test/Assembler/invalid-byval-type1.ll

@@ -0,0 +1,4 @@
+; RUN: not llvm-as %s -o /dev/null 2>&1 | FileCheck %s
+
+; CHECK: Attribute 'byval' type does not match parameter!
+declare void @foo(i32* byval(i8))

test/Assembler/invalid-byval-type2.ll

@@ -0,0 +1,4 @@
+; RUN: not llvm-as %s -o /dev/null 2>&1 | FileCheck %s
+
+; CHECK: error: void type only allowed for function results
+declare void @foo(i32* byval(void))

test/Assembler/invalid-byval-type3.ll

@@ -0,0 +1,4 @@
+; RUN: not llvm-as %s -o /dev/null 2>&1 | FileCheck %s
+
+; CHECK: Attributes 'byval' and 'inalloca' do not support unsized types!
+declare void @foo(void()* byval(void()))

test/Bitcode/attributes-3.3.ll

@@ -48,7 +48,7 @@ define void @f7(i8* noalias)
 }
 
 define void @f8(i8* byval)
-; CHECK: define void @f8(i8* byval)
+; CHECK: define void @f8(i8* byval(i8))
 {
         ret void;
 }

test/Bitcode/attributes.ll

@@ -45,7 +45,7 @@ define void @f7(i8* noalias)
 }
 
 define void @f8(i8* byval)
-; CHECK: define void @f8(i8* byval)
+; CHECK: define void @f8(i8* byval(i8))
 {
         ret void;
 }

test/Bitcode/byval-upgrade.test

@@ -0,0 +1,7 @@
+RUN: llvm-dis %p/Inputs/byval-upgrade.bc -o - | FileCheck %s
+
+Make sure we upgrade old-stile IntAttribute byval records to a fully typed
+version correctly.
+
+CHECK: call void @bar({ i32*, i8 }* byval({ i32*, i8 }) %ptr)
+CHECK: invoke void @bar({ i32*, i8 }* byval({ i32*, i8 }) %ptr)

test/Bitcode/compatibility-3.6.ll

@@ -404,7 +404,7 @@ declare void @f.param.signext(i8 signext)
 declare void @f.param.inreg(i8 inreg)
 ; CHECK: declare void @f.param.inreg(i8 inreg)
 declare void @f.param.byval({ i8, i8 }* byval)
-; CHECK: declare void @f.param.byval({ i8, i8 }* byval)
+; CHECK: declare void @f.param.byval({ i8, i8 }* byval({ i8, i8 }))
 declare void @f.param.inalloca(i8* inalloca)
 ; CHECK: declare void @f.param.inalloca(i8* inalloca)
 declare void @f.param.sret(i8* sret)

test/Bitcode/compatibility-3.7.ll

@@ -410,7 +410,7 @@ declare void @f.param.signext(i8 signext)
 declare void @f.param.inreg(i8 inreg)
 ; CHECK: declare void @f.param.inreg(i8 inreg)
 declare void @f.param.byval({ i8, i8 }* byval)
-; CHECK: declare void @f.param.byval({ i8, i8 }* byval)
+; CHECK: declare void @f.param.byval({ i8, i8 }* byval({ i8, i8 }))
 declare void @f.param.inalloca(i8* inalloca)
 ; CHECK: declare void @f.param.inalloca(i8* inalloca)
 declare void @f.param.sret(i8* sret)

test/Bitcode/compatibility-3.8.ll

@@ -435,7 +435,7 @@ declare void @f.param.signext(i8 signext)
 declare void @f.param.inreg(i8 inreg)
 ; CHECK: declare void @f.param.inreg(i8 inreg)
 declare void @f.param.byval({ i8, i8 }* byval)
-; CHECK: declare void @f.param.byval({ i8, i8 }* byval)
+; CHECK: declare void @f.param.byval({ i8, i8 }* byval({ i8, i8 }))
 declare void @f.param.inalloca(i8* inalloca)
 ; CHECK: declare void @f.param.inalloca(i8* inalloca)
 declare void @f.param.sret(i8* sret)

test/Bitcode/compatibility-3.9.ll

@@ -504,7 +504,7 @@ declare void @f.param.signext(i8 signext)
 declare void @f.param.inreg(i8 inreg)
 ; CHECK: declare void @f.param.inreg(i8 inreg)
 declare void @f.param.byval({ i8, i8 }* byval)
-; CHECK: declare void @f.param.byval({ i8, i8 }* byval)
+; CHECK: declare void @f.param.byval({ i8, i8 }* byval({ i8, i8 }))
 declare void @f.param.inalloca(i8* inalloca)
 ; CHECK: declare void @f.param.inalloca(i8* inalloca)
 declare void @f.param.sret(i8* sret)

test/Bitcode/compatibility-4.0.ll

@@ -504,7 +504,7 @@ declare void @f.param.signext(i8 signext)
 declare void @f.param.inreg(i8 inreg)
 ; CHECK: declare void @f.param.inreg(i8 inreg)
 declare void @f.param.byval({ i8, i8 }* byval)
-; CHECK: declare void @f.param.byval({ i8, i8 }* byval)
+; CHECK: declare void @f.param.byval({ i8, i8 }* byval({ i8, i8 }))
 declare void @f.param.inalloca(i8* inalloca)
 ; CHECK: declare void @f.param.inalloca(i8* inalloca)
 declare void @f.param.sret(i8* sret)

test/Bitcode/compatibility-5.0.ll

@@ -508,7 +508,7 @@ declare void @f.param.signext(i8 signext)
 declare void @f.param.inreg(i8 inreg)
 ; CHECK: declare void @f.param.inreg(i8 inreg)
 declare void @f.param.byval({ i8, i8 }* byval)
-; CHECK: declare void @f.param.byval({ i8, i8 }* byval)
+; CHECK: declare void @f.param.byval({ i8, i8 }* byval({ i8, i8 }))
 declare void @f.param.inalloca(i8* inalloca)
 ; CHECK: declare void @f.param.inalloca(i8* inalloca)
 declare void @f.param.sret(i8* sret)

test/Bitcode/compatibility-6.0.ll

@@ -515,7 +515,7 @@ declare void @f.param.signext(i8 signext)
 declare void @f.param.inreg(i8 inreg)
 ; CHECK: declare void @f.param.inreg(i8 inreg)
 declare void @f.param.byval({ i8, i8 }* byval)
-; CHECK: declare void @f.param.byval({ i8, i8 }* byval)
+; CHECK: declare void @f.param.byval({ i8, i8 }* byval({ i8, i8 }))
 declare void @f.param.inalloca(i8* inalloca)
 ; CHECK: declare void @f.param.inalloca(i8* inalloca)
 declare void @f.param.sret(i8* sret)

test/Bitcode/compatibility.ll

@@ -529,7 +529,7 @@ declare void @f.param.signext(i8 signext)
 declare void @f.param.inreg(i8 inreg)
 ; CHECK: declare void @f.param.inreg(i8 inreg)
 declare void @f.param.byval({ i8, i8 }* byval)
-; CHECK: declare void @f.param.byval({ i8, i8 }* byval)
+; CHECK: declare void @f.param.byval({ i8, i8 }* byval({ i8, i8 }))
 declare void @f.param.inalloca(i8* inalloca)
 ; CHECK: declare void @f.param.inalloca(i8* inalloca)
 declare void @f.param.sret(i8* sret)
@@ -1735,6 +1735,15 @@ define i8** @constexpr() {
 declare void @llvm.test.immarg.intrinsic(i32 immarg)
 ; CHECK: declare void @llvm.test.immarg.intrinsic(i32 immarg)
 
+; byval attribute with type
+%named_type = type [8 x i8]
+declare void @byval_type(i32* byval(i32) align 2)
+declare void @byval_type2({ i8, i8* }* byval({ i8, i8* }))
+declare void @byval_named_type(%named_type* byval(%named_type))
+; CHECK: declare void @byval_type(i32* byval(i32) align 2)
+; CHECK: declare void @byval_type2({ i8, i8* }* byval({ i8, i8* }))
+; CHECK: declare void @byval_named_type([8 x i8]* byval([8 x i8]))
+
 ; CHECK: attributes #0 = { alignstack=4 }
 ; CHECK: attributes #1 = { alignstack=8 }
 ; CHECK: attributes #2 = { alwaysinline }

test/Bitcode/highLevelStructure.3.2.ll

@@ -41,7 +41,7 @@ declare void @ParamAttr3(i8* sret)
 declare void @ParamAttr4(i8 signext)
 ; CHECK: declare void @ParamAttr5(i8* inreg)
 declare void @ParamAttr5(i8* inreg)
-; CHECK: declare void @ParamAttr6(i8* byval)
+; CHECK: declare void @ParamAttr6(i8* byval(i8))
 declare void @ParamAttr6(i8* byval)
 ; CHECK: declare void @ParamAttr7(i8* noalias)
 declare void @ParamAttr7(i8* noalias)
@@ -51,7 +51,7 @@ declare void @ParamAttr8(i8* nocapture)
 declare void @ParamAttr9(i8* nest noalias nocapture)
 ; CHECK: declare void @ParamAttr10{{[(i8* sret noalias nocapture) | (i8* noalias nocapture sret)]}}
 declare void @ParamAttr10(i8* sret noalias nocapture)
-;CHECK: declare void @ParamAttr11{{[(i8* byval noalias nocapture) | (i8* noalias nocapture byval)]}}
+;CHECK: declare void @ParamAttr11{{[(i8* byval(i8) noalias nocapture) | (i8* noalias nocapture byval(i8))]}}
 declare void @ParamAttr11(i8* byval noalias nocapture)
 ;CHECK: declare void @ParamAttr12{{[(i8* inreg noalias nocapture) | (i8* noalias nocapture inreg)]}}
 declare void @ParamAttr12(i8* inreg noalias nocapture)

test/CodeGen/AArch64/byval-type.ll

@@ -0,0 +1,37 @@
+; RUN: llc -mtriple=aarch64-linux-gnu %s -o - | FileCheck %s
+
+define i8 @byval_match(i8* byval(i8) align 1, i8* byval %ptr) {
+; CHECK-LABEL: byval_match:
+; CHECK: ldrb w0, [sp, #8]
+  %res = load i8, i8* %ptr
+  ret i8 %res
+}
+
+define void @caller_match(i8* %p0, i8* %p1) {
+; CHECK-LABEL: caller_match:
+; CHECK: ldrb [[P1:w[0-9]+]], [x1]
+; CHECK: strb [[P1]], [sp, #8]
+; CHECK: ldrb [[P0:w[0-9]+]], [x0]
+; CHECK: strb [[P0]], [sp]
+; CHECK: bl byval_match
+  call i8 @byval_match(i8* byval(i8) align 1 %p0, i8* byval %p1)
+  ret void
+}
+
+define i8 @byval_large([3 x i64]* byval([3 x i64]) align 8, i8* byval %ptr) {
+; CHECK-LABEL: byval_large:
+; CHECK: ldrb w0, [sp, #24]
+  %res = load i8, i8* %ptr
+  ret i8 %res
+}
+
+define void @caller_large([3 x i64]* %p0, i8* %p1) {
+; CHECK-LABEL: caller_large:
+; CHECK: ldr [[P0HI:x[0-9]+]], [x0, #16]
+; CHECK: ldr [[P0LO:q[0-9]+]], [x0]
+; CHECK: str [[P0HI]], [sp, #16]
+; CHECK: str [[P0LO]], [sp]
+; CHECK: bl byval_large
+  call i8 @byval_large([3 x i64]* byval([3 x i64]) align 8 %p0, i8* byval %p1)
+  ret void
+}

test/Linker/Inputs/byval-types-1.ll

@@ -0,0 +1,8 @@
+%struct = type {i32, i8}
+
+declare void @baz(%struct* byval(%struct))
+
+define void @foo(%struct* byval(%struct) %a) {
+  call void @baz(%struct* byval(%struct) %a)
+  ret void
+}

test/Linker/byval-types.ll

@@ -0,0 +1,17 @@
+; RUN: llvm-link %s %p/Inputs/byval-types-1.ll -S | FileCheck %s
+
+%struct = type {i32, i8}
+
+declare void @foo(%struct* byval(%struct) %a)
+
+define void @bar() {
+  %ptr = alloca %struct
+; CHECK: call void @foo(%struct* byval(%struct) %ptr)
+  call void @foo(%struct* byval(%struct) %ptr)
+  ret void
+}
+
+; CHECK: define void @foo(%struct* byval(%struct) %a)
+; CHECK-NEXT:   call void @baz(%struct* byval(%struct) %a)
+
+; CHECK: declare void @baz(%struct* byval(%struct))

test/Transforms/Inline/byval-tail-call.ll

@@ -56,7 +56,7 @@ define void @foobar(i32* %x) {
 ; CHECK: %[[POS:.*]] = alloca i32
 ; CHECK: %[[VAL:.*]] = load i32, i32* %x
 ; CHECK: store i32 %[[VAL]], i32* %[[POS]]
-; CHECK: tail call void @ext2(i32* byval nonnull %[[POS]]
+; CHECK: tail call void @ext2(i32* nonnull byval %[[POS]]
 ; CHECK: ret void
   tail call void @bar2(i32* byval %x)
   ret void
@@ -67,7 +67,7 @@ define void @barfoo() {
 ; CHECK: %[[POS:.*]] = alloca i32
 ; CHECK: %[[VAL:.*]] = load i32, i32* %x
 ; CHECK: store i32 %[[VAL]], i32* %[[POS]]
-; CHECK: tail call void @ext2(i32* byval nonnull %[[POS]]
+; CHECK: tail call void @ext2(i32* nonnull byval %[[POS]]
 ; CHECK: ret void
   %x = alloca i32
   tail call void @bar2(i32* byval %x)

unittests/IR/AttributesTest.cpp

@@ -8,6 +8,7 @@
 
 #include "llvm/IR/Attributes.h"
 #include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/DerivedTypes.h"
 #include "gtest/gtest.h"
 using namespace llvm;
 
@@ -40,6 +41,10 @@ TEST(Attributes, Ordering) {
   EXPECT_TRUE(Align4 < Deref5);
   EXPECT_TRUE(Align5 < Deref4);
 
+  Attribute ByVal = Attribute::get(C, Attribute::ByVal, Type::getInt32Ty(C));
+  EXPECT_FALSE(ByVal < Attribute::get(C, Attribute::ZExt));
+  EXPECT_TRUE(ByVal < Align4);
+
   AttributeList ASs[] = {AttributeList::get(C, 2, Attribute::ZExt),
                          AttributeList::get(C, 1, Attribute::SExt)};
 
@@ -166,4 +171,19 @@ TEST(Attributes, OverflowGet) {
   EXPECT_EQ(2U, AL.getNumAttrSets());
 }
 
+TEST(Attributes, StringRepresentation) {
+  LLVMContext C;
+  StructType *Ty = StructType::create(Type::getInt32Ty(C), "mystruct");
+
+  // Insufficiently careful printing can result in byval(%mystruct = { i32 })
+  Attribute A = Attribute::getWithByValType(C, Ty);
+  EXPECT_EQ(A.getAsString(), "byval(%mystruct)");
+
+  A = Attribute::getWithByValType(C, nullptr);
+  EXPECT_EQ(A.getAsString(), "byval");
+
+  A = Attribute::getWithByValType(C, Type::getInt32Ty(C));
+  EXPECT_EQ(A.getAsString(), "byval(i32)");
+}
+
 } // end anonymous namespace