/* ======================================================================== This is a customized malloc.h header file for vxWorks. ======================================================================== */ #ifndef MALLOC_272_H #define MALLOC_272_H /* vxWorks. */ #if 1 /* #define DEBUG 1 */ /* Use the supplied emulation of sbrk */ #define MORECORE vxSbrk #define MORECORE_CONTIGUOUS 0 #define MORECORE_FAILURE ((void*)(-1)) #define MORECORE_CANNOT_TRIM 1 /* No mmap and munmap. */ #define HAVE_MMAP 0 #include #include /* for size_t */ #include #include #include #include #include #include #include #include #include /* needed for malloc_stats */ #include /* needed for optional MALLOC_FAILURE_ACTION */ #include #define USE_PUBLIC_MALLOC_WRAPPERS /* MORECORE is the name of the routine to call to obtain more memory from the system. See below for general guidance on writing alternative MORECORE functions, as well as a version for WIN32 and a sample version for pre-OSX macos. */ #define MORECORE vxSbrk /* vxWorks memory semaphore. */ static SEMAPHORE mem_semaphore; #define MALLOC_PREACTION semTake(&mem_semaphore, WAIT_FOREVER) #define MALLOC_POSTACTION semGive(&mem_semaphore) /* The system page size. To the extent possible, this malloc manages memory from the system in page-size units. Note that this value is cached during initialization into a field of malloc_state. So even if malloc_getpagesize is a function, it is only called once. The following mechanics for getpagesize were adapted from bsd/gnu getpagesize.h. If none of the system-probes here apply, a value of 4096 is used, which should be OK: If they don't apply, then using the actual value probably doesn't impact performance. */ #define malloc_getpagesize (64*1024) /* ------------- Optional versions of memcopy ---------------- */ /* Note: memcpy is ONLY invoked with non-overlapping regions, so the (usually slower) memmove is not needed. */ #define USE_MEMCPY 1 /* #define MALLOC_COPY(dest, src, nbytes) __builtin_memcpy(dest, src, nbytes) */ /* #define MALLOC_ZERO(dest, nbytes) bzero((char*)dest, nbytes) */ #endif /* This is a version (aka dlmalloc) of malloc/free/realloc written by Doug Lea and released to the public domain. Use, modify, and redistribute this code without permission or acknowledgement in any way you wish. Send questions, comments, complaints, performance data, etc to d...@cs.oswego.edu * VERSION 2.7.2 Sat Aug 17 09:07:30 2002 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 (-O), and link it into another program. All of the compile-time options default to reasonable values for use on most unix platforms. Compile -DWIN32 for reasonable defaults on windows. 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-2.7.1.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. * Why use this malloc? 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. The main properties of the algorithms are: * For large (>= 512 bytes) requests, it is a pure best-fit allocator, with ties normally decided via FIFO (i.e. least recently used). * For small (<= 64 bytes by default) requests, it is a caching allocator, that maintains pools of quickly recycled chunks. * In between, and for combinations of large and small requests, it does the best it can trying to meet both goals at once. * For very large requests (>= 128KB by default), it relies on system memory mapping facilities, if supported. For a longer but slightly out of date high-level description, see http://gee.cs.oswego.edu/dl/html/malloc.html 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 in order to customize settings or to avoid overheads associated with library versions. * Contents, described in more detail in "description of public routines" below. Standard (ANSI/SVID/...) functions: malloc(size_t n); calloc(size_t n_elements, size_t element_size); free(Void_t* p); realloc(Void_t* p, size_t n); memalign(size_t alignment, size_t n); valloc(size_t n); mallinfo() mallopt(int parameter_number, int parameter_value) Additional functions: independent_calloc(size_t n_elements, size_t size, Void_t* chunks[]); independent_comalloc(size_t n_elements, size_t sizes[], Void_t* chunks[]); pvalloc(size_t n); cfree(Void_t* p); malloc_trim(size_t pad); malloc_usable_size(Void_t* p); malloc_stats(); * Vital statistics: Supported pointer representation: 4 or 8 bytes Supported size_t representation: 4 or 8 bytes Note that size_t is allowed to be 4 bytes even if pointers are 8. You can adjust this by defining INTERNAL_SIZE_T Alignment: 2 * sizeof(size_t) (default) (i.e., 8 byte alignment with 4byte size_t). This suffices for nearly all current machines and C compilers. However, you can define MALLOC_ALIGNMENT to be wider than this if necessary. Minimum overhead per allocated chunk: 4 or 8 bytes Each malloced chunk has a hidden word of overhead holding size and status information. Minimum allocated size: 4-byte ptrs: 16 bytes (including 4 overhead) 8-byte ptrs: 24/32 bytes (including, 4/8 overhead) When a chunk is freed, 12 (for 4byte ptrs) or 20 (for 8 byte ptrs but 4 byte size) or 24 (for 8/8) additional bytes are needed; 4 (8) for a trailing size field and 8 (16) bytes for free list pointers. Thus, the minimum allocatable size is 16/24/32 bytes. 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 2 * sizeof(size_t) bytes plus the remainder from a system page (the minimal mmap unit); typically 4096 or 8192 bytes. Maximum allocated size: 4-byte size_t: 2^32 minus about two pages 8-byte size_t: 2^64 minus about two pages It is assumed that (possibly signed) size_t values suffice to represent chunk sizes. `Possibly signed' is due to the fact that `size_t' may be defined on a system as either a signed or an unsigned type. The ISO C standard says that it must be unsigned, but a few systems are known not to adhere to this. Additionally, even when size_t is unsigned, sbrk (which is by default used to obtain memory from system) accepts signed arguments, and may not be able to handle size_t-wide arguments with negative sign bit. Generally, values that would appear as negative after accounting for overhead and alignment are supported only via mmap(), which does not have this limitation. Requests for sizes outside the allowed range will perform an optional failure action and then return null. (Requests may also also fail because a system is out of memory.) Thread-safety: NOT thread-safe unless USE_MALLOC_LOCK defined When USE_MALLOC_LOCK is defined, wrappers are created to surround every public call 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, you would be far better off obtaining ptmalloc, which is derived from a version of this malloc, and is well-tuned for concurrent programs. (See http://www.malloc.de) Note that even when USE_MALLOC_LOCK is defined, you can can guarantee full thread-safety only if no threads acquire memory through direct calls to MORECORE or other system-level allocators. Compliance: I believe it is compliant with the 1997 Single Unix Specification (See http://www.opennc.org). Also SVID/XPG, ANSI C, and probably others as well. * Synopsis of compile-time options: People have reported using previous versions of this malloc on all versions of Unix, sometimes by tweaking some of the defines below. It has been tested most extensively on Solaris and Linux. It is also reported to work on WIN32 platforms. People also report using it in stand-alone embedded systems. The implementation is in straight, hand-tuned ANSI C. It is not at all modular. (Sorry!) It uses a lot of macros. To be at all usable, this code should be compiled using an optimizing compiler (for example gcc -O3) that can simplify expressions and control paths. (FAQ: some macros import variables as arguments rather than declare locals because people reported that some debuggers otherwise get confused.) OPTION DEFAULT VALUE Compilation Environment options: __STD_C derived from C compiler defines WIN32 NOT defined HAVE_MEMCPY defined USE_MEMCPY 1 if HAVE_MEMCPY is defined HAVE_MMAP defined as 1 MMAP_CLEARS 1 HAVE_MREMAP 0 unless linux defined malloc_getpagesize derived from system #includes, or 4096 if not HAVE_USR_INCLUDE_MALLOC_H NOT defined LACKS_UNISTD_H NOT defined unless WIN32 LACKS_SYS_PARAM_H NOT defined unless WIN32 LACKS_SYS_MMAN_H NOT defined unless WIN32 LACKS_FCNTL_H NOT defined Changing default word sizes: INTERNAL_SIZE_T size_t MALLOC_ALIGNMENT 2 * sizeof(INTERNAL_SIZE_T) PTR_UINT unsigned long CHUNK_SIZE_T unsigned long Configuration and functionality options: USE_DL_PREFIX NOT defined USE_PUBLIC_MALLOC_WRAPPERS NOT defined USE_MALLOC_LOCK NOT defined DEBUG NOT defined REALLOC_ZERO_BYTES_FREES NOT defined MALLOC_FAILURE_ACTION errno = ENOMEM, if __STD_C defined, else no-op TRIM_FASTBINS 0 FIRST_SORTED_BIN_SIZE 512 Options for customizing MORECORE: MORECORE sbrk MORECORE_CONTIGUOUS 1 MORECORE_CANNOT_TRIM NOT defined MMAP_AS_MORECORE_SIZE (1024 * 1024) Tuning options that are also dynamically changeable via mallopt: DEFAULT_MXFAST 64 DEFAULT_TRIM_THRESHOLD 256 * 1024 DEFAULT_TOP_PAD 0 DEFAULT_MMAP_THRESHOLD 256 * 1024 DEFAULT_MMAP_MAX 65536 There are several other #defined constants and macros that you probably don't want to touch unless you are extending or adapting malloc. */ /* WIN32 sets up defaults for MS environment and compilers. Otherwise defaults are for unix. */ /* __STD_C should be nonzero if using ANSI-standard C compiler, a C++ compiler, or a C compiler sufficiently close to ANSI to get away with it. */ #ifndef __STD_C #if defined(__STDC__) || defined(_cplusplus) #define __STD_C 1 #else #define __STD_C 0 #endif #endif /*__STD_C*/ /* Void_t* is the pointer type that malloc should say it returns */ #ifndef Void_t #if (__STD_C || defined(WIN32)) #define Void_t void #else #define Void_t char #endif #endif /*Void_t*/ #if __STD_C #include /* for size_t */ #else #include #endif #ifdef __cplusplus extern "C" { #endif /* define LACKS_UNISTD_H if your system does not have a . */ /* #define LACKS_UNISTD_H */ #ifndef LACKS_UNISTD_H #include #endif /* define LACKS_SYS_PARAM_H if your system does not have a . */ /* #define LACKS_SYS_PARAM_H */ #include /* needed for malloc_stats */ #include /* needed for optional MALLOC_FAILURE_ACTION */ /* Debugging: Because freed chunks may be overwritten with bookkeeping fields, this malloc will often die when freed memory is overwritten by user programs. This can be very effective (albeit in an annoying way) in helping track down dangling pointers. If you compile with -DDEBUG, a number of assertion checks are enabled that will catch more memory errors. You probably won't be able to make much sense of the actual assertion errors, but they should help you locate incorrectly overwritten memory. 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 summmaries. (By nature, mmapped regions cannot be checked very much automatically.) Setting DEBUG may also be helpful if you are trying to modify this code. The assertions in the check routines spell out in more detail the assumptions and invariants underlying the algorithms. Setting DEBUG does NOT provide an automated mechanism for checking that all accesses to malloced memory stay within their bounds. However, there are several add-ons and adaptations of this or other mallocs available that do this. */ #if DEBUG #include #else #define assert(x) ((void)0) #endif /* The unsigned integer type used for comparing any two chunk sizes. This should be at least as wide as size_t, but should not be signed. */ #ifndef CHUNK_SIZE_T #define CHUNK_SIZE_T unsigned long #endif /* The unsigned integer type used to hold addresses when they are are manipulated as integers. Except that it is not defined on all systems, intptr_t would suffice. */ #ifndef PTR_UINT #define PTR_UINT unsigned long #endif /* INTERNAL_SIZE_T is the word-size used for internal bookkeeping of chunk sizes. The default version is the same as size_t. While not strictly necessary, it is best to define this as an unsigned type, even if size_t is a signed type. This may avoid some artificial size limitations on some systems. On a 64-bit machine, you may be able to reduce malloc overhead by defining INTERNAL_SIZE_T to be a 32 bit `unsigned int' at the expense of not being able to handle more than 2^32 of malloced space. If this limitation is acceptable, you are encouraged to set this unless you are on a platform requiring 16byte alignments. In this case the alignment requirements turn out to negate any potential advantages of decreasing size_t word size. Implementors: Beware of the possible combinations of: - INTERNAL_SIZE_T might be signed or unsigned, might be 32 or 64 bits, and might be the same width as int or as long - size_t might have different width and signedness as INTERNAL_SIZE_T - int and long might be 32 or 64 bits, and might be the same width To deal with this, most comparisons and difference computations among INTERNAL_SIZE_Ts should cast them to CHUNK_SIZE_T, being aware of the fact that casting an unsigned int to a wider long does not sign-extend. (This also makes checking for negative numbers awkward.) Some of these casts result in harmless compiler warnings on some systems. */ #ifndef INTERNAL_SIZE_T #define INTERNAL_SIZE_T size_t #endif /* The corresponding word size */ #define SIZE_SZ (sizeof(INTERNAL_SIZE_T)) /* MALLOC_ALIGNMENT is the minimum alignment for malloc'ed chunks. It must be a power of two at least 2 * SIZE_SZ, 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. */ #ifndef MALLOC_ALIGNMENT #define MALLOC_ALIGNMENT (2 * SIZE_SZ) #endif /* The corresponding bit mask value */ #define MALLOC_ALIGN_MASK (MALLOC_ALIGNMENT - 1) /* REALLOC_ZERO_BYTES_FREES 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). */ /* #define REALLOC_ZERO_BYTES_FREES */ /* TRIM_FASTBINS controls whether free() of a very small chunk can immediately lead to trimming. Setting to true (1) can reduce memory footprint, but will almost always slow down programs that use a lot of small chunks. Define this only if you are willing to give up some speed to more aggressively reduce system-level memory footprint when releasing memory in programs that use many small chunks. You can get essentially the same effect by setting MXFAST to 0, but this can lead to even greater slowdowns in programs using many small chunks. TRIM_FASTBINS is an in-between compile-time option, that disables only those chunks bordering topmost memory from being placed in fastbins. */ #ifndef TRIM_FASTBINS #define TRIM_FASTBINS 0 #endif /* USE_DL_PREFIX will prefix all public routines with the string 'dl'. This is necessary when you only want to use this malloc in one part of a program, using your regular system malloc elsewhere. */ /* #define USE_DL_PREFIX */ /* USE_MALLOC_LOCK causes wrapper functions to surround each callable routine with pthread mutex lock/unlock. USE_MALLOC_LOCK forces USE_PUBLIC_MALLOC_WRAPPERS to be defined */ /* #define USE_MALLOC_LOCK */ /* If USE_PUBLIC_MALLOC_WRAPPERS is defined, every public routine is actually a wrapper function that first calls MALLOC_PREACTION, then calls the internal routine, and follows it with MALLOC_POSTACTION. This is needed for locking, but you can also use this, without USE_MALLOC_LOCK, for purposes of interception, instrumentation, etc. It is a sad fact that using wrappers often noticeably degrades performance of malloc-intensive programs. */ #ifdef USE_MALLOC_LOCK #define USE_PUBLIC_MALLOC_WRAPPERS #else /* #define USE_PUBLIC_MALLOC_WRAPPERS */ #endif /* Two-phase name translation. All of the actual routines are given mangled names. When wrappers are used, they become the public callable versions. When DL_PREFIX is used, the callable names are prefixed. */ #ifndef USE_PUBLIC_MALLOC_WRAPPERS #define cALLOc public_cALLOc #define fREe public_fREe #define cFREe public_cFREe #define mALLOc public_mALLOc #define mEMALIGn public_mEMALIGn #define rEALLOc public_rEALLOc #define vALLOc public_vALLOc #define pVALLOc public_pVALLOc #define mALLINFo public_mALLINFo #define mALLOPt public_mALLOPt #define mTRIm public_mTRIm #define mSTATs public_mSTATs #define mUSABLe public_mUSABLe #define iCALLOc public_iCALLOc #define iCOMALLOc public_iCOMALLOc #endif #ifdef USE_DL_PREFIX #define public_cALLOc dlcalloc #define public_fREe dlfree #define public_cFREe dlcfree #define public_mALLOc dlmalloc #define public_mEMALIGn dlmemalign #define public_rEALLOc dlrealloc #define public_vALLOc dlvalloc #define public_pVALLOc dlpvalloc #define public_mALLINFo dlmallinfo #define public_mALLOPt dlmallopt #define public_mTRIm dlmalloc_trim #define public_mSTATs dlmalloc_stats #define public_mUSABLe dlmalloc_usable_size #define public_iCALLOc dlindependent_calloc #define public_iCOMALLOc dlindependent_comalloc #else /* USE_DL_PREFIX */ #define public_cALLOc calloc #define public_fREe free #define public_cFREe cfree #define public_mALLOc malloc #define public_mEMALIGn memalign #define public_rEALLOc realloc #define public_vALLOc valloc #define public_pVALLOc pvalloc #define public_mALLINFo mallinfo #define public_mALLOPt mallopt #define public_mTRIm malloc_trim #define public_mSTATs mstats #define public_mUSABLe malloc_usable_size #define public_iCALLOc independent_calloc #define public_iCOMALLOc independent_comalloc #endif /* USE_DL_PREFIX */ /* HAVE_MEMCPY should be defined if you are not otherwise using ANSI STD C, but still have memcpy and memset in your C library and want to use them in calloc and realloc. Otherwise simple macro versions are defined below. USE_MEMCPY should be defined as 1 if you actually want to have memset and memcpy called. People report that the macro versions are faster than libc versions on some systems. Even if USE_MEMCPY is set to 1, loops to copy/clear small chunks (of <= 36 bytes) are manually unrolled in realloc and calloc. */ #define HAVE_MEMCPY #ifndef USE_MEMCPY #ifdef HAVE_MEMCPY #define USE_MEMCPY 1 #else #define USE_MEMCPY 0 #endif #endif #if (__STD_C || defined(HAVE_MEMCPY)) #ifdef WIN32 /* On Win32 memset and memcpy are already declared in windows.h */ #else #if __STD_C void* memset(void*, int, size_t); void* memcpy(void*, const void*, size_t); #else Void_t* memset(); Void_t* memcpy(); #endif #endif #endif /* MALLOC_FAILURE_ACTION is the action to take before "return 0" when malloc fails to be able to return memory, either because memory is exhausted or because of illegal arguments. By default, sets errno if running on STD_C platform, else does nothing. */ #ifndef MALLOC_FAILURE_ACTION #if __STD_C #define MALLOC_FAILURE_ACTION \ errno = ENOMEM; #else #define MALLOC_FAILURE_ACTION #endif #endif /* MORECORE-related declarations. By default, rely on sbrk */ #ifdef LACKS_UNISTD_H #if !defined(__FreeBSD__) && !defined(__OpenBSD__) && !defined(__NetBSD__) #if __STD_C extern Void_t* sbrk(ptrdiff_t); #else extern Void_t* sbrk(); #endif #endif #endif /* MORECORE is the name of the routine to call to obtain more memory from the system. See below for general guidance on writing alternative MORECORE functions, as well as a version for WIN32 and a sample version for pre-OSX macos. */ #ifndef MORECORE #define MORECORE sbrk #endif /* MORECORE_FAILURE is the value returned upon failure of MORECORE as well as mmap. Since it cannot be an otherwise valid memory address, and must reflect values of standard sys calls, you probably ought not try to redefine it. */ #ifndef MORECORE_FAILURE #define MORECORE_FAILURE (-1) #endif /* If MORECORE_CONTIGUOUS is true, take advantage of fact that consecutive calls to MORECORE with positive arguments always return contiguous increasing addresses. This is true of unix sbrk. Even if not defined, when regions happen to be contiguous, malloc will permit allocations spanning regions obtained from different calls. But defining this when applicable enables some stronger consistency checks and space efficiencies. */ #ifndef MORECORE_CONTIGUOUS #define MORECORE_CONTIGUOUS 1 #endif /* Define MORECORE_CANNOT_TRIM if your version of 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. */ /* #define MORECORE_CANNOT_TRIM */ /* Define HAVE_MMAP as true to optionally make malloc() use mmap() to allocate very large blocks. These will be returned to the operating system immediately after a free(). Also, if mmap is available, it is used as a backup strategy in cases where MORECORE fails to provide space from system. This malloc is best tuned to work with mmap for large requests. If you do not have mmap, operations involving very large chunks (1MB or so) may be slower than you'd like. */ #ifndef HAVE_MMAP #define HAVE_MMAP 1 #endif #if HAVE_MMAP /* Standard unix mmap using /dev/zero clears memory so calloc doesn't need to. */ #ifndef MMAP_CLEARS #define MMAP_CLEARS 1 #endif #else /* no mmap */ #ifndef MMAP_CLEARS #define MMAP_CLEARS 0 #endif #endif /* MMAP_AS_MORECORE_SIZE is the minimum mmap size argument to use if sbrk fails, and mmap is used as a backup (which is done only if HAVE_MMAP). The value must be a multiple of page size. This backup strategy generally applies only when systems have "holes" in address space, so sbrk cannot perform contiguous expansion, but there is still space available on system. On systems for which this is known to be useful (i.e. most linux kernels), this occurs only when programs allocate huge amounts of memory. Between this, and the fact that mmap regions tend to be limited, the size should be large, to avoid too many mmap calls and thus avoid running out of kernel resources. */ #ifndef MMAP_AS_MORECORE_SIZE #define MMAP_AS_MORECORE_SIZE (1024 * 1024) #endif /* Define HAVE_MREMAP to make realloc() use mremap() to re-allocate large blocks. This is currently only possible on Linux with kernel versions newer than 1.3.77. */ #ifndef HAVE_MREMAP #ifdef linux #define HAVE_MREMAP 1 #else #define HAVE_MREMAP 0 #endif #endif /* HAVE_MMAP */ /* The system page size. To the extent possible, this malloc manages memory from the system in page-size units. Note that this value is cached during initialization into a field of malloc_state. So even if malloc_getpagesize is a function, it is only called once. The following mechanics for getpagesize were adapted from bsd/gnu getpagesize.h. If none of the system-probes here apply, a value of 4096 is used, which should be OK: If they don't apply, then using the actual value probably doesn't impact performance. */ #ifndef malloc_getpagesize #ifndef LACKS_UNISTD_H # include #endif # 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 # 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 (4096) # endif # endif # endif # endif # endif # endif # endif #endif /* 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 SVID/XPG compliant system that has a /usr/include/malloc.h defining struct mallinfo. (If you'd like to install such a thing yourself, cut out the preliminary declarations as described above and below and save them in a malloc.h file. But there's no compelling reason to bother to do this.) The main declaration needed is the mallinfo struct that is returned (by-copy) by mallinfo(). The SVID/XPG 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 an SVID2/XPG2 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 /* SVID2/XPG mallinfo structure */ struct mallinfo { int arena; /* non-mmapped space allocated from system */ int ordblks; /* number of free chunks */ int smblks; /* number of fastbin blocks */ int hblks; /* number of mmapped regions */ int hblkhd; /* space in mmapped regions */ int usmblks; /* maximum total allocated space */ int fsmblks; /* space available in freed fastbin blocks */ int uordblks; /* total allocated space */ int fordblks; /* total free space */ int keepcost; /* top-most, releasable (via malloc_trim) space */ }; /* SVID/XPG defines four standard parameter numbers for mallopt, normally defined in malloc.h. Only one of these (M_MXFAST) is used in this malloc. The others (M_NLBLKS, M_GRAIN, M_KEEP) don't apply, so setting them has no effect. But this malloc also supports other options in mallopt described below. */ #endif /* ---------- description of public routines ------------ */ /* malloc(size_t n) Returns a pointer to a newly allocated chunk of at least n bytes, or null if no space is available. Additionally, on failure, errno is set to ENOMEM on ANSI C systems. If n is zero, malloc returns a minumum-sized chunk. (The minimum size is 16 bytes on most 32bit systems, and 24 or 32 bytes on 64bit systems.) On most systems, size_t is an unsigned type, so calls with negative arguments 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. */ #if __STD_C Void_t* public_mALLOc(size_t); #else Void_t* public_mALLOc(); #endif /* free(Void_t* 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. It can have arbitrary (i.e., bad!) effects if p has already been freed. Unless disabled (using mallopt), freeing very large spaces will when possible, automatically trigger operations that give back unused memory to the system, thus reducing program footprint. */ #if __STD_C void public_fREe(Void_t*); #else void public_fREe(); #endif /* calloc(size_t n_elements, size_t element_size); Returns a pointer to n_elements * element_size bytes, with all locations set to zero. */ #if __STD_C Void_t* public_cALLOc(size_t, size_t); #else Void_t* public_cALLOc(); #endif /* realloc(Void_t* 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 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. Unless the #define REALLOC_ZERO_BYTES_FREES is set, realloc with a size argument of zero (re)allocates a minimum-sized chunk. Large chunks that were internally obtained via mmap will always be reallocated using malloc-copy-free sequences unless the system supports MREMAP (currently only linux). The old unix realloc convention of allowing the last-free'd chunk to be used as an argument to realloc is not supported. */ #if __STD_C Void_t* public_rEALLOc(Void_t*, size_t); #else Void_t* public_rEALLOc(); #endif /* 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. */ #if __STD_C Void_t* public_mEMALIGn(size_t, size_t); #else Void_t* public_mEMALIGn(); #endif /* 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. */ #if __STD_C Void_t* public_vALLOc(size_t); #else Void_t* public_vALLOc(); #endif /* 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. Only one of these (M_MXFAST) is used in this malloc. The others (M_NLBLKS, M_GRAIN, M_KEEP) don't apply, so setting them has no effect. But this malloc also supports four 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_MXFAST 1 64 0-80 (0 disables fastbins) M_TRIM_THRESHOLD -1 256*1024 any (-1U disables trimming) M_TOP_PAD -2 0 any M_MMAP_THRESHOLD -3 256*1024 any (or 0 if no MMAP support) M_MMAP_MAX -4 65536 any (0 disables use of mmap) */ #if __STD_C int public_mALLOPt(int, int); #else int public_mALLOPt(); #endif /* 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: the number of fastbin blocks (i.e., small chunks that have been freed but not use resused or consolidated) 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: total bytes held in fastbin blocks 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. */ #if __STD_C struct mallinfo public_mALLINFo(void); #else struct mallinfo public_mALLINFo(); #endif /* independent_calloc(size_t n_elements, size_t element_size, Void_t* 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; } */ #if __STD_C Void_t** public_iCALLOc(size_t, size_t, Void_t**); #else Void_t** public_iCALLOc(); #endif /* independent_comalloc(size_t n_elements, size_t sizes[], Void_t* 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. */ #if __STD_C Void_t** public_iCOMALLOc(size_t, size_t*, Void_t**); #else Void_t** public_iCOMALLOc(); #endif /* pvalloc(size_t n); Equivalent to valloc(minimum-page-that-holds(n)), that is, round up n to nearest pagesize. */ #if __STD_C Void_t* public_pVALLOc(size_t); #else Void_t* public_pVALLOc(); #endif /* cfree(Void_t* p); Equivalent to free(p). cfree is needed/defined on some systems that pair it with calloc, for odd historical reasons (such as: cfree is used in example code in the first edition of K&R). */ #if __STD_C STATUS public_cFREe(char *); #else STATUS public_cFREe(); #endif /* 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. 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 (one page or less). 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. On systems that do not support "negative sbrks", it will always rreturn 0. */ #if __STD_C int public_mTRIm(size_t); #else int public_mTRIm(); #endif /* malloc_usable_size(Void_t* 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); */ #if __STD_C size_t public_mUSABLe(Void_t*); #else size_t public_mUSABLe(); #endif /* 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. */ #if __STD_C void public_mSTATs(); #else void public_mSTATs(); #endif /* mallopt tuning options */ /* M_MXFAST is the maximum request size used for "fastbins", special bins that hold returned chunks without consolidating their spaces. This enables future requests for chunks of the same size to be handled very quickly, but can increase fragmentation, and thus increase the overall memory footprint of a program. This malloc manages fastbins very conservatively yet still efficiently, so fragmentation is rarely a problem for values less than or equal to the default. The maximum supported value of MXFAST is 80. You wouldn't want it any higher than this anyway. Fastbins are designed especially for use with many small structs, objects or strings -- the default handles structs/objects/arrays with sizes up to 16 4byte fields, or small strings representing words, tokens, etc. Using fastbins for larger objects normally worsens fragmentation without improving speed. M_MXFAST is set in REQUEST size units. It is internally used in chunksize units, which adds padding and alignment. You can reduce M_MXFAST to 0 to disable all use of fastbins. This causes the malloc algorithm to be a closer approximation of fifo-best-fit in all cases, not just for larger requests, but will generally cause it to be slower. */ /* M_MXFAST is a standard SVID/XPG tuning option, usually listed in malloc.h */ #ifndef M_MXFAST #define M_MXFAST 1 #endif #ifndef DEFAULT_MXFAST #define DEFAULT_MXFAST 64 #endif /* M_TRIM_THRESHOLD is 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. 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. The trim threshold and the mmap control parameters (see below) can be traded off with one another. Trimming and mmapping are two different ways of releasing unused memory back to the system. Between these two, it is often possible to keep system-level demands of a long-lived program down to a bare minimum. For example, in one test suite of sessions measuring the XF86 X server on Linux, using a trim threshold of 128K and a mmap threshold of 192K led to near-minimal long term resource consumption. If you are using this malloc in a long-lived program, it should pay to experiment with these values. 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's worth it to tune for trimming rather tham memory mapping 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. And in well-behaved long-lived programs, controlling release of large blocks via trimming versus mapping is usually faster. However, in most programs, these parameters serve mainly as protection against the system-level effects of carrying around massive amounts of unneeded memory. Since frequent calls to sbrk, mmap, and munmap otherwise degrade performance, the default parameters are set to relatively high values that serve only as safeguards. The trim value must be greater than page size to have any useful effect. To disable trimming completely, you can set to (unsigned long)(-1) Trim settings interact with fastbin (MXFAST) settings: Unless TRIM_FASTBINS is defined, automatic trimming never takes place upon freeing a chunk with size less than or equal to MXFAST. Trimming is instead delayed until subsequent freeing of larger chunks. However, you can still force an attempted trim by calling malloc_trim. Also, trimming is not generally possible in cases where the main arena is obtained via mmap. 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. */ #define M_TRIM_THRESHOLD -1 #ifndef DEFAULT_TRIM_THRESHOLD #define DEFAULT_TRIM_THRESHOLD (256 * 1024) #endif /* M_TOP_PAD is the amount of extra `padding' space to allocate or retain whenever sbrk is called. It is used in two ways internally: * When sbrk is called to extend the top of the arena to satisfy a new malloc request, this much padding is added to the sbrk request. * When malloc_trim is called automatically from free(), it is used as the `pad' argument. In both cases, the actual amount of padding is rounded so that the end of the arena is always a system page boundary. The main reason for using padding is to avoid calling sbrk so often. Having even a small pad greatly reduces the likelihood that nearly every malloc request during program start-up (or after trimming) will invoke sbrk, which needlessly wastes time. Automatic rounding-up to page-size units is normally sufficient to avoid measurable overhead, so the default is 0. However, in systems where sbrk is relatively slow, it can pay to increase this value, at the expense of carrying around more memory than the program needs. */ #define M_TOP_PAD -2 #ifndef DEFAULT_TOP_PAD #define DEFAULT_TOP_PAD (0) #endif /* M_MMAP_THRESHOLD is the request size threshold for using mmap() to 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: 1. 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. 2. Mapped memory can never become `locked' between other chunks, as can happen with normally allocated chunks, which means that even trimming via malloc_trim would not release them. 3. On some systems with "holes" in address spaces, mmap can obtain memory that sbrk cannot. However, it has the disadvantages that: 1. The space cannot be reclaimed, consolidated, and then used to service later requests, as happens with normal chunks. 2. It can lead to more wastage because of mmap page alignment requirements 3. It causes malloc performance to be more dependent on host system memory management support routines which may vary in implementation quality and may impose arbitrary limitations. Generally, servicing a request via normal malloc steps is faster than going through a system's mmap. The advantages of mmap nearly always outweigh disadvantages for "large" chunks, but the value of "large" varies across systems. The default is an empirically derived value that works well in most systems. */ #define M_MMAP_THRESHOLD -3 #ifndef DEFAULT_MMAP_THRESHOLD #define DEFAULT_MMAP_THRESHOLD (256 * 1024) #endif /* M_MMAP_MAX is the maximum number of requests to simultaneously service using mmap. This parameter exists because . Some systems have a limited number of internal tables for use by mmap, and using more than a few of them may degrade performance. The default is set to a value that serves only as a safeguard. Setting to 0 disables use of mmap for servicing large requests. If HAVE_MMAP is not set, the default value is 0, and attempts to set it to non-zero values in mallopt will fail. */ #define M_MMAP_MAX -4 #ifndef DEFAULT_MMAP_MAX #if HAVE_MMAP #define DEFAULT_MMAP_MAX (65536) #else #define DEFAULT_MMAP_MAX (0) #endif #endif /* vxworks */ void *vxSbrk(int size) { void *tmp; static void *previous_top; if(size) { if(!(tmp = memPartAlloc(memSysPartId, size+MALLOC_ALIGNMENT))) return (void*)-1; /* Must be aligned. */ tmp = (void*)(((int)tmp + MALLOC_ALIGN_MASK) & ~MALLOC_ALIGN_MASK); previous_top = (void*)((int)tmp + size + MALLOC_ALIGNMENT); return tmp; } return previous_top; } #ifdef __cplusplus }; /* end of extern "C" */ #endif #endif /* MALLOC_272_H */