[DebugInfo] Introduce DW_OP_LLVM_convert

Introduce a DW_OP_LLVM_convert Dwarf expression pseudo op that allows
for a convenient way to perform type conversions on the Dwarf expression
stack. As an additional bonus it paves the way for using other Dwarf
v5 ops that need to reference a base_type.

The new DW_OP_LLVM_convert is used from lib/Transforms/Utils/Local.cpp
to perform sext/zext on debug values but mainly the patch is about
preparing terrain for adding other Dwarf v5 ops that need to reference a
base_type.

For Dwarf v5 the op maps to DW_OP_convert and for earlier versions a
complex shift & mask pattern is generated to emulate sext/zext.

Differential Revision: https://reviews.llvm.org/D56587

llvm-svn: 356442

llvm/docs/LangRef.rst

@@ -4682,6 +4682,10 @@ The current supported opcode vocabulary is limited:
   here, respectively) of the variable fragment from the working expression. Note
   that contrary to DW_OP_bit_piece, the offset is describing the location
   within the described source variable.
+- ``DW_OP_LLVM_convert, 16, DW_ATE_signed`` specifies a bit size and encoding
+  (``16`` and ``DW_ATE_signed`` here, respectively) to which the top of the
+  expression stack is to be converted. Maps into a ``DW_OP_convert`` operation
+  that references a base type constructed from the supplied values.
 - ``DW_OP_swap`` swaps top two stack entries.
 - ``DW_OP_xderef`` provides extended dereference mechanism. The entry at the top
   of the stack is treated as an address. The second stack entry is treated as an

llvm/include/llvm/BinaryFormat/Dwarf.h

@@ -129,7 +129,8 @@ enum LocationAtom {
 #include "llvm/BinaryFormat/Dwarf.def"
   DW_OP_lo_user = 0xe0,
   DW_OP_hi_user = 0xff,
-  DW_OP_LLVM_fragment = 0x1000 ///< Only used in LLVM metadata.
+  DW_OP_LLVM_fragment = 0x1000, ///< Only used in LLVM metadata.
+  DW_OP_LLVM_convert  = 0x1001  ///< Only used in LLVM metadata.
 };
 
 enum TypeKind : uint8_t {

llvm/include/llvm/CodeGen/AsmPrinter.h

@@ -510,7 +510,7 @@ class AsmPrinter : public MachineFunctionPass {
   void EmitSLEB128(int64_t Value, const char *Desc = nullptr) const;
 
   /// Emit the specified unsigned leb128 value.
-  void EmitULEB128(uint64_t Value, const char *Desc = nullptr) const;
+  void EmitULEB128(uint64_t Value, const char *Desc = nullptr, unsigned PadTo = 0) const;
 
   /// Emit a .byte 42 directive that corresponds to an encoding.  If verbose
   /// assembly output is enabled, we output comments describing the encoding.

llvm/include/llvm/CodeGen/DIE.h

@@ -38,6 +38,7 @@ namespace llvm {
 class AsmPrinter;
 class DIE;
 class DIEUnit;
+class DwarfCompileUnit;
 class MCExpr;
 class MCSection;
 class MCSymbol;
@@ -229,6 +230,25 @@ class DIELabel {
   void print(raw_ostream &O) const;
 };
 
+//===--------------------------------------------------------------------===//
+/// A BaseTypeRef DIE.
+class DIEBaseTypeRef {
+  const DwarfCompileUnit *CU;
+  const uint64_t Index;
+  static constexpr unsigned ULEB128PadSize = 4;
+
+public:
+  explicit DIEBaseTypeRef(const DwarfCompileUnit *TheCU, uint64_t Idx)
+    : CU(TheCU), Index(Idx) {}
+
+  /// EmitValue - Emit base type reference.
+  void EmitValue(const AsmPrinter *AP, dwarf::Form Form) const;
+  /// SizeOf - Determine size of the base type reference in bytes.
+  unsigned SizeOf(const AsmPrinter *AP, dwarf::Form Form) const;
+
+  void print(raw_ostream &O) const;
+};
+
 //===--------------------------------------------------------------------===//
 /// A simple label difference DIE.
 ///
@@ -349,7 +369,7 @@ class DIEValue {
   /// should be stored by reference instead of by value.
   using ValTy = AlignedCharArrayUnion<DIEInteger, DIEString, DIEExpr, DIELabel,
                                       DIEDelta *, DIEEntry, DIEBlock *,
-                                      DIELoc *, DIELocList>;
+                                      DIELoc *, DIELocList, DIEBaseTypeRef *>;
 
   static_assert(sizeof(ValTy) <= sizeof(uint64_t) ||
                     sizeof(ValTy) <= sizeof(void *),
@@ -501,15 +521,34 @@ struct IntrusiveBackListBase {
     }
     Last = &N;
   }
+
+  void push_front(Node &N) {
+    assert(N.Next.getPointer() == &N && "Expected unlinked node");
+    assert(N.Next.getInt() == true && "Expected unlinked node");
+
+    if (Last) {
+      N.Next.setPointerAndInt(Last->Next.getPointer(), false);
+      Last->Next.setPointerAndInt(&N, true);
+    } else {
+      Last = &N;
+    }
+  }
 };
 
 template <class T> class IntrusiveBackList : IntrusiveBackListBase {
 public:
   using IntrusiveBackListBase::empty;
 
   void push_back(T &N) { IntrusiveBackListBase::push_back(N); }
+  void push_front(T &N) { IntrusiveBackListBase::push_front(N); }
   T &back() { return *static_cast<T *>(Last); }
   const T &back() const { return *static_cast<T *>(Last); }
+  T &front() {
+    return *static_cast<T *>(Last ? Last->Next.getPointer() : nullptr);
+  }
+  const T &front() const {
+    return *static_cast<T *>(Last ? Last->Next.getPointer() : nullptr);
+  }
 
   class const_iterator;
   class iterator
@@ -772,6 +811,13 @@ class DIE : IntrusiveBackListNode, public DIEValueList {
     return Children.back();
   }
 
+  DIE &addChildFront(DIE *Child) {
+    assert(!Child->getParent() && "Child should be orphaned");
+    Child->Owner = this;
+    Children.push_front(*Child);
+    return Children.front();
+  }
+
   /// Find a value in the DIE with the attribute given.
   ///
   /// Returns a default-constructed DIEValue (where \a DIEValue::getType()

llvm/include/llvm/CodeGen/DIEValue.def

@@ -34,6 +34,7 @@ HANDLE_DIEVALUE_SMALL(Integer)
 HANDLE_DIEVALUE_SMALL(String)
 HANDLE_DIEVALUE_SMALL(Expr)
 HANDLE_DIEVALUE_SMALL(Label)
+HANDLE_DIEVALUE_LARGE(BaseTypeRef)
 HANDLE_DIEVALUE_LARGE(Delta)
 HANDLE_DIEVALUE_SMALL(Entry)
 HANDLE_DIEVALUE_LARGE(Block)

llvm/include/llvm/DebugInfo/DWARF/DWARFDebugLoc.h

@@ -86,7 +86,7 @@ class DWARFDebugLoclists {
     SmallVector<Entry, 2> Entries;
     void dump(raw_ostream &OS, uint64_t BaseAddr, bool IsLittleEndian,
               unsigned AddressSize, const MCRegisterInfo *RegInfo,
-              unsigned Indent) const;
+              DWARFUnit *U, unsigned Indent) const;
   };
 
 private:

llvm/include/llvm/DebugInfo/DWARF/DWARFExpression.h

@@ -79,11 +79,13 @@ class DWARFExpression {
     bool Error;
     uint32_t EndOffset;
     uint64_t Operands[2];
+    uint32_t OperandEndOffsets[2];
 
   public:
     Description &getDescription() { return Desc; }
     uint8_t getCode() { return Opcode; }
     uint64_t getRawOperand(unsigned Idx) { return Operands[Idx]; }
+    uint32_t getOperandEndOffset(unsigned Idx) { return OperandEndOffsets[Idx]; }
     uint32_t getEndOffset() { return EndOffset; }
     bool extract(DataExtractor Data, uint16_t Version, uint8_t AddressSize,
                  uint32_t Offset);

llvm/include/llvm/MC/MCStreamer.h

@@ -634,7 +634,7 @@ class MCStreamer {
 
   /// Special case of EmitULEB128Value that avoids the client having to
   /// pass in a MCExpr for constant integers.
-  void EmitULEB128IntValue(uint64_t Value);
+  void EmitULEB128IntValue(uint64_t Value, unsigned PadTo = 0);
 
   /// Special case of EmitSLEB128Value that avoids the client having to
   /// pass in a MCExpr for constant integers.

llvm/lib/AsmParser/LLParser.cpp

@@ -4838,6 +4838,15 @@ bool LLParser::ParseDIExpression(MDNode *&Result, bool IsDistinct) {
         return TokError(Twine("invalid DWARF op '") + Lex.getStrVal() + "'");
       }
 
+      if (Lex.getKind() == lltok::DwarfAttEncoding) {
+        if (unsigned Op = dwarf::getAttributeEncoding(Lex.getStrVal())) {
+          Lex.Lex();
+          Elements.push_back(Op);
+          continue;
+        }
+        return TokError(Twine("invalid DWARF attribute encoding '") + Lex.getStrVal() + "'");
+      }
+
       if (Lex.getKind() != lltok::APSInt || Lex.getAPSIntVal().isSigned())
         return TokError("expected unsigned integer");
 

llvm/lib/BinaryFormat/Dwarf.cpp

@@ -143,6 +143,8 @@ StringRef llvm::dwarf::OperationEncodingString(unsigned Encoding) {
   case DW_OP_##NAME:                                                           \
     return "DW_OP_" #NAME;
 #include "llvm/BinaryFormat/Dwarf.def"
+  case DW_OP_LLVM_convert:
+    return "DW_OP_LLVM_convert";
   case DW_OP_LLVM_fragment:
     return "DW_OP_LLVM_fragment";
   }
@@ -153,6 +155,7 @@ unsigned llvm::dwarf::getOperationEncoding(StringRef OperationEncodingString) {
 #define HANDLE_DW_OP(ID, NAME, VERSION, VENDOR)                                \
   .Case("DW_OP_" #NAME, DW_OP_##NAME)
 #include "llvm/BinaryFormat/Dwarf.def"
+      .Case("DW_OP_LLVM_convert", DW_OP_LLVM_convert)
       .Case("DW_OP_LLVM_fragment", DW_OP_LLVM_fragment)
       .Default(0);
 }

llvm/lib/CodeGen/AsmPrinter/AsmPrinterDwarf.cpp

@@ -42,11 +42,11 @@ void AsmPrinter::EmitSLEB128(int64_t Value, const char *Desc) const {
   OutStreamer->EmitSLEB128IntValue(Value);
 }
 
-void AsmPrinter::EmitULEB128(uint64_t Value, const char *Desc) const {
+void AsmPrinter::EmitULEB128(uint64_t Value, const char *Desc, unsigned PadTo) const {
   if (isVerbose() && Desc)
     OutStreamer->AddComment(Desc);
 
-  OutStreamer->EmitULEB128IntValue(Value);
+  OutStreamer->EmitULEB128IntValue(Value, PadTo);
 }
 
 /// Emit something like ".uleb128 Hi-Lo".

llvm/lib/CodeGen/AsmPrinter/ByteStreamer.h

@@ -31,7 +31,7 @@ class ByteStreamer {
   // For now we're just handling the calls we need for dwarf emission/hashing.
   virtual void EmitInt8(uint8_t Byte, const Twine &Comment = "") = 0;
   virtual void EmitSLEB128(uint64_t DWord, const Twine &Comment = "") = 0;
-  virtual void EmitULEB128(uint64_t DWord, const Twine &Comment = "") = 0;
+  virtual void EmitULEB128(uint64_t DWord, const Twine &Comment = "", unsigned PadTo = 0) = 0;
 };
 
 class APByteStreamer final : public ByteStreamer {
@@ -48,7 +48,7 @@ class APByteStreamer final : public ByteStreamer {
     AP.OutStreamer->AddComment(Comment);
     AP.EmitSLEB128(DWord);
   }
-  void EmitULEB128(uint64_t DWord, const Twine &Comment) override {
+  void EmitULEB128(uint64_t DWord, const Twine &Comment, unsigned PadTo) override {
     AP.OutStreamer->AddComment(Comment);
     AP.EmitULEB128(DWord);
   }
@@ -65,7 +65,7 @@ class HashingByteStreamer final : public ByteStreamer {
   void EmitSLEB128(uint64_t DWord, const Twine &Comment) override {
     Hash.addSLEB128(DWord);
   }
-  void EmitULEB128(uint64_t DWord, const Twine &Comment) override {
+  void EmitULEB128(uint64_t DWord, const Twine &Comment, unsigned PadTo) override {
     Hash.addULEB128(DWord);
   }
 };
@@ -102,9 +102,9 @@ class BufferByteStreamer final : public ByteStreamer {
 
     }
   }
-  void EmitULEB128(uint64_t DWord, const Twine &Comment) override {
+  void EmitULEB128(uint64_t DWord, const Twine &Comment, unsigned PadTo) override {
     raw_svector_ostream OSE(Buffer);
-    unsigned Length = encodeULEB128(DWord, OSE);
+    unsigned Length = encodeULEB128(DWord, OSE, PadTo);
     if (GenerateComments) {
       Comments.push_back(Comment.str());
       // Add some empty comments to keep the Buffer and Comments vectors aligned

llvm/lib/CodeGen/AsmPrinter/DIE.cpp

@@ -505,6 +505,23 @@ unsigned DIELabel::SizeOf(const AsmPrinter *AP, dwarf::Form Form) const {
 LLVM_DUMP_METHOD
 void DIELabel::print(raw_ostream &O) const { O << "Lbl: " << Label->getName(); }
 
+//===----------------------------------------------------------------------===//
+// DIEBaseTypeRef Implementation
+//===----------------------------------------------------------------------===//
+
+void DIEBaseTypeRef::EmitValue(const AsmPrinter *AP, dwarf::Form Form) const {
+  uint64_t Offset = CU->ExprRefedBaseTypes[Index].Die->getOffset();
+  assert(Offset < (1ULL << (ULEB128PadSize * 7)) && "Offset wont fit");
+  AP->EmitULEB128(Offset, nullptr, ULEB128PadSize);
+}
+
+unsigned DIEBaseTypeRef::SizeOf(const AsmPrinter *AP, dwarf::Form Form) const {
+  return ULEB128PadSize;
+}
+
+LLVM_DUMP_METHOD
+void DIEBaseTypeRef::print(raw_ostream &O) const { O << "BaseTypeRef: " << Index; }
+
 //===----------------------------------------------------------------------===//
 // DIEDelta Implementation
 //===----------------------------------------------------------------------===//

llvm/lib/CodeGen/AsmPrinter/DIEHash.cpp

@@ -225,7 +225,7 @@ void DIEHash::hashLocList(const DIELocList &LocList) {
   DwarfDebug &DD = *AP->getDwarfDebug();
   const DebugLocStream &Locs = DD.getDebugLocs();
   for (const auto &Entry : Locs.getEntries(Locs.getList(LocList.getValue())))
-    DD.emitDebugLocEntry(Streamer, Entry);
+    DD.emitDebugLocEntry(Streamer, Entry, nullptr);
 }
 
 // Hash an individual attribute \param Attr based on the type of attribute and
@@ -309,6 +309,7 @@ void DIEHash::hashAttribute(const DIEValue &Value, dwarf::Tag Tag) {
     // FIXME: It's uncertain whether or not we should handle this at the moment.
   case DIEValue::isExpr:
   case DIEValue::isLabel:
+  case DIEValue::isBaseTypeRef:
   case DIEValue::isDelta:
     llvm_unreachable("Add support for additional value types.");
   }

llvm/lib/CodeGen/AsmPrinter/DebugLocEntry.h

@@ -148,8 +148,10 @@ class DebugLocEntry {
   }
 
   /// Lower this entry into a DWARF expression.
-  void finalize(const AsmPrinter &AP, DebugLocStream::ListBuilder &List,
-                const DIBasicType *BT);
+  void finalize(const AsmPrinter &AP,
+                DebugLocStream::ListBuilder &List,
+                const DIBasicType *BT,
+                DwarfCompileUnit &TheCU);
 };
 
 /// Compare two Values for equality.

llvm/lib/CodeGen/AsmPrinter/DwarfCompileUnit.cpp

@@ -17,6 +17,7 @@
 #include "DwarfUnit.h"
 #include "llvm/ADT/None.h"
 #include "llvm/ADT/STLExtras.h"
+#include "llvm/ADT/SmallString.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/BinaryFormat/Dwarf.h"
@@ -1185,3 +1186,26 @@ void DwarfCompileUnit::addAddrTableBase() {
                                          : dwarf::DW_AT_GNU_addr_base,
                   Label, TLOF.getDwarfAddrSection()->getBeginSymbol());
 }
+
+void DwarfCompileUnit::addBaseTypeRef(DIEValueList &Die, int64_t Idx) {
+  Die.addValue(DIEValueAllocator, (dwarf::Attribute)0, dwarf::DW_FORM_udata,
+               new (DIEValueAllocator) DIEBaseTypeRef(this, Idx));
+}
+
+void DwarfCompileUnit::createBaseTypeDIEs() {
+  // Insert the base_type DIEs directly after the CU so that their offsets will
+  // fit in the fixed size ULEB128 used inside the location expressions.
+  // Maintain order by iterating backwards and inserting to the front of CU
+  // child list.
+  for (auto &Btr : reverse(ExprRefedBaseTypes)) {
+    DIE &Die = getUnitDie().addChildFront(
+      DIE::get(DIEValueAllocator, dwarf::DW_TAG_base_type));
+    Twine T(dwarf::AttributeEncodingString(Btr.Encoding) + "_" + Twine(Btr.BitSize));
+    SmallString<32> Str;
+    addString(Die, dwarf::DW_AT_name, T.toStringRef(Str));
+    addUInt(Die, dwarf::DW_AT_encoding, dwarf::DW_FORM_data1, Btr.Encoding);
+    addUInt(Die, dwarf::DW_AT_byte_size, None, Btr.BitSize / 8);
+
+    Btr.Die = &Die;
+  }
+}

llvm/lib/CodeGen/AsmPrinter/DwarfCompileUnit.h

@@ -124,6 +124,16 @@ class DwarfCompileUnit final : public DwarfUnit {
     const DIExpression *Expr;
   };
 
+  struct BaseTypeRef {
+    BaseTypeRef(unsigned BitSize, dwarf::TypeKind Encoding) :
+      BitSize(BitSize), Encoding(Encoding) {}
+    unsigned BitSize;
+    dwarf::TypeKind Encoding;
+    DIE *Die = nullptr;
+  };
+
+  std::vector<BaseTypeRef> ExprRefedBaseTypes;
+
   /// Get or create global variable DIE.
   DIE *
   getOrCreateGlobalVariableDIE(const DIGlobalVariable *GV,
@@ -199,6 +209,8 @@ class DwarfCompileUnit final : public DwarfUnit {
                               SmallVectorImpl<DIE *> &Children,
                               bool *HasNonScopeChildren = nullptr);
 
+  void createBaseTypeDIEs();
+
   /// Construct a DIE for this subprogram scope.
   DIE &constructSubprogramScopeDIE(const DISubprogram *Sub,
                                    LexicalScope *Scope);
@@ -313,6 +325,8 @@ class DwarfCompileUnit final : public DwarfUnit {
   void setDWOId(uint64_t DwoId) { DWOId = DwoId; }
 
   bool hasDwarfPubSections() const;
+
+  void addBaseTypeRef(DIEValueList &Die, int64_t Idx);
 };
 
 } // end namespace llvm