Training courses

Kernel and Embedded Linux

Bootlin training courses

Embedded Linux, kernel,
Yocto Project, Buildroot, real-time,
graphics, boot time, debugging...

Bootlin logo

Elixir Cross Referencer

   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
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
//===-- combined.h ----------------------------------------------*- 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
//
//===----------------------------------------------------------------------===//

#ifndef SCUDO_COMBINED_H_
#define SCUDO_COMBINED_H_

#include "chunk.h"
#include "common.h"
#include "flags.h"
#include "flags_parser.h"
#include "local_cache.h"
#include "memtag.h"
#include "quarantine.h"
#include "report.h"
#include "secondary.h"
#include "stack_depot.h"
#include "string_utils.h"
#include "tsd.h"

#include "scudo/interface.h"

#ifdef GWP_ASAN_HOOKS
#include "gwp_asan/guarded_pool_allocator.h"
#include "gwp_asan/optional/backtrace.h"
#include "gwp_asan/optional/segv_handler.h"
#endif // GWP_ASAN_HOOKS

extern "C" inline void EmptyCallback() {}

#ifdef HAVE_ANDROID_UNSAFE_FRAME_POINTER_CHASE
// This function is not part of the NDK so it does not appear in any public
// header files. We only declare/use it when targeting the platform.
extern "C" size_t android_unsafe_frame_pointer_chase(scudo::uptr *buf,
                                                     size_t num_entries);
#endif

namespace scudo {

enum class Option { ReleaseInterval };

template <class Params, void (*PostInitCallback)(void) = EmptyCallback>
class Allocator {
public:
  using PrimaryT = typename Params::Primary;
  using CacheT = typename PrimaryT::CacheT;
  typedef Allocator<Params, PostInitCallback> ThisT;
  typedef typename Params::template TSDRegistryT<ThisT> TSDRegistryT;

  void callPostInitCallback() {
    static pthread_once_t OnceControl = PTHREAD_ONCE_INIT;
    pthread_once(&OnceControl, PostInitCallback);
  }

  struct QuarantineCallback {
    explicit QuarantineCallback(ThisT &Instance, CacheT &LocalCache)
        : Allocator(Instance), Cache(LocalCache) {}

    // Chunk recycling function, returns a quarantined chunk to the backend,
    // first making sure it hasn't been tampered with.
    void recycle(void *Ptr) {
      Chunk::UnpackedHeader Header;
      Chunk::loadHeader(Allocator.Cookie, Ptr, &Header);
      if (UNLIKELY(Header.State != Chunk::State::Quarantined))
        reportInvalidChunkState(AllocatorAction::Recycling, Ptr);

      Chunk::UnpackedHeader NewHeader = Header;
      NewHeader.State = Chunk::State::Available;
      Chunk::compareExchangeHeader(Allocator.Cookie, Ptr, &NewHeader, &Header);

      void *BlockBegin = Allocator::getBlockBegin(Ptr, &NewHeader);
      const uptr ClassId = NewHeader.ClassId;
      if (LIKELY(ClassId))
        Cache.deallocate(ClassId, BlockBegin);
      else
        Allocator.Secondary.deallocate(BlockBegin);
    }

    // We take a shortcut when allocating a quarantine batch by working with the
    // appropriate class ID instead of using Size. The compiler should optimize
    // the class ID computation and work with the associated cache directly.
    void *allocate(UNUSED uptr Size) {
      const uptr QuarantineClassId = SizeClassMap::getClassIdBySize(
          sizeof(QuarantineBatch) + Chunk::getHeaderSize());
      void *Ptr = Cache.allocate(QuarantineClassId);
      // Quarantine batch allocation failure is fatal.
      if (UNLIKELY(!Ptr))
        reportOutOfMemory(SizeClassMap::getSizeByClassId(QuarantineClassId));

      Ptr = reinterpret_cast<void *>(reinterpret_cast<uptr>(Ptr) +
                                     Chunk::getHeaderSize());
      Chunk::UnpackedHeader Header = {};
      Header.ClassId = QuarantineClassId & Chunk::ClassIdMask;
      Header.SizeOrUnusedBytes = sizeof(QuarantineBatch);
      Header.State = Chunk::State::Allocated;
      Chunk::storeHeader(Allocator.Cookie, Ptr, &Header);

      return Ptr;
    }

    void deallocate(void *Ptr) {
      const uptr QuarantineClassId = SizeClassMap::getClassIdBySize(
          sizeof(QuarantineBatch) + Chunk::getHeaderSize());
      Chunk::UnpackedHeader Header;
      Chunk::loadHeader(Allocator.Cookie, Ptr, &Header);

      if (UNLIKELY(Header.State != Chunk::State::Allocated))
        reportInvalidChunkState(AllocatorAction::Deallocating, Ptr);
      DCHECK_EQ(Header.ClassId, QuarantineClassId);
      DCHECK_EQ(Header.Offset, 0);
      DCHECK_EQ(Header.SizeOrUnusedBytes, sizeof(QuarantineBatch));

      Chunk::UnpackedHeader NewHeader = Header;
      NewHeader.State = Chunk::State::Available;
      Chunk::compareExchangeHeader(Allocator.Cookie, Ptr, &NewHeader, &Header);
      Cache.deallocate(QuarantineClassId,
                       reinterpret_cast<void *>(reinterpret_cast<uptr>(Ptr) -
                                                Chunk::getHeaderSize()));
    }

  private:
    ThisT &Allocator;
    CacheT &Cache;
  };

  typedef GlobalQuarantine<QuarantineCallback, void> QuarantineT;
  typedef typename QuarantineT::CacheT QuarantineCacheT;

  void initLinkerInitialized() {
    performSanityChecks();

    // Check if hardware CRC32 is supported in the binary and by the platform,
    // if so, opt for the CRC32 hardware version of the checksum.
    if (&computeHardwareCRC32 && hasHardwareCRC32())
      HashAlgorithm = Checksum::HardwareCRC32;

    if (UNLIKELY(!getRandom(&Cookie, sizeof(Cookie))))
      Cookie = static_cast<u32>(getMonotonicTime() ^
                                (reinterpret_cast<uptr>(this) >> 4));

    initFlags();
    reportUnrecognizedFlags();

    // Store some flags locally.
    Options.MayReturnNull = getFlags()->may_return_null;
    Options.FillContents =
        getFlags()->zero_contents
            ? ZeroFill
            : (getFlags()->pattern_fill_contents ? PatternOrZeroFill : NoFill);
    Options.DeallocTypeMismatch = getFlags()->dealloc_type_mismatch;
    Options.DeleteSizeMismatch = getFlags()->delete_size_mismatch;
    Options.TrackAllocationStacks = false;
    Options.QuarantineMaxChunkSize =
        static_cast<u32>(getFlags()->quarantine_max_chunk_size);

    Stats.initLinkerInitialized();
    const s32 ReleaseToOsIntervalMs = getFlags()->release_to_os_interval_ms;
    Primary.initLinkerInitialized(ReleaseToOsIntervalMs);
    Secondary.initLinkerInitialized(&Stats, ReleaseToOsIntervalMs);

    Quarantine.init(
        static_cast<uptr>(getFlags()->quarantine_size_kb << 10),
        static_cast<uptr>(getFlags()->thread_local_quarantine_size_kb << 10));
  }

  // Initialize the embedded GWP-ASan instance. Requires the main allocator to
  // be functional, best called from PostInitCallback.
  void initGwpAsan() {
#ifdef GWP_ASAN_HOOKS
    gwp_asan::options::Options Opt;
    Opt.Enabled = getFlags()->GWP_ASAN_Enabled;
    // Bear in mind - Scudo has its own alignment guarantees that are strictly
    // enforced. Scudo exposes the same allocation function for everything from
    // malloc() to posix_memalign, so in general this flag goes unused, as Scudo
    // will always ask GWP-ASan for an aligned amount of bytes.
    Opt.PerfectlyRightAlign = getFlags()->GWP_ASAN_PerfectlyRightAlign;
    Opt.MaxSimultaneousAllocations =
        getFlags()->GWP_ASAN_MaxSimultaneousAllocations;
    Opt.SampleRate = getFlags()->GWP_ASAN_SampleRate;
    Opt.InstallSignalHandlers = getFlags()->GWP_ASAN_InstallSignalHandlers;
    // Embedded GWP-ASan is locked through the Scudo atfork handler (via
    // Allocator::disable calling GWPASan.disable). Disable GWP-ASan's atfork
    // handler.
    Opt.InstallForkHandlers = false;
    Opt.Backtrace = gwp_asan::options::getBacktraceFunction();
    GuardedAlloc.init(Opt);

    if (Opt.InstallSignalHandlers)
      gwp_asan::crash_handler::installSignalHandlers(
          &GuardedAlloc, Printf, gwp_asan::options::getPrintBacktraceFunction(),
          Opt.Backtrace);
#endif // GWP_ASAN_HOOKS
  }

  void reset() { memset(this, 0, sizeof(*this)); }

  void unmapTestOnly() {
    TSDRegistry.unmapTestOnly();
    Primary.unmapTestOnly();
#ifdef GWP_ASAN_HOOKS
    if (getFlags()->GWP_ASAN_InstallSignalHandlers)
      gwp_asan::crash_handler::uninstallSignalHandlers();
    GuardedAlloc.uninitTestOnly();
#endif // GWP_ASAN_HOOKS
  }

  TSDRegistryT *getTSDRegistry() { return &TSDRegistry; }

  // The Cache must be provided zero-initialized.
  void initCache(CacheT *Cache) {
    Cache->initLinkerInitialized(&Stats, &Primary);
  }

  // Release the resources used by a TSD, which involves:
  // - draining the local quarantine cache to the global quarantine;
  // - releasing the cached pointers back to the Primary;
  // - unlinking the local stats from the global ones (destroying the cache does
  //   the last two items).
  void commitBack(TSD<ThisT> *TSD) {
    Quarantine.drain(&TSD->QuarantineCache,
                     QuarantineCallback(*this, TSD->Cache));
    TSD->Cache.destroy(&Stats);
  }

  ALWAYS_INLINE void *untagPointerMaybe(void *Ptr) {
    if (Primary.SupportsMemoryTagging)
      return reinterpret_cast<void *>(
          untagPointer(reinterpret_cast<uptr>(Ptr)));
    return Ptr;
  }

  NOINLINE u32 collectStackTrace() {
#ifdef HAVE_ANDROID_UNSAFE_FRAME_POINTER_CHASE
    // Discard collectStackTrace() frame and allocator function frame.
    constexpr uptr DiscardFrames = 2;
    uptr Stack[MaxTraceSize + DiscardFrames];
    uptr Size =
        android_unsafe_frame_pointer_chase(Stack, MaxTraceSize + DiscardFrames);
    Size = Min<uptr>(Size, MaxTraceSize + DiscardFrames);
    return Depot.insert(Stack + Min<uptr>(DiscardFrames, Size), Stack + Size);
#else
    return 0;
#endif
  }

  NOINLINE void *allocate(uptr Size, Chunk::Origin Origin,
                          uptr Alignment = MinAlignment,
                          bool ZeroContents = false) {
    initThreadMaybe();

#ifdef GWP_ASAN_HOOKS
    if (UNLIKELY(GuardedAlloc.shouldSample())) {
      if (void *Ptr = GuardedAlloc.allocate(roundUpTo(Size, Alignment)))
        return Ptr;
    }
#endif // GWP_ASAN_HOOKS

    FillContentsMode FillContents =
        ZeroContents ? ZeroFill : Options.FillContents;

    if (UNLIKELY(Alignment > MaxAlignment)) {
      if (Options.MayReturnNull)
        return nullptr;
      reportAlignmentTooBig(Alignment, MaxAlignment);
    }
    if (Alignment < MinAlignment)
      Alignment = MinAlignment;

    // If the requested size happens to be 0 (more common than you might think),
    // allocate MinAlignment bytes on top of the header. Then add the extra
    // bytes required to fulfill the alignment requirements: we allocate enough
    // to be sure that there will be an address in the block that will satisfy
    // the alignment.
    const uptr NeededSize =
        roundUpTo(Size, MinAlignment) +
        ((Alignment > MinAlignment) ? Alignment : Chunk::getHeaderSize());

    // Takes care of extravagantly large sizes as well as integer overflows.
    static_assert(MaxAllowedMallocSize < UINTPTR_MAX - MaxAlignment, "");
    if (UNLIKELY(Size >= MaxAllowedMallocSize)) {
      if (Options.MayReturnNull)
        return nullptr;
      reportAllocationSizeTooBig(Size, NeededSize, MaxAllowedMallocSize);
    }
    DCHECK_LE(Size, NeededSize);

    void *Block = nullptr;
    uptr ClassId = 0;
    uptr SecondaryBlockEnd;
    if (LIKELY(PrimaryT::canAllocate(NeededSize))) {
      ClassId = SizeClassMap::getClassIdBySize(NeededSize);
      DCHECK_NE(ClassId, 0U);
      bool UnlockRequired;
      auto *TSD = TSDRegistry.getTSDAndLock(&UnlockRequired);
      Block = TSD->Cache.allocate(ClassId);
      // If the allocation failed, the most likely reason with a 32-bit primary
      // is the region being full. In that event, retry in each successively
      // larger class until it fits. If it fails to fit in the largest class,
      // fallback to the Secondary.
      if (UNLIKELY(!Block)) {
        while (ClassId < SizeClassMap::LargestClassId) {
          Block = TSD->Cache.allocate(++ClassId);
          if (LIKELY(Block)) {
            break;
          }
        }
        if (UNLIKELY(!Block)) {
          ClassId = 0;
        }
      }
      if (UnlockRequired)
        TSD->unlock();
    }
    if (UNLIKELY(ClassId == 0))
      Block = Secondary.allocate(NeededSize, Alignment, &SecondaryBlockEnd,
                                 FillContents);

    if (UNLIKELY(!Block)) {
      if (Options.MayReturnNull)
        return nullptr;
      reportOutOfMemory(NeededSize);
    }

    const uptr BlockUptr = reinterpret_cast<uptr>(Block);
    const uptr UnalignedUserPtr = BlockUptr + Chunk::getHeaderSize();
    const uptr UserPtr = roundUpTo(UnalignedUserPtr, Alignment);

    void *Ptr = reinterpret_cast<void *>(UserPtr);
    void *TaggedPtr = Ptr;
    if (ClassId) {
      // We only need to zero or tag the contents for Primary backed
      // allocations. We only set tags for primary allocations in order to avoid
      // faulting potentially large numbers of pages for large secondary
      // allocations. We assume that guard pages are enough to protect these
      // allocations.
      //
      // FIXME: When the kernel provides a way to set the background tag of a
      // mapping, we should be able to tag secondary allocations as well.
      //
      // When memory tagging is enabled, zeroing the contents is done as part of
      // setting the tag.
      if (UNLIKELY(useMemoryTagging())) {
        uptr PrevUserPtr;
        Chunk::UnpackedHeader Header;
        const uptr BlockEnd = BlockUptr + PrimaryT::getSizeByClassId(ClassId);
        // If possible, try to reuse the UAF tag that was set by deallocate().
        // For simplicity, only reuse tags if we have the same start address as
        // the previous allocation. This handles the majority of cases since
        // most allocations will not be more aligned than the minimum alignment.
        //
        // We need to handle situations involving reclaimed chunks, and retag
        // the reclaimed portions if necessary. In the case where the chunk is
        // fully reclaimed, the chunk's header will be zero, which will trigger
        // the code path for new mappings and invalid chunks that prepares the
        // chunk from scratch. There are three possibilities for partial
        // reclaiming:
        //
        // (1) Header was reclaimed, data was partially reclaimed.
        // (2) Header was not reclaimed, all data was reclaimed (e.g. because
        //     data started on a page boundary).
        // (3) Header was not reclaimed, data was partially reclaimed.
        //
        // Case (1) will be handled in the same way as for full reclaiming,
        // since the header will be zero.
        //
        // We can detect case (2) by loading the tag from the start
        // of the chunk. If it is zero, it means that either all data was
        // reclaimed (since we never use zero as the chunk tag), or that the
        // previous allocation was of size zero. Either way, we need to prepare
        // a new chunk from scratch.
        //
        // We can detect case (3) by moving to the next page (if covered by the
        // chunk) and loading the tag of its first granule. If it is zero, it
        // means that all following pages may need to be retagged. On the other
        // hand, if it is nonzero, we can assume that all following pages are
        // still tagged, according to the logic that if any of the pages
        // following the next page were reclaimed, the next page would have been
        // reclaimed as well.
        uptr TaggedUserPtr;
        if (getChunkFromBlock(BlockUptr, &PrevUserPtr, &Header) &&
            PrevUserPtr == UserPtr &&
            (TaggedUserPtr = loadTag(UserPtr)) != UserPtr) {
          uptr PrevEnd = TaggedUserPtr + Header.SizeOrUnusedBytes;
          const uptr NextPage = roundUpTo(TaggedUserPtr, getPageSizeCached());
          if (NextPage < PrevEnd && loadTag(NextPage) != NextPage)
            PrevEnd = NextPage;
          TaggedPtr = reinterpret_cast<void *>(TaggedUserPtr);
          resizeTaggedChunk(PrevEnd, TaggedUserPtr + Size, BlockEnd);
          if (Size) {
            // Clear any stack metadata that may have previously been stored in
            // the chunk data.
            memset(TaggedPtr, 0, archMemoryTagGranuleSize());
          }
        } else {
          TaggedPtr = prepareTaggedChunk(Ptr, Size, BlockEnd);
        }
        storeAllocationStackMaybe(Ptr);
      } else if (UNLIKELY(FillContents != NoFill)) {
        // This condition is not necessarily unlikely, but since memset is
        // costly, we might as well mark it as such.
        memset(Block, FillContents == ZeroFill ? 0 : PatternFillByte,
               PrimaryT::getSizeByClassId(ClassId));
      }
    }

    Chunk::UnpackedHeader Header = {};
    if (UNLIKELY(UnalignedUserPtr != UserPtr)) {
      const uptr Offset = UserPtr - UnalignedUserPtr;
      DCHECK_GE(Offset, 2 * sizeof(u32));
      // The BlockMarker has no security purpose, but is specifically meant for
      // the chunk iteration function that can be used in debugging situations.
      // It is the only situation where we have to locate the start of a chunk
      // based on its block address.
      reinterpret_cast<u32 *>(Block)[0] = BlockMarker;
      reinterpret_cast<u32 *>(Block)[1] = static_cast<u32>(Offset);
      Header.Offset = (Offset >> MinAlignmentLog) & Chunk::OffsetMask;
    }
    Header.ClassId = ClassId & Chunk::ClassIdMask;
    Header.State = Chunk::State::Allocated;
    Header.Origin = Origin & Chunk::OriginMask;
    Header.SizeOrUnusedBytes =
        (ClassId ? Size : SecondaryBlockEnd - (UserPtr + Size)) &
        Chunk::SizeOrUnusedBytesMask;
    Chunk::storeHeader(Cookie, Ptr, &Header);

    if (&__scudo_allocate_hook)
      __scudo_allocate_hook(TaggedPtr, Size);

    return TaggedPtr;
  }

  NOINLINE void deallocate(void *Ptr, Chunk::Origin Origin, uptr DeleteSize = 0,
                           UNUSED uptr Alignment = MinAlignment) {
    // For a deallocation, we only ensure minimal initialization, meaning thread
    // local data will be left uninitialized for now (when using ELF TLS). The
    // fallback cache will be used instead. This is a workaround for a situation
    // where the only heap operation performed in a thread would be a free past
    // the TLS destructors, ending up in initialized thread specific data never
    // being destroyed properly. Any other heap operation will do a full init.
    initThreadMaybe(/*MinimalInit=*/true);

#ifdef GWP_ASAN_HOOKS
    if (UNLIKELY(GuardedAlloc.pointerIsMine(Ptr))) {
      GuardedAlloc.deallocate(Ptr);
      return;
    }
#endif // GWP_ASAN_HOOKS

    if (&__scudo_deallocate_hook)
      __scudo_deallocate_hook(Ptr);

    if (UNLIKELY(!Ptr))
      return;
    if (UNLIKELY(!isAligned(reinterpret_cast<uptr>(Ptr), MinAlignment)))
      reportMisalignedPointer(AllocatorAction::Deallocating, Ptr);

    Ptr = untagPointerMaybe(Ptr);

    Chunk::UnpackedHeader Header;
    Chunk::loadHeader(Cookie, Ptr, &Header);

    if (UNLIKELY(Header.State != Chunk::State::Allocated))
      reportInvalidChunkState(AllocatorAction::Deallocating, Ptr);
    if (Options.DeallocTypeMismatch) {
      if (Header.Origin != Origin) {
        // With the exception of memalign'd chunks, that can be still be free'd.
        if (UNLIKELY(Header.Origin != Chunk::Origin::Memalign ||
                     Origin != Chunk::Origin::Malloc))
          reportDeallocTypeMismatch(AllocatorAction::Deallocating, Ptr,
                                    Header.Origin, Origin);
      }
    }

    const uptr Size = getSize(Ptr, &Header);
    if (DeleteSize && Options.DeleteSizeMismatch) {
      if (UNLIKELY(DeleteSize != Size))
        reportDeleteSizeMismatch(Ptr, DeleteSize, Size);
    }

    quarantineOrDeallocateChunk(Ptr, &Header, Size);
  }

  void *reallocate(void *OldPtr, uptr NewSize, uptr Alignment = MinAlignment) {
    initThreadMaybe();

    if (UNLIKELY(NewSize >= MaxAllowedMallocSize)) {
      if (Options.MayReturnNull)
        return nullptr;
      reportAllocationSizeTooBig(NewSize, 0, MaxAllowedMallocSize);
    }

    void *OldTaggedPtr = OldPtr;
    OldPtr = untagPointerMaybe(OldPtr);

    // The following cases are handled by the C wrappers.
    DCHECK_NE(OldPtr, nullptr);
    DCHECK_NE(NewSize, 0);

#ifdef GWP_ASAN_HOOKS
    if (UNLIKELY(GuardedAlloc.pointerIsMine(OldPtr))) {
      uptr OldSize = GuardedAlloc.getSize(OldPtr);
      void *NewPtr = allocate(NewSize, Chunk::Origin::Malloc, Alignment);
      if (NewPtr)
        memcpy(NewPtr, OldPtr, (NewSize < OldSize) ? NewSize : OldSize);
      GuardedAlloc.deallocate(OldPtr);
      return NewPtr;
    }
#endif // GWP_ASAN_HOOKS

    if (UNLIKELY(!isAligned(reinterpret_cast<uptr>(OldPtr), MinAlignment)))
      reportMisalignedPointer(AllocatorAction::Reallocating, OldPtr);

    Chunk::UnpackedHeader OldHeader;
    Chunk::loadHeader(Cookie, OldPtr, &OldHeader);

    if (UNLIKELY(OldHeader.State != Chunk::State::Allocated))
      reportInvalidChunkState(AllocatorAction::Reallocating, OldPtr);

    // Pointer has to be allocated with a malloc-type function. Some
    // applications think that it is OK to realloc a memalign'ed pointer, which
    // will trigger this check. It really isn't.
    if (Options.DeallocTypeMismatch) {
      if (UNLIKELY(OldHeader.Origin != Chunk::Origin::Malloc))
        reportDeallocTypeMismatch(AllocatorAction::Reallocating, OldPtr,
                                  OldHeader.Origin, Chunk::Origin::Malloc);
    }

    void *BlockBegin = getBlockBegin(OldPtr, &OldHeader);
    uptr BlockEnd;
    uptr OldSize;
    const uptr ClassId = OldHeader.ClassId;
    if (LIKELY(ClassId)) {
      BlockEnd = reinterpret_cast<uptr>(BlockBegin) +
                 SizeClassMap::getSizeByClassId(ClassId);
      OldSize = OldHeader.SizeOrUnusedBytes;
    } else {
      BlockEnd = SecondaryT::getBlockEnd(BlockBegin);
      OldSize = BlockEnd -
                (reinterpret_cast<uptr>(OldPtr) + OldHeader.SizeOrUnusedBytes);
    }
    // If the new chunk still fits in the previously allocated block (with a
    // reasonable delta), we just keep the old block, and update the chunk
    // header to reflect the size change.
    if (reinterpret_cast<uptr>(OldPtr) + NewSize <= BlockEnd) {
      if (NewSize > OldSize || (OldSize - NewSize) < getPageSizeCached()) {
        Chunk::UnpackedHeader NewHeader = OldHeader;
        NewHeader.SizeOrUnusedBytes =
            (ClassId ? NewSize
                     : BlockEnd - (reinterpret_cast<uptr>(OldPtr) + NewSize)) &
            Chunk::SizeOrUnusedBytesMask;
        Chunk::compareExchangeHeader(Cookie, OldPtr, &NewHeader, &OldHeader);
        if (UNLIKELY(ClassId && useMemoryTagging())) {
          resizeTaggedChunk(reinterpret_cast<uptr>(OldTaggedPtr) + OldSize,
                            reinterpret_cast<uptr>(OldTaggedPtr) + NewSize,
                            BlockEnd);
          storeAllocationStackMaybe(OldPtr);
        }
        return OldTaggedPtr;
      }
    }

    // Otherwise we allocate a new one, and deallocate the old one. Some
    // allocators will allocate an even larger chunk (by a fixed factor) to
    // allow for potential further in-place realloc. The gains of such a trick
    // are currently unclear.
    void *NewPtr = allocate(NewSize, Chunk::Origin::Malloc, Alignment);
    if (NewPtr) {
      const uptr OldSize = getSize(OldPtr, &OldHeader);
      memcpy(NewPtr, OldTaggedPtr, Min(NewSize, OldSize));
      quarantineOrDeallocateChunk(OldPtr, &OldHeader, OldSize);
    }
    return NewPtr;
  }

  // TODO(kostyak): disable() is currently best-effort. There are some small
  //                windows of time when an allocation could still succeed after
  //                this function finishes. We will revisit that later.
  void disable() {
    initThreadMaybe();
#ifdef GWP_ASAN_HOOKS
    GuardedAlloc.disable();
#endif
    TSDRegistry.disable();
    Stats.disable();
    Quarantine.disable();
    Primary.disable();
    Secondary.disable();
  }

  void enable() {
    initThreadMaybe();
    Secondary.enable();
    Primary.enable();
    Quarantine.enable();
    Stats.enable();
    TSDRegistry.enable();
#ifdef GWP_ASAN_HOOKS
    GuardedAlloc.enable();
#endif
  }

  // The function returns the amount of bytes required to store the statistics,
  // which might be larger than the amount of bytes provided. Note that the
  // statistics buffer is not necessarily constant between calls to this
  // function. This can be called with a null buffer or zero size for buffer
  // sizing purposes.
  uptr getStats(char *Buffer, uptr Size) {
    ScopedString Str(1024);
    disable();
    const uptr Length = getStats(&Str) + 1;
    enable();
    if (Length < Size)
      Size = Length;
    if (Buffer && Size) {
      memcpy(Buffer, Str.data(), Size);
      Buffer[Size - 1] = '\0';
    }
    return Length;
  }

  void printStats() {
    ScopedString Str(1024);
    disable();
    getStats(&Str);
    enable();
    Str.output();
  }

  void releaseToOS() {
    initThreadMaybe();
    Primary.releaseToOS();
    Secondary.releaseToOS();
  }

  // Iterate over all chunks and call a callback for all busy chunks located
  // within the provided memory range. Said callback must not use this allocator
  // or a deadlock can ensue. This fits Android's malloc_iterate() needs.
  void iterateOverChunks(uptr Base, uptr Size, iterate_callback Callback,
                         void *Arg) {
    initThreadMaybe();
    const uptr From = Base;
    const uptr To = Base + Size;
    auto Lambda = [this, From, To, Callback, Arg](uptr Block) {
      if (Block < From || Block >= To)
        return;
      uptr Chunk;
      Chunk::UnpackedHeader Header;
      if (getChunkFromBlock(Block, &Chunk, &Header) &&
          Header.State == Chunk::State::Allocated) {
        uptr TaggedChunk = Chunk;
        if (useMemoryTagging())
          TaggedChunk = loadTag(Chunk);
        Callback(TaggedChunk, getSize(reinterpret_cast<void *>(Chunk), &Header),
                 Arg);
      }
    };
    Primary.iterateOverBlocks(Lambda);
    Secondary.iterateOverBlocks(Lambda);
#ifdef GWP_ASAN_HOOKS
    GuardedAlloc.iterate(reinterpret_cast<void *>(Base), Size, Callback, Arg);
#endif
  }

  bool canReturnNull() {
    initThreadMaybe();
    return Options.MayReturnNull;
  }

  bool setOption(Option O, sptr Value) {
    if (O == Option::ReleaseInterval) {
      Primary.setReleaseToOsIntervalMs(static_cast<s32>(Value));
      Secondary.setReleaseToOsIntervalMs(static_cast<s32>(Value));
      return true;
    }
    return false;
  }

  // Return the usable size for a given chunk. Technically we lie, as we just
  // report the actual size of a chunk. This is done to counteract code actively
  // writing past the end of a chunk (like sqlite3) when the usable size allows
  // for it, which then forces realloc to copy the usable size of a chunk as
  // opposed to its actual size.
  uptr getUsableSize(const void *Ptr) {
    initThreadMaybe();
    if (UNLIKELY(!Ptr))
      return 0;

#ifdef GWP_ASAN_HOOKS
    if (UNLIKELY(GuardedAlloc.pointerIsMine(Ptr)))
      return GuardedAlloc.getSize(Ptr);
#endif // GWP_ASAN_HOOKS

    Ptr = untagPointerMaybe(const_cast<void *>(Ptr));
    Chunk::UnpackedHeader Header;
    Chunk::loadHeader(Cookie, Ptr, &Header);
    // Getting the usable size of a chunk only makes sense if it's allocated.
    if (UNLIKELY(Header.State != Chunk::State::Allocated))
      reportInvalidChunkState(AllocatorAction::Sizing, const_cast<void *>(Ptr));
    return getSize(Ptr, &Header);
  }

  void getStats(StatCounters S) {
    initThreadMaybe();
    Stats.get(S);
  }

  // Returns true if the pointer provided was allocated by the current
  // allocator instance, which is compliant with tcmalloc's ownership concept.
  // A corrupted chunk will not be reported as owned, which is WAI.
  bool isOwned(const void *Ptr) {
    initThreadMaybe();
#ifdef GWP_ASAN_HOOKS
    if (GuardedAlloc.pointerIsMine(Ptr))
      return true;
#endif // GWP_ASAN_HOOKS
    if (!Ptr || !isAligned(reinterpret_cast<uptr>(Ptr), MinAlignment))
      return false;
    Ptr = untagPointerMaybe(const_cast<void *>(Ptr));
    Chunk::UnpackedHeader Header;
    return Chunk::isValid(Cookie, Ptr, &Header) &&
           Header.State == Chunk::State::Allocated;
  }

  bool useMemoryTagging() { return Primary.useMemoryTagging(); }

  void disableMemoryTagging() { Primary.disableMemoryTagging(); }

  void setTrackAllocationStacks(bool Track) {
    initThreadMaybe();
    Options.TrackAllocationStacks = Track;
  }

  void setFillContents(FillContentsMode FillContents) {
    initThreadMaybe();
    Options.FillContents = FillContents;
  }

  const char *getStackDepotAddress() const {
    return reinterpret_cast<const char *>(&Depot);
  }

  const char *getRegionInfoArrayAddress() const {
    return Primary.getRegionInfoArrayAddress();
  }

  static uptr getRegionInfoArraySize() {
    return PrimaryT::getRegionInfoArraySize();
  }

  static void getErrorInfo(struct scudo_error_info *ErrorInfo,
                           uintptr_t FaultAddr, const char *DepotPtr,
                           const char *RegionInfoPtr, const char *Memory,
                           const char *MemoryTags, uintptr_t MemoryAddr,
                           size_t MemorySize) {
    *ErrorInfo = {};
    if (!PrimaryT::SupportsMemoryTagging ||
        MemoryAddr + MemorySize < MemoryAddr)
      return;

    uptr UntaggedFaultAddr = untagPointer(FaultAddr);
    u8 FaultAddrTag = extractTag(FaultAddr);
    BlockInfo Info =
        PrimaryT::findNearestBlock(RegionInfoPtr, UntaggedFaultAddr);

    auto GetGranule = [&](uptr Addr, const char **Data, uint8_t *Tag) -> bool {
      if (Addr < MemoryAddr ||
          Addr + archMemoryTagGranuleSize() < Addr ||
          Addr + archMemoryTagGranuleSize() > MemoryAddr + MemorySize)
        return false;
      *Data = &Memory[Addr - MemoryAddr];
      *Tag = static_cast<u8>(
          MemoryTags[(Addr - MemoryAddr) / archMemoryTagGranuleSize()]);
      return true;
    };

    auto ReadBlock = [&](uptr Addr, uptr *ChunkAddr,
                         Chunk::UnpackedHeader *Header, const u32 **Data,
                         u8 *Tag) {
      const char *BlockBegin;
      u8 BlockBeginTag;
      if (!GetGranule(Addr, &BlockBegin, &BlockBeginTag))
        return false;
      uptr ChunkOffset = getChunkOffsetFromBlock(BlockBegin);
      *ChunkAddr = Addr + ChunkOffset;

      const char *ChunkBegin;
      if (!GetGranule(*ChunkAddr, &ChunkBegin, Tag))
        return false;
      *Header = *reinterpret_cast<const Chunk::UnpackedHeader *>(
          ChunkBegin - Chunk::getHeaderSize());
      *Data = reinterpret_cast<const u32 *>(ChunkBegin);
      return true;
    };

    auto *Depot = reinterpret_cast<const StackDepot *>(DepotPtr);

    auto MaybeCollectTrace = [&](uintptr_t(&Trace)[MaxTraceSize], u32 Hash) {
      uptr RingPos, Size;
      if (!Depot->find(Hash, &RingPos, &Size))
        return;
      for (unsigned I = 0; I != Size && I != MaxTraceSize; ++I)
        Trace[I] = (*Depot)[RingPos + I];
    };

    size_t NextErrorReport = 0;

    // First, check for UAF.
    {
      uptr ChunkAddr;
      Chunk::UnpackedHeader Header;
      const u32 *Data;
      uint8_t Tag;
      if (ReadBlock(Info.BlockBegin, &ChunkAddr, &Header, &Data, &Tag) &&
          Header.State != Chunk::State::Allocated &&
          Data[MemTagPrevTagIndex] == FaultAddrTag) {
        auto *R = &ErrorInfo->reports[NextErrorReport++];
        R->error_type = USE_AFTER_FREE;
        R->allocation_address = ChunkAddr;
        R->allocation_size = Header.SizeOrUnusedBytes;
        MaybeCollectTrace(R->allocation_trace,
                          Data[MemTagAllocationTraceIndex]);
        R->allocation_tid = Data[MemTagAllocationTidIndex];
        MaybeCollectTrace(R->deallocation_trace,
                          Data[MemTagDeallocationTraceIndex]);
        R->deallocation_tid = Data[MemTagDeallocationTidIndex];
      }
    }

    auto CheckOOB = [&](uptr BlockAddr) {
      if (BlockAddr < Info.RegionBegin || BlockAddr >= Info.RegionEnd)
        return false;

      uptr ChunkAddr;
      Chunk::UnpackedHeader Header;
      const u32 *Data;
      uint8_t Tag;
      if (!ReadBlock(BlockAddr, &ChunkAddr, &Header, &Data, &Tag) ||
          Header.State != Chunk::State::Allocated || Tag != FaultAddrTag)
        return false;

      auto *R = &ErrorInfo->reports[NextErrorReport++];
      R->error_type =
          UntaggedFaultAddr < ChunkAddr ? BUFFER_UNDERFLOW : BUFFER_OVERFLOW;
      R->allocation_address = ChunkAddr;
      R->allocation_size = Header.SizeOrUnusedBytes;
      MaybeCollectTrace(R->allocation_trace, Data[MemTagAllocationTraceIndex]);
      R->allocation_tid = Data[MemTagAllocationTidIndex];
      return NextErrorReport ==
             sizeof(ErrorInfo->reports) / sizeof(ErrorInfo->reports[0]);
    };

    if (CheckOOB(Info.BlockBegin))
      return;

    // Check for OOB in the 30 surrounding blocks. Beyond that we are likely to
    // hit false positives.
    for (int I = 1; I != 16; ++I)
      if (CheckOOB(Info.BlockBegin + I * Info.BlockSize) ||
          CheckOOB(Info.BlockBegin - I * Info.BlockSize))
        return;
  }

private:
  using SecondaryT = typename Params::Secondary;
  typedef typename PrimaryT::SizeClassMap SizeClassMap;

  static const uptr MinAlignmentLog = SCUDO_MIN_ALIGNMENT_LOG;
  static const uptr MaxAlignmentLog = 24U; // 16 MB seems reasonable.
  static const uptr MinAlignment = 1UL << MinAlignmentLog;
  static const uptr MaxAlignment = 1UL << MaxAlignmentLog;
  static const uptr MaxAllowedMallocSize =
      FIRST_32_SECOND_64(1UL << 31, 1ULL << 40);

  static_assert(MinAlignment >= sizeof(Chunk::PackedHeader),
                "Minimal alignment must at least cover a chunk header.");
  static_assert(!PrimaryT::SupportsMemoryTagging ||
                    MinAlignment >= archMemoryTagGranuleSize(),
                "");

  static const u32 BlockMarker = 0x44554353U;

  // These are indexes into an "array" of 32-bit values that store information
  // inline with a chunk that is relevant to diagnosing memory tag faults, where
  // 0 corresponds to the address of the user memory. This means that negative
  // indexes may be used to store information about allocations, while positive
  // indexes may only be used to store information about deallocations, because
  // the user memory is in use until it has been deallocated. The smallest index
  // that may be used is -2, which corresponds to 8 bytes before the user
  // memory, because the chunk header size is 8 bytes and in allocators that
  // support memory tagging the minimum alignment is at least the tag granule
  // size (16 on aarch64), and the largest index that may be used is 3 because
  // we are only guaranteed to have at least a granule's worth of space in the
  // user memory.
  static const sptr MemTagAllocationTraceIndex = -2;
  static const sptr MemTagAllocationTidIndex = -1;
  static const sptr MemTagDeallocationTraceIndex = 0;
  static const sptr MemTagDeallocationTidIndex = 1;
  static const sptr MemTagPrevTagIndex = 2;

  static const uptr MaxTraceSize = 64;

  GlobalStats Stats;
  TSDRegistryT TSDRegistry;
  PrimaryT Primary;
  SecondaryT Secondary;
  QuarantineT Quarantine;

  u32 Cookie;

  struct {
    u8 MayReturnNull : 1;       // may_return_null
    FillContentsMode FillContents : 2; // zero_contents, pattern_fill_contents
    u8 DeallocTypeMismatch : 1; // dealloc_type_mismatch
    u8 DeleteSizeMismatch : 1;  // delete_size_mismatch
    u8 TrackAllocationStacks : 1;
    u32 QuarantineMaxChunkSize; // quarantine_max_chunk_size
  } Options;

#ifdef GWP_ASAN_HOOKS
  gwp_asan::GuardedPoolAllocator GuardedAlloc;
#endif // GWP_ASAN_HOOKS

  StackDepot Depot;

  // The following might get optimized out by the compiler.
  NOINLINE void performSanityChecks() {
    // Verify that the header offset field can hold the maximum offset. In the
    // case of the Secondary allocator, it takes care of alignment and the
    // offset will always be small. In the case of the Primary, the worst case
    // scenario happens in the last size class, when the backend allocation
    // would already be aligned on the requested alignment, which would happen
    // to be the maximum alignment that would fit in that size class. As a
    // result, the maximum offset will be at most the maximum alignment for the
    // last size class minus the header size, in multiples of MinAlignment.
    Chunk::UnpackedHeader Header = {};
    const uptr MaxPrimaryAlignment = 1UL << getMostSignificantSetBitIndex(
                                         SizeClassMap::MaxSize - MinAlignment);
    const uptr MaxOffset =
        (MaxPrimaryAlignment - Chunk::getHeaderSize()) >> MinAlignmentLog;
    Header.Offset = MaxOffset & Chunk::OffsetMask;
    if (UNLIKELY(Header.Offset != MaxOffset))
      reportSanityCheckError("offset");

    // Verify that we can fit the maximum size or amount of unused bytes in the
    // header. Given that the Secondary fits the allocation to a page, the worst
    // case scenario happens in the Primary. It will depend on the second to
    // last and last class sizes, as well as the dynamic base for the Primary.
    // The following is an over-approximation that works for our needs.
    const uptr MaxSizeOrUnusedBytes = SizeClassMap::MaxSize - 1;
    Header.SizeOrUnusedBytes = MaxSizeOrUnusedBytes;
    if (UNLIKELY(Header.SizeOrUnusedBytes != MaxSizeOrUnusedBytes))
      reportSanityCheckError("size (or unused bytes)");

    const uptr LargestClassId = SizeClassMap::LargestClassId;
    Header.ClassId = LargestClassId;
    if (UNLIKELY(Header.ClassId != LargestClassId))
      reportSanityCheckError("class ID");
  }

  static inline void *getBlockBegin(const void *Ptr,
                                    Chunk::UnpackedHeader *Header) {
    return reinterpret_cast<void *>(
        reinterpret_cast<uptr>(Ptr) - Chunk::getHeaderSize() -
        (static_cast<uptr>(Header->Offset) << MinAlignmentLog));
  }

  // Return the size of a chunk as requested during its allocation.
  inline uptr getSize(const void *Ptr, Chunk::UnpackedHeader *Header) {
    const uptr SizeOrUnusedBytes = Header->SizeOrUnusedBytes;
    if (LIKELY(Header->ClassId))
      return SizeOrUnusedBytes;
    return SecondaryT::getBlockEnd(getBlockBegin(Ptr, Header)) -
           reinterpret_cast<uptr>(Ptr) - SizeOrUnusedBytes;
  }

  ALWAYS_INLINE void initThreadMaybe(bool MinimalInit = false) {
    TSDRegistry.initThreadMaybe(this, MinimalInit);
  }

  void quarantineOrDeallocateChunk(void *Ptr, Chunk::UnpackedHeader *Header,
                                   uptr Size) {
    Chunk::UnpackedHeader NewHeader = *Header;
    if (UNLIKELY(NewHeader.ClassId && useMemoryTagging())) {
      u8 PrevTag = extractTag(loadTag(reinterpret_cast<uptr>(Ptr)));
      uptr TaggedBegin, TaggedEnd;
      // Exclude the previous tag so that immediate use after free is detected
      // 100% of the time.
      setRandomTag(Ptr, Size, 1UL << PrevTag, &TaggedBegin, &TaggedEnd);
      storeDeallocationStackMaybe(Ptr, PrevTag);
    }
    // If the quarantine is disabled, the actual size of a chunk is 0 or larger
    // than the maximum allowed, we return a chunk directly to the backend.
    // Logical Or can be short-circuited, which introduces unnecessary
    // conditional jumps, so use bitwise Or and let the compiler be clever.
    const bool BypassQuarantine = !Quarantine.getCacheSize() | !Size |
                                  (Size > Options.QuarantineMaxChunkSize);
    if (BypassQuarantine) {
      NewHeader.State = Chunk::State::Available;
      Chunk::compareExchangeHeader(Cookie, Ptr, &NewHeader, Header);
      void *BlockBegin = getBlockBegin(Ptr, &NewHeader);
      const uptr ClassId = NewHeader.ClassId;
      if (LIKELY(ClassId)) {
        bool UnlockRequired;
        auto *TSD = TSDRegistry.getTSDAndLock(&UnlockRequired);
        TSD->Cache.deallocate(ClassId, BlockBegin);
        if (UnlockRequired)
          TSD->unlock();
      } else {
        Secondary.deallocate(BlockBegin);
      }
    } else {
      NewHeader.State = Chunk::State::Quarantined;
      Chunk::compareExchangeHeader(Cookie, Ptr, &NewHeader, Header);
      bool UnlockRequired;
      auto *TSD = TSDRegistry.getTSDAndLock(&UnlockRequired);
      Quarantine.put(&TSD->QuarantineCache,
                     QuarantineCallback(*this, TSD->Cache), Ptr, Size);
      if (UnlockRequired)
        TSD->unlock();
    }
  }

  bool getChunkFromBlock(uptr Block, uptr *Chunk,
                         Chunk::UnpackedHeader *Header) {
    *Chunk =
        Block + getChunkOffsetFromBlock(reinterpret_cast<const char *>(Block));
    return Chunk::isValid(Cookie, reinterpret_cast<void *>(*Chunk), Header);
  }

  static uptr getChunkOffsetFromBlock(const char *Block) {
    u32 Offset = 0;
    if (reinterpret_cast<const u32 *>(Block)[0] == BlockMarker)
      Offset = reinterpret_cast<const u32 *>(Block)[1];
    return Offset + Chunk::getHeaderSize();
  }

  void storeAllocationStackMaybe(void *Ptr) {
    if (!UNLIKELY(Options.TrackAllocationStacks))
      return;
    auto *Ptr32 = reinterpret_cast<u32 *>(Ptr);
    Ptr32[MemTagAllocationTraceIndex] = collectStackTrace();
    Ptr32[MemTagAllocationTidIndex] = getThreadID();
  }

  void storeDeallocationStackMaybe(void *Ptr, uint8_t PrevTag) {
    if (!UNLIKELY(Options.TrackAllocationStacks))
      return;

    // Disable tag checks here so that we don't need to worry about zero sized
    // allocations.
    ScopedDisableMemoryTagChecks x;
    auto *Ptr32 = reinterpret_cast<u32 *>(Ptr);
    Ptr32[MemTagDeallocationTraceIndex] = collectStackTrace();
    Ptr32[MemTagDeallocationTidIndex] = getThreadID();
    Ptr32[MemTagPrevTagIndex] = PrevTag;
  }

  uptr getStats(ScopedString *Str) {
    Primary.getStats(Str);
    Secondary.getStats(Str);
    Quarantine.getStats(Str);
    return Str->length();
  }
};

} // namespace scudo

#endif // SCUDO_COMBINED_H_