resolve comments

Co-authored-by: Paschalis Mpeis <paschalis.mpeis@arm.com>

llvm/include/llvm/ProfileData/SampleProf.h

@@ -62,7 +62,7 @@ enum class sampleprof_error {
   uncompress_failed,
   zlib_unavailable,
   hash_mismatch,
-  illegal_line_offset
+  illegal_line_offset,
 };
 
 inline std::error_code make_error_code(sampleprof_error E) {
@@ -91,6 +91,8 @@ struct is_error_code_enum<llvm::sampleprof_error> : std::true_type {};
 namespace llvm {
 namespace sampleprof {
 
+constexpr char kVTableProfPrefix[] = "vtables ";
+
 enum SampleProfileFormat {
   SPF_None = 0,
   SPF_Text = 0x1,
@@ -204,6 +206,9 @@ enum class SecProfSummaryFlags : uint32_t {
   /// SecFlagIsPreInlined means this profile contains ShouldBeInlined
   /// contexts thus this is CS preinliner computed.
   SecFlagIsPreInlined = (1 << 4),
+
+  /// SecFlagHasVTableTypeProf means this profile contains vtable type profiles.
+  SecFlagHasVTableTypeProf = (1 << 5),
 };
 
 enum class SecFuncMetadataFlags : uint32_t {
@@ -303,7 +308,7 @@ struct LineLocation {
   }
 
   uint64_t getHashCode() const {
-    return ((uint64_t) Discriminator << 32) | LineOffset;
+    return ((uint64_t)Discriminator << 32) | LineOffset;
   }
 
   uint32_t LineOffset;
@@ -318,16 +323,30 @@ struct LineLocationHash {
 
 LLVM_ABI raw_ostream &operator<<(raw_ostream &OS, const LineLocation &Loc);
 
+/// Key represents type of a C++ polymorphic class type by its vtable and value
+/// represents its counter.
+/// TODO: The class name FunctionId should be renamed to SymbolId in a refactor
+/// change.
+using TypeCountMap = std::map<FunctionId, uint64_t>;
+
+/// Write \p Map to the output stream. Keys are linearized using \p NameTable
+/// and written as ULEB128. Values are written as ULEB128 as well.
+std::error_code
+serializeTypeMap(const TypeCountMap &Map,
+                 const MapVector<FunctionId, uint32_t> &NameTable,
+                 raw_ostream &OS);
+
 /// Representation of a single sample record.
 ///
 /// A sample record is represented by a positive integer value, which
 /// indicates how frequently was the associated line location executed.
 ///
 /// Additionally, if the associated location contains a function call,
-/// the record will hold a list of all the possible called targets. For
+/// the record will hold a list of all the possible called targets and the types
-/// direct calls, this will be the exact function being invoked. For
+/// for virtual table dispatches. For direct calls, this will be the exact
-/// indirect calls (function pointers, virtual table dispatch), this
+/// function being invoked. For indirect calls (function pointers, virtual table
-/// will be a list of one or more functions.
+/// dispatch), this will be a list of one or more functions. For virtual table
+/// dispatches, this record will also hold the type of the object.
 class SampleRecord {
 public:
   using CallTarget = std::pair<FunctionId, uint64_t>;
@@ -746,6 +765,7 @@ using BodySampleMap = std::map<LineLocation, SampleRecord>;
 // memory, which is *very* significant for large profiles.
 using FunctionSamplesMap = std::map<FunctionId, FunctionSamples>;
 using CallsiteSampleMap = std::map<LineLocation, FunctionSamplesMap>;
+using CallsiteTypeMap = std::map<LineLocation, TypeCountMap>;
 using LocToLocMap =
     std::unordered_map<LineLocation, LineLocation, LineLocationHash>;
 
@@ -928,6 +948,14 @@ public:
     return &Iter->second;
   }
 
+  /// Returns the TypeCountMap for inlined callsites at the given \p Loc.
+  const TypeCountMap *findCallsiteTypeSamplesAt(const LineLocation &Loc) const {
+    auto Iter = VirtualCallsiteTypeCounts.find(mapIRLocToProfileLoc(Loc));
+    if (Iter == VirtualCallsiteTypeCounts.end())
+      return nullptr;
+    return &Iter->second;
+  }
+
   /// Returns a pointer to FunctionSamples at the given callsite location
   /// \p Loc with callee \p CalleeName. If no callsite can be found, relax
   /// the restriction to return the FunctionSamples at callsite location
@@ -989,6 +1017,46 @@ public:
     return CallsiteSamples;
   }
 
+  /// Returns vtable access samples for the C++ types collected in this
+  /// function.
+  const CallsiteTypeMap &getCallsiteTypeCounts() const {
+    return VirtualCallsiteTypeCounts;
+  }
+
+  /// Returns the vtable access samples for the C++ types for \p Loc.
+  /// Under the hood, the caller-specified \p Loc will be un-drifted before the
+  /// type sample lookup if possible.
+  TypeCountMap &getTypeSamplesAt(const LineLocation &Loc) {
+    return VirtualCallsiteTypeCounts[mapIRLocToProfileLoc(Loc)];
+  }
+
+  /// Scale \p Other sample counts by \p Weight and add the scaled result to the
+  /// type samples for \p Loc. Under the hoold, the caller-provided \p Loc will
+  /// be un-drifted before the type sample lookup if possible.
+  /// typename T is either a std::map or a DenseMap.
+  template <typename T>
+  sampleprof_error addCallsiteVTableTypeProfAt(const LineLocation &Loc,
+                                               const T &Other,
+                                               uint64_t Weight = 1) {
+    static_assert((std::is_same_v<typename T::key_type, StringRef> ||
+                   std::is_same_v<typename T::key_type, FunctionId>) &&
+                      std::is_same_v<typename T::mapped_type, uint64_t>,
+                  "T must be a map with StringRef or FunctionId as key and "
+                  "uint64_t as value");
+    TypeCountMap &TypeCounts = getTypeSamplesAt(Loc);
+    bool Overflowed = false;
+
+    for (const auto [Type, Count] : Other) {
+      FunctionId TypeId(Type);
+      bool RowOverflow = false;
+      TypeCounts[TypeId] = SaturatingMultiplyAdd(
+          Count, Weight, TypeCounts[TypeId], &RowOverflow);
+      Overflowed |= RowOverflow;
+    }
+    return Overflowed ? sampleprof_error::counter_overflow
+                      : sampleprof_error::success;
+  }
+
   /// Return the maximum of sample counts in a function body. When SkipCallSite
   /// is false, which is the default, the return count includes samples in the
   /// inlined functions. When SkipCallSite is true, the return count only
@@ -1043,6 +1111,10 @@ public:
         mergeSampleProfErrors(Result,
                               FSMap[Rec.first].merge(Rec.second, Weight));
     }
+    for (const auto &[Loc, OtherTypeMap] : Other.getCallsiteTypeCounts())
+      mergeSampleProfErrors(
+          Result, addCallsiteVTableTypeProfAt(Loc, OtherTypeMap, Weight));
+
     return Result;
   }
 
@@ -1286,6 +1358,23 @@ private:
   /// collected in the call to baz() at line offset 8.
   CallsiteSampleMap CallsiteSamples;
 
+  /// Map a virtual callsite to the list of accessed vtables and vtable counts.
+  /// The callsite is referenced by its source location.
+  ///
+  /// For example, given:
+  ///
+  ///     void foo() {
+  ///       ...
+  ///  5    inlined_vcall_bar();
+  ///       ...
+  ///  5    inlined_vcall_baz();
+  ///       ...
+  ///  200  inlined_vcall_qux();
+  ///     }
+  /// This map will contain two entries. One with two types for line offset 5
+  /// and one with one type for line offset 200.
+  CallsiteTypeMap VirtualCallsiteTypeCounts;
+
   /// IR to profile location map generated by stale profile matching.
   ///
   /// Each entry is a mapping from the location on current build to the matched

llvm/include/llvm/ProfileData/SampleProfReader.h

@@ -589,6 +589,10 @@ protected:
   /// Whether the function profiles use FS discriminators.
   bool ProfileIsFS = false;
 
+  /// If true, the profile has vtable profiles and reader should decode them
+  /// to parse profiles correctly.
+  bool ReadVTableProf = false;
+
   /// \brief The format of sample.
   SampleProfileFormat Format = SPF_None;
 
@@ -703,6 +707,14 @@ protected:
   /// otherwise same as readStringFromTable, also return its hash value.
   ErrorOr<std::pair<SampleContext, uint64_t>> readSampleContextFromTable();
 
+  /// Read all virtual functions' vtable access counts for \p FProfile.
+  std::error_code readCallsiteVTableProf(FunctionSamples &FProfile);
+
+  /// Read bytes from the input buffer pointed by `Data` and decode them into
+  /// \p M. `Data` will be advanced to the end of the read bytes when this
+  /// function returns. Returns error if any.
+  std::error_code readVTableTypeCountMap(TypeCountMap &M);
+
   /// Points to the current location in the buffer.
   const uint8_t *Data = nullptr;
 

llvm/include/llvm/ProfileData/SampleProfWriter.h

@@ -217,13 +217,20 @@ protected:
   std::error_code writeBody(const FunctionSamples &S);
   inline void stablizeNameTable(MapVector<FunctionId, uint32_t> &NameTable,
                                 std::set<FunctionId> &V);
-  
+
   MapVector<FunctionId, uint32_t> NameTable;
-  
+
   void addName(FunctionId FName);
   virtual void addContext(const SampleContext &Context);
   void addNames(const FunctionSamples &S);
 
+  /// Write \p CallsiteTypeMap to the output stream \p OS.
+  std::error_code
+  writeCallsiteVTableProf(const CallsiteTypeMap &CallsiteTypeMap,
+                          raw_ostream &OS);
+
+  bool WriteVTableProf = false;
+
 private:
   LLVM_ABI friend ErrorOr<std::unique_ptr<SampleProfileWriter>>
   SampleProfileWriter::create(std::unique_ptr<raw_ostream> &OS,
@@ -412,8 +419,7 @@ private:
 class LLVM_ABI SampleProfileWriterExtBinary
     : public SampleProfileWriterExtBinaryBase {
 public:
-  SampleProfileWriterExtBinary(std::unique_ptr<raw_ostream> &OS)
+  SampleProfileWriterExtBinary(std::unique_ptr<raw_ostream> &OS);
-      : SampleProfileWriterExtBinaryBase(OS) {}
 
 private:
   std::error_code writeDefaultLayout(const SampleProfileMap &ProfileMap);

llvm/lib/ProfileData/SampleProf.cpp

@@ -47,6 +47,24 @@ bool FunctionSamples::ProfileIsPreInlined = false;
 bool FunctionSamples::UseMD5 = false;
 bool FunctionSamples::HasUniqSuffix = true;
 bool FunctionSamples::ProfileIsFS = false;
+
+std::error_code
+serializeTypeMap(const TypeCountMap &Map,
+                 const MapVector<FunctionId, uint32_t> &NameTable,
+                 raw_ostream &OS) {
+  encodeULEB128(Map.size(), OS);
+  for (const auto &[TypeName, SampleCount] : Map) {
+    if (auto NameIndexIter = NameTable.find(TypeName);
+        NameIndexIter != NameTable.end()) {
+      encodeULEB128(NameIndexIter->second, OS);
+    } else {
+      // If the type is not in the name table, we cannot serialize it.
+      return sampleprof_error::truncated_name_table;
+    }
+    encodeULEB128(SampleCount, OS);
+  }
+  return sampleprof_error::success;
+}
 } // namespace sampleprof
 } // namespace llvm
 
@@ -178,6 +196,17 @@ raw_ostream &llvm::sampleprof::operator<<(raw_ostream &OS,
   return OS;
 }
 
+static void printTypeCountMap(raw_ostream &OS, LineLocation Loc,
+                              const TypeCountMap &TypeCountMap) {
+  if (TypeCountMap.empty()) {
+    return;
+  }
+  OS << Loc << ": vtables: ";
+  for (const auto &[Type, Count] : TypeCountMap)
+    OS << Type << ":" << Count << " ";
+  OS << "\n";
+}
+
 /// Print the samples collected for a function on stream \p OS.
 void FunctionSamples::print(raw_ostream &OS, unsigned Indent) const {
   if (getFunctionHash())
@@ -192,7 +221,13 @@ void FunctionSamples::print(raw_ostream &OS, unsigned Indent) const {
     SampleSorter<LineLocation, SampleRecord> SortedBodySamples(BodySamples);
     for (const auto &SI : SortedBodySamples.get()) {
       OS.indent(Indent + 2);
+      const auto &Loc = SI->first;
       OS << SI->first << ": " << SI->second;
+      if (const TypeCountMap *TypeCountMap =
+              this->findCallsiteTypeSamplesAt(Loc)) {
+        OS.indent(Indent + 2);
+        printTypeCountMap(OS, Loc, *TypeCountMap);
+      }
     }
     OS.indent(Indent);
     OS << "}\n";
@@ -214,6 +249,11 @@ void FunctionSamples::print(raw_ostream &OS, unsigned Indent) const {
         OS << Loc << ": inlined callee: " << FuncSample.getFunction() << ": ";
         FuncSample.print(OS, Indent + 4);
       }
+      auto TypeSamplesIter = VirtualCallsiteTypeCounts.find(Loc);
+      if (TypeSamplesIter != VirtualCallsiteTypeCounts.end()) {
+        OS.indent(Indent + 2);
+        printTypeCountMap(OS, Loc, TypeSamplesIter->second);
+      }
     }
     OS.indent(Indent);
     OS << "}\n";

llvm/lib/ProfileData/SampleProfReader.cpp

@@ -197,8 +197,37 @@ enum class LineType {
   CallSiteProfile,
   BodyProfile,
   Metadata,
+  VirtualCallTypeProfile,
 };
 
+// Parse `Input` as a white-space separated list of `vtable:count` pairs. An
+// example input line is `_ZTVbar:1471 _ZTVfoo:630`.
+static bool parseTypeCountMap(StringRef Input,
+                              DenseMap<StringRef, uint64_t> &TypeCountMap) {
+  for (size_t Index = Input.find_first_not_of(' '); Index != StringRef::npos;) {
+    size_t ColonIndex = Input.find(':', Index);
+    if (ColonIndex == StringRef::npos)
+      return false; // No colon found, invalid format.
+    StringRef TypeName = Input.substr(Index, ColonIndex - Index);
+    // CountIndex is the start index of count.
+    size_t CountStartIndex = ColonIndex + 1;
+    // NextIndex is the start index after the 'target:count' pair.
+    size_t NextIndex = Input.find_first_of(' ', CountStartIndex);
+    uint64_t Count;
+    if (Input.substr(CountStartIndex, NextIndex - CountStartIndex)
+            .getAsInteger(10, Count))
+      return false; // Invalid count.
+    // Error on duplicated type names in one line of input.
+    auto [Iter, Inserted] = TypeCountMap.insert({TypeName, Count});
+    if (!Inserted)
+      return false;
+    Index = (NextIndex == StringRef::npos)
+                ? StringRef::npos
+                : Input.find_first_not_of(' ', NextIndex);
+  }
+  return true;
+}
+
 /// Parse \p Input as line sample.
 ///
 /// \param Input input line.
@@ -215,6 +244,7 @@ static bool ParseLine(const StringRef &Input, LineType &LineTy, uint32_t &Depth,
                       uint64_t &NumSamples, uint32_t &LineOffset,
                       uint32_t &Discriminator, StringRef &CalleeName,
                       DenseMap<StringRef, uint64_t> &TargetCountMap,
+                      DenseMap<StringRef, uint64_t> &TypeCountMap,
                       uint64_t &FunctionHash, uint32_t &Attributes,
                       bool &IsFlat) {
   for (Depth = 0; Input[Depth] == ' '; Depth++)
@@ -306,6 +336,10 @@ static bool ParseLine(const StringRef &Input, LineType &LineTy, uint32_t &Depth,
       // Change n3 to the next blank space after colon + integer pair.
       n3 = n4;
     }
+  } else if (Rest.starts_with(kVTableProfPrefix)) {
+    LineTy = LineType::VirtualCallTypeProfile;
+    return parseTypeCountMap(Rest.substr(strlen(kVTableProfPrefix)),
+                             TypeCountMap);
   } else {
     LineTy = LineType::CallSiteProfile;
     size_t n3 = Rest.find_last_of(':');
@@ -374,14 +408,17 @@ std::error_code SampleProfileReaderText::readImpl() {
       uint64_t NumSamples;
       StringRef FName;
       DenseMap<StringRef, uint64_t> TargetCountMap;
+      DenseMap<StringRef, uint64_t> TypeCountMap;
       uint32_t Depth, LineOffset, Discriminator;
       LineType LineTy;
       uint64_t FunctionHash = 0;
       uint32_t Attributes = 0;
       bool IsFlat = false;
+      // TODO: Update ParseLine to return an error code instead of a bool and
+      // report it.
       if (!ParseLine(*LineIt, LineTy, Depth, NumSamples, LineOffset,
-                     Discriminator, FName, TargetCountMap, FunctionHash,
+                     Discriminator, FName, TargetCountMap, TypeCountMap,
-                     Attributes, IsFlat)) {
+                     FunctionHash, Attributes, IsFlat)) {
         reportError(LineIt.line_number(),
                     "Expected 'NUM[.NUM]: NUM[ mangled_name:NUM]*', found " +
                         *LineIt);
@@ -410,6 +447,14 @@ std::error_code SampleProfileReaderText::readImpl() {
         DepthMetadata = 0;
         break;
       }
+
+      case LineType::VirtualCallTypeProfile: {
+        mergeSampleProfErrors(
+            Result, InlineStack.back()->addCallsiteVTableTypeProfAt(
+                        LineLocation(LineOffset, Discriminator), TypeCountMap));
+        break;
+      }
+
       case LineType::BodyProfile: {
         FunctionSamples &FProfile = *InlineStack.back();
         for (const auto &name_count : TargetCountMap) {
@@ -591,6 +636,67 @@ SampleProfileReaderBinary::readSampleContextFromTable() {
   return std::make_pair(Context, Hash);
 }
 
+std::error_code
+SampleProfileReaderBinary::readVTableTypeCountMap(TypeCountMap &M) {
+  auto NumVTableTypes = readNumber<uint32_t>();
+  if (std::error_code EC = NumVTableTypes.getError())
+    return EC;
+
+  for (uint32_t I = 0; I < *NumVTableTypes; ++I) {
+    auto VTableType(readStringFromTable());
+    if (std::error_code EC = VTableType.getError())
+      return EC;
+
+    auto VTableSamples = readNumber<uint64_t>();
+    if (std::error_code EC = VTableSamples.getError())
+      return EC;
+    // The source profile should not have duplicate vtable records at the same
+    // location. In case duplicate vtables are found, reader can emit a warning
+    // but continue processing the profile.
+    if (!M.insert(std::make_pair(*VTableType, *VTableSamples)).second) {
+      Ctx.diagnose(DiagnosticInfoSampleProfile(
+          Buffer->getBufferIdentifier(), 0,
+          "Duplicate vtable type " + VTableType->str() +
+              " at the same location. Additional counters will be ignored.",
+          DS_Warning));
+      continue;
+    }
+  }
+  return sampleprof_error::success;
+}
+
+std::error_code
+SampleProfileReaderBinary::readCallsiteVTableProf(FunctionSamples &FProfile) {
+  assert(ReadVTableProf &&
+         "Cannot read vtable profiles if ReadVTableProf is false");
+
+  // Read the vtable type profile for the callsite.
+  auto NumCallsites = readNumber<uint32_t>();
+  if (std::error_code EC = NumCallsites.getError())
+    return EC;
+
+  for (uint32_t I = 0; I < *NumCallsites; ++I) {
+    auto LineOffset = readNumber<uint64_t>();
+    if (std::error_code EC = LineOffset.getError())
+      return EC;
+
+    if (!isOffsetLegal(*LineOffset))
+      return sampleprof_error::illegal_line_offset;
+
+    auto Discriminator = readNumber<uint64_t>();
+    if (std::error_code EC = Discriminator.getError())
+      return EC;
+
+    // Here we handle FS discriminators:
+    const uint32_t DiscriminatorVal = (*Discriminator) & getDiscriminatorMask();
+
+    if (std::error_code EC = readVTableTypeCountMap(FProfile.getTypeSamplesAt(
+            LineLocation(*LineOffset, DiscriminatorVal))))
+      return EC;
+  }
+  return sampleprof_error::success;
+}
+
 std::error_code
 SampleProfileReaderBinary::readProfile(FunctionSamples &FProfile) {
   auto NumSamples = readNumber<uint64_t>();
@@ -671,6 +777,9 @@ SampleProfileReaderBinary::readProfile(FunctionSamples &FProfile) {
       return EC;
   }
 
+  if (ReadVTableProf)
+    return readCallsiteVTableProf(FProfile);
+
   return sampleprof_error::success;
 }
 
@@ -733,6 +842,8 @@ std::error_code SampleProfileReaderExtBinaryBase::readOneSection(
       FunctionSamples::ProfileIsPreInlined = ProfileIsPreInlined = true;
     if (hasSecFlag(Entry, SecProfSummaryFlags::SecFlagFSDiscriminator))
       FunctionSamples::ProfileIsFS = ProfileIsFS = true;
+    if (hasSecFlag(Entry, SecProfSummaryFlags::SecFlagHasVTableTypeProf))
+      ReadVTableProf = true;
     break;
   case SecNameTable: {
     bool FixedLengthMD5 =

llvm/lib/ProfileData/SampleProfWriter.cpp

@@ -41,6 +41,11 @@
 using namespace llvm;
 using namespace sampleprof;
 
+// To begin with, make this option off by default.
+static cl::opt<bool> ExtBinaryWriteVTableTypeProf(
+    "extbinary-write-vtable-type-prof", cl::init(false), cl::Hidden,
+    cl::desc("Write vtable type profile in ext-binary sample profile writer"));
+
 namespace llvm {
 namespace support {
 namespace endian {
@@ -435,6 +440,9 @@ std::error_code SampleProfileWriterExtBinaryBase::writeOneSection(
     addSectionFlag(SecProfSummary, SecProfSummaryFlags::SecFlagIsPreInlined);
   if (Type == SecProfSummary && FunctionSamples::ProfileIsFS)
     addSectionFlag(SecProfSummary, SecProfSummaryFlags::SecFlagFSDiscriminator);
+  if (Type == SecProfSummary && ExtBinaryWriteVTableTypeProf)
+    addSectionFlag(SecProfSummary,
+                   SecProfSummaryFlags::SecFlagHasVTableTypeProf);
 
   uint64_t SectionStart = markSectionStart(Type, LayoutIdx);
   switch (Type) {
@@ -478,6 +486,12 @@ std::error_code SampleProfileWriterExtBinaryBase::writeOneSection(
   return sampleprof_error::success;
 }
 
+SampleProfileWriterExtBinary::SampleProfileWriterExtBinary(
+    std::unique_ptr<raw_ostream> &OS)
+    : SampleProfileWriterExtBinaryBase(OS) {
+  WriteVTableProf = ExtBinaryWriteVTableTypeProf;
+}
+
 std::error_code SampleProfileWriterExtBinary::writeDefaultLayout(
     const SampleProfileMap &ProfileMap) {
   // The const indices passed to writeOneSection below are specifying the
@@ -587,6 +601,19 @@ std::error_code SampleProfileWriterText::writeSample(const FunctionSamples &S) {
       OS << " " << J.first << ":" << J.second;
     OS << "\n";
     LineCount++;
+
+    if (const TypeCountMap *Map = S.findCallsiteTypeSamplesAt(Loc);
+        Map && !Map->empty()) {
+      OS.indent(Indent + 1);
+      Loc.print(OS);
+      OS << ": ";
+      OS << kVTableProfPrefix;
+      for (const auto [TypeName, Count] : *Map) {
+        OS << TypeName << ":" << Count << " ";
+      }
+      OS << "\n";
+      LineCount++;
+    }
   }
 
   SampleSorter<LineLocation, FunctionSamplesMap> SortedCallsiteSamples(
@@ -603,7 +630,21 @@ std::error_code SampleProfileWriterText::writeSample(const FunctionSamples &S) {
       if (std::error_code EC = writeSample(CalleeSamples))
         return EC;
     }
+
+    if (const TypeCountMap *Map = S.findCallsiteTypeSamplesAt(Loc);
+        Map && !Map->empty()) {
+      OS.indent(Indent);
+      Loc.print(OS);
+      OS << ": ";
+      OS << kVTableProfPrefix;
+      for (const auto [TypeId, Count] : *Map) {
+        OS << TypeId << ":" << Count << " ";
+      }
+      OS << "\n";
+      LineCount++;
+    }
   }
+
   Indent -= 1;
 
   if (FunctionSamples::ProfileIsProbeBased) {
@@ -663,6 +704,17 @@ void SampleProfileWriterBinary::addNames(const FunctionSamples &S) {
       addName(CalleeSamples.getFunction());
       addNames(CalleeSamples);
     }
+
+  if (!WriteVTableProf)
+    return;
+  // Add all the vtable names to NameTable.
+  for (const auto &VTableAccessCountMap :
+       llvm::make_second_range(S.getCallsiteTypeCounts())) {
+    // Add type name to NameTable.
+    for (const auto Type : llvm::make_first_range(VTableAccessCountMap)) {
+      addName(Type);
+    }
+  }
 }
 
 void SampleProfileWriterExtBinaryBase::addContext(
@@ -801,6 +853,22 @@ std::error_code SampleProfileWriterExtBinaryBase::writeHeader(
   return sampleprof_error::success;
 }
 
+std::error_code SampleProfileWriterBinary::writeCallsiteVTableProf(
+    const CallsiteTypeMap &CallsiteTypeMap, raw_ostream &OS) {
+  assert(WriteVTableProf &&
+         "writeCallsiteVTableProf should not be called if WriteVTableProf is "
+         "false");
+
+  encodeULEB128(CallsiteTypeMap.size(), OS);
+  for (const auto &[Loc, TypeMap] : CallsiteTypeMap) {
+    Loc.serialize(OS);
+    if (std::error_code EC = serializeTypeMap(TypeMap, getNameTable(), OS))
+      return EC;
+  }
+
+  return sampleprof_error::success;
+}
+
 std::error_code SampleProfileWriterBinary::writeSummary() {
   auto &OS = *OutputStream;
   encodeULEB128(Summary->getTotalCount(), OS);
@@ -838,14 +906,16 @@ std::error_code SampleProfileWriterBinary::writeBody(const FunctionSamples &S) {
   for (const auto &J : S.getCallsiteSamples())
     NumCallsites += J.second.size();
   encodeULEB128(NumCallsites, OS);
-  for (const auto &[Loc, CalleeFunctionSampleMap] : S.getCallsiteSamples())
+  for (const auto &J : S.getCallsiteSamples())
-    for (const auto &FunctionSample :
+    for (const auto &FS : J.second) {
-         llvm::make_second_range(CalleeFunctionSampleMap)) {
+      J.first.serialize(OS);
-      Loc.serialize(OS);
+      if (std::error_code EC = writeBody(FS.second))
-      if (std::error_code EC = writeBody(FunctionSample))
         return EC;
     }
 
+  if (WriteVTableProf)
+    return writeCallsiteVTableProf(S.getCallsiteTypeCounts(), OS);
+
   return sampleprof_error::success;
 }
 

llvm/test/tools/llvm-profdata/Inputs/profile-symbol-list-ext.expected

@@ -0,0 +1,44 @@
+Function: main: 368038, 0, 7 sampled lines
+Samples collected in the function's body {
+  4: 1068
+  4.2: 1068
+  5: 2150
+  5.1: 2150
+  6: 4160
+  7: 1068
+  9: 4128, calls: _Z3bari:2942 _Z3fooi:1262
+  9: vtables: _ZTVbar:2942 _ZTVfoo:1260
+}
+Samples collected in inlined callsites {
+  10: inlined callee: inline1: 2000, 0, 1 sampled lines
+    Samples collected in the function's body {
+      1: 2000
+    }
+    No inlined callsites in this function
+  10: inlined callee: inline2: 4000, 0, 1 sampled lines
+    Samples collected in the function's body {
+      1: 4000
+    }
+    No inlined callsites in this function
+  10: vtables: _ZTVinline1:2000 _ZTVinline2:4000
+}
+Function: _Z3bari: 40602, 2874, 1 sampled lines
+Samples collected in the function's body {
+  1: 2874
+}
+No inlined callsites in this function
+Function: _Z3fooi: 15422, 1220, 1 sampled lines
+Samples collected in the function's body {
+  1: 1220
+}
+No inlined callsites in this function
+======== Dump profile symbol list ========
+_Z3goov
+_Z3sumii
+__libc_csu_fini
+__libc_csu_init
+_dl_relocate_static_pie
+_fini
+_init
+_start
+main

llvm/test/tools/llvm-profdata/Inputs/sample-profile-ext.proftext

@@ -0,0 +1,18 @@
+main:184019:0
+ 4: 534
+ 4.2: 534
+ 5: 1075
+ 5.1: 1075
+ 6: 2080
+ 7: 534
+ 9: 2064 _Z3bari:1471 _Z3fooi:631
+ 9: vtables _ZTVbar:1471 _ZTVfoo:630
+ 10: inline1:1000
+  1: 1000
+ 10: inline2:2000
+  1: 2000
+ 10: vtables _ZTVinline1:1000 _ZTVinline2:2000
+_Z3bari:20301:1437
+ 1: 1437
+_Z3fooi:7711:610
+ 1: 610

llvm/test/tools/llvm-profdata/profile-symbol-list-compress.test

@@ -4,3 +4,12 @@ REQUIRES: zlib
 ; RUN: llvm-profdata merge -sample -extbinary -compress-all-sections %t.1.output %t.2.output -o %t.3.output
 ; RUN: llvm-profdata show -sample -show-prof-sym-list %t.3.output > %t.4.output
 ; RUN: diff -b %S/Inputs/profile-symbol-list.expected %t.4.output
+
+;; Generate two SampleFDO binary profiles and merge them.
+;; Tests that the vtable counters in the merged profile are the aggregated
+;; result from both sources.
+; RUN: llvm-profdata merge -sample -extbinary -compress-all-sections -extbinary-write-vtable-type-prof -prof-sym-list=%S/Inputs/profile-symbol-list-1.text %S/Inputs/sample-profile-ext.proftext -o %t.1.output
+; RUN: llvm-profdata merge -sample -extbinary -compress-all-sections -extbinary-write-vtable-type-prof -prof-sym-list=%S/Inputs/profile-symbol-list-2.text %S/Inputs/sample-profile-ext.proftext -o %t.2.output
+; RUN: llvm-profdata merge -sample -extbinary -compress-all-sections -extbinary-write-vtable-type-prof %t.1.output %t.2.output -o %t.3.output
+; RUN: llvm-profdata show -sample -show-prof-sym-list %t.3.output > %t.4.output
+; RUN: diff -b %S/Inputs/profile-symbol-list-ext.expected %t.4.output

llvm/test/tools/llvm-profdata/profile-symbol-list.test

@@ -7,3 +7,12 @@
 ; RUN: llvm-profdata show -sample -show-sec-info-only %t.5.output  | FileCheck %s -check-prefix=NOSYMLIST
 
 ; NOSYMLIST: ProfileSymbolListSection {{.*}} Size: 0
+
+;; Generate two SampleFDO binary profiles and merge them.
+;; Tests that the vtable counters in the merged profile are the aggregated
+;; result from both sources.
+; RUN: llvm-profdata merge -sample -extbinary -extbinary-write-vtable-type-prof -prof-sym-list=%S/Inputs/profile-symbol-list-1.text %S/Inputs/sample-profile-ext.proftext -o %t.1.output
+; RUN: llvm-profdata merge -sample -extbinary -extbinary-write-vtable-type-prof -prof-sym-list=%S/Inputs/profile-symbol-list-2.text %S/Inputs/sample-profile-ext.proftext -o %t.2.output
+; RUN: llvm-profdata merge -sample -extbinary -extbinary-write-vtable-type-prof %t.1.output %t.2.output -o %t.3.output
+; RUN: llvm-profdata show -sample -show-prof-sym-list %t.3.output > %t.4.output
+; RUN: diff -b %S/Inputs/profile-symbol-list-ext.expected %t.4.output

llvm/test/tools/llvm-profdata/roundtrip.test

@@ -16,3 +16,9 @@ RUN: llvm-profdata merge --sample --binary -output=%t.4.profdata %S/Inputs/sampl
 RUN: llvm-profdata merge --sample --extbinary -output=%t.5.profdata %t.4.profdata
 RUN: llvm-profdata merge --sample --text -output=%t.4.proftext %t.5.profdata
 RUN: diff -b %t.4.proftext %S/Inputs/sample-profile.proftext
+# Round trip from text --> extbinary --> text.
+# The vtable profile is supported by ext-binary profile but not raw binary profile format,
+# so we don't use raw binary profile format in this roundtrip.
+RUN: llvm-profdata merge --sample --extbinary -extbinary-write-vtable-type-prof --output=%t.5.profdata %S/Inputs/sample-profile-ext.proftext
+RUN: llvm-profdata merge --sample --text --output=%t.5.proftext %t.5.profdata
+RUN: diff -b %t.5.proftext %S/Inputs/sample-profile-ext.proftext