summaryrefslogtreecommitdiff
path: root/lib/sanitizer_common/sanitizer_allocator_primary32.h
blob: 6c682aff64a236da7f652e744ab1d07393bdc0b1 (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
//===-- sanitizer_allocator_primary32.h -------------------------*- C++ -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// Part of the Sanitizer Allocator.
//
//===----------------------------------------------------------------------===//
#ifndef SANITIZER_ALLOCATOR_H
#error This file must be included inside sanitizer_allocator.h
#endif

template<class SizeClassAllocator> struct SizeClassAllocator32LocalCache;

// SizeClassAllocator32 -- allocator for 32-bit address space.
// This allocator can theoretically be used on 64-bit arch, but there it is less
// efficient than SizeClassAllocator64.
//
// [kSpaceBeg, kSpaceBeg + kSpaceSize) is the range of addresses which can
// be returned by MmapOrDie().
//
// Region:
//   a result of a single call to MmapAlignedOrDieOnFatalError(kRegionSize,
//                                                             kRegionSize).
// Since the regions are aligned by kRegionSize, there are exactly
// kNumPossibleRegions possible regions in the address space and so we keep
// a ByteMap possible_regions to store the size classes of each Region.
// 0 size class means the region is not used by the allocator.
//
// One Region is used to allocate chunks of a single size class.
// A Region looks like this:
// UserChunk1 .. UserChunkN <gap> MetaChunkN .. MetaChunk1
//
// In order to avoid false sharing the objects of this class should be
// chache-line aligned.

struct SizeClassAllocator32FlagMasks {  //  Bit masks.
  enum {
    kRandomShuffleChunks = 1,
    kUseSeparateSizeClassForBatch = 2,
  };
};

template <class Params>
class SizeClassAllocator32 {
 public:
  static const uptr kSpaceBeg = Params::kSpaceBeg;
  static const u64 kSpaceSize = Params::kSpaceSize;
  static const uptr kMetadataSize = Params::kMetadataSize;
  typedef typename Params::SizeClassMap SizeClassMap;
  static const uptr kRegionSizeLog = Params::kRegionSizeLog;
  typedef typename Params::ByteMap ByteMap;
  typedef typename Params::MapUnmapCallback MapUnmapCallback;

  static const bool kRandomShuffleChunks = Params::kFlags &
      SizeClassAllocator32FlagMasks::kRandomShuffleChunks;
  static const bool kUseSeparateSizeClassForBatch = Params::kFlags &
      SizeClassAllocator32FlagMasks::kUseSeparateSizeClassForBatch;

  struct TransferBatch {
    static const uptr kMaxNumCached = SizeClassMap::kMaxNumCachedHint - 2;
    void SetFromArray(uptr region_beg_unused, void *batch[], uptr count) {
      count_ = count;
      CHECK_LE(count_, kMaxNumCached);
      for (uptr i = 0; i < count; i++)
        batch_[i] = batch[i];
    }
    uptr Count() const { return count_; }
    void Clear() { count_ = 0; }
    void Add(void *ptr) {
      batch_[count_++] = ptr;
      CHECK_LE(count_, kMaxNumCached);
    }
    void CopyToArray(void *to_batch[]) {
      for (uptr i = 0, n = Count(); i < n; i++)
        to_batch[i] = batch_[i];
    }

    // How much memory do we need for a batch containing n elements.
    static uptr AllocationSizeRequiredForNElements(uptr n) {
      return sizeof(uptr) * 2 + sizeof(void *) * n;
    }
    static uptr MaxCached(uptr class_id) {
      return Min(kMaxNumCached, SizeClassMap::MaxCachedHint(class_id));
    }

    TransferBatch *next;

   private:
    uptr count_;
    void *batch_[kMaxNumCached];
  };

  static const uptr kBatchSize = sizeof(TransferBatch);
  COMPILER_CHECK((kBatchSize & (kBatchSize - 1)) == 0);
  COMPILER_CHECK(kBatchSize == SizeClassMap::kMaxNumCachedHint * sizeof(uptr));

  static uptr ClassIdToSize(uptr class_id) {
    return (class_id == SizeClassMap::kBatchClassID) ?
        kBatchSize : SizeClassMap::Size(class_id);
  }

  typedef SizeClassAllocator32<Params> ThisT;
  typedef SizeClassAllocator32LocalCache<ThisT> AllocatorCache;

  void Init(s32 release_to_os_interval_ms) {
    possible_regions.TestOnlyInit();
    internal_memset(size_class_info_array, 0, sizeof(size_class_info_array));
  }

  s32 ReleaseToOSIntervalMs() const {
    return kReleaseToOSIntervalNever;
  }

  void SetReleaseToOSIntervalMs(s32 release_to_os_interval_ms) {
    // This is empty here. Currently only implemented in 64-bit allocator.
  }

  void ForceReleaseToOS() {
    // Currently implemented in 64-bit allocator only.
  }

  void *MapWithCallback(uptr size) {
    void *res = MmapOrDie(size, "SizeClassAllocator32");
    MapUnmapCallback().OnMap((uptr)res, size);
    return res;
  }

  void UnmapWithCallback(uptr beg, uptr size) {
    MapUnmapCallback().OnUnmap(beg, size);
    UnmapOrDie(reinterpret_cast<void *>(beg), size);
  }

  static bool CanAllocate(uptr size, uptr alignment) {
    return size <= SizeClassMap::kMaxSize &&
      alignment <= SizeClassMap::kMaxSize;
  }

  void *GetMetaData(const void *p) {
    CHECK(PointerIsMine(p));
    uptr mem = reinterpret_cast<uptr>(p);
    uptr beg = ComputeRegionBeg(mem);
    uptr size = ClassIdToSize(GetSizeClass(p));
    u32 offset = mem - beg;
    uptr n = offset / (u32)size;  // 32-bit division
    uptr meta = (beg + kRegionSize) - (n + 1) * kMetadataSize;
    return reinterpret_cast<void*>(meta);
  }

  NOINLINE TransferBatch *AllocateBatch(AllocatorStats *stat, AllocatorCache *c,
                                        uptr class_id) {
    CHECK_LT(class_id, kNumClasses);
    SizeClassInfo *sci = GetSizeClassInfo(class_id);
    SpinMutexLock l(&sci->mutex);
    if (sci->free_list.empty() &&
        UNLIKELY(!PopulateFreeList(stat, c, sci, class_id)))
      return nullptr;
    CHECK(!sci->free_list.empty());
    TransferBatch *b = sci->free_list.front();
    sci->free_list.pop_front();
    return b;
  }

  NOINLINE void DeallocateBatch(AllocatorStats *stat, uptr class_id,
                                TransferBatch *b) {
    CHECK_LT(class_id, kNumClasses);
    CHECK_GT(b->Count(), 0);
    SizeClassInfo *sci = GetSizeClassInfo(class_id);
    SpinMutexLock l(&sci->mutex);
    sci->free_list.push_front(b);
  }

  uptr GetRegionBeginBySizeClass(uptr class_id) { return 0; }

  bool PointerIsMine(const void *p) {
    uptr mem = reinterpret_cast<uptr>(p);
    if (mem < kSpaceBeg || mem >= kSpaceBeg + kSpaceSize)
      return false;
    return GetSizeClass(p) != 0;
  }

  uptr GetSizeClass(const void *p) {
    return possible_regions[ComputeRegionId(reinterpret_cast<uptr>(p))];
  }

  void *GetBlockBegin(const void *p) {
    CHECK(PointerIsMine(p));
    uptr mem = reinterpret_cast<uptr>(p);
    uptr beg = ComputeRegionBeg(mem);
    uptr size = ClassIdToSize(GetSizeClass(p));
    u32 offset = mem - beg;
    u32 n = offset / (u32)size;  // 32-bit division
    uptr res = beg + (n * (u32)size);
    return reinterpret_cast<void*>(res);
  }

  uptr GetActuallyAllocatedSize(void *p) {
    CHECK(PointerIsMine(p));
    return ClassIdToSize(GetSizeClass(p));
  }

  uptr ClassID(uptr size) { return SizeClassMap::ClassID(size); }

  uptr TotalMemoryUsed() {
    // No need to lock here.
    uptr res = 0;
    for (uptr i = 0; i < kNumPossibleRegions; i++)
      if (possible_regions[i])
        res += kRegionSize;
    return res;
  }

  void TestOnlyUnmap() {
    for (uptr i = 0; i < kNumPossibleRegions; i++)
      if (possible_regions[i])
        UnmapWithCallback((i * kRegionSize), kRegionSize);
  }

  // ForceLock() and ForceUnlock() are needed to implement Darwin malloc zone
  // introspection API.
  void ForceLock() {
    for (uptr i = 0; i < kNumClasses; i++) {
      GetSizeClassInfo(i)->mutex.Lock();
    }
  }

  void ForceUnlock() {
    for (int i = kNumClasses - 1; i >= 0; i--) {
      GetSizeClassInfo(i)->mutex.Unlock();
    }
  }

  // Iterate over all existing chunks.
  // The allocator must be locked when calling this function.
  void ForEachChunk(ForEachChunkCallback callback, void *arg) {
    for (uptr region = 0; region < kNumPossibleRegions; region++)
      if (possible_regions[region]) {
        uptr chunk_size = ClassIdToSize(possible_regions[region]);
        uptr max_chunks_in_region = kRegionSize / (chunk_size + kMetadataSize);
        uptr region_beg = region * kRegionSize;
        for (uptr chunk = region_beg;
             chunk < region_beg + max_chunks_in_region * chunk_size;
             chunk += chunk_size) {
          // Too slow: CHECK_EQ((void *)chunk, GetBlockBegin((void *)chunk));
          callback(chunk, arg);
        }
      }
  }

  void PrintStats() {
  }

  static uptr AdditionalSize() {
    return 0;
  }

  typedef SizeClassMap SizeClassMapT;
  static const uptr kNumClasses = SizeClassMap::kNumClasses;

 private:
  static const uptr kRegionSize = 1 << kRegionSizeLog;
  static const uptr kNumPossibleRegions = kSpaceSize / kRegionSize;

  struct SizeClassInfo {
    SpinMutex mutex;
    IntrusiveList<TransferBatch> free_list;
    u32 rand_state;
    char padding[kCacheLineSize - 2 * sizeof(uptr) -
                 sizeof(IntrusiveList<TransferBatch>)];
  };
  COMPILER_CHECK(sizeof(SizeClassInfo) == kCacheLineSize);

  uptr ComputeRegionId(uptr mem) {
    uptr res = mem >> kRegionSizeLog;
    CHECK_LT(res, kNumPossibleRegions);
    return res;
  }

  uptr ComputeRegionBeg(uptr mem) {
    return mem & ~(kRegionSize - 1);
  }

  uptr AllocateRegion(AllocatorStats *stat, uptr class_id) {
    CHECK_LT(class_id, kNumClasses);
    uptr res = reinterpret_cast<uptr>(MmapAlignedOrDieOnFatalError(
        kRegionSize, kRegionSize, "SizeClassAllocator32"));
    if (UNLIKELY(!res))
      return 0;
    MapUnmapCallback().OnMap(res, kRegionSize);
    stat->Add(AllocatorStatMapped, kRegionSize);
    CHECK(IsAligned(res, kRegionSize));
    possible_regions.set(ComputeRegionId(res), static_cast<u8>(class_id));
    return res;
  }

  SizeClassInfo *GetSizeClassInfo(uptr class_id) {
    CHECK_LT(class_id, kNumClasses);
    return &size_class_info_array[class_id];
  }

  bool PopulateBatches(AllocatorCache *c, SizeClassInfo *sci, uptr class_id,
                       TransferBatch **current_batch, uptr max_count,
                       uptr *pointers_array, uptr count) {
    // If using a separate class for batches, we do not need to shuffle it.
    if (kRandomShuffleChunks && (!kUseSeparateSizeClassForBatch ||
        class_id != SizeClassMap::kBatchClassID))
      RandomShuffle(pointers_array, count, &sci->rand_state);
    TransferBatch *b = *current_batch;
    for (uptr i = 0; i < count; i++) {
      if (!b) {
        b = c->CreateBatch(class_id, this, (TransferBatch*)pointers_array[i]);
        if (UNLIKELY(!b))
          return false;
        b->Clear();
      }
      b->Add((void*)pointers_array[i]);
      if (b->Count() == max_count) {
        sci->free_list.push_back(b);
        b = nullptr;
      }
    }
    *current_batch = b;
    return true;
  }

  bool PopulateFreeList(AllocatorStats *stat, AllocatorCache *c,
                        SizeClassInfo *sci, uptr class_id) {
    uptr size = ClassIdToSize(class_id);
    uptr reg = AllocateRegion(stat, class_id);
    if (UNLIKELY(!reg))
      return false;
    if (kRandomShuffleChunks)
      if (UNLIKELY(sci->rand_state == 0))
        // The random state is initialized from ASLR (PIE) and time.
        sci->rand_state = reinterpret_cast<uptr>(sci) ^ NanoTime();
    uptr n_chunks = kRegionSize / (size + kMetadataSize);
    uptr max_count = TransferBatch::MaxCached(class_id);
    CHECK_GT(max_count, 0);
    TransferBatch *b = nullptr;
    const uptr kShuffleArraySize = 48;
    uptr shuffle_array[kShuffleArraySize];
    uptr count = 0;
    for (uptr i = reg; i < reg + n_chunks * size; i += size) {
      shuffle_array[count++] = i;
      if (count == kShuffleArraySize) {
        if (UNLIKELY(!PopulateBatches(c, sci, class_id, &b, max_count,
                                      shuffle_array, count)))
          return false;
        count = 0;
      }
    }
    if (count) {
      if (UNLIKELY(!PopulateBatches(c, sci, class_id, &b, max_count,
                                    shuffle_array, count)))
        return false;
    }
    if (b) {
      CHECK_GT(b->Count(), 0);
      sci->free_list.push_back(b);
    }
    return true;
  }

  ByteMap possible_regions;
  SizeClassInfo size_class_info_array[kNumClasses];
};