/* Alternative malloc implementation for multiple threads without
lock contention based on dlmalloc. (C) 2005-2012 Niall Douglas

Boost Software License - Version 1.0 - August 17th, 2003

Permission is hereby granted, free of charge, to any person or organization
obtaining a copy of the software and accompanying documentation covered by
this license (the "Software") to use, reproduce, display, distribute,
execute, and transmit the Software, and to prepare derivative works of the
Software, and to permit third-parties to whom the Software is furnished to
do so, all subject to the following:

The copyright notices in the Software and this entire statement, including
the above license grant, this restriction and the following disclaimer,
must be included in all copies of the Software, in whole or in part, and
all derivative works of the Software, unless such copies or derivative
works are solely in the form of machine-executable object code generated by
a source language processor.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.
*/

#if 0 /* Effectively makes nedmalloc = dlmalloc */
#define THREADCACHEMAX 0
#define DEFAULT_GRANULARITY 65536
#define DEFAULTMAXTHREADSINPOOL 1
#endif

#ifdef _MSC_VER
/* Enable full aliasing on MSVC */
/*#pragma optimize("a", on)*/
/*#pragma optimize("g", off)*/

#pragma warning(push)
#pragma warning(disable:4100)	/* unreferenced formal parameter */
#pragma warning(disable:4127)	/* conditional expression is constant */
#pragma warning(disable:4232)	/* address of dllimport is not static, identity not guaranteed */
#pragma warning(disable:4706)	/* assignment within conditional expression */

#define _CRT_SECURE_NO_WARNINGS 1	/* Don't care about MSVC warnings on POSIX functions */
#include <stdio.h>
#define fopen(f, m) _fsopen((f), (m), 0x40/*_SH_DENYNO*/)	/* Have Windows let other programs view the log file as it is written */
#ifndef UNICODE
#define UNICODE					/* Turn on windows unicode support */
#endif
#else
#include <stdio.h>
#endif

/*#define NEDMALLOC_DEBUG 1*/
/*#define ENABLE_LOGGING 7
#define NEDMALLOC_TESTLOGENTRY(tc, np, type, mspace, size, mem, alignment, flags, returned) (((type)&ENABLE_LOGGING)&&((size)>16*1024))
#define NEDMALLOC_STACKBACKTRACEDEPTH 16*/
/*#define NEDMALLOC_FORCERESERVE(p, mem, size) (((size)>=(256*1024)) ? M2_RESERVE_MULT(8) : 0)*/
/*#define WIN32_DIRECT_USE_FILE_MAPPINGS 0*/

/*#define NEDMALLOC_DEBUG 1*/

/*#define FULLSANITYCHECKS*/

/*#define FORCEINLINE*/

/* There is only support for the user mode page allocator on Windows at present */
#if !defined(ENABLE_USERMODEPAGEALLOCATOR)
#define ENABLE_USERMODEPAGEALLOCATOR 0
#endif

/* If link time code generation is on, don't force or prevent inlining */
#if defined(_MSC_VER) && defined(NEDMALLOC_DLL_EXPORTS)
#define FORCEINLINE
#define NOINLINE
#endif

#include "nedmalloc.h"
#include <errno.h>
#ifdef HAVE_VALGRIND
#include <valgrind/valgrind.h>
#include <valgrind/memcheck.h>
#endif
#if defined(WIN32)
 #include <malloc.h>
#else
 #if defined(__cplusplus)
extern "C"
 #else
extern
 #endif
 #if defined(__linux__) || defined(__FreeBSD__)
/* Sadly we can't include <malloc.h> as it causes a redefinition error */
size_t malloc_usable_size(void *);
 #elif defined(__APPLE__)
  #if TARGET_OS_IPHONE
   #include <malloc/malloc.h>
  #else
   #include <malloc.h>
  #endif
 #else
  #error Do not know what to do here
 #endif
#endif

#if USE_ALLOCATOR==1
 #define MSPACES 1
 #define ONLY_MSPACES 1
#endif
#define USE_DL_PREFIX 1
#define USE_RECURSIVE_LOCKS 1
#ifndef USE_LOCKS
 #define USE_LOCKS 1
#endif
#define FOOTERS 1           /* Need to enable footers so frees lock the right mspace */
#define INSECURE 0          /* nedblkmstate works a lot better with magic enabled */
#ifndef NEDMALLOC_DEBUG
 #if defined(DEBUG) || defined(_DEBUG)
  #define NEDMALLOC_DEBUG 1
 #else
  #define NEDMALLOC_DEBUG 0
 #endif
#endif
/* We need to consistently define DEBUG=0|1, _DEBUG and NDEBUG for dlmalloc */
#if !defined(DEBUG) && !defined(NDEBUG)
 #ifdef __GNUC__
  #warning DEBUG may not be defined but without NDEBUG being defined allocator will run with assert checking! Define NDEBUG to run at full speed.
 #elif defined(_MSC_VER)
  #pragma message(__FILE__ ": WARNING: DEBUG may not be defined but without NDEBUG being defined allocator will run with assert checking! Define NDEBUG to run at full speed.")
 #endif
#endif
#undef DEBUG
#undef _DEBUG
#if NEDMALLOC_DEBUG
 #define _DEBUG
 #define DEBUG 1
#else
 #define DEBUG 0
#endif
#ifdef NDEBUG               /* Disable assert checking on release builds */
 #undef DEBUG
 #undef _DEBUG
#endif
/* The default of 64Kb means we spend too much time kernel-side */
#ifndef DEFAULT_GRANULARITY
 #define DEFAULT_GRANULARITY (1*1024*1024)
 #if DEBUG
  #define DEFAULT_GRANULARITY_ALIGNED
 #endif
#endif
/*#define USE_SPIN_LOCKS 0*/

#if ENABLE_USERMODEPAGEALLOCATOR
extern int OSHavePhysicalPageSupport(void);
extern void *userpage_malloc(size_t toallocate, unsigned flags);
extern int userpage_free(void *mem, size_t size);
extern void *userpage_realloc(void *mem, size_t oldsize, size_t newsize, int flags, unsigned flags2);

#define USERPAGE_TOPDOWN                   (M2_CUSTOM_FLAGS_BEGIN<<0)
#define USERPAGE_NOCOMMIT                  (M2_CUSTOM_FLAGS_BEGIN<<1)

/* This can provide a very significant speed boost */
#undef MMAP_CLEARS
#define MMAP_CLEARS 0

#define MUNMAP(h, a, s)                    (!OSHavePhysicalPageSupport() ? MUNMAP_DEFAULT((h), (a), (s)) : userpage_free((a), (s)))
#define MMAP(s, f)                         (!OSHavePhysicalPageSupport() ? MMAP_DEFAULT((s)) : userpage_malloc((s), (f)))
#define MREMAP(addr, osz, nsz, mv)         (!OSHavePhysicalPageSupport() ? MREMAP_DEFAULT((addr), (osz), (nsz), (mv)) : userpage_realloc((addr), (osz), (nsz), (mv), 0))
#define DIRECT_MMAP(h, s, f)               (!OSHavePhysicalPageSupport() ? DIRECT_MMAP_DEFAULT((h), (s), (f)) : userpage_malloc((s), (f)|USERPAGE_TOPDOWN))
#define DIRECT_MREMAP(h, a, os, ns, f, f2) (!OSHavePhysicalPageSupport() ? DIRECT_MREMAP_DEFAULT((h), (a), (os), (ns), (f), (f2)) : userpage_realloc((a), (os), (ns), (f), (f2)|USERPAGE_TOPDOWN))

/*#undef MREMAP
#define MREMAP(addr, osz, nsz, mv)         (!OSHavePhysicalPageSupport() ? MREMAP_DEFAULT((addr), (osz), (nsz), (mv)) : MFAIL)*/
/*#undef DIRECT_MREMAP
#define DIRECT_MREMAP(h, a, os, ns, f, f2) (!OSHavePhysicalPageSupport() ? DIRECT_MREMAP_DEFAULT((h), (a), (os), (ns), (f), (f2)) : MFAIL)*/

#endif
#include "malloc.c.h"
#ifdef NDEBUG               /* Disable assert checking on release builds */
 #undef DEBUG
#endif

/* The default number of threads allowed into a pool at once */
#ifndef DEFAULTMAXTHREADSINPOOL
#define DEFAULTMAXTHREADSINPOOL 4
#endif
/* The maximum size to be allocated from the thread cache */
#ifndef THREADCACHEMAX
#define THREADCACHEMAX 8192
#elif THREADCACHEMAX && !defined(THREADCACHEMAXBINS)
 #ifdef __GNUC__
  #warning If you are changing THREADCACHEMAX, do you also need to change THREADCACHEMAXBINS=(topbitpos(THREADCACHEMAX)-4)?
 #elif defined(_MSC_VER)
  #pragma message(__FILE__ ": WARNING: If you are changing THREADCACHEMAX, do you also need to change THREADCACHEMAXBINS=(topbitpos(THREADCACHEMAX)-4)?")
 #endif
#endif
/* The maximum concurrent threads in a pool possible */
#ifndef MAXTHREADSINPOOL
#define MAXTHREADSINPOOL 16
#endif
/* The maximum number of threadcaches which can be allocated */
#ifndef THREADCACHEMAXCACHES
#define THREADCACHEMAXCACHES 256
#endif
#ifndef THREADCACHEMAXBINS
#if 0
/* The number of cache entries for finer grained bins. This is (topbitpos(THREADCACHEMAX)-4)*2 */
#define THREADCACHEMAXBINS ((13-4)*2)
#else
/* The number of cache entries. This is (topbitpos(THREADCACHEMAX)-4) */
#define THREADCACHEMAXBINS (13-4)
#endif
#endif
/* Point at which the free space in a thread cache is garbage collected */
#ifndef THREADCACHEMAXFREESPACE
#define THREADCACHEMAXFREESPACE (1024*1024)
#endif
/* NEDMALLOC_FORCERESERVE is used to force malloc2 flags for normal malloc, calloc et al */
#ifndef NEDMALLOC_FORCERESERVE
#define NEDMALLOC_FORCERESERVE(p, mem, size) 0
#endif
/* ENABLE_LOGGING is a bitmask of what events to log */
#if ENABLE_LOGGING
#ifndef NEDMALLOC_LOGFILE
#define NEDMALLOC_LOGFILE "nedmalloc.csv"
#endif
#endif
/* NEDMALLOC_TESTLOGENTRY returns non-zero if the entry should be logged */
#ifndef NEDMALLOC_TESTLOGENTRY
#define NEDMALLOC_TESTLOGENTRY(tc, np, type, mspace, size, mem, alignment, flags, returned) ((type)&ENABLE_LOGGING)
#endif
/* NEDMALLOC_STACKBACKTRACEDEPTH has the logger store a stack backtrace per logged item. Slow! */
#ifndef NEDMALLOC_STACKBACKTRACEDEPTH
#define NEDMALLOC_STACKBACKTRACEDEPTH 0
#endif
#if NEDMALLOC_STACKBACKTRACEDEPTH
#include "Dbghelp.h"
#include "psapi.h"
#pragma comment(lib, "dbghelp.lib")
#pragma comment(lib, "psapi.lib")
#endif
#define NM_FLAGS_MASK (M2_FLAGS_MASK&~M2_ZERO_MEMORY)

#if USE_LOCKS
#ifdef WIN32
 #define TLSVAR			DWORD
 #define TLSALLOC(k)	(*(k)=TlsAlloc(), TLS_OUT_OF_INDEXES==*(k))
 #define TLSFREE(k)		(!TlsFree(k))
 #define TLSGET(k)		TlsGetValue(k)
 #define TLSSET(k, a)	(!TlsSetValue(k, a))
 #ifdef DEBUG
static LPVOID ChkedTlsGetValue(DWORD idx)
{
	LPVOID ret=TlsGetValue(idx);
	assert(S_OK==GetLastError());
	return ret;
}
  #undef TLSGET
  #define TLSGET(k) ChkedTlsGetValue(k)
 #endif
#else
 #define TLSVAR			pthread_key_t
 #define TLSALLOC(k)	pthread_key_create(k, 0)
 #define TLSFREE(k)		pthread_key_delete(k)
 #define TLSGET(k)		pthread_getspecific(k)
 #define TLSSET(k, a)	pthread_setspecific(k, a)
#endif
#else /* Probably if you're not using locks then you don't want ANY pthread stuff at all */
 #define TLSVAR			void *
 #define TLSALLOC(k)	(*k=0)
 #define TLSFREE(k)		(k=0)
 #define TLSGET(k)		k
 #define TLSSET(k, a)	(k=a, 0)
#endif

#if ENABLE_USERMODEPAGEALLOCATOR
#include "usermodepageallocator.c"
#endif

#if defined(__cplusplus)
#if !defined(NO_NED_NAMESPACE)
namespace nedalloc {
#else
extern "C" {
#endif
#endif

#if USE_ALLOCATOR==0
static void *unsupported_operation(const char *opname) THROWSPEC
{
	fprintf(stderr, "nedmalloc: The operation %s is not supported under this build configuration\n", opname);
	abort();
	return 0;
}
static size_t mspacecounter=(size_t) 0xdeadbeef;
#endif
#ifndef ENABLE_FAST_HEAP_DETECTION
static void *RESTRICT leastusedaddress;
static size_t largestusedblock;
#endif
/* Used to redirect system allocator ops if needed */
extern void *(*sysmalloc)(size_t);
extern void *(*syscalloc)(size_t, size_t);
extern void *(*sysrealloc)(void *, size_t);
extern void (*sysfree)(void *);
extern size_t (*sysblksize)(void *);

#if !defined(REPLACE_SYSTEM_ALLOCATOR) || (!defined(_MSC_VER) && !defined(__MINGW32__))
void *(*sysmalloc)(size_t)=malloc;
void *(*syscalloc)(size_t, size_t)=calloc;
void *(*sysrealloc)(void *, size_t)=realloc;
void (*sysfree)(void *)=free;
size_t (*sysblksize)(void *)=
#if defined(_MSC_VER) || defined(__MINGW32__)
	/* This is the MSVCRT equivalent */
	_msize;
#elif defined(__linux__) || defined(__FreeBSD__)
	/* This is the glibc/ptmalloc2/dlmalloc/BSD equivalent.  */
	malloc_usable_size;
#elif defined(__APPLE__)
	/* This is the Apple BSD libc equivalent.  */
	(size_t (*)(void *)) malloc_size;
#else
#error Cannot tolerate the memory allocator of an unknown system!
#endif
#else
/* Remove the MSVCRT dependency on the memory functions */
void *(*sysmalloc)(size_t);
void *(*syscalloc)(size_t, size_t);
void *(*sysrealloc)(void *, size_t);
void (*sysfree)(void *);
size_t (*sysblksize)(void *);
#endif

static FORCEINLINE NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void *CallMalloc(void *RESTRICT mspace, size_t size, size_t alignment, unsigned flags) THROWSPEC
{
	void *RESTRICT ret=0;
#if USE_MAGIC_HEADERS
	size_t _alignment=alignment;
	size_t *_ret=0;
	size_t bytes=size+alignment+3*sizeof(size_t);
	/* Avoid addition overflow. */
	if(bytes<size)
		return 0;
	size=bytes;
	_alignment=0;
#endif
#if USE_ALLOCATOR==0
	ret=(flags & M2_ZERO_MEMORY) ? syscalloc(1, size) : sysmalloc(size);	/* magic headers takes care of alignment */
#elif USE_ALLOCATOR==1
	ret=mspace_malloc2((mstate) mspace, size, alignment, flags);
#ifdef HAVE_VALGRIND
	if(ret) VALGRIND_MEMPOOL_ALLOC(mspace, ret, size);
#endif
#ifndef ENABLE_FAST_HEAP_DETECTION
	if(ret)
	{
		mchunkptr p=mem2chunk(ret);
		size_t truesize=chunksize(p) - overhead_for(p);
		if(!leastusedaddress || (void *)((mstate) mspace)->least_addr<leastusedaddress) leastusedaddress=(void *)((mstate) mspace)->least_addr;
		if(!largestusedblock || truesize>largestusedblock) largestusedblock=(truesize+mparams.page_size) & ~(mparams.page_size-1);
	}
#endif
#endif
	if(!ret) return 0;
#if DEBUG
	if(flags & M2_ZERO_MEMORY)
	{
		const char *RESTRICT n;
		for(n=(const char *)ret; n<(const char *)ret+size; n++)
		{
			assert(!*n);
		}
	}
#endif
#if USE_MAGIC_HEADERS
	_ret=(size_t *) ret;
	ret=(void *)(_ret+3);
	if(alignment) ret=(void *)(((size_t) ret+alignment-1)&~(alignment-1));
	for(; _ret<(size_t *)ret-2; _ret++) *_ret=*(size_t *)"NEDMALOC";
	_ret[0]=(size_t) mspace;
	_ret[1]=size-3*sizeof(size_t);
#endif
	return ret;
}

static FORCEINLINE NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void *CallRealloc(void *RESTRICT mspace, void *RESTRICT mem, int isforeign, size_t oldsize, size_t newsize, size_t alignment, unsigned flags) THROWSPEC
{
	void *RESTRICT ret=0;
#if USE_MAGIC_HEADERS
	mstate oldmspace=0;
	size_t *_ret=0, *_mem=(size_t *) mem-3;
#endif
	if(isforeign)
	{	/* Transfer */
#if USE_MAGIC_HEADERS
		assert(_mem[0]!=*(size_t *) "NEDMALOC");
#endif
		if((ret=CallMalloc(mspace, newsize, alignment, flags)))
		{
#if defined(DEBUG)
			printf("*** nedmalloc frees system allocated block %p\n", mem);
#endif
			memcpy(ret, mem, oldsize<newsize ? oldsize : newsize);
			sysfree(mem);
		}
		return ret;
	}
#if USE_MAGIC_HEADERS
	assert(_mem[0]==*(size_t *) "NEDMALOC");
	newsize+=3*sizeof(size_t);
	oldmspace=(mstate) _mem[1];
	assert(oldsize>=_mem[2]);
	for(; *_mem==*(size_t *) "NEDMALOC"; *_mem--=*(size_t *) "nedmaloc");
	mem=(void *)(++_mem);
#endif
#if USE_ALLOCATOR==0
	ret=sysrealloc(mem, newsize);
#elif USE_ALLOCATOR==1
	ret=mspace_realloc2((mstate) mspace, mem, newsize, alignment, flags);
#ifdef HAVE_VALGRIND
	if(ret) VALGRIND_MEMPOOL_CHANGE(mspace, mem, ret, newsize);
#endif
#ifndef ENABLE_FAST_HEAP_DETECTION
	if(ret)
	{
		mchunkptr p=mem2chunk(ret);
		size_t truesize=chunksize(p) - overhead_for(p);
		if(!leastusedaddress || (void *)((mstate) mspace)->least_addr<leastusedaddress) leastusedaddress=(void *)((mstate) mspace)->least_addr;
		if(!largestusedblock || truesize>largestusedblock) largestusedblock=(truesize+mparams.page_size) & ~(mparams.page_size-1);
	}
#endif
#endif
	if(!ret)
	{	/* Put it back the way it was */
#if USE_MAGIC_HEADERS
		for(; *_mem==0; *_mem++=*(size_t *) "NEDMALOC");
#endif
		return 0;
	}
#if USE_MAGIC_HEADERS
	_ret=(size_t *) ret;
	ret=(void *)(_ret+3);
	for(; _ret<(size_t *)ret-2; _ret++) *_ret=*(size_t *) "NEDMALOC";
	_ret[0]=(size_t) mspace;
	_ret[1]=newsize-3*sizeof(size_t);
#endif
	return ret;
}

static FORCEINLINE void CallFree(void *RESTRICT mspace, void *RESTRICT mem, int isforeign) THROWSPEC
{
#if USE_MAGIC_HEADERS
	mstate oldmspace=0;
	size_t *_mem=(size_t *) mem-3, oldsize=0;
#endif
	if(isforeign)
	{
#if USE_MAGIC_HEADERS
		assert(_mem[0]!=*(size_t *) "NEDMALOC");
#endif
#if defined(DEBUG)
		printf("*** nedmalloc frees system allocated block %p\n", mem);
#endif
		sysfree(mem);
		return;
	}
#if USE_MAGIC_HEADERS
	assert(_mem[0]==*(size_t *) "NEDMALOC");
	oldmspace=(mstate) _mem[1];
	oldsize=_mem[2];
	for(; *_mem==*(size_t *) "NEDMALOC"; *_mem--=*(size_t *) "nedmaloc");
	mem=(void *)(++_mem);
#endif
#if USE_ALLOCATOR==0
	sysfree(mem);
#elif USE_ALLOCATOR==1
#ifdef HAVE_VALGRIND
	{
		void *m=mspace ? mspace : get_mstate_for(mem2chunk(mem));
		mspace_free((mstate) mspace, mem);
		VALGRIND_MEMPOOL_FREE(m, mem);
		/* Mark the first two pointers in the newly freed block as used (linked list of freed blocks) */
		VALGRIND_MAKE_MEM_DEFINED(mem, 2*sizeof(void *));
	}
#else
	mspace_free((mstate) mspace, mem);
#endif
#endif
}

static NEDMALLOCNOALIASATTR mstate nedblkmstate(void *RESTRICT mem) THROWSPEC
{
	if(mem)
	{
#if USE_MAGIC_HEADERS
		size_t *_mem=(size_t *) mem-3;
		if(_mem[0]==*(size_t *) "NEDMALOC")
		{
			return (mstate) _mem[1];
		}
		else return 0;
#else
#if USE_ALLOCATOR==0
		/* Fail everything */
		return 0;
#elif USE_ALLOCATOR==1
#ifdef ENABLE_FAST_HEAP_DETECTION
#ifdef WIN32
		/*  On Windows for RELEASE both x86 and x64 the NT heap precedes each block with an eight byte header
			which looks like:
				normal: 4 bytes of size, 4 bytes of [char < 64, char < 64, char < 64 bit 0 always set, char random ]
				mmaped: 4 bytes of size  4 bytes of [zero,      zero,      0xb,                        zero        ]

			On Windows for DEBUG both x86 and x64 the preceding four bytes is always 0xfdfdfdfd (no man's land).
		*/
#pragma pack(push, 1)
		struct _HEAP_ENTRY
		{
			USHORT Size;
			USHORT PreviousSize;
			UCHAR Cookie;			/* SegmentIndex */
			UCHAR Flags;			/* always bit 0 (HEAP_ENTRY_BUSY). bit 1=(HEAP_ENTRY_EXTRA_PRESENT), bit 2=normal block (HEAP_ENTRY_FILL_PATTERN), bit 3=mmap block (HEAP_ENTRY_VIRTUAL_ALLOC). Bit 4 (HEAP_ENTRY_LAST_ENTRY) could be set */
			UCHAR UnusedBytes;
			UCHAR SmallTagIndex;	/* fastbin index. Always one of 0x02, 0x03, 0x04 < 0x80 */
		} *RESTRICT he=((struct _HEAP_ENTRY *) mem)-1;
#pragma pack(pop)
		unsigned int header=((unsigned int *)mem)[-1], mask1=0x8080E100, result1, mask2=0xFFFFFF06, result2;
		result1=header & mask1;	/* Positive testing for NT heap */
		result2=header & mask2;	/* Positive testing for dlmalloc */
		if(result1==0x00000100 && result2!=0x00000102)
		{	/* This is likely a NT heap block */
			return 0;
		}
#endif
#ifdef __linux__
		/* On Linux glibc uses ptmalloc2 (really dlmalloc) just as we do, but prev_foot contains rubbish
		when the preceding block is allocated because ptmalloc2 finds the local mstate by rounding the ptr
		down to the nearest megabyte. It's like dlmalloc with FOOTERS disabled. */
		mchunkptr p=mem2chunk(mem);
		mstate fm=get_mstate_for(p);
		/* If it's a ptmalloc2 block, fm is likely to be some crazy value */
		if(!is_aligned(fm)) return 0;
		if((size_t)mem-(size_t)fm>=(size_t)1<<(SIZE_T_BITSIZE-1)) return 0;
		if(ok_magic(fm))
			return fm;
		else
			return 0;
		if(1) { }
#endif
		else
		{
			mchunkptr p=mem2chunk(mem);
			mstate fm=get_mstate_for(p);
			assert(ok_magic(fm));	/* If this fails, someone tried to free a block twice */
			if(ok_magic(fm))
				return fm;
		}
#else /* ENABLE_FAST_HEAP_DETECTION */
#ifdef WIN32
#ifdef _MSC_VER
		__try
#else
#if ENABLE_TOLERANT_NEDMALLOC
#error Lack of SEH support makes nedmalloc unreliable with foreign memory blocks. Make sure ENABLE_TOLERANT_NEDMALLOC is turned off!
#endif
#endif /* defined(_MSC_VER) */
#elif ENABLE_TOLERANT_NEDMALLOC
#warning nedmalloc is unreliable with foreign memory blocks, so make sure you really want ENABLE_TOLERANT_NEDMALLOC turned on!
#endif
		{
			/* We try to return zero here if it isn't one of our own blocks, however
			the current block annotation scheme used by dlmalloc makes it impossible
			to be absolutely sure of avoiding a segfault.

			mchunkptr->prev_foot = mem-(2*size_t) = mstate ^ mparams.magic for PRECEDING block;
			mchunkptr->head      = mem-(1*size_t) = 8 multiple size of this block with bottom three bits = FLAG_BITS
			    FLAG_BITS = bit 0 is CINUSE (currently in use unless is mmap), bit 1 is PINUSE (previous block currently
				            in use unless mmap), bit 2 is UNUSED and currently is always zero.
			*/
			register void *RESTRICT leastusedaddress_=leastusedaddress;		/* Cache these to avoid register reloading */
			register size_t largestusedblock_=largestusedblock;
			if(!is_aligned(mem)) return 0;		/* Would fail very rarely as all allocators return aligned blocks */
			if(mem<leastusedaddress_) return 0;	/* Simple but effective */
			{
				mchunkptr p=mem2chunk(mem);
				mstate fm=0;
				int ismmapped=is_mmapped(p);
				if((!ismmapped && !is_inuse(p)) || (p->head & FLAG4_BIT)) return 0;
				/* Reduced uncertainty by 0.5^2 = 25.0% */
				/* size should never exceed largestusedblock */
				if(chunksize(p)-overhead_for(p)>largestusedblock_) return 0;
				/* Reduced uncertainty by a minimum of 0.5^3 = 12.5%, maximum 0.5^16 = 0.0015% */
				/* Having sanity checked prev_foot and head, check next block */
				if(!ismmapped && (!next_pinuse(p) || (next_chunk(p)->head & FLAG4_BIT))) return 0;
				/* Reduced uncertainty by 0.5^5 = 3.13% or 0.5^18 = 0.00038% */
#if 0
				/* If previous block is free, check that its next block pointer equals us */
				if(!ismmapped && !pinuse(p))
					if(next_chunk(prev_chunk(p))!=p) return 0;
				/* We could start comparing prev_foot's for similarity but it starts getting slow. */
#endif
				fm = get_mstate_for(p);
				if(!is_aligned(fm) || (void *)fm<leastusedaddress_) return 0;
#if 0
				/* See if mem is lower in memory than mem */
				if((size_t)mem-(size_t)fm>=(size_t)1<<(SIZE_T_BITSIZE-1)) return 0;
#endif
				assert(ok_magic(fm));	/* If this fails, someone tried to free a block twice */
				if(ok_magic(fm))
					return fm;
			}
		}
#ifdef WIN32
#ifdef _MSC_VER
		__except(1) { }
#endif
#endif /* WIN32 */
#endif /* ENABLE_FAST_HEAP_DETECTION */
#endif /* USE_ALLOCATOR */
#endif /* USE_MAGIC_HEADERS */
	}
	return 0;
}
NEDMALLOCNOALIASATTR size_t nedblksize(int *RESTRICT isforeign, void *RESTRICT mem, unsigned flags) THROWSPEC
{
	if(mem)
	{
		if(isforeign) *isforeign=1;
#if USE_MAGIC_HEADERS
		{
			size_t *_mem=(size_t *) mem-3;
			if(_mem[0]==*(size_t *) "NEDMALOC")
			{
				mstate mspace=(mstate) _mem[1];
				size_t size=_mem[2];
				if(isforeign) *isforeign=0;
				return size;
			}
		}
#elif USE_ALLOCATOR==1
		if((flags & NM_SKIP_TOLERANCE_CHECKS) || nedblkmstate(mem))
		{
			mchunkptr p=mem2chunk(mem);
			if(isforeign) *isforeign=0;
			return chunksize(p)-overhead_for(p);
		}
#ifdef DEBUG
		else
		{
			int a=1; /* Set breakpoints here if needed */
		}
#endif
#endif
#if defined(ENABLE_TOLERANT_NEDMALLOC) || USE_ALLOCATOR==0
		return sysblksize(mem);
#endif
	}
	return 0;
}
NEDMALLOCNOALIASATTR size_t nedmemsize(void *RESTRICT mem) THROWSPEC { return nedblksize(0, mem, 0); }

NEDMALLOCNOALIASATTR void nedsetvalue(void *v) THROWSPEC																		{ nedpsetvalue((nedpool *) 0, v); }
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedmalloc(size_t size) THROWSPEC													{ return nedpmalloc((nedpool *) 0, size); }
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedcalloc(size_t no, size_t size) THROWSPEC										{ return nedpcalloc((nedpool *) 0, no, size); }
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedrealloc(void *mem, size_t size) THROWSPEC										{ return nedprealloc((nedpool *) 0, mem, size); }
NEDMALLOCNOALIASATTR void   nedfree(void *mem) THROWSPEC																		{ nedpfree((nedpool *) 0, mem); }
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedmemalign(size_t alignment, size_t bytes) THROWSPEC								{ return nedpmemalign((nedpool *) 0, alignment, bytes); }
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedmalloc2(size_t size, size_t alignment, unsigned flags) THROWSPEC				{ return nedpmalloc2((nedpool *) 0, size, alignment, flags); }
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedrealloc2(void *mem, size_t size, size_t alignment, unsigned flags) THROWSPEC	{ return nedprealloc2((nedpool *) 0, mem, size, alignment, flags); }
NEDMALLOCNOALIASATTR void   nedfree2(void *mem, unsigned flags) THROWSPEC														{ nedpfree2((nedpool *) 0, mem, flags); }
NEDMALLOCNOALIASATTR struct nedmallinfo nedmallinfo(void) THROWSPEC																{ return nedpmallinfo((nedpool *) 0); }
NEDMALLOCNOALIASATTR int    nedmallopt(int parno, int value) THROWSPEC															{ return nedpmallopt((nedpool *) 0, parno, value); }
NEDMALLOCNOALIASATTR int    nedmalloc_trim(size_t pad) THROWSPEC																{ return nedpmalloc_trim((nedpool *) 0, pad); }
void   nedmalloc_stats() THROWSPEC																								{ nedpmalloc_stats((nedpool *) 0); }
NEDMALLOCNOALIASATTR size_t nedmalloc_footprint() THROWSPEC																		{ return nedpmalloc_footprint((nedpool *) 0); }
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void **nedindependent_calloc(size_t elemsno, size_t elemsize, void **chunks) THROWSPEC	{ return nedpindependent_calloc((nedpool *) 0, elemsno, elemsize, chunks); }
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void **nedindependent_comalloc(size_t elems, size_t *sizes, void **chunks) THROWSPEC		{ return nedpindependent_comalloc((nedpool *) 0, elems, sizes, chunks); }

#ifdef WIN32
typedef unsigned __int64 timeCount;
static timeCount GetTimestamp()
{
	static LARGE_INTEGER ticksPerSec;
	static double scalefactor;
	static timeCount baseCount;
	LARGE_INTEGER val;
	timeCount ret;
	if(!scalefactor)
	{
		if(QueryPerformanceFrequency(&ticksPerSec))
			scalefactor=ticksPerSec.QuadPart/1000000000000.0;
		else
			scalefactor=1;
	}
	if(!QueryPerformanceCounter(&val))
		return (timeCount) GetTickCount() * 1000000000;
	ret=(timeCount) (val.QuadPart/scalefactor);
	if(!baseCount) baseCount=ret;
	return ret-baseCount;
}
#else
#include <sys/time.h>

typedef unsigned long long timeCount;
static timeCount GetTimestamp()
{
	static timeCount baseCount;
	timeCount ret;
#ifdef CLOCK_MONOTONIC
	struct timespec ts;
	clock_gettime(CLOCK_MONOTONIC, &ts);
	ret=((timeCount) ts.tv_sec*1000000000000LL)+ts.tv_nsec*1000LL;
#else
	struct timeval tv;
	gettimeofday(&tv, 0);
	ret=((timeCount) tv.tv_sec*1000000000000LL)+tv.tv_usec*1000000LL;
#endif
	if(!baseCount) baseCount=ret;
	return ret-baseCount;
}
#endif

/* Set ENABLE_LOGGING to an AND mask of which of these you want to
log, so set it to 0xffffffff for everything */
typedef enum LogEntryType_t
{
	LOGENTRY_MALLOC					=(1<<0),
	LOGENTRY_REALLOC				=(1<<1),
	LOGENTRY_FREE					=(1<<2),

	LOGENTRY_THREADCACHE_MALLOC		=(1<<3),
	LOGENTRY_THREADCACHE_FREE		=(1<<4),
	LOGENTRY_THREADCACHE_CLEAN		=(1<<5),

	LOGENTRY_POOL_MALLOC			=(1<<6),
	LOGENTRY_POOL_REALLOC			=(1<<7),
	LOGENTRY_POOL_FREE				=(1<<8)
} LogEntryType;
#if NEDMALLOC_STACKBACKTRACEDEPTH
typedef struct StackFrameType_t
{
	void *pc;
	char module[64];
	char functname[256];
	char file[96];
	int lineno;
} StackFrameType;
#endif
typedef struct logentry_t
{
	timeCount timestamp;
	nedpool *np;
	LogEntryType type;
	int mspace;
	size_t size;
	void *mem;
	size_t alignment;
	unsigned flags;
	void *returned;
#if NEDMALLOC_STACKBACKTRACEDEPTH
	StackFrameType stack[NEDMALLOC_STACKBACKTRACEDEPTH];
#endif
} logentry;
static const char *LogEntryTypeStrings[]={
	"LOGENTRY_MALLOC",
	"LOGENTRY_REALLOC",
	"LOGENTRY_FREE",

	"LOGENTRY_THREADCACHE_MALLOC",
	"LOGENTRY_THREADCACHE_FREE",
	"LOGENTRY_THREADCACHE_CLEAN",

	"LOGENTRY_POOL_MALLOC",
	"LOGENTRY_POOL_REALLOC",
	"LOGENTRY_POOL_FREE",
	"******************"
};

struct threadcacheblk_t;
typedef struct threadcacheblk_t threadcacheblk;
struct threadcacheblk_t
{	/* Keep less than 32 bytes as sizeof(threadcacheblk) is the minimum allocation size */
#ifdef FULLSANITYCHECKS
	unsigned int magic;
#endif
	int isforeign;
	unsigned int lastUsed;
	size_t size;
	threadcacheblk *RESTRICT next, *RESTRICT prev;
};
typedef struct threadcache_t
{
#ifdef FULLSANITYCHECKS
	unsigned int magic1;
#endif
	int mymspace;						/* Last mspace entry this thread used */
	long threadid;
	unsigned int mallocs, frees, successes;
#if ENABLE_LOGGING
	logentry *logentries, *logentriesptr, *logentriesend;
#endif
	size_t freeInCache;					/* How much free space is stored in this cache */
	threadcacheblk *RESTRICT bins[(THREADCACHEMAXBINS+1)*2];
#ifdef FULLSANITYCHECKS
	unsigned int magic2;
#endif
} threadcache;
struct nedpool_t
{
#if USE_LOCKS
	MLOCK_T mutex;
#endif
	void *uservalue;
	int threads;						/* Max entries in m to use */
	threadcache *RESTRICT caches[THREADCACHEMAXCACHES];
	TLSVAR mycache;						/* Thread cache for this thread. 0 for unset, negative for use mspace-1 directly, otherwise is cache-1 */
	mstate m[MAXTHREADSINPOOL+1];		/* mspace entries for this pool */
};
static nedpool syspool;

#if ENABLE_LOGGING
#if NEDMALLOC_STACKBACKTRACEDEPTH
#if defined(WIN32) && defined(_MSC_VER)
#define COPY_STRING(d, s, maxlen) { size_t len=strlen(s); len=(len>maxlen) ? maxlen-1 : len; memcpy(d, s, len); d[len]=0; }

#pragma optimize("g", off)
static int ExceptionFilter(unsigned int code, struct _EXCEPTION_POINTERS *ep, CONTEXT *ct) THROWSPEC
{
	*ct=*ep->ContextRecord;
	return EXCEPTION_EXECUTE_HANDLER;
}

static DWORD64 __stdcall GetModBase(HANDLE hProcess, DWORD64 dwAddr) THROWSPEC
{
	DWORD64 modulebase;
	// Try to get the module base if already loaded, otherwise load the module
	modulebase=SymGetModuleBase64(hProcess, dwAddr);
	if(modulebase)
		return modulebase;
	else
	{
		MEMORY_BASIC_INFORMATION stMBI ;
		if ( 0 != VirtualQueryEx ( hProcess, (LPCVOID)(size_t)dwAddr, &stMBI, sizeof(stMBI)))
		{
			int n;
			DWORD dwPathLen=0, dwNameLen=0 ;
			TCHAR szFile[ MAX_PATH ], szModuleName[ MAX_PATH ] ;
			MODULEINFO mi={0};
			dwPathLen = GetModuleFileName ( (HMODULE) stMBI.AllocationBase , szFile, MAX_PATH );
			dwNameLen = GetModuleBaseName (hProcess, (HMODULE) stMBI.AllocationBase , szModuleName, MAX_PATH );
			for(n=dwNameLen; n>0; n--)
			{
				if(szModuleName[n]=='.')
				{
					szModuleName[n]=0;
					break;
				}
			}
			if(!GetModuleInformation(hProcess, (HMODULE) stMBI.AllocationBase, &mi, sizeof(mi)))
			{
				//fxmessage("WARNING: GetModuleInformation() returned error code %d\n", GetLastError());
			}
			if(!SymLoadModule64 ( hProcess, NULL, (PSTR)( (dwPathLen) ? szFile : 0), (PSTR)( (dwNameLen) ? szModuleName : 0),
				(DWORD64) mi.lpBaseOfDll, mi.SizeOfImage))
			{
				//fxmessage("WARNING: SymLoadModule64() returned error code %d\n", GetLastError());
			}
			//fxmessage("%s, %p, %x, %x\n", szFile, mi.lpBaseOfDll, mi.SizeOfImage, (DWORD) mi.lpBaseOfDll+mi.SizeOfImage);
			modulebase=SymGetModuleBase64(hProcess, dwAddr);
			return modulebase;
		}
	}
	return 0;
}

extern HANDLE sym_myprocess;
extern VOID (WINAPI *RtlCaptureContextAddr)(PCONTEXT);
extern void DeinitSym(void) THROWSPEC;
static void DoStackWalk(logentry *p) THROWSPEC
{
	int i,i2;
	HANDLE mythread=(HANDLE) GetCurrentThread();
	STACKFRAME64 sf={ 0 };
	CONTEXT ct={ 0 };
	if(!sym_myprocess)
	{
		DWORD symopts;
		DuplicateHandle(GetCurrentProcess(), GetCurrentProcess(), GetCurrentProcess(), &sym_myprocess, 0, FALSE, DUPLICATE_SAME_ACCESS);
		symopts=SymGetOptions();
		SymSetOptions(symopts /*| SYMOPT_DEFERRED_LOADS*/ | SYMOPT_LOAD_LINES);
		SymInitialize(sym_myprocess, NULL, TRUE);
		atexit(DeinitSym);
	}
	ct.ContextFlags=CONTEXT_FULL;

	// Use RtlCaptureContext() if we have it as it saves an exception throw
	if((VOID (WINAPI *)(PCONTEXT)) -1==RtlCaptureContextAddr)
		RtlCaptureContextAddr=(VOID (WINAPI *)(PCONTEXT)) GetProcAddress(GetModuleHandle(L"kernel32"), "RtlCaptureContext");
	if(RtlCaptureContextAddr)
		RtlCaptureContextAddr(&ct);
	else
	{	// This is nasty, but it works
		__try
		{
			int *foo=0;
			*foo=78;
		}
		__except (ExceptionFilter(GetExceptionCode(), GetExceptionInformation(), &ct))
		{
		}
	}

	sf.AddrPC.Mode=sf.AddrStack.Mode=sf.AddrFrame.Mode=AddrModeFlat;
#if !(defined(_M_AMD64) || defined(_M_X64))
	sf.AddrPC.Offset   =ct.Eip;
	sf.AddrStack.Offset=ct.Esp;
	sf.AddrFrame.Offset=ct.Ebp;
#else
	sf.AddrPC.Offset   =ct.Rip;
	sf.AddrStack.Offset=ct.Rsp;
	sf.AddrFrame.Offset=ct.Rbp; // maybe Rdi?
#endif
	for(i2=0; i2<NEDMALLOC_STACKBACKTRACEDEPTH; i2++)
	{
		IMAGEHLP_MODULE64 ihm={ sizeof(IMAGEHLP_MODULE64) };
		char temp[MAX_PATH+sizeof(IMAGEHLP_SYMBOL64)];
		IMAGEHLP_SYMBOL64 *ihs;
		IMAGEHLP_LINE64 ihl={ sizeof(IMAGEHLP_LINE64) };
		DWORD64 offset;
		if(!StackWalk64(
#if !(defined(_M_AMD64) || defined(_M_X64))
			IMAGE_FILE_MACHINE_I386,
#else
			IMAGE_FILE_MACHINE_AMD64,
#endif
			sym_myprocess, mythread, &sf, &ct, NULL, SymFunctionTableAccess64, GetModBase, NULL))
			break;
		if(0==sf.AddrPC.Offset)
			break;
		i=i2;
		if(i)	// Skip first entry relating to this function
		{
			DWORD lineoffset=0;
			p->stack[i-1].pc=(void *)(size_t) sf.AddrPC.Offset;
			if(SymGetModuleInfo64(sym_myprocess, sf.AddrPC.Offset, &ihm))
			{
				char *leaf;
				leaf=strrchr(ihm.ImageName, '\\');
				if(!leaf) leaf=ihm.ImageName-1;
				COPY_STRING(p->stack[i-1].module, leaf+1, sizeof(p->stack[i-1].module));
			}
			else strcpy(p->stack[i-1].module, "<unknown>");
			//fxmessage("WARNING: SymGetModuleInfo64() returned error code %d\n", GetLastError());
			memset(temp, 0, MAX_PATH+sizeof(IMAGEHLP_SYMBOL64));
			ihs=(IMAGEHLP_SYMBOL64 *) temp;
			ihs->SizeOfStruct=sizeof(IMAGEHLP_SYMBOL64);
			ihs->Address=sf.AddrPC.Offset;
			ihs->MaxNameLength=MAX_PATH;

			if(SymGetSymFromAddr64(sym_myprocess, sf.AddrPC.Offset, &offset, ihs))
			{
				COPY_STRING(p->stack[i-1].functname, ihs->Name, sizeof(p->stack[i-1].functname));
				if(strlen(p->stack[i-1].functname)<sizeof(p->stack[i-1].functname)-8)
				{
					sprintf(strchr(p->stack[i-1].functname, 0), " +0x%x", offset);
				}
			}
			else
				strcpy(p->stack[i-1].functname, "<unknown>");
			if(SymGetLineFromAddr64(sym_myprocess, sf.AddrPC.Offset, &lineoffset, &ihl))
			{
				char *leaf;
				p->stack[i-1].lineno=ihl.LineNumber;

				leaf=strrchr(ihl.FileName, '\\');
				if(!leaf) leaf=ihl.FileName-1;
				COPY_STRING(p->stack[i-1].file, leaf+1, sizeof(p->stack[i-1].file));
			}
			else
				strcpy(p->stack[i-1].file, "<unknown>");
		}
	}
}
#pragma optimize("g", on)
#else
static void DoStackWalk(logentry *p) THROWSPEC
{
	void *backtr[NEDMALLOC_STACKBACKTRACEDEPTH];
	size_t size;
	char **strings;
	size_t i2;
	size=backtrace(backtr, NEDMALLOC_STACKBACKTRACEDEPTH);
	strings=backtrace_symbols(backtr, size);
	for(i2=0; i2<size; i2++)
	{	// Format can be <file path>(<mangled symbol>+0x<offset>) [<pc>]
		// or can be <file path> [<pc>]
		int start=0, end=strlen(strings[i2]), which=0, idx;
		for(idx=0; idx<end; idx++)
		{
			if(0==which && (' '==strings[i2][idx] || '('==strings[i2][idx]))
			{
				int len=FXMIN(idx-start, (int) sizeof(p->stack[i2].file));
				memcpy(p->stack[i2].file, strings[i2]+start, len);
				p->stack[i2].file[len]=0;
				which=(' '==strings[i2][idx]) ? 2 : 1;
				start=idx+1;
			}
			else if(1==which && ')'==strings[i2][idx])
			{
				FXString functname(strings[i2]+start, idx-start);
				FXint offset=functname.rfind("+0x");
				FXString rawsymbol(functname.left(offset));
				FXString symbol(rawsymbol.length() ? fxdemanglesymbol(rawsymbol, false) : rawsymbol);
				symbol.append(functname.mid(offset));
				int len=FXMIN(symbol.length(), (int) sizeof(p->stack[i2].functname));
				memcpy(p->stack[i2].functname, symbol.text(), len);
				p->stack[i2].functname[len]=0;
				which=2;
			}
			else if(2==which && '['==strings[i2][idx])
			{
				start=idx+1;
				which=3;
			}
			else if(3==which && ']'==strings[i2][idx])
			{
				FXString v(strings[i2]+start+2, idx-start-2);
				p->stack[i2].pc=(void *)(FXuval)v.toULong(0, 16);
			}
		}
	}
	free(strings);
}
#endif
#endif
#endif
static FORCEINLINE logentry *LogOperation(threadcache *tc, nedpool *np, LogEntryType type, int mspace, size_t size, void *mem, size_t alignment, unsigned flags, void *returned) THROWSPEC
{
#if ENABLE_LOGGING
	if(tc->logentries && NEDMALLOC_TESTLOGENTRY(tc, np, type, mspace, size, mem, alignment, flags, returned))
	{
		logentry *le;
		if(tc->logentriesptr==tc->logentriesend)
		{
			mchunkptr cp=mem2chunk(tc->logentries);
			size_t logentrieslen=chunksize(cp)-overhead_for(cp);
			le=(logentry *) CallRealloc(0, tc->logentries, 0, logentrieslen, (logentrieslen*3)/2, 0, M2_ZERO_MEMORY|M2_ALWAYS_MMAP|M2_RESERVE_MULT(8));
			if(!le) return 0;
			tc->logentriesptr=le+(tc->logentriesptr-tc->logentries);
			tc->logentries=le;
			cp=mem2chunk(tc->logentries);
			logentrieslen=(chunksize(cp)-overhead_for(cp))/sizeof(logentry);
			tc->logentriesend=tc->logentries+logentrieslen;
		}
		le=tc->logentriesptr++;
		assert(le+1<=tc->logentriesend);
		le->timestamp=GetTimestamp();
		le->np=np;
		le->type=type;
		le->mspace=mspace;
		le->size=size;
		le->mem=mem;
		le->alignment=alignment;
		le->flags=flags;
		le->returned=returned;
#if NEDMALLOC_STACKBACKTRACEDEPTH
		DoStackWalk(le);
#endif
		return le;
	}
#endif
	return 0;
}

static FORCEINLINE NEDMALLOCNOALIASATTR unsigned int size2binidx(size_t _size) THROWSPEC
{	/* 8=1000	16=10000	20=10100	24=11000	32=100000	48=110000	4096=1000000000000 */
	unsigned int topbit, size=(unsigned int)(_size>>4);
	/* 16=1		20=1	24=1	32=10	48=11	64=100	96=110	128=1000	4096=100000000 */

#if defined(__GNUC__)
        topbit = sizeof(size)*__CHAR_BIT__ - 1 - __builtin_clz(size);
#elif defined(_MSC_VER) && _MSC_VER>=1300
	{
            unsigned long bsrTopBit;

            _BitScanReverse(&bsrTopBit, size);

            topbit = bsrTopBit;
        }
#else
#if 0
	union {
		unsigned asInt[2];
		double asDouble;
	};
	int n;

	asDouble = (double)size + 0.5;
	topbit = (asInt[!FOX_BIGENDIAN] >> 20) - 1023;
#else
	{
		unsigned int x=size;
		x = x | (x >> 1);
		x = x | (x >> 2);
		x = x | (x >> 4);
		x = x | (x >> 8);
		x = x | (x >>16);
		x = ~x;
		x = x - ((x >> 1) & 0x55555555);
		x = (x & 0x33333333) + ((x >> 2) & 0x33333333);
		x = (x + (x >> 4)) & 0x0F0F0F0F;
		x = x + (x << 8);
		x = x + (x << 16);
		topbit=31 - (x >> 24);
	}
#endif
#endif
	return topbit;
}


#ifdef FULLSANITYCHECKS
static void tcsanitycheck(threadcacheblk *RESTRICT *RESTRICT ptr) THROWSPEC
{
	assert((ptr[0] && ptr[1]) || (!ptr[0] && !ptr[1]));
	if(ptr[0] && ptr[1])
	{
		assert(ptr[0]->isforeign || nedblkmstate(ptr[0]));
		assert(ptr[1]->isforeign || nedblkmstate(ptr[1]));
		assert(nedblksize(0, ptr[0], 0)>=sizeof(threadcacheblk));
		assert(nedblksize(0, ptr[1], 0)>=sizeof(threadcacheblk));
		assert(*(unsigned int *) "NEDN"==ptr[0]->magic);
		assert(*(unsigned int *) "NEDN"==ptr[1]->magic);
		assert(!ptr[0]->prev);
		assert(!ptr[1]->next);
		if(ptr[0]==ptr[1])
		{
			assert(!ptr[0]->next);
			assert(!ptr[1]->prev);
		}
	}
}
static void tcfullsanitycheck(threadcache *tc) THROWSPEC
{
	threadcacheblk *RESTRICT *RESTRICT tcbptr=tc->bins;
	int n;
	for(n=0; n<=THREADCACHEMAXBINS; n++, tcbptr+=2)
	{
		threadcacheblk *RESTRICT b, *RESTRICT ob=0;
		tcsanitycheck(tcbptr);
		for(b=tcbptr[0]; b; ob=b, b=b->next)
		{
			assert(b->isforeign || nedblkmstate(b));
			assert(nedblksize(0, b, 0)>=sizeof(threadcacheblk));
			assert(*(unsigned int *) "NEDN"==b->magic);
			assert(!ob || ob->next==b);
			assert(!ob || b->prev==ob);
		}
	}
}
#endif

static NOINLINE int InitPool(nedpool *RESTRICT p, size_t capacity, int threads) THROWSPEC;
static NOINLINE void RemoveCacheEntries(nedpool *RESTRICT p, threadcache *RESTRICT tc, unsigned int age) THROWSPEC
{
#ifdef FULLSANITYCHECKS
	tcfullsanitycheck(tc);
#endif
	if(tc->freeInCache)
	{
		threadcacheblk *RESTRICT *RESTRICT tcbptr=tc->bins;
		int n;
		for(n=0; n<=THREADCACHEMAXBINS; n++, tcbptr+=2)
		{
			threadcacheblk *RESTRICT *RESTRICT tcb=tcbptr+1;		/* come from oldest end of list */
			/*tcsanitycheck(tcbptr);*/
			for(; *tcb && tc->frees-(*tcb)->lastUsed>=age; )
			{
				threadcacheblk *RESTRICT f=*tcb;
				size_t blksize=f->size; /*nedblksize(f);*/
				assert(blksize<=nedblksize(0, f, 0));
				assert(blksize);
#ifdef FULLSANITYCHECKS
				assert(*(unsigned int *) "NEDN"==(*tcb)->magic);
#endif
				*tcb=(*tcb)->prev;
				if(*tcb)
					(*tcb)->next=0;
				else
					*tcbptr=0;
				tc->freeInCache-=blksize;
				assert((long) tc->freeInCache>=0);
				CallFree(0, f, f->isforeign);
				/*tcsanitycheck(tcbptr);*/
				LogOperation(tc, p, LOGENTRY_THREADCACHE_CLEAN, age, blksize, f, 0, 0, 0);
			}
		}
	}
#ifdef FULLSANITYCHECKS
	tcfullsanitycheck(tc);
#endif
}
size_t nedflushlogs(nedpool *p, char *filepath) THROWSPEC
{
	size_t count=0;
	if(!p)
	{
		p=&syspool;
		if(!syspool.threads) InitPool(&syspool, 0, -1);
	}
	if(p->caches)
	{
		threadcache *tc;
		int n;
#if ENABLE_LOGGING
		int haslogentries=0;
#endif
		for(n=0; n<THREADCACHEMAXCACHES; n++)
		{
			if((tc=p->caches[n]))
			{
				count+=tc->freeInCache;
				tc->frees++;
				RemoveCacheEntries(p, tc, 0);
				assert(!tc->freeInCache);
#if ENABLE_LOGGING
				haslogentries|=!!tc->logentries;
#endif
			}
		}
#if ENABLE_LOGGING
		if(haslogentries)
		{
			char buffer[MAX_PATH]=NEDMALLOC_LOGFILE;
			FILE *oh;
			fpos_t pos1, pos2;
			if(!filepath) filepath=buffer;
			oh=fopen(filepath, "r+");
			while(!oh)
			{
				char *bptr;
				if((oh=fopen(filepath, "w"))) break;
				if(ENOSPC==errno) break;
				bptr=strrchr(filepath, '.');
				if(bptr-filepath>=MAX_PATH-6) abort();
				memcpy(bptr, "!.csv", 6);
			}
			if(oh)
			{
				fgetpos(oh, &pos1);
				fseek(oh, 0, SEEK_END);
				fgetpos(oh, &pos2);
				if(pos1==pos2)
					fprintf(oh, "Timestamp, Pool, Operation, MSpace, Size, Block, Alignment, Flags, Returned,\"Stack Backtrace\"\n");
				for(n=0; n<THREADCACHEMAXCACHES; n++)
				{
					if((tc=p->caches[n]) && tc->logentries)
					{
						logentry *le;
						for(le=tc->logentries; le<tc->logentriesptr; le++)
						{
							const char *LogEntryTypeString=LogEntryTypeStrings[size2binidx(((size_t)le->type)<<4)];
							char stackbacktrace[16384]="?";
#if NEDMALLOC_STACKBACKTRACEDEPTH
							char *sbtp=stackbacktrace;
							int i;
							for(i=0; i<NEDMALLOC_STACKBACKTRACEDEPTH && le->stack[i].pc; i++)
							{
								sbtp+=sprintf(sbtp, "0x%p:%s:%s (%s:%u),",
									le->stack[i].pc, le->stack[i].module, le->stack[i].functname, le->stack[i].file, le->stack[i].lineno);
								if(sbtp>=stackbacktrace+sizeof(stackbacktrace)) abort();
							}
							if(NEDMALLOC_STACKBACKTRACEDEPTH==i)
								strcpy(sbtp, "<backtrace may continue ...>");
							else
								strcpy(sbtp, "<backtrace ends>");
							if(strchr(sbtp, 0)>=stackbacktrace+sizeof(stackbacktrace)) abort();
#endif
							fprintf(oh, "%llu, 0x%p, %s, %d, %Iu, 0x%p, %Iu, 0x%x, 0x%p,\"%s\"\n",
								le->timestamp, le->np, LogEntryTypeString, le->mspace, le->size, le->mem, le->alignment, le->flags, le->returned, stackbacktrace);
						}
						CallFree(0, tc->logentries, 0);
						tc->logentries=tc->logentriesptr=tc->logentriesend=0;
					}
				}
				fclose(oh);
			}
		}
#endif
	}
	return count;
}
static void DestroyCaches(nedpool *RESTRICT p) THROWSPEC
{
	if(p->caches)
	{
		threadcache *tc;
		int n;
		nedflushlogs(p, 0);
		for(n=0; n<THREADCACHEMAXCACHES; n++)
		{
			if((tc=p->caches[n]))
			{
				tc->mymspace=-1;
				tc->threadid=0;
				CallFree(0, tc, 0);
				p->caches[n]=0;
			}
		}
	}
}

static NOINLINE threadcache *AllocCache(nedpool *RESTRICT p) THROWSPEC
{
	threadcache *tc=0;
	int n, end;
#if USE_LOCKS
	ACQUIRE_LOCK(&p->mutex);
#endif
	for(n=0; n<THREADCACHEMAXCACHES && p->caches[n]; n++);
	if(THREADCACHEMAXCACHES==n)
	{	/* List exhausted, so disable for this thread */
#if USE_LOCKS
		RELEASE_LOCK(&p->mutex);
#endif
		return 0;
	}
	tc=p->caches[n]=(threadcache *) CallMalloc(p->m[0], sizeof(threadcache), 0, M2_ZERO_MEMORY);
	if(!tc)
	{
#if USE_LOCKS
		RELEASE_LOCK(&p->mutex);
#endif
		return 0;
	}
#ifdef FULLSANITYCHECKS
	tc->magic1=*(unsigned int *)"NEDMALC1";
	tc->magic2=*(unsigned int *)"NEDMALC2";
#endif
	tc->threadid=
#if USE_LOCKS
		(long)(size_t)CURRENT_THREAD;
#else
		1;
#endif
	for(end=1; p->m[end]; end++);
	tc->mymspace=abs(tc->threadid) % end;
#if ENABLE_LOGGING
	{
		mchunkptr cp;
		size_t logentrieslen=2048/sizeof(logentry);		/* One page */
		tc->logentries=tc->logentriesptr=(logentry *) CallMalloc(p->m[0], logentrieslen*sizeof(logentry), 0, M2_ZERO_MEMORY|M2_ALWAYS_MMAP|M2_RESERVE_MULT(8));
		if(!tc->logentries)
		{
#if USE_LOCKS
			RELEASE_LOCK(&p->mutex);
#endif
			return 0;
		}
		cp=mem2chunk(tc->logentries);
		logentrieslen=(chunksize(cp)-overhead_for(cp))/sizeof(logentry);
		tc->logentriesend=tc->logentries+logentrieslen;
	}
#endif
#if USE_LOCKS
	RELEASE_LOCK(&p->mutex);
#endif
	if(TLSSET(p->mycache, (void *)(size_t)(n+1))) abort();
	return tc;
}

static void *threadcache_malloc(nedpool *RESTRICT p, threadcache *RESTRICT tc, size_t *RESTRICT _size) THROWSPEC
{
	void *RESTRICT ret=0;
	size_t size=*_size, blksize=0;
	unsigned int bestsize;
	unsigned int idx=size2binidx(size);
	threadcacheblk *RESTRICT blk, *RESTRICT *RESTRICT binsptr;
#ifdef FULLSANITYCHECKS
	tcfullsanitycheck(tc);
#endif
	/* Calculate best fit bin size */
	bestsize=1<<(idx+4);
#if 0
	/* Finer grained bin fit */
	idx<<=1;
	if(size>bestsize)
	{
		idx++;
		bestsize+=bestsize>>1;
	}
	if(size>bestsize)
	{
		idx++;
		bestsize=1<<(4+(idx>>1));
	}
#else
	if(size>bestsize)
	{
		idx++;
		bestsize<<=1;
	}
#endif
	assert(bestsize>=size);
	if(size<bestsize) size=bestsize;
	assert(size<=THREADCACHEMAX);
	assert(idx<=THREADCACHEMAXBINS);
	binsptr=&tc->bins[idx*2];
	/* Try to match close, but move up a bin if necessary */
	blk=*binsptr;
	if(!blk || blk->size<size)
	{	/* Bump it up a bin */
		if(idx<THREADCACHEMAXBINS)
		{
			idx++;
			binsptr+=2;
			blk=*binsptr;
		}
	}
	if(blk)
	{
		blksize=blk->size; /*nedblksize(blk);*/
		assert(nedblksize(0, blk, 0)>=blksize);
		assert(blksize>=size);
		if(blk->next)
			blk->next->prev=0;
		*binsptr=blk->next;
		if(!*binsptr)
			binsptr[1]=0;
#ifdef FULLSANITYCHECKS
		blk->magic=0;
#endif
		assert(binsptr[0]!=blk && binsptr[1]!=blk);
		assert(nedblksize(0, blk, 0)>=sizeof(threadcacheblk) && nedblksize(0, blk, 0)<=THREADCACHEMAX+CHUNK_OVERHEAD);
		/*printf("malloc: %p, %p, %p, %lu\n", p, tc, blk, (long) _size);*/
		ret=(void *) blk;
	}
	++tc->mallocs;
	if(ret)
	{
		assert(blksize>=size);
		++tc->successes;
		tc->freeInCache-=blksize;
		assert((long) tc->freeInCache>=0);
	}
#if defined(DEBUG) && 0
	if(!(tc->mallocs & 0xfff))
	{
		printf("*** threadcache=%u, mallocs=%u (%f), free=%u (%f), freeInCache=%u\n", (unsigned int) tc->threadid, tc->mallocs,
			(float) tc->successes/tc->mallocs, tc->frees, (float) tc->successes/tc->frees, (unsigned int) tc->freeInCache);
	}
#endif
#ifdef FULLSANITYCHECKS
	tcfullsanitycheck(tc);
#endif
	*_size=size;
	return ret;
}
static NOINLINE void ReleaseFreeInCache(nedpool *RESTRICT p, threadcache *RESTRICT tc, int mymspace) THROWSPEC
{
	unsigned int age=THREADCACHEMAXFREESPACE/8192;
#if USE_LOCKS
	/*ACQUIRE_LOCK(&p->m[mymspace]->mutex);*/
#endif
	while(age && tc->freeInCache>=THREADCACHEMAXFREESPACE)
	{
		RemoveCacheEntries(p, tc, age);
		/*printf("*** Removing cache entries older than %u (%u)\n", age, (unsigned int) tc->freeInCache);*/
		age>>=1;
	}
#if USE_LOCKS
	/*RELEASE_LOCK(&p->m[mymspace]->mutex);*/
#endif
}
static void threadcache_free(nedpool *RESTRICT p, threadcache *RESTRICT tc, int mymspace, void *RESTRICT mem, size_t size, int isforeign) THROWSPEC
{
	unsigned int bestsize;
	unsigned int idx=size2binidx(size);
	threadcacheblk *RESTRICT *RESTRICT binsptr, *RESTRICT tck=(threadcacheblk *RESTRICT) mem;
	assert(size>=sizeof(threadcacheblk) && size<=THREADCACHEMAX+CHUNK_OVERHEAD);
#ifdef DEBUG
	/* Make sure this is a valid memory block */
	assert(nedblksize(0, mem, 0));
#endif
#ifdef FULLSANITYCHECKS
	tcfullsanitycheck(tc);
#endif
	/* Calculate best fit bin size */
	bestsize=1<<(idx+4);
#if 0
	/* Finer grained bin fit */
	idx<<=1;
	if(size>bestsize)
	{
		unsigned int biggerbestsize=bestsize+bestsize<<1;
		if(size>=biggerbestsize)
		{
			idx++;
			bestsize=biggerbestsize;
		}
	}
#endif
	if(bestsize!=size)	/* dlmalloc can round up, so we round down to preserve indexing */
		size=bestsize;
	binsptr=&tc->bins[idx*2];
	assert(idx<=THREADCACHEMAXBINS);
	if(tck==*binsptr)
	{
		fprintf(stderr, "nedmalloc: Attempt to free already freed memory block %p - aborting!\n", tck);
		abort();
	}
#ifdef FULLSANITYCHECKS
	tck->magic=*(unsigned int *) "NEDN";
#endif
	tck->isforeign=isforeign;
	tck->lastUsed=++tc->frees;
	tck->size=(unsigned int) size;
	tck->next=*binsptr;
	tck->prev=0;
	if(tck->next)
		tck->next->prev=tck;
	else
		binsptr[1]=tck;
	assert(!*binsptr || (*binsptr)->size==tck->size);
	*binsptr=tck;
	assert(tck==tc->bins[idx*2]);
	assert(tc->bins[idx*2+1]==tck || binsptr[0]->next->prev==tck);
	/*printf("free: %p, %p, %p, %lu\n", p, tc, mem, (long) size);*/
	tc->freeInCache+=size;
#ifdef FULLSANITYCHECKS
	tcfullsanitycheck(tc);
#endif
#if 1
	if(tc->freeInCache>=THREADCACHEMAXFREESPACE)
		ReleaseFreeInCache(p, tc, mymspace);
#endif
}




static NOINLINE int InitPool(nedpool *RESTRICT p, size_t capacity, int threads) THROWSPEC
{	/* threads is -1 for system pool */
	ensure_initialization();
	ACQUIRE_MALLOC_GLOBAL_LOCK();
	if(p->threads) goto done;
#if USE_LOCKS
	if(INITIAL_LOCK(&p->mutex)) goto err;
#endif
	if(TLSALLOC(&p->mycache)) goto err;
#if USE_ALLOCATOR==0
	p->m[0]=(mstate) mspacecounter++;
#elif USE_ALLOCATOR==1
	if(!(p->m[0]=(mstate) create_mspace(capacity, 1))) goto err;
#ifdef HAVE_VALGRIND
	VALGRIND_CREATE_MEMPOOL(p->m[0], 0, 1);
#endif
	p->m[0]->extp=p;
#endif
	p->threads=(threads>MAXTHREADSINPOOL) ? MAXTHREADSINPOOL : (threads<=0) ? DEFAULTMAXTHREADSINPOOL : threads;
done:
	RELEASE_MALLOC_GLOBAL_LOCK();
	return 1;
err:
	if(threads<0)
		abort();			/* If you can't allocate for system pool, we're screwed */
	DestroyCaches(p);
	if(p->m[0])
	{
#if USE_ALLOCATOR==1
#ifdef HAVE_VALGRIND
		VALGRIND_DESTROY_MEMPOOL(p->m[0]);
#endif
		destroy_mspace(p->m[0]);
#endif
		p->m[0]=0;
	}
	if(p->mycache)
	{
		if(TLSFREE(p->mycache)) abort();
		p->mycache=0;
	}
	RELEASE_MALLOC_GLOBAL_LOCK();
	return 0;
}
static NOINLINE mstate FindMSpace(nedpool *RESTRICT p, threadcache *RESTRICT tc, int *RESTRICT lastUsed, size_t size) THROWSPEC
{	/* Gets called when thread's last used mspace is in use. The strategy
	is to run through the list of all available mspaces looking for an
	unlocked one and if we fail, we create a new one so long as we don't
	exceed p->threads */
	int n, end;
	n=end=*lastUsed+1;
#if USE_LOCKS
	for(; p->m[n]; end=++n)
	{
		if(TRY_LOCK(&p->m[n]->mutex)) goto found;
	}
	for(n=0; n<*lastUsed && p->m[n]; n++)
	{
		if(TRY_LOCK(&p->m[n]->mutex)) goto found;
	}
	if(end<p->threads)
	{
		mstate temp;
#if USE_ALLOCATOR==0
		temp=(mstate) mspacecounter++;
#elif USE_ALLOCATOR==1
		if(!(temp=(mstate) create_mspace(size, 1)))
			goto badexit;
#endif
		/* Now we're ready to modify the lists, we lock */
		ACQUIRE_LOCK(&p->mutex);
		while(p->m[end] && end<p->threads)
			end++;
		if(end>=p->threads)
		{	/* Drat, must destroy it now */
			RELEASE_LOCK(&p->mutex);
#if USE_ALLOCATOR==1
			destroy_mspace((mstate) temp);
#endif
			goto badexit;
		}
		/* We really want to make sure this goes into memory now but we
		have to be careful of breaking aliasing rules, so write it twice */
		{
			volatile struct malloc_state **_m=(volatile struct malloc_state **) &p->m[end];
			*_m=(p->m[end]=temp);
		}
#if USE_ALLOCATOR==1 && defined(HAVE_VALGRIND)
		VALGRIND_CREATE_MEMPOOL(temp, 0, 1);
#endif
		ACQUIRE_LOCK(&p->m[end]->mutex);
		/*printf("Created mspace idx %d\n", end);*/
		RELEASE_LOCK(&p->mutex);
		n=end;
		goto found;
	}
	/* Let it lock on the last one it used */
badexit:
	ACQUIRE_LOCK(&p->m[*lastUsed]->mutex);
	return p->m[*lastUsed];
#endif
found:
	*lastUsed=n;
	if(tc)
		tc->mymspace=n;
	else
	{
		if(TLSSET(p->mycache, (void *)(size_t)(-(n+1)))) abort();
	}
	return p->m[n];
}

typedef struct PoolList_t
{
	size_t size;			/* Size of list */
	size_t length;			/* Actual entries in list */
#ifdef DEBUG
	nedpool *list[1];		/* Force testing of list expansion */
#else
	nedpool *list[16];
#endif
} PoolList;
#if USE_LOCKS
static MLOCK_T poollistlock;
#endif
static PoolList *poollist;
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR nedpool *nedcreatepool(size_t capacity, int threads) THROWSPEC
{
	nedpool *ret=0;
	if(!poollist)
	{
		PoolList *newpoollist=0;
		if(!(newpoollist=(PoolList *) nedpcalloc(0, 1, sizeof(PoolList)+sizeof(nedpool *)))) return 0;
#if USE_LOCKS
		INITIAL_LOCK(&poollistlock);
		ACQUIRE_LOCK(&poollistlock);
#endif
		poollist=newpoollist;
		poollist->size=sizeof(poollist->list)/sizeof(nedpool *);
	}
#if USE_LOCKS
	else
		ACQUIRE_LOCK(&poollistlock);
#endif
	if(poollist->length==poollist->size)
	{
		PoolList *newpoollist=0;
		size_t newsize=0, toclearsize;
		newsize=sizeof(PoolList)+(poollist->size+1)*sizeof(nedpool *);
		if(!(newpoollist=(PoolList *) nedprealloc(0, poollist, newsize))) goto badexit;
		poollist=newpoollist;
		toclearsize=newsize-sizeof(PoolList)-(poollist->size)*sizeof(nedpool *);
		memset(&poollist->list[poollist->size], 0, toclearsize);
		poollist->size+=toclearsize/sizeof(nedpool *);
		assert(poollist->size>poollist->length);
	}
	if(!(ret=(nedpool *) nedpcalloc(0, 1, sizeof(nedpool)))) goto badexit;
	if(!InitPool(ret, capacity, threads))
	{
		nedpfree(0, ret);
		goto badexit;
	}
	poollist->list[poollist->length++]=ret;
badexit:
	{
#if USE_LOCKS
		RELEASE_LOCK(&poollistlock);
#endif
	}
	return ret;
}
void neddestroypool(nedpool *p) THROWSPEC
{
	unsigned int n;
#if USE_LOCKS
	ACQUIRE_LOCK(&p->mutex);
#endif
	DestroyCaches(p);
	for(n=0; p->m[n]; n++)
	{
#if USE_ALLOCATOR==1
#ifdef HAVE_VALGRIND
		VALGRIND_DESTROY_MEMPOOL(p->m[n]);
#endif
		destroy_mspace(p->m[n]);
#endif
		p->m[n]=0;
	}
#if USE_LOCKS
	RELEASE_LOCK(&p->mutex);
	DESTROY_LOCK(&p->mutex);
#endif
	if(TLSFREE(p->mycache)) abort();
	nedpfree(0, p);
#if USE_LOCKS
	ACQUIRE_LOCK(&poollistlock);
#endif
	assert(poollist);
	for(n=0; n<poollist->length && poollist->list[n]!=p; n++)
		/* empty */;
	assert(n!=poollist->length);
	memmove(&poollist->list[n], &poollist->list[n+1], (size_t)&poollist->list[poollist->length]-(size_t)&poollist->list[n]);
	if(!--poollist->length)
	{
		assert(!poollist->list[0]);
		nedpfree(0, poollist);
		poollist=0;
	}
#if USE_LOCKS
	RELEASE_LOCK(&poollistlock);
#endif
}
void neddestroysyspool() THROWSPEC
{
	nedpool *p=&syspool;
	int n;
#if USE_LOCKS
	ACQUIRE_LOCK(&p->mutex);
#endif
	DestroyCaches(p);
	for(n=0; p->m[n]; n++)
	{
#if USE_ALLOCATOR==1
#ifdef HAVE_VALGRIND
		VALGRIND_DESTROY_MEMPOOL(p->m[n]);
#endif
		destroy_mspace(p->m[n]);
#endif
		p->m[n]=0;
	}
	/* Render syspool unusable */
	for(n=0; n<THREADCACHEMAXCACHES; n++)
		p->caches[n]=(threadcache *)(size_t)(sizeof(size_t)>4 ? 0xdeadbeefdeadbeefULL : 0xdeadbeefUL);
	for(n=0; n<MAXTHREADSINPOOL+1; n++)
		p->m[n]=(mstate)(size_t)(sizeof(size_t)>4 ? 0xdeadbeefdeadbeefULL : 0xdeadbeefUL);
	if(TLSFREE(p->mycache)) abort();
#if USE_LOCKS
	RELEASE_LOCK(&p->mutex);
	DESTROY_LOCK(&p->mutex);
#endif
}
nedpool **nedpoollist() THROWSPEC
{
	nedpool **ret=0;
	if(poollist)
	{
#if USE_LOCKS
		ACQUIRE_LOCK(&poollistlock);
#endif
		if(!(ret=(nedpool **) nedmalloc((poollist->length+1)*sizeof(nedpool *)))) goto badexit;
		memcpy(ret, poollist->list, (poollist->length+1)*sizeof(nedpool *));
badexit:
		{
#if USE_LOCKS
			RELEASE_LOCK(&poollistlock);
#endif
		}
	}
	return ret;
}

void nedpsetvalue(nedpool *p, void *v) THROWSPEC
{
	if(!p) { p=&syspool; if(!syspool.threads) InitPool(&syspool, 0, -1); }
	p->uservalue=v;
}
void *nedgetvalue(nedpool **p, void *mem) THROWSPEC
{
	nedpool *np=0;
	mstate fm=nedblkmstate(mem);
	if(!fm || !fm->extp) return 0;
	np=(nedpool *) fm->extp;
	if(p) *p=np;
	return np->uservalue;
}

void nedtrimthreadcache(nedpool *p, int disable) THROWSPEC
{
	int mycache;
	if(!p)
	{
		p=&syspool;
		if(!syspool.threads) InitPool(&syspool, 0, -1);
	}
	mycache=(int)(size_t) TLSGET(p->mycache);
	if(!mycache)
	{	/* Set to mspace 0 */
		if(disable && TLSSET(p->mycache, (void *)(size_t)-1)) abort();
	}
	else if(mycache>0)
	{	/* Set to last used mspace */
		threadcache *tc=p->caches[mycache-1];
#if defined(DEBUG)
		printf("Threadcache utilisation: %lf%% in cache with %lf%% lost to other threads\n",
			100.0*tc->successes/tc->mallocs, 100.0*((double) tc->mallocs-tc->frees)/tc->mallocs);
#endif
		if(disable && TLSSET(p->mycache, (void *)(size_t)(-tc->mymspace))) abort();
		tc->frees++;
		RemoveCacheEntries(p, tc, 0);
		assert(!tc->freeInCache);
		if(disable)
		{
			tc->mymspace=-1;
			tc->threadid=0;
			CallFree(0, p->caches[mycache-1], 0);
			p->caches[mycache-1]=0;
		}
	}
}
void neddisablethreadcache(nedpool *p) THROWSPEC
{
	nedtrimthreadcache(p, 1);
}

#if USE_LOCKS && USE_ALLOCATOR==1
#define GETMSPACE(m,p,tc,ms,s,action)                 \
  do                                                  \
  {                                                   \
    mstate m = GetMSpace((p),(tc),(ms),(s));          \
    action;                                           \
	RELEASE_LOCK(&m->mutex);                          \
  } while (0)
#else
#define GETMSPACE(m,p,tc,ms,s,action)                 \
  do                                                  \
  {                                                   \
    mstate m = GetMSpace((p),(tc),(ms),(s));          \
    action;                                           \
  } while (0)
#endif

static FORCEINLINE mstate GetMSpace(nedpool *RESTRICT p, threadcache *RESTRICT tc, int mymspace, size_t size) THROWSPEC
{	/* Returns a locked and ready for use mspace */
	mstate m=p->m[mymspace];
	assert(m);
#if USE_LOCKS && USE_ALLOCATOR==1
	if(!TRY_LOCK(&p->m[mymspace]->mutex)) m=FindMSpace(p, tc, &mymspace, size);
	/*assert(IS_LOCKED(&p->m[mymspace]->mutex));*/
#endif
	return m;
}
static NOINLINE void GetThreadCache_cold1(nedpool *RESTRICT *RESTRICT p) THROWSPEC
{
	*p=&syspool;
	if(!syspool.threads) InitPool(&syspool, 0, -1);
}
static NOINLINE void GetThreadCache_cold2(nedpool *RESTRICT *RESTRICT p, threadcache *RESTRICT *RESTRICT tc, int *RESTRICT mymspace, int mycache) THROWSPEC
{
	if(!mycache)
	{	/* Need to allocate a new cache */
		*tc=AllocCache(*p);
		if(!*tc)
		{	/* Disable */
			if(TLSSET((*p)->mycache, (void *)(size_t)-1)) abort();
			*mymspace=0;
		}
		else
			*mymspace=(*tc)->mymspace;
	}
	else
	{	/* Cache disabled, but we do have an assigned thread pool */
		*tc=0;
		*mymspace=-mycache-1;
	}
}
static FORCEINLINE void GetThreadCache(nedpool *RESTRICT *RESTRICT p, threadcache *RESTRICT *RESTRICT tc, int *RESTRICT mymspace, size_t *RESTRICT size) THROWSPEC
{
	int mycache;
#if THREADCACHEMAX
	if(size && *size<sizeof(threadcacheblk)) *size=sizeof(threadcacheblk);
#endif
	if(!*p)
		GetThreadCache_cold1(p);
	mycache=(int)(size_t) TLSGET((*p)->mycache);
	if(mycache>0)
	{	/* Already have a cache */
		*tc=(*p)->caches[mycache-1];
		*mymspace=(*tc)->mymspace;
	}
	else GetThreadCache_cold2(p, tc, mymspace, mycache);
	assert(*mymspace>=0);
#if USE_LOCKS
	assert(!(*tc) || (long)(size_t)CURRENT_THREAD==(*tc)->threadid);
#endif
#ifdef FULLSANITYCHECKS
	if(*tc)
	{
		if(*(unsigned int *)"NEDMALC1"!=(*tc)->magic1 || *(unsigned int *)"NEDMALC2"!=(*tc)->magic2)
		{
			abort();
		}
	}
#endif
}

NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedpmalloc2(nedpool *p, size_t size, size_t alignment, unsigned flags) THROWSPEC
{
	void *ret=0;
	threadcache *tc;
	int mymspace;
	GetThreadCache(&p, &tc, &mymspace, &size);
#if THREADCACHEMAX
	if(alignment<=MALLOC_ALIGNMENT && !(flags & NM_FLAGS_MASK) && tc && size<=THREADCACHEMAX)
	{	/* Use the thread cache */
		if((ret=threadcache_malloc(p, tc, &size)))
		{
			if((flags & M2_ZERO_MEMORY))
				memset(ret, 0, size);
			LogOperation(tc, p, LOGENTRY_THREADCACHE_MALLOC, mymspace, size, 0, alignment, flags, ret);
		}
	}
#endif
	if(!ret)
	{	/* Use this thread's mspace */
        GETMSPACE(m, p, tc, mymspace, size,
                  ret=CallMalloc(m, size, alignment, flags));
		if(ret)
			LogOperation(tc, p, LOGENTRY_POOL_MALLOC, mymspace, size, 0, alignment, flags, ret);
	}
	LogOperation(tc, p, LOGENTRY_MALLOC, mymspace, size, 0, alignment, flags, ret);
	return ret;
}
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedprealloc2(nedpool *p, void *mem, size_t size, size_t alignment, unsigned flags) THROWSPEC
{
	void *ret=0;
	threadcache *tc;
	int mymspace, isforeign=1;
	size_t memsize;
	if(!mem) return nedpmalloc2(p, size, alignment, flags);
#if REALLOC_ZERO_BYTES_FREES
	if(!size)
	{
		nedpfree2(p, mem, flags);
		return 0;
	}
#endif
	memsize=nedblksize(&isforeign, mem, flags);
	assert(memsize);
	if(!memsize)
	{
		fprintf(stderr, "nedmalloc: nedprealloc() called with a block not created by nedmalloc!\n");
		abort();
	}
	else if(size<=memsize && memsize-size<
#ifdef DEBUG
		32
#else
		1024
#endif
		)		/* If realloc size is within 1Kb smaller than existing, noop it */
		return mem;
	GetThreadCache(&p, &tc, &mymspace, &size);
#if THREADCACHEMAX
	if(alignment<=MALLOC_ALIGNMENT && !(flags & NM_FLAGS_MASK) && tc && size && size<=THREADCACHEMAX)
	{	/* Use the thread cache */
		if((ret=threadcache_malloc(p, tc, &size)))
		{
			size_t tocopy=memsize<size ? memsize : size;
			memcpy(ret, mem, tocopy);
			if((flags & M2_ZERO_MEMORY) && size>memsize)
				memset((void *)((size_t)ret+memsize), 0, size-memsize);
			LogOperation(tc, p, LOGENTRY_THREADCACHE_MALLOC, mymspace, size, mem, alignment, flags, ret);
			if(!isforeign && memsize>=sizeof(threadcacheblk) && memsize<=(THREADCACHEMAX+CHUNK_OVERHEAD))
			{
				threadcache_free(p, tc, mymspace, mem, memsize, isforeign);
				LogOperation(tc, p, LOGENTRY_THREADCACHE_FREE, mymspace, memsize, mem, 0, 0, 0);
			}
			else
			{
				CallFree(0, mem, isforeign);
				LogOperation(tc, p, LOGENTRY_POOL_FREE, mymspace, memsize, mem, 0, 0, 0);
			}
		}
	}
#endif
	if(!ret)
	{	/* Reallocs always happen in the mspace they happened in, so skip
		locking the preferred mspace for this thread */
		ret=CallRealloc(p->m[mymspace], mem, isforeign, memsize, size, alignment, flags);
		if(ret)
			LogOperation(tc, p, LOGENTRY_POOL_REALLOC, mymspace, size, mem, alignment, flags, ret);
	}
	LogOperation(tc, p, LOGENTRY_REALLOC, mymspace, size, mem, alignment, flags, ret);
	return ret;
}
NEDMALLOCNOALIASATTR void   nedpfree2(nedpool *p, void *mem, unsigned flags) THROWSPEC
{	/* Frees always happen in the mspace they happened in, so skip
	locking the preferred mspace for this thread */
	threadcache *tc;
	int mymspace, isforeign=1;
	size_t memsize;
	if(!mem)
	{	/* If you tried this on FreeBSD you'd be sorry! */
#ifdef DEBUG
		fprintf(stderr, "nedmalloc: WARNING nedpfree() called with zero. This is not portable behaviour!\n");
#endif
		return;
	}
	memsize=nedblksize(&isforeign, mem, flags);
	assert(memsize);
	if(!memsize)
	{
		fprintf(stderr, "nedmalloc: nedpfree() called with a block not created by nedmalloc!\n");
		abort();
	}
	GetThreadCache(&p, &tc, &mymspace, 0);
#if THREADCACHEMAX
	if(mem && tc && !isforeign && memsize>=sizeof(threadcacheblk) && memsize<=(THREADCACHEMAX+CHUNK_OVERHEAD))
	{
		threadcache_free(p, tc, mymspace, mem, memsize, isforeign);
		LogOperation(tc, p, LOGENTRY_THREADCACHE_FREE, mymspace, memsize, mem, 0, 0, 0);
	}
	else
#endif
	{
		CallFree(0, mem, isforeign);
		LogOperation(tc, p, LOGENTRY_POOL_FREE, mymspace, memsize, mem, 0, 0, 0);
	}
	LogOperation(tc, p, LOGENTRY_FREE, mymspace, memsize, mem, 0, 0, 0);
}
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedpmalloc(nedpool *p, size_t size) THROWSPEC
{
	unsigned flags=NEDMALLOC_FORCERESERVE(p, 0, size);
	return nedpmalloc2(p, size, 0, flags);
}
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedpcalloc(nedpool *p, size_t no, size_t size) THROWSPEC
{
	size_t bytes=no*size;
	unsigned flags=NEDMALLOC_FORCERESERVE(p, 0, bytes);
	/* Avoid multiplication overflow. */
	if(size && no!=bytes/size) return 0;
	return nedpmalloc2(p, bytes, 0, M2_ZERO_MEMORY|flags);
}
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedprealloc(nedpool *p, void *mem, size_t size) THROWSPEC
{
	unsigned flags=NEDMALLOC_FORCERESERVE(p, mem, size);
#if ENABLE_USERMODEPAGEALLOCATOR
	/* If the user mode page allocator is turned on in a 32 bit process,
	don't automatically reserve eight times the address space. */
	if(8==sizeof(size_t) || !OSHavePhysicalPageSupport())
#endif
	{	/* If he reallocs even once, it's probably wise to turn on address space reservation.
		If the size is larger than mmap_threshold then it'll set the reserve. */
		if(!(flags & M2_RESERVE_MASK)) flags=M2_RESERVE_MULT(8);
	}
	return nedprealloc2(p, mem, size, 0, flags);
}
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedpmemalign(nedpool *p, size_t alignment, size_t bytes) THROWSPEC
{
	unsigned flags=NEDMALLOC_FORCERESERVE(p, 0, bytes);
	return nedpmalloc2(p, bytes, alignment, flags);
}
NEDMALLOCNOALIASATTR void   nedpfree(nedpool *p, void *mem) THROWSPEC
{
  nedpfree2(p, mem, 0);
}

struct nedmallinfo nedpmallinfo(nedpool *p) THROWSPEC
{
	int n;
	struct nedmallinfo ret={0};
	if(!p) { p=&syspool; if(!syspool.threads) InitPool(&syspool, 0, -1); }
	for(n=0; p->m[n]; n++)
	{
#if USE_ALLOCATOR==1 && !NO_MALLINFO
		struct mallinfo t=mspace_mallinfo(p->m[n]);
		ret.arena+=t.arena;
		ret.ordblks+=t.ordblks;
		ret.hblkhd+=t.hblkhd;
		ret.usmblks+=t.usmblks;
		ret.uordblks+=t.uordblks;
		ret.fordblks+=t.fordblks;
		ret.keepcost+=t.keepcost;
#endif
	}
	return ret;
}
int    nedpmallopt(nedpool *p, int parno, int value) THROWSPEC
{
#if USE_ALLOCATOR==1
	return mspace_mallopt(parno, value);
#else
	return 0;
#endif
}
NEDMALLOCNOALIASATTR void*  nedmalloc_internals(size_t *granularity, size_t *magic) THROWSPEC
{
#if USE_ALLOCATOR==1
	if(granularity) *granularity=mparams.granularity;
	if(magic) *magic=mparams.magic;
	return (void *) &syspool;
#else
	if(granularity) *granularity=0;
	if(magic) *magic=0;
	return 0;
#endif
}
int    nedpmalloc_trim(nedpool *p, size_t pad) THROWSPEC
{
	int n, ret=0;
	if(!p) { p=&syspool; if(!syspool.threads) InitPool(&syspool, 0, -1); }
	for(n=0; p->m[n]; n++)
	{
#if USE_ALLOCATOR==1
		ret+=mspace_trim(p->m[n], pad);
#endif
	}
	return ret;
}
void   nedpmalloc_stats(nedpool *p) THROWSPEC
{
	int n;
	if(!p) { p=&syspool; if(!syspool.threads) InitPool(&syspool, 0, -1); }
	for(n=0; p->m[n]; n++)
	{
#if USE_ALLOCATOR==1
		mspace_malloc_stats(p->m[n]);
#endif
	}
}
size_t nedpmalloc_footprint(nedpool *p) THROWSPEC
{
	size_t ret=0;
	int n;
	if(!p) { p=&syspool; if(!syspool.threads) InitPool(&syspool, 0, -1); }
	for(n=0; p->m[n]; n++)
	{
#if USE_ALLOCATOR==1
		ret+=mspace_footprint(p->m[n]);
#endif
	}
	return ret;
}
static FORCEINLINE NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void ** CallIndependentCalloc(void *RESTRICT m, size_t elemsno, size_t elemsize, void **chunks) THROWSPEC
{
    void **ret;
#if USE_ALLOCATOR==0
    ret=(void **) unsupported_operation("independent_calloc");
#elif USE_ALLOCATOR==1
    ret=mspace_independent_calloc(m, elemsno, elemsize, chunks);
#ifdef HAVE_VALGRIND
    if(ret)
    {
        size_t n;
        for(n=0; n<elemsno; n++)
            VALGRIND_MEMPOOL_ALLOC(m, ret[n], elemsize);
    }
#endif
#endif
    if(ret)
    {
  		if(!leastusedaddress || (void *)((mstate) m)->least_addr<leastusedaddress) leastusedaddress=(void *)((mstate) m)->least_addr;
	  	/*if(!largestusedblock || truesize>largestusedblock) largestusedblock=(truesize+mparams.page_size) & ~(mparams.page_size-1);*/
    }
    return ret;
}
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void **nedpindependent_calloc(nedpool *p, size_t elemsno, size_t elemsize, void **chunks) THROWSPEC
{
	void **ret;
	threadcache *tc;
	int mymspace;
	GetThreadCache(&p, &tc, &mymspace, &elemsize);
	GETMSPACE(m, p, tc, mymspace, elemsno*elemsize,
		ret=CallIndependentCalloc(m, elemsno, elemsize, chunks));
#if ENABLE_LOGGING
	if(ret && (ENABLE_LOGGING & LOGENTRY_POOL_MALLOC))
	{
		size_t n;
		for(n=0; n<elemsno; n++)
		{
			LogOperation(tc, p, LOGENTRY_POOL_MALLOC, mymspace, elemsize, 0, 0, M2_ZERO_MEMORY, ret[n]);
		}
	}
#endif
	return ret;
}
static FORCEINLINE NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void **CallIndependentComalloc(void *RESTRICT m, size_t elems, size_t *RESTRICT sizes, void **chunks) THROWSPEC
{
	void **ret;
#if USE_ALLOCATOR==0
	ret=(void **) unsupported_operation("independent_comalloc");
#elif USE_ALLOCATOR==1
	ret=mspace_independent_comalloc(m, elems, sizes, chunks);
#ifdef HAVE_VALGRIND
	if(ret)
	{
		size_t n;
		for(n=0; n<elems; n++)
			VALGRIND_MEMPOOL_ALLOC(m, ret[n], sizes[n]);
	}
#endif
#endif
	if(ret)
	{
		if(!leastusedaddress || (void *)((mstate) m)->least_addr<leastusedaddress) leastusedaddress=(void *)((mstate) m)->least_addr;
		/*if(!largestusedblock || truesize>largestusedblock) largestusedblock=(truesize+mparams.page_size) & ~(mparams.page_size-1);*/
	}
	return ret;
}
NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void **nedpindependent_comalloc(nedpool *p, size_t elems, size_t *sizes, void **chunks) THROWSPEC
{
	void **ret;
	threadcache *tc;
	int mymspace;
	size_t i, *adjustedsizes=(size_t *) alloca(elems*sizeof(size_t));
	if(!adjustedsizes) return 0;
	for(i=0; i<elems; i++)
		adjustedsizes[i]=sizes[i]<sizeof(threadcacheblk) ? sizeof(threadcacheblk) : sizes[i];
	GetThreadCache(&p, &tc, &mymspace, 0);
	GETMSPACE(m, p, tc, mymspace, 0,
              ret=CallIndependentComalloc(m, elems, adjustedsizes, chunks));
#if ENABLE_LOGGING
	if(ret && (ENABLE_LOGGING & LOGENTRY_POOL_MALLOC))
	{
		size_t n;
		for(n=0; n<elems; n++)
		{
			LogOperation(tc, p, LOGENTRY_POOL_MALLOC, mymspace, sizes[n], 0, 0, 0, ret[n]);
		}
	}
#endif
	return ret;
}

#if defined(__cplusplus)
}
#endif

#ifdef _MSC_VER
#pragma warning(pop)
#endif