From a5f479787f64de61a1c58975adb806d794a1a63d Mon Sep 17 00:00:00 2001 From: terminx Date: Mon, 15 Oct 2012 00:17:30 +0000 Subject: [PATCH] Remove built-in copy of nedmalloc and update nedmalloc.dll. Note that the built-in copy of nedmalloc hasn't been updated or enabled in a really long time as modern system allocators (Windows 7 and Linux 3.x at least) are no longer consistently beat by nedmalloc (but nor are they consistently faster). So, the dll remains for users of Windows XP because it may still improve performance there (while not likely degrading it on Vista/7). git-svn-id: https://svn.eduke32.com/eduke32@3086 1a8010ca-5511-0410-912e-c29ae57300e0 --- polymer/eduke32/Makefile.common | 1 - polymer/eduke32/build/Makefile | 7 - polymer/eduke32/build/Makefile.deps | 1 - polymer/eduke32/build/Makefile.msvc | 32 +- polymer/eduke32/build/Makefile.shared | 5 - polymer/eduke32/build/include/compat.h | 13 - polymer/eduke32/build/include/malloc.c.h | 5871 --------------------- polymer/eduke32/build/include/nedmalloc.h | 1919 +++++-- polymer/eduke32/build/src/baselayer.c | 2 +- polymer/eduke32/build/src/compat.c | 12 - polymer/eduke32/build/src/engine.c | 13 +- polymer/eduke32/build/src/nedmalloc.c | 1603 ------ polymer/eduke32/build/src/sdlayer.c | 15 +- polymer/eduke32/build/src/winlayer.c | 45 - polymer/eduke32/eduke32.vcproj | 8 - polymer/eduke32/eduke32.vcxproj | 6 +- polymer/eduke32/eduke32.vcxproj.filters | 14 +- polymer/eduke32/nedmalloc.dll | Bin 88576 -> 87040 bytes 18 files changed, 1650 insertions(+), 7917 deletions(-) delete mode 100644 polymer/eduke32/build/include/malloc.c.h delete mode 100644 polymer/eduke32/build/src/nedmalloc.c diff --git a/polymer/eduke32/Makefile.common b/polymer/eduke32/Makefile.common index 810dfd717..b736c078a 100644 --- a/polymer/eduke32/Makefile.common +++ b/polymer/eduke32/Makefile.common @@ -31,7 +31,6 @@ NOASM = 0 LINKED_GTK = 0 BUILD32_ON_64 ?= 0 # DO NOT SET THIS TO 1 AND COMMIT IT. -NEDMALLOC = 0 USE_LIBPNG ?= 1 USE_LIBVPX ?= 1 diff --git a/polymer/eduke32/build/Makefile b/polymer/eduke32/build/Makefile index 7c7cc1edc..a3ebfff8a 100644 --- a/polymer/eduke32/build/Makefile +++ b/polymer/eduke32/build/Makefile @@ -60,9 +60,6 @@ endif UTILLIBS= -lm # -lpthread UTILADDOBJS= -ifneq (0,$(NEDMALLOC)) - UTILADDOBJS+= $(OBJ)/nedmalloc.$o -endif ENGINEOBJS= ifeq (0,$(NOASM)) @@ -101,10 +98,6 @@ ifeq (1,$(POLYMER)) ENGINEOBJS+= $(OBJ)/polymer.$o endif -ifeq (1,$(NEDMALLOC)) - ENGINEOBJS+= $(OBJ)/nedmalloc.$o -endif - EDITOROBJS=$(OBJ)/build.$o \ $(OBJ)/config.$o diff --git a/polymer/eduke32/build/Makefile.deps b/polymer/eduke32/build/Makefile.deps index 0b3846824..fa7c3fd19 100644 --- a/polymer/eduke32/build/Makefile.deps +++ b/polymer/eduke32/build/Makefile.deps @@ -28,7 +28,6 @@ $(OBJ)/winlayer.$o: $(SRC)/winlayer.c $(INC)/compat.h $(INC)/winlayer.h $(INC)/b $(OBJ)/gtkbits.$o: $(SRC)/gtkbits.c $(INC)/baselayer.h $(INC)/build.h $(INC)/dynamicgtk.h $(OBJ)/dynamicgtk.$o: $(SRC)/dynamicgtk.c $(INC)/dynamicgtk.h $(OBJ)/polymer.$o: $(SRC)/polymer.c $(INC)/polymer.h $(INC)/compat.h $(INC)/build.h $(INC)/glbuild.h $(INC)/osd.h $(INC)/pragmas.h $(INC)/mdsprite.h $(INC)/polymost.h -$(OBJ)/nedmalloc.$o: $(SRC)/nedmalloc.c $(INC)/nedmalloc.h $(INC)/malloc.c.h $(OBJ)/mutex.$o: $(SRC)/mutex.c $(INC)/mutex.h $(OBJ)/rawinput.$o: $(SRC)/rawinput.c $(INC)/rawinput.h diff --git a/polymer/eduke32/build/Makefile.msvc b/polymer/eduke32/build/Makefile.msvc index 976eecdd9..6809462bd 100644 --- a/polymer/eduke32/build/Makefile.msvc +++ b/polymer/eduke32/build/Makefile.msvc @@ -9,7 +9,7 @@ OBJ=obj.msc !endif INC=include\ # !ifndef CFLAGS -CFLAGS=/DUSE_OPENGL /DPOLYMER # /DNEDMALLOC +CFLAGS=/DUSE_OPENGL /DPOLYMER !endif o=obj @@ -131,59 +131,59 @@ $(OBJ)\$(EDITORLIB): $(EDITOROBJS) lib $(flags_lib) /out:$@ /nologo $** # the tools -kextract$(EXESUFFIX): $(OBJ)\kextract.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(OBJ)\nedmalloc.$o +kextract$(EXESUFFIX): $(OBJ)\kextract.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(LINK) /OUT:$@ /SUBSYSTEM:CONSOLE $(flags_link) /MAP $** $(LIBS) $(MT) -manifest $@.manifest -outputresource:$@ -kgroup$(EXESUFFIX): $(OBJ)\kgroup.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(OBJ)\nedmalloc.$o +kgroup$(EXESUFFIX): $(OBJ)\kgroup.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(LINK) /OUT:$@ /SUBSYSTEM:CONSOLE $(flags_link) /MAP $** $(LIBS) $(MT) -manifest $@.manifest -outputresource:$@ -transpal$(EXESUFFIX): $(OBJ)\transpal.$o $(OBJ)\pragmas.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(OBJ)\nedmalloc.$o +transpal$(EXESUFFIX): $(OBJ)\transpal.$o $(OBJ)\pragmas.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(LINK) /OUT:$@ /SUBSYSTEM:CONSOLE $(flags_link) /MAP $** $(LIBS) $(MT) -manifest $@.manifest -outputresource:$@ -wad2map$(EXESUFFIX): $(OBJ)\wad2map.$o $(OBJ)\pragmas.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(OBJ)\nedmalloc.$o +wad2map$(EXESUFFIX): $(OBJ)\wad2map.$o $(OBJ)\pragmas.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(LINK) /OUT:$@ /SUBSYSTEM:CONSOLE $(flags_link) /MAP $** $(LIBS) $(MT) -manifest $@.manifest -outputresource:$@ -wad2art$(EXESUFFIX): $(OBJ)\wad2art.$o $(OBJ)\pragmas.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(OBJ)\nedmalloc.$o +wad2art$(EXESUFFIX): $(OBJ)\wad2art.$o $(OBJ)\pragmas.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(LINK) /OUT:$@ /SUBSYSTEM:CONSOLE $(flags_link) /MAP $** $(LIBS) $(MT) -manifest $@.manifest -outputresource:$@ -kmd2tool$(EXESUFFIX): $(OBJ)\kmd2tool.$o $(OBJ)\nedmalloc.$o +kmd2tool$(EXESUFFIX): $(OBJ)\kmd2tool.$o $(LINK) /OUT:$@ /SUBSYSTEM:CONSOLE $(flags_link) /MAP $** $(LIBS) $(MT) -manifest $@.manifest -outputresource:$@ -md2tool$(EXESUFFIX): $(OBJ)\md2tool.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(OBJ)\nedmalloc.$o +md2tool$(EXESUFFIX): $(OBJ)\md2tool.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(LINK) /OUT:$@ /SUBSYSTEM:CONSOLE $(flags_link) /MAP $** $(LIBS) $(MT) -manifest $@.manifest -outputresource:$@ -generateicon$(EXESUFFIX): $(OBJ)\generateicon.$o $(OBJ)\compat.$o $(OBJ)\pragmas.$o $(OBJ)\kplib.$o $(OBJ)\cache1d.$o $(OBJ)\compat_tools.$o $(OBJ)\nedmalloc.$o +generateicon$(EXESUFFIX): $(OBJ)\generateicon.$o $(OBJ)\compat.$o $(OBJ)\pragmas.$o $(OBJ)\kplib.$o $(OBJ)\cache1d.$o $(OBJ)\compat_tools.$o $(LINK) /OUT:$@ /SUBSYSTEM:CONSOLE $(flags_link) /MAP $** $(LIBS) $(MT) -manifest $@.manifest -outputresource:$@ -cacheinfo$(EXESUFFIX): $(OBJ)\cacheinfo.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(OBJ)\nedmalloc.$o +cacheinfo$(EXESUFFIX): $(OBJ)\cacheinfo.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(LINK) /OUT:$@ /SUBSYSTEM:CONSOLE $(flags_link) /MAP $** $(LIBS) $(MT) -manifest $@.manifest -outputresource:$@ -arttool$(EXESUFFIX): $(OBJ)\arttool.$o $(OBJ)\nedmalloc.$o +arttool$(EXESUFFIX): $(OBJ)\arttool.$o $(LINK) /OUT:$@ /SUBSYSTEM:CONSOLE $(flags_link) /MAP $** $(LIBS) $(MT) -manifest $@.manifest -outputresource:$@ -givedepth$(EXESUFFIX): $(OBJ)\givedepth.$o $(OBJ)\nedmalloc.$o +givedepth$(EXESUFFIX): $(OBJ)\givedepth.$o $(LINK) /OUT:$@ /SUBSYSTEM:CONSOLE $(flags_link) /MAP $** $(LIBS) $(MT) -manifest $@.manifest -outputresource:$@ -mkpalette$(EXESUFFIX): $(OBJ)\mkpalette.$o $(OBJ)\nedmalloc.$o +mkpalette$(EXESUFFIX): $(OBJ)\mkpalette.$o $(LINK) /OUT:$@ /SUBSYSTEM:CONSOLE $(flags_link) /MAP $** $(LIBS) $(MT) -manifest $@.manifest -outputresource:$@ -unpackssi$(EXESUFFIX): $(OBJ)\unpackssi.$o $(OBJ)\nedmalloc.$o +unpackssi$(EXESUFFIX): $(OBJ)\unpackssi.$o $(LINK) /OUT:$@ /SUBSYSTEM:CONSOLE $(flags_link) /MAP $** $(LIBS) $(MT) -manifest $@.manifest -outputresource:$@ -bsuite$(EXESUFFIX): $(OBJ)\bsuite.$o $(OBJ)\nedmalloc.$o +bsuite$(EXESUFFIX): $(OBJ)\bsuite.$o $(LINK) /OUT:$@ /SUBSYSTEM:CONSOLE $(flags_link) /MAP $** $(LIBS) $(MT) -manifest $@.manifest -outputresource:$@ @@ -192,7 +192,7 @@ bsuite$(EXESUFFIX): $(OBJ)\bsuite.$o $(OBJ)\nedmalloc.$o # PHONIES clean: - -del /Q $(ENGINEOBJS) $(EDITOROBJS) $(OBJ)\kextract.$o $(OBJ)\kgroup.$o $(OBJ)\transpal.$o $(OBJ)\wad2art.$o $(OBJ)\wad2map.$o $(OBJ)\kmd2tool.$o $(OBJ)\md2tool.$o $(OBJ)\generateicon.$o $(OBJ)\cacheinfo.$o $(OBJ)\arttool.$o $(OBJ)\givedepth.$o $(OBJ)\mkpalette.$o $(OBJ)\unpackssi.$o $(OBJ)\bsuite.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(OBJ)\pragmas.$o $(OBJ)\kplib.$o $(OBJ)\cache1d.$o $(OBJ)\nedmalloc.$o + -del /Q $(ENGINEOBJS) $(EDITOROBJS) $(OBJ)\kextract.$o $(OBJ)\kgroup.$o $(OBJ)\transpal.$o $(OBJ)\wad2art.$o $(OBJ)\wad2map.$o $(OBJ)\kmd2tool.$o $(OBJ)\md2tool.$o $(OBJ)\generateicon.$o $(OBJ)\cacheinfo.$o $(OBJ)\arttool.$o $(OBJ)\givedepth.$o $(OBJ)\mkpalette.$o $(OBJ)\unpackssi.$o $(OBJ)\bsuite.$o $(OBJ)\compat.$o $(OBJ)\compat_tools.$o $(OBJ)\pragmas.$o $(OBJ)\kplib.$o $(OBJ)\cache1d.$o veryclean: clean -del /Q $(OBJ)\$(ENGINELIB) $(OBJ)\$(EDITORLIB) $(UTILS) *.map *.manifest *.pdb diff --git a/polymer/eduke32/build/Makefile.shared b/polymer/eduke32/build/Makefile.shared index 51cd9913f..18b1499dc 100644 --- a/polymer/eduke32/build/Makefile.shared +++ b/polymer/eduke32/build/Makefile.shared @@ -163,7 +163,6 @@ ifeq ($(PLATFORM),BSD) ifneq ($(findstring i386, $(shell uname -m)), i386) override NOASM=1 endif - override NEDMALLOC=0 STDCPPLIB=-lstdc++ endif ifeq ($(PLATFORM),BEOS) @@ -277,10 +276,6 @@ ifneq (0,$(POLYMER)) endif endif -ifneq (0,$(NEDMALLOC)) - BUILDCFLAGS+= -DNEDMALLOC -endif - ifneq ($(EXESUFFIX_OVERRIDE),) EXESUFFIX=$(EXESUFFIX_OVERRIDE) endif diff --git a/polymer/eduke32/build/include/compat.h b/polymer/eduke32/build/include/compat.h index 11c12ff1f..aa58f7ba7 100644 --- a/polymer/eduke32/build/include/compat.h +++ b/polymer/eduke32/build/include/compat.h @@ -39,10 +39,6 @@ # endif #endif -#ifdef NEDMALLOC -# include "nedmalloc.h" -#endif - #ifndef TRUE # define TRUE 1 #endif @@ -476,21 +472,12 @@ static inline uint16_t system_15bit_rand(void) { return ((uint16_t)rand())&0x7ff # define Bassert assert # define Brand rand # define Balloca alloca -# ifdef NEDMALLOC -# define Bmalloc nedmalloc -# define Bcalloc nedcalloc -# define Brealloc nedrealloc -# define Bfree nedfree -# define Bstrdup nedstrdup -# define Bmemalign nedmemalign -# else # define Bmalloc malloc # define Bcalloc calloc # define Brealloc realloc # define Bfree free # define Bstrdup strdup # define Bmemalign memalign -# endif # define Bopen open # define Bclose close # define Bwrite write diff --git a/polymer/eduke32/build/include/malloc.c.h b/polymer/eduke32/build/include/malloc.c.h deleted file mode 100644 index 4a1bb7adb..000000000 --- a/polymer/eduke32/build/include/malloc.c.h +++ /dev/null @@ -1,5871 +0,0 @@ -/* - This is a version (aka dlmalloc) of malloc/free/realloc written by - Doug Lea and released to the public domain, as explained at - http://creativecommons.org/licenses/publicdomain. Send questions, - comments, complaints, performance data, etc to dl@cs.oswego.edu - -* Version 2.8.4 Wed May 27 09:56:23 2009 Doug Lea (dl at gee) - - Note: There may be an updated version of this malloc obtainable at - ftp://gee.cs.oswego.edu/pub/misc/malloc.c - Check before installing! - -* Quickstart - - This library is all in one file to simplify the most common usage: - ftp it, compile it (-O3), and link it into another program. All of - the compile-time options default to reasonable values for use on - most platforms. You might later want to step through various - compile-time and dynamic tuning options. - - For convenience, an include file for code using this malloc is at: - ftp://gee.cs.oswego.edu/pub/misc/malloc-2.8.4.h - You don't really need this .h file unless you call functions not - defined in your system include files. The .h file contains only the - excerpts from this file needed for using this malloc on ANSI C/C++ - systems, so long as you haven't changed compile-time options about - naming and tuning parameters. If you do, then you can create your - own malloc.h that does include all settings by cutting at the point - indicated below. Note that you may already by default be using a C - library containing a malloc that is based on some version of this - malloc (for example in linux). You might still want to use the one - in this file to customize settings or to avoid overheads associated - with library versions. - -* Vital statistics: - - Supported pointer/size_t representation: 4 or 8 bytes - size_t MUST be an unsigned type of the same width as - pointers. (If you are using an ancient system that declares - size_t as a signed type, or need it to be a different width - than pointers, you can use a previous release of this malloc - (e.g. 2.7.2) supporting these.) - - Alignment: 8 bytes (default) - This suffices for nearly all current machines and C compilers. - However, you can define MALLOC_ALIGNMENT to be wider than this - if necessary (up to 128bytes), at the expense of using more space. - - Minimum overhead per allocated chunk: 4 or 8 bytes (if 4byte sizes) - 8 or 16 bytes (if 8byte sizes) - Each malloced chunk has a hidden word of overhead holding size - and status information, and additional cross-check word - if FOOTERS is defined. - - Minimum allocated size: 4-byte ptrs: 16 bytes (including overhead) - 8-byte ptrs: 32 bytes (including overhead) - - Even a request for zero bytes (i.e., malloc(0)) returns a - pointer to something of the minimum allocatable size. - The maximum overhead wastage (i.e., number of extra bytes - allocated than were requested in malloc) is less than or equal - to the minimum size, except for requests >= mmap_threshold that - are serviced via mmap(), where the worst case wastage is about - 32 bytes plus the remainder from a system page (the minimal - mmap unit); typically 4096 or 8192 bytes. - - Security: static-safe; optionally more or less - The "security" of malloc refers to the ability of malicious - code to accentuate the effects of errors (for example, freeing - space that is not currently malloc'ed or overwriting past the - ends of chunks) in code that calls malloc. This malloc - guarantees not to modify any memory locations below the base of - heap, i.e., static variables, even in the presence of usage - errors. The routines additionally detect most improper frees - and reallocs. All this holds as long as the static bookkeeping - for malloc itself is not corrupted by some other means. This - is only one aspect of security -- these checks do not, and - cannot, detect all possible programming errors. - - If FOOTERS is defined nonzero, then each allocated chunk - carries an additional check word to verify that it was malloced - from its space. These check words are the same within each - execution of a program using malloc, but differ across - executions, so externally crafted fake chunks cannot be - freed. This improves security by rejecting frees/reallocs that - could corrupt heap memory, in addition to the checks preventing - writes to statics that are always on. This may further improve - security at the expense of time and space overhead. (Note that - FOOTERS may also be worth using with MSPACES.) - - By default detected errors cause the program to abort (calling - "abort()"). You can override this to instead proceed past - errors by defining PROCEED_ON_ERROR. In this case, a bad free - has no effect, and a malloc that encounters a bad address - caused by user overwrites will ignore the bad address by - dropping pointers and indices to all known memory. This may - be appropriate for programs that should continue if at all - possible in the face of programming errors, although they may - run out of memory because dropped memory is never reclaimed. - - If you don't like either of these options, you can define - CORRUPTION_ERROR_ACTION and USAGE_ERROR_ACTION to do anything - else. And if if you are sure that your program using malloc has - no errors or vulnerabilities, you can define INSECURE to 1, - which might (or might not) provide a small performance improvement. - - Thread-safety: NOT thread-safe unless USE_LOCKS defined - When USE_LOCKS is defined, each public call to malloc, free, - etc is surrounded with either a pthread mutex or a win32 - spinlock (depending on WIN32). This is not especially fast, and - can be a major bottleneck. It is designed only to provide - minimal protection in concurrent environments, and to provide a - basis for extensions. If you are using malloc in a concurrent - program, consider instead using nedmalloc - (http://www.nedprod.com/programs/portable/nedmalloc/) or - ptmalloc (See http://www.malloc.de), which are derived - from versions of this malloc. - - System requirements: Any combination of MORECORE and/or MMAP/MUNMAP - This malloc can use unix sbrk or any emulation (invoked using - the CALL_MORECORE macro) and/or mmap/munmap or any emulation - (invoked using CALL_MMAP/CALL_MUNMAP) to get and release system - memory. On most unix systems, it tends to work best if both - MORECORE and MMAP are enabled. On Win32, it uses emulations - based on VirtualAlloc. It also uses common C library functions - like memset. - - Compliance: I believe it is compliant with the Single Unix Specification - (See http://www.unix.org). Also SVID/XPG, ANSI C, and probably - others as well. - -* Overview of algorithms - - This is not the fastest, most space-conserving, most portable, or - most tunable malloc ever written. However it is among the fastest - while also being among the most space-conserving, portable and - tunable. Consistent balance across these factors results in a good - general-purpose allocator for malloc-intensive programs. - - In most ways, this malloc is a best-fit allocator. Generally, it - chooses the best-fitting existing chunk for a request, with ties - broken in approximately least-recently-used order. (This strategy - normally maintains low fragmentation.) However, for requests less - than 256bytes, it deviates from best-fit when there is not an - exactly fitting available chunk by preferring to use space adjacent - to that used for the previous small request, as well as by breaking - ties in approximately most-recently-used order. (These enhance - locality of series of small allocations.) And for very large requests - (>= 256Kb by default), it relies on system memory mapping - facilities, if supported. (This helps avoid carrying around and - possibly fragmenting memory used only for large chunks.) - - All operations (except malloc_stats and mallinfo) have execution - times that are bounded by a constant factor of the number of bits in - a size_t, not counting any clearing in calloc or copying in realloc, - or actions surrounding MORECORE and MMAP that have times - proportional to the number of non-contiguous regions returned by - system allocation routines, which is often just 1. In real-time - applications, you can optionally suppress segment traversals using - NO_SEGMENT_TRAVERSAL, which assures bounded execution even when - system allocators return non-contiguous spaces, at the typical - expense of carrying around more memory and increased fragmentation. - - The implementation is not very modular and seriously overuses - macros. Perhaps someday all C compilers will do as good a job - inlining modular code as can now be done by brute-force expansion, - but now, enough of them seem not to. - - Some compilers issue a lot of warnings about code that is - dead/unreachable only on some platforms, and also about intentional - uses of negation on unsigned types. All known cases of each can be - ignored. - - For a longer but out of date high-level description, see - http://gee.cs.oswego.edu/dl/html/malloc.html - -* MSPACES - If MSPACES is defined, then in addition to malloc, free, etc., - this file also defines mspace_malloc, mspace_free, etc. These - are versions of malloc routines that take an "mspace" argument - obtained using create_mspace, to control all internal bookkeeping. - If ONLY_MSPACES is defined, only these versions are compiled. - So if you would like to use this allocator for only some allocations, - and your system malloc for others, you can compile with - ONLY_MSPACES and then do something like... - static mspace mymspace = create_mspace(0,0); // for example - #define mymalloc(bytes) mspace_malloc(mymspace, bytes) - - (Note: If you only need one instance of an mspace, you can instead - use "USE_DL_PREFIX" to relabel the global malloc.) - - You can similarly create thread-local allocators by storing - mspaces as thread-locals. For example: - static __thread mspace tlms = 0; - void* tlmalloc(size_t bytes) { - if (tlms == 0) tlms = create_mspace(0, 0); - return mspace_malloc(tlms, bytes); - } - void tlfree(void* mem) { mspace_free(tlms, mem); } - - Unless FOOTERS is defined, each mspace is completely independent. - You cannot allocate from one and free to another (although - conformance is only weakly checked, so usage errors are not always - caught). If FOOTERS is defined, then each chunk carries around a tag - indicating its originating mspace, and frees are directed to their - originating spaces. - - ------------------------- Compile-time options --------------------------- - -Be careful in setting #define values for numerical constants of type -size_t. On some systems, literal values are not automatically extended -to size_t precision unless they are explicitly casted. You can also -use the symbolic values MAX_SIZE_T, SIZE_T_ONE, etc below. - -WIN32 default: defined if _WIN32 defined - Defining WIN32 sets up defaults for MS environment and compilers. - Otherwise defaults are for unix. Beware that there seem to be some - cases where this malloc might not be a pure drop-in replacement for - Win32 malloc: Random-looking failures from Win32 GDI API's (eg; - SetDIBits()) may be due to bugs in some video driver implementations - when pixel buffers are malloc()ed, and the region spans more than - one VirtualAlloc()ed region. Because dlmalloc uses a small (64Kb) - default granularity, pixel buffers may straddle virtual allocation - regions more often than when using the Microsoft allocator. You can - avoid this by using VirtualAlloc() and VirtualFree() for all pixel - buffers rather than using malloc(). If this is not possible, - recompile this malloc with a larger DEFAULT_GRANULARITY. - -MALLOC_ALIGNMENT default: (size_t)8 - Controls the minimum alignment for malloc'ed chunks. It must be a - power of two and at least 8, even on machines for which smaller - alignments would suffice. It may be defined as larger than this - though. Note however that code and data structures are optimized for - the case of 8-byte alignment. - -MSPACES default: 0 (false) - If true, compile in support for independent allocation spaces. - This is only supported if HAVE_MMAP is true. - -ONLY_MSPACES default: 0 (false) - If true, only compile in mspace versions, not regular versions. - -USE_LOCKS default: 0 (false) - Causes each call to each public routine to be surrounded with - pthread or WIN32 mutex lock/unlock. (If set true, this can be - overridden on a per-mspace basis for mspace versions.) If set to a - non-zero value other than 1, locks are used, but their - implementation is left out, so lock functions must be supplied manually, - as described below. - -USE_SPIN_LOCKS default: 1 iff USE_LOCKS and on x86 using gcc or MSC - If true, uses custom spin locks for locking. This is currently - supported only for x86 platforms using gcc or recent MS compilers. - Otherwise, posix locks or win32 critical sections are used. - -FOOTERS default: 0 - If true, provide extra checking and dispatching by placing - information in the footers of allocated chunks. This adds - space and time overhead. - -INSECURE default: 0 - If true, omit checks for usage errors and heap space overwrites. - -USE_DL_PREFIX default: NOT defined - Causes compiler to prefix all public routines with the string 'dl'. - This can be useful when you only want to use this malloc in one part - of a program, using your regular system malloc elsewhere. - -ABORT default: defined as abort() - Defines how to abort on failed checks. On most systems, a failed - check cannot die with an "assert" or even print an informative - message, because the underlying print routines in turn call malloc, - which will fail again. Generally, the best policy is to simply call - abort(). It's not very useful to do more than this because many - errors due to overwriting will show up as address faults (null, odd - addresses etc) rather than malloc-triggered checks, so will also - abort. Also, most compilers know that abort() does not return, so - can better optimize code conditionally calling it. - -PROCEED_ON_ERROR default: defined as 0 (false) - Controls whether detected bad addresses cause them to bypassed - rather than aborting. If set, detected bad arguments to free and - realloc are ignored. And all bookkeeping information is zeroed out - upon a detected overwrite of freed heap space, thus losing the - ability to ever return it from malloc again, but enabling the - application to proceed. If PROCEED_ON_ERROR is defined, the - static variable malloc_corruption_error_count is compiled in - and can be examined to see if errors have occurred. This option - generates slower code than the default abort policy. - -DEBUG default: NOT defined - The DEBUG setting is mainly intended for people trying to modify - this code or diagnose problems when porting to new platforms. - However, it may also be able to better isolate user errors than just - using runtime checks. The assertions in the check routines spell - out in more detail the assumptions and invariants underlying the - algorithms. The checking is fairly extensive, and will slow down - execution noticeably. Calling malloc_stats or mallinfo with DEBUG - set will attempt to check every non-mmapped allocated and free chunk - in the course of computing the summaries. - -ABORT_ON_ASSERT_FAILURE default: defined as 1 (true) - Debugging assertion failures can be nearly impossible if your - version of the assert macro causes malloc to be called, which will - lead to a cascade of further failures, blowing the runtime stack. - ABORT_ON_ASSERT_FAILURE cause assertions failures to call abort(), - which will usually make debugging easier. - -MALLOC_FAILURE_ACTION default: sets errno to ENOMEM, or no-op on win32 - The action to take before "return 0" when malloc fails to be able to - return memory because there is none available. - -HAVE_MORECORE default: 1 (true) unless win32 or ONLY_MSPACES - True if this system supports sbrk or an emulation of it. - -MORECORE default: sbrk - The name of the sbrk-style system routine to call to obtain more - memory. See below for guidance on writing custom MORECORE - functions. The type of the argument to sbrk/MORECORE varies across - systems. It cannot be size_t, because it supports negative - arguments, so it is normally the signed type of the same width as - size_t (sometimes declared as "intptr_t"). It doesn't much matter - though. Internally, we only call it with arguments less than half - the max value of a size_t, which should work across all reasonable - possibilities, although sometimes generating compiler warnings. - -MORECORE_CONTIGUOUS default: 1 (true) if HAVE_MORECORE - If true, take advantage of fact that consecutive calls to MORECORE - with positive arguments always return contiguous increasing - addresses. This is true of unix sbrk. It does not hurt too much to - set it true anyway, since malloc copes with non-contiguities. - Setting it false when definitely non-contiguous saves time - and possibly wasted space it would take to discover this though. - -MORECORE_CANNOT_TRIM default: NOT defined - True if MORECORE cannot release space back to the system when given - negative arguments. This is generally necessary only if you are - using a hand-crafted MORECORE function that cannot handle negative - arguments. - -NO_SEGMENT_TRAVERSAL default: 0 - If non-zero, suppresses traversals of memory segments - returned by either MORECORE or CALL_MMAP. This disables - merging of segments that are contiguous, and selectively - releasing them to the OS if unused, but bounds execution times. - -HAVE_MMAP default: 1 (true) - True if this system supports mmap or an emulation of it. If so, and - HAVE_MORECORE is not true, MMAP is used for all system - allocation. If set and HAVE_MORECORE is true as well, MMAP is - primarily used to directly allocate very large blocks. It is also - used as a backup strategy in cases where MORECORE fails to provide - space from system. Note: A single call to MUNMAP is assumed to be - able to unmap memory that may have be allocated using multiple calls - to MMAP, so long as they are adjacent. - -HAVE_MREMAP default: 1 on linux, else 0 - If true realloc() uses mremap() to re-allocate large blocks and - extend or shrink allocation spaces. - -MMAP_CLEARS default: 1 except on WINCE. - True if mmap clears memory so calloc doesn't need to. This is true - for standard unix mmap using /dev/zero and on WIN32 except for WINCE. - -USE_BUILTIN_FFS default: 0 (i.e., not used) - Causes malloc to use the builtin ffs() function to compute indices. - Some compilers may recognize and intrinsify ffs to be faster than the - supplied C version. Also, the case of x86 using gcc is special-cased - to an asm instruction, so is already as fast as it can be, and so - this setting has no effect. Similarly for Win32 under recent MS compilers. - (On most x86s, the asm version is only slightly faster than the C version.) - -malloc_getpagesize default: derive from system includes, or 4096. - The system page size. To the extent possible, this malloc manages - memory from the system in page-size units. This may be (and - usually is) a function rather than a constant. This is ignored - if WIN32, where page size is determined using getSystemInfo during - initialization. This may be several megabytes if ENABLE_LARGE_PAGES - is enabled. - -ENABLE_LARGE_PAGES default: NOT defined - Causes the system page size to be the value of GetLargePageMinimum() - if that function is available (Windows Server 2003/Vista or later). - This allows the use of large page entries in the MMU which can - significantly improve performance in large working set applications - as TLB cache load is reduced by a factor of three. Note that enabling - this option is equal to locking the process' memory in current - implementations of Windows and requires the SE_LOCK_MEMORY_PRIVILEGE - to be held by the process in order to succeed. - -USE_DEV_RANDOM default: 0 (i.e., not used) - Causes malloc to use /dev/random to initialize secure magic seed for - stamping footers. Otherwise, the current time is used. - -NO_MALLINFO default: 0 - If defined, don't compile "mallinfo". This can be a simple way - of dealing with mismatches between system declarations and - those in this file. - -MALLINFO_FIELD_TYPE default: size_t - The type of the fields in the mallinfo struct. This was originally - defined as "int" in SVID etc, but is more usefully defined as - size_t. The value is used only if HAVE_USR_INCLUDE_MALLOC_H is not set - -REALLOC_ZERO_BYTES_FREES default: not defined - This should be set if a call to realloc with zero bytes should - be the same as a call to free. Some people think it should. Otherwise, - since this malloc returns a unique pointer for malloc(0), so does - realloc(p, 0). - -LACKS_UNISTD_H, LACKS_FCNTL_H, LACKS_SYS_PARAM_H, LACKS_SYS_MMAN_H -LACKS_STRINGS_H, LACKS_STRING_H, LACKS_SYS_TYPES_H, LACKS_ERRNO_H -LACKS_STDLIB_H default: NOT defined unless on WIN32 - Define these if your system does not have these header files. - You might need to manually insert some of the declarations they provide. - -DEFAULT_GRANULARITY default: page size if MORECORE_CONTIGUOUS, - system_info.dwAllocationGranularity in WIN32, - GetLargePageMinimum() if ENABLE_LARGE_PAGES, - otherwise 64K. - Also settable using mallopt(M_GRANULARITY, x) - The unit for allocating and deallocating memory from the system. On - most systems with contiguous MORECORE, there is no reason to - make this more than a page. However, systems with MMAP tend to - either require or encourage larger granularities. You can increase - this value to prevent system allocation functions to be called so - often, especially if they are slow. The value must be at least one - page and must be a power of two. Setting to 0 causes initialization - to either page size or win32 region size. (Note: In previous - versions of malloc, the equivalent of this option was called - "TOP_PAD") - -DEFAULT_GRANULARITY_ALIGNED default: undefined (which means page size) - Whether to enforce alignment when allocating and deallocating memory - from the system i.e. the base address of all allocations will be - aligned to DEFAULT_GRANULARITY if it is set. Note that enabling this carries - some overhead as multiple calls must now be made when probing for a valid - aligned value, however it does greatly ease the checking for whether - a given memory pointer was allocated by this allocator rather than - some other. - -DEFAULT_TRIM_THRESHOLD default: 2MB - Also settable using mallopt(M_TRIM_THRESHOLD, x) - The maximum amount of unused top-most memory to keep before - releasing via malloc_trim in free(). Automatic trimming is mainly - useful in long-lived programs using contiguous MORECORE. Because - trimming via sbrk can be slow on some systems, and can sometimes be - wasteful (in cases where programs immediately afterward allocate - more large chunks) the value should be high enough so that your - overall system performance would improve by releasing this much - memory. As a rough guide, you might set to a value close to the - average size of a process (program) running on your system. - Releasing this much memory would allow such a process to run in - memory. Generally, it is worth tuning trim thresholds when a - program undergoes phases where several large chunks are allocated - and released in ways that can reuse each other's storage, perhaps - mixed with phases where there are no such chunks at all. The trim - value must be greater than page size to have any useful effect. To - disable trimming completely, you can set to MAX_SIZE_T. Note that the trick - some people use of mallocing a huge space and then freeing it at - program startup, in an attempt to reserve system memory, doesn't - have the intended effect under automatic trimming, since that memory - will immediately be returned to the system. - -DEFAULT_MMAP_THRESHOLD default: 256K - Also settable using mallopt(M_MMAP_THRESHOLD, x) - The request size threshold for using MMAP to directly service a - request. Requests of at least this size that cannot be allocated - using already-existing space will be serviced via mmap. (If enough - normal freed space already exists it is used instead.) Using mmap - segregates relatively large chunks of memory so that they can be - individually obtained and released from the host system. A request - serviced through mmap is never reused by any other request (at least - not directly; the system may just so happen to remap successive - requests to the same locations). Segregating space in this way has - the benefits that: Mmapped space can always be individually released - back to the system, which helps keep the system level memory demands - of a long-lived program low. Also, mapped memory doesn't become - `locked' between other chunks, as can happen with normally allocated - chunks, which means that even trimming via malloc_trim would not - release them. However, it has the disadvantage that the space - cannot be reclaimed, consolidated, and then used to service later - requests, as happens with normal chunks. The advantages of mmap - nearly always outweigh disadvantages for "large" chunks, but the - value of "large" may vary across systems. The default is an - empirically derived value that works well in most systems. You can - disable mmap by setting to MAX_SIZE_T. - -MAX_RELEASE_CHECK_RATE default: 4095 unless not HAVE_MMAP - The number of consolidated frees between checks to release - unused segments when freeing. When using non-contiguous segments, - especially with multiple mspaces, checking only for topmost space - doesn't always suffice to trigger trimming. To compensate for this, - free() will, with a period of MAX_RELEASE_CHECK_RATE (or the - current number of segments, if greater) try to release unused - segments to the OS when freeing chunks that result in - consolidation. The best value for this parameter is a compromise - between slowing down frees with relatively costly checks that - rarely trigger versus holding on to unused memory. To effectively - disable, set to MAX_SIZE_T. This may lead to a very slight speed - improvement at the expense of carrying around more memory. -*/ - -/* Version identifier to allow people to support multiple versions */ -#ifndef DLMALLOC_VERSION -#define DLMALLOC_VERSION 20804 -#endif /* DLMALLOC_VERSION */ - -#ifndef WIN32 -#ifdef _WIN32 -#define WIN32 1 -#endif /* _WIN32 */ -#ifdef _WIN32_WCE -#define LACKS_FCNTL_H -#define WIN32 1 -#endif /* _WIN32_WCE */ -#endif /* WIN32 */ -#ifdef WIN32 -#define WIN32_LEAN_AND_MEAN -#include -#include -#define HAVE_MMAP 1 -#define HAVE_MORECORE 0 -#define LACKS_UNISTD_H -#define LACKS_SYS_PARAM_H -#define LACKS_SYS_MMAN_H -#define LACKS_STRING_H -#define LACKS_STRINGS_H -#define LACKS_SYS_TYPES_H -#define LACKS_ERRNO_H -#ifndef MALLOC_FAILURE_ACTION -#define MALLOC_FAILURE_ACTION -#endif /* MALLOC_FAILURE_ACTION */ -#ifdef _WIN32_WCE /* WINCE reportedly does not clear */ -#define MMAP_CLEARS 0 -#else -#define MMAP_CLEARS 1 -#endif /* _WIN32_WCE */ -#endif /* WIN32 */ - -#if defined(DARWIN) || defined(_DARWIN) -/* Mac OSX docs advise not to use sbrk; it seems better to use mmap */ -#ifndef HAVE_MORECORE -#define HAVE_MORECORE 0 -#define HAVE_MMAP 1 -/* OSX allocators provide 16 byte alignment */ -#ifndef MALLOC_ALIGNMENT -#define MALLOC_ALIGNMENT ((size_t)16U) -#endif -#endif /* HAVE_MORECORE */ -#endif /* DARWIN */ - -#ifndef LACKS_SYS_TYPES_H -#include /* For size_t */ -#endif /* LACKS_SYS_TYPES_H */ - -#if (defined(__GNUC__) && ((defined(__i386__) || defined(__x86_64__)))) || (defined(_MSC_VER) && _MSC_VER>=1310) -#define SPIN_LOCKS_AVAILABLE 1 -#else -#define SPIN_LOCKS_AVAILABLE 0 -#endif - -/* The maximum possible size_t value has all bits set */ -#define MAX_SIZE_T (~(size_t)0) - -#ifndef ONLY_MSPACES -#define ONLY_MSPACES 0 /* define to a value */ -#else -#define ONLY_MSPACES 1 -#endif /* ONLY_MSPACES */ -#ifndef MSPACES -#if ONLY_MSPACES -#define MSPACES 1 -#else /* ONLY_MSPACES */ -#define MSPACES 0 -#endif /* ONLY_MSPACES */ -#endif /* MSPACES */ -#ifndef MALLOC_ALIGNMENT -#define MALLOC_ALIGNMENT ((size_t)8U) -#endif /* MALLOC_ALIGNMENT */ -#ifndef FOOTERS -#define FOOTERS 0 -#endif /* FOOTERS */ -#ifndef ABORT -#define ABORT abort() -#endif /* ABORT */ -#ifndef ABORT_ON_ASSERT_FAILURE -#define ABORT_ON_ASSERT_FAILURE 1 -#endif /* ABORT_ON_ASSERT_FAILURE */ -#ifndef PROCEED_ON_ERROR -#define PROCEED_ON_ERROR 0 -#endif /* PROCEED_ON_ERROR */ -#ifndef USE_LOCKS -#define USE_LOCKS 0 -#endif /* USE_LOCKS */ -#ifndef USE_SPIN_LOCKS -#if USE_LOCKS && SPIN_LOCKS_AVAILABLE -#define USE_SPIN_LOCKS 1 -#else -#define USE_SPIN_LOCKS 0 -#endif /* USE_LOCKS && SPIN_LOCKS_AVAILABLE. */ -#endif /* USE_SPIN_LOCKS */ -#ifndef INSECURE -#define INSECURE 0 -#endif /* INSECURE */ -#ifndef HAVE_MMAP -#define HAVE_MMAP 1 -#endif /* HAVE_MMAP */ -#ifndef MMAP_CLEARS -#define MMAP_CLEARS 1 -#endif /* MMAP_CLEARS */ -#ifndef HAVE_MREMAP -#ifdef linux -#define HAVE_MREMAP 1 -#else /* linux */ -#define HAVE_MREMAP 0 -#endif /* linux */ -#endif /* HAVE_MREMAP */ -#ifndef MALLOC_FAILURE_ACTION -#define MALLOC_FAILURE_ACTION errno = ENOMEM; -#endif /* MALLOC_FAILURE_ACTION */ -#ifndef HAVE_MORECORE -#if ONLY_MSPACES -#define HAVE_MORECORE 0 -#else /* ONLY_MSPACES */ -#define HAVE_MORECORE 1 -#endif /* ONLY_MSPACES */ -#endif /* HAVE_MORECORE */ -#if !HAVE_MORECORE -#define MORECORE_CONTIGUOUS 0 -#else /* !HAVE_MORECORE */ -#define MORECORE_DEFAULT sbrk -#ifndef MORECORE_CONTIGUOUS -#define MORECORE_CONTIGUOUS 1 -#endif /* MORECORE_CONTIGUOUS */ -#endif /* HAVE_MORECORE */ -#ifndef DEFAULT_GRANULARITY -#if (MORECORE_CONTIGUOUS || defined(WIN32)) -#define DEFAULT_GRANULARITY (0) /* 0 means to compute in init_mparams */ -#else /* MORECORE_CONTIGUOUS */ -#define DEFAULT_GRANULARITY ((size_t)64U * (size_t)1024U) -#endif /* MORECORE_CONTIGUOUS */ -#endif /* DEFAULT_GRANULARITY */ -#ifndef DEFAULT_TRIM_THRESHOLD -#ifndef MORECORE_CANNOT_TRIM -#define DEFAULT_TRIM_THRESHOLD ((size_t)2U * (size_t)1024U * (size_t)1024U) -#else /* MORECORE_CANNOT_TRIM */ -#define DEFAULT_TRIM_THRESHOLD MAX_SIZE_T -#endif /* MORECORE_CANNOT_TRIM */ -#endif /* DEFAULT_TRIM_THRESHOLD */ -#ifndef DEFAULT_MMAP_THRESHOLD -#if HAVE_MMAP -#define DEFAULT_MMAP_THRESHOLD ((size_t)256U * (size_t)1024U) -#else /* HAVE_MMAP */ -#define DEFAULT_MMAP_THRESHOLD MAX_SIZE_T -#endif /* HAVE_MMAP */ -#endif /* DEFAULT_MMAP_THRESHOLD */ -#ifndef MAX_RELEASE_CHECK_RATE -#if HAVE_MMAP -#define MAX_RELEASE_CHECK_RATE 4095 -#else -#define MAX_RELEASE_CHECK_RATE MAX_SIZE_T -#endif /* HAVE_MMAP */ -#endif /* MAX_RELEASE_CHECK_RATE */ -#ifndef USE_BUILTIN_FFS -#define USE_BUILTIN_FFS 0 -#endif /* USE_BUILTIN_FFS */ -#ifndef USE_DEV_RANDOM -#define USE_DEV_RANDOM 0 -#endif /* USE_DEV_RANDOM */ -#ifndef NO_MALLINFO -#define NO_MALLINFO 0 -#endif /* NO_MALLINFO */ -#ifndef MALLINFO_FIELD_TYPE -#define MALLINFO_FIELD_TYPE size_t -#endif /* MALLINFO_FIELD_TYPE */ -#ifndef NO_SEGMENT_TRAVERSAL -#define NO_SEGMENT_TRAVERSAL 0 -#endif /* NO_SEGMENT_TRAVERSAL */ - -/* - mallopt tuning options. SVID/XPG defines four standard parameter - numbers for mallopt, normally defined in malloc.h. None of these - are used in this malloc, so setting them has no effect. But this - malloc does support the following options. -*/ - -#define M_TRIM_THRESHOLD (-1) -#define M_GRANULARITY (-2) -#define M_MMAP_THRESHOLD (-3) - -/* ------------------------ Mallinfo declarations ------------------------ */ - -#if !NO_MALLINFO -/* - This version of malloc supports the standard SVID/XPG mallinfo - routine that returns a struct containing usage properties and - statistics. It should work on any system that has a - /usr/include/malloc.h defining struct mallinfo. The main - declaration needed is the mallinfo struct that is returned (by-copy) - by mallinfo(). The malloinfo struct contains a bunch of fields that - are not even meaningful in this version of malloc. These fields are - are instead filled by mallinfo() with other numbers that might be of - interest. - - HAVE_USR_INCLUDE_MALLOC_H should be set if you have a - /usr/include/malloc.h file that includes a declaration of struct - mallinfo. If so, it is included; else a compliant version is - declared below. These must be precisely the same for mallinfo() to - work. The original SVID version of this struct, defined on most - systems with mallinfo, declares all fields as ints. But some others - define as unsigned long. If your system defines the fields using a - type of different width than listed here, you MUST #include your - system version and #define HAVE_USR_INCLUDE_MALLOC_H. -*/ - -/* #define HAVE_USR_INCLUDE_MALLOC_H */ - -#ifdef HAVE_USR_INCLUDE_MALLOC_H -#include "/usr/include/malloc.h" -#else /* HAVE_USR_INCLUDE_MALLOC_H */ -#ifndef STRUCT_MALLINFO_DECLARED -#define STRUCT_MALLINFO_DECLARED 1 -struct mallinfo { - MALLINFO_FIELD_TYPE arena; /* non-mmapped space allocated from system */ - MALLINFO_FIELD_TYPE ordblks; /* number of free chunks */ - MALLINFO_FIELD_TYPE smblks; /* always 0 */ - MALLINFO_FIELD_TYPE hblks; /* always 0 */ - MALLINFO_FIELD_TYPE hblkhd; /* space in mmapped regions */ - MALLINFO_FIELD_TYPE usmblks; /* maximum total allocated space */ - MALLINFO_FIELD_TYPE fsmblks; /* always 0 */ - MALLINFO_FIELD_TYPE uordblks; /* total allocated space */ - MALLINFO_FIELD_TYPE fordblks; /* total free space */ - MALLINFO_FIELD_TYPE keepcost; /* releasable (via malloc_trim) space */ -}; -#endif /* STRUCT_MALLINFO_DECLARED */ -#endif /* HAVE_USR_INCLUDE_MALLOC_H */ -#endif /* NO_MALLINFO */ - -/* - Try to persuade compilers to inline. The most critical functions for - inlining are defined as macros, so these aren't used for them. -*/ - -#ifndef FORCEINLINE - #if defined(__GNUC__) -#define FORCEINLINE __inline __attribute__ ((always_inline)) - #elif defined(_MSC_VER) - #define FORCEINLINE __forceinline - #endif -#endif -#ifndef NOINLINE - #if defined(__GNUC__) - #define NOINLINE __attribute__ ((noinline)) - #elif defined(_MSC_VER) - #define NOINLINE __declspec(noinline) - #else - #define NOINLINE - #endif -#endif - -#ifdef __cplusplus -extern "C" { -#ifndef FORCEINLINE - #define FORCEINLINE inline -#endif -#endif /* __cplusplus */ -#ifndef FORCEINLINE - #define FORCEINLINE -#endif - -#if !ONLY_MSPACES - -/* ------------------- Declarations of public routines ------------------- */ - -#ifndef USE_DL_PREFIX -#define dlcalloc calloc -#define dlfree free -#define dlmalloc malloc -#define dlmemalign memalign -#define dlrealloc realloc -#define dlvalloc valloc -#define dlpvalloc pvalloc -#define dlmallinfo mallinfo -#define dlmallopt mallopt -#define dlmalloc_trim malloc_trim -#define dlmalloc_stats malloc_stats -#define dlmalloc_usable_size malloc_usable_size -#define dlmalloc_footprint malloc_footprint -#define dlmalloc_max_footprint malloc_max_footprint -#define dlindependent_calloc independent_calloc -#define dlindependent_comalloc independent_comalloc -#endif /* USE_DL_PREFIX */ - - -/* - malloc(size_t n) - Returns a pointer to a newly allocated chunk of at least n bytes, or - null if no space is available, in which case errno is set to ENOMEM - on ANSI C systems. - - If n is zero, malloc returns a minimum-sized chunk. (The minimum - size is 16 bytes on most 32bit systems, and 32 bytes on 64bit - systems.) Note that size_t is an unsigned type, so calls with - arguments that would be negative if signed are interpreted as - requests for huge amounts of space, which will often fail. The - maximum supported value of n differs across systems, but is in all - cases less than the maximum representable value of a size_t. -*/ -void* dlmalloc(size_t); - -/* - free(void* p) - Releases the chunk of memory pointed to by p, that had been previously - allocated using malloc or a related routine such as realloc. - It has no effect if p is null. If p was not malloced or already - freed, free(p) will by default cause the current program to abort. -*/ -void dlfree(void*); - -/* - calloc(size_t n_elements, size_t element_size); - Returns a pointer to n_elements * element_size bytes, with all locations - set to zero. -*/ -void* dlcalloc(size_t, size_t); - -/* - realloc(void* p, size_t n) - Returns a pointer to a chunk of size n that contains the same data - as does chunk p up to the minimum of (n, p's size) bytes, or null - if no space is available. - - The returned pointer may or may not be the same as p. The algorithm - prefers extending p in most cases when possible, otherwise it - employs the equivalent of a malloc-copy-free sequence. - - If p is null, realloc is equivalent to malloc. - - If space is not available, realloc returns null, errno is set (if on - ANSI) and p is NOT freed. - - if n is for fewer bytes than already held by p, the newly unused - space is lopped off and freed if possible. realloc with a size - argument of zero (re)allocates a minimum-sized chunk. - - The old unix realloc convention of allowing the last-free'd chunk - to be used as an argument to realloc is not supported. -*/ - -void* dlrealloc(void*, size_t); - -/* - memalign(size_t alignment, size_t n); - Returns a pointer to a newly allocated chunk of n bytes, aligned - in accord with the alignment argument. - - The alignment argument should be a power of two. If the argument is - not a power of two, the nearest greater power is used. - 8-byte alignment is guaranteed by normal malloc calls, so don't - bother calling memalign with an argument of 8 or less. - - Overreliance on memalign is a sure way to fragment space. -*/ -void* dlmemalign(size_t, size_t); - -/* - valloc(size_t n); - Equivalent to memalign(pagesize, n), where pagesize is the page - size of the system. If the pagesize is unknown, 4096 is used. -*/ -void* dlvalloc(size_t); - -/* - mallopt(int parameter_number, int parameter_value) - Sets tunable parameters The format is to provide a - (parameter-number, parameter-value) pair. mallopt then sets the - corresponding parameter to the argument value if it can (i.e., so - long as the value is meaningful), and returns 1 if successful else - 0. To workaround the fact that mallopt is specified to use int, - not size_t parameters, the value -1 is specially treated as the - maximum unsigned size_t value. - - SVID/XPG/ANSI defines four standard param numbers for mallopt, - normally defined in malloc.h. None of these are use in this malloc, - so setting them has no effect. But this malloc also supports other - options in mallopt. See below for details. Briefly, supported - parameters are as follows (listed defaults are for "typical" - configurations). - - Symbol param # default allowed param values - M_TRIM_THRESHOLD -1 2*1024*1024 any (-1 disables) - M_GRANULARITY -2 page size any power of 2 >= page size - M_MMAP_THRESHOLD -3 256*1024 any (or 0 if no MMAP support) -*/ -int dlmallopt(int, int); - -/* - malloc_footprint(); - Returns the number of bytes obtained from the system. The total - number of bytes allocated by malloc, realloc etc., is less than this - value. Unlike mallinfo, this function returns only a precomputed - result, so can be called frequently to monitor memory consumption. - Even if locks are otherwise defined, this function does not use them, - so results might not be up to date. -*/ -size_t dlmalloc_footprint(void); - -/* - malloc_max_footprint(); - Returns the maximum number of bytes obtained from the system. This - value will be greater than current footprint if deallocated space - has been reclaimed by the system. The peak number of bytes allocated - by malloc, realloc etc., is less than this value. Unlike mallinfo, - this function returns only a precomputed result, so can be called - frequently to monitor memory consumption. Even if locks are - otherwise defined, this function does not use them, so results might - not be up to date. -*/ -size_t dlmalloc_max_footprint(void); - -#if !NO_MALLINFO -/* - mallinfo() - Returns (by copy) a struct containing various summary statistics: - - arena: current total non-mmapped bytes allocated from system - ordblks: the number of free chunks - smblks: always zero. - hblks: current number of mmapped regions - hblkhd: total bytes held in mmapped regions - usmblks: the maximum total allocated space. This will be greater - than current total if trimming has occurred. - fsmblks: always zero - uordblks: current total allocated space (normal or mmapped) - fordblks: total free space - keepcost: the maximum number of bytes that could ideally be released - back to system via malloc_trim. ("ideally" means that - it ignores page restrictions etc.) - - Because these fields are ints, but internal bookkeeping may - be kept as longs, the reported values may wrap around zero and - thus be inaccurate. -*/ -struct mallinfo dlmallinfo(void); -#endif /* NO_MALLINFO */ - -/* - independent_calloc(size_t n_elements, size_t element_size, void* chunks[]); - - independent_calloc is similar to calloc, but instead of returning a - single cleared space, it returns an array of pointers to n_elements - independent elements that can hold contents of size elem_size, each - of which starts out cleared, and can be independently freed, - realloc'ed etc. The elements are guaranteed to be adjacently - allocated (this is not guaranteed to occur with multiple callocs or - mallocs), which may also improve cache locality in some - applications. - - The "chunks" argument is optional (i.e., may be null, which is - probably the most typical usage). If it is null, the returned array - is itself dynamically allocated and should also be freed when it is - no longer needed. Otherwise, the chunks array must be of at least - n_elements in length. It is filled in with the pointers to the - chunks. - - In either case, independent_calloc returns this pointer array, or - null if the allocation failed. If n_elements is zero and "chunks" - is null, it returns a chunk representing an array with zero elements - (which should be freed if not wanted). - - Each element must be individually freed when it is no longer - needed. If you'd like to instead be able to free all at once, you - should instead use regular calloc and assign pointers into this - space to represent elements. (In this case though, you cannot - independently free elements.) - - independent_calloc simplifies and speeds up implementations of many - kinds of pools. It may also be useful when constructing large data - structures that initially have a fixed number of fixed-sized nodes, - but the number is not known at compile time, and some of the nodes - may later need to be freed. For example: - - struct Node { int item; struct Node* next; }; - - struct Node* build_list() { - struct Node** pool; - int n = read_number_of_nodes_needed(); - if (n <= 0) return 0; - pool = (struct Node**)(independent_calloc(n, sizeof(struct Node), 0); - if (pool == 0) die(); - // organize into a linked list... - struct Node* first = pool[0]; - for (i = 0; i < n-1; ++i) - pool[i]->next = pool[i+1]; - free(pool); // Can now free the array (or not, if it is needed later) - return first; - } -*/ -void** dlindependent_calloc(size_t, size_t, void**); - -/* - independent_comalloc(size_t n_elements, size_t sizes[], void* chunks[]); - - independent_comalloc allocates, all at once, a set of n_elements - chunks with sizes indicated in the "sizes" array. It returns - an array of pointers to these elements, each of which can be - independently freed, realloc'ed etc. The elements are guaranteed to - be adjacently allocated (this is not guaranteed to occur with - multiple callocs or mallocs), which may also improve cache locality - in some applications. - - The "chunks" argument is optional (i.e., may be null). If it is null - the returned array is itself dynamically allocated and should also - be freed when it is no longer needed. Otherwise, the chunks array - must be of at least n_elements in length. It is filled in with the - pointers to the chunks. - - In either case, independent_comalloc returns this pointer array, or - null if the allocation failed. If n_elements is zero and chunks is - null, it returns a chunk representing an array with zero elements - (which should be freed if not wanted). - - Each element must be individually freed when it is no longer - needed. If you'd like to instead be able to free all at once, you - should instead use a single regular malloc, and assign pointers at - particular offsets in the aggregate space. (In this case though, you - cannot independently free elements.) - - independent_comallac differs from independent_calloc in that each - element may have a different size, and also that it does not - automatically clear elements. - - independent_comalloc can be used to speed up allocation in cases - where several structs or objects must always be allocated at the - same time. For example: - - struct Head { ... } - struct Foot { ... } - - void send_message(char* msg) { - int msglen = strlen(msg); - size_t sizes[3] = { sizeof(struct Head), msglen, sizeof(struct Foot) }; - void* chunks[3]; - if (independent_comalloc(3, sizes, chunks) == 0) - die(); - struct Head* head = (struct Head*)(chunks[0]); - char* body = (char*)(chunks[1]); - struct Foot* foot = (struct Foot*)(chunks[2]); - // ... - } - - In general though, independent_comalloc is worth using only for - larger values of n_elements. For small values, you probably won't - detect enough difference from series of malloc calls to bother. - - Overuse of independent_comalloc can increase overall memory usage, - since it cannot reuse existing noncontiguous small chunks that - might be available for some of the elements. -*/ -void** dlindependent_comalloc(size_t, size_t*, void**); - - -/* - pvalloc(size_t n); - Equivalent to valloc(minimum-page-that-holds(n)), that is, - round up n to nearest pagesize. - */ -void* dlpvalloc(size_t); - -/* - malloc_trim(size_t pad); - - If possible, gives memory back to the system (via negative arguments - to sbrk) if there is unused memory at the `high' end of the malloc - pool or in unused MMAP segments. You can call this after freeing - large blocks of memory to potentially reduce the system-level memory - requirements of a program. However, it cannot guarantee to reduce - memory. Under some allocation patterns, some large free blocks of - memory will be locked between two used chunks, so they cannot be - given back to the system. - - The `pad' argument to malloc_trim represents the amount of free - trailing space to leave untrimmed. If this argument is zero, only - the minimum amount of memory to maintain internal data structures - will be left. Non-zero arguments can be supplied to maintain enough - trailing space to service future expected allocations without having - to re-obtain memory from the system. - - Malloc_trim returns 1 if it actually released any memory, else 0. -*/ -int dlmalloc_trim(size_t); - -/* - malloc_stats(); - Prints on stderr the amount of space obtained from the system (both - via sbrk and mmap), the maximum amount (which may be more than - current if malloc_trim and/or munmap got called), and the current - number of bytes allocated via malloc (or realloc, etc) but not yet - freed. Note that this is the number of bytes allocated, not the - number requested. It will be larger than the number requested - because of alignment and bookkeeping overhead. Because it includes - alignment wastage as being in use, this figure may be greater than - zero even when no user-level chunks are allocated. - - The reported current and maximum system memory can be inaccurate if - a program makes other calls to system memory allocation functions - (normally sbrk) outside of malloc. - - malloc_stats prints only the most commonly interesting statistics. - More information can be obtained by calling mallinfo. -*/ -void dlmalloc_stats(void); - -#endif /* ONLY_MSPACES */ - -/* - malloc_usable_size(void* p); - - Returns the number of bytes you can actually use in - an allocated chunk, which may be more than you requested (although - often not) due to alignment and minimum size constraints. - You can use this many bytes without worrying about - overwriting other allocated objects. This is not a particularly great - programming practice. malloc_usable_size can be more useful in - debugging and assertions, for example: - - p = malloc(n); - assert(malloc_usable_size(p) >= 256); -*/ -size_t dlmalloc_usable_size(void*); - - -#if MSPACES - -/* - mspace is an opaque type representing an independent - region of space that supports mspace_malloc, etc. -*/ -typedef void* mspace; - -/* - create_mspace creates and returns a new independent space with the - given initial capacity, or, if 0, the default granularity size. It - returns null if there is no system memory available to create the - space. If argument locked is non-zero, the space uses a separate - lock to control access. The capacity of the space will grow - dynamically as needed to service mspace_malloc requests. You can - control the sizes of incremental increases of this space by - compiling with a different DEFAULT_GRANULARITY or dynamically - setting with mallopt(M_GRANULARITY, value). -*/ -mspace create_mspace(size_t capacity, int locked); - -/* - destroy_mspace destroys the given space, and attempts to return all - of its memory back to the system, returning the total number of - bytes freed. After destruction, the results of access to all memory - used by the space become undefined. -*/ -size_t destroy_mspace(mspace msp); - -/* - create_mspace_with_base uses the memory supplied as the initial base - of a new mspace. Part (less than 128*sizeof(size_t) bytes) of this - space is used for bookkeeping, so the capacity must be at least this - large. (Otherwise 0 is returned.) When this initial space is - exhausted, additional memory will be obtained from the system. - Destroying this space will deallocate all additionally allocated - space (if possible) but not the initial base. -*/ -mspace create_mspace_with_base(void* base, size_t capacity, int locked); - -/* - mspace_track_large_chunks controls whether requests for large chunks - are allocated in their own untracked mmapped regions, separate from - others in this mspace. By default large chunks are not tracked, - which reduces fragmentation. However, such chunks are not - necessarily released to the system upon destroy_mspace. Enabling - tracking by setting to true may increase fragmentation, but avoids - leakage when relying on destroy_mspace to release all memory - allocated using this space. The function returns the previous - setting. -*/ -int mspace_track_large_chunks(mspace msp, int enable); - - -/* - mspace_malloc behaves as malloc, but operates within - the given space. -*/ -void* mspace_malloc(mspace msp, size_t bytes); - -/* - mspace_free behaves as free, but operates within - the given space. - - If compiled with FOOTERS==1, mspace_free is not actually needed. - free may be called instead of mspace_free because freed chunks from - any space are handled by their originating spaces. -*/ -void mspace_free(mspace msp, void* mem); - -/* - mspace_realloc behaves as realloc, but operates within - the given space. - - If compiled with FOOTERS==1, mspace_realloc is not actually - needed. realloc may be called instead of mspace_realloc because - realloced chunks from any space are handled by their originating - spaces. -*/ -void* mspace_realloc(mspace msp, void* mem, size_t newsize); - -/* - mspace_calloc behaves as calloc, but operates within - the given space. -*/ -void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size); - -/* - mspace_memalign behaves as memalign, but operates within - the given space. -*/ -void* mspace_memalign(mspace msp, size_t alignment, size_t bytes); - -/* - mspace_independent_calloc behaves as independent_calloc, but - operates within the given space. -*/ -void** mspace_independent_calloc(mspace msp, size_t n_elements, - size_t elem_size, void* chunks[]); - -/* - mspace_independent_comalloc behaves as independent_comalloc, but - operates within the given space. -*/ -void** mspace_independent_comalloc(mspace msp, size_t n_elements, - size_t sizes[], void* chunks[]); - -/* - mspace_footprint() returns the number of bytes obtained from the - system for this space. -*/ -size_t mspace_footprint(mspace msp); - -/* - mspace_max_footprint() returns the peak number of bytes obtained from the - system for this space. -*/ -size_t mspace_max_footprint(mspace msp); - - -#if !NO_MALLINFO -/* - mspace_mallinfo behaves as mallinfo, but reports properties of - the given space. -*/ -struct mallinfo mspace_mallinfo(mspace msp); -#endif /* NO_MALLINFO */ - -/* - malloc_usable_size(void* p) behaves the same as malloc_usable_size; -*/ - size_t mspace_usable_size(void* mem); - -/* - mspace_malloc_stats behaves as malloc_stats, but reports - properties of the given space. -*/ -void mspace_malloc_stats(mspace msp); - -/* - mspace_trim behaves as malloc_trim, but - operates within the given space. -*/ -int mspace_trim(mspace msp, size_t pad); - -/* - An alias for mallopt. -*/ -int mspace_mallopt(int, int); - -#endif /* MSPACES */ - -#ifdef __cplusplus -} /* end of extern "C" */ -#endif /* __cplusplus */ - -/* - ======================================================================== - To make a fully customizable malloc.h header file, cut everything - above this line, put into file malloc.h, edit to suit, and #include it - on the next line, as well as in programs that use this malloc. - ======================================================================== -*/ - -/* #include "malloc.h" */ - -/*------------------------------ internal #includes ---------------------- */ - -#if defined(WIN32) && defined(_MSC_VER) -#pragma warning( disable : 4146 ) /* no "unsigned" warnings */ -#endif /* WIN32 */ - -#include /* for printing in malloc_stats */ - -#ifndef LACKS_ERRNO_H -#include /* for MALLOC_FAILURE_ACTION */ -#endif /* LACKS_ERRNO_H */ -#if FOOTERS || DEBUG -#include /* for magic initialization */ -#endif /* FOOTERS */ -#ifndef LACKS_STDLIB_H -#include /* for abort() */ -#endif /* LACKS_STDLIB_H */ -#ifdef DEBUG -#if ABORT_ON_ASSERT_FAILURE -#undef assert -#define assert(x) if(!(x)) ABORT -#else /* ABORT_ON_ASSERT_FAILURE */ -#include -#endif /* ABORT_ON_ASSERT_FAILURE */ -#else /* DEBUG */ -#ifndef assert -#define assert(x) -#endif -#define DEBUG 0 -#endif /* DEBUG */ -#ifndef LACKS_STRING_H -#include /* for memset etc */ -#endif /* LACKS_STRING_H */ -#if USE_BUILTIN_FFS -#ifndef LACKS_STRINGS_H -#include /* for ffs */ -#endif /* LACKS_STRINGS_H */ -#endif /* USE_BUILTIN_FFS */ -#if HAVE_MMAP -#ifndef LACKS_SYS_MMAN_H -/* On some versions of linux, mremap decl in mman.h needs __USE_GNU set */ -#if (defined(linux) && !defined(__USE_GNU)) -#define __USE_GNU 1 -#include /* for mmap */ -#undef __USE_GNU -#else -#include /* for mmap */ -#endif /* linux */ -#endif /* LACKS_SYS_MMAN_H */ -#ifndef LACKS_FCNTL_H -#include -#endif /* LACKS_FCNTL_H */ -#endif /* HAVE_MMAP */ -#ifndef LACKS_UNISTD_H -#include /* for sbrk, sysconf */ -#else /* LACKS_UNISTD_H */ -#if !defined(__FreeBSD__) && !defined(__OpenBSD__) && !defined(__NetBSD__) -extern void* sbrk(ptrdiff_t); -#endif /* FreeBSD etc */ -#endif /* LACKS_UNISTD_H */ - -/* Declarations for locking */ -#if USE_LOCKS -#ifndef WIN32 -#include -#if defined (__SVR4) && defined (__sun) /* solaris */ -#include -#endif /* solaris */ -#else -#ifndef _M_AMD64 -/* These are already defined on AMD64 builds */ -#ifdef __cplusplus -extern "C" { -#endif /* __cplusplus */ -#ifndef __MINGW32__ -LONG __cdecl _InterlockedCompareExchange(LONG volatile *Dest, LONG Exchange, LONG Comp); -LONG __cdecl _InterlockedExchange(LONG volatile *Target, LONG Value); -#endif -#ifdef __cplusplus -} -#endif /* __cplusplus */ -#endif /* _M_AMD64 */ -#ifndef __MINGW32__ -#pragma intrinsic (_InterlockedCompareExchange) -#pragma intrinsic (_InterlockedExchange) -#else - /* --[ start GCC compatibility ]---------------------------------------------- - * Compatibility header for GCC -- GCC equivalents of intrinsic - * Microsoft Visual C++ functions. Originally developed for the ReactOS - * () and TinyKrnl () - * projects. - * - * Copyright (c) 2006 KJK::Hyperion - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * 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 AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - */ - - /*** Atomic operations ***/ - #if (__GNUC__ * 10000 + __GNUC_MINOR__ * 100 + __GNUC_PATCHLEVEL__) > 40100 - #define _ReadWriteBarrier() __sync_synchronize() - #else - static __inline__ __attribute__((always_inline)) long __sync_lock_test_and_set(volatile long * const Target, const long Value) - { - long res; - __asm__ __volatile__("xchg%z0 %2, %0" : "=g" (*(Target)), "=r" (res) : "1" (Value)); - return res; - } - static void __inline__ __attribute__((always_inline)) _MemoryBarrier(void) - { - __asm__ __volatile__("" : : : "memory"); - } - #define _ReadWriteBarrier() _MemoryBarrier() - #endif - /* BUGBUG: GCC only supports full barriers */ - static __inline__ __attribute__((always_inline)) long _InterlockedExchange(volatile long * const Target, const long Value) - { - /* NOTE: __sync_lock_test_and_set would be an acquire barrier, so we force a full barrier */ - _ReadWriteBarrier(); - return __sync_lock_test_and_set(Target, Value); - } - /* --[ end GCC compatibility ]---------------------------------------------- */ -#endif -#define interlockedcompareexchange _InterlockedCompareExchange -#define interlockedexchange _InterlockedExchange -#endif /* Win32 */ -#endif /* USE_LOCKS */ - -/* Declarations for bit scanning on win32 */ -#if defined(_MSC_VER) && _MSC_VER>=1300 -#ifndef BitScanForward /* Try to avoid pulling in WinNT.h */ -#ifdef __cplusplus -extern "C" { -#endif /* __cplusplus */ -unsigned char _BitScanForward(unsigned long *index, unsigned long mask); -unsigned char _BitScanReverse(unsigned long *index, unsigned long mask); -#ifdef __cplusplus -} -#endif /* __cplusplus */ - -#define BitScanForward _BitScanForward -#define BitScanReverse _BitScanReverse -#pragma intrinsic(_BitScanForward) -#pragma intrinsic(_BitScanReverse) -#endif /* BitScanForward */ -#endif /* defined(_MSC_VER) && _MSC_VER>=1300 */ - -#ifndef WIN32 -#ifndef malloc_getpagesize -# ifdef _SC_PAGESIZE /* some SVR4 systems omit an underscore */ -# ifndef _SC_PAGE_SIZE -# define _SC_PAGE_SIZE _SC_PAGESIZE -# endif -# endif -# ifdef _SC_PAGE_SIZE -# define malloc_getpagesize sysconf(_SC_PAGE_SIZE) -# else -# if defined(BSD) || defined(DGUX) || defined(HAVE_GETPAGESIZE) - extern size_t getpagesize(); -# define malloc_getpagesize getpagesize() -# else -# ifdef WIN32 /* use supplied emulation of getpagesize */ -# define malloc_getpagesize getpagesize() -# else -# ifndef LACKS_SYS_PARAM_H -# include -# endif -# ifdef EXEC_PAGESIZE -# define malloc_getpagesize EXEC_PAGESIZE -# else -# ifdef NBPG -# ifndef CLSIZE -# define malloc_getpagesize NBPG -# else -# define malloc_getpagesize (NBPG * CLSIZE) -# endif -# else -# ifdef NBPC -# define malloc_getpagesize NBPC -# else -# ifdef PAGESIZE -# define malloc_getpagesize PAGESIZE -# else /* just guess */ -# define malloc_getpagesize ((size_t)4096U) -# endif -# endif -# endif -# endif -# endif -# endif -# endif -#endif -#endif - - - -/* ------------------- size_t and alignment properties -------------------- */ - -/* The byte and bit size of a size_t */ -#define SIZE_T_SIZE (sizeof(size_t)) -#define SIZE_T_BITSIZE (sizeof(size_t) << 3) - -/* Some constants coerced to size_t */ -/* Annoying but necessary to avoid errors on some platforms */ -#define SIZE_T_ZERO ((size_t)0) -#define SIZE_T_ONE ((size_t)1) -#define SIZE_T_TWO ((size_t)2) -#define SIZE_T_FOUR ((size_t)4) -#define TWO_SIZE_T_SIZES (SIZE_T_SIZE<<1) -#define FOUR_SIZE_T_SIZES (SIZE_T_SIZE<<2) -#define SIX_SIZE_T_SIZES (FOUR_SIZE_T_SIZES+TWO_SIZE_T_SIZES) -#define HALF_MAX_SIZE_T (MAX_SIZE_T / 2U) - -/* The bit mask value corresponding to MALLOC_ALIGNMENT */ -#define CHUNK_ALIGN_MASK (MALLOC_ALIGNMENT - SIZE_T_ONE) - -/* True if address a has acceptable alignment */ -#define is_aligned(A) (((size_t)((A)) & (CHUNK_ALIGN_MASK)) == 0) - -/* the number of bytes to offset an address to align it */ -#define align_offset(A)\ - ((((size_t)(A) & CHUNK_ALIGN_MASK) == 0)? 0 :\ - ((MALLOC_ALIGNMENT - ((size_t)(A) & CHUNK_ALIGN_MASK)) & CHUNK_ALIGN_MASK)) - -/* - malloc_params holds global properties, including those that can be - dynamically set using mallopt. There is a single instance, mparams, - initialized in init_mparams. Note that the non-zeroness of "magic" - also serves as an initialization flag. -*/ -typedef unsigned int flag_t; -struct malloc_params { - volatile size_t magic; - size_t page_size; - size_t granularity; - size_t mmap_threshold; - size_t trim_threshold; - flag_t default_mflags; -}; - -static struct malloc_params mparams; - -/* Ensure mparams initialized */ -#define ensure_initialization() (void)(mparams.magic != 0 || init_mparams()) - -/* -------------------------- MMAP preliminaries ------------------------- */ - -/* - If HAVE_MORECORE or HAVE_MMAP are false, we just define calls and - checks to fail so compiler optimizer can delete code rather than - using so many "#if"s. -*/ - - -/* MORECORE and MMAP must return MFAIL on failure */ -#define MFAIL ((void*)(MAX_SIZE_T)) -#define CMFAIL ((char*)(MFAIL)) /* defined for convenience */ - -#if HAVE_MMAP - -#ifndef WIN32 -#if !defined(MAP_ANONYMOUS) && defined(MAP_ANON) -#define MAP_ANONYMOUS MAP_ANON -#endif /* MAP_ANON */ -#ifdef DEFAULT_GRANULARITY_ALIGNED -#define MMAP_IMPL mmap_aligned -static void* lastAlignedmmap; /* Used as a hint */ -static void* mmap_aligned(void *start, size_t length, int prot, int flags, int fd, off_t offset) { - void* baseaddress = 0; - void* ptr = 0; - if(!start) { - baseaddress = lastAlignedmmap; - for(;;) { - if(baseaddress) flags|=MAP_FIXED; - ptr = mmap(baseaddress, length, prot, flags, fd, offset); - if(!ptr) - baseaddress = (void*)((size_t)baseaddress + mparams.granularity); - else if((size_t)ptr & (mparams.granularity - SIZE_T_ONE)) { - munmap(ptr, length); - baseaddress = (void*)(((size_t)ptr + mparams.granularity) & ~(mparams.granularity - SIZE_T_ONE)); - } - else break; - } - } - else ptr = mmap(start, length, prot, flags, fd, offset); - if(ptr) lastAlignedmmap = (void*)((size_t) ptr + mparams.granularity); - return ptr; -} -#else -#define MMAP_IMPL mmap -#endif /* DEFAULT_GRANULARITY_ALIGNED */ -#define MUNMAP_DEFAULT(a, s) munmap((a), (s)) -#define MMAP_PROT (PROT_READ|PROT_WRITE) -#ifdef MAP_ANONYMOUS -#define MMAP_FLAGS (MAP_PRIVATE|MAP_ANONYMOUS) -#define MMAP_DEFAULT(s) MMAP_IMPL(0, (s), MMAP_PROT, MMAP_FLAGS, -1, 0) -#else /* MAP_ANONYMOUS */ -/* - Nearly all versions of mmap support MAP_ANONYMOUS, so the following - is unlikely to be needed, but is supplied just in case. -*/ -#define MMAP_FLAGS (MAP_PRIVATE) -static int dev_zero_fd = -1; /* Cached file descriptor for /dev/zero. */ -#define MMAP_DEFAULT(s) ((dev_zero_fd < 0) ? \ - (dev_zero_fd = open("/dev/zero", O_RDWR), \ - MMAP_IMPL(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0)) : \ - MMAP_IMPL(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0)) -#endif /* MAP_ANONYMOUS */ - -#define DIRECT_MMAP_DEFAULT(s) MMAP_DEFAULT(s) - -#else /* WIN32 */ - -/* Win32 MMAP via VirtualAlloc */ -#ifdef DEFAULT_GRANULARITY_ALIGNED -static void* lastWin32mmap; /* Used as a hint */ -#endif /* DEFAULT_GRANULARITY_ALIGNED */ -#ifdef ENABLE_LARGE_PAGES -int largepagesavailable = 1; -#ifndef MEM_LARGE_PAGES - #define MEM_LARGE_PAGES 0x20000000 -#endif -#endif /* ENABLE_LARGE_PAGES */ -static FORCEINLINE void* win32mmap(size_t size) { - void* baseaddress = 0; - void* ptr = 0; -#ifdef ENABLE_LARGE_PAGES - /* Note that large pages are *always* allocated on a large page boundary. - If however granularity is small then don't waste a kernel call if size - isn't around the size of a large page */ - if(largepagesavailable && size >= 1*1024*1024) { - ptr = VirtualAlloc(baseaddress, size, MEM_RESERVE|MEM_COMMIT|MEM_LARGE_PAGES, PAGE_READWRITE); - if(!ptr && ERROR_PRIVILEGE_NOT_HELD==GetLastError()) largepagesavailable=0; - } -#endif - if(!ptr) { -#ifdef DEFAULT_GRANULARITY_ALIGNED - /* We try to avoid overhead by speculatively reserving at aligned - addresses until we succeed */ - baseaddress = lastWin32mmap; - for(;;) { - void* reserveaddr = VirtualAlloc(baseaddress, size, MEM_RESERVE, PAGE_READWRITE); - if(!reserveaddr) - baseaddress = (void*)((size_t)baseaddress + mparams.granularity); - else if((size_t)reserveaddr & (mparams.granularity - SIZE_T_ONE)) { - VirtualFree(reserveaddr, 0, MEM_RELEASE); - baseaddress = (void*)(((size_t)reserveaddr + mparams.granularity) & ~(mparams.granularity - SIZE_T_ONE)); - } - else break; - } -#endif - if(!ptr) ptr = VirtualAlloc(baseaddress, size, baseaddress ? MEM_COMMIT : MEM_RESERVE|MEM_COMMIT, PAGE_READWRITE); -#if DEBUG - if(lastWin32mmap && ptr!=lastWin32mmap) printf("Non-contiguous VirtualAlloc between %p and %p\n", ptr, lastWin32mmap); -#endif -#ifdef DEFAULT_GRANULARITY_ALIGNED - if(ptr) lastWin32mmap = (void*)((size_t) ptr + mparams.granularity); -#endif - } -#if DEBUG -#ifdef ENABLE_LARGE_PAGES - printf("VirtualAlloc returns %p size %u. LargePagesAvailable=%d\n", ptr, size, largepagesavailable); -#else - printf("VirtualAlloc returns %p size %u\n", ptr, size); -#endif -#endif - return (ptr != 0)? ptr: MFAIL; -} - -/* For direct MMAP, use MEM_TOP_DOWN to minimize interference */ -static FORCEINLINE void* win32direct_mmap(size_t size) { - void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT|MEM_TOP_DOWN, - PAGE_READWRITE); - return (ptr != 0)? ptr: MFAIL; -} - -/* This function supports releasing coalesed segments */ -static FORCEINLINE int win32munmap(void* ptr, size_t size) { - MEMORY_BASIC_INFORMATION minfo; - char* cptr = (char*)ptr; - while (size) { - if (VirtualQuery(cptr, &minfo, sizeof(minfo)) == 0) - return -1; - if (minfo.BaseAddress != cptr || minfo.AllocationBase != cptr || - minfo.State != MEM_COMMIT || minfo.RegionSize > size) - return -1; - if (VirtualFree(cptr, 0, MEM_RELEASE) == 0) - return -1; - cptr += minfo.RegionSize; - size -= minfo.RegionSize; - } - return 0; -} - -#define MMAP_DEFAULT(s) win32mmap(s) -#define MUNMAP_DEFAULT(a, s) win32munmap((a), (s)) -#define DIRECT_MMAP_DEFAULT(s) win32direct_mmap(s) -#endif /* WIN32 */ -#endif /* HAVE_MMAP */ - -#if HAVE_MREMAP -#ifndef WIN32 -#define MREMAP_DEFAULT(addr, osz, nsz, mv) mremap((addr), (osz), (nsz), (mv)) -#endif /* WIN32 */ -#endif /* HAVE_MREMAP */ - - -/** - * Define CALL_MORECORE - */ -#if HAVE_MORECORE - #ifdef MORECORE - #define CALL_MORECORE(S) MORECORE(S) - #else /* MORECORE */ - #define CALL_MORECORE(S) MORECORE_DEFAULT(S) - #endif /* MORECORE */ -#else /* HAVE_MORECORE */ - #define CALL_MORECORE(S) MFAIL -#endif /* HAVE_MORECORE */ - -/** - * Define CALL_MMAP/CALL_MUNMAP/CALL_DIRECT_MMAP - */ -#if HAVE_MMAP - #define USE_MMAP_BIT (SIZE_T_ONE) - - #ifdef MMAP - #define CALL_MMAP(s) MMAP(s) - #else /* MMAP */ - #define CALL_MMAP(s) MMAP_DEFAULT(s) - #endif /* MMAP */ - #ifdef MUNMAP - #define CALL_MUNMAP(a, s) MUNMAP((a), (s)) - #else /* MUNMAP */ - #define CALL_MUNMAP(a, s) MUNMAP_DEFAULT((a), (s)) - #endif /* MUNMAP */ - #ifdef DIRECT_MMAP - #define CALL_DIRECT_MMAP(s) DIRECT_MMAP(s) - #else /* DIRECT_MMAP */ - #define CALL_DIRECT_MMAP(s) DIRECT_MMAP_DEFAULT(s) - #endif /* DIRECT_MMAP */ -#else /* HAVE_MMAP */ - #define USE_MMAP_BIT (SIZE_T_ZERO) - - #define MMAP(s) MFAIL - #define MUNMAP(a, s) (-1) - #define DIRECT_MMAP(s) MFAIL - #define CALL_DIRECT_MMAP(s) DIRECT_MMAP(s) - #define CALL_MMAP(s) MMAP(s) - #define CALL_MUNMAP(a, s) MUNMAP((a), (s)) -#endif /* HAVE_MMAP */ - -/** - * Define CALL_MREMAP - */ -#if HAVE_MMAP && HAVE_MREMAP - #ifdef MREMAP - #define CALL_MREMAP(addr, osz, nsz, mv) MREMAP((addr), (osz), (nsz), (mv)) - #else /* MREMAP */ - #define CALL_MREMAP(addr, osz, nsz, mv) MREMAP_DEFAULT((addr), (osz), (nsz), (mv)) - #endif /* MREMAP */ -#else /* HAVE_MMAP && HAVE_MREMAP */ - #define CALL_MREMAP(addr, osz, nsz, mv) MFAIL -#endif /* HAVE_MMAP && HAVE_MREMAP */ - -/* mstate bit set if continguous morecore disabled or failed */ -#define USE_NONCONTIGUOUS_BIT (4U) - -/* segment bit set in create_mspace_with_base */ -#define EXTERN_BIT (8U) - - -/* --------------------------- Lock preliminaries ------------------------ */ - -/* - When locks are defined, there is one global lock, plus - one per-mspace lock. - - The global lock_ensures that mparams.magic and other unique - mparams values are initialized only once. It also protects - sequences of calls to MORECORE. In many cases sys_alloc requires - two calls, that should not be interleaved with calls by other - threads. This does not protect against direct calls to MORECORE - by other threads not using this lock, so there is still code to - cope the best we can on interference. - - Per-mspace locks surround calls to malloc, free, etc. To enable use - in layered extensions, per-mspace locks are reentrant. - - Because lock-protected regions generally have bounded times, it is - OK to use the supplied simple spinlocks in the custom versions for - x86. Spinlocks are likely to improve performance for lightly - contended applications, but worsen performance under heavy - contention. - - If USE_LOCKS is > 1, the definitions of lock routines here are - bypassed, in which case you will need to define the type MLOCK_T, - and at least INITIAL_LOCK, ACQUIRE_LOCK, RELEASE_LOCK and possibly - TRY_LOCK (which is not used in this malloc, but commonly needed in - extensions.) You must also declare a - static MLOCK_T malloc_global_mutex = { initialization values };. - -*/ - -#if USE_LOCKS == 1 - -#if USE_SPIN_LOCKS && SPIN_LOCKS_AVAILABLE -#ifndef WIN32 - -/* Custom pthread-style spin locks on x86 and x64 for gcc */ -struct pthread_mlock_t { - volatile unsigned int l; - char cachelinepadding[64]; - unsigned int c; - pthread_t threadid; -}; -#define MLOCK_T struct pthread_mlock_t -#define CURRENT_THREAD pthread_self() -#define INITIAL_LOCK(sl) ((sl)->threadid = 0, (sl)->l = (sl)->c = 0, 0) -#define ACQUIRE_LOCK(sl) pthread_acquire_lock(sl) -#define RELEASE_LOCK(sl) pthread_release_lock(sl) -#define TRY_LOCK(sl) pthread_try_lock(sl) -#define SPINS_PER_YIELD 63 - -static MLOCK_T malloc_global_mutex = { 0, "", 0, 0}; - -static FORCEINLINE int pthread_acquire_lock (MLOCK_T *sl) { - int spins = 0; - volatile unsigned int* lp = &sl->l; - for (;;) { - if (*lp != 0) { - if (sl->threadid == CURRENT_THREAD) { - ++sl->c; - return 0; - } - } - else { - /* place args to cmpxchgl in locals to evade oddities in some gccs */ - int cmp = 0; - int val = 1; - int ret; - __asm__ __volatile__ ("lock; cmpxchgl %1, %2" - : "=a" (ret) - : "r" (val), "m" (*(lp)), "0"(cmp) - : "memory", "cc"); - if (!ret) { - assert(!sl->threadid); - sl->threadid = CURRENT_THREAD; - sl->c = 1; - return 0; - } - } - if ((++spins & SPINS_PER_YIELD) == 0) { -#if defined (__SVR4) && defined (__sun) /* solaris */ - thr_yield(); -#else -#if defined(__linux__) || defined(__FreeBSD__) || defined(__APPLE__) - sched_yield(); -#else /* no-op yield on unknown systems */ - ; -#endif /* __linux__ || __FreeBSD__ || __APPLE__ */ -#endif /* solaris */ - } - } -} - -static FORCEINLINE void pthread_release_lock (MLOCK_T *sl) { - volatile unsigned int* lp = &sl->l; - assert(*lp != 0); - assert(sl->threadid == CURRENT_THREAD); - if (--sl->c == 0) { - sl->threadid = 0; - int prev = 0; - int ret; - __asm__ __volatile__ ("lock; xchgl %0, %1" - : "=r" (ret) - : "m" (*(lp)), "0"(prev) - : "memory"); - } -} - -static FORCEINLINE int pthread_try_lock (MLOCK_T *sl) { - volatile unsigned int* lp = &sl->l; - if (*lp != 0) { - if (sl->threadid == CURRENT_THREAD) { - ++sl->c; - return 1; - } - } - else { - int cmp = 0; - int val = 1; - int ret; - __asm__ __volatile__ ("lock; cmpxchgl %1, %2" - : "=a" (ret) - : "r" (val), "m" (*(lp)), "0"(cmp) - : "memory", "cc"); - if (!ret) { - assert(!sl->threadid); - sl->threadid = CURRENT_THREAD; - sl->c = 1; - return 1; - } - } - return 0; -} - - -#else /* WIN32 */ -/* Custom win32-style spin locks on x86 and x64 for MSC */ -struct win32_mlock_t { - volatile long l; - char cachelinepadding[64]; - unsigned int c; - long threadid; -}; - -#define MLOCK_T struct win32_mlock_t -#define CURRENT_THREAD ((long)GetCurrentThreadId()) -#define INITIAL_LOCK(sl) ((sl)->threadid = 0, (sl)->l = (sl)->c = 0, 0) -#define ACQUIRE_LOCK(sl) win32_acquire_lock(sl) -#define RELEASE_LOCK(sl) win32_release_lock(sl) -#define TRY_LOCK(sl) win32_try_lock(sl) -#define SPINS_PER_YIELD 63 - -static MLOCK_T malloc_global_mutex = { 0, "", 0, 0}; - -static FORCEINLINE int win32_acquire_lock (MLOCK_T *sl) { - int spins = 0; - for (;;) { - if (sl->l != 0) { - if (sl->threadid == CURRENT_THREAD) { - ++sl->c; - return 0; - } - } - else { - if (!interlockedexchange(&sl->l, 1)) { - assert(!sl->threadid); - sl->threadid = CURRENT_THREAD; - sl->c = 1; - return 0; - } - } - if ((++spins & SPINS_PER_YIELD) == 0) - SleepEx(0, FALSE); - } -} - -static FORCEINLINE void win32_release_lock (MLOCK_T *sl) { - assert(sl->threadid == CURRENT_THREAD); - assert(sl->l != 0); - if (--sl->c == 0) { - sl->threadid = 0; - interlockedexchange (&sl->l, 0); - } -} - -static FORCEINLINE int win32_try_lock (MLOCK_T *sl) { - if (sl->l != 0) { - if (sl->threadid == CURRENT_THREAD) { - ++sl->c; - return 1; - } - } - else { - if (!interlockedexchange(&sl->l, 1)){ - assert(!sl->threadid); - sl->threadid = CURRENT_THREAD; - sl->c = 1; - return 1; - } - } - return 0; -} - -#endif /* WIN32 */ -#else /* USE_SPIN_LOCKS */ - -#ifndef WIN32 -/* pthreads-based locks */ - -#define MLOCK_T pthread_mutex_t -#define CURRENT_THREAD pthread_self() -#define INITIAL_LOCK(sl) pthread_init_lock(sl) -#define ACQUIRE_LOCK(sl) pthread_mutex_lock(sl) -#define RELEASE_LOCK(sl) pthread_mutex_unlock(sl) -#define TRY_LOCK(sl) (!pthread_mutex_trylock(sl)) - -static MLOCK_T malloc_global_mutex = PTHREAD_MUTEX_INITIALIZER; - -/* Cope with old-style linux recursive lock initialization by adding */ -/* skipped internal declaration from pthread.h */ -#ifdef linux -#ifndef PTHREAD_MUTEX_RECURSIVE -extern int pthread_mutexattr_setkind_np __P ((pthread_mutexattr_t *__attr, - int __kind)); -#define PTHREAD_MUTEX_RECURSIVE PTHREAD_MUTEX_RECURSIVE_NP -#define pthread_mutexattr_settype(x,y) pthread_mutexattr_setkind_np(x,y) -#endif -#endif - -static int pthread_init_lock (MLOCK_T *sl) { - pthread_mutexattr_t attr; - if (pthread_mutexattr_init(&attr)) return 1; - if (pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_RECURSIVE)) return 1; - if (pthread_mutex_init(sl, &attr)) return 1; - if (pthread_mutexattr_destroy(&attr)) return 1; - return 0; -} - -#else /* WIN32 */ -/* Win32 critical sections */ -#define MLOCK_T CRITICAL_SECTION -#define CURRENT_THREAD GetCurrentThreadId() -#define INITIAL_LOCK(s) (!InitializeCriticalSectionAndSpinCount((s), 0x80000000|4000)) -#define ACQUIRE_LOCK(s) (EnterCriticalSection(sl), 0) -#define RELEASE_LOCK(s) LeaveCriticalSection(sl) -#define TRY_LOCK(s) TryEnterCriticalSection(sl) -#define NEED_GLOBAL_LOCK_INIT - -static MLOCK_T malloc_global_mutex; -static volatile long malloc_global_mutex_status; - -/* Use spin loop to initialize global lock */ -static void init_malloc_global_mutex() { - for (;;) { - long stat = malloc_global_mutex_status; - if (stat > 0) - return; - /* transition to < 0 while initializing, then to > 0) */ - if (stat == 0 && - interlockedcompareexchange(&malloc_global_mutex_status, -1, 0) == 0) { - InitializeCriticalSection(&malloc_global_mutex); - interlockedexchange(&malloc_global_mutex_status,1); - return; - } - SleepEx(0, FALSE); - } -} - -#endif /* WIN32 */ -#endif /* USE_SPIN_LOCKS */ -#endif /* USE_LOCKS == 1 */ - -/* ----------------------- User-defined locks ------------------------ */ - -#if USE_LOCKS > 1 -/* Define your own lock implementation here */ -/* #define INITIAL_LOCK(sl) ... */ -/* #define ACQUIRE_LOCK(sl) ... */ -/* #define RELEASE_LOCK(sl) ... */ -/* #define TRY_LOCK(sl) ... */ -/* static MLOCK_T malloc_global_mutex = ... */ -#endif /* USE_LOCKS > 1 */ - -/* ----------------------- Lock-based state ------------------------ */ - -#if USE_LOCKS -#define USE_LOCK_BIT (2U) -#else /* USE_LOCKS */ -#define USE_LOCK_BIT (0U) -#define INITIAL_LOCK(l) -#endif /* USE_LOCKS */ - -#if USE_LOCKS -#ifndef ACQUIRE_MALLOC_GLOBAL_LOCK -#define ACQUIRE_MALLOC_GLOBAL_LOCK() ACQUIRE_LOCK(&malloc_global_mutex); -#endif -#ifndef RELEASE_MALLOC_GLOBAL_LOCK -#define RELEASE_MALLOC_GLOBAL_LOCK() RELEASE_LOCK(&malloc_global_mutex); -#endif -#else /* USE_LOCKS */ -#define ACQUIRE_MALLOC_GLOBAL_LOCK() -#define RELEASE_MALLOC_GLOBAL_LOCK() -#endif /* USE_LOCKS */ - - -/* ----------------------- Chunk representations ------------------------ */ - -/* - (The following includes lightly edited explanations by Colin Plumb.) - - The malloc_chunk declaration below is misleading (but accurate and - necessary). It declares a "view" into memory allowing access to - necessary fields at known offsets from a given base. - - Chunks of memory are maintained using a `boundary tag' method as - originally described by Knuth. (See the paper by Paul Wilson - ftp://ftp.cs.utexas.edu/pub/garbage/allocsrv.ps for a survey of such - techniques.) Sizes of free chunks are stored both in the front of - each chunk and at the end. This makes consolidating fragmented - chunks into bigger chunks fast. The head fields also hold bits - representing whether chunks are free or in use. - - Here are some pictures to make it clearer. They are "exploded" to - show that the state of a chunk can be thought of as extending from - the high 31 bits of the head field of its header through the - prev_foot and PINUSE_BIT bit of the following chunk header. - - A chunk that's in use looks like: - - chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Size of previous chunk (if P = 0) | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P| - | Size of this chunk 1| +-+ - mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | | - +- -+ - | | - +- -+ - | : - +- size - sizeof(size_t) available payload bytes -+ - : | - chunk-> +- -+ - | | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |1| - | Size of next chunk (may or may not be in use) | +-+ - mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - - And if it's free, it looks like this: - - chunk-> +- -+ - | User payload (must be in use, or we would have merged!) | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P| - | Size of this chunk 0| +-+ - mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Next pointer | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Prev pointer | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | : - +- size - sizeof(struct chunk) unused bytes -+ - : | - chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Size of this chunk | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |0| - | Size of next chunk (must be in use, or we would have merged)| +-+ - mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | : - +- User payload -+ - : | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - |0| - +-+ - Note that since we always merge adjacent free chunks, the chunks - adjacent to a free chunk must be in use. - - Given a pointer to a chunk (which can be derived trivially from the - payload pointer) we can, in O(1) time, find out whether the adjacent - chunks are free, and if so, unlink them from the lists that they - are on and merge them with the current chunk. - - Chunks always begin on even word boundaries, so the mem portion - (which is returned to the user) is also on an even word boundary, and - thus at least double-word aligned. - - The P (PINUSE_BIT) bit, stored in the unused low-order bit of the - chunk size (which is always a multiple of two words), is an in-use - bit for the *previous* chunk. If that bit is *clear*, then the - word before the current chunk size contains the previous chunk - size, and can be used to find the front of the previous chunk. - The very first chunk allocated always has this bit set, preventing - access to non-existent (or non-owned) memory. If pinuse is set for - any given chunk, then you CANNOT determine the size of the - previous chunk, and might even get a memory addressing fault when - trying to do so. - - The C (CINUSE_BIT) bit, stored in the unused second-lowest bit of - the chunk size redundantly records whether the current chunk is - inuse (unless the chunk is mmapped). This redundancy enables usage - checks within free and realloc, and reduces indirection when freeing - and consolidating chunks. - - Each freshly allocated chunk must have both cinuse and pinuse set. - That is, each allocated chunk borders either a previously allocated - and still in-use chunk, or the base of its memory arena. This is - ensured by making all allocations from the the `lowest' part of any - found chunk. Further, no free chunk physically borders another one, - so each free chunk is known to be preceded and followed by either - inuse chunks or the ends of memory. - - Note that the `foot' of the current chunk is actually represented - as the prev_foot of the NEXT chunk. This makes it easier to - deal with alignments etc but can be very confusing when trying - to extend or adapt this code. - - The exceptions to all this are - - 1. The special chunk `top' is the top-most available chunk (i.e., - the one bordering the end of available memory). It is treated - specially. Top is never included in any bin, is used only if - no other chunk is available, and is released back to the - system if it is very large (see M_TRIM_THRESHOLD). In effect, - the top chunk is treated as larger (and thus less well - fitting) than any other available chunk. The top chunk - doesn't update its trailing size field since there is no next - contiguous chunk that would have to index off it. However, - space is still allocated for it (TOP_FOOT_SIZE) to enable - separation or merging when space is extended. - - 3. Chunks allocated via mmap, have both cinuse and pinuse bits - cleared in their head fields. Because they are allocated - one-by-one, each must carry its own prev_foot field, which is - also used to hold the offset this chunk has within its mmapped - region, which is needed to preserve alignment. Each mmapped - chunk is trailed by the first two fields of a fake next-chunk - for sake of usage checks. - -*/ - -struct malloc_chunk { - size_t prev_foot; /* Size of previous chunk (if free). */ - size_t head; /* Size and inuse bits. */ - struct malloc_chunk* fd; /* double links -- used only if free. */ - struct malloc_chunk* bk; -}; - -typedef struct malloc_chunk mchunk; -typedef struct malloc_chunk* mchunkptr; -typedef struct malloc_chunk* sbinptr; /* The type of bins of chunks */ -typedef unsigned int bindex_t; /* Described below */ -typedef unsigned int binmap_t; /* Described below */ - -/* ------------------- Chunks sizes and alignments ----------------------- */ - -#define MCHUNK_SIZE (sizeof(mchunk)) - -#if FOOTERS -#define CHUNK_OVERHEAD (TWO_SIZE_T_SIZES) -#else /* FOOTERS */ -#define CHUNK_OVERHEAD (SIZE_T_SIZE) -#endif /* FOOTERS */ - -/* MMapped chunks need a second word of overhead ... */ -#define MMAP_CHUNK_OVERHEAD (TWO_SIZE_T_SIZES) -/* ... and additional padding for fake next-chunk at foot */ -#define MMAP_FOOT_PAD (FOUR_SIZE_T_SIZES) - -/* The smallest size we can malloc is an aligned minimal chunk */ -#define MIN_CHUNK_SIZE\ - ((MCHUNK_SIZE + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK) - -/* conversion from malloc headers to user pointers, and back */ -#define chunk2mem(p) ((void*)((char*)(p) + TWO_SIZE_T_SIZES)) -#define mem2chunk(mem) ((mchunkptr)((char*)(mem) - TWO_SIZE_T_SIZES)) -/* chunk associated with aligned address A */ -#define align_as_chunk(A) (mchunkptr)((A) + align_offset(chunk2mem(A))) - -/* Bounds on request (not chunk) sizes. */ -#define MAX_REQUEST ((-MIN_CHUNK_SIZE) << 2) -#define MIN_REQUEST (MIN_CHUNK_SIZE - CHUNK_OVERHEAD - SIZE_T_ONE) - -/* pad request bytes into a usable size */ -#define pad_request(req) \ - (((req) + CHUNK_OVERHEAD + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK) - -/* pad request, checking for minimum (but not maximum) */ -#define request2size(req) \ - (((req) < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(req)) - - -/* ------------------ Operations on head and foot fields ----------------- */ - -/* - The head field of a chunk is or'ed with PINUSE_BIT when previous - adjacent chunk in use, and or'ed with CINUSE_BIT if this chunk is in - use, unless mmapped, in which case both bits are cleared. - - FLAG4_BIT is not used by this malloc, but might be useful in extensions. -*/ - -#define PINUSE_BIT (SIZE_T_ONE) -#define CINUSE_BIT (SIZE_T_TWO) -#define FLAG4_BIT (SIZE_T_FOUR) -#define INUSE_BITS (PINUSE_BIT|CINUSE_BIT) -#define FLAG_BITS (PINUSE_BIT|CINUSE_BIT|FLAG4_BIT) - -/* Head value for fenceposts */ -#define FENCEPOST_HEAD (INUSE_BITS|SIZE_T_SIZE) - -/* extraction of fields from head words */ -#define cinuse(p) ((p)->head & CINUSE_BIT) -#define pinuse(p) ((p)->head & PINUSE_BIT) -#define is_inuse(p) (((p)->head & INUSE_BITS) != PINUSE_BIT) -#define is_mmapped(p) (((p)->head & INUSE_BITS) == 0) - -#define chunksize(p) ((p)->head & ~(FLAG_BITS)) - -#define clear_pinuse(p) ((p)->head &= ~PINUSE_BIT) - -/* Treat space at ptr +/- offset as a chunk */ -#define chunk_plus_offset(p, s) ((mchunkptr)(((char*)(p)) + (s))) -#define chunk_minus_offset(p, s) ((mchunkptr)(((char*)(p)) - (s))) - -/* Ptr to next or previous physical malloc_chunk. */ -#define next_chunk(p) ((mchunkptr)( ((char*)(p)) + ((p)->head & ~FLAG_BITS))) -#define prev_chunk(p) ((mchunkptr)( ((char*)(p)) - ((p)->prev_foot) )) - -/* extract next chunk's pinuse bit */ -#define next_pinuse(p) ((next_chunk(p)->head) & PINUSE_BIT) - -/* Get/set size at footer */ -#define get_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot) -#define set_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot = (s)) - -/* Set size, pinuse bit, and foot */ -#define set_size_and_pinuse_of_free_chunk(p, s)\ - ((p)->head = (s|PINUSE_BIT), set_foot(p, s)) - -/* Set size, pinuse bit, foot, and clear next pinuse */ -#define set_free_with_pinuse(p, s, n)\ - (clear_pinuse(n), set_size_and_pinuse_of_free_chunk(p, s)) - -/* Get the internal overhead associated with chunk p */ -#define overhead_for(p)\ - (is_mmapped(p)? MMAP_CHUNK_OVERHEAD : CHUNK_OVERHEAD) - -/* Return true if malloced space is not necessarily cleared */ -#if MMAP_CLEARS -#define calloc_must_clear(p) (!is_mmapped(p)) -#else /* MMAP_CLEARS */ -#define calloc_must_clear(p) (1) -#endif /* MMAP_CLEARS */ - -/* ---------------------- Overlaid data structures ----------------------- */ - -/* - When chunks are not in use, they are treated as nodes of either - lists or trees. - - "Small" chunks are stored in circular doubly-linked lists, and look - like this: - - chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Size of previous chunk | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - `head:' | Size of chunk, in bytes |P| - mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Forward pointer to next chunk in list | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Back pointer to previous chunk in list | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Unused space (may be 0 bytes long) . - . . - . | -nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - `foot:' | Size of chunk, in bytes | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - - Larger chunks are kept in a form of bitwise digital trees (aka - tries) keyed on chunksizes. Because malloc_tree_chunks are only for - free chunks greater than 256 bytes, their size doesn't impose any - constraints on user chunk sizes. Each node looks like: - - chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Size of previous chunk | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - `head:' | Size of chunk, in bytes |P| - mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Forward pointer to next chunk of same size | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Back pointer to previous chunk of same size | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Pointer to left child (child[0]) | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Pointer to right child (child[1]) | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Pointer to parent | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | bin index of this chunk | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Unused space . - . | -nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - `foot:' | Size of chunk, in bytes | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - - Each tree holding treenodes is a tree of unique chunk sizes. Chunks - of the same size are arranged in a circularly-linked list, with only - the oldest chunk (the next to be used, in our FIFO ordering) - actually in the tree. (Tree members are distinguished by a non-null - parent pointer.) If a chunk with the same size an an existing node - is inserted, it is linked off the existing node using pointers that - work in the same way as fd/bk pointers of small chunks. - - Each tree contains a power of 2 sized range of chunk sizes (the - smallest is 0x100 <= x < 0x180), which is is divided in half at each - tree level, with the chunks in the smaller half of the range (0x100 - <= x < 0x140 for the top nose) in the left subtree and the larger - half (0x140 <= x < 0x180) in the right subtree. This is, of course, - done by inspecting individual bits. - - Using these rules, each node's left subtree contains all smaller - sizes than its right subtree. However, the node at the root of each - subtree has no particular ordering relationship to either. (The - dividing line between the subtree sizes is based on trie relation.) - If we remove the last chunk of a given size from the interior of the - tree, we need to replace it with a leaf node. The tree ordering - rules permit a node to be replaced by any leaf below it. - - The smallest chunk in a tree (a common operation in a best-fit - allocator) can be found by walking a path to the leftmost leaf in - the tree. Unlike a usual binary tree, where we follow left child - pointers until we reach a null, here we follow the right child - pointer any time the left one is null, until we reach a leaf with - both child pointers null. The smallest chunk in the tree will be - somewhere along that path. - - The worst case number of steps to add, find, or remove a node is - bounded by the number of bits differentiating chunks within - bins. Under current bin calculations, this ranges from 6 up to 21 - (for 32 bit sizes) or up to 53 (for 64 bit sizes). The typical case - is of course much better. -*/ - -struct malloc_tree_chunk { - /* The first four fields must be compatible with malloc_chunk */ - size_t prev_foot; - size_t head; - struct malloc_tree_chunk* fd; - struct malloc_tree_chunk* bk; - - struct malloc_tree_chunk* child[2]; - struct malloc_tree_chunk* parent; - bindex_t index; -}; - -typedef struct malloc_tree_chunk tchunk; -typedef struct malloc_tree_chunk* tchunkptr; -typedef struct malloc_tree_chunk* tbinptr; /* The type of bins of trees */ - -/* A little helper macro for trees */ -#define leftmost_child(t) ((t)->child[0] != 0? (t)->child[0] : (t)->child[1]) - -/* ----------------------------- Segments -------------------------------- */ - -/* - Each malloc space may include non-contiguous segments, held in a - list headed by an embedded malloc_segment record representing the - top-most space. Segments also include flags holding properties of - the space. Large chunks that are directly allocated by mmap are not - included in this list. They are instead independently created and - destroyed without otherwise keeping track of them. - - Segment management mainly comes into play for spaces allocated by - MMAP. Any call to MMAP might or might not return memory that is - adjacent to an existing segment. MORECORE normally contiguously - extends the current space, so this space is almost always adjacent, - which is simpler and faster to deal with. (This is why MORECORE is - used preferentially to MMAP when both are available -- see - sys_alloc.) When allocating using MMAP, we don't use any of the - hinting mechanisms (inconsistently) supported in various - implementations of unix mmap, or distinguish reserving from - committing memory. Instead, we just ask for space, and exploit - contiguity when we get it. It is probably possible to do - better than this on some systems, but no general scheme seems - to be significantly better. - - Management entails a simpler variant of the consolidation scheme - used for chunks to reduce fragmentation -- new adjacent memory is - normally prepended or appended to an existing segment. However, - there are limitations compared to chunk consolidation that mostly - reflect the fact that segment processing is relatively infrequent - (occurring only when getting memory from system) and that we - don't expect to have huge numbers of segments: - - * Segments are not indexed, so traversal requires linear scans. (It - would be possible to index these, but is not worth the extra - overhead and complexity for most programs on most platforms.) - * New segments are only appended to old ones when holding top-most - memory; if they cannot be prepended to others, they are held in - different segments. - - Except for the top-most segment of an mstate, each segment record - is kept at the tail of its segment. Segments are added by pushing - segment records onto the list headed by &mstate.seg for the - containing mstate. - - Segment flags control allocation/merge/deallocation policies: - * If EXTERN_BIT set, then we did not allocate this segment, - and so should not try to deallocate or merge with others. - (This currently holds only for the initial segment passed - into create_mspace_with_base.) - * If USE_MMAP_BIT set, the segment may be merged with - other surrounding mmapped segments and trimmed/de-allocated - using munmap. - * If neither bit is set, then the segment was obtained using - MORECORE so can be merged with surrounding MORECORE'd segments - and deallocated/trimmed using MORECORE with negative arguments. -*/ - -struct malloc_segment { - char* base; /* base address */ - size_t size; /* allocated size */ - struct malloc_segment* next; /* ptr to next segment */ - flag_t sflags; /* mmap and extern flag */ -}; - -#define is_mmapped_segment(S) ((S)->sflags & USE_MMAP_BIT) -#define is_extern_segment(S) ((S)->sflags & EXTERN_BIT) - -typedef struct malloc_segment msegment; -typedef struct malloc_segment* msegmentptr; - -/* ---------------------------- malloc_state ----------------------------- */ - -/* - A malloc_state holds all of the bookkeeping for a space. - The main fields are: - - Top - The topmost chunk of the currently active segment. Its size is - cached in topsize. The actual size of topmost space is - topsize+TOP_FOOT_SIZE, which includes space reserved for adding - fenceposts and segment records if necessary when getting more - space from the system. The size at which to autotrim top is - cached from mparams in trim_check, except that it is disabled if - an autotrim fails. - - Designated victim (dv) - This is the preferred chunk for servicing small requests that - don't have exact fits. It is normally the chunk split off most - recently to service another small request. Its size is cached in - dvsize. The link fields of this chunk are not maintained since it - is not kept in a bin. - - SmallBins - An array of bin headers for free chunks. These bins hold chunks - with sizes less than MIN_LARGE_SIZE bytes. Each bin contains - chunks of all the same size, spaced 8 bytes apart. To simplify - use in double-linked lists, each bin header acts as a malloc_chunk - pointing to the real first node, if it exists (else pointing to - itself). This avoids special-casing for headers. But to avoid - waste, we allocate only the fd/bk pointers of bins, and then use - repositioning tricks to treat these as the fields of a chunk. - - TreeBins - Treebins are pointers to the roots of trees holding a range of - sizes. There are 2 equally spaced treebins for each power of two - from TREE_SHIFT to TREE_SHIFT+16. The last bin holds anything - larger. - - Bin maps - There is one bit map for small bins ("smallmap") and one for - treebins ("treemap). Each bin sets its bit when non-empty, and - clears the bit when empty. Bit operations are then used to avoid - bin-by-bin searching -- nearly all "search" is done without ever - looking at bins that won't be selected. The bit maps - conservatively use 32 bits per map word, even if on 64bit system. - For a good description of some of the bit-based techniques used - here, see Henry S. Warren Jr's book "Hacker's Delight" (and - supplement at http://hackersdelight.org/). Many of these are - intended to reduce the branchiness of paths through malloc etc, as - well as to reduce the number of memory locations read or written. - - Segments - A list of segments headed by an embedded malloc_segment record - representing the initial space. - - Address check support - The least_addr field is the least address ever obtained from - MORECORE or MMAP. Attempted frees and reallocs of any address less - than this are trapped (unless INSECURE is defined). - - Magic tag - A cross-check field that should always hold same value as mparams.magic. - - Flags - Bits recording whether to use MMAP, locks, or contiguous MORECORE - - Statistics - Each space keeps track of current and maximum system memory - obtained via MORECORE or MMAP. - - Trim support - Fields holding the amount of unused topmost memory that should trigger - timming, and a counter to force periodic scanning to release unused - non-topmost segments. - - Locking - If USE_LOCKS is defined, the "mutex" lock is acquired and released - around every public call using this mspace. - - Extension support - A void* pointer and a size_t field that can be used to help implement - extensions to this malloc. -*/ - -/* Bin types, widths and sizes */ -#define NSMALLBINS (32U) -#define NTREEBINS (32U) -#define SMALLBIN_SHIFT (3U) -#define SMALLBIN_WIDTH (SIZE_T_ONE << SMALLBIN_SHIFT) -#define TREEBIN_SHIFT (8U) -#define MIN_LARGE_SIZE (SIZE_T_ONE << TREEBIN_SHIFT) -#define MAX_SMALL_SIZE (MIN_LARGE_SIZE - SIZE_T_ONE) -#define MAX_SMALL_REQUEST (MAX_SMALL_SIZE - CHUNK_ALIGN_MASK - CHUNK_OVERHEAD) - -struct malloc_state { - binmap_t smallmap; - binmap_t treemap; - size_t dvsize; - size_t topsize; - char* least_addr; - mchunkptr dv; - mchunkptr top; - size_t trim_check; - size_t release_checks; - size_t magic; - mchunkptr smallbins[(NSMALLBINS+1)*2]; - tbinptr treebins[NTREEBINS]; - size_t footprint; - size_t max_footprint; - flag_t mflags; - msegment seg; -#if USE_LOCKS - MLOCK_T mutex; /* locate lock among fields that rarely change */ -#endif /* USE_LOCKS */ - void* extp; /* Unused but available for extensions */ - size_t exts; -}; - -typedef struct malloc_state* mstate; - -/* ------------- Global malloc_state and malloc_params ------------------- */ - -#if !ONLY_MSPACES - -/* The global malloc_state used for all non-"mspace" calls */ -static struct malloc_state _gm_; -#define gm (&_gm_) -#define is_global(M) ((M) == &_gm_) - -#endif /* !ONLY_MSPACES */ - -#define is_initialized(M) ((M)->top != 0) - -/* -------------------------- system alloc setup ------------------------- */ - -/* Operations on mflags */ - -#define use_lock(M) ((M)->mflags & USE_LOCK_BIT) -#define enable_lock(M) ((M)->mflags |= USE_LOCK_BIT) -#define disable_lock(M) ((M)->mflags &= ~USE_LOCK_BIT) - -#define use_mmap(M) ((M)->mflags & USE_MMAP_BIT) -#define enable_mmap(M) ((M)->mflags |= USE_MMAP_BIT) -#define disable_mmap(M) ((M)->mflags &= ~USE_MMAP_BIT) - -#define use_noncontiguous(M) ((M)->mflags & USE_NONCONTIGUOUS_BIT) -#define disable_contiguous(M) ((M)->mflags |= USE_NONCONTIGUOUS_BIT) - -#define set_lock(M,L)\ - ((M)->mflags = (L)?\ - ((M)->mflags | USE_LOCK_BIT) :\ - ((M)->mflags & ~USE_LOCK_BIT)) - -/* page-align a size */ -#define page_align(S)\ - (((S) + (mparams.page_size - SIZE_T_ONE)) & ~(mparams.page_size - SIZE_T_ONE)) - -/* granularity-align a size */ -#define granularity_align(S)\ - (((S) + (mparams.granularity - SIZE_T_ONE))\ - & ~(mparams.granularity - SIZE_T_ONE)) - - -/* For mmap, use granularity alignment on windows, else page-align */ -#ifdef WIN32 -#define mmap_align(S) granularity_align(S) -#else -#define mmap_align(S) page_align(S) -#endif - -/* For sys_alloc, enough padding to ensure can malloc request on success */ -#define SYS_ALLOC_PADDING (TOP_FOOT_SIZE + MALLOC_ALIGNMENT) - -#define is_page_aligned(S)\ - (((size_t)(S) & (mparams.page_size - SIZE_T_ONE)) == 0) -#define is_granularity_aligned(S)\ - (((size_t)(S) & (mparams.granularity - SIZE_T_ONE)) == 0) - -/* True if segment S holds address A */ -#define segment_holds(S, A)\ - ((char*)(A) >= S->base && (char*)(A) < S->base + S->size) - -/* Return segment holding given address */ -static msegmentptr segment_holding(mstate m, char* addr) { - msegmentptr sp = &m->seg; - for (;;) { - if (addr >= sp->base && addr < sp->base + sp->size) - return sp; - if ((sp = sp->next) == 0) - return 0; - } -} - -/* Return true if segment contains a segment link */ -static int has_segment_link(mstate m, msegmentptr ss) { - msegmentptr sp = &m->seg; - for (;;) { - if ((char*)sp >= ss->base && (char*)sp < ss->base + ss->size) - return 1; - if ((sp = sp->next) == 0) - return 0; - } -} - -#ifndef MORECORE_CANNOT_TRIM -#define should_trim(M,s) ((s) > (M)->trim_check) -#else /* MORECORE_CANNOT_TRIM */ -#define should_trim(M,s) (0) -#endif /* MORECORE_CANNOT_TRIM */ - -/* - TOP_FOOT_SIZE is padding at the end of a segment, including space - that may be needed to place segment records and fenceposts when new - noncontiguous segments are added. -*/ -#define TOP_FOOT_SIZE\ - (align_offset(chunk2mem(0))+pad_request(sizeof(struct malloc_segment))+MIN_CHUNK_SIZE) - - -/* ------------------------------- Hooks -------------------------------- */ - -/* - PREACTION should be defined to return 0 on success, and nonzero on - failure. If you are not using locking, you can redefine these to do - anything you like. -*/ - -#if USE_LOCKS - -#define PREACTION(M) ((use_lock(M))? ACQUIRE_LOCK(&(M)->mutex) : 0) -#define POSTACTION(M) { if (use_lock(M)) RELEASE_LOCK(&(M)->mutex); } -#else /* USE_LOCKS */ - -#ifndef PREACTION -#define PREACTION(M) (0) -#endif /* PREACTION */ - -#ifndef POSTACTION -#define POSTACTION(M) -#endif /* POSTACTION */ - -#endif /* USE_LOCKS */ - -/* - CORRUPTION_ERROR_ACTION is triggered upon detected bad addresses. - USAGE_ERROR_ACTION is triggered on detected bad frees and - reallocs. The argument p is an address that might have triggered the - fault. It is ignored by the two predefined actions, but might be - useful in custom actions that try to help diagnose errors. -*/ - -#if PROCEED_ON_ERROR - -/* A count of the number of corruption errors causing resets */ -int malloc_corruption_error_count; - -/* default corruption action */ -static void reset_on_error(mstate m); - -#define CORRUPTION_ERROR_ACTION(m) reset_on_error(m) -#define USAGE_ERROR_ACTION(m, p) - -#else /* PROCEED_ON_ERROR */ - -#ifndef CORRUPTION_ERROR_ACTION -#define CORRUPTION_ERROR_ACTION(m) ABORT -#endif /* CORRUPTION_ERROR_ACTION */ - -#ifndef USAGE_ERROR_ACTION -#define USAGE_ERROR_ACTION(m,p) ABORT -#endif /* USAGE_ERROR_ACTION */ - -#endif /* PROCEED_ON_ERROR */ - -/* -------------------------- Debugging setup ---------------------------- */ - -#if ! DEBUG - -#define check_free_chunk(M,P) -#define check_inuse_chunk(M,P) -#define check_malloced_chunk(M,P,N) -#define check_mmapped_chunk(M,P) -#define check_malloc_state(M) -#define check_top_chunk(M,P) - -#else /* DEBUG */ -#define check_free_chunk(M,P) do_check_free_chunk(M,P) -#define check_inuse_chunk(M,P) do_check_inuse_chunk(M,P) -#define check_top_chunk(M,P) do_check_top_chunk(M,P) -#define check_malloced_chunk(M,P,N) do_check_malloced_chunk(M,P,N) -#define check_mmapped_chunk(M,P) do_check_mmapped_chunk(M,P) -#define check_malloc_state(M) do_check_malloc_state(M) - -static void do_check_any_chunk(mstate m, mchunkptr p); -static void do_check_top_chunk(mstate m, mchunkptr p); -static void do_check_mmapped_chunk(mstate m, mchunkptr p); -static void do_check_inuse_chunk(mstate m, mchunkptr p); -static void do_check_free_chunk(mstate m, mchunkptr p); -static void do_check_malloced_chunk(mstate m, void* mem, size_t s); -static void do_check_tree(mstate m, tchunkptr t); -static void do_check_treebin(mstate m, bindex_t i); -static void do_check_smallbin(mstate m, bindex_t i); -static void do_check_malloc_state(mstate m); -static int bin_find(mstate m, mchunkptr x); -static size_t traverse_and_check(mstate m); -#endif /* DEBUG */ - -/* ---------------------------- Indexing Bins ---------------------------- */ - -#define is_small(s) (((s) >> SMALLBIN_SHIFT) < NSMALLBINS) -#define small_index(s) (bindex_t)((s) >> SMALLBIN_SHIFT) -#define small_index2size(i) ((i) << SMALLBIN_SHIFT) -#define MIN_SMALL_INDEX (small_index(MIN_CHUNK_SIZE)) - -/* addressing by index. See above about smallbin repositioning */ -#define smallbin_at(M, i) ((sbinptr)((char*)&((M)->smallbins[(i)<<1]))) -#define treebin_at(M,i) (&((M)->treebins[i])) - -/* assign tree index for size S to variable I. Use x86 asm if possible */ -#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__)) -#define compute_tree_index(S, I)\ -{\ - unsigned int X = S >> TREEBIN_SHIFT;\ - if (X == 0)\ - I = 0;\ - else if (X > 0xFFFF)\ - I = NTREEBINS-1;\ - else {\ - unsigned int K;\ - __asm__("bsrl\t%1, %0\n\t" : "=r" (K) : "g" (X));\ - I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\ - }\ -} - -#elif defined (__INTEL_COMPILER) -#define compute_tree_index(S, I)\ -{\ - size_t X = S >> TREEBIN_SHIFT;\ - if (X == 0)\ - I = 0;\ - else if (X > 0xFFFF)\ - I = NTREEBINS-1;\ - else {\ - unsigned int K = _bit_scan_reverse (X); \ - I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\ - }\ -} - -#elif defined(_MSC_VER) && _MSC_VER>=1300 -#define compute_tree_index(S, I)\ -{\ - size_t X = S >> TREEBIN_SHIFT;\ - if (X == 0)\ - I = 0;\ - else if (X > 0xFFFF)\ - I = NTREEBINS-1;\ - else {\ - unsigned int K;\ - _BitScanReverse((DWORD *) &K, (DWORD) X);\ - I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\ - }\ -} - -#else /* GNUC */ -#define compute_tree_index(S, I)\ -{\ - size_t X = S >> TREEBIN_SHIFT;\ - if (X == 0)\ - I = 0;\ - else if (X > 0xFFFF)\ - I = NTREEBINS-1;\ - else {\ - unsigned int Y = (unsigned int)X;\ - unsigned int N = ((Y - 0x100) >> 16) & 8;\ - unsigned int K = (((Y <<= N) - 0x1000) >> 16) & 4;\ - N += K;\ - N += K = (((Y <<= K) - 0x4000) >> 16) & 2;\ - K = 14 - N + ((Y <<= K) >> 15);\ - I = (K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1));\ - }\ -} -#endif /* GNUC */ - -/* Bit representing maximum resolved size in a treebin at i */ -#define bit_for_tree_index(i) \ - (i == NTREEBINS-1)? (SIZE_T_BITSIZE-1) : (((i) >> 1) + TREEBIN_SHIFT - 2) - -/* Shift placing maximum resolved bit in a treebin at i as sign bit */ -#define leftshift_for_tree_index(i) \ - ((i == NTREEBINS-1)? 0 : \ - ((SIZE_T_BITSIZE-SIZE_T_ONE) - (((i) >> 1) + TREEBIN_SHIFT - 2))) - -/* The size of the smallest chunk held in bin with index i */ -#define minsize_for_tree_index(i) \ - ((SIZE_T_ONE << (((i) >> 1) + TREEBIN_SHIFT)) | \ - (((size_t)((i) & SIZE_T_ONE)) << (((i) >> 1) + TREEBIN_SHIFT - 1))) - - -/* ------------------------ Operations on bin maps ----------------------- */ - -/* bit corresponding to given index */ -#define idx2bit(i) ((binmap_t)(1) << (i)) - -/* Mark/Clear bits with given index */ -#define mark_smallmap(M,i) ((M)->smallmap |= idx2bit(i)) -#define clear_smallmap(M,i) ((M)->smallmap &= ~idx2bit(i)) -#define smallmap_is_marked(M,i) ((M)->smallmap & idx2bit(i)) - -#define mark_treemap(M,i) ((M)->treemap |= idx2bit(i)) -#define clear_treemap(M,i) ((M)->treemap &= ~idx2bit(i)) -#define treemap_is_marked(M,i) ((M)->treemap & idx2bit(i)) - -/* isolate the least set bit of a bitmap */ -#define least_bit(x) ((x) & -(x)) - -/* mask with all bits to left of least bit of x on */ -#define left_bits(x) ((x<<1) | -(x<<1)) - -/* mask with all bits to left of or equal to least bit of x on */ -#define same_or_left_bits(x) ((x) | -(x)) - -/* index corresponding to given bit. Use x86 asm if possible */ - -#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__)) -#define compute_bit2idx(X, I)\ -{\ - unsigned int J;\ - __asm__("bsfl\t%1, %0\n\t" : "=r" (J) : "g" (X));\ - I = (bindex_t)J;\ -} - -#elif defined (__INTEL_COMPILER) -#define compute_bit2idx(X, I)\ -{\ - unsigned int J;\ - J = _bit_scan_forward (X); \ - I = (bindex_t)J;\ -} - -#elif defined(_MSC_VER) && _MSC_VER>=1300 -#define compute_bit2idx(X, I)\ -{\ - unsigned int J;\ - _BitScanForward((DWORD *) &J, X);\ - I = (bindex_t)J;\ -} - -#elif USE_BUILTIN_FFS -#define compute_bit2idx(X, I) I = ffs(X)-1 - -#else -#define compute_bit2idx(X, I)\ -{\ - unsigned int Y = X - 1;\ - unsigned int K = Y >> (16-4) & 16;\ - unsigned int N = K; Y >>= K;\ - N += K = Y >> (8-3) & 8; Y >>= K;\ - N += K = Y >> (4-2) & 4; Y >>= K;\ - N += K = Y >> (2-1) & 2; Y >>= K;\ - N += K = Y >> (1-0) & 1; Y >>= K;\ - I = (bindex_t)(N + Y);\ -} -#endif /* GNUC */ - - -/* ----------------------- Runtime Check Support ------------------------- */ - -/* - For security, the main invariant is that malloc/free/etc never - writes to a static address other than malloc_state, unless static - malloc_state itself has been corrupted, which cannot occur via - malloc (because of these checks). In essence this means that we - believe all pointers, sizes, maps etc held in malloc_state, but - check all of those linked or offsetted from other embedded data - structures. These checks are interspersed with main code in a way - that tends to minimize their run-time cost. - - When FOOTERS is defined, in addition to range checking, we also - verify footer fields of inuse chunks, which can be used guarantee - that the mstate controlling malloc/free is intact. This is a - streamlined version of the approach described by William Robertson - et al in "Run-time Detection of Heap-based Overflows" LISA'03 - http://www.usenix.org/events/lisa03/tech/robertson.html The footer - of an inuse chunk holds the xor of its mstate and a random seed, - that is checked upon calls to free() and realloc(). This is - (probablistically) unguessable from outside the program, but can be - computed by any code successfully malloc'ing any chunk, so does not - itself provide protection against code that has already broken - security through some other means. Unlike Robertson et al, we - always dynamically check addresses of all offset chunks (previous, - next, etc). This turns out to be cheaper than relying on hashes. -*/ - -#if !INSECURE -/* Check if address a is at least as high as any from MORECORE or MMAP */ -#define ok_address(M, a) ((char*)(a) >= (M)->least_addr) -/* Check if address of next chunk n is higher than base chunk p */ -#define ok_next(p, n) ((char*)(p) < (char*)(n)) -/* Check if p has inuse status */ -#define ok_inuse(p) is_inuse(p) -/* Check if p has its pinuse bit on */ -#define ok_pinuse(p) pinuse(p) - -#else /* !INSECURE */ -#define ok_address(M, a) (1) -#define ok_next(b, n) (1) -#define ok_inuse(p) (1) -#define ok_pinuse(p) (1) -#endif /* !INSECURE */ - -#if (FOOTERS && !INSECURE) -/* Check if (alleged) mstate m has expected magic field */ -#define ok_magic(M) ((M)->magic == mparams.magic) -#else /* (FOOTERS && !INSECURE) */ -#define ok_magic(M) (1) -#endif /* (FOOTERS && !INSECURE) */ - - -/* In gcc, use __builtin_expect to minimize impact of checks */ -#if !INSECURE -#if defined(__GNUC__) && __GNUC__ >= 3 -#define RTCHECK(e) __builtin_expect(e, 1) -#else /* GNUC */ -#define RTCHECK(e) (e) -#endif /* GNUC */ -#else /* !INSECURE */ -#define RTCHECK(e) (1) -#endif /* !INSECURE */ - -/* macros to set up inuse chunks with or without footers */ - -#if !FOOTERS - -#define mark_inuse_foot(M,p,s) - -/* Macros for setting head/foot of non-mmapped chunks */ - -/* Set cinuse bit and pinuse bit of next chunk */ -#define set_inuse(M,p,s)\ - ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\ - ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT) - -/* Set cinuse and pinuse of this chunk and pinuse of next chunk */ -#define set_inuse_and_pinuse(M,p,s)\ - ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ - ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT) - -/* Set size, cinuse and pinuse bit of this chunk */ -#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\ - ((p)->head = (s|PINUSE_BIT|CINUSE_BIT)) - -#else /* FOOTERS */ - -/* Set foot of inuse chunk to be xor of mstate and seed */ -#define mark_inuse_foot(M,p,s)\ - (((mchunkptr)((char*)(p) + (s)))->prev_foot = ((size_t)(M) ^ mparams.magic)) - -#define get_mstate_for(p)\ - ((mstate)(((mchunkptr)((char*)(p) +\ - (chunksize(p))))->prev_foot ^ mparams.magic)) - -#define set_inuse(M,p,s)\ - ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\ - (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT), \ - mark_inuse_foot(M,p,s)) - -#define set_inuse_and_pinuse(M,p,s)\ - ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ - (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT),\ - mark_inuse_foot(M,p,s)) - -#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\ - ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ - mark_inuse_foot(M, p, s)) - -#endif /* !FOOTERS */ - -/* ---------------------------- setting mparams -------------------------- */ - -#if defined(ENABLE_LARGE_PAGES) && defined(WIN32) -typedef size_t (WINAPI *GetLargePageMinimum_t)(void); -#endif - -/* Initialize mparams */ -static int init_mparams(void) { -#ifdef NEED_GLOBAL_LOCK_INIT - if (malloc_global_mutex_status <= 0) - init_malloc_global_mutex(); -#endif - - ACQUIRE_MALLOC_GLOBAL_LOCK(); - if (mparams.magic == 0) { - size_t magic; - size_t psize; - size_t gsize; - -#ifndef WIN32 - psize = malloc_getpagesize; - gsize = ((DEFAULT_GRANULARITY != 0)? DEFAULT_GRANULARITY : psize); -#else /* WIN32 */ - { - SYSTEM_INFO system_info; - GetSystemInfo(&system_info); - psize = system_info.dwPageSize; - gsize = ((DEFAULT_GRANULARITY != 0)? - DEFAULT_GRANULARITY : system_info.dwAllocationGranularity); -#ifdef ENABLE_LARGE_PAGES - { - GetLargePageMinimum_t GetLargePageMinimum_ = (GetLargePageMinimum_t) GetProcAddress(GetModuleHandle("kernel32.dll"), "GetLargePageMinimum"); - if(GetLargePageMinimum_) { - size_t largepagesize = GetLargePageMinimum_(); - if(largepagesize) { - psize = largepagesize; - gsize = ((DEFAULT_GRANULARITY != 0)? - DEFAULT_GRANULARITY : largepagesize); - if(gsize < largepagesize) gsize = largepagesize; - } - } - } -#endif - } -#endif /* WIN32 */ - - /* Sanity-check configuration: - size_t must be unsigned and as wide as pointer type. - ints must be at least 4 bytes. - alignment must be at least 8. - Alignment, min chunk size, and page size must all be powers of 2. - */ - if ((sizeof(size_t) != sizeof(char*)) || - (MAX_SIZE_T < MIN_CHUNK_SIZE) || - (sizeof(int) < 4) || - (MALLOC_ALIGNMENT < (size_t)8U) || - ((MALLOC_ALIGNMENT & (MALLOC_ALIGNMENT-SIZE_T_ONE)) != 0) || - ((MCHUNK_SIZE & (MCHUNK_SIZE-SIZE_T_ONE)) != 0) || - ((gsize & (gsize-SIZE_T_ONE)) != 0) || - ((psize & (psize-SIZE_T_ONE)) != 0)) - ABORT; - - mparams.granularity = gsize; - mparams.page_size = psize; - mparams.mmap_threshold = DEFAULT_MMAP_THRESHOLD; - mparams.trim_threshold = DEFAULT_TRIM_THRESHOLD; -#if MORECORE_CONTIGUOUS - mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT; -#else /* MORECORE_CONTIGUOUS */ - mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT|USE_NONCONTIGUOUS_BIT; -#endif /* MORECORE_CONTIGUOUS */ - -#if !ONLY_MSPACES - /* Set up lock for main malloc area */ - gm->mflags = mparams.default_mflags; - INITIAL_LOCK(&gm->mutex); -#endif - - { -#if USE_DEV_RANDOM - int fd; - unsigned char buf[sizeof(size_t)]; - /* Try to use /dev/urandom, else fall back on using time */ - if ((fd = open("/dev/urandom", O_RDONLY)) >= 0 && - read(fd, buf, sizeof(buf)) == sizeof(buf)) { - magic = *((size_t *) buf); - close(fd); - } - else -#endif /* USE_DEV_RANDOM */ -#ifdef WIN32 - magic = (size_t)(GetTickCount() ^ (size_t)0x55555555U); -#else - magic = (size_t)(time(0) ^ (size_t)0x55555555U); -#endif - magic |= (size_t)8U; /* ensure nonzero */ - magic &= ~(size_t)7U; /* improve chances of fault for bad values */ - mparams.magic = magic; - } - } - - RELEASE_MALLOC_GLOBAL_LOCK(); - return 1; -} - -/* support for mallopt */ -static int change_mparam(int param_number, int value) { - size_t val; - ensure_initialization(); - val = (value == -1)? MAX_SIZE_T : (size_t)value; - switch(param_number) { - case M_TRIM_THRESHOLD: - mparams.trim_threshold = val; - return 1; - case M_GRANULARITY: - if (val >= mparams.page_size && ((val & (val-1)) == 0)) { - mparams.granularity = val; - return 1; - } - else - return 0; - case M_MMAP_THRESHOLD: - mparams.mmap_threshold = val; - return 1; - default: - return 0; - } -} - -#if DEBUG -/* ------------------------- Debugging Support --------------------------- */ - -/* Check properties of any chunk, whether free, inuse, mmapped etc */ -static void do_check_any_chunk(mstate m, mchunkptr p) { - assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); - assert(ok_address(m, p)); -} - -/* Check properties of top chunk */ -static void do_check_top_chunk(mstate m, mchunkptr p) { - msegmentptr sp = segment_holding(m, (char*)p); - size_t sz = p->head & ~INUSE_BITS; /* third-lowest bit can be set! */ - assert(sp != 0); - assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); - assert(ok_address(m, p)); - assert(sz == m->topsize); - assert(sz > 0); - assert(sz == ((sp->base + sp->size) - (char*)p) - TOP_FOOT_SIZE); - assert(pinuse(p)); - assert(!pinuse(chunk_plus_offset(p, sz))); -} - -/* Check properties of (inuse) mmapped chunks */ -static void do_check_mmapped_chunk(mstate m, mchunkptr p) { - size_t sz = chunksize(p); - size_t len = (sz + (p->prev_foot) + MMAP_FOOT_PAD); - assert(is_mmapped(p)); - assert(use_mmap(m)); - assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); - assert(ok_address(m, p)); - assert(!is_small(sz)); - assert((len & (mparams.page_size-SIZE_T_ONE)) == 0); - assert(chunk_plus_offset(p, sz)->head == FENCEPOST_HEAD); - assert(chunk_plus_offset(p, sz+SIZE_T_SIZE)->head == 0); -} - -/* Check properties of inuse chunks */ -static void do_check_inuse_chunk(mstate m, mchunkptr p) { - do_check_any_chunk(m, p); - assert(is_inuse(p)); - assert(next_pinuse(p)); - /* If not pinuse and not mmapped, previous chunk has OK offset */ - assert(is_mmapped(p) || pinuse(p) || next_chunk(prev_chunk(p)) == p); - if (is_mmapped(p)) - do_check_mmapped_chunk(m, p); -} - -/* Check properties of free chunks */ -static void do_check_free_chunk(mstate m, mchunkptr p) { - size_t sz = chunksize(p); - mchunkptr next = chunk_plus_offset(p, sz); - do_check_any_chunk(m, p); - assert(!is_inuse(p)); - assert(!next_pinuse(p)); - assert (!is_mmapped(p)); - if (p != m->dv && p != m->top) { - if (sz >= MIN_CHUNK_SIZE) { - assert((sz & CHUNK_ALIGN_MASK) == 0); - assert(is_aligned(chunk2mem(p))); - assert(next->prev_foot == sz); - assert(pinuse(p)); - assert (next == m->top || is_inuse(next)); - assert(p->fd->bk == p); - assert(p->bk->fd == p); - } - else /* markers are always of size SIZE_T_SIZE */ - assert(sz == SIZE_T_SIZE); - } -} - -/* Check properties of malloced chunks at the point they are malloced */ -static void do_check_malloced_chunk(mstate m, void* mem, size_t s) { - if (mem != 0) { - mchunkptr p = mem2chunk(mem); - size_t sz = p->head & ~INUSE_BITS; - do_check_inuse_chunk(m, p); - assert((sz & CHUNK_ALIGN_MASK) == 0); - assert(sz >= MIN_CHUNK_SIZE); - assert(sz >= s); - /* unless mmapped, size is less than MIN_CHUNK_SIZE more than request */ - assert(is_mmapped(p) || sz < (s + MIN_CHUNK_SIZE)); - } -} - -/* Check a tree and its subtrees. */ -static void do_check_tree(mstate m, tchunkptr t) { - tchunkptr head = 0; - tchunkptr u = t; - bindex_t tindex = t->index; - size_t tsize = chunksize(t); - bindex_t idx; - compute_tree_index(tsize, idx); - assert(tindex == idx); - assert(tsize >= MIN_LARGE_SIZE); - assert(tsize >= minsize_for_tree_index(idx)); - assert((idx == NTREEBINS-1) || (tsize < minsize_for_tree_index((idx+1)))); - - do { /* traverse through chain of same-sized nodes */ - do_check_any_chunk(m, ((mchunkptr)u)); - assert(u->index == tindex); - assert(chunksize(u) == tsize); - assert(!is_inuse(u)); - assert(!next_pinuse(u)); - assert(u->fd->bk == u); - assert(u->bk->fd == u); - if (u->parent == 0) { - assert(u->child[0] == 0); - assert(u->child[1] == 0); - } - else { - assert(head == 0); /* only one node on chain has parent */ - head = u; - assert(u->parent != u); - assert (u->parent->child[0] == u || - u->parent->child[1] == u || - *((tbinptr*)(u->parent)) == u); - if (u->child[0] != 0) { - assert(u->child[0]->parent == u); - assert(u->child[0] != u); - do_check_tree(m, u->child[0]); - } - if (u->child[1] != 0) { - assert(u->child[1]->parent == u); - assert(u->child[1] != u); - do_check_tree(m, u->child[1]); - } - if (u->child[0] != 0 && u->child[1] != 0) { - assert(chunksize(u->child[0]) < chunksize(u->child[1])); - } - } - u = u->fd; - } while (u != t); - assert(head != 0); -} - -/* Check all the chunks in a treebin. */ -static void do_check_treebin(mstate m, bindex_t i) { - tbinptr* tb = treebin_at(m, i); - tchunkptr t = *tb; - int empty = (m->treemap & (1U << i)) == 0; - if (t == 0) - assert(empty); - if (!empty) - do_check_tree(m, t); -} - -/* Check all the chunks in a smallbin. */ -static void do_check_smallbin(mstate m, bindex_t i) { - sbinptr b = smallbin_at(m, i); - mchunkptr p = b->bk; - unsigned int empty = (m->smallmap & (1U << i)) == 0; - if (p == b) - assert(empty); - if (!empty) { - for (; p != b; p = p->bk) { - size_t size = chunksize(p); - mchunkptr q; - /* each chunk claims to be free */ - do_check_free_chunk(m, p); - /* chunk belongs in bin */ - assert(small_index(size) == i); - assert(p->bk == b || chunksize(p->bk) == chunksize(p)); - /* chunk is followed by an inuse chunk */ - q = next_chunk(p); - if (q->head != FENCEPOST_HEAD) - do_check_inuse_chunk(m, q); - } - } -} - -/* Find x in a bin. Used in other check functions. */ -static int bin_find(mstate m, mchunkptr x) { - size_t size = chunksize(x); - if (is_small(size)) { - bindex_t sidx = small_index(size); - sbinptr b = smallbin_at(m, sidx); - if (smallmap_is_marked(m, sidx)) { - mchunkptr p = b; - do { - if (p == x) - return 1; - } while ((p = p->fd) != b); - } - } - else { - bindex_t tidx; - compute_tree_index(size, tidx); - if (treemap_is_marked(m, tidx)) { - tchunkptr t = *treebin_at(m, tidx); - size_t sizebits = size << leftshift_for_tree_index(tidx); - while (t != 0 && chunksize(t) != size) { - t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]; - sizebits <<= 1; - } - if (t != 0) { - tchunkptr u = t; - do { - if (u == (tchunkptr)x) - return 1; - } while ((u = u->fd) != t); - } - } - } - return 0; -} - -/* Traverse each chunk and check it; return total */ -static size_t traverse_and_check(mstate m) { - size_t sum = 0; - if (is_initialized(m)) { - msegmentptr s = &m->seg; - sum += m->topsize + TOP_FOOT_SIZE; - while (s != 0) { - mchunkptr q = align_as_chunk(s->base); - mchunkptr lastq = 0; - assert(pinuse(q)); - while (segment_holds(s, q) && - q != m->top && q->head != FENCEPOST_HEAD) { - sum += chunksize(q); - if (is_inuse(q)) { - assert(!bin_find(m, q)); - do_check_inuse_chunk(m, q); - } - else { - assert(q == m->dv || bin_find(m, q)); - assert(lastq == 0 || is_inuse(lastq)); /* Not 2 consecutive free */ - do_check_free_chunk(m, q); - } - lastq = q; - q = next_chunk(q); - } - s = s->next; - } - } - return sum; -} - -/* Check all properties of malloc_state. */ -static void do_check_malloc_state(mstate m) { - bindex_t i; - size_t total; - /* check bins */ - for (i = 0; i < NSMALLBINS; ++i) - do_check_smallbin(m, i); - for (i = 0; i < NTREEBINS; ++i) - do_check_treebin(m, i); - - if (m->dvsize != 0) { /* check dv chunk */ - do_check_any_chunk(m, m->dv); - assert(m->dvsize == chunksize(m->dv)); - assert(m->dvsize >= MIN_CHUNK_SIZE); - assert(bin_find(m, m->dv) == 0); - } - - if (m->top != 0) { /* check top chunk */ - do_check_top_chunk(m, m->top); - /*assert(m->topsize == chunksize(m->top)); redundant */ - assert(m->topsize > 0); - assert(bin_find(m, m->top) == 0); - } - - total = traverse_and_check(m); - assert(total <= m->footprint); - assert(m->footprint <= m->max_footprint); -} -#endif /* DEBUG */ - -/* ----------------------------- statistics ------------------------------ */ - -#if !NO_MALLINFO -static struct mallinfo internal_mallinfo(mstate m) { - struct mallinfo nm = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }; - ensure_initialization(); - if (!PREACTION(m)) { - check_malloc_state(m); - if (is_initialized(m)) { - size_t nfree = SIZE_T_ONE; /* top always free */ - size_t mfree = m->topsize + TOP_FOOT_SIZE; - size_t sum = mfree; - msegmentptr s = &m->seg; - while (s != 0) { - mchunkptr q = align_as_chunk(s->base); - while (segment_holds(s, q) && - q != m->top && q->head != FENCEPOST_HEAD) { - size_t sz = chunksize(q); - sum += sz; - if (!is_inuse(q)) { - mfree += sz; - ++nfree; - } - q = next_chunk(q); - } - s = s->next; - } - - nm.arena = sum; - nm.ordblks = nfree; - nm.hblkhd = m->footprint - sum; - nm.usmblks = m->max_footprint; - nm.uordblks = m->footprint - mfree; - nm.fordblks = mfree; - nm.keepcost = m->topsize; - } - - POSTACTION(m); - } - return nm; -} -#endif /* !NO_MALLINFO */ - -static void internal_malloc_stats(mstate m) { - ensure_initialization(); - if (!PREACTION(m)) { - size_t maxfp = 0; - size_t fp = 0; - size_t used = 0; - check_malloc_state(m); - if (is_initialized(m)) { - msegmentptr s = &m->seg; - maxfp = m->max_footprint; - fp = m->footprint; - used = fp - (m->topsize + TOP_FOOT_SIZE); - - while (s != 0) { - mchunkptr q = align_as_chunk(s->base); - while (segment_holds(s, q) && - q != m->top && q->head != FENCEPOST_HEAD) { - if (!is_inuse(q)) - used -= chunksize(q); - q = next_chunk(q); - } - s = s->next; - } - } - - fprintf(stderr, "max system bytes = %10lu\n", (unsigned long)(maxfp)); - fprintf(stderr, "system bytes = %10lu\n", (unsigned long)(fp)); - fprintf(stderr, "in use bytes = %10lu\n", (unsigned long)(used)); - - POSTACTION(m); - } -} - -/* ----------------------- Operations on smallbins ----------------------- */ - -/* - Various forms of linking and unlinking are defined as macros. Even - the ones for trees, which are very long but have very short typical - paths. This is ugly but reduces reliance on inlining support of - compilers. -*/ - -/* Link a free chunk into a smallbin */ -#define insert_small_chunk(M, P, S) {\ - bindex_t I = small_index(S);\ - mchunkptr B = smallbin_at(M, I);\ - mchunkptr F = B;\ - assert(S >= MIN_CHUNK_SIZE);\ - if (!smallmap_is_marked(M, I))\ - mark_smallmap(M, I);\ - else if (RTCHECK(ok_address(M, B->fd)))\ - F = B->fd;\ - else {\ - CORRUPTION_ERROR_ACTION(M);\ - }\ - B->fd = P;\ - F->bk = P;\ - P->fd = F;\ - P->bk = B;\ -} - -/* Unlink a chunk from a smallbin */ -#define unlink_small_chunk(M, P, S) {\ - mchunkptr F = P->fd;\ - mchunkptr B = P->bk;\ - bindex_t I = small_index(S);\ - assert(P != B);\ - assert(P != F);\ - assert(chunksize(P) == small_index2size(I));\ - if (F == B)\ - clear_smallmap(M, I);\ - else if (RTCHECK((F == smallbin_at(M,I) || ok_address(M, F)) &&\ - (B == smallbin_at(M,I) || ok_address(M, B)))) {\ - F->bk = B;\ - B->fd = F;\ - }\ - else {\ - CORRUPTION_ERROR_ACTION(M);\ - }\ -} - -/* Unlink the first chunk from a smallbin */ -#define unlink_first_small_chunk(M, B, P, I) {\ - mchunkptr F = P->fd;\ - assert(P != B);\ - assert(P != F);\ - assert(chunksize(P) == small_index2size(I));\ - if (B == F)\ - clear_smallmap(M, I);\ - else if (RTCHECK(ok_address(M, F))) {\ - B->fd = F;\ - F->bk = B;\ - }\ - else {\ - CORRUPTION_ERROR_ACTION(M);\ - }\ -} - - - -/* Replace dv node, binning the old one */ -/* Used only when dvsize known to be small */ -#define replace_dv(M, P, S) {\ - size_t DVS = M->dvsize;\ - if (DVS != 0) {\ - mchunkptr DV = M->dv;\ - assert(is_small(DVS));\ - insert_small_chunk(M, DV, DVS);\ - }\ - M->dvsize = S;\ - M->dv = P;\ -} - -/* ------------------------- Operations on trees ------------------------- */ - -/* Insert chunk into tree */ -#define insert_large_chunk(M, X, S) {\ - tbinptr* H;\ - bindex_t I;\ - compute_tree_index(S, I);\ - H = treebin_at(M, I);\ - X->index = I;\ - X->child[0] = X->child[1] = 0;\ - if (!treemap_is_marked(M, I)) {\ - mark_treemap(M, I);\ - *H = X;\ - X->parent = (tchunkptr)H;\ - X->fd = X->bk = X;\ - }\ - else {\ - tchunkptr T = *H;\ - size_t K = S << leftshift_for_tree_index(I);\ - for (;;) {\ - if (chunksize(T) != S) {\ - tchunkptr* C = &(T->child[(K >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]);\ - K <<= 1;\ - if (*C != 0)\ - T = *C;\ - else if (RTCHECK(ok_address(M, C))) {\ - *C = X;\ - X->parent = T;\ - X->fd = X->bk = X;\ - break;\ - }\ - else {\ - CORRUPTION_ERROR_ACTION(M);\ - break;\ - }\ - }\ - else {\ - tchunkptr F = T->fd;\ - if (RTCHECK(ok_address(M, T) && ok_address(M, F))) {\ - T->fd = F->bk = X;\ - X->fd = F;\ - X->bk = T;\ - X->parent = 0;\ - break;\ - }\ - else {\ - CORRUPTION_ERROR_ACTION(M);\ - break;\ - }\ - }\ - }\ - }\ -} - -/* - Unlink steps: - - 1. If x is a chained node, unlink it from its same-sized fd/bk links - and choose its bk node as its replacement. - 2. If x was the last node of its size, but not a leaf node, it must - be replaced with a leaf node (not merely one with an open left or - right), to make sure that lefts and rights of descendents - correspond properly to bit masks. We use the rightmost descendent - of x. We could use any other leaf, but this is easy to locate and - tends to counteract removal of leftmosts elsewhere, and so keeps - paths shorter than minimally guaranteed. This doesn't loop much - because on average a node in a tree is near the bottom. - 3. If x is the base of a chain (i.e., has parent links) relink - x's parent and children to x's replacement (or null if none). -*/ - -#define unlink_large_chunk(M, X) {\ - tchunkptr XP = X->parent;\ - tchunkptr R;\ - if (X->bk != X) {\ - tchunkptr F = X->fd;\ - R = X->bk;\ - if (RTCHECK(ok_address(M, F))) {\ - F->bk = R;\ - R->fd = F;\ - }\ - else {\ - CORRUPTION_ERROR_ACTION(M);\ - }\ - }\ - else {\ - tchunkptr* RP;\ - if (((R = *(RP = &(X->child[1]))) != 0) ||\ - ((R = *(RP = &(X->child[0]))) != 0)) {\ - tchunkptr* CP;\ - while ((*(CP = &(R->child[1])) != 0) ||\ - (*(CP = &(R->child[0])) != 0)) {\ - R = *(RP = CP);\ - }\ - if (RTCHECK(ok_address(M, RP)))\ - *RP = 0;\ - else {\ - CORRUPTION_ERROR_ACTION(M);\ - }\ - }\ - }\ - if (XP != 0) {\ - tbinptr* H = treebin_at(M, X->index);\ - if (X == *H) {\ - if ((*H = R) == 0) \ - clear_treemap(M, X->index);\ - }\ - else if (RTCHECK(ok_address(M, XP))) {\ - if (XP->child[0] == X) \ - XP->child[0] = R;\ - else \ - XP->child[1] = R;\ - }\ - else\ - CORRUPTION_ERROR_ACTION(M);\ - if (R != 0) {\ - if (RTCHECK(ok_address(M, R))) {\ - tchunkptr C0, C1;\ - R->parent = XP;\ - if ((C0 = X->child[0]) != 0) {\ - if (RTCHECK(ok_address(M, C0))) {\ - R->child[0] = C0;\ - C0->parent = R;\ - }\ - else\ - CORRUPTION_ERROR_ACTION(M);\ - }\ - if ((C1 = X->child[1]) != 0) {\ - if (RTCHECK(ok_address(M, C1))) {\ - R->child[1] = C1;\ - C1->parent = R;\ - }\ - else\ - CORRUPTION_ERROR_ACTION(M);\ - }\ - }\ - else\ - CORRUPTION_ERROR_ACTION(M);\ - }\ - }\ -} - -/* Relays to large vs small bin operations */ - -#define insert_chunk(M, P, S)\ - if (is_small(S)) insert_small_chunk(M, P, S)\ - else { tchunkptr TP = (tchunkptr)(P); insert_large_chunk(M, TP, S); } - -#define unlink_chunk(M, P, S)\ - if (is_small(S)) unlink_small_chunk(M, P, S)\ - else { tchunkptr TP = (tchunkptr)(P); unlink_large_chunk(M, TP); } - - -/* Relays to internal calls to malloc/free from realloc, memalign etc */ - -#if ONLY_MSPACES -#define internal_malloc(m, b) mspace_malloc(m, b) -#define internal_free(m, mem) mspace_free(m,mem); -#else /* ONLY_MSPACES */ -#if MSPACES -#define internal_malloc(m, b)\ - (m == gm)? dlmalloc(b) : mspace_malloc(m, b) -#define internal_free(m, mem)\ - if (m == gm) dlfree(mem); else mspace_free(m,mem); -#else /* MSPACES */ -#define internal_malloc(m, b) dlmalloc(b) -#define internal_free(m, mem) dlfree(mem) -#endif /* MSPACES */ -#endif /* ONLY_MSPACES */ - -/* ----------------------- Direct-mmapping chunks ----------------------- */ - -/* - Directly mmapped chunks are set up with an offset to the start of - the mmapped region stored in the prev_foot field of the chunk. This - allows reconstruction of the required argument to MUNMAP when freed, - and also allows adjustment of the returned chunk to meet alignment - requirements (especially in memalign). -*/ - -/* Malloc using mmap */ -static void* mmap_alloc(mstate m, size_t nb) { - size_t mmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK); - if (mmsize > nb) { /* Check for wrap around 0 */ - char* mm = (char*)(CALL_DIRECT_MMAP(mmsize)); - if (mm != CMFAIL) { - size_t offset = align_offset(chunk2mem(mm)); - size_t psize = mmsize - offset - MMAP_FOOT_PAD; - mchunkptr p = (mchunkptr)(mm + offset); - p->prev_foot = offset; - p->head = psize; - mark_inuse_foot(m, p, psize); - chunk_plus_offset(p, psize)->head = FENCEPOST_HEAD; - chunk_plus_offset(p, psize+SIZE_T_SIZE)->head = 0; - - if (m->least_addr == 0 || mm < m->least_addr) - m->least_addr = mm; - if ((m->footprint += mmsize) > m->max_footprint) - m->max_footprint = m->footprint; - assert(is_aligned(chunk2mem(p))); - check_mmapped_chunk(m, p); - return chunk2mem(p); - } - } - return 0; -} - -/* Realloc using mmap */ -static mchunkptr mmap_resize(mstate m, mchunkptr oldp, size_t nb) { - size_t oldsize = chunksize(oldp); - if (is_small(nb)) /* Can't shrink mmap regions below small size */ - return 0; - /* Keep old chunk if big enough but not too big */ - if (oldsize >= nb + SIZE_T_SIZE && - (oldsize - nb) <= (mparams.granularity << 1)) - return oldp; - else { - size_t offset = oldp->prev_foot; - size_t oldmmsize = oldsize + offset + MMAP_FOOT_PAD; - size_t newmmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK); - char* cp = (char*)CALL_MREMAP((char*)oldp - offset, - oldmmsize, newmmsize, 1); - if (cp != CMFAIL) { - mchunkptr newp = (mchunkptr)(cp + offset); - size_t psize = newmmsize - offset - MMAP_FOOT_PAD; - newp->head = psize; - mark_inuse_foot(m, newp, psize); - chunk_plus_offset(newp, psize)->head = FENCEPOST_HEAD; - chunk_plus_offset(newp, psize+SIZE_T_SIZE)->head = 0; - - if (cp < m->least_addr) - m->least_addr = cp; - if ((m->footprint += newmmsize - oldmmsize) > m->max_footprint) - m->max_footprint = m->footprint; - check_mmapped_chunk(m, newp); - return newp; - } - } - return 0; -} - -/* -------------------------- mspace management -------------------------- */ - -/* Initialize top chunk and its size */ -static void init_top(mstate m, mchunkptr p, size_t psize) { - /* Ensure alignment */ - size_t offset = align_offset(chunk2mem(p)); - p = (mchunkptr)((char*)p + offset); - psize -= offset; - - m->top = p; - m->topsize = psize; - p->head = psize | PINUSE_BIT; - /* set size of fake trailing chunk holding overhead space only once */ - chunk_plus_offset(p, psize)->head = TOP_FOOT_SIZE; - m->trim_check = mparams.trim_threshold; /* reset on each update */ -} - -/* Initialize bins for a new mstate that is otherwise zeroed out */ -static void init_bins(mstate m) { - /* Establish circular links for smallbins */ - bindex_t i; - for (i = 0; i < NSMALLBINS; ++i) { - sbinptr bin = smallbin_at(m,i); - bin->fd = bin->bk = bin; - } -} - -#if PROCEED_ON_ERROR - -/* default corruption action */ -static void reset_on_error(mstate m) { - int i; - ++malloc_corruption_error_count; - /* Reinitialize fields to forget about all memory */ - m->smallbins = m->treebins = 0; - m->dvsize = m->topsize = 0; - m->seg.base = 0; - m->seg.size = 0; - m->seg.next = 0; - m->top = m->dv = 0; - for (i = 0; i < NTREEBINS; ++i) - *treebin_at(m, i) = 0; - init_bins(m); -} -#endif /* PROCEED_ON_ERROR */ - -/* Allocate chunk and prepend remainder with chunk in successor base. */ -static void* prepend_alloc(mstate m, char* newbase, char* oldbase, - size_t nb) { - mchunkptr p = align_as_chunk(newbase); - mchunkptr oldfirst = align_as_chunk(oldbase); - size_t psize = (char*)oldfirst - (char*)p; - mchunkptr q = chunk_plus_offset(p, nb); - size_t qsize = psize - nb; - set_size_and_pinuse_of_inuse_chunk(m, p, nb); - - assert((char*)oldfirst > (char*)q); - assert(pinuse(oldfirst)); - assert(qsize >= MIN_CHUNK_SIZE); - - /* consolidate remainder with first chunk of old base */ - if (oldfirst == m->top) { - size_t tsize = m->topsize += qsize; - m->top = q; - q->head = tsize | PINUSE_BIT; - check_top_chunk(m, q); - } - else if (oldfirst == m->dv) { - size_t dsize = m->dvsize += qsize; - m->dv = q; - set_size_and_pinuse_of_free_chunk(q, dsize); - } - else { - if (!is_inuse(oldfirst)) { - size_t nsize = chunksize(oldfirst); - unlink_chunk(m, oldfirst, nsize); - oldfirst = chunk_plus_offset(oldfirst, nsize); - qsize += nsize; - } - set_free_with_pinuse(q, qsize, oldfirst); - insert_chunk(m, q, qsize); - check_free_chunk(m, q); - } - - check_malloced_chunk(m, chunk2mem(p), nb); - return chunk2mem(p); -} - -/* Add a segment to hold a new noncontiguous region */ -static void add_segment(mstate m, char* tbase, size_t tsize, flag_t mmapped) { - /* Determine locations and sizes of segment, fenceposts, old top */ - char* old_top = (char*)m->top; - msegmentptr oldsp = segment_holding(m, old_top); - char* old_end = oldsp->base + oldsp->size; - size_t ssize = pad_request(sizeof(struct malloc_segment)); - char* rawsp = old_end - (ssize + FOUR_SIZE_T_SIZES + CHUNK_ALIGN_MASK); - size_t offset = align_offset(chunk2mem(rawsp)); - char* asp = rawsp + offset; - char* csp = (asp < (old_top + MIN_CHUNK_SIZE))? old_top : asp; - mchunkptr sp = (mchunkptr)csp; - msegmentptr ss = (msegmentptr)(chunk2mem(sp)); - mchunkptr tnext = chunk_plus_offset(sp, ssize); - mchunkptr p = tnext; - int nfences = 0; - - /* reset top to new space */ - init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE); - - /* Set up segment record */ - assert(is_aligned(ss)); - set_size_and_pinuse_of_inuse_chunk(m, sp, ssize); - *ss = m->seg; /* Push current record */ - m->seg.base = tbase; - m->seg.size = tsize; - m->seg.sflags = mmapped; - m->seg.next = ss; - - /* Insert trailing fenceposts */ - for (;;) { - mchunkptr nextp = chunk_plus_offset(p, SIZE_T_SIZE); - p->head = FENCEPOST_HEAD; - ++nfences; - if ((char*)(&(nextp->head)) < old_end) - p = nextp; - else - break; - } - assert(nfences >= 2); - - /* Insert the rest of old top into a bin as an ordinary free chunk */ - if (csp != old_top) { - mchunkptr q = (mchunkptr)old_top; - size_t psize = csp - old_top; - mchunkptr tn = chunk_plus_offset(q, psize); - set_free_with_pinuse(q, psize, tn); - insert_chunk(m, q, psize); - } - - check_top_chunk(m, m->top); -} - -/* -------------------------- System allocation -------------------------- */ - -/* Get memory from system using MORECORE or MMAP */ -static void* sys_alloc(mstate m, size_t nb) { - char* tbase = CMFAIL; - size_t tsize = 0; - flag_t mmap_flag = 0; - - ensure_initialization(); - - /* Directly map large chunks, but only if already initialized */ - if (use_mmap(m) && nb >= mparams.mmap_threshold && m->topsize != 0) { - void* mem = mmap_alloc(m, nb); - if (mem != 0) - return mem; - } - - /* - Try getting memory in any of three ways (in most-preferred to - least-preferred order): - 1. A call to MORECORE that can normally contiguously extend memory. - (disabled if not MORECORE_CONTIGUOUS or not HAVE_MORECORE or - or main space is mmapped or a previous contiguous call failed) - 2. A call to MMAP new space (disabled if not HAVE_MMAP). - Note that under the default settings, if MORECORE is unable to - fulfill a request, and HAVE_MMAP is true, then mmap is - used as a noncontiguous system allocator. This is a useful backup - strategy for systems with holes in address spaces -- in this case - sbrk cannot contiguously expand the heap, but mmap may be able to - find space. - 3. A call to MORECORE that cannot usually contiguously extend memory. - (disabled if not HAVE_MORECORE) - - In all cases, we need to request enough bytes from system to ensure - we can malloc nb bytes upon success, so pad with enough space for - top_foot, plus alignment-pad to make sure we don't lose bytes if - not on boundary, and round this up to a granularity unit. - */ - - if (MORECORE_CONTIGUOUS && !use_noncontiguous(m)) { - char* br = CMFAIL; - msegmentptr ss = (m->top == 0)? 0 : segment_holding(m, (char*)m->top); - size_t asize = 0; - ACQUIRE_MALLOC_GLOBAL_LOCK(); - - if (ss == 0) { /* First time through or recovery */ - char* base = (char*)CALL_MORECORE(0); - if (base != CMFAIL) { - asize = granularity_align(nb + SYS_ALLOC_PADDING); - /* Adjust to end on a page boundary */ - if (!is_page_aligned(base)) - asize += (page_align((size_t)base) - (size_t)base); - /* Can't call MORECORE if size is negative when treated as signed */ - if (asize < HALF_MAX_SIZE_T && - (br = (char*)(CALL_MORECORE(asize))) == base) { - tbase = base; - tsize = asize; - } - } - } - else { - /* Subtract out existing available top space from MORECORE request. */ - asize = granularity_align(nb - m->topsize + SYS_ALLOC_PADDING); - /* Use mem here only if it did continuously extend old space */ - if (asize < HALF_MAX_SIZE_T && - (br = (char*)(CALL_MORECORE(asize))) == ss->base+ss->size) { - tbase = br; - tsize = asize; - } - } - - if (tbase == CMFAIL) { /* Cope with partial failure */ - if (br != CMFAIL) { /* Try to use/extend the space we did get */ - if (asize < HALF_MAX_SIZE_T && - asize < nb + SYS_ALLOC_PADDING) { - size_t esize = granularity_align(nb + SYS_ALLOC_PADDING - asize); - if (esize < HALF_MAX_SIZE_T) { - char* end = (char*)CALL_MORECORE(esize); - if (end != CMFAIL) - asize += esize; - else { /* Can't use; try to release */ - (void) CALL_MORECORE(-asize); - br = CMFAIL; - } - } - } - } - if (br != CMFAIL) { /* Use the space we did get */ - tbase = br; - tsize = asize; - } - else - disable_contiguous(m); /* Don't try contiguous path in the future */ - } - - RELEASE_MALLOC_GLOBAL_LOCK(); - } - - if (HAVE_MMAP && tbase == CMFAIL) { /* Try MMAP */ - size_t rsize = granularity_align(nb + SYS_ALLOC_PADDING); - if (rsize > nb) { /* Fail if wraps around zero */ - char* mp = (char*)(CALL_MMAP(rsize)); - if (mp != CMFAIL) { - tbase = mp; - tsize = rsize; - mmap_flag = USE_MMAP_BIT; - } - } - } - - if (HAVE_MORECORE && tbase == CMFAIL) { /* Try noncontiguous MORECORE */ - size_t asize = granularity_align(nb + SYS_ALLOC_PADDING); - if (asize < HALF_MAX_SIZE_T) { - char* br = CMFAIL; - char* end = CMFAIL; - ACQUIRE_MALLOC_GLOBAL_LOCK(); - br = (char*)(CALL_MORECORE(asize)); - end = (char*)(CALL_MORECORE(0)); - RELEASE_MALLOC_GLOBAL_LOCK(); - if (br != CMFAIL && end != CMFAIL && br < end) { - size_t ssize = end - br; - if (ssize > nb + TOP_FOOT_SIZE) { - tbase = br; - tsize = ssize; - } - } - } - } - - if (tbase != CMFAIL) { - - if ((m->footprint += tsize) > m->max_footprint) - m->max_footprint = m->footprint; - - if (!is_initialized(m)) { /* first-time initialization */ - if (m->least_addr == 0 || tbase < m->least_addr) - m->least_addr = tbase; - m->seg.base = tbase; - m->seg.size = tsize; - m->seg.sflags = mmap_flag; - m->magic = mparams.magic; - m->release_checks = MAX_RELEASE_CHECK_RATE; - init_bins(m); -#if !ONLY_MSPACES - if (is_global(m)) - init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE); - else -#endif - { - /* Offset top by embedded malloc_state */ - mchunkptr mn = next_chunk(mem2chunk(m)); - init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) -TOP_FOOT_SIZE); - } - } - - else { - /* Try to merge with an existing segment */ - msegmentptr sp = &m->seg; - /* Only consider most recent segment if traversal suppressed */ - while (sp != 0 && tbase != sp->base + sp->size) - sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next; - if (sp != 0 && - !is_extern_segment(sp) && - (sp->sflags & USE_MMAP_BIT) == mmap_flag && - segment_holds(sp, m->top)) { /* append */ - sp->size += tsize; - init_top(m, m->top, m->topsize + tsize); - } - else { - if (tbase < m->least_addr) - m->least_addr = tbase; - sp = &m->seg; - while (sp != 0 && sp->base != tbase + tsize) - sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next; - if (sp != 0 && - !is_extern_segment(sp) && - (sp->sflags & USE_MMAP_BIT) == mmap_flag) { - char* oldbase = sp->base; - sp->base = tbase; - sp->size += tsize; - return prepend_alloc(m, tbase, oldbase, nb); - } - else - add_segment(m, tbase, tsize, mmap_flag); - } - } - - if (nb < m->topsize) { /* Allocate from new or extended top space */ - size_t rsize = m->topsize -= nb; - mchunkptr p = m->top; - mchunkptr r = m->top = chunk_plus_offset(p, nb); - r->head = rsize | PINUSE_BIT; - set_size_and_pinuse_of_inuse_chunk(m, p, nb); - check_top_chunk(m, m->top); - check_malloced_chunk(m, chunk2mem(p), nb); - return chunk2mem(p); - } - } - - MALLOC_FAILURE_ACTION; - return 0; -} - -/* ----------------------- system deallocation -------------------------- */ - -/* Unmap and unlink any mmapped segments that don't contain used chunks */ -static size_t release_unused_segments(mstate m) { - size_t released = 0; - int nsegs = 0; - msegmentptr pred = &m->seg; - msegmentptr sp = pred->next; - while (sp != 0) { - char* base = sp->base; - size_t size = sp->size; - msegmentptr next = sp->next; - ++nsegs; - if (is_mmapped_segment(sp) && !is_extern_segment(sp)) { - mchunkptr p = align_as_chunk(base); - size_t psize = chunksize(p); - /* Can unmap if first chunk holds entire segment and not pinned */ - if (!is_inuse(p) && (char*)p + psize >= base + size - TOP_FOOT_SIZE) { - tchunkptr tp = (tchunkptr)p; - assert(segment_holds(sp, (char*)sp)); - if (p == m->dv) { - m->dv = 0; - m->dvsize = 0; - } - else { - unlink_large_chunk(m, tp); - } - if (CALL_MUNMAP(base, size) == 0) { - released += size; - m->footprint -= size; - /* unlink obsoleted record */ - sp = pred; - sp->next = next; - } - else { /* back out if cannot unmap */ - insert_large_chunk(m, tp, psize); - } - } - } - if (NO_SEGMENT_TRAVERSAL) /* scan only first segment */ - break; - pred = sp; - sp = next; - } - /* Reset check counter */ - m->release_checks = ((nsegs > MAX_RELEASE_CHECK_RATE)? - nsegs : MAX_RELEASE_CHECK_RATE); - return released; -} - -static int sys_trim(mstate m, size_t pad) { - size_t released = 0; - ensure_initialization(); - if (pad < MAX_REQUEST && is_initialized(m)) { - pad += TOP_FOOT_SIZE; /* ensure enough room for segment overhead */ - - if (m->topsize > pad) { - /* Shrink top space in granularity-size units, keeping at least one */ - size_t unit = mparams.granularity; - size_t extra = ((m->topsize - pad + (unit - SIZE_T_ONE)) / unit - - SIZE_T_ONE) * unit; - msegmentptr sp = segment_holding(m, (char*)m->top); - - if (!is_extern_segment(sp)) { - if (is_mmapped_segment(sp)) { - if (HAVE_MMAP && - sp->size >= extra && - !has_segment_link(m, sp)) { /* can't shrink if pinned */ - size_t newsize = sp->size - extra; - /* Prefer mremap, fall back to munmap */ - if ((CALL_MREMAP(sp->base, sp->size, newsize, 0) != MFAIL) || - (CALL_MUNMAP(sp->base + newsize, extra) == 0)) { - released = extra; - } - } - } - else if (HAVE_MORECORE) { - if (extra >= HALF_MAX_SIZE_T) /* Avoid wrapping negative */ - extra = (HALF_MAX_SIZE_T) + SIZE_T_ONE - unit; - ACQUIRE_MALLOC_GLOBAL_LOCK(); - { - /* Make sure end of memory is where we last set it. */ - char* old_br = (char*)(CALL_MORECORE(0)); - if (old_br == sp->base + sp->size) { - char* rel_br = (char*)(CALL_MORECORE(-extra)); - char* new_br = (char*)(CALL_MORECORE(0)); - if (rel_br != CMFAIL && new_br < old_br) - released = old_br - new_br; - } - } - RELEASE_MALLOC_GLOBAL_LOCK(); - } - } - - if (released != 0) { - sp->size -= released; - m->footprint -= released; - init_top(m, m->top, m->topsize - released); - check_top_chunk(m, m->top); - } - } - - /* Unmap any unused mmapped segments */ - if (HAVE_MMAP) - released += release_unused_segments(m); - - /* On failure, disable autotrim to avoid repeated failed future calls */ - if (released == 0 && m->topsize > m->trim_check) - m->trim_check = MAX_SIZE_T; - } - - return (released != 0)? 1 : 0; -} - - -/* ---------------------------- malloc support --------------------------- */ - -/* allocate a large request from the best fitting chunk in a treebin */ -static void* tmalloc_large(mstate m, size_t nb) { - tchunkptr v = 0; - size_t rsize = -nb; /* Unsigned negation */ - tchunkptr t; - bindex_t idx; - compute_tree_index(nb, idx); - if ((t = *treebin_at(m, idx)) != 0) { - /* Traverse tree for this bin looking for node with size == nb */ - size_t sizebits = nb << leftshift_for_tree_index(idx); - tchunkptr rst = 0; /* The deepest untaken right subtree */ - for (;;) { - tchunkptr rt; - size_t trem = chunksize(t) - nb; - if (trem < rsize) { - v = t; - if ((rsize = trem) == 0) - break; - } - rt = t->child[1]; - t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]; - if (rt != 0 && rt != t) - rst = rt; - if (t == 0) { - t = rst; /* set t to least subtree holding sizes > nb */ - break; - } - sizebits <<= 1; - } - } - if (t == 0 && v == 0) { /* set t to root of next non-empty treebin */ - binmap_t leftbits = left_bits(idx2bit(idx)) & m->treemap; - if (leftbits != 0) { - bindex_t i; - binmap_t leastbit = least_bit(leftbits); - compute_bit2idx(leastbit, i); - t = *treebin_at(m, i); - } - } - - while (t != 0) { /* find smallest of tree or subtree */ - size_t trem = chunksize(t) - nb; - if (trem < rsize) { - rsize = trem; - v = t; - } - t = leftmost_child(t); - } - - /* If dv is a better fit, return 0 so malloc will use it */ - if (v != 0 && rsize < (size_t)(m->dvsize - nb)) { - if (RTCHECK(ok_address(m, v))) { /* split */ - mchunkptr r = chunk_plus_offset(v, nb); - assert(chunksize(v) == rsize + nb); - if (RTCHECK(ok_next(v, r))) { - unlink_large_chunk(m, v); - if (rsize < MIN_CHUNK_SIZE) - set_inuse_and_pinuse(m, v, (rsize + nb)); - else { - set_size_and_pinuse_of_inuse_chunk(m, v, nb); - set_size_and_pinuse_of_free_chunk(r, rsize); - insert_chunk(m, r, rsize); - } - return chunk2mem(v); - } - } - CORRUPTION_ERROR_ACTION(m); - } - return 0; -} - -/* allocate a small request from the best fitting chunk in a treebin */ -static void* tmalloc_small(mstate m, size_t nb) { - tchunkptr t, v; - size_t rsize; - bindex_t i; - binmap_t leastbit = least_bit(m->treemap); - compute_bit2idx(leastbit, i); - v = t = *treebin_at(m, i); - rsize = chunksize(t) - nb; - - while ((t = leftmost_child(t)) != 0) { - size_t trem = chunksize(t) - nb; - if (trem < rsize) { - rsize = trem; - v = t; - } - } - - if (RTCHECK(ok_address(m, v))) { - mchunkptr r = chunk_plus_offset(v, nb); - assert(chunksize(v) == rsize + nb); - if (RTCHECK(ok_next(v, r))) { - unlink_large_chunk(m, v); - if (rsize < MIN_CHUNK_SIZE) - set_inuse_and_pinuse(m, v, (rsize + nb)); - else { - set_size_and_pinuse_of_inuse_chunk(m, v, nb); - set_size_and_pinuse_of_free_chunk(r, rsize); - replace_dv(m, r, rsize); - } - return chunk2mem(v); - } - } - - CORRUPTION_ERROR_ACTION(m); - return 0; -} - -/* --------------------------- realloc support --------------------------- */ - -static void* internal_realloc(mstate m, void* oldmem, size_t bytes) { - if (bytes >= MAX_REQUEST) { - MALLOC_FAILURE_ACTION; - return 0; - } - if (!PREACTION(m)) { - mchunkptr oldp = mem2chunk(oldmem); - size_t oldsize = chunksize(oldp); - mchunkptr next = chunk_plus_offset(oldp, oldsize); - mchunkptr newp = 0; - void* extra = 0; - - /* Try to either shrink or extend into top. Else malloc-copy-free */ - - if (RTCHECK(ok_address(m, oldp) && ok_inuse(oldp) && - ok_next(oldp, next) && ok_pinuse(next))) { - size_t nb = request2size(bytes); - if (is_mmapped(oldp)) - newp = mmap_resize(m, oldp, nb); - else if (oldsize >= nb) { /* already big enough */ - size_t rsize = oldsize - nb; - newp = oldp; - if (rsize >= MIN_CHUNK_SIZE) { - mchunkptr remainder = chunk_plus_offset(newp, nb); - set_inuse(m, newp, nb); - set_inuse_and_pinuse(m, remainder, rsize); - extra = chunk2mem(remainder); - } - } - else if (next == m->top && oldsize + m->topsize > nb) { - /* Expand into top */ - size_t newsize = oldsize + m->topsize; - size_t newtopsize = newsize - nb; - mchunkptr newtop = chunk_plus_offset(oldp, nb); - set_inuse(m, oldp, nb); - newtop->head = newtopsize |PINUSE_BIT; - m->top = newtop; - m->topsize = newtopsize; - newp = oldp; - } - } - else { - USAGE_ERROR_ACTION(m, oldmem); - POSTACTION(m); - return 0; - } -#if DEBUG - if (newp != 0) { - check_inuse_chunk(m, newp); /* Check requires lock */ - } -#endif - - POSTACTION(m); - - if (newp != 0) { - if (extra != 0) { - internal_free(m, extra); - } - return chunk2mem(newp); - } - else { - void* newmem = internal_malloc(m, bytes); - if (newmem != 0) { - size_t oc = oldsize - overhead_for(oldp); - memcpy(newmem, oldmem, (oc < bytes)? oc : bytes); - internal_free(m, oldmem); - } - return newmem; - } - } - return 0; -} - -/* --------------------------- memalign support -------------------------- */ - -static void* internal_memalign(mstate m, size_t alignment, size_t bytes) { - if (alignment <= MALLOC_ALIGNMENT) /* Can just use malloc */ - return internal_malloc(m, bytes); - if (alignment < MIN_CHUNK_SIZE) /* must be at least a minimum chunk size */ - alignment = MIN_CHUNK_SIZE; - if ((alignment & (alignment-SIZE_T_ONE)) != 0) {/* Ensure a power of 2 */ - size_t a = MALLOC_ALIGNMENT << 1; - while (a < alignment) a <<= 1; - alignment = a; - } - - if (bytes >= MAX_REQUEST - alignment) { - if (m != 0) { /* Test isn't needed but avoids compiler warning */ - MALLOC_FAILURE_ACTION; - } - } - else { - size_t nb = request2size(bytes); - size_t req = nb + alignment + MIN_CHUNK_SIZE - CHUNK_OVERHEAD; - char* mem = (char*)internal_malloc(m, req); - if (mem != 0) { - void* leader = 0; - void* trailer = 0; - mchunkptr p = mem2chunk(mem); - - if (PREACTION(m)) return 0; - if ((((size_t)(mem)) % alignment) != 0) { /* misaligned */ - /* - Find an aligned spot inside chunk. Since we need to give - back leading space in a chunk of at least MIN_CHUNK_SIZE, if - the first calculation places us at a spot with less than - MIN_CHUNK_SIZE leader, we can move to the next aligned spot. - We've allocated enough total room so that this is always - possible. - */ - char* br = (char*)mem2chunk((size_t)(((size_t)(mem + - alignment - - SIZE_T_ONE)) & - -alignment)); - char* pos = ((size_t)(br - (char*)(p)) >= MIN_CHUNK_SIZE)? - br : br+alignment; - mchunkptr newp = (mchunkptr)pos; - size_t leadsize = pos - (char*)(p); - size_t newsize = chunksize(p) - leadsize; - - if (is_mmapped(p)) { /* For mmapped chunks, just adjust offset */ - newp->prev_foot = p->prev_foot + leadsize; - newp->head = newsize; - } - else { /* Otherwise, give back leader, use the rest */ - set_inuse(m, newp, newsize); - set_inuse(m, p, leadsize); - leader = chunk2mem(p); - } - p = newp; - } - - /* Give back spare room at the end */ - if (!is_mmapped(p)) { - size_t size = chunksize(p); - if (size > nb + MIN_CHUNK_SIZE) { - size_t remainder_size = size - nb; - mchunkptr remainder = chunk_plus_offset(p, nb); - set_inuse(m, p, nb); - set_inuse(m, remainder, remainder_size); - trailer = chunk2mem(remainder); - } - } - - assert (chunksize(p) >= nb); - assert((((size_t)(chunk2mem(p))) % alignment) == 0); - check_inuse_chunk(m, p); - POSTACTION(m); - if (leader != 0) { - internal_free(m, leader); - } - if (trailer != 0) { - internal_free(m, trailer); - } - return chunk2mem(p); - } - } - return 0; -} - -/* ------------------------ comalloc/coalloc support --------------------- */ - -static void** ialloc(mstate m, - size_t n_elements, - size_t* sizes, - int opts, - void* chunks[]) { - /* - This provides common support for independent_X routines, handling - all of the combinations that can result. - - The opts arg has: - bit 0 set if all elements are same size (using sizes[0]) - bit 1 set if elements should be zeroed - */ - - size_t element_size; /* chunksize of each element, if all same */ - size_t contents_size; /* total size of elements */ - size_t array_size; /* request size of pointer array */ - void* mem; /* malloced aggregate space */ - mchunkptr p; /* corresponding chunk */ - size_t remainder_size; /* remaining bytes while splitting */ - void** marray; /* either "chunks" or malloced ptr array */ - mchunkptr array_chunk; /* chunk for malloced ptr array */ - flag_t was_enabled; /* to disable mmap */ - size_t size; - size_t i; - - ensure_initialization(); - /* compute array length, if needed */ - if (chunks != 0) { - if (n_elements == 0) - return chunks; /* nothing to do */ - marray = chunks; - array_size = 0; - } - else { - /* if empty req, must still return chunk representing empty array */ - if (n_elements == 0) - return (void**)internal_malloc(m, 0); - marray = 0; - array_size = request2size(n_elements * (sizeof(void*))); - } - - /* compute total element size */ - if (opts & 0x1) { /* all-same-size */ - element_size = request2size(*sizes); - contents_size = n_elements * element_size; - } - else { /* add up all the sizes */ - element_size = 0; - contents_size = 0; - for (i = 0; i != n_elements; ++i) - contents_size += request2size(sizes[i]); - } - - size = contents_size + array_size; - - /* - Allocate the aggregate chunk. First disable direct-mmapping so - malloc won't use it, since we would not be able to later - free/realloc space internal to a segregated mmap region. - */ - was_enabled = use_mmap(m); - disable_mmap(m); - mem = internal_malloc(m, size - CHUNK_OVERHEAD); - if (was_enabled) - enable_mmap(m); - if (mem == 0) - return 0; - - if (PREACTION(m)) return 0; - p = mem2chunk(mem); - remainder_size = chunksize(p); - - assert(!is_mmapped(p)); - - if (opts & 0x2) { /* optionally clear the elements */ - memset((size_t*)mem, 0, remainder_size - SIZE_T_SIZE - array_size); - } - - /* If not provided, allocate the pointer array as final part of chunk */ - if (marray == 0) { - size_t array_chunk_size; - array_chunk = chunk_plus_offset(p, contents_size); - array_chunk_size = remainder_size - contents_size; - marray = (void**) (chunk2mem(array_chunk)); - set_size_and_pinuse_of_inuse_chunk(m, array_chunk, array_chunk_size); - remainder_size = contents_size; - } - - /* split out elements */ - for (i = 0; ; ++i) { - marray[i] = chunk2mem(p); - if (i != n_elements-1) { - if (element_size != 0) - size = element_size; - else - size = request2size(sizes[i]); - remainder_size -= size; - set_size_and_pinuse_of_inuse_chunk(m, p, size); - p = chunk_plus_offset(p, size); - } - else { /* the final element absorbs any overallocation slop */ - set_size_and_pinuse_of_inuse_chunk(m, p, remainder_size); - break; - } - } - -#if DEBUG - if (marray != chunks) { - /* final element must have exactly exhausted chunk */ - if (element_size != 0) { - assert(remainder_size == element_size); - } - else { - assert(remainder_size == request2size(sizes[i])); - } - check_inuse_chunk(m, mem2chunk(marray)); - } - for (i = 0; i != n_elements; ++i) - check_inuse_chunk(m, mem2chunk(marray[i])); - -#endif /* DEBUG */ - - POSTACTION(m); - return marray; -} - - -/* -------------------------- public routines ---------------------------- */ - -#if !ONLY_MSPACES - -void* dlmalloc(size_t bytes) { - /* - Basic algorithm: - If a small request (< 256 bytes minus per-chunk overhead): - 1. If one exists, use a remainderless chunk in associated smallbin. - (Remainderless means that there are too few excess bytes to - represent as a chunk.) - 2. If it is big enough, use the dv chunk, which is normally the - chunk adjacent to the one used for the most recent small request. - 3. If one exists, split the smallest available chunk in a bin, - saving remainder in dv. - 4. If it is big enough, use the top chunk. - 5. If available, get memory from system and use it - Otherwise, for a large request: - 1. Find the smallest available binned chunk that fits, and use it - if it is better fitting than dv chunk, splitting if necessary. - 2. If better fitting than any binned chunk, use the dv chunk. - 3. If it is big enough, use the top chunk. - 4. If request size >= mmap threshold, try to directly mmap this chunk. - 5. If available, get memory from system and use it - - The ugly goto's here ensure that postaction occurs along all paths. - */ - -#if USE_LOCKS - ensure_initialization(); /* initialize in sys_alloc if not using locks */ -#endif - - if (!PREACTION(gm)) { - void* mem; - size_t nb; - if (bytes <= MAX_SMALL_REQUEST) { - bindex_t idx; - binmap_t smallbits; - nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes); - idx = small_index(nb); - smallbits = gm->smallmap >> idx; - - if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */ - mchunkptr b, p; - idx += ~smallbits & 1; /* Uses next bin if idx empty */ - b = smallbin_at(gm, idx); - p = b->fd; - assert(chunksize(p) == small_index2size(idx)); - unlink_first_small_chunk(gm, b, p, idx); - set_inuse_and_pinuse(gm, p, small_index2size(idx)); - mem = chunk2mem(p); - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - - else if (nb > gm->dvsize) { - if (smallbits != 0) { /* Use chunk in next nonempty smallbin */ - mchunkptr b, p, r; - size_t rsize; - bindex_t i; - binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx)); - binmap_t leastbit = least_bit(leftbits); - compute_bit2idx(leastbit, i); - b = smallbin_at(gm, i); - p = b->fd; - assert(chunksize(p) == small_index2size(i)); - unlink_first_small_chunk(gm, b, p, i); - rsize = small_index2size(i) - nb; - /* Fit here cannot be remainderless if 4byte sizes */ - if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE) - set_inuse_and_pinuse(gm, p, small_index2size(i)); - else { - set_size_and_pinuse_of_inuse_chunk(gm, p, nb); - r = chunk_plus_offset(p, nb); - set_size_and_pinuse_of_free_chunk(r, rsize); - replace_dv(gm, r, rsize); - } - mem = chunk2mem(p); - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - - else if (gm->treemap != 0 && (mem = tmalloc_small(gm, nb)) != 0) { - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - } - } - else if (bytes >= MAX_REQUEST) - nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */ - else { - nb = pad_request(bytes); - if (gm->treemap != 0 && (mem = tmalloc_large(gm, nb)) != 0) { - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - } - - if (nb <= gm->dvsize) { - size_t rsize = gm->dvsize - nb; - mchunkptr p = gm->dv; - if (rsize >= MIN_CHUNK_SIZE) { /* split dv */ - mchunkptr r = gm->dv = chunk_plus_offset(p, nb); - gm->dvsize = rsize; - set_size_and_pinuse_of_free_chunk(r, rsize); - set_size_and_pinuse_of_inuse_chunk(gm, p, nb); - } - else { /* exhaust dv */ - size_t dvs = gm->dvsize; - gm->dvsize = 0; - gm->dv = 0; - set_inuse_and_pinuse(gm, p, dvs); - } - mem = chunk2mem(p); - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - - else if (nb < gm->topsize) { /* Split top */ - size_t rsize = gm->topsize -= nb; - mchunkptr p = gm->top; - mchunkptr r = gm->top = chunk_plus_offset(p, nb); - r->head = rsize | PINUSE_BIT; - set_size_and_pinuse_of_inuse_chunk(gm, p, nb); - mem = chunk2mem(p); - check_top_chunk(gm, gm->top); - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - - mem = sys_alloc(gm, nb); - - postaction: - POSTACTION(gm); - return mem; - } - - return 0; -} - -void dlfree(void* mem) { - /* - Consolidate freed chunks with preceeding or succeeding bordering - free chunks, if they exist, and then place in a bin. Intermixed - with special cases for top, dv, mmapped chunks, and usage errors. - */ - - if (mem != 0) { - mchunkptr p = mem2chunk(mem); -#if FOOTERS - mstate fm = get_mstate_for(p); - if (!ok_magic(fm)) { - USAGE_ERROR_ACTION(fm, p); - return; - } -#else /* FOOTERS */ -#define fm gm -#endif /* FOOTERS */ - if (!PREACTION(fm)) { - check_inuse_chunk(fm, p); - if (RTCHECK(ok_address(fm, p) && ok_inuse(p))) { - size_t psize = chunksize(p); - mchunkptr next = chunk_plus_offset(p, psize); - if (!pinuse(p)) { - size_t prevsize = p->prev_foot; - if (is_mmapped(p)) { - psize += prevsize + MMAP_FOOT_PAD; - if (CALL_MUNMAP((char*)p - prevsize, psize) == 0) - fm->footprint -= psize; - goto postaction; - } - else { - mchunkptr prev = chunk_minus_offset(p, prevsize); - psize += prevsize; - p = prev; - if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */ - if (p != fm->dv) { - unlink_chunk(fm, p, prevsize); - } - else if ((next->head & INUSE_BITS) == INUSE_BITS) { - fm->dvsize = psize; - set_free_with_pinuse(p, psize, next); - goto postaction; - } - } - else - goto erroraction; - } - } - - if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) { - if (!cinuse(next)) { /* consolidate forward */ - if (next == fm->top) { - size_t tsize = fm->topsize += psize; - fm->top = p; - p->head = tsize | PINUSE_BIT; - if (p == fm->dv) { - fm->dv = 0; - fm->dvsize = 0; - } - if (should_trim(fm, tsize)) - sys_trim(fm, 0); - goto postaction; - } - else if (next == fm->dv) { - size_t dsize = fm->dvsize += psize; - fm->dv = p; - set_size_and_pinuse_of_free_chunk(p, dsize); - goto postaction; - } - else { - size_t nsize = chunksize(next); - psize += nsize; - unlink_chunk(fm, next, nsize); - set_size_and_pinuse_of_free_chunk(p, psize); - if (p == fm->dv) { - fm->dvsize = psize; - goto postaction; - } - } - } - else - set_free_with_pinuse(p, psize, next); - - if (is_small(psize)) { - insert_small_chunk(fm, p, psize); - check_free_chunk(fm, p); - } - else { - tchunkptr tp = (tchunkptr)p; - insert_large_chunk(fm, tp, psize); - check_free_chunk(fm, p); - if (--fm->release_checks == 0) - release_unused_segments(fm); - } - goto postaction; - } - } - erroraction: - USAGE_ERROR_ACTION(fm, p); - postaction: - POSTACTION(fm); - } - } -#if !FOOTERS -#undef fm -#endif /* FOOTERS */ -} - -void* dlcalloc(size_t n_elements, size_t elem_size) { - void* mem; - size_t req = 0; - if (n_elements != 0) { - req = n_elements * elem_size; - if (((n_elements | elem_size) & ~(size_t)0xffff) && - (req / n_elements != elem_size)) - req = MAX_SIZE_T; /* force downstream failure on overflow */ - } - mem = dlmalloc(req); - if (mem != 0 && calloc_must_clear(mem2chunk(mem))) - memset(mem, 0, req); - return mem; -} - -void* dlrealloc(void* oldmem, size_t bytes) { - if (oldmem == 0) - return dlmalloc(bytes); -#ifdef REALLOC_ZERO_BYTES_FREES - if (bytes == 0) { - dlfree(oldmem); - return 0; - } -#endif /* REALLOC_ZERO_BYTES_FREES */ - else { -#if ! FOOTERS - mstate m = gm; -#else /* FOOTERS */ - mstate m = get_mstate_for(mem2chunk(oldmem)); - if (!ok_magic(m)) { - USAGE_ERROR_ACTION(m, oldmem); - return 0; - } -#endif /* FOOTERS */ - return internal_realloc(m, oldmem, bytes); - } -} - -void* dlmemalign(size_t alignment, size_t bytes) { - return internal_memalign(gm, alignment, bytes); -} - -void** dlindependent_calloc(size_t n_elements, size_t elem_size, - void* chunks[]) { - size_t sz = elem_size; /* serves as 1-element array */ - return ialloc(gm, n_elements, &sz, 3, chunks); -} - -void** dlindependent_comalloc(size_t n_elements, size_t sizes[], - void* chunks[]) { - return ialloc(gm, n_elements, sizes, 0, chunks); -} - -void* dlvalloc(size_t bytes) { - size_t pagesz; - ensure_initialization(); - pagesz = mparams.page_size; - return dlmemalign(pagesz, bytes); -} - -void* dlpvalloc(size_t bytes) { - size_t pagesz; - ensure_initialization(); - pagesz = mparams.page_size; - return dlmemalign(pagesz, (bytes + pagesz - SIZE_T_ONE) & ~(pagesz - SIZE_T_ONE)); -} - -int dlmalloc_trim(size_t pad) { - int result = 0; - ensure_initialization(); - if (!PREACTION(gm)) { - result = sys_trim(gm, pad); - POSTACTION(gm); - } - return result; -} - -size_t dlmalloc_footprint(void) { - return gm->footprint; -} - -size_t dlmalloc_max_footprint(void) { - return gm->max_footprint; -} - -#if !NO_MALLINFO -struct mallinfo dlmallinfo(void) { - return internal_mallinfo(gm); -} -#endif /* NO_MALLINFO */ - -void dlmalloc_stats() { - internal_malloc_stats(gm); -} - -int dlmallopt(int param_number, int value) { - return change_mparam(param_number, value); -} - -#endif /* !ONLY_MSPACES */ - -size_t dlmalloc_usable_size(void* mem) { - if (mem != 0) { - mchunkptr p = mem2chunk(mem); - if (is_inuse(p)) - return chunksize(p) - overhead_for(p); - } - return 0; -} - -/* ----------------------------- user mspaces ---------------------------- */ - -#if MSPACES - -static mstate init_user_mstate(char* tbase, size_t tsize) { - size_t msize = pad_request(sizeof(struct malloc_state)); - mchunkptr mn; - mchunkptr msp = align_as_chunk(tbase); - mstate m = (mstate)(chunk2mem(msp)); - memset(m, 0, msize); - INITIAL_LOCK(&m->mutex); - msp->head = (msize|INUSE_BITS); - m->seg.base = m->least_addr = tbase; - m->seg.size = m->footprint = m->max_footprint = tsize; - m->magic = mparams.magic; - m->release_checks = MAX_RELEASE_CHECK_RATE; - m->mflags = mparams.default_mflags; - m->extp = 0; - m->exts = 0; - disable_contiguous(m); - init_bins(m); - mn = next_chunk(mem2chunk(m)); - init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) - TOP_FOOT_SIZE); - check_top_chunk(m, m->top); - return m; -} - -mspace create_mspace(size_t capacity, int locked) { - mstate m = 0; - size_t msize; - ensure_initialization(); - msize = pad_request(sizeof(struct malloc_state)); - if (capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) { - size_t rs = ((capacity == 0)? mparams.granularity : - (capacity + TOP_FOOT_SIZE + msize)); - size_t tsize = granularity_align(rs); - char* tbase = (char*)(CALL_MMAP(tsize)); - if (tbase != CMFAIL) { - m = init_user_mstate(tbase, tsize); - m->seg.sflags = USE_MMAP_BIT; - set_lock(m, locked); - } - } - return (mspace)m; -} - -mspace create_mspace_with_base(void* base, size_t capacity, int locked) { - mstate m = 0; - size_t msize; - ensure_initialization(); - msize = pad_request(sizeof(struct malloc_state)); - if (capacity > msize + TOP_FOOT_SIZE && - capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) { - m = init_user_mstate((char*)base, capacity); - m->seg.sflags = EXTERN_BIT; - set_lock(m, locked); - } - return (mspace)m; -} - -int mspace_track_large_chunks(mspace msp, int enable) { - int ret = 0; - mstate ms = (mstate)msp; - if (!PREACTION(ms)) { - if (!use_mmap(ms)) - ret = 1; - if (!enable) - enable_mmap(ms); - else - disable_mmap(ms); - POSTACTION(ms); - } - return ret; -} - -size_t destroy_mspace(mspace msp) { - size_t freed = 0; - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - msegmentptr sp = &ms->seg; - while (sp != 0) { - char* base = sp->base; - size_t size = sp->size; - flag_t flag = sp->sflags; - sp = sp->next; - if ((flag & USE_MMAP_BIT) && !(flag & EXTERN_BIT) && - CALL_MUNMAP(base, size) == 0) - freed += size; - } - } - else { - USAGE_ERROR_ACTION(ms,ms); - } - return freed; -} - -/* - mspace versions of routines are near-clones of the global - versions. This is not so nice but better than the alternatives. -*/ - - -void* mspace_malloc(mspace msp, size_t bytes) { - mstate ms = (mstate)msp; - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - return 0; - } - if (!PREACTION(ms)) { - void* mem; - size_t nb; - if (bytes <= MAX_SMALL_REQUEST) { - bindex_t idx; - binmap_t smallbits; - nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes); - idx = small_index(nb); - smallbits = ms->smallmap >> idx; - - if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */ - mchunkptr b, p; - idx += ~smallbits & 1; /* Uses next bin if idx empty */ - b = smallbin_at(ms, idx); - p = b->fd; - assert(chunksize(p) == small_index2size(idx)); - unlink_first_small_chunk(ms, b, p, idx); - set_inuse_and_pinuse(ms, p, small_index2size(idx)); - mem = chunk2mem(p); - check_malloced_chunk(ms, mem, nb); - goto postaction; - } - - else if (nb > ms->dvsize) { - if (smallbits != 0) { /* Use chunk in next nonempty smallbin */ - mchunkptr b, p, r; - size_t rsize; - bindex_t i; - binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx)); - binmap_t leastbit = least_bit(leftbits); - compute_bit2idx(leastbit, i); - b = smallbin_at(ms, i); - p = b->fd; - assert(chunksize(p) == small_index2size(i)); - unlink_first_small_chunk(ms, b, p, i); - rsize = small_index2size(i) - nb; - /* Fit here cannot be remainderless if 4byte sizes */ - if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE) - set_inuse_and_pinuse(ms, p, small_index2size(i)); - else { - set_size_and_pinuse_of_inuse_chunk(ms, p, nb); - r = chunk_plus_offset(p, nb); - set_size_and_pinuse_of_free_chunk(r, rsize); - replace_dv(ms, r, rsize); - } - mem = chunk2mem(p); - check_malloced_chunk(ms, mem, nb); - goto postaction; - } - - else if (ms->treemap != 0 && (mem = tmalloc_small(ms, nb)) != 0) { - check_malloced_chunk(ms, mem, nb); - goto postaction; - } - } - } - else if (bytes >= MAX_REQUEST) - nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */ - else { - nb = pad_request(bytes); - if (ms->treemap != 0 && (mem = tmalloc_large(ms, nb)) != 0) { - check_malloced_chunk(ms, mem, nb); - goto postaction; - } - } - - if (nb <= ms->dvsize) { - size_t rsize = ms->dvsize - nb; - mchunkptr p = ms->dv; - if (rsize >= MIN_CHUNK_SIZE) { /* split dv */ - mchunkptr r = ms->dv = chunk_plus_offset(p, nb); - ms->dvsize = rsize; - set_size_and_pinuse_of_free_chunk(r, rsize); - set_size_and_pinuse_of_inuse_chunk(ms, p, nb); - } - else { /* exhaust dv */ - size_t dvs = ms->dvsize; - ms->dvsize = 0; - ms->dv = 0; - set_inuse_and_pinuse(ms, p, dvs); - } - mem = chunk2mem(p); - check_malloced_chunk(ms, mem, nb); - goto postaction; - } - - else if (nb < ms->topsize) { /* Split top */ - size_t rsize = ms->topsize -= nb; - mchunkptr p = ms->top; - mchunkptr r = ms->top = chunk_plus_offset(p, nb); - r->head = rsize | PINUSE_BIT; - set_size_and_pinuse_of_inuse_chunk(ms, p, nb); - mem = chunk2mem(p); - check_top_chunk(ms, ms->top); - check_malloced_chunk(ms, mem, nb); - goto postaction; - } - - mem = sys_alloc(ms, nb); - - postaction: - POSTACTION(ms); - return mem; - } - - return 0; -} - -void mspace_free(mspace msp, void* mem) { - if (mem != 0) { - mchunkptr p = mem2chunk(mem); -#if FOOTERS - mstate fm = get_mstate_for(p); - msp = msp; /* placate people compiling -Wunused */ -#else /* FOOTERS */ - mstate fm = (mstate)msp; -#endif /* FOOTERS */ - if (!ok_magic(fm)) { - USAGE_ERROR_ACTION(fm, p); - return; - } - if (!PREACTION(fm)) { - check_inuse_chunk(fm, p); - if (RTCHECK(ok_address(fm, p) && ok_inuse(p))) { - size_t psize = chunksize(p); - mchunkptr next = chunk_plus_offset(p, psize); - if (!pinuse(p)) { - size_t prevsize = p->prev_foot; - if (is_mmapped(p)) { - psize += prevsize + MMAP_FOOT_PAD; - if (CALL_MUNMAP((char*)p - prevsize, psize) == 0) - fm->footprint -= psize; - goto postaction; - } - else { - mchunkptr prev = chunk_minus_offset(p, prevsize); - psize += prevsize; - p = prev; - if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */ - if (p != fm->dv) { - unlink_chunk(fm, p, prevsize); - } - else if ((next->head & INUSE_BITS) == INUSE_BITS) { - fm->dvsize = psize; - set_free_with_pinuse(p, psize, next); - goto postaction; - } - } - else - goto erroraction; - } - } - - if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) { - if (!cinuse(next)) { /* consolidate forward */ - if (next == fm->top) { - size_t tsize = fm->topsize += psize; - fm->top = p; - p->head = tsize | PINUSE_BIT; - if (p == fm->dv) { - fm->dv = 0; - fm->dvsize = 0; - } - if (should_trim(fm, tsize)) - sys_trim(fm, 0); - goto postaction; - } - else if (next == fm->dv) { - size_t dsize = fm->dvsize += psize; - fm->dv = p; - set_size_and_pinuse_of_free_chunk(p, dsize); - goto postaction; - } - else { - size_t nsize = chunksize(next); - psize += nsize; - unlink_chunk(fm, next, nsize); - set_size_and_pinuse_of_free_chunk(p, psize); - if (p == fm->dv) { - fm->dvsize = psize; - goto postaction; - } - } - } - else - set_free_with_pinuse(p, psize, next); - - if (is_small(psize)) { - insert_small_chunk(fm, p, psize); - check_free_chunk(fm, p); - } - else { - tchunkptr tp = (tchunkptr)p; - insert_large_chunk(fm, tp, psize); - check_free_chunk(fm, p); - if (--fm->release_checks == 0) - release_unused_segments(fm); - } - goto postaction; - } - } - erroraction: - USAGE_ERROR_ACTION(fm, p); - postaction: - POSTACTION(fm); - } - } -} - -void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size) { - void* mem; - size_t req = 0; - mstate ms = (mstate)msp; - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - return 0; - } - if (n_elements != 0) { - req = n_elements * elem_size; - if (((n_elements | elem_size) & ~(size_t)0xffff) && - (req / n_elements != elem_size)) - req = MAX_SIZE_T; /* force downstream failure on overflow */ - } - mem = internal_malloc(ms, req); - if (mem != 0 && calloc_must_clear(mem2chunk(mem))) - memset(mem, 0, req); - return mem; -} - -void* mspace_realloc(mspace msp, void* oldmem, size_t bytes) { - if (oldmem == 0) - return mspace_malloc(msp, bytes); -#ifdef REALLOC_ZERO_BYTES_FREES - if (bytes == 0) { - mspace_free(msp, oldmem); - return 0; - } -#endif /* REALLOC_ZERO_BYTES_FREES */ - else { -#if FOOTERS - mchunkptr p = mem2chunk(oldmem); - mstate ms = get_mstate_for(p); -#else /* FOOTERS */ - mstate ms = (mstate)msp; -#endif /* FOOTERS */ - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - return 0; - } - return internal_realloc(ms, oldmem, bytes); - } -} - -void* mspace_memalign(mspace msp, size_t alignment, size_t bytes) { - mstate ms = (mstate)msp; - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - return 0; - } - return internal_memalign(ms, alignment, bytes); -} - -void** mspace_independent_calloc(mspace msp, size_t n_elements, - size_t elem_size, void* chunks[]) { - size_t sz = elem_size; /* serves as 1-element array */ - mstate ms = (mstate)msp; - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - return 0; - } - return ialloc(ms, n_elements, &sz, 3, chunks); -} - -void** mspace_independent_comalloc(mspace msp, size_t n_elements, - size_t sizes[], void* chunks[]) { - mstate ms = (mstate)msp; - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - return 0; - } - return ialloc(ms, n_elements, sizes, 0, chunks); -} - -int mspace_trim(mspace msp, size_t pad) { - int result = 0; - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - if (!PREACTION(ms)) { - result = sys_trim(ms, pad); - POSTACTION(ms); - } - } - else { - USAGE_ERROR_ACTION(ms,ms); - } - return result; -} - -void mspace_malloc_stats(mspace msp) { - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - internal_malloc_stats(ms); - } - else { - USAGE_ERROR_ACTION(ms,ms); - } -} - -size_t mspace_footprint(mspace msp) { - size_t result = 0; - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - result = ms->footprint; - } - else { - USAGE_ERROR_ACTION(ms,ms); - } - return result; -} - - -size_t mspace_max_footprint(mspace msp) { - size_t result = 0; - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - result = ms->max_footprint; - } - else { - USAGE_ERROR_ACTION(ms,ms); - } - return result; -} - - -#if !NO_MALLINFO -struct mallinfo mspace_mallinfo(mspace msp) { - mstate ms = (mstate)msp; - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - } - return internal_mallinfo(ms); -} -#endif /* NO_MALLINFO */ - -size_t mspace_usable_size(void* mem) { - if (mem != 0) { - mchunkptr p = mem2chunk(mem); - if (is_inuse(p)) - return chunksize(p) - overhead_for(p); - } - return 0; -} - -int mspace_mallopt(int param_number, int value) { - return change_mparam(param_number, value); -} - -#endif /* MSPACES */ - - -/* -------------------- Alternative MORECORE functions ------------------- */ - -/* - Guidelines for creating a custom version of MORECORE: - - * For best performance, MORECORE should allocate in multiples of pagesize. - * MORECORE may allocate more memory than requested. (Or even less, - but this will usually result in a malloc failure.) - * MORECORE must not allocate memory when given argument zero, but - instead return one past the end address of memory from previous - nonzero call. - * For best performance, consecutive calls to MORECORE with positive - arguments should return increasing addresses, indicating that - space has been contiguously extended. - * Even though consecutive calls to MORECORE need not return contiguous - addresses, it must be OK for malloc'ed chunks to span multiple - regions in those cases where they do happen to be contiguous. - * MORECORE need not handle negative arguments -- it may instead - just return MFAIL when given negative arguments. - Negative arguments are always multiples of pagesize. MORECORE - must not misinterpret negative args as large positive unsigned - args. You can suppress all such calls from even occurring by defining - MORECORE_CANNOT_TRIM, - - As an example alternative MORECORE, here is a custom allocator - kindly contributed for pre-OSX macOS. It uses virtually but not - necessarily physically contiguous non-paged memory (locked in, - present and won't get swapped out). You can use it by uncommenting - this section, adding some #includes, and setting up the appropriate - defines above: - - #define MORECORE osMoreCore - - There is also a shutdown routine that should somehow be called for - cleanup upon program exit. - - #define MAX_POOL_ENTRIES 100 - #define MINIMUM_MORECORE_SIZE (64 * 1024U) - static int next_os_pool; - void *our_os_pools[MAX_POOL_ENTRIES]; - - void *osMoreCore(int size) - { - void *ptr = 0; - static void *sbrk_top = 0; - - if (size > 0) - { - if (size < MINIMUM_MORECORE_SIZE) - size = MINIMUM_MORECORE_SIZE; - if (CurrentExecutionLevel() == kTaskLevel) - ptr = PoolAllocateResident(size + RM_PAGE_SIZE, 0); - if (ptr == 0) - { - return (void *) MFAIL; - } - // save ptrs so they can be freed during cleanup - our_os_pools[next_os_pool] = ptr; - next_os_pool++; - ptr = (void *) ((((size_t) ptr) + RM_PAGE_MASK) & ~RM_PAGE_MASK); - sbrk_top = (char *) ptr + size; - return ptr; - } - else if (size < 0) - { - // we don't currently support shrink behavior - return (void *) MFAIL; - } - else - { - return sbrk_top; - } - } - - // cleanup any allocated memory pools - // called as last thing before shutting down driver - - void osCleanupMem(void) - { - void **ptr; - - for (ptr = our_os_pools; ptr < &our_os_pools[MAX_POOL_ENTRIES]; ptr++) - if (*ptr) - { - PoolDeallocate(*ptr); - *ptr = 0; - } - } - -*/ - - -/* ----------------------------------------------------------------------- -History: - V2.8.4 Wed May 27 09:56:23 2009 Doug Lea (dl at gee) - * Use zeros instead of prev foot for is_mmapped - * Add mspace_track_large_chunks; thanks to Jean Brouwers - * Fix set_inuse in internal_realloc; thanks to Jean Brouwers - * Fix insufficient sys_alloc padding when using 16byte alignment - * Fix bad error check in mspace_footprint - * Adaptations for ptmalloc; thanks to Wolfram Gloger. - * Reentrant spin locks; thanks to Earl Chew and others - * Win32 improvements; thanks to Niall Douglas and Earl Chew - * Add NO_SEGMENT_TRAVERSAL and MAX_RELEASE_CHECK_RATE options - * Extension hook in malloc_state - * Various small adjustments to reduce warnings on some compilers - * Various configuration extensions/changes for more platforms. Thanks - to all who contributed these. - - V2.8.3 Thu Sep 22 11:16:32 2005 Doug Lea (dl at gee) - * Add max_footprint functions - * Ensure all appropriate literals are size_t - * Fix conditional compilation problem for some #define settings - * Avoid concatenating segments with the one provided - in create_mspace_with_base - * Rename some variables to avoid compiler shadowing warnings - * Use explicit lock initialization. - * Better handling of sbrk interference. - * Simplify and fix segment insertion, trimming and mspace_destroy - * Reinstate REALLOC_ZERO_BYTES_FREES option from 2.7.x - * Thanks especially to Dennis Flanagan for help on these. - - V2.8.2 Sun Jun 12 16:01:10 2005 Doug Lea (dl at gee) - * Fix memalign brace error. - - V2.8.1 Wed Jun 8 16:11:46 2005 Doug Lea (dl at gee) - * Fix improper #endif nesting in C++ - * Add explicit casts needed for C++ - - V2.8.0 Mon May 30 14:09:02 2005 Doug Lea (dl at gee) - * Use trees for large bins - * Support mspaces - * Use segments to unify sbrk-based and mmap-based system allocation, - removing need for emulation on most platforms without sbrk. - * Default safety checks - * Optional footer checks. Thanks to William Robertson for the idea. - * Internal code refactoring - * Incorporate suggestions and platform-specific changes. - Thanks to Dennis Flanagan, Colin Plumb, Niall Douglas, - Aaron Bachmann, Emery Berger, and others. - * Speed up non-fastbin processing enough to remove fastbins. - * Remove useless cfree() to avoid conflicts with other apps. - * Remove internal memcpy, memset. Compilers handle builtins better. - * Remove some options that no one ever used and rename others. - - V2.7.2 Sat Aug 17 09:07:30 2002 Doug Lea (dl at gee) - * Fix malloc_state bitmap array misdeclaration - - V2.7.1 Thu Jul 25 10:58:03 2002 Doug Lea (dl at gee) - * Allow tuning of FIRST_SORTED_BIN_SIZE - * Use PTR_UINT as type for all ptr->int casts. Thanks to John Belmonte. - * Better detection and support for non-contiguousness of MORECORE. - Thanks to Andreas Mueller, Conal Walsh, and Wolfram Gloger - * Bypass most of malloc if no frees. Thanks To Emery Berger. - * Fix freeing of old top non-contiguous chunk im sysmalloc. - * Raised default trim and map thresholds to 256K. - * Fix mmap-related #defines. Thanks to Lubos Lunak. - * Fix copy macros; added LACKS_FCNTL_H. Thanks to Neal Walfield. - * Branch-free bin calculation - * Default trim and mmap thresholds now 256K. - - V2.7.0 Sun Mar 11 14:14:06 2001 Doug Lea (dl at gee) - * Introduce independent_comalloc and independent_calloc. - Thanks to Michael Pachos for motivation and help. - * Make optional .h file available - * Allow > 2GB requests on 32bit systems. - * new WIN32 sbrk, mmap, munmap, lock code from . - Thanks also to Andreas Mueller , - and Anonymous. - * Allow override of MALLOC_ALIGNMENT (Thanks to Ruud Waij for - helping test this.) - * memalign: check alignment arg - * realloc: don't try to shift chunks backwards, since this - leads to more fragmentation in some programs and doesn't - seem to help in any others. - * Collect all cases in malloc requiring system memory into sysmalloc - * Use mmap as backup to sbrk - * Place all internal state in malloc_state - * Introduce fastbins (although similar to 2.5.1) - * Many minor tunings and cosmetic improvements - * Introduce USE_PUBLIC_MALLOC_WRAPPERS, USE_MALLOC_LOCK - * Introduce MALLOC_FAILURE_ACTION, MORECORE_CONTIGUOUS - Thanks to Tony E. Bennett and others. - * Include errno.h to support default failure action. - - V2.6.6 Sun Dec 5 07:42:19 1999 Doug Lea (dl at gee) - * return null for negative arguments - * Added Several WIN32 cleanups from Martin C. Fong - * Add 'LACKS_SYS_PARAM_H' for those systems without 'sys/param.h' - (e.g. WIN32 platforms) - * Cleanup header file inclusion for WIN32 platforms - * Cleanup code to avoid Microsoft Visual C++ compiler complaints - * Add 'USE_DL_PREFIX' to quickly allow co-existence with existing - memory allocation routines - * Set 'malloc_getpagesize' for WIN32 platforms (needs more work) - * Use 'assert' rather than 'ASSERT' in WIN32 code to conform to - usage of 'assert' in non-WIN32 code - * Improve WIN32 'sbrk()' emulation's 'findRegion()' routine to - avoid infinite loop - * Always call 'fREe()' rather than 'free()' - - V2.6.5 Wed Jun 17 15:57:31 1998 Doug Lea (dl at gee) - * Fixed ordering problem with boundary-stamping - - V2.6.3 Sun May 19 08:17:58 1996 Doug Lea (dl at gee) - * Added pvalloc, as recommended by H.J. Liu - * Added 64bit pointer support mainly from Wolfram Gloger - * Added anonymously donated WIN32 sbrk emulation - * Malloc, calloc, getpagesize: add optimizations from Raymond Nijssen - * malloc_extend_top: fix mask error that caused wastage after - foreign sbrks - * Add linux mremap support code from HJ Liu - - V2.6.2 Tue Dec 5 06:52:55 1995 Doug Lea (dl at gee) - * Integrated most documentation with the code. - * Add support for mmap, with help from - Wolfram Gloger (Gloger@lrz.uni-muenchen.de). - * Use last_remainder in more cases. - * Pack bins using idea from colin@nyx10.cs.du.edu - * Use ordered bins instead of best-fit threshhold - * Eliminate block-local decls to simplify tracing and debugging. - * Support another case of realloc via move into top - * Fix error occuring when initial sbrk_base not word-aligned. - * Rely on page size for units instead of SBRK_UNIT to - avoid surprises about sbrk alignment conventions. - * Add mallinfo, mallopt. Thanks to Raymond Nijssen - (raymond@es.ele.tue.nl) for the suggestion. - * Add `pad' argument to malloc_trim and top_pad mallopt parameter. - * More precautions for cases where other routines call sbrk, - courtesy of Wolfram Gloger (Gloger@lrz.uni-muenchen.de). - * Added macros etc., allowing use in linux libc from - H.J. Lu (hjl@gnu.ai.mit.edu) - * Inverted this history list - - V2.6.1 Sat Dec 2 14:10:57 1995 Doug Lea (dl at gee) - * Re-tuned and fixed to behave more nicely with V2.6.0 changes. - * Removed all preallocation code since under current scheme - the work required to undo bad preallocations exceeds - the work saved in good cases for most test programs. - * No longer use return list or unconsolidated bins since - no scheme using them consistently outperforms those that don't - given above changes. - * Use best fit for very large chunks to prevent some worst-cases. - * Added some support for debugging - - V2.6.0 Sat Nov 4 07:05:23 1995 Doug Lea (dl at gee) - * Removed footers when chunks are in use. Thanks to - Paul Wilson (wilson@cs.texas.edu) for the suggestion. - - V2.5.4 Wed Nov 1 07:54:51 1995 Doug Lea (dl at gee) - * Added malloc_trim, with help from Wolfram Gloger - (wmglo@Dent.MED.Uni-Muenchen.DE). - - V2.5.3 Tue Apr 26 10:16:01 1994 Doug Lea (dl at g) - - V2.5.2 Tue Apr 5 16:20:40 1994 Doug Lea (dl at g) - * realloc: try to expand in both directions - * malloc: swap order of clean-bin strategy; - * realloc: only conditionally expand backwards - * Try not to scavenge used bins - * Use bin counts as a guide to preallocation - * Occasionally bin return list chunks in first scan - * Add a few optimizations from colin@nyx10.cs.du.edu - - V2.5.1 Sat Aug 14 15:40:43 1993 Doug Lea (dl at g) - * faster bin computation & slightly different binning - * merged all consolidations to one part of malloc proper - (eliminating old malloc_find_space & malloc_clean_bin) - * Scan 2 returns chunks (not just 1) - * Propagate failure in realloc if malloc returns 0 - * Add stuff to allow compilation on non-ANSI compilers - from kpv@research.att.com - - V2.5 Sat Aug 7 07:41:59 1993 Doug Lea (dl at g.oswego.edu) - * removed potential for odd address access in prev_chunk - * removed dependency on getpagesize.h - * misc cosmetics and a bit more internal documentation - * anticosmetics: mangled names in macros to evade debugger strangeness - * tested on sparc, hp-700, dec-mips, rs6000 - with gcc & native cc (hp, dec only) allowing - Detlefs & Zorn comparison study (in SIGPLAN Notices.) - - Trial version Fri Aug 28 13:14:29 1992 Doug Lea (dl at g.oswego.edu) - * Based loosely on libg++-1.2X malloc. (It retains some of the overall - structure of old version, but most details differ.) - -*/ - diff --git a/polymer/eduke32/build/include/nedmalloc.h b/polymer/eduke32/build/include/nedmalloc.h index 4ea9d93ff..e525fd7d8 100644 --- a/polymer/eduke32/build/include/nedmalloc.h +++ b/polymer/eduke32/build/include/nedmalloc.h @@ -1,302 +1,1617 @@ -/* nedalloc, an alternative malloc implementation for multiple threads without -lock contention based on dlmalloc v2.8.3. (C) 2005-2009 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. -*/ - -#ifndef NEDMALLOC_H -#define NEDMALLOC_H - - -/* See malloc.c.h for what each function does. - -REPLACE_SYSTEM_ALLOCATOR on POSIX causes nedalloc's functions to be called -malloc, free etc. instead of nedmalloc, nedfree etc. You may or may not want -this. On Windows it causes nedmalloc to patch all loaded DLLs and binaries -to replace usage of the system allocator. - -NO_NED_NAMESPACE prevents the functions from being defined in the nedalloc -namespace when in C++ (uses the global namespace instead). - -NEDMALLOCEXTSPEC can be defined to be __declspec(dllexport) or -__attribute__ ((visibility("default"))) or whatever you like. It defaults -to extern unless NEDMALLOC_DLL_EXPORTS is set as it would be when building -nedmalloc.dll. - -USE_LOCKS can be 2 if you want to define your own MLOCK_T, INITIAL_LOCK, -ACQUIRE_LOCK, RELEASE_LOCK, TRY_LOCK, IS_LOCKED and NULL_LOCK_INITIALIZER. - -NEDMALLOC_DEBUG can be defined to cause DEBUG to be set differently for nedmalloc -than for the rest of the build. Remember to set NDEBUG to disable all assertion -checking too. - -USE_MAGIC_HEADERS causes nedalloc to allocate an extra three sizeof(size_t) -to each block. nedpfree() and nedprealloc() can then automagically know when -to free a system allocated block. Enabling this typically adds 20-50% to -application memory usage. - -ENABLE_TOLERANT_NEDMALLOC is automatically turned on if REPLACE_SYSTEM_ALLOCATOR -is set or the Windows DLL is being built. This causes nedmalloc to detect when a -system allocator block is passed to it and to handle it appropriately. Note that -without USE_MAGIC_HEADERS there is a very tiny chance that nedmalloc will segfault -on non-Windows builds (it uses Win32 SEH to trap segfaults on Windows and there -is no comparable system on POSIX). - -USE_ALLOCATOR can be one of these settings (it defaults to 1): - 0: System allocator (nedmalloc now simply acts as a threadcache). - WARNING: Intended for DEBUG USE ONLY - not all functions work correctly. - 1: dlmalloc - -ENABLE_LARGE_PAGES enables support for requesting memory from the system in large -(typically >=2Mb) pages if the host OS supports this. These occupy just a single -TLB entry and can significantly improve performance in large working set applications. - -ENABLE_FAST_HEAP_DETECTION enables special logic to detect blocks allocated -by the system heap. This avoids 1.5%-2% overhead when checking for non-nedmalloc -blocks, but it assumes that the NT and glibc heaps function in a very specific -fashion which may not hold true across OS upgrades. -*/ - -#include /* for size_t */ - -#define USE_ALLOCATOR 1 -#define USE_MAGIC_HEADERS 1 -#define MAXTHREADSINPOOL 2 -#define FINEGRAINEDBINS 1 -#define ENABLE_LARGE_PAGES 1 -#define ENABLE_FAST_HEAP_DETECTION 1 -#define NDEBUG 1 -#define THREADCACHEMAX 4194304 -#define THREADCACHEMAXBINS ((22-4)*2) - -#ifndef NEDMALLOCEXTSPEC - #ifdef NEDMALLOC_DLL_EXPORTS - #ifdef WIN32 - #define NEDMALLOCEXTSPEC extern __declspec(dllexport) - #elif defined(__GNUC__) - #define NEDMALLOCEXTSPEC extern __attribute__ ((visibility("default"))) - #endif - #ifndef ENABLE_TOLERANT_NEDMALLOC - #define ENABLE_TOLERANT_NEDMALLOC 1 - #endif - #else - #define NEDMALLOCEXTSPEC extern - #endif -#endif - -#if __STDC_VERSION__ >= 199901L /* C99 or better */ - #define RESTRICT restrict -#else - #if defined(_MSC_VER) && _MSC_VER>=1400 - #define RESTRICT __restrict - #endif - #ifdef __GNUC__ - #define RESTRICT __restrict - #endif -#endif -#ifndef RESTRICT - #define RESTRICT -#endif - -#if defined(_MSC_VER) && _MSC_VER>=1400 - #define NEDMALLOCPTRATTR __declspec(restrict) - #define NEDMALLOCNOALIASATTR __declspec(noalias) -#endif -#ifdef __GNUC__ - #define NEDMALLOCPTRATTR __attribute__ ((malloc)) -#endif -#ifndef NEDMALLOCPTRATTR - #define NEDMALLOCPTRATTR -#endif -#ifndef NEDMALLOCNOALIASATTR - #define NEDMALLOCNOALIASATTR -#endif - -#ifndef USE_MAGIC_HEADERS - #define USE_MAGIC_HEADERS 0 -#endif - -#ifndef USE_ALLOCATOR - #define USE_ALLOCATOR 1 /* dlmalloc */ -#endif - -#if !USE_ALLOCATOR && !USE_MAGIC_HEADERS -#error If you are using the system allocator then you MUST use magic headers -#endif - -#ifdef REPLACE_SYSTEM_ALLOCATOR - #if USE_ALLOCATOR==0 - #error Cannot combine using the system allocator with replacing the system allocator - #endif - #ifndef ENABLE_TOLERANT_NEDMALLOC - #define ENABLE_TOLERANT_NEDMALLOC 1 - #endif - #ifndef WIN32 /* We have a dedicated patcher for Windows */ - #define nedmalloc malloc - #define nedcalloc calloc - #define nedrealloc realloc - #define nedfree free - #define nedmemalign memalign - #define nedmallinfo mallinfo - #define nedmallopt mallopt - #define nedmalloc_trim malloc_trim - #define nedmalloc_stats malloc_stats - #define nedmalloc_footprint malloc_footprint - #define nedindependent_calloc independent_calloc - #define nedindependent_comalloc independent_comalloc - #ifdef _MSC_VER - #define nedblksize _msize - #endif - #endif -#endif - -#if defined(__cplusplus) -extern "C" { -#endif -struct nedmallinfo { - size_t arena; /* non-mmapped space allocated from system */ - size_t ordblks; /* number of free chunks */ - size_t smblks; /* always 0 */ - size_t hblks; /* always 0 */ - size_t hblkhd; /* space in mmapped regions */ - size_t usmblks; /* maximum total allocated space */ - size_t fsmblks; /* always 0 */ - size_t uordblks; /* total allocated space */ - size_t fordblks; /* total free space */ - size_t keepcost; /* releasable (via malloc_trim) space */ -}; -#if defined(__cplusplus) -} -#endif - -#if defined(__cplusplus) - #if !defined(NO_NED_NAMESPACE) -namespace nedalloc { - #else -extern "C" { - #endif - #define THROWSPEC throw() -#else - #define THROWSPEC -#endif - -/* These are the global functions */ - -/* Gets the usable size of an allocated block. Note this will always be bigger than what was -asked for due to rounding etc. Optionally returns 1 in isforeign if the block came from the -system allocator - note that there is a small (>0.01%) but real chance of segfault on non-Windows -systems when passing non-nedmalloc blocks if you don't use USE_MAGIC_HEADERS. -*/ -NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR size_t nedblksize(int *RESTRICT isforeign, void *RESTRICT mem) THROWSPEC; - -NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR void nedsetvalue(void *v) THROWSPEC; - -NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedmalloc(size_t size) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedcalloc(size_t no, size_t size) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedrealloc(void *mem, size_t size) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR void nedfree(void *mem) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedmemalign(size_t alignment, size_t bytes) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR struct nedmallinfo nedmallinfo(void) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR int nedmallopt(int parno, int value) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR void* nedmalloc_internals(size_t *granularity, size_t *magic) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR int nedmalloc_trim(size_t pad) THROWSPEC; -NEDMALLOCEXTSPEC void nedmalloc_stats(void) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR size_t nedmalloc_footprint(void) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void **nedindependent_calloc(size_t elemsno, size_t elemsize, void **chunks) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void **nedindependent_comalloc(size_t elems, size_t *sizes, void **chunks) THROWSPEC; - -/* Destroys the system memory pool used by the functions above. -Useful for when you have nedmalloc in a DLL you're about to unload. -If you call ANY nedmalloc functions after calling this you will -get a fatal exception! -*/ -NEDMALLOCEXTSPEC void neddestroysyspool() THROWSPEC; - -/* These are the pool functions */ -struct nedpool_t; -typedef struct nedpool_t nedpool; - -/* Creates a memory pool for use with the nedp* functions below. -Capacity is how much to allocate immediately (if you know you'll be allocating a lot -of memory very soon) which you can leave at zero. Threads specifies how many threads -will *normally* be accessing the pool concurrently. Setting this to zero means it -extends on demand, but be careful of this as it can rapidly consume system resources -where bursts of concurrent threads use a pool at once. -*/ -NEDMALLOCEXTSPEC NEDMALLOCPTRATTR nedpool *nedcreatepool(size_t capacity, int threads) THROWSPEC; - -/* Destroys a memory pool previously created by nedcreatepool(). -*/ -NEDMALLOCEXTSPEC void neddestroypool(nedpool *p) THROWSPEC; - -/* Returns a zero terminated snapshot of threadpools existing at the time of call. Call -nedfree() on the returned list when you are done. Returns zero if there is only the -system pool in existence. -*/ -NEDMALLOCEXTSPEC nedpool **nedpoollist() THROWSPEC; - -/* Sets a value to be associated with a pool. You can retrieve this value by passing -any memory block allocated from that pool. -*/ -NEDMALLOCEXTSPEC void nedpsetvalue(nedpool *p, void *v) THROWSPEC; - -/* Gets a previously set value using nedpsetvalue() or zero if memory is unknown. -Optionally can also retrieve pool. You can detect an unknown block by the return -being zero and *p being unmodifed. -*/ -NEDMALLOCEXTSPEC void *nedgetvalue(nedpool **p, void *mem) THROWSPEC; - -/* Trims the thread cache for the calling thread, returning any existing cache -data to the central pool. Remember to ALWAYS call with zero if you used the -system pool. Setting disable to non-zero replicates neddisablethreadcache(). -*/ -NEDMALLOCEXTSPEC void nedtrimthreadcache(nedpool *p, int disable) THROWSPEC; - -/* Disables the thread cache for the calling thread, returning any existing cache -data to the central pool. Remember to ALWAYS call with zero if you used the -system pool. -*/ -NEDMALLOCEXTSPEC void neddisablethreadcache(nedpool *p) THROWSPEC; - - -NEDMALLOCEXTSPEC NEDMALLOCPTRATTR void * nedpmalloc(nedpool *p, size_t size) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCPTRATTR void * nedpcalloc(nedpool *p, size_t no, size_t size) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCPTRATTR void * nedprealloc(nedpool *p, void *mem, size_t size) THROWSPEC; -NEDMALLOCEXTSPEC void nedpfree(nedpool *p, void *mem) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCPTRATTR void * nedpmemalign(nedpool *p, size_t alignment, size_t bytes) THROWSPEC; -NEDMALLOCEXTSPEC struct nedmallinfo nedpmallinfo(nedpool *p) THROWSPEC; -NEDMALLOCEXTSPEC int nedpmallopt(nedpool *p, int parno, int value) THROWSPEC; -NEDMALLOCEXTSPEC int nedpmalloc_trim(nedpool *p, size_t pad) THROWSPEC; -NEDMALLOCEXTSPEC void nedpmalloc_stats(nedpool *p) THROWSPEC; -NEDMALLOCEXTSPEC size_t nedpmalloc_footprint(nedpool *p) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCPTRATTR void **nedpindependent_calloc(nedpool *p, size_t elemsno, size_t elemsize, void **chunks) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCPTRATTR void **nedpindependent_comalloc(nedpool *p, size_t elems, size_t *sizes, void **chunks) THROWSPEC; -NEDMALLOCEXTSPEC NEDMALLOCPTRATTR char * nedstrdup(const char *str) THROWSPEC; - -#if defined(__cplusplus) -} -#endif - -#endif +/* nedalloc, an alternative malloc implementation for multiple threads without +lock contention based on dlmalloc v2.8.4. (C) 2005-2010 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. +*/ + +#ifndef NEDMALLOC_H +#define NEDMALLOC_H + +/*! \file nedmalloc.h +\brief Defines the functionality provided by nedalloc. +*/ + +/*! \mainpage + +Please see the Readme.html +*/ + +/*! \def NEDMALLOC_DEBUG +\brief Defines the assertion checking performed by nedalloc + +NEDMALLOC_DEBUG can be defined to cause DEBUG to be set differently for nedmalloc +than for the rest of the build. Remember to set NDEBUG to disable all assertion +checking too. +*/ + +/*! \def ENABLE_LARGE_PAGES +\brief Defines whether nedalloc uses large pages (>=2Mb) + +ENABLE_LARGE_PAGES enables support for requesting memory from the system in large +(typically >=2Mb) pages if the host OS supports this. These occupy just a single +TLB entry and can significantly improve performance in large working set applications. +*/ + +/*! \def ENABLE_FAST_HEAP_DETECTION +\brief Defines whether nedalloc takes platform specific shortcuts when detecting foreign blocks. + +ENABLE_FAST_HEAP_DETECTION enables special logic to detect blocks allocated +by the system heap. This avoids 1.5%-2% overhead when checking for non-nedmalloc +blocks, but it assumes that the NT and glibc heaps function in a very specific +fashion which may not hold true across OS upgrades. +*/ + +/*! \def HAVE_CPP0XRVALUEREFS +\ingroup C++ +\brief Enables rvalue references + +Define to enable the usage of rvalue references which enables move semantics and +other things. Automatically defined if __cplusplus indicates a C++0x compiler, +otherwise you'll need to set it yourself. +*/ + +/*! \def HAVE_CPP0XVARIADICTEMPLATES +\ingroup C++ +\brief Enables variadic templates + +Define to enable the usage of variadic templates which enables the use of arbitrary +numbers of policies and other useful things. Automatically defined if __cplusplus +indicates a C++0x compiler, otherwise you'll need to set it yourself. +*/ + +/*! \def HAVE_CPP0XSTATICASSERT +\ingroup C++ +\brief Enables static assertions + +Define to enable the usage of static assertions. Automatically defined if __cplusplus +indicates a C++0x compiler, otherwise you'll need to set it yourself. +*/ + +/*! \def HAVE_CPP0XTYPETRAITS +\ingroup C++ +\brief Enables type traits + +Define to enable the usage of <type_traits>. Automatically defined if __cplusplus +indicates a C++0x compiler, otherwise you'll need to set it yourself. +*/ + +#if __cplusplus > 199711L || defined(HAVE_CPP0X) /* Do we have C++0x? */ +#undef HAVE_CPP0XRVALUEREFS +#define HAVE_CPP0XRVALUEREFS 1 +#undef HAVE_CPP0XVARIADICTEMPLATES +#define HAVE_CPP0XVARIADICTEMPLATES 1 +#undef HAVE_CPP0XSTATICASSERT +#define HAVE_CPP0XSTATICASSERT 1 +#undef HAVE_CPP0XTYPETRAITS +#define HAVE_CPP0XTYPETRAITS 1 +#endif + +#include /* for size_t */ + +/*! \def NEDMALLOCEXTSPEC +\brief Defines how nedalloc's API is to be made visible. + +NEDMALLOCEXTSPEC can be defined to be __declspec(dllexport) or +__attribute__ ((visibility("default"))) or whatever you like. It defaults +to extern unless NEDMALLOC_DLL_EXPORTS is set as it would be when building +nedmalloc.dll. + */ +#ifndef NEDMALLOCEXTSPEC + #ifdef NEDMALLOC_DLL_EXPORTS + #ifdef WIN32 + #define NEDMALLOCEXTSPEC extern __declspec(dllexport) + #elif defined(__GNUC__) + #define NEDMALLOCEXTSPEC extern __attribute__ ((visibility("default"))) + #endif + #ifndef ENABLE_TOLERANT_NEDMALLOC + #define ENABLE_TOLERANT_NEDMALLOC 1 + #endif + #else + #define NEDMALLOCEXTSPEC extern + #endif +#endif + +/*! \def NEDMALLOCDEPRECATED +\brief Defined to mark an API as deprecated */ +#ifndef NEDMALLOCDEPRECATED +#if defined(_MSC_VER) && !defined(__GCCXML__) + #define NEDMALLOCDEPRECATED __declspec(deprecated) +#elif defined(__GNUC__) && !defined(__GCCXML__) + #define NEDMALLOCDEPRECATED __attribute ((deprecated)) +#else +//! Marks a function as being deprecated + #define NEDMALLOCDEPRECATED +#endif +#endif + +/*! \def RESTRICT +\brief Defined to the restrict keyword or equivalent if available */ +#ifndef RESTRICT +#if __STDC_VERSION__ >= 199901L /* C99 or better */ + #define RESTRICT restrict +#else + #if defined(_MSC_VER) && _MSC_VER>=1400 + #define RESTRICT __restrict + #endif + #ifdef __GNUC__ + #define RESTRICT __restrict + #endif +#endif +#ifndef RESTRICT + #define RESTRICT +#endif +#endif + +#if defined(_MSC_VER) && _MSC_VER>=1400 + #define NEDMALLOCPTRATTR __declspec(restrict) + #define NEDMALLOCNOALIASATTR __declspec(noalias) +#endif +#ifdef __GNUC__ + #define NEDMALLOCPTRATTR __attribute__ ((malloc)) +#endif +/*! \def NEDMALLOCPTRATTR +\brief Defined to the specifier for a pointer which points to a memory block. Like NEDMALLOCNOALIASATTR, but sadly not identical. */ +#ifndef NEDMALLOCPTRATTR + #define NEDMALLOCPTRATTR +#endif +/*! \def NEDMALLOCNOALIASATTR +\brief Defined to the specifier for a pointer which does not alias any other variable. */ +#ifndef NEDMALLOCNOALIASATTR + #define NEDMALLOCNOALIASATTR +#endif + +/*! \def USE_MAGIC_HEADERS +\brief Defines whether nedalloc should use magic headers in foreign heap block detection + +USE_MAGIC_HEADERS causes nedalloc to allocate an extra three sizeof(size_t) +to each block. nedpfree() and nedprealloc() can then automagically know when +to free a system allocated block. Enabling this typically adds 20-50% to +application memory usage, and is mandatory if USE_ALLOCATOR is not 1. +*/ +#ifndef USE_MAGIC_HEADERS + #define USE_MAGIC_HEADERS 0 +#endif + +/*! \def USE_ALLOCATOR +\brief Defines the underlying allocator to use + +USE_ALLOCATOR can be one of these settings (it defaults to 1): + 0: System allocator (nedmalloc now simply acts as a threadcache) which is + very useful for testing with valgrind and Glowcode. + WARNING: Intended for DEBUG USE ONLY - not all functions work correctly. + 1: dlmalloc +*/ +#ifndef USE_ALLOCATOR + #define USE_ALLOCATOR 1 /* dlmalloc */ +#endif + +#if !USE_ALLOCATOR && !USE_MAGIC_HEADERS +#error If you are using the system allocator then you MUST use magic headers +#endif + +/*! \def REPLACE_SYSTEM_ALLOCATOR +\brief Defines whether to replace the system allocator (malloc(), free() et al) with nedalloc's implementation. + +REPLACE_SYSTEM_ALLOCATOR on POSIX causes nedalloc's functions to be called +malloc, free etc. instead of nedmalloc, nedfree etc. You may or may not want +this. On Windows it causes nedmalloc to patch all loaded DLLs and binaries +to replace usage of the system allocator. + +Always turns on ENABLE_TOLERANT_NEDMALLOC. +*/ +#ifdef REPLACE_SYSTEM_ALLOCATOR + #if USE_ALLOCATOR==0 + #error Cannot combine using the system allocator with replacing the system allocator + #endif + #ifndef ENABLE_TOLERANT_NEDMALLOC + #define ENABLE_TOLERANT_NEDMALLOC 1 + #endif + #ifndef WIN32 /* We have a dedicated patcher for Windows */ + #define nedmalloc malloc + #define nedmalloc2 malloc2 + #define nedcalloc calloc + #define nedrealloc realloc + #define nedrealloc2 realloc2 + #define nedfree free + #define nedfree2 free2 + #define nedmemalign memalign + #define nedmallinfo mallinfo + #define nedmallopt mallopt + #define nedmalloc_trim malloc_trim + #define nedmalloc_stats malloc_stats + #define nedmalloc_footprint malloc_footprint + #define nedindependent_calloc independent_calloc + #define nedindependent_comalloc independent_comalloc + #ifdef __GNUC__ + #define nedmemsize malloc_usable_size + #endif + #endif +#endif + +/*! \def ENABLE_TOLERANT_NEDMALLOC +\brief Defines whether nedalloc should check for blocks from the system allocator. + +ENABLE_TOLERANT_NEDMALLOC is automatically turned on if REPLACE_SYSTEM_ALLOCATOR +is set or the Windows DLL is being built. This causes nedmalloc to detect when a +system allocator block is passed to it and to handle it appropriately. Note that +without USE_MAGIC_HEADERS there is a very tiny chance that nedmalloc will segfault +on non-Windows builds (it uses Win32 SEH to trap segfaults on Windows and there +is no comparable system on POSIX). +*/ + +#if defined(__cplusplus) +extern "C" { +#endif +/*! \brief Returns information about a memory pool */ +struct nedmallinfo { + size_t arena; /*!< non-mmapped space allocated from system */ + size_t ordblks; /*!< number of free chunks */ + size_t smblks; /*!< always 0 */ + size_t hblks; /*!< always 0 */ + size_t hblkhd; /*!< space in mmapped regions */ + size_t usmblks; /*!< maximum total allocated space */ + size_t fsmblks; /*!< always 0 */ + size_t uordblks; /*!< total allocated space */ + size_t fordblks; /*!< total free space */ + size_t keepcost; /*!< releasable (via malloc_trim) space */ +}; +#if defined(__cplusplus) +} +#endif + +/*! \def NO_NED_NAMESPACE +\brief Defines the use of the nedalloc namespace for the C functions. + +NO_NED_NAMESPACE prevents the functions from being defined in the nedalloc +namespace when in C++ (uses the global C namespace instead). +*/ +/*! \def THROWSPEC +\brief Defined to throw() or noexcept(true) (as in, throws nothing) under C++, otherwise nothing. +*/ +#if defined(__cplusplus) + #if !defined(NO_NED_NAMESPACE) +namespace nedalloc { + #else +extern "C" { + #endif + #if __cplusplus > 199711L + #define THROWSPEC noexcept(true) + #else + #define THROWSPEC throw() + #endif +#else + #define THROWSPEC +#endif + +/* These are the global functions */ + +/*! \defgroup v2malloc The v2 malloc API + +\warning This API is being completely retired in v1.10 beta 2 and replaced with the API +being developed for inclusion into the C1X programming language standard + +For the v1.10 release which was generously sponsored by +Applied Research Associates (USA), +a new general purpose allocator API was designed which is intended to remedy many +of the long standing problems and inefficiencies introduced by the ISO C allocator +API. Internally nedalloc's implementations of nedmalloc(), nedcalloc(), nedmemalign() +and nedrealloc() call into this API: + +
    +
  • void* malloc2(size_t bytes, size_t alignment, unsigned flags)
    • +
  • void* realloc2(void* mem, size_t bytes, size_t alignment, unsigned + flags)
    • +
  • void free2(void* mem, unsigned flags)
    • +
+ +If nedmalloc.h is being included by C++ code, the alignment and flags parameters +default to zero which makes the new API identical to the old API (roll on the introduction +of default parameters to C!). The ability for realloc2() to take an alignment is +particularly useful for extending aligned vector arrays such as SSE/AVX +vector arrays. Hitherto SSE/AVX vector code had to jump through all sorts of unpleasant +hoops to maintain alignment :(. + +Note that using any of these flags other than M2_ZERO_MEMORY or any alignment +other than zero inhibits the threadcache. + +Currently MREMAP support is limited to Linux and Windows. Patches implementing +support for other platforms are welcome. + +On Linux the non portable mremap() kernel function is currently used, so in fact +the M2_RESERVE_* options are currently ignored. + +On Windows, there are two different MREMAP implementations which are chosen according +to whether a 32 bit or a 64 bit build is being performed. The 32 bit implementation +is based on Win32 file mappings where it reserves the address space within the Windows +VM system, so you can safely specify silly reservation quantities like 2Gb per block +and not exhaust local process address space. Note however that on x86 this costs +2Kb (1Kb if PAE is off) of kernel memory per Mb reserved, and as kernel memory has +a hard limit of 447Mb on x86 you will find the total address space reservable in +the system is limited. On x64, or if you define WIN32_DIRECT_USE_FILE_MAPPINGS=0 +on x86, a much faster implementation of using VirtualAlloc(MEM_RESERVE) to directly +reserve the address space is used. + +When using M2_RESERVE_* with realloc2(), the setting only takes effect when the +mmapped chunk has exceeded its reservation space and a new reservation space needs +to be created. +*/ + +#ifndef M2_FLAGS_DEFINED +#define M2_FLAGS_DEFINED + +/*! \def M2_ZERO_MEMORY +\ingroup v2malloc +\brief Sets the contents of the allocated block (or any increase in the allocated +block) to zero. + +Note that this zeroes only the increase from what dlmalloc thinks +the chunk's size is, so if you realloc2() a block which wasn't allocated using +malloc2() using this flag then you may have garbage just before the newly extended +space. + +\li Rationale: Memory returned by the system is guaranteed to +be zero on most platforms, and hence dlmalloc knows when it can skip zeroing +memory. This improves performance. +*/ +#define M2_ZERO_MEMORY (1<<0) + +/*! \def M2_PREVENT_MOVE +\ingroup v2malloc +\brief Cause realloc2() to attempt to extend a block in place, but to never move +it. + +\li Rationale: C++ makes almost no use of realloc(), even for +contiguous arrays such as std::vector<> because most C++ objects cannot be relocated +in memory without a copy or rvalue construction (though some clever STL implementations +specialise for Plain Old Data (POD) types, and use realloc() then and only then). +This flag allows C++ containers to speculatively try to extend in place, thus +improving performance especially for large allocations which will use +mmap(). +*/ +#define M2_PREVENT_MOVE (1<<1) + +/*! \def M2_ALWAYS_MMAP +\ingroup v2malloc +\brief Always allocate as though mmap_threshold were being exceeded. + +In the case of realloc2(), note that setting this bit will not necessarily mmap a chunk +which isn't already mmapped, but it will force a mmapped chunk if new memory +needs allocating. + +\li Rationale: If you know that an array you are allocating +is going to be repeatedly extended up into the hundred of kilobytes range, then +you can avoid the constant memory copying into larger blocks by specifying this +flag at the beginning along with one of the M2_RESERVE_* flags below. This can +greatly improve performance for large arrays. +*/ +#define M2_ALWAYS_MMAP (1<<2) +#define M2_RESERVED1 (1<<3) +#define M2_RESERVED2 (1<<4) +#define M2_RESERVED3 (1<<5) +#define M2_RESERVED4 (1<<6) +#define M2_RESERVED5 (1<<7) +#define M2_RESERVE_ISMULTIPLIER (1<<15) +/* 7 bits is given to the address reservation specifier. +This lets you set a multiplier (bit 15 set) or a 1<< shift value. +*/ +#define M2_RESERVE_MASK 0x00007f00 + +/*! \def M2_RESERVE_MULT(n) +\ingroup v2malloc +\brief Reserve n times as much address space such that mmapped realloc2(size <= +n * original size) avoids memory copying and hence is much faster. +*/ +#define M2_RESERVE_MULT(n) (M2_RESERVE_ISMULTIPLIER|(((n)<<8)&M2_RESERVE_MASK)) + +/*! \def M2_RESERVE_SHIFT(n) +\ingroup v2malloc +\brief Reserve (1<0.01%) but real chance of segfault on non-Windows +systems when passing non-nedmalloc blocks if you don't use USE_MAGIC_HEADERS. +*/ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR size_t nedblksize(int *RESTRICT isforeign, void *RESTRICT mem, unsigned flags=0) THROWSPEC; +#else +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR size_t nedblksize(int *RESTRICT isforeign, void *RESTRICT mem, unsigned flags) THROWSPEC; +#endif +/*! \brief Identical to nedblksize() except without the isforeign */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR size_t nedmemsize(void *RESTRICT mem) THROWSPEC; + +/*! \brief Equivalent to nedpsetvalue((nedpool *) 0, v) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR void nedsetvalue(void *v) THROWSPEC; + +/*! \brief Equivalent to nedpmalloc2((nedpool *) 0, size, 0, 0) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedmalloc(size_t size) THROWSPEC; +/*! \brief Equivalent to nedpmalloc2((nedpool *) 0, no*size, 0, M2_ZERO_MEMORY) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedcalloc(size_t no, size_t size) THROWSPEC; +/*! \brief Equivalent to nedprealloc2((nedpool *) 0, size, mem, size, 0, M2_RESERVE_MULT(8)) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedrealloc(void *mem, size_t size) THROWSPEC; +/*! \brief Equivalent to nedpfree2((nedpool *) 0, mem, 0) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR void nedfree(void *mem) THROWSPEC; +/*! \brief Equivalent to nedpmalloc2((nedpool *) 0, size, alignment, 0) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedmemalign(size_t alignment, size_t bytes) THROWSPEC; + +#if defined(__cplusplus) +/*! \ingroup v2malloc +\brief Equivalent to nedpmalloc2((nedpool *) 0, size, alignment, flags) */ +NEDMALLOCDEPRECATED NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedmalloc2(size_t size, size_t alignment=0, unsigned flags=0) THROWSPEC; +/*! \ingroup v2malloc +\brief Equivalent to nedprealloc2((nedpool *) 0, mem, size, alignment, flags) */ +NEDMALLOCDEPRECATED NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedrealloc2(void *mem, size_t size, size_t alignment=0, unsigned flags=0) THROWSPEC; +/*! \ingroup v2malloc +\brief Equivalent to nedpfree2((nedpool *) 0, mem, flags) */ +NEDMALLOCDEPRECATED NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR void nedfree2(void *mem, unsigned flags=0) THROWSPEC; +#else +NEDMALLOCDEPRECATED NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedmalloc2(size_t size, size_t alignment, unsigned flags) THROWSPEC; +NEDMALLOCDEPRECATED NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedrealloc2(void *mem, size_t size, size_t alignment, unsigned flags) THROWSPEC; +NEDMALLOCDEPRECATED NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR void nedfree2(void *mem, unsigned flags) THROWSPEC; +#endif + +/*! \brief Equivalent to nedpmallinfo((nedpool *) 0) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR struct nedmallinfo nedmallinfo(void) THROWSPEC; +/*! \brief Equivalent to nedpmallopt((nedpool *) 0, parno, value) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR int nedmallopt(int parno, int value) THROWSPEC; +/*! \brief Returns the internal allocation granularity and the magic header XOR used for internal consistency checks. */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR void* nedmalloc_internals(size_t *granularity, size_t *magic) THROWSPEC; +/*! \brief Equivalent to nedpmalloc_trim((nedpool *) 0, pad) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR int nedmalloc_trim(size_t pad) THROWSPEC; +/*! \brief Equivalent to nedpmalloc_stats((nedpool *) 0) */ +NEDMALLOCEXTSPEC void nedmalloc_stats(void) THROWSPEC; +/*! \brief Equivalent to nedpmalloc_footprint((nedpool *) 0) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR size_t nedmalloc_footprint(void) THROWSPEC; +/*! \brief Equivalent to nedpindependent_calloc((nedpool *) 0, elemsno, elemsize, chunks) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void **nedindependent_calloc(size_t elemsno, size_t elemsize, void **chunks) THROWSPEC; +/*! \brief Equivalent to nedpindependent_comalloc((nedpool *) 0, elems, sizes, chunks) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void **nedindependent_comalloc(size_t elems, size_t *sizes, void **chunks) THROWSPEC; + +/*! \brief Destroys the system memory pool used by the functions above. + +Useful for when you have nedmalloc in a DLL you're about to unload. +If you call ANY nedmalloc functions after calling this you will +get a fatal exception! +*/ +NEDMALLOCEXTSPEC void neddestroysyspool() THROWSPEC; + +/*! \brief A nedpool type */ +struct nedpool_t; +/*! \brief A nedpool type */ +typedef struct nedpool_t nedpool; + +/*! \brief Creates a memory pool for use with the nedp* functions below. + +Capacity is how much to allocate immediately (if you know you'll be allocating a lot +of memory very soon) which you can leave at zero. Threads specifies how many threads +will *normally* be accessing the pool concurrently. Setting this to zero means it +extends on demand, but be careful of this as it can rapidly consume system resources +where bursts of concurrent threads use a pool at once. +*/ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR nedpool *nedcreatepool(size_t capacity, int threads) THROWSPEC; + +/*! \brief Destroys a memory pool previously created by nedcreatepool(). +*/ +NEDMALLOCEXTSPEC void neddestroypool(nedpool *p) THROWSPEC; + +/*! \brief Returns a zero terminated snapshot of threadpools existing at the time of call. + +Call nedfree() on the returned list when you are done. Returns zero if there is only the +system pool in existence. +*/ +NEDMALLOCEXTSPEC nedpool **nedpoollist() THROWSPEC; + +/*! \brief Sets a value to be associated with a pool. + +You can retrieve this value by passing any memory block allocated from that pool. +*/ +NEDMALLOCEXTSPEC void nedpsetvalue(nedpool *p, void *v) THROWSPEC; + +/*! \brief Gets a previously set value using nedpsetvalue() or zero if memory is unknown. + +Optionally can also retrieve pool. You can detect an unknown block by the return +being zero and *p being unmodifed. +*/ +NEDMALLOCEXTSPEC void *nedgetvalue(nedpool **p, void *mem) THROWSPEC; + +/*! \brief Trims the thread cache for the calling thread, returning any existing cache +data to the central pool. + +Remember to ALWAYS call with zero if you used the system pool. Setting disable to +non-zero replicates neddisablethreadcache(). +*/ +NEDMALLOCEXTSPEC void nedtrimthreadcache(nedpool *p, int disable) THROWSPEC; + +/*! \brief Disables the thread cache for the calling thread, returning any existing cache +data to the central pool. + +Remember to ALWAYS call with zero if you used the system pool. +*/ +NEDMALLOCEXTSPEC void neddisablethreadcache(nedpool *p) THROWSPEC; + +/*! \brief Releases all memory in all threadcaches in the pool, and writes all +accumulated memory operations to the log if enabled. + +You can pass zero for filepath to use the compiled default, or else a char[MAX_PATH] +containing the path you wish to use for the log file. The log file is always +appended to if it already exists. After writing the logs, the logging ability +is disabled for that pool. + +\warning Do NOT call this if the pool is in use - this call is NOT threadsafe. +*/ +NEDMALLOCEXTSPEC size_t nedflushlogs(nedpool *p, char *filepath) THROWSPEC; + + +/*! \brief Equivalent to nedpmalloc2(p, size, 0, 0) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedpmalloc(nedpool *p, size_t size) THROWSPEC; +/*! \brief Equivalent to nedpmalloc2(p, no*size, 0, M2_ZERO_MEMORY) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedpcalloc(nedpool *p, size_t no, size_t size) THROWSPEC; +/*! \brief Equivalent to nedprealloc2(p, mem, size, 0, M2_RESERVE_MULT(8)) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedprealloc(nedpool *p, void *mem, size_t size) THROWSPEC; +/*! \brief Equivalent to nedpfree2(p, mem, 0) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR void nedpfree(nedpool *p, void *mem) THROWSPEC; +/*! \brief Equivalent to nedpmalloc2(p, bytes, alignment, 0) */ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedpmemalign(nedpool *p, size_t alignment, size_t bytes) THROWSPEC; +#if defined(__cplusplus) +/*! \ingroup v2malloc +\brief Allocates a block of memory sized \em size from pool \em p, aligned to \em alignment and according to the flags \em flags. +*/ +NEDMALLOCDEPRECATED NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedpmalloc2(nedpool *p, size_t size, size_t alignment=0, unsigned flags=0) THROWSPEC; +/*! \ingroup v2malloc +\brief Resizes the block of memory at \em mem in pool \em p to size \em size, aligned to \em alignment and according to the flags \em flags. +*/ +NEDMALLOCDEPRECATED NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedprealloc2(nedpool *p, void *mem, size_t size, size_t alignment=0, unsigned flags=0) THROWSPEC; +/*! \brief Frees the block \em mem from the pool \em p according to flags \em flags. */ +NEDMALLOCDEPRECATED NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR void nedpfree2(nedpool *p, void *mem, unsigned flags=0) THROWSPEC; +#else +NEDMALLOCDEPRECATED NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedpmalloc2(nedpool *p, size_t size, size_t alignment, unsigned flags) THROWSPEC; +NEDMALLOCDEPRECATED NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void * nedprealloc2(nedpool *p, void *mem, size_t size, size_t alignment, unsigned flags) THROWSPEC; +NEDMALLOCDEPRECATED NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR void nedpfree2(nedpool *p, void *mem, unsigned flags) THROWSPEC; +#endif +/*! \brief Returns information about the memory pool */ +NEDMALLOCEXTSPEC struct nedmallinfo nedpmallinfo(nedpool *p) THROWSPEC; +/*! \brief Changes the operational parameters of the memory pool */ +NEDMALLOCEXTSPEC int nedpmallopt(nedpool *p, int parno, int value) THROWSPEC; +/*! \brief Tries to release as much free memory back to the system as possible, leaving \em pad remaining per threadpool. */ +NEDMALLOCEXTSPEC int nedpmalloc_trim(nedpool *p, size_t pad) THROWSPEC; +/*! \brief Prints some operational statistics to stdout. */ +NEDMALLOCEXTSPEC void nedpmalloc_stats(nedpool *p) THROWSPEC; +/*! \brief Returns how much memory is currently in use by the memory pool */ +NEDMALLOCEXTSPEC size_t nedpmalloc_footprint(nedpool *p) THROWSPEC; +/*! \brief Returns a series of guaranteed consecutive cleared memory allocations. + + 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; + } +*/ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void **nedpindependent_calloc(nedpool *p, size_t elemsno, size_t elemsize, void **chunks) THROWSPEC; +/*! \brief Returns a series of guaranteed consecutive allocations. + + 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. +*/ +NEDMALLOCEXTSPEC NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void **nedpindependent_comalloc(nedpool *p, size_t elems, size_t *sizes, void **chunks) THROWSPEC; + +#if defined(__cplusplus) +} /* namespace or extern "C" */ +#include +#include +#ifdef HAVE_CPP0XTYPETRAITS +#include +#endif + +// Touch into existence for future platforms +namespace std { namespace tr1 { } } + +/*! \defgroup C++ C++ language support + +Thanks to the generous support of Applied Research Associates (USA), nedalloc has extensive +C++ language support which uses C++ metaprogramming techniques to provide a policy driven +STL container reimplementor. The metaprogramming silently overrides or replaces the STL implementation +on your system (MSVC and GCC are the two currently supported) to \b substantially improve +the performance of STL containers by making use of nedalloc's additional features. + +Sounds difficult to use? Not really. Simply do this: +\code +using namespace nedalloc; +typedef nedallocatorise::policy, + nedpolicy::mmap<>::policy, + nedpolicy::reserveN<26>::policy // 1<<26 = 64Mb. 10,000,000 * sizeof(unsigned int) = 38Mb. +>::value myvectortype; +myvectortype a; +for(int n=0; n<10000000; n++) + a.push_back(n); +\endcode + +The metaprogramming requires a new C++ compiler (> year 2008), and it will readily make use +of a C++0x compiler where it will use rvalue referencing, variadic templates, type traits and more. +Visual Studio 2008 or later is sufficent, as is GCC v4.4 or later. + +nedalloc's metaprogramming is designed to be extensible, so the rest of this page is intended for those +wishing to customise the metaprogramming. If you simply wish to know how to use the +nedalloc::nedallocator STL allocator or the nedalloc::nedallocatorise STL reimplementor, please refer +to test.cpp which gives several examples of usage. + +

Extending the metaprogramming:

+A nedallocator policy looks as follows: +\code +namespace nedpolicy { + template struct sizedalign + { + template class policy : public Base + { + template friend class nedallocatorI::baseimplementation; + protected: + size_t policy_alignment(size_t bytes) const + { + return (bytes < size) ? alignment : 0; + } + }; + }; +} +\endcode +The policy above implements a size based alignment, so if the block being allocated is +less than \em size then it causes \em alignment to be used, otherwise it does not align. +The sizedalign struct is merely a template parameter encapsulator used to capture +additional parameters, so the real policy is in fact the class policy held within in. +If you did not need to specify any additional parameters e.g. if you were defining +policy_nedpool(), then you would directly define a policy returning your nedpool and pass +it directly to nedallocator<>. + +The primary policy functions which are intended to be overridden are listed in +nedalloc::nedallocatorI::baseimplementation in nedmalloc.h and are prefixed by "policy_". +However, there is absolutely no reason why the meatier functions such as +nedalloc::nedallocatorI::baseimplementation::allocate() cannot be overriden, and indeed +some of the policies defined in nedmalloc.h do just that. + +Policy composition is handled by a dedicated recursive variadic template called +nedalloc::nedallocatorI::policycompositor. If you have \em really specialised needs, you +can partially specialise this class to make it do all sorts of interesting things - hence +its separation into its own class. +*/ + +/*! \brief The nedalloc namespace */ +namespace nedalloc { + +/*! \def NEDSTATIC_ASSERT(expr, msg) +\brief Generates a static assertion if (expr)==0 at compile time. + +Make SURE your message contains no spaces or anything else which would make it an invalid +variable name. +*/ +#ifndef HAVE_CPP0XSTATICASSERT +template struct StaticAssert; +template<> struct StaticAssert +{ + StaticAssert() { } +}; +#define NEDSTATIC_ASSERT(expr, msg) \ + nedalloc::StaticAssert<(expr)!=0> ERROR_##msg +#else +#define NEDSTATIC_ASSERT(expr, msg) static_assert((expr)!=0, #msg ) +#endif + +/*! \brief The policy namespace in which all nedallocator policies live. */ +namespace nedpolicy { + /*! \class empty + \ingroup C++ + \brief An empty policy which does nothing. + */ + template class empty : public Base + { + }; +} + +/*! \brief The implementation namespace where the internals live. */ +namespace nedallocatorI +{ + using namespace std; + using namespace tr1; + + /* Roll on variadic templates is all I can say! */ +#ifdef HAVE_CPP0XVARIADICTEMPLATES + template class... policies> class policycompositor + { + public: + typedef policies value; + }; +#else + template class A=nedpolicy::empty, + template class B=nedpolicy::empty, + template class C=nedpolicy::empty, + template class D=nedpolicy::empty, + template class E=nedpolicy::empty, + template class F=nedpolicy::empty, + template class G=nedpolicy::empty, + template class H=nedpolicy::empty, + template class I=nedpolicy::empty, + template class J=nedpolicy::empty, + template class K=nedpolicy::empty, + template class L=nedpolicy::empty, + template class M=nedpolicy::empty, + template class N=nedpolicy::empty, + template class O=nedpolicy::empty + > class policycompositor + { + typedef policycompositor temp; + public: + typedef A value; + }; +#endif + template class policycompositor + { + public: + typedef Impl value; + }; +} + +template class... policies +#else + template class policy1=nedpolicy::empty, + template class policy2=nedpolicy::empty, + template class policy3=nedpolicy::empty, + template class policy4=nedpolicy::empty, + template class policy5=nedpolicy::empty, + template class policy6=nedpolicy::empty, + template class policy7=nedpolicy::empty, + template class policy8=nedpolicy::empty, + template class policy9=nedpolicy::empty, + template class policy10=nedpolicy::empty, + template class policy11=nedpolicy::empty, + template class policy12=nedpolicy::empty, + template class policy13=nedpolicy::empty, + template class policy14=nedpolicy::empty, + template class policy15=nedpolicy::empty +#endif +> class nedallocator; + +namespace nedallocatorI +{ + /*! \brief The base implementation class */ + template class baseimplementation + { + //NEDSTATIC_ASSERT(false, Bad_policies_specified); + }; + /*! \brief The base implementation class */ + template class... policies +#else + template class policy1, + template class policy2, + template class policy3, + template class policy4, + template class policy5, + template class policy6, + template class policy7, + template class policy8, + template class policy9, + template class policy10, + template class policy11, + template class policy12, + template class policy13, + template class policy14, + template class policy15 +#endif + > class baseimplementation > + { + protected: + //! \brief The most derived nedallocator implementation type + typedef nedallocator implementationType; + //! \brief Returns a this for the most derived nedallocator implementation type + implementationType *_this() { return static_cast(this); } + //! \brief Returns a this for the most derived nedallocator implementation type + const implementationType *_this() const { return static_cast(this); } + //! \brief Specifies the nedpool to use. Defaults to zero (the system pool). + nedpool *policy_nedpool(size_t bytes) const + { + return 0; + } + //! \brief Specifies the granularity to use. Defaults to \em bytes (no granularity). + size_t policy_granularity(size_t bytes) const + { + return bytes; + } + //! \brief Specifies the alignment to use. Defaults to zero (no alignment). + size_t policy_alignment(size_t bytes) const + { + return 0; + } + //! \brief Specifies the flags to use. Defaults to zero (no flags). + unsigned policy_flags(size_t bytes) const + { + return 0; + } + //! \brief Specifies what to do when the allocation fails. Defaults to throwing std::bad_alloc. + void policy_throwbadalloc(size_t bytes) const + { + throw std::bad_alloc(); + } + //! \brief Specifies if the type is POD. Is std::is_pod::value on C++0x compilers, otherwise false. + static const bool policy_typeIsPOD= +#ifdef HAVE_CPP0XTYPETRAITS + is_pod::value; +#else + false; +#endif + public: + typedef T *pointer; + typedef const T *const_pointer; + typedef T &reference; + typedef const T &const_reference; + typedef T value_type; + typedef size_t size_type; + typedef ptrdiff_t difference_type; + T *address(T &r) const { return &r; } + const T *address(const T &s) const { return &s; } + size_t max_size() const { return (static_cast(0) - static_cast(1)) / sizeof(T); } + bool operator!=(const baseimplementation &other) const { return !(*this == other); } + bool operator==(const baseimplementation &other) const { return true; } + + void construct(T *const p, const T &t) const { + void *const _p = static_cast(p); + new (_p) T(t); + } + void destroy(T *const p) const { + p->~T(); + } + baseimplementation() { } + baseimplementation(const baseimplementation &) { } +#ifdef HAVE_CPP0XRVALUEREFS + baseimplementation(baseimplementation &&) { } +#endif + template struct rebind { + typedef nedallocator other; + }; + template baseimplementation(const nedallocator &) { } + + T *allocate(const size_t n) const { + // Leave these spelled out to aid debugging + const size_t t_size = sizeof(T); + size_t size = _this()->policy_granularity(n*t_size); + nedpool *pool = _this()->policy_nedpool(size); + size_t alignment = _this()->policy_alignment(size); + unsigned flags = _this()->policy_flags(size); + void *ptr = nedpmalloc2(pool, size, alignment, flags); + if(!ptr) + _this()->policy_throwbadalloc(size); + return static_cast(ptr); + } + void deallocate(T *p, const size_t n) const { + nedpfree(0/*not needed*/, p); + } + template T *allocate(const size_t n, const U * /* hint */) const { + return allocate(n); + } + private: + baseimplementation &operator=(const baseimplementation &); + }; + +} + +namespace nedpolicy +{ + /*! \class granulate + \ingroup C++ + \brief A policy setting the granularity of the allocated memory. + + Memory is sized according to (size+granularity-1) & ~(granularity-1). + In other words, granularity \b must be a power of two. + */ + template struct granulate + { + template class policy : public Base + { + template friend class nedallocatorI::baseimplementation; + protected: + size_t policy_granularity(size_t bytes) const + { + return (bytes+granularity-1) & ~(granularity-1); + } + }; + }; + /*! \class align + \ingroup C++ + \brief A policy setting the alignment of the allocated memory. + */ + template struct align + { + template class policy : public Base + { + template friend class nedallocatorI::baseimplementation; + protected: + size_t policy_alignment(size_t bytes) const + { + return alignment; + } + }; + }; + /*! \class zero + \ingroup C++ + \brief A policy causing the zeroing of the allocated memory. + */ + template struct zero + { + template class policy : public Base + { + template friend class nedallocatorI::baseimplementation; + protected: + unsigned policy_flags(size_t bytes) const + { + return dozero ? Base::policy_flags(bytes)|M2_ZERO_MEMORY : Base::policy_flags(bytes); + } + }; + }; + /*! \class preventmove + \ingroup C++ + \brief A policy preventing the moving of the allocated memory. + */ + template struct preventmove + { + template class policy : public Base + { + template friend class nedallocatorI::baseimplementation; + protected: + unsigned policy_flags(size_t bytes) const + { + return doprevent ? Base::policy_flags(bytes)|M2_PREVENT_MOVE : Base::policy_flags(bytes); + } + }; + }; + /*! \class mmap + \ingroup C++ + \brief A policy causing the mmapping of the allocated memory. + */ + template struct mmap + { + template class policy : public Base + { + template friend class nedallocatorI::baseimplementation; + protected: + unsigned policy_flags(size_t bytes) const + { + return dommap ? Base::policy_flags(bytes)|M2_ALWAYS_MMAP : Base::policy_flags(bytes); + } + }; + }; + /*! \class reserveX + \ingroup C++ + \brief A policy causing the address reservation of X times the allocated memory. + */ + template struct reserveX + { + template class policy : public Base + { + template friend class nedallocatorI::baseimplementation; + protected: + unsigned policy_flags(size_t bytes) const + { + return Base::policy_flags(bytes)|M2_RESERVE_MULT(X); + } + }; + }; + /*! \class reserveN + \ingroup C++ + \brief A policy causing the address reservation of (1< struct reserveN + { + template class policy : public Base + { + template friend class nedallocatorI::baseimplementation; + protected: + unsigned policy_flags(size_t bytes) const + { + return Base::policy_flags(bytes)|M2_RESERVE_SHIFT(N); + } + }; + }; + /*! \class badalloc + \ingroup C++ + \brief A policy specifying what to throw when an allocation failure occurs. + + A type specialisation exists for badalloc which is equivalent to new(nothrow) + i.e. return zero and don't throw anything. + */ + template struct badalloc + { + template class policy : public Base + { + template friend class nedallocatorI::baseimplementation; + protected: + void policy_throwbadalloc(size_t bytes) const + { + throw T(); + } + }; + }; + template<> struct badalloc + { + template class policy : public Base + { + template friend class nedallocatorI::baseimplementation; + protected: + void policy_throwbadalloc(size_t bytes) const + { + } + }; + }; + /*! \class typeIsPOD + \ingroup C++ + \brief A policy forcing the treatment of the type as Plain Old Data (POD) + + On C++0x compilers, the <type_traits> is_pod::value is used by default. + However, for earlier compilers and for types where is_pod<>::value returns false + even though the type actually is POD (for example, if you declare a + constructor you lose PODness even if the data contents are still POD), you can + force PODness one way or another. When treated as POD, memcpy() is used instead + of copy construction and realloc() is permitted to move the memory contents when + resizing. + */ + template struct typeIsPOD + { + template class policy : public Base + { + template friend class nedallocatorI::baseimplementation; + protected: + static const bool policy_typeIsPOD=ispod; + }; + }; +} + +/*! \class nedallocator +\ingroup C++ +\brief A policy driven STL allocator which uses nedmalloc + +One of the lesser known features of STL container classes is their ability to take +an allocator implementation class, so where you had std::vector you can now +have std::vector > such that +std::vector<> will now use nedalloc as the policy specifies. + +You almost certainly don't want to use this directly except in the naive +case. See nedalloc::nedallocatorise to see what I mean. +*/ +template class... policies +#else + template class policy1, + template class policy2, + template class policy3, + template class policy4, + template class policy5, + template class policy6, + template class policy7, + template class policy8, + template class policy9, + template class policy10, + template class policy11, + template class policy12, + template class policy13, + template class policy14, + template class policy15 +#endif +> class nedallocator : public nedallocatorI::policycompositor< +#ifdef HAVE_CPP0XVARIADICTEMPLATES + nedallocatorI::baseimplementation >, + policies... +#else + nedallocatorI::baseimplementation >, + policy1, policy2, policy3, policy4, policy5, + policy6, policy7, policy8, policy9, policy10, + policy11, policy12, policy13, policy14, policy15 +#endif +>::value +{ + typedef typename nedallocatorI::policycompositor< +#ifdef HAVE_CPP0XVARIADICTEMPLATES + nedallocatorI::baseimplementation >, + policies... +#else + nedallocatorI::baseimplementation >, + policy1, policy2, policy3, policy4, policy5, + policy6, policy7, policy8, policy9, policy10, + policy11, policy12, policy13, policy14, policy15 +#endif + >::value Base; +public: + nedallocator() { } + nedallocator(const nedallocator &o) : Base(o) { } +#ifdef HAVE_CPP0XRVALUEREFS + nedallocator(nedallocator &&o) : Base(std::move(o)) { } +#endif + /* This templated constructor and rebind() are used by MSVC's secure iterator checker. + I think it's best to not copy state even though it may break policies which store data. */ + template nedallocator(const nedallocator &o) { } +#ifdef HAVE_CPP0XRVALUEREFS + template nedallocator(nedallocator &&o) { } +#endif + + template struct rebind { + typedef nedallocator other; + }; +}; + +namespace nedallocatorI { + // Holds a static allocator instance shared by anything allocating from allocator + template struct StaticAllocator + { + static allocator &get() + { + static allocator a; + return a; + } + }; + // RAII holder for a Newed object + template struct PtrHolder + { + T *mem; + PtrHolder(T *_mem) : mem(_mem) { } + ~PtrHolder() + { + if(mem) + { + allocator &a=nedallocatorI::StaticAllocator::get(); + a.deallocate(mem, sizeof(T)); + mem=0; + } + } + T *release() { T *ret=mem; mem=0; return ret; } + T *operator *() { return mem; } + const T *operator *() const { return mem; } + }; +} +/*! \brief Allocates the memory for an instance of object \em T and constructs it. + +If an exception is thrown during construction, the memory is freed before +rethrowing the exception. + +Usage is very simple: +\code + SSEVectorType *foo1=New(4, 5, 6, 7); +\endcode +*/ +#ifdef HAVE_CPP0XVARIADICTEMPLATES +template, typename... Parameters> inline T *New(const Parameters&... parameters) +#else +template inline T *New() +#endif +{ + allocator &a=nedallocatorI::StaticAllocator::get(); + nedallocatorI::PtrHolder ret(a.allocate(sizeof(T))); + if(*ret) + { +#ifdef HAVE_CPP0XVARIADICTEMPLATES + new((void *) *ret) T(parameters...); +#else + new((void *) *ret) T; +#endif + } + return ret.release(); +} +#ifndef HAVE_CPP0XVARIADICTEMPLATES +// Extremely annoying not to have default template arguments for functions pre-C++0x +template inline T *New() +{ + return New >(); +} +// Also, it's painful to replicate function overloads :( +#define NEDMALLOC_NEWIMPL \ +template inline T *New(NEDMALLOC_NEWIMPLPARSDEFS) \ +{ \ + allocator &a=nedallocatorI::StaticAllocator::get(); \ + nedallocatorI::PtrHolder ret(a.allocate(sizeof(T))); \ + if(*ret) \ + { \ + new((void *) *ret) T(NEDMALLOC_NEWIMPLPARS); \ + } \ + return ret.release(); \ +} \ +template inline T *New(NEDMALLOC_NEWIMPLPARSDEFS)\ +{ \ + return New >(NEDMALLOC_NEWIMPLPARS); \ +} +#define NEDMALLOC_NEWIMPLTYPES typename P1 +#define NEDMALLOC_NEWIMPLPARSDEFS const P1 &p1 +#define NEDMALLOC_NEWIMPLPARS p1 +NEDMALLOC_NEWIMPL +#undef NEDMALLOC_NEWIMPLTYPES +#undef NEDMALLOC_NEWIMPLPARSDEFS +#undef NEDMALLOC_NEWIMPLPARS + +#define NEDMALLOC_NEWIMPLTYPES typename P1, typename P2 +#define NEDMALLOC_NEWIMPLPARSDEFS const P1 &p1, const P2 &p2 +#define NEDMALLOC_NEWIMPLPARS p1, p2 +NEDMALLOC_NEWIMPL +#undef NEDMALLOC_NEWIMPLTYPES +#undef NEDMALLOC_NEWIMPLPARSDEFS +#undef NEDMALLOC_NEWIMPLPARS + +#define NEDMALLOC_NEWIMPLTYPES typename P1, typename P2, typename P3 +#define NEDMALLOC_NEWIMPLPARSDEFS const P1 &p1, const P2 &p2, const P3 &p3 +#define NEDMALLOC_NEWIMPLPARS p1, p2, p3 +NEDMALLOC_NEWIMPL +#undef NEDMALLOC_NEWIMPLTYPES +#undef NEDMALLOC_NEWIMPLPARSDEFS +#undef NEDMALLOC_NEWIMPLPARS + +#define NEDMALLOC_NEWIMPLTYPES typename P1, typename P2, typename P3, typename P4 +#define NEDMALLOC_NEWIMPLPARSDEFS const P1 &p1, const P2 &p2, const P3 &p3, const P4 &p4 +#define NEDMALLOC_NEWIMPLPARS p1, p2, p3, p4 +NEDMALLOC_NEWIMPL +#undef NEDMALLOC_NEWIMPLTYPES +#undef NEDMALLOC_NEWIMPLPARSDEFS +#undef NEDMALLOC_NEWIMPLPARS + +#define NEDMALLOC_NEWIMPLTYPES typename P1, typename P2, typename P3, typename P4, typename P5 +#define NEDMALLOC_NEWIMPLPARSDEFS const P1 &p1, const P2 &p2, const P3 &p3, const P4 &p4, const P5 &p5 +#define NEDMALLOC_NEWIMPLPARS p1, p2, p3, p4, p5 +NEDMALLOC_NEWIMPL +#undef NEDMALLOC_NEWIMPLTYPES +#undef NEDMALLOC_NEWIMPLPARSDEFS +#undef NEDMALLOC_NEWIMPLPARS + +#undef NEDMALLOC_NEWIMPL +#endif + +/*! \brief Destructs an instance of object T, and releases the memory used to store it. +*/ +template inline void Delete(const T *_obj) +{ + T *obj=const_cast(_obj); + allocator &a=nedallocatorI::StaticAllocator::get(); + obj->~T(); + a.deallocate(obj, sizeof(T)); +} +template inline void Delete(const T *obj) { Delete >(obj); } + +/*! \class nedallocatorise +\ingroup C++ +\brief Reimplements a given STL container to make full and efficient usage of nedalloc +\param stlcontainer The STL container you wish to reimplement +\param T The type to be contained +\param policies... Any policies you want applied to the allocator + + +This is a clever bit of C++ metaprogramming if I do say so myself! What it does +is to specialise a STL container implementation to make full use of nedalloc's +advanced facilities, so for example if you do: +\code +using namespace nedalloc; +typedef nedallocatorise::policy, + nedpolicy::mmap<>::policy, + nedpolicy::reserveN<26>::policy // 1<<26 = 64Mb. 10,000,000 * sizeof(unsigned int) = 38Mb. +>::value myvectortype; +myvectortype a; +for(int n=0; n<10000000; n++) + a.push_back(n); +\endcode +What happens here is that nedallocatorise reimplements the parts of +std::vector which extend and shrink the actual memory allocation. +Because the typeIsPOD policy is specified, it means that realloc() +rather than realloc(M2_PREVENT_MOVE) can be used. Also, because the +mmap and the reserveN policies are specified, std::vector immediately +reserves 64Mb of address space and forces the immediate use of mmap(). +This allows you to push_back() a lot of data very, very quickly indeed. +You will also find that pop_back() actually reduces the allocation now +(most implementations don't bother ever releasing memory except when +reaching empty or when resize() is called). When mmapped, reserve() +is automatically held at a minimum of <page size>/sizeof(type) though +larger values are respected. + +test.cpp has a benchmark of the speed differences you may realise, plus +an example of usage. +*/ +template class stlcontainer, + typename T, +#ifdef HAVE_CPP0XVARIADICTEMPLATES + template class... policies +#else + template class policy1=nedpolicy::empty, + template class policy2=nedpolicy::empty, + template class policy3=nedpolicy::empty, + template class policy4=nedpolicy::empty, + template class policy5=nedpolicy::empty, + template class policy6=nedpolicy::empty, + template class policy7=nedpolicy::empty, + template class policy8=nedpolicy::empty, + template class policy9=nedpolicy::empty, + template class policy10=nedpolicy::empty, + template class policy11=nedpolicy::empty, + template class policy12=nedpolicy::empty, + template class policy13=nedpolicy::empty, + template class policy14=nedpolicy::empty, + template class policy15=nedpolicy::empty +#endif +> class nedallocatorise +{ +public: + //! The reimplemented STL container type + typedef stlcontainer > value; +}; + +} /* namespace */ +#endif + +/* Some miscellaneous dlmalloc option documentation */ + +#ifdef DOXYGEN_IS_PARSING_ME +/* Just some false defines to keep doxygen happy */ + +#define NEDMALLOC_DEBUG DEBUG +#define ENABLE_LARGE_PAGES undef +#define ENABLE_FAST_HEAP_DETECTION undef +#define REPLACE_SYSTEM_ALLOCATOR undef +#define ENABLE_TOLERANT_NEDMALLOC undef +#define NO_NED_NAMESPACE undef + +/*! \def MALLOC_ALIGNMENT +\brief Defines what alignment normally returned blocks should use. Is 16 bytes on Mac OS X, otherwise 8 bytes. */ +#define MALLOC_ALIGNMENT 8 + +/*! \def USE_LOCKS +\brief Defines the threadsafety of nedalloc + +USE_LOCKS can be 2 if you want to define your own MLOCK_T, INITIAL_LOCK, +ACQUIRE_LOCK, RELEASE_LOCK, TRY_LOCK, IS_LOCKED and NULL_LOCK_INITIALIZER. +*/ +#define USE_LOCKS 1 + +/*! \def DEFAULT_GRANULARITY +\brief Defines the granularity in which to request or free system memory. +*/ +#define DEFAULT_GRANULARITY (2*1024*1024) + +/*! \def DEFAULT_TRIM_THRESHOLD +\brief Defines how much memory must be free before returning it to the system. +*/ +#define DEFAULT_TRIM_THRESHOLD (2*1024*1024) + +/*! \def DEFAULT_MMAP_THRESHOLD +\brief Defines the threshold above which mmap() is used to perform direct allocation. +*/ +#define DEFAULT_MMAP_THRESHOLD (256*1024) + +/*! \def MAX_RELEASE_CHECK_RATE +\brief Defines how many free() ops should occur before checking how much free memory there is. +*/ +#define MAX_RELEASE_CHECK_RATE 4095 + +/*! \def NEDMALLOC_FORCERESERVE +\brief Lets you force address space reservation in the \b standard malloc API + +Note that by default realloc() sets M2_RESERVE_MULT(8) when thunking to realloc2(), +so you probably don't need to override this +*/ +#define NEDMALLOC_FORCERESERVE(p, mem, size) 0 + +/*! \def NEDMALLOC_TESTLOGENTRY +\brief Used to determine whether a given memory operation should be logged. +*/ +#define NEDMALLOC_TESTLOGENTRY(tc, np, type, mspace, size, mem, alignment, flags, returned) ((type)&ENABLE_LOGGING) + +/*! \def NEDMALLOC_STACKBACKTRACEDEPTH +\brief Turns on stack backtracing in the logger. + +You almost certainly want to constrain what gets logged using NEDMALLOC_TESTLOGENTRY +if you turn this on as the sheer volume of data output can make execution very slow. +*/ +#define NEDMALLOC_STACKBACKTRACEDEPTH 0 + +#endif + +#endif diff --git a/polymer/eduke32/build/src/baselayer.c b/polymer/eduke32/build/src/baselayer.c index 26b33721b..7dd4be45a 100644 --- a/polymer/eduke32/build/src/baselayer.c +++ b/polymer/eduke32/build/src/baselayer.c @@ -383,7 +383,7 @@ int32_t baselayer_init(void) void makeasmwriteable(void) { -#if !defined(NOASM) && !defined(GEKKO) +#if !defined(NOASM) && !defined(GEKKO) && !defined(__ANDROID__) extern int32_t dep_begin, dep_end; # if defined _WIN32 DWORD oldprot; diff --git a/polymer/eduke32/build/src/compat.c b/polymer/eduke32/build/src/compat.c index 5887b2be8..2611d78ab 100644 --- a/polymer/eduke32/build/src/compat.c +++ b/polymer/eduke32/build/src/compat.c @@ -59,20 +59,12 @@ int32_t Brand(void) void *Bmalloc(bsize_t size) { -#ifdef NEDMALLOC - return nedmalloc(size); -#else return malloc(size); -#endif } void Bfree(void *ptr) { -#ifdef NEDMALLOC - nedfree(ptr); -#else free(ptr); -#endif } int32_t Bopen(const char *pathname, int32_t flags, uint32_t mode) @@ -170,11 +162,7 @@ bsize_t Bfwrite(const void *ptr, bsize_t size, bsize_t nmemb, BFILE *stream) char *Bstrdup(const char *s) { -#ifdef NEDMALLOC - return nedstrdup(s); -#else return strdup(s); -#endif } char *Bstrcpy(char *dest, const char *src) diff --git a/polymer/eduke32/build/src/engine.c b/polymer/eduke32/build/src/engine.c index f1061946a..f31ed2444 100644 --- a/polymer/eduke32/build/src/engine.c +++ b/polymer/eduke32/build/src/engine.c @@ -36,9 +36,6 @@ #ifdef USE_LIBPNG //# include -# ifdef NEDMALLOC -# define PNG_USER_MEM_SUPPORTED -# endif # include #endif @@ -47,7 +44,7 @@ #include "engine_priv.h" #define CACHEAGETIME 16 -//#define CLASSIC_NONPOW2_YSIZE_WALLS +// #define CLASSIC_NONPOW2_YSIZE_WALLS #define CLASSIC_NONPOW2_YSIZE_SPRITES #if !defined DEBUG_MAIN_ARRAYS @@ -9426,10 +9423,6 @@ int32_t loadboard(char *filename, char flags, vec3_t *dapos, int16_t *daang, int if (!ok) { kclose(fil); return(-2); } } -#ifdef NEDMALLOC - nedtrimthreadcache(0, 0); -#endif - prepare_loadboard(fil, dapos, daang, dacursectnum); kread(fil,&numsectors,2); numsectors = B_LITTLE16(numsectors); @@ -15851,11 +15844,7 @@ static int32_t screencapture_png(const char *filename, char inverseit, const cha return i; /* Create and initialize the png_struct with default error handling. */ -# ifndef NEDMALLOC - png_ptr = png_create_write_struct(PNG_LIBPNG_VER_STRING, NULL, NULL, NULL); -# else png_ptr = png_create_write_struct_2(PNG_LIBPNG_VER_STRING, NULL, NULL, NULL, Bmalloc, Bfree); -# endif if (png_ptr == NULL) { Bfclose(fp); diff --git a/polymer/eduke32/build/src/nedmalloc.c b/polymer/eduke32/build/src/nedmalloc.c deleted file mode 100644 index 68ab11a85..000000000 --- a/polymer/eduke32/build/src/nedmalloc.c +++ /dev/null @@ -1,1603 +0,0 @@ -/* Alternative malloc implementation for multiple threads without -lock contention based on dlmalloc. (C) 2005-2009 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. -*/ - -#include "compat.h" - -#ifdef _MSC_VER -/* Enable full aliasing on MSVC */ -/*#pragma optimize("a", on)*/ -#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 */ -#endif - -/*#define ENABLE_TOLERANT_NEDMALLOC 1*/ -/*#define ENABLE_FAST_HEAP_DETECTION 1*/ -/*#define NEDMALLOC_DEBUG 1*/ - -/*#define FULLSANITYCHECKS*/ -/* 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" -#if defined(_WIN32) -#include -#endif -#if defined(__linux__) || defined(__FreeBSD__) -/* Sadly we can't include as it causes a redefinition error */ -extern size_t malloc_usable_size(void *); -#endif -#if defined(__APPLE__) -/* PK: for malloc_size(): */ -#include -#endif -#if USE_ALLOCATOR==1 -#define MSPACES 1 -#define ONLY_MSPACES 1 -#endif -#define USE_DL_PREFIX 1 -#ifndef USE_LOCKS -#define USE_LOCKS 1 -#endif -#define FOOTERS 1 /* Need to enable footers so frees lock the right mspace */ -#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 */ -#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*/ - - -#include "malloc.c.h" -#ifdef NDEBUG /* Disable assert checking on release builds */ -#undef DEBUG -#elif !NEDMALLOC_DEBUG -#ifdef __GNUC__ -#warning DEBUG is defined so allocator will run with assert checking! Define NDEBUG to run at full speed. -#elif defined(_MSC_VER) -#pragma message(__FILE__ ": WARNING: DEBUG is defined so allocator will run with assert checking! Define NDEBUG to run at full speed.") -#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 -/* 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 -#ifndef THREADCACHEMAXBINS -#ifdef FINEGRAINEDBINS -/* 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 (512*1024) -#endif - - -#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 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 *); - -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 *)= -#ifdef WIN32 - /* This is the MSVCRT equivalent */ - _msize; -#elif defined(__linux__) || defined(__FreeBSD__) - /* This is the glibc/ptmalloc2/dlmalloc equivalent. */ - malloc_usable_size; -#elif defined(__APPLE__) - /* This is the BSD libc equivalent. */ - malloc_size; -#else -#error Cannot tolerate the memory allocator of an unknown system! -#endif - -static FORCEINLINE NEDMALLOCNOALIASATTR NEDMALLOCPTRATTR void *CallMalloc(void *RESTRICT mspace, size_t size, size_t alignment) THROWSPEC -{ - void *RESTRICT ret=0; - size_t _alignment=alignment; -#if USE_MAGIC_HEADERS - size_t *_ret=0; - size+=alignment+3*sizeof(size_t); - _alignment=0; -#endif -#if USE_ALLOCATOR==0 - ret=sysmalloc(size); /* magic headers takes care of alignment */ -#elif USE_ALLOCATOR==1 - ret=_alignment ? mspace_memalign((mstate) mspace, _alignment, size) : mspace_malloc((mstate) mspace, size); -#ifndef ENABLE_FAST_HEAP_DETECTION - if (ret) - { - size_t truesize=chunksize(mem2chunk(ret)); - if (!leastusedaddress || (void *)((mstate) mspace)->least_addrleast_addr; - if (!largestusedblock || truesize>largestusedblock) largestusedblock=(truesize+mparams.page_size) & ~(mparams.page_size-1); - } -#endif -#endif - if (!ret) return 0; -#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 *CallCalloc(void *RESTRICT mspace, size_t size, size_t alignment) THROWSPEC -{ - void *RESTRICT ret=0; -#if USE_MAGIC_HEADERS - size_t *_ret=0; - size+=alignment+3*sizeof(size_t); -#endif -#if USE_ALLOCATOR==0 - ret=syscalloc(1, size); -#elif USE_ALLOCATOR==1 - ret=mspace_calloc((mstate) mspace, 1, size); -#ifndef ENABLE_FAST_HEAP_DETECTION - if (ret) - { - size_t truesize=chunksize(mem2chunk(ret)); - if (!leastusedaddress || (void *)((mstate) mspace)->least_addrleast_addr; - if (!largestusedblock || truesize>largestusedblock) largestusedblock=(truesize+mparams.page_size) & ~(mparams.page_size-1); - } -#endif -#endif - if (!ret) return 0; -#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) 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, 0))) - { -#if defined(DEBUG) - printf("*** nedmalloc frees system allocated block %p\n", mem); -#endif - memcpy(ret, mem, 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_realloc((mstate) mspace, mem, newsize); -#ifndef ENABLE_FAST_HEAP_DETECTION - if (ret) - { - size_t truesize=chunksize(mem2chunk(ret)); - 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 - mspace_free((mstate) mspace, mem); -#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 -#ifdef WIN32 -#ifdef _MSC_VER - __try -#elif defined(__MINGW32__) - __try1 -#endif -#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 (memhead &FLAG4_BIT)) return 0; - /* Reduced uncertainty by 0.5^2 = 25.0% */ - /* size should never exceed largestusedblock */ - if (chunksize(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=(size_t)1<<(SIZE_T_BITSIZE-1)) return 0; - 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) { } -#elif defined(__MINGW32__) - __except1(1) { } -#endif -#endif -#endif -#endif -#endif - } - return 0; -} -NEDMALLOCNOALIASATTR size_t nedblksize(int *RESTRICT isforeign, void *RESTRICT mem) 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 (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 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 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); } - -struct threadcacheblk_t; -typedef struct threadcacheblk_t threadcacheblk; -struct threadcacheblk_t -{ - /* Keep less than 16 bytes on 32 bit systems and 32 bytes on 64 bit systems */ -#ifdef FULLSANITYCHECKS - unsigned int magic; -#endif - unsigned int lastUsed, size; - threadcacheblk *next, *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; - size_t freeInCache; /* How much free space is stored in this cache */ - threadcacheblk *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 *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; - -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 **ptr) THROWSPEC -{ - assert((ptr[0] && ptr[1]) || (!ptr[0] && !ptr[1])); - if (ptr[0] && ptr[1]) - { - assert(nedblksize(ptr[0])>=sizeof(threadcacheblk)); - assert(nedblksize(ptr[1])>=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 **tcbptr=tc->bins; - int n; - for (n=0; n<=THREADCACHEMAXBINS; n++, tcbptr+=2) - { - threadcacheblk *b, *ob=0; - tcsanitycheck(tcbptr); - for (b=tcbptr[0]; b; ob=b, b=b->next) - { - assert(*(unsigned int *) "NEDN"==b->magic); - assert(!ob || ob->next==b); - assert(!ob || b->prev==ob); - } - } -} -#endif - -static NOINLINE void RemoveCacheEntries(nedpool *RESTRICT p, threadcache *RESTRICT tc, unsigned int age) THROWSPEC -{ - UNREFERENCED_PARAMETER(p); -#ifdef FULLSANITYCHECKS - tcfullsanitycheck(tc); -#endif - if (tc->freeInCache) - { - threadcacheblk **tcbptr=tc->bins; - int n; - for (n=0; n<=THREADCACHEMAXBINS; n++, tcbptr+=2) - { - threadcacheblk **tcb=tcbptr+1; /* come from oldest end of list */ - /*tcsanitycheck(tcbptr);*/ - for (; *tcb && tc->frees-(*tcb)->lastUsed>=age;) - { - threadcacheblk *f=*tcb; - size_t blksize=f->size; /*nedblksize(f);*/ - assert(blksize<=nedblksize(0, f)); - 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, 0); - /*tcsanitycheck(tcbptr);*/ - } - } - } -#ifdef FULLSANITYCHECKS - tcfullsanitycheck(tc); -#endif -} -static void DestroyCaches(nedpool *RESTRICT p) THROWSPEC -{ - if (p->caches) - { - threadcache *tc; - int n; - for (n=0; ncaches[n])) - { - tc->frees++; - RemoveCacheEntries(p, tc, 0); - assert(!tc->freeInCache); - 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; ncaches[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 *) CallCalloc(p->m[0], sizeof(threadcache), 0); - 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=0; p->m[end]; end++); - tc->mymspace=abs(tc->threadid) % end; -#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 -{ - UNREFERENCED_PARAMETER(p); - - void *RESTRICT ret=0; - size_t size=*_size, blksize=0; - unsigned int bestsize; - unsigned int idx=size2binidx(size); - threadcacheblk *RESTRICT blk, * *RESTRICT binsptr; -#ifdef FULLSANITYCHECKS - tcfullsanitycheck(tc); -#endif - /* Calculate best fit bin size */ - bestsize=1<<(idx+4); -#ifdef FINEGRAINEDBINS - /* 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 (sizebins[idx*2]; - /* Try to match close, but move up a bin if necessary */ - blk=*binsptr; - if (!blk || blk->sizesize; /*nedblksize(blk);*/ - assert(nedblksize(0, blk)>=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)>=sizeof(threadcacheblk) && nedblksize(0, blk)<=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 -{ - UNREFERENCED_PARAMETER(mymspace); - - 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) THROWSPEC -{ - unsigned int bestsize; - unsigned int idx=size2binidx(size); - threadcacheblk **RESTRICT binsptr, *RESTRICT tck=(threadcacheblk *) mem; - assert(size>=sizeof(threadcacheblk) && size<=THREADCACHEMAX+CHUNK_OVERHEAD); -#ifdef DEBUG - /* Make sure this is a valid memory block */ - assert(nedblksize(0, mem)); -#endif -#ifdef FULLSANITYCHECKS - tcfullsanitycheck(tc); -#endif - /* Calculate best fit bin size */ - bestsize=1<<(idx+4); -#ifdef FINEGRAINEDBINS - /* 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->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; - p->m[0]->extp=p; -#endif - p->threads=(threads<1 || threads>MAXTHREADSINPOOL) ? MAXTHREADSINPOOL : 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 - 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 (endthreads) - { - 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] && endthreads) - 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 **) &p->m[end])=p->m[end]=temp; - 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; -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; - newsize=sizeof(PoolList)+(poollist->size+1)*sizeof(nedpool *); - if (!(newpoollist=(PoolList *) nedprealloc(0, poollist, newsize))) goto badexit; - poollist=newpoollist; - memset(&poollist->list[poollist->size], 0, newsize-((size_t)&poollist->list[poollist->size]-(size_t)&poollist->list[0])); - poollist->size=((newsize-((char *)&poollist->list[0]-(char *)poollist))/sizeof(nedpool *))-1; - 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 - destroy_mspace(p->m[n]); -#endif - p->m[n]=0; - } -#if USE_LOCKS - RELEASE_LOCK(&p->mutex); -#endif - if (TLSFREE(p->mycache)) abort(); - nedpfree(0, p); -#if USE_LOCKS - ACQUIRE_LOCK(&poollistlock); -#endif - assert(poollist); - for (n=0; nlength && poollist->list[n]!=p; n++); - 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 - destroy_mspace(p->m[n]); -#endif - p->m[n]=0; - } - /* Render syspool unusable */ - for (n=0; ncaches[n]=(threadcache *)(size_t)(sizeof(size_t)>4 ? 0xdeadbeefdeadbeefULL : 0xdeadbeefUL); - for (n=0; nm[n]=(mstate)(size_t)(sizeof(size_t)>4 ? 0xdeadbeefdeadbeefULL : 0xdeadbeefUL); - if (TLSFREE(p->mycache)) abort(); -#if USE_LOCKS - RELEASE_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 (size && *sizemycache); - 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 -} - -NEDMALLOCPTRATTR void *nedpmalloc(nedpool *p, size_t size) THROWSPEC -{ - void *ret=0; - threadcache *tc; - int mymspace; - GetThreadCache(&p, &tc, &mymspace, &size); -#if THREADCACHEMAX - if (tc && size<=THREADCACHEMAX) - { - /* Use the thread cache */ - ret=threadcache_malloc(p, tc, &size); - } -#endif - if (!ret) - { - /* Use this thread's mspace */ - GETMSPACE(m, p, tc, mymspace, size, - ret=CallMalloc(m, size, 0)); - } - return ret; -} -NEDMALLOCPTRATTR void *nedpcalloc(nedpool *p, size_t no, size_t size) THROWSPEC -{ - size_t rsize=size*no; - void *ret=0; - threadcache *tc; - int mymspace; - GetThreadCache(&p, &tc, &mymspace, &rsize); -#if THREADCACHEMAX - if (tc && rsize<=THREADCACHEMAX) - { - /* Use the thread cache */ - if ((ret=threadcache_malloc(p, tc, &rsize))) - memset(ret, 0, rsize); - } -#endif - if (!ret) - { - /* Use this thread's mspace */ - GETMSPACE(m, p, tc, mymspace, rsize, - ret=CallCalloc(m, rsize, 0)); - } - return ret; -} -NEDMALLOCPTRATTR void *nedprealloc(nedpool *p, void *mem, size_t size) THROWSPEC -{ - void *ret=0; - threadcache *tc; - int mymspace, isforeign=1; - size_t memsize; - if (!mem) return nedpmalloc(p, size); - memsize=nedblksize(&isforeign, mem); - 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 (tc && size && size<=THREADCACHEMAX) - { - /* Use the thread cache */ - if ((ret=threadcache_malloc(p, tc, &size))) - { - memcpy(ret, mem, memsize=sizeof(threadcacheblk) && memsize<=(THREADCACHEMAX+CHUNK_OVERHEAD)) - threadcache_free(p, tc, mymspace, mem, memsize); - else - CallFree(0, mem, isforeign); - } - } -#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); - } - return ret; -} -void nedpfree(nedpool *p, void *mem) 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); - 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 && memsize>=sizeof(threadcacheblk) && memsize<=(THREADCACHEMAX+CHUNK_OVERHEAD)) - threadcache_free(p, tc, mymspace, mem, memsize); - else -#endif - CallFree(0, mem, isforeign); -} -NEDMALLOCPTRATTR void *nedpmemalign(nedpool *p, size_t alignment, size_t bytes) THROWSPEC -{ - void *ret; - threadcache *tc; - int mymspace; - GetThreadCache(&p, &tc, &mymspace, &bytes); - { /* Use this thread's mspace */ - GETMSPACE(m, p, tc, mymspace, bytes, - ret=CallMalloc(m, bytes, alignment)); - } - return ret; -} -struct nedmallinfo nedpmallinfo(nedpool *p) THROWSPEC -{ - int n; - struct nedmallinfo ret= {0,0,0,0,0,0,0,0,0,0}; -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 -{ - UNREFERENCED_PARAMETER(p); -#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; -} -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); -#if USE_ALLOCATOR==0 - GETMSPACE(m, p, tc, mymspace, elemsno *elemsize, - ret=unsupported_operation("independent_calloc")); -#elif USE_ALLOCATOR==1 - GETMSPACE(m, p, tc, mymspace, elemsno *elemsize, - ret=mspace_independent_calloc(m, elemsno, elemsize, chunks)); -#endif - return ret; -} -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 #endif @@ -363,7 +358,7 @@ int32_t initsystem(void) } #endif -#ifndef __APPLE__ +#if !defined(__APPLE__) && !defined(__ANDROID__) //icon = loadtarga("icon.tga"); @@ -719,7 +714,7 @@ void grabmouse(char a) { if (a != mousegrab) { -#if !defined DEBUGGINGAIDS || defined __APPLE__ +#if !defined __ANDROID__ && (!defined DEBUGGINGAIDS || defined __APPLE__) SDL_GrabMode g; g = SDL_WM_GrabInput(a ? SDL_GRAB_ON : SDL_GRAB_OFF); @@ -950,6 +945,7 @@ static int32_t sortmodes(const struct validmode_t *a, const struct validmode_t * static char modeschecked=0; void getvalidmodes(void) { + int32_t i, j, maxx=0, maxy=0; static int32_t cdepths[] = { 8, @@ -966,7 +962,6 @@ void getvalidmodes(void) pf.BitsPerPixel = 8; pf.BytesPerPixel = 1; #endif - int32_t i, j, maxx=0, maxy=0; if (modeschecked || novideo) return; @@ -1838,7 +1833,7 @@ int32_t setgamma(void) return i; } -#ifndef __APPLE__ +#if !defined(__APPLE__) && !defined(__ANDROID__) extern struct sdlappicon sdlappicon; static SDL_Surface *loadappicon(void) { diff --git a/polymer/eduke32/build/src/winlayer.c b/polymer/eduke32/build/src/winlayer.c index ba97aa109..a762faef2 100644 --- a/polymer/eduke32/build/src/winlayer.c +++ b/polymer/eduke32/build/src/winlayer.c @@ -135,11 +135,7 @@ static char taskswitching=1; static OSVERSIONINFOEX osv; -#ifdef NEDMALLOC -extern int32_t largepagesavailable; -#else static HMODULE nedhandle = NULL; -#endif //------------------------------------------------------------------------------------------------- @@ -350,34 +346,6 @@ int32_t WINAPI WinMain(HINSTANCE hInst, HINSTANCE hPrevInst, LPSTR lpCmdLine, in return -1; } -#ifdef NEDMALLOC - /* Attempt to enable SeLockMemoryPrivilege, 2003/Vista/7 only */ - if (Bgetenv("BUILD_NOLARGEPAGES") == NULL && - (osv.dwMajorVersion >= 6 || (osv.dwMajorVersion == 5 && osv.dwMinorVersion == 2))) - { - HANDLE token; - if (OpenProcessToken(GetCurrentProcess(), TOKEN_ADJUST_PRIVILEGES, &token)) - { - TOKEN_PRIVILEGES privs; - privs.PrivilegeCount = 1; - if (LookupPrivilegeValue(NULL, SE_LOCK_MEMORY_NAME, &privs.Privileges[0].Luid)) - { - privs.Privileges[0].Attributes=SE_PRIVILEGE_ENABLED; - - if (!AdjustTokenPrivileges(token, FALSE, &privs, 0, NULL, NULL) || GetLastError() != S_OK) - { - // failure... - largepagesavailable = 0; - } - } - CloseHandle(token); - } - } - - nedcreatepool(SYSTEM_POOL_SIZE, -1); - // atexit(neddestroysyspool); -#else - // don't want to mix msvcrt with msvcrtd! #ifndef DEBUGGINGAIDS if ((nedhandle = LoadLibrary("nedmalloc.dll"))) { @@ -387,7 +355,6 @@ int32_t WINAPI WinMain(HINSTANCE hInst, HINSTANCE hPrevInst, LPSTR lpCmdLine, in nedcreatepool(SYSTEM_POOL_SIZE, -1); } #endif -#endif #ifdef DEBUGGINGAIDS LoadLibraryA("ebacktrace1.dll"); @@ -621,15 +588,7 @@ static void win_printversion(void) initprintf("Windows %s (build %lu.%lu.%lu) %s", ver, osv.dwMajorVersion, osv.dwMinorVersion, osv.dwBuildNumber, osv.szCSDVersion); -#ifdef NEDMALLOC - initprintf("\n"); - - if (largepagesavailable) - initprintf("Large page support available\n"); -#else initprintf(nedhandle ? "\nInitialized nedmalloc\n" : "\n"); -#endif - } @@ -737,10 +696,6 @@ void uninitsystem(void) #ifdef USE_OPENGL unloadgldriver(); #endif - -#ifndef NEDMALLOC - // if (nedhandle) FreeLibrary(nedhandle), nedhandle = NULL; -#endif } diff --git a/polymer/eduke32/eduke32.vcproj b/polymer/eduke32/eduke32.vcproj index 23febdbe7..a6676999f 100644 --- a/polymer/eduke32/eduke32.vcproj +++ b/polymer/eduke32/eduke32.vcproj @@ -144,10 +144,6 @@ RelativePath=".\build\include\mmulti.h" > - - @@ -280,10 +276,6 @@ RelativePath=".\build\src\mdsprite.c" > - - diff --git a/polymer/eduke32/eduke32.vcxproj b/polymer/eduke32/eduke32.vcxproj index 6652cae31..572194708 100644 --- a/polymer/eduke32/eduke32.vcxproj +++ b/polymer/eduke32/eduke32.vcxproj @@ -92,7 +92,6 @@ - @@ -116,6 +115,7 @@ + @@ -200,7 +200,6 @@ - @@ -226,6 +225,7 @@ + @@ -285,4 +285,4 @@ - \ No newline at end of file + diff --git a/polymer/eduke32/eduke32.vcxproj.filters b/polymer/eduke32/eduke32.vcxproj.filters index e9e730380..ee41839af 100644 --- a/polymer/eduke32/eduke32.vcxproj.filters +++ b/polymer/eduke32/eduke32.vcxproj.filters @@ -123,9 +123,6 @@ build\headers - - build\headers - build\headers @@ -390,6 +387,9 @@ xdelta3\headers + + eduke32\headers + @@ -443,9 +443,6 @@ build\source - - build\source - build\source @@ -677,6 +674,9 @@ xdelta3\source + + eduke32\source + @@ -686,4 +686,4 @@ build - \ No newline at end of file + diff --git a/polymer/eduke32/nedmalloc.dll b/polymer/eduke32/nedmalloc.dll index 872d1ea5057073d0e74f254e2b6408f58c702536..e52c86a66c2e6d6e6a3503c6fdbfa06643e2f0d6 100644 GIT binary patch delta 20343 zcmeIaeLz%I7cYFyFvzHb49d5t2&gEiGt3P0J%fsh2{;N2B7Te4g@U3+iXR!JDV5eSw5Uu;$+^FM2DJCN@4fH)-~H!K{mx!{?eD$U zT6^t%4i@k8FRt`2FP^^THCbHa{bfZRsCnkAqGO2HJkwP4HNtZ*-!3{Qq`Qjt3jBtm zZ-nq-(Lo`+(H_6v9{wnV6P|s_PU~FP6cHPl^OBWm|1~kOeY>(<80J?np7b#rULsNK z5YeG(@&wyEtR<0Uwu>1iB#vcf(hSus;%^uZs33 z%dBG8^^NL2#4&4;1H5l<;UNQlCHL9h-PXxzK9*sU5&S{=iw3aqBug}4pb@-({Zbhw zb;!I~v*$j=Ft>t{fR>r=2!~g_A$pP}#o{nFhg67D*oowfIJ%FPVP&P&jvj?#J8dn` z>J7~iSk5grZ>XJg_D>2(1%vCAL5%)WrFLKbUyx`dZ~OOVr<3FU8a9pmrX{bm+Ud_{ z-ocPp&>^#!FquPVFfBpi{D8X{p4c(Sy-dnD;<=3Yknvm{ca@)V&+B#9iqY}Xb0{R_ z3MxGTa{D5b%PpI&9h!cxA&xiv7PMkF*mSueQLfxV#<$>HL+SaTlJ!V(-}hqpAlMJ~ z;>oR`Ps56RcrNJV5kmK}2qvhs3{%97qS7NaG|cz&*kr;8Jfq@0uO2~e&j%2Hrf$Va zJn=tMH!8*(#4u%}5)Q>6>PeM)5>qAaYRMSq9WJZQ{e5fM5=Cp`*W6k6_W@;TgBl(F z_r9TIhz^qwLO$)++vTxEH$PFfmR4VS%F&(ka>K-atf9g295+T%ddk^iu*rn3l&ui* zR6DwrNeAg9j+eMp38wb1LN<2-cY?q1fKHf{8znWg2D#mIBv}!Ob)HdDwB|m^dTbG% z;bLJt?z4VVJTHosC#FsHxI|^cBn36xFlnX4xv`RUtm7heQzPcBrrl@+HNV*JxM!G{ zvq@2(-&gz_SeWL`T)On`QHitU?ol?VEd*2` z9{t?6V#?ffEXwnqG%`5k7tsd=Br-HpG_8QxLkEab3dp+9a9OVc3?U;vn#+k#P*(FB zs}6>CWmyra4a;FwBr^O}_I0v1JdWK}bus(`E9#v`c12DU)!K+()X+F$6AH(3!$Po{ zVW=m@FibX2;u#gB2)2-1h=1S~`93z89Y{jrK4ce?6LAUbL-JePP?0&e zDkfgUiu5@ozF)n|r+rGVpnv0+}WT#XRts)%JbaOdv^`34*zL%IttlBW_%&TPw0x!kuT*|~I#5z5QT+lD`#k)N%CNa}hu;^~wYdb4eOI(!ajO4+C! zLrqXgF$3d@-Kh?>Q^T9bX$=n?1>EQm?`WwX@0lGRVyJP9En67zDV!NbH&yIVaihds zx{R|*JXvDH7Y=_`-CLZd6Yv9=z6rfTI|h;r(0&U zbM3UL-0>+e0Fs(|TUk*Kmcf*V$>fKU-kScRRez9Cnm(d?Uy^4u^LrF%A*WtcA@eL* zkyGjoD&0nIYr+!??Nn75?hF2nUtuI$>6Yeo)NrHQD*YVY-A%1-UV`Px!o@b^1E!te)| zaV;Wf_#b6C*CMbH`RiVg%VAR;`Mq~($&JG&D2efk67x@N6>!O@jUi!PDpcM0=x3NXx^9g9@!}rS*FQ>(Lu$kf&DzLglH$v~w%FOq)t=k>_9ptUBf(!rdxc z7I2UbyScNW#^rwyMH$a%t1zDf{U6s6^#7=&poZKs42DA-WsG6_5`!^gFqJ?qtn|F2 zziw2zbBK3T+RdX_dn{UnXGI8_t6L$%lZwO5O0v%wm(YVI2U1TE-i$xr=@iDA5g&h8 z*o;Dj&FFNH`!++o#;9?_k$L%1x*7d%_M)JYcTqj2HmGDf2tMm)RN3NQE9^>-y)&o_ z`P`(0C;z7@ZoG`kv>N_i+8HW7+O1`re;SrrmrVC&ra1%aMy8`0xFg*0l`?G3u{`R_ ziI3q#+`dw}3O>c-T9ucZJNtBv;k@KYvyvS{UNw(?taRrTgg494Vx&bwvMiBoD6v}- zqsE*-g>^gRSev>4VHJWt(;~vl$@`WV)m*r8wyR&aW z7jpT+PDpRWUSasop+)y1sBllPX7j;5&kr&hn46u;pYKeJsTq=-<7o2){|_lo9Topb zaxM);RfUWVhB+242-;{L+u$^EKeZ(6d8BU_`hb*lu`@Uu4ZKJ;3{y!$YK00vB@M$i z1=0$qO%>E)_z>b8ZtRs< z*9u;ulv_c?7{aY0pO1(NY&Ty|O)a>2E{Xg!A|~XKL3=w13o%-Xo-0XIT2AtryFQ2a zQ3X^o8%r-cqqw!S&O$GaZSAFVQD1lx*_IamxW2ymwb!fk z>P&P;3MzdQBk`CTKzmH}!jtY-J~iKQr4kDUEte_p@~^^9qdd}#Mg}9FTm&C^~F$}XXr3~j|D_@1d zLL0Hs-F3v>t-<+V614#Ez~Nlj_?gLq*iGY3U_YRnD-~mib2NA4WvXk~d*j<>@)de6 z#$F`TtqgHtxXwiHN@`r1hY9;vnUKCRxb(cUyJw|fdxT^ZVw!sk3XEN20wvJ11h^x7 zBTk{vAg)!g>blYK4k>RMNL|dEucH)KLr2(6=qq=Y-+T>Do|Kl)<$})g(r+FQ?CkpV z@Xo6g!ce$TM5m2S94DLKnHwkb1lqA4Tp-=G(RZ=o=z@^{-qFc(>1whyeZ-(b7}TtS&=w^8g8@W3Cf0QqIqs#!%jp6HmGZR5I7Y(TD7ivu z9F*vh_af-!_vw-Ztvm_34EzcFlPze<=YIs1yic<`;uE;zhF@`yaRQ4QZ_Uo*Z(~0~ zZ*ba{vyM>1Ukid0|FV^dhf=ra_n|H!(T#OyoKKWx-dg_mojzFiY`TJlOfL5)Kje2h zzY?4S3Z_g&MRajvuv@Q;qkheoi6@u;&0vj#+&vJV0ui8jvb~{e@}NYu;(wK^;a`TD z{ELA>ki;iqT|;2(g(d80qJBK}C1vmp#dPIM@A|GfXs5ERxV@3u#`CABMThN_!aVe} zw+J^T&@y3;@6gG{98c{}9ZO+8oju%w>NB5H4a278xsUP{RC6Xyc%(XmxU`j4oQy_e zMx=~$blKRB85vv1Wb>Uc;iz|7!PNX3XB>9{6|Gou!9`Q_}OXU*tiVQ)U8BjjTF5fLlUjS z(yF1voKy06=kQrF2{(C#mFwD^>>P-F?AIiQ%MvYGp+53>9@nNiktQ?=n7Lls)2?LA$SQ#|tg#lE0 zWX&OES<>-VyVb`n5V%l^JboY%PZ-=K4gAD!vaNh1F-)-FSp3oiOJF6K?qkxzVH5bZ z{Yl+~Cvdvzo?XZ?WNG$P&{wj1vscK2?C4&r=-$?=1kbW(rQAqrO^tr=>&8Qdiis*G z2Q_+fhO9e3f&7aWRZ{P8&?3_>n2YJ?(DAZV265oc3 zR-^F0E1!w@&2N#wb>&QJ$fveJp${Wbe+t$%W`ea)1fM?18(L1p#AJ5k-Co7I0L4O5A@>gV56$I=GgbG@zAi%^%*Ai4l(MjBMt1G{9JK za6Nb>6%OZ{ailFjzvlp0KiCw{(l*c12G7!3o#`a(m=nf-CMlZKC)C&Xp^8FD=`rjUa`oxnqKlo$!>4ma3pB0}6++cJgeY3MS!=!fLjdOnc7A zTFI8@`gaRKE&TDHsNjkDFw*c`r0BMoG(R^kq<<|_ZlQ$$iN*gfew}n)GAOd0!94`>mr(3 z4ys`hDS19u+kkoCzQ!GuH*_LqTUm_@pEdFEeKDANzKQA^j0`wQ;NU=AFC3QnI+g^_ z?I|kiMq9?Ac=BAU>wjBQ;Qy+oJ5U|kgioa5aiD7qE*Q8!oc=p#WW3GFx8RBnp36f& zr-eUs9y8YppF5rl;O;@vd*H_7qSx!fU6=cWn7Z86&f9tX1f0|m!AVJrR8SaLO+iiR zUDUClqmKUVb%atQQce%3?Um4%3e9>33+La7*ca$U6O9{N4~@ z<>-BjguBEi!-P#eCS|<+(lD{!epca`E<7{vGz3~RU?@d@*4zvZg*~Mf9mA0nhVgzN z^Y8jsk6~pZM{pr)M|x_ZAO8>`m2*E{EA_o#s?X(a<=Hr=lp{A^$QD&ECFXfyy)Q0d zWZw9)hNXNfUg|r%7WLE@O85zINAhbx6h%>j^V;}(gK3pEz6mmJ z<1b@BvGEtdv+7bCI=?Hmy=>+x^`Fm-7@Hu)Y&cfR{iQieJRLdVFmzJgBo~Wm5aBx<8noUU4 z^JbFolCyDSwJT=AbsRCV3+X0G9o_9zY4W%W+)4f?ADhc;^`uL=PVUx+jzBI;?5q1A z4q>#dj`}KTd}IrkF5$k$b$pvEid{#-i)V?LHG;~7aDuSP*7#Ir1ES^ecvt}kC#Vc^ zQk6kKRfa)M2<<(jWAL&oz(t@Qs0EGy`#3>mXim;cYmNZo0qq(=Www+(Qkjf0L1nff z5eh^T%J+i42()33gUW0v6I2EPRT-KCty>XH1f~Oapa@t56a%D8P#Iq%yTRB8)B=rV zMDHGt1zzJ`7E}+(+;Inz1d-xQ^(3-H!Pb+pB{2cTR2HOt$-I&QYy#O_67SkZIfr6| z#c;Q>&c*yd$QEQR09OZESa^PXf-lYwK|=FQ{s^uWyrB)Wjq7NG{|z^5JEAv%;&JO; zTK!@G{|`=A&1d;2q?A@Kis4^_#DNHh#l3^eEh@@gz5Wp>LrkRxb`yEAbWpcBC{)v2 z=x!A`^Z6w5Vd19F zq}xO@Fir{bT!Yr;+dGSy>PIe46ZvGNnthf0zVft-RtHBEP18EcN*i%LMO(BMj1+fC zPO1BW*AbA-Z^uOBbD3?^lwTI`J8^bDMeRi)`&l^ZwiSx_v_hiqIe^yUnpQ$R~@OeZFL+ooZLo(ooqwk##p3Fpr zcwbz@>&U4!mR@(zfbtZ+Uf6ha$82qZnEnv>L!TF+wmkj~lD#(8 zxCPC9@&H$3=u98`7UaP@w5JCNTPEf}s;susAD;)`%f=@oAr*BS7YwrT{m6%Fdt`1v z5#fAlfY{>F0QG!oUjyc6v@Kg6{{h4sGYc7=*nVfr_m@Kt0NSVPf5iqX;_FWuMA{m zRh`O{SyoDP>(s1-%w3n=gMo3yJ(kz&7!FU!oaYUdlCRbcMylWX1l%hmtyjV4p0VD_ zMv#Z=qe%UFg+OKc;=xC8r!*B7UuJKjiyzRPEF>CsJlR92uYQ&!u_s6yNn_E-HvR^7IV)d73M$UCnPkYO0qiki+tdfH<$_HaY>%p% zO~=`!R?MusDTsC==(Cce5qM8i7;v;zobM@JgE!)aqd_ZUU{<{GrDc1n_H7OovE!;v zZ<)igwM6^II`#rN{l8Jzb0P0q-!f z{%_$B2kZlww;5SiU_7w=9b$M(-J`?*>j>#f?fGv#nUsU=*E5oSfRbPNvNN3j1SgC- zrZb#eca}89ebRe#C@{PtzzX*Qt<7@|s>z%!p7w|T|y<8h^4N-1N4V_&2X@h&Ilvxah}Q|jFSXehUn9>~MoJ@v46(HBorF}L5T*Ae1-k}ym!0%_`2jFhHTFwY z*rGz~NyV;21Km7uuQC(CF)`i-*}Uqsaa6rk;BYPQwR?KivK<|U2yRYC1}phzSJW74 zf#5O(rqV*&X;JzTp_|qBmd_n1RCaSCPW6QnyPe8X91f*+2NvFU0>tp@Moq2`BGca; z5c?9Y3G&^u+8FNwyEil%DpEJH4Jzm5%@|Ojl%GU)y=w{^f$HFcNqN0Mpx00z2WfjZ zhTTDWy%%Nk^$Hdvf?n0Pq6T3rL0{cjVlVu_&Nlu$Uf|^`@1o=)@aa9i;LN$unlNrj zp^SeEr;L1>g3g!sC1vmRbd}O#+^8f}9$@7c`eG_y>{(yT=!+HjVyV7ZrZ1M}i&=cJ zbYD#2i%m9FV_ImnF_cjl$lu1jx-cKyGCQn9RGv2>GzPN*^A)t*TZGwm1my95Vrla` zCMwT2QTxca-6LXNqbYpk-(D|WTx@QEe929)YA7w`7m<&4$Krhd)$YMVd{YJ&f?tH` zdbEsUAd$i!SGRFWGm}aEFvi$|d_IAtH#)C40FL2@z7< zCYpoc)K-+;5dqo}<~Grcj3dx(qL~;6J^saSrvkWxrfi=Ls?MJl9KDZ`dDJu)$_jh; zOmgb|xWKbtV%5|%2dAzlf4`p`JO!6RnB1p06CIdcvY!|~=*`X|1s^2gzI4?G(E%-e zuq(9mA?H5mEjidqBds(t5Wdrc58e+r2wC-g=W;?+^a)wGcO$!)1b*leg&iSlKYR+? z=pP>r#yw2TM~UnYB;%ugkw=a}W&7Q!z!0Fh&DT3NtAeW4AJwyP!1DH4VZkc*jmDI> z>>B{n9Px2)IM14o`$l~AIhMuaY{N^0BrGsDvaPu@rAg7pKg_Mg_U#R&w?yBF!DY%F>0#NRxCj!P1upJ6D7Z<@eM*e=}~-<5SMqvcW6Oj!esX8 zGIDf(I5w_t_E!$@$IUl&THudRLzD+g6u>Q&!p8~a{l0=yhfVd!`BzBgfzj-Tq~(CV z>jE6reOwVyA1q;iCWjBEc76Lo2RE7cA5ybV6T=~mbO^ZZ_U;f_b|`9$3z5tzU(m`?$ceA0D#38aFnrnLgb32-lS$Z67k|=+)soGh{Dx&-eI!BD z#*lqS@(@%7ema|_(U(4Jq(ScIXOJbnS{_cF3iMy<_i+Mt2E$d?7tMIB?I6!pr_zk? zSNFoj?-$hrdVcT)?FZeG`28R~@@9+o<201v50k*7{iM$e>CrTO0Wlwq$xGNPcqlS^ zE1ePsTLd>n;(qYZ*^}2JFC9XkM|INeie877US1?I^tyt}$9YkFkM?Y>ryn)#t|M1} z>`yKq9Uy(BmRy^x(5e*0J7F)#HqxlSRiy43rCF#`!?Fy!VW} z-Yj;{y3V+lUS}MU{I{@!T;_F;1m4v3V+M9PiK&SSd>Y*L;s1V|jIMc-b(42%=Cetp zcWoA1T{WjRob4*wEeu&|*T#}pjwb}q!D}9va{iBN*aBe(4dmqUUP+IP=|i6}wecx? zkZ=2@YJM3t`7>_)myQvPF-_2ppp z1G41H{HQNJ>#!nupP>B{%{I6|bpFH1Z(j}!3BjDex95wIt&V}6V0b4J zE!FqLb|x!T4hxHKkwSD+q(P;H=qN77@m1KT9#(ksf^~AYE)FWSBE|4$P|186J_uUz z9Kt*tNXC%sXEf|DJEG6BYzgVr5FHVXBDhw^=Mp`9f($k8Y=!cTZ%7htiY2aw$j&{F z_!NyH+Z+0X{D}cjwQEG!F3V4miw!pEg2#+yB;}li^(PC?6%3gO%b5R31CD3ZzZzoW zM^gs9Fp0JC2GB=a{cUB&(k7@Y-ZpyA#SH4=%OT``NFAB>+<$=nckUm~uRk9~rk(FR z@Tf1BP~zi%mDu%PCH_O!oqru)1P{HShu{`on29sV*$XM`Yoyb~6gHyDbTNjFsl;~3 zn-9P|m2P=}&G@b}kspd^yVX5RmVV`kl!ahGzViV0aV@evSKT>ie~Da9x?GAAMKxCq zy_D@QYTZvtE-T>h@4xI6CPgBvy#GiFI+s^v=W$^i*Gq9bh`F>$Z9=bvurV^ed)znu>5kCV3&+|F3 z<^yi_VSgf{Z^q$l`P|LuFz?F$mm<%S*Kdw=jpd+y3ncsqA(Zk4A(Zh-Aq?RYg)oAT zqhSgkEktAZ5Fw1`r9zm%i-jHHxf%-}y1LMy*Z2y^)DLO7BCj}T7g*9qZt-XnxF`Q<`r=U)`U+58Ja zSj0aogbsd&5H8~Lg>VT!9-)hNVt+BUX(K3me+ebE0=bHkg9UO8C1VA$oRZ-JNq2Kz zDv+Bf$qM8aO5VjHdG~LlWV1l-q-2voR#NgSfjok5W*GjoKvz@pbAha-5jmc3ke4)St^i?lw2&3S137GAe$&TQy{NXGG8EhkS;z;pl?z32!Xsv zNv%M(P;#(9-l1fyK(m8azq^XgfP|9GAca2Dx77T1LIU-* z`SYt>G*bwr>jZWLC65SXG$lV2NL(H<{M!N6be2LF(DPLz)mWAKk? z=SX~NFj@vJMwuS2#e%}6nUmHd8-@Hyv{n`_+s&4!`GB6GO?YJV+ z63uT9GNRUcz2os!mn88d{*cP=XwOq!kLKSLgG-N%g?{+o4w+50Z;Ga8KQT=4j_GK= zW;=aSA3#dC^8natd)2a*MphgTr>5#dQGeD|4uLy~KX}{^ybZhxtN@CDsXzvh3Zwvo zfG|MbpJmKI7BC$s0u}?Sfla{Mz02qOEAP1NZECSvDb^}KMxR1)86h^s&g5HW~l`U6_P3QPowfK|W-;9Z~=_!hVWh%p<&uOG`K0ck)OKz}pa!$yS5 zfMdXBU^j3F5MxF{rr@y#k^la+7BjMU)-tm5uQIatFXB$J{nvb-k?mUkINrhU_zPDN z7?Xfv{AFr!aMk_4M55SS{p8&Fv*yj8oHJ|QoM)e(I5}XL0&a4bCLYY*A(Fj{4tPJlEn7s(`H4(!Hu(BA0#R&T{@Wsn< zTeAp^B7`p@%t5#qp%x)E&T@oagt7xSMC=zq2P%88MeOh zW267$x${=r>+Ad}|Nna$DyD|AvE7grU*w|oPZ*}Wd0pSIify56NT)GHjBH9##olQ19mWSm zhkZS`QtNB+{d!-x;!7X@%?6Tk}#kOATWZ6i{v(B6Q z)UcT|=gpcwzv6x`c6#>+%FUcR(>Z%q`i$pi&YqQbU?RTZ^rK!N(_xpc4`!(^#o&#q zfCxA@4Zte!t^lGaYyL(=D(KPr#mxg$>CBJr3!^@n`qor=}vzf^rUnasty4 zPX(VrD5LR-pb@sDGA^bZ%qAo@pweO+5^&#Ll#9w>A!7;v#HWMbG#-`a@z10PWaL<0i>btE3c zfGnT@cp8`oER!EN5y$Gqq*|2vY62_C)%xKUy8V~*FFNL5wCrCr{#5%>{yX?Gt)nde zFS@b9nZU*c?*12ROU2OyHk@5UgPv^30U_3T5prMwWkv1rnTStEd~$o-ia6$7mfjvu zMZ6kuZF@WkajdT_`oN4Ks9h>XoWWOtcYGd>jFs+8Wo1_olYtALCx$&xtze7%Q)PJ7 zz)-aRU}=Tlq-I9;{|Dql(bNOD+c_>#ECIY0)G3a9`% zkOag4Qh)*QtpWpa5q_=R@wFhp15H39&;XnS4g!_HCZGf;0;U5QKpJ2KR6tVqr!jgE z(Le|w1;jvGFe|$Q+ybruCxIitUV!G`iEtCJ3UB~30V`kxR6r6C0kq)l!xf-nTM9e5 zVxpNX>QWwxq$m{cS#jRXF78X?>%$+fB^?~yIyZnv$2z1!k;3*cCc>*~c0ml>xCTOq z`$$=9FIILPxCk5swgAO|9k2pMAOXN~XB?2EvTgqONS9&41OA`6%UL${>wJGg_0Saceludd(?~Mq8$ROZ$fYBG^b7Qd_221# z)bsjZ_4oAwhG4^J!$iYQ!(PK7!%@RYLy9rmm~VX2INN1(7>kXYjoXax8h=0Zi{v(@E1e7~?II z*eo@Nnf2z0=IQ3=%&RftHnRvL)>)pm9I+g;T($g3M{dOzbqK=cGvqJGm&skL<>m5M zGzQHA%~H(<&1;&=njbWG zG!HZe?Qm_5wm`cA0=P~4j`oPQMtf0vSsSM7r5mPm=$7hM=vM2>G3}dmZ|HXFDs>;| zKGGe~9nsb4I_pF9GxV;_`YZaM^|6MbhC5gW#@NXyH6|Gs8+RLPjb9iq7#odOj7`SQ zrlF=xQ;un(X|id$X{N~z(JV3@HdUKyA%OL!WU~o^H_bfLY&Xv~mzfWkZ<<@ocg(F2 zLdGJtNGwu|%`(|C-7?c+x71ipSuRsyEQVu49c`0*wtODe^(Rc_pYp%uJs@^NA#`IE z6QKKZFr9BG_QDulfI0F@PDvh_oRvH;d3*A^$-R~Rl%thd%3qatl#EJ)m2XhBsPC%1 z>P{&MDX*uzm2xnpCgo(xw<*_CZl?Haf;9a!a?KN(T+I~C9L;=murcQGk)7ecM zs!i2)*WJ?H(Mk0K^vj^bxAbB|S3?g&gdy4xV;EzYYbY~pFl;hxF>Hf2S3-FA3bQ6Q zN-%Hpj7yE1j9ZO6jg^?cFOBz%15I+13dYE2N;RdK(oGqrS4~??+e|y5!VgR$a~GF+ zvDsx_Wv(zEHh*reHD5LlfxbRxaawj+j$)e5(`hPa7SL1=m1^a1WwCOla)WZS@`AEa`JM6yL4S2d}IK}@acODUIAeoN`98KN1cS)?h^lxc|OKbotW>zZFRL$t%R z+1kypj7PLzYp-c(5ZA|bc=Nrx*v7HdaX-8Qa@Jj)W4?RuKz+WGlUzG4D$_3 zF}2l(s|JxV*_eiD-DrHxxYyWV{L2^t3o#f1ILGuNEZ`@mI#ZL0HFq&9%x3cl^LTTT zWt?S_WvQj!!feCaMoeB0d6Ya}o`Nl|05-2g&OxOQ%0H9W$-jk>bD0(EF*ScF0+Oqe zKS^##zKoqM2ljrGs#O)Bj#X>4gLOwC1#-i9gW6PPS!da3`H$sw%XZ6KSfbzQ^6bSw zuZ895CeOs=-%9>QDN}_(sRu%xhpWb@a#aP`LFQlvm#9ir>r@r0t*W8$=CtO#rcrZEb3=1W^M~d>tXd~+H*L5!PMZKDtki0>CfJB{ZKigzcAj>Twpd#V zTd^LCvQ_)G_G7KIifuN$a)LN^YEW3jGSm!Kc4x9F$nU(heq|D|UQ zQlrW^!uXQ0)Of;p&Uo2)3-W!yeA3)tz67!T-kfR4w#>CuSbntpW@)o9)%fQvFgZIh z(dS_+dHHQ&PmwCZu&eZkrA$#+6i>JmMSG(2JW*$`!{~1^m`0kaOqWb!%qz^Vo0$fN*@Q*| z<-O$-<+J2-;nb|a23IRTi;e9Md7C^)p;QzqwqnU+lP$@sl3n*;pE+fP@?BWwua(!7 zKPw+9!&OR^5okT~p4aw52#SYq1248h@=!8?PI#JET9M zzlNPeXP9AV#_pbHe9?Fe+gXJ{OgZ67*`tjz z^ftsA`Wprrh8U6!DTXD6?+v#Nvy3j|D&s2Cano7T&nB69xVg~W#S(5wvE*3_EiYT% zwERUYZef_o2zo)nC&*pcst&-J`4ijGSjBb4zT_dw@ycJ6Uuk~U{H^J#?WG-oP5Bw^ zi&{?mx^|EDsMd7>T6s^~S=Upi)*JPg_227%g4O#+f60hi;ajKSxdEH(7R5HjZWv*S zTB_av8@AK5+q4f3NG+`YMbj12b+{mROl^W25@L=v$D5PPDzg!%8Qhhk4u@rtg^9s+ zC+HA)gj^-pVu=>1VapCeJX+-uig-n;VzOeoqFAv8(y&ia4_noukR{8Lt;t2n<;i=Y Ro-N5zrA&FC(aKH^_#cM4>Z1Sv delta 21340 zcmeIadt6l2{x`n&Fz6_Q3<`*dI_jt(pmS&LprWFJ4uT+wcgPV@5e9EZ9c@6JwivcF ztgJBYWMwA}uW5#&;)N8=%CwGTRNK%Kl}AabdERRenCJWbKF{xY{r>s=^F!Zzeb#5) z*ZN%6T6@FVJ^pJC_*bl*^+sC%teeV7;ttfj-y}YXc+LA)#McmBP5xTkAf!(e9}@WA zif;(v_u^whc&$DDd3$(O2q({<>!5XRX$&7wkd`=!Y5!?t2J{bLyE04*7|;5cvsRM` zc9`f`6&cU=4O0$dnVn*WIiO&fS#$VH#PMiQLk^ci43~%Ov`$ zXn(Ry6}zQ>ME7CNyyZ^tp7|FZGN6S#V*7TxqNe#+hS4IpPX>#Iuu){9Xh?J-cu)N# zGECyIqP&8|a~Ve69SLZe2|+lf`gPG9*0r<~ zFiJ+Ana_B?EUPIQ;|+Bni*VwPe}7p}xMA?8x+nZXzCW zY-c<2aD8Txm8U2qY2MIPv{;ft z!L3qAPteJ<(npbqYjG^cARL?U*j2Ebj%+HjqU8c#4;C>Dx*g&^EwwvN)1=`YNjH%M zc9x@&vco&rrx%g^l4scc)zU6utd7p8CrN?j4J!3uI?PT*$kLAa&1|1vUj}CZ8VUz1 zr8=uCD-vzVCC^CHM7CV=zBEP@oJ(#Km!ni>xie~b^23IKEm`J&2d#gH&R+R1 zUN6_`_PV@5r7wfQR`0`;bJM5UeE`p;ojgLwjS8m~Kac6)Mp3~Rn_G+hJb#mMp|roA zW5fGn>#DB(GgX3zVM`pxpXP2^!tMQjeiF#)x4EU zmOeNs2`XFZ^$ztuILQW;EhIH->_a(pIx1=*?OrKUeQ&U3&vZ%-Jq8D?> z{E$@9s2p-6WQZsthkP5-Q^w|?(AGj<_D68N`gkWvMP>tL?LRKX4j0y1+hBy23nOWqm zULQ*;Gm#G#fvgP-uYN8ffDJ2{;^Ux?Sk-Bm!&-jo6tb)LXCik7Sss}oipwCEB3108 z7yCqtzDXy2`?y6@)5)$r(W1C?a;cAz^(T_P#cY4Fs_%6+nM~2)8i$B>cSFx$pHF7Q6ZBJ*RJ9HHO{HsJX zU>Iv5ssU=Y7s(y4pPfg-21c=$NW#G3qQ05cg#$&bC}Ik6D(YRCT#K;0SsJgPc#(}> z@6mm*IWd7w$ea0>;t_%#ap%e&I6IYZwu>OvPKj4gDgM$oke^nsvrjtrPyXbeh-?%r z)wG#)Ydh3oMlA*~qr;%P@5;GAsymsQ2Og(_Tpl!mwUge13)Lk`5*hqsL*gMhtx$p5@NaJ|e#{L=uxL zdTlgW6k``n7)@$oG@`K4)&GtOVMR<535d%Oy*rA`j*Ahk9z{0C^%l(NNvJ)4P*jH2p=U?j%Gzu;=$Z+Or~`1S%l5 zr=hkN$VBZR_IKjcmP(s?(j1anuwN!(ogCsiNT(59F%#LuFjA=N-v3ef(;Y-bQdA^? zN}{sKD0YGD(hcl{hM4kK$zEdu3D6HBHK~2=eX;F=X=S*JeD9wHmjFNFb=GiW+xGZ5yTeMm zc?qUAi$Y0Ad9*4sn_#2l6PLM?}2$|_o z&zPQFivujOr{b-fjh{*V#ns7IN39aHYX-pX9|;(D|T`&v93T5sViLbNX4M z-&IeBLTaup4k?$Gp&`cnRZ-`Wl*gSk*K!44h6jzlZvJ_KJwQLAT7vS&?_ z$L0;)NOwi+GpLxt&h?;T#2@_0>-DUk>H-s!IoG&K5whB!pRPxD&+=6t!H02>@J-M zcdKko=Oc9A+&sJsTK7MKqKs#ZU6}P~|NprT!TgdP<~VG7FPPARkvP-CzX;rk4Ua%U{oP!pZUga!=Klm$5>MoijM?` z5h^&03qkJjEcw6^;o6GK>rPUK!RhGUygbL}Hm-Nnp6^4H#(W7YOZo;HpsBDp*%*Lp^$ST?m!t`QJ=~}V9{1VSlm8My9VU8I`Ro+O4zxRk|ELqvufrvnzi}GSr*JA7lkMsJ$w$J54s#ed zC4CA%pexytkRs8ZL7Qj!)ubh1jN*ytT~MN`e0uKUi?Gu`8|?$a*5#SR(y$pw-zoF~ zDaqoJ;B+)_p4?B=O77PR6H=T-{H4y;C~O!&^08ujZaH?m9LtL1jNlNW@2RNaP-UDPy>wGp+O z|0tQxv*_*-+ARMJPBJ?M{u$Vs9oV~h;%Iay?TPu!f0~*LF|_M6rQOunFc65Crsk+% zYFO+}YU?(Hi%>nSz0RKwnR>P-rpcH8>JcG77JYhcJxLm^jM)x5%XQ*5(z(V=Ct>=_ zYSsjDVO-L4c28%H@%Yu24C6ZSms`jiqeHtsS;#hWV)RIt`wz*osa%dC>S67lUR)g5 zshP!IHhJADg`ANy%rYC!=JGV|I{z&_yS2~*-vj3$9QLAcfXJd&35toGMkdc_1W}&J zoyFFf?pkQQR6Ss*BDv%1sN&)jt7wg(quaBR6XxP*TribN(4 zaQz!O9wsT2bjE|qenbp26;gIHsPrbKahxi<8dUlj=yi|i8U$^q16>aOWd23EU4s1) z)9ia`_EnhVGv=RhOHv14s<3CK^W|`D=nWQ0$vQ*Le=H4-`6H`b978v1Ta@tLNOZ4K z$e5CG<*9eq{eHh67J4$>cjPlT*e`COlP;c#4d3(`$XZKR#C#@bg8~A{eHwFa-R}(6 zGRPf*_;f5c%|q{gvY>?jQSL0Sfo42a5yrp~>$v`|TR#X3JCnQK-bQ_WS|<80t4mUd zAyrJ-gP>C3^bY|_w?iJJnQ8nA>Ig7;DGW?+M+Kc^9=at=@>V+Am}JoqTqt2yLdv`) zJ=|8RNz5lyt6&g}Fw$HlbR~zG{6tw|xRecctnheDiIgcBU!Hz<-6LU2CSp2j`O%ni zI;?3kvTI8QadmvgUDR?87UmMS!Dr)OIiDz&doakY?Fk`S#Re8 zn$;!I@QfEB2ZF!2_uu`6KmUj{PKrSDk0+({`W#B;GX-N6zDpqUDQ6e{Z*nrr9?EVY zOYKpjSUIV(hp`TF*dD`fCEwYjqO1H^S$Y<)!c7iJH;0r@l&0Aog+6X?feWe6;_nb` zT3pv$@MFG8xAR|-1!)O5AHSED5O@wu_bF-qh{^oKA>?7&cy>D(IXR!LA@5I~0a}{g zmu(|4>5+Z*Q191gH=gD5rQB$GJ!0|0gALGXQ0NT=_A=4q%D0s%8bp3>y{Y_ zJwJUKB43Nm7kMsYXmlGI^oDLlHJYo>dbTR+k=R_}+nPZ?lJlS-&Bti&&okzWhABwm zlo8>3ksa&Ysjf4$(#v&*V=IA>JIKpZVuTv&N)>IW=y?==y7FAa@7zEF7ry;8@iXoW)?`4VqClO$pcAM<`lMxJjhJPh{k6{NOqugB=jN$ zStS_Q?W}?Q&fsXueLua{vq^Cs)uZ`F1TWCOAEo_LOpWPIN7~*mdLM{>k=av2uz*Xa z>IeSUX%KoUr-N&`LjzjL<*6fkSM?Xp?u;yVCmLYv?z@sBUngSgIY&Wav$K2u2=fM; z;aT10S>51SecEU}2TN4~+rElaW%mp9_5HUn7@eAu0gmhFh@-9gT6UaBRIsGlFXt57 z`%9=is^D5YCH3ZqB@uO_8QOum(c(7JIDMQVT}YRdpOB(3cgxcmHFeJS@_b)xfnurM z?cbZE&KNq#U&t831$kJmr`yB`xn4sq$6Azxz3H09U#Z?P;}$F0zNC8fEQu)g;g7U! z33uHyy&iUtR=WiY1h1bcE|(_you~hBbCAw|99F%5P7W(d=uLuhdsCUr&2yQg@Evb$ z#l%dn9Y3Fu*#I>#80Z581OCA8xX!-^d<%RI)GcIW$AAxjUBD~AX5cwsDKH<%0VV-H z`{a9i2knC_JmCzj_YOMnG^2j!HR@4ooPD4a+gWUxXdLt=V$7S$ZX_?}so3M>bly1j z2^AcpJkJ9-hlk% zGmgX}Mz(V~iJKqIt|D3UN5HzhJYUOJkxTPy@O&ZPg4?kA{K4G}sD(cxxJfa8d^WWplJg=vW)FYx$+rQwmM|*OX|~Bcy0*935%obitUA%YJ|LYidW`eHZo>*=5AG zFiylu$-;$whT=sVeFX&#oFz~jLDdKp-9N}z(9{Z0RV&DWg;NaoF%8_8*kIx{6DC_z zGjj&FNulVEw(9xa^oR=+15PYBGiPY(h0{3CiO7gWy;&u(E*!>wOExXCyZ(3G zKUGAlqX|BFcHa%(X-`2fPGch*g3Sf`$)scVCdaM*FWjS&P9A~h{*w(Vb3^6I;rH$N za>$YkGYcV?Ab{*Iz=kG7Qw4-&;SdkQDkrU%sVhX7NEG*!5xO^rv4*D$ifR+P31pO~G~M z9-^5ZcE0p8@W#-~K5TVhyzXW3vvHP01c%glNTfR;dIgAzLooAiq6_ZR;k9KCO00Zk zM}>piD-0EOn)K}3UZteWRa4TO#dqtdlOBDMPVE}b7edXbHMPCgC)T6Bo^A@Im{089 z_ThpF6C%U@2v^LP_$Bn(`?Pq*DJkO}lmp@L4sr<3S;8|HPjet$t`gC2wefcXF{}I^ zxKYK3CHY~z7i9JW|C({EOymsCXB|jS%=hCTA*8zM$7^9a$)v*RBD;(HqcE&*?ixns zRg}+iF|rDTO^8-F@u&h$uOYV!htQk>OB6IvEr}dtN6zwb%vc0kAQn&nkpLD%CI!SU zQnVyFgy!VDv}On31U9u?$^aHvGt_bxq=O^zUK^M*#;tBs>U;ZsTp>(c<=RrNA@kfkJkrpEt|w%C;whHvKJLtJHHe6=GmT3&A0ilK=~@SFHaHu7DrxRZeo?y zUoG#+_N)+On!fMFx`jH{QiZ{bU($JH|B+vVTc0oCC-+88wIB-N7;%H@&E$W?ae!;d zyJZjzfeT zd+^|Q!rNyfPf12*mgDS4F!(A7?gH?lKz3p``Dx|Q0j(%NE1~)-qUMTukD4n?gWSOk zKoxHj{okx?BXRyMHstwOhB0<_-ZMWgvU%gZU*LSbj2!rzF}em7u3OzykDxf18{NcF zX%%@J+@qVs%|FzQZfp=TG+rZNt0uEY$^2FI!Jq#MMVpATt;FxLMrz>CkTI*1SS{gJ z#|2MrPs&S*Rd7_GPL1lJt5`?v?+@~@M z8Xf?z5fGOPDubL9Wb=`vf9cS$Ml|AWfDrb~%H*dYJv$p0IAnHd->$m{Bc`cI#Jed^ zX+rdU)X#Get|iWC zmdxJhf@FNVah9xAhAnF9*IZy52*1EqlIH2no*)Z7)7h-*i=F^hBw@+*=Tk#0I2EAp zosOJKMTL0TUCT!kBbU%eiVws7>bXI$WA$L)3ywJ43wS=@g`5(|}-S5T-u_+qh2(QCk+j znbd9?U^#;E9D9sC2RhTwk%TU{iA3h6P#!P+y5)x6jW$DmNK9uw? z?~!Uj5#dlB1F^+T2kQCQp#}2Uj<2zJj3$fk zOxBf$L2tH~o3+tY{_N#t5|prGxk4~6bYW-Em5sPfR~AG22#wOQIzth8pLE`wgoQ}i z9L+{mFWszWamDe@3p!R#ZoQD+Bb?TN?^C?ak=P#Dvb>=RGP)uTsl^phY$VxHp=D#q zl?pp{mW#GT5X%;oK&ATP!6)epcUXLxV=Z0$hr#5>E%CVE?Dt|nluLLqmOVrYUQ9xL z`(KId5|K52s{(Y+);WK<)pInLjC{Iv z3DOg`8QFKpifzVT4OCFE&Qww}arKhPe;vW?ZJUVqH8LDeU!&a&*6)n#w8?4Z(mx)v3O z_b{?Ue`jPr07-Ad6a%jU-vYt!koR`!{OBwA-*(N3&4s)5jD|~-X772fq^EFARL69o z+rx=cIlfc7GaQ1uC(#**8?SY{M+TZ3uotY6n_F-{Je)M_Zqwv`kMlW$Lp{U){4Eku z<~SnUY8j?RYJTjDH2+o-&RhS=c8+-8+Ly2n-ww2wllsa{ucebozrt{@mNLr%`58~L zG;0L)5Al}3&`UENj~dCp{@zO(Eo2x#+de>gynR;04W<#BZ5<62G+={OPWO0ISCxD1$*q?UY%@LhvC7trXxcxS-mG>oXAmpZ(mTBt8K8SE-61=Akb^5i-W9sN6uE0 z*WQW9^z{lBBAmV*XhjWz>%frQ6UAQa`?_TExA7h`Tk`-Vw}Ve#9SEB@7g`g>Ey>4A z->b+&Q_y+kKoacF(nYL%3cAISfKi$`HTxHS$~g@`O~RHy;70&^9#&RdAtc6QF<{b=rviOTX# z)M;}0-BI%Qu;|%*uiw31y0~y=f&A7xVAWDu%5Nm<_Xe;@WXgMS!+cYQEd#$C)AeK} zyWlwGyJ4ovoz<~$WZ!$CF8T$eV=B6w<^95uLc?8BDk)z$5`~B$HeWalLL@{;aa(B) zyc^C%*(S9%C@c8tjbz;3 zfq}O^#j5FO4o=rZR_s*=FT~9iCU-7pr2}(pJWP)7?aP*sn|ot%?IC$TvU5d$c!7%k zB<=mak|Wz`WIK&SW3TkL_uub4bs&lfU*((?wHzl8|FMnTOv*oSiC+4cblW$V{U<5f z7su`+Rr_MtUrGJGLA~lvLDdJ{uf!0b@y$&g&S^n)*ZtU3Cz3Bew6oulsOqt73Ms4} zf-h>eSNFxc;=|Sb!@vIo%i<|%ONZuRfw|Fb&0Q!>TB>g^E(oUDLa(yueRWW&jNS}b zh3TJ#q;&cfZcynXYGQO$q3u`#J5AUXwHqbBq;ZQ7k9`uC3vp#fe3t6Uz7a97-KF!=vQiAW?_LvL{L5AydHmYaQI~ zkX)DPI@p# z>UJ73`N=ono4Hp0ML79PemNB1&Yu#TI=a2W-+kHJ+?^W}i6I2o`RQc#k_`(1bo@``wZ7Cma6cXK(a%`suE(N8AuQ1z z%R*3Heyo6{(Z|QH)8O-uFCokB6Uv@+6M_Cq{SHRKGnoJBy4Z}j^A6H{B9Uf{`=k$U zrzd((Z@n=DLl+6j=gGnfZZ?4Ke86;gJq~mg*;n$NBpUAT;`-B~d%(0zL z2?H0wO_#VI|5?(TACJ6r2*aP$N!=B_vn{*1Tw?C?HEu|YBKU#r*(6W0@uZH-xILIm zs~IBw$Au>yIz%?t#Pv8r+ll?|Njp9Gx#Ut!Uun``884I8no-e-5LYZnfbS;BGrFl+ z?9OXq+^d@yXD|LIST-)T$s^%ECAlZf>=sgWG9qv(xb4Gd&yu>6b67%#o+`!%eXpOI z$Tn2pJJpj72-_2zutligdLnfl27-EePT@i^cmAke#{5R zw{v?scFJQNoK7H0ny|&wk}aou_6&xzr>A@fi2JTAU2`+NJhg@Yl6-PH0>|DPrw6bG z^2g~nW0bN4so;& zB;j@O>@i}mGt1jM8O)7wSbg2J^L;VAY|jiwI%n0A_v-qw=g7snWj))o_7Dc}By%3g zKG(PJNNk0&Ynunrw=?o}k9{?z^TXc*o8LjUolC$7K0o&gMo@VE6IeUt1v$RSOuNui zItBgm9-?~~emrqrkjF)X!L6?c`#MIgOFoD(39+L8R z=7|m~GVd7LKiiy%EfAgmA!KoVbch0Tg1tOnfoydQ>;%J?k-hc(0`h3N0n}3cLcXY< zn3xPjGuJvpjMJq-W%(EyZt%?)ogaHx;q?&K$=$j#sLYNO^KU_=#WZ{zw0;4?EF3_x zN$#id?4w;fK4tNy@3l*j;jt)!yMKI|)x#&qP~$FkDBqP!u_A+lcrW$p5_89cgfMv`+)_~&}-CqsMoHD z-%w$PufI_uX1kNU|IAD6vW4mjZcJ27j7)W#k+pG?>?z8BqLg zhva$5xyBeAXzt^FaV-h^_JaU=(G3$uFT+X0w{gR>A^O>L2Y^FO`;ly_0;}>RJ}`P> zcKag}HM^bOA+fjnggk;q(C96M?c$J6rr#dJmXqDLM^ojwor2?H{C5j_%h4QOu}V9^ zr8S50uD73**g!u1u6LIOV9=`UTnat7kvU{)ZFA&OY*z&_sFMBgVCk?O<7p>l<#Mt zlka_R#2NMb@1Mh6tmB6iIJAR53<^v1&?V|Hme^ZTUHv<0`C&E+PW~|i_WbQ1`>_v5 z-H-4Wr1{6lupS%#haxLTAAYoJ8VCJbD&f#B!6EB4g6gpwD3&`-KP`1uBD0mR{}4IzaoUm z{COcv;ZF*ooj)ps8T@`BoXWo=ggN|9A)Lj(EQGoI79n)-9w98?*9l=Ezd{I|{1PEt z&d(RZRs3v(F4~DhYpGRBr|d(eluQ=Ljg+(sB@-!t+3*GwW-CxMhu@-f6u=retp&fi1Kdx-9~`P&;^ln$Zv zmjXMSlJx=^Ny(D}iR&VUKO~R}O1>wMQIxC_$XH5l6G$Z`pBG3iC0zn3+`2ji(n7iO z1u~JH1$u@+CsB5~KqgZ%8KltZ6dE%L33f^j7sw1sDg<&WC3^{E4kfz@yrEU@T^TZ9D6>kCSNjH?(sae4He+zongX!pBKA`zN+@_6nS(DP~=g zz{%uap`4EUE_^+P3mE>nLr-5E_2TcmM#kOijSJDdd!qw0(7TRHqGWRT-s6;^o4wvN zyo;5@oTI-3cCz>RfRovGLcpa5$9zBhcR*$n9f^JD=`RGPc-Jg6U%Qh&sgssc_um=D zdQbBc0H}dv;2EF*SPN_db_2(OYrt)w1z=)WMg|N3EWl)-09YI2 zVwoKvJ_0TQKLM>kCum=HU;v;6a)5kb6|fc90UQA8f$PA(010NIFJJ(Y0s2!v81(@% z%u#UiB50Ob8K-J#VteiMlXk22*`@@4Z23gn9xJLPloMKF0+711-%e-5wn7^<2j#M3KW1l4`9g62M5WjKe|@G^zhHluIquUOoFkj zMM%%HQ3z2V(RE}R#VE*rm9*FLL?u#$~$`^m; z8(+RLEk1tIuR>quU$Zf?8^FePQ$qVO7*+xwmM}Y>;@QB%mq<+Ppua50X2F`kK0cLi zB&^JGLHCQDql=0b7gbjDLc-s}*};Kj%&4L~n6c4I^A@i4tN209oVPDe&Z~N&w!gi6VL*5Qep1^3HW z3O2a1UcpM)y_F{wY;Sh=VFW$dF58g-3oEN=kC)N{iHvMjd%O^FtcT3e9-oDHBH~lq z<0*(^-DQ@;vxn096o@y#gM|3vk~ZA+H6mWUUnFM_*Tk`f{)tC|SlJ$+V?tp1g`XRD zVTb=OK=zAf9KNJsFNj?YxWB3g&H<-^8sIoU@3r;;dw?onE3gq*3pjy7pa5_Hxxg$S z2f!ETvJ3#foFq#Dl7S?^0w{qfKn~FS;UTO`CIcY>+Iq0E`v4Do4O|DV0q1}Nz#agf zun5XY$6bZ^cAx^-2&@H`1BJjWzz!q=u|PN=0q%EaWp{xl;A`Mo_h&JB5T}9TzyV+{ zup8I`Yz0bzLLe8I3efy10KBnG2}A-?pcOBqnt-o?Yd{UK9Vi7VtJG{xT9qS}6O|dtmz19>e^UOT zl&Ewnv+5PqTdLElHq{{YaP=tl4E0>KL%m2{qF$@spgy4fNL{18puVR5r}|&&M`}M! zH%))d676u^c-?H>F5U0CHToU;+j_tFu=v>cBk^Lx&*oOM*w){cWvjL+5?*s9Fmi@b zpc9=nBQ$gL<@)c8tmzr^YV-T%AFaPzlWY##mo`SpVCTj#Hsx03$4ZN8r0Pr6eN})u zM4g8Y@ahK5Gg^Z#N5|=Y)Xmcu>1~z_%N@&O3u_IsMp_-#UDkuvW7hN5>(&R>$JRib z#KN&{aW?M>RR;~ zjYXTQ&DXBdKCj)TZPLp09{n$RHhy6Iiuld(FU7wWeq4F5KWjDw6C zW2SMA(P3O@Tw!z>PZ)nSK4bdE6mF(NbelK2%$v=xnBO+)wask^>gbtR)3q+7HkW%^|r}vgKR@>!);od z(Pp!avL)M6ZIdy@IkwrDzZDqmCfjb?UfUtt4O^>?NeD<7nxIVBk?>}M>qNp=3D{XP zH5hp(WsY)=a*dKG4=Y(!cU3=Cj7p`7$9#-brK;wt@`d?0tU9Z@sQNSr}|8l!fCHcdNIyFhzi>#yIUKcqjdZ_xLN*TxSuC=F8$ zR}6m`x)^)9FhwTgcw?He$hh3N%NS!)nQ~39nRb~jm@MX(%@55pEqRtzmcLsrSO!_w zTR*hkwEkjM*;d*r3saC0;Q*Bl4R(+~U zgUD`GzokB|eynzAdTF)V{o3EO{d7v5YqV~a?m6A-x^Hzq=)4e~#rhTc7xcUI=k%ZJ zb@2z$&ksyLm|W&h%@gno{Y)X+f)XxPu2PmNYn0cOKPVq53si+Fr)oJGT&pToZB%Vi zRiNSRsvW8-G`~l+SG7-dKy^fQTvemGs=BTE1=_@_CF*YK@hLSQq?72vbq{rIx(NMX{cOEM zze@j_{saAt_*dgkLB#?LV+^T=T*Csxdxj4Urwtbk0mkk|g)s)AINexiTxQ&4B*xvw z_l!RnUH6Q^rX*9UDbw_fX%?nF-?Yf&G%Yu+F+FG6VA^D=G<{`iGO5h@=Dp^_=KE&G z5@H!@QCUV%$&>AtIMQQlX!D$`Zjss&ivHkC*ntX`^KrFN@5>Rsv&)t{&@s&A@q ztAA1dq3)^~rb*OH)Xdc^)DX>C&F7kbYD8L<)};N1_MrAlt?QrKHM&w=g|1F_OE*iu zHhz8l3(({v@o@&7A=!`)NzFGn4J!=W3~v|?8fpwT4Bs2>L3aI&A;wf=mT|SQ)cCsb zEn|c6P17oKsd)!xshedy=4PwqRm(2R9?M?KKFe1YucePwVU4oJT9sC<)nK(irJuJ} zxG-(oq1Pf?pe;(!U<0Oax^08)sIA6!+IG%XZ)>n!vt74+Z5x~r3$4{A7!tUI7ZYAd zU@90U1vAxE8KewX4pEL*PJ;1Xpgf^`pnRc?|;lk>KwX-x+3V*e%)c+C%R7h z0R3qFczv2aQ$JllM_;JFqQ9YU)ISUHbQxZC8BRdOB$&)T#(~CY<07NexCUnOit#(+ zP}4|LifNu{v8lx5HXSydhA4J54>1>;cbdbpejeTOZ6`F_N?j~Sh`ps`rgh#uldjMVc*9Yr+>ig*j=~eo8eUg5nK0`l4 zzgE9Ze@y=vPADc`6(1j;8lM->#rqqg3~C5&5oY(2;hLe*@Ppxjp$!fx*w_!VJlr@M zHg~dds?jymm}e}2@m*5+*s?}79F#Qcr<7ntu7%R0*@>jAi| z$8cCTovU9SDvh$x6F2Q#nmJ8{3Z0ls_wb!qqH>F;%F?swYEU9qNVZ zHR|>1P3o7_JJf$y?^Pdyj$cq;hS=U#-&03n8FDl;ba}c3n5kv@FZ3(oUyk>{_5~PM zn9|Jyu^Y&@yax|5&-$|Uq}6Q8gG3y&ov~>WT$u^y>Do8oW(`3nIFNGH>#FPUZa=I3 zP<4WDOHxl#XRC`~U|vvHtAA4W)2KCXYCh3Ow9B+FX#*hlLvWsEYk)=Rq#v$N#6nf+f7ZuiVI~?@8SWdpVG*Vp%ZwGq-7eE9lhHE9GSjl!aukBH zz0U{R*6lLFgjsU!n}kESlFLvT`i1o_w~H8Qh7-EC4^k0at%DDX3^4UE4L6N2rJM3h z%S;~AtEPkI4N* zlO@;0YLYb>ngUIsrb4q%)1Yb5$h1nWU0bNF(C*dl(=v&^KT9c5hA8FASfxRk1i3r> QQ3^Yz^I`n$%6j&H0hZ|=pa1{>