[SampleFDO] Add ExtBinary format to support extension of binary profile.

This is a patch split from https://reviews.llvm.org/D66374. It tries to add
a new format of profile called ExtBinary. The format adds a section header
table to the profile and organize the profile in sections, so the future
extension like adding a new section or extending an existing section will be
easier while keeping backward compatiblity feasible.

Differential Revision: https://reviews.llvm.org/D66513

llvm-svn: 369798

llvm/include/llvm/ProfileData/SampleProf.h

@@ -84,6 +84,7 @@ enum SampleProfileFormat {
   SPF_Text = 0x1,
   SPF_Compact_Binary = 0x2,
   SPF_GCC = 0x3,
+  SPF_Ext_Binary = 0x4,
   SPF_Binary = 0xff
 };
 
@@ -106,6 +107,27 @@ static inline StringRef getRepInFormat(StringRef Name,
 
 static inline uint64_t SPVersion() { return 103; }
 
+// Section Type used by SampleProfileExtBinaryBaseReader and
+// SampleProfileExtBinaryBaseWriter. Never change the existing
+// value of enum. Only append new ones.
+enum SecType {
+  SecInValid = 0,
+  SecProfSummary = 1,
+  SecNameTable = 2,
+  // marker for the first type of profile.
+  SecFuncProfileFirst = 32,
+  SecLBRProfile = SecFuncProfileFirst
+};
+
+// Entry type of section header table used by SampleProfileExtBinaryBaseReader
+// and SampleProfileExtBinaryBaseWriter.
+struct SecHdrTableEntry {
+  SecType Type;
+  uint64_t Flag;
+  uint64_t Offset;
+  uint64_t Size;
+};
+
 /// Represents the relative location of an instruction.
 ///
 /// Instruction locations are specified by the line offset from the

llvm/include/llvm/ProfileData/SampleProfReader.h

@@ -416,38 +416,89 @@ class SampleProfileReaderBinary : public SampleProfileReader {
   /// Read the contents of the given profile instance.
   std::error_code readProfile(FunctionSamples &FProfile);
 
+  /// Read the contents of Magic number and Version number.
+  std::error_code readMagicIdent();
+
+  /// Read profile summary.
+  std::error_code readSummary();
+
+  /// Read the whole name table.
+  virtual std::error_code readNameTable();
+
   /// Points to the current location in the buffer.
   const uint8_t *Data = nullptr;
 
   /// Points to the end of the buffer.
   const uint8_t *End = nullptr;
 
+  /// Function name table.
+  std::vector<StringRef> NameTable;
+
+  /// Read a string indirectly via the name table.
+  virtual ErrorOr<StringRef> readStringFromTable();
+
 private:
   std::error_code readSummaryEntry(std::vector<ProfileSummaryEntry> &Entries);
   virtual std::error_code verifySPMagic(uint64_t Magic) = 0;
+};
 
-  /// Read profile summary.
-  std::error_code readSummary();
+class SampleProfileReaderRawBinary : public SampleProfileReaderBinary {
+private:
+  virtual std::error_code verifySPMagic(uint64_t Magic) override;
 
-  /// Read the whole name table.
-  virtual std::error_code readNameTable() = 0;
+public:
+  SampleProfileReaderRawBinary(std::unique_ptr<MemoryBuffer> B, LLVMContext &C,
+                               SampleProfileFormat Format = SPF_Binary)
+      : SampleProfileReaderBinary(std::move(B), C, Format) {}
 
-  /// Read a string indirectly via the name table.
-  virtual ErrorOr<StringRef> readStringFromTable() = 0;
+  /// \brief Return true if \p Buffer is in the format supported by this class.
+  static bool hasFormat(const MemoryBuffer &Buffer);
 };
 
-class SampleProfileReaderRawBinary : public SampleProfileReaderBinary {
+/// SampleProfileReaderExtBinaryBase/SampleProfileWriterExtBinaryBase defines
+/// the basic structure of the extensible binary format.
+/// The format is organized in sections except the magic and version number
+/// at the beginning. There is a section table before all the sections, and
+/// each entry in the table describes the entry type, start, size and
+/// attributes. The format in each section is defined by the section itself.
+///
+/// It is easy to add a new section while maintaining the backward
+/// compatibility of the profile. Nothing extra needs to be done. If we want
+/// to extend an existing section, like add cache misses information in
+/// addition to the sample count in the profile body, we can add a new section
+/// with the extension and retire the existing section, and we could choose
+/// to keep the parser of the old section if we want the reader to be able
+/// to read both new and old format profile.
+///
+/// SampleProfileReaderExtBinary/SampleProfileWriterExtBinary define the
+/// commonly used sections of a profile in extensible binary format. It is
+/// possible to define other types of profile inherited from
+/// SampleProfileReaderExtBinaryBase/SampleProfileWriterExtBinaryBase.
+class SampleProfileReaderExtBinaryBase : public SampleProfileReaderBinary {
+protected:
+  std::vector<SecHdrTableEntry> SecHdrTable;
+  std::error_code readSecHdrTableEntry();
+  std::error_code readSecHdrTable();
+  virtual std::error_code readHeader() override;
+  virtual std::error_code verifySPMagic(uint64_t Magic) = 0;
+
+public:
+  SampleProfileReaderExtBinaryBase(std::unique_ptr<MemoryBuffer> B,
+                                   LLVMContext &C, SampleProfileFormat Format)
+      : SampleProfileReaderBinary(std::move(B), C, Format) {}
+
+  /// Read sample profiles in extensible format from the associated file.
+  std::error_code read() override;
+};
+
+class SampleProfileReaderExtBinary : public SampleProfileReaderExtBinaryBase {
 private:
-  /// Function name table.
-  std::vector<StringRef> NameTable;
   virtual std::error_code verifySPMagic(uint64_t Magic) override;
-  virtual std::error_code readNameTable() override;
-  /// Read a string indirectly via the name table.
-  virtual ErrorOr<StringRef> readStringFromTable() override;
 
 public:
-  SampleProfileReaderRawBinary(std::unique_ptr<MemoryBuffer> B, LLVMContext &C)
-      : SampleProfileReaderBinary(std::move(B), C, SPF_Binary) {}
+  SampleProfileReaderExtBinary(std::unique_ptr<MemoryBuffer> B, LLVMContext &C,
+                               SampleProfileFormat Format = SPF_Ext_Binary)
+      : SampleProfileReaderExtBinaryBase(std::move(B), C, Format) {}
 
   /// \brief Return true if \p Buffer is in the format supported by this class.
   static bool hasFormat(const MemoryBuffer &Buffer);

llvm/include/llvm/ProfileData/SampleProfWriter.h

@@ -36,7 +36,7 @@ class SampleProfileWriter {
   /// Write sample profiles in \p S.
   ///
   /// \returns status code of the file update operation.
-  virtual std::error_code write(const FunctionSamples &S) = 0;
+  virtual std::error_code writeSample(const FunctionSamples &S) = 0;
 
   /// Write all the sample profiles in the given map of samples.
   ///
@@ -64,6 +64,10 @@ class SampleProfileWriter {
   virtual std::error_code
   writeHeader(const StringMap<FunctionSamples> &ProfileMap) = 0;
 
+  // Write function profiles to the profile file.
+  virtual std::error_code
+  writeFuncProfiles(const StringMap<FunctionSamples> &ProfileMap);
+
   /// Output stream where to emit the profile to.
   std::unique_ptr<raw_ostream> OutputStream;
 
@@ -72,12 +76,15 @@ class SampleProfileWriter {
 
   /// Compute summary for this profile.
   void computeSummary(const StringMap<FunctionSamples> &ProfileMap);
+
+  /// Profile format.
+  SampleProfileFormat Format;
 };
 
 /// Sample-based profile writer (text format).
 class SampleProfileWriterText : public SampleProfileWriter {
 public:
-  std::error_code write(const FunctionSamples &S) override;
+  std::error_code writeSample(const FunctionSamples &S) override;
 
 protected:
   SampleProfileWriterText(std::unique_ptr<raw_ostream> &OS)
@@ -102,13 +109,14 @@ class SampleProfileWriterText : public SampleProfileWriter {
 /// Sample-based profile writer (binary format).
 class SampleProfileWriterBinary : public SampleProfileWriter {
 public:
-  virtual std::error_code write(const FunctionSamples &S) override;
+  virtual std::error_code writeSample(const FunctionSamples &S) override;
+
+protected:
   SampleProfileWriterBinary(std::unique_ptr<raw_ostream> &OS)
       : SampleProfileWriter(OS) {}
 
-protected:
-  virtual std::error_code writeNameTable() = 0;
-  virtual std::error_code writeMagicIdent() = 0;
+  virtual std::error_code writeMagicIdent(SampleProfileFormat Format);
+  virtual std::error_code writeNameTable();
   virtual std::error_code
   writeHeader(const StringMap<FunctionSamples> &ProfileMap) override;
   std::error_code writeSummary();
@@ -118,21 +126,61 @@ class SampleProfileWriterBinary : public SampleProfileWriter {
 
   MapVector<StringRef, uint32_t> NameTable;
 
-private:
   void addName(StringRef FName);
   void addNames(const FunctionSamples &S);
 
+private:
   friend ErrorOr<std::unique_ptr<SampleProfileWriter>>
   SampleProfileWriter::create(std::unique_ptr<raw_ostream> &OS,
                               SampleProfileFormat Format);
 };
 
 class SampleProfileWriterRawBinary : public SampleProfileWriterBinary {
   using SampleProfileWriterBinary::SampleProfileWriterBinary;
+};
+
+class SampleProfileWriterExtBinaryBase : public SampleProfileWriterBinary {
+  using SampleProfileWriterBinary::SampleProfileWriterBinary;
+
+public:
+  virtual std::error_code
+  write(const StringMap<FunctionSamples> &ProfileMap) override;
 
 protected:
-  virtual std::error_code writeNameTable() override;
-  virtual std::error_code writeMagicIdent() override;
+  uint64_t markSectionStart();
+  uint64_t addNewSection(SecType Sec, uint64_t SectionStart);
+  virtual void initSectionLayout() = 0;
+  virtual std::error_code
+  writeSections(const StringMap<FunctionSamples> &ProfileMap) = 0;
+
+  // Specifiy the section layout in the profile. Note that the order in
+  // SecHdrTable (order to collect sections) may be different from the
+  // order in SectionLayout (order to write out sections into profile).
+  SmallVector<SecType, 8> SectionLayout;
+
+private:
+  void allocSecHdrTable();
+  std::error_code writeSecHdrTable();
+  virtual std::error_code
+  writeHeader(const StringMap<FunctionSamples> &ProfileMap) override;
+
+  // The location where the output stream starts.
+  uint64_t FileStart;
+  // The location in the output stream where the SecHdrTable should be
+  // written to.
+  uint64_t SecHdrTableOffset;
+  std::vector<SecHdrTableEntry> SecHdrTable;
+};
+
+class SampleProfileWriterExtBinary : public SampleProfileWriterExtBinaryBase {
+  using SampleProfileWriterExtBinaryBase::SampleProfileWriterExtBinaryBase;
+
+private:
+  virtual void initSectionLayout() {
+    SectionLayout = {SecProfSummary, SecNameTable, SecLBRProfile};
+  };
+  virtual std::error_code
+  writeSections(const StringMap<FunctionSamples> &ProfileMap) override;
 };
 
 // CompactBinary is a compact format of binary profile which both reduces
@@ -169,7 +217,7 @@ class SampleProfileWriterCompactBinary : public SampleProfileWriterBinary {
   using SampleProfileWriterBinary::SampleProfileWriterBinary;
 
 public:
-  virtual std::error_code write(const FunctionSamples &S) override;
+  virtual std::error_code writeSample(const FunctionSamples &S) override;
   virtual std::error_code
   write(const StringMap<FunctionSamples> &ProfileMap) override;
 
@@ -181,7 +229,6 @@ class SampleProfileWriterCompactBinary : public SampleProfileWriterBinary {
   /// towards profile start.
   uint64_t TableOffset;
   virtual std::error_code writeNameTable() override;
-  virtual std::error_code writeMagicIdent() override;
   virtual std::error_code
   writeHeader(const StringMap<FunctionSamples> &ProfileMap) override;
   std::error_code writeFuncOffsetTable();