[Profile] Refactor profile correlation. (llvm#70856)

ZequanWu · web-flow · commit 3c97c8b6fc28 · 2023-11-01T14:16:43.000-04:00
Refactor some code from llvm#69493. llvm#70712 was reverted due to linking failures. So, `-debug-info-correlate` remains unchanged and no new flag added.
diff --git a/compiler-rt/lib/profile/InstrProfiling.c b/compiler-rt/lib/profile/InstrProfiling.c
@@ -89,3 +89,7 @@ COMPILER_RT_VISIBILITY void __llvm_profile_reset_counters(void) {
   }
   lprofSetProfileDumped(0);
 }
+
+inline int hasCorrelation() {
+  return (__llvm_profile_get_version() & VARIANT_MASK_DBG_CORRELATE) != 0ULL;
+}
diff --git a/compiler-rt/lib/profile/InstrProfiling.h b/compiler-rt/lib/profile/InstrProfiling.h
@@ -261,6 +261,9 @@ uint64_t __llvm_profile_get_magic(void);
 /*! \brief Get the version of the file format. */
 uint64_t __llvm_profile_get_version(void);
 
+/*! \brief If the binary is compiled with profile correlation. */
+int hasCorrelation();
+
 /*! \brief Get the number of entries in the profile data section. */
 uint64_t __llvm_profile_get_num_data(const __llvm_profile_data *Begin,
                                      const __llvm_profile_data *End);
@@ -282,6 +285,9 @@ uint64_t __llvm_profile_get_counters_size(const char *Begin, const char *End);
 uint64_t __llvm_profile_get_num_bitmap_bytes(const char *Begin,
                                              const char *End);
 
+/*! \brief Get the size of the profile name section in bytes. */
+uint64_t __llvm_profile_get_name_size(const char *Begin, const char *End);
+
 /* ! \brief Given the sizes of the data and counter information, return the
  * number of padding bytes before and after the counters, and after the names,
  * in the raw profile.
diff --git a/compiler-rt/lib/profile/InstrProfilingBuffer.c b/compiler-rt/lib/profile/InstrProfilingBuffer.c
@@ -56,6 +56,8 @@ uint64_t __llvm_profile_get_size_for_buffer(void) {
 COMPILER_RT_VISIBILITY
 uint64_t __llvm_profile_get_num_data(const __llvm_profile_data *Begin,
                                      const __llvm_profile_data *End) {
+  if (hasCorrelation())
+    return 0;
   intptr_t BeginI = (intptr_t)Begin, EndI = (intptr_t)End;
   return ((EndI + sizeof(__llvm_profile_data) - 1) - BeginI) /
          sizeof(__llvm_profile_data);
@@ -64,6 +66,8 @@ uint64_t __llvm_profile_get_num_data(const __llvm_profile_data *Begin,
 COMPILER_RT_VISIBILITY
 uint64_t __llvm_profile_get_data_size(const __llvm_profile_data *Begin,
                                       const __llvm_profile_data *End) {
+  if (hasCorrelation())
+    return 0;
   return __llvm_profile_get_num_data(Begin, End) * sizeof(__llvm_profile_data);
 }
 
@@ -92,6 +96,13 @@ uint64_t __llvm_profile_get_num_bitmap_bytes(const char *Begin,
   return (End - Begin);
 }
 
+COMPILER_RT_VISIBILITY
+uint64_t __llvm_profile_get_name_size(const char *Begin, const char *End) {
+  if (hasCorrelation())
+    return 0;
+  return End - Begin;
+}
+
 /// Calculate the number of padding bytes needed to add to \p Offset in order
 /// for (\p Offset + Padding) to be page-aligned.
 static uint64_t calculateBytesNeededToPageAlign(uint64_t Offset) {
diff --git a/compiler-rt/lib/profile/InstrProfilingMerge.c b/compiler-rt/lib/profile/InstrProfilingMerge.c
@@ -69,8 +69,9 @@ int __llvm_profile_check_compatibility(const char *ProfileData,
       Header->NumBitmapBytes !=
           __llvm_profile_get_num_bitmap_bytes(__llvm_profile_begin_bitmap(),
                                               __llvm_profile_end_bitmap()) ||
-      Header->NamesSize != (uint64_t)(__llvm_profile_end_names() -
-                                      __llvm_profile_begin_names()) ||
+      Header->NamesSize !=
+          __llvm_profile_get_name_size(__llvm_profile_begin_names(),
+                                       __llvm_profile_end_names()) ||
       Header->ValueKindLast != IPVK_Last)
     return 1;
 
@@ -138,9 +139,9 @@ int __llvm_profile_merge_from_buffer(const char *ProfileData,
   if (SrcNameStart < SrcCountersStart || SrcNameStart < SrcBitmapStart)
     return 1;
 
-  // Merge counters by iterating the entire counter section when debug info
-  // correlation is enabled.
-  if (__llvm_profile_get_version() & VARIANT_MASK_DBG_CORRELATE) {
+  // Merge counters by iterating the entire counter section when correlation is
+  // enabled.
+  if (hasCorrelation()) {
     for (SrcCounter = SrcCountersStart,
         DstCounter = __llvm_profile_begin_counters();
          SrcCounter < SrcCountersEnd;) {
diff --git a/compiler-rt/lib/profile/InstrProfilingWriter.c b/compiler-rt/lib/profile/InstrProfilingWriter.c
@@ -262,21 +262,19 @@ lprofWriteDataImpl(ProfDataWriter *Writer, const __llvm_profile_data *DataBegin,
                    const char *BitmapBegin, const char *BitmapEnd,
                    VPDataReaderType *VPDataReader, const char *NamesBegin,
                    const char *NamesEnd, int SkipNameDataWrite) {
-  int DebugInfoCorrelate =
-      (__llvm_profile_get_version() & VARIANT_MASK_DBG_CORRELATE) != 0ULL;
+  int ProfileCorrelation = hasCorrelation();
 
   /* Calculate size of sections. */
   const uint64_t DataSectionSize =
-      DebugInfoCorrelate ? 0 : __llvm_profile_get_data_size(DataBegin, DataEnd);
-  const uint64_t NumData =
-      DebugInfoCorrelate ? 0 : __llvm_profile_get_num_data(DataBegin, DataEnd);
+      __llvm_profile_get_data_size(DataBegin, DataEnd);
+  const uint64_t NumData = __llvm_profile_get_num_data(DataBegin, DataEnd);
   const uint64_t CountersSectionSize =
       __llvm_profile_get_counters_size(CountersBegin, CountersEnd);
   const uint64_t NumCounters =
       __llvm_profile_get_num_counters(CountersBegin, CountersEnd);
   const uint64_t NumBitmapBytes =
       __llvm_profile_get_num_bitmap_bytes(BitmapBegin, BitmapEnd);
-  const uint64_t NamesSize = DebugInfoCorrelate ? 0 : NamesEnd - NamesBegin;
+  const uint64_t NamesSize = __llvm_profile_get_name_size(NamesBegin, NamesEnd);
 
   /* Create the header. */
   __llvm_profile_header Header;
@@ -304,7 +302,7 @@ lprofWriteDataImpl(ProfDataWriter *Writer, const __llvm_profile_data *DataBegin,
 #endif
 
   /* The data and names sections are omitted in lightweight mode. */
-  if (DebugInfoCorrelate) {
+  if (ProfileCorrelation) {
     Header.CountersDelta = 0;
     Header.NamesDelta = 0;
   }
@@ -320,21 +318,22 @@ lprofWriteDataImpl(ProfDataWriter *Writer, const __llvm_profile_data *DataBegin,
 
   /* Write the profile data. */
   ProfDataIOVec IOVecData[] = {
-      {DebugInfoCorrelate ? NULL : DataBegin, sizeof(uint8_t), DataSectionSize,
+      {ProfileCorrelation ? NULL : DataBegin, sizeof(uint8_t), DataSectionSize,
        0},
       {NULL, sizeof(uint8_t), PaddingBytesBeforeCounters, 1},
       {CountersBegin, sizeof(uint8_t), CountersSectionSize, 0},
       {NULL, sizeof(uint8_t), PaddingBytesAfterCounters, 1},
       {BitmapBegin, sizeof(uint8_t), NumBitmapBytes, 0},
       {NULL, sizeof(uint8_t), PaddingBytesAfterBitmapBytes, 1},
-      {(SkipNameDataWrite || DebugInfoCorrelate) ? NULL : NamesBegin,
+      {(SkipNameDataWrite || ProfileCorrelation) ? NULL : NamesBegin,
        sizeof(uint8_t), NamesSize, 0},
       {NULL, sizeof(uint8_t), PaddingBytesAfterNames, 1}};
   if (Writer->Write(Writer, IOVecData, sizeof(IOVecData) / sizeof(*IOVecData)))
     return -1;
 
-  /* Value profiling is not yet supported in continuous mode. */
-  if (__llvm_profile_is_continuous_mode_enabled())
+  /* Value profiling is not yet supported in continuous mode and profile
+   * correlation mode. */
+  if (__llvm_profile_is_continuous_mode_enabled() || ProfileCorrelation)
     return 0;
 
   return writeValueProfData(Writer, VPDataReader, DataBegin, DataEnd);
diff --git a/compiler-rt/test/profile/Linux/instrprof-show-debug-info-correlation.c b/compiler-rt/test/profile/Linux/instrprof-show-debug-info-correlation.c
@@ -4,7 +4,7 @@
 
 // RUN: %clang_pgogen -o %t.no.dbg -mllvm --debug-info-correlate -mllvm --disable-vp=true %s
 // RUN: not llvm-profdata show --debug-info=%t.no.dbg 2>&1 | FileCheck %s --check-prefix NO-DBG
-// NO-DBG: unable to correlate profile: could not find any profile metadata in debug info
+// NO-DBG: unable to correlate profile: could not find any profile data metadata in correlated file
 
 // YAML: Probes:
 // YAML:   - Function Name:   a
diff --git a/llvm/include/llvm/ProfileData/InstrProfCorrelator.h b/llvm/include/llvm/ProfileData/InstrProfCorrelator.h
@@ -31,8 +31,11 @@ class ObjectFile;
 /// to their functions.
 class InstrProfCorrelator {
 public:
+  /// Indicate which kind correlator to use.
+  enum ProfCorrelatorKind { NONE, DEBUG_INFO };
+
   static llvm::Expected<std::unique_ptr<InstrProfCorrelator>>
-  get(StringRef DebugInfoFilename);
+  get(StringRef Filename, ProfCorrelatorKind FileKind);
 
   /// Construct a ProfileData vector used to correlate raw instrumentation data
   /// to their functions.
@@ -104,7 +107,7 @@ class InstrProfCorrelator {
 
 private:
   static llvm::Expected<std::unique_ptr<InstrProfCorrelator>>
-  get(std::unique_ptr<MemoryBuffer> Buffer);
+  get(std::unique_ptr<MemoryBuffer> Buffer, ProfCorrelatorKind FileKind);
 
   const InstrProfCorrelatorKind Kind;
 };
@@ -128,7 +131,7 @@ class InstrProfCorrelatorImpl : public InstrProfCorrelator {
 
   static llvm::Expected<std::unique_ptr<InstrProfCorrelatorImpl<IntPtrT>>>
   get(std::unique_ptr<InstrProfCorrelator::Context> Ctx,
-      const object::ObjectFile &Obj);
+      const object::ObjectFile &Obj, ProfCorrelatorKind FileKind);
 
 protected:
   std::vector<RawInstrProf::ProfileData<IntPtrT>> Data;
@@ -138,6 +141,8 @@ class InstrProfCorrelatorImpl : public InstrProfCorrelator {
       int MaxWarnings,
       InstrProfCorrelator::CorrelationData *Data = nullptr) = 0;
 
+  virtual Error correlateProfileNameImpl() = 0;
+
   Error dumpYaml(int MaxWarnings, raw_ostream &OS) override;
 
   void addProbe(StringRef FunctionName, uint64_t CFGHash, IntPtrT CounterOffset,
@@ -205,6 +210,8 @@ class DwarfInstrProfCorrelator : public InstrProfCorrelatorImpl<IntPtrT> {
   void correlateProfileDataImpl(
       int MaxWarnings,
       InstrProfCorrelator::CorrelationData *Data = nullptr) override;
+
+  Error correlateProfileNameImpl() override;
 };
 
 } // end namespace llvm
diff --git a/llvm/include/llvm/ProfileData/InstrProfReader.h b/llvm/include/llvm/ProfileData/InstrProfReader.h
@@ -386,6 +386,8 @@ class RawInstrProfReader : public InstrProfReader {
     return (Version & VARIANT_MASK_DBG_CORRELATE) != 0;
   }
 
+  bool useCorrelate() const { return useDebugInfoCorrelate(); }
+
   bool hasSingleByteCoverage() const override {
     return (Version & VARIANT_MASK_BYTE_COVERAGE) != 0;
   }
diff --git a/llvm/lib/ProfileData/InstrProfCorrelator.cpp b/llvm/lib/ProfileData/InstrProfCorrelator.cpp
@@ -24,15 +24,20 @@
 
 using namespace llvm;
 
-/// Get the __llvm_prf_cnts section.
-Expected<object::SectionRef> getCountersSection(const object::ObjectFile &Obj) {
+/// Get profile section.
+Expected<object::SectionRef> getInstrProfSection(const object::ObjectFile &Obj,
+                                                 InstrProfSectKind IPSK) {
+  Triple::ObjectFormatType ObjFormat = Obj.getTripleObjectFormat();
+  std::string ExpectedSectionName =
+      getInstrProfSectionName(IPSK, ObjFormat,
+                              /*AddSegmentInfo=*/false);
   for (auto &Section : Obj.sections())
     if (auto SectionName = Section.getName())
-      if (SectionName.get() == INSTR_PROF_CNTS_SECT_NAME)
+      if (SectionName.get() == ExpectedSectionName)
         return Section;
   return make_error<InstrProfError>(
       instrprof_error::unable_to_correlate_profile,
-      "could not find counter section (" INSTR_PROF_CNTS_SECT_NAME ")");
+      "could not find section (" + Twine(ExpectedSectionName) + ")");
 }
 
 const char *InstrProfCorrelator::FunctionNameAttributeName = "Function Name";
@@ -42,7 +47,7 @@ const char *InstrProfCorrelator::NumCountersAttributeName = "Num Counters";
 llvm::Expected<std::unique_ptr<InstrProfCorrelator::Context>>
 InstrProfCorrelator::Context::get(std::unique_ptr<MemoryBuffer> Buffer,
                                   const object::ObjectFile &Obj) {
-  auto CountersSection = getCountersSection(Obj);
+  auto CountersSection = getInstrProfSection(Obj, IPSK_cnts);
   if (auto Err = CountersSection.takeError())
     return std::move(Err);
   auto C = std::make_unique<Context>();
@@ -54,30 +59,32 @@ InstrProfCorrelator::Context::get(std::unique_ptr<MemoryBuffer> Buffer,
 }
 
 llvm::Expected<std::unique_ptr<InstrProfCorrelator>>
-InstrProfCorrelator::get(StringRef DebugInfoFilename) {
-  auto DsymObjectsOrErr =
-      object::MachOObjectFile::findDsymObjectMembers(DebugInfoFilename);
-  if (auto Err = DsymObjectsOrErr.takeError())
-    return std::move(Err);
-  if (!DsymObjectsOrErr->empty()) {
-    // TODO: Enable profile correlation when there are multiple objects in a
-    // dSYM bundle.
-    if (DsymObjectsOrErr->size() > 1)
-      return make_error<InstrProfError>(
-          instrprof_error::unable_to_correlate_profile,
-          "using multiple objects is not yet supported");
-    DebugInfoFilename = *DsymObjectsOrErr->begin();
+InstrProfCorrelator::get(StringRef Filename, ProfCorrelatorKind FileKind) {
+  if (FileKind == DEBUG_INFO) {
+    auto DsymObjectsOrErr =
+        object::MachOObjectFile::findDsymObjectMembers(Filename);
+    if (auto Err = DsymObjectsOrErr.takeError())
+      return std::move(Err);
+    if (!DsymObjectsOrErr->empty()) {
+      // TODO: Enable profile correlation when there are multiple objects in a
+      // dSYM bundle.
+      if (DsymObjectsOrErr->size() > 1)
+        return make_error<InstrProfError>(
+            instrprof_error::unable_to_correlate_profile,
+            "using multiple objects is not yet supported");
+      Filename = *DsymObjectsOrErr->begin();
+    }
   }
-  auto BufferOrErr =
-      errorOrToExpected(MemoryBuffer::getFile(DebugInfoFilename));
+  auto BufferOrErr = errorOrToExpected(MemoryBuffer::getFile(Filename));
   if (auto Err = BufferOrErr.takeError())
     return std::move(Err);
 
-  return get(std::move(*BufferOrErr));
+  return get(std::move(*BufferOrErr), FileKind);
 }
 
 llvm::Expected<std::unique_ptr<InstrProfCorrelator>>
-InstrProfCorrelator::get(std::unique_ptr<MemoryBuffer> Buffer) {
+InstrProfCorrelator::get(std::unique_ptr<MemoryBuffer> Buffer,
+                         ProfCorrelatorKind FileKind) {
   auto BinOrErr = object::createBinary(*Buffer);
   if (auto Err = BinOrErr.takeError())
     return std::move(Err);
@@ -88,9 +95,11 @@ InstrProfCorrelator::get(std::unique_ptr<MemoryBuffer> Buffer) {
       return std::move(Err);
     auto T = Obj->makeTriple();
     if (T.isArch64Bit())
-      return InstrProfCorrelatorImpl<uint64_t>::get(std::move(*CtxOrErr), *Obj);
+      return InstrProfCorrelatorImpl<uint64_t>::get(std::move(*CtxOrErr), *Obj,
+                                                    FileKind);
     if (T.isArch32Bit())
-      return InstrProfCorrelatorImpl<uint32_t>::get(std::move(*CtxOrErr), *Obj);
+      return InstrProfCorrelatorImpl<uint32_t>::get(std::move(*CtxOrErr), *Obj,
+                                                    FileKind);
   }
   return make_error<InstrProfError>(
       instrprof_error::unable_to_correlate_profile, "not an object file");
@@ -132,29 +141,33 @@ template <class IntPtrT>
 llvm::Expected<std::unique_ptr<InstrProfCorrelatorImpl<IntPtrT>>>
 InstrProfCorrelatorImpl<IntPtrT>::get(
     std::unique_ptr<InstrProfCorrelator::Context> Ctx,
-    const object::ObjectFile &Obj) {
-  if (Obj.isELF() || Obj.isMachO()) {
-    auto DICtx = DWARFContext::create(Obj);
-    return std::make_unique<DwarfInstrProfCorrelator<IntPtrT>>(std::move(DICtx),
-                                                               std::move(Ctx));
+    const object::ObjectFile &Obj, ProfCorrelatorKind FileKind) {
+  if (FileKind == DEBUG_INFO) {
+    if (Obj.isELF() || Obj.isMachO()) {
+      auto DICtx = DWARFContext::create(Obj);
+      return std::make_unique<DwarfInstrProfCorrelator<IntPtrT>>(
+          std::move(DICtx), std::move(Ctx));
+    }
+    return make_error<InstrProfError>(
+        instrprof_error::unable_to_correlate_profile,
+        "unsupported debug info format (only DWARF is supported)");
   }
   return make_error<InstrProfError>(
       instrprof_error::unable_to_correlate_profile,
-      "unsupported debug info format (only DWARF is supported)");
+      "unsupported correlation file type (only DWARF is supported)");
 }
 
 template <class IntPtrT>
 Error InstrProfCorrelatorImpl<IntPtrT>::correlateProfileData(int MaxWarnings) {
   assert(Data.empty() && Names.empty() && NamesVec.empty());
   correlateProfileDataImpl(MaxWarnings);
-  if (Data.empty() || NamesVec.empty())
+  if (this->Data.empty())
     return make_error<InstrProfError>(
         instrprof_error::unable_to_correlate_profile,
-        "could not find any profile metadata in debug info");
-  auto Result =
-      collectGlobalObjectNameStrings(NamesVec, /*doCompression=*/false, Names);
-  CounterOffsets.clear();
-  NamesVec.clear();
+        "could not find any profile data metadata in correlated file");
+  Error Result = correlateProfileNameImpl();
+  this->CounterOffsets.clear();
+  this->NamesVec.clear();
   return Result;
 }
 
@@ -189,7 +202,7 @@ Error InstrProfCorrelatorImpl<IntPtrT>::dumpYaml(int MaxWarnings,
   if (Data.Probes.empty())
     return make_error<InstrProfError>(
         instrprof_error::unable_to_correlate_profile,
-        "could not find any profile metadata in debug info");
+        "could not find any profile data metadata in debug info");
   yaml::Output YamlOS(OS);
   YamlOS << Data;
   return Error::success();
@@ -365,3 +378,16 @@ void DwarfInstrProfCorrelator<IntPtrT>::correlateProfileDataImpl(
     WithColor::warning() << format("Suppressed %d additional warnings\n",
                                    NumSuppressedWarnings);
 }
+
+template <class IntPtrT>
+Error DwarfInstrProfCorrelator<IntPtrT>::correlateProfileNameImpl() {
+  if (this->NamesVec.empty()) {
+    return make_error<InstrProfError>(
+        instrprof_error::unable_to_correlate_profile,
+        "could not find any profile name metadata in debug info");
+  }
+  auto Result =
+      collectGlobalObjectNameStrings(this->NamesVec,
+                                     /*doCompression=*/false, this->Names);
+  return Result;
+}
diff --git a/llvm/lib/ProfileData/InstrProfReader.cpp b/llvm/lib/ProfileData/InstrProfReader.cpp
@@ -566,9 +566,9 @@ Error RawInstrProfReader<IntPtrT>::readHeader(
                   "\nPLEASE update this tool to version in the raw profile, or "
                   "regenerate raw profile with expected version.")
                      .str());
-  if (useDebugInfoCorrelate() && !Correlator)
+  if (useCorrelate() && !Correlator)
     return error(instrprof_error::missing_debug_info_for_correlation);
-  if (!useDebugInfoCorrelate() && Correlator)
+  if (!useCorrelate() && Correlator)
     return error(instrprof_error::unexpected_debug_info_for_correlation);
 
   BinaryIdsSize = swap(Header.BinaryIdsSize);
diff --git a/llvm/tools/llvm-profdata/llvm-profdata.cpp b/llvm/tools/llvm-profdata/llvm-profdata.cpp

Original file line number	Diff line number	Diff line change
`@@ -89,3 +89,7 @@ COMPILER_RT_VISIBILITY void __llvm_profile_reset_counters(void) {`
`89`	`89`	`}`
`90`	`90`	`lprofSetProfileDumped(0);`
`91`	`91`	`}`
	`92`	`+`
	`93`	`+inline int hasCorrelation() {`
	`94`	`+ return (__llvm_profile_get_version() & VARIANT_MASK_DBG_CORRELATE) != 0ULL;`
	`95`	`+}`
Original file line number	Diff line number	Diff line change
`@@ -386,6 +386,8 @@ class RawInstrProfReader : public InstrProfReader {`
`386`	`386`	`return (Version & VARIANT_MASK_DBG_CORRELATE) != 0;`
`387`	`387`	`}`
`388`	`388`
	`389`	`+ bool useCorrelate() const { return useDebugInfoCorrelate(); }`
	`390`	`+`
`389`	`391`	`bool hasSingleByteCoverage() const override {`
`390`	`392`	`return (Version & VARIANT_MASK_BYTE_COVERAGE) != 0;`
`391`	`393`	`}`