//===- InstrProf.h - Instrumented profiling format support ------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// Instrumentation-based profiling data is generated by instrumented
// binaries through library functions in compiler-rt, and read by the clang
// frontend to feed PGO.
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_PROFILEDATA_INSTRPROF_H
#define LLVM_PROFILEDATA_INSTRPROF_H

#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/BitmaskEnum.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/StringSet.h"
#include "llvm/IR/GlobalValue.h"
#include "llvm/IR/ProfileSummary.h"
#include "llvm/ProfileData/InstrProfData.inc"
#include "llvm/Support/BalancedPartitioning.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Error.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/MD5.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/TargetParser/Host.h"
#include "llvm/TargetParser/Triple.h"
#include <algorithm>
#include <cassert>
#include <cstddef>
#include <cstdint>
#include <cstring>
#include <list>
#include <memory>
#include <string>
#include <system_error>
#include <utility>
#include <vector>

namespace llvm {

class Function;
class GlobalVariable;
struct InstrProfRecord;
class InstrProfSymtab;
class Instruction;
class MDNode;
class Module;

enum InstrProfSectKind {
#define INSTR_PROF_SECT_ENTRY(Kind, SectNameCommon, SectNameCoff, Prefix) Kind,
#include "llvm/ProfileData/InstrProfData.inc"
};

/// Return the max count value. We reserver a few large values for special use.
inline uint64_t getInstrMaxCountValue() {
  return std::numeric_limits<uint64_t>::max() - 2;
}

/// Return the name of the profile section corresponding to \p IPSK.
///
/// The name of the section depends on the object format type \p OF. If
/// \p AddSegmentInfo is true, a segment prefix and additional linker hints may
/// be added to the section name (this is the default).
std::string getInstrProfSectionName(InstrProfSectKind IPSK,
                                    Triple::ObjectFormatType OF,
                                    bool AddSegmentInfo = true);

/// Return the name profile runtime entry point to do value profiling
/// for a given site.
inline StringRef getInstrProfValueProfFuncName() {
  return INSTR_PROF_VALUE_PROF_FUNC_STR;
}

/// Return the name profile runtime entry point to do memop size value
/// profiling.
inline StringRef getInstrProfValueProfMemOpFuncName() {
  return INSTR_PROF_VALUE_PROF_MEMOP_FUNC_STR;
}

/// Return the name prefix of variables containing instrumented function names.
inline StringRef getInstrProfNameVarPrefix() { return "__profn_"; }

/// Return the name prefix of variables containing per-function control data.
inline StringRef getInstrProfDataVarPrefix() { return "__profd_"; }

/// Return the name prefix of profile counter variables.
inline StringRef getInstrProfCountersVarPrefix() { return "__profc_"; }

/// Return the name prefix of profile bitmap variables.
inline StringRef getInstrProfBitmapVarPrefix() { return "__profbm_"; }

/// Return the name prefix of value profile variables.
inline StringRef getInstrProfValuesVarPrefix() { return "__profvp_"; }

/// Return the name of value profile node array variables:
inline StringRef getInstrProfVNodesVarName() { return "__llvm_prf_vnodes"; }

/// Return the name of the variable holding the strings (possibly compressed)
/// of all function's PGO names.
inline StringRef getInstrProfNamesVarName() {
  return "__llvm_prf_nm";
}

/// Return the name of a covarage mapping variable (internal linkage)
/// for each instrumented source module. Such variables are allocated
/// in the __llvm_covmap section.
inline StringRef getCoverageMappingVarName() {
  return "__llvm_coverage_mapping";
}

/// Return the name of the internal variable recording the array
/// of PGO name vars referenced by the coverage mapping. The owning
/// functions of those names are not emitted by FE (e.g, unused inline
/// functions.)
inline StringRef getCoverageUnusedNamesVarName() {
  return "__llvm_coverage_names";
}

/// Return the name of function that registers all the per-function control
/// data at program startup time by calling __llvm_register_function. This
/// function has internal linkage and is called by  __llvm_profile_init
/// runtime method. This function is not generated for these platforms:
/// Darwin, Linux, and FreeBSD.
inline StringRef getInstrProfRegFuncsName() {
  return "__llvm_profile_register_functions";
}

/// Return the name of the runtime interface that registers per-function control
/// data for one instrumented function.
inline StringRef getInstrProfRegFuncName() {
  return "__llvm_profile_register_function";
}

/// Return the name of the runtime interface that registers the PGO name strings.
inline StringRef getInstrProfNamesRegFuncName() {
  return "__llvm_profile_register_names_function";
}

/// Return the name of the runtime initialization method that is generated by
/// the compiler. The function calls __llvm_profile_register_functions and
/// __llvm_profile_override_default_filename functions if needed. This function
/// has internal linkage and invoked at startup time via init_array.
inline StringRef getInstrProfInitFuncName() { return "__llvm_profile_init"; }

/// Return the name of the hook variable defined in profile runtime library.
/// A reference to the variable causes the linker to link in the runtime
/// initialization module (which defines the hook variable).
inline StringRef getInstrProfRuntimeHookVarName() {
  return INSTR_PROF_QUOTE(INSTR_PROF_PROFILE_RUNTIME_VAR);
}

/// Return the name of the compiler generated function that references the
/// runtime hook variable. The function is a weak global.
inline StringRef getInstrProfRuntimeHookVarUseFuncName() {
  return "__llvm_profile_runtime_user";
}

inline StringRef getInstrProfCounterBiasVarName() {
  return INSTR_PROF_QUOTE(INSTR_PROF_PROFILE_COUNTER_BIAS_VAR);
}

/// Return the marker used to separate PGO names during serialization.
inline StringRef getInstrProfNameSeparator() { return "\01"; }

/// Please use getIRPGOFuncName for LLVM IR instrumentation. This function is
/// for front-end (Clang, etc) instrumentation.
/// Return the modified name for function \c F suitable to be
/// used the key for profile lookup. Variable \c InLTO indicates if this
/// is called in LTO optimization passes.
std::string getPGOFuncName(const Function &F, bool InLTO = false,
                           uint64_t Version = INSTR_PROF_INDEX_VERSION);

/// Return the modified name for a function suitable to be
/// used the key for profile lookup. The function's original
/// name is \c RawFuncName and has linkage of type \c Linkage.
/// The function is defined in module \c FileName.
std::string getPGOFuncName(StringRef RawFuncName,
                           GlobalValue::LinkageTypes Linkage,
                           StringRef FileName,
                           uint64_t Version = INSTR_PROF_INDEX_VERSION);

/// \return the modified name for function \c F suitable to be
/// used as the key for IRPGO profile lookup. \c InLTO indicates if this is
/// called from LTO optimization passes.
std::string getIRPGOFuncName(const Function &F, bool InLTO = false);

/// \return the filename and the function name parsed from the output of
/// \c getIRPGOFuncName()
std::pair<StringRef, StringRef> getParsedIRPGOFuncName(StringRef IRPGOFuncName);

/// Return the name of the global variable used to store a function
/// name in PGO instrumentation. \c FuncName is the IRPGO function name
/// (returned by \c getIRPGOFuncName) for LLVM IR instrumentation and PGO
/// function name (returned by \c getPGOFuncName) for front-end instrumentation.
std::string getPGOFuncNameVarName(StringRef FuncName,
                                  GlobalValue::LinkageTypes Linkage);

/// Create and return the global variable for function name used in PGO
/// instrumentation. \c FuncName is the IRPGO function name (returned by
/// \c getIRPGOFuncName) for LLVM IR instrumentation and PGO function name
/// (returned by \c getPGOFuncName) for front-end instrumentation.
GlobalVariable *createPGOFuncNameVar(Function &F, StringRef PGOFuncName);

/// Create and return the global variable for function name used in PGO
/// instrumentation. \c FuncName is the IRPGO function name (returned by
/// \c getIRPGOFuncName) for LLVM IR instrumentation and PGO function name
/// (returned by \c getPGOFuncName) for front-end instrumentation.
GlobalVariable *createPGOFuncNameVar(Module &M,
                                     GlobalValue::LinkageTypes Linkage,
                                     StringRef PGOFuncName);

/// Return the initializer in string of the PGO name var \c NameVar.
StringRef getPGOFuncNameVarInitializer(GlobalVariable *NameVar);

/// Given a PGO function name, remove the filename prefix and return
/// the original (static) function name.
StringRef getFuncNameWithoutPrefix(StringRef PGOFuncName,
                                   StringRef FileName = "<unknown>");

/// Given a vector of strings (names of global objects like functions or,
/// virtual tables) \c NameStrs, the method generates a combined string \c
/// Result that is ready to be serialized.  The \c Result string is comprised of
/// three fields: The first field is the length of the uncompressed strings, and
/// the the second field is the length of the zlib-compressed string. Both
/// fields are encoded in ULEB128.  If \c doCompress is false, the
///  third field is the uncompressed strings; otherwise it is the
/// compressed string. When the string compression is off, the
/// second field will have value zero.
Error collectGlobalObjectNameStrings(ArrayRef<std::string> NameStrs,
                                     bool doCompression, std::string &Result);

/// Produce \c Result string with the same format described above. The input
/// is vector of PGO function name variables that are referenced.
/// The global variable element in 'NameVars' is a string containing the pgo
/// name of a function. See `createPGOFuncNameVar` that creates these global
/// variables.
Error collectPGOFuncNameStrings(ArrayRef<GlobalVariable *> NameVars,
                                std::string &Result, bool doCompression = true);

/// Check if INSTR_PROF_RAW_VERSION_VAR is defined. This global is only being
/// set in IR PGO compilation.
bool isIRPGOFlagSet(const Module *M);

/// Check if we can safely rename this Comdat function. Instances of the same
/// comdat function may have different control flows thus can not share the
/// same counter variable.
bool canRenameComdatFunc(const Function &F, bool CheckAddressTaken = false);

enum InstrProfValueKind : uint32_t {
#define VALUE_PROF_KIND(Enumerator, Value, Descr) Enumerator = Value,
#include "llvm/ProfileData/InstrProfData.inc"
};

/// Get the value profile data for value site \p SiteIdx from \p InstrProfR
/// and annotate the instruction \p Inst with the value profile meta data.
/// Annotate up to \p MaxMDCount (default 3) number of records per value site.
void annotateValueSite(Module &M, Instruction &Inst,
                       const InstrProfRecord &InstrProfR,
                       InstrProfValueKind ValueKind, uint32_t SiteIndx,
                       uint32_t MaxMDCount = 3);

/// Same as the above interface but using an ArrayRef, as well as \p Sum.
void annotateValueSite(Module &M, Instruction &Inst,
                       ArrayRef<InstrProfValueData> VDs, uint64_t Sum,
                       InstrProfValueKind ValueKind, uint32_t MaxMDCount);

/// Extract the value profile data from \p Inst which is annotated with
/// value profile meta data. Return false if there is no value data annotated,
/// otherwise  return true.
bool getValueProfDataFromInst(const Instruction &Inst,
                              InstrProfValueKind ValueKind,
                              uint32_t MaxNumValueData,
                              InstrProfValueData ValueData[],
                              uint32_t &ActualNumValueData, uint64_t &TotalC,
                              bool GetNoICPValue = false);

inline StringRef getPGOFuncNameMetadataName() { return "PGOFuncName"; }

/// Return the PGOFuncName meta data associated with a function.
MDNode *getPGOFuncNameMetadata(const Function &F);

/// Create the PGOFuncName meta data if PGOFuncName is different from
/// function's raw name. This should only apply to internal linkage functions
/// declared by users only.
void createPGOFuncNameMetadata(Function &F, StringRef PGOFuncName);

/// Check if we can use Comdat for profile variables. This will eliminate
/// the duplicated profile variables for Comdat functions.
bool needsComdatForCounter(const Function &F, const Module &M);

/// An enum describing the attributes of an instrumented profile.
enum class InstrProfKind {
  Unknown = 0x0,
  // A frontend clang profile, incompatible with other attrs.
  FrontendInstrumentation = 0x1,
  // An IR-level profile (default when -fprofile-generate is used).
  IRInstrumentation = 0x2,
  // A profile with entry basic block instrumentation.
  FunctionEntryInstrumentation = 0x4,
  // A context sensitive IR-level profile.
  ContextSensitive = 0x8,
  // Use single byte probes for coverage.
  SingleByteCoverage = 0x10,
  // Only instrument the function entry basic block.
  FunctionEntryOnly = 0x20,
  // A memory profile collected using -fprofile=memory.
  MemProf = 0x40,
  // A temporal profile.
  TemporalProfile = 0x80,
  LLVM_MARK_AS_BITMASK_ENUM(/*LargestValue=*/TemporalProfile)
};

const std::error_category &instrprof_category();

enum class instrprof_error {
  success = 0,
  eof,
  unrecognized_format,
  bad_magic,
  bad_header,
  unsupported_version,
  unsupported_hash_type,
  too_large,
  truncated,
  malformed,
  missing_correlation_info,
  unexpected_correlation_info,
  unable_to_correlate_profile,
  unknown_function,
  invalid_prof,
  hash_mismatch,
  count_mismatch,
  bitmap_mismatch,
  counter_overflow,
  value_site_count_mismatch,
  compress_failed,
  uncompress_failed,
  empty_raw_profile,
  zlib_unavailable,
  raw_profile_version_mismatch,
  counter_value_too_large,
};

/// An ordered list of functions identified by their NameRef found in
/// INSTR_PROF_DATA
struct TemporalProfTraceTy {
  std::vector<uint64_t> FunctionNameRefs;
  uint64_t Weight;
  TemporalProfTraceTy(std::initializer_list<uint64_t> Trace = {},
                      uint64_t Weight = 1)
      : FunctionNameRefs(Trace), Weight(Weight) {}

  /// Use a set of temporal profile traces to create a list of balanced
  /// partitioning function nodes used by BalancedPartitioning to generate a
  /// function order that reduces page faults during startup
  static std::vector<BPFunctionNode>
  createBPFunctionNodes(ArrayRef<TemporalProfTraceTy> Traces);
};

inline std::error_code make_error_code(instrprof_error E) {
  return std::error_code(static_cast<int>(E), instrprof_category());
}

class InstrProfError : public ErrorInfo<InstrProfError> {
public:
  InstrProfError(instrprof_error Err, const Twine &ErrStr = Twine())
      : Err(Err), Msg(ErrStr.str()) {
    assert(Err != instrprof_error::success && "Not an error");
  }

  std::string message() const override;

  void log(raw_ostream &OS) const override { OS << message(); }

  std::error_code convertToErrorCode() const override {
    return make_error_code(Err);
  }

  instrprof_error get() const { return Err; }
  const std::string &getMessage() const { return Msg; }

  /// Consume an Error and return the raw enum value contained within it, and
  /// the optional error message. The Error must either be a success value, or
  /// contain a single InstrProfError.
  static std::pair<instrprof_error, std::string> take(Error E) {
    auto Err = instrprof_error::success;
    std::string Msg = "";
    handleAllErrors(std::move(E), [&Err, &Msg](const InstrProfError &IPE) {
      assert(Err == instrprof_error::success && "Multiple errors encountered");
      Err = IPE.get();
      Msg = IPE.getMessage();
    });
    return {Err, Msg};
  }

  static char ID;

private:
  instrprof_error Err;
  std::string Msg;
};

namespace object {

class SectionRef;

} // end namespace object

namespace IndexedInstrProf {

uint64_t ComputeHash(StringRef K);

} // end namespace IndexedInstrProf

/// A symbol table used for function [IR]PGO name look-up with keys
/// (such as pointers, md5hash values) to the function. A function's
/// [IR]PGO name or name's md5hash are used in retrieving the profile
/// data of the function. See \c getIRPGOFuncName() and \c getPGOFuncName
/// methods for details how [IR]PGO name is formed.
class InstrProfSymtab {
public:
  using AddrHashMap = std::vector<std::pair<uint64_t, uint64_t>>;

private:
  StringRef Data;
  uint64_t Address = 0;
  // Unique name strings.
  StringSet<> NameTab;
  // A map from MD5 keys to function name strings.
  std::vector<std::pair<uint64_t, StringRef>> MD5NameMap;
  // A map from MD5 keys to function define. We only populate this map
  // when build the Symtab from a Module.
  std::vector<std::pair<uint64_t, Function *>> MD5FuncMap;
  // A map from function runtime address to function name MD5 hash.
  // This map is only populated and used by raw instr profile reader.
  AddrHashMap AddrToMD5Map;
  bool Sorted = false;

  static StringRef getExternalSymbol() {
    return "** External Symbol **";
  }

  Error addFuncWithName(Function &F, StringRef PGOFuncName);

  // If the symtab is created by a series of calls to \c addFuncName, \c
  // finalizeSymtab needs to be called before looking up function names.
  // This is required because the underlying map is a vector (for space
  // efficiency) which needs to be sorted.
  inline void finalizeSymtab();

public:
  InstrProfSymtab() = default;

  /// Create InstrProfSymtab from an object file section which
  /// contains function PGO names. When section may contain raw
  /// string data or string data in compressed form. This method
  /// only initialize the symtab with reference to the data and
  /// the section base address. The decompression will be delayed
  /// until before it is used. See also \c create(StringRef) method.
  Error create(object::SectionRef &Section);

  /// \c NameStrings is a string composed of one of more sub-strings
  ///  encoded in the format described in \c collectPGOFuncNameStrings.
  /// This method is a wrapper to \c readPGOFuncNameStrings method.
  Error create(StringRef NameStrings);

  /// This interface is used by reader of CoverageMapping test
  /// format.
  inline Error create(StringRef D, uint64_t BaseAddr);

  /// A wrapper interface to populate the PGO symtab with functions
  /// decls from module \c M. This interface is used by transformation
  /// passes such as indirect function call promotion. Variable \c InLTO
  /// indicates if this is called from LTO optimization passes.
  Error create(Module &M, bool InLTO = false);

  /// Create InstrProfSymtab from a set of names iteratable from
  /// \p IterRange. This interface is used by IndexedProfReader.
  template <typename NameIterRange> Error create(const NameIterRange &IterRange);

  /// Update the symtab by adding \p FuncName to the table. This interface
  /// is used by the raw and text profile readers.
  Error addFuncName(StringRef FuncName) {
    if (FuncName.empty())
      return make_error<InstrProfError>(instrprof_error::malformed,
                                        "function name is empty");
    auto Ins = NameTab.insert(FuncName);
    if (Ins.second) {
      MD5NameMap.push_back(std::make_pair(
          IndexedInstrProf::ComputeHash(FuncName), Ins.first->getKey()));
      Sorted = false;
    }
    return Error::success();
  }

  /// Map a function address to its name's MD5 hash. This interface
  /// is only used by the raw profiler reader.
  void mapAddress(uint64_t Addr, uint64_t MD5Val) {
    AddrToMD5Map.push_back(std::make_pair(Addr, MD5Val));
  }

  /// Return a function's hash, or 0, if the function isn't in this SymTab.
  uint64_t getFunctionHashFromAddress(uint64_t Address);

  /// Return function's PGO name from the function name's symbol
  /// address in the object file. If an error occurs, return
  /// an empty string.
  StringRef getFuncName(uint64_t FuncNameAddress, size_t NameSize);

  /// Return name of functions or global variables from the name's md5 hash
  /// value. If not found, return an empty string.
  inline StringRef getFuncOrVarName(uint64_t ValMD5Hash);

  /// Just like getFuncOrVarName, except that it will return literal string
  /// 'External Symbol' if the function or global variable is external to
  /// this symbol table.
  inline StringRef getFuncOrVarNameIfDefined(uint64_t ValMD5Hash);

  /// True if Symbol is the value used to represent external symbols.
  static bool isExternalSymbol(const StringRef &Symbol) {
    return Symbol == InstrProfSymtab::getExternalSymbol();
  }

  /// Return function from the name's md5 hash. Return nullptr if not found.
  inline Function *getFunction(uint64_t FuncMD5Hash);

  /// Return the name section data.
  inline StringRef getNameData() const { return Data; }

  /// Dump the symbols in this table.
  void dumpNames(raw_ostream &OS) const;
};

Error InstrProfSymtab::create(StringRef D, uint64_t BaseAddr) {
  Data = D;
  Address = BaseAddr;
  return Error::success();
}

template <typename NameIterRange>
Error InstrProfSymtab::create(const NameIterRange &IterRange) {
  for (auto Name : IterRange)
    if (Error E = addFuncName(Name))
      return E;

  finalizeSymtab();
  return Error::success();
}

void InstrProfSymtab::finalizeSymtab() {
  if (Sorted)
    return;
  llvm::sort(MD5NameMap, less_first());
  llvm::sort(MD5FuncMap, less_first());
  llvm::sort(AddrToMD5Map, less_first());
  AddrToMD5Map.erase(std::unique(AddrToMD5Map.begin(), AddrToMD5Map.end()),
                     AddrToMD5Map.end());
  Sorted = true;
}

StringRef InstrProfSymtab::getFuncOrVarNameIfDefined(uint64_t MD5Hash) {
  StringRef ret = getFuncOrVarName(MD5Hash);
  if (ret.empty())
    return InstrProfSymtab::getExternalSymbol();
  return ret;
}

StringRef InstrProfSymtab::getFuncOrVarName(uint64_t MD5Hash) {
  finalizeSymtab();
  auto Result = llvm::lower_bound(MD5NameMap, MD5Hash,
                                  [](const std::pair<uint64_t, StringRef> &LHS,
                                     uint64_t RHS) { return LHS.first < RHS; });
  if (Result != MD5NameMap.end() && Result->first == MD5Hash)
    return Result->second;
  return StringRef();
}

Function* InstrProfSymtab::getFunction(uint64_t FuncMD5Hash) {
  finalizeSymtab();
  auto Result = llvm::lower_bound(MD5FuncMap, FuncMD5Hash,
                                  [](const std::pair<uint64_t, Function *> &LHS,
                                     uint64_t RHS) { return LHS.first < RHS; });
  if (Result != MD5FuncMap.end() && Result->first == FuncMD5Hash)
    return Result->second;
  return nullptr;
}

// To store the sums of profile count values, or the percentage of
// the sums of the total count values.
struct CountSumOrPercent {
  uint64_t NumEntries;
  double CountSum;
  double ValueCounts[IPVK_Last - IPVK_First + 1];
  CountSumOrPercent() : NumEntries(0), CountSum(0.0f), ValueCounts() {}
  void reset() {
    NumEntries = 0;
    CountSum = 0.0f;
    for (double &VC : ValueCounts)
      VC = 0.0f;
  }
};

// Function level or program level overlap information.
struct OverlapStats {
  enum OverlapStatsLevel { ProgramLevel, FunctionLevel };
  // Sum of the total count values for the base profile.
  CountSumOrPercent Base;
  // Sum of the total count values for the test profile.
  CountSumOrPercent Test;
  // Overlap lap score. Should be in range of [0.0f to 1.0f].
  CountSumOrPercent Overlap;
  CountSumOrPercent Mismatch;
  CountSumOrPercent Unique;
  OverlapStatsLevel Level;
  const std::string *BaseFilename;
  const std::string *TestFilename;
  StringRef FuncName;
  uint64_t FuncHash;
  bool Valid;

  OverlapStats(OverlapStatsLevel L = ProgramLevel)
      : Level(L), BaseFilename(nullptr), TestFilename(nullptr), FuncHash(0),
        Valid(false) {}

  void dump(raw_fd_ostream &OS) const;

  void setFuncInfo(StringRef Name, uint64_t Hash) {
    FuncName = Name;
    FuncHash = Hash;
  }

  Error accumulateCounts(const std::string &BaseFilename,
                         const std::string &TestFilename, bool IsCS);
  void addOneMismatch(const CountSumOrPercent &MismatchFunc);
  void addOneUnique(const CountSumOrPercent &UniqueFunc);

  static inline double score(uint64_t Val1, uint64_t Val2, double Sum1,
                             double Sum2) {
    if (Sum1 < 1.0f || Sum2 < 1.0f)
      return 0.0f;
    return std::min(Val1 / Sum1, Val2 / Sum2);
  }
};

// This is used to filter the functions whose overlap information
// to be output.
struct OverlapFuncFilters {
  uint64_t ValueCutoff;
  const std::string NameFilter;
};

struct InstrProfValueSiteRecord {
  /// Value profiling data pairs at a given value site.
  std::list<InstrProfValueData> ValueData;

  InstrProfValueSiteRecord() { ValueData.clear(); }
  template <class InputIterator>
  InstrProfValueSiteRecord(InputIterator F, InputIterator L)
      : ValueData(F, L) {}

  /// Sort ValueData ascending by Value
  void sortByTargetValues() {
    ValueData.sort(
        [](const InstrProfValueData &left, const InstrProfValueData &right) {
          return left.Value < right.Value;
        });
  }
  /// Sort ValueData Descending by Count
  inline void sortByCount();

  /// Merge data from another InstrProfValueSiteRecord
  /// Optionally scale merged counts by \p Weight.
  void merge(InstrProfValueSiteRecord &Input, uint64_t Weight,
             function_ref<void(instrprof_error)> Warn);
  /// Scale up value profile data counts by N (Numerator) / D (Denominator).
  void scale(uint64_t N, uint64_t D, function_ref<void(instrprof_error)> Warn);

  /// Compute the overlap b/w this record and Input record.
  void overlap(InstrProfValueSiteRecord &Input, uint32_t ValueKind,
               OverlapStats &Overlap, OverlapStats &FuncLevelOverlap);
};

/// Profiling information for a single function.
struct InstrProfRecord {
  std::vector<uint64_t> Counts;
  std::vector<uint8_t> BitmapBytes;

  InstrProfRecord() = default;
  InstrProfRecord(std::vector<uint64_t> Counts) : Counts(std::move(Counts)) {}
  InstrProfRecord(std::vector<uint64_t> Counts,
                  std::vector<uint8_t> BitmapBytes)
      : Counts(std::move(Counts)), BitmapBytes(std::move(BitmapBytes)) {}
  InstrProfRecord(InstrProfRecord &&) = default;
  InstrProfRecord(const InstrProfRecord &RHS)
      : Counts(RHS.Counts), BitmapBytes(RHS.BitmapBytes),
        ValueData(RHS.ValueData
                      ? std::make_unique<ValueProfData>(*RHS.ValueData)
                      : nullptr) {}
  InstrProfRecord &operator=(InstrProfRecord &&) = default;
  InstrProfRecord &operator=(const InstrProfRecord &RHS) {
    Counts = RHS.Counts;
    BitmapBytes = RHS.BitmapBytes;
    if (!RHS.ValueData) {
      ValueData = nullptr;
      return *this;
    }
    if (!ValueData)
      ValueData = std::make_unique<ValueProfData>(*RHS.ValueData);
    else
      *ValueData = *RHS.ValueData;
    return *this;
  }

  /// Return the number of value profile kinds with non-zero number
  /// of profile sites.
  inline uint32_t getNumValueKinds() const;
  /// Return the number of instrumented sites for ValueKind.
  inline uint32_t getNumValueSites(uint32_t ValueKind) const;

  /// Return the total number of ValueData for ValueKind.
  inline uint32_t getNumValueData(uint32_t ValueKind) const;

  /// Return the number of value data collected for ValueKind at profiling
  /// site: Site.
  inline uint32_t getNumValueDataForSite(uint32_t ValueKind,
                                         uint32_t Site) const;

  /// Return the array of profiled values at \p Site. If \p TotalC
  /// is not null, the total count of all target values at this site
  /// will be stored in \c *TotalC.
  inline std::unique_ptr<InstrProfValueData[]>
  getValueForSite(uint32_t ValueKind, uint32_t Site,
                  uint64_t *TotalC = nullptr) const;

  /// Get the target value/counts of kind \p ValueKind collected at site
  /// \p Site and store the result in array \p Dest. Return the total
  /// counts of all target values at this site.
  inline uint64_t getValueForSite(InstrProfValueData Dest[], uint32_t ValueKind,
                                  uint32_t Site) const;

  /// Reserve space for NumValueSites sites.
  inline void reserveSites(uint32_t ValueKind, uint32_t NumValueSites);

  /// Add ValueData for ValueKind at value Site.
  void addValueData(uint32_t ValueKind, uint32_t Site,
                    InstrProfValueData *VData, uint32_t N,
                    InstrProfSymtab *SymTab);

  /// Merge the counts in \p Other into this one.
  /// Optionally scale merged counts by \p Weight.
  void merge(InstrProfRecord &Other, uint64_t Weight,
             function_ref<void(instrprof_error)> Warn);

  /// Scale up profile counts (including value profile data) by
  /// a factor of (N / D).
  void scale(uint64_t N, uint64_t D, function_ref<void(instrprof_error)> Warn);

  /// Sort value profile data (per site) by count.
  void sortValueData() {
    for (uint32_t Kind = IPVK_First; Kind <= IPVK_Last; ++Kind)
      for (auto &SR : getValueSitesForKind(Kind))
        SR.sortByCount();
  }

  /// Clear value data entries and edge counters.
  void Clear() {
    Counts.clear();
    clearValueData();
  }

  /// Clear value data entries
  void clearValueData() { ValueData = nullptr; }

  /// Compute the sums of all counts and store in Sum.
  void accumulateCounts(CountSumOrPercent &Sum) const;

  /// Compute the overlap b/w this IntrprofRecord and Other.
  void overlap(InstrProfRecord &Other, OverlapStats &Overlap,
               OverlapStats &FuncLevelOverlap, uint64_t ValueCutoff);

  /// Compute the overlap of value profile counts.
  void overlapValueProfData(uint32_t ValueKind, InstrProfRecord &Src,
                            OverlapStats &Overlap,
                            OverlapStats &FuncLevelOverlap);

  enum CountPseudoKind {
    NotPseudo = 0,
    PseudoHot,
    PseudoWarm,
  };
  enum PseudoCountVal {
    HotFunctionVal = -1,
    WarmFunctionVal = -2,
  };
  CountPseudoKind getCountPseudoKind() const {
    uint64_t FirstCount = Counts[0];
    if (FirstCount == (uint64_t)HotFunctionVal)
      return PseudoHot;
    if (FirstCount == (uint64_t)WarmFunctionVal)
      return PseudoWarm;
    return NotPseudo;
  }
  void setPseudoCount(CountPseudoKind Kind) {
    if (Kind == PseudoHot)
      Counts[0] = (uint64_t)HotFunctionVal;
    else if (Kind == PseudoWarm)
      Counts[0] = (uint64_t)WarmFunctionVal;
  }

private:
  struct ValueProfData {
    std::vector<InstrProfValueSiteRecord> IndirectCallSites;
    std::vector<InstrProfValueSiteRecord> MemOPSizes;
  };
  std::unique_ptr<ValueProfData> ValueData;

  MutableArrayRef<InstrProfValueSiteRecord>
  getValueSitesForKind(uint32_t ValueKind) {
    // Cast to /add/ const (should be an implicit_cast, ideally, if that's ever
    // implemented in LLVM) to call the const overload of this function, then
    // cast away the constness from the result.
    auto AR = const_cast<const InstrProfRecord *>(this)->getValueSitesForKind(
        ValueKind);
    return MutableArrayRef(
        const_cast<InstrProfValueSiteRecord *>(AR.data()), AR.size());
  }
  ArrayRef<InstrProfValueSiteRecord>
  getValueSitesForKind(uint32_t ValueKind) const {
    if (!ValueData)
      return std::nullopt;
    switch (ValueKind) {
    case IPVK_IndirectCallTarget:
      return ValueData->IndirectCallSites;
    case IPVK_MemOPSize:
      return ValueData->MemOPSizes;
    default:
      llvm_unreachable("Unknown value kind!");
    }
  }

  std::vector<InstrProfValueSiteRecord> &
  getOrCreateValueSitesForKind(uint32_t ValueKind) {
    if (!ValueData)
      ValueData = std::make_unique<ValueProfData>();
    switch (ValueKind) {
    case IPVK_IndirectCallTarget:
      return ValueData->IndirectCallSites;
    case IPVK_MemOPSize:
      return ValueData->MemOPSizes;
    default:
      llvm_unreachable("Unknown value kind!");
    }
  }

  // Map indirect call target name hash to name string.
  uint64_t remapValue(uint64_t Value, uint32_t ValueKind,
                      InstrProfSymtab *SymTab);

  // Merge Value Profile data from Src record to this record for ValueKind.
  // Scale merged value counts by \p Weight.
  void mergeValueProfData(uint32_t ValkeKind, InstrProfRecord &Src,
                          uint64_t Weight,
                          function_ref<void(instrprof_error)> Warn);

  // Scale up value profile data count by N (Numerator) / D (Denominator).
  void scaleValueProfData(uint32_t ValueKind, uint64_t N, uint64_t D,
                          function_ref<void(instrprof_error)> Warn);
};

struct NamedInstrProfRecord : InstrProfRecord {
  StringRef Name;
  uint64_t Hash;

  // We reserve this bit as the flag for context sensitive profile record.
  static const int CS_FLAG_IN_FUNC_HASH = 60;

  NamedInstrProfRecord() = default;
  NamedInstrProfRecord(StringRef Name, uint64_t Hash,
                       std::vector<uint64_t> Counts)
      : InstrProfRecord(std::move(Counts)), Name(Name), Hash(Hash) {}
  NamedInstrProfRecord(StringRef Name, uint64_t Hash,
                       std::vector<uint64_t> Counts,
                       std::vector<uint8_t> BitmapBytes)
      : InstrProfRecord(std::move(Counts), std::move(BitmapBytes)), Name(Name),
        Hash(Hash) {}

  static bool hasCSFlagInHash(uint64_t FuncHash) {
    return ((FuncHash >> CS_FLAG_IN_FUNC_HASH) & 1);
  }
  static void setCSFlagInHash(uint64_t &FuncHash) {
    FuncHash |= ((uint64_t)1 << CS_FLAG_IN_FUNC_HASH);
  }
};

uint32_t InstrProfRecord::getNumValueKinds() const {
  uint32_t NumValueKinds = 0;
  for (uint32_t Kind = IPVK_First; Kind <= IPVK_Last; ++Kind)
    NumValueKinds += !(getValueSitesForKind(Kind).empty());
  return NumValueKinds;
}

uint32_t InstrProfRecord::getNumValueData(uint32_t ValueKind) const {
  uint32_t N = 0;
  for (const auto &SR : getValueSitesForKind(ValueKind))
    N += SR.ValueData.size();
  return N;
}

uint32_t InstrProfRecord::getNumValueSites(uint32_t ValueKind) const {
  return getValueSitesForKind(ValueKind).size();
}

uint32_t InstrProfRecord::getNumValueDataForSite(uint32_t ValueKind,
                                                 uint32_t Site) const {
  return getValueSitesForKind(ValueKind)[Site].ValueData.size();
}

std::unique_ptr<InstrProfValueData[]>
InstrProfRecord::getValueForSite(uint32_t ValueKind, uint32_t Site,
                                 uint64_t *TotalC) const {
  uint64_t Dummy = 0;
  uint64_t &TotalCount = (TotalC == nullptr ? Dummy : *TotalC);
  uint32_t N = getNumValueDataForSite(ValueKind, Site);
  if (N == 0) {
    TotalCount = 0;
    return std::unique_ptr<InstrProfValueData[]>(nullptr);
  }

  auto VD = std::make_unique<InstrProfValueData[]>(N);
  TotalCount = getValueForSite(VD.get(), ValueKind, Site);

  return VD;
}

uint64_t InstrProfRecord::getValueForSite(InstrProfValueData Dest[],
                                          uint32_t ValueKind,
                                          uint32_t Site) const {
  uint32_t I = 0;
  uint64_t TotalCount = 0;
  for (auto V : getValueSitesForKind(ValueKind)[Site].ValueData) {
    Dest[I].Value = V.Value;
    Dest[I].Count = V.Count;
    TotalCount = SaturatingAdd(TotalCount, V.Count);
    I++;
  }
  return TotalCount;
}

void InstrProfRecord::reserveSites(uint32_t ValueKind, uint32_t NumValueSites) {
  if (!NumValueSites)
    return;
  getOrCreateValueSitesForKind(ValueKind).reserve(NumValueSites);
}

// Include definitions for value profile data
#define INSTR_PROF_VALUE_PROF_DATA
#include "llvm/ProfileData/InstrProfData.inc"

void InstrProfValueSiteRecord::sortByCount() {
  ValueData.sort(
      [](const InstrProfValueData &left, const InstrProfValueData &right) {
        return left.Count > right.Count;
      });
  // Now truncate
  size_t max_s = INSTR_PROF_MAX_NUM_VAL_PER_SITE;
  if (ValueData.size() > max_s)
    ValueData.resize(max_s);
}

namespace IndexedInstrProf {

enum class HashT : uint32_t {
  MD5,
  Last = MD5
};

inline uint64_t ComputeHash(HashT Type, StringRef K) {
  switch (Type) {
  case HashT::MD5:
    return MD5Hash(K);
  }
  llvm_unreachable("Unhandled hash type");
}

const uint64_t Magic = 0x8169666f72706cff; // "\xfflprofi\x81"

enum ProfVersion {
  // Version 1 is the first version. In this version, the value of
  // a key/value pair can only include profile data of a single function.
  // Due to this restriction, the number of block counters for a given
  // function is not recorded but derived from the length of the value.
  Version1 = 1,
  // The version 2 format supports recording profile data of multiple
  // functions which share the same key in one value field. To support this,
  // the number block counters is recorded as an uint64_t field right after the
  // function structural hash.
  Version2 = 2,
  // Version 3 supports value profile data. The value profile data is expected
  // to follow the block counter profile data.
  Version3 = 3,
  // In this version, profile summary data \c IndexedInstrProf::Summary is
  // stored after the profile header.
  Version4 = 4,
  // In this version, the frontend PGO stable hash algorithm defaults to V2.
  Version5 = 5,
  // In this version, the frontend PGO stable hash algorithm got fixed and
  // may produce hashes different from Version5.
  Version6 = 6,
  // An additional counter is added around logical operators.
  Version7 = 7,
  // An additional (optional) memory profile type is added.
  Version8 = 8,
  // Binary ids are added.
  Version9 = 9,
  // An additional (optional) temporal profile traces section is added.
  Version10 = 10,
  // An additional field is used for bitmap bytes.
  Version11 = 11,
  // The current version is 11.
  CurrentVersion = INSTR_PROF_INDEX_VERSION
};
const uint64_t Version = ProfVersion::CurrentVersion;

const HashT HashType = HashT::MD5;

inline uint64_t ComputeHash(StringRef K) { return ComputeHash(HashType, K); }

// This structure defines the file header of the LLVM profile
// data file in indexed-format. Please update llvm/docs/InstrProfileFormat.rst
// as appropriate when updating the indexed profile format.
struct Header {
  uint64_t Magic;
  uint64_t Version;
  uint64_t Unused; // Becomes unused since version 4
  uint64_t HashType;
  uint64_t HashOffset;
  uint64_t MemProfOffset;
  uint64_t BinaryIdOffset;
  uint64_t TemporalProfTracesOffset;
  // New fields should only be added at the end to ensure that the size
  // computation is correct. The methods below need to be updated to ensure that
  // the new field is read correctly.

  // Reads a header struct from the buffer.
  static Expected<Header> readFromBuffer(const unsigned char *Buffer);

  // Returns the size of the header in bytes for all valid fields based on the
  // version. I.e a older version header will return a smaller size.
  size_t size() const;

  // Returns the format version in little endian. The header retains the version
  // in native endian of the compiler runtime.
  uint64_t formatVersion() const;
};

// Profile summary data recorded in the profile data file in indexed
// format. It is introduced in version 4. The summary data follows
// right after the profile file header.
struct Summary {
  struct Entry {
    uint64_t Cutoff; ///< The required percentile of total execution count.
    uint64_t
        MinBlockCount;  ///< The minimum execution count for this percentile.
    uint64_t NumBlocks; ///< Number of blocks >= the minumum execution count.
  };
  // The field kind enumerator to assigned value mapping should remain
  // unchanged  when a new kind is added or an old kind gets deleted in
  // the future.
  enum SummaryFieldKind {
    /// The total number of functions instrumented.
    TotalNumFunctions = 0,
    /// Total number of instrumented blocks/edges.
    TotalNumBlocks = 1,
    /// The maximal execution count among all functions.
    /// This field does not exist for profile data from IR based
    /// instrumentation.
    MaxFunctionCount = 2,
    /// Max block count of the program.
    MaxBlockCount = 3,
    /// Max internal block count of the program (excluding entry blocks).
    MaxInternalBlockCount = 4,
    /// The sum of all instrumented block counts.
    TotalBlockCount = 5,
    NumKinds = TotalBlockCount + 1
  };

  // The number of summmary fields following the summary header.
  uint64_t NumSummaryFields;
  // The number of Cutoff Entries (Summary::Entry) following summary fields.
  uint64_t NumCutoffEntries;

  Summary() = delete;
  Summary(uint32_t Size) { memset(this, 0, Size); }

  void operator delete(void *ptr) { ::operator delete(ptr); }

  static uint32_t getSize(uint32_t NumSumFields, uint32_t NumCutoffEntries) {
    return sizeof(Summary) + NumCutoffEntries * sizeof(Entry) +
           NumSumFields * sizeof(uint64_t);
  }

  const uint64_t *getSummaryDataBase() const {
    return reinterpret_cast<const uint64_t *>(this + 1);
  }

  uint64_t *getSummaryDataBase() {
    return reinterpret_cast<uint64_t *>(this + 1);
  }

  const Entry *getCutoffEntryBase() const {
    return reinterpret_cast<const Entry *>(
        &getSummaryDataBase()[NumSummaryFields]);
  }

  Entry *getCutoffEntryBase() {
    return reinterpret_cast<Entry *>(&getSummaryDataBase()[NumSummaryFields]);
  }

  uint64_t get(SummaryFieldKind K) const {
    return getSummaryDataBase()[K];
  }

  void set(SummaryFieldKind K, uint64_t V) {
    getSummaryDataBase()[K] = V;
  }

  const Entry &getEntry(uint32_t I) const { return getCutoffEntryBase()[I]; }

  void setEntry(uint32_t I, const ProfileSummaryEntry &E) {
    Entry &ER = getCutoffEntryBase()[I];
    ER.Cutoff = E.Cutoff;
    ER.MinBlockCount = E.MinCount;
    ER.NumBlocks = E.NumCounts;
  }
};

inline std::unique_ptr<Summary> allocSummary(uint32_t TotalSize) {
  return std::unique_ptr<Summary>(new (::operator new(TotalSize))
                                      Summary(TotalSize));
}

} // end namespace IndexedInstrProf

namespace RawInstrProf {

// Version 1: First version
// Version 2: Added value profile data section. Per-function control data
// struct has more fields to describe value profile information.
// Version 3: Compressed name section support. Function PGO name reference
// from control data struct is changed from raw pointer to Name's MD5 value.
// Version 4: ValueDataBegin and ValueDataSizes fields are removed from the
// raw header.
// Version 5: Bit 60 of FuncHash is reserved for the flag for the context
// sensitive records.
// Version 6: Added binary id.
// Version 7: Reorder binary id and include version in signature.
// Version 8: Use relative counter pointer.
// Version 9: Added relative bitmap bytes pointer and count used by MC/DC.
const uint64_t Version = INSTR_PROF_RAW_VERSION;

template <class IntPtrT> inline uint64_t getMagic();
template <> inline uint64_t getMagic<uint64_t>() {
  return INSTR_PROF_RAW_MAGIC_64;
}

template <> inline uint64_t getMagic<uint32_t>() {
  return INSTR_PROF_RAW_MAGIC_32;
}

// Per-function profile data header/control structure.
// The definition should match the structure defined in
// compiler-rt/lib/profile/InstrProfiling.h.
// It should also match the synthesized type in
// Transforms/Instrumentation/InstrProfiling.cpp:getOrCreateRegionCounters.
template <class IntPtrT> struct alignas(8) ProfileData {
  #define INSTR_PROF_DATA(Type, LLVMType, Name, Init) Type Name;
  #include "llvm/ProfileData/InstrProfData.inc"
};

// File header structure of the LLVM profile data in raw format.
// The definition should match the header referenced in
// compiler-rt/lib/profile/InstrProfilingFile.c  and
// InstrProfilingBuffer.c.
struct Header {
#define INSTR_PROF_RAW_HEADER(Type, Name, Init) const Type Name;
#include "llvm/ProfileData/InstrProfData.inc"
};

} // end namespace RawInstrProf

// Create the variable for the profile file name.
void createProfileFileNameVar(Module &M, StringRef InstrProfileOutput);

// Whether to compress function names in profile records, and filenames in
// code coverage mappings. Used by the Instrumentation library and unit tests.
extern cl::opt<bool> DoInstrProfNameCompression;

} // end namespace llvm
#endif // LLVM_PROFILEDATA_INSTRPROF_H