diff options
47 files changed, 7964 insertions, 7356 deletions
diff --git a/build/Android.common.mk b/build/Android.common.mk index ed2229fb2f..ba34206ba1 100644 --- a/build/Android.common.mk +++ b/build/Android.common.mk @@ -126,6 +126,7 @@ LIBART_COMMON_SRC_FILES := \ src/dex_file_verifier.cc \ src/dex_instruction.cc \ src/dex_verifier.cc \ + src/dlmalloc.c \ src/file.cc \ src/file_linux.cc \ src/heap.cc \ @@ -168,7 +169,6 @@ LIBART_COMMON_SRC_FILES := \ src/mem_map.cc \ src/memory_region.cc \ src/monitor.cc \ - src/mspace.c \ src/mutex.cc \ src/oat.cc \ src/oat_file.cc \ diff --git a/src/card_table.cc b/src/card_table.cc index 0871ed92b5..386b27cfbd 100644 --- a/src/card_table.cc +++ b/src/card_table.cc @@ -43,76 +43,73 @@ namespace art { * rather strange value. In order to keep the JIT from having to * fabricate or load GC_DIRTY_CARD to store into the card table, * biased base is within the mmap allocation at a point where its low - * byte is equal to GC_DIRTY_CARD. See CardTable::Init for details. + * byte is equal to GC_DIRTY_CARD. See CardTable::Create for details. */ -CardTable* CardTable::Create(const byte* heap_base, size_t heap_max_size, size_t growth_size) { - CardTable* bitmap = new CardTable; - bitmap->Init(heap_base, heap_max_size, growth_size); - return bitmap; -} - -/* - * Initializes the card table; must be called before any other - * CardTable functions. - */ -void CardTable::Init(const byte* heap_base, size_t heap_max_size, size_t growth_size) { +CardTable* CardTable::Create(const byte* heap_begin, size_t heap_capacity) { /* Set up the card table */ - size_t length = heap_max_size / GC_CARD_SIZE; + size_t capacity = heap_capacity / GC_CARD_SIZE; /* Allocate an extra 256 bytes to allow fixed low-byte of base */ - mem_map_.reset(MemMap::MapAnonymous("dalvik-card-table", NULL, length + 256, PROT_READ | PROT_WRITE)); - if (mem_map_.get() == NULL) { + UniquePtr<MemMap> mem_map(MemMap::MapAnonymous("dalvik-card-table", NULL, + capacity + 256, PROT_READ | PROT_WRITE)); + if (mem_map.get() == NULL) { std::string maps; ReadFileToString("/proc/self/maps", &maps); LOG(FATAL) << "couldn't allocate card table\n" << maps; } - byte* alloc_base = mem_map_->GetAddress(); - CHECK(alloc_base != NULL); - base_ = alloc_base; - length_ = growth_size / GC_CARD_SIZE; - max_length_ = length; - offset_ = 0; - /* All zeros is the correct initial value; all clean. */ + // All zeros is the correct initial value; all clean. Anonymous mmaps are initialized to zero, we + // don't clear the card table to avoid unnecessary pages being allocated CHECK_EQ(GC_CARD_CLEAN, 0); - biased_base_ = (byte *)((uintptr_t)alloc_base -((uintptr_t)heap_base >> GC_CARD_SHIFT)); - if (((uintptr_t)biased_base_ & 0xff) != GC_CARD_DIRTY) { - int offset = GC_CARD_DIRTY - (reinterpret_cast<int>(biased_base_) & 0xff); - offset_ = offset + (offset < 0 ? 0x100 : 0); - biased_base_ += offset_; + + byte* cardtable_begin = mem_map->Begin(); + CHECK(cardtable_begin != NULL); + + // We allocated up to a bytes worth of extra space to allow biased_begin's byte value to equal + // GC_CARD_DIRTY, compute a offset value to make this the case + size_t offset = 0; + byte* biased_begin = (byte *)((uintptr_t)cardtable_begin -((uintptr_t)heap_begin >> GC_CARD_SHIFT)); + if (((uintptr_t)biased_begin & 0xff) != GC_CARD_DIRTY) { + int delta = GC_CARD_DIRTY - (reinterpret_cast<int>(biased_begin) & 0xff); + offset = delta + (delta < 0 ? 0x100 : 0); + biased_begin += offset; } - CHECK_EQ(reinterpret_cast<int>(biased_base_) & 0xff, GC_CARD_DIRTY); - ClearCardTable(); + CHECK_EQ(reinterpret_cast<int>(biased_begin) & 0xff, GC_CARD_DIRTY); + + return new CardTable(mem_map.release(), biased_begin, offset); } void CardTable::ClearCardTable() { - CHECK(mem_map_->GetAddress() != NULL); - memset(mem_map_->GetAddress(), GC_CARD_CLEAN, length_); + // TODO: clear just the range of the table that has been modified + memset(mem_map_->Begin(), GC_CARD_CLEAN, mem_map_->Size()); } -/* - * Returns the first address in the heap which maps to this card. - */ -void* CardTable::AddrFromCard(const byte *cardAddr) const { - CHECK(IsValidCard(cardAddr)); - uintptr_t offset = cardAddr - biased_base_; - return (void *)(offset << GC_CARD_SHIFT); +void CardTable::CheckAddrIsInCardTable(const byte* addr) const { + byte* cardAddr = biased_begin_ + ((uintptr_t)addr >> GC_CARD_SHIFT); + if (!IsValidCard(cardAddr)) { + byte* begin = mem_map_->Begin() + offset_; + byte* end = mem_map_->End(); + LOG(FATAL) << "Cardtable - begin: " << reinterpret_cast<void*>(begin) + << " end: " << reinterpret_cast<void*>(end) + << " addr: " << reinterpret_cast<const void*>(addr) + << " cardAddr: " << reinterpret_cast<void*>(cardAddr); + } } -void CardTable::Scan(byte* base, byte* limit, Callback* visitor, void* arg) const { - byte* cur = CardFromAddr(base); - byte* end = CardFromAddr(limit); - while (cur < end) { - while (cur < end && *cur == GC_CARD_CLEAN) { - cur++; +void CardTable::Scan(byte* heap_begin, byte* heap_end, Callback* visitor, void* arg) const { + byte* card_cur = CardFromAddr(heap_begin); + byte* card_end = CardFromAddr(heap_end); + while (card_cur < card_end) { + while (card_cur < card_end && *card_cur == GC_CARD_CLEAN) { + card_cur++; } - byte* run_start = cur; + byte* run_start = card_cur; size_t run = 0; - while (cur < end && *cur == GC_CARD_DIRTY) { + while (card_cur < card_end && *card_cur == GC_CARD_DIRTY) { run++; - cur++; + card_cur++; } if (run > 0) { - byte* run_end = &cur[run]; + byte* run_end = &card_cur[run]; Heap::GetLiveBits()->VisitRange(reinterpret_cast<uintptr_t>(AddrFromCard(run_start)), reinterpret_cast<uintptr_t>(AddrFromCard(run_end)), visitor, arg); @@ -120,9 +117,6 @@ void CardTable::Scan(byte* base, byte* limit, Callback* visitor, void* arg) cons } } -/* - * Verifies that gray objects are on a dirty card. - */ void CardTable::VerifyCardTable() { UNIMPLEMENTED(WARNING) << "Card table verification"; } diff --git a/src/card_table.h b/src/card_table.h index 1f58507cc4..804e97bbdb 100644 --- a/src/card_table.h +++ b/src/card_table.h @@ -25,84 +25,75 @@ class Object; class CardTable { public: - typedef void Callback(Object* obj, void* arg); - static CardTable* Create(const byte* heap_base, size_t heap_max_size, size_t growth_size); + static CardTable* Create(const byte* heap_begin, size_t heap_capacity); - /* - * Set the card associated with the given address to GC_CARD_DIRTY. - */ + // Set the card associated with the given address to GC_CARD_DIRTY. void MarkCard(const void *addr) { byte* cardAddr = CardFromAddr(addr); *cardAddr = GC_CARD_DIRTY; } - byte* GetBiasedBase() { - return biased_base_; - } - - void Scan(byte* base, byte* limit, Callback* visitor, void* arg) const; - + // Is the object on a dirty card? bool IsDirty(const Object* obj) const { return *CardFromAddr(obj) == GC_CARD_DIRTY; } - void ClearGrowthLimit() { - CHECK_GE(max_length_, length_); - length_ = max_length_; + // Returns a value that when added to a heap address >> GC_CARD_SHIFT will address the appropriate + // card table byte. For convenience this value is cached in every Thread + byte* GetBiasedBegin() const { + return biased_begin_; } - private: + // For every dirty card between begin and end invoke the visitor with the specified argument + typedef void Callback(Object* obj, void* arg); + void Scan(byte* begin, byte* end, Callback* visitor, void* arg) const; - CardTable() {} - /* - * Initializes the card table; must be called before any other - * CardTable functions. - */ - void Init(const byte* heap_base, size_t heap_max_size, size_t growth_size); + // Assertion used to check the given address is covered by the card table + void CheckAddrIsInCardTable(const byte* addr) const; - /* - * Resets all of the bytes in the card table to clean. - */ + private: + + CardTable(MemMap* begin, byte* biased_begin, size_t offset) : + mem_map_(begin), biased_begin_(biased_begin), offset_(offset) {} + + // Resets all of the bytes in the card table to clean. void ClearCardTable(); - /* - * Returns the address of the relevant byte in the card table, given - * an address on the heap. - */ + // Returns the address of the relevant byte in the card table, given an address on the heap. byte* CardFromAddr(const void *addr) const { - byte *cardAddr = biased_base_ + ((uintptr_t)addr >> GC_CARD_SHIFT); - CHECK(IsValidCard(cardAddr)); + byte *cardAddr = biased_begin_ + ((uintptr_t)addr >> GC_CARD_SHIFT); + // Sanity check the caller was asking for address covered by the card table + DCHECK(IsValidCard(cardAddr)) << "addr: " << addr + << " cardAddr: " << reinterpret_cast<void*>(cardAddr); return cardAddr; } - /* - * Returns the first address in the heap which maps to this card. - */ - void* AddrFromCard(const byte *card) const; + // Returns the first address in the heap which maps to this card. + void* AddrFromCard(const byte *cardAddr) const { + DCHECK(IsValidCard(cardAddr)); + uintptr_t offset = cardAddr - biased_begin_; + return (void *)(offset << GC_CARD_SHIFT); + } - /* - * Returns true iff the address is within the bounds of the card table. - */ + // Returns true iff the card table address is within the bounds of the card table. bool IsValidCard(const byte* cardAddr) const { - byte* begin = mem_map_->GetAddress() + offset_; - byte* end = &begin[length_]; + byte* begin = mem_map_->Begin() + offset_; + byte* end = mem_map_->End(); return cardAddr >= begin && cardAddr < end; } - /* - * Verifies that all gray objects are on a dirty card. - */ + // Verifies that all gray objects are on a dirty card. void VerifyCardTable(); - + // Mmapped pages for the card table UniquePtr<MemMap> mem_map_; - byte* base_; - byte* biased_base_; - size_t length_; - size_t max_length_; - size_t offset_; + // Value used to compute card table addresses from object addresses, see GetBiasedBegin + byte* const biased_begin_; + // Card table doesn't begin at the beginning of the mem_map_, instead it is displaced by offset + // to allow the byte value of biased_begin_ to equal GC_CARD_DIRTY + const size_t offset_; }; } // namespace art diff --git a/src/class_linker.cc b/src/class_linker.cc index 5033c240a0..e0bcd04e44 100644 --- a/src/class_linker.cc +++ b/src/class_linker.cc @@ -558,7 +558,7 @@ bool ClassLinker::GenerateOatFile(const std::string& dex_filename, const char* class_path = Runtime::Current()->GetClassPath().c_str(); std::string boot_image_option_string("--boot-image="); - boot_image_option_string += Heap::GetSpaces()[0]->GetImageFilename(); + boot_image_option_string += Heap::GetSpaces()[0]->AsImageSpace()->GetImageFilename(); const char* boot_image_option = boot_image_option_string.c_str(); std::string dex_file_option_string("--dex-file="); @@ -630,10 +630,9 @@ void ClassLinker::RegisterOatFileLocked(const OatFile& oat_file) { oat_files_.push_back(&oat_file); } -OatFile* ClassLinker::OpenOat(const Space* space) { +OatFile* ClassLinker::OpenOat(const ImageSpace* space) { MutexLock mu(dex_lock_); const Runtime* runtime = Runtime::Current(); - VLOG(startup) << "ClassLinker::OpenOat entering"; const ImageHeader& image_header = space->GetImageHeader(); // Grab location but don't use Object::AsString as we haven't yet initialized the roots to // check the down cast @@ -641,7 +640,8 @@ OatFile* ClassLinker::OpenOat(const Space* space) { std::string oat_filename; oat_filename += runtime->GetHostPrefix(); oat_filename += oat_location->ToModifiedUtf8(); - OatFile* oat_file = OatFile::Open(oat_filename, "", image_header.GetOatBaseAddr()); + OatFile* oat_file = OatFile::Open(oat_filename, "", image_header.GetOatBegin()); + VLOG(startup) << "ClassLinker::OpenOat entering oat_filename=" << oat_filename; if (oat_file == NULL) { LOG(ERROR) << "Failed to open oat file " << oat_filename << " referenced from image."; return NULL; @@ -832,8 +832,8 @@ void ClassLinker::InitFromImage() { const std::vector<Space*>& spaces = Heap::GetSpaces(); for (size_t i = 0; i < spaces.size(); i++) { - Space* space = spaces[i]; - if (space->IsImageSpace()) { + if (spaces[i]->IsImageSpace()) { + ImageSpace* space = spaces[i]->AsImageSpace(); OatFile* oat_file = OpenOat(space); CHECK(oat_file != NULL) << "Failed to open oat file for image"; Object* dex_caches_object = space->GetImageHeader().GetImageRoot(ImageHeader::kDexCaches); @@ -842,7 +842,7 @@ void ClassLinker::InitFromImage() { if (i == 0) { // Special case of setting up the String class early so that we can test arbitrary objects // as being Strings or not - Class* java_lang_String = spaces[0]->GetImageHeader().GetImageRoot(ImageHeader::kClassRoots) + Class* java_lang_String = space->GetImageHeader().GetImageRoot(ImageHeader::kClassRoots) ->AsObjectArray<Class>()->Get(kJavaLangString); String::SetClass(java_lang_String); } @@ -873,7 +873,8 @@ void ClassLinker::InitFromImage() { heap_bitmap->Walk(InitFromImageCallback, this); // reinit class_roots_ - Object* class_roots_object = spaces[0]->GetImageHeader().GetImageRoot(ImageHeader::kClassRoots); + Object* class_roots_object = + spaces[0]->AsImageSpace()->GetImageHeader().GetImageRoot(ImageHeader::kClassRoots); class_roots_ = class_roots_object->AsObjectArray<Class>(); // reinit array_iftable_ from any array class instance, they should be == @@ -2568,7 +2569,7 @@ bool ClassLinker::LinkVirtualMethods(SirtRef<Class>& klass) { size_t actual_count = klass->GetSuperClass()->GetVTable()->GetLength(); CHECK_LE(actual_count, max_count); // TODO: do not assign to the vtable field until it is fully constructed. - ObjectArray<Method>* vtable = klass->GetSuperClass()->GetVTable()->CopyOf(max_count); + SirtRef<ObjectArray<Method> > vtable(klass->GetSuperClass()->GetVTable()->CopyOf(max_count)); // See if any of our virtual methods override the superclass. MethodHelper local_mh(NULL, this); MethodHelper super_mh(NULL, this); @@ -2607,9 +2608,9 @@ bool ClassLinker::LinkVirtualMethods(SirtRef<Class>& klass) { // Shrink vtable if possible CHECK_LE(actual_count, max_count); if (actual_count < max_count) { - vtable = vtable->CopyOf(actual_count); + vtable.reset(vtable->CopyOf(actual_count)); } - klass->SetVTable(vtable); + klass->SetVTable(vtable.get()); } else { CHECK(klass.get() == GetClassRoot(kJavaLangObject)); uint32_t num_virtual_methods = klass->NumVirtualMethods(); @@ -2775,11 +2776,11 @@ bool ClassLinker::LinkInterfaceMethods(SirtRef<Class>& klass, ObjectArray<Class> ? AllocObjectArray<Method>(new_method_count) : klass->GetVirtualMethods()->CopyOf(new_method_count)); - ObjectArray<Method>* vtable = klass->GetVTableDuringLinking(); - CHECK(vtable != NULL); + SirtRef<ObjectArray<Method> > vtable(klass->GetVTableDuringLinking()); + CHECK(vtable.get() != NULL); int old_vtable_count = vtable->GetLength(); int new_vtable_count = old_vtable_count + miranda_list.size(); - vtable = vtable->CopyOf(new_vtable_count); + vtable.reset(vtable->CopyOf(new_vtable_count)); for (size_t i = 0; i < miranda_list.size(); ++i) { Method* method = miranda_list[i]; // Leave the declaring class alone as type indices are relative to it @@ -2789,7 +2790,7 @@ bool ClassLinker::LinkInterfaceMethods(SirtRef<Class>& klass, ObjectArray<Class> vtable->Set(old_vtable_count + i, method); } // TODO: do not assign to the vtable field until it is fully constructed. - klass->SetVTable(vtable); + klass->SetVTable(vtable.get()); } ObjectArray<Method>* vtable = klass->GetVTableDuringLinking(); diff --git a/src/class_linker.h b/src/class_linker.h index 1c5de63610..8471cbc0cb 100644 --- a/src/class_linker.h +++ b/src/class_linker.h @@ -35,6 +35,7 @@ namespace art { class ClassLoader; +class ImageSpace; class InternTable; class ObjectLock; @@ -282,7 +283,7 @@ class ClassLinker { // Initialize class linker from one or more images. void InitFromImage(); - OatFile* OpenOat(const Space* space); + OatFile* OpenOat(const ImageSpace* space); static void InitFromImageCallback(Object* obj, void* arg); struct InitFromImageCallbackState; diff --git a/src/common_test.h b/src/common_test.h index 14adfbe182..15893b2b03 100644 --- a/src/common_test.h +++ b/src/common_test.h @@ -228,12 +228,15 @@ class CommonTest : public testing::Test { boot_class_path += "-Xbootclasspath:"; boot_class_path += GetLibCoreDexFileName(); + std::string min_heap_string = StringPrintf("-Xms%dm",Heap::kInitialSize / MB); + std::string max_heap_string = StringPrintf("-Xmx%dm",Heap::kMaximumSize / MB); + Runtime::Options options; options.push_back(std::make_pair("compiler", reinterpret_cast<void*>(NULL))); options.push_back(std::make_pair(boot_class_path.c_str(), reinterpret_cast<void*>(NULL))); options.push_back(std::make_pair("-Xcheck:jni", reinterpret_cast<void*>(NULL))); - options.push_back(std::make_pair("-Xms64m", reinterpret_cast<void*>(NULL))); - options.push_back(std::make_pair("-Xmx64m", reinterpret_cast<void*>(NULL))); + options.push_back(std::make_pair(min_heap_string.c_str(), reinterpret_cast<void*>(NULL))); + options.push_back(std::make_pair(max_heap_string.c_str(), reinterpret_cast<void*>(NULL))); runtime_.reset(Runtime::Create(options, false)); ASSERT_TRUE(runtime_.get() != NULL); class_linker_ = runtime_->GetClassLinker(); diff --git a/src/debugger.cc b/src/debugger.cc index f8f52483a7..ef3ac88e9d 100644 --- a/src/debugger.cc +++ b/src/debugger.cc @@ -26,6 +26,7 @@ #include "object_utils.h" #include "ScopedLocalRef.h" #include "ScopedPrimitiveArray.h" +#include "space.h" #include "stack_indirect_reference_table.h" #include "thread_list.h" @@ -2035,78 +2036,84 @@ enum HpsgKind { #define HPSG_PARTIAL (1<<7) #define HPSG_STATE(solidity, kind) ((uint8_t)((((kind) & 0x7) << 3) | ((solidity) & 0x7))) -struct HeapChunkContext { - std::vector<uint8_t> buf; - uint8_t* p; - uint8_t* pieceLenField; - size_t totalAllocationUnits; - uint32_t type; - bool merge; - bool needHeader; - +class HeapChunkContext { + public: // Maximum chunk size. Obtain this from the formula: // (((maximum_heap_size / ALLOCATION_UNIT_SIZE) + 255) / 256) * 2 HeapChunkContext(bool merge, bool native) - : buf(16384 - 16), - type(0), - merge(merge) { + : buf_(16384 - 16), + type_(0), + merge_(merge) { Reset(); if (native) { - type = CHUNK_TYPE("NHSG"); + type_ = CHUNK_TYPE("NHSG"); } else { - type = merge ? CHUNK_TYPE("HPSG") : CHUNK_TYPE("HPSO"); + type_ = merge ? CHUNK_TYPE("HPSG") : CHUNK_TYPE("HPSO"); } } ~HeapChunkContext() { - if (p > &buf[0]) { + if (p_ > &buf_[0]) { Flush(); } } void EnsureHeader(const void* chunk_ptr) { - if (!needHeader) { + if (!needHeader_) { return; } // Start a new HPSx chunk. - JDWP::Write4BE(&p, 1); // Heap id (bogus; we only have one heap). - JDWP::Write1BE(&p, 8); // Size of allocation unit, in bytes. + JDWP::Write4BE(&p_, 1); // Heap id (bogus; we only have one heap). + JDWP::Write1BE(&p_, 8); // Size of allocation unit, in bytes. - JDWP::Write4BE(&p, reinterpret_cast<uintptr_t>(chunk_ptr)); // virtual address of segment start. - JDWP::Write4BE(&p, 0); // offset of this piece (relative to the virtual address). + JDWP::Write4BE(&p_, reinterpret_cast<uintptr_t>(chunk_ptr)); // virtual address of segment start. + JDWP::Write4BE(&p_, 0); // offset of this piece (relative to the virtual address). // [u4]: length of piece, in allocation units // We won't know this until we're done, so save the offset and stuff in a dummy value. - pieceLenField = p; - JDWP::Write4BE(&p, 0x55555555); - needHeader = false; + pieceLenField_ = p_; + JDWP::Write4BE(&p_, 0x55555555); + needHeader_ = false; } void Flush() { // Patch the "length of piece" field. - CHECK_LE(&buf[0], pieceLenField); - CHECK_LE(pieceLenField, p); - JDWP::Set4BE(pieceLenField, totalAllocationUnits); + CHECK_LE(&buf_[0], pieceLenField_); + CHECK_LE(pieceLenField_, p_); + JDWP::Set4BE(pieceLenField_, totalAllocationUnits_); - Dbg::DdmSendChunk(type, p - &buf[0], &buf[0]); + Dbg::DdmSendChunk(type_, p_ - &buf_[0], &buf_[0]); Reset(); } - static void HeapChunkCallback(const void* chunk_ptr, size_t chunk_len, const void* user_ptr, size_t user_len, void* arg) { - reinterpret_cast<HeapChunkContext*>(arg)->HeapChunkCallback(chunk_ptr, chunk_len, user_ptr, user_len); + static void HeapChunkCallback(void* start, void* end, size_t used_bytes, void* arg) { + reinterpret_cast<HeapChunkContext*>(arg)->HeapChunkCallback(start, end, used_bytes); } private: enum { ALLOCATION_UNIT_SIZE = 8 }; void Reset() { - p = &buf[0]; - totalAllocationUnits = 0; - needHeader = true; - pieceLenField = NULL; + p_ = &buf_[0]; + totalAllocationUnits_ = 0; + needHeader_ = true; + pieceLenField_ = NULL; } - void HeapChunkCallback(const void* chunk_ptr, size_t chunk_len, const void* user_ptr, size_t user_len) { + void HeapChunkCallback(void* start, void* end, size_t used_bytes) { + // Note: heap call backs cannot manipulate the heap upon which they are crawling, care is taken + // in the following code not to allocate memory, by ensuring buf_ is of the correct size + + const void* user_ptr = used_bytes > 0 ? const_cast<void*>(start) : NULL; + // from malloc.c mem2chunk(mem) + const void* chunk_ptr = + reinterpret_cast<const void*>(reinterpret_cast<const char*>(const_cast<void*>(start)) - + (2 * sizeof(size_t))); + // from malloc.c chunksize + size_t chunk_len = (*reinterpret_cast<size_t* const*>(chunk_ptr))[1] & ~7; + + + //size_t chunk_len = malloc_usable_size(user_ptr); CHECK_EQ((chunk_len & (ALLOCATION_UNIT_SIZE-1)), 0U); /* Make sure there's enough room left in the buffer. @@ -2115,12 +2122,12 @@ struct HeapChunkContext { */ { size_t needed = (((chunk_len/ALLOCATION_UNIT_SIZE + 255) / 256) * 2); - size_t bytesLeft = buf.size() - (size_t)(p - &buf[0]); + size_t bytesLeft = buf_.size() - (size_t)(p_ - &buf_[0]); if (bytesLeft < needed) { Flush(); } - bytesLeft = buf.size() - (size_t)(p - &buf[0]); + bytesLeft = buf_.size() - (size_t)(p_ - &buf_[0]); if (bytesLeft < needed) { LOG(WARNING) << "Chunk is too big to transmit (chunk_len=" << chunk_len << ", " << needed << " bytes)"; return; @@ -2133,18 +2140,18 @@ struct HeapChunkContext { // Determine the type of this chunk. // OLD-TODO: if context.merge, see if this chunk is different from the last chunk. // If it's the same, we should combine them. - uint8_t state = ExamineObject(reinterpret_cast<const Object*>(user_ptr), (type == CHUNK_TYPE("NHSG"))); + uint8_t state = ExamineObject(reinterpret_cast<const Object*>(user_ptr), (type_ == CHUNK_TYPE("NHSG"))); // Write out the chunk description. chunk_len /= ALLOCATION_UNIT_SIZE; // convert to allocation units - totalAllocationUnits += chunk_len; + totalAllocationUnits_ += chunk_len; while (chunk_len > 256) { - *p++ = state | HPSG_PARTIAL; - *p++ = 255; // length - 1 + *p_++ = state | HPSG_PARTIAL; + *p_++ = 255; // length - 1 chunk_len -= 256; } - *p++ = state; - *p++ = chunk_len - 1; + *p_++ = state; + *p_++ = chunk_len - 1; } uint8_t ExamineObject(const Object* o, bool is_native_heap) { @@ -2190,6 +2197,14 @@ struct HeapChunkContext { return HPSG_STATE(SOLIDITY_HARD, KIND_OBJECT); } + std::vector<uint8_t> buf_; + uint8_t* p_; + uint8_t* pieceLenField_; + size_t totalAllocationUnits_; + uint32_t type_; + bool merge_; + bool needHeader_; + DISALLOW_COPY_AND_ASSIGN(HeapChunkContext); }; @@ -2218,9 +2233,11 @@ void Dbg::DdmSendHeapSegments(bool native) { // Send a series of heap segment chunks. HeapChunkContext context((what == HPSG_WHAT_MERGED_OBJECTS), native); if (native) { - dlmalloc_walk_heap(HeapChunkContext::HeapChunkCallback, &context); + // TODO: enable when bionic has moved to dlmalloc 2.8.5 + // dlmalloc_inspect_all(HeapChunkContext::HeapChunkCallback, &context); + UNIMPLEMENTED(WARNING) << "Native heap send heap segments"; } else { - Heap::WalkHeap(HeapChunkContext::HeapChunkCallback, &context); + Heap::GetAllocSpace()->Walk(HeapChunkContext::HeapChunkCallback, &context); } // Finally, send a heap end chunk. diff --git a/src/dex2oat.cc b/src/dex2oat.cc index b3aec1a4cb..cd977b5f3e 100644 --- a/src/dex2oat.cc +++ b/src/dex2oat.cc @@ -201,11 +201,17 @@ class Dex2Oat { const std::string& host_prefix) { // If we have an existing boot image, position new space after its oat file if (Heap::GetSpaces().size() > 1) { - Space* last_image_space = Heap::GetSpaces()[Heap::GetSpaces().size()-2]; + ImageSpace* last_image_space = NULL; + const std::vector<Space*>& spaces = Heap::GetSpaces(); + for (size_t i=0; i < spaces.size(); i++) { + if (spaces[i]->IsImageSpace()) { + last_image_space = spaces[i]->AsImageSpace(); + } + } CHECK(last_image_space != NULL); CHECK(last_image_space->IsImageSpace()); CHECK(!Heap::GetSpaces()[Heap::GetSpaces().size()-1]->IsImageSpace()); - byte* oat_limit_addr = last_image_space->GetImageHeader().GetOatLimitAddr(); + byte* oat_limit_addr = last_image_space->GetImageHeader().GetOatEnd(); image_base = RoundUp(reinterpret_cast<uintptr_t>(oat_limit_addr), kPageSize); } diff --git a/src/dex_file.cc b/src/dex_file.cc index 3f141b10e5..e119ce0360 100644 --- a/src/dex_file.cc +++ b/src/dex_file.cc @@ -72,7 +72,7 @@ const DexFile* DexFile::Open(const std::string& filename, } void DexFile::ChangePermissions(int prot) const { - if (mprotect(mem_map_->GetAddress(), mem_map_->GetLength(), prot) != 0) { + if (mprotect(mem_map_->Begin(), mem_map_->Size(), prot) != 0) { PLOG(FATAL) << "Failed to change dex file permissions to " << prot << " for " << GetLocation(); } } @@ -193,7 +193,7 @@ jobject DexFile::GetDexObject(JNIEnv* env) const { return dex_object_; } - void* address = const_cast<void*>(reinterpret_cast<const void*>(base_)); + void* address = const_cast<void*>(reinterpret_cast<const void*>(begin_)); jobject byte_buffer = env->NewDirectByteBuffer(address, length_); if (byte_buffer == NULL) { return NULL; @@ -226,14 +226,14 @@ bool DexFile::Init() { return false; } InitIndex(); - if (!DexFileVerifier::Verify(this, base_, length_)) { + if (!DexFileVerifier::Verify(this, begin_, length_)) { return false; } return true; } void DexFile::InitMembers() { - const byte* b = base_; + const byte* b = begin_; header_ = reinterpret_cast<const Header*>(b); const Header* h = header_; string_ids_ = reinterpret_cast<const StringId*>(b + h->string_ids_off_); @@ -281,14 +281,14 @@ uint32_t DexFile::GetVersion() const { } int32_t DexFile::GetStringLength(const StringId& string_id) const { - const byte* ptr = base_ + string_id.string_data_off_; + const byte* ptr = begin_ + string_id.string_data_off_; return DecodeUnsignedLeb128(&ptr); } // Returns a pointer to the UTF-8 string data referred to by the given string_id. const char* DexFile::GetStringDataAndLength(const StringId& string_id, int32_t* length) const { CHECK(length != NULL) << GetLocation(); - const byte* ptr = base_ + string_id.string_data_off_; + const byte* ptr = begin_ + string_id.string_data_off_; *length = DecodeUnsignedLeb128(&ptr); return reinterpret_cast<const char*>(ptr); } diff --git a/src/dex_file.h b/src/dex_file.h index 2f2106b82e..81813c3a77 100644 --- a/src/dex_file.h +++ b/src/dex_file.h @@ -551,7 +551,7 @@ class DexFile { if (class_def.interfaces_off_ == 0) { return NULL; } else { - const byte* addr = base_ + class_def.interfaces_off_; + const byte* addr = begin_ + class_def.interfaces_off_; return reinterpret_cast<const TypeList*>(addr); } } @@ -561,7 +561,7 @@ class DexFile { if (class_def.class_data_off_ == 0) { return NULL; } else { - return base_ + class_def.class_data_off_; + return begin_ + class_def.class_data_off_; } } @@ -570,7 +570,7 @@ class DexFile { if (code_off == 0) { return NULL; // native or abstract method } else { - const byte* addr = base_ + code_off; + const byte* addr = begin_ + code_off; return reinterpret_cast<const CodeItem*>(addr); } } @@ -618,7 +618,7 @@ class DexFile { if (proto_id.parameters_off_ == 0) { return NULL; } else { - const byte* addr = base_ + proto_id.parameters_off_; + const byte* addr = begin_ + proto_id.parameters_off_; return reinterpret_cast<const TypeList*>(addr); } } @@ -627,7 +627,7 @@ class DexFile { if (class_def.static_values_off_ == 0) { return 0; } else { - return base_ + class_def.static_values_off_; + return begin_ + class_def.static_values_off_; } } @@ -655,7 +655,7 @@ class DexFile { if (code_item->debug_info_off_ == 0) { return NULL; } else { - return base_ + code_item->debug_info_off_; + return begin_ + code_item->debug_info_off_; } } @@ -761,8 +761,8 @@ class DexFile { // Opens a .dex file at the given address backed by a MemMap static const DexFile* OpenMemory(const std::string& location, MemMap* mem_map) { - return OpenMemory(mem_map->GetAddress(), - mem_map->GetLength(), + return OpenMemory(mem_map->Begin(), + mem_map->Size(), location, mem_map); } @@ -774,7 +774,7 @@ class DexFile { MemMap* mem_map); DexFile(const byte* base, size_t length, const std::string& location, MemMap* mem_map) - : base_(base), + : begin_(base), length_(length), location_(location), mem_map_(mem_map), @@ -787,7 +787,7 @@ class DexFile { method_ids_(0), proto_ids_(0), class_defs_(0) { - CHECK(base_ != NULL) << GetLocation(); + CHECK(begin_ != NULL) << GetLocation(); CHECK_GT(length_, 0U) << GetLocation(); } @@ -812,7 +812,7 @@ class DexFile { Index index_; // The base address of the memory mapping. - const byte* base_; + const byte* begin_; // The size of the underlying memory allocation in bytes. size_t length_; diff --git a/src/dex_file_verifier.cc b/src/dex_file_verifier.cc index 6a53ebeba8..90c0a878e5 100644 --- a/src/dex_file_verifier.cc +++ b/src/dex_file_verifier.cc @@ -85,15 +85,15 @@ static bool CheckShortyDescriptorMatch(char shorty_char, const char* descriptor, return true; } -bool DexFileVerifier::Verify(DexFile* dex_file, const byte* base, size_t length) { - UniquePtr<DexFileVerifier> verifier(new DexFileVerifier(dex_file, base, length)); +bool DexFileVerifier::Verify(DexFile* dex_file, const byte* begin, size_t length) { + UniquePtr<DexFileVerifier> verifier(new DexFileVerifier(dex_file, begin, length)); return verifier->Verify(); } bool DexFileVerifier::CheckPointerRange(const void* start, const void* end, const char* label) const { uint32_t range_start = reinterpret_cast<uint32_t>(start); uint32_t range_end = reinterpret_cast<uint32_t>(end); - uint32_t file_start = reinterpret_cast<uint32_t>(base_); + uint32_t file_start = reinterpret_cast<uint32_t>(begin_); uint32_t file_end = file_start + length_; if ((range_start < file_start) || (range_start > file_end) || (range_end < file_start) || (range_end > file_end)) { @@ -151,7 +151,7 @@ bool DexFileVerifier::CheckHeader() const { } bool DexFileVerifier::CheckMap() const { - const DexFile::MapList* map = reinterpret_cast<const DexFile::MapList*>(base_ + header_->map_off_); + const DexFile::MapList* map = reinterpret_cast<const DexFile::MapList*>(begin_ + header_->map_off_); const DexFile::MapItem* item = map->list_; uint32_t count = map->size_; @@ -366,7 +366,7 @@ bool DexFileVerifier::CheckClassDataItemMethod(uint32_t idx, uint32_t access_fla bool DexFileVerifier::CheckPadding(uint32_t offset, uint32_t aligned_offset) { if (offset < aligned_offset) { - if (!CheckPointerRange(base_ + offset, base_ + aligned_offset, "section")) { + if (!CheckPointerRange(begin_ + offset, begin_ + aligned_offset, "section")) { return false; } while (offset < aligned_offset) { @@ -671,7 +671,7 @@ bool DexFileVerifier::CheckIntraCodeItem() { bool DexFileVerifier::CheckIntraStringDataItem() { uint32_t size = DecodeUnsignedLeb128(&ptr_); - const byte* file_end = base_ + length_; + const byte* file_end = begin_ + length_; for (uint32_t i = 0; i < size; i++) { if (ptr_ >= file_end) { @@ -1106,7 +1106,7 @@ bool DexFileVerifier::CheckIntraSectionIterate(uint32_t offset, uint32_t count, offset_to_type_map_.insert(std::make_pair(aligned_offset, type)); } - aligned_offset = reinterpret_cast<uint32_t>(ptr_) - reinterpret_cast<uint32_t>(base_); + aligned_offset = reinterpret_cast<uint32_t>(ptr_) - reinterpret_cast<uint32_t>(begin_); if (aligned_offset > length_) { LOG(ERROR) << StringPrintf("Item %d at ends out of bounds", i); return false; @@ -1180,7 +1180,7 @@ bool DexFileVerifier::CheckIntraDataSection(uint32_t offset, uint32_t count, uin return false; } - uint32_t next_offset = reinterpret_cast<uint32_t>(ptr_) - reinterpret_cast<uint32_t>(base_); + uint32_t next_offset = reinterpret_cast<uint32_t>(ptr_) - reinterpret_cast<uint32_t>(begin_); if (next_offset > data_end) { LOG(ERROR) << StringPrintf("Out-of-bounds end of data subsection: %x", next_offset); return false; @@ -1190,12 +1190,12 @@ bool DexFileVerifier::CheckIntraDataSection(uint32_t offset, uint32_t count, uin } bool DexFileVerifier::CheckIntraSection() { - const DexFile::MapList* map = reinterpret_cast<const DexFile::MapList*>(base_ + header_->map_off_); + const DexFile::MapList* map = reinterpret_cast<const DexFile::MapList*>(begin_ + header_->map_off_); const DexFile::MapItem* item = map->list_; uint32_t count = map->size_; uint32_t offset = 0; - ptr_ = base_; + ptr_ = begin_; // Check the items listed in the map. while (count--) { @@ -1222,7 +1222,7 @@ bool DexFileVerifier::CheckIntraSection() { LOG(ERROR) << StringPrintf("Header at %x, not at start of file", section_offset); return false; } - ptr_ = base_ + header_->header_size_; + ptr_ = begin_ + header_->header_size_; offset = header_->header_size_; break; case DexFile::kDexTypeStringIdItem: @@ -1234,7 +1234,7 @@ bool DexFileVerifier::CheckIntraSection() { if (!CheckIntraIdSection(section_offset, section_count, type)) { return false; } - offset = reinterpret_cast<uint32_t>(ptr_) - reinterpret_cast<uint32_t>(base_); + offset = reinterpret_cast<uint32_t>(ptr_) - reinterpret_cast<uint32_t>(begin_); break; case DexFile::kDexTypeMapList: if (section_count != 1) { @@ -1261,7 +1261,7 @@ bool DexFileVerifier::CheckIntraSection() { if (!CheckIntraDataSection(section_offset, section_count, type)) { return false; } - offset = reinterpret_cast<uint32_t>(ptr_) - reinterpret_cast<uint32_t>(base_); + offset = reinterpret_cast<uint32_t>(ptr_) - reinterpret_cast<uint32_t>(begin_); break; default: LOG(ERROR) << StringPrintf("Unknown map item type %x", type); @@ -1593,7 +1593,7 @@ bool DexFileVerifier::CheckInterClassDefItem() { // Check that references in class_data_item are to the right class. if (item->class_data_off_ != 0) { - const byte* data = base_ + item->class_data_off_; + const byte* data = begin_ + item->class_data_off_; uint16_t data_definer = FindFirstClassDataDefiner(data); if ((data_definer != item->class_idx_) && (data_definer != DexFile::kDexNoIndex16)) { LOG(ERROR) << "Invalid class_data_item"; @@ -1603,7 +1603,7 @@ bool DexFileVerifier::CheckInterClassDefItem() { // Check that references in annotations_directory_item are to right class. if (item->annotations_off_ != 0) { - const byte* data = base_ + item->annotations_off_; + const byte* data = begin_ + item->annotations_off_; uint16_t annotations_definer = FindFirstAnnotationsDirectoryDefiner(data); if ((annotations_definer != item->class_idx_) && (annotations_definer != DexFile::kDexNoIndex16)) { LOG(ERROR) << "Invalid annotations_directory_item"; @@ -1646,7 +1646,7 @@ bool DexFileVerifier::CheckInterAnnotationSetItem() { // Get the annotation from the offset and the type index for the annotation. const DexFile::AnnotationItem* annotation = - reinterpret_cast<const DexFile::AnnotationItem*>(base_ + *offsets); + reinterpret_cast<const DexFile::AnnotationItem*>(begin_ + *offsets); const uint8_t* data = annotation->annotation_; uint32_t idx = DecodeUnsignedLeb128(&data); @@ -1768,7 +1768,7 @@ bool DexFileVerifier::CheckInterSectionIterate(uint32_t offset, uint32_t count, previous_item_ = NULL; for (uint32_t i = 0; i < count; i++) { uint32_t new_offset = (offset + alignment_mask) & ~alignment_mask; - ptr_ = base_ + new_offset; + ptr_ = begin_ + new_offset; const byte* prev_ptr = ptr_; // Check depending on the section type. @@ -1839,14 +1839,14 @@ bool DexFileVerifier::CheckInterSectionIterate(uint32_t offset, uint32_t count, } previous_item_ = prev_ptr; - offset = reinterpret_cast<uint32_t>(ptr_) - reinterpret_cast<uint32_t>(base_); + offset = reinterpret_cast<uint32_t>(ptr_) - reinterpret_cast<uint32_t>(begin_); } return true; } bool DexFileVerifier::CheckInterSection() { - const DexFile::MapList* map = reinterpret_cast<const DexFile::MapList*>(base_ + header_->map_off_); + const DexFile::MapList* map = reinterpret_cast<const DexFile::MapList*>(begin_ + header_->map_off_); const DexFile::MapItem* item = map->list_; uint32_t count = map->size_; diff --git a/src/dex_file_verifier.h b/src/dex_file_verifier.h index 6b8fcf4696..9b66b6eacf 100644 --- a/src/dex_file_verifier.h +++ b/src/dex_file_verifier.h @@ -11,11 +11,11 @@ namespace art { class DexFileVerifier { public: - static bool Verify(DexFile* dex_file, const byte* base, size_t length); + static bool Verify(DexFile* dex_file, const byte* begin, size_t length); private: - DexFileVerifier(DexFile* dex_file, const byte* base, size_t length) - : dex_file_(dex_file), base_(base), length_(length), + DexFileVerifier(DexFile* dex_file, const byte* begin, size_t length) + : dex_file_(dex_file), begin_(begin), length_(length), header_(&dex_file->GetHeader()), ptr_(NULL), previous_item_(NULL) { } @@ -70,7 +70,7 @@ class DexFileVerifier { bool CheckInterSection(); DexFile* dex_file_; - const byte* base_; + const byte* begin_; size_t length_; const DexFile::Header* header_; diff --git a/src/dlmalloc.c b/src/dlmalloc.c index e366ec942c..931a44edc7 100644 --- a/src/dlmalloc.c +++ b/src/dlmalloc.c @@ -1,5454 +1,19 @@ -/* - * Copyright (C) 2008 The Android Open Source Project - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS - * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE - * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, - * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, - * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS - * OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED - * AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, - * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT - * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF - * SUCH DAMAGE. - */ -/* - This is a version (aka dlmalloc) of malloc/free/realloc written by - Doug Lea and released to the public domain, as explained at - http://creativecommons.org/licenses/publicdomain. Send questions, - comments, complaints, performance data, etc to dl@cs.oswego.edu +// Copyright 2012 Google Inc. All Rights Reserved. +#define FOR_DLMALLOC_C // Avoid inclusion of src/malloc.h +#include "dlmalloc.h" -* Version 2.8.3 Thu Sep 22 11:16:15 2005 Doug Lea (dl at gee) +#include <stddef.h> +#include <stdint.h> +#include <stdlib.h> - Note: There may be an updated version of this malloc obtainable at - ftp://gee.cs.oswego.edu/pub/misc/malloc.c - Check before installing! +// Disable GCC diagnostics so that -Werror won't fail +#pragma GCC diagnostic ignored "-Wsign-compare" +#pragma GCC diagnostic ignored "-Wunused-variable" +#pragma GCC diagnostic ignored "-Wempty-body" -* Quickstart +// ART specific morecore implementation +#define MORECORE(x) art_heap_morecore(m, x) +extern void* art_heap_morecore(void* m, intptr_t increment); - This library is all in one file to simplify the most common usage: - ftp it, compile it (-O3), and link it into another program. All of - the compile-time options default to reasonable values for use on - most platforms. You might later want to step through various - compile-time and dynamic tuning options. - - For convenience, an include file for code using this malloc is at: - ftp://gee.cs.oswego.edu/pub/misc/malloc-2.8.3.h - You don't really need this .h file unless you call functions not - defined in your system include files. The .h file contains only the - excerpts from this file needed for using this malloc on ANSI C/C++ - systems, so long as you haven't changed compile-time options about - naming and tuning parameters. If you do, then you can create your - own malloc.h that does include all settings by cutting at the point - indicated below. Note that you may already by default be using a C - library containing a malloc that is based on some version of this - malloc (for example in linux). You might still want to use the one - in this file to customize settings or to avoid overheads associated - with library versions. - -* Vital statistics: - - Supported pointer/size_t representation: 4 or 8 bytes - size_t MUST be an unsigned type of the same width as - pointers. (If you are using an ancient system that declares - size_t as a signed type, or need it to be a different width - than pointers, you can use a previous release of this malloc - (e.g. 2.7.2) supporting these.) - - Alignment: 8 bytes (default) - This suffices for nearly all current machines and C compilers. - However, you can define MALLOC_ALIGNMENT to be wider than this - if necessary (up to 128bytes), at the expense of using more space. - - Minimum overhead per allocated chunk: 4 or 8 bytes (if 4byte sizes) - 8 or 16 bytes (if 8byte sizes) - Each malloced chunk has a hidden word of overhead holding size - and status information, and additional cross-check word - if FOOTERS is defined. - - Minimum allocated size: 4-byte ptrs: 16 bytes (including overhead) - 8-byte ptrs: 32 bytes (including overhead) - - Even a request for zero bytes (i.e., malloc(0)) returns a - pointer to something of the minimum allocatable size. - The maximum overhead wastage (i.e., number of extra bytes - allocated than were requested in malloc) is less than or equal - to the minimum size, except for requests >= mmap_threshold that - are serviced via mmap(), where the worst case wastage is about - 32 bytes plus the remainder from a system page (the minimal - mmap unit); typically 4096 or 8192 bytes. - - Security: static-safe; optionally more or less - The "security" of malloc refers to the ability of malicious - code to accentuate the effects of errors (for example, freeing - space that is not currently malloc'ed or overwriting past the - ends of chunks) in code that calls malloc. This malloc - guarantees not to modify any memory locations below the base of - heap, i.e., static variables, even in the presence of usage - errors. The routines additionally detect most improper frees - and reallocs. All this holds as long as the static bookkeeping - for malloc itself is not corrupted by some other means. This - is only one aspect of security -- these checks do not, and - cannot, detect all possible programming errors. - - If FOOTERS is defined nonzero, then each allocated chunk - carries an additional check word to verify that it was malloced - from its space. These check words are the same within each - execution of a program using malloc, but differ across - executions, so externally crafted fake chunks cannot be - freed. This improves security by rejecting frees/reallocs that - could corrupt heap memory, in addition to the checks preventing - writes to statics that are always on. This may further improve - security at the expense of time and space overhead. (Note that - FOOTERS may also be worth using with MSPACES.) - - By default detected errors cause the program to abort (calling - "abort()"). You can override this to instead proceed past - errors by defining PROCEED_ON_ERROR. In this case, a bad free - has no effect, and a malloc that encounters a bad address - caused by user overwrites will ignore the bad address by - dropping pointers and indices to all known memory. This may - be appropriate for programs that should continue if at all - possible in the face of programming errors, although they may - run out of memory because dropped memory is never reclaimed. - - If you don't like either of these options, you can define - CORRUPTION_ERROR_ACTION and USAGE_ERROR_ACTION to do anything - else. And if if you are sure that your program using malloc has - no errors or vulnerabilities, you can define INSECURE to 1, - which might (or might not) provide a small performance improvement. - - Thread-safety: NOT thread-safe unless USE_LOCKS defined - When USE_LOCKS is defined, each public call to malloc, free, - etc is surrounded with either a pthread mutex or a win32 - spinlock (depending on WIN32). This is not especially fast, and - can be a major bottleneck. It is designed only to provide - minimal protection in concurrent environments, and to provide a - basis for extensions. If you are using malloc in a concurrent - program, consider instead using ptmalloc, which is derived from - a version of this malloc. (See http://www.malloc.de). - - System requirements: Any combination of MORECORE and/or MMAP/MUNMAP - This malloc can use unix sbrk or any emulation (invoked using - the CALL_MORECORE macro) and/or mmap/munmap or any emulation - (invoked using CALL_MMAP/CALL_MUNMAP) to get and release system - memory. On most unix systems, it tends to work best if both - MORECORE and MMAP are enabled. On Win32, it uses emulations - based on VirtualAlloc. It also uses common C library functions - like memset. - - Compliance: I believe it is compliant with the Single Unix Specification - (See http://www.unix.org). Also SVID/XPG, ANSI C, and probably - others as well. - -* Overview of algorithms - - This is not the fastest, most space-conserving, most portable, or - most tunable malloc ever written. However it is among the fastest - while also being among the most space-conserving, portable and - tunable. Consistent balance across these factors results in a good - general-purpose allocator for malloc-intensive programs. - - In most ways, this malloc is a best-fit allocator. Generally, it - chooses the best-fitting existing chunk for a request, with ties - broken in approximately least-recently-used order. (This strategy - normally maintains low fragmentation.) However, for requests less - than 256bytes, it deviates from best-fit when there is not an - exactly fitting available chunk by preferring to use space adjacent - to that used for the previous small request, as well as by breaking - ties in approximately most-recently-used order. (These enhance - locality of series of small allocations.) And for very large requests - (>= 256Kb by default), it relies on system memory mapping - facilities, if supported. (This helps avoid carrying around and - possibly fragmenting memory used only for large chunks.) - - All operations (except malloc_stats and mallinfo) have execution - times that are bounded by a constant factor of the number of bits in - a size_t, not counting any clearing in calloc or copying in realloc, - or actions surrounding MORECORE and MMAP that have times - proportional to the number of non-contiguous regions returned by - system allocation routines, which is often just 1. - - The implementation is not very modular and seriously overuses - macros. Perhaps someday all C compilers will do as good a job - inlining modular code as can now be done by brute-force expansion, - but now, enough of them seem not to. - - Some compilers issue a lot of warnings about code that is - dead/unreachable only on some platforms, and also about intentional - uses of negation on unsigned types. All known cases of each can be - ignored. - - For a longer but out of date high-level description, see - http://gee.cs.oswego.edu/dl/html/malloc.html - -* MSPACES - If MSPACES is defined, then in addition to malloc, free, etc., - this file also defines mspace_malloc, mspace_free, etc. These - are versions of malloc routines that take an "mspace" argument - obtained using create_mspace, to control all internal bookkeeping. - If ONLY_MSPACES is defined, only these versions are compiled. - So if you would like to use this allocator for only some allocations, - and your system malloc for others, you can compile with - ONLY_MSPACES and then do something like... - static mspace mymspace = create_mspace(0,0); // for example - #define mymalloc(bytes) mspace_malloc(mymspace, bytes) - - (Note: If you only need one instance of an mspace, you can instead - use "USE_DL_PREFIX" to relabel the global malloc.) - - You can similarly create thread-local allocators by storing - mspaces as thread-locals. For example: - static __thread mspace tlms = 0; - void* tlmalloc(size_t bytes) { - if (tlms == 0) tlms = create_mspace(0, 0); - return mspace_malloc(tlms, bytes); - } - void tlfree(void* mem) { mspace_free(tlms, mem); } - - Unless FOOTERS is defined, each mspace is completely independent. - You cannot allocate from one and free to another (although - conformance is only weakly checked, so usage errors are not always - caught). If FOOTERS is defined, then each chunk carries around a tag - indicating its originating mspace, and frees are directed to their - originating spaces. - - ------------------------- Compile-time options --------------------------- - -Be careful in setting #define values for numerical constants of type -size_t. On some systems, literal values are not automatically extended -to size_t precision unless they are explicitly casted. - -WIN32 default: defined if _WIN32 defined - Defining WIN32 sets up defaults for MS environment and compilers. - Otherwise defaults are for unix. - -MALLOC_ALIGNMENT default: (size_t)8 - Controls the minimum alignment for malloc'ed chunks. It must be a - power of two and at least 8, even on machines for which smaller - alignments would suffice. It may be defined as larger than this - though. Note however that code and data structures are optimized for - the case of 8-byte alignment. - -MSPACES default: 0 (false) - If true, compile in support for independent allocation spaces. - This is only supported if HAVE_MMAP is true. - -ONLY_MSPACES default: 0 (false) - If true, only compile in mspace versions, not regular versions. - -USE_LOCKS default: 0 (false) - Causes each call to each public routine to be surrounded with - pthread or WIN32 mutex lock/unlock. (If set true, this can be - overridden on a per-mspace basis for mspace versions.) - -FOOTERS default: 0 - If true, provide extra checking and dispatching by placing - information in the footers of allocated chunks. This adds - space and time overhead. - -INSECURE default: 0 - If true, omit checks for usage errors and heap space overwrites. - -USE_DL_PREFIX default: NOT defined - Causes compiler to prefix all public routines with the string 'dl'. - This can be useful when you only want to use this malloc in one part - of a program, using your regular system malloc elsewhere. - -ABORT default: defined as abort() - Defines how to abort on failed checks. On most systems, a failed - check cannot die with an "assert" or even print an informative - message, because the underlying print routines in turn call malloc, - which will fail again. Generally, the best policy is to simply call - abort(). It's not very useful to do more than this because many - errors due to overwriting will show up as address faults (null, odd - addresses etc) rather than malloc-triggered checks, so will also - abort. Also, most compilers know that abort() does not return, so - can better optimize code conditionally calling it. - -PROCEED_ON_ERROR default: defined as 0 (false) - Controls whether detected bad addresses cause them to bypassed - rather than aborting. If set, detected bad arguments to free and - realloc are ignored. And all bookkeeping information is zeroed out - upon a detected overwrite of freed heap space, thus losing the - ability to ever return it from malloc again, but enabling the - application to proceed. If PROCEED_ON_ERROR is defined, the - static variable malloc_corruption_error_count is compiled in - and can be examined to see if errors have occurred. This option - generates slower code than the default abort policy. - -DEBUG default: NOT defined - The DEBUG setting is mainly intended for people trying to modify - this code or diagnose problems when porting to new platforms. - However, it may also be able to better isolate user errors than just - using runtime checks. The assertions in the check routines spell - out in more detail the assumptions and invariants underlying the - algorithms. The checking is fairly extensive, and will slow down - execution noticeably. Calling malloc_stats or mallinfo with DEBUG - set will attempt to check every non-mmapped allocated and free chunk - in the course of computing the summaries. - -ABORT_ON_ASSERT_FAILURE default: defined as 1 (true) - Debugging assertion failures can be nearly impossible if your - version of the assert macro causes malloc to be called, which will - lead to a cascade of further failures, blowing the runtime stack. - ABORT_ON_ASSERT_FAILURE cause assertions failures to call abort(), - which will usually make debugging easier. - -MALLOC_FAILURE_ACTION default: sets errno to ENOMEM, or no-op on win32 - The action to take before "return 0" when malloc fails to be able to - return memory because there is none available. - -HAVE_MORECORE default: 1 (true) unless win32 or ONLY_MSPACES - True if this system supports sbrk or an emulation of it. - -MORECORE default: sbrk - The name of the sbrk-style system routine to call to obtain more - memory. See below for guidance on writing custom MORECORE - functions. The type of the argument to sbrk/MORECORE varies across - systems. It cannot be size_t, because it supports negative - arguments, so it is normally the signed type of the same width as - size_t (sometimes declared as "intptr_t"). It doesn't much matter - though. Internally, we only call it with arguments less than half - the max value of a size_t, which should work across all reasonable - possibilities, although sometimes generating compiler warnings. See - near the end of this file for guidelines for creating a custom - version of MORECORE. - -MORECORE_CONTIGUOUS default: 1 (true) - If true, take advantage of fact that consecutive calls to MORECORE - with positive arguments always return contiguous increasing - addresses. This is true of unix sbrk. It does not hurt too much to - set it true anyway, since malloc copes with non-contiguities. - Setting it false when definitely non-contiguous saves time - and possibly wasted space it would take to discover this though. - -MORECORE_CANNOT_TRIM default: NOT defined - True if MORECORE cannot release space back to the system when given - negative arguments. This is generally necessary only if you are - using a hand-crafted MORECORE function that cannot handle negative - arguments. - -HAVE_MMAP default: 1 (true) - True if this system supports mmap or an emulation of it. If so, and - HAVE_MORECORE is not true, MMAP is used for all system - allocation. If set and HAVE_MORECORE is true as well, MMAP is - primarily used to directly allocate very large blocks. It is also - used as a backup strategy in cases where MORECORE fails to provide - space from system. Note: A single call to MUNMAP is assumed to be - able to unmap memory that may have be allocated using multiple calls - to MMAP, so long as they are adjacent. - -HAVE_MREMAP default: 1 on linux, else 0 - If true realloc() uses mremap() to re-allocate large blocks and - extend or shrink allocation spaces. - -MMAP_CLEARS default: 1 on unix - True if mmap clears memory so calloc doesn't need to. This is true - for standard unix mmap using /dev/zero. - -USE_BUILTIN_FFS default: 0 (i.e., not used) - Causes malloc to use the builtin ffs() function to compute indices. - Some compilers may recognize and intrinsify ffs to be faster than the - supplied C version. Also, the case of x86 using gcc is special-cased - to an asm instruction, so is already as fast as it can be, and so - this setting has no effect. (On most x86s, the asm version is only - slightly faster than the C version.) - -malloc_getpagesize default: derive from system includes, or 4096. - The system page size. To the extent possible, this malloc manages - memory from the system in page-size units. This may be (and - usually is) a function rather than a constant. This is ignored - if WIN32, where page size is determined using getSystemInfo during - initialization. - -USE_DEV_RANDOM default: 0 (i.e., not used) - Causes malloc to use /dev/random to initialize secure magic seed for - stamping footers. Otherwise, the current time is used. - -NO_MALLINFO default: 0 - If defined, don't compile "mallinfo". This can be a simple way - of dealing with mismatches between system declarations and - those in this file. - -MALLINFO_FIELD_TYPE default: size_t - The type of the fields in the mallinfo struct. This was originally - defined as "int" in SVID etc, but is more usefully defined as - size_t. The value is used only if HAVE_USR_INCLUDE_MALLOC_H is not set - -REALLOC_ZERO_BYTES_FREES default: not defined - This should be set if a call to realloc with zero bytes should - be the same as a call to free. Some people think it should. Otherwise, - since this malloc returns a unique pointer for malloc(0), so does - realloc(p, 0). - -LACKS_UNISTD_H, LACKS_FCNTL_H, LACKS_SYS_PARAM_H, LACKS_SYS_MMAN_H -LACKS_STRINGS_H, LACKS_STRING_H, LACKS_SYS_TYPES_H, LACKS_ERRNO_H -LACKS_STDLIB_H default: NOT defined unless on WIN32 - Define these if your system does not have these header files. - You might need to manually insert some of the declarations they provide. - -DEFAULT_GRANULARITY default: page size if MORECORE_CONTIGUOUS, - system_info.dwAllocationGranularity in WIN32, - otherwise 64K. - Also settable using mallopt(M_GRANULARITY, x) - The unit for allocating and deallocating memory from the system. On - most systems with contiguous MORECORE, there is no reason to - make this more than a page. However, systems with MMAP tend to - either require or encourage larger granularities. You can increase - this value to prevent system allocation functions to be called so - often, especially if they are slow. The value must be at least one - page and must be a power of two. Setting to 0 causes initialization - to either page size or win32 region size. (Note: In previous - versions of malloc, the equivalent of this option was called - "TOP_PAD") - -DEFAULT_TRIM_THRESHOLD default: 2MB - Also settable using mallopt(M_TRIM_THRESHOLD, x) - The maximum amount of unused top-most memory to keep before - releasing via malloc_trim in free(). Automatic trimming is mainly - useful in long-lived programs using contiguous MORECORE. Because - trimming via sbrk can be slow on some systems, and can sometimes be - wasteful (in cases where programs immediately afterward allocate - more large chunks) the value should be high enough so that your - overall system performance would improve by releasing this much - memory. As a rough guide, you might set to a value close to the - average size of a process (program) running on your system. - Releasing this much memory would allow such a process to run in - memory. Generally, it is worth tuning trim thresholds when a - program undergoes phases where several large chunks are allocated - and released in ways that can reuse each other's storage, perhaps - mixed with phases where there are no such chunks at all. The trim - value must be greater than page size to have any useful effect. To - disable trimming completely, you can set to MAX_SIZE_T. Note that the trick - some people use of mallocing a huge space and then freeing it at - program startup, in an attempt to reserve system memory, doesn't - have the intended effect under automatic trimming, since that memory - will immediately be returned to the system. - -DEFAULT_MMAP_THRESHOLD default: 256K - Also settable using mallopt(M_MMAP_THRESHOLD, x) - The request size threshold for using MMAP to directly service a - request. Requests of at least this size that cannot be allocated - using already-existing space will be serviced via mmap. (If enough - normal freed space already exists it is used instead.) Using mmap - segregates relatively large chunks of memory so that they can be - individually obtained and released from the host system. A request - serviced through mmap is never reused by any other request (at least - not directly; the system may just so happen to remap successive - requests to the same locations). Segregating space in this way has - the benefits that: Mmapped space can always be individually released - back to the system, which helps keep the system level memory demands - of a long-lived program low. Also, mapped memory doesn't become - `locked' between other chunks, as can happen with normally allocated - chunks, which means that even trimming via malloc_trim would not - release them. However, it has the disadvantage that the space - cannot be reclaimed, consolidated, and then used to service later - requests, as happens with normal chunks. The advantages of mmap - nearly always outweigh disadvantages for "large" chunks, but the - value of "large" may vary across systems. The default is an - empirically derived value that works well in most systems. You can - disable mmap by setting to MAX_SIZE_T. - -*/ - -#ifndef WIN32 -#ifdef _WIN32 -#define WIN32 1 -#endif /* _WIN32 */ -#endif /* WIN32 */ -#ifdef WIN32 -#define WIN32_LEAN_AND_MEAN -#include <windows.h> -#define HAVE_MMAP 1 -#define HAVE_MORECORE 0 -#define LACKS_UNISTD_H -#define LACKS_SYS_PARAM_H -#define LACKS_SYS_MMAN_H -#define LACKS_STRING_H -#define LACKS_STRINGS_H -#define LACKS_SYS_TYPES_H -#define LACKS_ERRNO_H -#define MALLOC_FAILURE_ACTION -#define MMAP_CLEARS 0 /* WINCE and some others apparently don't clear */ -#endif /* WIN32 */ - -#if defined(DARWIN) || defined(_DARWIN) -/* Mac OSX docs advise not to use sbrk; it seems better to use mmap */ -#ifndef HAVE_MORECORE -#define HAVE_MORECORE 0 -#define HAVE_MMAP 1 -#endif /* HAVE_MORECORE */ -#endif /* DARWIN */ - -#ifndef LACKS_SYS_TYPES_H -#include <sys/types.h> /* For size_t */ -#endif /* LACKS_SYS_TYPES_H */ - -/* The maximum possible size_t value has all bits set */ -#define MAX_SIZE_T (~(size_t)0) - -#ifndef ONLY_MSPACES -#define ONLY_MSPACES 0 -#endif /* ONLY_MSPACES */ -#ifndef MSPACES -#if ONLY_MSPACES -#define MSPACES 1 -#else /* ONLY_MSPACES */ -#define MSPACES 0 -#endif /* ONLY_MSPACES */ -#endif /* MSPACES */ -#ifndef MALLOC_ALIGNMENT -#define MALLOC_ALIGNMENT ((size_t)8U) -#endif /* MALLOC_ALIGNMENT */ -#ifndef FOOTERS -#define FOOTERS 0 -#endif /* FOOTERS */ -#ifndef USE_MAX_ALLOWED_FOOTPRINT -#define USE_MAX_ALLOWED_FOOTPRINT 0 -#endif -#ifndef ABORT -#define ABORT abort() -#endif /* ABORT */ -#ifndef ABORT_ON_ASSERT_FAILURE -#define ABORT_ON_ASSERT_FAILURE 1 -#endif /* ABORT_ON_ASSERT_FAILURE */ -#ifndef PROCEED_ON_ERROR -#define PROCEED_ON_ERROR 0 -#endif /* PROCEED_ON_ERROR */ -#ifndef USE_LOCKS -#define USE_LOCKS 0 -#endif /* USE_LOCKS */ -#ifndef INSECURE -#define INSECURE 0 -#endif /* INSECURE */ -#ifndef HAVE_MMAP -#define HAVE_MMAP 1 -#endif /* HAVE_MMAP */ -#ifndef MMAP_CLEARS -#define MMAP_CLEARS 1 -#endif /* MMAP_CLEARS */ -#ifndef HAVE_MREMAP -#ifdef linux -#define HAVE_MREMAP 1 -#else /* linux */ -#define HAVE_MREMAP 0 -#endif /* linux */ -#endif /* HAVE_MREMAP */ -#ifndef MALLOC_FAILURE_ACTION -#define MALLOC_FAILURE_ACTION errno = ENOMEM; -#endif /* MALLOC_FAILURE_ACTION */ -#ifndef HAVE_MORECORE -#if ONLY_MSPACES -#define HAVE_MORECORE 0 -#else /* ONLY_MSPACES */ -#define HAVE_MORECORE 1 -#endif /* ONLY_MSPACES */ -#endif /* HAVE_MORECORE */ -#if !HAVE_MORECORE -#define MORECORE_CONTIGUOUS 0 -#else /* !HAVE_MORECORE */ -#ifndef MORECORE -#define MORECORE sbrk -#endif /* MORECORE */ -#ifndef MORECORE_CONTIGUOUS -#define MORECORE_CONTIGUOUS 1 -#endif /* MORECORE_CONTIGUOUS */ -#endif /* HAVE_MORECORE */ -#ifndef DEFAULT_GRANULARITY -#if MORECORE_CONTIGUOUS -#define DEFAULT_GRANULARITY (0) /* 0 means to compute in init_mparams */ -#else /* MORECORE_CONTIGUOUS */ -#define DEFAULT_GRANULARITY ((size_t)64U * (size_t)1024U) -#endif /* MORECORE_CONTIGUOUS */ -#endif /* DEFAULT_GRANULARITY */ -#ifndef DEFAULT_TRIM_THRESHOLD -#ifndef MORECORE_CANNOT_TRIM -#define DEFAULT_TRIM_THRESHOLD ((size_t)2U * (size_t)1024U * (size_t)1024U) -#else /* MORECORE_CANNOT_TRIM */ -#define DEFAULT_TRIM_THRESHOLD MAX_SIZE_T -#endif /* MORECORE_CANNOT_TRIM */ -#endif /* DEFAULT_TRIM_THRESHOLD */ -#ifndef DEFAULT_MMAP_THRESHOLD -#if HAVE_MMAP -#define DEFAULT_MMAP_THRESHOLD ((size_t)64U * (size_t)1024U) -#else /* HAVE_MMAP */ -#define DEFAULT_MMAP_THRESHOLD MAX_SIZE_T -#endif /* HAVE_MMAP */ -#endif /* DEFAULT_MMAP_THRESHOLD */ -#ifndef USE_BUILTIN_FFS -#define USE_BUILTIN_FFS 0 -#endif /* USE_BUILTIN_FFS */ -#ifndef USE_DEV_RANDOM -#define USE_DEV_RANDOM 0 -#endif /* USE_DEV_RANDOM */ -#ifndef NO_MALLINFO -#define NO_MALLINFO 0 -#endif /* NO_MALLINFO */ -#ifndef MALLINFO_FIELD_TYPE -#define MALLINFO_FIELD_TYPE size_t -#endif /* MALLINFO_FIELD_TYPE */ - -/* - mallopt tuning options. SVID/XPG defines four standard parameter - numbers for mallopt, normally defined in malloc.h. None of these - are used in this malloc, so setting them has no effect. But this - malloc does support the following options. -*/ - -#define M_TRIM_THRESHOLD (-1) -#define M_GRANULARITY (-2) -#define M_MMAP_THRESHOLD (-3) - -/* ------------------------ Mallinfo declarations ------------------------ */ - -#if !NO_MALLINFO -/* - This version of malloc supports the standard SVID/XPG mallinfo - routine that returns a struct containing usage properties and - statistics. It should work on any system that has a - /usr/include/malloc.h defining struct mallinfo. The main - declaration needed is the mallinfo struct that is returned (by-copy) - by mallinfo(). The malloinfo struct contains a bunch of fields that - are not even meaningful in this version of malloc. These fields are - are instead filled by mallinfo() with other numbers that might be of - interest. - - HAVE_USR_INCLUDE_MALLOC_H should be set if you have a - /usr/include/malloc.h file that includes a declaration of struct - mallinfo. If so, it is included; else a compliant version is - declared below. These must be precisely the same for mallinfo() to - work. The original SVID version of this struct, defined on most - systems with mallinfo, declares all fields as ints. But some others - define as unsigned long. If your system defines the fields using a - type of different width than listed here, you MUST #include your - system version and #define HAVE_USR_INCLUDE_MALLOC_H. -*/ - -/* #define HAVE_USR_INCLUDE_MALLOC_H */ - -#if !ANDROID -#ifdef HAVE_USR_INCLUDE_MALLOC_H -#include "/usr/include/malloc.h" -#else /* HAVE_USR_INCLUDE_MALLOC_H */ - -struct mallinfo { - MALLINFO_FIELD_TYPE arena; /* non-mmapped space allocated from system */ - MALLINFO_FIELD_TYPE ordblks; /* number of free chunks */ - MALLINFO_FIELD_TYPE smblks; /* always 0 */ - MALLINFO_FIELD_TYPE hblks; /* always 0 */ - MALLINFO_FIELD_TYPE hblkhd; /* space in mmapped regions */ - MALLINFO_FIELD_TYPE usmblks; /* maximum total allocated space */ - MALLINFO_FIELD_TYPE fsmblks; /* always 0 */ - MALLINFO_FIELD_TYPE uordblks; /* total allocated space */ - MALLINFO_FIELD_TYPE fordblks; /* total free space */ - MALLINFO_FIELD_TYPE keepcost; /* releasable (via malloc_trim) space */ -}; - -#endif /* HAVE_USR_INCLUDE_MALLOC_H */ -#endif /* NO_MALLINFO */ -#endif /* ANDROID */ - -#ifdef __cplusplus -extern "C" { -#endif /* __cplusplus */ - -#if !ONLY_MSPACES - -/* ------------------- Declarations of public routines ------------------- */ - -/* Check an additional macro for the five primary functions */ -#ifndef USE_DL_PREFIX -#define dlcalloc calloc -#define dlfree free -#define dlmalloc malloc -#define dlmemalign memalign -#define dlrealloc realloc -#endif - -#ifndef USE_DL_PREFIX -#define dlvalloc valloc -#define dlpvalloc pvalloc -#define dlmallinfo mallinfo -#define dlmallopt mallopt -#define dlmalloc_trim malloc_trim -#define dlmalloc_walk_free_pages \ - malloc_walk_free_pages -#define dlmalloc_walk_heap \ - malloc_walk_heap -#define dlmalloc_stats malloc_stats -#define dlmalloc_usable_size malloc_usable_size -#define dlmalloc_footprint malloc_footprint -#define dlmalloc_max_allowed_footprint \ - malloc_max_allowed_footprint -#define dlmalloc_set_max_allowed_footprint \ - malloc_set_max_allowed_footprint -#define dlmalloc_max_footprint malloc_max_footprint -#define dlindependent_calloc independent_calloc -#define dlindependent_comalloc independent_comalloc -#endif /* USE_DL_PREFIX */ - - -/* - malloc(size_t n) - Returns a pointer to a newly allocated chunk of at least n bytes, or - null if no space is available, in which case errno is set to ENOMEM - on ANSI C systems. - - If n is zero, malloc returns a minimum-sized chunk. (The minimum - size is 16 bytes on most 32bit systems, and 32 bytes on 64bit - systems.) Note that size_t is an unsigned type, so calls with - arguments that would be negative if signed are interpreted as - requests for huge amounts of space, which will often fail. The - maximum supported value of n differs across systems, but is in all - cases less than the maximum representable value of a size_t. -*/ -void* dlmalloc(size_t); - -/* - free(void* p) - Releases the chunk of memory pointed to by p, that had been previously - allocated using malloc or a related routine such as realloc. - It has no effect if p is null. If p was not malloced or already - freed, free(p) will by default cause the current program to abort. -*/ -void dlfree(void*); - -/* - calloc(size_t n_elements, size_t element_size); - Returns a pointer to n_elements * element_size bytes, with all locations - set to zero. -*/ -void* dlcalloc(size_t, size_t); - -/* - realloc(void* p, size_t n) - Returns a pointer to a chunk of size n that contains the same data - as does chunk p up to the minimum of (n, p's size) bytes, or null - if no space is available. - - The returned pointer may or may not be the same as p. The algorithm - prefers extending p in most cases when possible, otherwise it - employs the equivalent of a malloc-copy-free sequence. - - If p is null, realloc is equivalent to malloc. - - If space is not available, realloc returns null, errno is set (if on - ANSI) and p is NOT freed. - - if n is for fewer bytes than already held by p, the newly unused - space is lopped off and freed if possible. realloc with a size - argument of zero (re)allocates a minimum-sized chunk. - - The old unix realloc convention of allowing the last-free'd chunk - to be used as an argument to realloc is not supported. -*/ - -void* dlrealloc(void*, size_t); - -/* - memalign(size_t alignment, size_t n); - Returns a pointer to a newly allocated chunk of n bytes, aligned - in accord with the alignment argument. - - The alignment argument should be a power of two. If the argument is - not a power of two, the nearest greater power is used. - 8-byte alignment is guaranteed by normal malloc calls, so don't - bother calling memalign with an argument of 8 or less. - - Overreliance on memalign is a sure way to fragment space. -*/ -void* dlmemalign(size_t, size_t); - -/* - valloc(size_t n); - Equivalent to memalign(pagesize, n), where pagesize is the page - size of the system. If the pagesize is unknown, 4096 is used. -*/ -void* dlvalloc(size_t); - -/* - mallopt(int parameter_number, int parameter_value) - Sets tunable parameters The format is to provide a - (parameter-number, parameter-value) pair. mallopt then sets the - corresponding parameter to the argument value if it can (i.e., so - long as the value is meaningful), and returns 1 if successful else - 0. SVID/XPG/ANSI defines four standard param numbers for mallopt, - normally defined in malloc.h. None of these are use in this malloc, - so setting them has no effect. But this malloc also supports other - options in mallopt. See below for details. Briefly, supported - parameters are as follows (listed defaults are for "typical" - configurations). - - Symbol param # default allowed param values - M_TRIM_THRESHOLD -1 2*1024*1024 any (MAX_SIZE_T disables) - M_GRANULARITY -2 page size any power of 2 >= page size - M_MMAP_THRESHOLD -3 256*1024 any (or 0 if no MMAP support) -*/ -int dlmallopt(int, int); - -/* - malloc_footprint(); - Returns the number of bytes obtained from the system. The total - number of bytes allocated by malloc, realloc etc., is less than this - value. Unlike mallinfo, this function returns only a precomputed - result, so can be called frequently to monitor memory consumption. - Even if locks are otherwise defined, this function does not use them, - so results might not be up to date. -*/ -size_t dlmalloc_footprint(void); - -#if USE_MAX_ALLOWED_FOOTPRINT -/* - malloc_max_allowed_footprint(); - Returns the number of bytes that the heap is allowed to obtain - from the system. malloc_footprint() should always return a - size less than or equal to max_allowed_footprint, unless the - max_allowed_footprint was set to a value smaller than the - footprint at the time. -*/ -size_t dlmalloc_max_allowed_footprint(); - -/* - malloc_set_max_allowed_footprint(); - Set the maximum number of bytes that the heap is allowed to - obtain from the system. The size will be rounded up to a whole - page, and the rounded number will be returned from future calls - to malloc_max_allowed_footprint(). If the new max_allowed_footprint - is larger than the current footprint, the heap will never grow - larger than max_allowed_footprint. If the new max_allowed_footprint - is smaller than the current footprint, the heap will not grow - further. - - TODO: try to force the heap to give up memory in the shrink case, - and update this comment once that happens. -*/ -void dlmalloc_set_max_allowed_footprint(size_t bytes); -#endif /* USE_MAX_ALLOWED_FOOTPRINT */ - -/* - malloc_max_footprint(); - Returns the maximum number of bytes obtained from the system. This - value will be greater than current footprint if deallocated space - has been reclaimed by the system. The peak number of bytes allocated - by malloc, realloc etc., is less than this value. Unlike mallinfo, - this function returns only a precomputed result, so can be called - frequently to monitor memory consumption. Even if locks are - otherwise defined, this function does not use them, so results might - not be up to date. -*/ -size_t dlmalloc_max_footprint(void); - -#if !NO_MALLINFO -/* - mallinfo() - Returns (by copy) a struct containing various summary statistics: - - arena: current total non-mmapped bytes allocated from system - ordblks: the number of free chunks - smblks: always zero. - hblks: current number of mmapped regions - hblkhd: total bytes held in mmapped regions - usmblks: the maximum total allocated space. This will be greater - than current total if trimming has occurred. - fsmblks: always zero - uordblks: current total allocated space (normal or mmapped) - fordblks: total free space - keepcost: the maximum number of bytes that could ideally be released - back to system via malloc_trim. ("ideally" means that - it ignores page restrictions etc.) - - Because these fields are ints, but internal bookkeeping may - be kept as longs, the reported values may wrap around zero and - thus be inaccurate. -*/ -struct mallinfo dlmallinfo(void); -#endif /* NO_MALLINFO */ - -/* - independent_calloc(size_t n_elements, size_t element_size, void* chunks[]); - - independent_calloc is similar to calloc, but instead of returning a - single cleared space, it returns an array of pointers to n_elements - independent elements that can hold contents of size elem_size, each - of which starts out cleared, and can be independently freed, - realloc'ed etc. The elements are guaranteed to be adjacently - allocated (this is not guaranteed to occur with multiple callocs or - mallocs), which may also improve cache locality in some - applications. - - The "chunks" argument is optional (i.e., may be null, which is - probably the most typical usage). If it is null, the returned array - is itself dynamically allocated and should also be freed when it is - no longer needed. Otherwise, the chunks array must be of at least - n_elements in length. It is filled in with the pointers to the - chunks. - - In either case, independent_calloc returns this pointer array, or - null if the allocation failed. If n_elements is zero and "chunks" - is null, it returns a chunk representing an array with zero elements - (which should be freed if not wanted). - - Each element must be individually freed when it is no longer - needed. If you'd like to instead be able to free all at once, you - should instead use regular calloc and assign pointers into this - space to represent elements. (In this case though, you cannot - independently free elements.) - - independent_calloc simplifies and speeds up implementations of many - kinds of pools. It may also be useful when constructing large data - structures that initially have a fixed number of fixed-sized nodes, - but the number is not known at compile time, and some of the nodes - may later need to be freed. For example: - - struct Node { int item; struct Node* next; }; - - struct Node* build_list() { - struct Node** pool; - int n = read_number_of_nodes_needed(); - if (n <= 0) return 0; - pool = (struct Node**)(independent_calloc(n, sizeof(struct Node), 0); - if (pool == 0) die(); - // organize into a linked list... - struct Node* first = pool[0]; - for (i = 0; i < n-1; ++i) - pool[i]->next = pool[i+1]; - free(pool); // Can now free the array (or not, if it is needed later) - return first; - } -*/ -void** dlindependent_calloc(size_t, size_t, void**); - -/* - independent_comalloc(size_t n_elements, size_t sizes[], void* chunks[]); - - independent_comalloc allocates, all at once, a set of n_elements - chunks with sizes indicated in the "sizes" array. It returns - an array of pointers to these elements, each of which can be - independently freed, realloc'ed etc. The elements are guaranteed to - be adjacently allocated (this is not guaranteed to occur with - multiple callocs or mallocs), which may also improve cache locality - in some applications. - - The "chunks" argument is optional (i.e., may be null). If it is null - the returned array is itself dynamically allocated and should also - be freed when it is no longer needed. Otherwise, the chunks array - must be of at least n_elements in length. It is filled in with the - pointers to the chunks. - - In either case, independent_comalloc returns this pointer array, or - null if the allocation failed. If n_elements is zero and chunks is - null, it returns a chunk representing an array with zero elements - (which should be freed if not wanted). - - Each element must be individually freed when it is no longer - needed. If you'd like to instead be able to free all at once, you - should instead use a single regular malloc, and assign pointers at - particular offsets in the aggregate space. (In this case though, you - cannot independently free elements.) - - independent_comallac differs from independent_calloc in that each - element may have a different size, and also that it does not - automatically clear elements. - - independent_comalloc can be used to speed up allocation in cases - where several structs or objects must always be allocated at the - same time. For example: - - struct Head { ... } - struct Foot { ... } - - void send_message(char* msg) { - int msglen = strlen(msg); - size_t sizes[3] = { sizeof(struct Head), msglen, sizeof(struct Foot) }; - void* chunks[3]; - if (independent_comalloc(3, sizes, chunks) == 0) - die(); - struct Head* head = (struct Head*)(chunks[0]); - char* body = (char*)(chunks[1]); - struct Foot* foot = (struct Foot*)(chunks[2]); - // ... - } - - In general though, independent_comalloc is worth using only for - larger values of n_elements. For small values, you probably won't - detect enough difference from series of malloc calls to bother. - - Overuse of independent_comalloc can increase overall memory usage, - since it cannot reuse existing noncontiguous small chunks that - might be available for some of the elements. -*/ -void** dlindependent_comalloc(size_t, size_t*, void**); - - -/* - pvalloc(size_t n); - Equivalent to valloc(minimum-page-that-holds(n)), that is, - round up n to nearest pagesize. - */ -void* dlpvalloc(size_t); - -/* - malloc_trim(size_t pad); - - If possible, gives memory back to the system (via negative arguments - to sbrk) if there is unused memory at the `high' end of the malloc - pool or in unused MMAP segments. You can call this after freeing - large blocks of memory to potentially reduce the system-level memory - requirements of a program. However, it cannot guarantee to reduce - memory. Under some allocation patterns, some large free blocks of - memory will be locked between two used chunks, so they cannot be - given back to the system. - - The `pad' argument to malloc_trim represents the amount of free - trailing space to leave untrimmed. If this argument is zero, only - the minimum amount of memory to maintain internal data structures - will be left. Non-zero arguments can be supplied to maintain enough - trailing space to service future expected allocations without having - to re-obtain memory from the system. - - Malloc_trim returns 1 if it actually released any memory, else 0. -*/ -int dlmalloc_trim(size_t); - -/* - malloc_walk_free_pages(handler, harg) - - Calls the provided handler on each free region in the heap. The - memory between start and end are guaranteed not to contain any - important data, so the handler is free to alter the contents - in any way. This can be used to advise the OS that large free - regions may be swapped out. - - The value in harg will be passed to each call of the handler. - */ -void dlmalloc_walk_free_pages(void(*)(void*, void*, void*), void*); - -/* - malloc_walk_heap(handler, harg) - - Calls the provided handler on each object or free region in the - heap. The handler will receive the chunk pointer and length, the - object pointer and length, and the value in harg on each call. - */ -void dlmalloc_walk_heap(void(*)(const void*, size_t, - const void*, size_t, void*), - void*); - -/* - malloc_usable_size(void* p); - - Returns the number of bytes you can actually use in - an allocated chunk, which may be more than you requested (although - often not) due to alignment and minimum size constraints. - You can use this many bytes without worrying about - overwriting other allocated objects. This is not a particularly great - programming practice. malloc_usable_size can be more useful in - debugging and assertions, for example: - - p = malloc(n); - assert(malloc_usable_size(p) >= 256); -*/ -size_t dlmalloc_usable_size(void*); - -/* - malloc_stats(); - Prints on stderr the amount of space obtained from the system (both - via sbrk and mmap), the maximum amount (which may be more than - current if malloc_trim and/or munmap got called), and the current - number of bytes allocated via malloc (or realloc, etc) but not yet - freed. Note that this is the number of bytes allocated, not the - number requested. It will be larger than the number requested - because of alignment and bookkeeping overhead. Because it includes - alignment wastage as being in use, this figure may be greater than - zero even when no user-level chunks are allocated. - - The reported current and maximum system memory can be inaccurate if - a program makes other calls to system memory allocation functions - (normally sbrk) outside of malloc. - - malloc_stats prints only the most commonly interesting statistics. - More information can be obtained by calling mallinfo. -*/ -void dlmalloc_stats(void); - -#endif /* ONLY_MSPACES */ - -#if MSPACES - -/* - mspace is an opaque type representing an independent - region of space that supports mspace_malloc, etc. -*/ -typedef void* mspace; - -/* - create_mspace creates and returns a new independent space with the - given initial capacity, or, if 0, the default granularity size. It - returns null if there is no system memory available to create the - space. If argument locked is non-zero, the space uses a separate - lock to control access. The capacity of the space will grow - dynamically as needed to service mspace_malloc requests. You can - control the sizes of incremental increases of this space by - compiling with a different DEFAULT_GRANULARITY or dynamically - setting with mallopt(M_GRANULARITY, value). -*/ -mspace create_mspace(size_t capacity, int locked); - -/* - destroy_mspace destroys the given space, and attempts to return all - of its memory back to the system, returning the total number of - bytes freed. After destruction, the results of access to all memory - used by the space become undefined. -*/ -size_t destroy_mspace(mspace msp); - -/* - create_mspace_with_base uses the memory supplied as the initial base - of a new mspace. Part (less than 128*sizeof(size_t) bytes) of this - space is used for bookkeeping, so the capacity must be at least this - large. (Otherwise 0 is returned.) When this initial space is - exhausted, additional memory will be obtained from the system. - Destroying this space will deallocate all additionally allocated - space (if possible) but not the initial base. -*/ -mspace create_mspace_with_base(void* base, size_t capacity, int locked); - -/* - mspace_malloc behaves as malloc, but operates within - the given space. -*/ -void* mspace_malloc(mspace msp, size_t bytes); - -/* - mspace_free behaves as free, but operates within - the given space. - - If compiled with FOOTERS==1, mspace_free is not actually needed. - free may be called instead of mspace_free because freed chunks from - any space are handled by their originating spaces. -*/ -void mspace_free(mspace msp, void* mem); - -/* - mspace_realloc behaves as realloc, but operates within - the given space. - - If compiled with FOOTERS==1, mspace_realloc is not actually - needed. realloc may be called instead of mspace_realloc because - realloced chunks from any space are handled by their originating - spaces. -*/ -void* mspace_realloc(mspace msp, void* mem, size_t newsize); - -#if ANDROID /* Added for Android, not part of dlmalloc as released */ -/* - mspace_merge_objects will merge allocated memory mema and memb - together, provided memb immediately follows mema. It is roughly as - if memb has been freed and mema has been realloced to a larger size. - On successfully merging, mema will be returned. If either argument - is null or memb does not immediately follow mema, null will be - returned. - - Both mema and memb should have been previously allocated using - malloc or a related routine such as realloc. If either mema or memb - was not malloced or was previously freed, the result is undefined, - but like mspace_free, the default is to abort the program. -*/ -void* mspace_merge_objects(mspace msp, void* mema, void* memb); -#endif - -/* - mspace_calloc behaves as calloc, but operates within - the given space. -*/ -void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size); - -/* - mspace_memalign behaves as memalign, but operates within - the given space. -*/ -void* mspace_memalign(mspace msp, size_t alignment, size_t bytes); - -/* - mspace_independent_calloc behaves as independent_calloc, but - operates within the given space. -*/ -void** mspace_independent_calloc(mspace msp, size_t n_elements, - size_t elem_size, void* chunks[]); - -/* - mspace_independent_comalloc behaves as independent_comalloc, but - operates within the given space. -*/ -void** mspace_independent_comalloc(mspace msp, size_t n_elements, - size_t sizes[], void* chunks[]); - -/* - mspace_footprint() returns the number of bytes obtained from the - system for this space. -*/ -size_t mspace_footprint(mspace msp); - -/* - mspace_max_footprint() returns the peak number of bytes obtained from the - system for this space. -*/ -size_t mspace_max_footprint(mspace msp); - - -#if !NO_MALLINFO -/* - mspace_mallinfo behaves as mallinfo, but reports properties of - the given space. -*/ -struct mallinfo mspace_mallinfo(mspace msp); -#endif /* NO_MALLINFO */ - -/* - mspace_malloc_stats behaves as malloc_stats, but reports - properties of the given space. -*/ -void mspace_malloc_stats(mspace msp); - -/* - mspace_trim behaves as malloc_trim, but - operates within the given space. -*/ -int mspace_trim(mspace msp, size_t pad); - -/* - An alias for mallopt. -*/ -int mspace_mallopt(int, int); - -#endif /* MSPACES */ - -#ifdef __cplusplus -}; /* end of extern "C" */ -#endif /* __cplusplus */ - -/* - ======================================================================== - To make a fully customizable malloc.h header file, cut everything - above this line, put into file malloc.h, edit to suit, and #include it - on the next line, as well as in programs that use this malloc. - ======================================================================== -*/ - -/* #include "malloc.h" */ - -/*------------------------------ internal #includes ---------------------- */ - -#ifdef WIN32 -#pragma warning( disable : 4146 ) /* no "unsigned" warnings */ -#endif /* WIN32 */ - -#include <stdio.h> /* for printing in malloc_stats */ - -#ifndef LACKS_ERRNO_H -#include <errno.h> /* for MALLOC_FAILURE_ACTION */ -#endif /* LACKS_ERRNO_H */ -#if FOOTERS -#include <time.h> /* for magic initialization */ -#endif /* FOOTERS */ -#ifndef LACKS_STDLIB_H -#include <stdlib.h> /* for abort() */ -#endif /* LACKS_STDLIB_H */ -#ifdef DEBUG -#if ABORT_ON_ASSERT_FAILURE -#define assert(x) if(!(x)) ABORT -#else /* ABORT_ON_ASSERT_FAILURE */ -#include <assert.h> -#endif /* ABORT_ON_ASSERT_FAILURE */ -#else /* DEBUG */ -#define assert(x) -#endif /* DEBUG */ -#ifndef LACKS_STRING_H -#include <string.h> /* for memset etc */ -#endif /* LACKS_STRING_H */ -#if USE_BUILTIN_FFS -#ifndef LACKS_STRINGS_H -#include <strings.h> /* for ffs */ -#endif /* LACKS_STRINGS_H */ -#endif /* USE_BUILTIN_FFS */ -#if HAVE_MMAP -#ifndef LACKS_SYS_MMAN_H -#include <sys/mman.h> /* for mmap */ -#endif /* LACKS_SYS_MMAN_H */ -#ifndef LACKS_FCNTL_H -#include <fcntl.h> -#endif /* LACKS_FCNTL_H */ -#endif /* HAVE_MMAP */ -#if HAVE_MORECORE -#ifndef LACKS_UNISTD_H -#include <unistd.h> /* for sbrk */ -#else /* LACKS_UNISTD_H */ -#if !defined(__FreeBSD__) && !defined(__OpenBSD__) && !defined(__NetBSD__) -extern void* sbrk(ptrdiff_t); -#endif /* FreeBSD etc */ -#endif /* LACKS_UNISTD_H */ -#endif /* HAVE_MMAP */ - -#ifndef WIN32 -#ifndef malloc_getpagesize -# ifdef _SC_PAGESIZE /* some SVR4 systems omit an underscore */ -# ifndef _SC_PAGE_SIZE -# define _SC_PAGE_SIZE _SC_PAGESIZE -# endif -# endif -# ifdef _SC_PAGE_SIZE -# define malloc_getpagesize sysconf(_SC_PAGE_SIZE) -# else -# if defined(BSD) || defined(DGUX) || defined(HAVE_GETPAGESIZE) - extern size_t getpagesize(); -# define malloc_getpagesize getpagesize() -# else -# ifdef WIN32 /* use supplied emulation of getpagesize */ -# define malloc_getpagesize getpagesize() -# else -# ifndef LACKS_SYS_PARAM_H -# include <sys/param.h> -# endif -# ifdef EXEC_PAGESIZE -# define malloc_getpagesize EXEC_PAGESIZE -# else -# ifdef NBPG -# ifndef CLSIZE -# define malloc_getpagesize NBPG -# else -# define malloc_getpagesize (NBPG * CLSIZE) -# endif -# else -# ifdef NBPC -# define malloc_getpagesize NBPC -# else -# ifdef PAGESIZE -# define malloc_getpagesize PAGESIZE -# else /* just guess */ -# define malloc_getpagesize ((size_t)4096U) -# endif -# endif -# endif -# endif -# endif -# endif -# endif -#endif -#endif - -/* ------------------- size_t and alignment properties -------------------- */ - -/* The byte and bit size of a size_t */ -#define SIZE_T_SIZE (sizeof(size_t)) -#define SIZE_T_BITSIZE (sizeof(size_t) << 3) - -/* Some constants coerced to size_t */ -/* Annoying but necessary to avoid errors on some plaftorms */ -#define SIZE_T_ZERO ((size_t)0) -#define SIZE_T_ONE ((size_t)1) -#define SIZE_T_TWO ((size_t)2) -#define TWO_SIZE_T_SIZES (SIZE_T_SIZE<<1) -#define FOUR_SIZE_T_SIZES (SIZE_T_SIZE<<2) -#define SIX_SIZE_T_SIZES (FOUR_SIZE_T_SIZES+TWO_SIZE_T_SIZES) -#define HALF_MAX_SIZE_T (MAX_SIZE_T / 2U) - -/* The bit mask value corresponding to MALLOC_ALIGNMENT */ -#define CHUNK_ALIGN_MASK (MALLOC_ALIGNMENT - SIZE_T_ONE) - -/* True if address a has acceptable alignment */ -#define is_aligned(A) (((size_t)((A)) & (CHUNK_ALIGN_MASK)) == 0) - -/* the number of bytes to offset an address to align it */ -#define align_offset(A)\ - ((((size_t)(A) & CHUNK_ALIGN_MASK) == 0)? 0 :\ - ((MALLOC_ALIGNMENT - ((size_t)(A) & CHUNK_ALIGN_MASK)) & CHUNK_ALIGN_MASK)) - -/* -------------------------- MMAP preliminaries ------------------------- */ - -/* - If HAVE_MORECORE or HAVE_MMAP are false, we just define calls and - checks to fail so compiler optimizer can delete code rather than - using so many "#if"s. -*/ - - -/* MORECORE and MMAP must return MFAIL on failure */ -#define MFAIL ((void*)(MAX_SIZE_T)) -#define CMFAIL ((char*)(MFAIL)) /* defined for convenience */ - -#if !HAVE_MMAP -#define IS_MMAPPED_BIT (SIZE_T_ZERO) -#define USE_MMAP_BIT (SIZE_T_ZERO) -#define CALL_MMAP(s) MFAIL -#define CALL_MUNMAP(a, s) (-1) -#define DIRECT_MMAP(s) MFAIL - -#else /* HAVE_MMAP */ -#define IS_MMAPPED_BIT (SIZE_T_ONE) -#define USE_MMAP_BIT (SIZE_T_ONE) - -#ifndef WIN32 -#define CALL_MUNMAP(a, s) munmap((a), (s)) -#define MMAP_PROT (PROT_READ|PROT_WRITE) -#if !defined(MAP_ANONYMOUS) && defined(MAP_ANON) -#define MAP_ANONYMOUS MAP_ANON -#endif /* MAP_ANON */ -#ifdef MAP_ANONYMOUS -#define MMAP_FLAGS (MAP_PRIVATE|MAP_ANONYMOUS) -#define CALL_MMAP(s) mmap(0, (s), MMAP_PROT, MMAP_FLAGS, -1, 0) -#else /* MAP_ANONYMOUS */ -/* - Nearly all versions of mmap support MAP_ANONYMOUS, so the following - is unlikely to be needed, but is supplied just in case. -*/ -#define MMAP_FLAGS (MAP_PRIVATE) -static int dev_zero_fd = -1; /* Cached file descriptor for /dev/zero. */ -#define CALL_MMAP(s) ((dev_zero_fd < 0) ? \ - (dev_zero_fd = open("/dev/zero", O_RDWR), \ - mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0)) : \ - mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0)) -#endif /* MAP_ANONYMOUS */ - -#define DIRECT_MMAP(s) CALL_MMAP(s) -#else /* WIN32 */ - -/* Win32 MMAP via VirtualAlloc */ -static void* win32mmap(size_t size) { - void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT, PAGE_READWRITE); - return (ptr != 0)? ptr: MFAIL; -} - -/* For direct MMAP, use MEM_TOP_DOWN to minimize interference */ -static void* win32direct_mmap(size_t size) { - void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT|MEM_TOP_DOWN, - PAGE_READWRITE); - return (ptr != 0)? ptr: MFAIL; -} - -/* This function supports releasing coalesed segments */ -static int win32munmap(void* ptr, size_t size) { - MEMORY_BASIC_INFORMATION minfo; - char* cptr = ptr; - while (size) { - if (VirtualQuery(cptr, &minfo, sizeof(minfo)) == 0) - return -1; - if (minfo.BaseAddress != cptr || minfo.AllocationBase != cptr || - minfo.State != MEM_COMMIT || minfo.RegionSize > size) - return -1; - if (VirtualFree(cptr, 0, MEM_RELEASE) == 0) - return -1; - cptr += minfo.RegionSize; - size -= minfo.RegionSize; - } - return 0; -} - -#define CALL_MMAP(s) win32mmap(s) -#define CALL_MUNMAP(a, s) win32munmap((a), (s)) -#define DIRECT_MMAP(s) win32direct_mmap(s) -#endif /* WIN32 */ -#endif /* HAVE_MMAP */ - -#if HAVE_MMAP && HAVE_MREMAP -#define CALL_MREMAP(addr, osz, nsz, mv) mremap((addr), (osz), (nsz), (mv)) -#else /* HAVE_MMAP && HAVE_MREMAP */ -#define CALL_MREMAP(addr, osz, nsz, mv) MFAIL -#endif /* HAVE_MMAP && HAVE_MREMAP */ - -#if HAVE_MORECORE -#define CALL_MORECORE(S) MORECORE(S) -#else /* HAVE_MORECORE */ -#define CALL_MORECORE(S) MFAIL -#endif /* HAVE_MORECORE */ - -/* mstate bit set if continguous morecore disabled or failed */ -#define USE_NONCONTIGUOUS_BIT (4U) - -/* segment bit set in create_mspace_with_base */ -#define EXTERN_BIT (8U) - - -/* --------------------------- Lock preliminaries ------------------------ */ - -#if USE_LOCKS - -/* - When locks are defined, there are up to two global locks: - - * If HAVE_MORECORE, morecore_mutex protects sequences of calls to - MORECORE. In many cases sys_alloc requires two calls, that should - not be interleaved with calls by other threads. This does not - protect against direct calls to MORECORE by other threads not - using this lock, so there is still code to cope the best we can on - interference. - - * magic_init_mutex ensures that mparams.magic and other - unique mparams values are initialized only once. -*/ - -#ifndef WIN32 -/* By default use posix locks */ -#include <pthread.h> -#define MLOCK_T pthread_mutex_t -#define INITIAL_LOCK(l) pthread_mutex_init(l, NULL) -#define ACQUIRE_LOCK(l) pthread_mutex_lock(l) -#define RELEASE_LOCK(l) pthread_mutex_unlock(l) - -#if HAVE_MORECORE -static MLOCK_T morecore_mutex = PTHREAD_MUTEX_INITIALIZER; -#endif /* HAVE_MORECORE */ - -static MLOCK_T magic_init_mutex = PTHREAD_MUTEX_INITIALIZER; - -#else /* WIN32 */ -/* - Because lock-protected regions have bounded times, and there - are no recursive lock calls, we can use simple spinlocks. -*/ - -#define MLOCK_T long -static int win32_acquire_lock (MLOCK_T *sl) { - for (;;) { -#ifdef InterlockedCompareExchangePointer - if (!InterlockedCompareExchange(sl, 1, 0)) - return 0; -#else /* Use older void* version */ - if (!InterlockedCompareExchange((void**)sl, (void*)1, (void*)0)) - return 0; -#endif /* InterlockedCompareExchangePointer */ - Sleep (0); - } -} - -static void win32_release_lock (MLOCK_T *sl) { - InterlockedExchange (sl, 0); -} - -#define INITIAL_LOCK(l) *(l)=0 -#define ACQUIRE_LOCK(l) win32_acquire_lock(l) -#define RELEASE_LOCK(l) win32_release_lock(l) -#if HAVE_MORECORE -static MLOCK_T morecore_mutex; -#endif /* HAVE_MORECORE */ -static MLOCK_T magic_init_mutex; -#endif /* WIN32 */ - -#define USE_LOCK_BIT (2U) -#else /* USE_LOCKS */ -#define USE_LOCK_BIT (0U) -#define INITIAL_LOCK(l) -#endif /* USE_LOCKS */ - -#if USE_LOCKS && HAVE_MORECORE -#define ACQUIRE_MORECORE_LOCK() ACQUIRE_LOCK(&morecore_mutex); -#define RELEASE_MORECORE_LOCK() RELEASE_LOCK(&morecore_mutex); -#else /* USE_LOCKS && HAVE_MORECORE */ -#define ACQUIRE_MORECORE_LOCK() -#define RELEASE_MORECORE_LOCK() -#endif /* USE_LOCKS && HAVE_MORECORE */ - -#if USE_LOCKS -#define ACQUIRE_MAGIC_INIT_LOCK() ACQUIRE_LOCK(&magic_init_mutex); -#define RELEASE_MAGIC_INIT_LOCK() RELEASE_LOCK(&magic_init_mutex); -#else /* USE_LOCKS */ -#define ACQUIRE_MAGIC_INIT_LOCK() -#define RELEASE_MAGIC_INIT_LOCK() -#endif /* USE_LOCKS */ - - -/* ----------------------- Chunk representations ------------------------ */ - -/* - (The following includes lightly edited explanations by Colin Plumb.) - - The malloc_chunk declaration below is misleading (but accurate and - necessary). It declares a "view" into memory allowing access to - necessary fields at known offsets from a given base. - - Chunks of memory are maintained using a `boundary tag' method as - originally described by Knuth. (See the paper by Paul Wilson - ftp://ftp.cs.utexas.edu/pub/garbage/allocsrv.ps for a survey of such - techniques.) Sizes of free chunks are stored both in the front of - each chunk and at the end. This makes consolidating fragmented - chunks into bigger chunks fast. The head fields also hold bits - representing whether chunks are free or in use. - - Here are some pictures to make it clearer. They are "exploded" to - show that the state of a chunk can be thought of as extending from - the high 31 bits of the head field of its header through the - prev_foot and PINUSE_BIT bit of the following chunk header. - - A chunk that's in use looks like: - - chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Size of previous chunk (if P = 1) | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P| - | Size of this chunk 1| +-+ - mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | | - +- -+ - | | - +- -+ - | : - +- size - sizeof(size_t) available payload bytes -+ - : | - chunk-> +- -+ - | | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |1| - | Size of next chunk (may or may not be in use) | +-+ - mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - - And if it's free, it looks like this: - - chunk-> +- -+ - | User payload (must be in use, or we would have merged!) | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P| - | Size of this chunk 0| +-+ - mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Next pointer | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Prev pointer | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | : - +- size - sizeof(struct chunk) unused bytes -+ - : | - chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Size of this chunk | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |0| - | Size of next chunk (must be in use, or we would have merged)| +-+ - mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | : - +- User payload -+ - : | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - |0| - +-+ - Note that since we always merge adjacent free chunks, the chunks - adjacent to a free chunk must be in use. - - Given a pointer to a chunk (which can be derived trivially from the - payload pointer) we can, in O(1) time, find out whether the adjacent - chunks are free, and if so, unlink them from the lists that they - are on and merge them with the current chunk. - - Chunks always begin on even word boundaries, so the mem portion - (which is returned to the user) is also on an even word boundary, and - thus at least double-word aligned. - - The P (PINUSE_BIT) bit, stored in the unused low-order bit of the - chunk size (which is always a multiple of two words), is an in-use - bit for the *previous* chunk. If that bit is *clear*, then the - word before the current chunk size contains the previous chunk - size, and can be used to find the front of the previous chunk. - The very first chunk allocated always has this bit set, preventing - access to non-existent (or non-owned) memory. If pinuse is set for - any given chunk, then you CANNOT determine the size of the - previous chunk, and might even get a memory addressing fault when - trying to do so. - - The C (CINUSE_BIT) bit, stored in the unused second-lowest bit of - the chunk size redundantly records whether the current chunk is - inuse. This redundancy enables usage checks within free and realloc, - and reduces indirection when freeing and consolidating chunks. - - Each freshly allocated chunk must have both cinuse and pinuse set. - That is, each allocated chunk borders either a previously allocated - and still in-use chunk, or the base of its memory arena. This is - ensured by making all allocations from the the `lowest' part of any - found chunk. Further, no free chunk physically borders another one, - so each free chunk is known to be preceded and followed by either - inuse chunks or the ends of memory. - - Note that the `foot' of the current chunk is actually represented - as the prev_foot of the NEXT chunk. This makes it easier to - deal with alignments etc but can be very confusing when trying - to extend or adapt this code. - - The exceptions to all this are - - 1. The special chunk `top' is the top-most available chunk (i.e., - the one bordering the end of available memory). It is treated - specially. Top is never included in any bin, is used only if - no other chunk is available, and is released back to the - system if it is very large (see M_TRIM_THRESHOLD). In effect, - the top chunk is treated as larger (and thus less well - fitting) than any other available chunk. The top chunk - doesn't update its trailing size field since there is no next - contiguous chunk that would have to index off it. However, - space is still allocated for it (TOP_FOOT_SIZE) to enable - separation or merging when space is extended. - - 3. Chunks allocated via mmap, which have the lowest-order bit - (IS_MMAPPED_BIT) set in their prev_foot fields, and do not set - PINUSE_BIT in their head fields. Because they are allocated - one-by-one, each must carry its own prev_foot field, which is - also used to hold the offset this chunk has within its mmapped - region, which is needed to preserve alignment. Each mmapped - chunk is trailed by the first two fields of a fake next-chunk - for sake of usage checks. - -*/ - -struct malloc_chunk { - size_t prev_foot; /* Size of previous chunk (if free). */ - size_t head; /* Size and inuse bits. */ - struct malloc_chunk* fd; /* double links -- used only if free. */ - struct malloc_chunk* bk; -}; - -typedef struct malloc_chunk mchunk; -typedef struct malloc_chunk* mchunkptr; -typedef struct malloc_chunk* sbinptr; /* The type of bins of chunks */ -typedef unsigned int bindex_t; /* Described below */ -typedef unsigned int binmap_t; /* Described below */ -typedef unsigned int flag_t; /* The type of various bit flag sets */ - -/* ------------------- Chunks sizes and alignments ----------------------- */ - -#define MCHUNK_SIZE (sizeof(mchunk)) - -#if FOOTERS -#define CHUNK_OVERHEAD (TWO_SIZE_T_SIZES) -#else /* FOOTERS */ -#define CHUNK_OVERHEAD (SIZE_T_SIZE) -#endif /* FOOTERS */ - -/* MMapped chunks need a second word of overhead ... */ -#define MMAP_CHUNK_OVERHEAD (TWO_SIZE_T_SIZES) -/* ... and additional padding for fake next-chunk at foot */ -#define MMAP_FOOT_PAD (FOUR_SIZE_T_SIZES) - -/* The smallest size we can malloc is an aligned minimal chunk */ -#define MIN_CHUNK_SIZE\ - ((MCHUNK_SIZE + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK) - -/* conversion from malloc headers to user pointers, and back */ -#define chunk2mem(p) ((void*)((char*)(p) + TWO_SIZE_T_SIZES)) -#define mem2chunk(mem) ((mchunkptr)((char*)(mem) - TWO_SIZE_T_SIZES)) -/* chunk associated with aligned address A */ -#define align_as_chunk(A) (mchunkptr)((A) + align_offset(chunk2mem(A))) - -/* Bounds on request (not chunk) sizes. */ -#define MAX_REQUEST ((-MIN_CHUNK_SIZE) << 2) -#define MIN_REQUEST (MIN_CHUNK_SIZE - CHUNK_OVERHEAD - SIZE_T_ONE) - -/* pad request bytes into a usable size */ -#define pad_request(req) \ - (((req) + CHUNK_OVERHEAD + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK) - -/* pad request, checking for minimum (but not maximum) */ -#define request2size(req) \ - (((req) < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(req)) - - -/* ------------------ Operations on head and foot fields ----------------- */ - -/* - The head field of a chunk is or'ed with PINUSE_BIT when previous - adjacent chunk in use, and or'ed with CINUSE_BIT if this chunk is in - use. If the chunk was obtained with mmap, the prev_foot field has - IS_MMAPPED_BIT set, otherwise holding the offset of the base of the - mmapped region to the base of the chunk. -*/ - -#define PINUSE_BIT (SIZE_T_ONE) -#define CINUSE_BIT (SIZE_T_TWO) -#define INUSE_BITS (PINUSE_BIT|CINUSE_BIT) - -/* Head value for fenceposts */ -#define FENCEPOST_HEAD (INUSE_BITS|SIZE_T_SIZE) - -/* extraction of fields from head words */ -#define cinuse(p) ((p)->head & CINUSE_BIT) -#define pinuse(p) ((p)->head & PINUSE_BIT) -#define chunksize(p) ((p)->head & ~(INUSE_BITS)) - -#define clear_pinuse(p) ((p)->head &= ~PINUSE_BIT) -#define clear_cinuse(p) ((p)->head &= ~CINUSE_BIT) - -/* Treat space at ptr +/- offset as a chunk */ -#define chunk_plus_offset(p, s) ((mchunkptr)(((char*)(p)) + (s))) -#define chunk_minus_offset(p, s) ((mchunkptr)(((char*)(p)) - (s))) - -/* Ptr to next or previous physical malloc_chunk. */ -#define next_chunk(p) ((mchunkptr)( ((char*)(p)) + ((p)->head & ~INUSE_BITS))) -#define prev_chunk(p) ((mchunkptr)( ((char*)(p)) - ((p)->prev_foot) )) - -/* extract next chunk's pinuse bit */ -#define next_pinuse(p) ((next_chunk(p)->head) & PINUSE_BIT) - -/* Get/set size at footer */ -#define get_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot) -#define set_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot = (s)) - -/* Set size, pinuse bit, and foot */ -#define set_size_and_pinuse_of_free_chunk(p, s)\ - ((p)->head = (s|PINUSE_BIT), set_foot(p, s)) - -/* Set size, pinuse bit, foot, and clear next pinuse */ -#define set_free_with_pinuse(p, s, n)\ - (clear_pinuse(n), set_size_and_pinuse_of_free_chunk(p, s)) - -#define is_mmapped(p)\ - (!((p)->head & PINUSE_BIT) && ((p)->prev_foot & IS_MMAPPED_BIT)) - -/* Get the internal overhead associated with chunk p */ -#define overhead_for(p)\ - (is_mmapped(p)? MMAP_CHUNK_OVERHEAD : CHUNK_OVERHEAD) - -/* Return true if malloced space is not necessarily cleared */ -#if MMAP_CLEARS -#define calloc_must_clear(p) (!is_mmapped(p)) -#else /* MMAP_CLEARS */ -#define calloc_must_clear(p) (1) -#endif /* MMAP_CLEARS */ - -/* ---------------------- Overlaid data structures ----------------------- */ - -/* - When chunks are not in use, they are treated as nodes of either - lists or trees. - - "Small" chunks are stored in circular doubly-linked lists, and look - like this: - - chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Size of previous chunk | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - `head:' | Size of chunk, in bytes |P| - mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Forward pointer to next chunk in list | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Back pointer to previous chunk in list | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Unused space (may be 0 bytes long) . - . . - . | -nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - `foot:' | Size of chunk, in bytes | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - - Larger chunks are kept in a form of bitwise digital trees (aka - tries) keyed on chunksizes. Because malloc_tree_chunks are only for - free chunks greater than 256 bytes, their size doesn't impose any - constraints on user chunk sizes. Each node looks like: - - chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Size of previous chunk | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - `head:' | Size of chunk, in bytes |P| - mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Forward pointer to next chunk of same size | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Back pointer to previous chunk of same size | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Pointer to left child (child[0]) | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Pointer to right child (child[1]) | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Pointer to parent | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | bin index of this chunk | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Unused space . - . | -nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - `foot:' | Size of chunk, in bytes | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - - Each tree holding treenodes is a tree of unique chunk sizes. Chunks - of the same size are arranged in a circularly-linked list, with only - the oldest chunk (the next to be used, in our FIFO ordering) - actually in the tree. (Tree members are distinguished by a non-null - parent pointer.) If a chunk with the same size an an existing node - is inserted, it is linked off the existing node using pointers that - work in the same way as fd/bk pointers of small chunks. - - Each tree contains a power of 2 sized range of chunk sizes (the - smallest is 0x100 <= x < 0x180), which is is divided in half at each - tree level, with the chunks in the smaller half of the range (0x100 - <= x < 0x140 for the top nose) in the left subtree and the larger - half (0x140 <= x < 0x180) in the right subtree. This is, of course, - done by inspecting individual bits. - - Using these rules, each node's left subtree contains all smaller - sizes than its right subtree. However, the node at the root of each - subtree has no particular ordering relationship to either. (The - dividing line between the subtree sizes is based on trie relation.) - If we remove the last chunk of a given size from the interior of the - tree, we need to replace it with a leaf node. The tree ordering - rules permit a node to be replaced by any leaf below it. - - The smallest chunk in a tree (a common operation in a best-fit - allocator) can be found by walking a path to the leftmost leaf in - the tree. Unlike a usual binary tree, where we follow left child - pointers until we reach a null, here we follow the right child - pointer any time the left one is null, until we reach a leaf with - both child pointers null. The smallest chunk in the tree will be - somewhere along that path. - - The worst case number of steps to add, find, or remove a node is - bounded by the number of bits differentiating chunks within - bins. Under current bin calculations, this ranges from 6 up to 21 - (for 32 bit sizes) or up to 53 (for 64 bit sizes). The typical case - is of course much better. -*/ - -struct malloc_tree_chunk { - /* The first four fields must be compatible with malloc_chunk */ - size_t prev_foot; - size_t head; - struct malloc_tree_chunk* fd; - struct malloc_tree_chunk* bk; - - struct malloc_tree_chunk* child[2]; - struct malloc_tree_chunk* parent; - bindex_t index; -}; - -typedef struct malloc_tree_chunk tchunk; -typedef struct malloc_tree_chunk* tchunkptr; -typedef struct malloc_tree_chunk* tbinptr; /* The type of bins of trees */ - -/* A little helper macro for trees */ -#define leftmost_child(t) ((t)->child[0] != 0? (t)->child[0] : (t)->child[1]) - -/* ----------------------------- Segments -------------------------------- */ - -/* - Each malloc space may include non-contiguous segments, held in a - list headed by an embedded malloc_segment record representing the - top-most space. Segments also include flags holding properties of - the space. Large chunks that are directly allocated by mmap are not - included in this list. They are instead independently created and - destroyed without otherwise keeping track of them. - - Segment management mainly comes into play for spaces allocated by - MMAP. Any call to MMAP might or might not return memory that is - adjacent to an existing segment. MORECORE normally contiguously - extends the current space, so this space is almost always adjacent, - which is simpler and faster to deal with. (This is why MORECORE is - used preferentially to MMAP when both are available -- see - sys_alloc.) When allocating using MMAP, we don't use any of the - hinting mechanisms (inconsistently) supported in various - implementations of unix mmap, or distinguish reserving from - committing memory. Instead, we just ask for space, and exploit - contiguity when we get it. It is probably possible to do - better than this on some systems, but no general scheme seems - to be significantly better. - - Management entails a simpler variant of the consolidation scheme - used for chunks to reduce fragmentation -- new adjacent memory is - normally prepended or appended to an existing segment. However, - there are limitations compared to chunk consolidation that mostly - reflect the fact that segment processing is relatively infrequent - (occurring only when getting memory from system) and that we - don't expect to have huge numbers of segments: - - * Segments are not indexed, so traversal requires linear scans. (It - would be possible to index these, but is not worth the extra - overhead and complexity for most programs on most platforms.) - * New segments are only appended to old ones when holding top-most - memory; if they cannot be prepended to others, they are held in - different segments. - - Except for the top-most segment of an mstate, each segment record - is kept at the tail of its segment. Segments are added by pushing - segment records onto the list headed by &mstate.seg for the - containing mstate. - - Segment flags control allocation/merge/deallocation policies: - * If EXTERN_BIT set, then we did not allocate this segment, - and so should not try to deallocate or merge with others. - (This currently holds only for the initial segment passed - into create_mspace_with_base.) - * If IS_MMAPPED_BIT set, the segment may be merged with - other surrounding mmapped segments and trimmed/de-allocated - using munmap. - * If neither bit is set, then the segment was obtained using - MORECORE so can be merged with surrounding MORECORE'd segments - and deallocated/trimmed using MORECORE with negative arguments. -*/ - -struct malloc_segment { - char* base; /* base address */ - size_t size; /* allocated size */ - struct malloc_segment* next; /* ptr to next segment */ - flag_t sflags; /* mmap and extern flag */ -}; - -#define is_mmapped_segment(S) ((S)->sflags & IS_MMAPPED_BIT) -#define is_extern_segment(S) ((S)->sflags & EXTERN_BIT) - -typedef struct malloc_segment msegment; -typedef struct malloc_segment* msegmentptr; - -/* ---------------------------- malloc_state ----------------------------- */ - -/* - A malloc_state holds all of the bookkeeping for a space. - The main fields are: - - Top - The topmost chunk of the currently active segment. Its size is - cached in topsize. The actual size of topmost space is - topsize+TOP_FOOT_SIZE, which includes space reserved for adding - fenceposts and segment records if necessary when getting more - space from the system. The size at which to autotrim top is - cached from mparams in trim_check, except that it is disabled if - an autotrim fails. - - Designated victim (dv) - This is the preferred chunk for servicing small requests that - don't have exact fits. It is normally the chunk split off most - recently to service another small request. Its size is cached in - dvsize. The link fields of this chunk are not maintained since it - is not kept in a bin. - - SmallBins - An array of bin headers for free chunks. These bins hold chunks - with sizes less than MIN_LARGE_SIZE bytes. Each bin contains - chunks of all the same size, spaced 8 bytes apart. To simplify - use in double-linked lists, each bin header acts as a malloc_chunk - pointing to the real first node, if it exists (else pointing to - itself). This avoids special-casing for headers. But to avoid - waste, we allocate only the fd/bk pointers of bins, and then use - repositioning tricks to treat these as the fields of a chunk. - - TreeBins - Treebins are pointers to the roots of trees holding a range of - sizes. There are 2 equally spaced treebins for each power of two - from TREE_SHIFT to TREE_SHIFT+16. The last bin holds anything - larger. - - Bin maps - There is one bit map for small bins ("smallmap") and one for - treebins ("treemap). Each bin sets its bit when non-empty, and - clears the bit when empty. Bit operations are then used to avoid - bin-by-bin searching -- nearly all "search" is done without ever - looking at bins that won't be selected. The bit maps - conservatively use 32 bits per map word, even if on 64bit system. - For a good description of some of the bit-based techniques used - here, see Henry S. Warren Jr's book "Hacker's Delight" (and - supplement at http://hackersdelight.org/). Many of these are - intended to reduce the branchiness of paths through malloc etc, as - well as to reduce the number of memory locations read or written. - - Segments - A list of segments headed by an embedded malloc_segment record - representing the initial space. - - Address check support - The least_addr field is the least address ever obtained from - MORECORE or MMAP. Attempted frees and reallocs of any address less - than this are trapped (unless INSECURE is defined). - - Magic tag - A cross-check field that should always hold same value as mparams.magic. - - Flags - Bits recording whether to use MMAP, locks, or contiguous MORECORE - - Statistics - Each space keeps track of current and maximum system memory - obtained via MORECORE or MMAP. - - Locking - If USE_LOCKS is defined, the "mutex" lock is acquired and released - around every public call using this mspace. -*/ - -/* Bin types, widths and sizes */ -#define NSMALLBINS (32U) -#define NTREEBINS (32U) -#define SMALLBIN_SHIFT (3U) -#define SMALLBIN_WIDTH (SIZE_T_ONE << SMALLBIN_SHIFT) -#define TREEBIN_SHIFT (8U) -#define MIN_LARGE_SIZE (SIZE_T_ONE << TREEBIN_SHIFT) -#define MAX_SMALL_SIZE (MIN_LARGE_SIZE - SIZE_T_ONE) -#define MAX_SMALL_REQUEST (MAX_SMALL_SIZE - CHUNK_ALIGN_MASK - CHUNK_OVERHEAD) - -struct malloc_state { - binmap_t smallmap; - binmap_t treemap; - size_t dvsize; - size_t topsize; - char* least_addr; - mchunkptr dv; - mchunkptr top; - size_t trim_check; - size_t magic; - mchunkptr smallbins[(NSMALLBINS+1)*2]; - tbinptr treebins[NTREEBINS]; - size_t footprint; -#if USE_MAX_ALLOWED_FOOTPRINT - size_t max_allowed_footprint; -#endif - size_t max_footprint; - flag_t mflags; -#if USE_LOCKS - MLOCK_T mutex; /* locate lock among fields that rarely change */ -#endif /* USE_LOCKS */ - msegment seg; -}; - -typedef struct malloc_state* mstate; - -/* ------------- Global malloc_state and malloc_params ------------------- */ - -/* - malloc_params holds global properties, including those that can be - dynamically set using mallopt. There is a single instance, mparams, - initialized in init_mparams. -*/ - -struct malloc_params { - size_t magic; - size_t page_size; - size_t granularity; - size_t mmap_threshold; - size_t trim_threshold; - flag_t default_mflags; -}; - -static struct malloc_params mparams; - -/* The global malloc_state used for all non-"mspace" calls */ -static struct malloc_state _gm_ -#if USE_MAX_ALLOWED_FOOTPRINT - = { .max_allowed_footprint = MAX_SIZE_T }; -#else - ; -#endif - -#define gm (&_gm_) -#define is_global(M) ((M) == &_gm_) -#define is_initialized(M) ((M)->top != 0) - -/* -------------------------- system alloc setup ------------------------- */ - -/* Operations on mflags */ - -#define use_lock(M) ((M)->mflags & USE_LOCK_BIT) -#define enable_lock(M) ((M)->mflags |= USE_LOCK_BIT) -#define disable_lock(M) ((M)->mflags &= ~USE_LOCK_BIT) - -#define use_mmap(M) ((M)->mflags & USE_MMAP_BIT) -#define enable_mmap(M) ((M)->mflags |= USE_MMAP_BIT) -#define disable_mmap(M) ((M)->mflags &= ~USE_MMAP_BIT) - -#define use_noncontiguous(M) ((M)->mflags & USE_NONCONTIGUOUS_BIT) -#define disable_contiguous(M) ((M)->mflags |= USE_NONCONTIGUOUS_BIT) - -#define set_lock(M,L)\ - ((M)->mflags = (L)?\ - ((M)->mflags | USE_LOCK_BIT) :\ - ((M)->mflags & ~USE_LOCK_BIT)) - -/* page-align a size */ -#define page_align(S)\ - (((S) + (mparams.page_size)) & ~(mparams.page_size - SIZE_T_ONE)) - -/* granularity-align a size */ -#define granularity_align(S)\ - (((S) + (mparams.granularity)) & ~(mparams.granularity - SIZE_T_ONE)) - -#define is_page_aligned(S)\ - (((size_t)(S) & (mparams.page_size - SIZE_T_ONE)) == 0) -#define is_granularity_aligned(S)\ - (((size_t)(S) & (mparams.granularity - SIZE_T_ONE)) == 0) - -/* True if segment S holds address A */ -#define segment_holds(S, A)\ - ((char*)(A) >= S->base && (char*)(A) < S->base + S->size) - -/* Return segment holding given address */ -static msegmentptr segment_holding(mstate m, char* addr) { - msegmentptr sp = &m->seg; - for (;;) { - if (addr >= sp->base && addr < sp->base + sp->size) - return sp; - if ((sp = sp->next) == 0) - return 0; - } -} - -/* Return true if segment contains a segment link */ -static int has_segment_link(mstate m, msegmentptr ss) { - msegmentptr sp = &m->seg; - for (;;) { - if ((char*)sp >= ss->base && (char*)sp < ss->base + ss->size) - return 1; - if ((sp = sp->next) == 0) - return 0; - } -} - -#ifndef MORECORE_CANNOT_TRIM -#define should_trim(M,s) ((s) > (M)->trim_check) -#else /* MORECORE_CANNOT_TRIM */ -#define should_trim(M,s) (0) -#endif /* MORECORE_CANNOT_TRIM */ - -/* - TOP_FOOT_SIZE is padding at the end of a segment, including space - that may be needed to place segment records and fenceposts when new - noncontiguous segments are added. -*/ -#define TOP_FOOT_SIZE\ - (align_offset(chunk2mem(0))+pad_request(sizeof(struct malloc_segment))+MIN_CHUNK_SIZE) - - -/* ------------------------------- Hooks -------------------------------- */ - -/* - PREACTION should be defined to return 0 on success, and nonzero on - failure. If you are not using locking, you can redefine these to do - anything you like. -*/ - -#if USE_LOCKS - -/* Ensure locks are initialized */ -#define GLOBALLY_INITIALIZE() (mparams.page_size == 0 && init_mparams()) - -#define PREACTION(M) ((GLOBALLY_INITIALIZE() || use_lock(M))? ACQUIRE_LOCK(&(M)->mutex) : 0) -#define POSTACTION(M) { if (use_lock(M)) RELEASE_LOCK(&(M)->mutex); } -#else /* USE_LOCKS */ - -#ifndef PREACTION -#define PREACTION(M) (0) -#endif /* PREACTION */ - -#ifndef POSTACTION -#define POSTACTION(M) -#endif /* POSTACTION */ - -#endif /* USE_LOCKS */ - -/* - CORRUPTION_ERROR_ACTION is triggered upon detected bad addresses. - USAGE_ERROR_ACTION is triggered on detected bad frees and - reallocs. The argument p is an address that might have triggered the - fault. It is ignored by the two predefined actions, but might be - useful in custom actions that try to help diagnose errors. -*/ - -#if PROCEED_ON_ERROR - -/* A count of the number of corruption errors causing resets */ -int malloc_corruption_error_count; - -/* default corruption action */ -static void reset_on_error(mstate m); - -#define CORRUPTION_ERROR_ACTION(m) reset_on_error(m) -#define USAGE_ERROR_ACTION(m, p) - -#else /* PROCEED_ON_ERROR */ - -#ifndef CORRUPTION_ERROR_ACTION -#define CORRUPTION_ERROR_ACTION(m) ABORT -#endif /* CORRUPTION_ERROR_ACTION */ - -#ifndef USAGE_ERROR_ACTION -#define USAGE_ERROR_ACTION(m,p) ABORT -#endif /* USAGE_ERROR_ACTION */ - -#endif /* PROCEED_ON_ERROR */ - -/* -------------------------- Debugging setup ---------------------------- */ - -#if ! DEBUG - -#define check_free_chunk(M,P) -#define check_inuse_chunk(M,P) -#define check_malloced_chunk(M,P,N) -#define check_mmapped_chunk(M,P) -#define check_malloc_state(M) -#define check_top_chunk(M,P) - -#else /* DEBUG */ -#define check_free_chunk(M,P) do_check_free_chunk(M,P) -#define check_inuse_chunk(M,P) do_check_inuse_chunk(M,P) -#define check_top_chunk(M,P) do_check_top_chunk(M,P) -#define check_malloced_chunk(M,P,N) do_check_malloced_chunk(M,P,N) -#define check_mmapped_chunk(M,P) do_check_mmapped_chunk(M,P) -#define check_malloc_state(M) do_check_malloc_state(M) - -static void do_check_any_chunk(mstate m, mchunkptr p); -static void do_check_top_chunk(mstate m, mchunkptr p); -static void do_check_mmapped_chunk(mstate m, mchunkptr p); -static void do_check_inuse_chunk(mstate m, mchunkptr p); -static void do_check_free_chunk(mstate m, mchunkptr p); -static void do_check_malloced_chunk(mstate m, void* mem, size_t s); -static void do_check_tree(mstate m, tchunkptr t); -static void do_check_treebin(mstate m, bindex_t i); -static void do_check_smallbin(mstate m, bindex_t i); -static void do_check_malloc_state(mstate m); -static int bin_find(mstate m, mchunkptr x); -static size_t traverse_and_check(mstate m); -#endif /* DEBUG */ - -/* ---------------------------- Indexing Bins ---------------------------- */ - -#define is_small(s) (((s) >> SMALLBIN_SHIFT) < NSMALLBINS) -#define small_index(s) ((s) >> SMALLBIN_SHIFT) -#define small_index2size(i) ((i) << SMALLBIN_SHIFT) -#define MIN_SMALL_INDEX (small_index(MIN_CHUNK_SIZE)) - -/* addressing by index. See above about smallbin repositioning */ -#define smallbin_at(M, i) ((sbinptr)((char*)&((M)->smallbins[(i)<<1]))) -#define treebin_at(M,i) (&((M)->treebins[i])) - -/* assign tree index for size S to variable I */ -#if defined(__GNUC__) && defined(i386) -#define compute_tree_index(S, I)\ -{\ - size_t X = S >> TREEBIN_SHIFT;\ - if (X == 0)\ - I = 0;\ - else if (X > 0xFFFF)\ - I = NTREEBINS-1;\ - else {\ - unsigned int K;\ - __asm__("bsrl %1,%0\n\t" : "=r" (K) : "rm" (X));\ - I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\ - }\ -} -#else /* GNUC */ -#define compute_tree_index(S, I)\ -{\ - size_t X = S >> TREEBIN_SHIFT;\ - if (X == 0)\ - I = 0;\ - else if (X > 0xFFFF)\ - I = NTREEBINS-1;\ - else {\ - unsigned int Y = (unsigned int)X;\ - unsigned int N = ((Y - 0x100) >> 16) & 8;\ - unsigned int K = (((Y <<= N) - 0x1000) >> 16) & 4;\ - N += K;\ - N += K = (((Y <<= K) - 0x4000) >> 16) & 2;\ - K = 14 - N + ((Y <<= K) >> 15);\ - I = (K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1));\ - }\ -} -#endif /* GNUC */ - -/* Bit representing maximum resolved size in a treebin at i */ -#define bit_for_tree_index(i) \ - (i == NTREEBINS-1)? (SIZE_T_BITSIZE-1) : (((i) >> 1) + TREEBIN_SHIFT - 2) - -/* Shift placing maximum resolved bit in a treebin at i as sign bit */ -#define leftshift_for_tree_index(i) \ - ((i == NTREEBINS-1)? 0 : \ - ((SIZE_T_BITSIZE-SIZE_T_ONE) - (((i) >> 1) + TREEBIN_SHIFT - 2))) - -/* The size of the smallest chunk held in bin with index i */ -#define minsize_for_tree_index(i) \ - ((SIZE_T_ONE << (((i) >> 1) + TREEBIN_SHIFT)) | \ - (((size_t)((i) & SIZE_T_ONE)) << (((i) >> 1) + TREEBIN_SHIFT - 1))) - - -/* ------------------------ Operations on bin maps ----------------------- */ - -/* bit corresponding to given index */ -#define idx2bit(i) ((binmap_t)(1) << (i)) - -/* Mark/Clear bits with given index */ -#define mark_smallmap(M,i) ((M)->smallmap |= idx2bit(i)) -#define clear_smallmap(M,i) ((M)->smallmap &= ~idx2bit(i)) -#define smallmap_is_marked(M,i) ((M)->smallmap & idx2bit(i)) - -#define mark_treemap(M,i) ((M)->treemap |= idx2bit(i)) -#define clear_treemap(M,i) ((M)->treemap &= ~idx2bit(i)) -#define treemap_is_marked(M,i) ((M)->treemap & idx2bit(i)) - -/* index corresponding to given bit */ - -#if defined(__GNUC__) && defined(i386) -#define compute_bit2idx(X, I)\ -{\ - unsigned int J;\ - __asm__("bsfl %1,%0\n\t" : "=r" (J) : "rm" (X));\ - I = (bindex_t)J;\ -} - -#else /* GNUC */ -#if USE_BUILTIN_FFS -#define compute_bit2idx(X, I) I = ffs(X)-1 - -#else /* USE_BUILTIN_FFS */ -#define compute_bit2idx(X, I)\ -{\ - unsigned int Y = X - 1;\ - unsigned int K = Y >> (16-4) & 16;\ - unsigned int N = K; Y >>= K;\ - N += K = Y >> (8-3) & 8; Y >>= K;\ - N += K = Y >> (4-2) & 4; Y >>= K;\ - N += K = Y >> (2-1) & 2; Y >>= K;\ - N += K = Y >> (1-0) & 1; Y >>= K;\ - I = (bindex_t)(N + Y);\ -} -#endif /* USE_BUILTIN_FFS */ -#endif /* GNUC */ - -/* isolate the least set bit of a bitmap */ -#define least_bit(x) ((x) & -(x)) - -/* mask with all bits to left of least bit of x on */ -#define left_bits(x) ((x<<1) | -(x<<1)) - -/* mask with all bits to left of or equal to least bit of x on */ -#define same_or_left_bits(x) ((x) | -(x)) - - -/* ----------------------- Runtime Check Support ------------------------- */ - -/* - For security, the main invariant is that malloc/free/etc never - writes to a static address other than malloc_state, unless static - malloc_state itself has been corrupted, which cannot occur via - malloc (because of these checks). In essence this means that we - believe all pointers, sizes, maps etc held in malloc_state, but - check all of those linked or offsetted from other embedded data - structures. These checks are interspersed with main code in a way - that tends to minimize their run-time cost. - - When FOOTERS is defined, in addition to range checking, we also - verify footer fields of inuse chunks, which can be used guarantee - that the mstate controlling malloc/free is intact. This is a - streamlined version of the approach described by William Robertson - et al in "Run-time Detection of Heap-based Overflows" LISA'03 - http://www.usenix.org/events/lisa03/tech/robertson.html The footer - of an inuse chunk holds the xor of its mstate and a random seed, - that is checked upon calls to free() and realloc(). This is - (probablistically) unguessable from outside the program, but can be - computed by any code successfully malloc'ing any chunk, so does not - itself provide protection against code that has already broken - security through some other means. Unlike Robertson et al, we - always dynamically check addresses of all offset chunks (previous, - next, etc). This turns out to be cheaper than relying on hashes. -*/ - -#if !INSECURE -/* Check if address a is at least as high as any from MORECORE or MMAP */ -#define ok_address(M, a) ((char*)(a) >= (M)->least_addr) -/* Check if address of next chunk n is higher than base chunk p */ -#define ok_next(p, n) ((char*)(p) < (char*)(n)) -/* Check if p has its cinuse bit on */ -#define ok_cinuse(p) cinuse(p) -/* Check if p has its pinuse bit on */ -#define ok_pinuse(p) pinuse(p) - -#else /* !INSECURE */ -#define ok_address(M, a) (1) -#define ok_next(b, n) (1) -#define ok_cinuse(p) (1) -#define ok_pinuse(p) (1) -#endif /* !INSECURE */ - -#if (FOOTERS && !INSECURE) -/* Check if (alleged) mstate m has expected magic field */ -#define ok_magic(M) ((M)->magic == mparams.magic) -#else /* (FOOTERS && !INSECURE) */ -#define ok_magic(M) (1) -#endif /* (FOOTERS && !INSECURE) */ - - -/* In gcc, use __builtin_expect to minimize impact of checks */ -#if !INSECURE -#if defined(__GNUC__) && __GNUC__ >= 3 -#define RTCHECK(e) __builtin_expect(e, 1) -#else /* GNUC */ -#define RTCHECK(e) (e) -#endif /* GNUC */ -#else /* !INSECURE */ -#define RTCHECK(e) (1) -#endif /* !INSECURE */ - -/* macros to set up inuse chunks with or without footers */ - -#if !FOOTERS - -#define mark_inuse_foot(M,p,s) - -/* Set cinuse bit and pinuse bit of next chunk */ -#define set_inuse(M,p,s)\ - ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\ - ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT) - -/* Set cinuse and pinuse of this chunk and pinuse of next chunk */ -#define set_inuse_and_pinuse(M,p,s)\ - ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ - ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT) - -/* Set size, cinuse and pinuse bit of this chunk */ -#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\ - ((p)->head = (s|PINUSE_BIT|CINUSE_BIT)) - -#else /* FOOTERS */ - -/* Set foot of inuse chunk to be xor of mstate and seed */ -#define mark_inuse_foot(M,p,s)\ - (((mchunkptr)((char*)(p) + (s)))->prev_foot = ((size_t)(M) ^ mparams.magic)) - -#define get_mstate_for(p)\ - ((mstate)(((mchunkptr)((char*)(p) +\ - (chunksize(p))))->prev_foot ^ mparams.magic)) - -#define set_inuse(M,p,s)\ - ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\ - (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT), \ - mark_inuse_foot(M,p,s)) - -#define set_inuse_and_pinuse(M,p,s)\ - ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ - (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT),\ - mark_inuse_foot(M,p,s)) - -#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\ - ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ - mark_inuse_foot(M, p, s)) - -#endif /* !FOOTERS */ - -/* ---------------------------- setting mparams -------------------------- */ - -/* Initialize mparams */ -static int init_mparams(void) { - if (mparams.page_size == 0) { - size_t s; - - mparams.mmap_threshold = DEFAULT_MMAP_THRESHOLD; - mparams.trim_threshold = DEFAULT_TRIM_THRESHOLD; -#if MORECORE_CONTIGUOUS - mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT; -#else /* MORECORE_CONTIGUOUS */ - mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT|USE_NONCONTIGUOUS_BIT; -#endif /* MORECORE_CONTIGUOUS */ - -#if (FOOTERS && !INSECURE) - { -#if USE_DEV_RANDOM - int fd; - unsigned char buf[sizeof(size_t)]; - /* Try to use /dev/urandom, else fall back on using time */ - if ((fd = open("/dev/urandom", O_RDONLY)) >= 0 && - read(fd, buf, sizeof(buf)) == sizeof(buf)) { - s = *((size_t *) buf); - close(fd); - } - else -#endif /* USE_DEV_RANDOM */ - s = (size_t)(time(0) ^ (size_t)0x55555555U); - - s |= (size_t)8U; /* ensure nonzero */ - s &= ~(size_t)7U; /* improve chances of fault for bad values */ - - } -#else /* (FOOTERS && !INSECURE) */ - s = (size_t)0x58585858U; -#endif /* (FOOTERS && !INSECURE) */ - ACQUIRE_MAGIC_INIT_LOCK(); - if (mparams.magic == 0) { - mparams.magic = s; - /* Set up lock for main malloc area */ - INITIAL_LOCK(&gm->mutex); - gm->mflags = mparams.default_mflags; - } - RELEASE_MAGIC_INIT_LOCK(); - -#ifndef WIN32 - mparams.page_size = malloc_getpagesize; - mparams.granularity = ((DEFAULT_GRANULARITY != 0)? - DEFAULT_GRANULARITY : mparams.page_size); -#else /* WIN32 */ - { - SYSTEM_INFO system_info; - GetSystemInfo(&system_info); - mparams.page_size = system_info.dwPageSize; - mparams.granularity = system_info.dwAllocationGranularity; - } -#endif /* WIN32 */ - - /* Sanity-check configuration: - size_t must be unsigned and as wide as pointer type. - ints must be at least 4 bytes. - alignment must be at least 8. - Alignment, min chunk size, and page size must all be powers of 2. - */ - if ((sizeof(size_t) != sizeof(char*)) || - (MAX_SIZE_T < MIN_CHUNK_SIZE) || - (sizeof(int) < 4) || - (MALLOC_ALIGNMENT < (size_t)8U) || - ((MALLOC_ALIGNMENT & (MALLOC_ALIGNMENT-SIZE_T_ONE)) != 0) || - ((MCHUNK_SIZE & (MCHUNK_SIZE-SIZE_T_ONE)) != 0) || - ((mparams.granularity & (mparams.granularity-SIZE_T_ONE)) != 0) || - ((mparams.page_size & (mparams.page_size-SIZE_T_ONE)) != 0)) - ABORT; - } - return 0; -} - -/* support for mallopt */ -static int change_mparam(int param_number, int value) { - size_t val = (size_t)value; - init_mparams(); - switch(param_number) { - case M_TRIM_THRESHOLD: - mparams.trim_threshold = val; - return 1; - case M_GRANULARITY: - if (val >= mparams.page_size && ((val & (val-1)) == 0)) { - mparams.granularity = val; - return 1; - } - else - return 0; - case M_MMAP_THRESHOLD: - mparams.mmap_threshold = val; - return 1; - default: - return 0; - } -} - -#if DEBUG -/* ------------------------- Debugging Support --------------------------- */ - -/* Check properties of any chunk, whether free, inuse, mmapped etc */ -static void do_check_any_chunk(mstate m, mchunkptr p) { - assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); - assert(ok_address(m, p)); -} - -/* Check properties of top chunk */ -static void do_check_top_chunk(mstate m, mchunkptr p) { - msegmentptr sp = segment_holding(m, (char*)p); - size_t sz = chunksize(p); - assert(sp != 0); - assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); - assert(ok_address(m, p)); - assert(sz == m->topsize); - assert(sz > 0); - assert(sz == ((sp->base + sp->size) - (char*)p) - TOP_FOOT_SIZE); - assert(pinuse(p)); - assert(!next_pinuse(p)); -} - -/* Check properties of (inuse) mmapped chunks */ -static void do_check_mmapped_chunk(mstate m, mchunkptr p) { - size_t sz = chunksize(p); - size_t len = (sz + (p->prev_foot & ~IS_MMAPPED_BIT) + MMAP_FOOT_PAD); - assert(is_mmapped(p)); - assert(use_mmap(m)); - assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); - assert(ok_address(m, p)); - assert(!is_small(sz)); - assert((len & (mparams.page_size-SIZE_T_ONE)) == 0); - assert(chunk_plus_offset(p, sz)->head == FENCEPOST_HEAD); - assert(chunk_plus_offset(p, sz+SIZE_T_SIZE)->head == 0); -} - -/* Check properties of inuse chunks */ -static void do_check_inuse_chunk(mstate m, mchunkptr p) { - do_check_any_chunk(m, p); - assert(cinuse(p)); - assert(next_pinuse(p)); - /* If not pinuse and not mmapped, previous chunk has OK offset */ - assert(is_mmapped(p) || pinuse(p) || next_chunk(prev_chunk(p)) == p); - if (is_mmapped(p)) - do_check_mmapped_chunk(m, p); -} - -/* Check properties of free chunks */ -static void do_check_free_chunk(mstate m, mchunkptr p) { - size_t sz = p->head & ~(PINUSE_BIT|CINUSE_BIT); - mchunkptr next = chunk_plus_offset(p, sz); - do_check_any_chunk(m, p); - assert(!cinuse(p)); - assert(!next_pinuse(p)); - assert (!is_mmapped(p)); - if (p != m->dv && p != m->top) { - if (sz >= MIN_CHUNK_SIZE) { - assert((sz & CHUNK_ALIGN_MASK) == 0); - assert(is_aligned(chunk2mem(p))); - assert(next->prev_foot == sz); - assert(pinuse(p)); - assert (next == m->top || cinuse(next)); - assert(p->fd->bk == p); - assert(p->bk->fd == p); - } - else /* markers are always of size SIZE_T_SIZE */ - assert(sz == SIZE_T_SIZE); - } -} - -/* Check properties of malloced chunks at the point they are malloced */ -static void do_check_malloced_chunk(mstate m, void* mem, size_t s) { - if (mem != 0) { - mchunkptr p = mem2chunk(mem); - size_t sz = p->head & ~(PINUSE_BIT|CINUSE_BIT); - do_check_inuse_chunk(m, p); - assert((sz & CHUNK_ALIGN_MASK) == 0); - assert(sz >= MIN_CHUNK_SIZE); - assert(sz >= s); - /* unless mmapped, size is less than MIN_CHUNK_SIZE more than request */ - assert(is_mmapped(p) || sz < (s + MIN_CHUNK_SIZE)); - } -} - -/* Check a tree and its subtrees. */ -static void do_check_tree(mstate m, tchunkptr t) { - tchunkptr head = 0; - tchunkptr u = t; - bindex_t tindex = t->index; - size_t tsize = chunksize(t); - bindex_t idx; - compute_tree_index(tsize, idx); - assert(tindex == idx); - assert(tsize >= MIN_LARGE_SIZE); - assert(tsize >= minsize_for_tree_index(idx)); - assert((idx == NTREEBINS-1) || (tsize < minsize_for_tree_index((idx+1)))); - - do { /* traverse through chain of same-sized nodes */ - do_check_any_chunk(m, ((mchunkptr)u)); - assert(u->index == tindex); - assert(chunksize(u) == tsize); - assert(!cinuse(u)); - assert(!next_pinuse(u)); - assert(u->fd->bk == u); - assert(u->bk->fd == u); - if (u->parent == 0) { - assert(u->child[0] == 0); - assert(u->child[1] == 0); - } - else { - assert(head == 0); /* only one node on chain has parent */ - head = u; - assert(u->parent != u); - assert (u->parent->child[0] == u || - u->parent->child[1] == u || - *((tbinptr*)(u->parent)) == u); - if (u->child[0] != 0) { - assert(u->child[0]->parent == u); - assert(u->child[0] != u); - do_check_tree(m, u->child[0]); - } - if (u->child[1] != 0) { - assert(u->child[1]->parent == u); - assert(u->child[1] != u); - do_check_tree(m, u->child[1]); - } - if (u->child[0] != 0 && u->child[1] != 0) { - assert(chunksize(u->child[0]) < chunksize(u->child[1])); - } - } - u = u->fd; - } while (u != t); - assert(head != 0); -} - -/* Check all the chunks in a treebin. */ -static void do_check_treebin(mstate m, bindex_t i) { - tbinptr* tb = treebin_at(m, i); - tchunkptr t = *tb; - int empty = (m->treemap & (1U << i)) == 0; - if (t == 0) - assert(empty); - if (!empty) - do_check_tree(m, t); -} - -/* Check all the chunks in a smallbin. */ -static void do_check_smallbin(mstate m, bindex_t i) { - sbinptr b = smallbin_at(m, i); - mchunkptr p = b->bk; - unsigned int empty = (m->smallmap & (1U << i)) == 0; - if (p == b) - assert(empty); - if (!empty) { - for (; p != b; p = p->bk) { - size_t size = chunksize(p); - mchunkptr q; - /* each chunk claims to be free */ - do_check_free_chunk(m, p); - /* chunk belongs in bin */ - assert(small_index(size) == i); - assert(p->bk == b || chunksize(p->bk) == chunksize(p)); - /* chunk is followed by an inuse chunk */ - q = next_chunk(p); - if (q->head != FENCEPOST_HEAD) - do_check_inuse_chunk(m, q); - } - } -} - -/* Find x in a bin. Used in other check functions. */ -static int bin_find(mstate m, mchunkptr x) { - size_t size = chunksize(x); - if (is_small(size)) { - bindex_t sidx = small_index(size); - sbinptr b = smallbin_at(m, sidx); - if (smallmap_is_marked(m, sidx)) { - mchunkptr p = b; - do { - if (p == x) - return 1; - } while ((p = p->fd) != b); - } - } - else { - bindex_t tidx; - compute_tree_index(size, tidx); - if (treemap_is_marked(m, tidx)) { - tchunkptr t = *treebin_at(m, tidx); - size_t sizebits = size << leftshift_for_tree_index(tidx); - while (t != 0 && chunksize(t) != size) { - t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]; - sizebits <<= 1; - } - if (t != 0) { - tchunkptr u = t; - do { - if (u == (tchunkptr)x) - return 1; - } while ((u = u->fd) != t); - } - } - } - return 0; -} - -/* Traverse each chunk and check it; return total */ -static size_t traverse_and_check(mstate m) { - size_t sum = 0; - if (is_initialized(m)) { - msegmentptr s = &m->seg; - sum += m->topsize + TOP_FOOT_SIZE; - while (s != 0) { - mchunkptr q = align_as_chunk(s->base); - mchunkptr lastq = 0; - assert(pinuse(q)); - while (segment_holds(s, q) && - q != m->top && q->head != FENCEPOST_HEAD) { - sum += chunksize(q); - if (cinuse(q)) { - assert(!bin_find(m, q)); - do_check_inuse_chunk(m, q); - } - else { - assert(q == m->dv || bin_find(m, q)); - assert(lastq == 0 || cinuse(lastq)); /* Not 2 consecutive free */ - do_check_free_chunk(m, q); - } - lastq = q; - q = next_chunk(q); - } - s = s->next; - } - } - return sum; -} - -/* Check all properties of malloc_state. */ -static void do_check_malloc_state(mstate m) { - bindex_t i; - size_t total; - /* check bins */ - for (i = 0; i < NSMALLBINS; ++i) - do_check_smallbin(m, i); - for (i = 0; i < NTREEBINS; ++i) - do_check_treebin(m, i); - - if (m->dvsize != 0) { /* check dv chunk */ - do_check_any_chunk(m, m->dv); - assert(m->dvsize == chunksize(m->dv)); - assert(m->dvsize >= MIN_CHUNK_SIZE); - assert(bin_find(m, m->dv) == 0); - } - - if (m->top != 0) { /* check top chunk */ - do_check_top_chunk(m, m->top); - assert(m->topsize == chunksize(m->top)); - assert(m->topsize > 0); - assert(bin_find(m, m->top) == 0); - } - - total = traverse_and_check(m); - assert(total <= m->footprint); - assert(m->footprint <= m->max_footprint); -#if USE_MAX_ALLOWED_FOOTPRINT - //TODO: change these assertions if we allow for shrinking. - assert(m->footprint <= m->max_allowed_footprint); - assert(m->max_footprint <= m->max_allowed_footprint); -#endif -} -#endif /* DEBUG */ - -/* ----------------------------- statistics ------------------------------ */ - -#if !NO_MALLINFO -static struct mallinfo internal_mallinfo(mstate m) { - struct mallinfo nm = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }; - if (!PREACTION(m)) { - check_malloc_state(m); - if (is_initialized(m)) { - size_t nfree = SIZE_T_ONE; /* top always free */ - size_t mfree = m->topsize + TOP_FOOT_SIZE; - size_t sum = mfree; - msegmentptr s = &m->seg; - while (s != 0) { - mchunkptr q = align_as_chunk(s->base); - while (segment_holds(s, q) && - q != m->top && q->head != FENCEPOST_HEAD) { - size_t sz = chunksize(q); - sum += sz; - if (!cinuse(q)) { - mfree += sz; - ++nfree; - } - q = next_chunk(q); - } - s = s->next; - } - - nm.arena = sum; - nm.ordblks = nfree; - nm.hblkhd = m->footprint - sum; - nm.usmblks = m->max_footprint; - nm.uordblks = m->footprint - mfree; - nm.fordblks = mfree; - nm.keepcost = m->topsize; - } - - POSTACTION(m); - } - return nm; -} -#endif /* !NO_MALLINFO */ - -static void internal_malloc_stats(mstate m) { - if (!PREACTION(m)) { - size_t maxfp = 0; - size_t fp = 0; - size_t used = 0; - check_malloc_state(m); - if (is_initialized(m)) { - msegmentptr s = &m->seg; - maxfp = m->max_footprint; - fp = m->footprint; - used = fp - (m->topsize + TOP_FOOT_SIZE); - - while (s != 0) { - mchunkptr q = align_as_chunk(s->base); - while (segment_holds(s, q) && - q != m->top && q->head != FENCEPOST_HEAD) { - if (!cinuse(q)) - used -= chunksize(q); - q = next_chunk(q); - } - s = s->next; - } - } - - fprintf(stderr, "max system bytes = %10lu\n", (unsigned long)(maxfp)); - fprintf(stderr, "system bytes = %10lu\n", (unsigned long)(fp)); - fprintf(stderr, "in use bytes = %10lu\n", (unsigned long)(used)); - - POSTACTION(m); - } -} - -/* ----------------------- Operations on smallbins ----------------------- */ - -/* - Various forms of linking and unlinking are defined as macros. Even - the ones for trees, which are very long but have very short typical - paths. This is ugly but reduces reliance on inlining support of - compilers. -*/ - -/* Link a free chunk into a smallbin */ -#define insert_small_chunk(M, P, S) {\ - bindex_t I = small_index(S);\ - mchunkptr B = smallbin_at(M, I);\ - mchunkptr F = B;\ - assert(S >= MIN_CHUNK_SIZE);\ - if (!smallmap_is_marked(M, I))\ - mark_smallmap(M, I);\ - else if (RTCHECK(ok_address(M, B->fd)))\ - F = B->fd;\ - else {\ - CORRUPTION_ERROR_ACTION(M);\ - }\ - B->fd = P;\ - F->bk = P;\ - P->fd = F;\ - P->bk = B;\ -} - -/* Unlink a chunk from a smallbin - * Added check: if F->bk != P or B->fd != P, we have double linked list - * corruption, and abort. - */ -#define unlink_small_chunk(M, P, S) {\ - mchunkptr F = P->fd;\ - mchunkptr B = P->bk;\ - bindex_t I = small_index(S);\ - if (__builtin_expect (F->bk != P || B->fd != P, 0))\ - CORRUPTION_ERROR_ACTION(M);\ - assert(P != B);\ - assert(P != F);\ - assert(chunksize(P) == small_index2size(I));\ - if (F == B)\ - clear_smallmap(M, I);\ - else if (RTCHECK((F == smallbin_at(M,I) || ok_address(M, F)) &&\ - (B == smallbin_at(M,I) || ok_address(M, B)))) {\ - F->bk = B;\ - B->fd = F;\ - }\ - else {\ - CORRUPTION_ERROR_ACTION(M);\ - }\ -} - -/* Unlink the first chunk from a smallbin - * Added check: if F->bk != P or B->fd != P, we have double linked list - * corruption, and abort. - */ -#define unlink_first_small_chunk(M, B, P, I) {\ - mchunkptr F = P->fd;\ - if (__builtin_expect (F->bk != P || B->fd != P, 0))\ - CORRUPTION_ERROR_ACTION(M);\ - assert(P != B);\ - assert(P != F);\ - assert(chunksize(P) == small_index2size(I));\ - if (B == F)\ - clear_smallmap(M, I);\ - else if (RTCHECK(ok_address(M, F))) {\ - B->fd = F;\ - F->bk = B;\ - }\ - else {\ - CORRUPTION_ERROR_ACTION(M);\ - }\ -} - -/* Replace dv node, binning the old one */ -/* Used only when dvsize known to be small */ -#define replace_dv(M, P, S) {\ - size_t DVS = M->dvsize;\ - if (DVS != 0) {\ - mchunkptr DV = M->dv;\ - assert(is_small(DVS));\ - insert_small_chunk(M, DV, DVS);\ - }\ - M->dvsize = S;\ - M->dv = P;\ -} - -/* ------------------------- Operations on trees ------------------------- */ - -/* Insert chunk into tree */ -#define insert_large_chunk(M, X, S) {\ - tbinptr* H;\ - bindex_t I;\ - compute_tree_index(S, I);\ - H = treebin_at(M, I);\ - X->index = I;\ - X->child[0] = X->child[1] = 0;\ - if (!treemap_is_marked(M, I)) {\ - mark_treemap(M, I);\ - *H = X;\ - X->parent = (tchunkptr)H;\ - X->fd = X->bk = X;\ - }\ - else {\ - tchunkptr T = *H;\ - size_t K = S << leftshift_for_tree_index(I);\ - for (;;) {\ - if (chunksize(T) != S) {\ - tchunkptr* C = &(T->child[(K >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]);\ - K <<= 1;\ - if (*C != 0)\ - T = *C;\ - else if (RTCHECK(ok_address(M, C))) {\ - *C = X;\ - X->parent = T;\ - X->fd = X->bk = X;\ - break;\ - }\ - else {\ - CORRUPTION_ERROR_ACTION(M);\ - break;\ - }\ - }\ - else {\ - tchunkptr F = T->fd;\ - if (RTCHECK(ok_address(M, T) && ok_address(M, F))) {\ - T->fd = F->bk = X;\ - X->fd = F;\ - X->bk = T;\ - X->parent = 0;\ - break;\ - }\ - else {\ - CORRUPTION_ERROR_ACTION(M);\ - break;\ - }\ - }\ - }\ - }\ -} - -/* - Unlink steps: - - 1. If x is a chained node, unlink it from its same-sized fd/bk links - and choose its bk node as its replacement. - 2. If x was the last node of its size, but not a leaf node, it must - be replaced with a leaf node (not merely one with an open left or - right), to make sure that lefts and rights of descendents - correspond properly to bit masks. We use the rightmost descendent - of x. We could use any other leaf, but this is easy to locate and - tends to counteract removal of leftmosts elsewhere, and so keeps - paths shorter than minimally guaranteed. This doesn't loop much - because on average a node in a tree is near the bottom. - 3. If x is the base of a chain (i.e., has parent links) relink - x's parent and children to x's replacement (or null if none). - - Added check: if F->bk != X or R->fd != X, we have double linked list - corruption, and abort. -*/ - -#define unlink_large_chunk(M, X) {\ - tchunkptr XP = X->parent;\ - tchunkptr R;\ - if (X->bk != X) {\ - tchunkptr F = X->fd;\ - R = X->bk;\ - if (__builtin_expect (F->bk != X || R->fd != X, 0))\ - CORRUPTION_ERROR_ACTION(M);\ - if (RTCHECK(ok_address(M, F))) {\ - F->bk = R;\ - R->fd = F;\ - }\ - else {\ - CORRUPTION_ERROR_ACTION(M);\ - }\ - }\ - else {\ - tchunkptr* RP;\ - if (((R = *(RP = &(X->child[1]))) != 0) ||\ - ((R = *(RP = &(X->child[0]))) != 0)) {\ - tchunkptr* CP;\ - while ((*(CP = &(R->child[1])) != 0) ||\ - (*(CP = &(R->child[0])) != 0)) {\ - R = *(RP = CP);\ - }\ - if (RTCHECK(ok_address(M, RP)))\ - *RP = 0;\ - else {\ - CORRUPTION_ERROR_ACTION(M);\ - }\ - }\ - }\ - if (XP != 0) {\ - tbinptr* H = treebin_at(M, X->index);\ - if (X == *H) {\ - if ((*H = R) == 0) \ - clear_treemap(M, X->index);\ - }\ - else if (RTCHECK(ok_address(M, XP))) {\ - if (XP->child[0] == X) \ - XP->child[0] = R;\ - else \ - XP->child[1] = R;\ - }\ - else\ - CORRUPTION_ERROR_ACTION(M);\ - if (R != 0) {\ - if (RTCHECK(ok_address(M, R))) {\ - tchunkptr C0, C1;\ - R->parent = XP;\ - if ((C0 = X->child[0]) != 0) {\ - if (RTCHECK(ok_address(M, C0))) {\ - R->child[0] = C0;\ - C0->parent = R;\ - }\ - else\ - CORRUPTION_ERROR_ACTION(M);\ - }\ - if ((C1 = X->child[1]) != 0) {\ - if (RTCHECK(ok_address(M, C1))) {\ - R->child[1] = C1;\ - C1->parent = R;\ - }\ - else\ - CORRUPTION_ERROR_ACTION(M);\ - }\ - }\ - else\ - CORRUPTION_ERROR_ACTION(M);\ - }\ - }\ -} - -/* Relays to large vs small bin operations */ - -#define insert_chunk(M, P, S)\ - if (is_small(S)) insert_small_chunk(M, P, S)\ - else { tchunkptr TP = (tchunkptr)(P); insert_large_chunk(M, TP, S); } - -#define unlink_chunk(M, P, S)\ - if (is_small(S)) unlink_small_chunk(M, P, S)\ - else { tchunkptr TP = (tchunkptr)(P); unlink_large_chunk(M, TP); } - - -/* Relays to internal calls to malloc/free from realloc, memalign etc */ - -#if ONLY_MSPACES -#define internal_malloc(m, b) mspace_malloc(m, b) -#define internal_free(m, mem) mspace_free(m,mem); -#else /* ONLY_MSPACES */ -#if MSPACES -#define internal_malloc(m, b)\ - (m == gm)? dlmalloc(b) : mspace_malloc(m, b) -#define internal_free(m, mem)\ - if (m == gm) dlfree(mem); else mspace_free(m,mem); -#else /* MSPACES */ -#define internal_malloc(m, b) dlmalloc(b) -#define internal_free(m, mem) dlfree(mem) -#endif /* MSPACES */ -#endif /* ONLY_MSPACES */ - -/* ----------------------- Direct-mmapping chunks ----------------------- */ - -/* - Directly mmapped chunks are set up with an offset to the start of - the mmapped region stored in the prev_foot field of the chunk. This - allows reconstruction of the required argument to MUNMAP when freed, - and also allows adjustment of the returned chunk to meet alignment - requirements (especially in memalign). There is also enough space - allocated to hold a fake next chunk of size SIZE_T_SIZE to maintain - the PINUSE bit so frees can be checked. -*/ - -/* Malloc using mmap */ -static void* mmap_alloc(mstate m, size_t nb) { - size_t mmsize = granularity_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK); -#if USE_MAX_ALLOWED_FOOTPRINT - size_t new_footprint = m->footprint + mmsize; - if (new_footprint <= m->footprint || /* Check for wrap around 0 */ - new_footprint > m->max_allowed_footprint) - return 0; -#endif - if (mmsize > nb) { /* Check for wrap around 0 */ - char* mm = (char*)(DIRECT_MMAP(mmsize)); - if (mm != CMFAIL) { - size_t offset = align_offset(chunk2mem(mm)); - size_t psize = mmsize - offset - MMAP_FOOT_PAD; - mchunkptr p = (mchunkptr)(mm + offset); - p->prev_foot = offset | IS_MMAPPED_BIT; - (p)->head = (psize|CINUSE_BIT); - mark_inuse_foot(m, p, psize); - chunk_plus_offset(p, psize)->head = FENCEPOST_HEAD; - chunk_plus_offset(p, psize+SIZE_T_SIZE)->head = 0; - - if (mm < m->least_addr) - m->least_addr = mm; - if ((m->footprint += mmsize) > m->max_footprint) - m->max_footprint = m->footprint; - assert(is_aligned(chunk2mem(p))); - check_mmapped_chunk(m, p); - return chunk2mem(p); - } - } - return 0; -} - -/* Realloc using mmap */ -static mchunkptr mmap_resize(mstate m, mchunkptr oldp, size_t nb) { - size_t oldsize = chunksize(oldp); - if (is_small(nb)) /* Can't shrink mmap regions below small size */ - return 0; - /* Keep old chunk if big enough but not too big */ - if (oldsize >= nb + SIZE_T_SIZE && - (oldsize - nb) <= (mparams.granularity << 1)) - return oldp; - else { - size_t offset = oldp->prev_foot & ~IS_MMAPPED_BIT; - size_t oldmmsize = oldsize + offset + MMAP_FOOT_PAD; - size_t newmmsize = granularity_align(nb + SIX_SIZE_T_SIZES + - CHUNK_ALIGN_MASK); - char* cp = (char*)CALL_MREMAP((char*)oldp - offset, - oldmmsize, newmmsize, 1); - if (cp != CMFAIL) { - mchunkptr newp = (mchunkptr)(cp + offset); - size_t psize = newmmsize - offset - MMAP_FOOT_PAD; - newp->head = (psize|CINUSE_BIT); - mark_inuse_foot(m, newp, psize); - chunk_plus_offset(newp, psize)->head = FENCEPOST_HEAD; - chunk_plus_offset(newp, psize+SIZE_T_SIZE)->head = 0; - - if (cp < m->least_addr) - m->least_addr = cp; - if ((m->footprint += newmmsize - oldmmsize) > m->max_footprint) - m->max_footprint = m->footprint; - check_mmapped_chunk(m, newp); - return newp; - } - } - return 0; -} - -/* -------------------------- mspace management -------------------------- */ - -/* Initialize top chunk and its size */ -static void init_top(mstate m, mchunkptr p, size_t psize) { - /* Ensure alignment */ - size_t offset = align_offset(chunk2mem(p)); - p = (mchunkptr)((char*)p + offset); - psize -= offset; - - m->top = p; - m->topsize = psize; - p->head = psize | PINUSE_BIT; - /* set size of fake trailing chunk holding overhead space only once */ - chunk_plus_offset(p, psize)->head = TOP_FOOT_SIZE; - m->trim_check = mparams.trim_threshold; /* reset on each update */ -} - -/* Initialize bins for a new mstate that is otherwise zeroed out */ -static void init_bins(mstate m) { - /* Establish circular links for smallbins */ - bindex_t i; - for (i = 0; i < NSMALLBINS; ++i) { - sbinptr bin = smallbin_at(m,i); - bin->fd = bin->bk = bin; - } -} - -#if PROCEED_ON_ERROR - -/* default corruption action */ -static void reset_on_error(mstate m) { - int i; - ++malloc_corruption_error_count; - /* Reinitialize fields to forget about all memory */ - m->smallbins = m->treebins = 0; - m->dvsize = m->topsize = 0; - m->seg.base = 0; - m->seg.size = 0; - m->seg.next = 0; - m->top = m->dv = 0; - for (i = 0; i < NTREEBINS; ++i) - *treebin_at(m, i) = 0; - init_bins(m); -} -#endif /* PROCEED_ON_ERROR */ - -/* Allocate chunk and prepend remainder with chunk in successor base. */ -static void* prepend_alloc(mstate m, char* newbase, char* oldbase, - size_t nb) { - mchunkptr p = align_as_chunk(newbase); - mchunkptr oldfirst = align_as_chunk(oldbase); - size_t psize = (char*)oldfirst - (char*)p; - mchunkptr q = chunk_plus_offset(p, nb); - size_t qsize = psize - nb; - set_size_and_pinuse_of_inuse_chunk(m, p, nb); - - assert((char*)oldfirst > (char*)q); - assert(pinuse(oldfirst)); - assert(qsize >= MIN_CHUNK_SIZE); - - /* consolidate remainder with first chunk of old base */ - if (oldfirst == m->top) { - size_t tsize = m->topsize += qsize; - m->top = q; - q->head = tsize | PINUSE_BIT; - check_top_chunk(m, q); - } - else if (oldfirst == m->dv) { - size_t dsize = m->dvsize += qsize; - m->dv = q; - set_size_and_pinuse_of_free_chunk(q, dsize); - } - else { - if (!cinuse(oldfirst)) { - size_t nsize = chunksize(oldfirst); - unlink_chunk(m, oldfirst, nsize); - oldfirst = chunk_plus_offset(oldfirst, nsize); - qsize += nsize; - } - set_free_with_pinuse(q, qsize, oldfirst); - insert_chunk(m, q, qsize); - check_free_chunk(m, q); - } - - check_malloced_chunk(m, chunk2mem(p), nb); - return chunk2mem(p); -} - - -/* Add a segment to hold a new noncontiguous region */ -static void add_segment(mstate m, char* tbase, size_t tsize, flag_t mmapped) { - /* Determine locations and sizes of segment, fenceposts, old top */ - char* old_top = (char*)m->top; - msegmentptr oldsp = segment_holding(m, old_top); - char* old_end = oldsp->base + oldsp->size; - size_t ssize = pad_request(sizeof(struct malloc_segment)); - char* rawsp = old_end - (ssize + FOUR_SIZE_T_SIZES + CHUNK_ALIGN_MASK); - size_t offset = align_offset(chunk2mem(rawsp)); - char* asp = rawsp + offset; - char* csp = (asp < (old_top + MIN_CHUNK_SIZE))? old_top : asp; - mchunkptr sp = (mchunkptr)csp; - msegmentptr ss = (msegmentptr)(chunk2mem(sp)); - mchunkptr tnext = chunk_plus_offset(sp, ssize); - mchunkptr p = tnext; - int nfences = 0; - - /* reset top to new space */ - init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE); - - /* Set up segment record */ - assert(is_aligned(ss)); - set_size_and_pinuse_of_inuse_chunk(m, sp, ssize); - *ss = m->seg; /* Push current record */ - m->seg.base = tbase; - m->seg.size = tsize; - m->seg.sflags = mmapped; - m->seg.next = ss; - - /* Insert trailing fenceposts */ - for (;;) { - mchunkptr nextp = chunk_plus_offset(p, SIZE_T_SIZE); - p->head = FENCEPOST_HEAD; - ++nfences; - if ((char*)(&(nextp->head)) < old_end) - p = nextp; - else - break; - } - assert(nfences >= 2); - - /* Insert the rest of old top into a bin as an ordinary free chunk */ - if (csp != old_top) { - mchunkptr q = (mchunkptr)old_top; - size_t psize = csp - old_top; - mchunkptr tn = chunk_plus_offset(q, psize); - set_free_with_pinuse(q, psize, tn); - insert_chunk(m, q, psize); - } - - check_top_chunk(m, m->top); -} - -/* -------------------------- System allocation -------------------------- */ - -/* Get memory from system using MORECORE or MMAP */ -static void* sys_alloc(mstate m, size_t nb) { - char* tbase = CMFAIL; - size_t tsize = 0; - flag_t mmap_flag = 0; - - init_mparams(); - - /* Directly map large chunks */ - if (use_mmap(m) && nb >= mparams.mmap_threshold) { - void* mem = mmap_alloc(m, nb); - if (mem != 0) - return mem; - } - -#if USE_MAX_ALLOWED_FOOTPRINT - /* Make sure the footprint doesn't grow past max_allowed_footprint. - * This covers all cases except for where we need to page align, below. - */ - { - size_t new_footprint = m->footprint + - granularity_align(nb + TOP_FOOT_SIZE + SIZE_T_ONE); - if (new_footprint <= m->footprint || /* Check for wrap around 0 */ - new_footprint > m->max_allowed_footprint) - return 0; - } -#endif - - /* - Try getting memory in any of three ways (in most-preferred to - least-preferred order): - 1. A call to MORECORE that can normally contiguously extend memory. - (disabled if not MORECORE_CONTIGUOUS or not HAVE_MORECORE or - or main space is mmapped or a previous contiguous call failed) - 2. A call to MMAP new space (disabled if not HAVE_MMAP). - Note that under the default settings, if MORECORE is unable to - fulfill a request, and HAVE_MMAP is true, then mmap is - used as a noncontiguous system allocator. This is a useful backup - strategy for systems with holes in address spaces -- in this case - sbrk cannot contiguously expand the heap, but mmap may be able to - find space. - 3. A call to MORECORE that cannot usually contiguously extend memory. - (disabled if not HAVE_MORECORE) - */ - - if (MORECORE_CONTIGUOUS && !use_noncontiguous(m)) { - char* br = CMFAIL; - msegmentptr ss = (m->top == 0)? 0 : segment_holding(m, (char*)m->top); - size_t asize = 0; - ACQUIRE_MORECORE_LOCK(); - - if (ss == 0) { /* First time through or recovery */ - char* base = (char*)CALL_MORECORE(0); - if (base != CMFAIL) { - asize = granularity_align(nb + TOP_FOOT_SIZE + SIZE_T_ONE); - /* Adjust to end on a page boundary */ - if (!is_page_aligned(base)) { - asize += (page_align((size_t)base) - (size_t)base); -#if USE_MAX_ALLOWED_FOOTPRINT - /* If the alignment pushes us over max_allowed_footprint, - * poison the upcoming call to MORECORE and continue. - */ - { - size_t new_footprint = m->footprint + asize; - if (new_footprint <= m->footprint || /* Check for wrap around 0 */ - new_footprint > m->max_allowed_footprint) { - asize = HALF_MAX_SIZE_T; - } - } -#endif - } - /* Can't call MORECORE if size is negative when treated as signed */ - if (asize < HALF_MAX_SIZE_T && - (br = (char*)(CALL_MORECORE(asize))) == base) { - tbase = base; - tsize = asize; - } - } - } - else { - /* Subtract out existing available top space from MORECORE request. */ - asize = granularity_align(nb - m->topsize + TOP_FOOT_SIZE + SIZE_T_ONE); - /* Use mem here only if it did continuously extend old space */ - if (asize < HALF_MAX_SIZE_T && - (br = (char*)(CALL_MORECORE(asize))) == ss->base+ss->size) { - tbase = br; - tsize = asize; - } - } - - if (tbase == CMFAIL) { /* Cope with partial failure */ - if (br != CMFAIL) { /* Try to use/extend the space we did get */ - if (asize < HALF_MAX_SIZE_T && - asize < nb + TOP_FOOT_SIZE + SIZE_T_ONE) { - size_t esize = granularity_align(nb + TOP_FOOT_SIZE + SIZE_T_ONE - asize); - if (esize < HALF_MAX_SIZE_T) { - char* end = (char*)CALL_MORECORE(esize); - if (end != CMFAIL) - asize += esize; - else { /* Can't use; try to release */ - CALL_MORECORE(-asize); - br = CMFAIL; - } - } - } - } - if (br != CMFAIL) { /* Use the space we did get */ - tbase = br; - tsize = asize; - } - else - disable_contiguous(m); /* Don't try contiguous path in the future */ - } - - RELEASE_MORECORE_LOCK(); - } - - if (HAVE_MMAP && tbase == CMFAIL) { /* Try MMAP */ - size_t req = nb + TOP_FOOT_SIZE + SIZE_T_ONE; - size_t rsize = granularity_align(req); - if (rsize > nb) { /* Fail if wraps around zero */ - char* mp = (char*)(CALL_MMAP(rsize)); - if (mp != CMFAIL) { - tbase = mp; - tsize = rsize; - mmap_flag = IS_MMAPPED_BIT; - } - } - } - - if (HAVE_MORECORE && tbase == CMFAIL) { /* Try noncontiguous MORECORE */ - size_t asize = granularity_align(nb + TOP_FOOT_SIZE + SIZE_T_ONE); - if (asize < HALF_MAX_SIZE_T) { - char* br = CMFAIL; - char* end = CMFAIL; - ACQUIRE_MORECORE_LOCK(); - br = (char*)(CALL_MORECORE(asize)); - end = (char*)(CALL_MORECORE(0)); - RELEASE_MORECORE_LOCK(); - if (br != CMFAIL && end != CMFAIL && br < end) { - size_t ssize = end - br; - if (ssize > nb + TOP_FOOT_SIZE) { - tbase = br; - tsize = ssize; - } - } - } - } - - if (tbase != CMFAIL) { - - if ((m->footprint += tsize) > m->max_footprint) - m->max_footprint = m->footprint; - - if (!is_initialized(m)) { /* first-time initialization */ - m->seg.base = m->least_addr = tbase; - m->seg.size = tsize; - m->seg.sflags = mmap_flag; - m->magic = mparams.magic; - init_bins(m); - if (is_global(m)) - init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE); - else { - /* Offset top by embedded malloc_state */ - mchunkptr mn = next_chunk(mem2chunk(m)); - init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) -TOP_FOOT_SIZE); - } - } - - else { - /* Try to merge with an existing segment */ - msegmentptr sp = &m->seg; - while (sp != 0 && tbase != sp->base + sp->size) - sp = sp->next; - if (sp != 0 && - !is_extern_segment(sp) && - (sp->sflags & IS_MMAPPED_BIT) == mmap_flag && - segment_holds(sp, m->top)) { /* append */ - sp->size += tsize; - init_top(m, m->top, m->topsize + tsize); - } - else { - if (tbase < m->least_addr) - m->least_addr = tbase; - sp = &m->seg; - while (sp != 0 && sp->base != tbase + tsize) - sp = sp->next; - if (sp != 0 && - !is_extern_segment(sp) && - (sp->sflags & IS_MMAPPED_BIT) == mmap_flag) { - char* oldbase = sp->base; - sp->base = tbase; - sp->size += tsize; - return prepend_alloc(m, tbase, oldbase, nb); - } - else - add_segment(m, tbase, tsize, mmap_flag); - } - } - - if (nb < m->topsize) { /* Allocate from new or extended top space */ - size_t rsize = m->topsize -= nb; - mchunkptr p = m->top; - mchunkptr r = m->top = chunk_plus_offset(p, nb); - r->head = rsize | PINUSE_BIT; - set_size_and_pinuse_of_inuse_chunk(m, p, nb); - check_top_chunk(m, m->top); - check_malloced_chunk(m, chunk2mem(p), nb); - return chunk2mem(p); - } - } - - MALLOC_FAILURE_ACTION; - return 0; -} - -/* ----------------------- system deallocation -------------------------- */ - -/* Unmap and unlink any mmapped segments that don't contain used chunks */ -static size_t release_unused_segments(mstate m) { - size_t released = 0; - msegmentptr pred = &m->seg; - msegmentptr sp = pred->next; - while (sp != 0) { - char* base = sp->base; - size_t size = sp->size; - msegmentptr next = sp->next; - if (is_mmapped_segment(sp) && !is_extern_segment(sp)) { - mchunkptr p = align_as_chunk(base); - size_t psize = chunksize(p); - /* Can unmap if first chunk holds entire segment and not pinned */ - if (!cinuse(p) && (char*)p + psize >= base + size - TOP_FOOT_SIZE) { - tchunkptr tp = (tchunkptr)p; - assert(segment_holds(sp, (char*)sp)); - if (p == m->dv) { - m->dv = 0; - m->dvsize = 0; - } - else { - unlink_large_chunk(m, tp); - } - if (CALL_MUNMAP(base, size) == 0) { - released += size; - m->footprint -= size; - /* unlink obsoleted record */ - sp = pred; - sp->next = next; - } - else { /* back out if cannot unmap */ - insert_large_chunk(m, tp, psize); - } - } - } - pred = sp; - sp = next; - } - return released; -} - -static int sys_trim(mstate m, size_t pad) { - size_t released = 0; - if (pad < MAX_REQUEST && is_initialized(m)) { - pad += TOP_FOOT_SIZE; /* ensure enough room for segment overhead */ - - if (m->topsize > pad) { - /* Shrink top space in granularity-size units, keeping at least one */ - size_t unit = mparams.granularity; - size_t extra = ((m->topsize - pad + (unit - SIZE_T_ONE)) / unit - - SIZE_T_ONE) * unit; - msegmentptr sp = segment_holding(m, (char*)m->top); - - if (!is_extern_segment(sp)) { - if (is_mmapped_segment(sp)) { - if (HAVE_MMAP && - sp->size >= extra && - !has_segment_link(m, sp)) { /* can't shrink if pinned */ -#if HAVE_MMAP && HAVE_MREMAP - size_t newsize = sp->size - extra; -#endif - /* Prefer mremap, fall back to munmap */ - if ((CALL_MREMAP(sp->base, sp->size, newsize, 0) != MFAIL) || - (CALL_MUNMAP(sp->base + newsize, extra) == 0)) { - released = extra; - } - } - } - else if (HAVE_MORECORE) { - if (extra >= HALF_MAX_SIZE_T) /* Avoid wrapping negative */ - extra = (HALF_MAX_SIZE_T) + SIZE_T_ONE - unit; - ACQUIRE_MORECORE_LOCK(); - { - /* Make sure end of memory is where we last set it. */ - char* old_br = (char*)(CALL_MORECORE(0)); - if (old_br == sp->base + sp->size) { - char* rel_br = (char*)(CALL_MORECORE(-extra)); - char* new_br = (char*)(CALL_MORECORE(0)); - if (rel_br != CMFAIL && new_br < old_br) - released = old_br - new_br; - } - } - RELEASE_MORECORE_LOCK(); - } - } - - if (released != 0) { - sp->size -= released; - m->footprint -= released; - init_top(m, m->top, m->topsize - released); - check_top_chunk(m, m->top); - } - } - - /* Unmap any unused mmapped segments */ - if (HAVE_MMAP) - released += release_unused_segments(m); - - /* On failure, disable autotrim to avoid repeated failed future calls */ - if (released == 0) - m->trim_check = MAX_SIZE_T; - } - - return (released != 0)? 1 : 0; -} - -/* ---------------------------- malloc support --------------------------- */ - -/* allocate a large request from the best fitting chunk in a treebin */ -static void* tmalloc_large(mstate m, size_t nb) { - tchunkptr v = 0; - size_t rsize = -nb; /* Unsigned negation */ - tchunkptr t; - bindex_t idx; - compute_tree_index(nb, idx); - - if ((t = *treebin_at(m, idx)) != 0) { - /* Traverse tree for this bin looking for node with size == nb */ - size_t sizebits = nb << leftshift_for_tree_index(idx); - tchunkptr rst = 0; /* The deepest untaken right subtree */ - for (;;) { - tchunkptr rt; - size_t trem = chunksize(t) - nb; - if (trem < rsize) { - v = t; - if ((rsize = trem) == 0) - break; - } - rt = t->child[1]; - t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]; - if (rt != 0 && rt != t) - rst = rt; - if (t == 0) { - t = rst; /* set t to least subtree holding sizes > nb */ - break; - } - sizebits <<= 1; - } - } - - if (t == 0 && v == 0) { /* set t to root of next non-empty treebin */ - binmap_t leftbits = left_bits(idx2bit(idx)) & m->treemap; - if (leftbits != 0) { - bindex_t i; - binmap_t leastbit = least_bit(leftbits); - compute_bit2idx(leastbit, i); - t = *treebin_at(m, i); - } - } - - while (t != 0) { /* find smallest of tree or subtree */ - size_t trem = chunksize(t) - nb; - if (trem < rsize) { - rsize = trem; - v = t; - } - t = leftmost_child(t); - } - - /* If dv is a better fit, return 0 so malloc will use it */ - if (v != 0 && rsize < (size_t)(m->dvsize - nb)) { - if (RTCHECK(ok_address(m, v))) { /* split */ - mchunkptr r = chunk_plus_offset(v, nb); - assert(chunksize(v) == rsize + nb); - if (RTCHECK(ok_next(v, r))) { - unlink_large_chunk(m, v); - if (rsize < MIN_CHUNK_SIZE) - set_inuse_and_pinuse(m, v, (rsize + nb)); - else { - set_size_and_pinuse_of_inuse_chunk(m, v, nb); - set_size_and_pinuse_of_free_chunk(r, rsize); - insert_chunk(m, r, rsize); - } - return chunk2mem(v); - } - } - CORRUPTION_ERROR_ACTION(m); - } - return 0; -} - -/* allocate a small request from the best fitting chunk in a treebin */ -static void* tmalloc_small(mstate m, size_t nb) { - tchunkptr t, v; - size_t rsize; - bindex_t i; - binmap_t leastbit = least_bit(m->treemap); - compute_bit2idx(leastbit, i); - - v = t = *treebin_at(m, i); - rsize = chunksize(t) - nb; - - while ((t = leftmost_child(t)) != 0) { - size_t trem = chunksize(t) - nb; - if (trem < rsize) { - rsize = trem; - v = t; - } - } - - if (RTCHECK(ok_address(m, v))) { - mchunkptr r = chunk_plus_offset(v, nb); - assert(chunksize(v) == rsize + nb); - if (RTCHECK(ok_next(v, r))) { - unlink_large_chunk(m, v); - if (rsize < MIN_CHUNK_SIZE) - set_inuse_and_pinuse(m, v, (rsize + nb)); - else { - set_size_and_pinuse_of_inuse_chunk(m, v, nb); - set_size_and_pinuse_of_free_chunk(r, rsize); - replace_dv(m, r, rsize); - } - return chunk2mem(v); - } - } - - CORRUPTION_ERROR_ACTION(m); - return 0; -} - -/* --------------------------- realloc support --------------------------- */ - -static void* internal_realloc(mstate m, void* oldmem, size_t bytes) { - if (bytes >= MAX_REQUEST) { - MALLOC_FAILURE_ACTION; - return 0; - } - if (!PREACTION(m)) { - mchunkptr oldp = mem2chunk(oldmem); - size_t oldsize = chunksize(oldp); - mchunkptr next = chunk_plus_offset(oldp, oldsize); - mchunkptr newp = 0; - void* extra = 0; - - /* Try to either shrink or extend into top. Else malloc-copy-free */ - - if (RTCHECK(ok_address(m, oldp) && ok_cinuse(oldp) && - ok_next(oldp, next) && ok_pinuse(next))) { - size_t nb = request2size(bytes); - if (is_mmapped(oldp)) - newp = mmap_resize(m, oldp, nb); - else if (oldsize >= nb) { /* already big enough */ - size_t rsize = oldsize - nb; - newp = oldp; - if (rsize >= MIN_CHUNK_SIZE) { - mchunkptr remainder = chunk_plus_offset(newp, nb); - set_inuse(m, newp, nb); - set_inuse(m, remainder, rsize); - extra = chunk2mem(remainder); - } - } - else if (next == m->top && oldsize + m->topsize > nb) { - /* Expand into top */ - size_t newsize = oldsize + m->topsize; - size_t newtopsize = newsize - nb; - mchunkptr newtop = chunk_plus_offset(oldp, nb); - set_inuse(m, oldp, nb); - newtop->head = newtopsize |PINUSE_BIT; - m->top = newtop; - m->topsize = newtopsize; - newp = oldp; - } - } - else { - USAGE_ERROR_ACTION(m, oldmem); - POSTACTION(m); - return 0; - } - - POSTACTION(m); - - if (newp != 0) { - if (extra != 0) { - internal_free(m, extra); - } - check_inuse_chunk(m, newp); - return chunk2mem(newp); - } - else { - void* newmem = internal_malloc(m, bytes); - if (newmem != 0) { - size_t oc = oldsize - overhead_for(oldp); - memcpy(newmem, oldmem, (oc < bytes)? oc : bytes); - internal_free(m, oldmem); - } - return newmem; - } - } - return 0; -} - -/* --------------------------- memalign support -------------------------- */ - -static void* internal_memalign(mstate m, size_t alignment, size_t bytes) { - if (alignment <= MALLOC_ALIGNMENT) /* Can just use malloc */ - return internal_malloc(m, bytes); - if (alignment < MIN_CHUNK_SIZE) /* must be at least a minimum chunk size */ - alignment = MIN_CHUNK_SIZE; - if ((alignment & (alignment-SIZE_T_ONE)) != 0) {/* Ensure a power of 2 */ - size_t a = MALLOC_ALIGNMENT << 1; - while (a < alignment) a <<= 1; - alignment = a; - } - - if (bytes >= MAX_REQUEST - alignment) { - if (m != 0) { /* Test isn't needed but avoids compiler warning */ - MALLOC_FAILURE_ACTION; - } - } - else { - size_t nb = request2size(bytes); - size_t req = nb + alignment + MIN_CHUNK_SIZE - CHUNK_OVERHEAD; - char* mem = (char*)internal_malloc(m, req); - if (mem != 0) { - void* leader = 0; - void* trailer = 0; - mchunkptr p = mem2chunk(mem); - - if (PREACTION(m)) return 0; - if ((((size_t)(mem)) % alignment) != 0) { /* misaligned */ - /* - Find an aligned spot inside chunk. Since we need to give - back leading space in a chunk of at least MIN_CHUNK_SIZE, if - the first calculation places us at a spot with less than - MIN_CHUNK_SIZE leader, we can move to the next aligned spot. - We've allocated enough total room so that this is always - possible. - */ - char* br = (char*)mem2chunk((size_t)(((size_t)(mem + - alignment - - SIZE_T_ONE)) & - -alignment)); - char* pos = ((size_t)(br - (char*)(p)) >= MIN_CHUNK_SIZE)? - br : br+alignment; - mchunkptr newp = (mchunkptr)pos; - size_t leadsize = pos - (char*)(p); - size_t newsize = chunksize(p) - leadsize; - - if (is_mmapped(p)) { /* For mmapped chunks, just adjust offset */ - newp->prev_foot = p->prev_foot + leadsize; - newp->head = (newsize|CINUSE_BIT); - } - else { /* Otherwise, give back leader, use the rest */ - set_inuse(m, newp, newsize); - set_inuse(m, p, leadsize); - leader = chunk2mem(p); - } - p = newp; - } - - /* Give back spare room at the end */ - if (!is_mmapped(p)) { - size_t size = chunksize(p); - if (size > nb + MIN_CHUNK_SIZE) { - size_t remainder_size = size - nb; - mchunkptr remainder = chunk_plus_offset(p, nb); - set_inuse(m, p, nb); - set_inuse(m, remainder, remainder_size); - trailer = chunk2mem(remainder); - } - } - - assert (chunksize(p) >= nb); - assert((((size_t)(chunk2mem(p))) % alignment) == 0); - check_inuse_chunk(m, p); - POSTACTION(m); - if (leader != 0) { - internal_free(m, leader); - } - if (trailer != 0) { - internal_free(m, trailer); - } - return chunk2mem(p); - } - } - return 0; -} - -/* ------------------------ comalloc/coalloc support --------------------- */ - -static void** ialloc(mstate m, - size_t n_elements, - size_t* sizes, - int opts, - void* chunks[]) { - /* - This provides common support for independent_X routines, handling - all of the combinations that can result. - - The opts arg has: - bit 0 set if all elements are same size (using sizes[0]) - bit 1 set if elements should be zeroed - */ - - size_t element_size; /* chunksize of each element, if all same */ - size_t contents_size; /* total size of elements */ - size_t array_size; /* request size of pointer array */ - void* mem; /* malloced aggregate space */ - mchunkptr p; /* corresponding chunk */ - size_t remainder_size; /* remaining bytes while splitting */ - void** marray; /* either "chunks" or malloced ptr array */ - mchunkptr array_chunk; /* chunk for malloced ptr array */ - flag_t was_enabled; /* to disable mmap */ - size_t size; - size_t i; - - /* compute array length, if needed */ - if (chunks != 0) { - if (n_elements == 0) - return chunks; /* nothing to do */ - marray = chunks; - array_size = 0; - } - else { - /* if empty req, must still return chunk representing empty array */ - if (n_elements == 0) - return (void**)internal_malloc(m, 0); - marray = 0; - array_size = request2size(n_elements * (sizeof(void*))); - } - - /* compute total element size */ - if (opts & 0x1) { /* all-same-size */ - element_size = request2size(*sizes); - contents_size = n_elements * element_size; - } - else { /* add up all the sizes */ - element_size = 0; - contents_size = 0; - for (i = 0; i != n_elements; ++i) - contents_size += request2size(sizes[i]); - } - - size = contents_size + array_size; - - /* - Allocate the aggregate chunk. First disable direct-mmapping so - malloc won't use it, since we would not be able to later - free/realloc space internal to a segregated mmap region. - */ - was_enabled = use_mmap(m); - disable_mmap(m); - mem = internal_malloc(m, size - CHUNK_OVERHEAD); - if (was_enabled) - enable_mmap(m); - if (mem == 0) - return 0; - - if (PREACTION(m)) return 0; - p = mem2chunk(mem); - remainder_size = chunksize(p); - - assert(!is_mmapped(p)); - - if (opts & 0x2) { /* optionally clear the elements */ - memset((size_t*)mem, 0, remainder_size - SIZE_T_SIZE - array_size); - } - - /* If not provided, allocate the pointer array as final part of chunk */ - if (marray == 0) { - size_t array_chunk_size; - array_chunk = chunk_plus_offset(p, contents_size); - array_chunk_size = remainder_size - contents_size; - marray = (void**) (chunk2mem(array_chunk)); - set_size_and_pinuse_of_inuse_chunk(m, array_chunk, array_chunk_size); - remainder_size = contents_size; - } - - /* split out elements */ - for (i = 0; ; ++i) { - marray[i] = chunk2mem(p); - if (i != n_elements-1) { - if (element_size != 0) - size = element_size; - else - size = request2size(sizes[i]); - remainder_size -= size; - set_size_and_pinuse_of_inuse_chunk(m, p, size); - p = chunk_plus_offset(p, size); - } - else { /* the final element absorbs any overallocation slop */ - set_size_and_pinuse_of_inuse_chunk(m, p, remainder_size); - break; - } - } - -#if DEBUG - if (marray != chunks) { - /* final element must have exactly exhausted chunk */ - if (element_size != 0) { - assert(remainder_size == element_size); - } - else { - assert(remainder_size == request2size(sizes[i])); - } - check_inuse_chunk(m, mem2chunk(marray)); - } - for (i = 0; i != n_elements; ++i) - check_inuse_chunk(m, mem2chunk(marray[i])); - -#endif /* DEBUG */ - - POSTACTION(m); - return marray; -} - - -/* -------------------------- public routines ---------------------------- */ - -#if !ONLY_MSPACES - -void* dlmalloc(size_t bytes) { - /* - Basic algorithm: - If a small request (< 256 bytes minus per-chunk overhead): - 1. If one exists, use a remainderless chunk in associated smallbin. - (Remainderless means that there are too few excess bytes to - represent as a chunk.) - 2. If it is big enough, use the dv chunk, which is normally the - chunk adjacent to the one used for the most recent small request. - 3. If one exists, split the smallest available chunk in a bin, - saving remainder in dv. - 4. If it is big enough, use the top chunk. - 5. If available, get memory from system and use it - Otherwise, for a large request: - 1. Find the smallest available binned chunk that fits, and use it - if it is better fitting than dv chunk, splitting if necessary. - 2. If better fitting than any binned chunk, use the dv chunk. - 3. If it is big enough, use the top chunk. - 4. If request size >= mmap threshold, try to directly mmap this chunk. - 5. If available, get memory from system and use it - - The ugly goto's here ensure that postaction occurs along all paths. - */ - - if (!PREACTION(gm)) { - void* mem; - size_t nb; - if (bytes <= MAX_SMALL_REQUEST) { - bindex_t idx; - binmap_t smallbits; - nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes); - idx = small_index(nb); - smallbits = gm->smallmap >> idx; - - if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */ - mchunkptr b, p; - idx += ~smallbits & 1; /* Uses next bin if idx empty */ - b = smallbin_at(gm, idx); - p = b->fd; - assert(chunksize(p) == small_index2size(idx)); - unlink_first_small_chunk(gm, b, p, idx); - set_inuse_and_pinuse(gm, p, small_index2size(idx)); - mem = chunk2mem(p); - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - - else if (nb > gm->dvsize) { - if (smallbits != 0) { /* Use chunk in next nonempty smallbin */ - mchunkptr b, p, r; - size_t rsize; - bindex_t i; - binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx)); - binmap_t leastbit = least_bit(leftbits); - compute_bit2idx(leastbit, i); - b = smallbin_at(gm, i); - p = b->fd; - assert(chunksize(p) == small_index2size(i)); - unlink_first_small_chunk(gm, b, p, i); - rsize = small_index2size(i) - nb; - /* Fit here cannot be remainderless if 4byte sizes */ - if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE) - set_inuse_and_pinuse(gm, p, small_index2size(i)); - else { - set_size_and_pinuse_of_inuse_chunk(gm, p, nb); - r = chunk_plus_offset(p, nb); - set_size_and_pinuse_of_free_chunk(r, rsize); - replace_dv(gm, r, rsize); - } - mem = chunk2mem(p); - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - - else if (gm->treemap != 0 && (mem = tmalloc_small(gm, nb)) != 0) { - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - } - } - else if (bytes >= MAX_REQUEST) - nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */ - else { - nb = pad_request(bytes); - if (gm->treemap != 0 && (mem = tmalloc_large(gm, nb)) != 0) { - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - } - - if (nb <= gm->dvsize) { - size_t rsize = gm->dvsize - nb; - mchunkptr p = gm->dv; - if (rsize >= MIN_CHUNK_SIZE) { /* split dv */ - mchunkptr r = gm->dv = chunk_plus_offset(p, nb); - gm->dvsize = rsize; - set_size_and_pinuse_of_free_chunk(r, rsize); - set_size_and_pinuse_of_inuse_chunk(gm, p, nb); - } - else { /* exhaust dv */ - size_t dvs = gm->dvsize; - gm->dvsize = 0; - gm->dv = 0; - set_inuse_and_pinuse(gm, p, dvs); - } - mem = chunk2mem(p); - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - - else if (nb < gm->topsize) { /* Split top */ - size_t rsize = gm->topsize -= nb; - mchunkptr p = gm->top; - mchunkptr r = gm->top = chunk_plus_offset(p, nb); - r->head = rsize | PINUSE_BIT; - set_size_and_pinuse_of_inuse_chunk(gm, p, nb); - mem = chunk2mem(p); - check_top_chunk(gm, gm->top); - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - - mem = sys_alloc(gm, nb); - - postaction: - POSTACTION(gm); - return mem; - } - - return 0; -} - -void dlfree(void* mem) { - /* - Consolidate freed chunks with preceeding or succeeding bordering - free chunks, if they exist, and then place in a bin. Intermixed - with special cases for top, dv, mmapped chunks, and usage errors. - */ - - if (mem != 0) { - mchunkptr p = mem2chunk(mem); -#if FOOTERS - mstate fm = get_mstate_for(p); - if (!ok_magic(fm)) { - USAGE_ERROR_ACTION(fm, p); - return; - } -#else /* FOOTERS */ -#define fm gm -#endif /* FOOTERS */ - if (!PREACTION(fm)) { - check_inuse_chunk(fm, p); - if (RTCHECK(ok_address(fm, p) && ok_cinuse(p))) { - size_t psize = chunksize(p); - mchunkptr next = chunk_plus_offset(p, psize); - if (!pinuse(p)) { - size_t prevsize = p->prev_foot; - if ((prevsize & IS_MMAPPED_BIT) != 0) { - prevsize &= ~IS_MMAPPED_BIT; - psize += prevsize + MMAP_FOOT_PAD; - if (CALL_MUNMAP((char*)p - prevsize, psize) == 0) - fm->footprint -= psize; - goto postaction; - } - else { - mchunkptr prev = chunk_minus_offset(p, prevsize); - psize += prevsize; - p = prev; - if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */ - if (p != fm->dv) { - unlink_chunk(fm, p, prevsize); - } - else if ((next->head & INUSE_BITS) == INUSE_BITS) { - fm->dvsize = psize; - set_free_with_pinuse(p, psize, next); - goto postaction; - } - } - else - goto erroraction; - } - } - - if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) { - if (!cinuse(next)) { /* consolidate forward */ - if (next == fm->top) { - size_t tsize = fm->topsize += psize; - fm->top = p; - p->head = tsize | PINUSE_BIT; - if (p == fm->dv) { - fm->dv = 0; - fm->dvsize = 0; - } - if (should_trim(fm, tsize)) - sys_trim(fm, 0); - goto postaction; - } - else if (next == fm->dv) { - size_t dsize = fm->dvsize += psize; - fm->dv = p; - set_size_and_pinuse_of_free_chunk(p, dsize); - goto postaction; - } - else { - size_t nsize = chunksize(next); - psize += nsize; - unlink_chunk(fm, next, nsize); - set_size_and_pinuse_of_free_chunk(p, psize); - if (p == fm->dv) { - fm->dvsize = psize; - goto postaction; - } - } - } - else - set_free_with_pinuse(p, psize, next); - insert_chunk(fm, p, psize); - check_free_chunk(fm, p); - goto postaction; - } - } - erroraction: - USAGE_ERROR_ACTION(fm, p); - postaction: - POSTACTION(fm); - } - } -#if !FOOTERS -#undef fm -#endif /* FOOTERS */ -} - -void* dlcalloc(size_t n_elements, size_t elem_size) { - void *mem; - if (n_elements && MAX_SIZE_T / n_elements < elem_size) { - /* Fail on overflow */ - MALLOC_FAILURE_ACTION; - return NULL; - } - elem_size *= n_elements; - mem = dlmalloc(elem_size); - if (mem && calloc_must_clear(mem2chunk(mem))) - memset(mem, 0, elem_size); - return mem; -} - -void* dlrealloc(void* oldmem, size_t bytes) { - if (oldmem == 0) - return dlmalloc(bytes); -#ifdef REALLOC_ZERO_BYTES_FREES - if (bytes == 0) { - dlfree(oldmem); - return 0; - } -#endif /* REALLOC_ZERO_BYTES_FREES */ - else { -#if ! FOOTERS - mstate m = gm; -#else /* FOOTERS */ - mstate m = get_mstate_for(mem2chunk(oldmem)); - if (!ok_magic(m)) { - USAGE_ERROR_ACTION(m, oldmem); - return 0; - } -#endif /* FOOTERS */ - return internal_realloc(m, oldmem, bytes); - } -} - -void* dlmemalign(size_t alignment, size_t bytes) { - return internal_memalign(gm, alignment, bytes); -} - -void** dlindependent_calloc(size_t n_elements, size_t elem_size, - void* chunks[]) { - size_t sz = elem_size; /* serves as 1-element array */ - return ialloc(gm, n_elements, &sz, 3, chunks); -} - -void** dlindependent_comalloc(size_t n_elements, size_t sizes[], - void* chunks[]) { - return ialloc(gm, n_elements, sizes, 0, chunks); -} - -void* dlvalloc(size_t bytes) { - size_t pagesz; - init_mparams(); - pagesz = mparams.page_size; - return dlmemalign(pagesz, bytes); -} - -void* dlpvalloc(size_t bytes) { - size_t pagesz; - init_mparams(); - pagesz = mparams.page_size; - return dlmemalign(pagesz, (bytes + pagesz - SIZE_T_ONE) & ~(pagesz - SIZE_T_ONE)); -} - -int dlmalloc_trim(size_t pad) { - int result = 0; - if (!PREACTION(gm)) { - result = sys_trim(gm, pad); - POSTACTION(gm); - } - return result; -} - -size_t dlmalloc_footprint(void) { - return gm->footprint; -} - -#if USE_MAX_ALLOWED_FOOTPRINT -size_t dlmalloc_max_allowed_footprint(void) { - return gm->max_allowed_footprint; -} - -void dlmalloc_set_max_allowed_footprint(size_t bytes) { - if (bytes > gm->footprint) { - /* Increase the size in multiples of the granularity, - * which is the smallest unit we request from the system. - */ - gm->max_allowed_footprint = gm->footprint + - granularity_align(bytes - gm->footprint); - } - else { - //TODO: allow for reducing the max footprint - gm->max_allowed_footprint = gm->footprint; - } -} -#endif - -size_t dlmalloc_max_footprint(void) { - return gm->max_footprint; -} - -#if !NO_MALLINFO -struct mallinfo dlmallinfo(void) { - return internal_mallinfo(gm); -} -#endif /* NO_MALLINFO */ - -void dlmalloc_stats() { - internal_malloc_stats(gm); -} - -size_t dlmalloc_usable_size(void* mem) { - if (mem != 0) { - mchunkptr p = mem2chunk(mem); - if (cinuse(p)) - return chunksize(p) - overhead_for(p); - } - return 0; -} - -int dlmallopt(int param_number, int value) { - return change_mparam(param_number, value); -} - -#endif /* !ONLY_MSPACES */ - -/* ----------------------------- user mspaces ---------------------------- */ - -#if MSPACES - -static mstate init_user_mstate(char* tbase, size_t tsize) { - size_t msize = pad_request(sizeof(struct malloc_state)); - mchunkptr mn; - mchunkptr msp = align_as_chunk(tbase); - mstate m = (mstate)(chunk2mem(msp)); - memset(m, 0, msize); - INITIAL_LOCK(&m->mutex); - msp->head = (msize|PINUSE_BIT|CINUSE_BIT); - m->seg.base = m->least_addr = tbase; - m->seg.size = m->footprint = m->max_footprint = tsize; -#if USE_MAX_ALLOWED_FOOTPRINT - m->max_allowed_footprint = MAX_SIZE_T; -#endif - m->magic = mparams.magic; - m->mflags = mparams.default_mflags; - disable_contiguous(m); - init_bins(m); - mn = next_chunk(mem2chunk(m)); - init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) - TOP_FOOT_SIZE); - check_top_chunk(m, m->top); - return m; -} - -mspace create_mspace(size_t capacity, int locked) { - mstate m = 0; - size_t msize = pad_request(sizeof(struct malloc_state)); - init_mparams(); /* Ensure pagesize etc initialized */ - - if (capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) { - size_t rs = ((capacity == 0)? mparams.granularity : - (capacity + TOP_FOOT_SIZE + msize)); - size_t tsize = granularity_align(rs); - char* tbase = (char*)(CALL_MMAP(tsize)); - if (tbase != CMFAIL) { - m = init_user_mstate(tbase, tsize); - m->seg.sflags = IS_MMAPPED_BIT; - set_lock(m, locked); - } - } - return (mspace)m; -} - -mspace create_mspace_with_base(void* base, size_t capacity, int locked) { - mstate m = 0; - size_t msize = pad_request(sizeof(struct malloc_state)); - init_mparams(); /* Ensure pagesize etc initialized */ - - if (capacity > msize + TOP_FOOT_SIZE && - capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) { - m = init_user_mstate((char*)base, capacity); - m->seg.sflags = EXTERN_BIT; - set_lock(m, locked); - } - return (mspace)m; -} - -size_t destroy_mspace(mspace msp) { - size_t freed = 0; - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - msegmentptr sp = &ms->seg; - while (sp != 0) { -#if HAVE_MMAP && HAVE_MREMAP - char* base = sp->base; -#endif - size_t size = sp->size; - flag_t flag = sp->sflags; - sp = sp->next; - if ((flag & IS_MMAPPED_BIT) && !(flag & EXTERN_BIT) && - CALL_MUNMAP(base, size) == 0) - freed += size; - } - } - else { - USAGE_ERROR_ACTION(ms,ms); - } - return freed; -} - -/* - mspace versions of routines are near-clones of the global - versions. This is not so nice but better than the alternatives. -*/ - - -void* mspace_malloc(mspace msp, size_t bytes) { - mstate ms = (mstate)msp; - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - return 0; - } - if (!PREACTION(ms)) { - void* mem; - size_t nb; - if (bytes <= MAX_SMALL_REQUEST) { - bindex_t idx; - binmap_t smallbits; - nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes); - idx = small_index(nb); - smallbits = ms->smallmap >> idx; - - if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */ - mchunkptr b, p; - idx += ~smallbits & 1; /* Uses next bin if idx empty */ - b = smallbin_at(ms, idx); - p = b->fd; - assert(chunksize(p) == small_index2size(idx)); - unlink_first_small_chunk(ms, b, p, idx); - set_inuse_and_pinuse(ms, p, small_index2size(idx)); - mem = chunk2mem(p); - check_malloced_chunk(ms, mem, nb); - goto postaction; - } - - else if (nb > ms->dvsize) { - if (smallbits != 0) { /* Use chunk in next nonempty smallbin */ - mchunkptr b, p, r; - size_t rsize; - bindex_t i; - binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx)); - binmap_t leastbit = least_bit(leftbits); - compute_bit2idx(leastbit, i); - b = smallbin_at(ms, i); - p = b->fd; - assert(chunksize(p) == small_index2size(i)); - unlink_first_small_chunk(ms, b, p, i); - rsize = small_index2size(i) - nb; - /* Fit here cannot be remainderless if 4byte sizes */ - if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE) - set_inuse_and_pinuse(ms, p, small_index2size(i)); - else { - set_size_and_pinuse_of_inuse_chunk(ms, p, nb); - r = chunk_plus_offset(p, nb); - set_size_and_pinuse_of_free_chunk(r, rsize); - replace_dv(ms, r, rsize); - } - mem = chunk2mem(p); - check_malloced_chunk(ms, mem, nb); - goto postaction; - } - - else if (ms->treemap != 0 && (mem = tmalloc_small(ms, nb)) != 0) { - check_malloced_chunk(ms, mem, nb); - goto postaction; - } - } - } - else if (bytes >= MAX_REQUEST) - nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */ - else { - nb = pad_request(bytes); - if (ms->treemap != 0 && (mem = tmalloc_large(ms, nb)) != 0) { - check_malloced_chunk(ms, mem, nb); - goto postaction; - } - } - - if (nb <= ms->dvsize) { - size_t rsize = ms->dvsize - nb; - mchunkptr p = ms->dv; - if (rsize >= MIN_CHUNK_SIZE) { /* split dv */ - mchunkptr r = ms->dv = chunk_plus_offset(p, nb); - ms->dvsize = rsize; - set_size_and_pinuse_of_free_chunk(r, rsize); - set_size_and_pinuse_of_inuse_chunk(ms, p, nb); - } - else { /* exhaust dv */ - size_t dvs = ms->dvsize; - ms->dvsize = 0; - ms->dv = 0; - set_inuse_and_pinuse(ms, p, dvs); - } - mem = chunk2mem(p); - check_malloced_chunk(ms, mem, nb); - goto postaction; - } - - else if (nb < ms->topsize) { /* Split top */ - size_t rsize = ms->topsize -= nb; - mchunkptr p = ms->top; - mchunkptr r = ms->top = chunk_plus_offset(p, nb); - r->head = rsize | PINUSE_BIT; - set_size_and_pinuse_of_inuse_chunk(ms, p, nb); - mem = chunk2mem(p); - check_top_chunk(ms, ms->top); - check_malloced_chunk(ms, mem, nb); - goto postaction; - } - - mem = sys_alloc(ms, nb); - - postaction: - POSTACTION(ms); - return mem; - } - - return 0; -} - -void mspace_free(mspace msp, void* mem) { - if (mem != 0) { - mchunkptr p = mem2chunk(mem); -#if FOOTERS - mstate fm = get_mstate_for(p); -#else /* FOOTERS */ - mstate fm = (mstate)msp; -#endif /* FOOTERS */ - if (!ok_magic(fm)) { - USAGE_ERROR_ACTION(fm, p); - return; - } - if (!PREACTION(fm)) { - check_inuse_chunk(fm, p); - if (RTCHECK(ok_address(fm, p) && ok_cinuse(p))) { - size_t psize = chunksize(p); - mchunkptr next = chunk_plus_offset(p, psize); - if (!pinuse(p)) { - size_t prevsize = p->prev_foot; - if ((prevsize & IS_MMAPPED_BIT) != 0) { - prevsize &= ~IS_MMAPPED_BIT; - psize += prevsize + MMAP_FOOT_PAD; - if (CALL_MUNMAP((char*)p - prevsize, psize) == 0) - fm->footprint -= psize; - goto postaction; - } - else { - mchunkptr prev = chunk_minus_offset(p, prevsize); - psize += prevsize; - p = prev; - if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */ - if (p != fm->dv) { - unlink_chunk(fm, p, prevsize); - } - else if ((next->head & INUSE_BITS) == INUSE_BITS) { - fm->dvsize = psize; - set_free_with_pinuse(p, psize, next); - goto postaction; - } - } - else - goto erroraction; - } - } - - if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) { - if (!cinuse(next)) { /* consolidate forward */ - if (next == fm->top) { - size_t tsize = fm->topsize += psize; - fm->top = p; - p->head = tsize | PINUSE_BIT; - if (p == fm->dv) { - fm->dv = 0; - fm->dvsize = 0; - } - if (should_trim(fm, tsize)) - sys_trim(fm, 0); - goto postaction; - } - else if (next == fm->dv) { - size_t dsize = fm->dvsize += psize; - fm->dv = p; - set_size_and_pinuse_of_free_chunk(p, dsize); - goto postaction; - } - else { - size_t nsize = chunksize(next); - psize += nsize; - unlink_chunk(fm, next, nsize); - set_size_and_pinuse_of_free_chunk(p, psize); - if (p == fm->dv) { - fm->dvsize = psize; - goto postaction; - } - } - } - else - set_free_with_pinuse(p, psize, next); - insert_chunk(fm, p, psize); - check_free_chunk(fm, p); - goto postaction; - } - } - erroraction: - USAGE_ERROR_ACTION(fm, p); - postaction: - POSTACTION(fm); - } - } -} - -void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size) { - void *mem; - mstate ms = (mstate)msp; - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - return 0; - } - if (n_elements && MAX_SIZE_T / n_elements < elem_size) { - /* Fail on overflow */ - MALLOC_FAILURE_ACTION; - return NULL; - } - elem_size *= n_elements; - mem = internal_malloc(ms, elem_size); - if (mem && calloc_must_clear(mem2chunk(mem))) - memset(mem, 0, elem_size); - return mem; -} - -void* mspace_realloc(mspace msp, void* oldmem, size_t bytes) { - if (oldmem == 0) - return mspace_malloc(msp, bytes); -#ifdef REALLOC_ZERO_BYTES_FREES - if (bytes == 0) { - mspace_free(msp, oldmem); - return 0; - } -#endif /* REALLOC_ZERO_BYTES_FREES */ - else { -#if FOOTERS - mchunkptr p = mem2chunk(oldmem); - mstate ms = get_mstate_for(p); -#else /* FOOTERS */ - mstate ms = (mstate)msp; -#endif /* FOOTERS */ - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - return 0; - } - return internal_realloc(ms, oldmem, bytes); - } -} - -#if ANDROID -void* mspace_merge_objects(mspace msp, void* mema, void* memb) -{ - /* PREACTION/POSTACTION aren't necessary because we are only - modifying fields of inuse chunks owned by the current thread, in - which case no other malloc operations can touch them. - */ - if (mema == NULL || memb == NULL) { - return NULL; - } - mchunkptr pa = mem2chunk(mema); - mchunkptr pb = mem2chunk(memb); - -#if FOOTERS - mstate fm = get_mstate_for(pa); -#else /* FOOTERS */ - mstate fm = (mstate)msp; -#endif /* FOOTERS */ - if (!ok_magic(fm)) { - USAGE_ERROR_ACTION(fm, pa); - return NULL; - } - check_inuse_chunk(fm, pa); - if (RTCHECK(ok_address(fm, pa) && ok_cinuse(pa))) { - if (next_chunk(pa) != pb) { - /* Since pb may not be in fm, we can't check ok_address(fm, pb); - since ok_cinuse(pb) would be unsafe before an address check, - return NULL rather than invoke USAGE_ERROR_ACTION if pb is not - in use or is a bogus address. - */ - return NULL; - } - /* Since b follows a, they share the mspace. */ -#if FOOTERS - assert(fm == get_mstate_for(pb)); -#endif /* FOOTERS */ - check_inuse_chunk(fm, pb); - if (RTCHECK(ok_address(fm, pb) && ok_cinuse(pb))) { - size_t sz = chunksize(pb); - pa->head += sz; - /* Make sure pa still passes. */ - check_inuse_chunk(fm, pa); - return mema; - } - else { - USAGE_ERROR_ACTION(fm, pb); - return NULL; - } - } - else { - USAGE_ERROR_ACTION(fm, pa); - return NULL; - } -} -#endif /* ANDROID */ - -void* mspace_memalign(mspace msp, size_t alignment, size_t bytes) { - mstate ms = (mstate)msp; - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - return 0; - } - return internal_memalign(ms, alignment, bytes); -} - -void** mspace_independent_calloc(mspace msp, size_t n_elements, - size_t elem_size, void* chunks[]) { - size_t sz = elem_size; /* serves as 1-element array */ - mstate ms = (mstate)msp; - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - return 0; - } - return ialloc(ms, n_elements, &sz, 3, chunks); -} - -void** mspace_independent_comalloc(mspace msp, size_t n_elements, - size_t sizes[], void* chunks[]) { - mstate ms = (mstate)msp; - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - return 0; - } - return ialloc(ms, n_elements, sizes, 0, chunks); -} - -int mspace_trim(mspace msp, size_t pad) { - int result = 0; - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - if (!PREACTION(ms)) { - result = sys_trim(ms, pad); - POSTACTION(ms); - } - } - else { - USAGE_ERROR_ACTION(ms,ms); - } - return result; -} - -void mspace_malloc_stats(mspace msp) { - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - internal_malloc_stats(ms); - } - else { - USAGE_ERROR_ACTION(ms,ms); - } -} - -size_t mspace_footprint(mspace msp) { - size_t result; - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - result = ms->footprint; - } - else { - USAGE_ERROR_ACTION(ms,ms); - } - return result; -} - -#if USE_MAX_ALLOWED_FOOTPRINT -size_t mspace_max_allowed_footprint(mspace msp) { - size_t result; - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - result = ms->max_allowed_footprint; - } - else { - USAGE_ERROR_ACTION(ms,ms); - } - return result; -} - -void mspace_set_max_allowed_footprint(mspace msp, size_t bytes) { - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - if (bytes > ms->footprint) { - /* Increase the size in multiples of the granularity, - * which is the smallest unit we request from the system. - */ - ms->max_allowed_footprint = ms->footprint + - granularity_align(bytes - ms->footprint); - } - else { - //TODO: allow for reducing the max footprint - ms->max_allowed_footprint = ms->footprint; - } - } - else { - USAGE_ERROR_ACTION(ms,ms); - } -} -#endif - -size_t mspace_max_footprint(mspace msp) { - size_t result; - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - result = ms->max_footprint; - } - else { - USAGE_ERROR_ACTION(ms,ms); - } - return result; -} - - -#if !NO_MALLINFO -struct mallinfo mspace_mallinfo(mspace msp) { - mstate ms = (mstate)msp; - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - } - return internal_mallinfo(ms); -} -#endif /* NO_MALLINFO */ - -int mspace_mallopt(int param_number, int value) { - return change_mparam(param_number, value); -} - -#endif /* MSPACES */ - -#if MSPACES && ONLY_MSPACES -void mspace_walk_free_pages(mspace msp, - void(*handler)(void *start, void *end, void *arg), void *harg) -{ - mstate m = (mstate)msp; - if (!ok_magic(m)) { - USAGE_ERROR_ACTION(m,m); - return; - } -#else -void dlmalloc_walk_free_pages(void(*handler)(void *start, void *end, void *arg), - void *harg) -{ - mstate m = (mstate)gm; -#endif - if (!PREACTION(m)) { - if (is_initialized(m)) { - msegmentptr s = &m->seg; - while (s != 0) { - mchunkptr p = align_as_chunk(s->base); - while (segment_holds(s, p) && - p != m->top && p->head != FENCEPOST_HEAD) { - void *chunkptr; - size_t chunklen; - chunkptr = p; - chunklen = chunksize(p); - if (!cinuse(p)) { - void *start; - if (is_small(chunklen)) { - start = (void *)(p + 1); - } - else { - start = (void *)((tchunkptr)p + 1); - } - handler(start, next_chunk(p), harg); - } - p = next_chunk(p); - } - if (p == m->top) { - handler((void *)(p + 1), next_chunk(p), harg); - } - s = s->next; - } - } - POSTACTION(m); - } -} - - -#if MSPACES && ONLY_MSPACES -void mspace_walk_heap(mspace msp, - void(*handler)(const void *chunkptr, size_t chunklen, - const void *userptr, size_t userlen, - void *arg), - void *harg) -{ - msegmentptr s; - mstate m = (mstate)msp; - if (!ok_magic(m)) { - USAGE_ERROR_ACTION(m,m); - return; - } -#else -void dlmalloc_walk_heap(void(*handler)(const void *chunkptr, size_t chunklen, - const void *userptr, size_t userlen, - void *arg), - void *harg) -{ - msegmentptr s; - mstate m = (mstate)gm; -#endif - - s = &m->seg; - while (s != 0) { - mchunkptr p = align_as_chunk(s->base); - while (segment_holds(s, p) && - p != m->top && p->head != FENCEPOST_HEAD) { - void *chunkptr, *userptr; - size_t chunklen, userlen; - chunkptr = p; - chunklen = chunksize(p); - if (cinuse(p)) { - userptr = chunk2mem(p); - userlen = chunklen - overhead_for(p); - } - else { - userptr = NULL; - userlen = 0; - } - handler(chunkptr, chunklen, userptr, userlen, harg); - p = next_chunk(p); - } - if (p == m->top) { - /* The top chunk is just a big free chunk for our purposes. - */ - handler(m->top, m->topsize, NULL, 0, harg); - } - s = s->next; - } -} - -/* -------------------- Alternative MORECORE functions ------------------- */ - -/* - Guidelines for creating a custom version of MORECORE: - - * For best performance, MORECORE should allocate in multiples of pagesize. - * MORECORE may allocate more memory than requested. (Or even less, - but this will usually result in a malloc failure.) - * MORECORE must not allocate memory when given argument zero, but - instead return one past the end address of memory from previous - nonzero call. - * For best performance, consecutive calls to MORECORE with positive - arguments should return increasing addresses, indicating that - space has been contiguously extended. - * Even though consecutive calls to MORECORE need not return contiguous - addresses, it must be OK for malloc'ed chunks to span multiple - regions in those cases where they do happen to be contiguous. - * MORECORE need not handle negative arguments -- it may instead - just return MFAIL when given negative arguments. - Negative arguments are always multiples of pagesize. MORECORE - must not misinterpret negative args as large positive unsigned - args. You can suppress all such calls from even occurring by defining - MORECORE_CANNOT_TRIM, - - As an example alternative MORECORE, here is a custom allocator - kindly contributed for pre-OSX macOS. It uses virtually but not - necessarily physically contiguous non-paged memory (locked in, - present and won't get swapped out). You can use it by uncommenting - this section, adding some #includes, and setting up the appropriate - defines above: - - #define MORECORE osMoreCore - - There is also a shutdown routine that should somehow be called for - cleanup upon program exit. - - #define MAX_POOL_ENTRIES 100 - #define MINIMUM_MORECORE_SIZE (64 * 1024U) - static int next_os_pool; - void *our_os_pools[MAX_POOL_ENTRIES]; - - void *osMoreCore(int size) - { - void *ptr = 0; - static void *sbrk_top = 0; - - if (size > 0) - { - if (size < MINIMUM_MORECORE_SIZE) - size = MINIMUM_MORECORE_SIZE; - if (CurrentExecutionLevel() == kTaskLevel) - ptr = PoolAllocateResident(size + RM_PAGE_SIZE, 0); - if (ptr == 0) - { - return (void *) MFAIL; - } - // save ptrs so they can be freed during cleanup - our_os_pools[next_os_pool] = ptr; - next_os_pool++; - ptr = (void *) ((((size_t) ptr) + RM_PAGE_MASK) & ~RM_PAGE_MASK); - sbrk_top = (char *) ptr + size; - return ptr; - } - else if (size < 0) - { - // we don't currently support shrink behavior - return (void *) MFAIL; - } - else - { - return sbrk_top; - } - } - - // cleanup any allocated memory pools - // called as last thing before shutting down driver - - void osCleanupMem(void) - { - void **ptr; - - for (ptr = our_os_pools; ptr < &our_os_pools[MAX_POOL_ENTRIES]; ptr++) - if (*ptr) - { - PoolDeallocate(*ptr); - *ptr = 0; - } - } - -*/ - - -/* ----------------------------------------------------------------------- -History: - V2.8.3 Thu Sep 22 11:16:32 2005 Doug Lea (dl at gee) - * Add max_footprint functions - * Ensure all appropriate literals are size_t - * Fix conditional compilation problem for some #define settings - * Avoid concatenating segments with the one provided - in create_mspace_with_base - * Rename some variables to avoid compiler shadowing warnings - * Use explicit lock initialization. - * Better handling of sbrk interference. - * Simplify and fix segment insertion, trimming and mspace_destroy - * Reinstate REALLOC_ZERO_BYTES_FREES option from 2.7.x - * Thanks especially to Dennis Flanagan for help on these. - - V2.8.2 Sun Jun 12 16:01:10 2005 Doug Lea (dl at gee) - * Fix memalign brace error. - - V2.8.1 Wed Jun 8 16:11:46 2005 Doug Lea (dl at gee) - * Fix improper #endif nesting in C++ - * Add explicit casts needed for C++ - - V2.8.0 Mon May 30 14:09:02 2005 Doug Lea (dl at gee) - * Use trees for large bins - * Support mspaces - * Use segments to unify sbrk-based and mmap-based system allocation, - removing need for emulation on most platforms without sbrk. - * Default safety checks - * Optional footer checks. Thanks to William Robertson for the idea. - * Internal code refactoring - * Incorporate suggestions and platform-specific changes. - Thanks to Dennis Flanagan, Colin Plumb, Niall Douglas, - Aaron Bachmann, Emery Berger, and others. - * Speed up non-fastbin processing enough to remove fastbins. - * Remove useless cfree() to avoid conflicts with other apps. - * Remove internal memcpy, memset. Compilers handle builtins better. - * Remove some options that no one ever used and rename others. - - V2.7.2 Sat Aug 17 09:07:30 2002 Doug Lea (dl at gee) - * Fix malloc_state bitmap array misdeclaration - - V2.7.1 Thu Jul 25 10:58:03 2002 Doug Lea (dl at gee) - * Allow tuning of FIRST_SORTED_BIN_SIZE - * Use PTR_UINT as type for all ptr->int casts. Thanks to John Belmonte. - * Better detection and support for non-contiguousness of MORECORE. - Thanks to Andreas Mueller, Conal Walsh, and Wolfram Gloger - * Bypass most of malloc if no frees. Thanks To Emery Berger. - * Fix freeing of old top non-contiguous chunk im sysmalloc. - * Raised default trim and map thresholds to 256K. - * Fix mmap-related #defines. Thanks to Lubos Lunak. - * Fix copy macros; added LACKS_FCNTL_H. Thanks to Neal Walfield. - * Branch-free bin calculation - * Default trim and mmap thresholds now 256K. - - V2.7.0 Sun Mar 11 14:14:06 2001 Doug Lea (dl at gee) - * Introduce independent_comalloc and independent_calloc. - Thanks to Michael Pachos for motivation and help. - * Make optional .h file available - * Allow > 2GB requests on 32bit systems. - * new WIN32 sbrk, mmap, munmap, lock code from <Walter@GeNeSys-e.de>. - Thanks also to Andreas Mueller <a.mueller at paradatec.de>, - and Anonymous. - * Allow override of MALLOC_ALIGNMENT (Thanks to Ruud Waij for - helping test this.) - * memalign: check alignment arg - * realloc: don't try to shift chunks backwards, since this - leads to more fragmentation in some programs and doesn't - seem to help in any others. - * Collect all cases in malloc requiring system memory into sysmalloc - * Use mmap as backup to sbrk - * Place all internal state in malloc_state - * Introduce fastbins (although similar to 2.5.1) - * Many minor tunings and cosmetic improvements - * Introduce USE_PUBLIC_MALLOC_WRAPPERS, USE_MALLOC_LOCK - * Introduce MALLOC_FAILURE_ACTION, MORECORE_CONTIGUOUS - Thanks to Tony E. Bennett <tbennett@nvidia.com> and others. - * Include errno.h to support default failure action. - - V2.6.6 Sun Dec 5 07:42:19 1999 Doug Lea (dl at gee) - * return null for negative arguments - * Added Several WIN32 cleanups from Martin C. Fong <mcfong at yahoo.com> - * Add 'LACKS_SYS_PARAM_H' for those systems without 'sys/param.h' - (e.g. WIN32 platforms) - * Cleanup header file inclusion for WIN32 platforms - * Cleanup code to avoid Microsoft Visual C++ compiler complaints - * Add 'USE_DL_PREFIX' to quickly allow co-existence with existing - memory allocation routines - * Set 'malloc_getpagesize' for WIN32 platforms (needs more work) - * Use 'assert' rather than 'ASSERT' in WIN32 code to conform to - usage of 'assert' in non-WIN32 code - * Improve WIN32 'sbrk()' emulation's 'findRegion()' routine to - avoid infinite loop - * Always call 'fREe()' rather than 'free()' - - V2.6.5 Wed Jun 17 15:57:31 1998 Doug Lea (dl at gee) - * Fixed ordering problem with boundary-stamping - - V2.6.3 Sun May 19 08:17:58 1996 Doug Lea (dl at gee) - * Added pvalloc, as recommended by H.J. Liu - * Added 64bit pointer support mainly from Wolfram Gloger - * Added anonymously donated WIN32 sbrk emulation - * Malloc, calloc, getpagesize: add optimizations from Raymond Nijssen - * malloc_extend_top: fix mask error that caused wastage after - foreign sbrks - * Add linux mremap support code from HJ Liu - - V2.6.2 Tue Dec 5 06:52:55 1995 Doug Lea (dl at gee) - * Integrated most documentation with the code. - * Add support for mmap, with help from - Wolfram Gloger (Gloger@lrz.uni-muenchen.de). - * Use last_remainder in more cases. - * Pack bins using idea from colin@nyx10.cs.du.edu - * Use ordered bins instead of best-fit threshhold - * Eliminate block-local decls to simplify tracing and debugging. - * Support another case of realloc via move into top - * Fix error occuring when initial sbrk_base not word-aligned. - * Rely on page size for units instead of SBRK_UNIT to - avoid surprises about sbrk alignment conventions. - * Add mallinfo, mallopt. Thanks to Raymond Nijssen - (raymond@es.ele.tue.nl) for the suggestion. - * Add `pad' argument to malloc_trim and top_pad mallopt parameter. - * More precautions for cases where other routines call sbrk, - courtesy of Wolfram Gloger (Gloger@lrz.uni-muenchen.de). - * Added macros etc., allowing use in linux libc from - H.J. Lu (hjl@gnu.ai.mit.edu) - * Inverted this history list - - V2.6.1 Sat Dec 2 14:10:57 1995 Doug Lea (dl at gee) - * Re-tuned and fixed to behave more nicely with V2.6.0 changes. - * Removed all preallocation code since under current scheme - the work required to undo bad preallocations exceeds - the work saved in good cases for most test programs. - * No longer use return list or unconsolidated bins since - no scheme using them consistently outperforms those that don't - given above changes. - * Use best fit for very large chunks to prevent some worst-cases. - * Added some support for debugging - - V2.6.0 Sat Nov 4 07:05:23 1995 Doug Lea (dl at gee) - * Removed footers when chunks are in use. Thanks to - Paul Wilson (wilson@cs.texas.edu) for the suggestion. - - V2.5.4 Wed Nov 1 07:54:51 1995 Doug Lea (dl at gee) - * Added malloc_trim, with help from Wolfram Gloger - (wmglo@Dent.MED.Uni-Muenchen.DE). - - V2.5.3 Tue Apr 26 10:16:01 1994 Doug Lea (dl at g) - - V2.5.2 Tue Apr 5 16:20:40 1994 Doug Lea (dl at g) - * realloc: try to expand in both directions - * malloc: swap order of clean-bin strategy; - * realloc: only conditionally expand backwards - * Try not to scavenge used bins - * Use bin counts as a guide to preallocation - * Occasionally bin return list chunks in first scan - * Add a few optimizations from colin@nyx10.cs.du.edu - - V2.5.1 Sat Aug 14 15:40:43 1993 Doug Lea (dl at g) - * faster bin computation & slightly different binning - * merged all consolidations to one part of malloc proper - (eliminating old malloc_find_space & malloc_clean_bin) - * Scan 2 returns chunks (not just 1) - * Propagate failure in realloc if malloc returns 0 - * Add stuff to allow compilation on non-ANSI compilers - from kpv@research.att.com - - V2.5 Sat Aug 7 07:41:59 1993 Doug Lea (dl at g.oswego.edu) - * removed potential for odd address access in prev_chunk - * removed dependency on getpagesize.h - * misc cosmetics and a bit more internal documentation - * anticosmetics: mangled names in macros to evade debugger strangeness - * tested on sparc, hp-700, dec-mips, rs6000 - with gcc & native cc (hp, dec only) allowing - Detlefs & Zorn comparison study (in SIGPLAN Notices.) - - Trial version Fri Aug 28 13:14:29 1992 Doug Lea (dl at g.oswego.edu) - * Based loosely on libg++-1.2X malloc. (It retains some of the overall - structure of old version, but most details differ.) - -*/ +// Ugly inclusion of C file so that ART specific #defines configure dlmalloc +#include "dlmalloc/malloc.c" diff --git a/src/dlmalloc.h b/src/dlmalloc.h index 1b642d2896..892e930b0d 100644 --- a/src/dlmalloc.h +++ b/src/dlmalloc.h @@ -1,655 +1,20 @@ -/* - Default header file for malloc-2.8.x, written by Doug Lea - and released to the public domain, as explained at - http://creativecommons.org/licenses/publicdomain. - - last update: Mon Aug 15 08:55:52 2005 Doug Lea (dl at gee) - - This header is for ANSI C/C++ only. You can set any of - the following #defines before including: - - * If USE_DL_PREFIX is defined, it is assumed that malloc.c - was also compiled with this option, so all routines - have names starting with "dl". - - * If HAVE_USR_INCLUDE_MALLOC_H is defined, it is assumed that this - file will be #included AFTER <malloc.h>. This is needed only if - your system defines a struct mallinfo that is incompatible with the - standard one declared here. Otherwise, you can include this file - INSTEAD of your system system <malloc.h>. At least on ANSI, all - declarations should be compatible with system versions - - * If MSPACES is defined, declarations for mspace versions are included. -*/ - -#ifndef MALLOC_280_H -#define MALLOC_280_H - -#ifdef __cplusplus -extern "C" { -#endif - -#include <stddef.h> /* for size_t */ - -#if !ONLY_MSPACES - -/* Check an additional macro for the five primary functions */ -#if !defined(USE_DL_PREFIX) -#define dlcalloc calloc -#define dlfree free -#define dlmalloc malloc -#define dlmemalign memalign -#define dlrealloc realloc -#endif - -#ifndef USE_DL_PREFIX -#define dlvalloc valloc -#define dlpvalloc pvalloc -#define dlmallinfo mallinfo -#define dlmallopt mallopt -#define dlmalloc_trim malloc_trim -#define dlmalloc_walk_free_pages \ - malloc_walk_free_pages -#define dlmalloc_walk_heap \ - malloc_walk_heap -#define dlmalloc_stats malloc_stats -#define dlmalloc_usable_size malloc_usable_size -#define dlmalloc_footprint malloc_footprint -#define dlmalloc_max_allowed_footprint \ - malloc_max_allowed_footprint -#define dlmalloc_set_max_allowed_footprint \ - malloc_set_max_allowed_footprint -#define dlmalloc_max_footprint malloc_max_footprint -#define dlindependent_calloc independent_calloc -#define dlindependent_comalloc independent_comalloc -#endif /* USE_DL_PREFIX */ - - -/* - malloc(size_t n) - Returns a pointer to a newly allocated chunk of at least n bytes, or - null if no space is available, in which case errno is set to ENOMEM - on ANSI C systems. - - If n is zero, malloc returns a minimum-sized chunk. (The minimum - size is 16 bytes on most 32bit systems, and 32 bytes on 64bit - systems.) Note that size_t is an unsigned type, so calls with - arguments that would be negative if signed are interpreted as - requests for huge amounts of space, which will often fail. The - maximum supported value of n differs across systems, but is in all - cases less than the maximum representable value of a size_t. -*/ -void* dlmalloc(size_t); - -/* - free(void* p) - Releases the chunk of memory pointed to by p, that had been previously - allocated using malloc or a related routine such as realloc. - It has no effect if p is null. If p was not malloced or already - freed, free(p) will by default cuase the current program to abort. -*/ -void dlfree(void*); - -/* - calloc(size_t n_elements, size_t element_size); - Returns a pointer to n_elements * element_size bytes, with all locations - set to zero. -*/ -void* dlcalloc(size_t, size_t); - -/* - realloc(void* p, size_t n) - Returns a pointer to a chunk of size n that contains the same data - as does chunk p up to the minimum of (n, p's size) bytes, or null - if no space is available. - - The returned pointer may or may not be the same as p. The algorithm - prefers extending p in most cases when possible, otherwise it - employs the equivalent of a malloc-copy-free sequence. - - If p is null, realloc is equivalent to malloc. - - If space is not available, realloc returns null, errno is set (if on - ANSI) and p is NOT freed. - - if n is for fewer bytes than already held by p, the newly unused - space is lopped off and freed if possible. realloc with a size - argument of zero (re)allocates a minimum-sized chunk. - - The old unix realloc convention of allowing the last-free'd chunk - to be used as an argument to realloc is not supported. -*/ - -void* dlrealloc(void*, size_t); - -/* - memalign(size_t alignment, size_t n); - Returns a pointer to a newly allocated chunk of n bytes, aligned - in accord with the alignment argument. - - The alignment argument should be a power of two. If the argument is - not a power of two, the nearest greater power is used. - 8-byte alignment is guaranteed by normal malloc calls, so don't - bother calling memalign with an argument of 8 or less. - - Overreliance on memalign is a sure way to fragment space. -*/ -void* dlmemalign(size_t, size_t); - -/* - valloc(size_t n); - Equivalent to memalign(pagesize, n), where pagesize is the page - size of the system. If the pagesize is unknown, 4096 is used. -*/ -void* dlvalloc(size_t); - -/* - mallopt(int parameter_number, int parameter_value) - Sets tunable parameters The format is to provide a - (parameter-number, parameter-value) pair. mallopt then sets the - corresponding parameter to the argument value if it can (i.e., so - long as the value is meaningful), and returns 1 if successful else - 0. SVID/XPG/ANSI defines four standard param numbers for mallopt, - normally defined in malloc.h. None of these are use in this malloc, - so setting them has no effect. But this malloc also supports other - options in mallopt: - - Symbol param # default allowed param values - M_TRIM_THRESHOLD -1 2*1024*1024 any (-1U disables trimming) - M_GRANULARITY -2 page size any power of 2 >= page size - M_MMAP_THRESHOLD -3 256*1024 any (or 0 if no MMAP support) -*/ -int dlmallopt(int, int); - -#define M_TRIM_THRESHOLD (-1) -#define M_GRANULARITY (-2) -#define M_MMAP_THRESHOLD (-3) - - -/* - malloc_footprint(); - Returns the number of bytes obtained from the system. The total - number of bytes allocated by malloc, realloc etc., is less than this - value. Unlike mallinfo, this function returns only a precomputed - result, so can be called frequently to monitor memory consumption. - Even if locks are otherwise defined, this function does not use them, - so results might not be up to date. -*/ -size_t dlmalloc_footprint(); - -/* - malloc_max_allowed_footprint(); - Returns the number of bytes that the heap is allowed to obtain - from the system. malloc_footprint() should always return a - size less than or equal to max_allowed_footprint, unless the - max_allowed_footprint was set to a value smaller than the - footprint at the time. - - This function is only available if dlmalloc.c was compiled - with USE_MAX_ALLOWED_FOOTPRINT set. -*/ -size_t dlmalloc_max_allowed_footprint(); - -/* - malloc_set_max_allowed_footprint(); - Set the maximum number of bytes that the heap is allowed to - obtain from the system. The size will be rounded up to a whole - page, and the rounded number will be returned from future calls - to malloc_max_allowed_footprint(). If the new max_allowed_footprint - is larger than the current footprint, the heap will never grow - larger than max_allowed_footprint. If the new max_allowed_footprint - is smaller than the current footprint, the heap will not grow - further. - - This function is only available if dlmalloc.c was compiled - with USE_MAX_ALLOWED_FOOTPRINT set. - - TODO: try to force the heap to give up memory in the shrink case, - and update this comment once that happens. -*/ -void dlmalloc_set_max_allowed_footprint(size_t bytes); - -/* - malloc_max_footprint(); - Returns the maximum number of bytes obtained from the system. This - value will be greater than current footprint if deallocated space - has been reclaimed by the system. The peak number of bytes allocated - by malloc, realloc etc., is less than this value. Unlike mallinfo, - this function returns only a precomputed result, so can be called - frequently to monitor memory consumption. Even if locks are - otherwise defined, this function does not use them, so results might - not be up to date. -*/ -size_t dlmalloc_max_footprint(void); - -#if !NO_MALLINFO -/* - mallinfo() - Returns (by copy) a struct containing various summary statistics: - - arena: current total non-mmapped bytes allocated from system - ordblks: the number of free chunks - smblks: always zero. - hblks: current number of mmapped regions - hblkhd: total bytes held in mmapped regions - usmblks: the maximum total allocated space. This will be greater - than current total if trimming has occurred. - fsmblks: always zero - uordblks: current total allocated space (normal or mmapped) - fordblks: total free space - keepcost: the maximum number of bytes that could ideally be released - back to system via malloc_trim. ("ideally" means that - it ignores page restrictions etc.) - - Because these fields are ints, but internal bookkeeping may - be kept as longs, the reported values may wrap around zero and - thus be inaccurate. -*/ -#ifndef HAVE_USR_INCLUDE_MALLOC_H -#ifndef _MALLOC_H_ -#ifndef MALLINFO_FIELD_TYPE -#define MALLINFO_FIELD_TYPE size_t -#endif /* MALLINFO_FIELD_TYPE */ -struct mallinfo { - MALLINFO_FIELD_TYPE arena; /* non-mmapped space allocated from system */ - MALLINFO_FIELD_TYPE ordblks; /* number of free chunks */ - MALLINFO_FIELD_TYPE smblks; /* always 0 */ - MALLINFO_FIELD_TYPE hblks; /* always 0 */ - MALLINFO_FIELD_TYPE hblkhd; /* space in mmapped regions */ - MALLINFO_FIELD_TYPE usmblks; /* maximum total allocated space */ - MALLINFO_FIELD_TYPE fsmblks; /* always 0 */ - MALLINFO_FIELD_TYPE uordblks; /* total allocated space */ - MALLINFO_FIELD_TYPE fordblks; /* total free space */ - MALLINFO_FIELD_TYPE keepcost; /* releasable (via malloc_trim) space */ -}; -#endif /* _MALLOC_H_ */ -#endif /* HAVE_USR_INCLUDE_MALLOC_H */ - -struct mallinfo dlmallinfo(void); -#endif /* NO_MALLINFO */ - -/* - independent_calloc(size_t n_elements, size_t element_size, void* chunks[]); - - independent_calloc is similar to calloc, but instead of returning a - single cleared space, it returns an array of pointers to n_elements - independent elements that can hold contents of size elem_size, each - of which starts out cleared, and can be independently freed, - realloc'ed etc. The elements are guaranteed to be adjacently - allocated (this is not guaranteed to occur with multiple callocs or - mallocs), which may also improve cache locality in some - applications. - - The "chunks" argument is optional (i.e., may be null, which is - probably the most typical usage). If it is null, the returned array - is itself dynamically allocated and should also be freed when it is - no longer needed. Otherwise, the chunks array must be of at least - n_elements in length. It is filled in with the pointers to the - chunks. - - In either case, independent_calloc returns this pointer array, or - null if the allocation failed. If n_elements is zero and "chunks" - is null, it returns a chunk representing an array with zero elements - (which should be freed if not wanted). - - Each element must be individually freed when it is no longer - needed. If you'd like to instead be able to free all at once, you - should instead use regular calloc and assign pointers into this - space to represent elements. (In this case though, you cannot - independently free elements.) - - independent_calloc simplifies and speeds up implementations of many - kinds of pools. It may also be useful when constructing large data - structures that initially have a fixed number of fixed-sized nodes, - but the number is not known at compile time, and some of the nodes - may later need to be freed. For example: - - struct Node { int item; struct Node* next; }; - - struct Node* build_list() { - struct Node** pool; - int n = read_number_of_nodes_needed(); - if (n <= 0) return 0; - pool = (struct Node**)(independent_calloc(n, sizeof(struct Node), 0); - if (pool == 0) die(); - // organize into a linked list... - struct Node* first = pool[0]; - for (i = 0; i < n-1; ++i) - pool[i]->next = pool[i+1]; - free(pool); // Can now free the array (or not, if it is needed later) - return first; - } -*/ -void** dlindependent_calloc(size_t, size_t, void**); - -/* - independent_comalloc(size_t n_elements, size_t sizes[], void* chunks[]); - - independent_comalloc allocates, all at once, a set of n_elements - chunks with sizes indicated in the "sizes" array. It returns - an array of pointers to these elements, each of which can be - independently freed, realloc'ed etc. The elements are guaranteed to - be adjacently allocated (this is not guaranteed to occur with - multiple callocs or mallocs), which may also improve cache locality - in some applications. - - The "chunks" argument is optional (i.e., may be null). If it is null - the returned array is itself dynamically allocated and should also - be freed when it is no longer needed. Otherwise, the chunks array - must be of at least n_elements in length. It is filled in with the - pointers to the chunks. - - In either case, independent_comalloc returns this pointer array, or - null if the allocation failed. If n_elements is zero and chunks is - null, it returns a chunk representing an array with zero elements - (which should be freed if not wanted). - - Each element must be individually freed when it is no longer - needed. If you'd like to instead be able to free all at once, you - should instead use a single regular malloc, and assign pointers at - particular offsets in the aggregate space. (In this case though, you - cannot independently free elements.) - - independent_comallac differs from independent_calloc in that each - element may have a different size, and also that it does not - automatically clear elements. - - independent_comalloc can be used to speed up allocation in cases - where several structs or objects must always be allocated at the - same time. For example: - - struct Head { ... } - struct Foot { ... } - - void send_message(char* msg) { - int msglen = strlen(msg); - size_t sizes[3] = { sizeof(struct Head), msglen, sizeof(struct Foot) }; - void* chunks[3]; - if (independent_comalloc(3, sizes, chunks) == 0) - die(); - struct Head* head = (struct Head*)(chunks[0]); - char* body = (char*)(chunks[1]); - struct Foot* foot = (struct Foot*)(chunks[2]); - // ... - } - - In general though, independent_comalloc is worth using only for - larger values of n_elements. For small values, you probably won't - detect enough difference from series of malloc calls to bother. - - Overuse of independent_comalloc can increase overall memory usage, - since it cannot reuse existing noncontiguous small chunks that - might be available for some of the elements. -*/ -void** dlindependent_comalloc(size_t, size_t*, void**); - - -/* - pvalloc(size_t n); - Equivalent to valloc(minimum-page-that-holds(n)), that is, - round up n to nearest pagesize. - */ -void* dlpvalloc(size_t); - -/* - malloc_trim(size_t pad); - - If possible, gives memory back to the system (via negative arguments - to sbrk) if there is unused memory at the `high' end of the malloc - pool or in unused MMAP segments. You can call this after freeing - large blocks of memory to potentially reduce the system-level memory - requirements of a program. However, it cannot guarantee to reduce - memory. Under some allocation patterns, some large free blocks of - memory will be locked between two used chunks, so they cannot be - given back to the system. - - The `pad' argument to malloc_trim represents the amount of free - trailing space to leave untrimmed. If this argument is zero, only - the minimum amount of memory to maintain internal data structures - will be left. Non-zero arguments can be supplied to maintain enough - trailing space to service future expected allocations without having - to re-obtain memory from the system. - - Malloc_trim returns 1 if it actually released any memory, else 0. -*/ -int dlmalloc_trim(size_t); - -/* - malloc_walk_free_pages(handler, harg) - - Calls the provided handler on each free region in the heap. The - memory between start and end are guaranteed not to contain any - important data, so the handler is free to alter the contents - in any way. This can be used to advise the OS that large free - regions may be swapped out. - - The value in harg will be passed to each call of the handler. - */ -void dlmalloc_walk_free_pages(void(*handler)(void *start, void *end, void *arg), - void *harg); - -/* - malloc_walk_heap(handler, harg) - - Calls the provided handler on each object or free region in the - heap. The handler will receive the chunk pointer and length, the - object pointer and length, and the value in harg on each call. - */ -void dlmalloc_walk_heap(void(*handler)(const void *chunkptr, size_t chunklen, - const void *userptr, size_t userlen, - void *arg), - void *harg); - -/* - malloc_usable_size(void* p); - - Returns the number of bytes you can actually use in - an allocated chunk, which may be more than you requested (although - often not) due to alignment and minimum size constraints. - You can use this many bytes without worrying about - overwriting other allocated objects. This is not a particularly great - programming practice. malloc_usable_size can be more useful in - debugging and assertions, for example: - - p = malloc(n); - assert(malloc_usable_size(p) >= 256); -*/ -size_t dlmalloc_usable_size(void*); - -/* - malloc_stats(); - Prints on stderr the amount of space obtained from the system (both - via sbrk and mmap), the maximum amount (which may be more than - current if malloc_trim and/or munmap got called), and the current - number of bytes allocated via malloc (or realloc, etc) but not yet - freed. Note that this is the number of bytes allocated, not the - number requested. It will be larger than the number requested - because of alignment and bookkeeping overhead. Because it includes - alignment wastage as being in use, this figure may be greater than - zero even when no user-level chunks are allocated. - - The reported current and maximum system memory can be inaccurate if - a program makes other calls to system memory allocation functions - (normally sbrk) outside of malloc. - - malloc_stats prints only the most commonly interesting statistics. - More information can be obtained by calling mallinfo. -*/ -void dlmalloc_stats(); - -#endif /* !ONLY_MSPACES */ - -#if MSPACES - -/* - mspace is an opaque type representing an independent - region of space that supports mspace_malloc, etc. -*/ -typedef void* mspace; - -/* - create_mspace creates and returns a new independent space with the - given initial capacity, or, if 0, the default granularity size. It - returns null if there is no system memory available to create the - space. If argument locked is non-zero, the space uses a separate - lock to control access. The capacity of the space will grow - dynamically as needed to service mspace_malloc requests. You can - control the sizes of incremental increases of this space by - compiling with a different DEFAULT_GRANULARITY or dynamically - setting with mallopt(M_GRANULARITY, value). -*/ -mspace create_mspace(size_t capacity, int locked); - -/* - destroy_mspace destroys the given space, and attempts to return all - of its memory back to the system, returning the total number of - bytes freed. After destruction, the results of access to all memory - used by the space become undefined. -*/ -size_t destroy_mspace(mspace msp); - -/* - create_mspace_with_base uses the memory supplied as the initial base - of a new mspace. Part (less than 128*sizeof(size_t) bytes) of this - space is used for bookkeeping, so the capacity must be at least this - large. (Otherwise 0 is returned.) When this initial space is - exhausted, additional memory will be obtained from the system. - Destroying this space will deallocate all additionally allocated - space (if possible) but not the initial base. -*/ -mspace create_mspace_with_base(void* base, size_t capacity, int locked); - -/* - mspace_malloc behaves as malloc, but operates within - the given space. -*/ -void* mspace_malloc(mspace msp, size_t bytes); - -/* - mspace_free behaves as free, but operates within - the given space. - - If compiled with FOOTERS==1, mspace_free is not actually needed. - free may be called instead of mspace_free because freed chunks from - any space are handled by their originating spaces. -*/ -void mspace_free(mspace msp, void* mem); - -/* - mspace_realloc behaves as realloc, but operates within - the given space. - - If compiled with FOOTERS==1, mspace_realloc is not actually - needed. realloc may be called instead of mspace_realloc because - realloced chunks from any space are handled by their originating - spaces. -*/ -void* mspace_realloc(mspace msp, void* mem, size_t newsize); - -/* - mspace_merge_objects will merge allocated memory mema and memb - together, provided memb immediately follows mema. It is roughly as - if memb has been freed and mema has been realloced to a larger size. - On successfully merging, mema will be returned. If either argument - is null or memb does not immediately follow mema, null will be - returned. - - Both mema and memb should have been previously allocated using - malloc or a related routine such as realloc. If either mema or memb - was not malloced or was previously freed, the result is undefined, - but like mspace_free, the default is to abort the program. -*/ -void* mspace_merge_objects(mspace msp, void* mema, void* memb); - -/* - mspace_calloc behaves as calloc, but operates within - the given space. -*/ -void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size); - -/* - mspace_memalign behaves as memalign, but operates within - the given space. -*/ -void* mspace_memalign(mspace msp, size_t alignment, size_t bytes); - -/* - mspace_independent_calloc behaves as independent_calloc, but - operates within the given space. -*/ -void** mspace_independent_calloc(mspace msp, size_t n_elements, - size_t elem_size, void* chunks[]); - -/* - mspace_independent_comalloc behaves as independent_comalloc, but - operates within the given space. -*/ -void** mspace_independent_comalloc(mspace msp, size_t n_elements, - size_t sizes[], void* chunks[]); - -/* - mspace_footprint() returns the number of bytes obtained from the - system for this space. -*/ -size_t mspace_footprint(mspace msp); - -/* - mspace_max_allowed_footprint() returns the number of bytes that - this space is allowed to obtain from the system. See - malloc_max_allowed_footprint() for a more in-depth description. - - This function is only available if dlmalloc.c was compiled - with USE_MAX_ALLOWED_FOOTPRINT set. -*/ -size_t mspace_max_allowed_footprint(mspace msp); - -/* - mspace_set_max_allowed_footprint() sets the maximum number of - bytes (rounded up to a page) that this space is allowed to - obtain from the system. See malloc_set_max_allowed_footprint() - for a more in-depth description. - - This function is only available if dlmalloc.c was compiled - with USE_MAX_ALLOWED_FOOTPRINT set. -*/ -void mspace_set_max_allowed_footprint(mspace msp, size_t bytes); - -/* - mspace_max_footprint() returns the maximum number of bytes obtained - from the system over the lifetime of this space. -*/ -size_t mspace_max_footprint(mspace msp); - - -#if !NO_MALLINFO -/* - mspace_mallinfo behaves as mallinfo, but reports properties of - the given space. -*/ -struct mallinfo mspace_mallinfo(mspace msp); -#endif /* NO_MALLINFO */ - -/* - mspace_malloc_stats behaves as malloc_stats, but reports - properties of the given space. -*/ -void mspace_malloc_stats(mspace msp); - -/* - mspace_trim behaves as malloc_trim, but - operates within the given space. -*/ -int mspace_trim(mspace msp, size_t pad); - -/* - An alias for mallopt. -*/ -int mspace_mallopt(int, int); - -#endif /* MSPACES */ - -#ifdef __cplusplus -}; /* end of extern "C" */ +// Copyright 2012 Google Inc. All Rights Reserved. + +#ifndef ART_SRC_DLMALLOC_H_ +#define ART_SRC_DLMALLOC_H_ + +#define NO_MALLINFO 1 +#define HAVE_MMAP 0 +#define HAVE_MREMAP 0 +#define HAVE_MORECORE 1 +#define MSPACES 1 +#define ONLY_MSPACES 1 +#define USE_DL_PREFIX 1 +#define MALLOC_INSPECT_ALL 1 + +// Only #include if we are not compiling dlmalloc.c (to avoid symbol redefinitions) +#ifndef FOR_DLMALLOC_C +#include "dlmalloc/malloc.h" #endif -#endif /* MALLOC_280_H */ +#endif // ART_SRC_DLMALLOC_H_ diff --git a/src/dlmalloc/malloc.c b/src/dlmalloc/malloc.c new file mode 100644 index 0000000000..b0192ac5c4 --- /dev/null +++ b/src/dlmalloc/malloc.c @@ -0,0 +1,6256 @@ +/* + This is a version (aka dlmalloc) of malloc/free/realloc written by + Doug Lea and released to the public domain, as explained at + http://creativecommons.org/publicdomain/zero/1.0/ Send questions, + comments, complaints, performance data, etc to dl@cs.oswego.edu + +* Version 2.8.5 Sun May 22 10:26:02 2011 Doug Lea (dl at gee) + + Note: There may be an updated version of this malloc obtainable at + ftp://gee.cs.oswego.edu/pub/misc/malloc.c + Check before installing! + +* Quickstart + + This library is all in one file to simplify the most common usage: + ftp it, compile it (-O3), and link it into another program. All of + the compile-time options default to reasonable values for use on + most platforms. You might later want to step through various + compile-time and dynamic tuning options. + + For convenience, an include file for code using this malloc is at: + ftp://gee.cs.oswego.edu/pub/misc/malloc-2.8.5.h + You don't really need this .h file unless you call functions not + defined in your system include files. The .h file contains only the + excerpts from this file needed for using this malloc on ANSI C/C++ + systems, so long as you haven't changed compile-time options about + naming and tuning parameters. If you do, then you can create your + own malloc.h that does include all settings by cutting at the point + indicated below. Note that you may already by default be using a C + library containing a malloc that is based on some version of this + malloc (for example in linux). You might still want to use the one + in this file to customize settings or to avoid overheads associated + with library versions. + +* Vital statistics: + + Supported pointer/size_t representation: 4 or 8 bytes + size_t MUST be an unsigned type of the same width as + pointers. (If you are using an ancient system that declares + size_t as a signed type, or need it to be a different width + than pointers, you can use a previous release of this malloc + (e.g. 2.7.2) supporting these.) + + Alignment: 8 bytes (default) + This suffices for nearly all current machines and C compilers. + However, you can define MALLOC_ALIGNMENT to be wider than this + if necessary (up to 128bytes), at the expense of using more space. + + Minimum overhead per allocated chunk: 4 or 8 bytes (if 4byte sizes) + 8 or 16 bytes (if 8byte sizes) + Each malloced chunk has a hidden word of overhead holding size + and status information, and additional cross-check word + if FOOTERS is defined. + + Minimum allocated size: 4-byte ptrs: 16 bytes (including overhead) + 8-byte ptrs: 32 bytes (including overhead) + + Even a request for zero bytes (i.e., malloc(0)) returns a + pointer to something of the minimum allocatable size. + The maximum overhead wastage (i.e., number of extra bytes + allocated than were requested in malloc) is less than or equal + to the minimum size, except for requests >= mmap_threshold that + are serviced via mmap(), where the worst case wastage is about + 32 bytes plus the remainder from a system page (the minimal + mmap unit); typically 4096 or 8192 bytes. + + Security: static-safe; optionally more or less + The "security" of malloc refers to the ability of malicious + code to accentuate the effects of errors (for example, freeing + space that is not currently malloc'ed or overwriting past the + ends of chunks) in code that calls malloc. This malloc + guarantees not to modify any memory locations below the base of + heap, i.e., static variables, even in the presence of usage + errors. The routines additionally detect most improper frees + and reallocs. All this holds as long as the static bookkeeping + for malloc itself is not corrupted by some other means. This + is only one aspect of security -- these checks do not, and + cannot, detect all possible programming errors. + + If FOOTERS is defined nonzero, then each allocated chunk + carries an additional check word to verify that it was malloced + from its space. These check words are the same within each + execution of a program using malloc, but differ across + executions, so externally crafted fake chunks cannot be + freed. This improves security by rejecting frees/reallocs that + could corrupt heap memory, in addition to the checks preventing + writes to statics that are always on. This may further improve + security at the expense of time and space overhead. (Note that + FOOTERS may also be worth using with MSPACES.) + + By default detected errors cause the program to abort (calling + "abort()"). You can override this to instead proceed past + errors by defining PROCEED_ON_ERROR. In this case, a bad free + has no effect, and a malloc that encounters a bad address + caused by user overwrites will ignore the bad address by + dropping pointers and indices to all known memory. This may + be appropriate for programs that should continue if at all + possible in the face of programming errors, although they may + run out of memory because dropped memory is never reclaimed. + + If you don't like either of these options, you can define + CORRUPTION_ERROR_ACTION and USAGE_ERROR_ACTION to do anything + else. And if if you are sure that your program using malloc has + no errors or vulnerabilities, you can define INSECURE to 1, + which might (or might not) provide a small performance improvement. + + It is also possible to limit the maximum total allocatable + space, using malloc_set_footprint_limit. This is not + designed as a security feature in itself (calls to set limits + are not screened or privileged), but may be useful as one + aspect of a secure implementation. + + Thread-safety: NOT thread-safe unless USE_LOCKS defined non-zero + When USE_LOCKS is defined, each public call to malloc, free, + etc is surrounded with a lock. By default, this uses a plain + pthread mutex, win32 critical section, or a spin-lock if if + available for the platform and not disabled by setting + USE_SPIN_LOCKS=0. However, if USE_RECURSIVE_LOCKS is defined, + recursive versions are used instead (which are not required for + base functionality but may be needed in layered extensions). + Using a global lock is not especially fast, and can be a major + bottleneck. It is designed only to provide minimal protection + in concurrent environments, and to provide a basis for + extensions. If you are using malloc in a concurrent program, + consider instead using nedmalloc + (http://www.nedprod.com/programs/portable/nedmalloc/) or + ptmalloc (See http://www.malloc.de), which are derived from + versions of this malloc. + + System requirements: Any combination of MORECORE and/or MMAP/MUNMAP + This malloc can use unix sbrk or any emulation (invoked using + the CALL_MORECORE macro) and/or mmap/munmap or any emulation + (invoked using CALL_MMAP/CALL_MUNMAP) to get and release system + memory. On most unix systems, it tends to work best if both + MORECORE and MMAP are enabled. On Win32, it uses emulations + based on VirtualAlloc. It also uses common C library functions + like memset. + + Compliance: I believe it is compliant with the Single Unix Specification + (See http://www.unix.org). Also SVID/XPG, ANSI C, and probably + others as well. + +* Overview of algorithms + + This is not the fastest, most space-conserving, most portable, or + most tunable malloc ever written. However it is among the fastest + while also being among the most space-conserving, portable and + tunable. Consistent balance across these factors results in a good + general-purpose allocator for malloc-intensive programs. + + In most ways, this malloc is a best-fit allocator. Generally, it + chooses the best-fitting existing chunk for a request, with ties + broken in approximately least-recently-used order. (This strategy + normally maintains low fragmentation.) However, for requests less + than 256bytes, it deviates from best-fit when there is not an + exactly fitting available chunk by preferring to use space adjacent + to that used for the previous small request, as well as by breaking + ties in approximately most-recently-used order. (These enhance + locality of series of small allocations.) And for very large requests + (>= 256Kb by default), it relies on system memory mapping + facilities, if supported. (This helps avoid carrying around and + possibly fragmenting memory used only for large chunks.) + + All operations (except malloc_stats and mallinfo) have execution + times that are bounded by a constant factor of the number of bits in + a size_t, not counting any clearing in calloc or copying in realloc, + or actions surrounding MORECORE and MMAP that have times + proportional to the number of non-contiguous regions returned by + system allocation routines, which is often just 1. In real-time + applications, you can optionally suppress segment traversals using + NO_SEGMENT_TRAVERSAL, which assures bounded execution even when + system allocators return non-contiguous spaces, at the typical + expense of carrying around more memory and increased fragmentation. + + The implementation is not very modular and seriously overuses + macros. Perhaps someday all C compilers will do as good a job + inlining modular code as can now be done by brute-force expansion, + but now, enough of them seem not to. + + Some compilers issue a lot of warnings about code that is + dead/unreachable only on some platforms, and also about intentional + uses of negation on unsigned types. All known cases of each can be + ignored. + + For a longer but out of date high-level description, see + http://gee.cs.oswego.edu/dl/html/malloc.html + +* MSPACES + If MSPACES is defined, then in addition to malloc, free, etc., + this file also defines mspace_malloc, mspace_free, etc. These + are versions of malloc routines that take an "mspace" argument + obtained using create_mspace, to control all internal bookkeeping. + If ONLY_MSPACES is defined, only these versions are compiled. + So if you would like to use this allocator for only some allocations, + and your system malloc for others, you can compile with + ONLY_MSPACES and then do something like... + static mspace mymspace = create_mspace(0,0); // for example + #define mymalloc(bytes) mspace_malloc(mymspace, bytes) + + (Note: If you only need one instance of an mspace, you can instead + use "USE_DL_PREFIX" to relabel the global malloc.) + + You can similarly create thread-local allocators by storing + mspaces as thread-locals. For example: + static __thread mspace tlms = 0; + void* tlmalloc(size_t bytes) { + if (tlms == 0) tlms = create_mspace(0, 0); + return mspace_malloc(tlms, bytes); + } + void tlfree(void* mem) { mspace_free(tlms, mem); } + + Unless FOOTERS is defined, each mspace is completely independent. + You cannot allocate from one and free to another (although + conformance is only weakly checked, so usage errors are not always + caught). If FOOTERS is defined, then each chunk carries around a tag + indicating its originating mspace, and frees are directed to their + originating spaces. Normally, this requires use of locks. + + ------------------------- Compile-time options --------------------------- + +Be careful in setting #define values for numerical constants of type +size_t. On some systems, literal values are not automatically extended +to size_t precision unless they are explicitly casted. You can also +use the symbolic values MAX_SIZE_T, SIZE_T_ONE, etc below. + +WIN32 default: defined if _WIN32 defined + Defining WIN32 sets up defaults for MS environment and compilers. + Otherwise defaults are for unix. Beware that there seem to be some + cases where this malloc might not be a pure drop-in replacement for + Win32 malloc: Random-looking failures from Win32 GDI API's (eg; + SetDIBits()) may be due to bugs in some video driver implementations + when pixel buffers are malloc()ed, and the region spans more than + one VirtualAlloc()ed region. Because dlmalloc uses a small (64Kb) + default granularity, pixel buffers may straddle virtual allocation + regions more often than when using the Microsoft allocator. You can + avoid this by using VirtualAlloc() and VirtualFree() for all pixel + buffers rather than using malloc(). If this is not possible, + recompile this malloc with a larger DEFAULT_GRANULARITY. Note: + in cases where MSC and gcc (cygwin) are known to differ on WIN32, + conditions use _MSC_VER to distinguish them. + +DLMALLOC_EXPORT default: extern + Defines how public APIs are declared. If you want to export via a + Windows DLL, you might define this as + #define DLMALLOC_EXPORT extern __declspace(dllexport) + If you want a POSIX ELF shared object, you might use + #define DLMALLOC_EXPORT extern __attribute__((visibility("default"))) + +MALLOC_ALIGNMENT default: (size_t)8 + Controls the minimum alignment for malloc'ed chunks. It must be a + power of two and at least 8, even on machines for which smaller + alignments would suffice. It may be defined as larger than this + though. Note however that code and data structures are optimized for + the case of 8-byte alignment. + +MSPACES default: 0 (false) + If true, compile in support for independent allocation spaces. + This is only supported if HAVE_MMAP is true. + +ONLY_MSPACES default: 0 (false) + If true, only compile in mspace versions, not regular versions. + +USE_LOCKS default: 0 (false) + Causes each call to each public routine to be surrounded with + pthread or WIN32 mutex lock/unlock. (If set true, this can be + overridden on a per-mspace basis for mspace versions.) If set to a + non-zero value other than 1, locks are used, but their + implementation is left out, so lock functions must be supplied manually, + as described below. + +USE_SPIN_LOCKS default: 1 iff USE_LOCKS and spin locks available + If true, uses custom spin locks for locking. This is currently + supported only gcc >= 4.1, older gccs on x86 platforms, and recent + MS compilers. Otherwise, posix locks or win32 critical sections are + used. + +USE_RECURSIVE_LOCKS default: not defined + If defined nonzero, uses recursive (aka reentrant) locks, otherwise + uses plain mutexes. This is not required for malloc proper, but may + be needed for layered allocators such as nedmalloc. + +FOOTERS default: 0 + If true, provide extra checking and dispatching by placing + information in the footers of allocated chunks. This adds + space and time overhead. + +INSECURE default: 0 + If true, omit checks for usage errors and heap space overwrites. + +USE_DL_PREFIX default: NOT defined + Causes compiler to prefix all public routines with the string 'dl'. + This can be useful when you only want to use this malloc in one part + of a program, using your regular system malloc elsewhere. + +MALLOC_INSPECT_ALL default: NOT defined + If defined, compiles malloc_inspect_all and mspace_inspect_all, that + perform traversal of all heap space. Unless access to these + functions is otherwise restricted, you probably do not want to + include them in secure implementations. + +ABORT default: defined as abort() + Defines how to abort on failed checks. On most systems, a failed + check cannot die with an "assert" or even print an informative + message, because the underlying print routines in turn call malloc, + which will fail again. Generally, the best policy is to simply call + abort(). It's not very useful to do more than this because many + errors due to overwriting will show up as address faults (null, odd + addresses etc) rather than malloc-triggered checks, so will also + abort. Also, most compilers know that abort() does not return, so + can better optimize code conditionally calling it. + +PROCEED_ON_ERROR default: defined as 0 (false) + Controls whether detected bad addresses cause them to bypassed + rather than aborting. If set, detected bad arguments to free and + realloc are ignored. And all bookkeeping information is zeroed out + upon a detected overwrite of freed heap space, thus losing the + ability to ever return it from malloc again, but enabling the + application to proceed. If PROCEED_ON_ERROR is defined, the + static variable malloc_corruption_error_count is compiled in + and can be examined to see if errors have occurred. This option + generates slower code than the default abort policy. + +DEBUG default: NOT defined + The DEBUG setting is mainly intended for people trying to modify + this code or diagnose problems when porting to new platforms. + However, it may also be able to better isolate user errors than just + using runtime checks. The assertions in the check routines spell + out in more detail the assumptions and invariants underlying the + algorithms. The checking is fairly extensive, and will slow down + execution noticeably. Calling malloc_stats or mallinfo with DEBUG + set will attempt to check every non-mmapped allocated and free chunk + in the course of computing the summaries. + +ABORT_ON_ASSERT_FAILURE default: defined as 1 (true) + Debugging assertion failures can be nearly impossible if your + version of the assert macro causes malloc to be called, which will + lead to a cascade of further failures, blowing the runtime stack. + ABORT_ON_ASSERT_FAILURE cause assertions failures to call abort(), + which will usually make debugging easier. + +MALLOC_FAILURE_ACTION default: sets errno to ENOMEM, or no-op on win32 + The action to take before "return 0" when malloc fails to be able to + return memory because there is none available. + +HAVE_MORECORE default: 1 (true) unless win32 or ONLY_MSPACES + True if this system supports sbrk or an emulation of it. + +MORECORE default: sbrk + The name of the sbrk-style system routine to call to obtain more + memory. See below for guidance on writing custom MORECORE + functions. The type of the argument to sbrk/MORECORE varies across + systems. It cannot be size_t, because it supports negative + arguments, so it is normally the signed type of the same width as + size_t (sometimes declared as "intptr_t"). It doesn't much matter + though. Internally, we only call it with arguments less than half + the max value of a size_t, which should work across all reasonable + possibilities, although sometimes generating compiler warnings. + +MORECORE_CONTIGUOUS default: 1 (true) if HAVE_MORECORE + If true, take advantage of fact that consecutive calls to MORECORE + with positive arguments always return contiguous increasing + addresses. This is true of unix sbrk. It does not hurt too much to + set it true anyway, since malloc copes with non-contiguities. + Setting it false when definitely non-contiguous saves time + and possibly wasted space it would take to discover this though. + +MORECORE_CANNOT_TRIM default: NOT defined + True if MORECORE cannot release space back to the system when given + negative arguments. This is generally necessary only if you are + using a hand-crafted MORECORE function that cannot handle negative + arguments. + +NO_SEGMENT_TRAVERSAL default: 0 + If non-zero, suppresses traversals of memory segments + returned by either MORECORE or CALL_MMAP. This disables + merging of segments that are contiguous, and selectively + releasing them to the OS if unused, but bounds execution times. + +HAVE_MMAP default: 1 (true) + True if this system supports mmap or an emulation of it. If so, and + HAVE_MORECORE is not true, MMAP is used for all system + allocation. If set and HAVE_MORECORE is true as well, MMAP is + primarily used to directly allocate very large blocks. It is also + used as a backup strategy in cases where MORECORE fails to provide + space from system. Note: A single call to MUNMAP is assumed to be + able to unmap memory that may have be allocated using multiple calls + to MMAP, so long as they are adjacent. + +HAVE_MREMAP default: 1 on linux, else 0 + If true realloc() uses mremap() to re-allocate large blocks and + extend or shrink allocation spaces. + +MMAP_CLEARS default: 1 except on WINCE. + True if mmap clears memory so calloc doesn't need to. This is true + for standard unix mmap using /dev/zero and on WIN32 except for WINCE. + +USE_BUILTIN_FFS default: 0 (i.e., not used) + Causes malloc to use the builtin ffs() function to compute indices. + Some compilers may recognize and intrinsify ffs to be faster than the + supplied C version. Also, the case of x86 using gcc is special-cased + to an asm instruction, so is already as fast as it can be, and so + this setting has no effect. Similarly for Win32 under recent MS compilers. + (On most x86s, the asm version is only slightly faster than the C version.) + +malloc_getpagesize default: derive from system includes, or 4096. + The system page size. To the extent possible, this malloc manages + memory from the system in page-size units. This may be (and + usually is) a function rather than a constant. This is ignored + if WIN32, where page size is determined using getSystemInfo during + initialization. + +USE_DEV_RANDOM default: 0 (i.e., not used) + Causes malloc to use /dev/random to initialize secure magic seed for + stamping footers. Otherwise, the current time is used. + +NO_MALLINFO default: 0 + If defined, don't compile "mallinfo". This can be a simple way + of dealing with mismatches between system declarations and + those in this file. + +MALLINFO_FIELD_TYPE default: size_t + The type of the fields in the mallinfo struct. This was originally + defined as "int" in SVID etc, but is more usefully defined as + size_t. The value is used only if HAVE_USR_INCLUDE_MALLOC_H is not set + +NO_MALLOC_STATS default: 0 + If defined, don't compile "malloc_stats". This avoids calls to + fprintf and bringing in stdio dependencies you might not want. + +REALLOC_ZERO_BYTES_FREES default: not defined + This should be set if a call to realloc with zero bytes should + be the same as a call to free. Some people think it should. Otherwise, + since this malloc returns a unique pointer for malloc(0), so does + realloc(p, 0). + +LACKS_UNISTD_H, LACKS_FCNTL_H, LACKS_SYS_PARAM_H, LACKS_SYS_MMAN_H +LACKS_STRINGS_H, LACKS_STRING_H, LACKS_SYS_TYPES_H, LACKS_ERRNO_H +LACKS_STDLIB_H LACKS_SCHED_H LACKS_TIME_H default: NOT defined unless on WIN32 + Define these if your system does not have these header files. + You might need to manually insert some of the declarations they provide. + +DEFAULT_GRANULARITY default: page size if MORECORE_CONTIGUOUS, + system_info.dwAllocationGranularity in WIN32, + otherwise 64K. + Also settable using mallopt(M_GRANULARITY, x) + The unit for allocating and deallocating memory from the system. On + most systems with contiguous MORECORE, there is no reason to + make this more than a page. However, systems with MMAP tend to + either require or encourage larger granularities. You can increase + this value to prevent system allocation functions to be called so + often, especially if they are slow. The value must be at least one + page and must be a power of two. Setting to 0 causes initialization + to either page size or win32 region size. (Note: In previous + versions of malloc, the equivalent of this option was called + "TOP_PAD") + +DEFAULT_TRIM_THRESHOLD default: 2MB + Also settable using mallopt(M_TRIM_THRESHOLD, x) + The maximum amount of unused top-most memory to keep before + releasing via malloc_trim in free(). Automatic trimming is mainly + useful in long-lived programs using contiguous MORECORE. Because + trimming via sbrk can be slow on some systems, and can sometimes be + wasteful (in cases where programs immediately afterward allocate + more large chunks) the value should be high enough so that your + overall system performance would improve by releasing this much + memory. As a rough guide, you might set to a value close to the + average size of a process (program) running on your system. + Releasing this much memory would allow such a process to run in + memory. Generally, it is worth tuning trim thresholds when a + program undergoes phases where several large chunks are allocated + and released in ways that can reuse each other's storage, perhaps + mixed with phases where there are no such chunks at all. The trim + value must be greater than page size to have any useful effect. To + disable trimming completely, you can set to MAX_SIZE_T. Note that the trick + some people use of mallocing a huge space and then freeing it at + program startup, in an attempt to reserve system memory, doesn't + have the intended effect under automatic trimming, since that memory + will immediately be returned to the system. + +DEFAULT_MMAP_THRESHOLD default: 256K + Also settable using mallopt(M_MMAP_THRESHOLD, x) + The request size threshold for using MMAP to directly service a + request. Requests of at least this size that cannot be allocated + using already-existing space will be serviced via mmap. (If enough + normal freed space already exists it is used instead.) Using mmap + segregates relatively large chunks of memory so that they can be + individually obtained and released from the host system. A request + serviced through mmap is never reused by any other request (at least + not directly; the system may just so happen to remap successive + requests to the same locations). Segregating space in this way has + the benefits that: Mmapped space can always be individually released + back to the system, which helps keep the system level memory demands + of a long-lived program low. Also, mapped memory doesn't become + `locked' between other chunks, as can happen with normally allocated + chunks, which means that even trimming via malloc_trim would not + release them. However, it has the disadvantage that the space + cannot be reclaimed, consolidated, and then used to service later + requests, as happens with normal chunks. The advantages of mmap + nearly always outweigh disadvantages for "large" chunks, but the + value of "large" may vary across systems. The default is an + empirically derived value that works well in most systems. You can + disable mmap by setting to MAX_SIZE_T. + +MAX_RELEASE_CHECK_RATE default: 4095 unless not HAVE_MMAP + The number of consolidated frees between checks to release + unused segments when freeing. When using non-contiguous segments, + especially with multiple mspaces, checking only for topmost space + doesn't always suffice to trigger trimming. To compensate for this, + free() will, with a period of MAX_RELEASE_CHECK_RATE (or the + current number of segments, if greater) try to release unused + segments to the OS when freeing chunks that result in + consolidation. The best value for this parameter is a compromise + between slowing down frees with relatively costly checks that + rarely trigger versus holding on to unused memory. To effectively + disable, set to MAX_SIZE_T. This may lead to a very slight speed + improvement at the expense of carrying around more memory. +*/ + +/* Version identifier to allow people to support multiple versions */ +#ifndef DLMALLOC_VERSION +#define DLMALLOC_VERSION 20805 +#endif /* DLMALLOC_VERSION */ + +#ifndef DLMALLOC_EXPORT +#define DLMALLOC_EXPORT extern +#endif + +#ifndef WIN32 +#ifdef _WIN32 +#define WIN32 1 +#endif /* _WIN32 */ +#ifdef _WIN32_WCE +#define LACKS_FCNTL_H +#define WIN32 1 +#endif /* _WIN32_WCE */ +#endif /* WIN32 */ +#ifdef WIN32 +#define WIN32_LEAN_AND_MEAN +#include <windows.h> +#include <tchar.h> +#define HAVE_MMAP 1 +#define HAVE_MORECORE 0 +#define LACKS_UNISTD_H +#define LACKS_SYS_PARAM_H +#define LACKS_SYS_MMAN_H +#define LACKS_STRING_H +#define LACKS_STRINGS_H +#define LACKS_SYS_TYPES_H +#define LACKS_ERRNO_H +#define LACKS_SCHED_H +#ifndef MALLOC_FAILURE_ACTION +#define MALLOC_FAILURE_ACTION +#endif /* MALLOC_FAILURE_ACTION */ +#ifndef MMAP_CLEARS +#ifdef _WIN32_WCE /* WINCE reportedly does not clear */ +#define MMAP_CLEARS 0 +#else +#define MMAP_CLEARS 1 +#endif /* _WIN32_WCE */ +#endif /*MMAP_CLEARS */ +#endif /* WIN32 */ + +#if defined(DARWIN) || defined(_DARWIN) +/* Mac OSX docs advise not to use sbrk; it seems better to use mmap */ +#ifndef HAVE_MORECORE +#define HAVE_MORECORE 0 +#define HAVE_MMAP 1 +/* OSX allocators provide 16 byte alignment */ +#ifndef MALLOC_ALIGNMENT +#define MALLOC_ALIGNMENT ((size_t)16U) +#endif +#endif /* HAVE_MORECORE */ +#endif /* DARWIN */ + +#ifndef LACKS_SYS_TYPES_H +#include <sys/types.h> /* For size_t */ +#endif /* LACKS_SYS_TYPES_H */ + +/* The maximum possible size_t value has all bits set */ +#define MAX_SIZE_T (~(size_t)0) + +#ifndef USE_LOCKS /* ensure true if spin or recursive locks set */ +#define USE_LOCKS ((defined(USE_SPIN_LOCKS) && USE_SPIN_LOCKS != 0) || \ + (defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0)) +#endif /* USE_LOCKS */ + +#if USE_LOCKS /* Spin locks for gcc >= 4.1, older gcc on x86, MSC >= 1310 */ +#if ((defined(__GNUC__) && \ + ((__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 1)) || \ + defined(__i386__) || defined(__x86_64__))) || \ + (defined(_MSC_VER) && _MSC_VER>=1310)) +#ifndef USE_SPIN_LOCKS +#define USE_SPIN_LOCKS 1 +#endif /* USE_SPIN_LOCKS */ +#elif USE_SPIN_LOCKS +#error "USE_SPIN_LOCKS defined without implementation" +#endif /* ... locks available... */ +#elif !defined(USE_SPIN_LOCKS) +#define USE_SPIN_LOCKS 0 +#endif /* USE_LOCKS */ + +#ifndef ONLY_MSPACES +#define ONLY_MSPACES 0 +#endif /* ONLY_MSPACES */ +#ifndef MSPACES +#if ONLY_MSPACES +#define MSPACES 1 +#else /* ONLY_MSPACES */ +#define MSPACES 0 +#endif /* ONLY_MSPACES */ +#endif /* MSPACES */ +#ifndef MALLOC_ALIGNMENT +#define MALLOC_ALIGNMENT ((size_t)8U) +#endif /* MALLOC_ALIGNMENT */ +#ifndef FOOTERS +#define FOOTERS 0 +#endif /* FOOTERS */ +#ifndef ABORT +#define ABORT abort() +#endif /* ABORT */ +#ifndef ABORT_ON_ASSERT_FAILURE +#define ABORT_ON_ASSERT_FAILURE 1 +#endif /* ABORT_ON_ASSERT_FAILURE */ +#ifndef PROCEED_ON_ERROR +#define PROCEED_ON_ERROR 0 +#endif /* PROCEED_ON_ERROR */ + +#ifndef INSECURE +#define INSECURE 0 +#endif /* INSECURE */ +#ifndef MALLOC_INSPECT_ALL +#define MALLOC_INSPECT_ALL 0 +#endif /* MALLOC_INSPECT_ALL */ +#ifndef HAVE_MMAP +#define HAVE_MMAP 1 +#endif /* HAVE_MMAP */ +#ifndef MMAP_CLEARS +#define MMAP_CLEARS 1 +#endif /* MMAP_CLEARS */ +#ifndef HAVE_MREMAP +#ifdef linux +#define HAVE_MREMAP 1 +#define _GNU_SOURCE /* Turns on mremap() definition */ +#else /* linux */ +#define HAVE_MREMAP 0 +#endif /* linux */ +#endif /* HAVE_MREMAP */ +#ifndef MALLOC_FAILURE_ACTION +#define MALLOC_FAILURE_ACTION errno = ENOMEM; +#endif /* MALLOC_FAILURE_ACTION */ +#ifndef HAVE_MORECORE +#if ONLY_MSPACES +#define HAVE_MORECORE 0 +#else /* ONLY_MSPACES */ +#define HAVE_MORECORE 1 +#endif /* ONLY_MSPACES */ +#endif /* HAVE_MORECORE */ +#if !HAVE_MORECORE +#define MORECORE_CONTIGUOUS 0 +#else /* !HAVE_MORECORE */ +#define MORECORE_DEFAULT sbrk +#ifndef MORECORE_CONTIGUOUS +#define MORECORE_CONTIGUOUS 1 +#endif /* MORECORE_CONTIGUOUS */ +#endif /* HAVE_MORECORE */ +#ifndef DEFAULT_GRANULARITY +#if (MORECORE_CONTIGUOUS || defined(WIN32)) +#define DEFAULT_GRANULARITY (0) /* 0 means to compute in init_mparams */ +#else /* MORECORE_CONTIGUOUS */ +#define DEFAULT_GRANULARITY ((size_t)64U * (size_t)1024U) +#endif /* MORECORE_CONTIGUOUS */ +#endif /* DEFAULT_GRANULARITY */ +#ifndef DEFAULT_TRIM_THRESHOLD +#ifndef MORECORE_CANNOT_TRIM +#define DEFAULT_TRIM_THRESHOLD ((size_t)2U * (size_t)1024U * (size_t)1024U) +#else /* MORECORE_CANNOT_TRIM */ +#define DEFAULT_TRIM_THRESHOLD MAX_SIZE_T +#endif /* MORECORE_CANNOT_TRIM */ +#endif /* DEFAULT_TRIM_THRESHOLD */ +#ifndef DEFAULT_MMAP_THRESHOLD +#if HAVE_MMAP +#define DEFAULT_MMAP_THRESHOLD ((size_t)256U * (size_t)1024U) +#else /* HAVE_MMAP */ +#define DEFAULT_MMAP_THRESHOLD MAX_SIZE_T +#endif /* HAVE_MMAP */ +#endif /* DEFAULT_MMAP_THRESHOLD */ +#ifndef MAX_RELEASE_CHECK_RATE +#if HAVE_MMAP +#define MAX_RELEASE_CHECK_RATE 4095 +#else +#define MAX_RELEASE_CHECK_RATE MAX_SIZE_T +#endif /* HAVE_MMAP */ +#endif /* MAX_RELEASE_CHECK_RATE */ +#ifndef USE_BUILTIN_FFS +#define USE_BUILTIN_FFS 0 +#endif /* USE_BUILTIN_FFS */ +#ifndef USE_DEV_RANDOM +#define USE_DEV_RANDOM 0 +#endif /* USE_DEV_RANDOM */ +#ifndef NO_MALLINFO +#define NO_MALLINFO 0 +#endif /* NO_MALLINFO */ +#ifndef MALLINFO_FIELD_TYPE +#define MALLINFO_FIELD_TYPE size_t +#endif /* MALLINFO_FIELD_TYPE */ +#ifndef NO_MALLOC_STATS +#define NO_MALLOC_STATS 0 +#endif /* NO_MALLOC_STATS */ +#ifndef NO_SEGMENT_TRAVERSAL +#define NO_SEGMENT_TRAVERSAL 0 +#endif /* NO_SEGMENT_TRAVERSAL */ + +/* + mallopt tuning options. SVID/XPG defines four standard parameter + numbers for mallopt, normally defined in malloc.h. None of these + are used in this malloc, so setting them has no effect. But this + malloc does support the following options. +*/ + +#define M_TRIM_THRESHOLD (-1) +#define M_GRANULARITY (-2) +#define M_MMAP_THRESHOLD (-3) + +/* ------------------------ Mallinfo declarations ------------------------ */ + +#if !NO_MALLINFO +/* + This version of malloc supports the standard SVID/XPG mallinfo + routine that returns a struct containing usage properties and + statistics. It should work on any system that has a + /usr/include/malloc.h defining struct mallinfo. The main + declaration needed is the mallinfo struct that is returned (by-copy) + by mallinfo(). The malloinfo struct contains a bunch of fields that + are not even meaningful in this version of malloc. These fields are + are instead filled by mallinfo() with other numbers that might be of + interest. + + HAVE_USR_INCLUDE_MALLOC_H should be set if you have a + /usr/include/malloc.h file that includes a declaration of struct + mallinfo. If so, it is included; else a compliant version is + declared below. These must be precisely the same for mallinfo() to + work. The original SVID version of this struct, defined on most + systems with mallinfo, declares all fields as ints. But some others + define as unsigned long. If your system defines the fields using a + type of different width than listed here, you MUST #include your + system version and #define HAVE_USR_INCLUDE_MALLOC_H. +*/ + +/* #define HAVE_USR_INCLUDE_MALLOC_H */ + +#ifdef HAVE_USR_INCLUDE_MALLOC_H +#include "/usr/include/malloc.h" +#else /* HAVE_USR_INCLUDE_MALLOC_H */ +#ifndef STRUCT_MALLINFO_DECLARED +/* HP-UX (and others?) redefines mallinfo unless _STRUCT_MALLINFO is defined */ +#define _STRUCT_MALLINFO +#define STRUCT_MALLINFO_DECLARED 1 +struct mallinfo { + MALLINFO_FIELD_TYPE arena; /* non-mmapped space allocated from system */ + MALLINFO_FIELD_TYPE ordblks; /* number of free chunks */ + MALLINFO_FIELD_TYPE smblks; /* always 0 */ + MALLINFO_FIELD_TYPE hblks; /* always 0 */ + MALLINFO_FIELD_TYPE hblkhd; /* space in mmapped regions */ + MALLINFO_FIELD_TYPE usmblks; /* maximum total allocated space */ + MALLINFO_FIELD_TYPE fsmblks; /* always 0 */ + MALLINFO_FIELD_TYPE uordblks; /* total allocated space */ + MALLINFO_FIELD_TYPE fordblks; /* total free space */ + MALLINFO_FIELD_TYPE keepcost; /* releasable (via malloc_trim) space */ +}; +#endif /* STRUCT_MALLINFO_DECLARED */ +#endif /* HAVE_USR_INCLUDE_MALLOC_H */ +#endif /* NO_MALLINFO */ + +/* + Try to persuade compilers to inline. The most critical functions for + inlining are defined as macros, so these aren't used for them. +*/ + +#ifndef FORCEINLINE + #if defined(__GNUC__) +#define FORCEINLINE __inline __attribute__ ((always_inline)) + #elif defined(_MSC_VER) + #define FORCEINLINE __forceinline + #endif +#endif +#ifndef NOINLINE + #if defined(__GNUC__) + #define NOINLINE __attribute__ ((noinline)) + #elif defined(_MSC_VER) + #define NOINLINE __declspec(noinline) + #else + #define NOINLINE + #endif +#endif + +#ifdef __cplusplus +extern "C" { +#ifndef FORCEINLINE + #define FORCEINLINE inline +#endif +#endif /* __cplusplus */ +#ifndef FORCEINLINE + #define FORCEINLINE +#endif + +#if !ONLY_MSPACES + +/* ------------------- Declarations of public routines ------------------- */ + +#ifndef USE_DL_PREFIX +#define dlcalloc calloc +#define dlfree free +#define dlmalloc malloc +#define dlmemalign memalign +#define dlposix_memalign posix_memalign +#define dlrealloc realloc +#define dlrealloc_in_place realloc_in_place +#define dlvalloc valloc +#define dlpvalloc pvalloc +#define dlmallinfo mallinfo +#define dlmallopt mallopt +#define dlmalloc_trim malloc_trim +#define dlmalloc_stats malloc_stats +#define dlmalloc_usable_size malloc_usable_size +#define dlmalloc_footprint malloc_footprint +#define dlmalloc_max_footprint malloc_max_footprint +#define dlmalloc_footprint_limit malloc_footprint_limit +#define dlmalloc_set_footprint_limit malloc_set_footprint_limit +#define dlmalloc_inspect_all malloc_inspect_all +#define dlindependent_calloc independent_calloc +#define dlindependent_comalloc independent_comalloc +#define dlbulk_free bulk_free +#endif /* USE_DL_PREFIX */ + +/* + malloc(size_t n) + Returns a pointer to a newly allocated chunk of at least n bytes, or + null if no space is available, in which case errno is set to ENOMEM + on ANSI C systems. + + If n is zero, malloc returns a minimum-sized chunk. (The minimum + size is 16 bytes on most 32bit systems, and 32 bytes on 64bit + systems.) Note that size_t is an unsigned type, so calls with + arguments that would be negative if signed are interpreted as + requests for huge amounts of space, which will often fail. The + maximum supported value of n differs across systems, but is in all + cases less than the maximum representable value of a size_t. +*/ +DLMALLOC_EXPORT void* dlmalloc(size_t); + +/* + free(void* p) + Releases the chunk of memory pointed to by p, that had been previously + allocated using malloc or a related routine such as realloc. + It has no effect if p is null. If p was not malloced or already + freed, free(p) will by default cause the current program to abort. +*/ +DLMALLOC_EXPORT void dlfree(void*); + +/* + calloc(size_t n_elements, size_t element_size); + Returns a pointer to n_elements * element_size bytes, with all locations + set to zero. +*/ +DLMALLOC_EXPORT void* dlcalloc(size_t, size_t); + +/* + realloc(void* p, size_t n) + Returns a pointer to a chunk of size n that contains the same data + as does chunk p up to the minimum of (n, p's size) bytes, or null + if no space is available. + + The returned pointer may or may not be the same as p. The algorithm + prefers extending p in most cases when possible, otherwise it + employs the equivalent of a malloc-copy-free sequence. + + If p is null, realloc is equivalent to malloc. + + If space is not available, realloc returns null, errno is set (if on + ANSI) and p is NOT freed. + + if n is for fewer bytes than already held by p, the newly unused + space is lopped off and freed if possible. realloc with a size + argument of zero (re)allocates a minimum-sized chunk. + + The old unix realloc convention of allowing the last-free'd chunk + to be used as an argument to realloc is not supported. +*/ +DLMALLOC_EXPORT void* dlrealloc(void*, size_t); + +/* + realloc_in_place(void* p, size_t n) + Resizes the space allocated for p to size n, only if this can be + done without moving p (i.e., only if there is adjacent space + available if n is greater than p's current allocated size, or n is + less than or equal to p's size). This may be used instead of plain + realloc if an alternative allocation strategy is needed upon failure + to expand space; for example, reallocation of a buffer that must be + memory-aligned or cleared. You can use realloc_in_place to trigger + these alternatives only when needed. + + Returns p if successful; otherwise null. +*/ +DLMALLOC_EXPORT void* dlrealloc_in_place(void*, size_t); + +/* + memalign(size_t alignment, size_t n); + Returns a pointer to a newly allocated chunk of n bytes, aligned + in accord with the alignment argument. + + The alignment argument should be a power of two. If the argument is + not a power of two, the nearest greater power is used. + 8-byte alignment is guaranteed by normal malloc calls, so don't + bother calling memalign with an argument of 8 or less. + + Overreliance on memalign is a sure way to fragment space. +*/ +DLMALLOC_EXPORT void* dlmemalign(size_t, size_t); + +/* + int posix_memalign(void** pp, size_t alignment, size_t n); + Allocates a chunk of n bytes, aligned in accord with the alignment + argument. Differs from memalign only in that it (1) assigns the + allocated memory to *pp rather than returning it, (2) fails and + returns EINVAL if the alignment is not a power of two (3) fails and + returns ENOMEM if memory cannot be allocated. +*/ +DLMALLOC_EXPORT int dlposix_memalign(void**, size_t, size_t); + +/* + valloc(size_t n); + Equivalent to memalign(pagesize, n), where pagesize is the page + size of the system. If the pagesize is unknown, 4096 is used. +*/ +DLMALLOC_EXPORT void* dlvalloc(size_t); + +/* + mallopt(int parameter_number, int parameter_value) + Sets tunable parameters The format is to provide a + (parameter-number, parameter-value) pair. mallopt then sets the + corresponding parameter to the argument value if it can (i.e., so + long as the value is meaningful), and returns 1 if successful else + 0. To workaround the fact that mallopt is specified to use int, + not size_t parameters, the value -1 is specially treated as the + maximum unsigned size_t value. + + SVID/XPG/ANSI defines four standard param numbers for mallopt, + normally defined in malloc.h. None of these are use in this malloc, + so setting them has no effect. But this malloc also supports other + options in mallopt. See below for details. Briefly, supported + parameters are as follows (listed defaults are for "typical" + configurations). + + Symbol param # default allowed param values + M_TRIM_THRESHOLD -1 2*1024*1024 any (-1 disables) + M_GRANULARITY -2 page size any power of 2 >= page size + M_MMAP_THRESHOLD -3 256*1024 any (or 0 if no MMAP support) +*/ +DLMALLOC_EXPORT int dlmallopt(int, int); + +/* + malloc_footprint(); + Returns the number of bytes obtained from the system. The total + number of bytes allocated by malloc, realloc etc., is less than this + value. Unlike mallinfo, this function returns only a precomputed + result, so can be called frequently to monitor memory consumption. + Even if locks are otherwise defined, this function does not use them, + so results might not be up to date. +*/ +DLMALLOC_EXPORT size_t dlmalloc_footprint(void); + +/* + malloc_max_footprint(); + Returns the maximum number of bytes obtained from the system. This + value will be greater than current footprint if deallocated space + has been reclaimed by the system. The peak number of bytes allocated + by malloc, realloc etc., is less than this value. Unlike mallinfo, + this function returns only a precomputed result, so can be called + frequently to monitor memory consumption. Even if locks are + otherwise defined, this function does not use them, so results might + not be up to date. +*/ +DLMALLOC_EXPORT size_t dlmalloc_max_footprint(void); + +/* + malloc_footprint_limit(); + Returns the number of bytes that the heap is allowed to obtain from + the system, returning the last value returned by + malloc_set_footprint_limit, or the maximum size_t value if + never set. The returned value reflects a permission. There is no + guarantee that this number of bytes can actually be obtained from + the system. +*/ +DLMALLOC_EXPORT size_t dlmalloc_footprint_limit(); + +/* + malloc_set_footprint_limit(); + Sets the maximum number of bytes to obtain from the system, causing + failure returns from malloc and related functions upon attempts to + exceed this value. The argument value may be subject to page + rounding to an enforceable limit; this actual value is returned. + Using an argument of the maximum possible size_t effectively + disables checks. If the argument is less than or equal to the + current malloc_footprint, then all future allocations that require + additional system memory will fail. However, invocation cannot + retroactively deallocate existing used memory. +*/ +DLMALLOC_EXPORT size_t dlmalloc_set_footprint_limit(size_t bytes); + +#if MALLOC_INSPECT_ALL +/* + malloc_inspect_all(void(*handler)(void *start, + void *end, + size_t used_bytes, + void* callback_arg), + void* arg); + Traverses the heap and calls the given handler for each managed + region, skipping all bytes that are (or may be) used for bookkeeping + purposes. Traversal does not include include chunks that have been + directly memory mapped. Each reported region begins at the start + address, and continues up to but not including the end address. The + first used_bytes of the region contain allocated data. If + used_bytes is zero, the region is unallocated. The handler is + invoked with the given callback argument. If locks are defined, they + are held during the entire traversal. It is a bad idea to invoke + other malloc functions from within the handler. + + For example, to count the number of in-use chunks with size greater + than 1000, you could write: + static int count = 0; + void count_chunks(void* start, void* end, size_t used, void* arg) { + if (used >= 1000) ++count; + } + then: + malloc_inspect_all(count_chunks, NULL); + + malloc_inspect_all is compiled only if MALLOC_INSPECT_ALL is defined. +*/ +DLMALLOC_EXPORT void dlmalloc_inspect_all(void(*handler)(void*, void *, size_t, void*), + void* arg); + +#endif /* MALLOC_INSPECT_ALL */ + +#if !NO_MALLINFO +/* + mallinfo() + Returns (by copy) a struct containing various summary statistics: + + arena: current total non-mmapped bytes allocated from system + ordblks: the number of free chunks + smblks: always zero. + hblks: current number of mmapped regions + hblkhd: total bytes held in mmapped regions + usmblks: the maximum total allocated space. This will be greater + than current total if trimming has occurred. + fsmblks: always zero + uordblks: current total allocated space (normal or mmapped) + fordblks: total free space + keepcost: the maximum number of bytes that could ideally be released + back to system via malloc_trim. ("ideally" means that + it ignores page restrictions etc.) + + Because these fields are ints, but internal bookkeeping may + be kept as longs, the reported values may wrap around zero and + thus be inaccurate. +*/ +DLMALLOC_EXPORT struct mallinfo dlmallinfo(void); +#endif /* NO_MALLINFO */ + +/* + independent_calloc(size_t n_elements, size_t element_size, void* chunks[]); + + independent_calloc is similar to calloc, but instead of returning a + single cleared space, it returns an array of pointers to n_elements + independent elements that can hold contents of size elem_size, each + of which starts out cleared, and can be independently freed, + realloc'ed etc. The elements are guaranteed to be adjacently + allocated (this is not guaranteed to occur with multiple callocs or + mallocs), which may also improve cache locality in some + applications. + + The "chunks" argument is optional (i.e., may be null, which is + probably the most typical usage). If it is null, the returned array + is itself dynamically allocated and should also be freed when it is + no longer needed. Otherwise, the chunks array must be of at least + n_elements in length. It is filled in with the pointers to the + chunks. + + In either case, independent_calloc returns this pointer array, or + null if the allocation failed. If n_elements is zero and "chunks" + is null, it returns a chunk representing an array with zero elements + (which should be freed if not wanted). + + Each element must be freed when it is no longer needed. This can be + done all at once using bulk_free. + + independent_calloc simplifies and speeds up implementations of many + kinds of pools. It may also be useful when constructing large data + structures that initially have a fixed number of fixed-sized nodes, + but the number is not known at compile time, and some of the nodes + may later need to be freed. For example: + + struct Node { int item; struct Node* next; }; + + struct Node* build_list() { + struct Node** pool; + int n = read_number_of_nodes_needed(); + if (n <= 0) return 0; + pool = (struct Node**)(independent_calloc(n, sizeof(struct Node), 0); + if (pool == 0) die(); + // organize into a linked list... + struct Node* first = pool[0]; + for (i = 0; i < n-1; ++i) + pool[i]->next = pool[i+1]; + free(pool); // Can now free the array (or not, if it is needed later) + return first; + } +*/ +DLMALLOC_EXPORT void** dlindependent_calloc(size_t, size_t, void**); + +/* + independent_comalloc(size_t n_elements, size_t sizes[], void* chunks[]); + + independent_comalloc allocates, all at once, a set of n_elements + chunks with sizes indicated in the "sizes" array. It returns + an array of pointers to these elements, each of which can be + independently freed, realloc'ed etc. The elements are guaranteed to + be adjacently allocated (this is not guaranteed to occur with + multiple callocs or mallocs), which may also improve cache locality + in some applications. + + The "chunks" argument is optional (i.e., may be null). If it is null + the returned array is itself dynamically allocated and should also + be freed when it is no longer needed. Otherwise, the chunks array + must be of at least n_elements in length. It is filled in with the + pointers to the chunks. + + In either case, independent_comalloc returns this pointer array, or + null if the allocation failed. If n_elements is zero and chunks is + null, it returns a chunk representing an array with zero elements + (which should be freed if not wanted). + + Each element must be freed when it is no longer needed. This can be + done all at once using bulk_free. + + independent_comallac differs from independent_calloc in that each + element may have a different size, and also that it does not + automatically clear elements. + + independent_comalloc can be used to speed up allocation in cases + where several structs or objects must always be allocated at the + same time. For example: + + struct Head { ... } + struct Foot { ... } + + void send_message(char* msg) { + int msglen = strlen(msg); + size_t sizes[3] = { sizeof(struct Head), msglen, sizeof(struct Foot) }; + void* chunks[3]; + if (independent_comalloc(3, sizes, chunks) == 0) + die(); + struct Head* head = (struct Head*)(chunks[0]); + char* body = (char*)(chunks[1]); + struct Foot* foot = (struct Foot*)(chunks[2]); + // ... + } + + In general though, independent_comalloc is worth using only for + larger values of n_elements. For small values, you probably won't + detect enough difference from series of malloc calls to bother. + + Overuse of independent_comalloc can increase overall memory usage, + since it cannot reuse existing noncontiguous small chunks that + might be available for some of the elements. +*/ +DLMALLOC_EXPORT void** dlindependent_comalloc(size_t, size_t*, void**); + +/* + bulk_free(void* array[], size_t n_elements) + Frees and clears (sets to null) each non-null pointer in the given + array. This is likely to be faster than freeing them one-by-one. + If footers are used, pointers that have been allocated in different + mspaces are not freed or cleared, and the count of all such pointers + is returned. For large arrays of pointers with poor locality, it + may be worthwhile to sort this array before calling bulk_free. +*/ +DLMALLOC_EXPORT size_t dlbulk_free(void**, size_t n_elements); + +/* + pvalloc(size_t n); + Equivalent to valloc(minimum-page-that-holds(n)), that is, + round up n to nearest pagesize. + */ +DLMALLOC_EXPORT void* dlpvalloc(size_t); + +/* + malloc_trim(size_t pad); + + If possible, gives memory back to the system (via negative arguments + to sbrk) if there is unused memory at the `high' end of the malloc + pool or in unused MMAP segments. You can call this after freeing + large blocks of memory to potentially reduce the system-level memory + requirements of a program. However, it cannot guarantee to reduce + memory. Under some allocation patterns, some large free blocks of + memory will be locked between two used chunks, so they cannot be + given back to the system. + + The `pad' argument to malloc_trim represents the amount of free + trailing space to leave untrimmed. If this argument is zero, only + the minimum amount of memory to maintain internal data structures + will be left. Non-zero arguments can be supplied to maintain enough + trailing space to service future expected allocations without having + to re-obtain memory from the system. + + Malloc_trim returns 1 if it actually released any memory, else 0. +*/ +DLMALLOC_EXPORT int dlmalloc_trim(size_t); + +/* + malloc_stats(); + Prints on stderr the amount of space obtained from the system (both + via sbrk and mmap), the maximum amount (which may be more than + current if malloc_trim and/or munmap got called), and the current + number of bytes allocated via malloc (or realloc, etc) but not yet + freed. Note that this is the number of bytes allocated, not the + number requested. It will be larger than the number requested + because of alignment and bookkeeping overhead. Because it includes + alignment wastage as being in use, this figure may be greater than + zero even when no user-level chunks are allocated. + + The reported current and maximum system memory can be inaccurate if + a program makes other calls to system memory allocation functions + (normally sbrk) outside of malloc. + + malloc_stats prints only the most commonly interesting statistics. + More information can be obtained by calling mallinfo. +*/ +DLMALLOC_EXPORT void dlmalloc_stats(void); + +#endif /* ONLY_MSPACES */ + +/* + malloc_usable_size(void* p); + + Returns the number of bytes you can actually use in + an allocated chunk, which may be more than you requested (although + often not) due to alignment and minimum size constraints. + You can use this many bytes without worrying about + overwriting other allocated objects. This is not a particularly great + programming practice. malloc_usable_size can be more useful in + debugging and assertions, for example: + + p = malloc(n); + assert(malloc_usable_size(p) >= 256); +*/ +size_t dlmalloc_usable_size(void*); + +#if MSPACES + +/* + mspace is an opaque type representing an independent + region of space that supports mspace_malloc, etc. +*/ +typedef void* mspace; + +/* + create_mspace creates and returns a new independent space with the + given initial capacity, or, if 0, the default granularity size. It + returns null if there is no system memory available to create the + space. If argument locked is non-zero, the space uses a separate + lock to control access. The capacity of the space will grow + dynamically as needed to service mspace_malloc requests. You can + control the sizes of incremental increases of this space by + compiling with a different DEFAULT_GRANULARITY or dynamically + setting with mallopt(M_GRANULARITY, value). +*/ +DLMALLOC_EXPORT mspace create_mspace(size_t capacity, int locked); + +/* + destroy_mspace destroys the given space, and attempts to return all + of its memory back to the system, returning the total number of + bytes freed. After destruction, the results of access to all memory + used by the space become undefined. +*/ +DLMALLOC_EXPORT size_t destroy_mspace(mspace msp); + +/* + create_mspace_with_base uses the memory supplied as the initial base + of a new mspace. Part (less than 128*sizeof(size_t) bytes) of this + space is used for bookkeeping, so the capacity must be at least this + large. (Otherwise 0 is returned.) When this initial space is + exhausted, additional memory will be obtained from the system. + Destroying this space will deallocate all additionally allocated + space (if possible) but not the initial base. +*/ +DLMALLOC_EXPORT mspace create_mspace_with_base(void* base, size_t capacity, int locked); + +/* + mspace_track_large_chunks controls whether requests for large chunks + are allocated in their own untracked mmapped regions, separate from + others in this mspace. By default large chunks are not tracked, + which reduces fragmentation. However, such chunks are not + necessarily released to the system upon destroy_mspace. Enabling + tracking by setting to true may increase fragmentation, but avoids + leakage when relying on destroy_mspace to release all memory + allocated using this space. The function returns the previous + setting. +*/ +DLMALLOC_EXPORT int mspace_track_large_chunks(mspace msp, int enable); + + +/* + mspace_malloc behaves as malloc, but operates within + the given space. +*/ +DLMALLOC_EXPORT void* mspace_malloc(mspace msp, size_t bytes); + +/* + mspace_free behaves as free, but operates within + the given space. + + If compiled with FOOTERS==1, mspace_free is not actually needed. + free may be called instead of mspace_free because freed chunks from + any space are handled by their originating spaces. +*/ +DLMALLOC_EXPORT void mspace_free(mspace msp, void* mem); + +/* + mspace_realloc behaves as realloc, but operates within + the given space. + + If compiled with FOOTERS==1, mspace_realloc is not actually + needed. realloc may be called instead of mspace_realloc because + realloced chunks from any space are handled by their originating + spaces. +*/ +DLMALLOC_EXPORT void* mspace_realloc(mspace msp, void* mem, size_t newsize); + +/* + mspace_calloc behaves as calloc, but operates within + the given space. +*/ +DLMALLOC_EXPORT void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size); + +/* + mspace_memalign behaves as memalign, but operates within + the given space. +*/ +DLMALLOC_EXPORT void* mspace_memalign(mspace msp, size_t alignment, size_t bytes); + +/* + mspace_independent_calloc behaves as independent_calloc, but + operates within the given space. +*/ +DLMALLOC_EXPORT void** mspace_independent_calloc(mspace msp, size_t n_elements, + size_t elem_size, void* chunks[]); + +/* + mspace_independent_comalloc behaves as independent_comalloc, but + operates within the given space. +*/ +DLMALLOC_EXPORT void** mspace_independent_comalloc(mspace msp, size_t n_elements, + size_t sizes[], void* chunks[]); + +/* + mspace_footprint() returns the number of bytes obtained from the + system for this space. +*/ +DLMALLOC_EXPORT size_t mspace_footprint(mspace msp); + +/* + mspace_max_footprint() returns the peak number of bytes obtained from the + system for this space. +*/ +DLMALLOC_EXPORT size_t mspace_max_footprint(mspace msp); + + +#if !NO_MALLINFO +/* + mspace_mallinfo behaves as mallinfo, but reports properties of + the given space. +*/ +DLMALLOC_EXPORT struct mallinfo mspace_mallinfo(mspace msp); +#endif /* NO_MALLINFO */ + +/* + malloc_usable_size(void* p) behaves the same as malloc_usable_size; +*/ +DLMALLOC_EXPORT size_t mspace_usable_size(void* mem); + +/* + mspace_malloc_stats behaves as malloc_stats, but reports + properties of the given space. +*/ +DLMALLOC_EXPORT void mspace_malloc_stats(mspace msp); + +/* + mspace_trim behaves as malloc_trim, but + operates within the given space. +*/ +DLMALLOC_EXPORT int mspace_trim(mspace msp, size_t pad); + +/* + An alias for mallopt. +*/ +DLMALLOC_EXPORT int mspace_mallopt(int, int); + +#endif /* MSPACES */ + +#ifdef __cplusplus +} /* end of extern "C" */ +#endif /* __cplusplus */ + +/* + ======================================================================== + To make a fully customizable malloc.h header file, cut everything + above this line, put into file malloc.h, edit to suit, and #include it + on the next line, as well as in programs that use this malloc. + ======================================================================== +*/ + +/* #include "malloc.h" */ + +/*------------------------------ internal #includes ---------------------- */ + +#ifdef _MSC_VER +#pragma warning( disable : 4146 ) /* no "unsigned" warnings */ +#endif /* _MSC_VER */ +#if !NO_MALLOC_STATS +#include <stdio.h> /* for printing in malloc_stats */ +#endif /* NO_MALLOC_STATS */ +#ifndef LACKS_ERRNO_H +#include <errno.h> /* for MALLOC_FAILURE_ACTION */ +#endif /* LACKS_ERRNO_H */ +#ifdef DEBUG +#if ABORT_ON_ASSERT_FAILURE +#undef assert +#define assert(x) if(!(x)) ABORT +#else /* ABORT_ON_ASSERT_FAILURE */ +#include <assert.h> +#endif /* ABORT_ON_ASSERT_FAILURE */ +#else /* DEBUG */ +#ifndef assert +#define assert(x) +#endif +#define DEBUG 0 +#endif /* DEBUG */ +#if !defined(WIN32) && !defined(LACKS_TIME_H) +#include <time.h> /* for magic initialization */ +#endif /* WIN32 */ +#ifndef LACKS_STDLIB_H +#include <stdlib.h> /* for abort() */ +#endif /* LACKS_STDLIB_H */ +#ifndef LACKS_STRING_H +#include <string.h> /* for memset etc */ +#endif /* LACKS_STRING_H */ +#if USE_BUILTIN_FFS +#ifndef LACKS_STRINGS_H +#include <strings.h> /* for ffs */ +#endif /* LACKS_STRINGS_H */ +#endif /* USE_BUILTIN_FFS */ +#if HAVE_MMAP +#ifndef LACKS_SYS_MMAN_H +/* On some versions of linux, mremap decl in mman.h needs __USE_GNU set */ +#if (defined(linux) && !defined(__USE_GNU)) +#define __USE_GNU 1 +#include <sys/mman.h> /* for mmap */ +#undef __USE_GNU +#else +#include <sys/mman.h> /* for mmap */ +#endif /* linux */ +#endif /* LACKS_SYS_MMAN_H */ +#ifndef LACKS_FCNTL_H +#include <fcntl.h> +#endif /* LACKS_FCNTL_H */ +#endif /* HAVE_MMAP */ +#ifndef LACKS_UNISTD_H +#include <unistd.h> /* for sbrk, sysconf */ +#else /* LACKS_UNISTD_H */ +#if !defined(__FreeBSD__) && !defined(__OpenBSD__) && !defined(__NetBSD__) +extern void* sbrk(ptrdiff_t); +#endif /* FreeBSD etc */ +#endif /* LACKS_UNISTD_H */ + +/* Declarations for locking */ +#if USE_LOCKS +#ifndef WIN32 +#if defined (__SVR4) && defined (__sun) /* solaris */ +#include <thread.h> +#elif !defined(LACKS_SCHED_H) +#include <sched.h> +#endif /* solaris or LACKS_SCHED_H */ +#if (defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0) || !USE_SPIN_LOCKS +#include <pthread.h> +#endif /* USE_RECURSIVE_LOCKS ... */ +#elif defined(_MSC_VER) +#ifndef _M_AMD64 +/* These are already defined on AMD64 builds */ +#ifdef __cplusplus +extern "C" { +#endif /* __cplusplus */ +LONG __cdecl _InterlockedCompareExchange(LONG volatile *Dest, LONG Exchange, LONG Comp); +LONG __cdecl _InterlockedExchange(LONG volatile *Target, LONG Value); +#ifdef __cplusplus +} +#endif /* __cplusplus */ +#endif /* _M_AMD64 */ +#pragma intrinsic (_InterlockedCompareExchange) +#pragma intrinsic (_InterlockedExchange) +#define interlockedcompareexchange _InterlockedCompareExchange +#define interlockedexchange _InterlockedExchange +#elif defined(WIN32) && defined(__GNUC__) +#define interlockedcompareexchange(a, b, c) __sync_val_compare_and_swap(a, c, b) +#define interlockedexchange __sync_lock_test_and_set +#endif /* Win32 */ +#endif /* USE_LOCKS */ + +/* Declarations for bit scanning on win32 */ +#if defined(_MSC_VER) && _MSC_VER>=1300 +#ifndef BitScanForward /* Try to avoid pulling in WinNT.h */ +#ifdef __cplusplus +extern "C" { +#endif /* __cplusplus */ +unsigned char _BitScanForward(unsigned long *index, unsigned long mask); +unsigned char _BitScanReverse(unsigned long *index, unsigned long mask); +#ifdef __cplusplus +} +#endif /* __cplusplus */ + +#define BitScanForward _BitScanForward +#define BitScanReverse _BitScanReverse +#pragma intrinsic(_BitScanForward) +#pragma intrinsic(_BitScanReverse) +#endif /* BitScanForward */ +#endif /* defined(_MSC_VER) && _MSC_VER>=1300 */ + +#ifndef WIN32 +#ifndef malloc_getpagesize +# ifdef _SC_PAGESIZE /* some SVR4 systems omit an underscore */ +# ifndef _SC_PAGE_SIZE +# define _SC_PAGE_SIZE _SC_PAGESIZE +# endif +# endif +# ifdef _SC_PAGE_SIZE +# define malloc_getpagesize sysconf(_SC_PAGE_SIZE) +# else +# if defined(BSD) || defined(DGUX) || defined(HAVE_GETPAGESIZE) + extern size_t getpagesize(); +# define malloc_getpagesize getpagesize() +# else +# ifdef WIN32 /* use supplied emulation of getpagesize */ +# define malloc_getpagesize getpagesize() +# else +# ifndef LACKS_SYS_PARAM_H +# include <sys/param.h> +# endif +# ifdef EXEC_PAGESIZE +# define malloc_getpagesize EXEC_PAGESIZE +# else +# ifdef NBPG +# ifndef CLSIZE +# define malloc_getpagesize NBPG +# else +# define malloc_getpagesize (NBPG * CLSIZE) +# endif +# else +# ifdef NBPC +# define malloc_getpagesize NBPC +# else +# ifdef PAGESIZE +# define malloc_getpagesize PAGESIZE +# else /* just guess */ +# define malloc_getpagesize ((size_t)4096U) +# endif +# endif +# endif +# endif +# endif +# endif +# endif +#endif +#endif + +/* ------------------- size_t and alignment properties -------------------- */ + +/* The byte and bit size of a size_t */ +#define SIZE_T_SIZE (sizeof(size_t)) +#define SIZE_T_BITSIZE (sizeof(size_t) << 3) + +/* Some constants coerced to size_t */ +/* Annoying but necessary to avoid errors on some platforms */ +#define SIZE_T_ZERO ((size_t)0) +#define SIZE_T_ONE ((size_t)1) +#define SIZE_T_TWO ((size_t)2) +#define SIZE_T_FOUR ((size_t)4) +#define TWO_SIZE_T_SIZES (SIZE_T_SIZE<<1) +#define FOUR_SIZE_T_SIZES (SIZE_T_SIZE<<2) +#define SIX_SIZE_T_SIZES (FOUR_SIZE_T_SIZES+TWO_SIZE_T_SIZES) +#define HALF_MAX_SIZE_T (MAX_SIZE_T / 2U) + +/* The bit mask value corresponding to MALLOC_ALIGNMENT */ +#define CHUNK_ALIGN_MASK (MALLOC_ALIGNMENT - SIZE_T_ONE) + +/* True if address a has acceptable alignment */ +#define is_aligned(A) (((size_t)((A)) & (CHUNK_ALIGN_MASK)) == 0) + +/* the number of bytes to offset an address to align it */ +#define align_offset(A)\ + ((((size_t)(A) & CHUNK_ALIGN_MASK) == 0)? 0 :\ + ((MALLOC_ALIGNMENT - ((size_t)(A) & CHUNK_ALIGN_MASK)) & CHUNK_ALIGN_MASK)) + +/* -------------------------- MMAP preliminaries ------------------------- */ + +/* + If HAVE_MORECORE or HAVE_MMAP are false, we just define calls and + checks to fail so compiler optimizer can delete code rather than + using so many "#if"s. +*/ + + +/* MORECORE and MMAP must return MFAIL on failure */ +#define MFAIL ((void*)(MAX_SIZE_T)) +#define CMFAIL ((char*)(MFAIL)) /* defined for convenience */ + +#if HAVE_MMAP + +#ifndef WIN32 +#define MUNMAP_DEFAULT(a, s) munmap((a), (s)) +#define MMAP_PROT (PROT_READ|PROT_WRITE) +#if !defined(MAP_ANONYMOUS) && defined(MAP_ANON) +#define MAP_ANONYMOUS MAP_ANON +#endif /* MAP_ANON */ +#ifdef MAP_ANONYMOUS +#define MMAP_FLAGS (MAP_PRIVATE|MAP_ANONYMOUS) +#define MMAP_DEFAULT(s) mmap(0, (s), MMAP_PROT, MMAP_FLAGS, -1, 0) +#else /* MAP_ANONYMOUS */ +/* + Nearly all versions of mmap support MAP_ANONYMOUS, so the following + is unlikely to be needed, but is supplied just in case. +*/ +#define MMAP_FLAGS (MAP_PRIVATE) +static int dev_zero_fd = -1; /* Cached file descriptor for /dev/zero. */ +#define MMAP_DEFAULT(s) ((dev_zero_fd < 0) ? \ + (dev_zero_fd = open("/dev/zero", O_RDWR), \ + mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0)) : \ + mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0)) +#endif /* MAP_ANONYMOUS */ + +#define DIRECT_MMAP_DEFAULT(s) MMAP_DEFAULT(s) + +#else /* WIN32 */ + +/* Win32 MMAP via VirtualAlloc */ +static FORCEINLINE void* win32mmap(size_t size) { + void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT, PAGE_READWRITE); + return (ptr != 0)? ptr: MFAIL; +} + +/* For direct MMAP, use MEM_TOP_DOWN to minimize interference */ +static FORCEINLINE void* win32direct_mmap(size_t size) { + void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT|MEM_TOP_DOWN, + PAGE_READWRITE); + return (ptr != 0)? ptr: MFAIL; +} + +/* This function supports releasing coalesed segments */ +static FORCEINLINE int win32munmap(void* ptr, size_t size) { + MEMORY_BASIC_INFORMATION minfo; + char* cptr = (char*)ptr; + while (size) { + if (VirtualQuery(cptr, &minfo, sizeof(minfo)) == 0) + return -1; + if (minfo.BaseAddress != cptr || minfo.AllocationBase != cptr || + minfo.State != MEM_COMMIT || minfo.RegionSize > size) + return -1; + if (VirtualFree(cptr, 0, MEM_RELEASE) == 0) + return -1; + cptr += minfo.RegionSize; + size -= minfo.RegionSize; + } + return 0; +} + +#define MMAP_DEFAULT(s) win32mmap(s) +#define MUNMAP_DEFAULT(a, s) win32munmap((a), (s)) +#define DIRECT_MMAP_DEFAULT(s) win32direct_mmap(s) +#endif /* WIN32 */ +#endif /* HAVE_MMAP */ + +#if HAVE_MREMAP +#ifndef WIN32 +#define MREMAP_DEFAULT(addr, osz, nsz, mv) mremap((addr), (osz), (nsz), (mv)) +#endif /* WIN32 */ +#endif /* HAVE_MREMAP */ + +/** + * Define CALL_MORECORE + */ +#if HAVE_MORECORE + #ifdef MORECORE + #define CALL_MORECORE(S) MORECORE(S) + #else /* MORECORE */ + #define CALL_MORECORE(S) MORECORE_DEFAULT(S) + #endif /* MORECORE */ +#else /* HAVE_MORECORE */ + #define CALL_MORECORE(S) MFAIL +#endif /* HAVE_MORECORE */ + +/** + * Define CALL_MMAP/CALL_MUNMAP/CALL_DIRECT_MMAP + */ +#if HAVE_MMAP + #define USE_MMAP_BIT (SIZE_T_ONE) + + #ifdef MMAP + #define CALL_MMAP(s) MMAP(s) + #else /* MMAP */ + #define CALL_MMAP(s) MMAP_DEFAULT(s) + #endif /* MMAP */ + #ifdef MUNMAP + #define CALL_MUNMAP(a, s) MUNMAP((a), (s)) + #else /* MUNMAP */ + #define CALL_MUNMAP(a, s) MUNMAP_DEFAULT((a), (s)) + #endif /* MUNMAP */ + #ifdef DIRECT_MMAP + #define CALL_DIRECT_MMAP(s) DIRECT_MMAP(s) + #else /* DIRECT_MMAP */ + #define CALL_DIRECT_MMAP(s) DIRECT_MMAP_DEFAULT(s) + #endif /* DIRECT_MMAP */ +#else /* HAVE_MMAP */ + #define USE_MMAP_BIT (SIZE_T_ZERO) + + #define MMAP(s) MFAIL + #define MUNMAP(a, s) (-1) + #define DIRECT_MMAP(s) MFAIL + #define CALL_DIRECT_MMAP(s) DIRECT_MMAP(s) + #define CALL_MMAP(s) MMAP(s) + #define CALL_MUNMAP(a, s) MUNMAP((a), (s)) +#endif /* HAVE_MMAP */ + +/** + * Define CALL_MREMAP + */ +#if HAVE_MMAP && HAVE_MREMAP + #ifdef MREMAP + #define CALL_MREMAP(addr, osz, nsz, mv) MREMAP((addr), (osz), (nsz), (mv)) + #else /* MREMAP */ + #define CALL_MREMAP(addr, osz, nsz, mv) MREMAP_DEFAULT((addr), (osz), (nsz), (mv)) + #endif /* MREMAP */ +#else /* HAVE_MMAP && HAVE_MREMAP */ + #define CALL_MREMAP(addr, osz, nsz, mv) MFAIL +#endif /* HAVE_MMAP && HAVE_MREMAP */ + +/* mstate bit set if continguous morecore disabled or failed */ +#define USE_NONCONTIGUOUS_BIT (4U) + +/* segment bit set in create_mspace_with_base */ +#define EXTERN_BIT (8U) + + +/* --------------------------- Lock preliminaries ------------------------ */ + +/* + When locks are defined, there is one global lock, plus + one per-mspace lock. + + The global lock_ensures that mparams.magic and other unique + mparams values are initialized only once. It also protects + sequences of calls to MORECORE. In many cases sys_alloc requires + two calls, that should not be interleaved with calls by other + threads. This does not protect against direct calls to MORECORE + by other threads not using this lock, so there is still code to + cope the best we can on interference. + + Per-mspace locks surround calls to malloc, free, etc. + By default, locks are simple non-reentrant mutexes. + + Because lock-protected regions generally have bounded times, it is + OK to use the supplied simple spinlocks. Spinlocks are likely to + improve performance for lightly contended applications, but worsen + performance under heavy contention. + + If USE_LOCKS is > 1, the definitions of lock routines here are + bypassed, in which case you will need to define the type MLOCK_T, + and at least INITIAL_LOCK, DESTROY_LOCK, ACQUIRE_LOCK, RELEASE_LOCK + and TRY_LOCK. You must also declare a + static MLOCK_T malloc_global_mutex = { initialization values };. + +*/ + +#if !USE_LOCKS +#define USE_LOCK_BIT (0U) +#define INITIAL_LOCK(l) (0) +#define DESTROY_LOCK(l) (0) +#define ACQUIRE_MALLOC_GLOBAL_LOCK() +#define RELEASE_MALLOC_GLOBAL_LOCK() + +#else +#if USE_LOCKS > 1 +/* ----------------------- User-defined locks ------------------------ */ +/* Define your own lock implementation here */ +/* #define INITIAL_LOCK(lk) ... */ +/* #define DESTROY_LOCK(lk) ... */ +/* #define ACQUIRE_LOCK(lk) ... */ +/* #define RELEASE_LOCK(lk) ... */ +/* #define TRY_LOCK(lk) ... */ +/* static MLOCK_T malloc_global_mutex = ... */ + +#elif USE_SPIN_LOCKS + +/* First, define CAS_LOCK and CLEAR_LOCK on ints */ +/* Note CAS_LOCK defined to return 0 on success */ + +#if defined(__GNUC__)&& (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 1)) +#define CAS_LOCK(sl) __sync_lock_test_and_set(sl, 1) +#define CLEAR_LOCK(sl) __sync_lock_release(sl) + +#elif (defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))) +/* Custom spin locks for older gcc on x86 */ +static FORCEINLINE int x86_cas_lock(int *sl) { + int ret; + int val = 1; + int cmp = 0; + __asm__ __volatile__ ("lock; cmpxchgl %1, %2" + : "=a" (ret) + : "r" (val), "m" (*(sl)), "0"(cmp) + : "memory", "cc"); + return ret; +} + +static FORCEINLINE void x86_clear_lock(int* sl) { + assert(*sl != 0); + int prev = 0; + int ret; + __asm__ __volatile__ ("lock; xchgl %0, %1" + : "=r" (ret) + : "m" (*(sl)), "0"(prev) + : "memory"); +} + +#define CAS_LOCK(sl) x86_cas_lock(sl) +#define CLEAR_LOCK(sl) x86_clear_lock(sl) + +#else /* Win32 MSC */ +#define CAS_LOCK(sl) interlockedexchange(sl, 1) +#define CLEAR_LOCK(sl) interlockedexchange (sl, 0) + +#endif /* ... gcc spins locks ... */ + +/* How to yield for a spin lock */ +#define SPINS_PER_YIELD 63 +#if defined(_MSC_VER) +#define SLEEP_EX_DURATION 50 /* delay for yield/sleep */ +#define SPIN_LOCK_YIELD SleepEx(SLEEP_EX_DURATION, FALSE) +#elif defined (__SVR4) && defined (__sun) /* solaris */ +#define SPIN_LOCK_YIELD thr_yield(); +#elif !defined(LACKS_SCHED_H) +#define SPIN_LOCK_YIELD sched_yield(); +#else +#define SPIN_LOCK_YIELD +#endif /* ... yield ... */ + +#if !defined(USE_RECURSIVE_LOCKS) || USE_RECURSIVE_LOCKS == 0 +/* Plain spin locks use single word (embedded in malloc_states) */ +static int spin_acquire_lock(int *sl) { + int spins = 0; + while (*(volatile int *)sl != 0 || CAS_LOCK(sl)) { + if ((++spins & SPINS_PER_YIELD) == 0) { + SPIN_LOCK_YIELD; + } + } + return 0; +} + +#define MLOCK_T int +#define TRY_LOCK(sl) !CAS_LOCK(sl) +#define RELEASE_LOCK(sl) CLEAR_LOCK(sl) +#define ACQUIRE_LOCK(sl) (CAS_LOCK(sl)? spin_acquire_lock(sl) : 0) +#define INITIAL_LOCK(sl) (*sl = 0) +#define DESTROY_LOCK(sl) (0) +static MLOCK_T malloc_global_mutex = 0; + +#else /* USE_RECURSIVE_LOCKS */ +/* types for lock owners */ +#ifdef WIN32 +#define THREAD_ID_T DWORD +#define CURRENT_THREAD GetCurrentThreadId() +#define EQ_OWNER(X,Y) ((X) == (Y)) +#else +/* + Note: the following assume that pthread_t is a type that can be + initialized to (casted) zero. If this is not the case, you will need to + somehow redefine these or not use spin locks. +*/ +#define THREAD_ID_T pthread_t +#define CURRENT_THREAD pthread_self() +#define EQ_OWNER(X,Y) pthread_equal(X, Y) +#endif + +struct malloc_recursive_lock { + int sl; + unsigned int c; + THREAD_ID_T threadid; +}; + +#define MLOCK_T struct malloc_recursive_lock +static MLOCK_T malloc_global_mutex = { 0, 0, (THREAD_ID_T)0}; + +static FORCEINLINE void recursive_release_lock(MLOCK_T *lk) { + assert(lk->sl != 0); + if (--lk->c == 0) { + CLEAR_LOCK(&lk->sl); + } +} + +static FORCEINLINE int recursive_acquire_lock(MLOCK_T *lk) { + THREAD_ID_T mythreadid = CURRENT_THREAD; + int spins = 0; + for (;;) { + if (*((volatile int *)(&lk->sl)) == 0) { + if (!CAS_LOCK(&lk->sl)) { + lk->threadid = mythreadid; + lk->c = 1; + return 0; + } + } + else if (EQ_OWNER(lk->threadid, mythreadid)) { + ++lk->c; + return 0; + } + if ((++spins & SPINS_PER_YIELD) == 0) { + SPIN_LOCK_YIELD; + } + } +} + +static FORCEINLINE int recursive_try_lock(MLOCK_T *lk) { + THREAD_ID_T mythreadid = CURRENT_THREAD; + if (*((volatile int *)(&lk->sl)) == 0) { + if (!CAS_LOCK(&lk->sl)) { + lk->threadid = mythreadid; + lk->c = 1; + return 1; + } + } + else if (EQ_OWNER(lk->threadid, mythreadid)) { + ++lk->c; + return 1; + } + return 0; +} + +#define RELEASE_LOCK(lk) recursive_release_lock(lk) +#define TRY_LOCK(lk) recursive_try_lock(lk) +#define ACQUIRE_LOCK(lk) recursive_acquire_lock(lk) +#define INITIAL_LOCK(lk) ((lk)->threadid = (THREAD_ID_T)0, (lk)->sl = 0, (lk)->c = 0) +#define DESTROY_LOCK(lk) (0) +#endif /* USE_RECURSIVE_LOCKS */ + +#elif defined(WIN32) /* Win32 critical sections */ +#define MLOCK_T CRITICAL_SECTION +#define ACQUIRE_LOCK(lk) (EnterCriticalSection(lk), 0) +#define RELEASE_LOCK(lk) LeaveCriticalSection(lk) +#define TRY_LOCK(lk) TryEnterCriticalSection(lk) +#define INITIAL_LOCK(lk) (!InitializeCriticalSectionAndSpinCount((lk), 0x80000000|4000)) +#define DESTROY_LOCK(lk) (DeleteCriticalSection(lk), 0) +#define NEED_GLOBAL_LOCK_INIT + +static MLOCK_T malloc_global_mutex; +static volatile long malloc_global_mutex_status; + +/* Use spin loop to initialize global lock */ +static void init_malloc_global_mutex() { + for (;;) { + long stat = malloc_global_mutex_status; + if (stat > 0) + return; + /* transition to < 0 while initializing, then to > 0) */ + if (stat == 0 && + interlockedcompareexchange(&malloc_global_mutex_status, -1, 0) == 0) { + InitializeCriticalSection(&malloc_global_mutex); + interlockedexchange(&malloc_global_mutex_status,1); + return; + } + SleepEx(0, FALSE); + } +} + +#else /* pthreads-based locks */ +#define MLOCK_T pthread_mutex_t +#define ACQUIRE_LOCK(lk) pthread_mutex_lock(lk) +#define RELEASE_LOCK(lk) pthread_mutex_unlock(lk) +#define TRY_LOCK(lk) (!pthread_mutex_trylock(lk)) +#define INITIAL_LOCK(lk) pthread_init_lock(lk) +#define DESTROY_LOCK(lk) pthread_mutex_destroy(lk) + +#if defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0 && defined(linux) && !defined(PTHREAD_MUTEX_RECURSIVE) +/* Cope with old-style linux recursive lock initialization by adding */ +/* skipped internal declaration from pthread.h */ +extern int pthread_mutexattr_setkind_np __P ((pthread_mutexattr_t *__attr, + int __kind)); +#define PTHREAD_MUTEX_RECURSIVE PTHREAD_MUTEX_RECURSIVE_NP +#define pthread_mutexattr_settype(x,y) pthread_mutexattr_setkind_np(x,y) +#endif /* USE_RECURSIVE_LOCKS ... */ + +static MLOCK_T malloc_global_mutex = PTHREAD_MUTEX_INITIALIZER; + +static int pthread_init_lock (MLOCK_T *lk) { + pthread_mutexattr_t attr; + if (pthread_mutexattr_init(&attr)) return 1; +#if defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0 + if (pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_RECURSIVE)) return 1; +#endif + if (pthread_mutex_init(lk, &attr)) return 1; + if (pthread_mutexattr_destroy(&attr)) return 1; + return 0; +} + +#endif /* ... lock types ... */ + +/* Common code for all lock types */ +#define USE_LOCK_BIT (2U) + +#ifndef ACQUIRE_MALLOC_GLOBAL_LOCK +#define ACQUIRE_MALLOC_GLOBAL_LOCK() ACQUIRE_LOCK(&malloc_global_mutex); +#endif + +#ifndef RELEASE_MALLOC_GLOBAL_LOCK +#define RELEASE_MALLOC_GLOBAL_LOCK() RELEASE_LOCK(&malloc_global_mutex); +#endif + +#endif /* USE_LOCKS */ + +/* ----------------------- Chunk representations ------------------------ */ + +/* + (The following includes lightly edited explanations by Colin Plumb.) + + The malloc_chunk declaration below is misleading (but accurate and + necessary). It declares a "view" into memory allowing access to + necessary fields at known offsets from a given base. + + Chunks of memory are maintained using a `boundary tag' method as + originally described by Knuth. (See the paper by Paul Wilson + ftp://ftp.cs.utexas.edu/pub/garbage/allocsrv.ps for a survey of such + techniques.) Sizes of free chunks are stored both in the front of + each chunk and at the end. This makes consolidating fragmented + chunks into bigger chunks fast. The head fields also hold bits + representing whether chunks are free or in use. + + Here are some pictures to make it clearer. They are "exploded" to + show that the state of a chunk can be thought of as extending from + the high 31 bits of the head field of its header through the + prev_foot and PINUSE_BIT bit of the following chunk header. + + A chunk that's in use looks like: + + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of previous chunk (if P = 0) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P| + | Size of this chunk 1| +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | | + +- -+ + | | + +- -+ + | : + +- size - sizeof(size_t) available payload bytes -+ + : | + chunk-> +- -+ + | | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |1| + | Size of next chunk (may or may not be in use) | +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + + And if it's free, it looks like this: + + chunk-> +- -+ + | User payload (must be in use, or we would have merged!) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P| + | Size of this chunk 0| +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Next pointer | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Prev pointer | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | : + +- size - sizeof(struct chunk) unused bytes -+ + : | + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of this chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |0| + | Size of next chunk (must be in use, or we would have merged)| +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | : + +- User payload -+ + : | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + |0| + +-+ + Note that since we always merge adjacent free chunks, the chunks + adjacent to a free chunk must be in use. + + Given a pointer to a chunk (which can be derived trivially from the + payload pointer) we can, in O(1) time, find out whether the adjacent + chunks are free, and if so, unlink them from the lists that they + are on and merge them with the current chunk. + + Chunks always begin on even word boundaries, so the mem portion + (which is returned to the user) is also on an even word boundary, and + thus at least double-word aligned. + + The P (PINUSE_BIT) bit, stored in the unused low-order bit of the + chunk size (which is always a multiple of two words), is an in-use + bit for the *previous* chunk. If that bit is *clear*, then the + word before the current chunk size contains the previous chunk + size, and can be used to find the front of the previous chunk. + The very first chunk allocated always has this bit set, preventing + access to non-existent (or non-owned) memory. If pinuse is set for + any given chunk, then you CANNOT determine the size of the + previous chunk, and might even get a memory addressing fault when + trying to do so. + + The C (CINUSE_BIT) bit, stored in the unused second-lowest bit of + the chunk size redundantly records whether the current chunk is + inuse (unless the chunk is mmapped). This redundancy enables usage + checks within free and realloc, and reduces indirection when freeing + and consolidating chunks. + + Each freshly allocated chunk must have both cinuse and pinuse set. + That is, each allocated chunk borders either a previously allocated + and still in-use chunk, or the base of its memory arena. This is + ensured by making all allocations from the `lowest' part of any + found chunk. Further, no free chunk physically borders another one, + so each free chunk is known to be preceded and followed by either + inuse chunks or the ends of memory. + + Note that the `foot' of the current chunk is actually represented + as the prev_foot of the NEXT chunk. This makes it easier to + deal with alignments etc but can be very confusing when trying + to extend or adapt this code. + + The exceptions to all this are + + 1. The special chunk `top' is the top-most available chunk (i.e., + the one bordering the end of available memory). It is treated + specially. Top is never included in any bin, is used only if + no other chunk is available, and is released back to the + system if it is very large (see M_TRIM_THRESHOLD). In effect, + the top chunk is treated as larger (and thus less well + fitting) than any other available chunk. The top chunk + doesn't update its trailing size field since there is no next + contiguous chunk that would have to index off it. However, + space is still allocated for it (TOP_FOOT_SIZE) to enable + separation or merging when space is extended. + + 3. Chunks allocated via mmap, have both cinuse and pinuse bits + cleared in their head fields. Because they are allocated + one-by-one, each must carry its own prev_foot field, which is + also used to hold the offset this chunk has within its mmapped + region, which is needed to preserve alignment. Each mmapped + chunk is trailed by the first two fields of a fake next-chunk + for sake of usage checks. + +*/ + +struct malloc_chunk { + size_t prev_foot; /* Size of previous chunk (if free). */ + size_t head; /* Size and inuse bits. */ + struct malloc_chunk* fd; /* double links -- used only if free. */ + struct malloc_chunk* bk; +}; + +typedef struct malloc_chunk mchunk; +typedef struct malloc_chunk* mchunkptr; +typedef struct malloc_chunk* sbinptr; /* The type of bins of chunks */ +typedef unsigned int bindex_t; /* Described below */ +typedef unsigned int binmap_t; /* Described below */ +typedef unsigned int flag_t; /* The type of various bit flag sets */ + +/* ------------------- Chunks sizes and alignments ----------------------- */ + +#define MCHUNK_SIZE (sizeof(mchunk)) + +#if FOOTERS +#define CHUNK_OVERHEAD (TWO_SIZE_T_SIZES) +#else /* FOOTERS */ +#define CHUNK_OVERHEAD (SIZE_T_SIZE) +#endif /* FOOTERS */ + +/* MMapped chunks need a second word of overhead ... */ +#define MMAP_CHUNK_OVERHEAD (TWO_SIZE_T_SIZES) +/* ... and additional padding for fake next-chunk at foot */ +#define MMAP_FOOT_PAD (FOUR_SIZE_T_SIZES) + +/* The smallest size we can malloc is an aligned minimal chunk */ +#define MIN_CHUNK_SIZE\ + ((MCHUNK_SIZE + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK) + +/* conversion from malloc headers to user pointers, and back */ +#define chunk2mem(p) ((void*)((char*)(p) + TWO_SIZE_T_SIZES)) +#define mem2chunk(mem) ((mchunkptr)((char*)(mem) - TWO_SIZE_T_SIZES)) +/* chunk associated with aligned address A */ +#define align_as_chunk(A) (mchunkptr)((A) + align_offset(chunk2mem(A))) + +/* Bounds on request (not chunk) sizes. */ +#define MAX_REQUEST ((-MIN_CHUNK_SIZE) << 2) +#define MIN_REQUEST (MIN_CHUNK_SIZE - CHUNK_OVERHEAD - SIZE_T_ONE) + +/* pad request bytes into a usable size */ +#define pad_request(req) \ + (((req) + CHUNK_OVERHEAD + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK) + +/* pad request, checking for minimum (but not maximum) */ +#define request2size(req) \ + (((req) < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(req)) + + +/* ------------------ Operations on head and foot fields ----------------- */ + +/* + The head field of a chunk is or'ed with PINUSE_BIT when previous + adjacent chunk in use, and or'ed with CINUSE_BIT if this chunk is in + use, unless mmapped, in which case both bits are cleared. + + FLAG4_BIT is not used by this malloc, but might be useful in extensions. +*/ + +#define PINUSE_BIT (SIZE_T_ONE) +#define CINUSE_BIT (SIZE_T_TWO) +#define FLAG4_BIT (SIZE_T_FOUR) +#define INUSE_BITS (PINUSE_BIT|CINUSE_BIT) +#define FLAG_BITS (PINUSE_BIT|CINUSE_BIT|FLAG4_BIT) + +/* Head value for fenceposts */ +#define FENCEPOST_HEAD (INUSE_BITS|SIZE_T_SIZE) + +/* extraction of fields from head words */ +#define cinuse(p) ((p)->head & CINUSE_BIT) +#define pinuse(p) ((p)->head & PINUSE_BIT) +#define flag4inuse(p) ((p)->head & FLAG4_BIT) +#define is_inuse(p) (((p)->head & INUSE_BITS) != PINUSE_BIT) +#define is_mmapped(p) (((p)->head & INUSE_BITS) == 0) + +#define chunksize(p) ((p)->head & ~(FLAG_BITS)) + +#define clear_pinuse(p) ((p)->head &= ~PINUSE_BIT) +#define set_flag4(p) ((p)->head |= FLAG4_BIT) +#define clear_flag4(p) ((p)->head &= ~FLAG4_BIT) + +/* Treat space at ptr +/- offset as a chunk */ +#define chunk_plus_offset(p, s) ((mchunkptr)(((char*)(p)) + (s))) +#define chunk_minus_offset(p, s) ((mchunkptr)(((char*)(p)) - (s))) + +/* Ptr to next or previous physical malloc_chunk. */ +#define next_chunk(p) ((mchunkptr)( ((char*)(p)) + ((p)->head & ~FLAG_BITS))) +#define prev_chunk(p) ((mchunkptr)( ((char*)(p)) - ((p)->prev_foot) )) + +/* extract next chunk's pinuse bit */ +#define next_pinuse(p) ((next_chunk(p)->head) & PINUSE_BIT) + +/* Get/set size at footer */ +#define get_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot) +#define set_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot = (s)) + +/* Set size, pinuse bit, and foot */ +#define set_size_and_pinuse_of_free_chunk(p, s)\ + ((p)->head = (s|PINUSE_BIT), set_foot(p, s)) + +/* Set size, pinuse bit, foot, and clear next pinuse */ +#define set_free_with_pinuse(p, s, n)\ + (clear_pinuse(n), set_size_and_pinuse_of_free_chunk(p, s)) + +/* Get the internal overhead associated with chunk p */ +#define overhead_for(p)\ + (is_mmapped(p)? MMAP_CHUNK_OVERHEAD : CHUNK_OVERHEAD) + +/* Return true if malloced space is not necessarily cleared */ +#if MMAP_CLEARS +#define calloc_must_clear(p) (!is_mmapped(p)) +#else /* MMAP_CLEARS */ +#define calloc_must_clear(p) (1) +#endif /* MMAP_CLEARS */ + +/* ---------------------- Overlaid data structures ----------------------- */ + +/* + When chunks are not in use, they are treated as nodes of either + lists or trees. + + "Small" chunks are stored in circular doubly-linked lists, and look + like this: + + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of previous chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `head:' | Size of chunk, in bytes |P| + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Forward pointer to next chunk in list | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Back pointer to previous chunk in list | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Unused space (may be 0 bytes long) . + . . + . | +nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `foot:' | Size of chunk, in bytes | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + + Larger chunks are kept in a form of bitwise digital trees (aka + tries) keyed on chunksizes. Because malloc_tree_chunks are only for + free chunks greater than 256 bytes, their size doesn't impose any + constraints on user chunk sizes. Each node looks like: + + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of previous chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `head:' | Size of chunk, in bytes |P| + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Forward pointer to next chunk of same size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Back pointer to previous chunk of same size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Pointer to left child (child[0]) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Pointer to right child (child[1]) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Pointer to parent | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | bin index of this chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Unused space . + . | +nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `foot:' | Size of chunk, in bytes | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + + Each tree holding treenodes is a tree of unique chunk sizes. Chunks + of the same size are arranged in a circularly-linked list, with only + the oldest chunk (the next to be used, in our FIFO ordering) + actually in the tree. (Tree members are distinguished by a non-null + parent pointer.) If a chunk with the same size an an existing node + is inserted, it is linked off the existing node using pointers that + work in the same way as fd/bk pointers of small chunks. + + Each tree contains a power of 2 sized range of chunk sizes (the + smallest is 0x100 <= x < 0x180), which is is divided in half at each + tree level, with the chunks in the smaller half of the range (0x100 + <= x < 0x140 for the top nose) in the left subtree and the larger + half (0x140 <= x < 0x180) in the right subtree. This is, of course, + done by inspecting individual bits. + + Using these rules, each node's left subtree contains all smaller + sizes than its right subtree. However, the node at the root of each + subtree has no particular ordering relationship to either. (The + dividing line between the subtree sizes is based on trie relation.) + If we remove the last chunk of a given size from the interior of the + tree, we need to replace it with a leaf node. The tree ordering + rules permit a node to be replaced by any leaf below it. + + The smallest chunk in a tree (a common operation in a best-fit + allocator) can be found by walking a path to the leftmost leaf in + the tree. Unlike a usual binary tree, where we follow left child + pointers until we reach a null, here we follow the right child + pointer any time the left one is null, until we reach a leaf with + both child pointers null. The smallest chunk in the tree will be + somewhere along that path. + + The worst case number of steps to add, find, or remove a node is + bounded by the number of bits differentiating chunks within + bins. Under current bin calculations, this ranges from 6 up to 21 + (for 32 bit sizes) or up to 53 (for 64 bit sizes). The typical case + is of course much better. +*/ + +struct malloc_tree_chunk { + /* The first four fields must be compatible with malloc_chunk */ + size_t prev_foot; + size_t head; + struct malloc_tree_chunk* fd; + struct malloc_tree_chunk* bk; + + struct malloc_tree_chunk* child[2]; + struct malloc_tree_chunk* parent; + bindex_t index; +}; + +typedef struct malloc_tree_chunk tchunk; +typedef struct malloc_tree_chunk* tchunkptr; +typedef struct malloc_tree_chunk* tbinptr; /* The type of bins of trees */ + +/* A little helper macro for trees */ +#define leftmost_child(t) ((t)->child[0] != 0? (t)->child[0] : (t)->child[1]) + +/* ----------------------------- Segments -------------------------------- */ + +/* + Each malloc space may include non-contiguous segments, held in a + list headed by an embedded malloc_segment record representing the + top-most space. Segments also include flags holding properties of + the space. Large chunks that are directly allocated by mmap are not + included in this list. They are instead independently created and + destroyed without otherwise keeping track of them. + + Segment management mainly comes into play for spaces allocated by + MMAP. Any call to MMAP might or might not return memory that is + adjacent to an existing segment. MORECORE normally contiguously + extends the current space, so this space is almost always adjacent, + which is simpler and faster to deal with. (This is why MORECORE is + used preferentially to MMAP when both are available -- see + sys_alloc.) When allocating using MMAP, we don't use any of the + hinting mechanisms (inconsistently) supported in various + implementations of unix mmap, or distinguish reserving from + committing memory. Instead, we just ask for space, and exploit + contiguity when we get it. It is probably possible to do + better than this on some systems, but no general scheme seems + to be significantly better. + + Management entails a simpler variant of the consolidation scheme + used for chunks to reduce fragmentation -- new adjacent memory is + normally prepended or appended to an existing segment. However, + there are limitations compared to chunk consolidation that mostly + reflect the fact that segment processing is relatively infrequent + (occurring only when getting memory from system) and that we + don't expect to have huge numbers of segments: + + * Segments are not indexed, so traversal requires linear scans. (It + would be possible to index these, but is not worth the extra + overhead and complexity for most programs on most platforms.) + * New segments are only appended to old ones when holding top-most + memory; if they cannot be prepended to others, they are held in + different segments. + + Except for the top-most segment of an mstate, each segment record + is kept at the tail of its segment. Segments are added by pushing + segment records onto the list headed by &mstate.seg for the + containing mstate. + + Segment flags control allocation/merge/deallocation policies: + * If EXTERN_BIT set, then we did not allocate this segment, + and so should not try to deallocate or merge with others. + (This currently holds only for the initial segment passed + into create_mspace_with_base.) + * If USE_MMAP_BIT set, the segment may be merged with + other surrounding mmapped segments and trimmed/de-allocated + using munmap. + * If neither bit is set, then the segment was obtained using + MORECORE so can be merged with surrounding MORECORE'd segments + and deallocated/trimmed using MORECORE with negative arguments. +*/ + +struct malloc_segment { + char* base; /* base address */ + size_t size; /* allocated size */ + struct malloc_segment* next; /* ptr to next segment */ + flag_t sflags; /* mmap and extern flag */ +}; + +#define is_mmapped_segment(S) ((S)->sflags & USE_MMAP_BIT) +#define is_extern_segment(S) ((S)->sflags & EXTERN_BIT) + +typedef struct malloc_segment msegment; +typedef struct malloc_segment* msegmentptr; + +/* ---------------------------- malloc_state ----------------------------- */ + +/* + A malloc_state holds all of the bookkeeping for a space. + The main fields are: + + Top + The topmost chunk of the currently active segment. Its size is + cached in topsize. The actual size of topmost space is + topsize+TOP_FOOT_SIZE, which includes space reserved for adding + fenceposts and segment records if necessary when getting more + space from the system. The size at which to autotrim top is + cached from mparams in trim_check, except that it is disabled if + an autotrim fails. + + Designated victim (dv) + This is the preferred chunk for servicing small requests that + don't have exact fits. It is normally the chunk split off most + recently to service another small request. Its size is cached in + dvsize. The link fields of this chunk are not maintained since it + is not kept in a bin. + + SmallBins + An array of bin headers for free chunks. These bins hold chunks + with sizes less than MIN_LARGE_SIZE bytes. Each bin contains + chunks of all the same size, spaced 8 bytes apart. To simplify + use in double-linked lists, each bin header acts as a malloc_chunk + pointing to the real first node, if it exists (else pointing to + itself). This avoids special-casing for headers. But to avoid + waste, we allocate only the fd/bk pointers of bins, and then use + repositioning tricks to treat these as the fields of a chunk. + + TreeBins + Treebins are pointers to the roots of trees holding a range of + sizes. There are 2 equally spaced treebins for each power of two + from TREE_SHIFT to TREE_SHIFT+16. The last bin holds anything + larger. + + Bin maps + There is one bit map for small bins ("smallmap") and one for + treebins ("treemap). Each bin sets its bit when non-empty, and + clears the bit when empty. Bit operations are then used to avoid + bin-by-bin searching -- nearly all "search" is done without ever + looking at bins that won't be selected. The bit maps + conservatively use 32 bits per map word, even if on 64bit system. + For a good description of some of the bit-based techniques used + here, see Henry S. Warren Jr's book "Hacker's Delight" (and + supplement at http://hackersdelight.org/). Many of these are + intended to reduce the branchiness of paths through malloc etc, as + well as to reduce the number of memory locations read or written. + + Segments + A list of segments headed by an embedded malloc_segment record + representing the initial space. + + Address check support + The least_addr field is the least address ever obtained from + MORECORE or MMAP. Attempted frees and reallocs of any address less + than this are trapped (unless INSECURE is defined). + + Magic tag + A cross-check field that should always hold same value as mparams.magic. + + Max allowed footprint + The maximum allowed bytes to allocate from system (zero means no limit) + + Flags + Bits recording whether to use MMAP, locks, or contiguous MORECORE + + Statistics + Each space keeps track of current and maximum system memory + obtained via MORECORE or MMAP. + + Trim support + Fields holding the amount of unused topmost memory that should trigger + trimming, and a counter to force periodic scanning to release unused + non-topmost segments. + + Locking + If USE_LOCKS is defined, the "mutex" lock is acquired and released + around every public call using this mspace. + + Extension support + A void* pointer and a size_t field that can be used to help implement + extensions to this malloc. +*/ + +/* Bin types, widths and sizes */ +#define NSMALLBINS (32U) +#define NTREEBINS (32U) +#define SMALLBIN_SHIFT (3U) +#define SMALLBIN_WIDTH (SIZE_T_ONE << SMALLBIN_SHIFT) +#define TREEBIN_SHIFT (8U) +#define MIN_LARGE_SIZE (SIZE_T_ONE << TREEBIN_SHIFT) +#define MAX_SMALL_SIZE (MIN_LARGE_SIZE - SIZE_T_ONE) +#define MAX_SMALL_REQUEST (MAX_SMALL_SIZE - CHUNK_ALIGN_MASK - CHUNK_OVERHEAD) + +struct malloc_state { + binmap_t smallmap; + binmap_t treemap; + size_t dvsize; + size_t topsize; + char* least_addr; + mchunkptr dv; + mchunkptr top; + size_t trim_check; + size_t release_checks; + size_t magic; + mchunkptr smallbins[(NSMALLBINS+1)*2]; + tbinptr treebins[NTREEBINS]; + size_t footprint; + size_t max_footprint; + size_t footprint_limit; /* zero means no limit */ + flag_t mflags; +#if USE_LOCKS + MLOCK_T mutex; /* locate lock among fields that rarely change */ +#endif /* USE_LOCKS */ + msegment seg; + void* extp; /* Unused but available for extensions */ + size_t exts; +}; + +typedef struct malloc_state* mstate; + +/* ------------- Global malloc_state and malloc_params ------------------- */ + +/* + malloc_params holds global properties, including those that can be + dynamically set using mallopt. There is a single instance, mparams, + initialized in init_mparams. Note that the non-zeroness of "magic" + also serves as an initialization flag. +*/ + +struct malloc_params { + size_t magic; + size_t page_size; + size_t granularity; + size_t mmap_threshold; + size_t trim_threshold; + flag_t default_mflags; +}; + +static struct malloc_params mparams; + +/* Ensure mparams initialized */ +#define ensure_initialization() (void)(mparams.magic != 0 || init_mparams()) + +#if !ONLY_MSPACES + +/* The global malloc_state used for all non-"mspace" calls */ +static struct malloc_state _gm_; +#define gm (&_gm_) +#define is_global(M) ((M) == &_gm_) + +#endif /* !ONLY_MSPACES */ + +#define is_initialized(M) ((M)->top != 0) + +/* -------------------------- system alloc setup ------------------------- */ + +/* Operations on mflags */ + +#define use_lock(M) ((M)->mflags & USE_LOCK_BIT) +#define enable_lock(M) ((M)->mflags |= USE_LOCK_BIT) +#if USE_LOCKS +#define disable_lock(M) ((M)->mflags &= ~USE_LOCK_BIT) +#else +#define disable_lock(M) +#endif + +#define use_mmap(M) ((M)->mflags & USE_MMAP_BIT) +#define enable_mmap(M) ((M)->mflags |= USE_MMAP_BIT) +#if HAVE_MMAP +#define disable_mmap(M) ((M)->mflags &= ~USE_MMAP_BIT) +#else +#define disable_mmap(M) +#endif + +#define use_noncontiguous(M) ((M)->mflags & USE_NONCONTIGUOUS_BIT) +#define disable_contiguous(M) ((M)->mflags |= USE_NONCONTIGUOUS_BIT) + +#define set_lock(M,L)\ + ((M)->mflags = (L)?\ + ((M)->mflags | USE_LOCK_BIT) :\ + ((M)->mflags & ~USE_LOCK_BIT)) + +/* page-align a size */ +#define page_align(S)\ + (((S) + (mparams.page_size - SIZE_T_ONE)) & ~(mparams.page_size - SIZE_T_ONE)) + +/* granularity-align a size */ +#define granularity_align(S)\ + (((S) + (mparams.granularity - SIZE_T_ONE))\ + & ~(mparams.granularity - SIZE_T_ONE)) + + +/* For mmap, use granularity alignment on windows, else page-align */ +#ifdef WIN32 +#define mmap_align(S) granularity_align(S) +#else +#define mmap_align(S) page_align(S) +#endif + +/* For sys_alloc, enough padding to ensure can malloc request on success */ +#define SYS_ALLOC_PADDING (TOP_FOOT_SIZE + MALLOC_ALIGNMENT) + +#define is_page_aligned(S)\ + (((size_t)(S) & (mparams.page_size - SIZE_T_ONE)) == 0) +#define is_granularity_aligned(S)\ + (((size_t)(S) & (mparams.granularity - SIZE_T_ONE)) == 0) + +/* True if segment S holds address A */ +#define segment_holds(S, A)\ + ((char*)(A) >= S->base && (char*)(A) < S->base + S->size) + +/* Return segment holding given address */ +static msegmentptr segment_holding(mstate m, char* addr) { + msegmentptr sp = &m->seg; + for (;;) { + if (addr >= sp->base && addr < sp->base + sp->size) + return sp; + if ((sp = sp->next) == 0) + return 0; + } +} + +/* Return true if segment contains a segment link */ +static int has_segment_link(mstate m, msegmentptr ss) { + msegmentptr sp = &m->seg; + for (;;) { + if ((char*)sp >= ss->base && (char*)sp < ss->base + ss->size) + return 1; + if ((sp = sp->next) == 0) + return 0; + } +} + +#ifndef MORECORE_CANNOT_TRIM +#define should_trim(M,s) ((s) > (M)->trim_check) +#else /* MORECORE_CANNOT_TRIM */ +#define should_trim(M,s) (0) +#endif /* MORECORE_CANNOT_TRIM */ + +/* + TOP_FOOT_SIZE is padding at the end of a segment, including space + that may be needed to place segment records and fenceposts when new + noncontiguous segments are added. +*/ +#define TOP_FOOT_SIZE\ + (align_offset(chunk2mem(0))+pad_request(sizeof(struct malloc_segment))+MIN_CHUNK_SIZE) + + +/* ------------------------------- Hooks -------------------------------- */ + +/* + PREACTION should be defined to return 0 on success, and nonzero on + failure. If you are not using locking, you can redefine these to do + anything you like. +*/ + +#if USE_LOCKS +#define PREACTION(M) ((use_lock(M))? ACQUIRE_LOCK(&(M)->mutex) : 0) +#define POSTACTION(M) { if (use_lock(M)) RELEASE_LOCK(&(M)->mutex); } +#else /* USE_LOCKS */ + +#ifndef PREACTION +#define PREACTION(M) (0) +#endif /* PREACTION */ + +#ifndef POSTACTION +#define POSTACTION(M) +#endif /* POSTACTION */ + +#endif /* USE_LOCKS */ + +/* + CORRUPTION_ERROR_ACTION is triggered upon detected bad addresses. + USAGE_ERROR_ACTION is triggered on detected bad frees and + reallocs. The argument p is an address that might have triggered the + fault. It is ignored by the two predefined actions, but might be + useful in custom actions that try to help diagnose errors. +*/ + +#if PROCEED_ON_ERROR + +/* A count of the number of corruption errors causing resets */ +int malloc_corruption_error_count; + +/* default corruption action */ +static void reset_on_error(mstate m); + +#define CORRUPTION_ERROR_ACTION(m) reset_on_error(m) +#define USAGE_ERROR_ACTION(m, p) + +#else /* PROCEED_ON_ERROR */ + +#ifndef CORRUPTION_ERROR_ACTION +#define CORRUPTION_ERROR_ACTION(m) ABORT +#endif /* CORRUPTION_ERROR_ACTION */ + +#ifndef USAGE_ERROR_ACTION +#define USAGE_ERROR_ACTION(m,p) ABORT +#endif /* USAGE_ERROR_ACTION */ + +#endif /* PROCEED_ON_ERROR */ + + +/* -------------------------- Debugging setup ---------------------------- */ + +#if ! DEBUG + +#define check_free_chunk(M,P) +#define check_inuse_chunk(M,P) +#define check_malloced_chunk(M,P,N) +#define check_mmapped_chunk(M,P) +#define check_malloc_state(M) +#define check_top_chunk(M,P) + +#else /* DEBUG */ +#define check_free_chunk(M,P) do_check_free_chunk(M,P) +#define check_inuse_chunk(M,P) do_check_inuse_chunk(M,P) +#define check_top_chunk(M,P) do_check_top_chunk(M,P) +#define check_malloced_chunk(M,P,N) do_check_malloced_chunk(M,P,N) +#define check_mmapped_chunk(M,P) do_check_mmapped_chunk(M,P) +#define check_malloc_state(M) do_check_malloc_state(M) + +static void do_check_any_chunk(mstate m, mchunkptr p); +static void do_check_top_chunk(mstate m, mchunkptr p); +static void do_check_mmapped_chunk(mstate m, mchunkptr p); +static void do_check_inuse_chunk(mstate m, mchunkptr p); +static void do_check_free_chunk(mstate m, mchunkptr p); +static void do_check_malloced_chunk(mstate m, void* mem, size_t s); +static void do_check_tree(mstate m, tchunkptr t); +static void do_check_treebin(mstate m, bindex_t i); +static void do_check_smallbin(mstate m, bindex_t i); +static void do_check_malloc_state(mstate m); +static int bin_find(mstate m, mchunkptr x); +static size_t traverse_and_check(mstate m); +#endif /* DEBUG */ + +/* ---------------------------- Indexing Bins ---------------------------- */ + +#define is_small(s) (((s) >> SMALLBIN_SHIFT) < NSMALLBINS) +#define small_index(s) (bindex_t)((s) >> SMALLBIN_SHIFT) +#define small_index2size(i) ((i) << SMALLBIN_SHIFT) +#define MIN_SMALL_INDEX (small_index(MIN_CHUNK_SIZE)) + +/* addressing by index. See above about smallbin repositioning */ +#define smallbin_at(M, i) ((sbinptr)((char*)&((M)->smallbins[(i)<<1]))) +#define treebin_at(M,i) (&((M)->treebins[i])) + +/* assign tree index for size S to variable I. Use x86 asm if possible */ +#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__)) +#define compute_tree_index(S, I)\ +{\ + unsigned int X = S >> TREEBIN_SHIFT;\ + if (X == 0)\ + I = 0;\ + else if (X > 0xFFFF)\ + I = NTREEBINS-1;\ + else {\ + unsigned int K = (unsigned) sizeof(X)*__CHAR_BIT__ - 1 - (unsigned) __builtin_clz(X); \ + I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\ + }\ +} + +#elif defined (__INTEL_COMPILER) +#define compute_tree_index(S, I)\ +{\ + size_t X = S >> TREEBIN_SHIFT;\ + if (X == 0)\ + I = 0;\ + else if (X > 0xFFFF)\ + I = NTREEBINS-1;\ + else {\ + unsigned int K = _bit_scan_reverse (X); \ + I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\ + }\ +} + +#elif defined(_MSC_VER) && _MSC_VER>=1300 +#define compute_tree_index(S, I)\ +{\ + size_t X = S >> TREEBIN_SHIFT;\ + if (X == 0)\ + I = 0;\ + else if (X > 0xFFFF)\ + I = NTREEBINS-1;\ + else {\ + unsigned int K;\ + _BitScanReverse((DWORD *) &K, (DWORD) X);\ + I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\ + }\ +} + +#else /* GNUC */ +#define compute_tree_index(S, I)\ +{\ + size_t X = S >> TREEBIN_SHIFT;\ + if (X == 0)\ + I = 0;\ + else if (X > 0xFFFF)\ + I = NTREEBINS-1;\ + else {\ + unsigned int Y = (unsigned int)X;\ + unsigned int N = ((Y - 0x100) >> 16) & 8;\ + unsigned int K = (((Y <<= N) - 0x1000) >> 16) & 4;\ + N += K;\ + N += K = (((Y <<= K) - 0x4000) >> 16) & 2;\ + K = 14 - N + ((Y <<= K) >> 15);\ + I = (K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1));\ + }\ +} +#endif /* GNUC */ + +/* Bit representing maximum resolved size in a treebin at i */ +#define bit_for_tree_index(i) \ + (i == NTREEBINS-1)? (SIZE_T_BITSIZE-1) : (((i) >> 1) + TREEBIN_SHIFT - 2) + +/* Shift placing maximum resolved bit in a treebin at i as sign bit */ +#define leftshift_for_tree_index(i) \ + ((i == NTREEBINS-1)? 0 : \ + ((SIZE_T_BITSIZE-SIZE_T_ONE) - (((i) >> 1) + TREEBIN_SHIFT - 2))) + +/* The size of the smallest chunk held in bin with index i */ +#define minsize_for_tree_index(i) \ + ((SIZE_T_ONE << (((i) >> 1) + TREEBIN_SHIFT)) | \ + (((size_t)((i) & SIZE_T_ONE)) << (((i) >> 1) + TREEBIN_SHIFT - 1))) + + +/* ------------------------ Operations on bin maps ----------------------- */ + +/* bit corresponding to given index */ +#define idx2bit(i) ((binmap_t)(1) << (i)) + +/* Mark/Clear bits with given index */ +#define mark_smallmap(M,i) ((M)->smallmap |= idx2bit(i)) +#define clear_smallmap(M,i) ((M)->smallmap &= ~idx2bit(i)) +#define smallmap_is_marked(M,i) ((M)->smallmap & idx2bit(i)) + +#define mark_treemap(M,i) ((M)->treemap |= idx2bit(i)) +#define clear_treemap(M,i) ((M)->treemap &= ~idx2bit(i)) +#define treemap_is_marked(M,i) ((M)->treemap & idx2bit(i)) + +/* isolate the least set bit of a bitmap */ +#define least_bit(x) ((x) & -(x)) + +/* mask with all bits to left of least bit of x on */ +#define left_bits(x) ((x<<1) | -(x<<1)) + +/* mask with all bits to left of or equal to least bit of x on */ +#define same_or_left_bits(x) ((x) | -(x)) + +/* index corresponding to given bit. Use x86 asm if possible */ + +#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__)) +#define compute_bit2idx(X, I)\ +{\ + unsigned int J;\ + J = __builtin_ctz(X); \ + I = (bindex_t)J;\ +} + +#elif defined (__INTEL_COMPILER) +#define compute_bit2idx(X, I)\ +{\ + unsigned int J;\ + J = _bit_scan_forward (X); \ + I = (bindex_t)J;\ +} + +#elif defined(_MSC_VER) && _MSC_VER>=1300 +#define compute_bit2idx(X, I)\ +{\ + unsigned int J;\ + _BitScanForward((DWORD *) &J, X);\ + I = (bindex_t)J;\ +} + +#elif USE_BUILTIN_FFS +#define compute_bit2idx(X, I) I = ffs(X)-1 + +#else +#define compute_bit2idx(X, I)\ +{\ + unsigned int Y = X - 1;\ + unsigned int K = Y >> (16-4) & 16;\ + unsigned int N = K; Y >>= K;\ + N += K = Y >> (8-3) & 8; Y >>= K;\ + N += K = Y >> (4-2) & 4; Y >>= K;\ + N += K = Y >> (2-1) & 2; Y >>= K;\ + N += K = Y >> (1-0) & 1; Y >>= K;\ + I = (bindex_t)(N + Y);\ +} +#endif /* GNUC */ + + +/* ----------------------- Runtime Check Support ------------------------- */ + +/* + For security, the main invariant is that malloc/free/etc never + writes to a static address other than malloc_state, unless static + malloc_state itself has been corrupted, which cannot occur via + malloc (because of these checks). In essence this means that we + believe all pointers, sizes, maps etc held in malloc_state, but + check all of those linked or offsetted from other embedded data + structures. These checks are interspersed with main code in a way + that tends to minimize their run-time cost. + + When FOOTERS is defined, in addition to range checking, we also + verify footer fields of inuse chunks, which can be used guarantee + that the mstate controlling malloc/free is intact. This is a + streamlined version of the approach described by William Robertson + et al in "Run-time Detection of Heap-based Overflows" LISA'03 + http://www.usenix.org/events/lisa03/tech/robertson.html The footer + of an inuse chunk holds the xor of its mstate and a random seed, + that is checked upon calls to free() and realloc(). This is + (probabalistically) unguessable from outside the program, but can be + computed by any code successfully malloc'ing any chunk, so does not + itself provide protection against code that has already broken + security through some other means. Unlike Robertson et al, we + always dynamically check addresses of all offset chunks (previous, + next, etc). This turns out to be cheaper than relying on hashes. +*/ + +#if !INSECURE +/* Check if address a is at least as high as any from MORECORE or MMAP */ +#define ok_address(M, a) ((char*)(a) >= (M)->least_addr) +/* Check if address of next chunk n is higher than base chunk p */ +#define ok_next(p, n) ((char*)(p) < (char*)(n)) +/* Check if p has inuse status */ +#define ok_inuse(p) is_inuse(p) +/* Check if p has its pinuse bit on */ +#define ok_pinuse(p) pinuse(p) + +#else /* !INSECURE */ +#define ok_address(M, a) (1) +#define ok_next(b, n) (1) +#define ok_inuse(p) (1) +#define ok_pinuse(p) (1) +#endif /* !INSECURE */ + +#if (FOOTERS && !INSECURE) +/* Check if (alleged) mstate m has expected magic field */ +#define ok_magic(M) ((M)->magic == mparams.magic) +#else /* (FOOTERS && !INSECURE) */ +#define ok_magic(M) (1) +#endif /* (FOOTERS && !INSECURE) */ + +/* In gcc, use __builtin_expect to minimize impact of checks */ +#if !INSECURE +#if defined(__GNUC__) && __GNUC__ >= 3 +#define RTCHECK(e) __builtin_expect(e, 1) +#else /* GNUC */ +#define RTCHECK(e) (e) +#endif /* GNUC */ +#else /* !INSECURE */ +#define RTCHECK(e) (1) +#endif /* !INSECURE */ + +/* macros to set up inuse chunks with or without footers */ + +#if !FOOTERS + +#define mark_inuse_foot(M,p,s) + +/* Macros for setting head/foot of non-mmapped chunks */ + +/* Set cinuse bit and pinuse bit of next chunk */ +#define set_inuse(M,p,s)\ + ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\ + ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT) + +/* Set cinuse and pinuse of this chunk and pinuse of next chunk */ +#define set_inuse_and_pinuse(M,p,s)\ + ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ + ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT) + +/* Set size, cinuse and pinuse bit of this chunk */ +#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\ + ((p)->head = (s|PINUSE_BIT|CINUSE_BIT)) + +#else /* FOOTERS */ + +/* Set foot of inuse chunk to be xor of mstate and seed */ +#define mark_inuse_foot(M,p,s)\ + (((mchunkptr)((char*)(p) + (s)))->prev_foot = ((size_t)(M) ^ mparams.magic)) + +#define get_mstate_for(p)\ + ((mstate)(((mchunkptr)((char*)(p) +\ + (chunksize(p))))->prev_foot ^ mparams.magic)) + +#define set_inuse(M,p,s)\ + ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\ + (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT), \ + mark_inuse_foot(M,p,s)) + +#define set_inuse_and_pinuse(M,p,s)\ + ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ + (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT),\ + mark_inuse_foot(M,p,s)) + +#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\ + ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ + mark_inuse_foot(M, p, s)) + +#endif /* !FOOTERS */ + +/* ---------------------------- setting mparams -------------------------- */ + +/* Initialize mparams */ +static int init_mparams(void) { +#ifdef NEED_GLOBAL_LOCK_INIT + if (malloc_global_mutex_status <= 0) + init_malloc_global_mutex(); +#endif + + ACQUIRE_MALLOC_GLOBAL_LOCK(); + if (mparams.magic == 0) { + size_t magic; + size_t psize; + size_t gsize; + +#ifndef WIN32 + psize = malloc_getpagesize; + gsize = ((DEFAULT_GRANULARITY != 0)? DEFAULT_GRANULARITY : psize); +#else /* WIN32 */ + { + SYSTEM_INFO system_info; + GetSystemInfo(&system_info); + psize = system_info.dwPageSize; + gsize = ((DEFAULT_GRANULARITY != 0)? + DEFAULT_GRANULARITY : system_info.dwAllocationGranularity); + } +#endif /* WIN32 */ + + /* Sanity-check configuration: + size_t must be unsigned and as wide as pointer type. + ints must be at least 4 bytes. + alignment must be at least 8. + Alignment, min chunk size, and page size must all be powers of 2. + */ + if ((sizeof(size_t) != sizeof(char*)) || + (MAX_SIZE_T < MIN_CHUNK_SIZE) || + (sizeof(int) < 4) || + (MALLOC_ALIGNMENT < (size_t)8U) || + ((MALLOC_ALIGNMENT & (MALLOC_ALIGNMENT-SIZE_T_ONE)) != 0) || + ((MCHUNK_SIZE & (MCHUNK_SIZE-SIZE_T_ONE)) != 0) || + ((gsize & (gsize-SIZE_T_ONE)) != 0) || + ((psize & (psize-SIZE_T_ONE)) != 0)) + ABORT; + + mparams.granularity = gsize; + mparams.page_size = psize; + mparams.mmap_threshold = DEFAULT_MMAP_THRESHOLD; + mparams.trim_threshold = DEFAULT_TRIM_THRESHOLD; +#if MORECORE_CONTIGUOUS + mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT; +#else /* MORECORE_CONTIGUOUS */ + mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT|USE_NONCONTIGUOUS_BIT; +#endif /* MORECORE_CONTIGUOUS */ + +#if !ONLY_MSPACES + /* Set up lock for main malloc area */ + gm->mflags = mparams.default_mflags; + (void)INITIAL_LOCK(&gm->mutex); +#endif + + { +#if USE_DEV_RANDOM + int fd; + unsigned char buf[sizeof(size_t)]; + /* Try to use /dev/urandom, else fall back on using time */ + if ((fd = open("/dev/urandom", O_RDONLY)) >= 0 && + read(fd, buf, sizeof(buf)) == sizeof(buf)) { + magic = *((size_t *) buf); + close(fd); + } + else +#endif /* USE_DEV_RANDOM */ +#ifdef WIN32 + magic = (size_t)(GetTickCount() ^ (size_t)0x55555555U); +#elif defined(LACKS_TIME_H) + magic = (size_t)&magic ^ (size_t)0x55555555U; +#else + magic = (size_t)(time(0) ^ (size_t)0x55555555U); +#endif + magic |= (size_t)8U; /* ensure nonzero */ + magic &= ~(size_t)7U; /* improve chances of fault for bad values */ + /* Until memory modes commonly available, use volatile-write */ + (*(volatile size_t *)(&(mparams.magic))) = magic; + } + } + + RELEASE_MALLOC_GLOBAL_LOCK(); + return 1; +} + +/* support for mallopt */ +static int change_mparam(int param_number, int value) { + size_t val; + ensure_initialization(); + val = (value == -1)? MAX_SIZE_T : (size_t)value; + switch(param_number) { + case M_TRIM_THRESHOLD: + mparams.trim_threshold = val; + return 1; + case M_GRANULARITY: + if (val >= mparams.page_size && ((val & (val-1)) == 0)) { + mparams.granularity = val; + return 1; + } + else + return 0; + case M_MMAP_THRESHOLD: + mparams.mmap_threshold = val; + return 1; + default: + return 0; + } +} + +#if DEBUG +/* ------------------------- Debugging Support --------------------------- */ + +/* Check properties of any chunk, whether free, inuse, mmapped etc */ +static void do_check_any_chunk(mstate m, mchunkptr p) { + assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); + assert(ok_address(m, p)); +} + +/* Check properties of top chunk */ +static void do_check_top_chunk(mstate m, mchunkptr p) { + msegmentptr sp = segment_holding(m, (char*)p); + size_t sz = p->head & ~INUSE_BITS; /* third-lowest bit can be set! */ + assert(sp != 0); + assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); + assert(ok_address(m, p)); + assert(sz == m->topsize); + assert(sz > 0); + assert(sz == ((sp->base + sp->size) - (char*)p) - TOP_FOOT_SIZE); + assert(pinuse(p)); + assert(!pinuse(chunk_plus_offset(p, sz))); +} + +/* Check properties of (inuse) mmapped chunks */ +static void do_check_mmapped_chunk(mstate m, mchunkptr p) { + size_t sz = chunksize(p); + size_t len = (sz + (p->prev_foot) + MMAP_FOOT_PAD); + assert(is_mmapped(p)); + assert(use_mmap(m)); + assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); + assert(ok_address(m, p)); + assert(!is_small(sz)); + assert((len & (mparams.page_size-SIZE_T_ONE)) == 0); + assert(chunk_plus_offset(p, sz)->head == FENCEPOST_HEAD); + assert(chunk_plus_offset(p, sz+SIZE_T_SIZE)->head == 0); +} + +/* Check properties of inuse chunks */ +static void do_check_inuse_chunk(mstate m, mchunkptr p) { + do_check_any_chunk(m, p); + assert(is_inuse(p)); + assert(next_pinuse(p)); + /* If not pinuse and not mmapped, previous chunk has OK offset */ + assert(is_mmapped(p) || pinuse(p) || next_chunk(prev_chunk(p)) == p); + if (is_mmapped(p)) + do_check_mmapped_chunk(m, p); +} + +/* Check properties of free chunks */ +static void do_check_free_chunk(mstate m, mchunkptr p) { + size_t sz = chunksize(p); + mchunkptr next = chunk_plus_offset(p, sz); + do_check_any_chunk(m, p); + assert(!is_inuse(p)); + assert(!next_pinuse(p)); + assert (!is_mmapped(p)); + if (p != m->dv && p != m->top) { + if (sz >= MIN_CHUNK_SIZE) { + assert((sz & CHUNK_ALIGN_MASK) == 0); + assert(is_aligned(chunk2mem(p))); + assert(next->prev_foot == sz); + assert(pinuse(p)); + assert (next == m->top || is_inuse(next)); + assert(p->fd->bk == p); + assert(p->bk->fd == p); + } + else /* markers are always of size SIZE_T_SIZE */ + assert(sz == SIZE_T_SIZE); + } +} + +/* Check properties of malloced chunks at the point they are malloced */ +static void do_check_malloced_chunk(mstate m, void* mem, size_t s) { + if (mem != 0) { + mchunkptr p = mem2chunk(mem); + size_t sz = p->head & ~INUSE_BITS; + do_check_inuse_chunk(m, p); + assert((sz & CHUNK_ALIGN_MASK) == 0); + assert(sz >= MIN_CHUNK_SIZE); + assert(sz >= s); + /* unless mmapped, size is less than MIN_CHUNK_SIZE more than request */ + assert(is_mmapped(p) || sz < (s + MIN_CHUNK_SIZE)); + } +} + +/* Check a tree and its subtrees. */ +static void do_check_tree(mstate m, tchunkptr t) { + tchunkptr head = 0; + tchunkptr u = t; + bindex_t tindex = t->index; + size_t tsize = chunksize(t); + bindex_t idx; + compute_tree_index(tsize, idx); + assert(tindex == idx); + assert(tsize >= MIN_LARGE_SIZE); + assert(tsize >= minsize_for_tree_index(idx)); + assert((idx == NTREEBINS-1) || (tsize < minsize_for_tree_index((idx+1)))); + + do { /* traverse through chain of same-sized nodes */ + do_check_any_chunk(m, ((mchunkptr)u)); + assert(u->index == tindex); + assert(chunksize(u) == tsize); + assert(!is_inuse(u)); + assert(!next_pinuse(u)); + assert(u->fd->bk == u); + assert(u->bk->fd == u); + if (u->parent == 0) { + assert(u->child[0] == 0); + assert(u->child[1] == 0); + } + else { + assert(head == 0); /* only one node on chain has parent */ + head = u; + assert(u->parent != u); + assert (u->parent->child[0] == u || + u->parent->child[1] == u || + *((tbinptr*)(u->parent)) == u); + if (u->child[0] != 0) { + assert(u->child[0]->parent == u); + assert(u->child[0] != u); + do_check_tree(m, u->child[0]); + } + if (u->child[1] != 0) { + assert(u->child[1]->parent == u); + assert(u->child[1] != u); + do_check_tree(m, u->child[1]); + } + if (u->child[0] != 0 && u->child[1] != 0) { + assert(chunksize(u->child[0]) < chunksize(u->child[1])); + } + } + u = u->fd; + } while (u != t); + assert(head != 0); +} + +/* Check all the chunks in a treebin. */ +static void do_check_treebin(mstate m, bindex_t i) { + tbinptr* tb = treebin_at(m, i); + tchunkptr t = *tb; + int empty = (m->treemap & (1U << i)) == 0; + if (t == 0) + assert(empty); + if (!empty) + do_check_tree(m, t); +} + +/* Check all the chunks in a smallbin. */ +static void do_check_smallbin(mstate m, bindex_t i) { + sbinptr b = smallbin_at(m, i); + mchunkptr p = b->bk; + unsigned int empty = (m->smallmap & (1U << i)) == 0; + if (p == b) + assert(empty); + if (!empty) { + for (; p != b; p = p->bk) { + size_t size = chunksize(p); + mchunkptr q; + /* each chunk claims to be free */ + do_check_free_chunk(m, p); + /* chunk belongs in bin */ + assert(small_index(size) == i); + assert(p->bk == b || chunksize(p->bk) == chunksize(p)); + /* chunk is followed by an inuse chunk */ + q = next_chunk(p); + if (q->head != FENCEPOST_HEAD) + do_check_inuse_chunk(m, q); + } + } +} + +/* Find x in a bin. Used in other check functions. */ +static int bin_find(mstate m, mchunkptr x) { + size_t size = chunksize(x); + if (is_small(size)) { + bindex_t sidx = small_index(size); + sbinptr b = smallbin_at(m, sidx); + if (smallmap_is_marked(m, sidx)) { + mchunkptr p = b; + do { + if (p == x) + return 1; + } while ((p = p->fd) != b); + } + } + else { + bindex_t tidx; + compute_tree_index(size, tidx); + if (treemap_is_marked(m, tidx)) { + tchunkptr t = *treebin_at(m, tidx); + size_t sizebits = size << leftshift_for_tree_index(tidx); + while (t != 0 && chunksize(t) != size) { + t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]; + sizebits <<= 1; + } + if (t != 0) { + tchunkptr u = t; + do { + if (u == (tchunkptr)x) + return 1; + } while ((u = u->fd) != t); + } + } + } + return 0; +} + +/* Traverse each chunk and check it; return total */ +static size_t traverse_and_check(mstate m) { + size_t sum = 0; + if (is_initialized(m)) { + msegmentptr s = &m->seg; + sum += m->topsize + TOP_FOOT_SIZE; + while (s != 0) { + mchunkptr q = align_as_chunk(s->base); + mchunkptr lastq = 0; + assert(pinuse(q)); + while (segment_holds(s, q) && + q != m->top && q->head != FENCEPOST_HEAD) { + sum += chunksize(q); + if (is_inuse(q)) { + assert(!bin_find(m, q)); + do_check_inuse_chunk(m, q); + } + else { + assert(q == m->dv || bin_find(m, q)); + assert(lastq == 0 || is_inuse(lastq)); /* Not 2 consecutive free */ + do_check_free_chunk(m, q); + } + lastq = q; + q = next_chunk(q); + } + s = s->next; + } + } + return sum; +} + + +/* Check all properties of malloc_state. */ +static void do_check_malloc_state(mstate m) { + bindex_t i; + size_t total; + /* check bins */ + for (i = 0; i < NSMALLBINS; ++i) + do_check_smallbin(m, i); + for (i = 0; i < NTREEBINS; ++i) + do_check_treebin(m, i); + + if (m->dvsize != 0) { /* check dv chunk */ + do_check_any_chunk(m, m->dv); + assert(m->dvsize == chunksize(m->dv)); + assert(m->dvsize >= MIN_CHUNK_SIZE); + assert(bin_find(m, m->dv) == 0); + } + + if (m->top != 0) { /* check top chunk */ + do_check_top_chunk(m, m->top); + /*assert(m->topsize == chunksize(m->top)); redundant */ + assert(m->topsize > 0); + assert(bin_find(m, m->top) == 0); + } + + total = traverse_and_check(m); + assert(total <= m->footprint); + assert(m->footprint <= m->max_footprint); +} +#endif /* DEBUG */ + +/* ----------------------------- statistics ------------------------------ */ + +#if !NO_MALLINFO +static struct mallinfo internal_mallinfo(mstate m) { + struct mallinfo nm = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }; + ensure_initialization(); + if (!PREACTION(m)) { + check_malloc_state(m); + if (is_initialized(m)) { + size_t nfree = SIZE_T_ONE; /* top always free */ + size_t mfree = m->topsize + TOP_FOOT_SIZE; + size_t sum = mfree; + msegmentptr s = &m->seg; + while (s != 0) { + mchunkptr q = align_as_chunk(s->base); + while (segment_holds(s, q) && + q != m->top && q->head != FENCEPOST_HEAD) { + size_t sz = chunksize(q); + sum += sz; + if (!is_inuse(q)) { + mfree += sz; + ++nfree; + } + q = next_chunk(q); + } + s = s->next; + } + + nm.arena = sum; + nm.ordblks = nfree; + nm.hblkhd = m->footprint - sum; + nm.usmblks = m->max_footprint; + nm.uordblks = m->footprint - mfree; + nm.fordblks = mfree; + nm.keepcost = m->topsize; + } + + POSTACTION(m); + } + return nm; +} +#endif /* !NO_MALLINFO */ + +#if !NO_MALLOC_STATS +static void internal_malloc_stats(mstate m) { + ensure_initialization(); + if (!PREACTION(m)) { + size_t maxfp = 0; + size_t fp = 0; + size_t used = 0; + check_malloc_state(m); + if (is_initialized(m)) { + msegmentptr s = &m->seg; + maxfp = m->max_footprint; + fp = m->footprint; + used = fp - (m->topsize + TOP_FOOT_SIZE); + + while (s != 0) { + mchunkptr q = align_as_chunk(s->base); + while (segment_holds(s, q) && + q != m->top && q->head != FENCEPOST_HEAD) { + if (!is_inuse(q)) + used -= chunksize(q); + q = next_chunk(q); + } + s = s->next; + } + } + POSTACTION(m); /* drop lock */ + fprintf(stderr, "max system bytes = %10lu\n", (unsigned long)(maxfp)); + fprintf(stderr, "system bytes = %10lu\n", (unsigned long)(fp)); + fprintf(stderr, "in use bytes = %10lu\n", (unsigned long)(used)); + } +} +#endif /* NO_MALLOC_STATS */ + +/* ----------------------- Operations on smallbins ----------------------- */ + +/* + Various forms of linking and unlinking are defined as macros. Even + the ones for trees, which are very long but have very short typical + paths. This is ugly but reduces reliance on inlining support of + compilers. +*/ + +/* Link a free chunk into a smallbin */ +#define insert_small_chunk(M, P, S) {\ + bindex_t I = small_index(S);\ + mchunkptr B = smallbin_at(M, I);\ + mchunkptr F = B;\ + assert(S >= MIN_CHUNK_SIZE);\ + if (!smallmap_is_marked(M, I))\ + mark_smallmap(M, I);\ + else if (RTCHECK(ok_address(M, B->fd)))\ + F = B->fd;\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + B->fd = P;\ + F->bk = P;\ + P->fd = F;\ + P->bk = B;\ +} + +/* Unlink a chunk from a smallbin */ +#define unlink_small_chunk(M, P, S) {\ + mchunkptr F = P->fd;\ + mchunkptr B = P->bk;\ + bindex_t I = small_index(S);\ + assert(P != B);\ + assert(P != F);\ + assert(chunksize(P) == small_index2size(I));\ + if (RTCHECK(F == smallbin_at(M,I) || (ok_address(M, F) && F->bk == P))) { \ + if (B == F) {\ + clear_smallmap(M, I);\ + }\ + else if (RTCHECK(B == smallbin_at(M,I) ||\ + (ok_address(M, B) && B->fd == P))) {\ + F->bk = B;\ + B->fd = F;\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ +} + +/* Unlink the first chunk from a smallbin */ +#define unlink_first_small_chunk(M, B, P, I) {\ + mchunkptr F = P->fd;\ + assert(P != B);\ + assert(P != F);\ + assert(chunksize(P) == small_index2size(I));\ + if (B == F) {\ + clear_smallmap(M, I);\ + }\ + else if (RTCHECK(ok_address(M, F) && F->bk == P)) {\ + F->bk = B;\ + B->fd = F;\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ +} + +/* Replace dv node, binning the old one */ +/* Used only when dvsize known to be small */ +#define replace_dv(M, P, S) {\ + size_t DVS = M->dvsize;\ + assert(is_small(DVS));\ + if (DVS != 0) {\ + mchunkptr DV = M->dv;\ + insert_small_chunk(M, DV, DVS);\ + }\ + M->dvsize = S;\ + M->dv = P;\ +} + +/* ------------------------- Operations on trees ------------------------- */ + +/* Insert chunk into tree */ +#define insert_large_chunk(M, X, S) {\ + tbinptr* H;\ + bindex_t I;\ + compute_tree_index(S, I);\ + H = treebin_at(M, I);\ + X->index = I;\ + X->child[0] = X->child[1] = 0;\ + if (!treemap_is_marked(M, I)) {\ + mark_treemap(M, I);\ + *H = X;\ + X->parent = (tchunkptr)H;\ + X->fd = X->bk = X;\ + }\ + else {\ + tchunkptr T = *H;\ + size_t K = S << leftshift_for_tree_index(I);\ + for (;;) {\ + if (chunksize(T) != S) {\ + tchunkptr* C = &(T->child[(K >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]);\ + K <<= 1;\ + if (*C != 0)\ + T = *C;\ + else if (RTCHECK(ok_address(M, C))) {\ + *C = X;\ + X->parent = T;\ + X->fd = X->bk = X;\ + break;\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + break;\ + }\ + }\ + else {\ + tchunkptr F = T->fd;\ + if (RTCHECK(ok_address(M, T) && ok_address(M, F))) {\ + T->fd = F->bk = X;\ + X->fd = F;\ + X->bk = T;\ + X->parent = 0;\ + break;\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + break;\ + }\ + }\ + }\ + }\ +} + +/* + Unlink steps: + + 1. If x is a chained node, unlink it from its same-sized fd/bk links + and choose its bk node as its replacement. + 2. If x was the last node of its size, but not a leaf node, it must + be replaced with a leaf node (not merely one with an open left or + right), to make sure that lefts and rights of descendents + correspond properly to bit masks. We use the rightmost descendent + of x. We could use any other leaf, but this is easy to locate and + tends to counteract removal of leftmosts elsewhere, and so keeps + paths shorter than minimally guaranteed. This doesn't loop much + because on average a node in a tree is near the bottom. + 3. If x is the base of a chain (i.e., has parent links) relink + x's parent and children to x's replacement (or null if none). +*/ + +#define unlink_large_chunk(M, X) {\ + tchunkptr XP = X->parent;\ + tchunkptr R;\ + if (X->bk != X) {\ + tchunkptr F = X->fd;\ + R = X->bk;\ + if (RTCHECK(ok_address(M, F) && F->bk == X && R->fd == X)) {\ + F->bk = R;\ + R->fd = F;\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + }\ + else {\ + tchunkptr* RP;\ + if (((R = *(RP = &(X->child[1]))) != 0) ||\ + ((R = *(RP = &(X->child[0]))) != 0)) {\ + tchunkptr* CP;\ + while ((*(CP = &(R->child[1])) != 0) ||\ + (*(CP = &(R->child[0])) != 0)) {\ + R = *(RP = CP);\ + }\ + if (RTCHECK(ok_address(M, RP)))\ + *RP = 0;\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + }\ + }\ + if (XP != 0) {\ + tbinptr* H = treebin_at(M, X->index);\ + if (X == *H) {\ + if ((*H = R) == 0) \ + clear_treemap(M, X->index);\ + }\ + else if (RTCHECK(ok_address(M, XP))) {\ + if (XP->child[0] == X) \ + XP->child[0] = R;\ + else \ + XP->child[1] = R;\ + }\ + else\ + CORRUPTION_ERROR_ACTION(M);\ + if (R != 0) {\ + if (RTCHECK(ok_address(M, R))) {\ + tchunkptr C0, C1;\ + R->parent = XP;\ + if ((C0 = X->child[0]) != 0) {\ + if (RTCHECK(ok_address(M, C0))) {\ + R->child[0] = C0;\ + C0->parent = R;\ + }\ + else\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + if ((C1 = X->child[1]) != 0) {\ + if (RTCHECK(ok_address(M, C1))) {\ + R->child[1] = C1;\ + C1->parent = R;\ + }\ + else\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + }\ + else\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + }\ +} + +/* Relays to large vs small bin operations */ + +#define insert_chunk(M, P, S)\ + if (is_small(S)) insert_small_chunk(M, P, S)\ + else { tchunkptr TP = (tchunkptr)(P); insert_large_chunk(M, TP, S); } + +#define unlink_chunk(M, P, S)\ + if (is_small(S)) unlink_small_chunk(M, P, S)\ + else { tchunkptr TP = (tchunkptr)(P); unlink_large_chunk(M, TP); } + + +/* Relays to internal calls to malloc/free from realloc, memalign etc */ + +#if ONLY_MSPACES +#define internal_malloc(m, b) mspace_malloc(m, b) +#define internal_free(m, mem) mspace_free(m,mem); +#else /* ONLY_MSPACES */ +#if MSPACES +#define internal_malloc(m, b)\ + ((m == gm)? dlmalloc(b) : mspace_malloc(m, b)) +#define internal_free(m, mem)\ + if (m == gm) dlfree(mem); else mspace_free(m,mem); +#else /* MSPACES */ +#define internal_malloc(m, b) dlmalloc(b) +#define internal_free(m, mem) dlfree(mem) +#endif /* MSPACES */ +#endif /* ONLY_MSPACES */ + +/* ----------------------- Direct-mmapping chunks ----------------------- */ + +/* + Directly mmapped chunks are set up with an offset to the start of + the mmapped region stored in the prev_foot field of the chunk. This + allows reconstruction of the required argument to MUNMAP when freed, + and also allows adjustment of the returned chunk to meet alignment + requirements (especially in memalign). +*/ + +/* Malloc using mmap */ +static void* mmap_alloc(mstate m, size_t nb) { + size_t mmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK); + if (m->footprint_limit != 0) { + size_t fp = m->footprint + mmsize; + if (fp <= m->footprint || fp > m->footprint_limit) + return 0; + } + if (mmsize > nb) { /* Check for wrap around 0 */ + char* mm = (char*)(CALL_DIRECT_MMAP(mmsize)); + if (mm != CMFAIL) { + size_t offset = align_offset(chunk2mem(mm)); + size_t psize = mmsize - offset - MMAP_FOOT_PAD; + mchunkptr p = (mchunkptr)(mm + offset); + p->prev_foot = offset; + p->head = psize; + mark_inuse_foot(m, p, psize); + chunk_plus_offset(p, psize)->head = FENCEPOST_HEAD; + chunk_plus_offset(p, psize+SIZE_T_SIZE)->head = 0; + + if (m->least_addr == 0 || mm < m->least_addr) + m->least_addr = mm; + if ((m->footprint += mmsize) > m->max_footprint) + m->max_footprint = m->footprint; + assert(is_aligned(chunk2mem(p))); + check_mmapped_chunk(m, p); + return chunk2mem(p); + } + } + return 0; +} + +/* Realloc using mmap */ +static mchunkptr mmap_resize(mstate m, mchunkptr oldp, size_t nb, int flags) { + size_t oldsize = chunksize(oldp); + flags = flags; /* placate people compiling -Wunused */ + if (is_small(nb)) /* Can't shrink mmap regions below small size */ + return 0; + /* Keep old chunk if big enough but not too big */ + if (oldsize >= nb + SIZE_T_SIZE && + (oldsize - nb) <= (mparams.granularity << 1)) + return oldp; + else { + size_t offset = oldp->prev_foot; + size_t oldmmsize = oldsize + offset + MMAP_FOOT_PAD; + size_t newmmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK); + char* cp = (char*)CALL_MREMAP((char*)oldp - offset, + oldmmsize, newmmsize, flags); + if (cp != CMFAIL) { + mchunkptr newp = (mchunkptr)(cp + offset); + size_t psize = newmmsize - offset - MMAP_FOOT_PAD; + newp->head = psize; + mark_inuse_foot(m, newp, psize); + chunk_plus_offset(newp, psize)->head = FENCEPOST_HEAD; + chunk_plus_offset(newp, psize+SIZE_T_SIZE)->head = 0; + + if (cp < m->least_addr) + m->least_addr = cp; + if ((m->footprint += newmmsize - oldmmsize) > m->max_footprint) + m->max_footprint = m->footprint; + check_mmapped_chunk(m, newp); + return newp; + } + } + return 0; +} + + +/* -------------------------- mspace management -------------------------- */ + +/* Initialize top chunk and its size */ +static void init_top(mstate m, mchunkptr p, size_t psize) { + /* Ensure alignment */ + size_t offset = align_offset(chunk2mem(p)); + p = (mchunkptr)((char*)p + offset); + psize -= offset; + + m->top = p; + m->topsize = psize; + p->head = psize | PINUSE_BIT; + /* set size of fake trailing chunk holding overhead space only once */ + chunk_plus_offset(p, psize)->head = TOP_FOOT_SIZE; + m->trim_check = mparams.trim_threshold; /* reset on each update */ +} + +/* Initialize bins for a new mstate that is otherwise zeroed out */ +static void init_bins(mstate m) { + /* Establish circular links for smallbins */ + bindex_t i; + for (i = 0; i < NSMALLBINS; ++i) { + sbinptr bin = smallbin_at(m,i); + bin->fd = bin->bk = bin; + } +} + +#if PROCEED_ON_ERROR + +/* default corruption action */ +static void reset_on_error(mstate m) { + int i; + ++malloc_corruption_error_count; + /* Reinitialize fields to forget about all memory */ + m->smallmap = m->treemap = 0; + m->dvsize = m->topsize = 0; + m->seg.base = 0; + m->seg.size = 0; + m->seg.next = 0; + m->top = m->dv = 0; + for (i = 0; i < NTREEBINS; ++i) + *treebin_at(m, i) = 0; + init_bins(m); +} +#endif /* PROCEED_ON_ERROR */ + +/* Allocate chunk and prepend remainder with chunk in successor base. */ +static void* prepend_alloc(mstate m, char* newbase, char* oldbase, + size_t nb) { + mchunkptr p = align_as_chunk(newbase); + mchunkptr oldfirst = align_as_chunk(oldbase); + size_t psize = (char*)oldfirst - (char*)p; + mchunkptr q = chunk_plus_offset(p, nb); + size_t qsize = psize - nb; + set_size_and_pinuse_of_inuse_chunk(m, p, nb); + + assert((char*)oldfirst > (char*)q); + assert(pinuse(oldfirst)); + assert(qsize >= MIN_CHUNK_SIZE); + + /* consolidate remainder with first chunk of old base */ + if (oldfirst == m->top) { + size_t tsize = m->topsize += qsize; + m->top = q; + q->head = tsize | PINUSE_BIT; + check_top_chunk(m, q); + } + else if (oldfirst == m->dv) { + size_t dsize = m->dvsize += qsize; + m->dv = q; + set_size_and_pinuse_of_free_chunk(q, dsize); + } + else { + if (!is_inuse(oldfirst)) { + size_t nsize = chunksize(oldfirst); + unlink_chunk(m, oldfirst, nsize); + oldfirst = chunk_plus_offset(oldfirst, nsize); + qsize += nsize; + } + set_free_with_pinuse(q, qsize, oldfirst); + insert_chunk(m, q, qsize); + check_free_chunk(m, q); + } + + check_malloced_chunk(m, chunk2mem(p), nb); + return chunk2mem(p); +} + +/* Add a segment to hold a new noncontiguous region */ +static void add_segment(mstate m, char* tbase, size_t tsize, flag_t mmapped) { + /* Determine locations and sizes of segment, fenceposts, old top */ + char* old_top = (char*)m->top; + msegmentptr oldsp = segment_holding(m, old_top); + char* old_end = oldsp->base + oldsp->size; + size_t ssize = pad_request(sizeof(struct malloc_segment)); + char* rawsp = old_end - (ssize + FOUR_SIZE_T_SIZES + CHUNK_ALIGN_MASK); + size_t offset = align_offset(chunk2mem(rawsp)); + char* asp = rawsp + offset; + char* csp = (asp < (old_top + MIN_CHUNK_SIZE))? old_top : asp; + mchunkptr sp = (mchunkptr)csp; + msegmentptr ss = (msegmentptr)(chunk2mem(sp)); + mchunkptr tnext = chunk_plus_offset(sp, ssize); + mchunkptr p = tnext; + int nfences = 0; + + /* reset top to new space */ + init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE); + + /* Set up segment record */ + assert(is_aligned(ss)); + set_size_and_pinuse_of_inuse_chunk(m, sp, ssize); + *ss = m->seg; /* Push current record */ + m->seg.base = tbase; + m->seg.size = tsize; + m->seg.sflags = mmapped; + m->seg.next = ss; + + /* Insert trailing fenceposts */ + for (;;) { + mchunkptr nextp = chunk_plus_offset(p, SIZE_T_SIZE); + p->head = FENCEPOST_HEAD; + ++nfences; + if ((char*)(&(nextp->head)) < old_end) + p = nextp; + else + break; + } + assert(nfences >= 2); + + /* Insert the rest of old top into a bin as an ordinary free chunk */ + if (csp != old_top) { + mchunkptr q = (mchunkptr)old_top; + size_t psize = csp - old_top; + mchunkptr tn = chunk_plus_offset(q, psize); + set_free_with_pinuse(q, psize, tn); + insert_chunk(m, q, psize); + } + + check_top_chunk(m, m->top); +} + +/* -------------------------- System allocation -------------------------- */ + +/* Get memory from system using MORECORE or MMAP */ +static void* sys_alloc(mstate m, size_t nb) { + char* tbase = CMFAIL; + size_t tsize = 0; + flag_t mmap_flag = 0; + size_t asize; /* allocation size */ + + ensure_initialization(); + + /* Directly map large chunks, but only if already initialized */ + if (use_mmap(m) && nb >= mparams.mmap_threshold && m->topsize != 0) { + void* mem = mmap_alloc(m, nb); + if (mem != 0) + return mem; + } + + asize = granularity_align(nb + SYS_ALLOC_PADDING); + if (asize <= nb) + return 0; /* wraparound */ + if (m->footprint_limit != 0) { + size_t fp = m->footprint + asize; + if (fp <= m->footprint || fp > m->footprint_limit) + return 0; + } + + /* + Try getting memory in any of three ways (in most-preferred to + least-preferred order): + 1. A call to MORECORE that can normally contiguously extend memory. + (disabled if not MORECORE_CONTIGUOUS or not HAVE_MORECORE or + or main space is mmapped or a previous contiguous call failed) + 2. A call to MMAP new space (disabled if not HAVE_MMAP). + Note that under the default settings, if MORECORE is unable to + fulfill a request, and HAVE_MMAP is true, then mmap is + used as a noncontiguous system allocator. This is a useful backup + strategy for systems with holes in address spaces -- in this case + sbrk cannot contiguously expand the heap, but mmap may be able to + find space. + 3. A call to MORECORE that cannot usually contiguously extend memory. + (disabled if not HAVE_MORECORE) + + In all cases, we need to request enough bytes from system to ensure + we can malloc nb bytes upon success, so pad with enough space for + top_foot, plus alignment-pad to make sure we don't lose bytes if + not on boundary, and round this up to a granularity unit. + */ + + if (MORECORE_CONTIGUOUS && !use_noncontiguous(m)) { + char* br = CMFAIL; + msegmentptr ss = (m->top == 0)? 0 : segment_holding(m, (char*)m->top); + ACQUIRE_MALLOC_GLOBAL_LOCK(); + + if (ss == 0) { /* First time through or recovery */ + char* base = (char*)CALL_MORECORE(0); + if (base != CMFAIL) { + size_t fp; + /* Adjust to end on a page boundary */ + if (!is_page_aligned(base)) + asize += (page_align((size_t)base) - (size_t)base); + fp = m->footprint + asize; /* recheck limits */ + if (asize > nb && asize < HALF_MAX_SIZE_T && + (m->footprint_limit == 0 || + (fp > m->footprint && fp <= m->footprint_limit)) && + (br = (char*)(CALL_MORECORE(asize))) == base) { + tbase = base; + tsize = asize; + } + } + } + else { + /* Subtract out existing available top space from MORECORE request. */ + asize = granularity_align(nb - m->topsize + SYS_ALLOC_PADDING); + /* Use mem here only if it did continuously extend old space */ + if (asize < HALF_MAX_SIZE_T && + (br = (char*)(CALL_MORECORE(asize))) == ss->base+ss->size) { + tbase = br; + tsize = asize; + } + } + + if (tbase == CMFAIL) { /* Cope with partial failure */ + if (br != CMFAIL) { /* Try to use/extend the space we did get */ + if (asize < HALF_MAX_SIZE_T && + asize < nb + SYS_ALLOC_PADDING) { + size_t esize = granularity_align(nb + SYS_ALLOC_PADDING - asize); + if (esize < HALF_MAX_SIZE_T) { + char* end = (char*)CALL_MORECORE(esize); + if (end != CMFAIL) + asize += esize; + else { /* Can't use; try to release */ + (void) CALL_MORECORE(-asize); + br = CMFAIL; + } + } + } + } + if (br != CMFAIL) { /* Use the space we did get */ + tbase = br; + tsize = asize; + } + else + disable_contiguous(m); /* Don't try contiguous path in the future */ + } + + RELEASE_MALLOC_GLOBAL_LOCK(); + } + + if (HAVE_MMAP && tbase == CMFAIL) { /* Try MMAP */ + char* mp = (char*)(CALL_MMAP(asize)); + if (mp != CMFAIL) { + tbase = mp; + tsize = asize; + mmap_flag = USE_MMAP_BIT; + } + } + + if (HAVE_MORECORE && tbase == CMFAIL) { /* Try noncontiguous MORECORE */ + if (asize < HALF_MAX_SIZE_T) { + char* br = CMFAIL; + char* end = CMFAIL; + ACQUIRE_MALLOC_GLOBAL_LOCK(); + br = (char*)(CALL_MORECORE(asize)); + end = (char*)(CALL_MORECORE(0)); + RELEASE_MALLOC_GLOBAL_LOCK(); + if (br != CMFAIL && end != CMFAIL && br < end) { + size_t ssize = end - br; + if (ssize > nb + TOP_FOOT_SIZE) { + tbase = br; + tsize = ssize; + } + } + } + } + + if (tbase != CMFAIL) { + + if ((m->footprint += tsize) > m->max_footprint) + m->max_footprint = m->footprint; + + if (!is_initialized(m)) { /* first-time initialization */ + if (m->least_addr == 0 || tbase < m->least_addr) + m->least_addr = tbase; + m->seg.base = tbase; + m->seg.size = tsize; + m->seg.sflags = mmap_flag; + m->magic = mparams.magic; + m->release_checks = MAX_RELEASE_CHECK_RATE; + init_bins(m); +#if !ONLY_MSPACES + if (is_global(m)) + init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE); + else +#endif + { + /* Offset top by embedded malloc_state */ + mchunkptr mn = next_chunk(mem2chunk(m)); + init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) -TOP_FOOT_SIZE); + } + } + + else { + /* Try to merge with an existing segment */ + msegmentptr sp = &m->seg; + /* Only consider most recent segment if traversal suppressed */ + while (sp != 0 && tbase != sp->base + sp->size) + sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next; + if (sp != 0 && + !is_extern_segment(sp) && + (sp->sflags & USE_MMAP_BIT) == mmap_flag && + segment_holds(sp, m->top)) { /* append */ + sp->size += tsize; + init_top(m, m->top, m->topsize + tsize); + } + else { + if (tbase < m->least_addr) + m->least_addr = tbase; + sp = &m->seg; + while (sp != 0 && sp->base != tbase + tsize) + sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next; + if (sp != 0 && + !is_extern_segment(sp) && + (sp->sflags & USE_MMAP_BIT) == mmap_flag) { + char* oldbase = sp->base; + sp->base = tbase; + sp->size += tsize; + return prepend_alloc(m, tbase, oldbase, nb); + } + else + add_segment(m, tbase, tsize, mmap_flag); + } + } + + if (nb < m->topsize) { /* Allocate from new or extended top space */ + size_t rsize = m->topsize -= nb; + mchunkptr p = m->top; + mchunkptr r = m->top = chunk_plus_offset(p, nb); + r->head = rsize | PINUSE_BIT; + set_size_and_pinuse_of_inuse_chunk(m, p, nb); + check_top_chunk(m, m->top); + check_malloced_chunk(m, chunk2mem(p), nb); + return chunk2mem(p); + } + } + + MALLOC_FAILURE_ACTION; + return 0; +} + +/* ----------------------- system deallocation -------------------------- */ + +/* Unmap and unlink any mmapped segments that don't contain used chunks */ +static size_t release_unused_segments(mstate m) { + size_t released = 0; + int nsegs = 0; + msegmentptr pred = &m->seg; + msegmentptr sp = pred->next; + while (sp != 0) { + char* base = sp->base; + size_t size = sp->size; + msegmentptr next = sp->next; + ++nsegs; + if (is_mmapped_segment(sp) && !is_extern_segment(sp)) { + mchunkptr p = align_as_chunk(base); + size_t psize = chunksize(p); + /* Can unmap if first chunk holds entire segment and not pinned */ + if (!is_inuse(p) && (char*)p + psize >= base + size - TOP_FOOT_SIZE) { + tchunkptr tp = (tchunkptr)p; + assert(segment_holds(sp, (char*)sp)); + if (p == m->dv) { + m->dv = 0; + m->dvsize = 0; + } + else { + unlink_large_chunk(m, tp); + } + if (CALL_MUNMAP(base, size) == 0) { + released += size; + m->footprint -= size; + /* unlink obsoleted record */ + sp = pred; + sp->next = next; + } + else { /* back out if cannot unmap */ + insert_large_chunk(m, tp, psize); + } + } + } + if (NO_SEGMENT_TRAVERSAL) /* scan only first segment */ + break; + pred = sp; + sp = next; + } + /* Reset check counter */ + m->release_checks = ((nsegs > MAX_RELEASE_CHECK_RATE)? + nsegs : MAX_RELEASE_CHECK_RATE); + return released; +} + +static int sys_trim(mstate m, size_t pad) { + size_t released = 0; + ensure_initialization(); + if (pad < MAX_REQUEST && is_initialized(m)) { + pad += TOP_FOOT_SIZE; /* ensure enough room for segment overhead */ + + if (m->topsize > pad) { + /* Shrink top space in granularity-size units, keeping at least one */ + size_t unit = mparams.granularity; + size_t extra = ((m->topsize - pad + (unit - SIZE_T_ONE)) / unit - + SIZE_T_ONE) * unit; + msegmentptr sp = segment_holding(m, (char*)m->top); + + if (!is_extern_segment(sp)) { + if (is_mmapped_segment(sp)) { + if (HAVE_MMAP && + sp->size >= extra && + !has_segment_link(m, sp)) { /* can't shrink if pinned */ + size_t newsize = sp->size - extra; + /* Prefer mremap, fall back to munmap */ + if ((CALL_MREMAP(sp->base, sp->size, newsize, 0) != MFAIL) || + (CALL_MUNMAP(sp->base + newsize, extra) == 0)) { + released = extra; + } + } + } + else if (HAVE_MORECORE) { + if (extra >= HALF_MAX_SIZE_T) /* Avoid wrapping negative */ + extra = (HALF_MAX_SIZE_T) + SIZE_T_ONE - unit; + ACQUIRE_MALLOC_GLOBAL_LOCK(); + { + /* Make sure end of memory is where we last set it. */ + char* old_br = (char*)(CALL_MORECORE(0)); + if (old_br == sp->base + sp->size) { + char* rel_br = (char*)(CALL_MORECORE(-extra)); + char* new_br = (char*)(CALL_MORECORE(0)); + if (rel_br != CMFAIL && new_br < old_br) + released = old_br - new_br; + } + } + RELEASE_MALLOC_GLOBAL_LOCK(); + } + } + + if (released != 0) { + sp->size -= released; + m->footprint -= released; + init_top(m, m->top, m->topsize - released); + check_top_chunk(m, m->top); + } + } + + /* Unmap any unused mmapped segments */ + if (HAVE_MMAP) + released += release_unused_segments(m); + + /* On failure, disable autotrim to avoid repeated failed future calls */ + if (released == 0 && m->topsize > m->trim_check) + m->trim_check = MAX_SIZE_T; + } + + return (released != 0)? 1 : 0; +} + +/* Consolidate and bin a chunk. Differs from exported versions + of free mainly in that the chunk need not be marked as inuse. +*/ +static void dispose_chunk(mstate m, mchunkptr p, size_t psize) { + mchunkptr next = chunk_plus_offset(p, psize); + if (!pinuse(p)) { + mchunkptr prev; + size_t prevsize = p->prev_foot; + if (is_mmapped(p)) { + psize += prevsize + MMAP_FOOT_PAD; + if (CALL_MUNMAP((char*)p - prevsize, psize) == 0) + m->footprint -= psize; + return; + } + prev = chunk_minus_offset(p, prevsize); + psize += prevsize; + p = prev; + if (RTCHECK(ok_address(m, prev))) { /* consolidate backward */ + if (p != m->dv) { + unlink_chunk(m, p, prevsize); + } + else if ((next->head & INUSE_BITS) == INUSE_BITS) { + m->dvsize = psize; + set_free_with_pinuse(p, psize, next); + return; + } + } + else { + CORRUPTION_ERROR_ACTION(m); + return; + } + } + if (RTCHECK(ok_address(m, next))) { + if (!cinuse(next)) { /* consolidate forward */ + if (next == m->top) { + size_t tsize = m->topsize += psize; + m->top = p; + p->head = tsize | PINUSE_BIT; + if (p == m->dv) { + m->dv = 0; + m->dvsize = 0; + } + return; + } + else if (next == m->dv) { + size_t dsize = m->dvsize += psize; + m->dv = p; + set_size_and_pinuse_of_free_chunk(p, dsize); + return; + } + else { + size_t nsize = chunksize(next); + psize += nsize; + unlink_chunk(m, next, nsize); + set_size_and_pinuse_of_free_chunk(p, psize); + if (p == m->dv) { + m->dvsize = psize; + return; + } + } + } + else { + set_free_with_pinuse(p, psize, next); + } + insert_chunk(m, p, psize); + } + else { + CORRUPTION_ERROR_ACTION(m); + } +} + +/* ---------------------------- malloc --------------------------- */ + +/* allocate a large request from the best fitting chunk in a treebin */ +static void* tmalloc_large(mstate m, size_t nb) { + tchunkptr v = 0; + size_t rsize = -nb; /* Unsigned negation */ + tchunkptr t; + bindex_t idx; + compute_tree_index(nb, idx); + if ((t = *treebin_at(m, idx)) != 0) { + /* Traverse tree for this bin looking for node with size == nb */ + size_t sizebits = nb << leftshift_for_tree_index(idx); + tchunkptr rst = 0; /* The deepest untaken right subtree */ + for (;;) { + tchunkptr rt; + size_t trem = chunksize(t) - nb; + if (trem < rsize) { + v = t; + if ((rsize = trem) == 0) + break; + } + rt = t->child[1]; + t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]; + if (rt != 0 && rt != t) + rst = rt; + if (t == 0) { + t = rst; /* set t to least subtree holding sizes > nb */ + break; + } + sizebits <<= 1; + } + } + if (t == 0 && v == 0) { /* set t to root of next non-empty treebin */ + binmap_t leftbits = left_bits(idx2bit(idx)) & m->treemap; + if (leftbits != 0) { + bindex_t i; + binmap_t leastbit = least_bit(leftbits); + compute_bit2idx(leastbit, i); + t = *treebin_at(m, i); + } + } + + while (t != 0) { /* find smallest of tree or subtree */ + size_t trem = chunksize(t) - nb; + if (trem < rsize) { + rsize = trem; + v = t; + } + t = leftmost_child(t); + } + + /* If dv is a better fit, return 0 so malloc will use it */ + if (v != 0 && rsize < (size_t)(m->dvsize - nb)) { + if (RTCHECK(ok_address(m, v))) { /* split */ + mchunkptr r = chunk_plus_offset(v, nb); + assert(chunksize(v) == rsize + nb); + if (RTCHECK(ok_next(v, r))) { + unlink_large_chunk(m, v); + if (rsize < MIN_CHUNK_SIZE) + set_inuse_and_pinuse(m, v, (rsize + nb)); + else { + set_size_and_pinuse_of_inuse_chunk(m, v, nb); + set_size_and_pinuse_of_free_chunk(r, rsize); + insert_chunk(m, r, rsize); + } + return chunk2mem(v); + } + } + CORRUPTION_ERROR_ACTION(m); + } + return 0; +} + +/* allocate a small request from the best fitting chunk in a treebin */ +static void* tmalloc_small(mstate m, size_t nb) { + tchunkptr t, v; + size_t rsize; + bindex_t i; + binmap_t leastbit = least_bit(m->treemap); + compute_bit2idx(leastbit, i); + v = t = *treebin_at(m, i); + rsize = chunksize(t) - nb; + + while ((t = leftmost_child(t)) != 0) { + size_t trem = chunksize(t) - nb; + if (trem < rsize) { + rsize = trem; + v = t; + } + } + + if (RTCHECK(ok_address(m, v))) { + mchunkptr r = chunk_plus_offset(v, nb); + assert(chunksize(v) == rsize + nb); + if (RTCHECK(ok_next(v, r))) { + unlink_large_chunk(m, v); + if (rsize < MIN_CHUNK_SIZE) + set_inuse_and_pinuse(m, v, (rsize + nb)); + else { + set_size_and_pinuse_of_inuse_chunk(m, v, nb); + set_size_and_pinuse_of_free_chunk(r, rsize); + replace_dv(m, r, rsize); + } + return chunk2mem(v); + } + } + + CORRUPTION_ERROR_ACTION(m); + return 0; +} + +#if !ONLY_MSPACES + +void* dlmalloc(size_t bytes) { + /* + Basic algorithm: + If a small request (< 256 bytes minus per-chunk overhead): + 1. If one exists, use a remainderless chunk in associated smallbin. + (Remainderless means that there are too few excess bytes to + represent as a chunk.) + 2. If it is big enough, use the dv chunk, which is normally the + chunk adjacent to the one used for the most recent small request. + 3. If one exists, split the smallest available chunk in a bin, + saving remainder in dv. + 4. If it is big enough, use the top chunk. + 5. If available, get memory from system and use it + Otherwise, for a large request: + 1. Find the smallest available binned chunk that fits, and use it + if it is better fitting than dv chunk, splitting if necessary. + 2. If better fitting than any binned chunk, use the dv chunk. + 3. If it is big enough, use the top chunk. + 4. If request size >= mmap threshold, try to directly mmap this chunk. + 5. If available, get memory from system and use it + + The ugly goto's here ensure that postaction occurs along all paths. + */ + +#if USE_LOCKS + ensure_initialization(); /* initialize in sys_alloc if not using locks */ +#endif + + if (!PREACTION(gm)) { + void* mem; + size_t nb; + if (bytes <= MAX_SMALL_REQUEST) { + bindex_t idx; + binmap_t smallbits; + nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes); + idx = small_index(nb); + smallbits = gm->smallmap >> idx; + + if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */ + mchunkptr b, p; + idx += ~smallbits & 1; /* Uses next bin if idx empty */ + b = smallbin_at(gm, idx); + p = b->fd; + assert(chunksize(p) == small_index2size(idx)); + unlink_first_small_chunk(gm, b, p, idx); + set_inuse_and_pinuse(gm, p, small_index2size(idx)); + mem = chunk2mem(p); + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + + else if (nb > gm->dvsize) { + if (smallbits != 0) { /* Use chunk in next nonempty smallbin */ + mchunkptr b, p, r; + size_t rsize; + bindex_t i; + binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx)); + binmap_t leastbit = least_bit(leftbits); + compute_bit2idx(leastbit, i); + b = smallbin_at(gm, i); + p = b->fd; + assert(chunksize(p) == small_index2size(i)); + unlink_first_small_chunk(gm, b, p, i); + rsize = small_index2size(i) - nb; + /* Fit here cannot be remainderless if 4byte sizes */ + if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE) + set_inuse_and_pinuse(gm, p, small_index2size(i)); + else { + set_size_and_pinuse_of_inuse_chunk(gm, p, nb); + r = chunk_plus_offset(p, nb); + set_size_and_pinuse_of_free_chunk(r, rsize); + replace_dv(gm, r, rsize); + } + mem = chunk2mem(p); + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + + else if (gm->treemap != 0 && (mem = tmalloc_small(gm, nb)) != 0) { + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + } + } + else if (bytes >= MAX_REQUEST) + nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */ + else { + nb = pad_request(bytes); + if (gm->treemap != 0 && (mem = tmalloc_large(gm, nb)) != 0) { + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + } + + if (nb <= gm->dvsize) { + size_t rsize = gm->dvsize - nb; + mchunkptr p = gm->dv; + if (rsize >= MIN_CHUNK_SIZE) { /* split dv */ + mchunkptr r = gm->dv = chunk_plus_offset(p, nb); + gm->dvsize = rsize; + set_size_and_pinuse_of_free_chunk(r, rsize); + set_size_and_pinuse_of_inuse_chunk(gm, p, nb); + } + else { /* exhaust dv */ + size_t dvs = gm->dvsize; + gm->dvsize = 0; + gm->dv = 0; + set_inuse_and_pinuse(gm, p, dvs); + } + mem = chunk2mem(p); + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + + else if (nb < gm->topsize) { /* Split top */ + size_t rsize = gm->topsize -= nb; + mchunkptr p = gm->top; + mchunkptr r = gm->top = chunk_plus_offset(p, nb); + r->head = rsize | PINUSE_BIT; + set_size_and_pinuse_of_inuse_chunk(gm, p, nb); + mem = chunk2mem(p); + check_top_chunk(gm, gm->top); + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + + mem = sys_alloc(gm, nb); + + postaction: + POSTACTION(gm); + return mem; + } + + return 0; +} + +/* ---------------------------- free --------------------------- */ + +void dlfree(void* mem) { + /* + Consolidate freed chunks with preceeding or succeeding bordering + free chunks, if they exist, and then place in a bin. Intermixed + with special cases for top, dv, mmapped chunks, and usage errors. + */ + + if (mem != 0) { + mchunkptr p = mem2chunk(mem); +#if FOOTERS + mstate fm = get_mstate_for(p); + if (!ok_magic(fm)) { + USAGE_ERROR_ACTION(fm, p); + return; + } +#else /* FOOTERS */ +#define fm gm +#endif /* FOOTERS */ + if (!PREACTION(fm)) { + check_inuse_chunk(fm, p); + if (RTCHECK(ok_address(fm, p) && ok_inuse(p))) { + size_t psize = chunksize(p); + mchunkptr next = chunk_plus_offset(p, psize); + if (!pinuse(p)) { + size_t prevsize = p->prev_foot; + if (is_mmapped(p)) { + psize += prevsize + MMAP_FOOT_PAD; + if (CALL_MUNMAP((char*)p - prevsize, psize) == 0) + fm->footprint -= psize; + goto postaction; + } + else { + mchunkptr prev = chunk_minus_offset(p, prevsize); + psize += prevsize; + p = prev; + if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */ + if (p != fm->dv) { + unlink_chunk(fm, p, prevsize); + } + else if ((next->head & INUSE_BITS) == INUSE_BITS) { + fm->dvsize = psize; + set_free_with_pinuse(p, psize, next); + goto postaction; + } + } + else + goto erroraction; + } + } + + if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) { + if (!cinuse(next)) { /* consolidate forward */ + if (next == fm->top) { + size_t tsize = fm->topsize += psize; + fm->top = p; + p->head = tsize | PINUSE_BIT; + if (p == fm->dv) { + fm->dv = 0; + fm->dvsize = 0; + } + if (should_trim(fm, tsize)) + sys_trim(fm, 0); + goto postaction; + } + else if (next == fm->dv) { + size_t dsize = fm->dvsize += psize; + fm->dv = p; + set_size_and_pinuse_of_free_chunk(p, dsize); + goto postaction; + } + else { + size_t nsize = chunksize(next); + psize += nsize; + unlink_chunk(fm, next, nsize); + set_size_and_pinuse_of_free_chunk(p, psize); + if (p == fm->dv) { + fm->dvsize = psize; + goto postaction; + } + } + } + else + set_free_with_pinuse(p, psize, next); + + if (is_small(psize)) { + insert_small_chunk(fm, p, psize); + check_free_chunk(fm, p); + } + else { + tchunkptr tp = (tchunkptr)p; + insert_large_chunk(fm, tp, psize); + check_free_chunk(fm, p); + if (--fm->release_checks == 0) + release_unused_segments(fm); + } + goto postaction; + } + } + erroraction: + USAGE_ERROR_ACTION(fm, p); + postaction: + POSTACTION(fm); + } + } +#if !FOOTERS +#undef fm +#endif /* FOOTERS */ +} + +void* dlcalloc(size_t n_elements, size_t elem_size) { + void* mem; + size_t req = 0; + if (n_elements != 0) { + req = n_elements * elem_size; + if (((n_elements | elem_size) & ~(size_t)0xffff) && + (req / n_elements != elem_size)) + req = MAX_SIZE_T; /* force downstream failure on overflow */ + } + mem = dlmalloc(req); + if (mem != 0 && calloc_must_clear(mem2chunk(mem))) + memset(mem, 0, req); + return mem; +} + +#endif /* !ONLY_MSPACES */ + +/* ------------ Internal support for realloc, memalign, etc -------------- */ + +/* Try to realloc; only in-place unless can_move true */ +static mchunkptr try_realloc_chunk(mstate m, mchunkptr p, size_t nb, + int can_move) { + mchunkptr newp = 0; + size_t oldsize = chunksize(p); + mchunkptr next = chunk_plus_offset(p, oldsize); + if (RTCHECK(ok_address(m, p) && ok_inuse(p) && + ok_next(p, next) && ok_pinuse(next))) { + if (is_mmapped(p)) { + newp = mmap_resize(m, p, nb, can_move); + } + else if (oldsize >= nb) { /* already big enough */ + size_t rsize = oldsize - nb; + if (rsize >= MIN_CHUNK_SIZE) { /* split off remainder */ + mchunkptr r = chunk_plus_offset(p, nb); + set_inuse(m, p, nb); + set_inuse(m, r, rsize); + dispose_chunk(m, r, rsize); + } + newp = p; + } + else if (next == m->top) { /* extend into top */ + if (oldsize + m->topsize > nb) { + size_t newsize = oldsize + m->topsize; + size_t newtopsize = newsize - nb; + mchunkptr newtop = chunk_plus_offset(p, nb); + set_inuse(m, p, nb); + newtop->head = newtopsize |PINUSE_BIT; + m->top = newtop; + m->topsize = newtopsize; + newp = p; + } + } + else if (next == m->dv) { /* extend into dv */ + size_t dvs = m->dvsize; + if (oldsize + dvs >= nb) { + size_t dsize = oldsize + dvs - nb; + if (dsize >= MIN_CHUNK_SIZE) { + mchunkptr r = chunk_plus_offset(p, nb); + mchunkptr n = chunk_plus_offset(r, dsize); + set_inuse(m, p, nb); + set_size_and_pinuse_of_free_chunk(r, dsize); + clear_pinuse(n); + m->dvsize = dsize; + m->dv = r; + } + else { /* exhaust dv */ + size_t newsize = oldsize + dvs; + set_inuse(m, p, newsize); + m->dvsize = 0; + m->dv = 0; + } + newp = p; + } + } + else if (!cinuse(next)) { /* extend into next free chunk */ + size_t nextsize = chunksize(next); + if (oldsize + nextsize >= nb) { + size_t rsize = oldsize + nextsize - nb; + unlink_chunk(m, next, nextsize); + if (rsize < MIN_CHUNK_SIZE) { + size_t newsize = oldsize + nextsize; + set_inuse(m, p, newsize); + } + else { + mchunkptr r = chunk_plus_offset(p, nb); + set_inuse(m, p, nb); + set_inuse(m, r, rsize); + dispose_chunk(m, r, rsize); + } + newp = p; + } + } + } + else { + USAGE_ERROR_ACTION(m, oldmem); + } + return newp; +} + +static void* internal_memalign(mstate m, size_t alignment, size_t bytes) { + void* mem = 0; + if (alignment < MIN_CHUNK_SIZE) /* must be at least a minimum chunk size */ + alignment = MIN_CHUNK_SIZE; + if ((alignment & (alignment-SIZE_T_ONE)) != 0) {/* Ensure a power of 2 */ + size_t a = MALLOC_ALIGNMENT << 1; + while (a < alignment) a <<= 1; + alignment = a; + } + if (bytes >= MAX_REQUEST - alignment) { + if (m != 0) { /* Test isn't needed but avoids compiler warning */ + MALLOC_FAILURE_ACTION; + } + } + else { + size_t nb = request2size(bytes); + size_t req = nb + alignment + MIN_CHUNK_SIZE - CHUNK_OVERHEAD; + mem = internal_malloc(m, req); + if (mem != 0) { + mchunkptr p = mem2chunk(mem); + if (PREACTION(m)) + return 0; + if ((((size_t)(mem)) & (alignment - 1)) != 0) { /* misaligned */ + /* + Find an aligned spot inside chunk. Since we need to give + back leading space in a chunk of at least MIN_CHUNK_SIZE, if + the first calculation places us at a spot with less than + MIN_CHUNK_SIZE leader, we can move to the next aligned spot. + We've allocated enough total room so that this is always + possible. + */ + char* br = (char*)mem2chunk((size_t)(((size_t)((char*)mem + alignment - + SIZE_T_ONE)) & + -alignment)); + char* pos = ((size_t)(br - (char*)(p)) >= MIN_CHUNK_SIZE)? + br : br+alignment; + mchunkptr newp = (mchunkptr)pos; + size_t leadsize = pos - (char*)(p); + size_t newsize = chunksize(p) - leadsize; + + if (is_mmapped(p)) { /* For mmapped chunks, just adjust offset */ + newp->prev_foot = p->prev_foot + leadsize; + newp->head = newsize; + } + else { /* Otherwise, give back leader, use the rest */ + set_inuse(m, newp, newsize); + set_inuse(m, p, leadsize); + dispose_chunk(m, p, leadsize); + } + p = newp; + } + + /* Give back spare room at the end */ + if (!is_mmapped(p)) { + size_t size = chunksize(p); + if (size > nb + MIN_CHUNK_SIZE) { + size_t remainder_size = size - nb; + mchunkptr remainder = chunk_plus_offset(p, nb); + set_inuse(m, p, nb); + set_inuse(m, remainder, remainder_size); + dispose_chunk(m, remainder, remainder_size); + } + } + + mem = chunk2mem(p); + assert (chunksize(p) >= nb); + assert(((size_t)mem & (alignment - 1)) == 0); + check_inuse_chunk(m, p); + POSTACTION(m); + } + } + return mem; +} + +/* + Common support for independent_X routines, handling + all of the combinations that can result. + The opts arg has: + bit 0 set if all elements are same size (using sizes[0]) + bit 1 set if elements should be zeroed +*/ +static void** ialloc(mstate m, + size_t n_elements, + size_t* sizes, + int opts, + void* chunks[]) { + + size_t element_size; /* chunksize of each element, if all same */ + size_t contents_size; /* total size of elements */ + size_t array_size; /* request size of pointer array */ + void* mem; /* malloced aggregate space */ + mchunkptr p; /* corresponding chunk */ + size_t remainder_size; /* remaining bytes while splitting */ + void** marray; /* either "chunks" or malloced ptr array */ + mchunkptr array_chunk; /* chunk for malloced ptr array */ + flag_t was_enabled; /* to disable mmap */ + size_t size; + size_t i; + + ensure_initialization(); + /* compute array length, if needed */ + if (chunks != 0) { + if (n_elements == 0) + return chunks; /* nothing to do */ + marray = chunks; + array_size = 0; + } + else { + /* if empty req, must still return chunk representing empty array */ + if (n_elements == 0) + return (void**)internal_malloc(m, 0); + marray = 0; + array_size = request2size(n_elements * (sizeof(void*))); + } + + /* compute total element size */ + if (opts & 0x1) { /* all-same-size */ + element_size = request2size(*sizes); + contents_size = n_elements * element_size; + } + else { /* add up all the sizes */ + element_size = 0; + contents_size = 0; + for (i = 0; i != n_elements; ++i) + contents_size += request2size(sizes[i]); + } + + size = contents_size + array_size; + + /* + Allocate the aggregate chunk. First disable direct-mmapping so + malloc won't use it, since we would not be able to later + free/realloc space internal to a segregated mmap region. + */ + was_enabled = use_mmap(m); + disable_mmap(m); + mem = internal_malloc(m, size - CHUNK_OVERHEAD); + if (was_enabled) + enable_mmap(m); + if (mem == 0) + return 0; + + if (PREACTION(m)) return 0; + p = mem2chunk(mem); + remainder_size = chunksize(p); + + assert(!is_mmapped(p)); + + if (opts & 0x2) { /* optionally clear the elements */ + memset((size_t*)mem, 0, remainder_size - SIZE_T_SIZE - array_size); + } + + /* If not provided, allocate the pointer array as final part of chunk */ + if (marray == 0) { + size_t array_chunk_size; + array_chunk = chunk_plus_offset(p, contents_size); + array_chunk_size = remainder_size - contents_size; + marray = (void**) (chunk2mem(array_chunk)); + set_size_and_pinuse_of_inuse_chunk(m, array_chunk, array_chunk_size); + remainder_size = contents_size; + } + + /* split out elements */ + for (i = 0; ; ++i) { + marray[i] = chunk2mem(p); + if (i != n_elements-1) { + if (element_size != 0) + size = element_size; + else + size = request2size(sizes[i]); + remainder_size -= size; + set_size_and_pinuse_of_inuse_chunk(m, p, size); + p = chunk_plus_offset(p, size); + } + else { /* the final element absorbs any overallocation slop */ + set_size_and_pinuse_of_inuse_chunk(m, p, remainder_size); + break; + } + } + +#if DEBUG + if (marray != chunks) { + /* final element must have exactly exhausted chunk */ + if (element_size != 0) { + assert(remainder_size == element_size); + } + else { + assert(remainder_size == request2size(sizes[i])); + } + check_inuse_chunk(m, mem2chunk(marray)); + } + for (i = 0; i != n_elements; ++i) + check_inuse_chunk(m, mem2chunk(marray[i])); + +#endif /* DEBUG */ + + POSTACTION(m); + return marray; +} + +/* Try to free all pointers in the given array. + Note: this could be made faster, by delaying consolidation, + at the price of disabling some user integrity checks, We + still optimize some consolidations by combining adjacent + chunks before freeing, which will occur often if allocated + with ialloc or the array is sorted. +*/ +static size_t internal_bulk_free(mstate m, void* array[], size_t nelem) { + size_t unfreed = 0; + if (!PREACTION(m)) { + void** a; + void** fence = &(array[nelem]); + for (a = array; a != fence; ++a) { + void* mem = *a; + if (mem != 0) { + mchunkptr p = mem2chunk(mem); + size_t psize = chunksize(p); +#if FOOTERS + if (get_mstate_for(p) != m) { + ++unfreed; + continue; + } +#endif + check_inuse_chunk(m, p); + *a = 0; + if (RTCHECK(ok_address(m, p) && ok_inuse(p))) { + void ** b = a + 1; /* try to merge with next chunk */ + mchunkptr next = next_chunk(p); + if (b != fence && *b == chunk2mem(next)) { + size_t newsize = chunksize(next) + psize; + set_inuse(m, p, newsize); + *b = chunk2mem(p); + } + else + dispose_chunk(m, p, psize); + } + else { + CORRUPTION_ERROR_ACTION(m); + break; + } + } + } + if (should_trim(m, m->topsize)) + sys_trim(m, 0); + POSTACTION(m); + } + return unfreed; +} + +/* Traversal */ +#if MALLOC_INSPECT_ALL +static void internal_inspect_all(mstate m, + void(*handler)(void *start, + void *end, + size_t used_bytes, + void* callback_arg), + void* arg) { + if (is_initialized(m)) { + mchunkptr top = m->top; + msegmentptr s; + for (s = &m->seg; s != 0; s = s->next) { + mchunkptr q = align_as_chunk(s->base); + while (segment_holds(s, q) && q->head != FENCEPOST_HEAD) { + mchunkptr next = next_chunk(q); + size_t sz = chunksize(q); + size_t used; + void* start; + if (is_inuse(q)) { + used = sz - CHUNK_OVERHEAD; /* must not be mmapped */ + start = chunk2mem(q); + } + else { + used = 0; + if (is_small(sz)) { /* offset by possible bookkeeping */ + // BEGIN android-changed + start = (void*)((char*)q + sizeof(struct malloc_chunk)); + // END android-changed + } + else { + // BEGIN android-changed + start = (void*)((char*)q + sizeof(struct malloc_tree_chunk)); + // END android-changed + } + } + if (start < (void*)next) /* skip if all space is bookkeeping */ + handler(start, next, used, arg); + if (q == top) + break; + q = next; + } + } + } +} +#endif /* MALLOC_INSPECT_ALL */ + +/* ------------------ Exported realloc, memalign, etc -------------------- */ + +#if !ONLY_MSPACES + +void* dlrealloc(void* oldmem, size_t bytes) { + void* mem = 0; + if (oldmem == 0) { + mem = dlmalloc(bytes); + } + else if (bytes >= MAX_REQUEST) { + MALLOC_FAILURE_ACTION; + } +#ifdef REALLOC_ZERO_BYTES_FREES + else if (bytes == 0) { + dlfree(oldmem); + } +#endif /* REALLOC_ZERO_BYTES_FREES */ + else { + size_t nb = request2size(bytes); + mchunkptr oldp = mem2chunk(oldmem); +#if ! FOOTERS + mstate m = gm; +#else /* FOOTERS */ + mstate m = get_mstate_for(oldp); + if (!ok_magic(m)) { + USAGE_ERROR_ACTION(m, oldmem); + return 0; + } +#endif /* FOOTERS */ + if (!PREACTION(m)) { + mchunkptr newp = try_realloc_chunk(m, oldp, nb, 1); + POSTACTION(m); + if (newp != 0) { + check_inuse_chunk(m, newp); + mem = chunk2mem(newp); + } + else { + mem = internal_malloc(m, bytes); + if (mem != 0) { + size_t oc = chunksize(oldp) - overhead_for(oldp); + memcpy(mem, oldmem, (oc < bytes)? oc : bytes); + internal_free(m, oldmem); + } + } + } + } + return mem; +} + +void* dlrealloc_in_place(void* oldmem, size_t bytes) { + void* mem = 0; + if (oldmem != 0) { + if (bytes >= MAX_REQUEST) { + MALLOC_FAILURE_ACTION; + } + else { + size_t nb = request2size(bytes); + mchunkptr oldp = mem2chunk(oldmem); +#if ! FOOTERS + mstate m = gm; +#else /* FOOTERS */ + mstate m = get_mstate_for(oldp); + if (!ok_magic(m)) { + USAGE_ERROR_ACTION(m, oldmem); + return 0; + } +#endif /* FOOTERS */ + if (!PREACTION(m)) { + mchunkptr newp = try_realloc_chunk(m, oldp, nb, 0); + POSTACTION(m); + if (newp == oldp) { + check_inuse_chunk(m, newp); + mem = oldmem; + } + } + } + } + return mem; +} + +void* dlmemalign(size_t alignment, size_t bytes) { + if (alignment <= MALLOC_ALIGNMENT) { + return dlmalloc(bytes); + } + return internal_memalign(gm, alignment, bytes); +} + +int dlposix_memalign(void** pp, size_t alignment, size_t bytes) { + void* mem = 0; + if (alignment == MALLOC_ALIGNMENT) + mem = dlmalloc(bytes); + else { + size_t d = alignment / sizeof(void*); + size_t r = alignment % sizeof(void*); + if (r != 0 || d == 0 || (d & (d-SIZE_T_ONE)) != 0) + return EINVAL; + else if (bytes >= MAX_REQUEST - alignment) { + if (alignment < MIN_CHUNK_SIZE) + alignment = MIN_CHUNK_SIZE; + mem = internal_memalign(gm, alignment, bytes); + } + } + if (mem == 0) + return ENOMEM; + else { + *pp = mem; + return 0; + } +} + +void* dlvalloc(size_t bytes) { + size_t pagesz; + ensure_initialization(); + pagesz = mparams.page_size; + return dlmemalign(pagesz, bytes); +} + +void* dlpvalloc(size_t bytes) { + size_t pagesz; + ensure_initialization(); + pagesz = mparams.page_size; + return dlmemalign(pagesz, (bytes + pagesz - SIZE_T_ONE) & ~(pagesz - SIZE_T_ONE)); +} + +void** dlindependent_calloc(size_t n_elements, size_t elem_size, + void* chunks[]) { + size_t sz = elem_size; /* serves as 1-element array */ + return ialloc(gm, n_elements, &sz, 3, chunks); +} + +void** dlindependent_comalloc(size_t n_elements, size_t sizes[], + void* chunks[]) { + return ialloc(gm, n_elements, sizes, 0, chunks); +} + +size_t dlbulk_free(void* array[], size_t nelem) { + return internal_bulk_free(gm, array, nelem); +} + +#if MALLOC_INSPECT_ALL +void dlmalloc_inspect_all(void(*handler)(void *start, + void *end, + size_t used_bytes, + void* callback_arg), + void* arg) { + ensure_initialization(); + if (!PREACTION(gm)) { + internal_inspect_all(gm, handler, arg); + POSTACTION(gm); + } +} +#endif /* MALLOC_INSPECT_ALL */ + +int dlmalloc_trim(size_t pad) { + int result = 0; + ensure_initialization(); + if (!PREACTION(gm)) { + result = sys_trim(gm, pad); + POSTACTION(gm); + } + return result; +} + +size_t dlmalloc_footprint(void) { + return gm->footprint; +} + +size_t dlmalloc_max_footprint(void) { + return gm->max_footprint; +} + +size_t dlmalloc_footprint_limit(void) { + size_t maf = gm->footprint_limit; + return maf == 0 ? MAX_SIZE_T : maf; +} + +size_t dlmalloc_set_footprint_limit(size_t bytes) { + size_t result; /* invert sense of 0 */ + if (bytes == 0) + result = granularity_align(1); /* Use minimal size */ + if (bytes == MAX_SIZE_T) + result = 0; /* disable */ + else + result = granularity_align(bytes); + return gm->footprint_limit = result; +} + +#if !NO_MALLINFO +struct mallinfo dlmallinfo(void) { + return internal_mallinfo(gm); +} +#endif /* NO_MALLINFO */ + +#if !NO_MALLOC_STATS +void dlmalloc_stats() { + internal_malloc_stats(gm); +} +#endif /* NO_MALLOC_STATS */ + +int dlmallopt(int param_number, int value) { + return change_mparam(param_number, value); +} + +size_t dlmalloc_usable_size(void* mem) { + if (mem != 0) { + mchunkptr p = mem2chunk(mem); + if (is_inuse(p)) + return chunksize(p) - overhead_for(p); + } + return 0; +} + +#endif /* !ONLY_MSPACES */ + +/* ----------------------------- user mspaces ---------------------------- */ + +#if MSPACES + +static mstate init_user_mstate(char* tbase, size_t tsize) { + size_t msize = pad_request(sizeof(struct malloc_state)); + mchunkptr mn; + mchunkptr msp = align_as_chunk(tbase); + mstate m = (mstate)(chunk2mem(msp)); + memset(m, 0, msize); + (void)INITIAL_LOCK(&m->mutex); + msp->head = (msize|INUSE_BITS); + m->seg.base = m->least_addr = tbase; + m->seg.size = m->footprint = m->max_footprint = tsize; + m->magic = mparams.magic; + m->release_checks = MAX_RELEASE_CHECK_RATE; + m->mflags = mparams.default_mflags; + m->extp = 0; + m->exts = 0; + disable_contiguous(m); + init_bins(m); + mn = next_chunk(mem2chunk(m)); + init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) - TOP_FOOT_SIZE); + check_top_chunk(m, m->top); + return m; +} + +mspace create_mspace(size_t capacity, int locked) { + mstate m = 0; + size_t msize; + ensure_initialization(); + msize = pad_request(sizeof(struct malloc_state)); + if (capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) { + size_t rs = ((capacity == 0)? mparams.granularity : + (capacity + TOP_FOOT_SIZE + msize)); + size_t tsize = granularity_align(rs); + char* tbase = (char*)(CALL_MMAP(tsize)); + if (tbase != CMFAIL) { + m = init_user_mstate(tbase, tsize); + m->seg.sflags = USE_MMAP_BIT; + set_lock(m, locked); + } + } + return (mspace)m; +} + +mspace create_mspace_with_base(void* base, size_t capacity, int locked) { + mstate m = 0; + size_t msize; + ensure_initialization(); + msize = pad_request(sizeof(struct malloc_state)); + if (capacity > msize + TOP_FOOT_SIZE && + capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) { + m = init_user_mstate((char*)base, capacity); + m->seg.sflags = EXTERN_BIT; + set_lock(m, locked); + } + return (mspace)m; +} + +int mspace_track_large_chunks(mspace msp, int enable) { + int ret = 0; + mstate ms = (mstate)msp; + if (!PREACTION(ms)) { + if (!use_mmap(ms)) + ret = 1; + if (!enable) + enable_mmap(ms); + else + disable_mmap(ms); + POSTACTION(ms); + } + return ret; +} + +size_t destroy_mspace(mspace msp) { + size_t freed = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + msegmentptr sp = &ms->seg; + (void)DESTROY_LOCK(&ms->mutex); /* destroy before unmapped */ + while (sp != 0) { + char* base = sp->base; + size_t size = sp->size; + flag_t flag = sp->sflags; + sp = sp->next; + if ((flag & USE_MMAP_BIT) && !(flag & EXTERN_BIT) && + CALL_MUNMAP(base, size) == 0) + freed += size; + } + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return freed; +} + +/* + mspace versions of routines are near-clones of the global + versions. This is not so nice but better than the alternatives. +*/ + +void* mspace_malloc(mspace msp, size_t bytes) { + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + if (!PREACTION(ms)) { + void* mem; + size_t nb; + if (bytes <= MAX_SMALL_REQUEST) { + bindex_t idx; + binmap_t smallbits; + nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes); + idx = small_index(nb); + smallbits = ms->smallmap >> idx; + + if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */ + mchunkptr b, p; + idx += ~smallbits & 1; /* Uses next bin if idx empty */ + b = smallbin_at(ms, idx); + p = b->fd; + assert(chunksize(p) == small_index2size(idx)); + unlink_first_small_chunk(ms, b, p, idx); + set_inuse_and_pinuse(ms, p, small_index2size(idx)); + mem = chunk2mem(p); + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + + else if (nb > ms->dvsize) { + if (smallbits != 0) { /* Use chunk in next nonempty smallbin */ + mchunkptr b, p, r; + size_t rsize; + bindex_t i; + binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx)); + binmap_t leastbit = least_bit(leftbits); + compute_bit2idx(leastbit, i); + b = smallbin_at(ms, i); + p = b->fd; + assert(chunksize(p) == small_index2size(i)); + unlink_first_small_chunk(ms, b, p, i); + rsize = small_index2size(i) - nb; + /* Fit here cannot be remainderless if 4byte sizes */ + if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE) + set_inuse_and_pinuse(ms, p, small_index2size(i)); + else { + set_size_and_pinuse_of_inuse_chunk(ms, p, nb); + r = chunk_plus_offset(p, nb); + set_size_and_pinuse_of_free_chunk(r, rsize); + replace_dv(ms, r, rsize); + } + mem = chunk2mem(p); + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + + else if (ms->treemap != 0 && (mem = tmalloc_small(ms, nb)) != 0) { + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + } + } + else if (bytes >= MAX_REQUEST) + nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */ + else { + nb = pad_request(bytes); + if (ms->treemap != 0 && (mem = tmalloc_large(ms, nb)) != 0) { + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + } + + if (nb <= ms->dvsize) { + size_t rsize = ms->dvsize - nb; + mchunkptr p = ms->dv; + if (rsize >= MIN_CHUNK_SIZE) { /* split dv */ + mchunkptr r = ms->dv = chunk_plus_offset(p, nb); + ms->dvsize = rsize; + set_size_and_pinuse_of_free_chunk(r, rsize); + set_size_and_pinuse_of_inuse_chunk(ms, p, nb); + } + else { /* exhaust dv */ + size_t dvs = ms->dvsize; + ms->dvsize = 0; + ms->dv = 0; + set_inuse_and_pinuse(ms, p, dvs); + } + mem = chunk2mem(p); + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + + else if (nb < ms->topsize) { /* Split top */ + size_t rsize = ms->topsize -= nb; + mchunkptr p = ms->top; + mchunkptr r = ms->top = chunk_plus_offset(p, nb); + r->head = rsize | PINUSE_BIT; + set_size_and_pinuse_of_inuse_chunk(ms, p, nb); + mem = chunk2mem(p); + check_top_chunk(ms, ms->top); + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + + mem = sys_alloc(ms, nb); + + postaction: + POSTACTION(ms); + return mem; + } + + return 0; +} + +void mspace_free(mspace msp, void* mem) { + if (mem != 0) { + mchunkptr p = mem2chunk(mem); +#if FOOTERS + mstate fm = get_mstate_for(p); + msp = msp; /* placate people compiling -Wunused */ +#else /* FOOTERS */ + mstate fm = (mstate)msp; +#endif /* FOOTERS */ + if (!ok_magic(fm)) { + USAGE_ERROR_ACTION(fm, p); + return; + } + if (!PREACTION(fm)) { + check_inuse_chunk(fm, p); + if (RTCHECK(ok_address(fm, p) && ok_inuse(p))) { + size_t psize = chunksize(p); + mchunkptr next = chunk_plus_offset(p, psize); + if (!pinuse(p)) { + size_t prevsize = p->prev_foot; + if (is_mmapped(p)) { + psize += prevsize + MMAP_FOOT_PAD; + if (CALL_MUNMAP((char*)p - prevsize, psize) == 0) + fm->footprint -= psize; + goto postaction; + } + else { + mchunkptr prev = chunk_minus_offset(p, prevsize); + psize += prevsize; + p = prev; + if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */ + if (p != fm->dv) { + unlink_chunk(fm, p, prevsize); + } + else if ((next->head & INUSE_BITS) == INUSE_BITS) { + fm->dvsize = psize; + set_free_with_pinuse(p, psize, next); + goto postaction; + } + } + else + goto erroraction; + } + } + + if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) { + if (!cinuse(next)) { /* consolidate forward */ + if (next == fm->top) { + size_t tsize = fm->topsize += psize; + fm->top = p; + p->head = tsize | PINUSE_BIT; + if (p == fm->dv) { + fm->dv = 0; + fm->dvsize = 0; + } + if (should_trim(fm, tsize)) + sys_trim(fm, 0); + goto postaction; + } + else if (next == fm->dv) { + size_t dsize = fm->dvsize += psize; + fm->dv = p; + set_size_and_pinuse_of_free_chunk(p, dsize); + goto postaction; + } + else { + size_t nsize = chunksize(next); + psize += nsize; + unlink_chunk(fm, next, nsize); + set_size_and_pinuse_of_free_chunk(p, psize); + if (p == fm->dv) { + fm->dvsize = psize; + goto postaction; + } + } + } + else + set_free_with_pinuse(p, psize, next); + + if (is_small(psize)) { + insert_small_chunk(fm, p, psize); + check_free_chunk(fm, p); + } + else { + tchunkptr tp = (tchunkptr)p; + insert_large_chunk(fm, tp, psize); + check_free_chunk(fm, p); + if (--fm->release_checks == 0) + release_unused_segments(fm); + } + goto postaction; + } + } + erroraction: + USAGE_ERROR_ACTION(fm, p); + postaction: + POSTACTION(fm); + } + } +} + +void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size) { + void* mem; + size_t req = 0; + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + if (n_elements != 0) { + req = n_elements * elem_size; + if (((n_elements | elem_size) & ~(size_t)0xffff) && + (req / n_elements != elem_size)) + req = MAX_SIZE_T; /* force downstream failure on overflow */ + } + mem = internal_malloc(ms, req); + if (mem != 0 && calloc_must_clear(mem2chunk(mem))) + memset(mem, 0, req); + return mem; +} + +void* mspace_realloc(mspace msp, void* oldmem, size_t bytes) { + void* mem = 0; + if (oldmem == 0) { + mem = mspace_malloc(msp, bytes); + } + else if (bytes >= MAX_REQUEST) { + MALLOC_FAILURE_ACTION; + } +#ifdef REALLOC_ZERO_BYTES_FREES + else if (bytes == 0) { + mspace_free(msp, oldmem); + } +#endif /* REALLOC_ZERO_BYTES_FREES */ + else { + size_t nb = request2size(bytes); + mchunkptr oldp = mem2chunk(oldmem); +#if ! FOOTERS + mstate m = (mstate)msp; +#else /* FOOTERS */ + mstate m = get_mstate_for(oldp); + if (!ok_magic(m)) { + USAGE_ERROR_ACTION(m, oldmem); + return 0; + } +#endif /* FOOTERS */ + if (!PREACTION(m)) { + mchunkptr newp = try_realloc_chunk(m, oldp, nb, 1); + POSTACTION(m); + if (newp != 0) { + check_inuse_chunk(m, newp); + mem = chunk2mem(newp); + } + else { + mem = mspace_malloc(m, bytes); + if (mem != 0) { + size_t oc = chunksize(oldp) - overhead_for(oldp); + memcpy(mem, oldmem, (oc < bytes)? oc : bytes); + mspace_free(m, oldmem); + } + } + } + } + return mem; +} + +void* mspace_realloc_in_place(mspace msp, void* oldmem, size_t bytes) { + void* mem = 0; + if (oldmem != 0) { + if (bytes >= MAX_REQUEST) { + MALLOC_FAILURE_ACTION; + } + else { + size_t nb = request2size(bytes); + mchunkptr oldp = mem2chunk(oldmem); +#if ! FOOTERS + mstate m = (mstate)msp; +#else /* FOOTERS */ + mstate m = get_mstate_for(oldp); + msp = msp; /* placate people compiling -Wunused */ + if (!ok_magic(m)) { + USAGE_ERROR_ACTION(m, oldmem); + return 0; + } +#endif /* FOOTERS */ + if (!PREACTION(m)) { + mchunkptr newp = try_realloc_chunk(m, oldp, nb, 0); + POSTACTION(m); + if (newp == oldp) { + check_inuse_chunk(m, newp); + mem = oldmem; + } + } + } + } + return mem; +} + +void* mspace_memalign(mspace msp, size_t alignment, size_t bytes) { + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + if (alignment <= MALLOC_ALIGNMENT) + return mspace_malloc(msp, bytes); + return internal_memalign(ms, alignment, bytes); +} + +void** mspace_independent_calloc(mspace msp, size_t n_elements, + size_t elem_size, void* chunks[]) { + size_t sz = elem_size; /* serves as 1-element array */ + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + return ialloc(ms, n_elements, &sz, 3, chunks); +} + +void** mspace_independent_comalloc(mspace msp, size_t n_elements, + size_t sizes[], void* chunks[]) { + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + return ialloc(ms, n_elements, sizes, 0, chunks); +} + +size_t mspace_bulk_free(mspace msp, void* array[], size_t nelem) { + return internal_bulk_free((mstate)msp, array, nelem); +} + +#if MALLOC_INSPECT_ALL +void mspace_inspect_all(mspace msp, + void(*handler)(void *start, + void *end, + size_t used_bytes, + void* callback_arg), + void* arg) { + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + if (!PREACTION(ms)) { + internal_inspect_all(ms, handler, arg); + POSTACTION(ms); + } + } + else { + USAGE_ERROR_ACTION(ms,ms); + } +} +#endif /* MALLOC_INSPECT_ALL */ + +int mspace_trim(mspace msp, size_t pad) { + int result = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + if (!PREACTION(ms)) { + result = sys_trim(ms, pad); + POSTACTION(ms); + } + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return result; +} + +#if !NO_MALLOC_STATS +void mspace_malloc_stats(mspace msp) { + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + internal_malloc_stats(ms); + } + else { + USAGE_ERROR_ACTION(ms,ms); + } +} +#endif /* NO_MALLOC_STATS */ + +size_t mspace_footprint(mspace msp) { + size_t result = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + result = ms->footprint; + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return result; +} + +size_t mspace_max_footprint(mspace msp) { + size_t result = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + result = ms->max_footprint; + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return result; +} + +size_t mspace_footprint_limit(mspace msp) { + size_t result = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + size_t maf = ms->footprint_limit; + result = (maf == 0) ? MAX_SIZE_T : maf; + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return result; +} + +size_t mspace_set_footprint_limit(mspace msp, size_t bytes) { + size_t result = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + if (bytes == 0) + result = granularity_align(1); /* Use minimal size */ + if (bytes == MAX_SIZE_T) + result = 0; /* disable */ + else + result = granularity_align(bytes); + ms->footprint_limit = result; + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return result; +} + +#if !NO_MALLINFO +struct mallinfo mspace_mallinfo(mspace msp) { + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + } + return internal_mallinfo(ms); +} +#endif /* NO_MALLINFO */ + +size_t mspace_usable_size(void* mem) { + if (mem != 0) { + mchunkptr p = mem2chunk(mem); + if (is_inuse(p)) + return chunksize(p) - overhead_for(p); + } + return 0; +} + +int mspace_mallopt(int param_number, int value) { + return change_mparam(param_number, value); +} + +#endif /* MSPACES */ + + +/* -------------------- Alternative MORECORE functions ------------------- */ + +/* + Guidelines for creating a custom version of MORECORE: + + * For best performance, MORECORE should allocate in multiples of pagesize. + * MORECORE may allocate more memory than requested. (Or even less, + but this will usually result in a malloc failure.) + * MORECORE must not allocate memory when given argument zero, but + instead return one past the end address of memory from previous + nonzero call. + * For best performance, consecutive calls to MORECORE with positive + arguments should return increasing addresses, indicating that + space has been contiguously extended. + * Even though consecutive calls to MORECORE need not return contiguous + addresses, it must be OK for malloc'ed chunks to span multiple + regions in those cases where they do happen to be contiguous. + * MORECORE need not handle negative arguments -- it may instead + just return MFAIL when given negative arguments. + Negative arguments are always multiples of pagesize. MORECORE + must not misinterpret negative args as large positive unsigned + args. You can suppress all such calls from even occurring by defining + MORECORE_CANNOT_TRIM, + + As an example alternative MORECORE, here is a custom allocator + kindly contributed for pre-OSX macOS. It uses virtually but not + necessarily physically contiguous non-paged memory (locked in, + present and won't get swapped out). You can use it by uncommenting + this section, adding some #includes, and setting up the appropriate + defines above: + + #define MORECORE osMoreCore + + There is also a shutdown routine that should somehow be called for + cleanup upon program exit. + + #define MAX_POOL_ENTRIES 100 + #define MINIMUM_MORECORE_SIZE (64 * 1024U) + static int next_os_pool; + void *our_os_pools[MAX_POOL_ENTRIES]; + + void *osMoreCore(int size) + { + void *ptr = 0; + static void *sbrk_top = 0; + + if (size > 0) + { + if (size < MINIMUM_MORECORE_SIZE) + size = MINIMUM_MORECORE_SIZE; + if (CurrentExecutionLevel() == kTaskLevel) + ptr = PoolAllocateResident(size + RM_PAGE_SIZE, 0); + if (ptr == 0) + { + return (void *) MFAIL; + } + // save ptrs so they can be freed during cleanup + our_os_pools[next_os_pool] = ptr; + next_os_pool++; + ptr = (void *) ((((size_t) ptr) + RM_PAGE_MASK) & ~RM_PAGE_MASK); + sbrk_top = (char *) ptr + size; + return ptr; + } + else if (size < 0) + { + // we don't currently support shrink behavior + return (void *) MFAIL; + } + else + { + return sbrk_top; + } + } + + // cleanup any allocated memory pools + // called as last thing before shutting down driver + + void osCleanupMem(void) + { + void **ptr; + + for (ptr = our_os_pools; ptr < &our_os_pools[MAX_POOL_ENTRIES]; ptr++) + if (*ptr) + { + PoolDeallocate(*ptr); + *ptr = 0; + } + } + +*/ + + +/* ----------------------------------------------------------------------- +History: + v2.8.5 Sun May 22 10:26:02 2011 Doug Lea (dl at gee) + * Always perform unlink checks unless INSECURE + * Add posix_memalign. + * Improve realloc to expand in more cases; expose realloc_in_place. + Thanks to Peter Buhr for the suggestion. + * Add footprint_limit, inspect_all, bulk_free. Thanks + to Barry Hayes and others for the suggestions. + * Internal refactorings to avoid calls while holding locks + * Use non-reentrant locks by default. Thanks to Roland McGrath + for the suggestion. + * Small fixes to mspace_destroy, reset_on_error. + * Various configuration extensions/changes. Thanks + to all who contributed these. + + V2.8.4a Thu Apr 28 14:39:43 2011 (dl at gee.cs.oswego.edu) + * Update Creative Commons URL + + V2.8.4 Wed May 27 09:56:23 2009 Doug Lea (dl at gee) + * Use zeros instead of prev foot for is_mmapped + * Add mspace_track_large_chunks; thanks to Jean Brouwers + * Fix set_inuse in internal_realloc; thanks to Jean Brouwers + * Fix insufficient sys_alloc padding when using 16byte alignment + * Fix bad error check in mspace_footprint + * Adaptations for ptmalloc; thanks to Wolfram Gloger. + * Reentrant spin locks; thanks to Earl Chew and others + * Win32 improvements; thanks to Niall Douglas and Earl Chew + * Add NO_SEGMENT_TRAVERSAL and MAX_RELEASE_CHECK_RATE options + * Extension hook in malloc_state + * Various small adjustments to reduce warnings on some compilers + * Various configuration extensions/changes for more platforms. Thanks + to all who contributed these. + + V2.8.3 Thu Sep 22 11:16:32 2005 Doug Lea (dl at gee) + * Add max_footprint functions + * Ensure all appropriate literals are size_t + * Fix conditional compilation problem for some #define settings + * Avoid concatenating segments with the one provided + in create_mspace_with_base + * Rename some variables to avoid compiler shadowing warnings + * Use explicit lock initialization. + * Better handling of sbrk interference. + * Simplify and fix segment insertion, trimming and mspace_destroy + * Reinstate REALLOC_ZERO_BYTES_FREES option from 2.7.x + * Thanks especially to Dennis Flanagan for help on these. + + V2.8.2 Sun Jun 12 16:01:10 2005 Doug Lea (dl at gee) + * Fix memalign brace error. + + V2.8.1 Wed Jun 8 16:11:46 2005 Doug Lea (dl at gee) + * Fix improper #endif nesting in C++ + * Add explicit casts needed for C++ + + V2.8.0 Mon May 30 14:09:02 2005 Doug Lea (dl at gee) + * Use trees for large bins + * Support mspaces + * Use segments to unify sbrk-based and mmap-based system allocation, + removing need for emulation on most platforms without sbrk. + * Default safety checks + * Optional footer checks. Thanks to William Robertson for the idea. + * Internal code refactoring + * Incorporate suggestions and platform-specific changes. + Thanks to Dennis Flanagan, Colin Plumb, Niall Douglas, + Aaron Bachmann, Emery Berger, and others. + * Speed up non-fastbin processing enough to remove fastbins. + * Remove useless cfree() to avoid conflicts with other apps. + * Remove internal memcpy, memset. Compilers handle builtins better. + * Remove some options that no one ever used and rename others. + + V2.7.2 Sat Aug 17 09:07:30 2002 Doug Lea (dl at gee) + * Fix malloc_state bitmap array misdeclaration + + V2.7.1 Thu Jul 25 10:58:03 2002 Doug Lea (dl at gee) + * Allow tuning of FIRST_SORTED_BIN_SIZE + * Use PTR_UINT as type for all ptr->int casts. Thanks to John Belmonte. + * Better detection and support for non-contiguousness of MORECORE. + Thanks to Andreas Mueller, Conal Walsh, and Wolfram Gloger + * Bypass most of malloc if no frees. Thanks To Emery Berger. + * Fix freeing of old top non-contiguous chunk im sysmalloc. + * Raised default trim and map thresholds to 256K. + * Fix mmap-related #defines. Thanks to Lubos Lunak. + * Fix copy macros; added LACKS_FCNTL_H. Thanks to Neal Walfield. + * Branch-free bin calculation + * Default trim and mmap thresholds now 256K. + + V2.7.0 Sun Mar 11 14:14:06 2001 Doug Lea (dl at gee) + * Introduce independent_comalloc and independent_calloc. + Thanks to Michael Pachos for motivation and help. + * Make optional .h file available + * Allow > 2GB requests on 32bit systems. + * new WIN32 sbrk, mmap, munmap, lock code from <Walter@GeNeSys-e.de>. + Thanks also to Andreas Mueller <a.mueller at paradatec.de>, + and Anonymous. + * Allow override of MALLOC_ALIGNMENT (Thanks to Ruud Waij for + helping test this.) + * memalign: check alignment arg + * realloc: don't try to shift chunks backwards, since this + leads to more fragmentation in some programs and doesn't + seem to help in any others. + * Collect all cases in malloc requiring system memory into sysmalloc + * Use mmap as backup to sbrk + * Place all internal state in malloc_state + * Introduce fastbins (although similar to 2.5.1) + * Many minor tunings and cosmetic improvements + * Introduce USE_PUBLIC_MALLOC_WRAPPERS, USE_MALLOC_LOCK + * Introduce MALLOC_FAILURE_ACTION, MORECORE_CONTIGUOUS + Thanks to Tony E. Bennett <tbennett@nvidia.com> and others. + * Include errno.h to support default failure action. + + V2.6.6 Sun Dec 5 07:42:19 1999 Doug Lea (dl at gee) + * return null for negative arguments + * Added Several WIN32 cleanups from Martin C. Fong <mcfong at yahoo.com> + * Add 'LACKS_SYS_PARAM_H' for those systems without 'sys/param.h' + (e.g. WIN32 platforms) + * Cleanup header file inclusion for WIN32 platforms + * Cleanup code to avoid Microsoft Visual C++ compiler complaints + * Add 'USE_DL_PREFIX' to quickly allow co-existence with existing + memory allocation routines + * Set 'malloc_getpagesize' for WIN32 platforms (needs more work) + * Use 'assert' rather than 'ASSERT' in WIN32 code to conform to + usage of 'assert' in non-WIN32 code + * Improve WIN32 'sbrk()' emulation's 'findRegion()' routine to + avoid infinite loop + * Always call 'fREe()' rather than 'free()' + + V2.6.5 Wed Jun 17 15:57:31 1998 Doug Lea (dl at gee) + * Fixed ordering problem with boundary-stamping + + V2.6.3 Sun May 19 08:17:58 1996 Doug Lea (dl at gee) + * Added pvalloc, as recommended by H.J. Liu + * Added 64bit pointer support mainly from Wolfram Gloger + * Added anonymously donated WIN32 sbrk emulation + * Malloc, calloc, getpagesize: add optimizations from Raymond Nijssen + * malloc_extend_top: fix mask error that caused wastage after + foreign sbrks + * Add linux mremap support code from HJ Liu + + V2.6.2 Tue Dec 5 06:52:55 1995 Doug Lea (dl at gee) + * Integrated most documentation with the code. + * Add support for mmap, with help from + Wolfram Gloger (Gloger@lrz.uni-muenchen.de). + * Use last_remainder in more cases. + * Pack bins using idea from colin@nyx10.cs.du.edu + * Use ordered bins instead of best-fit threshhold + * Eliminate block-local decls to simplify tracing and debugging. + * Support another case of realloc via move into top + * Fix error occuring when initial sbrk_base not word-aligned. + * Rely on page size for units instead of SBRK_UNIT to + avoid surprises about sbrk alignment conventions. + * Add mallinfo, mallopt. Thanks to Raymond Nijssen + (raymond@es.ele.tue.nl) for the suggestion. + * Add `pad' argument to malloc_trim and top_pad mallopt parameter. + * More precautions for cases where other routines call sbrk, + courtesy of Wolfram Gloger (Gloger@lrz.uni-muenchen.de). + * Added macros etc., allowing use in linux libc from + H.J. Lu (hjl@gnu.ai.mit.edu) + * Inverted this history list + + V2.6.1 Sat Dec 2 14:10:57 1995 Doug Lea (dl at gee) + * Re-tuned and fixed to behave more nicely with V2.6.0 changes. + * Removed all preallocation code since under current scheme + the work required to undo bad preallocations exceeds + the work saved in good cases for most test programs. + * No longer use return list or unconsolidated bins since + no scheme using them consistently outperforms those that don't + given above changes. + * Use best fit for very large chunks to prevent some worst-cases. + * Added some support for debugging + + V2.6.0 Sat Nov 4 07:05:23 1995 Doug Lea (dl at gee) + * Removed footers when chunks are in use. Thanks to + Paul Wilson (wilson@cs.texas.edu) for the suggestion. + + V2.5.4 Wed Nov 1 07:54:51 1995 Doug Lea (dl at gee) + * Added malloc_trim, with help from Wolfram Gloger + (wmglo@Dent.MED.Uni-Muenchen.DE). + + V2.5.3 Tue Apr 26 10:16:01 1994 Doug Lea (dl at g) + + V2.5.2 Tue Apr 5 16:20:40 1994 Doug Lea (dl at g) + * realloc: try to expand in both directions + * malloc: swap order of clean-bin strategy; + * realloc: only conditionally expand backwards + * Try not to scavenge used bins + * Use bin counts as a guide to preallocation + * Occasionally bin return list chunks in first scan + * Add a few optimizations from colin@nyx10.cs.du.edu + + V2.5.1 Sat Aug 14 15:40:43 1993 Doug Lea (dl at g) + * faster bin computation & slightly different binning + * merged all consolidations to one part of malloc proper + (eliminating old malloc_find_space & malloc_clean_bin) + * Scan 2 returns chunks (not just 1) + * Propagate failure in realloc if malloc returns 0 + * Add stuff to allow compilation on non-ANSI compilers + from kpv@research.att.com + + V2.5 Sat Aug 7 07:41:59 1993 Doug Lea (dl at g.oswego.edu) + * removed potential for odd address access in prev_chunk + * removed dependency on getpagesize.h + * misc cosmetics and a bit more internal documentation + * anticosmetics: mangled names in macros to evade debugger strangeness + * tested on sparc, hp-700, dec-mips, rs6000 + with gcc & native cc (hp, dec only) allowing + Detlefs & Zorn comparison study (in SIGPLAN Notices.) + + Trial version Fri Aug 28 13:14:29 1992 Doug Lea (dl at g.oswego.edu) + * Based loosely on libg++-1.2X malloc. (It retains some of the overall + structure of old version, but most details differ.) + +*/ + diff --git a/src/dlmalloc/malloc.h b/src/dlmalloc/malloc.h new file mode 100644 index 0000000000..d51f1e0b04 --- /dev/null +++ b/src/dlmalloc/malloc.h @@ -0,0 +1,620 @@ +/* + Default header file for malloc-2.8.x, written by Doug Lea + and released to the public domain, as explained at + http://creativecommons.org/publicdomain/zero/1.0/ + + This header is for ANSI C/C++ only. You can set any of + the following #defines before including: + + * If USE_DL_PREFIX is defined, it is assumed that malloc.c + was also compiled with this option, so all routines + have names starting with "dl". + + * If HAVE_USR_INCLUDE_MALLOC_H is defined, it is assumed that this + file will be #included AFTER <malloc.h>. This is needed only if + your system defines a struct mallinfo that is incompatible with the + standard one declared here. Otherwise, you can include this file + INSTEAD of your system system <malloc.h>. At least on ANSI, all + declarations should be compatible with system versions + + * If MSPACES is defined, declarations for mspace versions are included. +*/ + +#ifndef MALLOC_280_H +#define MALLOC_280_H + +#ifdef __cplusplus +extern "C" { +#endif + +#include <stddef.h> /* for size_t */ + +#ifndef ONLY_MSPACES +#define ONLY_MSPACES 0 /* define to a value */ +#elif ONLY_MSPACES != 0 +#define ONLY_MSPACES 1 +#endif /* ONLY_MSPACES */ +#ifndef NO_MALLINFO +#define NO_MALLINFO 0 +#endif /* NO_MALLINFO */ + +#ifndef MSPACES +#if ONLY_MSPACES +#define MSPACES 1 +#else /* ONLY_MSPACES */ +#define MSPACES 0 +#endif /* ONLY_MSPACES */ +#endif /* MSPACES */ + +#if !ONLY_MSPACES + +#ifndef USE_DL_PREFIX +#define dlcalloc calloc +#define dlfree free +#define dlmalloc malloc +#define dlmemalign memalign +#define dlposix_memalign posix_memalign +#define dlrealloc realloc +#define dlvalloc valloc +#define dlpvalloc pvalloc +#define dlmallinfo mallinfo +#define dlmallopt mallopt +#define dlmalloc_trim malloc_trim +#define dlmalloc_stats malloc_stats +#define dlmalloc_usable_size malloc_usable_size +#define dlmalloc_footprint malloc_footprint +#define dlmalloc_max_footprint malloc_max_footprint +#define dlmalloc_footprint_limit malloc_footprint_limit +#define dlmalloc_set_footprint_limit malloc_set_footprint_limit +#define dlmalloc_inspect_all malloc_inspect_all +#define dlindependent_calloc independent_calloc +#define dlindependent_comalloc independent_comalloc +#define dlbulk_free bulk_free +#endif /* USE_DL_PREFIX */ + +#if !NO_MALLINFO +#ifndef HAVE_USR_INCLUDE_MALLOC_H +#ifndef _MALLOC_H +#ifndef MALLINFO_FIELD_TYPE +#define MALLINFO_FIELD_TYPE size_t +#endif /* MALLINFO_FIELD_TYPE */ +#ifndef STRUCT_MALLINFO_DECLARED +#define STRUCT_MALLINFO_DECLARED 1 +struct mallinfo { + MALLINFO_FIELD_TYPE arena; /* non-mmapped space allocated from system */ + MALLINFO_FIELD_TYPE ordblks; /* number of free chunks */ + MALLINFO_FIELD_TYPE smblks; /* always 0 */ + MALLINFO_FIELD_TYPE hblks; /* always 0 */ + MALLINFO_FIELD_TYPE hblkhd; /* space in mmapped regions */ + MALLINFO_FIELD_TYPE usmblks; /* maximum total allocated space */ + MALLINFO_FIELD_TYPE fsmblks; /* always 0 */ + MALLINFO_FIELD_TYPE uordblks; /* total allocated space */ + MALLINFO_FIELD_TYPE fordblks; /* total free space */ + MALLINFO_FIELD_TYPE keepcost; /* releasable (via malloc_trim) space */ +}; +#endif /* STRUCT_MALLINFO_DECLARED */ +#endif /* _MALLOC_H */ +#endif /* HAVE_USR_INCLUDE_MALLOC_H */ +#endif /* !NO_MALLINFO */ + +/* + malloc(size_t n) + Returns a pointer to a newly allocated chunk of at least n bytes, or + null if no space is available, in which case errno is set to ENOMEM + on ANSI C systems. + + If n is zero, malloc returns a minimum-sized chunk. (The minimum + size is 16 bytes on most 32bit systems, and 32 bytes on 64bit + systems.) Note that size_t is an unsigned type, so calls with + arguments that would be negative if signed are interpreted as + requests for huge amounts of space, which will often fail. The + maximum supported value of n differs across systems, but is in all + cases less than the maximum representable value of a size_t. +*/ +void* dlmalloc(size_t); + +/* + free(void* p) + Releases the chunk of memory pointed to by p, that had been previously + allocated using malloc or a related routine such as realloc. + It has no effect if p is null. If p was not malloced or already + freed, free(p) will by default cuase the current program to abort. +*/ +void dlfree(void*); + +/* + calloc(size_t n_elements, size_t element_size); + Returns a pointer to n_elements * element_size bytes, with all locations + set to zero. +*/ +void* dlcalloc(size_t, size_t); + +/* + realloc(void* p, size_t n) + Returns a pointer to a chunk of size n that contains the same data + as does chunk p up to the minimum of (n, p's size) bytes, or null + if no space is available. + + The returned pointer may or may not be the same as p. The algorithm + prefers extending p in most cases when possible, otherwise it + employs the equivalent of a malloc-copy-free sequence. + + If p is null, realloc is equivalent to malloc. + + If space is not available, realloc returns null, errno is set (if on + ANSI) and p is NOT freed. + + if n is for fewer bytes than already held by p, the newly unused + space is lopped off and freed if possible. realloc with a size + argument of zero (re)allocates a minimum-sized chunk. + + The old unix realloc convention of allowing the last-free'd chunk + to be used as an argument to realloc is not supported. +*/ +void* dlrealloc(void*, size_t); + +/* + realloc_in_place(void* p, size_t n) + Resizes the space allocated for p to size n, only if this can be + done without moving p (i.e., only if there is adjacent space + available if n is greater than p's current allocated size, or n is + less than or equal to p's size). This may be used instead of plain + realloc if an alternative allocation strategy is needed upon failure + to expand space; for example, reallocation of a buffer that must be + memory-aligned or cleared. You can use realloc_in_place to trigger + these alternatives only when needed. + + Returns p if successful; otherwise null. +*/ +void* dlrealloc_in_place(void*, size_t); + +/* + memalign(size_t alignment, size_t n); + Returns a pointer to a newly allocated chunk of n bytes, aligned + in accord with the alignment argument. + + The alignment argument should be a power of two. If the argument is + not a power of two, the nearest greater power is used. + 8-byte alignment is guaranteed by normal malloc calls, so don't + bother calling memalign with an argument of 8 or less. + + Overreliance on memalign is a sure way to fragment space. +*/ +void* dlmemalign(size_t, size_t); + +/* + int posix_memalign(void** pp, size_t alignment, size_t n); + Allocates a chunk of n bytes, aligned in accord with the alignment + argument. Differs from memalign only in that it (1) assigns the + allocated memory to *pp rather than returning it, (2) fails and + returns EINVAL if the alignment is not a power of two (3) fails and + returns ENOMEM if memory cannot be allocated. +*/ +int dlposix_memalign(void**, size_t, size_t); + +/* + valloc(size_t n); + Equivalent to memalign(pagesize, n), where pagesize is the page + size of the system. If the pagesize is unknown, 4096 is used. +*/ +void* dlvalloc(size_t); + +/* + mallopt(int parameter_number, int parameter_value) + Sets tunable parameters The format is to provide a + (parameter-number, parameter-value) pair. mallopt then sets the + corresponding parameter to the argument value if it can (i.e., so + long as the value is meaningful), and returns 1 if successful else + 0. SVID/XPG/ANSI defines four standard param numbers for mallopt, + normally defined in malloc.h. None of these are use in this malloc, + so setting them has no effect. But this malloc also supports other + options in mallopt: + + Symbol param # default allowed param values + M_TRIM_THRESHOLD -1 2*1024*1024 any (-1U disables trimming) + M_GRANULARITY -2 page size any power of 2 >= page size + M_MMAP_THRESHOLD -3 256*1024 any (or 0 if no MMAP support) +*/ +int dlmallopt(int, int); + +#define M_TRIM_THRESHOLD (-1) +#define M_GRANULARITY (-2) +#define M_MMAP_THRESHOLD (-3) + + +/* + malloc_footprint(); + Returns the number of bytes obtained from the system. The total + number of bytes allocated by malloc, realloc etc., is less than this + value. Unlike mallinfo, this function returns only a precomputed + result, so can be called frequently to monitor memory consumption. + Even if locks are otherwise defined, this function does not use them, + so results might not be up to date. +*/ +size_t dlmalloc_footprint(void); + +/* + malloc_max_footprint(); + Returns the maximum number of bytes obtained from the system. This + value will be greater than current footprint if deallocated space + has been reclaimed by the system. The peak number of bytes allocated + by malloc, realloc etc., is less than this value. Unlike mallinfo, + this function returns only a precomputed result, so can be called + frequently to monitor memory consumption. Even if locks are + otherwise defined, this function does not use them, so results might + not be up to date. +*/ +size_t dlmalloc_max_footprint(void); + +/* + malloc_footprint_limit(); + Returns the number of bytes that the heap is allowed to obtain from + the system, returning the last value returned by + malloc_set_footprint_limit, or the maximum size_t value if + never set. The returned value reflects a permission. There is no + guarantee that this number of bytes can actually be obtained from + the system. +*/ +size_t dlmalloc_footprint_limit(void); + +/* + malloc_set_footprint_limit(); + Sets the maximum number of bytes to obtain from the system, causing + failure returns from malloc and related functions upon attempts to + exceed this value. The argument value may be subject to page + rounding to an enforceable limit; this actual value is returned. + Using an argument of the maximum possible size_t effectively + disables checks. If the argument is less than or equal to the + current malloc_footprint, then all future allocations that require + additional system memory will fail. However, invocation cannot + retroactively deallocate existing used memory. +*/ +size_t dlmalloc_set_footprint_limit(size_t bytes); + +/* + malloc_inspect_all(void(*handler)(void *start, + void *end, + size_t used_bytes, + void* callback_arg), + void* arg); + Traverses the heap and calls the given handler for each managed + region, skipping all bytes that are (or may be) used for bookkeeping + purposes. Traversal does not include include chunks that have been + directly memory mapped. Each reported region begins at the start + address, and continues up to but not including the end address. The + first used_bytes of the region contain allocated data. If + used_bytes is zero, the region is unallocated. The handler is + invoked with the given callback argument. If locks are defined, they + are held during the entire traversal. It is a bad idea to invoke + other malloc functions from within the handler. + + For example, to count the number of in-use chunks with size greater + than 1000, you could write: + static int count = 0; + void count_chunks(void* start, void* end, size_t used, void* arg) { + if (used >= 1000) ++count; + } + then: + malloc_inspect_all(count_chunks, NULL); + + malloc_inspect_all is compiled only if MALLOC_INSPECT_ALL is defined. +*/ +void dlmalloc_inspect_all(void(*handler)(void*, void *, size_t, void*), + void* arg); + +#if !NO_MALLINFO +/* + mallinfo() + Returns (by copy) a struct containing various summary statistics: + + arena: current total non-mmapped bytes allocated from system + ordblks: the number of free chunks + smblks: always zero. + hblks: current number of mmapped regions + hblkhd: total bytes held in mmapped regions + usmblks: the maximum total allocated space. This will be greater + than current total if trimming has occurred. + fsmblks: always zero + uordblks: current total allocated space (normal or mmapped) + fordblks: total free space + keepcost: the maximum number of bytes that could ideally be released + back to system via malloc_trim. ("ideally" means that + it ignores page restrictions etc.) + + Because these fields are ints, but internal bookkeeping may + be kept as longs, the reported values may wrap around zero and + thus be inaccurate. +*/ + +struct mallinfo dlmallinfo(void); +#endif /* NO_MALLINFO */ + +/* + independent_calloc(size_t n_elements, size_t element_size, void* chunks[]); + + independent_calloc is similar to calloc, but instead of returning a + single cleared space, it returns an array of pointers to n_elements + independent elements that can hold contents of size elem_size, each + of which starts out cleared, and can be independently freed, + realloc'ed etc. The elements are guaranteed to be adjacently + allocated (this is not guaranteed to occur with multiple callocs or + mallocs), which may also improve cache locality in some + applications. + + The "chunks" argument is optional (i.e., may be null, which is + probably the most typical usage). If it is null, the returned array + is itself dynamically allocated and should also be freed when it is + no longer needed. Otherwise, the chunks array must be of at least + n_elements in length. It is filled in with the pointers to the + chunks. + + In either case, independent_calloc returns this pointer array, or + null if the allocation failed. If n_elements is zero and "chunks" + is null, it returns a chunk representing an array with zero elements + (which should be freed if not wanted). + + Each element must be freed when it is no longer needed. This can be + done all at once using bulk_free. + + independent_calloc simplifies and speeds up implementations of many + kinds of pools. It may also be useful when constructing large data + structures that initially have a fixed number of fixed-sized nodes, + but the number is not known at compile time, and some of the nodes + may later need to be freed. For example: + + struct Node { int item; struct Node* next; }; + + struct Node* build_list() { + struct Node** pool; + int n = read_number_of_nodes_needed(); + if (n <= 0) return 0; + pool = (struct Node**)(independent_calloc(n, sizeof(struct Node), 0); + if (pool == 0) die(); + // organize into a linked list... + struct Node* first = pool[0]; + for (i = 0; i < n-1; ++i) + pool[i]->next = pool[i+1]; + free(pool); // Can now free the array (or not, if it is needed later) + return first; + } +*/ +void** dlindependent_calloc(size_t, size_t, void**); + +/* + independent_comalloc(size_t n_elements, size_t sizes[], void* chunks[]); + + independent_comalloc allocates, all at once, a set of n_elements + chunks with sizes indicated in the "sizes" array. It returns + an array of pointers to these elements, each of which can be + independently freed, realloc'ed etc. The elements are guaranteed to + be adjacently allocated (this is not guaranteed to occur with + multiple callocs or mallocs), which may also improve cache locality + in some applications. + + The "chunks" argument is optional (i.e., may be null). If it is null + the returned array is itself dynamically allocated and should also + be freed when it is no longer needed. Otherwise, the chunks array + must be of at least n_elements in length. It is filled in with the + pointers to the chunks. + + In either case, independent_comalloc returns this pointer array, or + null if the allocation failed. If n_elements is zero and chunks is + null, it returns a chunk representing an array with zero elements + (which should be freed if not wanted). + + Each element must be freed when it is no longer needed. This can be + done all at once using bulk_free. + + independent_comallac differs from independent_calloc in that each + element may have a different size, and also that it does not + automatically clear elements. + + independent_comalloc can be used to speed up allocation in cases + where several structs or objects must always be allocated at the + same time. For example: + + struct Head { ... } + struct Foot { ... } + + void send_message(char* msg) { + int msglen = strlen(msg); + size_t sizes[3] = { sizeof(struct Head), msglen, sizeof(struct Foot) }; + void* chunks[3]; + if (independent_comalloc(3, sizes, chunks) == 0) + die(); + struct Head* head = (struct Head*)(chunks[0]); + char* body = (char*)(chunks[1]); + struct Foot* foot = (struct Foot*)(chunks[2]); + // ... + } + + In general though, independent_comalloc is worth using only for + larger values of n_elements. For small values, you probably won't + detect enough difference from series of malloc calls to bother. + + Overuse of independent_comalloc can increase overall memory usage, + since it cannot reuse existing noncontiguous small chunks that + might be available for some of the elements. +*/ +void** dlindependent_comalloc(size_t, size_t*, void**); + +/* + bulk_free(void* array[], size_t n_elements) + Frees and clears (sets to null) each non-null pointer in the given + array. This is likely to be faster than freeing them one-by-one. + If footers are used, pointers that have been allocated in different + mspaces are not freed or cleared, and the count of all such pointers + is returned. For large arrays of pointers with poor locality, it + may be worthwhile to sort this array before calling bulk_free. +*/ +size_t dlbulk_free(void**, size_t n_elements); + +/* + pvalloc(size_t n); + Equivalent to valloc(minimum-page-that-holds(n)), that is, + round up n to nearest pagesize. + */ +void* dlpvalloc(size_t); + +/* + malloc_trim(size_t pad); + + If possible, gives memory back to the system (via negative arguments + to sbrk) if there is unused memory at the `high' end of the malloc + pool or in unused MMAP segments. You can call this after freeing + large blocks of memory to potentially reduce the system-level memory + requirements of a program. However, it cannot guarantee to reduce + memory. Under some allocation patterns, some large free blocks of + memory will be locked between two used chunks, so they cannot be + given back to the system. + + The `pad' argument to malloc_trim represents the amount of free + trailing space to leave untrimmed. If this argument is zero, only + the minimum amount of memory to maintain internal data structures + will be left. Non-zero arguments can be supplied to maintain enough + trailing space to service future expected allocations without having + to re-obtain memory from the system. + + Malloc_trim returns 1 if it actually released any memory, else 0. +*/ +int dlmalloc_trim(size_t); + +/* + malloc_stats(); + Prints on stderr the amount of space obtained from the system (both + via sbrk and mmap), the maximum amount (which may be more than + current if malloc_trim and/or munmap got called), and the current + number of bytes allocated via malloc (or realloc, etc) but not yet + freed. Note that this is the number of bytes allocated, not the + number requested. It will be larger than the number requested + because of alignment and bookkeeping overhead. Because it includes + alignment wastage as being in use, this figure may be greater than + zero even when no user-level chunks are allocated. + + The reported current and maximum system memory can be inaccurate if + a program makes other calls to system memory allocation functions + (normally sbrk) outside of malloc. + + malloc_stats prints only the most commonly interesting statistics. + More information can be obtained by calling mallinfo. + + malloc_stats is not compiled if NO_MALLOC_STATS is defined. +*/ +void dlmalloc_stats(void); + +#endif /* !ONLY_MSPACES */ + +/* + malloc_usable_size(void* p); + + Returns the number of bytes you can actually use in + an allocated chunk, which may be more than you requested (although + often not) due to alignment and minimum size constraints. + You can use this many bytes without worrying about + overwriting other allocated objects. This is not a particularly great + programming practice. malloc_usable_size can be more useful in + debugging and assertions, for example: + + p = malloc(n); + assert(malloc_usable_size(p) >= 256); +*/ +size_t dlmalloc_usable_size(void*); + +#if MSPACES + +/* + mspace is an opaque type representing an independent + region of space that supports mspace_malloc, etc. +*/ +typedef void* mspace; + +/* + create_mspace creates and returns a new independent space with the + given initial capacity, or, if 0, the default granularity size. It + returns null if there is no system memory available to create the + space. If argument locked is non-zero, the space uses a separate + lock to control access. The capacity of the space will grow + dynamically as needed to service mspace_malloc requests. You can + control the sizes of incremental increases of this space by + compiling with a different DEFAULT_GRANULARITY or dynamically + setting with mallopt(M_GRANULARITY, value). +*/ +mspace create_mspace(size_t capacity, int locked); + +/* + destroy_mspace destroys the given space, and attempts to return all + of its memory back to the system, returning the total number of + bytes freed. After destruction, the results of access to all memory + used by the space become undefined. +*/ +size_t destroy_mspace(mspace msp); + +/* + create_mspace_with_base uses the memory supplied as the initial base + of a new mspace. Part (less than 128*sizeof(size_t) bytes) of this + space is used for bookkeeping, so the capacity must be at least this + large. (Otherwise 0 is returned.) When this initial space is + exhausted, additional memory will be obtained from the system. + Destroying this space will deallocate all additionally allocated + space (if possible) but not the initial base. +*/ +mspace create_mspace_with_base(void* base, size_t capacity, int locked); + +/* + mspace_track_large_chunks controls whether requests for large chunks + are allocated in their own untracked mmapped regions, separate from + others in this mspace. By default large chunks are not tracked, + which reduces fragmentation. However, such chunks are not + necessarily released to the system upon destroy_mspace. Enabling + tracking by setting to true may increase fragmentation, but avoids + leakage when relying on destroy_mspace to release all memory + allocated using this space. The function returns the previous + setting. +*/ +int mspace_track_large_chunks(mspace msp, int enable); + +#if !NO_MALLINFO +/* + mspace_mallinfo behaves as mallinfo, but reports properties of + the given space. +*/ +struct mallinfo mspace_mallinfo(mspace msp); +#endif /* NO_MALLINFO */ + +/* + An alias for mallopt. +*/ +int mspace_mallopt(int, int); + +/* + The following operate identically to their malloc counterparts + but operate only for the given mspace argument +*/ +void* mspace_malloc(mspace msp, size_t bytes); +void mspace_free(mspace msp, void* mem); +void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size); +void* mspace_realloc(mspace msp, void* mem, size_t newsize); +void* mspace_realloc_in_place(mspace msp, void* mem, size_t newsize); +void* mspace_memalign(mspace msp, size_t alignment, size_t bytes); +void** mspace_independent_calloc(mspace msp, size_t n_elements, + size_t elem_size, void* chunks[]); +void** mspace_independent_comalloc(mspace msp, size_t n_elements, + size_t sizes[], void* chunks[]); +size_t mspace_bulk_free(mspace msp, void**, size_t n_elements); +size_t mspace_usable_size(void* mem); +void mspace_malloc_stats(mspace msp); +int mspace_trim(mspace msp, size_t pad); +size_t mspace_footprint(mspace msp); +size_t mspace_max_footprint(mspace msp); +size_t mspace_footprint_limit(mspace msp); +size_t mspace_set_footprint_limit(mspace msp, size_t bytes); +void mspace_inspect_all(mspace msp, + void(*handler)(void *, void *, size_t, void*), + void* arg); +#endif /* MSPACES */ + +#ifdef __cplusplus +}; /* end of extern "C" */ +#endif + +#endif /* MALLOC_280_H */ diff --git a/src/heap.cc b/src/heap.cc index 7e44116d3c..858b9b2f94 100644 --- a/src/heap.cc +++ b/src/heap.cc @@ -21,11 +21,7 @@ namespace art { std::vector<Space*> Heap::spaces_; -Space* Heap::alloc_space_ = NULL; - -size_t Heap::maximum_size_ = 0; - -size_t Heap::growth_size_ = 0; +AllocSpace* Heap::alloc_space_ = NULL; size_t Heap::num_bytes_allocated_ = 0; @@ -56,71 +52,87 @@ Mutex* Heap::lock_ = NULL; bool Heap::verify_objects_ = false; -void Heap::Init(size_t initial_size, size_t maximum_size, size_t growth_size, +static void UpdateFirstAndLastSpace(Space** first_space, Space** last_space, Space* space) { + if (*first_space == NULL) { + *first_space = space; + *last_space = space; + } else { + if ((*first_space)->Begin() > space->Begin()) { + *first_space = space; + } else if (space->Begin() > (*last_space)->Begin()) { + *last_space = space; + } + } +} + +void Heap::Init(size_t initial_size, size_t growth_limit, size_t capacity, const std::vector<std::string>& image_file_names) { if (VLOG_IS_ON(heap) || VLOG_IS_ON(startup)) { LOG(INFO) << "Heap::Init entering"; } - // bounds of all spaces for allocating live and mark bitmaps - // there will be at least one space (the alloc space), - // so set base to max, and limit and min to start - byte* base = reinterpret_cast<byte*>(std::numeric_limits<uintptr_t>::max()); - byte* max = reinterpret_cast<byte*>(std::numeric_limits<uintptr_t>::min()); - byte* limit = reinterpret_cast<byte*>(std::numeric_limits<uintptr_t>::min()); + // Compute the bounds of all spaces for allocating live and mark bitmaps + // there will be at least one space (the alloc space) + Space* first_space = NULL; + Space* last_space = NULL; - byte* requested_base = NULL; + // Requested begin for the alloc space, to follow the mapped image and oat files + byte* requested_begin = NULL; std::vector<Space*> image_spaces; for (size_t i = 0; i < image_file_names.size(); i++) { - Space* space = Space::CreateFromImage(image_file_names[i]); + ImageSpace* space = Space::CreateImageSpace(image_file_names[i]); if (space == NULL) { LOG(FATAL) << "Failed to create space from " << image_file_names[i]; } image_spaces.push_back(space); - spaces_.push_back(space); - byte* oat_limit_addr = space->GetImageHeader().GetOatLimitAddr(); - if (oat_limit_addr > requested_base) { - requested_base = reinterpret_cast<byte*>(RoundUp(reinterpret_cast<uintptr_t>(oat_limit_addr), - kPageSize)); + AddSpace(space); + UpdateFirstAndLastSpace(&first_space, &last_space, space); + // Oat files referenced by image files immediately follow them in memory, ensure alloc space + // isn't going to get in the middle + byte* oat_end_addr = space->GetImageHeader().GetOatEnd(); + CHECK(oat_end_addr > space->End()); + if (oat_end_addr > requested_begin) { + requested_begin = reinterpret_cast<byte*>(RoundUp(reinterpret_cast<uintptr_t>(oat_end_addr), + kPageSize)); } - base = std::min(base, space->GetBase()); - max = std::max(max, space->GetMax()); - limit = std::max(limit, space->GetLimit()); } - alloc_space_ = Space::Create("alloc space", initial_size, maximum_size, growth_size, requested_base); + alloc_space_ = Space::CreateAllocSpace("alloc space", initial_size, growth_limit, capacity, + requested_begin); if (alloc_space_ == NULL) { LOG(FATAL) << "Failed to create alloc space"; } - base = std::min(base, alloc_space_->GetBase()); - max = std::max(max, alloc_space_->GetMax()); - limit = std::max(limit, alloc_space_->GetLimit()); - DCHECK_LT(base, max); - DCHECK_LT(base, limit); - size_t num_bytes = max - base; - size_t limit_bytes = limit - base; + AddSpace(alloc_space_); + UpdateFirstAndLastSpace(&first_space, &last_space, alloc_space_); + byte* heap_begin = first_space->Begin(); + size_t heap_capacity = (last_space->Begin() - first_space->Begin()) + last_space->UnimpededCapacity(); // Allocate the initial live bitmap. - UniquePtr<HeapBitmap> live_bitmap(HeapBitmap::Create("dalvik-bitmap-1", base, num_bytes)); + UniquePtr<HeapBitmap> live_bitmap(HeapBitmap::Create("dalvik-bitmap-1", heap_begin, heap_capacity)); if (live_bitmap.get() == NULL) { LOG(FATAL) << "Failed to create live bitmap"; } + // Mark image objects in the live bitmap + for (size_t i = 0; i < spaces_.size(); i++) { + Space* space = spaces_[i]; + if (space->IsImageSpace()) { + space->AsImageSpace()->RecordImageAllocations(live_bitmap.get()); + } + } + // Allocate the initial mark bitmap. - UniquePtr<HeapBitmap> mark_bitmap(HeapBitmap::Create("dalvik-bitmap-2", base, num_bytes)); + UniquePtr<HeapBitmap> mark_bitmap(HeapBitmap::Create("dalvik-bitmap-2", heap_begin, heap_capacity)); if (mark_bitmap.get() == NULL) { LOG(FATAL) << "Failed to create mark bitmap"; } // Allocate the card table. - UniquePtr<CardTable> card_table(CardTable::Create(base, num_bytes, limit_bytes)); + UniquePtr<CardTable> card_table(CardTable::Create(heap_begin, heap_capacity)); if (card_table.get() == NULL) { LOG(FATAL) << "Failed to create card table"; } - spaces_.push_back(alloc_space_); - maximum_size_ = maximum_size; - growth_size_ = growth_size; live_bitmap_ = live_bitmap.release(); mark_bitmap_ = mark_bitmap.release(); card_table_ = card_table.release(); @@ -128,18 +140,13 @@ void Heap::Init(size_t initial_size, size_t maximum_size, size_t growth_size, num_bytes_allocated_ = 0; num_objects_allocated_ = 0; - // Make image objects live (after live_bitmap_ is set) - for (size_t i = 0; i < image_spaces.size(); i++) { - RecordImageAllocations(image_spaces[i]); - } - - Heap::EnableObjectValidation(); - // It's still to early to take a lock because there are no threads yet, // but we can create the heap lock now. We don't create it earlier to // make it clear that you can't use locks during heap initialization. lock_ = new Mutex("Heap lock"); + Heap::EnableObjectValidation(); + if (VLOG_IS_ON(heap) || VLOG_IS_ON(startup)) { LOG(INFO) << "Heap::Init exiting"; } @@ -184,8 +191,12 @@ bool Heap::IsHeapAddress(const Object* obj) { if (obj == NULL || !IsAligned<kObjectAlignment>(obj)) { return false; } - // TODO - return true; + for (size_t i = 0; i < spaces_.size(); i++) { + if (spaces_[i]->Contains(obj)) { + return true; + } + } + return false; } bool Heap::IsLiveObjectLocked(const Object* obj) { @@ -209,8 +220,6 @@ void Heap::VerifyObjectLocked(const Object* obj) { if (!IsAligned<kObjectAlignment>(obj)) { LOG(FATAL) << "Object isn't aligned: " << obj; } else if (!live_bitmap_->Test(obj)) { - // TODO: we don't hold a lock here as it is assumed the live bit map - // isn't changing if the mutator is running. LOG(FATAL) << "Object is dead: " << obj; } // Ignore early dawn of the universe verifications @@ -228,11 +237,9 @@ void Heap::VerifyObjectLocked(const Object* obj) { // Check obj.getClass().getClass() == obj.getClass().getClass().getClass() // Note: we don't use the accessors here as they have internal sanity checks // that we don't want to run - raw_addr = reinterpret_cast<const byte*>(c) + - Object::ClassOffset().Int32Value(); + raw_addr = reinterpret_cast<const byte*>(c) + Object::ClassOffset().Int32Value(); const Class* c_c = *reinterpret_cast<Class* const *>(raw_addr); - raw_addr = reinterpret_cast<const byte*>(c_c) + - Object::ClassOffset().Int32Value(); + raw_addr = reinterpret_cast<const byte*>(c_c) + Object::ClassOffset().Int32Value(); const Class* c_c_c = *reinterpret_cast<Class* const *>(raw_addr); CHECK_EQ(c_c, c_c_c); } @@ -249,7 +256,7 @@ void Heap::VerifyHeap() { live_bitmap_->Walk(Heap::VerificationCallback, NULL); } -void Heap::RecordAllocationLocked(Space* space, const Object* obj) { +void Heap::RecordAllocationLocked(AllocSpace* space, const Object* obj) { #ifndef NDEBUG if (Runtime::Current()->IsStarted()) { lock_->AssertHeld(); @@ -296,29 +303,10 @@ void Heap::RecordFreeLocked(size_t freed_objects, size_t freed_bytes) { } } -void Heap::RecordImageAllocations(Space* space) { - if (VLOG_IS_ON(heap) || VLOG_IS_ON(startup)) { - LOG(INFO) << "Heap::RecordImageAllocations entering"; - } - DCHECK(!Runtime::Current()->IsStarted()); - CHECK(space != NULL); - CHECK(live_bitmap_ != NULL); - byte* current = space->GetBase() + RoundUp(sizeof(ImageHeader), kObjectAlignment); - while (current < space->GetLimit()) { - DCHECK_ALIGNED(current, kObjectAlignment); - const Object* obj = reinterpret_cast<const Object*>(current); - live_bitmap_->Set(obj); - current += RoundUp(obj->SizeOf(), kObjectAlignment); - } - if (VLOG_IS_ON(heap) || VLOG_IS_ON(startup)) { - LOG(INFO) << "Heap::RecordImageAllocations exiting"; - } -} - Object* Heap::AllocateLocked(size_t size) { lock_->AssertHeld(); DCHECK(alloc_space_ != NULL); - Space* space = alloc_space_; + AllocSpace* space = alloc_space_; Object* obj = AllocateLocked(space, size); if (obj != NULL) { RecordAllocationLocked(space, obj); @@ -326,30 +314,31 @@ Object* Heap::AllocateLocked(size_t size) { return obj; } -Object* Heap::AllocateLocked(Space* space, size_t size) { +Object* Heap::AllocateLocked(AllocSpace* space, size_t alloc_size) { lock_->AssertHeld(); // Since allocation can cause a GC which will need to SuspendAll, // make sure all allocators are in the kRunnable state. DCHECK_EQ(Thread::Current()->GetState(), Thread::kRunnable); - // Fail impossible allocations. TODO: collect soft references. - if (size > growth_size_) { + // Fail impossible allocations + if (alloc_size > space->Capacity()) { + // On failure collect soft references + CollectGarbageInternal(true); return NULL; } - Object* ptr = space->AllocWithoutGrowth(size); + Object* ptr = space->AllocWithoutGrowth(alloc_size); if (ptr != NULL) { return ptr; } - // The allocation failed. If the GC is running, block until it - // completes and retry. + // The allocation failed. If the GC is running, block until it completes and retry. if (is_gc_running_) { - // The GC is concurrently tracing the heap. Release the heap - // lock, wait for the GC to complete, and retrying allocating. + // The GC is concurrently tracing the heap. Release the heap lock, wait for the GC to + // complete, and retrying allocating. WaitForConcurrentGcToComplete(); - ptr = space->AllocWithoutGrowth(size); + ptr = space->AllocWithoutGrowth(alloc_size); if (ptr != NULL) { return ptr; } @@ -362,23 +351,23 @@ Object* Heap::AllocateLocked(Space* space, size_t size) { ++Runtime::Current()->GetStats()->gc_for_alloc_count; ++Thread::Current()->GetStats()->gc_for_alloc_count; } - CollectGarbageInternal(); - ptr = space->AllocWithoutGrowth(size); + CollectGarbageInternal(false); + ptr = space->AllocWithoutGrowth(alloc_size); if (ptr != NULL) { return ptr; } // Even that didn't work; this is an exceptional state. // Try harder, growing the heap if necessary. - ptr = space->AllocWithGrowth(size); + ptr = space->AllocWithGrowth(alloc_size); if (ptr != NULL) { //size_t new_footprint = dvmHeapSourceGetIdealFootprint(); - size_t new_footprint = space->GetMaxAllowedFootprint(); + size_t new_footprint = space->GetFootprintLimit(); // OLD-TODO: may want to grow a little bit more so that the amount of // free space is equal to the old free space + the // utilization slop for the new allocation. VLOG(gc) << "Grow heap (frag case) to " << (new_footprint/KB) << "KiB " - << "for a " << size << "-byte allocation"; + << "for a " << alloc_size << "-byte allocation"; return ptr; } @@ -389,14 +378,14 @@ Object* Heap::AllocateLocked(Space* space, size_t size) { // cleared before throwing an OOME. // OLD-TODO: wait for the finalizers from the previous GC to finish - VLOG(gc) << "Forcing collection of SoftReferences for " << size << "-byte allocation"; - CollectGarbageInternal(); - ptr = space->AllocWithGrowth(size); + VLOG(gc) << "Forcing collection of SoftReferences for " << alloc_size << "-byte allocation"; + CollectGarbageInternal(true); + ptr = space->AllocWithGrowth(alloc_size); if (ptr != NULL) { return ptr; } - LOG(ERROR) << "Out of memory on a " << size << "-byte allocation"; + LOG(ERROR) << "Out of memory on a " << alloc_size << "-byte allocation"; // TODO: tell the HeapSource to dump its state // TODO: dump stack traces for all threads @@ -405,15 +394,15 @@ Object* Heap::AllocateLocked(Space* space, size_t size) { } int64_t Heap::GetMaxMemory() { - return growth_size_; + return alloc_space_->Capacity(); } int64_t Heap::GetTotalMemory() { - return alloc_space_->Size(); + return alloc_space_->Capacity(); } int64_t Heap::GetFreeMemory() { - return alloc_space_->Size() - num_bytes_allocated_; + return alloc_space_->Capacity() - num_bytes_allocated_; } class InstanceCounter { @@ -456,12 +445,12 @@ int64_t Heap::CountInstances(Class* c, bool count_assignable) { return counter.GetCount(); } -void Heap::CollectGarbage() { +void Heap::CollectGarbage(bool clear_soft_references) { ScopedHeapLock lock; - CollectGarbageInternal(); + CollectGarbageInternal(clear_soft_references); } -void Heap::CollectGarbageInternal() { +void Heap::CollectGarbageInternal(bool clear_soft_references) { lock_->AssertHeld(); ThreadList* thread_list = Runtime::Current()->GetThreadList(); @@ -501,7 +490,7 @@ void Heap::CollectGarbageInternal() { // re-mark root set // scan dirty objects - mark_sweep.ProcessReferences(false); + mark_sweep.ProcessReferences(clear_soft_references); timings.AddSplit("ProcessReferences"); // TODO: if concurrent @@ -546,13 +535,6 @@ void Heap::WaitForConcurrentGcToComplete() { lock_->AssertHeld(); } -void Heap::WalkHeap(void(*callback)(const void*, size_t, const void*, size_t, void*), void* arg) { - typedef std::vector<Space*>::iterator It; // C++0x auto. - for (It it = spaces_.begin(); it != spaces_.end(); ++it) { - (*it)->Walk(callback, arg); - } -} - /* Terminology: * 1. Footprint: Capacity we allocate from system. * 2. Active space: a.k.a. alloc_space_. @@ -575,13 +557,14 @@ void Heap::WalkHeap(void(*callback)(const void*, size_t, const void*, size_t, vo // Old spaces will count against the ideal size. // void Heap::SetIdealFootprint(size_t max_allowed_footprint) { - if (max_allowed_footprint > Heap::growth_size_) { + size_t alloc_space_capacity = alloc_space_->Capacity(); + if (max_allowed_footprint > alloc_space_capacity) { VLOG(gc) << "Clamp target GC heap from " << (max_allowed_footprint/KB) << "KiB" - << " to " << (Heap::growth_size_/KB) << "KiB"; - max_allowed_footprint = Heap::growth_size_; + << " to " << (alloc_space_capacity/KB) << "KiB"; + max_allowed_footprint = alloc_space_capacity; } - alloc_space_->SetMaxAllowedFootprint(max_allowed_footprint); + alloc_space_->SetFootprintLimit(max_allowed_footprint); } // kHeapIdealFree is the ideal maximum free size, when we grow the heap for @@ -615,10 +598,7 @@ void Heap::GrowForUtilization() { void Heap::ClearGrowthLimit() { ScopedHeapLock lock; WaitForConcurrentGcToComplete(); - CHECK_GE(maximum_size_, growth_size_); - growth_size_ = maximum_size_; alloc_space_->ClearGrowthLimit(); - card_table_->ClearGrowthLimit(); } pid_t Heap::GetLockOwner() { diff --git a/src/heap.h b/src/heap.h index 2e9aa35241..678f8769e1 100644 --- a/src/heap.h +++ b/src/heap.h @@ -21,6 +21,7 @@ #include "card_table.h" #include "globals.h" +#include "gtest/gtest.h" #include "heap_bitmap.h" #include "mutex.h" #include "offsets.h" @@ -29,17 +30,19 @@ namespace art { +class AllocSpace; class Class; class Object; class Space; class Thread; class HeapBitmap; +class SpaceTest; class Heap { public: - static const size_t kInitialSize = 4 * MB; + static const size_t kInitialSize = 2 * MB; - static const size_t kMaximumSize = 16 * MB; + static const size_t kMaximumSize = 32 * MB; typedef void (RootVisitor)(const Object* root, void* arg); typedef bool (IsMarkedTester)(const Object* object, void* arg); @@ -47,7 +50,7 @@ class Heap { // Create a heap with the requested sizes. The possible empty // image_file_names names specify Spaces to load based on // ImageWriter output. - static void Init(size_t starting_size, size_t maximum_size, size_t growth_size, + static void Init(size_t starting_size, size_t growth_limit, size_t capacity, const std::vector<std::string>& image_file_names); static void Destroy(); @@ -74,7 +77,7 @@ class Heap { static bool IsLiveObjectLocked(const Object* obj); // Initiates an explicit garbage collection. - static void CollectGarbage(); + static void CollectGarbage(bool clear_soft_references); // Implements java.lang.Runtime.maxMemory. static int64_t GetMaxMemory(); @@ -89,12 +92,16 @@ class Heap { // Implements dalvik.system.VMRuntime.clearGrowthLimit. static void ClearGrowthLimit(); - // Implements dalvik.system.VMRuntime.getTargetHeapUtilization. + // Target ideal heap utilization ratio, implements + // dalvik.system.VMRuntime.getTargetHeapUtilization. static float GetTargetHeapUtilization() { return target_utilization_; } - // Implements dalvik.system.VMRuntime.setTargetHeapUtilization. + // Set target ideal heap utilization ratio, implements + // dalvik.system.VMRuntime.setTargetHeapUtilization. static void SetTargetHeapUtilization(float target) { + DCHECK_GT(target, 0.0f); // asserted in Java code + DCHECK_LT(target, 1.0f); target_utilization_ = target; } // Sets the maximum number of bytes that the heap is allowed to allocate @@ -155,6 +162,9 @@ class Heap { } static void EnableObjectValidation() { +#if VERIFY_OBJECT_ENABLED + Heap::VerifyHeap(); +#endif verify_objects_ = true; } @@ -189,33 +199,34 @@ class Heap { card_marking_disabled_ = true; } - // dlmalloc_walk_heap-compatible heap walker. - static void WalkHeap(void(*callback)(const void*, size_t, const void*, size_t, void*), void* arg); - static void AddFinalizerReference(Thread* self, Object* object); static size_t GetBytesAllocated() { return num_bytes_allocated_; } static size_t GetObjectsAllocated() { return num_objects_allocated_; } - static Space* GetAllocSpace() { + static AllocSpace* GetAllocSpace() { return alloc_space_; } private: // Allocates uninitialized storage. static Object* AllocateLocked(size_t num_bytes); - static Object* AllocateLocked(Space* space, size_t num_bytes); + static Object* AllocateLocked(AllocSpace* space, size_t num_bytes); // Pushes a list of cleared references out to the managed heap. static void EnqueueClearedReferences(Object** cleared_references); - static void RecordAllocationLocked(Space* space, const Object* object); + static void RecordAllocationLocked(AllocSpace* space, const Object* object); static void RecordImageAllocations(Space* space); - static void CollectGarbageInternal(); + static void CollectGarbageInternal(bool clear_soft_references); static void GrowForUtilization(); + static void AddSpace(Space* space) { + spaces_.push_back(space); + } + static void VerifyObjectLocked(const Object *obj); static void VerificationCallback(Object* obj, void* arg); @@ -225,7 +236,7 @@ class Heap { static std::vector<Space*> spaces_; // default Space for allocations - static Space* alloc_space_; + static AllocSpace* alloc_space_; static HeapBitmap* mark_bitmap_; @@ -237,16 +248,6 @@ class Heap { // TODO: remove static bool card_marking_disabled_; - // The maximum size of the heap in bytes. - static size_t maximum_size_; - - // The largest size the heap may grow. This value allows the app to limit the - // growth below the maximum size. This is a work around until we can - // dynamically set the maximum size. This value can range between the starting - // size and the maximum size but should never be set below the current - // footprint of the heap. - static size_t growth_size_; - // True while the garbage collector is running. static bool is_gc_running_; @@ -281,6 +282,8 @@ class Heap { static bool verify_objects_; + FRIEND_TEST(SpaceTest, AllocAndFree); + DISALLOW_IMPLICIT_CONSTRUCTORS(Heap); }; diff --git a/src/heap_bitmap.cc b/src/heap_bitmap.cc index 2adeedcb02..57c60ba9f6 100644 --- a/src/heap_bitmap.cc +++ b/src/heap_bitmap.cc @@ -22,30 +22,16 @@ namespace art { -HeapBitmap* HeapBitmap::Create(const char* name, byte* base, size_t length) { - UniquePtr<HeapBitmap> bitmap(new HeapBitmap(base, length)); - if (!bitmap->Init(name, base, length)) { +HeapBitmap* HeapBitmap::Create(const char* name, byte* heap_begin, size_t heap_capacity) { + CHECK(heap_begin != NULL); + size_t bitmap_size = HB_OFFSET_TO_INDEX(heap_capacity) * kWordSize; + UniquePtr<MemMap> mem_map(MemMap::MapAnonymous(name, NULL, bitmap_size, PROT_READ | PROT_WRITE)); + if (mem_map.get() == NULL) { + LOG(ERROR) << "Failed to allocate bitmap " << name; return NULL; - } else { - return bitmap.release(); - } -} - -// Initialize a HeapBitmap so that it points to a bitmap large enough -// to cover a heap at <base> of <max_size> bytes, where objects are -// guaranteed to be kAlignment-aligned. -bool HeapBitmap::Init(const char* name, const byte* base, size_t max_size) { - CHECK(base != NULL); - size_t length = HB_OFFSET_TO_INDEX(max_size) * kWordSize; - mem_map_.reset(MemMap::MapAnonymous(name, NULL, length, PROT_READ | PROT_WRITE)); - if (mem_map_.get() == NULL) { - return false; } - words_ = reinterpret_cast<word*>(mem_map_->GetAddress()); - num_bytes_ = length; - base_ = reinterpret_cast<uintptr_t>(base); - max_ = base_ - 1; - return true; + word* bitmap_begin = reinterpret_cast<word*>(mem_map->Begin()); + return new HeapBitmap(name, mem_map.release(), bitmap_begin, bitmap_size, heap_begin); } // Clean up any resources associated with the bitmap. @@ -54,37 +40,36 @@ HeapBitmap::~HeapBitmap() {} // Fill the bitmap with zeroes. Returns the bitmap's memory to the // system as a side-effect. void HeapBitmap::Clear() { - if (words_ != NULL) { + if (bitmap_begin_ != NULL) { // This returns the memory to the system. Successive page faults // will return zeroed memory. - int result = madvise(words_, num_bytes_, MADV_DONTNEED); + int result = madvise(bitmap_begin_, bitmap_size_, MADV_DONTNEED); if (result == -1) { PLOG(WARNING) << "madvise failed"; } - max_ = base_ - 1; + heap_end_ = heap_begin_ - 1; } } -// Return true iff <obj> is within the range of pointers that this -// bitmap could potentially cover, even if a bit has not been set for -// it. +// Return true iff <obj> is within the range of pointers that this bitmap could potentially cover, +// even if a bit has not been set for it. bool HeapBitmap::HasAddress(const void* obj) const { if (obj != NULL) { - const uintptr_t offset = (uintptr_t)obj - base_; + const uintptr_t offset = (uintptr_t)obj - heap_begin_; const size_t index = HB_OFFSET_TO_INDEX(offset); - return index < num_bytes_ / kWordSize; + return index < bitmap_size_ / kWordSize; } return false; } -void HeapBitmap::VisitRange(uintptr_t base, uintptr_t max, Callback* visitor, void* arg) const { - size_t start = HB_OFFSET_TO_INDEX(base - base_); - size_t end = HB_OFFSET_TO_INDEX(max - base_ - 1); +void HeapBitmap::VisitRange(uintptr_t visit_begin, uintptr_t visit_end, Callback* visitor, void* arg) const { + size_t start = HB_OFFSET_TO_INDEX(visit_begin - heap_begin_); + size_t end = HB_OFFSET_TO_INDEX(visit_end - heap_begin_ - 1); for (size_t i = start; i <= end; i++) { - word w = words_[i]; + word w = bitmap_begin_[i]; if (w != 0) { word high_bit = 1 << (kBitsPerWord - 1); - uintptr_t ptr_base = HB_INDEX_TO_OFFSET(i) + base_; + uintptr_t ptr_base = HB_INDEX_TO_OFFSET(i) + heap_begin_; while (w != 0) { const int shift = CLZ(w); Object* obj = reinterpret_cast<Object*>(ptr_base + shift * kAlignment); @@ -98,14 +83,14 @@ void HeapBitmap::VisitRange(uintptr_t base, uintptr_t max, Callback* visitor, vo // Visits set bits in address order. The callback is not permitted to // change the bitmap bits or max during the traversal. void HeapBitmap::Walk(HeapBitmap::Callback* callback, void* arg) { - CHECK(words_ != NULL); + CHECK(bitmap_begin_ != NULL); CHECK(callback != NULL); - uintptr_t end = HB_OFFSET_TO_INDEX(max_ - base_); + uintptr_t end = HB_OFFSET_TO_INDEX(heap_end_ - heap_begin_); for (uintptr_t i = 0; i <= end; ++i) { - word w = words_[i]; + word w = bitmap_begin_[i]; if (UNLIKELY(w != 0)) { word high_bit = 1 << (kBitsPerWord - 1); - uintptr_t ptr_base = HB_INDEX_TO_OFFSET(i) + base_; + uintptr_t ptr_base = HB_INDEX_TO_OFFSET(i) + heap_begin_; while (w != 0) { const int shift = CLZ(w); Object* obj = reinterpret_cast<Object*>(ptr_base + shift * kAlignment); @@ -116,32 +101,30 @@ void HeapBitmap::Walk(HeapBitmap::Callback* callback, void* arg) { } } -// Similar to Walk but the callback routine is permitted to change the -// bitmap bits and max during traversal. Used by the the root marking -// scan exclusively. +// Similar to Walk but the callback routine is permitted to change the bitmap bits and end during +// traversal. Used by the the root marking scan exclusively. // -// The callback is invoked with a finger argument. The finger is a -// pointer to an address not yet visited by the traversal. If the -// callback sets a bit for an address at or above the finger, this -// address will be visited by the traversal. If the callback sets a -// bit for an address below the finger, this address will not be -// visited. -void HeapBitmap::ScanWalk(uintptr_t base, uintptr_t max, ScanCallback* callback, void* arg) { - CHECK(words_ != NULL); +// The callback is invoked with a finger argument. The finger is a pointer to an address not yet +// visited by the traversal. If the callback sets a bit for an address at or above the finger, this +// address will be visited by the traversal. If the callback sets a bit for an address below the +// finger, this address will not be visited (typiscally such an address would be placed on the +// marking stack). +void HeapBitmap::ScanWalk(uintptr_t scan_begin, uintptr_t scan_end, ScanCallback* callback, void* arg) { + CHECK(bitmap_begin_ != NULL); CHECK(callback != NULL); - CHECK_LE(base, max); - CHECK_GE(base, base_); - size_t start = HB_OFFSET_TO_INDEX(base - base_); - if (max < max_) { + CHECK_LE(scan_begin, scan_end); + CHECK_GE(scan_begin, heap_begin_); + size_t start = HB_OFFSET_TO_INDEX(scan_begin - heap_begin_); + if (scan_end < heap_end_) { // The end of the space we're looking at is before the current maximum bitmap PC, scan to that // and don't recompute end on each iteration - size_t end = HB_OFFSET_TO_INDEX(max - base_ - 1); + size_t end = HB_OFFSET_TO_INDEX(scan_end - heap_begin_ - 1); for (size_t i = start; i <= end; i++) { - word w = words_[i]; + word w = bitmap_begin_[i]; if (UNLIKELY(w != 0)) { word high_bit = 1 << (kBitsPerWord - 1); - uintptr_t ptr_base = HB_INDEX_TO_OFFSET(i) + base_; - void* finger = reinterpret_cast<void*>(HB_INDEX_TO_OFFSET(i + 1) + base_); + uintptr_t ptr_base = HB_INDEX_TO_OFFSET(i) + heap_begin_; + void* finger = reinterpret_cast<void*>(HB_INDEX_TO_OFFSET(i + 1) + heap_begin_); while (w != 0) { const int shift = CLZ(w); Object* obj = reinterpret_cast<Object*>(ptr_base + shift * kAlignment); @@ -151,13 +134,13 @@ void HeapBitmap::ScanWalk(uintptr_t base, uintptr_t max, ScanCallback* callback, } } } else { - size_t end = HB_OFFSET_TO_INDEX(max_ - base_); + size_t end = HB_OFFSET_TO_INDEX(heap_end_ - heap_begin_); for (size_t i = start; i <= end; i++) { - word w = words_[i]; + word w = bitmap_begin_[i]; if (UNLIKELY(w != 0)) { word high_bit = 1 << (kBitsPerWord - 1); - uintptr_t ptr_base = HB_INDEX_TO_OFFSET(i) + base_; - void* finger = reinterpret_cast<void*>(HB_INDEX_TO_OFFSET(i + 1) + base_); + uintptr_t ptr_base = HB_INDEX_TO_OFFSET(i) + heap_begin_; + void* finger = reinterpret_cast<void*>(HB_INDEX_TO_OFFSET(i + 1) + heap_begin_); while (w != 0) { const int shift = CLZ(w); Object* obj = reinterpret_cast<Object*>(ptr_base + shift * kAlignment); @@ -165,7 +148,8 @@ void HeapBitmap::ScanWalk(uintptr_t base, uintptr_t max, ScanCallback* callback, w &= ~(high_bit >> shift); } } - end = HB_OFFSET_TO_INDEX(max_ - base_); + // update 'end' in case callback modified bitmap + end = HB_OFFSET_TO_INDEX(heap_end_ - heap_begin_); } } } @@ -177,37 +161,37 @@ void HeapBitmap::ScanWalk(uintptr_t base, uintptr_t max, ScanCallback* callback, // The callback is not permitted to increase the max of either bitmap. void HeapBitmap::SweepWalk(const HeapBitmap& live_bitmap, const HeapBitmap& mark_bitmap, - uintptr_t base, uintptr_t max, + uintptr_t sweep_begin, uintptr_t sweep_end, HeapBitmap::SweepCallback* callback, void* arg) { - CHECK(live_bitmap.words_ != NULL); - CHECK(mark_bitmap.words_ != NULL); - CHECK_EQ(live_bitmap.base_, mark_bitmap.base_); - CHECK_EQ(live_bitmap.num_bytes_, mark_bitmap.num_bytes_); + CHECK(live_bitmap.bitmap_begin_ != NULL); + CHECK(mark_bitmap.bitmap_begin_ != NULL); + CHECK_EQ(live_bitmap.heap_begin_, mark_bitmap.heap_begin_); + CHECK_EQ(live_bitmap.bitmap_size_, mark_bitmap.bitmap_size_); CHECK(callback != NULL); - CHECK_LE(base, max); - CHECK_GE(base, live_bitmap.base_); - max = std::min(max - 1, live_bitmap.max_); - if (live_bitmap.max_ < live_bitmap.base_) { + CHECK_LE(sweep_begin, sweep_end); + CHECK_GE(sweep_begin, live_bitmap.heap_begin_); + sweep_end = std::min(sweep_end - 1, live_bitmap.heap_end_); + if (live_bitmap.heap_end_ < live_bitmap.heap_begin_) { // Easy case; both are obviously empty. // TODO: this should never happen return; } - // TODO: rewrite the callbacks to accept a std::vector<void*> rather than a void**? - std::vector<void*> pointer_buf(4 * kBitsPerWord); - void** pb = &pointer_buf[0]; - size_t start = HB_OFFSET_TO_INDEX(base - live_bitmap.base_); - size_t end = HB_OFFSET_TO_INDEX(max - live_bitmap.base_); - word* live = live_bitmap.words_; - word* mark = mark_bitmap.words_; + // TODO: rewrite the callbacks to accept a std::vector<Object*> rather than a Object**? + std::vector<Object*> pointer_buf(4 * kBitsPerWord); + Object** pb = &pointer_buf[0]; + size_t start = HB_OFFSET_TO_INDEX(sweep_begin - live_bitmap.heap_begin_); + size_t end = HB_OFFSET_TO_INDEX(sweep_end - live_bitmap.heap_begin_); + word* live = live_bitmap.bitmap_begin_; + word* mark = mark_bitmap.bitmap_begin_; for (size_t i = start; i <= end; i++) { word garbage = live[i] & ~mark[i]; if (UNLIKELY(garbage != 0)) { word high_bit = 1 << (kBitsPerWord - 1); - uintptr_t ptr_base = HB_INDEX_TO_OFFSET(i) + live_bitmap.base_; + uintptr_t ptr_base = HB_INDEX_TO_OFFSET(i) + live_bitmap.heap_begin_; while (garbage != 0) { int shift = CLZ(garbage); garbage &= ~(high_bit >> shift); - *pb++ = reinterpret_cast<void*>(ptr_base + shift * kAlignment); + *pb++ = reinterpret_cast<Object*>(ptr_base + shift * kAlignment); } // Make sure that there are always enough slots available for an // entire word of one bits. diff --git a/src/heap_bitmap.h b/src/heap_bitmap.h index 31adebc70a..0d6de60917 100644 --- a/src/heap_bitmap.h +++ b/src/heap_bitmap.h @@ -51,9 +51,11 @@ class HeapBitmap { typedef void ScanCallback(Object* obj, void* finger, void* arg); - typedef void SweepCallback(size_t numPtrs, void** ptrs, void* arg); + typedef void SweepCallback(size_t numPtrs, Object** ptrs, void* arg); - static HeapBitmap* Create(const char* name, byte* base, size_t length); + // Initialize a HeapBitmap so that it points to a bitmap large enough to cover a heap at + // heap_begin of heap_capacity bytes, where objects are guaranteed to be kAlignment-aligned. + static HeapBitmap* Create(const char* name, byte* heap_begin, size_t heap_capacity); ~HeapBitmap(); @@ -70,11 +72,11 @@ class HeapBitmap { inline bool Test(const Object* obj) { uintptr_t addr = reinterpret_cast<uintptr_t>(obj); DCHECK(HasAddress(obj)) << obj; - DCHECK(words_ != NULL); - DCHECK_GE(addr, base_); - if (addr <= max_) { - const uintptr_t offset = addr - base_; - return (words_[HB_OFFSET_TO_INDEX(offset)] & HB_OFFSET_TO_MASK(offset)) != 0; + DCHECK(bitmap_begin_ != NULL); + DCHECK_GE(addr, heap_begin_); + if (addr <= heap_end_) { + const uintptr_t offset = addr - heap_begin_; + return (bitmap_begin_[HB_OFFSET_TO_INDEX(offset)] & HB_OFFSET_TO_MASK(offset)) != 0; } else { return false; } @@ -94,47 +96,50 @@ class HeapBitmap { SweepCallback* thunk, void* arg); private: - HeapBitmap(const void* base, size_t length) - : words_(NULL), - num_bytes_(length), - base_(reinterpret_cast<uintptr_t>(base)) { - }; + // TODO: heap_end_ is initialized so that the heap bitmap is empty, this doesn't require the -1, + // however, we document that this is expected on heap_end_ + HeapBitmap(const char* name, MemMap* mem_map, word* bitmap_begin, size_t bitmap_size, const void* heap_begin) + : mem_map_(mem_map), bitmap_begin_(bitmap_begin), bitmap_size_(bitmap_size), + heap_begin_(reinterpret_cast<uintptr_t>(heap_begin)), heap_end_(heap_begin_ - 1), + name_(name) {} inline void Modify(const Object* obj, bool do_set) { uintptr_t addr = reinterpret_cast<uintptr_t>(obj); - DCHECK_GE(addr, base_); - const uintptr_t offset = addr - base_; + DCHECK_GE(addr, heap_begin_); + const uintptr_t offset = addr - heap_begin_; const size_t index = HB_OFFSET_TO_INDEX(offset); const word mask = HB_OFFSET_TO_MASK(offset); - DCHECK_LT(index, num_bytes_ / kWordSize); + DCHECK_LT(index, bitmap_size_ / kWordSize); if (do_set) { - if (addr > max_) { - max_ = addr; + if (addr > heap_end_) { + heap_end_ = addr; } - words_[index] |= mask; + bitmap_begin_[index] |= mask; } else { - words_[index] &= ~mask; + bitmap_begin_[index] &= ~mask; } } - bool Init(const char* name, const byte* base, size_t length); - + // Backing storage for bitmap. UniquePtr<MemMap> mem_map_; - word* words_; + // This bitmap itself, word sized for efficiency in scanning. + word* const bitmap_begin_; - size_t num_bytes_; + // Size of this bitmap. + const size_t bitmap_size_; - // The base address, which corresponds to the word containing the - // first bit in the bitmap. - uintptr_t base_; + // The base address of the heap, which corresponds to the word containing the first bit in the + // bitmap. + const uintptr_t heap_begin_; // The highest pointer value ever returned by an allocation from // this heap. I.e., the highest address that may correspond to a - // set bit. If there are no bits set, (max_ < base_). - uintptr_t max_; + // set bit. If there are no bits set, (heap_end_ < heap_begin_). + uintptr_t heap_end_; - const char* name_; + // Name of this bitmap. + const char* const name_; }; } // namespace art diff --git a/src/heap_test.cc b/src/heap_test.cc index 77b98e4c33..2208e57f47 100644 --- a/src/heap_test.cc +++ b/src/heap_test.cc @@ -27,7 +27,7 @@ TEST_F(HeapTest, GarbageCollectClassLinkerInit) { } } - Heap::CollectGarbage(); + Heap::CollectGarbage(false); } } // namespace art diff --git a/src/image.h b/src/image.h index 76db7e5346..d0071d6aec 100644 --- a/src/image.h +++ b/src/image.h @@ -15,21 +15,21 @@ class PACKED ImageHeader { public: ImageHeader() {} - ImageHeader(uint32_t image_base_addr, + ImageHeader(uint32_t image_begin, uint32_t image_roots, uint32_t oat_checksum, - uint32_t oat_base_addr, - uint32_t oat_limit_addr) - : image_base_addr_(image_base_addr), + uint32_t oat_begin, + uint32_t oat_end) + : image_begin_(image_begin), oat_checksum_(oat_checksum), - oat_base_addr_(oat_base_addr), - oat_limit_addr_(oat_limit_addr), + oat_begin_(oat_begin), + oat_end_(oat_end), image_roots_(image_roots) { - CHECK_EQ(image_base_addr, RoundUp(image_base_addr, kPageSize)); - CHECK_EQ(oat_base_addr, RoundUp(oat_base_addr, kPageSize)); - CHECK_LT(image_base_addr, image_roots); - CHECK_LT(image_roots, oat_base_addr); - CHECK_LT(oat_base_addr, oat_limit_addr); + CHECK_EQ(image_begin, RoundUp(image_begin, kPageSize)); + CHECK_EQ(oat_begin, RoundUp(oat_begin, kPageSize)); + CHECK_LT(image_begin, image_roots); + CHECK_LT(image_roots, oat_begin); + CHECK_LT(oat_begin, oat_end); memcpy(magic_, kImageMagic, sizeof(kImageMagic)); memcpy(version_, kImageVersion, sizeof(kImageVersion)); } @@ -49,20 +49,20 @@ class PACKED ImageHeader { return reinterpret_cast<const char*>(magic_); } - byte* GetImageBaseAddr() const { - return reinterpret_cast<byte*>(image_base_addr_); + byte* GetImageBegin() const { + return reinterpret_cast<byte*>(image_begin_); } uint32_t GetOatChecksum() const { return oat_checksum_; } - byte* GetOatBaseAddr() const { - return reinterpret_cast<byte*>(oat_base_addr_); + byte* GetOatBegin() const { + return reinterpret_cast<byte*>(oat_begin_); } - byte* GetOatLimitAddr() const { - return reinterpret_cast<byte*>(oat_limit_addr_); + byte* GetOatEnd() const { + return reinterpret_cast<byte*>(oat_end_); } enum ImageRoot { @@ -96,16 +96,16 @@ class PACKED ImageHeader { byte version_[4]; // required base address for mapping the image. - uint32_t image_base_addr_; + uint32_t image_begin_; // checksum of the oat file we link to for load time sanity check uint32_t oat_checksum_; // required oat address expected by image Method::GetCode() pointers. - uint32_t oat_base_addr_; + uint32_t oat_begin_; // end of oat address range for this image file, used for positioning a following image - uint32_t oat_limit_addr_; + uint32_t oat_end_; // absolute address of an Object[] of objects needed to reinitialize from an image uint32_t image_roots_; diff --git a/src/image_test.cc b/src/image_test.cc index f5f96d8803..950ca92691 100644 --- a/src/image_test.cc +++ b/src/image_test.cc @@ -77,17 +77,17 @@ TEST_F(ImageTest, WriteRead) { ASSERT_TRUE(Heap::GetSpaces()[0]->IsImageSpace()); ASSERT_FALSE(Heap::GetSpaces()[1]->IsImageSpace()); - Space* image_space = Heap::GetSpaces()[0]; - byte* image_base = image_space->GetBase(); - byte* image_limit = image_space->GetLimit(); - CHECK_EQ(requested_image_base, reinterpret_cast<uintptr_t>(image_base)); + ImageSpace* image_space = Heap::GetSpaces()[0]->AsImageSpace(); + byte* image_begin = image_space->Begin(); + byte* image_end = image_space->End(); + CHECK_EQ(requested_image_base, reinterpret_cast<uintptr_t>(image_begin)); for (size_t i = 0; i < dex->NumClassDefs(); i++) { const DexFile::ClassDef& class_def = dex->GetClassDef(i); const char* descriptor = dex->GetClassDescriptor(class_def); Class* klass = class_linker_->FindSystemClass(descriptor); EXPECT_TRUE(klass != NULL) << descriptor; - EXPECT_LT(image_base, reinterpret_cast<byte*>(klass)) << descriptor; - EXPECT_LT(reinterpret_cast<byte*>(klass), image_limit) << descriptor; + EXPECT_LT(image_begin, reinterpret_cast<byte*>(klass)) << descriptor; + EXPECT_LT(reinterpret_cast<byte*>(klass), image_end) << descriptor; EXPECT_EQ(*klass->GetRawLockWordAddress(), 0); // address should have been removed from monitor } } diff --git a/src/image_writer.cc b/src/image_writer.cc index 861a878bf2..ca57f41e74 100644 --- a/src/image_writer.cc +++ b/src/image_writer.cc @@ -26,13 +26,13 @@ namespace art { bool ImageWriter::Write(const char* image_filename, - uintptr_t image_base, + uintptr_t image_begin, const std::string& oat_filename, const std::string& strip_location_prefix) { CHECK(image_filename != NULL); - CHECK_NE(image_base, 0U); - image_base_ = reinterpret_cast<byte*>(image_base); + CHECK_NE(image_begin, 0U); + image_begin_ = reinterpret_cast<byte*>(image_begin); const std::vector<Space*>& spaces = Heap::GetSpaces(); // currently just write the last space, assuming it is the space that was being used for allocation @@ -59,7 +59,7 @@ bool ImageWriter::Write(const char* image_filename, return false; } PruneNonImageClasses(); - Heap::CollectGarbage(); + Heap::CollectGarbage(false); #ifndef NDEBUG CheckNonImageClassesRemoved(); #endif @@ -72,7 +72,7 @@ bool ImageWriter::Write(const char* image_filename, LOG(ERROR) << "Failed to open image file " << image_filename; return false; } - bool success = file->WriteFully(image_->GetAddress(), image_top_); + bool success = file->WriteFully(image_->Begin(), image_end_); if (!success) { PLOG(ERROR) << "Failed to write image file " << image_filename; return false; @@ -273,26 +273,26 @@ void ImageWriter::CalculateNewObjectOffsets() { HeapBitmap* heap_bitmap = Heap::GetLiveBits(); DCHECK(heap_bitmap != NULL); - DCHECK_EQ(0U, image_top_); + DCHECK_EQ(0U, image_end_); // leave space for the header, but do not write it yet, we need to // know where image_roots is going to end up - image_top_ += RoundUp(sizeof(ImageHeader), 8); // 64-bit-alignment + image_end_ += RoundUp(sizeof(ImageHeader), 8); // 64-bit-alignment heap_bitmap->Walk(CalculateNewObjectOffsetsCallback, this); // TODO: add Space-limited Walk - DCHECK_LT(image_top_, image_->GetLength()); + DCHECK_LT(image_end_, image_->Size()); // Note that image_top_ is left at end of used space - oat_base_ = image_base_ + RoundUp(image_top_, kPageSize); - const byte* oat_limit = oat_base_ + oat_file_->GetSize(); + oat_begin_ = image_begin_ + RoundUp(image_end_, kPageSize); + const byte* oat_limit = oat_begin_ + oat_file_->Size(); // return to write header at start of image with future location of image_roots - ImageHeader image_header(reinterpret_cast<uint32_t>(image_base_), + ImageHeader image_header(reinterpret_cast<uint32_t>(image_begin_), reinterpret_cast<uint32_t>(GetImageAddress(image_roots.get())), oat_file_->GetOatHeader().GetChecksum(), - reinterpret_cast<uint32_t>(oat_base_), + reinterpret_cast<uint32_t>(oat_begin_), reinterpret_cast<uint32_t>(oat_limit)); - memcpy(image_->GetAddress(), &image_header, sizeof(image_header)); + memcpy(image_->Begin(), &image_header, sizeof(image_header)); } void ImageWriter::CopyAndFixupObjects() { @@ -315,10 +315,10 @@ void ImageWriter::CopyAndFixupObjectsCallback(Object* object, void* arg) { // see GetLocalAddress for similar computation size_t offset = image_writer->GetImageOffset(obj); - byte* dst = image_writer->image_->GetAddress() + offset; + byte* dst = image_writer->image_->Begin() + offset; const byte* src = reinterpret_cast<const byte*>(obj); size_t n = obj->SizeOf(); - DCHECK_LT(offset + n, image_writer->image_->GetLength()); + DCHECK_LT(offset + n, image_writer->image_->Size()); memcpy(dst, src, n); Object* copy = reinterpret_cast<Object*>(dst); ResetImageOffset(copy); @@ -363,7 +363,7 @@ void ImageWriter::FixupMethod(const Method* orig, Method* copy) { FixupInstanceFields(orig, copy); // OatWriter replaces the code_ and invoke_stub_ with offset values. - // Here we readjust to a pointer relative to oat_base_ + // Here we readjust to a pointer relative to oat_begin_ // Every type of method can have an invoke stub uint32_t invoke_stub_offset = orig->GetOatInvokeStubOffset(); diff --git a/src/image_writer.h b/src/image_writer.h index d32724cbb0..d834361bcb 100644 --- a/src/image_writer.h +++ b/src/image_writer.h @@ -23,12 +23,13 @@ namespace art { class ImageWriter { public: explicit ImageWriter(const std::set<std::string>* image_classes) - : source_space_(NULL), image_top_(0), image_base_(NULL), image_classes_(image_classes) {} + : source_space_(NULL), image_end_(0), image_begin_(NULL), image_classes_(image_classes), + oat_begin_(NULL) {} ~ImageWriter() {} bool Write(const char* image_filename, - uintptr_t image_base, + uintptr_t image_begin, const std::string& oat_filename, const std::string& strip_location_prefix); private: @@ -39,9 +40,9 @@ class ImageWriter { void AssignImageOffset(Object* object) { DCHECK(object != NULL); DCHECK_EQ(object->monitor_, 0U); // should be no lock - SetImageOffset(object, image_top_); - image_top_ += RoundUp(object->SizeOf(), 8); // 64-bit alignment - DCHECK_LT(image_top_, image_->GetLength()); + SetImageOffset(object, image_end_); + image_end_ += RoundUp(object->SizeOf(), 8); // 64-bit alignment + DCHECK_LT(image_end_, image_->Size()); } static void SetImageOffset(Object* object, size_t offset) { DCHECK(object != NULL); @@ -69,8 +70,7 @@ class ImageWriter { bool InSourceSpace(const Object* object) const { DCHECK(source_space_ != NULL); - const byte* o = reinterpret_cast<const byte*>(object); - return (o >= source_space_->GetBase() && o < source_space_->GetLimit()); + return source_space_->Contains(object); } Object* GetImageAddress(const Object* object) const { if (object == NULL) { @@ -80,20 +80,20 @@ class ImageWriter { if (!InSourceSpace(object)) { return const_cast<Object*>(object); } - return reinterpret_cast<Object*>(image_base_ + GetImageOffset(object)); + return reinterpret_cast<Object*>(image_begin_ + GetImageOffset(object)); } Object* GetLocalAddress(const Object* object) const { size_t offset = GetImageOffset(object); - byte* dst = image_->GetAddress() + offset; + byte* dst = image_->Begin() + offset; return reinterpret_cast<Object*>(dst); } const byte* GetOatAddress(uint32_t offset) const { - DCHECK_LT(offset, oat_file_->GetSize()); + DCHECK_LT(offset, oat_file_->Size()); if (offset == 0) { return NULL; } - return oat_base_ + offset; + return oat_begin_ + offset; } bool IsImageClass(const Class* klass); @@ -132,16 +132,16 @@ class ImageWriter { UniquePtr<MemMap> image_; // Offset to the free space in image_ - size_t image_top_; + size_t image_end_; - // Target image base address for the output image - byte* image_base_; + // Beginning target image address for the output image + byte* image_begin_; // Set of classes to be include in the image, or NULL for all. const std::set<std::string>* image_classes_; - // Target oat base address for the pointers from the output image to its oat file - const byte* oat_base_; + // Beginning target oat address for the pointers from the output image to its oat file + const byte* oat_begin_; // DexCaches seen while scanning for fixing up CodeAndDirectMethods typedef std::set<DexCache*> Set; diff --git a/src/java_lang_Runtime.cc b/src/java_lang_Runtime.cc index 981db70689..96337af699 100644 --- a/src/java_lang_Runtime.cc +++ b/src/java_lang_Runtime.cc @@ -31,7 +31,7 @@ namespace { void Runtime_gc(JNIEnv*, jclass) { ScopedThreadStateChange tsc(Thread::Current(), Thread::kRunnable); - Heap::CollectGarbage(); + Heap::CollectGarbage(false); } void Runtime_nativeExit(JNIEnv* env, jclass, jint status, jboolean isExit) { diff --git a/src/mark_stack.cc b/src/mark_stack.cc index 707b98bb0b..917c7b4827 100644 --- a/src/mark_stack.cc +++ b/src/mark_stack.cc @@ -25,9 +25,9 @@ void MarkStack::Init() { ReadFileToString("/proc/self/maps", &maps); LOG(FATAL) << "couldn't allocate mark stack\n" << maps; } - byte* addr = mem_map_->GetAddress(); + byte* addr = mem_map_->Begin(); CHECK(addr != NULL); - base_ = reinterpret_cast<const Object**>(addr); + begin_ = reinterpret_cast<const Object**>(addr); limit_ = reinterpret_cast<const Object**>(addr + length); ptr_ = reinterpret_cast<Object const**>(addr); int result = madvise(addr, length, MADV_DONTNEED); diff --git a/src/mark_stack.h b/src/mark_stack.h index 47d18cd773..28ad1651ef 100644 --- a/src/mark_stack.h +++ b/src/mark_stack.h @@ -26,19 +26,19 @@ class MarkStack { } const Object* Pop() { - DCHECK_NE(ptr_, base_); + DCHECK_NE(ptr_, begin_); --ptr_; DCHECK(*ptr_ != NULL); return *ptr_; } bool IsEmpty() const { - return ptr_ == base_; + return ptr_ == begin_; } private: MarkStack() : - base_(NULL), limit_(NULL), ptr_(NULL) { + begin_(NULL), limit_(NULL), ptr_(NULL) { } void Init(); @@ -47,7 +47,7 @@ class MarkStack { UniquePtr<MemMap> mem_map_; // Base of the mark stack. - const Object* const* base_; + const Object* const* begin_; // Exclusive limit of the mark stack. const Object* const* limit_; diff --git a/src/mark_sweep.cc b/src/mark_sweep.cc index 9078340c7c..cc1dcde961 100644 --- a/src/mark_sweep.cc +++ b/src/mark_sweep.cc @@ -90,9 +90,9 @@ void MarkSweep::ScanDirtyImageRoots() { CardTable* card_table = Heap::GetCardTable(); for (size_t i = 0; i < spaces.size(); ++i) { if (spaces[i]->IsImageSpace()) { - byte* base = spaces[i]->GetBase(); - byte* limit = spaces[i]->GetLimit(); - card_table->Scan(base, limit, ScanImageRootVisitor, this); + byte* begin = spaces[i]->Begin(); + byte* end = spaces[i]->End(); + card_table->Scan(begin, end, ScanImageRootVisitor, this); } } } @@ -124,18 +124,18 @@ void MarkSweep::RecursiveMark() { const std::vector<Space*>& spaces = Heap::GetSpaces(); for (size_t i = 0; i < spaces.size(); ++i) { #ifndef NDEBUG - uintptr_t base = reinterpret_cast<uintptr_t>(spaces[i]->GetBase()); - uintptr_t limit = reinterpret_cast<uintptr_t>(spaces[i]->GetLimit()); + uintptr_t begin = reinterpret_cast<uintptr_t>(spaces[i]->Begin()); + uintptr_t end = reinterpret_cast<uintptr_t>(spaces[i]->End()); if (!spaces[i]->IsImageSpace()) { - mark_bitmap_->ScanWalk(base, limit, &MarkSweep::ScanBitmapCallback, arg); + mark_bitmap_->ScanWalk(begin, end, &MarkSweep::ScanBitmapCallback, arg); } else{ - mark_bitmap_->ScanWalk(base, limit, &MarkSweep::CheckBitmapCallback, arg); + mark_bitmap_->ScanWalk(begin, end, &MarkSweep::CheckBitmapCallback, arg); } #else if (!spaces[i]->IsImageSpace()) { - uintptr_t base = reinterpret_cast<uintptr_t>(spaces[i]->GetBase()); - uintptr_t limit = reinterpret_cast<uintptr_t>(spaces[i]->GetLimit()); - mark_bitmap_->ScanWalk(base, limit, &MarkSweep::ScanBitmapCallback, arg); + uintptr_t begin = reinterpret_cast<uintptr_t>(spaces[i]->Begin()); + uintptr_t end = reinterpret_cast<uintptr_t>(spaces[i]->End()); + mark_bitmap_->ScanWalk(begin, end, &MarkSweep::ScanBitmapCallback, arg); } #endif } @@ -167,27 +167,30 @@ void MarkSweep::SweepSystemWeaks() { SweepJniWeakGlobals(); } -void MarkSweep::SweepCallback(size_t num_ptrs, void** ptrs, void* arg) { +void MarkSweep::SweepCallback(size_t num_ptrs, Object** ptrs, void* arg) { // TODO: lock heap if concurrent size_t freed_objects = num_ptrs; size_t freed_bytes = 0; - Space* space = static_cast<Space*>(arg); + AllocSpace* space = static_cast<AllocSpace*>(arg); // Use a bulk free, that merges consecutive objects before freeing or free per object? // Documentation suggests better free performance with merging, but this may be at the expensive // of allocation. // TODO: investigate performance - static const bool kFreeUsingMerge = true; - if (kFreeUsingMerge) { - freed_bytes = space->FreeList(num_ptrs, ptrs); + static const bool kUseFreeList = true; + if (kUseFreeList) { for (size_t i = 0; i < num_ptrs; ++i) { Object* obj = static_cast<Object*>(ptrs[i]); + freed_bytes += space->AllocationSize(obj); Heap::GetLiveBits()->Clear(obj); } + // AllocSpace::FreeList clears the value in ptrs, so perform after clearing the live bit + space->FreeList(num_ptrs, ptrs); } else { for (size_t i = 0; i < num_ptrs; ++i) { Object* obj = static_cast<Object*>(ptrs[i]); + freed_bytes += space->AllocationSize(obj); Heap::GetLiveBits()->Clear(obj); - freed_bytes += space->Free(obj); + space->Free(obj); } } Heap::RecordFreeLocked(freed_objects, freed_bytes); @@ -200,10 +203,10 @@ void MarkSweep::Sweep() { const std::vector<Space*>& spaces = Heap::GetSpaces(); for (size_t i = 0; i < spaces.size(); ++i) { if (!spaces[i]->IsImageSpace()) { - uintptr_t base = reinterpret_cast<uintptr_t>(spaces[i]->GetBase()); - uintptr_t limit = reinterpret_cast<uintptr_t>(spaces[i]->GetLimit()); + uintptr_t begin = reinterpret_cast<uintptr_t>(spaces[i]->Begin()); + uintptr_t end = reinterpret_cast<uintptr_t>(spaces[i]->End()); void* arg = static_cast<void*>(spaces[i]); - HeapBitmap::SweepWalk(*live_bitmap_, *mark_bitmap_, base, limit, + HeapBitmap::SweepWalk(*live_bitmap_, *mark_bitmap_, begin, end, &MarkSweep::SweepCallback, arg); } } @@ -266,14 +269,15 @@ inline void MarkSweep::ScanFields(const Object* obj, uint32_t ref_offsets, bool } inline void MarkSweep::CheckReference(const Object* obj, const Object* ref, MemberOffset offset, bool is_static) { - Space* alloc_space = Heap::GetAllocSpace(); + AllocSpace* alloc_space = Heap::GetAllocSpace(); if (alloc_space->Contains(ref)) { bool is_marked = mark_bitmap_->Test(ref); if(!is_marked) { - LOG(INFO) << StringPrintf("Alloc space %p-%p (%s)", alloc_space->GetBase(), alloc_space->GetLimit(), alloc_space->GetName().c_str()); - LOG(WARNING) << (is_static ? "Static ref'" : "Instance ref'") << PrettyTypeOf(ref) << "' (" << (void*)ref - << ") in '" << PrettyTypeOf(obj) << "' (" << (void*)obj << ") at offset " - << (void*)offset.Int32Value() << " wasn't marked"; + LOG(INFO) << *alloc_space; + LOG(WARNING) << (is_static ? "Static ref'" : "Instance ref'") << PrettyTypeOf(ref) + << "' (" << (void*)ref << ") in '" << PrettyTypeOf(obj) + << "' (" << (void*)obj << ") at offset " + << (void*)offset.Int32Value() << " wasn't marked"; bool obj_marked = Heap::GetCardTable()->IsDirty(obj); if (!obj_marked) { LOG(WARNING) << "Object '" << PrettyTypeOf(obj) << "' (" << (void*)obj diff --git a/src/mark_sweep.h b/src/mark_sweep.h index c517246ac2..3b72d1a4bc 100644 --- a/src/mark_sweep.h +++ b/src/mark_sweep.h @@ -85,7 +85,7 @@ class MarkSweep { static void CheckBitmapCallback(Object* obj, void* finger, void* arg); - static void SweepCallback(size_t num_ptrs, void** ptrs, void* arg); + static void SweepCallback(size_t num_ptrs, Object** ptrs, void* arg); void CheckReference(const Object* obj, const Object* ref, MemberOffset offset, bool is_static); diff --git a/src/mem_map.cc b/src/mem_map.cc index 673098df6b..92c6a591ff 100644 --- a/src/mem_map.cc +++ b/src/mem_map.cc @@ -156,23 +156,21 @@ MemMap* MemMap::MapFileAtAddress(byte* addr, size_t length, int prot, int flags, } MemMap::~MemMap() { - if (base_addr_ == NULL && base_length_ == 0) { + if (base_begin_ == NULL && base_size_ == 0) { return; } - int result = munmap(base_addr_, base_length_); - base_addr_ = NULL; - base_length_ = 0; + int result = munmap(base_begin_, base_size_); if (result == -1) { PLOG(FATAL) << "munmap failed"; } } -MemMap::MemMap(byte* addr, size_t length, void* base_addr, size_t base_length) - : addr_(addr), length_(length), base_addr_(base_addr), base_length_(base_length) { - CHECK(addr_ != NULL); - CHECK_NE(length_, 0U); - CHECK(base_addr_ != NULL); - CHECK_NE(base_length_, 0U); +MemMap::MemMap(byte* begin, size_t size, void* base_begin, size_t base_size) + : begin_(begin), size_(size), base_begin_(base_begin), base_size_(base_size) { + CHECK(begin_ != NULL); + CHECK_NE(size_, 0U); + CHECK(base_begin_ != NULL); + CHECK_NE(base_size_, 0U); }; } // namespace art diff --git a/src/mem_map.h b/src/mem_map.h index 43e1cfd03e..ce2f4fae96 100644 --- a/src/mem_map.h +++ b/src/mem_map.h @@ -57,26 +57,26 @@ class MemMap { // Releases the memory mapping ~MemMap(); - byte* GetAddress() const { - return addr_; + byte* Begin() const { + return begin_; } - size_t GetLength() const { - return length_; + size_t Size() const { + return size_; } - byte* GetLimit() const { - return addr_ + length_; + byte* End() const { + return begin_ + size_; } private: - MemMap(byte* addr, size_t length, void* base_addr, size_t base_length); + MemMap(byte* begin, size_t size, void* base_begin, size_t base_size); - byte* addr_; // start of data - size_t length_; // length of data + byte* const begin_; // start of data + const size_t size_; // length of data - void* base_addr_; // page-aligned base address - size_t base_length_; // length of mapping + void* const base_begin_; // page-aligned base address + const size_t base_size_; // length of mapping }; } // namespace art diff --git a/src/mspace.c b/src/mspace.c deleted file mode 100644 index a4263d5974..0000000000 --- a/src/mspace.c +++ /dev/null @@ -1,231 +0,0 @@ -/* Copyright 2006 The Android Open Source Project */ - -/* A wrapper file for dlmalloc.c that compiles in the - * mspace_*() functions, which provide an interface for - * creating multiple heaps. - */ -#include <sys/types.h> -#include <sys/stat.h> -#include <fcntl.h> -#include <unistd.h> -#include <stdint.h> -#include <sys/ioctl.h> - -/* It's a pain getting the mallinfo stuff to work - * with Linux, OSX, and klibc, so just turn it off - * for now. - * TODO: make mallinfo work - */ -#define NO_MALLINFO 1 - -/* Allow setting the maximum heap footprint. - */ -#define USE_MAX_ALLOWED_FOOTPRINT 1 - -/* Don't try to trim memory. - * TODO: support this. - */ -#define MORECORE_CANNOT_TRIM 1 - -/* Use mmap()d anonymous memory to guarantee - * that an mspace is contiguous. - * - * create_mspace() won't work right if this is - * defined, so hide the definition of it and - * break any users at build time. - */ -#define USE_CONTIGUOUS_MSPACES 1 -#if USE_CONTIGUOUS_MSPACES -/* This combination of settings forces sys_alloc() - * to always use MORECORE(). It won't expect the - * results to be contiguous, but we'll guarantee - * that they are. - */ -#define HAVE_MMAP 0 -#define HAVE_MORECORE 1 -#define MORECORE_CONTIGUOUS 0 -/* m is always the appropriate local when MORECORE() is called. */ -#define MORECORE(S) contiguous_mspace_morecore(m, S) -#define create_mspace HIDDEN_create_mspace_HIDDEN -#define destroy_mspace HIDDEN_destroy_mspace_HIDDEN -typedef struct malloc_state *mstate0; -static void *contiguous_mspace_morecore(mstate0 m, ssize_t nb); -#endif /* USE_CONTIGUOUS_MSPACES */ - -#define MSPACES 1 -#define ONLY_MSPACES 1 -#include "dlmalloc.c" - -#ifndef PAGESIZE -#define PAGESIZE mparams.page_size -#endif - -#define ALIGN_UP(p, alignment) \ - (((uintptr_t)(p) + (alignment)-1) & ~((alignment)-1)) - -/* A direct copy of dlmalloc_usable_size(), - * which isn't compiled in when ONLY_MSPACES is set. - * The mspace parameter isn't actually necessary, - * but we include it to be consistent with the - * rest of the mspace_*() functions. - */ -size_t mspace_usable_size(mspace _unused, const void* mem) { - if (mem != 0) { - const mchunkptr p = mem2chunk(mem); - if (cinuse(p)) - return chunksize(p) - overhead_for(p); - } - return 0; -} - -#if USE_CONTIGUOUS_MSPACES -#include <sys/mman.h> -#include <limits.h> - -#define CONTIG_STATE_MAGIC 0xf00dd00d -struct mspace_contig_state { - unsigned int magic; - char *brk; - char *top; - mspace m; -}; - -static void *contiguous_mspace_morecore(mstate m, ssize_t nb) { - struct mspace_contig_state *cs; - char *oldbrk; - const unsigned int pagesize = PAGESIZE; - - cs = (struct mspace_contig_state *)((uintptr_t)m & ~(pagesize-1)); - assert(cs->magic == CONTIG_STATE_MAGIC); - assert(cs->m == m); -assert(nb >= 0); //xxx deal with the trim case - - oldbrk = cs->brk; - if (nb > 0) { - /* Break to the first page boundary that satisfies the request. - */ - char *newbrk = (char *)ALIGN_UP(oldbrk + nb, pagesize); - if (newbrk > cs->top) - return CMFAIL; - - /* Update the protection on the underlying memory. - * Pages we've given to dlmalloc are read/write, and - * pages we haven't are not accessable (read or write - * will cause a seg fault). - */ - if (mprotect(cs, newbrk - (char *)cs, PROT_READ | PROT_WRITE) < 0) - return CMFAIL; - if (newbrk != cs->top) { - if (mprotect(newbrk, cs->top - newbrk, PROT_NONE) < 0) - return CMFAIL; - } - - cs->brk = newbrk; - - /* Make sure that dlmalloc will merge this block with the - * initial block that was passed to create_mspace_with_base(). - * We don't care about extern vs. non-extern, so just clear it. - */ - m->seg.sflags &= ~EXTERN_BIT; - } - - return oldbrk; -} - -mspace create_contiguous_mspace_with_base(size_t starting_capacity, - size_t max_capacity, int locked, void *base) { - struct mspace_contig_state *cs; - unsigned int pagesize; - mstate m; - - init_mparams(); - pagesize = PAGESIZE; - assert(starting_capacity <= max_capacity); - assert(((uintptr_t)base & (pagesize-1)) == 0); - assert(((uintptr_t)max_capacity & (pagesize-1)) == 0); - starting_capacity = (size_t)ALIGN_UP(starting_capacity, pagesize); - - /* Make the first page read/write. dlmalloc needs to use that page. - */ - if (mprotect(base, starting_capacity, PROT_READ | PROT_WRITE) < 0) { - goto error; - } - - /* Create the mspace, pointing to the memory given. - */ - m = create_mspace_with_base((char *)base + sizeof(*cs), starting_capacity, - locked); - if (m == (mspace)0) { - goto error; - } - /* Make sure that m is in the same page as base. - */ - assert(((uintptr_t)m & (uintptr_t)~(pagesize-1)) == (uintptr_t)base); - /* Use some space for the information that our MORECORE needs. - */ - cs = (struct mspace_contig_state *)base; - - /* Find out exactly how much of the memory the mspace - * is using. - */ - cs->brk = m->seg.base + m->seg.size; - cs->top = (char *)base + max_capacity; - - assert((char *)base <= cs->brk); - assert(cs->brk <= cs->top); - /* Prevent access to the memory we haven't handed out yet. - */ - if (cs->brk != cs->top) { - /* mprotect() requires page-aligned arguments, but it's possible - * for cs->brk not to be page-aligned at this point. - */ - char *prot_brk = (char *)ALIGN_UP(cs->brk, pagesize); - if ((mprotect(base, prot_brk - (char *)base, PROT_READ | PROT_WRITE) < 0) || - (mprotect(prot_brk, cs->top - prot_brk, PROT_NONE) < 0)) { - goto error; - } - } - - cs->m = m; - cs->magic = CONTIG_STATE_MAGIC; - - return (mspace)m; - -error: - return (mspace)0; -} - -size_t destroy_contiguous_mspace(mspace msp) { - mstate ms = (mstate)msp; - - if (ok_magic(ms)) { - struct mspace_contig_state *cs; - size_t length; - const unsigned int pagesize = PAGESIZE; - - cs = (struct mspace_contig_state *)((uintptr_t)ms & ~(pagesize-1)); - assert(cs->magic == CONTIG_STATE_MAGIC); - assert(cs->m == ms); - - length = cs->top - (char *)cs; - if (munmap((char *)cs, length) != 0) - return length; - } - else { - USAGE_ERROR_ACTION(ms, ms); - } - return 0; -} - -void *contiguous_mspace_sbrk0(mspace msp) { - struct mspace_contig_state *cs; - mstate ms; - const unsigned int pagesize = PAGESIZE; - - ms = (mstate)msp; - cs = (struct mspace_contig_state *)((uintptr_t)ms & ~(pagesize-1)); - assert(cs->magic == CONTIG_STATE_MAGIC); - assert(cs->m == ms); - return cs->brk; -} -#endif /* USE_CONTIGUOUS_MSPACES */ diff --git a/src/mspace.h b/src/mspace.h deleted file mode 100644 index b22d9a4d8e..0000000000 --- a/src/mspace.h +++ /dev/null @@ -1,128 +0,0 @@ -/* - * Copyright (C) 2006 The Android Open Source Project - * - * Licensed under the Apache License, Version 2.0 (the "License"); - * you may not use this file except in compliance with the License. - * You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -/* A wrapper file for dlmalloc.h that defines prototypes for the - * mspace_*() functions, which provide an interface for creating - * multiple heaps. - */ - -#ifndef MSPACE_H_ -#define MSPACE_H_ - -/* It's a pain getting the mallinfo stuff to work - * with Linux, OSX, and klibc, so just turn it off - * for now. - * TODO: make mallinfo work - */ -#define NO_MALLINFO 1 - -/* Allow setting the maximum heap footprint. - */ -#define USE_MAX_ALLOWED_FOOTPRINT 1 - -#define USE_CONTIGUOUS_MSPACES 1 -#if USE_CONTIGUOUS_MSPACES -#define HAVE_MMAP 0 -#define HAVE_MORECORE 1 -#define MORECORE_CONTIGUOUS 0 -#endif - -#define MSPACES 1 -#define ONLY_MSPACES 1 -#include "dlmalloc.h" - -#ifdef __cplusplus -extern "C" { -#endif - -/* - mspace_usable_size(void* p); - - Returns the number of bytes you can actually use in - an allocated chunk, which may be more than you requested (although - often not) due to alignment and minimum size constraints. - You can use this many bytes without worrying about - overwriting other allocated objects. This is not a particularly great - programming practice. mspace_usable_size can be more useful in - debugging and assertions, for example: - - p = mspace_malloc(msp, n); - assert(mspace_usable_size(msp, p) >= 256); -*/ -size_t mspace_usable_size(mspace, const void*); - -#if USE_CONTIGUOUS_MSPACES -/* - Similar to create_mspace(), but the underlying memory is - guaranteed to be contiguous. No more than max_capacity - bytes is ever allocated to the mspace. - */ -mspace create_contiguous_mspace(size_t starting_capacity, size_t max_capacity, - int locked); - -/* - Identical to create_contiguous_mspace, but labels the mapping 'mspace/name' - instead of 'mspace' -*/ -mspace create_contiguous_mspace_with_name(size_t starting_capacity, - size_t max_capacity, int locked, const char *name); - -/* - Identical to create_contiguous_mspace, but uses previously mapped memory. -*/ -mspace create_contiguous_mspace_with_base(size_t starting_capacity, - size_t max_capacity, int locked, void *base); - -size_t destroy_contiguous_mspace(mspace msp); - -/* - Returns the position of the "break" within the given mspace. -*/ -void *contiguous_mspace_sbrk0(mspace msp); -#endif - -/* - Call the handler for each block in the specified mspace. - chunkptr and chunklen refer to the heap-level chunk including - the chunk overhead, and userptr and userlen refer to the - user-usable part of the chunk. If the chunk is free, userptr - will be NULL and userlen will be 0. userlen is not guaranteed - to be the same value passed into malloc() for a given chunk; - it is >= the requested size. - */ -void mspace_walk_heap(mspace msp, - void(*handler)(const void *chunkptr, size_t chunklen, - const void *userptr, size_t userlen, void *arg), void *harg); - -/* - mspace_walk_free_pages(handler, harg) - - Calls the provided handler on each free region in the specified - mspace. The memory between start and end are guaranteed not to - contain any important data, so the handler is free to alter the - contents in any way. This can be used to advise the OS that large - free regions may be swapped out. - - The value in harg will be passed to each call of the handler. - */ -void mspace_walk_free_pages(mspace msp, - void(*handler)(void *start, void *end, void *arg), void *harg); - -#ifdef __cplusplus -}; /* end of extern "C" */ -#endif - -#endif /* MSPACE_H_ */ diff --git a/src/oat_file.cc b/src/oat_file.cc index 7cc42ab91f..168f0e34f3 100644 --- a/src/oat_file.cc +++ b/src/oat_file.cc @@ -65,13 +65,13 @@ bool OatFile::Read(const std::string& filename, byte* requested_base) { LOG(WARNING) << "Failed to map oat file " << filename; return false; } - CHECK(requested_base == 0 || requested_base == map->GetAddress()) - << filename << " " << reinterpret_cast<void*>(map->GetAddress()); - DCHECK_EQ(0, memcmp(&oat_header, map->GetAddress(), sizeof(OatHeader))) << filename; + CHECK(requested_base == 0 || requested_base == map->Begin()) + << filename << " " << reinterpret_cast<void*>(map->Begin()); + DCHECK_EQ(0, memcmp(&oat_header, map->Begin(), sizeof(OatHeader))) << filename; off_t code_offset = oat_header.GetExecutableOffset(); if (code_offset < file->Length()) { - byte* code_address = map->GetAddress() + code_offset; + byte* code_address = map->Begin() + code_offset; size_t code_length = file->Length() - code_offset; if (mprotect(code_address, code_length, PROT_READ | PROT_EXEC) != 0) { PLOG(ERROR) << "Failed to make oat code executable in " << filename; @@ -82,40 +82,40 @@ bool OatFile::Read(const std::string& filename, byte* requested_base) { DCHECK_EQ(code_offset, RoundUp(file->Length(), kPageSize)) << filename; } - const byte* oat = map->GetAddress(); + const byte* oat = map->Begin(); oat += sizeof(OatHeader); - CHECK_LE(oat, map->GetLimit()) << filename; + CHECK_LE(oat, map->End()) << filename; for (size_t i = 0; i < oat_header.GetDexFileCount(); i++) { size_t dex_file_location_size = *reinterpret_cast<const uint32_t*>(oat); CHECK_GT(dex_file_location_size, 0U) << filename; oat += sizeof(dex_file_location_size); - CHECK_LT(oat, map->GetLimit()) << filename; + CHECK_LT(oat, map->End()) << filename; const char* dex_file_location_data = reinterpret_cast<const char*>(oat); oat += dex_file_location_size; - CHECK_LT(oat, map->GetLimit()) << filename; + CHECK_LT(oat, map->End()) << filename; std::string dex_file_location(dex_file_location_data, dex_file_location_size); uint32_t dex_file_checksum = *reinterpret_cast<const uint32_t*>(oat); oat += sizeof(dex_file_checksum); - CHECK_LT(oat, map->GetLimit()) << filename; + CHECK_LT(oat, map->End()) << filename; uint32_t dex_file_offset = *reinterpret_cast<const uint32_t*>(oat); CHECK_GT(dex_file_offset, 0U) << filename; CHECK_LT(dex_file_offset, static_cast<uint32_t>(file->Length())) << filename; oat += sizeof(dex_file_offset); - CHECK_LT(oat, map->GetLimit()) << filename; + CHECK_LT(oat, map->End()) << filename; - uint8_t* dex_file_pointer = map->GetAddress() + dex_file_offset; + uint8_t* dex_file_pointer = map->Begin() + dex_file_offset; CHECK(DexFile::IsMagicValid(dex_file_pointer)) << filename << " " << dex_file_pointer; CHECK(DexFile::IsVersionValid(dex_file_pointer)) << filename << " " << dex_file_pointer; const DexFile::Header* header = reinterpret_cast<const DexFile::Header*>(dex_file_pointer); const uint32_t* methods_offsets_pointer = reinterpret_cast<const uint32_t*>(oat); oat += (sizeof(*methods_offsets_pointer) * header->class_defs_size_); - CHECK_LE(oat, map->GetLimit()) << filename; + CHECK_LE(oat, map->End()) << filename; oat_dex_files_[dex_file_location] = new OatDexFile(this, dex_file_location, @@ -129,17 +129,17 @@ bool OatFile::Read(const std::string& filename, byte* requested_base) { } const OatHeader& OatFile::GetOatHeader() const { - return *reinterpret_cast<const OatHeader*>(GetBase()); + return *reinterpret_cast<const OatHeader*>(Begin()); } -const byte* OatFile::GetBase() const { - CHECK(mem_map_->GetAddress() != NULL); - return mem_map_->GetAddress(); +const byte* OatFile::Begin() const { + CHECK(mem_map_->Begin() != NULL); + return mem_map_->Begin(); } -const byte* OatFile::GetLimit() const { - CHECK(mem_map_->GetLimit() != NULL); - return mem_map_->GetLimit(); +const byte* OatFile::End() const { + CHECK(mem_map_->End() != NULL); + return mem_map_->End(); } const OatFile::OatDexFile* OatFile::GetOatDexFile(const std::string& dex_file_location, @@ -183,12 +183,12 @@ const DexFile* OatFile::OatDexFile::OpenDexFile() const { const OatFile::OatClass* OatFile::OatDexFile::GetOatClass(uint32_t class_def_index) const { uint32_t oat_class_offset = oat_class_offsets_pointer_[class_def_index]; - const byte* oat_class_pointer = oat_file_->GetBase() + oat_class_offset; - CHECK_LT(oat_class_pointer, oat_file_->GetLimit()); + const byte* oat_class_pointer = oat_file_->Begin() + oat_class_offset; + CHECK_LT(oat_class_pointer, oat_file_->End()); Class::Status status = *reinterpret_cast<const Class::Status*>(oat_class_pointer); const byte* methods_pointer = oat_class_pointer + sizeof(status); - CHECK_LT(methods_pointer, oat_file_->GetLimit()); + CHECK_LT(methods_pointer, oat_file_->End()); return new OatClass(oat_file_, status, @@ -209,7 +209,7 @@ Class::Status OatFile::OatClass::GetStatus() const { const OatFile::OatMethod OatFile::OatClass::GetOatMethod(uint32_t method_index) const { const OatMethodOffsets& oat_method_offsets = methods_pointer_[method_index]; return OatMethod( - oat_file_->GetBase(), + oat_file_->Begin(), oat_method_offsets.code_offset_, oat_method_offsets.frame_size_in_bytes_, oat_method_offsets.core_spill_mask_, @@ -229,7 +229,7 @@ OatFile::OatMethod::OatMethod(const byte* base, const uint32_t vmap_table_offset, const uint32_t gc_map_offset, const uint32_t invoke_stub_offset) - : base_(base), + : begin_(base), code_offset_(code_offset), frame_size_in_bytes_(frame_size_in_bytes), core_spill_mask_(core_spill_mask), @@ -243,7 +243,7 @@ OatFile::OatMethod::OatMethod(const byte* base, if (vmap_table_offset_ == 0) { DCHECK_EQ(0U, static_cast<uint32_t>(__builtin_popcount(core_spill_mask_) + __builtin_popcount(fp_spill_mask_))); } else { - const uint16_t* vmap_table_ = reinterpret_cast<const uint16_t*>(base_ + vmap_table_offset_); + const uint16_t* vmap_table_ = reinterpret_cast<const uint16_t*>(begin_ + vmap_table_offset_); DCHECK_EQ(vmap_table_[0], static_cast<uint32_t>(__builtin_popcount(core_spill_mask_) + __builtin_popcount(fp_spill_mask_))); } } else { diff --git a/src/oat_file.h b/src/oat_file.h index 07e235b9f1..8415140549 100644 --- a/src/oat_file.h +++ b/src/oat_file.h @@ -103,10 +103,10 @@ class OatFile { if (offset == 0) { return NULL; } - return reinterpret_cast<T>(base_ + offset); + return reinterpret_cast<T>(begin_ + offset); } - const byte* base_; + const byte* begin_; uint32_t code_offset_; size_t frame_size_in_bytes_; @@ -178,16 +178,16 @@ class OatFile { bool warn_if_not_found = true) const; std::vector<const OatDexFile*> GetOatDexFiles() const; - size_t GetSize() const { - return GetLimit() - GetBase(); + size_t Size() const { + return End() - Begin(); } private: explicit OatFile(const std::string& filename); bool Read(const std::string& filename, byte* requested_base); - const byte* GetBase() const; - const byte* GetLimit() const; + const byte* Begin() const; + const byte* End() const; // The oat file name. // diff --git a/src/oatdump.cc b/src/oatdump.cc index be02d4d7be..bf9962cea4 100644 --- a/src/oatdump.cc +++ b/src/oatdump.cc @@ -84,11 +84,11 @@ class OatDump { os << "EXECUTABLE OFFSET:\n"; os << StringPrintf("%08x\n\n", oat_header.GetExecutableOffset()); - os << "BASE:\n"; - os << reinterpret_cast<const void*>(oat_file.GetBase()) << "\n\n"; + os << "BEGIN:\n"; + os << reinterpret_cast<const void*>(oat_file.Begin()) << "\n\n"; - os << "LIMIT:\n"; - os << reinterpret_cast<const void*>(oat_file.GetLimit()) << "\n\n"; + os << "END:\n"; + os << reinterpret_cast<const void*>(oat_file.End()) << "\n\n"; os << std::flush; @@ -207,17 +207,17 @@ class ImageDump { os << "MAGIC:\n"; os << image_header.GetMagic() << "\n\n"; - os << "IMAGE BASE:\n"; - os << reinterpret_cast<void*>(image_header.GetImageBaseAddr()) << "\n\n"; + os << "IMAGE BEGIN:\n"; + os << reinterpret_cast<void*>(image_header.GetImageBegin()) << "\n\n"; os << "OAT CHECKSUM:\n"; os << StringPrintf("%08x\n\n", image_header.GetOatChecksum()); - os << "OAT BASE:\n"; - os << reinterpret_cast<void*>(image_header.GetOatBaseAddr()) << "\n\n"; + os << "OAT BEGIN:\n"; + os << reinterpret_cast<void*>(image_header.GetOatBegin()) << "\n\n"; - os << "OAT LIMIT:\n"; - os << reinterpret_cast<void*>(image_header.GetOatLimitAddr()) << "\n\n"; + os << "OAT END:\n"; + os << reinterpret_cast<void*>(image_header.GetOatEnd()) << "\n\n"; os << "ROOTS:\n"; os << reinterpret_cast<void*>(image_header.GetImageRoots()) << "\n"; @@ -381,8 +381,7 @@ class ImageDump { } bool InDumpSpace(const Object* object) { - const byte* o = reinterpret_cast<const byte*>(object); - return (o >= dump_space_.GetBase() && o < dump_space_.GetLimit()); + return dump_space_.Contains(object); } public: @@ -584,7 +583,7 @@ int oatdump(int argc, char** argv) { return EXIT_FAILURE; } - Space* image_space = Heap::GetSpaces()[Heap::GetSpaces().size()-2]; + ImageSpace* image_space = Heap::GetSpaces()[Heap::GetSpaces().size()-2]->AsImageSpace(); CHECK(image_space != NULL); const ImageHeader& image_header = image_space->GetImageHeader(); if (!image_header.IsValid()) { diff --git a/src/object.h b/src/object.h index 7d8b7683b8..58c36be1b5 100644 --- a/src/object.h +++ b/src/object.h @@ -350,8 +350,8 @@ class MANAGED Object { } template<typename T> - void SetFieldPtr(MemberOffset field_offset, T new_value, bool is_volatile) { - SetField32(field_offset, reinterpret_cast<uint32_t>(new_value), is_volatile); + void SetFieldPtr(MemberOffset field_offset, T new_value, bool is_volatile, bool this_is_valid = true) { + SetField32(field_offset, reinterpret_cast<uint32_t>(new_value), is_volatile, this_is_valid); } private: diff --git a/src/runtime.cc b/src/runtime.cc index fcbcc08aa8..c70ca77afa 100644 --- a/src/runtime.cc +++ b/src/runtime.cc @@ -577,8 +577,8 @@ bool Runtime::Init(const Options& raw_options, bool ignore_unrecognized) { intern_table_ = new InternTable; Heap::Init(options->heap_initial_size_, - options->heap_maximum_size_, options->heap_growth_limit_, + options->heap_maximum_size_, options->images_); BlockSignals(); diff --git a/src/signal_catcher.cc b/src/signal_catcher.cc index 80563e2bf4..423083459e 100644 --- a/src/signal_catcher.cc +++ b/src/signal_catcher.cc @@ -131,7 +131,7 @@ void SignalCatcher::HandleSigQuit() { void SignalCatcher::HandleSigUsr1() { LOG(INFO) << "SIGUSR1 forcing GC (no HPROF)"; - Heap::CollectGarbage(); + Heap::CollectGarbage(false); } int SignalCatcher::WaitForSignal(sigset_t& mask) { diff --git a/src/space.cc b/src/space.cc index 053d2df739..5cdeeebed3 100644 --- a/src/space.cc +++ b/src/space.cc @@ -5,6 +5,7 @@ #include <sys/mman.h> #include "UniquePtr.h" +#include "dlmalloc.h" #include "file.h" #include "image.h" #include "logging.h" @@ -13,108 +14,263 @@ namespace art { -Space* Space::Create(const std::string& name, size_t initial_size, size_t maximum_size, size_t growth_size, byte* requested_base) { - UniquePtr<Space> space(new Space(name)); - bool success = space->Init(initial_size, maximum_size, growth_size, requested_base); - if (!success) { +#ifndef NDEBUG +#define DEBUG_SPACES 1 +#endif + +#define CHECK_MEMORY_CALL(call, args, what) \ + do { \ + int rc = call args; \ + if (UNLIKELY(rc != 0)) { \ + errno = rc; \ + PLOG(FATAL) << # call << " failed for " << what; \ + } \ + } while (false) + +AllocSpace* Space::CreateAllocSpace(const std::string& name, size_t initial_size, + size_t growth_limit, size_t capacity, + byte* requested_begin) { + uint64_t start_time = 0; + if (VLOG_IS_ON(heap) || VLOG_IS_ON(startup)) { + start_time = NanoTime(); + VLOG(startup) << "Space::CreateAllocSpace entering " << name + << " initial_size=" << (initial_size / KB) << "KiB" + << " growth_limit=" << (growth_limit / KB) << "KiB" + << " capacity=" << (capacity / KB) << "KiB" + << " requested_begin=" << reinterpret_cast<void*>(requested_begin); + } + + // Sanity check arguments + if (initial_size > growth_limit) { + LOG(ERROR) << "Failed to create alloc space (" << name << ") where the initial size (" + << initial_size << ") is larger than its capacity (" << growth_limit << ")"; + return NULL; + } + if (growth_limit > capacity) { + LOG(ERROR) << "Failed to create alloc space (" << name << ") where the growth limit capacity" + " (" << growth_limit << ") is larger than the capacity (" << capacity << ")"; return NULL; - } else { - return space.release(); } -} -Space* Space::CreateFromImage(const std::string& image_file_name) { - CHECK(image_file_name != NULL); - UniquePtr<Space> space(new Space(image_file_name)); - bool success = space->InitFromImage(image_file_name); - if (!success) { + // Page align growth limit and capacity which will be used to manage mmapped storage + growth_limit = RoundUp(growth_limit, kPageSize); + capacity = RoundUp(capacity, kPageSize); + + UniquePtr<MemMap> mem_map(MemMap::MapAnonymous(name.c_str(), requested_begin, + capacity, PROT_READ | PROT_WRITE)); + if (mem_map.get() == NULL) { + LOG(ERROR) << "Failed to allocate pages for alloc space (" << name << ") of size " + << capacity << " bytes"; return NULL; - } else { - return space.release(); } -} -Space::~Space() {} + void* mspace = AllocSpace::CreateMallocSpace(mem_map->Begin(), initial_size, capacity); + if (mspace == NULL) { + LOG(ERROR) << "Failed to initialize mspace for alloc space (" << name << ")"; + return NULL; + } + + // Protect memory beyond the initial size + byte* end = mem_map->Begin() + initial_size; + if (capacity - initial_size > 0) { + CHECK_MEMORY_CALL(mprotect, (end, capacity - initial_size, PROT_NONE), name); + } -void* Space::CreateMallocSpace(void* base, - size_t initial_size, - size_t maximum_size) { + // Everything is set so record in immutable structure and leave + AllocSpace* space = new AllocSpace(name, mem_map.release(), mspace, end, growth_limit); + if (VLOG_IS_ON(heap) || VLOG_IS_ON(startup)) { + uint64_t duration_ms = (NanoTime() - start_time)/1000/1000; + LOG(INFO) << "Space::CreateAllocSpace exiting (" << duration_ms << " ms) " << *space; + } + return space; +} + +void* AllocSpace::CreateMallocSpace(void* begin, size_t size, size_t capacity) { + // clear errno to allow PLOG on error errno = 0; - bool is_locked = false; - size_t commit_size = initial_size / 2; - void* msp = create_contiguous_mspace_with_base(commit_size, maximum_size, - is_locked, base); + // create mspace using our backing storage starting at begin and of half the specified size. + // Don't use an internal dlmalloc lock (as we already hold heap lock). When size is exhaused + // morecore will be called. + void* msp = create_mspace_with_base(begin, size, false /*locked*/); if (msp != NULL) { - // Do not permit the heap grow past the starting size without our - // intervention. - mspace_set_max_allowed_footprint(msp, initial_size); + // Do not allow morecore requests to succeed beyond the initial size of the heap + mspace_set_footprint_limit(msp, size); } else { - // There is no guarantee that errno has meaning when the call - // fails, but it often does. - PLOG(ERROR) << "create_contiguous_mspace_with_base failed"; + PLOG(ERROR) << "create_mspace_with_base failed"; } return msp; } -bool Space::Init(size_t initial_size, size_t maximum_size, size_t growth_size, byte* requested_base) { - VLOG(startup) << "Space::Init entering " << name_ - << " initial_size=" << initial_size - << " maximum_size=" << maximum_size - << " growth_size=" << growth_size - << " requested_base=" << reinterpret_cast<void*>(requested_base); - if (initial_size > growth_size) { - LOG(ERROR) << "Failed to create space with initial size > growth size (" - << initial_size << ">" << growth_size << "): " << name_; - return false; +Object* AllocSpace::AllocWithoutGrowth(size_t num_bytes) { + Object* result = reinterpret_cast<Object*>(mspace_calloc(mspace_, 1, num_bytes)); +#if DEBUG_SPACES + if (result != NULL) { + CHECK(Contains(result)) << "Allocation (" << reinterpret_cast<void*>(result) + << ") not in bounds of heap " << *this; } - if (growth_size > maximum_size) { - LOG(ERROR) << "Failed to create space with growth size > maximum size (" - << growth_size << ">" << maximum_size << "): " << name_; - return false; +#endif + return result; +} + +Object* AllocSpace::AllocWithGrowth(size_t num_bytes) { + // Grow as much as possible within the mspace. + size_t max_allowed = Capacity(); + mspace_set_footprint_limit(mspace_, max_allowed); + // Try the allocation. + void* ptr = AllocWithoutGrowth(num_bytes); + // Shrink back down as small as possible. + size_t footprint = mspace_footprint(mspace_); + mspace_set_footprint_limit(mspace_, footprint); + // Return the new allocation or NULL. + Object* result = reinterpret_cast<Object*>(ptr); + CHECK(result == NULL || Contains(result)); + return result; +} + +void AllocSpace::Free(Object* ptr) { +#if DEBUG_SPACES + CHECK(ptr != NULL); + CHECK(Contains(ptr)) << "Free (" << ptr << ") not in bounds of heap " << *this; +#endif + mspace_free(mspace_, ptr); +} + +void AllocSpace::FreeList(size_t num_ptrs, Object** ptrs) { +#if DEBUG_SPACES + CHECK(ptrs != NULL); + size_t num_broken_ptrs = 0; + for (size_t i = 0; i < num_ptrs; i++) { + if(!Contains(ptrs[i])) { + num_broken_ptrs++; + LOG(ERROR) << "FreeList[" << i << "] (" << ptrs[i] << ") not in bounds of heap " << *this; + } } - size_t length = RoundUp(maximum_size, kPageSize); - int prot = PROT_READ | PROT_WRITE; - UniquePtr<MemMap> mem_map(MemMap::MapAnonymous(name_.c_str(), requested_base, length, prot)); - if (mem_map.get() == NULL) { - LOG(WARNING) << "Failed to allocate " << length << " bytes for space: " << name_; - return false; + CHECK_EQ(num_broken_ptrs, 0u); +#endif + mspace_bulk_free(mspace_, reinterpret_cast<void**>(ptrs), num_ptrs); +} + +// Callback from dlmalloc when it needs to increase the footprint +extern "C" void* art_heap_morecore(void* mspace, intptr_t increment) { + AllocSpace* space = Heap::GetAllocSpace(); + if (LIKELY(space->GetMspace() == mspace)) { + return space->MoreCore(increment); + } else { + // Exhaustively search alloc spaces + const std::vector<Space*>& spaces = Heap::GetSpaces(); + for (size_t i = 0; i < spaces.size(); i++) { + if (spaces[i]->IsAllocSpace()) { + AllocSpace* space = spaces[i]->AsAllocSpace(); + if (mspace == space->GetMspace()) { + return space->MoreCore(increment); + } + } + } + LOG(FATAL) << "Unexpected call to art_heap_morecore. mspace: " << mspace + << " increment: " << increment; + return NULL; } - InitFromMemMap(mem_map.release()); - maximum_size_ = maximum_size; - size_t growth_length = RoundUp(growth_size, kPageSize); - growth_size_ = growth_size; - growth_limit_ = base_ + growth_length; - mspace_ = CreateMallocSpace(base_, initial_size, maximum_size); - if (mspace_ == NULL) { - LOG(WARNING) << "Failed to create mspace for space: " << name_; - return false; +} + +void* AllocSpace::MoreCore(intptr_t increment) { + byte* original_end = end_; + if (increment != 0) { + VLOG(heap) << "AllocSpace::MoreCore " << (increment/KB) << "KiB"; + byte* new_end = original_end + increment; + if (increment > 0) { +#if DEBUG_SPACES + // Should never be asked to increase the allocation beyond the capacity of the space. Enforced + // by mspace_set_footprint_limit. + CHECK_LE(new_end, Begin() + Capacity()); +#endif + CHECK_MEMORY_CALL(mprotect, (original_end, increment, PROT_READ | PROT_WRITE), GetSpaceName()); + } else { +#if DEBUG_SPACES + // Should never be asked for negative footprint (ie before begin) + CHECK_GT(original_end + increment, Begin()); +#endif + // Advise we don't need the pages and protect them + size_t size = -increment; + CHECK_MEMORY_CALL(madvise, (new_end, size, MADV_DONTNEED), GetSpaceName()); + CHECK_MEMORY_CALL(mprotect, (new_end, size, PROT_NONE), GetSpaceName()); + } + // Update end_ + end_ = new_end; } - VLOG(startup) << "Space::Init exiting"; - return true; + return original_end; } -void Space::InitFromMemMap(MemMap* mem_map) { - mem_map_.reset(mem_map); - base_ = mem_map_->GetAddress(); - limit_ = base_ + mem_map->GetLength(); +size_t AllocSpace::AllocationSize(const Object* obj) { + return mspace_usable_size(const_cast<void*>(reinterpret_cast<const void*>(obj))) + kChunkOverhead; } -bool Space::InitFromImage(const std::string& image_file_name) { - Runtime* runtime = Runtime::Current(); - VLOG(startup) << "Space::InitFromImage entering" - << " image_file_name=" << image_file_name; +// Call back from mspace_inspect_all returning the start and end of chunks and the bytes used, +// if used_bytes is 0 then it indicates the range isn't in use and we madvise to the system that +// we don't need it +static void DontNeed(void* start, void* end, size_t used_bytes, void* num_bytes) { + if (used_bytes == 0) { + start = reinterpret_cast<void*>(RoundUp((uintptr_t)start, kPageSize)); + end = reinterpret_cast<void*>(RoundDown((uintptr_t)end, kPageSize)); + if (end > start) { + // We have a page aligned region to madvise on + size_t length = reinterpret_cast<byte*>(end) - reinterpret_cast<byte*>(start); + CHECK_MEMORY_CALL(madvise, (start, length, MADV_DONTNEED), "trim"); + } + } +} + +void AllocSpace::Trim() { + // Trim to release memory at the end of the space + mspace_trim(mspace_, 0); + // Visit space looking for page size holes to advise we don't need + size_t num_bytes_released = 0; + mspace_inspect_all(mspace_, DontNeed, &num_bytes_released); +} + + +void AllocSpace::Walk(void(*callback)(void *start, void *end, size_t num_bytes, void* callback_arg), + void* arg) { + mspace_inspect_all(mspace_, callback, arg); +} + +size_t AllocSpace::GetFootprintLimit() { + return mspace_footprint_limit(mspace_); +} + +void AllocSpace::SetFootprintLimit(size_t new_size) { + VLOG(heap) << "AllocSpace::SetFootprintLimit " << (new_size/KB) << "KiB"; + // Compare against the actual footprint, rather than the Size(), because the heap may not have + // grown all the way to the allowed size yet. + // + size_t current_space_size = mspace_footprint(mspace_); + if (new_size < current_space_size) { + // Don't let the space grow any more. + new_size = current_space_size; + } + mspace_set_footprint_limit(mspace_, new_size); +} + +ImageSpace* Space::CreateImageSpace(const std::string& image_file_name) { + CHECK(image_file_name != NULL); + + uint64_t start_time = 0; + if (VLOG_IS_ON(heap) || VLOG_IS_ON(startup)) { + start_time = NanoTime(); + LOG(INFO) << "Space::CreateImageSpace entering" << " image_file_name=" << image_file_name; + } + UniquePtr<File> file(OS::OpenFile(image_file_name.c_str(), false)); if (file.get() == NULL) { - LOG(WARNING) << "Failed to open " << image_file_name; - return false; + LOG(ERROR) << "Failed to open " << image_file_name; + return NULL; } ImageHeader image_header; bool success = file->ReadFully(&image_header, sizeof(image_header)); if (!success || !image_header.IsValid()) { - LOG(WARNING) << "Invalid image header " << image_file_name; - return false; + LOG(ERROR) << "Invalid image header " << image_file_name; + return NULL; } - UniquePtr<MemMap> map(MemMap::MapFileAtAddress(image_header.GetImageBaseAddr(), + UniquePtr<MemMap> map(MemMap::MapFileAtAddress(image_header.GetImageBegin(), file->Length(), // TODO: selectively PROT_EXEC stubs PROT_READ | PROT_WRITE | PROT_EXEC, @@ -122,13 +278,13 @@ bool Space::InitFromImage(const std::string& image_file_name) { file->Fd(), 0)); if (map.get() == NULL) { - LOG(WARNING) << "Failed to map " << image_file_name; - return false; + LOG(ERROR) << "Failed to map " << image_file_name; + return NULL; } - CHECK_EQ(image_header.GetImageBaseAddr(), map->GetAddress()); - image_header_ = reinterpret_cast<ImageHeader*>(map->GetAddress()); - DCHECK_EQ(0, memcmp(&image_header, image_header_, sizeof(ImageHeader))); + CHECK_EQ(image_header.GetImageBegin(), map->Begin()); + DCHECK_EQ(0, memcmp(&image_header, map->Begin(), sizeof(ImageHeader))); + Runtime* runtime = Runtime::Current(); Object* jni_stub_array = image_header.GetImageRoot(ImageHeader::kJniStubArray); runtime->SetJniDlsymLookupStub(down_cast<ByteArray*>(jni_stub_array)); @@ -152,113 +308,44 @@ bool Space::InitFromImage(const std::string& image_file_name) { callee_save_method = image_header.GetImageRoot(ImageHeader::kRefsAndArgsSaveMethod); runtime->SetCalleeSaveMethod(down_cast<Method*>(callee_save_method), Runtime::kRefsAndArgs); - InitFromMemMap(map.release()); - growth_limit_ = limit_; - VLOG(startup) << "Space::InitFromImage exiting"; - return true; -} - -Object* Space::AllocWithoutGrowth(size_t num_bytes) { - DCHECK(mspace_ != NULL); - return reinterpret_cast<Object*>(mspace_calloc(mspace_, 1, num_bytes)); -} - -Object* Space::AllocWithGrowth(size_t num_bytes) { - DCHECK(mspace_ != NULL); - // Grow as much as possible within the mspace. - size_t max_allowed = growth_size_; - mspace_set_max_allowed_footprint(mspace_, max_allowed); - // Try the allocation. - void* ptr = AllocWithoutGrowth(num_bytes); - // Shrink back down as small as possible. - size_t footprint = mspace_footprint(mspace_); - mspace_set_max_allowed_footprint(mspace_, footprint); - // Return the new allocation or NULL. - return reinterpret_cast<Object*>(ptr); -} - -size_t Space::Free(void* ptr) { - DCHECK(mspace_ != NULL); - DCHECK(ptr != NULL); - size_t num_bytes = mspace_usable_size(mspace_, ptr); - mspace_free(mspace_, ptr); - return num_bytes; -} - -size_t Space::FreeList(size_t num_ptrs, void** ptrs) { - DCHECK(mspace_ != NULL); - DCHECK(ptrs != NULL); - void* merged = ptrs[0]; - size_t num_bytes = 0; - for (size_t i = 1; i < num_ptrs; i++) { - num_bytes += mspace_usable_size(mspace_, ptrs[i]); - if (mspace_merge_objects(mspace_, merged, ptrs[i]) == NULL) { - mspace_free(mspace_, merged); - merged = ptrs[i]; - } + ImageSpace* space = new ImageSpace(image_file_name, map.release()); + if (VLOG_IS_ON(heap) || VLOG_IS_ON(startup)) { + uint64_t duration_ms = (NanoTime() - start_time)/1000/1000; + LOG(INFO) << "Space::CreateImageSpace exiting (" << duration_ms << " ms) " << *space; } - CHECK(merged != NULL); - mspace_free(mspace_, merged); - return num_bytes; + return space; } -size_t Space::AllocationSize(const Object* obj) { - DCHECK(mspace_ != NULL); - return mspace_usable_size(mspace_, obj) + kChunkOverhead; -} - -void Space::DontNeed(void* start, void* end, void* num_bytes) { - start = (void*)RoundUp((uintptr_t)start, kPageSize); - end = (void*)RoundDown((uintptr_t)end, kPageSize); - if (start >= end) { - return; - } - size_t length = reinterpret_cast<byte*>(end) - reinterpret_cast<byte*>(start); - int result = madvise(start, length, MADV_DONTNEED); - if (result == -1) { - PLOG(WARNING) << "madvise failed"; - } else { - *reinterpret_cast<size_t*>(num_bytes) += length; +void ImageSpace::RecordImageAllocations(HeapBitmap* live_bitmap) const { + uint64_t start_time = 0; + if (VLOG_IS_ON(heap) || VLOG_IS_ON(startup)) { + LOG(INFO) << "ImageSpace::RecordImageAllocations entering"; + start_time = NanoTime(); } -} - -void Space::Trim() { - CHECK(mspace_ != NULL); - mspace_trim(mspace_, 0); - size_t num_bytes_released = 0; - mspace_walk_free_pages(mspace_, DontNeed, &num_bytes_released); -} - -void Space::Walk(void(*callback)(const void*, size_t, const void*, size_t, void*), void* arg) { - if (mspace_ != NULL) { - mspace_walk_heap(mspace_, callback, arg); + DCHECK(!Runtime::Current()->IsStarted()); + CHECK(live_bitmap != NULL); + byte* current = Begin() + RoundUp(sizeof(ImageHeader), kObjectAlignment); + byte* end = End(); + while (current < end) { + DCHECK_ALIGNED(current, kObjectAlignment); + const Object* obj = reinterpret_cast<const Object*>(current); + live_bitmap->Set(obj); + current += RoundUp(obj->SizeOf(), kObjectAlignment); } -} - -size_t Space::GetMaxAllowedFootprint() { - DCHECK(mspace_ != NULL); - return mspace_max_allowed_footprint(mspace_); -} - -void Space::SetMaxAllowedFootprint(size_t limit) { - DCHECK(mspace_ != NULL); - - // Compare against the actual footprint, rather than the - // max_allowed, because the heap may not have grown all the - // way to the allowed size yet. - // - size_t current_space_size = mspace_footprint(mspace_); - if (limit < current_space_size) { - // Don't let the space grow any more. - mspace_set_max_allowed_footprint(mspace_, current_space_size); - } else { - // Let the heap grow to the requested limit. - mspace_set_max_allowed_footprint(mspace_, limit); + if (VLOG_IS_ON(heap) || VLOG_IS_ON(startup)) { + uint64_t duration_ms = (NanoTime() - start_time)/1000/1000; + LOG(INFO) << "ImageSpace::RecordImageAllocations exiting (" << duration_ms << " ms)"; } } -void Space::Grow(size_t new_size) { - UNIMPLEMENTED(FATAL); +std::ostream& operator<<(std::ostream& os, const Space& space) { + os << (space.IsImageSpace() ? "Image" : "Alloc") << "Space[" + << "begin=" << reinterpret_cast<void*>(space.Begin()) + << ",end=" << reinterpret_cast<void*>(space.End()) + << ",size=" << (space.Size()/KB) << "KiB" + << ",capacity=" << (space.Capacity()/KB) << "KiB" + << ",name=\"" << space.GetSpaceName() << "\"]"; + return os; } } // namespace art diff --git a/src/space.h b/src/space.h index be7dfdc709..a932d7b126 100644 --- a/src/space.h +++ b/src/space.h @@ -23,135 +23,217 @@ #include "globals.h" #include "image.h" #include "macros.h" +#include "dlmalloc.h" #include "mem_map.h" -#include "mspace.h" namespace art { +class AllocSpace; +class ImageSpace; class Object; // A space contains memory allocated for managed objects. class Space { public: - // Create a Space with the requested sizes. The requested + // Create a AllocSpace with the requested sizes. The requested // base address is not guaranteed to be granted, if it is required, - // the caller should call GetBase on the returned space to confirm + // the caller should call Begin on the returned space to confirm // the request was granted. - static Space* Create(const std::string& name, size_t initial_size, - size_t maximum_size, size_t growth_size, byte* requested_base); + static AllocSpace* CreateAllocSpace(const std::string& name, size_t initial_size, + size_t growth_limit, size_t capacity, + byte* requested_begin); // create a Space from an image file. cannot be used for future allocation or collected. - static Space* CreateFromImage(const std::string& image); + static ImageSpace* CreateImageSpace(const std::string& image); - ~Space(); + virtual ~Space() {} - Object* AllocWithGrowth(size_t num_bytes); + const std::string& GetSpaceName() const { + return name_; + } - Object* AllocWithoutGrowth(size_t num_bytes); + // Address at which the space begins + byte* Begin() const { + return begin_; + } - size_t Free(void* ptr); + // Address at which the space ends, which may vary as the space is filled + byte* End() const { + return end_; + } - size_t FreeList(size_t num_ptrs, void** ptrs); + // Is object within this space? + bool Contains(const Object* obj) const { + const byte* byte_ptr = reinterpret_cast<const byte*>(obj); + return Begin() <= byte_ptr && byte_ptr < End(); + } - void Trim(); + // Current size of space + size_t Size() const { + return End() - Begin(); + } - size_t GetMaxAllowedFootprint(); - void SetMaxAllowedFootprint(size_t limit); + // Maximum size of space + virtual size_t Capacity() const { + return mem_map_->Size(); + } - void Grow(size_t num_bytes); + // Support for having an impediment (GrowthLimit) removed from the space + virtual size_t UnimpededCapacity() const { + return Capacity(); + } - byte* GetBase() const { - return base_; + ImageSpace* AsImageSpace() { + DCHECK(IsImageSpace()); + return down_cast<ImageSpace*>(this); } - byte* GetLimit() const { - return growth_limit_; + AllocSpace* AsAllocSpace() { + DCHECK(IsAllocSpace()); + return down_cast<AllocSpace*>(this); } - byte* GetMax() const { - return base_ + maximum_size_; + virtual bool IsAllocSpace() const = 0; + virtual bool IsImageSpace() const = 0; + + protected: + Space(const std::string& name, MemMap* mem_map, byte* end) : name_(name), mem_map_(mem_map), + begin_(mem_map->Begin()), end_(end) {} + + std::string name_; + // Underlying storage of the space + UniquePtr<MemMap> mem_map_; + + // The beginning of the storage for fast access (always equals mem_map_->GetAddress()) + byte* const begin_; + + // Current end of the space + byte* end_; + + DISALLOW_COPY_AND_ASSIGN(Space); +}; + +std::ostream& operator<<(std::ostream& os, const Space& space); + +// An alloc space is a space where objects may be allocated and garbage collected. +class AllocSpace : public Space { + public: + // Allocate num_bytes without allowing the underlying mspace to grow + Object* AllocWithGrowth(size_t num_bytes); + + // Allocate num_bytes allowing the underlying mspace to grow + Object* AllocWithoutGrowth(size_t num_bytes); + + // Return the storage space required by obj + size_t AllocationSize(const Object* obj); + + void Free(Object* ptr); + + void FreeList(size_t num_ptrs, Object** ptrs); + + void* MoreCore(intptr_t increment); + + void* GetMspace() const { + return mspace_; } - const std::string& GetName() const { - return name_; + // Hand unused pages back to the system + void Trim(); + + // Perform a mspace_inspect_all which calls back for each allocation chunk. The chunk may not be + // in use, indicated by num_bytes equaling zero + void Walk(void(*callback)(void *start, void *end, size_t num_bytes, void* callback_arg), + void* arg); + + // Returns the number of bytes that the heap is allowed to obtain from the system via MoreCore + size_t GetFootprintLimit(); + + // Set the maximum number of bytes that the heap is allowed to obtain from the system via MoreCore + void SetFootprintLimit(size_t limit); + + // Removes the fork time growth limit (fence on capacity), allowing the application to allocate + // up to the maximum heap size. + void ClearGrowthLimit() { + growth_limit_ = UnimpededCapacity(); } - size_t Size() const { - return growth_limit_ - base_; + // Override capacity so that we only return the possibly limited capacity + virtual size_t Capacity() const { + return growth_limit_; } - bool IsImageSpace() const { - return (image_header_ != NULL); + virtual size_t UnimpededCapacity() const { + return mem_map_->End() - mem_map_->Begin(); } - const ImageHeader& GetImageHeader() const { - CHECK(IsImageSpace()); - return *image_header_; + virtual bool IsAllocSpace() const { + return true; } - const std::string& GetImageFilename() const { - CHECK(IsImageSpace()); - return name_; + virtual bool IsImageSpace() const { + return false; } - size_t AllocationSize(const Object* obj); + private: + friend class Space; - void ClearGrowthLimit() { - CHECK_GE(maximum_size_, growth_size_); - CHECK_GE(limit_, growth_limit_); - growth_size_ = maximum_size_; - growth_limit_ = limit_; + AllocSpace(const std::string& name, MemMap* mem_map, void* mspace, byte* end, + size_t growth_limit) : + Space(name, mem_map, end), mspace_(mspace), growth_limit_(growth_limit) { + CHECK(mspace != NULL); } - void Walk(void(*callback)(const void*, size_t, const void*, size_t, void*), void* arg); + bool Init(size_t initial_size, size_t maximum_size, size_t growth_size, byte* requested_base); - bool Contains(const Object* obj) const { - const byte* byte_ptr = reinterpret_cast<const byte*>(obj); - return GetBase() <= byte_ptr && byte_ptr < GetLimit(); - } + static void* CreateMallocSpace(void* base, size_t initial_size, size_t maximum_size); - private: // The boundary tag overhead. static const size_t kChunkOverhead = kWordSize; - // create a Space from an existing memory mapping, taking ownership of the address space. - static Space* Create(MemMap* mem_map); - - explicit Space(const std::string& name) - : name_(name), mspace_(NULL), maximum_size_(0), growth_size_(0), - image_header_(NULL), base_(0), limit_(0), growth_limit_(0) { - } - - // Initializes the space and underlying storage. - bool Init(size_t initial_size, size_t maximum_size, size_t growth_size, byte* requested_base); + // Underlying malloc space + void* const mspace_; - // Initializes the space from existing storage, taking ownership of the storage. - void InitFromMemMap(MemMap* map); + // The capacity of the alloc space until such time that ClearGrowthLimit is called. + // The underlying mem_map_ controls the maximum size we allow the heap to grow to. The growth + // limit is a value <= to the mem_map_ capacity used for ergonomic reasons because of the zygote. + // Prior to forking the zygote the heap will have a maximally sized mem_map_ but the growth_limit_ + // will be set to a lower value. The growth_limit_ is used as the capacity of the alloc_space_, + // however, capacity normally can't vary. In the case of the growth_limit_ it can be cleared + // one time by a call to ClearGrowthLimit. + size_t growth_limit_; - // Initializes the space from an image file - bool InitFromImage(const std::string& image_file_name); + DISALLOW_COPY_AND_ASSIGN(AllocSpace); +}; - void* CreateMallocSpace(void* base, size_t initial_size, size_t maximum_size); +// An image space is a space backed with a memory mapped image +class ImageSpace : public Space { + public: + const ImageHeader& GetImageHeader() const { + return *reinterpret_cast<ImageHeader*>(Begin()); + } - static void DontNeed(void* start, void* end, void* num_bytes); + const std::string& GetImageFilename() const { + return name_; + } - std::string name_; + // Mark the objects defined in this space in the given live bitmap + void RecordImageAllocations(HeapBitmap* live_bitmap) const; - // TODO: have a Space subclass for non-image Spaces with mspace_ and maximum_size_ - void* mspace_; - size_t maximum_size_; - size_t growth_size_; + virtual bool IsAllocSpace() const { + return false; + } - // TODO: have a Space subclass for image Spaces with image_header_ - ImageHeader* image_header_; + virtual bool IsImageSpace() const { + return true; + } - UniquePtr<MemMap> mem_map_; + private: + friend class Space; - byte* base_; - byte* limit_; - byte* growth_limit_; + ImageSpace(const std::string& name, MemMap* mem_map) : + Space(name, mem_map, mem_map->End()) {} - DISALLOW_COPY_AND_ASSIGN(Space); + DISALLOW_COPY_AND_ASSIGN(ImageSpace); }; } // namespace art diff --git a/src/space_test.cc b/src/space_test.cc index c54a58414d..f6d119110b 100644 --- a/src/space_test.cc +++ b/src/space_test.cc @@ -13,67 +13,71 @@ class SpaceTest : public CommonTest {}; TEST_F(SpaceTest, Init) { { // Init < max == growth - UniquePtr<Space> space(Space::Create("test", 16 * MB, 32 * MB, 32 * MB, NULL)); + UniquePtr<Space> space(Space::CreateAllocSpace("test", 16 * MB, 32 * MB, 32 * MB, NULL)); EXPECT_TRUE(space.get() != NULL); } { // Init == max == growth - UniquePtr<Space> space(Space::Create("test", 16 * MB, 16 * MB, 16 * MB, NULL)); + UniquePtr<Space> space(Space::CreateAllocSpace("test", 16 * MB, 16 * MB, 16 * MB, NULL)); EXPECT_TRUE(space.get() != NULL); } { // Init > max == growth - UniquePtr<Space> space(Space::Create("test", 32 * MB, 16 * MB, 16 * MB, NULL)); + UniquePtr<Space> space(Space::CreateAllocSpace("test", 32 * MB, 16 * MB, 16 * MB, NULL)); EXPECT_TRUE(space.get() == NULL); } { // Growth == init < max - UniquePtr<Space> space(Space::Create("test", 16 * MB, 32 * MB, 16 * MB, NULL)); + UniquePtr<Space> space(Space::CreateAllocSpace("test", 16 * MB, 16 * MB, 32 * MB, NULL)); EXPECT_TRUE(space.get() != NULL); } { // Growth < init < max - UniquePtr<Space> space(Space::Create("test", 16 * MB, 32 * MB, 8 * MB, NULL)); + UniquePtr<Space> space(Space::CreateAllocSpace("test", 16 * MB, 8 * MB, 32 * MB, NULL)); EXPECT_TRUE(space.get() == NULL); } { // Init < growth < max - UniquePtr<Space> space(Space::Create("test", 8 * MB, 32 * MB, 16 * MB, NULL)); + UniquePtr<Space> space(Space::CreateAllocSpace("test", 8 * MB, 16 * MB, 32 * MB, NULL)); EXPECT_TRUE(space.get() != NULL); } { // Init < max < growth - UniquePtr<Space> space(Space::Create("test", 8 * MB, 16 * MB, 32 * MB, NULL)); + UniquePtr<Space> space(Space::CreateAllocSpace("test", 8 * MB, 32 * MB, 16 * MB, NULL)); EXPECT_TRUE(space.get() == NULL); } } TEST_F(SpaceTest, AllocAndFree) { - UniquePtr<Space> space(Space::Create("test", 4 * MB, 16 * MB, 16 * MB, NULL)); - ASSERT_TRUE(space.get() != NULL); + AllocSpace* space(Space::CreateAllocSpace("test", 4 * MB, 16 * MB, 16 * MB, NULL)); + ASSERT_TRUE(space != NULL); + + // Make space findable to the heap, will also delete class when runtime is cleaned up + Heap::AddSpace(space); // Succeeds, fits without adjusting the max allowed footprint. - void* ptr1 = space->AllocWithoutGrowth(1 * MB); + Object* ptr1 = space->AllocWithoutGrowth(1 * MB); EXPECT_TRUE(ptr1 != NULL); // Fails, requires a higher allowed footprint. - void* ptr2 = space->AllocWithoutGrowth(8 * MB); + Object* ptr2 = space->AllocWithoutGrowth(8 * MB); EXPECT_TRUE(ptr2 == NULL); // Succeeds, adjusts the footprint. - void* ptr3 = space->AllocWithGrowth(8 * MB); + Object* ptr3 = space->AllocWithGrowth(8 * MB); EXPECT_TRUE(ptr3 != NULL); // Fails, requires a higher allowed footprint. - void* ptr4 = space->AllocWithoutGrowth(8 * MB); + Object* ptr4 = space->AllocWithoutGrowth(8 * MB); EXPECT_FALSE(ptr4 != NULL); // Also fails, requires a higher allowed footprint. - void* ptr5 = space->AllocWithGrowth(8 * MB); + Object* ptr5 = space->AllocWithGrowth(8 * MB); EXPECT_FALSE(ptr5 != NULL); // Release some memory. - size_t free3 = space->Free(ptr3); + size_t free3 = space->AllocationSize(ptr3); + space->Free(ptr3); EXPECT_LE(8U * MB, free3); // Succeeds, now that memory has been freed. @@ -81,7 +85,8 @@ TEST_F(SpaceTest, AllocAndFree) { EXPECT_TRUE(ptr6 != NULL); // Final clean up. - size_t free1 = space->Free(ptr1); + size_t free1 = space->AllocationSize(ptr1); + space->Free(ptr1); EXPECT_LE(1U * MB, free1); } diff --git a/src/thread.cc b/src/thread.cc index 772286675f..1a534f1171 100644 --- a/src/thread.cc +++ b/src/thread.cc @@ -43,6 +43,7 @@ #include "runtime_support.h" #include "ScopedLocalRef.h" #include "scoped_jni_thread_state.h" +#include "space.h" #include "stack.h" #include "stack_indirect_reference_table.h" #include "thread_list.h" @@ -68,7 +69,7 @@ static Method* gThreadGroup_removeThread = NULL; static Method* gUncaughtExceptionHandler_uncaughtException = NULL; void Thread::InitCardTable() { - card_table_ = Heap::GetCardTable()->GetBiasedBase(); + card_table_ = Heap::GetCardTable()->GetBiasedBegin(); } void Thread::InitFunctionPointers() { @@ -357,7 +358,7 @@ void Thread::InitStackHwm() { void* temp_stack_base; CHECK_PTHREAD_CALL(pthread_attr_getstack, (&attributes, &temp_stack_base, &stack_size_), __FUNCTION__); - stack_base_ = reinterpret_cast<byte*>(temp_stack_base); + stack_begin_ = reinterpret_cast<byte*>(temp_stack_base); if (stack_size_ <= kStackOverflowReservedBytes) { LOG(FATAL) << "Attempt to attach a thread with a too-small stack (" << stack_size_ << " bytes)"; diff --git a/src/thread.h b/src/thread.h index 856fd5cb7d..d612f62def 100644 --- a/src/thread.h +++ b/src/thread.h @@ -419,26 +419,26 @@ class PACKED Thread { // Size of stack less any space reserved for stack overflow size_t GetStackSize() { - return stack_size_ - (stack_end_ - stack_base_); + return stack_size_ - (stack_end_ - stack_begin_); } // Set the stack end to that to be used during a stack overflow void SetStackEndForStackOverflow() { // During stack overflow we allow use of the full stack - if (stack_end_ == stack_base_) { + if (stack_end_ == stack_begin_) { DumpStack(std::cerr); LOG(FATAL) << "Need to increase kStackOverflowReservedBytes (currently " << kStackOverflowReservedBytes << ")"; } - stack_end_ = stack_base_; + stack_end_ = stack_begin_; } // Set the stack end to that to be used during regular execution void ResetDefaultStackEnd() { // Our stacks grow down, so we want stack_end_ to be near there, but reserving enough room // to throw a StackOverflowError. - stack_end_ = stack_base_ + kStackOverflowReservedBytes; + stack_end_ = stack_begin_ + kStackOverflowReservedBytes; } static ThreadOffset StackEndOffset() { @@ -578,7 +578,7 @@ class PACKED Thread { size_t stack_size_; // The "lowest addressable byte" of the stack - byte* stack_base_; + byte* stack_begin_; // A linked list (of stack allocated records) recording transitions from // native to managed code. diff --git a/src/zip_archive.cc b/src/zip_archive.cc index 73728a29b3..fd7086f599 100644 --- a/src/zip_archive.cc +++ b/src/zip_archive.cc @@ -121,7 +121,7 @@ off_t ZipEntry::GetDataOffset() { } static bool CopyFdToMemory(MemMap& mem_map, int in, size_t count) { - uint8_t* dst = mem_map.GetAddress(); + uint8_t* dst = mem_map.Begin(); std::vector<uint8_t> buf(kBufSize); while (count != 0) { size_t bytes_to_read = (count > kBufSize) ? kBufSize : count; @@ -134,7 +134,7 @@ static bool CopyFdToMemory(MemMap& mem_map, int in, size_t count) { dst += bytes_to_read; count -= bytes_to_read; } - DCHECK_EQ(dst, mem_map.GetLimit()); + DCHECK_EQ(dst, mem_map.End()); return true; } @@ -165,7 +165,7 @@ class ZStream { }; static bool InflateToMemory(MemMap& mem_map, int in, size_t uncompressed_length, size_t compressed_length) { - uint8_t* dst = mem_map.GetAddress(); + uint8_t* dst = mem_map.Begin(); UniquePtr<uint8_t[]> read_buf(new uint8_t[kBufSize]); UniquePtr<uint8_t[]> write_buf(new uint8_t[kBufSize]); if (read_buf.get() == NULL || write_buf.get() == NULL) { @@ -235,7 +235,7 @@ static bool InflateToMemory(MemMap& mem_map, int in, size_t uncompressed_length, return false; } - DCHECK_EQ(dst, mem_map.GetLimit()); + DCHECK_EQ(dst, mem_map.End()); return true; } @@ -438,8 +438,8 @@ bool ZipArchive::MapCentralDirectory() { } bool ZipArchive::Parse() { - const byte* cd_ptr = dir_map_->GetAddress(); - size_t cd_length = dir_map_->GetLength(); + const byte* cd_ptr = dir_map_->Begin(); + size_t cd_length = dir_map_->Size(); // Walk through the central directory, adding entries to the hash // table and verifying values. diff --git a/test/061-out-of-memory/src/Main.java b/test/061-out-of-memory/src/Main.java index b5999b34b3..c04d41f3fa 100644 --- a/test/061-out-of-memory/src/Main.java +++ b/test/061-out-of-memory/src/Main.java @@ -46,15 +46,15 @@ public class Main { /* Just shy of the typical max heap size so that it will actually * try to allocate it instead of short-circuiting. * - * TODO: stop assuming the VM defaults to 16MB max + * TODO: stop assuming the VM defaults to 64MB max */ - final int SIXTEEN_MB = (16 * 1024 * 1024 - 32); + final int SIXTY_FOUR_MB = (64 * 1024 * 1024 - 32); Boolean sawEx = false; byte a[]; try { - a = new byte[SIXTEEN_MB]; + a = new byte[SIXTY_FOUR_MB]; } catch (OutOfMemoryError oom) { //Log.i(TAG, "HeapTest/OomeLarge caught " + oom); sawEx = true; @@ -72,10 +72,10 @@ public class Main { * list afterwards. Even if we null out list when we're done, the conservative * GC may see a stale pointer to it in a register. * - * TODO: stop assuming the VM defaults to 16MB max + * TODO: stop assuming the VM defaults to 64MB max */ private static boolean testOomeSmallInternal() { - final int SIXTEEN_MB = (16 * 1024 * 1024); + final int SIXTY_FOUR_MB = (64 * 1024 * 1024); final int LINK_SIZE = 6 * 4; // estimated size of a LinkedList's node LinkedList<Object> list = new LinkedList<Object>(); @@ -86,7 +86,7 @@ public class Main { while (objSize >= LINK_SIZE) { boolean sawEx = false; try { - for (int i = 0; i < SIXTEEN_MB / objSize; i++) { + for (int i = 0; i < SIXTY_FOUR_MB / objSize; i++) { list.add((Object)new byte[objSize]); } } catch (OutOfMemoryError oom) { |