llvm.org GIT mirror llvm / c887230 lib / ProfileData / InstrProfReader.cpp
c887230

Tree @c887230 (Download .tar.gz)

InstrProfReader.cpp @c887230raw · history · blame

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
//=-- InstrProfReader.cpp - Instrumented profiling reader -------------------=//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file contains support for reading profiling data for clang's
// instrumentation based PGO and coverage.
//
//===----------------------------------------------------------------------===//

#include "llvm/ProfileData/InstrProfReader.h"
#include "llvm/ADT/STLExtras.h"
#include <cassert>

using namespace llvm;

static Expected<std::unique_ptr<MemoryBuffer>>
setupMemoryBuffer(const Twine &Path) {
  ErrorOr<std::unique_ptr<MemoryBuffer>> BufferOrErr =
      MemoryBuffer::getFileOrSTDIN(Path);
  if (std::error_code EC = BufferOrErr.getError())
    return errorCodeToError(EC);
  return std::move(BufferOrErr.get());
}

static Error initializeReader(InstrProfReader &Reader) {
  return Reader.readHeader();
}

Expected<std::unique_ptr<InstrProfReader>>
InstrProfReader::create(const Twine &Path) {
  // Set up the buffer to read.
  auto BufferOrError = setupMemoryBuffer(Path);
  if (Error E = BufferOrError.takeError())
    return std::move(E);
  return InstrProfReader::create(std::move(BufferOrError.get()));
}

Expected<std::unique_ptr<InstrProfReader>>
InstrProfReader::create(std::unique_ptr<MemoryBuffer> Buffer) {
  // Sanity check the buffer.
  if (Buffer->getBufferSize() > std::numeric_limits<unsigned>::max())
    return make_error<InstrProfError>(instrprof_error::too_large);

  if (Buffer->getBufferSize() == 0)
    return make_error<InstrProfError>(instrprof_error::empty_raw_profile);

  std::unique_ptr<InstrProfReader> Result;
  // Create the reader.
  if (IndexedInstrProfReader::hasFormat(*Buffer))
    Result.reset(new IndexedInstrProfReader(std::move(Buffer)));
  else if (RawInstrProfReader64::hasFormat(*Buffer))
    Result.reset(new RawInstrProfReader64(std::move(Buffer)));
  else if (RawInstrProfReader32::hasFormat(*Buffer))
    Result.reset(new RawInstrProfReader32(std::move(Buffer)));
  else if (TextInstrProfReader::hasFormat(*Buffer))
    Result.reset(new TextInstrProfReader(std::move(Buffer)));
  else
    return make_error<InstrProfError>(instrprof_error::unrecognized_format);

  // Initialize the reader and return the result.
  if (Error E = initializeReader(*Result))
    return std::move(E);

  return std::move(Result);
}

Expected<std::unique_ptr<IndexedInstrProfReader>>
IndexedInstrProfReader::create(const Twine &Path) {
  // Set up the buffer to read.
  auto BufferOrError = setupMemoryBuffer(Path);
  if (Error E = BufferOrError.takeError())
    return std::move(E);
  return IndexedInstrProfReader::create(std::move(BufferOrError.get()));
}


Expected<std::unique_ptr<IndexedInstrProfReader>>
IndexedInstrProfReader::create(std::unique_ptr<MemoryBuffer> Buffer) {
  // Sanity check the buffer.
  if (Buffer->getBufferSize() > std::numeric_limits<unsigned>::max())
    return make_error<InstrProfError>(instrprof_error::too_large);

  // Create the reader.
  if (!IndexedInstrProfReader::hasFormat(*Buffer))
    return make_error<InstrProfError>(instrprof_error::bad_magic);
  auto Result = llvm::make_unique<IndexedInstrProfReader>(std::move(Buffer));

  // Initialize the reader and return the result.
  if (Error E = initializeReader(*Result))
    return std::move(E);

  return std::move(Result);
}

void InstrProfIterator::Increment() {
  if (auto E = Reader->readNextRecord(Record)) {
    // Handle errors in the reader.
    InstrProfError::take(std::move(E));
    *this = InstrProfIterator();
  }
}

bool TextInstrProfReader::hasFormat(const MemoryBuffer &Buffer) {
  // Verify that this really looks like plain ASCII text by checking a
  // 'reasonable' number of characters (up to profile magic size).
  size_t count = std::min(Buffer.getBufferSize(), sizeof(uint64_t));
  StringRef buffer = Buffer.getBufferStart();
  return count == 0 ||
         std::all_of(buffer.begin(), buffer.begin() + count,
                     [](char c) { return ::isprint(c) || ::isspace(c); });
}

// Read the profile variant flag from the header: ":FE" means this is a FE
// generated profile. ":IR" means this is an IR level profile. Other strings
// with a leading ':' will be reported an error format.
Error TextInstrProfReader::readHeader() {
  Symtab.reset(new InstrProfSymtab());
  bool IsIRInstr = false;
  if (!Line->startswith(":")) {
    IsIRLevelProfile = false;
    return success();
  }
  StringRef Str = (Line)->substr(1);
  if (Str.equals_lower("ir"))
    IsIRInstr = true;
  else if (Str.equals_lower("fe"))
    IsIRInstr = false;
  else
    return error(instrprof_error::bad_header);

  ++Line;
  IsIRLevelProfile = IsIRInstr;
  return success();
}

Error
TextInstrProfReader::readValueProfileData(InstrProfRecord &Record) {

#define CHECK_LINE_END(Line)                                                   \
  if (Line.is_at_end())                                                        \
    return error(instrprof_error::truncated);
#define READ_NUM(Str, Dst)                                                     \
  if ((Str).getAsInteger(10, (Dst)))                                           \
    return error(instrprof_error::malformed);
#define VP_READ_ADVANCE(Val)                                                   \
  CHECK_LINE_END(Line);                                                        \
  uint32_t Val;                                                                \
  READ_NUM((*Line), (Val));                                                    \
  Line++;

  if (Line.is_at_end())
    return success();

  uint32_t NumValueKinds;
  if (Line->getAsInteger(10, NumValueKinds)) {
    // No value profile data
    return success();
  }
  if (NumValueKinds == 0 || NumValueKinds > IPVK_Last + 1)
    return error(instrprof_error::malformed);
  Line++;

  for (uint32_t VK = 0; VK < NumValueKinds; VK++) {
    VP_READ_ADVANCE(ValueKind);
    if (ValueKind > IPVK_Last)
      return error(instrprof_error::malformed);
    VP_READ_ADVANCE(NumValueSites);
    if (!NumValueSites)
      continue;

    Record.reserveSites(VK, NumValueSites);
    for (uint32_t S = 0; S < NumValueSites; S++) {
      VP_READ_ADVANCE(NumValueData);

      std::vector<InstrProfValueData> CurrentValues;
      for (uint32_t V = 0; V < NumValueData; V++) {
        CHECK_LINE_END(Line);
        std::pair<StringRef, StringRef> VD = Line->rsplit(':');
        uint64_t TakenCount, Value;
        if (VK == IPVK_IndirectCallTarget) {
          Symtab->addFuncName(VD.first);
          Value = IndexedInstrProf::ComputeHash(VD.first);
        } else {
          READ_NUM(VD.first, Value);
        }
        READ_NUM(VD.second, TakenCount);
        CurrentValues.push_back({Value, TakenCount});
        Line++;
      }
      Record.addValueData(VK, S, CurrentValues.data(), NumValueData, nullptr);
    }
  }
  return success();

#undef CHECK_LINE_END
#undef READ_NUM
#undef VP_READ_ADVANCE
}

Error TextInstrProfReader::readNextRecord(InstrProfRecord &Record) {
  // Skip empty lines and comments.
  while (!Line.is_at_end() && (Line->empty() || Line->startswith("#")))
    ++Line;
  // If we hit EOF while looking for a name, we're done.
  if (Line.is_at_end()) {
    Symtab->finalizeSymtab();
    return error(instrprof_error::eof);
  }

  // Read the function name.
  Record.Name = *Line++;
  Symtab->addFuncName(Record.Name);

  // Read the function hash.
  if (Line.is_at_end())
    return error(instrprof_error::truncated);
  if ((Line++)->getAsInteger(0, Record.Hash))
    return error(instrprof_error::malformed);

  // Read the number of counters.
  uint64_t NumCounters;
  if (Line.is_at_end())
    return error(instrprof_error::truncated);
  if ((Line++)->getAsInteger(10, NumCounters))
    return error(instrprof_error::malformed);
  if (NumCounters == 0)
    return error(instrprof_error::malformed);

  // Read each counter and fill our internal storage with the values.
  Record.Counts.clear();
  Record.Counts.reserve(NumCounters);
  for (uint64_t I = 0; I < NumCounters; ++I) {
    if (Line.is_at_end())
      return error(instrprof_error::truncated);
    uint64_t Count;
    if ((Line++)->getAsInteger(10, Count))
      return error(instrprof_error::malformed);
    Record.Counts.push_back(Count);
  }

  // Check if value profile data exists and read it if so.
  if (Error E = readValueProfileData(Record))
    return E;

  // This is needed to avoid two pass parsing because llvm-profdata
  // does dumping while reading.
  Symtab->finalizeSymtab();
  return success();
}

template <class IntPtrT>
bool RawInstrProfReader<IntPtrT>::hasFormat(const MemoryBuffer &DataBuffer) {
  if (DataBuffer.getBufferSize() < sizeof(uint64_t))
    return false;
  uint64_t Magic =
    *reinterpret_cast<const uint64_t *>(DataBuffer.getBufferStart());
  return RawInstrProf::getMagic<IntPtrT>() == Magic ||
         sys::getSwappedBytes(RawInstrProf::getMagic<IntPtrT>()) == Magic;
}

template <class IntPtrT>
Error RawInstrProfReader<IntPtrT>::readHeader() {
  if (!hasFormat(*DataBuffer))
    return error(instrprof_error::bad_magic);
  if (DataBuffer->getBufferSize() < sizeof(RawInstrProf::Header))
    return error(instrprof_error::bad_header);
  auto *Header = reinterpret_cast<const RawInstrProf::Header *>(
      DataBuffer->getBufferStart());
  ShouldSwapBytes = Header->Magic != RawInstrProf::getMagic<IntPtrT>();
  return readHeader(*Header);
}

template <class IntPtrT>
Error RawInstrProfReader<IntPtrT>::readNextHeader(const char *CurrentPos) {
  const char *End = DataBuffer->getBufferEnd();
  // Skip zero padding between profiles.
  while (CurrentPos != End && *CurrentPos == 0)
    ++CurrentPos;
  // If there's nothing left, we're done.
  if (CurrentPos == End)
    return make_error<InstrProfError>(instrprof_error::eof);
  // If there isn't enough space for another header, this is probably just
  // garbage at the end of the file.
  if (CurrentPos + sizeof(RawInstrProf::Header) > End)
    return make_error<InstrProfError>(instrprof_error::malformed);
  // The writer ensures each profile is padded to start at an aligned address.
  if (reinterpret_cast<size_t>(CurrentPos) % alignOf<uint64_t>())
    return make_error<InstrProfError>(instrprof_error::malformed);
  // The magic should have the same byte order as in the previous header.
  uint64_t Magic = *reinterpret_cast<const uint64_t *>(CurrentPos);
  if (Magic != swap(RawInstrProf::getMagic<IntPtrT>()))
    return make_error<InstrProfError>(instrprof_error::bad_magic);

  // There's another profile to read, so we need to process the header.
  auto *Header = reinterpret_cast<const RawInstrProf::Header *>(CurrentPos);
  return readHeader(*Header);
}

template <class IntPtrT>
Error RawInstrProfReader<IntPtrT>::createSymtab(InstrProfSymtab &Symtab) {
  if (Error E = Symtab.create(StringRef(NamesStart, NamesSize)))
    return error(std::move(E));
  for (const RawInstrProf::ProfileData<IntPtrT> *I = Data; I != DataEnd; ++I) {
    const IntPtrT FPtr = swap(I->FunctionPointer);
    if (!FPtr)
      continue;
    Symtab.mapAddress(FPtr, I->NameRef);
  }
  Symtab.finalizeSymtab();
  return success();
}

template <class IntPtrT>
Error RawInstrProfReader<IntPtrT>::readHeader(
    const RawInstrProf::Header &Header) {
  Version = swap(Header.Version);
  if (GET_VERSION(Version) != RawInstrProf::Version)
    return error(instrprof_error::unsupported_version);

  CountersDelta = swap(Header.CountersDelta);
  NamesDelta = swap(Header.NamesDelta);
  auto DataSize = swap(Header.DataSize);
  auto CountersSize = swap(Header.CountersSize);
  NamesSize = swap(Header.NamesSize);
  ValueKindLast = swap(Header.ValueKindLast);

  auto DataSizeInBytes = DataSize * sizeof(RawInstrProf::ProfileData<IntPtrT>);
  auto PaddingSize = getNumPaddingBytes(NamesSize);

  ptrdiff_t DataOffset = sizeof(RawInstrProf::Header);
  ptrdiff_t CountersOffset = DataOffset + DataSizeInBytes;
  ptrdiff_t NamesOffset = CountersOffset + sizeof(uint64_t) * CountersSize;
  ptrdiff_t ValueDataOffset = NamesOffset + NamesSize + PaddingSize;

  auto *Start = reinterpret_cast<const char *>(&Header);
  if (Start + ValueDataOffset > DataBuffer->getBufferEnd())
    return error(instrprof_error::bad_header);

  Data = reinterpret_cast<const RawInstrProf::ProfileData<IntPtrT> *>(
      Start + DataOffset);
  DataEnd = Data + DataSize;
  CountersStart = reinterpret_cast<const uint64_t *>(Start + CountersOffset);
  NamesStart = Start + NamesOffset;
  ValueDataStart = reinterpret_cast<const uint8_t *>(Start + ValueDataOffset);

  std::unique_ptr<InstrProfSymtab> NewSymtab = make_unique<InstrProfSymtab>();
  if (Error E = createSymtab(*NewSymtab.get()))
    return E;

  Symtab = std::move(NewSymtab);
  return success();
}

template <class IntPtrT>
Error RawInstrProfReader<IntPtrT>::readName(InstrProfRecord &Record) {
  Record.Name = getName(Data->NameRef);
  return success();
}

template <class IntPtrT>
Error RawInstrProfReader<IntPtrT>::readFuncHash(InstrProfRecord &Record) {
  Record.Hash = swap(Data->FuncHash);
  return success();
}

template <class IntPtrT>
Error RawInstrProfReader<IntPtrT>::readRawCounts(
    InstrProfRecord &Record) {
  uint32_t NumCounters = swap(Data->NumCounters);
  IntPtrT CounterPtr = Data->CounterPtr;
  if (NumCounters == 0)
    return error(instrprof_error::malformed);

  auto RawCounts = makeArrayRef(getCounter(CounterPtr), NumCounters);
  auto *NamesStartAsCounter = reinterpret_cast<const uint64_t *>(NamesStart);

  // Check bounds.
  if (RawCounts.data() < CountersStart ||
      RawCounts.data() + RawCounts.size() > NamesStartAsCounter)
    return error(instrprof_error::malformed);

  if (ShouldSwapBytes) {
    Record.Counts.clear();
    Record.Counts.reserve(RawCounts.size());
    for (uint64_t Count : RawCounts)
      Record.Counts.push_back(swap(Count));
  } else
    Record.Counts = RawCounts;

  return success();
}

template <class IntPtrT>
Error RawInstrProfReader<IntPtrT>::readValueProfilingData(
    InstrProfRecord &Record) {

  Record.clearValueData();
  CurValueDataSize = 0;
  // Need to match the logic in value profile dumper code in compiler-rt:
  uint32_t NumValueKinds = 0;
  for (uint32_t I = 0; I < IPVK_Last + 1; I++)
    NumValueKinds += (Data->NumValueSites[I] != 0);

  if (!NumValueKinds)
    return success();

  Expected<std::unique_ptr<ValueProfData>> VDataPtrOrErr =
      ValueProfData::getValueProfData(
          ValueDataStart, (const unsigned char *)DataBuffer->getBufferEnd(),
          getDataEndianness());

  if (Error E = VDataPtrOrErr.takeError())
    return E;

  // Note that besides deserialization, this also performs the conversion for
  // indirect call targets.  The function pointers from the raw profile are
  // remapped into function name hashes.
  VDataPtrOrErr.get()->deserializeTo(Record, &Symtab->getAddrHashMap());
  CurValueDataSize = VDataPtrOrErr.get()->getSize();
  return success();
}

template <class IntPtrT>
Error RawInstrProfReader<IntPtrT>::readNextRecord(InstrProfRecord &Record) {
  if (atEnd())
    // At this point, ValueDataStart field points to the next header.
    if (Error E = readNextHeader(getNextHeaderPos()))
      return E;

  // Read name ad set it in Record.
  if (Error E = readName(Record))
    return E;

  // Read FuncHash and set it in Record.
  if (Error E = readFuncHash(Record))
    return E;

  // Read raw counts and set Record.
  if (Error E = readRawCounts(Record))
    return E;

  // Read value data and set Record.
  if (Error E = readValueProfilingData(Record))
    return E;

  // Iterate.
  advanceData();
  return success();
}

namespace llvm {
template class RawInstrProfReader<uint32_t>;
template class RawInstrProfReader<uint64_t>;
}

InstrProfLookupTrait::hash_value_type
InstrProfLookupTrait::ComputeHash(StringRef K) {
  return IndexedInstrProf::ComputeHash(HashType, K);
}

typedef InstrProfLookupTrait::data_type data_type;
typedef InstrProfLookupTrait::offset_type offset_type;

bool InstrProfLookupTrait::readValueProfilingData(
    const unsigned char *&D, const unsigned char *const End) {
  Expected<std::unique_ptr<ValueProfData>> VDataPtrOrErr =
      ValueProfData::getValueProfData(D, End, ValueProfDataEndianness);

  if (VDataPtrOrErr.takeError())
    return false;

  VDataPtrOrErr.get()->deserializeTo(DataBuffer.back(), nullptr);
  D += VDataPtrOrErr.get()->TotalSize;

  return true;
}

data_type InstrProfLookupTrait::ReadData(StringRef K, const unsigned char *D,
                                         offset_type N) {
  // Check if the data is corrupt. If so, don't try to read it.
  if (N % sizeof(uint64_t))
    return data_type();

  DataBuffer.clear();
  std::vector<uint64_t> CounterBuffer;

  using namespace support;
  const unsigned char *End = D + N;
  while (D < End) {
    // Read hash.
    if (D + sizeof(uint64_t) >= End)
      return data_type();
    uint64_t Hash = endian::readNext<uint64_t, little, unaligned>(D);

    // Initialize number of counters for GET_VERSION(FormatVersion) == 1.
    uint64_t CountsSize = N / sizeof(uint64_t) - 1;
    // If format version is different then read the number of counters.
    if (GET_VERSION(FormatVersion) != IndexedInstrProf::ProfVersion::Version1) {
      if (D + sizeof(uint64_t) > End)
        return data_type();
      CountsSize = endian::readNext<uint64_t, little, unaligned>(D);
    }
    // Read counter values.
    if (D + CountsSize * sizeof(uint64_t) > End)
      return data_type();

    CounterBuffer.clear();
    CounterBuffer.reserve(CountsSize);
    for (uint64_t J = 0; J < CountsSize; ++J)
      CounterBuffer.push_back(endian::readNext<uint64_t, little, unaligned>(D));

    DataBuffer.emplace_back(K, Hash, std::move(CounterBuffer));

    // Read value profiling data.
    if (GET_VERSION(FormatVersion) > IndexedInstrProf::ProfVersion::Version2 &&
        !readValueProfilingData(D, End)) {
      DataBuffer.clear();
      return data_type();
    }
  }
  return DataBuffer;
}

template <typename HashTableImpl>
Error InstrProfReaderIndex<HashTableImpl>::getRecords(
    StringRef FuncName, ArrayRef<InstrProfRecord> &Data) {
  auto Iter = HashTable->find(FuncName);
  if (Iter == HashTable->end())
    return make_error<InstrProfError>(instrprof_error::unknown_function);

  Data = (*Iter);
  if (Data.empty())
    return make_error<InstrProfError>(instrprof_error::malformed);

  return Error::success();
}

template <typename HashTableImpl>
Error InstrProfReaderIndex<HashTableImpl>::getRecords(
    ArrayRef<InstrProfRecord> &Data) {
  if (atEnd())
    return make_error<InstrProfError>(instrprof_error::eof);

  Data = *RecordIterator;

  if (Data.empty())
    return make_error<InstrProfError>(instrprof_error::malformed);

  return Error::success();
}

template <typename HashTableImpl>
InstrProfReaderIndex<HashTableImpl>::InstrProfReaderIndex(
    const unsigned char *Buckets, const unsigned char *const Payload,
    const unsigned char *const Base, IndexedInstrProf::HashT HashType,
    uint64_t Version) {
  FormatVersion = Version;
  HashTable.reset(HashTableImpl::Create(
      Buckets, Payload, Base,
      typename HashTableImpl::InfoType(HashType, Version)));
  RecordIterator = HashTable->data_begin();
}

bool IndexedInstrProfReader::hasFormat(const MemoryBuffer &DataBuffer) {
  if (DataBuffer.getBufferSize() < 8)
    return false;
  using namespace support;
  uint64_t Magic =
      endian::read<uint64_t, little, aligned>(DataBuffer.getBufferStart());
  // Verify that it's magical.
  return Magic == IndexedInstrProf::Magic;
}

const unsigned char *
IndexedInstrProfReader::readSummary(IndexedInstrProf::ProfVersion Version,
                                    const unsigned char *Cur) {
  using namespace IndexedInstrProf;
  using namespace support;
  if (Version >= IndexedInstrProf::Version4) {
    const IndexedInstrProf::Summary *SummaryInLE =
        reinterpret_cast<const IndexedInstrProf::Summary *>(Cur);
    uint64_t NFields =
        endian::byte_swap<uint64_t, little>(SummaryInLE->NumSummaryFields);
    uint64_t NEntries =
        endian::byte_swap<uint64_t, little>(SummaryInLE->NumCutoffEntries);
    uint32_t SummarySize =
        IndexedInstrProf::Summary::getSize(NFields, NEntries);
    std::unique_ptr<IndexedInstrProf::Summary> SummaryData =
        IndexedInstrProf::allocSummary(SummarySize);

    const uint64_t *Src = reinterpret_cast<const uint64_t *>(SummaryInLE);
    uint64_t *Dst = reinterpret_cast<uint64_t *>(SummaryData.get());
    for (unsigned I = 0; I < SummarySize / sizeof(uint64_t); I++)
      Dst[I] = endian::byte_swap<uint64_t, little>(Src[I]);

    llvm::SummaryEntryVector DetailedSummary;
    for (unsigned I = 0; I < SummaryData->NumCutoffEntries; I++) {
      const IndexedInstrProf::Summary::Entry &Ent = SummaryData->getEntry(I);
      DetailedSummary.emplace_back((uint32_t)Ent.Cutoff, Ent.MinBlockCount,
                                   Ent.NumBlocks);
    }
    // initialize InstrProfSummary using the SummaryData from disk.
    this->Summary = llvm::make_unique<ProfileSummary>(
        ProfileSummary::PSK_Instr, DetailedSummary,
        SummaryData->get(Summary::TotalBlockCount),
        SummaryData->get(Summary::MaxBlockCount),
        SummaryData->get(Summary::MaxInternalBlockCount),
        SummaryData->get(Summary::MaxFunctionCount),
        SummaryData->get(Summary::TotalNumBlocks),
        SummaryData->get(Summary::TotalNumFunctions));
    return Cur + SummarySize;
  } else {
    // For older version of profile data, we need to compute on the fly:
    using namespace IndexedInstrProf;
    InstrProfSummaryBuilder Builder(ProfileSummaryBuilder::DefaultCutoffs);
    // FIXME: This only computes an empty summary. Need to call addRecord for
    // all InstrProfRecords to get the correct summary.
    this->Summary = Builder.getSummary();
    return Cur;
  }
}

Error IndexedInstrProfReader::readHeader() {
  const unsigned char *Start =
      (const unsigned char *)DataBuffer->getBufferStart();
  const unsigned char *Cur = Start;
  if ((const unsigned char *)DataBuffer->getBufferEnd() - Cur < 24)
    return error(instrprof_error::truncated);

  using namespace support;

  auto *Header = reinterpret_cast<const IndexedInstrProf::Header *>(Cur);
  Cur += sizeof(IndexedInstrProf::Header);

  // Check the magic number.
  uint64_t Magic = endian::byte_swap<uint64_t, little>(Header->Magic);
  if (Magic != IndexedInstrProf::Magic)
    return error(instrprof_error::bad_magic);

  // Read the version.
  uint64_t FormatVersion = endian::byte_swap<uint64_t, little>(Header->Version);
  if (GET_VERSION(FormatVersion) >
      IndexedInstrProf::ProfVersion::CurrentVersion)
    return error(instrprof_error::unsupported_version);

  Cur = readSummary((IndexedInstrProf::ProfVersion)FormatVersion, Cur);

  // Read the hash type and start offset.
  IndexedInstrProf::HashT HashType = static_cast<IndexedInstrProf::HashT>(
      endian::byte_swap<uint64_t, little>(Header->HashType));
  if (HashType > IndexedInstrProf::HashT::Last)
    return error(instrprof_error::unsupported_hash_type);

  uint64_t HashOffset = endian::byte_swap<uint64_t, little>(Header->HashOffset);

  // The rest of the file is an on disk hash table.
  InstrProfReaderIndexBase *IndexPtr = nullptr;
  IndexPtr = new InstrProfReaderIndex<OnDiskHashTableImplV3>(
      Start + HashOffset, Cur, Start, HashType, FormatVersion);
  Index.reset(IndexPtr);
  return success();
}

InstrProfSymtab &IndexedInstrProfReader::getSymtab() {
  if (Symtab.get())
    return *Symtab.get();

  std::unique_ptr<InstrProfSymtab> NewSymtab = make_unique<InstrProfSymtab>();
  Index->populateSymtab(*NewSymtab.get());

  Symtab = std::move(NewSymtab);
  return *Symtab.get();
}

Expected<InstrProfRecord>
IndexedInstrProfReader::getInstrProfRecord(StringRef FuncName,
                                           uint64_t FuncHash) {
  ArrayRef<InstrProfRecord> Data;
  Error Err = Index->getRecords(FuncName, Data);
  if (Err)
    return std::move(Err);
  // Found it. Look for counters with the right hash.
  for (unsigned I = 0, E = Data.size(); I < E; ++I) {
    // Check for a match and fill the vector if there is one.
    if (Data[I].Hash == FuncHash) {
      return std::move(Data[I]);
    }
  }
  return error(instrprof_error::hash_mismatch);
}

Error IndexedInstrProfReader::getFunctionCounts(StringRef FuncName,
                                                uint64_t FuncHash,
                                                std::vector<uint64_t> &Counts) {
  Expected<InstrProfRecord> Record = getInstrProfRecord(FuncName, FuncHash);
  if (Error E = Record.takeError())
    return error(std::move(E));

  Counts = Record.get().Counts;
  return success();
}

Error IndexedInstrProfReader::readNextRecord(InstrProfRecord &Record) {
  static unsigned RecordIndex = 0;

  ArrayRef<InstrProfRecord> Data;

  Error E = Index->getRecords(Data);
  if (E)
    return error(std::move(E));

  Record = Data[RecordIndex++];
  if (RecordIndex >= Data.size()) {
    Index->advanceToNextKey();
    RecordIndex = 0;
  }
  return success();
}