[scudo] Minor changes and refactoring

[cryptoad]

Summary

This is part of D31947 that is being split into several smaller changes.

This one deals with all the minor changes, more specifically:

• Rename some variables and functions to make their purpose clearer;
• Reorder some code;
• Mark the hot termination incurring checks as UNLIKELY; if they happen, the program will die anyway;
• Add a getScudoChunk method;
• Add an eraseHeader method to ScudoChunk that will clear a header with 0s;
• Add a parameter to allocate to know if the allocated chunk should be filled with zeros. This allows calloc to not have to call GetActuallyAllocatedSize; more changes to get rid of this function on the hot paths will follow;
• reallocate was missing a check to verify that the pointer is properly aligned on MinAlignment;
• The Stats in the secondary have to be protected by a mutex as the Add and Sub methods are actually not atomic;
• The software CRC32 function was moved to the header to allow for inlining.

[cryptoad]

Additional rename of a variable I forgot in the first round.

[dvyukov]

LGTM with a nit

lib/scudo/scudo_allocator.cpp

363

StaticSpinMutex does not need initialization. If anything this can only do harm if the mutex turned out to be locked by somebody else at the moment.
Drop this.

[cryptoad]

Addressing review comments.

[cryptoad]

Thank you Dmitry.

lib/scudo/scudo_allocator.h

enum ChunkState : u8 {
   ChunkAllocated  = 1,
   ChunkQuarantine = 2
 };
 
 // Our header requires 64 bits of storage. Having the offset saves us from
 // using functions such as GetBlockBegin, that is fairly costly. Our first
 // implementation used the MetaData as well, which offers the advantage of
 // being stored away from the chunk itself, but accessing it was costly as
-// well. The header will be atomically loaded and stored using the 16-byte
-// primitives offered by the platform (likely requires cmpxchg16b support).
+// well. The header will be atomically loaded and stored.
 typedef u64 PackedHeader;
 struct UnpackedHeader {
   u64 Checksum    : 16;
   u64 UnusedBytes : 20; // Needed for reallocation purposes.
   u64 State       : 2;  // available, allocated, or quarantined
   u64 AllocType   : 2;  // malloc, new, new[], or memalign
   u64 Offset      : 16; // Offset from the beginning of the backend
                         // allocation to the beginning of the chunk itself,

lib/scudo/scudo_allocator.cpp

 #include "scudo_allocator.h"
 #include "scudo_utils.h"
 
 #include "sanitizer_common/sanitizer_allocator_interface.h"
 #include "sanitizer_common/sanitizer_quarantine.h"
 
 #include <limits.h>
 #include <pthread.h>
-
-#include <cstring>
+#include <string.h>
 
 namespace __scudo {
 
 #if SANITIZER_CAN_USE_ALLOCATOR64
 const uptr AllocatorSpace = ~0ULL;
 const uptr AllocatorSize = 0x40000000000ULL;
 typedef DefaultSizeClassMap SizeClassMap;
 struct AP {

 typedef DefaultSizeClassMap SizeClassMap;
 typedef SizeClassAllocator32<0, SANITIZER_MMAP_RANGE_SIZE, 0, SizeClassMap,
     RegionSizeLog, ByteMap> PrimaryAllocator;
 #endif  // SANITIZER_CAN_USE_ALLOCATOR64
 
 typedef SizeClassAllocatorLocalCache<PrimaryAllocator> AllocatorCache;
 typedef ScudoLargeMmapAllocator SecondaryAllocator;
 typedef CombinedAllocator<PrimaryAllocator, AllocatorCache, SecondaryAllocator>
-  ScudoAllocator;
+  ScudoBackendAllocator;
 
-static ScudoAllocator &getAllocator();
+static ScudoBackendAllocator &getBackendAllocator();
 
 static thread_local Xorshift128Plus Prng;
 // Global static cookie, initialized at start-up.
 static uptr Cookie;
 
 // We default to software CRC32 if the alternatives are not supported, either
 // at compilation or at runtime.
 static atomic_uint8_t HashAlgorithm = { CRC32Software };
struct ScudoChunk : UnpackedHeader {
   void *getAllocBeg(UnpackedHeader *Header) {
     return reinterpret_cast<void *>(
         reinterpret_cast<uptr>(this) - (Header->Offset << MinAlignmentLog));
   }
 
   // Returns the usable size for a chunk, meaning the amount of bytes from the
   // beginning of the user data to the end of the backend allocated chunk.
   uptr getUsableSize(UnpackedHeader *Header) {
-    uptr Size = getAllocator().GetActuallyAllocatedSize(getAllocBeg(Header));
+    uptr Size = getBackendAllocator().GetActuallyAllocatedSize(
+        getAllocBeg(Header));
     if (Size == 0)
-      return Size;
+      return 0;
     return Size - AlignedChunkHeaderSize - (Header->Offset << MinAlignmentLog);
   }
 
   // Compute the checksum of the Chunk pointer and its ChunkHeader.
   u16 computeChecksum(UnpackedHeader *Header) const {
     UnpackedHeader ZeroChecksumHeader = *Header;
     ZeroChecksumHeader.Checksum = 0;
     uptr HeaderHolder[sizeof(UnpackedHeader) / sizeof(uptr)];
     memcpy(&HeaderHolder, &ZeroChecksumHeader, sizeof(HeaderHolder));
     u8 HashType = atomic_load_relaxed(&HashAlgorithm);
     u32 Crc = computeCRC32(Cookie, reinterpret_cast<uptr>(this), HashType);
     for (uptr i = 0; i < ARRAY_SIZE(HeaderHolder); i++)
       Crc = computeCRC32(Crc, HeaderHolder[i], HashType);
     return static_cast<u16>(Crc);
   }
 
-  // Checks the validity of a chunk by verifying its checksum.
+  // Checks the validity of a chunk by verifying its checksum. It doesn't
+  // incur termination in the event of an invalid chunk.
   bool isValid() {
     UnpackedHeader NewUnpackedHeader;
     const AtomicPackedHeader *AtomicHeader =
         reinterpret_cast<const AtomicPackedHeader *>(this);
     PackedHeader NewPackedHeader = atomic_load_relaxed(AtomicHeader);
     NewUnpackedHeader = bit_cast<UnpackedHeader>(NewPackedHeader);
     return (NewUnpackedHeader.Checksum == computeChecksum(&NewUnpackedHeader));
   }
 
+  // Nulls out a chunk header. When returning the chunk to the backend, there
+  // is no need to store a valid ChunkAvailable header, as this would be
+  // computationally expensive. Zeroing out serves the same purpose by making
+  // the header invalid. In the extremely rare event where 0 would be a valid
+  // checksum for the chunk, the state of the chunk is ChunkAvailable anyway.
+  COMPILER_CHECK(ChunkAvailable == 0);
+  void eraseHeader() {
+    PackedHeader NullPackedHeader = 0;
+    AtomicPackedHeader *AtomicHeader =
+        reinterpret_cast<AtomicPackedHeader *>(this);
+    atomic_store_relaxed(AtomicHeader, NullPackedHeader);
+  }
+
   // Loads and unpacks the header, verifying the checksum in the process.
   void loadHeader(UnpackedHeader *NewUnpackedHeader) const {
     const AtomicPackedHeader *AtomicHeader =
         reinterpret_cast<const AtomicPackedHeader *>(this);
     PackedHeader NewPackedHeader = atomic_load_relaxed(AtomicHeader);
     *NewUnpackedHeader = bit_cast<UnpackedHeader>(NewPackedHeader);
-    if (NewUnpackedHeader->Checksum != computeChecksum(NewUnpackedHeader)) {
+    if (UNLIKELY(NewUnpackedHeader->Checksum !=
+        computeChecksum(NewUnpackedHeader))) {
       dieWithMessage("ERROR: corrupted chunk header at address %p\n", this);
     }
   }
 
   // Packs and stores the header, computing the checksum in the process.
   void storeHeader(UnpackedHeader *NewUnpackedHeader) {
     NewUnpackedHeader->Checksum = computeChecksum(NewUnpackedHeader);
     PackedHeader NewPackedHeader = bit_cast<PackedHeader>(*NewUnpackedHeader);
     AtomicPackedHeader *AtomicHeader =
         reinterpret_cast<AtomicPackedHeader *>(this);
     atomic_store_relaxed(AtomicHeader, NewPackedHeader);
   }
 
   // Packs and stores the header, computing the checksum in the process. We
   // compare the current header with the expected provided one to ensure that
   // we are not being raced by a corruption occurring in another thread.
   void compareExchangeHeader(UnpackedHeader *NewUnpackedHeader,
                              UnpackedHeader *OldUnpackedHeader) {
     NewUnpackedHeader->Checksum = computeChecksum(NewUnpackedHeader);
     PackedHeader NewPackedHeader = bit_cast<PackedHeader>(*NewUnpackedHeader);
     PackedHeader OldPackedHeader = bit_cast<PackedHeader>(*OldUnpackedHeader);
     AtomicPackedHeader *AtomicHeader =
         reinterpret_cast<AtomicPackedHeader *>(this);
-    if (!atomic_compare_exchange_strong(AtomicHeader,
+    if (UNLIKELY(!atomic_compare_exchange_strong(AtomicHeader,
                                                  &OldPackedHeader,
                                                  NewPackedHeader,
-                                        memory_order_relaxed)) {
+                                                 memory_order_relaxed))) {
       dieWithMessage("ERROR: race on chunk header at address %p\n", this);
     }
   }
 };
 
+ScudoChunk *getScudoChunk(uptr UserBeg) {
+  return reinterpret_cast<ScudoChunk *>(UserBeg - AlignedChunkHeaderSize);
+}
+
 static bool ScudoInitIsRunning = false;
 
 static pthread_once_t GlobalInited = PTHREAD_ONCE_INIT;
 static pthread_key_t PThreadKey;
 
 static thread_local bool ThreadInited = false;
 static thread_local bool ThreadTornDown = false;
 static thread_local AllocatorCache Cache;
 
 static void teardownThread(void *p) {
   uptr v = reinterpret_cast<uptr>(p);
   // The glibc POSIX thread-local-storage deallocation routine calls user
   // provided destructors in a loop of PTHREAD_DESTRUCTOR_ITERATIONS.
   // We want to be called last since other destructors might call free and the
   // like, so we wait until PTHREAD_DESTRUCTOR_ITERATIONS before draining the
   // quarantine and swallowing the cache.
   if (v < PTHREAD_DESTRUCTOR_ITERATIONS) {
     pthread_setspecific(PThreadKey, reinterpret_cast<void *>(v + 1));
     return;
   }
   drainQuarantine();
-  getAllocator().DestroyCache(&Cache);
+  getBackendAllocator().DestroyCache(&Cache);
   ThreadTornDown = true;
 }
 
 static void initInternal() {
   SanitizerToolName = "Scudo";
   CHECK(!ScudoInitIsRunning && "Scudo init calls itself!");
   ScudoInitIsRunning = true;
 

 static void initGlobal() {
   pthread_key_create(&PThreadKey, teardownThread);
   initInternal();
 }
 
 static void NOINLINE initThread() {
   pthread_once(&GlobalInited, initGlobal);
   pthread_setspecific(PThreadKey, reinterpret_cast<void *>(1));
-  getAllocator().InitCache(&Cache);
+  getBackendAllocator().InitCache(&Cache);
   ThreadInited = true;
 }
 
 struct QuarantineCallback {
   explicit QuarantineCallback(AllocatorCache *Cache)
     : Cache_(Cache) {}
 
   // Chunk recycling function, returns a quarantined chunk to the backend.
   void Recycle(ScudoChunk *Chunk) {
     UnpackedHeader Header;
     Chunk->loadHeader(&Header);
-    if (Header.State != ChunkQuarantine) {
+    if (UNLIKELY(Header.State != ChunkQuarantine)) {
       dieWithMessage("ERROR: invalid chunk state when recycling address %p\n",
                      Chunk);
     }
+    Chunk->eraseHeader();
     void *Ptr = Chunk->getAllocBeg(&Header);
-    getAllocator().Deallocate(Cache_, Ptr);
+    getBackendAllocator().Deallocate(Cache_, Ptr);
   }
 
   /// Internal quarantine allocation and deallocation functions.
   void *Allocate(uptr Size) {
-    // The internal quarantine memory cannot be protected by us. But the only
-    // structures allocated are QuarantineBatch, that are 8KB for x64. So we
-    // will use mmap for those, and given that Deallocate doesn't pass a size
-    // in, we enforce the size of the allocation to be sizeof(QuarantineBatch).
-    // TODO(kostyak): switching to mmap impacts greatly performances, we have
-    //                to find another solution
-    // CHECK_EQ(Size, sizeof(QuarantineBatch));
-    // return MmapOrDie(Size, "QuarantineBatch");
-    return getAllocator().Allocate(Cache_, Size, 1, false);
+    // TODO(kostyak): figure out the best way to protect the batches.
+    return getBackendAllocator().Allocate(Cache_, Size, MinAlignment);
   }
 
   void Deallocate(void *Ptr) {
-    // UnmapOrDie(Ptr, sizeof(QuarantineBatch));
-    getAllocator().Deallocate(Cache_, Ptr);
+    getBackendAllocator().Deallocate(Cache_, Ptr);
   }
 
   AllocatorCache *Cache_;
 };
 
 typedef Quarantine<QuarantineCallback, ScudoChunk> ScudoQuarantine;
-typedef ScudoQuarantine::Cache QuarantineCache;
-static thread_local QuarantineCache ThreadQuarantineCache;
+typedef ScudoQuarantine::Cache ScudoQuarantineCache;
+static thread_local ScudoQuarantineCache ThreadQuarantineCache;
 
 void AllocatorOptions::setFrom(const Flags *f, const CommonFlags *cf) {
   MayReturnNull = cf->allocator_may_return_null;
   ReleaseToOSIntervalMs = cf->allocator_release_to_os_interval_ms;
   QuarantineSizeMb = f->QuarantineSizeMb;
   ThreadLocalQuarantineSizeKb = f->ThreadLocalQuarantineSizeKb;
   DeallocationTypeMismatch = f->DeallocationTypeMismatch;
   DeleteSizeMismatch = f->DeleteSizeMismatch;
   ZeroContents = f->ZeroContents;
 }
 
 void AllocatorOptions::copyTo(Flags *f, CommonFlags *cf) const {
   cf->allocator_may_return_null = MayReturnNull;
   cf->allocator_release_to_os_interval_ms = ReleaseToOSIntervalMs;
   f->QuarantineSizeMb = QuarantineSizeMb;
   f->ThreadLocalQuarantineSizeKb = ThreadLocalQuarantineSizeKb;
   f->DeallocationTypeMismatch = DeallocationTypeMismatch;
   f->DeleteSizeMismatch = DeleteSizeMismatch;
   f->ZeroContents = ZeroContents;
 }
 
-struct Allocator {
+struct ScudoAllocator {
   static const uptr MaxAllowedMallocSize =
       FIRST_32_SECOND_64(2UL << 30, 1ULL << 40);
 
-  ScudoAllocator BackendAllocator;
+  ScudoBackendAllocator BackendAllocator;
   ScudoQuarantine AllocatorQuarantine;
 
   // The fallback caches are used when the thread local caches have been
   // 'detroyed' on thread tear-down. They are protected by a Mutex as they can
   // be accessed by different threads.
   StaticSpinMutex FallbackMutex;
   AllocatorCache FallbackAllocatorCache;
-  QuarantineCache FallbackQuarantineCache;
+  ScudoQuarantineCache FallbackQuarantineCache;
 
   bool DeallocationTypeMismatch;
   bool ZeroContents;
   bool DeleteSizeMismatch;
 
-  explicit Allocator(LinkerInitialized)
+  explicit ScudoAllocator(LinkerInitialized)
     : AllocatorQuarantine(LINKER_INITIALIZED),
       FallbackQuarantineCache(LINKER_INITIALIZED) {}
 
   void init(const AllocatorOptions &Options) {
     // 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 0. In the case of the Primary, the worst case
     // scenario happens in the last size class, when the backend allocation
void init(const AllocatorOptions &Options) {
 
     DeallocationTypeMismatch = Options.DeallocationTypeMismatch;
     DeleteSizeMismatch = Options.DeleteSizeMismatch;
     ZeroContents = Options.ZeroContents;
     BackendAllocator.Init(Options.MayReturnNull, Options.ReleaseToOSIntervalMs);
     AllocatorQuarantine.Init(
         static_cast<uptr>(Options.QuarantineSizeMb) << 20,
         static_cast<uptr>(Options.ThreadLocalQuarantineSizeKb) << 10);
     BackendAllocator.InitCache(&FallbackAllocatorCache);
-    Cookie = Prng.Next();
+    Cookie = Prng.getNext();
   }
 
-  // Helper function that checks for a valid Scudo chunk.
+  // Helper function that checks for a valid Scudo chunk. nullptr isn't.
   bool isValidPointer(const void *UserPtr) {
     if (UNLIKELY(!ThreadInited))
       initThread();
-    uptr ChunkBeg = reinterpret_cast<uptr>(UserPtr);
-    if (!IsAligned(ChunkBeg, MinAlignment)) {
+    if (!UserPtr)
       return false;
-    }
-    ScudoChunk *Chunk =
-        reinterpret_cast<ScudoChunk *>(ChunkBeg - AlignedChunkHeaderSize);
-    return Chunk->isValid();
+    uptr UserBeg = reinterpret_cast<uptr>(UserPtr);
+    if (!IsAligned(UserBeg, MinAlignment))
+      return false;
+    return getScudoChunk(UserBeg)->isValid();
   }
 
   // Allocates a chunk.
-  void *allocate(uptr Size, uptr Alignment, AllocType Type) {
+  void *allocate(uptr Size, uptr Alignment, AllocType Type,
+                 bool ForceZeroContents = false) {
     if (UNLIKELY(!ThreadInited))
       initThread();
-    if (!IsPowerOfTwo(Alignment)) {
+    if (UNLIKELY(!IsPowerOfTwo(Alignment))) {
       dieWithMessage("ERROR: alignment is not a power of 2\n");
     }
     if (Alignment > MaxAlignment)
       return BackendAllocator.ReturnNullOrDieOnBadRequest();
     if (Alignment < MinAlignment)
       Alignment = MinAlignment;
-    if (Size == 0)
-      Size = 1;
     if (Size >= MaxAllowedMallocSize)
       return BackendAllocator.ReturnNullOrDieOnBadRequest();
+    if (Size == 0)
+      Size = 1;
 
     uptr NeededSize = RoundUpTo(Size, MinAlignment) + AlignedChunkHeaderSize;
     if (Alignment > MinAlignment)
       NeededSize += Alignment;
     if (NeededSize >= MaxAllowedMallocSize)
       return BackendAllocator.ReturnNullOrDieOnBadRequest();
 
     // Primary backed and Secondary backed allocations have a different
     // treatment. We deal with alignment requirements of Primary serviced
     // allocations here, but the Secondary will take care of its own alignment
     // needs, which means we also have to work around some limitations of the
     // combined allocator to accommodate the situation.
     bool FromPrimary = PrimaryAllocator::CanAllocate(NeededSize, MinAlignment);
 
     void *Ptr;
+    uptr AllocationAlignment = FromPrimary ? MinAlignment : Alignment;
     if (LIKELY(!ThreadTornDown)) {
-      Ptr = BackendAllocator.Allocate(&Cache, NeededSize,
-                                      FromPrimary ? MinAlignment : Alignment);
+      Ptr = BackendAllocator.Allocate(&Cache, NeededSize, AllocationAlignment);
     } else {
       SpinMutexLock l(&FallbackMutex);
       Ptr = BackendAllocator.Allocate(&FallbackAllocatorCache, NeededSize,
-                                      FromPrimary ? MinAlignment : Alignment);
+                                      AllocationAlignment);
     }
     if (!Ptr)
       return BackendAllocator.ReturnNullOrDieOnOOM();
 
     uptr AllocBeg = reinterpret_cast<uptr>(Ptr);
     // If the allocation was serviced by the secondary, the returned pointer
     // accounts for ChunkHeaderSize to pass the alignment check of the combined
     // allocator. Adjust it here.
     if (!FromPrimary) {
       AllocBeg -= AlignedChunkHeaderSize;
       if (Alignment > MinAlignment)
         NeededSize -= Alignment;
     }
 
     uptr ActuallyAllocatedSize = BackendAllocator.GetActuallyAllocatedSize(
         reinterpret_cast<void *>(AllocBeg));
     // If requested, we will zero out the entire contents of the returned chunk.
-    if (ZeroContents && FromPrimary)
+    if ((ForceZeroContents || ZeroContents) && FromPrimary)
        memset(Ptr, 0, ActuallyAllocatedSize);
 
-    uptr ChunkBeg = AllocBeg + AlignedChunkHeaderSize;
-    if (!IsAligned(ChunkBeg, Alignment))
-      ChunkBeg = RoundUpTo(ChunkBeg, Alignment);
-    CHECK_LE(ChunkBeg + Size, AllocBeg + NeededSize);
-    ScudoChunk *Chunk =
-        reinterpret_cast<ScudoChunk *>(ChunkBeg - AlignedChunkHeaderSize);
+    uptr UserBeg = AllocBeg + AlignedChunkHeaderSize;
+    if (!IsAligned(UserBeg, Alignment))
+      UserBeg = RoundUpTo(UserBeg, Alignment);
+    CHECK_LE(UserBeg + Size, AllocBeg + NeededSize);
     UnpackedHeader Header = {};
     Header.State = ChunkAllocated;
-    uptr Offset = ChunkBeg - AlignedChunkHeaderSize - AllocBeg;
+    uptr Offset = UserBeg - AlignedChunkHeaderSize - AllocBeg;
     Header.Offset = Offset >> MinAlignmentLog;
     Header.AllocType = Type;
     Header.UnusedBytes = ActuallyAllocatedSize - Offset -
         AlignedChunkHeaderSize - Size;
-    Header.Salt = static_cast<u8>(Prng.Next());
-    Chunk->storeHeader(&Header);
-    void *UserPtr = reinterpret_cast<void *>(ChunkBeg);
-    // TODO(kostyak): hooks sound like a terrible idea security wise but might
-    //                be needed for things to work properly?
+    Header.Salt = static_cast<u8>(Prng.getNext());
+    getScudoChunk(UserBeg)->storeHeader(&Header);
+    void *UserPtr = reinterpret_cast<void *>(UserBeg);
     // if (&__sanitizer_malloc_hook) __sanitizer_malloc_hook(UserPtr, Size);
     return UserPtr;
   }
 
   // Deallocates a Chunk, which means adding it to the delayed free list (or
   // Quarantine).
   void deallocate(void *UserPtr, uptr DeleteSize, AllocType Type) {
     if (UNLIKELY(!ThreadInited))
       initThread();
-    // TODO(kostyak): see hook comment above
     // if (&__sanitizer_free_hook) __sanitizer_free_hook(UserPtr);
     if (!UserPtr)
       return;
-    uptr ChunkBeg = reinterpret_cast<uptr>(UserPtr);
-    if (!IsAligned(ChunkBeg, MinAlignment)) {
+    uptr UserBeg = reinterpret_cast<uptr>(UserPtr);
+    if (UNLIKELY(!IsAligned(UserBeg, MinAlignment))) {
       dieWithMessage("ERROR: attempted to deallocate a chunk not properly "
                      "aligned at address %p\n", UserPtr);
     }
-    ScudoChunk *Chunk =
-        reinterpret_cast<ScudoChunk *>(ChunkBeg - AlignedChunkHeaderSize);
+    ScudoChunk *Chunk = getScudoChunk(UserBeg);
     UnpackedHeader OldHeader;
     Chunk->loadHeader(&OldHeader);
-    if (OldHeader.State != ChunkAllocated) {
+    if (UNLIKELY(OldHeader.State != ChunkAllocated)) {
       dieWithMessage("ERROR: invalid chunk state when deallocating address "
                      "%p\n", UserPtr);
     }
-    uptr UsableSize = Chunk->getUsableSize(&OldHeader);
-    UnpackedHeader NewHeader = OldHeader;
-    NewHeader.State = ChunkQuarantine;
-    Chunk->compareExchangeHeader(&NewHeader, &OldHeader);
     if (DeallocationTypeMismatch) {
       // The deallocation type has to match the allocation one.
-      if (NewHeader.AllocType != Type) {
+      if (OldHeader.AllocType != Type) {
         // With the exception of memalign'd Chunks, that can be still be free'd.
-        if (NewHeader.AllocType != FromMemalign || Type != FromMalloc) {
+        if (OldHeader.AllocType != FromMemalign || Type != FromMalloc) {
           dieWithMessage("ERROR: allocation type mismatch on address %p\n",
-                         Chunk);
+                         UserPtr);
         }
       }
     }
+    uptr UsableSize = Chunk->getUsableSize(&OldHeader);
     uptr Size = UsableSize - OldHeader.UnusedBytes;
     if (DeleteSizeMismatch) {
       if (DeleteSize && DeleteSize != Size) {
         dieWithMessage("ERROR: invalid sized delete on chunk at address %p\n",
-                       Chunk);
+                       UserPtr);
       }
     }
 
+    UnpackedHeader NewHeader = OldHeader;
+    NewHeader.State = ChunkQuarantine;
+    Chunk->compareExchangeHeader(&NewHeader, &OldHeader);
+
     if (LIKELY(!ThreadTornDown)) {
       AllocatorQuarantine.Put(&ThreadQuarantineCache,
                               QuarantineCallback(&Cache), Chunk, UsableSize);
     } else {
       SpinMutexLock l(&FallbackMutex);
       AllocatorQuarantine.Put(&FallbackQuarantineCache,
                               QuarantineCallback(&FallbackAllocatorCache),
                               Chunk, UsableSize);
     }
   }
 
   // Reallocates a chunk. We can save on a new allocation if the new requested
   // size still fits in the chunk.
   void *reallocate(void *OldPtr, uptr NewSize) {
     if (UNLIKELY(!ThreadInited))
       initThread();
-    uptr ChunkBeg = reinterpret_cast<uptr>(OldPtr);
-    ScudoChunk *Chunk =
-        reinterpret_cast<ScudoChunk *>(ChunkBeg - AlignedChunkHeaderSize);
+    uptr UserBeg = reinterpret_cast<uptr>(OldPtr);
+    if (UNLIKELY(!IsAligned(UserBeg, MinAlignment))) {
+      dieWithMessage("ERROR: attempted to reallocate a chunk not properly "
+                     "aligned at address %p\n", OldPtr);
+    }
+    ScudoChunk *Chunk = getScudoChunk(UserBeg);
     UnpackedHeader OldHeader;
     Chunk->loadHeader(&OldHeader);
-    if (OldHeader.State != ChunkAllocated) {
+    if (UNLIKELY(OldHeader.State != ChunkAllocated)) {
       dieWithMessage("ERROR: invalid chunk state when reallocating address "
                      "%p\n", OldPtr);
     }
-    uptr Size = Chunk->getUsableSize(&OldHeader);
-    if (OldHeader.AllocType != FromMalloc) {
+    if (UNLIKELY(OldHeader.AllocType != FromMalloc)) {
       dieWithMessage("ERROR: invalid chunk type when reallocating address %p\n",
-                     Chunk);
+                     OldPtr);
     }
+    uptr UsableSize = Chunk->getUsableSize(&OldHeader);
     UnpackedHeader NewHeader = OldHeader;
     // The new size still fits in the current chunk.
-    if (NewSize <= Size) {
-      NewHeader.UnusedBytes = Size - NewSize;
+    if (NewSize <= UsableSize) {
+      NewHeader.UnusedBytes = UsableSize - NewSize;
       Chunk->compareExchangeHeader(&NewHeader, &OldHeader);
       return OldPtr;
     }
     // Otherwise, we have to allocate a new chunk and copy the contents of the
     // old one.
     void *NewPtr = allocate(NewSize, MinAlignment, FromMalloc);
     if (NewPtr) {
-      uptr OldSize = Size - OldHeader.UnusedBytes;
+      uptr OldSize = UsableSize - OldHeader.UnusedBytes;
       memcpy(NewPtr, OldPtr, Min(NewSize, OldSize));
       NewHeader.State = ChunkQuarantine;
       Chunk->compareExchangeHeader(&NewHeader, &OldHeader);
       if (LIKELY(!ThreadTornDown)) {
         AllocatorQuarantine.Put(&ThreadQuarantineCache,
-                                QuarantineCallback(&Cache), Chunk, Size);
+                                QuarantineCallback(&Cache), Chunk, UsableSize);
       } else {
         SpinMutexLock l(&FallbackMutex);
         AllocatorQuarantine.Put(&FallbackQuarantineCache,
                                 QuarantineCallback(&FallbackAllocatorCache),
-                                Chunk, Size);
+                                Chunk, UsableSize);
       }
     }
     return NewPtr;
   }
 
   // Helper function that returns the actual usable size of a chunk.
   uptr getUsableSize(const void *Ptr) {
     if (UNLIKELY(!ThreadInited))
       initThread();
     if (!Ptr)
       return 0;
-    uptr ChunkBeg = reinterpret_cast<uptr>(Ptr);
-    ScudoChunk *Chunk =
-        reinterpret_cast<ScudoChunk *>(ChunkBeg - AlignedChunkHeaderSize);
+    uptr UserBeg = reinterpret_cast<uptr>(Ptr);
+    ScudoChunk *Chunk = getScudoChunk(UserBeg);
     UnpackedHeader Header;
     Chunk->loadHeader(&Header);
     // Getting the usable size of a chunk only makes sense if it's allocated.
-    if (Header.State != ChunkAllocated) {
+    if (UNLIKELY(Header.State != ChunkAllocated)) {
       dieWithMessage("ERROR: invalid chunk state when sizing address %p\n",
                      Ptr);
     }
     return Chunk->getUsableSize(&Header);
   }
 
   void *calloc(uptr NMemB, uptr Size) {
     if (UNLIKELY(!ThreadInited))
       initThread();
     uptr Total = NMemB * Size;
-    if (Size != 0 && Total / Size != NMemB) // Overflow check
+    if (Size != 0 && Total / Size != NMemB)  // Overflow check
       return BackendAllocator.ReturnNullOrDieOnBadRequest();
-    void *Ptr = allocate(Total, MinAlignment, FromMalloc);
-    // If ZeroContents, the content of the chunk has already been zero'd out.
-    if (!ZeroContents && Ptr && BackendAllocator.FromPrimary(Ptr))
-      memset(Ptr, 0, getUsableSize(Ptr));
-    return Ptr;
+    return allocate(Total, MinAlignment, FromMalloc, true);
   }
 
   void drainQuarantine() {
     AllocatorQuarantine.Drain(&ThreadQuarantineCache,
                               QuarantineCallback(&Cache));
   }
 
   uptr getStats(AllocatorStat StatType) {
     if (UNLIKELY(!ThreadInited))
       initThread();
     uptr stats[AllocatorStatCount];
     BackendAllocator.GetStats(stats);
     return stats[StatType];
   }
 };
 
-static Allocator Instance(LINKER_INITIALIZED);
+static ScudoAllocator Instance(LINKER_INITIALIZED);
 
-static ScudoAllocator &getAllocator() {
+static ScudoBackendAllocator &getBackendAllocator() {
   return Instance.BackendAllocator;
 }
 
 void initAllocator(const AllocatorOptions &Options) {
   Instance.init(Options);
 }
 
 void drainQuarantine() {

lib/scudo/scudo_allocator_secondary.h

CHECK_EQ(MapBeg + PageSize, reinterpret_cast<uptr>(
         MmapFixedOrDie(MapBeg + PageSize, MapSize - 2 * PageSize)));
     uptr Ptr = UserBeg - AlignedChunkHeaderSize;
     SecondaryHeader *Header = getHeader(Ptr);
     Header->MapBeg = MapBeg;
     Header->MapSize = MapSize;
     // The primary adds the whole class size to the stats when allocating a
     // chunk, so we will do something similar here. But we will not account for
     // the guard pages.
+    {
+      SpinMutexLock l(&StatsMutex);
       Stats->Add(AllocatorStatAllocated, MapSize - 2 * PageSize);
       Stats->Add(AllocatorStatMapped, MapSize - 2 * PageSize);
+    }
 
     return reinterpret_cast<void *>(UserBeg);
   }
 
   void *ReturnNullOrDieOnBadRequest() {
     if (atomic_load(&MayReturnNull, memory_order_acquire))
       return nullptr;
     ReportAllocatorCannotReturnNull(false);
   }
 
   void *ReturnNullOrDieOnOOM() {
     if (atomic_load(&MayReturnNull, memory_order_acquire))
       return nullptr;
     ReportAllocatorCannotReturnNull(true);
   }
 
   void SetMayReturnNull(bool AllocatorMayReturnNull) {
     atomic_store(&MayReturnNull, AllocatorMayReturnNull, memory_order_release);
   }
 
   void Deallocate(AllocatorStats *Stats, void *Ptr) {
     SecondaryHeader *Header = getHeader(Ptr);
+    {
+      SpinMutexLock l(&StatsMutex);
       Stats->Sub(AllocatorStatAllocated, Header->MapSize - 2 * PageSize);
       Stats->Sub(AllocatorStatMapped, Header->MapSize - 2 * PageSize);
+    }
     UnmapOrDie(reinterpret_cast<void *>(Header->MapBeg), Header->MapSize);
   }
 
   uptr TotalMemoryUsed() {
     UNIMPLEMENTED();
   }
 
   bool PointerIsMine(const void *Ptr) {
     UNIMPLEMENTED();
   }
 
   uptr GetActuallyAllocatedSize(void *Ptr) {
     SecondaryHeader *Header = getHeader(Ptr);
-    // Deduct PageSize as MapEnd includes the trailing guard page.
+    // Deduct PageSize as MapSize includes the trailing guard page.
     uptr MapEnd = Header->MapBeg + Header->MapSize - PageSize;
     return MapEnd - reinterpret_cast<uptr>(Ptr);
   }
 
   void *GetMetaData(const void *Ptr) {
     UNIMPLEMENTED();
   }
 
private:
   }
   SecondaryHeader *getHeader(const void *Ptr) {
     return getHeader(reinterpret_cast<uptr>(Ptr));
   }
 
   const uptr SecondaryHeaderSize = sizeof(SecondaryHeader);
   const uptr HeadersSize = SecondaryHeaderSize + AlignedChunkHeaderSize;
   uptr PageSize;
+  SpinMutex StatsMutex;
   atomic_uint8_t MayReturnNull;
 };
 
 #endif  // SCUDO_ALLOCATOR_SECONDARY_H_

lib/scudo/scudo_utils.h

 };
 bool testCPUFeature(CPUFeature feature);
 
 // Tiny PRNG based on https://en.wikipedia.org/wiki/Xorshift#xorshift.2B
 // The state (128 bits) will be stored in thread local storage.
 struct Xorshift128Plus {
  public:
   Xorshift128Plus();
-  u64 Next() {
+  u64 getNext() {
     u64 x = State[0];
     const u64 y = State[1];
     State[0] = y;
     x ^= x << 23;
     State[1] = x ^ y ^ (x >> 17) ^ (y >> 26);
     return State[1] + y;
   }
  private:
   u64 State[2];
 };
 
 enum : u8 {
   CRC32Software = 0,
   CRC32Hardware = 1,
 };
 
-u32 computeSoftwareCRC32(u32 Crc, uptr Data);
+const static u32 CRC32Table[] = {
+  0x00000000, 0x77073096, 0xee0e612c, 0x990951ba, 0x076dc419, 0x706af48f,
+  0xe963a535, 0x9e6495a3, 0x0edb8832, 0x79dcb8a4, 0xe0d5e91e, 0x97d2d988,
+  0x09b64c2b, 0x7eb17cbd, 0xe7b82d07, 0x90bf1d91, 0x1db71064, 0x6ab020f2,
+  0xf3b97148, 0x84be41de, 0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7,
+  0x136c9856, 0x646ba8c0, 0xfd62f97a, 0x8a65c9ec, 0x14015c4f, 0x63066cd9,
+  0xfa0f3d63, 0x8d080df5, 0x3b6e20c8, 0x4c69105e, 0xd56041e4, 0xa2677172,
+  0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b, 0x35b5a8fa, 0x42b2986c,
+  0xdbbbc9d6, 0xacbcf940, 0x32d86ce3, 0x45df5c75, 0xdcd60dcf, 0xabd13d59,
+  0x26d930ac, 0x51de003a, 0xc8d75180, 0xbfd06116, 0x21b4f4b5, 0x56b3c423,
+  0xcfba9599, 0xb8bda50f, 0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924,
+  0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d, 0x76dc4190, 0x01db7106,
+  0x98d220bc, 0xefd5102a, 0x71b18589, 0x06b6b51f, 0x9fbfe4a5, 0xe8b8d433,
+  0x7807c9a2, 0x0f00f934, 0x9609a88e, 0xe10e9818, 0x7f6a0dbb, 0x086d3d2d,
+  0x91646c97, 0xe6635c01, 0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e,
+  0x6c0695ed, 0x1b01a57b, 0x8208f4c1, 0xf50fc457, 0x65b0d9c6, 0x12b7e950,
+  0x8bbeb8ea, 0xfcb9887c, 0x62dd1ddf, 0x15da2d49, 0x8cd37cf3, 0xfbd44c65,
+  0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2, 0x4adfa541, 0x3dd895d7,
+  0xa4d1c46d, 0xd3d6f4fb, 0x4369e96a, 0x346ed9fc, 0xad678846, 0xda60b8d0,
+  0x44042d73, 0x33031de5, 0xaa0a4c5f, 0xdd0d7cc9, 0x5005713c, 0x270241aa,
+  0xbe0b1010, 0xc90c2086, 0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f,
+  0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4, 0x59b33d17, 0x2eb40d81,
+  0xb7bd5c3b, 0xc0ba6cad, 0xedb88320, 0x9abfb3b6, 0x03b6e20c, 0x74b1d29a,
+  0xead54739, 0x9dd277af, 0x04db2615, 0x73dc1683, 0xe3630b12, 0x94643b84,
+  0x0d6d6a3e, 0x7a6a5aa8, 0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1,
+  0xf00f9344, 0x8708a3d2, 0x1e01f268, 0x6906c2fe, 0xf762575d, 0x806567cb,
+  0x196c3671, 0x6e6b06e7, 0xfed41b76, 0x89d32be0, 0x10da7a5a, 0x67dd4acc,
+  0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5, 0xd6d6a3e8, 0xa1d1937e,
+  0x38d8c2c4, 0x4fdff252, 0xd1bb67f1, 0xa6bc5767, 0x3fb506dd, 0x48b2364b,
+  0xd80d2bda, 0xaf0a1b4c, 0x36034af6, 0x41047a60, 0xdf60efc3, 0xa867df55,
+  0x316e8eef, 0x4669be79, 0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236,
+  0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f, 0xc5ba3bbe, 0xb2bd0b28,
+  0x2bb45a92, 0x5cb36a04, 0xc2d7ffa7, 0xb5d0cf31, 0x2cd99e8b, 0x5bdeae1d,
+  0x9b64c2b0, 0xec63f226, 0x756aa39c, 0x026d930a, 0x9c0906a9, 0xeb0e363f,
+  0x72076785, 0x05005713, 0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38,
+  0x92d28e9b, 0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21, 0x86d3d2d4, 0xf1d4e242,
+  0x68ddb3f8, 0x1fda836e, 0x81be16cd, 0xf6b9265b, 0x6fb077e1, 0x18b74777,
+  0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c, 0x8f659eff, 0xf862ae69,
+  0x616bffd3, 0x166ccf45, 0xa00ae278, 0xd70dd2ee, 0x4e048354, 0x3903b3c2,
+  0xa7672661, 0xd06016f7, 0x4969474d, 0x3e6e77db, 0xaed16a4a, 0xd9d65adc,
+  0x40df0b66, 0x37d83bf0, 0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9,
+  0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6, 0xbad03605, 0xcdd70693,
+  0x54de5729, 0x23d967bf, 0xb3667a2e, 0xc4614ab8, 0x5d681b02, 0x2a6f2b94,
+  0xb40bbe37, 0xc30c8ea1, 0x5a05df1b, 0x2d02ef8d
+};
+
+INLINE u32 computeSoftwareCRC32(u32 Crc, uptr Data) {
+  for (uptr i = 0; i < sizeof(Data); i++) {
+    Crc = CRC32Table[(Crc ^ Data) & 0xff] ^ (Crc >> 8);
+    Data >>= 8;
+  }
+  return Crc;
+}
 
 }  // namespace __scudo
 
 #endif  // SCUDO_UTILS_H_

lib/scudo/scudo_utils.cpp

 }
 
 // Default constructor for Xorshift128Plus seeds the state with /dev/urandom.
 // TODO(kostyak): investigate using getrandom() if available.
 Xorshift128Plus::Xorshift128Plus() {
   fillRandom(reinterpret_cast<u8 *>(State), sizeof(State));
 }
 
-const static u32 CRC32Table[] = {
-  0x00000000, 0x77073096, 0xee0e612c, 0x990951ba, 0x076dc419, 0x706af48f,
-  0xe963a535, 0x9e6495a3, 0x0edb8832, 0x79dcb8a4, 0xe0d5e91e, 0x97d2d988,
-  0x09b64c2b, 0x7eb17cbd, 0xe7b82d07, 0x90bf1d91, 0x1db71064, 0x6ab020f2,
-  0xf3b97148, 0x84be41de, 0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7,
-  0x136c9856, 0x646ba8c0, 0xfd62f97a, 0x8a65c9ec, 0x14015c4f, 0x63066cd9,
-  0xfa0f3d63, 0x8d080df5, 0x3b6e20c8, 0x4c69105e, 0xd56041e4, 0xa2677172,
-  0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b, 0x35b5a8fa, 0x42b2986c,
-  0xdbbbc9d6, 0xacbcf940, 0x32d86ce3, 0x45df5c75, 0xdcd60dcf, 0xabd13d59,
-  0x26d930ac, 0x51de003a, 0xc8d75180, 0xbfd06116, 0x21b4f4b5, 0x56b3c423,
-  0xcfba9599, 0xb8bda50f, 0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924,
-  0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d, 0x76dc4190, 0x01db7106,
-  0x98d220bc, 0xefd5102a, 0x71b18589, 0x06b6b51f, 0x9fbfe4a5, 0xe8b8d433,
-  0x7807c9a2, 0x0f00f934, 0x9609a88e, 0xe10e9818, 0x7f6a0dbb, 0x086d3d2d,
-  0x91646c97, 0xe6635c01, 0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e,
-  0x6c0695ed, 0x1b01a57b, 0x8208f4c1, 0xf50fc457, 0x65b0d9c6, 0x12b7e950,
-  0x8bbeb8ea, 0xfcb9887c, 0x62dd1ddf, 0x15da2d49, 0x8cd37cf3, 0xfbd44c65,
-  0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2, 0x4adfa541, 0x3dd895d7,
-  0xa4d1c46d, 0xd3d6f4fb, 0x4369e96a, 0x346ed9fc, 0xad678846, 0xda60b8d0,
-  0x44042d73, 0x33031de5, 0xaa0a4c5f, 0xdd0d7cc9, 0x5005713c, 0x270241aa,
-  0xbe0b1010, 0xc90c2086, 0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f,
-  0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4, 0x59b33d17, 0x2eb40d81,
-  0xb7bd5c3b, 0xc0ba6cad, 0xedb88320, 0x9abfb3b6, 0x03b6e20c, 0x74b1d29a,
-  0xead54739, 0x9dd277af, 0x04db2615, 0x73dc1683, 0xe3630b12, 0x94643b84,
-  0x0d6d6a3e, 0x7a6a5aa8, 0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1,
-  0xf00f9344, 0x8708a3d2, 0x1e01f268, 0x6906c2fe, 0xf762575d, 0x806567cb,
-  0x196c3671, 0x6e6b06e7, 0xfed41b76, 0x89d32be0, 0x10da7a5a, 0x67dd4acc,
-  0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5, 0xd6d6a3e8, 0xa1d1937e,
-  0x38d8c2c4, 0x4fdff252, 0xd1bb67f1, 0xa6bc5767, 0x3fb506dd, 0x48b2364b,
-  0xd80d2bda, 0xaf0a1b4c, 0x36034af6, 0x41047a60, 0xdf60efc3, 0xa867df55,
-  0x316e8eef, 0x4669be79, 0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236,
-  0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f, 0xc5ba3bbe, 0xb2bd0b28,
-  0x2bb45a92, 0x5cb36a04, 0xc2d7ffa7, 0xb5d0cf31, 0x2cd99e8b, 0x5bdeae1d,
-  0x9b64c2b0, 0xec63f226, 0x756aa39c, 0x026d930a, 0x9c0906a9, 0xeb0e363f,
-  0x72076785, 0x05005713, 0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38,
-  0x92d28e9b, 0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21, 0x86d3d2d4, 0xf1d4e242,
-  0x68ddb3f8, 0x1fda836e, 0x81be16cd, 0xf6b9265b, 0x6fb077e1, 0x18b74777,
-  0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c, 0x8f659eff, 0xf862ae69,
-  0x616bffd3, 0x166ccf45, 0xa00ae278, 0xd70dd2ee, 0x4e048354, 0x3903b3c2,
-  0xa7672661, 0xd06016f7, 0x4969474d, 0x3e6e77db, 0xaed16a4a, 0xd9d65adc,
-  0x40df0b66, 0x37d83bf0, 0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9,
-  0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6, 0xbad03605, 0xcdd70693,
-  0x54de5729, 0x23d967bf, 0xb3667a2e, 0xc4614ab8, 0x5d681b02, 0x2a6f2b94,
-  0xb40bbe37, 0xc30c8ea1, 0x5a05df1b, 0x2d02ef8d
-};
-
-u32 computeSoftwareCRC32(u32 Crc, uptr Data) {
-  for (uptr i = 0; i < sizeof(Data); i++) {
-    Crc = CRC32Table[(Crc ^ Data) & 0xff] ^ (Crc >> 8);
-    Data >>= 8;
-  }
-  return Crc;
-}
-
 }  // namespace __scudo