[DWARF] Extend .debug_info abbreviations with DW_AT and DW_FORM offsets

[ayermolo]

Summary

Extend DWARFAbbreviationDeclaration::AttributeSpec (abbreviations used in
.debug_info section) with AttrOffset and FormOffset, pointing at offsets of
DW_AT (attribute) and DW_FORM (format) in a DIE. This enables a client to patch
these fields (used by BOLT)

[Amir]

clang-format

llvm/include/llvm/DebugInfo/DWARF/DWARFAbbreviationDeclaration.h

 
 class DWARFFormValue;
 class DWARFUnit;
 class raw_ostream;
 
 class DWARFAbbreviationDeclaration {
 public:
   struct AttributeSpec {
-    AttributeSpec(dwarf::Attribute A, dwarf::Form F, int64_t Value)
-        : Attr(A), Form(F), Value(Value) {
+    AttributeSpec(dwarf::Attribute A, dwarf::Form F, int64_t Value,
+                  uint32_t AttrOffset = -1U, uint32_t FormOffset = -1U)
+        : Attr(A), Form(F), AttrOffset(AttrOffset), FormOffset(FormOffset),
+          Value(Value) {
       assert(isImplicitConst());
     }
-    AttributeSpec(dwarf::Attribute A, dwarf::Form F, Optional<uint8_t> ByteSize)
-        : Attr(A), Form(F) {
+    AttributeSpec(dwarf::Attribute A, dwarf::Form F, Optional<uint8_t> ByteSize,
+                  uint32_t AttrOffset = -1U, uint32_t FormOffset = -1U)
+        : Attr(A), Form(F), AttrOffset(AttrOffset), FormOffset(FormOffset) {
       assert(!isImplicitConst());
       this->ByteSize.HasByteSize = ByteSize.hasValue();
       if (this->ByteSize.HasByteSize)
         this->ByteSize.ByteSize = *ByteSize;
     }
 
     dwarf::Attribute Attr;
     dwarf::Form Form;
+    uint32_t AttrOffset;
+    uint32_t FormOffset;
 
   private:
     /// The following field is used for ByteSize for non-implicit_const
     /// attributes and as value for implicit_const ones, indicated by
     /// Form == DW_FORM_implicit_const.
     /// The following cases are distinguished:
     /// * Form != DW_FORM_implicit_const and HasByteSize is true:
     ///     ByteSize contains the fixed size in bytes for the Form in this
bool getAttrIsImplicitConstByIndex(uint32_t idx) const {
     return AttributeSpecs[idx].isImplicitConst();
   }
 
   int64_t getAttrImplicitConstValueByIndex(uint32_t idx) const {
     assert(idx < AttributeSpecs.size());
     return AttributeSpecs[idx].getImplicitConstValue();
   }
 
+  const AttributeSpec *findAttribute(dwarf::Attribute Attr) const;
+
   /// Get the index of the specified attribute.
   ///
   /// Searches the this abbreviation declaration for the index of the specified
   /// attribute.
   ///
   /// \param attr DWARF attribute to search for.
   /// \returns Optional index of the attribute if found, None otherwise.
   Optional<uint32_t> findAttributeIndex(dwarf::Attribute attr) const;
 
   /// Extract a DWARF form value from a DIE specified by DIE offset.
   ///
   /// Extract an attribute value for a DWARFUnit given the DIE offset and the
   /// attribute.
   ///
   /// \param DIEOffset the DIE offset that points to the ULEB128 abbreviation
   /// code in the .debug_info data.
   /// \param Attr DWARF attribute to search for.
   /// \param U the DWARFUnit the contains the DIE.
   /// \returns Optional DWARF form value if the attribute was extracted.
   Optional<DWARFFormValue> getAttributeValue(const uint64_t DIEOffset,
                                              const dwarf::Attribute Attr,
-                                             const DWARFUnit &U) const;
+                                             const DWARFUnit &U,
+                                             uint64_t *OffsetPtr = 0) const;
 
   bool extract(DataExtractor Data, uint64_t* OffsetPtr);
   void dump(raw_ostream &OS) const;
 
   // Return an optional byte size of all attribute data in this abbreviation
   // if a constant byte size can be calculated given a DWARFUnit. This allows
   // DWARF parsing to be faster as many DWARF DIEs have a fixed byte size.
   Optional<size_t> getFixedAttributesByteSize(const DWARFUnit &U) const;

llvm/include/llvm/DebugInfo/DWARF/DWARFContext.h

public:
   };
 
   /// Get the compilation unit, the function DIE and lexical block DIE for the
   /// given address where applicable.
   /// TODO: change input parameter from "uint64_t Address"
   ///       into "SectionedAddress Address"
   DIEsForAddress getDIEsForAddress(uint64_t Address);
 
+  /// Get offset to an attribute value within a compile unit
+  /// or 0 if the attribute was not found.
+  uint64_t getAttrFieldOffsetForUnit(DWARFUnit *U, dwarf::Attribute Attr) const;
+
   DILineInfo getLineInfoForAddress(
       object::SectionedAddress Address,
       DILineInfoSpecifier Specifier = DILineInfoSpecifier()) override;
   DILineInfoTable getLineInfoForAddressRange(
       object::SectionedAddress Address, uint64_t Size,
       DILineInfoSpecifier Specifier = DILineInfoSpecifier()) override;
   DIInliningInfo getInliningInfoForAddress(
       object::SectionedAddress Address,

llvm/include/llvm/DebugInfo/DWARF/DWARFDie.h

public:
   ///
   /// Extract an attribute value from this DIE only. This call doesn't look
   /// for the attribute value in any DW_AT_specification or
   /// DW_AT_abstract_origin referenced DIEs.
   ///
   /// \param Attr the attribute to extract.
   /// \returns an optional DWARFFormValue that will have the form value if the
   /// attribute was successfully extracted.
-  Optional<DWARFFormValue> find(dwarf::Attribute Attr) const;
+  Optional<DWARFFormValue> find(dwarf::Attribute Attr,
+                                uint64_t *OffsetPtr = 0) const;
 
   /// Extract the first value of any attribute in Attrs from this DIE.
   ///
   /// Extract the first attribute that matches from this DIE only. This call
   /// doesn't look for the attribute value in any DW_AT_specification or
   /// DW_AT_abstract_origin referenced DIEs. The attributes will be searched
   /// linearly in the order they are specified within Attrs.
   ///

llvm/lib/DebugInfo/DWARF/DWARFAbbreviationDeclaration.cpp

DWARFAbbreviationDeclaration::extract(DataExtractor Data,
   HasChildren = (ChildrenByte == DW_CHILDREN_yes);
   // Assign a value to our optional FixedAttributeSize member variable. If
   // this member variable still has a value after the while loop below, then
   // all attribute data in this abbreviation declaration has a fixed byte size.
   FixedAttributeSize = FixedSizeInfo();
 
   // Read all of the abbreviation attributes and forms.
   while (true) {
+    uint32_t AOff = *OffsetPtr;
     auto A = static_cast<Attribute>(Data.getULEB128(OffsetPtr));
+    uint32_t FOff = *OffsetPtr;
     auto F = static_cast<Form>(Data.getULEB128(OffsetPtr));
     if (A && F) {
       bool IsImplicitConst = (F == DW_FORM_implicit_const);
       if (IsImplicitConst) {
         int64_t V = Data.getSLEB128(OffsetPtr);
-        AttributeSpecs.push_back(AttributeSpec(A, F, V));
+        AttributeSpecs.push_back(AttributeSpec(A, F, V, AOff, FOff));
         continue;
       }
       Optional<uint8_t> ByteSize;
       // If this abbrevation still has a fixed byte size, then update the
       // FixedAttributeSize as needed.
       switch (F) {
       case DW_FORM_addr:
         if (FixedAttributeSize)
if (A && F) {
         }
         // Indicate we no longer have a fixed byte size for this
         // abbreviation by clearing the FixedAttributeSize optional value
         // so it doesn't have a value.
         FixedAttributeSize.reset();
         break;
       }
       // Record this attribute and its fixed size if it has one.
-      AttributeSpecs.push_back(AttributeSpec(A, F, ByteSize));
+      AttributeSpecs.push_back(AttributeSpec(A, F, ByteSize, AOff, FOff));
     } else if (A == 0 && F == 0) {
       // We successfully reached the end of this abbreviation declaration
       // since both attribute and form are zero.
       break;
     } else {
       // Attribute and form pairs must either both be non-zero, in which case
       // they are added to the abbreviation declaration, or both be zero to
       // terminate the abbrevation declaration. In this case only one was
for (const AttributeSpec &Spec : AttributeSpecs) {
     OS << formatv("\t{0}\t{1}", Spec.Attr, Spec.Form);
     if (Spec.isImplicitConst())
       OS << '\t' << Spec.getImplicitConstValue();
     OS << '\n';
   }
   OS << '\n';
 }
 
+const DWARFAbbreviationDeclaration::AttributeSpec *
+DWARFAbbreviationDeclaration::findAttribute(dwarf::Attribute Attr) const {
+  for (uint32_t i = 0, e = AttributeSpecs.size(); i != e; ++i) {
+    if (AttributeSpecs[i].Attr == Attr)
+      return &AttributeSpecs[i];
+  }
+  return nullptr;
+}
+
 Optional<uint32_t>
 DWARFAbbreviationDeclaration::findAttributeIndex(dwarf::Attribute Attr) const {
   for (uint32_t i = 0, e = AttributeSpecs.size(); i != e; ++i) {
     if (AttributeSpecs[i].Attr == Attr)
       return i;
   }
   return None;
 }
 
 Optional<DWARFFormValue> DWARFAbbreviationDeclaration::getAttributeValue(
-    const uint64_t DIEOffset, const dwarf::Attribute Attr,
-    const DWARFUnit &U) const {
+    const uint64_t DIEOffset, const dwarf::Attribute Attr, const DWARFUnit &U,
+    uint64_t *OffsetPtr) const {
   // Check if this abbreviation has this attribute without needing to skip
   // any data so we can return quickly if it doesn't.
   Optional<uint32_t> MatchAttrIndex = findAttributeIndex(Attr);
   if (!MatchAttrIndex)
     return None;
 
   auto DebugInfoData = U.getDebugInfoExtractor();
 
   // Add the byte size of ULEB that for the abbrev Code so we can start
   // skipping the attribute data.
   uint64_t Offset = DIEOffset + CodeByteSize;
   for (uint32_t CurAttrIdx = 0; CurAttrIdx != *MatchAttrIndex; ++CurAttrIdx)
     // Match Offset along until we get to the attribute we want.
     if (auto FixedSize = AttributeSpecs[CurAttrIdx].getByteSize(U))
       Offset += *FixedSize;
     else
       DWARFFormValue::skipValue(AttributeSpecs[CurAttrIdx].Form, DebugInfoData,
                                 &Offset, U.getFormParams());
 
   // We have arrived at the attribute to extract, extract if from Offset.
+  if (OffsetPtr)
+    *OffsetPtr = Offset;
   const AttributeSpec &Spec = AttributeSpecs[*MatchAttrIndex];
   if (Spec.isImplicitConst())
     return DWARFFormValue::createFromSValue(Spec.Form,
                                             Spec.getImplicitConstValue());
 
   DWARFFormValue FormValue(Spec.Form);
   if (FormValue.extractValue(DebugInfoData, &Offset, U.getFormParams(), &U))
     return FormValue;

llvm/lib/DebugInfo/DWARF/DWARFContext.cpp

if (Spec.FLIKind != FileLineInfoKind::None) {
                                    CallDiscriminator);
       }
     }
     InliningInfo.addFrame(Frame);
   }
   return InliningInfo;
 }
 
+uint64_t DWARFContext::getAttrFieldOffsetForUnit(DWARFUnit *U,
+                                                 dwarf::Attribute Attr) const {
+  const auto UnitDIE = U->getUnitDIE();
+  if (!UnitDIE)
+    return 0;
+
+  uint64_t Offset = 0;
+  if (!UnitDIE.find(Attr, &Offset))
+    return 0;
+
+  return Offset;
+}
+
 std::shared_ptr<DWARFContext>
 DWARFContext::getDWOContext(StringRef AbsolutePath) {
   if (auto S = DWP.lock()) {
     DWARFContext *Ctxt = S->Context.get();
     return std::shared_ptr<DWARFContext>(std::move(S), Ctxt);
   }
 
   std::weak_ptr<DWOFile> *Entry = &DWOFiles[AbsolutePath];

llvm/lib/DebugInfo/DWARF/DWARFDie.cpp

 
 bool DWARFDie::isSubprogramDIE() const { return getTag() == DW_TAG_subprogram; }
 
 bool DWARFDie::isSubroutineDIE() const {
   auto Tag = getTag();
   return Tag == DW_TAG_subprogram || Tag == DW_TAG_inlined_subroutine;
 }
 
-Optional<DWARFFormValue> DWARFDie::find(dwarf::Attribute Attr) const {
+Optional<DWARFFormValue> DWARFDie::find(dwarf::Attribute Attr,
+                                        uint64_t *OffsetPtr) const {
   if (!isValid())
     return None;
   auto AbbrevDecl = getAbbreviationDeclarationPtr();
   if (AbbrevDecl)
-    return AbbrevDecl->getAttributeValue(getOffset(), Attr, *U);
+    return AbbrevDecl->getAttributeValue(getOffset(), Attr, *U, OffsetPtr);
   return None;
 }
 
 Optional<DWARFFormValue>
 DWARFDie::find(ArrayRef<dwarf::Attribute> Attrs) const {
   if (!isValid())
     return None;
   auto AbbrevDecl = getAbbreviationDeclarationPtr();