[Metadata] Extend 'count' field of DISubrange to take a metadata node

Summary:
This patch extends the DISubrange 'count' field to take either a
(signed) constant integer value or a reference to a DILocalVariable
or DIGlobalVariable.

This is patch [1/3] in a series to extend LLVM's DISubrange Metadata
node to support debugging of C99 variable length arrays and vectors with
runtime length like the Scalable Vector Extension for AArch64. It is
also a first step towards representing more complex cases like arrays
in Fortran.

Reviewers: echristo, pcc, aprantl, dexonsmith, clayborg, kristof.beyls, dblaikie

Reviewed By: aprantl

Subscribers: rnk, probinson, fhahn, aemerson, rengolin, JDevlieghere, llvm-commits

Differential Revision: https://reviews.llvm.org/D41695

llvm-svn: 323313

10 files changed, 164 insertions, 25 deletions

diff --git a/llvm/lib/AsmParser/LLParser.cpp b/llvm/lib/AsmParser/LLParser.cpp
index f94b616e596..9bc34f927e8 100644
--- a/llvm/lib/AsmParser/LLParser.cpp
+++ b/llvm/lib/AsmParser/LLParser.cpp
@@ -3492,6 +3492,39 @@ template <class FieldTy> struct MDFieldImpl {
       : Val(std::move(Default)), Seen(false) {}
 };
 
+/// Structure to represent an optional metadata field that
+/// can be of either type (A or B) and encapsulates the
+/// MD<typeofA>Field and MD<typeofB>Field structs, so not
+/// to reimplement the specifics for representing each Field.
+template <class FieldTypeA, class FieldTypeB> struct MDEitherFieldImpl {
+  typedef MDEitherFieldImpl<FieldTypeA, FieldTypeB> ImplTy;
+  FieldTypeA A;
+  FieldTypeB B;
+  bool Seen;
+
+  enum {
+    IsInvalid = 0,
+    IsTypeA = 1,
+    IsTypeB = 2
+  } WhatIs;
+
+  void assign(FieldTypeA A) {
+    Seen = true;
+    this->A = std::move(A);
+    WhatIs = IsTypeA;
+  }
+
+  void assign(FieldTypeB B) {
+    Seen = true;
+    this->B = std::move(B);
+    WhatIs = IsTypeB;
+  }
+
+  explicit MDEitherFieldImpl(FieldTypeA DefaultA, FieldTypeB DefaultB)
+      : A(std::move(DefaultA)), B(std::move(DefaultB)), Seen(false),
+        WhatIs(IsInvalid) {}
+};
+
 struct MDUnsignedField : public MDFieldImpl<uint64_t> {
   uint64_t Max;
 
@@ -3582,6 +3615,26 @@ struct ChecksumKindField : public MDFieldImpl<DIFile::ChecksumKind> {
   ChecksumKindField(DIFile::ChecksumKind CSKind) : ImplTy(CSKind) {}
 };
 
+struct MDSignedOrMDField : MDEitherFieldImpl<MDSignedField, MDField> {
+  MDSignedOrMDField(int64_t Default = 0, bool AllowNull = true)
+      : ImplTy(MDSignedField(Default), MDField(AllowNull)) {}
+
+  MDSignedOrMDField(int64_t Default, int64_t Min, int64_t Max,
+                    bool AllowNull = true)
+      : ImplTy(MDSignedField(Default, Min, Max), MDField(AllowNull)) {}
+
+  bool isMDSignedField() const { return WhatIs == IsTypeA; }
+  bool isMDField() const { return WhatIs == IsTypeB; }
+  int64_t getMDSignedValue() const {
+    assert(isMDSignedField() && "Wrong field type");
+    return A.Val;
+  }
+  Metadata *getMDFieldValue() const {
+    assert(isMDField() && "Wrong field type");
+    return B.Val;
+  }
+};
+
 } // end anonymous namespace
 
 namespace llvm {
@@ -3836,6 +3889,29 @@ bool LLParser::ParseMDField(LocTy Loc, StringRef Name, MDField &Result) {
 }
 
 template <>
+bool LLParser::ParseMDField(LocTy Loc, StringRef Name,
+                            MDSignedOrMDField &Result) {
+  // Try to parse a signed int.
+  if (Lex.getKind() == lltok::APSInt) {
+    MDSignedField Res = Result.A;
+    if (!ParseMDField(Loc, Name, Res)) {
+      Result.assign(Res);
+      return false;
+    }
+    return true;
+  }
+
+  // Otherwise, try to parse as an MDField.
+  MDField Res = Result.B;
+  if (!ParseMDField(Loc, Name, Res)) {
+    Result.assign(Res);
+    return false;
+  }
+
+  return true;
+}
+
+template <>
 bool LLParser::ParseMDField(LocTy Loc, StringRef Name, MDStringField &Result) {
   LocTy ValueLoc = Lex.getLoc();
   std::string S;
@@ -3979,14 +4055,23 @@ bool LLParser::ParseGenericDINode(MDNode *&Result, bool IsDistinct) {
 
 /// ParseDISubrange:
 ///   ::= !DISubrange(count: 30, lowerBound: 2)
+///   ::= !DISubrange(count: !node, lowerBound: 2)
 bool LLParser::ParseDISubrange(MDNode *&Result, bool IsDistinct) {
 #define VISIT_MD_FIELDS(OPTIONAL, REQUIRED)                                    \
-  REQUIRED(count, MDSignedField, (-1, -1, INT64_MAX));                         \
+  REQUIRED(count, MDSignedOrMDField, (-1, -1, INT64_MAX, false));              \
   OPTIONAL(lowerBound, MDSignedField, );
   PARSE_MD_FIELDS();
 #undef VISIT_MD_FIELDS
 
-  Result = GET_OR_DISTINCT(DISubrange, (Context, count.Val, lowerBound.Val));
+  if (count.isMDSignedField())
+    Result = GET_OR_DISTINCT(
+        DISubrange, (Context, count.getMDSignedValue(), lowerBound.Val));
+  else if (count.isMDField())
+    Result = GET_OR_DISTINCT(
+        DISubrange, (Context, count.getMDFieldValue(), lowerBound.Val));
+  else
+    return true;
+
   return false;
 }
 
diff --git a/llvm/lib/Bitcode/Reader/MetadataLoader.cpp b/llvm/lib/Bitcode/Reader/MetadataLoader.cpp
index 7d79956a811..5250ac5176d 100644
--- a/llvm/lib/Bitcode/Reader/MetadataLoader.cpp
+++ b/llvm/lib/Bitcode/Reader/MetadataLoader.cpp
@@ -1174,14 +1174,25 @@ Error MetadataLoader::MetadataLoaderImpl::parseOneMetadata(
     break;
   }
   case bitc::METADATA_SUBRANGE: {
-    if (Record.size() != 3)
-      return error("Invalid record");
+    Metadata *Val = nullptr;
+    // Operand 'count' is interpreted as:
+    // - Signed integer (version 0)
+    // - Metadata node  (version 1)
+    switch (Record[0] >> 1) {
+    case 0:
+      Val = GET_OR_DISTINCT(DISubrange,
+                            (Context, Record[1], unrotateSign(Record.back())));
+      break;
+    case 1:
+      Val = GET_OR_DISTINCT(DISubrange, (Context, getMDOrNull(Record[1]),
+                                         unrotateSign(Record.back())));
+      break;
+    default:
+      return error("Invalid record: Unsupported version of DISubrange");
+    }
 
-    IsDistinct = Record[0];
-    MetadataList.assignValue(
-        GET_OR_DISTINCT(DISubrange,
-                        (Context, Record[1], unrotateSign(Record[2]))),
-        NextMetadataNo);
+    MetadataList.assignValue(Val, NextMetadataNo);
+    IsDistinct = Record[0] & 1;
     NextMetadataNo++;
     break;
   }
diff --git a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
index f3f33c4474b..3876b5ffe35 100644
--- a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -1442,8 +1442,9 @@ static uint64_t rotateSign(int64_t I) {
 void ModuleBitcodeWriter::writeDISubrange(const DISubrange *N,
                                           SmallVectorImpl<uint64_t> &Record,
                                           unsigned Abbrev) {
-  Record.push_back(N->isDistinct());
-  Record.push_back(N->getCount());
+  const uint64_t Version = 1 << 1;
+  Record.push_back((uint64_t)N->isDistinct() | Version);
+  Record.push_back(VE.getMetadataOrNullID(N->getRawCountNode()));
   Record.push_back(rotateSign(N->getLowerBound()));
 
   Stream.EmitRecord(bitc::METADATA_SUBRANGE, Record, Abbrev);
diff --git a/llvm/lib/CodeGen/AsmPrinter/CodeViewDebug.cpp b/llvm/lib/CodeGen/AsmPrinter/CodeViewDebug.cpp
index 11c28ba6d9a..bee4d119300 100644
--- a/llvm/lib/CodeGen/AsmPrinter/CodeViewDebug.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/CodeViewDebug.cpp
@@ -1325,7 +1325,9 @@ TypeIndex CodeViewDebug::lowerTypeArray(const DICompositeType *Ty) {
     const DISubrange *Subrange = cast<DISubrange>(Element);
     assert(Subrange->getLowerBound() == 0 &&
            "codeview doesn't support subranges with lower bounds");
-    int64_t Count = Subrange->getCount();
+    int64_t Count = -1;
+    if (auto *CI = Subrange->getCount().dyn_cast<ConstantInt*>())
+      Count = CI->getSExtValue();
 
     // Forward declarations of arrays without a size and VLAs use a count of -1.
     // Emit a count of zero in these cases to match what MSVC does for arrays
diff --git a/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp b/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp
index 61868a3bc06..907ede0a633 100644
--- a/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp
@@ -1328,7 +1328,9 @@ void DwarfUnit::constructSubrangeDIE(DIE &Buffer, const DISubrange *SR,
   // DW_AT_lower_bound and DW_AT_count attributes.
   int64_t LowerBound = SR->getLowerBound();
   int64_t DefaultLowerBound = getDefaultLowerBound();
-  int64_t Count = SR->getCount();
+  int64_t Count = -1;
+  if (auto *CI = SR->getCount().dyn_cast<ConstantInt*>())
+    Count = CI->getSExtValue();
 
   if (DefaultLowerBound == -1 || LowerBound != DefaultLowerBound)
     addUInt(DW_Subrange, dwarf::DW_AT_lower_bound, None, LowerBound);
diff --git a/llvm/lib/IR/AsmWriter.cpp b/llvm/lib/IR/AsmWriter.cpp
index 7c647605894..638b0244148 100644
--- a/llvm/lib/IR/AsmWriter.cpp
+++ b/llvm/lib/IR/AsmWriter.cpp
@@ -1621,10 +1621,15 @@ static void writeDILocation(raw_ostream &Out, const DILocation *DL,
 }
 
 static void writeDISubrange(raw_ostream &Out, const DISubrange *N,
-                            TypePrinting *, SlotTracker *, const Module *) {
+                            TypePrinting *TypePrinter, SlotTracker *Machine,
+                            const Module *Context) {
   Out << "!DISubrange(";
-  MDFieldPrinter Printer(Out);
-  Printer.printInt("count", N->getCount(), /* ShouldSkipZero */ false);
+  MDFieldPrinter Printer(Out, TypePrinter, Machine, Context);
+  if (auto *CE = N->getCount().dyn_cast<ConstantInt*>())
+    Printer.printInt("count", CE->getSExtValue(), /* ShouldSkipZero */ false);
+  else
+    Printer.printMetadata("count", N->getCount().dyn_cast<DIVariable*>(),
+                          /*ShouldSkipNull */ false);
   Printer.printInt("lowerBound", N->getLowerBound());
   Out << ")";
 }
diff --git a/llvm/lib/IR/DIBuilder.cpp b/llvm/lib/IR/DIBuilder.cpp
index f8ae23d4395..5ef3cdd88fd 100644
--- a/llvm/lib/IR/DIBuilder.cpp
+++ b/llvm/lib/IR/DIBuilder.cpp
@@ -582,6 +582,10 @@ DISubrange *DIBuilder::getOrCreateSubrange(int64_t Lo, int64_t Count) {
   return DISubrange::get(VMContext, Count, Lo);
 }
 
+DISubrange *DIBuilder::getOrCreateSubrange(int64_t Lo, Metadata *CountNode) {
+  return DISubrange::get(VMContext, CountNode, Lo);
+}
+
 static void checkGlobalVariableScope(DIScope *Context) {
 #ifndef NDEBUG
   if (auto *CT =
diff --git a/llvm/lib/IR/DebugInfoMetadata.cpp b/llvm/lib/IR/DebugInfoMetadata.cpp
index 75ddd47b259..b6eda6a2921 100644
--- a/llvm/lib/IR/DebugInfoMetadata.cpp
+++ b/llvm/lib/IR/DebugInfoMetadata.cpp
@@ -249,8 +249,17 @@ void GenericDINode::recalculateHash() {
 
 DISubrange *DISubrange::getImpl(LLVMContext &Context, int64_t Count, int64_t Lo,
                                 StorageType Storage, bool ShouldCreate) {
-  DEFINE_GETIMPL_LOOKUP(DISubrange, (Count, Lo));
-  DEFINE_GETIMPL_STORE_NO_OPS(DISubrange, (Count, Lo));
+  auto *CountNode = ConstantAsMetadata::get(
+      ConstantInt::getSigned(Type::getInt64Ty(Context), Count));
+  return getImpl(Context, CountNode, Lo, Storage, ShouldCreate);
+}
+
+DISubrange *DISubrange::getImpl(LLVMContext &Context, Metadata *CountNode,
+                                int64_t Lo, StorageType Storage,
+                                bool ShouldCreate) {
+  DEFINE_GETIMPL_LOOKUP(DISubrange, (CountNode, Lo));
+  Metadata *Ops[] = { CountNode };
+  DEFINE_GETIMPL_STORE(DISubrange, (CountNode, Lo), Ops);
 }
 
 DIEnumerator *DIEnumerator::getImpl(LLVMContext &Context, int64_t Value,
diff --git a/llvm/lib/IR/LLVMContextImpl.h b/llvm/lib/IR/LLVMContextImpl.h
index f41acfa8ea9..e981a806602 100644
--- a/llvm/lib/IR/LLVMContextImpl.h
+++ b/llvm/lib/IR/LLVMContextImpl.h
@@ -321,19 +321,34 @@ template <> struct MDNodeKeyImpl<GenericDINode> : MDNodeOpsKey {
 };
 
 template <> struct MDNodeKeyImpl<DISubrange> {
-  int64_t Count;
+  Metadata *CountNode;
   int64_t LowerBound;
 
-  MDNodeKeyImpl(int64_t Count, int64_t LowerBound)
-      : Count(Count), LowerBound(LowerBound) {}
+  MDNodeKeyImpl(Metadata *CountNode, int64_t LowerBound)
+      : CountNode(CountNode), LowerBound(LowerBound) {}
   MDNodeKeyImpl(const DISubrange *N)
-      : Count(N->getCount()), LowerBound(N->getLowerBound()) {}
+      : CountNode(N->getRawCountNode()),
+        LowerBound(N->getLowerBound()) {}
 
   bool isKeyOf(const DISubrange *RHS) const {
-    return Count == RHS->getCount() && LowerBound == RHS->getLowerBound();
+    if (LowerBound != RHS->getLowerBound())
+      return false;
+
+    if (auto *RHSCount = RHS->getCount().dyn_cast<ConstantInt*>())
+      if (auto *MD = dyn_cast<ConstantAsMetadata>(CountNode))
+        if (RHSCount->getSExtValue() ==
+            cast<ConstantInt>(MD->getValue())->getSExtValue())
+          return true;
+
+    return CountNode == RHS->getRawCountNode();
   }
 
-  unsigned getHashValue() const { return hash_combine(Count, LowerBound); }
+  unsigned getHashValue() const {
+    if (auto *MD = dyn_cast<ConstantAsMetadata>(CountNode))
+      return hash_combine(cast<ConstantInt>(MD->getValue())->getSExtValue(),
+                          LowerBound);
+    return hash_combine(CountNode, LowerBound);
+  }
 };
 
 template <> struct MDNodeKeyImpl<DIEnumerator> {
diff --git a/llvm/lib/IR/Verifier.cpp b/llvm/lib/IR/Verifier.cpp
index 4dd5aebfc59..92389b60545 100644
--- a/llvm/lib/IR/Verifier.cpp
+++ b/llvm/lib/IR/Verifier.cpp
@@ -868,7 +868,12 @@ void Verifier::visitDIScope(const DIScope &N) {
 
 void Verifier::visitDISubrange(const DISubrange &N) {
   AssertDI(N.getTag() == dwarf::DW_TAG_subrange_type, "invalid tag", &N);
-  AssertDI(N.getCount() >= -1, "invalid subrange count", &N);
+  auto Count = N.getCount();
+  AssertDI(Count, "Count must either be a signed constant or a DIVariable",
+           &N);
+  AssertDI(!Count.is<ConstantInt*>() ||
+               Count.get<ConstantInt*>()->getSExtValue() >= -1,
+           "invalid subrange count", &N);
 }
 
 void Verifier::visitDIEnumerator(const DIEnumerator &N) {