aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm14/lib/Bitstream/Reader/BitstreamReader.cpp
blob: 28adfe6268f9ab526afa510c9dbe972304c77180 (plain) (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
//===- BitstreamReader.cpp - BitstreamReader implementation ---------------===//
//
// 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
//
//===----------------------------------------------------------------------===//

#include "llvm/Bitstream/BitstreamReader.h"
#include "llvm/ADT/StringRef.h"
#include <cassert>
#include <string>

using namespace llvm;

//===----------------------------------------------------------------------===//
//  BitstreamCursor implementation
//===----------------------------------------------------------------------===//

/// Having read the ENTER_SUBBLOCK abbrevid, enter the block.
Error BitstreamCursor::EnterSubBlock(unsigned BlockID, unsigned *NumWordsP) {
  // Save the current block's state on BlockScope.
  BlockScope.push_back(Block(CurCodeSize));
  BlockScope.back().PrevAbbrevs.swap(CurAbbrevs);

  // Add the abbrevs specific to this block to the CurAbbrevs list.
  if (BlockInfo) {
    if (const BitstreamBlockInfo::BlockInfo *Info =
            BlockInfo->getBlockInfo(BlockID)) {
      llvm::append_range(CurAbbrevs, Info->Abbrevs);
    }
  }

  // Get the codesize of this block.
  Expected<uint32_t> MaybeVBR = ReadVBR(bitc::CodeLenWidth);
  if (!MaybeVBR)
    return MaybeVBR.takeError();
  CurCodeSize = MaybeVBR.get();

  if (CurCodeSize > MaxChunkSize)
    return llvm::createStringError(
        std::errc::illegal_byte_sequence,
        "can't read more than %zu at a time, trying to read %u", +MaxChunkSize,
        CurCodeSize);

  SkipToFourByteBoundary();
  Expected<word_t> MaybeNum = Read(bitc::BlockSizeWidth);
  if (!MaybeNum)
    return MaybeNum.takeError();
  word_t NumWords = MaybeNum.get();
  if (NumWordsP)
    *NumWordsP = NumWords;

  if (CurCodeSize == 0)
    return llvm::createStringError(
        std::errc::illegal_byte_sequence,
        "can't enter sub-block: current code size is 0");
  if (AtEndOfStream())
    return llvm::createStringError(
        std::errc::illegal_byte_sequence,
        "can't enter sub block: already at end of stream");

  return Error::success();
}

static Expected<uint64_t> readAbbreviatedField(BitstreamCursor &Cursor,
                                               const BitCodeAbbrevOp &Op) {
  assert(!Op.isLiteral() && "Not to be used with literals!");

  // Decode the value as we are commanded.
  switch (Op.getEncoding()) {
  case BitCodeAbbrevOp::Array:
  case BitCodeAbbrevOp::Blob:
    llvm_unreachable("Should not reach here");
  case BitCodeAbbrevOp::Fixed:
    assert((unsigned)Op.getEncodingData() <= Cursor.MaxChunkSize);
    return Cursor.Read((unsigned)Op.getEncodingData());
  case BitCodeAbbrevOp::VBR:
    assert((unsigned)Op.getEncodingData() <= Cursor.MaxChunkSize);
    return Cursor.ReadVBR64((unsigned)Op.getEncodingData());
  case BitCodeAbbrevOp::Char6:
    if (Expected<unsigned> Res = Cursor.Read(6))
      return BitCodeAbbrevOp::DecodeChar6(Res.get());
    else
      return Res.takeError();
  }
  llvm_unreachable("invalid abbreviation encoding");
}

/// skipRecord - Read the current record and discard it.
Expected<unsigned> BitstreamCursor::skipRecord(unsigned AbbrevID) {
  // Skip unabbreviated records by reading past their entries.
  if (AbbrevID == bitc::UNABBREV_RECORD) {
    Expected<uint32_t> MaybeCode = ReadVBR(6);
    if (!MaybeCode)
      return MaybeCode.takeError();
    unsigned Code = MaybeCode.get();
    Expected<uint32_t> MaybeVBR = ReadVBR(6);
    if (!MaybeVBR)
      return MaybeVBR.get();
    unsigned NumElts = MaybeVBR.get();
    for (unsigned i = 0; i != NumElts; ++i)
      if (Expected<uint64_t> Res = ReadVBR64(6))
        ; // Skip!
      else
        return Res.takeError();
    return Code;
  }

  const BitCodeAbbrev *Abbv = getAbbrev(AbbrevID);
  const BitCodeAbbrevOp &CodeOp = Abbv->getOperandInfo(0);
  unsigned Code;
  if (CodeOp.isLiteral())
    Code = CodeOp.getLiteralValue();
  else {
    if (CodeOp.getEncoding() == BitCodeAbbrevOp::Array ||
        CodeOp.getEncoding() == BitCodeAbbrevOp::Blob)
      return llvm::createStringError(
          std::errc::illegal_byte_sequence,
          "Abbreviation starts with an Array or a Blob");
    Expected<uint64_t> MaybeCode = readAbbreviatedField(*this, CodeOp);
    if (!MaybeCode)
      return MaybeCode.takeError();
    Code = MaybeCode.get();
  }

  for (unsigned i = 1, e = Abbv->getNumOperandInfos(); i < e; ++i) {
    const BitCodeAbbrevOp &Op = Abbv->getOperandInfo(i);
    if (Op.isLiteral())
      continue;

    if (Op.getEncoding() != BitCodeAbbrevOp::Array &&
        Op.getEncoding() != BitCodeAbbrevOp::Blob) {
      if (Expected<uint64_t> MaybeField = readAbbreviatedField(*this, Op))
        continue;
      else
        return MaybeField.takeError();
    }

    if (Op.getEncoding() == BitCodeAbbrevOp::Array) {
      // Array case.  Read the number of elements as a vbr6.
      Expected<uint32_t> MaybeNum = ReadVBR(6);
      if (!MaybeNum)
        return MaybeNum.takeError();
      unsigned NumElts = MaybeNum.get();

      // Get the element encoding.
      assert(i+2 == e && "array op not second to last?");
      const BitCodeAbbrevOp &EltEnc = Abbv->getOperandInfo(++i);

      // Read all the elements.
      // Decode the value as we are commanded.
      switch (EltEnc.getEncoding()) {
      default:
        report_fatal_error("Array element type can't be an Array or a Blob");
      case BitCodeAbbrevOp::Fixed:
        assert((unsigned)EltEnc.getEncodingData() <= MaxChunkSize);
        if (Error Err =
                JumpToBit(GetCurrentBitNo() + static_cast<uint64_t>(NumElts) *
                                                  EltEnc.getEncodingData()))
          return std::move(Err);
        break;
      case BitCodeAbbrevOp::VBR:
        assert((unsigned)EltEnc.getEncodingData() <= MaxChunkSize);
        for (; NumElts; --NumElts)
          if (Expected<uint64_t> Res =
                  ReadVBR64((unsigned)EltEnc.getEncodingData()))
            ; // Skip!
          else
            return Res.takeError();
        break;
      case BitCodeAbbrevOp::Char6:
        if (Error Err = JumpToBit(GetCurrentBitNo() + NumElts * 6))
          return std::move(Err);
        break;
      }
      continue;
    }

    assert(Op.getEncoding() == BitCodeAbbrevOp::Blob);
    // Blob case.  Read the number of bytes as a vbr6.
    Expected<uint32_t> MaybeNum = ReadVBR(6);
    if (!MaybeNum)
      return MaybeNum.takeError();
    unsigned NumElts = MaybeNum.get();
    SkipToFourByteBoundary();  // 32-bit alignment

    // Figure out where the end of this blob will be including tail padding.
    const size_t NewEnd = GetCurrentBitNo() + alignTo(NumElts, 4) * 8;

    // If this would read off the end of the bitcode file, just set the
    // record to empty and return.
    if (!canSkipToPos(NewEnd/8)) {
      skipToEnd();
      break;
    }

    // Skip over the blob.
    if (Error Err = JumpToBit(NewEnd))
      return std::move(Err);
  }
  return Code;
}

Expected<unsigned> BitstreamCursor::readRecord(unsigned AbbrevID,
                                               SmallVectorImpl<uint64_t> &Vals,
                                               StringRef *Blob) {
  if (AbbrevID == bitc::UNABBREV_RECORD) {
    Expected<uint32_t> MaybeCode = ReadVBR(6);
    if (!MaybeCode)
      return MaybeCode.takeError();
    uint32_t Code = MaybeCode.get();
    Expected<uint32_t> MaybeNumElts = ReadVBR(6);
    if (!MaybeNumElts)
      return MaybeNumElts.takeError();
    uint32_t NumElts = MaybeNumElts.get();
    Vals.reserve(Vals.size() + NumElts);

    for (unsigned i = 0; i != NumElts; ++i)
      if (Expected<uint64_t> MaybeVal = ReadVBR64(6))
        Vals.push_back(MaybeVal.get());
      else
        return MaybeVal.takeError();
    return Code;
  }

  const BitCodeAbbrev *Abbv = getAbbrev(AbbrevID);

  // Read the record code first.
  assert(Abbv->getNumOperandInfos() != 0 && "no record code in abbreviation?");
  const BitCodeAbbrevOp &CodeOp = Abbv->getOperandInfo(0);
  unsigned Code;
  if (CodeOp.isLiteral())
    Code = CodeOp.getLiteralValue();
  else {
    if (CodeOp.getEncoding() == BitCodeAbbrevOp::Array ||
        CodeOp.getEncoding() == BitCodeAbbrevOp::Blob)
      report_fatal_error("Abbreviation starts with an Array or a Blob");
    if (Expected<uint64_t> MaybeCode = readAbbreviatedField(*this, CodeOp))
      Code = MaybeCode.get();
    else
      return MaybeCode.takeError();
  }

  for (unsigned i = 1, e = Abbv->getNumOperandInfos(); i != e; ++i) {
    const BitCodeAbbrevOp &Op = Abbv->getOperandInfo(i);
    if (Op.isLiteral()) {
      Vals.push_back(Op.getLiteralValue());
      continue;
    }

    if (Op.getEncoding() != BitCodeAbbrevOp::Array &&
        Op.getEncoding() != BitCodeAbbrevOp::Blob) {
      if (Expected<uint64_t> MaybeVal = readAbbreviatedField(*this, Op))
        Vals.push_back(MaybeVal.get());
      else
        return MaybeVal.takeError();
      continue;
    }

    if (Op.getEncoding() == BitCodeAbbrevOp::Array) {
      // Array case.  Read the number of elements as a vbr6.
      Expected<uint32_t> MaybeNumElts = ReadVBR(6);
      if (!MaybeNumElts)
        return MaybeNumElts.takeError();
      uint32_t NumElts = MaybeNumElts.get();
      Vals.reserve(Vals.size() + NumElts);

      // Get the element encoding.
      if (i + 2 != e)
        report_fatal_error("Array op not second to last");
      const BitCodeAbbrevOp &EltEnc = Abbv->getOperandInfo(++i);
      if (!EltEnc.isEncoding())
        report_fatal_error(
            "Array element type has to be an encoding of a type");

      // Read all the elements.
      switch (EltEnc.getEncoding()) {
      default:
        report_fatal_error("Array element type can't be an Array or a Blob");
      case BitCodeAbbrevOp::Fixed:
        for (; NumElts; --NumElts)
          if (Expected<SimpleBitstreamCursor::word_t> MaybeVal =
                  Read((unsigned)EltEnc.getEncodingData()))
            Vals.push_back(MaybeVal.get());
          else
            return MaybeVal.takeError();
        break;
      case BitCodeAbbrevOp::VBR:
        for (; NumElts; --NumElts)
          if (Expected<uint64_t> MaybeVal =
                  ReadVBR64((unsigned)EltEnc.getEncodingData()))
            Vals.push_back(MaybeVal.get());
          else
            return MaybeVal.takeError();
        break;
      case BitCodeAbbrevOp::Char6:
        for (; NumElts; --NumElts)
          if (Expected<SimpleBitstreamCursor::word_t> MaybeVal = Read(6))
            Vals.push_back(BitCodeAbbrevOp::DecodeChar6(MaybeVal.get()));
          else
            return MaybeVal.takeError();
      }
      continue;
    }

    assert(Op.getEncoding() == BitCodeAbbrevOp::Blob);
    // Blob case.  Read the number of bytes as a vbr6.
    Expected<uint32_t> MaybeNumElts = ReadVBR(6);
    if (!MaybeNumElts)
      return MaybeNumElts.takeError();
    uint32_t NumElts = MaybeNumElts.get();
    SkipToFourByteBoundary();  // 32-bit alignment

    // Figure out where the end of this blob will be including tail padding.
    size_t CurBitPos = GetCurrentBitNo();
    const size_t NewEnd = CurBitPos + alignTo(NumElts, 4) * 8;

    // If this would read off the end of the bitcode file, just set the
    // record to empty and return.
    if (!canSkipToPos(NewEnd/8)) {
      Vals.append(NumElts, 0);
      skipToEnd();
      break;
    }

    // Otherwise, inform the streamer that we need these bytes in memory.  Skip
    // over tail padding first, in case jumping to NewEnd invalidates the Blob
    // pointer.
    if (Error Err = JumpToBit(NewEnd))
      return std::move(Err);
    const char *Ptr = (const char *)getPointerToBit(CurBitPos, NumElts);

    // If we can return a reference to the data, do so to avoid copying it.
    if (Blob) {
      *Blob = StringRef(Ptr, NumElts);
    } else {
      // Otherwise, unpack into Vals with zero extension.
      auto *UPtr = reinterpret_cast<const unsigned char *>(Ptr);
      Vals.append(UPtr, UPtr + NumElts);
    }
  }

  return Code;
}

Error BitstreamCursor::ReadAbbrevRecord() {
  auto Abbv = std::make_shared<BitCodeAbbrev>();
  Expected<uint32_t> MaybeNumOpInfo = ReadVBR(5);
  if (!MaybeNumOpInfo)
    return MaybeNumOpInfo.takeError();
  unsigned NumOpInfo = MaybeNumOpInfo.get();
  for (unsigned i = 0; i != NumOpInfo; ++i) {
    Expected<word_t> MaybeIsLiteral = Read(1);
    if (!MaybeIsLiteral)
      return MaybeIsLiteral.takeError();
    bool IsLiteral = MaybeIsLiteral.get();
    if (IsLiteral) {
      Expected<uint64_t> MaybeOp = ReadVBR64(8);
      if (!MaybeOp)
        return MaybeOp.takeError();
      Abbv->Add(BitCodeAbbrevOp(MaybeOp.get()));
      continue;
    }

    Expected<word_t> MaybeEncoding = Read(3);
    if (!MaybeEncoding)
      return MaybeEncoding.takeError();
    BitCodeAbbrevOp::Encoding E =
        (BitCodeAbbrevOp::Encoding)MaybeEncoding.get();
    if (BitCodeAbbrevOp::hasEncodingData(E)) {
      Expected<uint64_t> MaybeData = ReadVBR64(5);
      if (!MaybeData)
        return MaybeData.takeError();
      uint64_t Data = MaybeData.get();

      // As a special case, handle fixed(0) (i.e., a fixed field with zero bits)
      // and vbr(0) as a literal zero.  This is decoded the same way, and avoids
      // a slow path in Read() to have to handle reading zero bits.
      if ((E == BitCodeAbbrevOp::Fixed || E == BitCodeAbbrevOp::VBR) &&
          Data == 0) {
        Abbv->Add(BitCodeAbbrevOp(0));
        continue;
      }

      if ((E == BitCodeAbbrevOp::Fixed || E == BitCodeAbbrevOp::VBR) &&
          Data > MaxChunkSize)
        report_fatal_error(
            "Fixed or VBR abbrev record with size > MaxChunkData");

      Abbv->Add(BitCodeAbbrevOp(E, Data));
    } else
      Abbv->Add(BitCodeAbbrevOp(E));
  }

  if (Abbv->getNumOperandInfos() == 0)
    report_fatal_error("Abbrev record with no operands");
  CurAbbrevs.push_back(std::move(Abbv));

  return Error::success();
}

Expected<Optional<BitstreamBlockInfo>>
BitstreamCursor::ReadBlockInfoBlock(bool ReadBlockInfoNames) {
  if (llvm::Error Err = EnterSubBlock(bitc::BLOCKINFO_BLOCK_ID))
    return std::move(Err);

  BitstreamBlockInfo NewBlockInfo;

  SmallVector<uint64_t, 64> Record;
  BitstreamBlockInfo::BlockInfo *CurBlockInfo = nullptr;

  // Read all the records for this module.
  while (true) {
    Expected<BitstreamEntry> MaybeEntry =
        advanceSkippingSubblocks(AF_DontAutoprocessAbbrevs);
    if (!MaybeEntry)
      return MaybeEntry.takeError();
    BitstreamEntry Entry = MaybeEntry.get();

    switch (Entry.Kind) {
    case llvm::BitstreamEntry::SubBlock: // Handled for us already.
    case llvm::BitstreamEntry::Error:
      return None;
    case llvm::BitstreamEntry::EndBlock:
      return std::move(NewBlockInfo);
    case llvm::BitstreamEntry::Record:
      // The interesting case.
      break;
    }

    // Read abbrev records, associate them with CurBID.
    if (Entry.ID == bitc::DEFINE_ABBREV) {
      if (!CurBlockInfo) return None;
      if (Error Err = ReadAbbrevRecord())
        return std::move(Err);

      // ReadAbbrevRecord installs the abbrev in CurAbbrevs.  Move it to the
      // appropriate BlockInfo.
      CurBlockInfo->Abbrevs.push_back(std::move(CurAbbrevs.back()));
      CurAbbrevs.pop_back();
      continue;
    }

    // Read a record.
    Record.clear();
    Expected<unsigned> MaybeBlockInfo = readRecord(Entry.ID, Record);
    if (!MaybeBlockInfo)
      return MaybeBlockInfo.takeError();
    switch (MaybeBlockInfo.get()) {
    default:
      break; // Default behavior, ignore unknown content.
    case bitc::BLOCKINFO_CODE_SETBID:
      if (Record.size() < 1)
        return None;
      CurBlockInfo = &NewBlockInfo.getOrCreateBlockInfo((unsigned)Record[0]);
      break;
    case bitc::BLOCKINFO_CODE_BLOCKNAME: {
      if (!CurBlockInfo)
        return None;
      if (!ReadBlockInfoNames)
        break; // Ignore name.
      CurBlockInfo->Name = std::string(Record.begin(), Record.end());
      break;
    }
      case bitc::BLOCKINFO_CODE_SETRECORDNAME: {
        if (!CurBlockInfo) return None;
        if (!ReadBlockInfoNames)
          break; // Ignore name.
        CurBlockInfo->RecordNames.emplace_back(
            (unsigned)Record[0], std::string(Record.begin() + 1, Record.end()));
        break;
      }
      }
  }
}