summaryrefslogtreecommitdiff
path: root/lib/tsan/rtl/tsan_rtl.h
blob: d58c1dca472c94c547818a15b590ed4fd446a3b0 (plain)
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
//===-- tsan_rtl.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
//
//===----------------------------------------------------------------------===//
//
// This file is a part of ThreadSanitizer (TSan), a race detector.
//
// Main internal TSan header file.
//
// Ground rules:
//   - C++ run-time should not be used (static CTORs, RTTI, exceptions, static
//     function-scope locals)
//   - All functions/classes/etc reside in namespace __tsan, except for those
//     declared in tsan_interface.h.
//   - Platform-specific files should be used instead of ifdefs (*).
//   - No system headers included in header files (*).
//   - Platform specific headres included only into platform-specific files (*).
//
//  (*) Except when inlining is critical for performance.
//===----------------------------------------------------------------------===//

#ifndef TSAN_RTL_H
#define TSAN_RTL_H

#include "sanitizer_common/sanitizer_allocator.h"
#include "sanitizer_common/sanitizer_allocator_internal.h"
#include "sanitizer_common/sanitizer_asm.h"
#include "sanitizer_common/sanitizer_common.h"
#include "sanitizer_common/sanitizer_deadlock_detector_interface.h"
#include "sanitizer_common/sanitizer_libignore.h"
#include "sanitizer_common/sanitizer_suppressions.h"
#include "sanitizer_common/sanitizer_thread_registry.h"
#include "sanitizer_common/sanitizer_vector.h"
#include "tsan_clock.h"
#include "tsan_defs.h"
#include "tsan_flags.h"
#include "tsan_mman.h"
#include "tsan_sync.h"
#include "tsan_trace.h"
#include "tsan_report.h"
#include "tsan_platform.h"
#include "tsan_mutexset.h"
#include "tsan_ignoreset.h"
#include "tsan_stack_trace.h"

#if SANITIZER_WORDSIZE != 64
# error "ThreadSanitizer is supported only on 64-bit platforms"
#endif

namespace __tsan {

#if !SANITIZER_GO
struct MapUnmapCallback;
#if defined(__mips64) || defined(__aarch64__) || defined(__powerpc__)

struct AP32 {
  static const uptr kSpaceBeg = 0;
  static const u64 kSpaceSize = SANITIZER_MMAP_RANGE_SIZE;
  static const uptr kMetadataSize = 0;
  typedef __sanitizer::CompactSizeClassMap SizeClassMap;
  static const uptr kRegionSizeLog = 20;
  using AddressSpaceView = LocalAddressSpaceView;
  typedef __tsan::MapUnmapCallback MapUnmapCallback;
  static const uptr kFlags = 0;
};
typedef SizeClassAllocator32<AP32> PrimaryAllocator;
#else
struct AP64 {  // Allocator64 parameters. Deliberately using a short name.
  static const uptr kSpaceBeg = Mapping::kHeapMemBeg;
  static const uptr kSpaceSize = Mapping::kHeapMemEnd - Mapping::kHeapMemBeg;
  static const uptr kMetadataSize = 0;
  typedef DefaultSizeClassMap SizeClassMap;
  typedef __tsan::MapUnmapCallback MapUnmapCallback;
  static const uptr kFlags = 0;
  using AddressSpaceView = LocalAddressSpaceView;
};
typedef SizeClassAllocator64<AP64> PrimaryAllocator;
#endif
typedef CombinedAllocator<PrimaryAllocator> Allocator;
typedef Allocator::AllocatorCache AllocatorCache;
Allocator *allocator();
#endif

void TsanCheckFailed(const char *file, int line, const char *cond,
                     u64 v1, u64 v2);

const u64 kShadowRodata = (u64)-1;  // .rodata shadow marker

// FastState (from most significant bit):
//   ignore          : 1
//   tid             : kTidBits
//   unused          : -
//   history_size    : 3
//   epoch           : kClkBits
class FastState {
 public:
  FastState(u64 tid, u64 epoch) {
    x_ = tid << kTidShift;
    x_ |= epoch;
    DCHECK_EQ(tid, this->tid());
    DCHECK_EQ(epoch, this->epoch());
    DCHECK_EQ(GetIgnoreBit(), false);
  }

  explicit FastState(u64 x)
      : x_(x) {
  }

  u64 raw() const {
    return x_;
  }

  u64 tid() const {
    u64 res = (x_ & ~kIgnoreBit) >> kTidShift;
    return res;
  }

  u64 TidWithIgnore() const {
    u64 res = x_ >> kTidShift;
    return res;
  }

  u64 epoch() const {
    u64 res = x_ & ((1ull << kClkBits) - 1);
    return res;
  }

  void IncrementEpoch() {
    u64 old_epoch = epoch();
    x_ += 1;
    DCHECK_EQ(old_epoch + 1, epoch());
    (void)old_epoch;
  }

  void SetIgnoreBit() { x_ |= kIgnoreBit; }
  void ClearIgnoreBit() { x_ &= ~kIgnoreBit; }
  bool GetIgnoreBit() const { return (s64)x_ < 0; }

  void SetHistorySize(int hs) {
    CHECK_GE(hs, 0);
    CHECK_LE(hs, 7);
    x_ = (x_ & ~(kHistoryMask << kHistoryShift)) | (u64(hs) << kHistoryShift);
  }

  ALWAYS_INLINE
  int GetHistorySize() const {
    return (int)((x_ >> kHistoryShift) & kHistoryMask);
  }

  void ClearHistorySize() {
    SetHistorySize(0);
  }

  ALWAYS_INLINE
  u64 GetTracePos() const {
    const int hs = GetHistorySize();
    // When hs == 0, the trace consists of 2 parts.
    const u64 mask = (1ull << (kTracePartSizeBits + hs + 1)) - 1;
    return epoch() & mask;
  }

 private:
  friend class Shadow;
  static const int kTidShift = 64 - kTidBits - 1;
  static const u64 kIgnoreBit = 1ull << 63;
  static const u64 kFreedBit = 1ull << 63;
  static const u64 kHistoryShift = kClkBits;
  static const u64 kHistoryMask = 7;
  u64 x_;
};

// Shadow (from most significant bit):
//   freed           : 1
//   tid             : kTidBits
//   is_atomic       : 1
//   is_read         : 1
//   size_log        : 2
//   addr0           : 3
//   epoch           : kClkBits
class Shadow : public FastState {
 public:
  explicit Shadow(u64 x)
      : FastState(x) {
  }

  explicit Shadow(const FastState &s)
      : FastState(s.x_) {
    ClearHistorySize();
  }

  void SetAddr0AndSizeLog(u64 addr0, unsigned kAccessSizeLog) {
    DCHECK_EQ((x_ >> kClkBits) & 31, 0);
    DCHECK_LE(addr0, 7);
    DCHECK_LE(kAccessSizeLog, 3);
    x_ |= ((kAccessSizeLog << 3) | addr0) << kClkBits;
    DCHECK_EQ(kAccessSizeLog, size_log());
    DCHECK_EQ(addr0, this->addr0());
  }

  void SetWrite(unsigned kAccessIsWrite) {
    DCHECK_EQ(x_ & kReadBit, 0);
    if (!kAccessIsWrite)
      x_ |= kReadBit;
    DCHECK_EQ(kAccessIsWrite, IsWrite());
  }

  void SetAtomic(bool kIsAtomic) {
    DCHECK(!IsAtomic());
    if (kIsAtomic)
      x_ |= kAtomicBit;
    DCHECK_EQ(IsAtomic(), kIsAtomic);
  }

  bool IsAtomic() const {
    return x_ & kAtomicBit;
  }

  bool IsZero() const {
    return x_ == 0;
  }

  static inline bool TidsAreEqual(const Shadow s1, const Shadow s2) {
    u64 shifted_xor = (s1.x_ ^ s2.x_) >> kTidShift;
    DCHECK_EQ(shifted_xor == 0, s1.TidWithIgnore() == s2.TidWithIgnore());
    return shifted_xor == 0;
  }

  static ALWAYS_INLINE
  bool Addr0AndSizeAreEqual(const Shadow s1, const Shadow s2) {
    u64 masked_xor = ((s1.x_ ^ s2.x_) >> kClkBits) & 31;
    return masked_xor == 0;
  }

  static ALWAYS_INLINE bool TwoRangesIntersect(Shadow s1, Shadow s2,
      unsigned kS2AccessSize) {
    bool res = false;
    u64 diff = s1.addr0() - s2.addr0();
    if ((s64)diff < 0) {  // s1.addr0 < s2.addr0  // NOLINT
      // if (s1.addr0() + size1) > s2.addr0()) return true;
      if (s1.size() > -diff)
        res = true;
    } else {
      // if (s2.addr0() + kS2AccessSize > s1.addr0()) return true;
      if (kS2AccessSize > diff)
        res = true;
    }
    DCHECK_EQ(res, TwoRangesIntersectSlow(s1, s2));
    DCHECK_EQ(res, TwoRangesIntersectSlow(s2, s1));
    return res;
  }

  u64 ALWAYS_INLINE addr0() const { return (x_ >> kClkBits) & 7; }
  u64 ALWAYS_INLINE size() const { return 1ull << size_log(); }
  bool ALWAYS_INLINE IsWrite() const { return !IsRead(); }
  bool ALWAYS_INLINE IsRead() const { return x_ & kReadBit; }

  // The idea behind the freed bit is as follows.
  // When the memory is freed (or otherwise unaccessible) we write to the shadow
  // values with tid/epoch related to the free and the freed bit set.
  // During memory accesses processing the freed bit is considered
  // as msb of tid. So any access races with shadow with freed bit set
  // (it is as if write from a thread with which we never synchronized before).
  // This allows us to detect accesses to freed memory w/o additional
  // overheads in memory access processing and at the same time restore
  // tid/epoch of free.
  void MarkAsFreed() {
     x_ |= kFreedBit;
  }

  bool IsFreed() const {
    return x_ & kFreedBit;
  }

  bool GetFreedAndReset() {
    bool res = x_ & kFreedBit;
    x_ &= ~kFreedBit;
    return res;
  }

  bool ALWAYS_INLINE IsBothReadsOrAtomic(bool kIsWrite, bool kIsAtomic) const {
    bool v = x_ & ((u64(kIsWrite ^ 1) << kReadShift)
        | (u64(kIsAtomic) << kAtomicShift));
    DCHECK_EQ(v, (!IsWrite() && !kIsWrite) || (IsAtomic() && kIsAtomic));
    return v;
  }

  bool ALWAYS_INLINE IsRWNotWeaker(bool kIsWrite, bool kIsAtomic) const {
    bool v = ((x_ >> kReadShift) & 3)
        <= u64((kIsWrite ^ 1) | (kIsAtomic << 1));
    DCHECK_EQ(v, (IsAtomic() < kIsAtomic) ||
        (IsAtomic() == kIsAtomic && !IsWrite() <= !kIsWrite));
    return v;
  }

  bool ALWAYS_INLINE IsRWWeakerOrEqual(bool kIsWrite, bool kIsAtomic) const {
    bool v = ((x_ >> kReadShift) & 3)
        >= u64((kIsWrite ^ 1) | (kIsAtomic << 1));
    DCHECK_EQ(v, (IsAtomic() > kIsAtomic) ||
        (IsAtomic() == kIsAtomic && !IsWrite() >= !kIsWrite));
    return v;
  }

 private:
  static const u64 kReadShift   = 5 + kClkBits;
  static const u64 kReadBit     = 1ull << kReadShift;
  static const u64 kAtomicShift = 6 + kClkBits;
  static const u64 kAtomicBit   = 1ull << kAtomicShift;

  u64 size_log() const { return (x_ >> (3 + kClkBits)) & 3; }

  static bool TwoRangesIntersectSlow(const Shadow s1, const Shadow s2) {
    if (s1.addr0() == s2.addr0()) return true;
    if (s1.addr0() < s2.addr0() && s1.addr0() + s1.size() > s2.addr0())
      return true;
    if (s2.addr0() < s1.addr0() && s2.addr0() + s2.size() > s1.addr0())
      return true;
    return false;
  }
};

struct ThreadSignalContext;

struct JmpBuf {
  uptr sp;
  uptr mangled_sp;
  int int_signal_send;
  bool in_blocking_func;
  uptr in_signal_handler;
  uptr *shadow_stack_pos;
};

// A Processor represents a physical thread, or a P for Go.
// It is used to store internal resources like allocate cache, and does not
// participate in race-detection logic (invisible to end user).
// In C++ it is tied to an OS thread just like ThreadState, however ideally
// it should be tied to a CPU (this way we will have fewer allocator caches).
// In Go it is tied to a P, so there are significantly fewer Processor's than
// ThreadState's (which are tied to Gs).
// A ThreadState must be wired with a Processor to handle events.
struct Processor {
  ThreadState *thr; // currently wired thread, or nullptr
#if !SANITIZER_GO
  AllocatorCache alloc_cache;
  InternalAllocatorCache internal_alloc_cache;
#endif
  DenseSlabAllocCache block_cache;
  DenseSlabAllocCache sync_cache;
  DenseSlabAllocCache clock_cache;
  DDPhysicalThread *dd_pt;
};

#if !SANITIZER_GO
// ScopedGlobalProcessor temporary setups a global processor for the current
// thread, if it does not have one. Intended for interceptors that can run
// at the very thread end, when we already destroyed the thread processor.
struct ScopedGlobalProcessor {
  ScopedGlobalProcessor();
  ~ScopedGlobalProcessor();
};
#endif

// This struct is stored in TLS.
struct ThreadState {
  FastState fast_state;
  // Synch epoch represents the threads's epoch before the last synchronization
  // action. It allows to reduce number of shadow state updates.
  // For example, fast_synch_epoch=100, last write to addr X was at epoch=150,
  // if we are processing write to X from the same thread at epoch=200,
  // we do nothing, because both writes happen in the same 'synch epoch'.
  // That is, if another memory access does not race with the former write,
  // it does not race with the latter as well.
  // QUESTION: can we can squeeze this into ThreadState::Fast?
  // E.g. ThreadState::Fast is a 44-bit, 32 are taken by synch_epoch and 12 are
  // taken by epoch between synchs.
  // This way we can save one load from tls.
  u64 fast_synch_epoch;
  // Technically `current` should be a separate THREADLOCAL variable;
  // but it is placed here in order to share cache line with previous fields.
  ThreadState* current;
  // This is a slow path flag. On fast path, fast_state.GetIgnoreBit() is read.
  // We do not distinguish beteween ignoring reads and writes
  // for better performance.
  int ignore_reads_and_writes;
  int ignore_sync;
  int suppress_reports;
  // Go does not support ignores.
#if !SANITIZER_GO
  IgnoreSet mop_ignore_set;
  IgnoreSet sync_ignore_set;
#endif
  // C/C++ uses fixed size shadow stack embed into Trace.
  // Go uses malloc-allocated shadow stack with dynamic size.
  uptr *shadow_stack;
  uptr *shadow_stack_end;
  uptr *shadow_stack_pos;
  u64 *racy_shadow_addr;
  u64 racy_state[2];
  MutexSet mset;
  ThreadClock clock;
#if !SANITIZER_GO
  Vector<JmpBuf> jmp_bufs;
  int ignore_interceptors;
#endif
#if TSAN_COLLECT_STATS
  u64 stat[StatCnt];
#endif
  const int tid;
  const int unique_id;
  bool in_symbolizer;
  bool in_ignored_lib;
  bool is_inited;
  bool is_dead;
  bool is_freeing;
  bool is_vptr_access;
  const uptr stk_addr;
  const uptr stk_size;
  const uptr tls_addr;
  const uptr tls_size;
  ThreadContext *tctx;

#if SANITIZER_DEBUG && !SANITIZER_GO
  InternalDeadlockDetector internal_deadlock_detector;
#endif
  DDLogicalThread *dd_lt;

  // Current wired Processor, or nullptr. Required to handle any events.
  Processor *proc1;
#if !SANITIZER_GO
  Processor *proc() { return proc1; }
#else
  Processor *proc();
#endif

  atomic_uintptr_t in_signal_handler;
  ThreadSignalContext *signal_ctx;

#if !SANITIZER_GO
  u32 last_sleep_stack_id;
  ThreadClock last_sleep_clock;
#endif

  // Set in regions of runtime that must be signal-safe and fork-safe.
  // If set, malloc must not be called.
  int nomalloc;

  const ReportDesc *current_report;

  explicit ThreadState(Context *ctx, int tid, int unique_id, u64 epoch,
                       unsigned reuse_count,
                       uptr stk_addr, uptr stk_size,
                       uptr tls_addr, uptr tls_size);
};

#if !SANITIZER_GO
#if SANITIZER_MAC || SANITIZER_ANDROID
ThreadState *cur_thread();
void set_cur_thread(ThreadState *thr);
void cur_thread_finalize();
INLINE void cur_thread_init() { }
#else
__attribute__((tls_model("initial-exec")))
extern THREADLOCAL char cur_thread_placeholder[];
INLINE ThreadState *cur_thread() {
  return reinterpret_cast<ThreadState *>(cur_thread_placeholder)->current;
}
INLINE void cur_thread_init() {
  ThreadState *thr = reinterpret_cast<ThreadState *>(cur_thread_placeholder);
  if (UNLIKELY(!thr->current))
    thr->current = thr;
}
INLINE void set_cur_thread(ThreadState *thr) {
  reinterpret_cast<ThreadState *>(cur_thread_placeholder)->current = thr;
}
INLINE void cur_thread_finalize() { }
#endif  // SANITIZER_MAC || SANITIZER_ANDROID
#endif  // SANITIZER_GO

class ThreadContext : public ThreadContextBase {
 public:
  explicit ThreadContext(int tid);
  ~ThreadContext();
  ThreadState *thr;
  u32 creation_stack_id;
  SyncClock sync;
  // Epoch at which the thread had started.
  // If we see an event from the thread stamped by an older epoch,
  // the event is from a dead thread that shared tid with this thread.
  u64 epoch0;
  u64 epoch1;

  // Override superclass callbacks.
  void OnDead() override;
  void OnJoined(void *arg) override;
  void OnFinished() override;
  void OnStarted(void *arg) override;
  void OnCreated(void *arg) override;
  void OnReset() override;
  void OnDetached(void *arg) override;
};

struct RacyStacks {
  MD5Hash hash[2];
  bool operator==(const RacyStacks &other) const {
    if (hash[0] == other.hash[0] && hash[1] == other.hash[1])
      return true;
    if (hash[0] == other.hash[1] && hash[1] == other.hash[0])
      return true;
    return false;
  }
};

struct RacyAddress {
  uptr addr_min;
  uptr addr_max;
};

struct FiredSuppression {
  ReportType type;
  uptr pc_or_addr;
  Suppression *supp;
};

struct Context {
  Context();

  bool initialized;
#if !SANITIZER_GO
  bool after_multithreaded_fork;
#endif

  MetaMap metamap;

  Mutex report_mtx;
  int nreported;
  int nmissed_expected;
  atomic_uint64_t last_symbolize_time_ns;

  void *background_thread;
  atomic_uint32_t stop_background_thread;

  ThreadRegistry *thread_registry;

  Mutex racy_mtx;
  Vector<RacyStacks> racy_stacks;
  Vector<RacyAddress> racy_addresses;
  // Number of fired suppressions may be large enough.
  Mutex fired_suppressions_mtx;
  InternalMmapVector<FiredSuppression> fired_suppressions;
  DDetector *dd;

  ClockAlloc clock_alloc;

  Flags flags;

  u64 stat[StatCnt];
  u64 int_alloc_cnt[MBlockTypeCount];
  u64 int_alloc_siz[MBlockTypeCount];
};

extern Context *ctx;  // The one and the only global runtime context.

ALWAYS_INLINE Flags *flags() {
  return &ctx->flags;
}

struct ScopedIgnoreInterceptors {
  ScopedIgnoreInterceptors() {
#if !SANITIZER_GO
    cur_thread()->ignore_interceptors++;
#endif
  }

  ~ScopedIgnoreInterceptors() {
#if !SANITIZER_GO
    cur_thread()->ignore_interceptors--;
#endif
  }
};

const char *GetObjectTypeFromTag(uptr tag);
const char *GetReportHeaderFromTag(uptr tag);
uptr TagFromShadowStackFrame(uptr pc);

class ScopedReportBase {
 public:
  void AddMemoryAccess(uptr addr, uptr external_tag, Shadow s, StackTrace stack,
                       const MutexSet *mset);
  void AddStack(StackTrace stack, bool suppressable = false);
  void AddThread(const ThreadContext *tctx, bool suppressable = false);
  void AddThread(int unique_tid, bool suppressable = false);
  void AddUniqueTid(int unique_tid);
  void AddMutex(const SyncVar *s);
  u64 AddMutex(u64 id);
  void AddLocation(uptr addr, uptr size);
  void AddSleep(u32 stack_id);
  void SetCount(int count);

  const ReportDesc *GetReport() const;

 protected:
  ScopedReportBase(ReportType typ, uptr tag);
  ~ScopedReportBase();

 private:
  ReportDesc *rep_;
  // Symbolizer makes lots of intercepted calls. If we try to process them,
  // at best it will cause deadlocks on internal mutexes.
  ScopedIgnoreInterceptors ignore_interceptors_;

  void AddDeadMutex(u64 id);

  ScopedReportBase(const ScopedReportBase &) = delete;
  void operator=(const ScopedReportBase &) = delete;
};

class ScopedReport : public ScopedReportBase {
 public:
  explicit ScopedReport(ReportType typ, uptr tag = kExternalTagNone);
  ~ScopedReport();

 private:
  ScopedErrorReportLock lock_;
};

ThreadContext *IsThreadStackOrTls(uptr addr, bool *is_stack);
void RestoreStack(int tid, const u64 epoch, VarSizeStackTrace *stk,
                  MutexSet *mset, uptr *tag = nullptr);

// The stack could look like:
//   <start> | <main> | <foo> | tag | <bar>
// This will extract the tag and keep:
//   <start> | <main> | <foo> | <bar>
template<typename StackTraceTy>
void ExtractTagFromStack(StackTraceTy *stack, uptr *tag = nullptr) {
  if (stack->size < 2) return;
  uptr possible_tag_pc = stack->trace[stack->size - 2];
  uptr possible_tag = TagFromShadowStackFrame(possible_tag_pc);
  if (possible_tag == kExternalTagNone) return;
  stack->trace_buffer[stack->size - 2] = stack->trace_buffer[stack->size - 1];
  stack->size -= 1;
  if (tag) *tag = possible_tag;
}

template<typename StackTraceTy>
void ObtainCurrentStack(ThreadState *thr, uptr toppc, StackTraceTy *stack,
                        uptr *tag = nullptr) {
  uptr size = thr->shadow_stack_pos - thr->shadow_stack;
  uptr start = 0;
  if (size + !!toppc > kStackTraceMax) {
    start = size + !!toppc - kStackTraceMax;
    size = kStackTraceMax - !!toppc;
  }
  stack->Init(&thr->shadow_stack[start], size, toppc);
  ExtractTagFromStack(stack, tag);
}

#define GET_STACK_TRACE_FATAL(thr, pc) \
  VarSizeStackTrace stack; \
  ObtainCurrentStack(thr, pc, &stack); \
  stack.ReverseOrder();

#if TSAN_COLLECT_STATS
void StatAggregate(u64 *dst, u64 *src);
void StatOutput(u64 *stat);
#endif

void ALWAYS_INLINE StatInc(ThreadState *thr, StatType typ, u64 n = 1) {
#if TSAN_COLLECT_STATS
  thr->stat[typ] += n;
#endif
}
void ALWAYS_INLINE StatSet(ThreadState *thr, StatType typ, u64 n) {
#if TSAN_COLLECT_STATS
  thr->stat[typ] = n;
#endif
}

void MapShadow(uptr addr, uptr size);
void MapThreadTrace(uptr addr, uptr size, const char *name);
void DontNeedShadowFor(uptr addr, uptr size);
void InitializeShadowMemory();
void InitializeInterceptors();
void InitializeLibIgnore();
void InitializeDynamicAnnotations();

void ForkBefore(ThreadState *thr, uptr pc);
void ForkParentAfter(ThreadState *thr, uptr pc);
void ForkChildAfter(ThreadState *thr, uptr pc);

void ReportRace(ThreadState *thr);
bool OutputReport(ThreadState *thr, const ScopedReport &srep);
bool IsFiredSuppression(Context *ctx, ReportType type, StackTrace trace);
bool IsExpectedReport(uptr addr, uptr size);
void PrintMatchedBenignRaces();

#if defined(TSAN_DEBUG_OUTPUT) && TSAN_DEBUG_OUTPUT >= 1
# define DPrintf Printf
#else
# define DPrintf(...)
#endif

#if defined(TSAN_DEBUG_OUTPUT) && TSAN_DEBUG_OUTPUT >= 2
# define DPrintf2 Printf
#else
# define DPrintf2(...)
#endif

u32 CurrentStackId(ThreadState *thr, uptr pc);
ReportStack *SymbolizeStackId(u32 stack_id);
void PrintCurrentStack(ThreadState *thr, uptr pc);
void PrintCurrentStackSlow(uptr pc);  // uses libunwind

void Initialize(ThreadState *thr);
void MaybeSpawnBackgroundThread();
int Finalize(ThreadState *thr);

void OnUserAlloc(ThreadState *thr, uptr pc, uptr p, uptr sz, bool write);
void OnUserFree(ThreadState *thr, uptr pc, uptr p, bool write);

void MemoryAccess(ThreadState *thr, uptr pc, uptr addr,
    int kAccessSizeLog, bool kAccessIsWrite, bool kIsAtomic);
void MemoryAccessImpl(ThreadState *thr, uptr addr,
    int kAccessSizeLog, bool kAccessIsWrite, bool kIsAtomic,
    u64 *shadow_mem, Shadow cur);
void MemoryAccessRange(ThreadState *thr, uptr pc, uptr addr,
    uptr size, bool is_write);
void MemoryAccessRangeStep(ThreadState *thr, uptr pc, uptr addr,
    uptr size, uptr step, bool is_write);
void UnalignedMemoryAccess(ThreadState *thr, uptr pc, uptr addr,
    int size, bool kAccessIsWrite, bool kIsAtomic);

const int kSizeLog1 = 0;
const int kSizeLog2 = 1;
const int kSizeLog4 = 2;
const int kSizeLog8 = 3;

void ALWAYS_INLINE MemoryRead(ThreadState *thr, uptr pc,
                                     uptr addr, int kAccessSizeLog) {
  MemoryAccess(thr, pc, addr, kAccessSizeLog, false, false);
}

void ALWAYS_INLINE MemoryWrite(ThreadState *thr, uptr pc,
                                      uptr addr, int kAccessSizeLog) {
  MemoryAccess(thr, pc, addr, kAccessSizeLog, true, false);
}

void ALWAYS_INLINE MemoryReadAtomic(ThreadState *thr, uptr pc,
                                           uptr addr, int kAccessSizeLog) {
  MemoryAccess(thr, pc, addr, kAccessSizeLog, false, true);
}

void ALWAYS_INLINE MemoryWriteAtomic(ThreadState *thr, uptr pc,
                                            uptr addr, int kAccessSizeLog) {
  MemoryAccess(thr, pc, addr, kAccessSizeLog, true, true);
}

void MemoryResetRange(ThreadState *thr, uptr pc, uptr addr, uptr size);
void MemoryRangeFreed(ThreadState *thr, uptr pc, uptr addr, uptr size);
void MemoryRangeImitateWrite(ThreadState *thr, uptr pc, uptr addr, uptr size);

void ThreadIgnoreBegin(ThreadState *thr, uptr pc, bool save_stack = true);
void ThreadIgnoreEnd(ThreadState *thr, uptr pc);
void ThreadIgnoreSyncBegin(ThreadState *thr, uptr pc, bool save_stack = true);
void ThreadIgnoreSyncEnd(ThreadState *thr, uptr pc);

void FuncEntry(ThreadState *thr, uptr pc);
void FuncExit(ThreadState *thr);

int ThreadCreate(ThreadState *thr, uptr pc, uptr uid, bool detached);
void ThreadStart(ThreadState *thr, int tid, tid_t os_id,
                 ThreadType thread_type);
void ThreadFinish(ThreadState *thr);
int ThreadTid(ThreadState *thr, uptr pc, uptr uid);
void ThreadJoin(ThreadState *thr, uptr pc, int tid);
void ThreadDetach(ThreadState *thr, uptr pc, int tid);
void ThreadFinalize(ThreadState *thr);
void ThreadSetName(ThreadState *thr, const char *name);
int ThreadCount(ThreadState *thr);
void ProcessPendingSignals(ThreadState *thr);
void ThreadNotJoined(ThreadState *thr, uptr pc, int tid, uptr uid);

Processor *ProcCreate();
void ProcDestroy(Processor *proc);
void ProcWire(Processor *proc, ThreadState *thr);
void ProcUnwire(Processor *proc, ThreadState *thr);

// Note: the parameter is called flagz, because flags is already taken
// by the global function that returns flags.
void MutexCreate(ThreadState *thr, uptr pc, uptr addr, u32 flagz = 0);
void MutexDestroy(ThreadState *thr, uptr pc, uptr addr, u32 flagz = 0);
void MutexPreLock(ThreadState *thr, uptr pc, uptr addr, u32 flagz = 0);
void MutexPostLock(ThreadState *thr, uptr pc, uptr addr, u32 flagz = 0,
    int rec = 1);
int  MutexUnlock(ThreadState *thr, uptr pc, uptr addr, u32 flagz = 0);
void MutexPreReadLock(ThreadState *thr, uptr pc, uptr addr, u32 flagz = 0);
void MutexPostReadLock(ThreadState *thr, uptr pc, uptr addr, u32 flagz = 0);
void MutexReadUnlock(ThreadState *thr, uptr pc, uptr addr);
void MutexReadOrWriteUnlock(ThreadState *thr, uptr pc, uptr addr);
void MutexRepair(ThreadState *thr, uptr pc, uptr addr);  // call on EOWNERDEAD
void MutexInvalidAccess(ThreadState *thr, uptr pc, uptr addr);

void Acquire(ThreadState *thr, uptr pc, uptr addr);
// AcquireGlobal synchronizes the current thread with all other threads.
// In terms of happens-before relation, it draws a HB edge from all threads
// (where they happen to execute right now) to the current thread. We use it to
// handle Go finalizers. Namely, finalizer goroutine executes AcquireGlobal
// right before executing finalizers. This provides a coarse, but simple
// approximation of the actual required synchronization.
void AcquireGlobal(ThreadState *thr, uptr pc);
void Release(ThreadState *thr, uptr pc, uptr addr);
void ReleaseStore(ThreadState *thr, uptr pc, uptr addr);
void AfterSleep(ThreadState *thr, uptr pc);
void AcquireImpl(ThreadState *thr, uptr pc, SyncClock *c);
void ReleaseImpl(ThreadState *thr, uptr pc, SyncClock *c);
void ReleaseStoreImpl(ThreadState *thr, uptr pc, SyncClock *c);
void AcquireReleaseImpl(ThreadState *thr, uptr pc, SyncClock *c);

// The hacky call uses custom calling convention and an assembly thunk.
// It is considerably faster that a normal call for the caller
// if it is not executed (it is intended for slow paths from hot functions).
// The trick is that the call preserves all registers and the compiler
// does not treat it as a call.
// If it does not work for you, use normal call.
#if !SANITIZER_DEBUG && defined(__x86_64__) && !SANITIZER_MAC
// The caller may not create the stack frame for itself at all,
// so we create a reserve stack frame for it (1024b must be enough).
#define HACKY_CALL(f) \
  __asm__ __volatile__("sub $1024, %%rsp;" \
                       CFI_INL_ADJUST_CFA_OFFSET(1024) \
                       ".hidden " #f "_thunk;" \
                       "call " #f "_thunk;" \
                       "add $1024, %%rsp;" \
                       CFI_INL_ADJUST_CFA_OFFSET(-1024) \
                       ::: "memory", "cc");
#else
#define HACKY_CALL(f) f()
#endif

void TraceSwitch(ThreadState *thr);
uptr TraceTopPC(ThreadState *thr);
uptr TraceSize();
uptr TraceParts();
Trace *ThreadTrace(int tid);

extern "C" void __tsan_trace_switch();
void ALWAYS_INLINE TraceAddEvent(ThreadState *thr, FastState fs,
                                        EventType typ, u64 addr) {
  if (!kCollectHistory)
    return;
  DCHECK_GE((int)typ, 0);
  DCHECK_LE((int)typ, 7);
  DCHECK_EQ(GetLsb(addr, kEventPCBits), addr);
  StatInc(thr, StatEvents);
  u64 pos = fs.GetTracePos();
  if (UNLIKELY((pos % kTracePartSize) == 0)) {
#if !SANITIZER_GO
    HACKY_CALL(__tsan_trace_switch);
#else
    TraceSwitch(thr);
#endif
  }
  Event *trace = (Event*)GetThreadTrace(fs.tid());
  Event *evp = &trace[pos];
  Event ev = (u64)addr | ((u64)typ << kEventPCBits);
  *evp = ev;
}

#if !SANITIZER_GO
uptr ALWAYS_INLINE HeapEnd() {
  return HeapMemEnd() + PrimaryAllocator::AdditionalSize();
}
#endif

ThreadState *FiberCreate(ThreadState *thr, uptr pc, unsigned flags);
void FiberDestroy(ThreadState *thr, uptr pc, ThreadState *fiber);
void FiberSwitch(ThreadState *thr, uptr pc, ThreadState *fiber, unsigned flags);

// These need to match __tsan_switch_to_fiber_* flags defined in
// tsan_interface.h. See documentation there as well.
enum FiberSwitchFlags {
  FiberSwitchFlagNoSync = 1 << 0, // __tsan_switch_to_fiber_no_sync
};

}  // namespace __tsan

#endif  // TSAN_RTL_H