From 44d43901b1401fdb76bde82af620e84887f9026f Mon Sep 17 00:00:00 2001 From: Aurelien Bouteiller Date: Wed, 7 May 2025 13:05:04 -0400 Subject: [PATCH] Remove unused parts of dlmalloc to improve coverity score (#106) [ROCm/rocshmem commit: 87179b1ffd61ea9bec7a45d3bc40b672ea0d3eff] --- projects/rocshmem/src/memory/dlmalloc.cpp | 2440 +-------------------- 1 file changed, 13 insertions(+), 2427 deletions(-) diff --git a/projects/rocshmem/src/memory/dlmalloc.cpp b/projects/rocshmem/src/memory/dlmalloc.cpp index 01203cbc5a..8c50513495 100644 --- a/projects/rocshmem/src/memory/dlmalloc.cpp +++ b/projects/rocshmem/src/memory/dlmalloc.cpp @@ -25,23 +25,22 @@ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. */ /* BEGIN AMD ROCSHMEM CHANGES */ +// To improve code coverage score, code for the following cases has been +// stripped from imported dlmalloc.c: +// !ONLY_MSPACES; MALLOC_INSPECT_ALL; USE_LOCKS; DEBUG; #include "dlmalloc.hpp" #include namespace rocshmem { -#define USE_DL_PREFIX 1 -#define HAVE_MORECORE 0 -#if HAVE_MORECORE -// TODO morecore not implemented -#define MORECORE DLMalloc::sbrk -#define MORECORE_CONTIGUOUS 1 -#else -#define ONLY_MSPACES 1 #define ROCSHMEM_ENCAPSULATE 1 -#endif +#define ONLY_MSPACES 1 +#define USE_LOCKS 0 +#define HAVE_MORECORE 0 #define HAVE_MMAP 0 #define HAVE_MREMAP 0 +#define NO_MALLOC_STATS 1 + #define USAGE_ERROR_ACTION(m, p) do { \ fprintf(stderr, "Symmetric heap usage error detected, " \ "possibly at %p\n", p); \ @@ -53,7 +52,6 @@ namespace rocshmem { ABORT; \ } while (0) -#define USE_LOCKS 0 #define DLMALLOC_EXPORT static // alignment imported from ../constants.hpp #define MALLOC_ALIGNMENT ALIGNMENT @@ -859,459 +857,6 @@ extern "C" { #define FORCEINLINE #endif -#if !ONLY_MSPACES - -/* ------------------- Declarations of public routines ------------------- */ - -#ifndef USE_DL_PREFIX -#define dlcalloc calloc -#define dlfree free -#define dlmalloc malloc -#define dlmemalign memalign -#define dlposix_memalign posix_memalign -#define dlrealloc realloc -#define dlrealloc_in_place realloc_in_place -#define dlvalloc valloc -#define dlpvalloc pvalloc -#define dlmallinfo mallinfo -#define dlmallopt mallopt -#define dlmalloc_trim malloc_trim -#define dlmalloc_stats malloc_stats -#define dlmalloc_usable_size malloc_usable_size -#define dlmalloc_footprint malloc_footprint -#define dlmalloc_max_footprint malloc_max_footprint -#define dlmalloc_footprint_limit malloc_footprint_limit -#define dlmalloc_set_footprint_limit malloc_set_footprint_limit -#define dlmalloc_inspect_all malloc_inspect_all -#define dlindependent_calloc independent_calloc -#define dlindependent_comalloc independent_comalloc -#define dlbulk_free bulk_free -#endif /* USE_DL_PREFIX */ - -/* - malloc(size_t n) - Returns a pointer to a newly allocated chunk of at least n bytes, or - null if no space is available, in which case errno is set to ENOMEM - on ANSI C systems. - - If n is zero, malloc returns a minimum-sized chunk. (The minimum - size is 16 bytes on most 32bit systems, and 32 bytes on 64bit - systems.) Note that size_t is an unsigned type, so calls with - arguments that would be negative if signed are interpreted as - requests for huge amounts of space, which will often fail. The - maximum supported value of n differs across systems, but is in all - cases less than the maximum representable value of a size_t. -*/ -DLMALLOC_EXPORT void* dlmalloc(size_t); - -/* - free(void* p) - Releases the chunk of memory pointed to by p, that had been previously - allocated using malloc or a related routine such as realloc. - It has no effect if p is null. If p was not malloced or already - freed, free(p) will by default cause the current program to abort. -*/ -DLMALLOC_EXPORT void dlfree(void*); - -/* - calloc(size_t n_elements, size_t element_size); - Returns a pointer to n_elements * element_size bytes, with all locations - set to zero. -*/ -DLMALLOC_EXPORT void* dlcalloc(size_t, size_t); - -/* - realloc(void* p, size_t n) - Returns a pointer to a chunk of size n that contains the same data - as does chunk p up to the minimum of (n, p's size) bytes, or null - if no space is available. - - The returned pointer may or may not be the same as p. The algorithm - prefers extending p in most cases when possible, otherwise it - employs the equivalent of a malloc-copy-free sequence. - - If p is null, realloc is equivalent to malloc. - - If space is not available, realloc returns null, errno is set (if on - ANSI) and p is NOT freed. - - if n is for fewer bytes than already held by p, the newly unused - space is lopped off and freed if possible. realloc with a size - argument of zero (re)allocates a minimum-sized chunk. - - The old unix realloc convention of allowing the last-free'd chunk - to be used as an argument to realloc is not supported. -*/ -DLMALLOC_EXPORT void* dlrealloc(void*, size_t); - -/* - realloc_in_place(void* p, size_t n) - Resizes the space allocated for p to size n, only if this can be - done without moving p (i.e., only if there is adjacent space - available if n is greater than p's current allocated size, or n is - less than or equal to p's size). This may be used instead of plain - realloc if an alternative allocation strategy is needed upon failure - to expand space; for example, reallocation of a buffer that must be - memory-aligned or cleared. You can use realloc_in_place to trigger - these alternatives only when needed. - - Returns p if successful; otherwise null. -*/ -DLMALLOC_EXPORT void* dlrealloc_in_place(void*, size_t); - -/* - memalign(size_t alignment, size_t n); - Returns a pointer to a newly allocated chunk of n bytes, aligned - in accord with the alignment argument. - - The alignment argument should be a power of two. If the argument is - not a power of two, the nearest greater power is used. - 8-byte alignment is guaranteed by normal malloc calls, so don't - bother calling memalign with an argument of 8 or less. - - Overreliance on memalign is a sure way to fragment space. -*/ -DLMALLOC_EXPORT void* dlmemalign(size_t, size_t); - -/* - int posix_memalign(void** pp, size_t alignment, size_t n); - Allocates a chunk of n bytes, aligned in accord with the alignment - argument. Differs from memalign only in that it (1) assigns the - allocated memory to *pp rather than returning it, (2) fails and - returns EINVAL if the alignment is not a power of two (3) fails and - returns ENOMEM if memory cannot be allocated. -*/ -DLMALLOC_EXPORT int dlposix_memalign(void**, size_t, size_t); - -/* - valloc(size_t n); - Equivalent to memalign(pagesize, n), where pagesize is the page - size of the system. If the pagesize is unknown, 4096 is used. -*/ -DLMALLOC_EXPORT void* dlvalloc(size_t); - -/* - mallopt(int parameter_number, int parameter_value) - Sets tunable parameters The format is to provide a - (parameter-number, parameter-value) pair. mallopt then sets the - corresponding parameter to the argument value if it can (i.e., so - long as the value is meaningful), and returns 1 if successful else - 0. To workaround the fact that mallopt is specified to use int, - not size_t parameters, the value -1 is specially treated as the - maximum unsigned size_t value. - - SVID/XPG/ANSI defines four standard param numbers for mallopt, - normally defined in malloc.h. None of these are use in this malloc, - so setting them has no effect. But this malloc also supports other - options in mallopt. See below for details. Briefly, supported - parameters are as follows (listed defaults are for "typical" - configurations). - - Symbol param # default allowed param values - M_TRIM_THRESHOLD -1 2*1024*1024 any (-1 disables) - M_GRANULARITY -2 page size any power of 2 >= page size - M_MMAP_THRESHOLD -3 256*1024 any (or 0 if no MMAP support) -*/ -DLMALLOC_EXPORT int dlmallopt(int, int); - -/* - malloc_footprint(); - Returns the number of bytes obtained from the system. The total - number of bytes allocated by malloc, realloc etc., is less than this - value. Unlike mallinfo, this function returns only a precomputed - result, so can be called frequently to monitor memory consumption. - Even if locks are otherwise defined, this function does not use them, - so results might not be up to date. -*/ -DLMALLOC_EXPORT size_t dlmalloc_footprint(void); - -/* - malloc_max_footprint(); - Returns the maximum number of bytes obtained from the system. This - value will be greater than current footprint if deallocated space - has been reclaimed by the system. The peak number of bytes allocated - by malloc, realloc etc., is less than this value. Unlike mallinfo, - this function returns only a precomputed result, so can be called - frequently to monitor memory consumption. Even if locks are - otherwise defined, this function does not use them, so results might - not be up to date. -*/ -DLMALLOC_EXPORT size_t dlmalloc_max_footprint(void); - -/* - malloc_footprint_limit(); - Returns the number of bytes that the heap is allowed to obtain from - the system, returning the last value returned by - malloc_set_footprint_limit, or the maximum size_t value if - never set. The returned value reflects a permission. There is no - guarantee that this number of bytes can actually be obtained from - the system. -*/ -DLMALLOC_EXPORT size_t dlmalloc_footprint_limit(); - -/* - malloc_set_footprint_limit(); - Sets the maximum number of bytes to obtain from the system, causing - failure returns from malloc and related functions upon attempts to - exceed this value. The argument value may be subject to page - rounding to an enforceable limit; this actual value is returned. - Using an argument of the maximum possible size_t effectively - disables checks. If the argument is less than or equal to the - current malloc_footprint, then all future allocations that require - additional system memory will fail. However, invocation cannot - retroactively deallocate existing used memory. -*/ -DLMALLOC_EXPORT size_t dlmalloc_set_footprint_limit(size_t bytes); - -#if MALLOC_INSPECT_ALL -/* - malloc_inspect_all(void(*handler)(void *start, - void *end, - size_t used_bytes, - void* callback_arg), - void* arg); - Traverses the heap and calls the given handler for each managed - region, skipping all bytes that are (or may be) used for bookkeeping - purposes. Traversal does not include include chunks that have been - directly memory mapped. Each reported region begins at the start - address, and continues up to but not including the end address. The - first used_bytes of the region contain allocated data. If - used_bytes is zero, the region is unallocated. The handler is - invoked with the given callback argument. If locks are defined, they - are held during the entire traversal. It is a bad idea to invoke - other malloc functions from within the handler. - - For example, to count the number of in-use chunks with size greater - than 1000, you could write: - static int count = 0; - void count_chunks(void* start, void* end, size_t used, void* arg) { - if (used >= 1000) ++count; - } - then: - malloc_inspect_all(count_chunks, NULL); - - malloc_inspect_all is compiled only if MALLOC_INSPECT_ALL is defined. -*/ -DLMALLOC_EXPORT void dlmalloc_inspect_all(void(*handler)(void*, void *, size_t, void*), - void* arg); - -#endif /* MALLOC_INSPECT_ALL */ - -#if !NO_MALLINFO -/* - mallinfo() - Returns (by copy) a struct containing various summary statistics: - - arena: current total non-mmapped bytes allocated from system - ordblks: the number of free chunks - smblks: always zero. - hblks: current number of mmapped regions - hblkhd: total bytes held in mmapped regions - usmblks: the maximum total allocated space. This will be greater - than current total if trimming has occurred. - fsmblks: always zero - uordblks: current total allocated space (normal or mmapped) - fordblks: total free space - keepcost: the maximum number of bytes that could ideally be released - back to system via malloc_trim. ("ideally" means that - it ignores page restrictions etc.) - - Because these fields are ints, but internal bookkeeping may - be kept as longs, the reported values may wrap around zero and - thus be inaccurate. -*/ -DLMALLOC_EXPORT struct mallinfo dlmallinfo(void); -#endif /* NO_MALLINFO */ - -/* - independent_calloc(size_t n_elements, size_t element_size, void* chunks[]); - - independent_calloc is similar to calloc, but instead of returning a - single cleared space, it returns an array of pointers to n_elements - independent elements that can hold contents of size elem_size, each - of which starts out cleared, and can be independently freed, - realloc'ed etc. The elements are guaranteed to be adjacently - allocated (this is not guaranteed to occur with multiple callocs or - mallocs), which may also improve cache locality in some - applications. - - The "chunks" argument is optional (i.e., may be null, which is - probably the most typical usage). If it is null, the returned array - is itself dynamically allocated and should also be freed when it is - no longer needed. Otherwise, the chunks array must be of at least - n_elements in length. It is filled in with the pointers to the - chunks. - - In either case, independent_calloc returns this pointer array, or - null if the allocation failed. If n_elements is zero and "chunks" - is null, it returns a chunk representing an array with zero elements - (which should be freed if not wanted). - - Each element must be freed when it is no longer needed. This can be - done all at once using bulk_free. - - independent_calloc simplifies and speeds up implementations of many - kinds of pools. It may also be useful when constructing large data - structures that initially have a fixed number of fixed-sized nodes, - but the number is not known at compile time, and some of the nodes - may later need to be freed. For example: - - struct Node { int item; struct Node* next; }; - - struct Node* build_list() { - struct Node** pool; - int n = read_number_of_nodes_needed(); - if (n <= 0) return 0; - pool = (struct Node**)(independent_calloc(n, sizeof(struct Node), 0); - if (pool == 0) die(); - // organize into a linked list... - struct Node* first = pool[0]; - for (i = 0; i < n-1; ++i) - pool[i]->next = pool[i+1]; - free(pool); // Can now free the array (or not, if it is needed later) - return first; - } -*/ -DLMALLOC_EXPORT void** dlindependent_calloc(size_t, size_t, void**); - -/* - independent_comalloc(size_t n_elements, size_t sizes[], void* chunks[]); - - independent_comalloc allocates, all at once, a set of n_elements - chunks with sizes indicated in the "sizes" array. It returns - an array of pointers to these elements, each of which can be - independently freed, realloc'ed etc. The elements are guaranteed to - be adjacently allocated (this is not guaranteed to occur with - multiple callocs or mallocs), which may also improve cache locality - in some applications. - - The "chunks" argument is optional (i.e., may be null). If it is null - the returned array is itself dynamically allocated and should also - be freed when it is no longer needed. Otherwise, the chunks array - must be of at least n_elements in length. It is filled in with the - pointers to the chunks. - - In either case, independent_comalloc returns this pointer array, or - null if the allocation failed. If n_elements is zero and chunks is - null, it returns a chunk representing an array with zero elements - (which should be freed if not wanted). - - Each element must be freed when it is no longer needed. This can be - done all at once using bulk_free. - - independent_comallac differs from independent_calloc in that each - element may have a different size, and also that it does not - automatically clear elements. - - independent_comalloc can be used to speed up allocation in cases - where several structs or objects must always be allocated at the - same time. For example: - - struct Head { ... } - struct Foot { ... } - - void send_message(char* msg) { - int msglen = strlen(msg); - size_t sizes[3] = { sizeof(struct Head), msglen, sizeof(struct Foot) }; - void* chunks[3]; - if (independent_comalloc(3, sizes, chunks) == 0) - die(); - struct Head* head = (struct Head*)(chunks[0]); - char* body = (char*)(chunks[1]); - struct Foot* foot = (struct Foot*)(chunks[2]); - // ... - } - - In general though, independent_comalloc is worth using only for - larger values of n_elements. For small values, you probably won't - detect enough difference from series of malloc calls to bother. - - Overuse of independent_comalloc can increase overall memory usage, - since it cannot reuse existing noncontiguous small chunks that - might be available for some of the elements. -*/ -DLMALLOC_EXPORT void** dlindependent_comalloc(size_t, size_t*, void**); - -/* - bulk_free(void* array[], size_t n_elements) - Frees and clears (sets to null) each non-null pointer in the given - array. This is likely to be faster than freeing them one-by-one. - If footers are used, pointers that have been allocated in different - mspaces are not freed or cleared, and the count of all such pointers - is returned. For large arrays of pointers with poor locality, it - may be worthwhile to sort this array before calling bulk_free. -*/ -DLMALLOC_EXPORT size_t dlbulk_free(void**, size_t n_elements); - -/* - pvalloc(size_t n); - Equivalent to valloc(minimum-page-that-holds(n)), that is, - round up n to nearest pagesize. - */ -DLMALLOC_EXPORT void* dlpvalloc(size_t); - -/* - malloc_trim(size_t pad); - - If possible, gives memory back to the system (via negative arguments - to sbrk) if there is unused memory at the `high' end of the malloc - pool or in unused MMAP segments. You can call this after freeing - large blocks of memory to potentially reduce the system-level memory - requirements of a program. However, it cannot guarantee to reduce - memory. Under some allocation patterns, some large free blocks of - memory will be locked between two used chunks, so they cannot be - given back to the system. - - The `pad' argument to malloc_trim represents the amount of free - trailing space to leave untrimmed. If this argument is zero, only - the minimum amount of memory to maintain internal data structures - will be left. Non-zero arguments can be supplied to maintain enough - trailing space to service future expected allocations without having - to re-obtain memory from the system. - - Malloc_trim returns 1 if it actually released any memory, else 0. -*/ -DLMALLOC_EXPORT int dlmalloc_trim(size_t); - -/* - malloc_stats(); - Prints on stderr the amount of space obtained from the system (both - via sbrk and mmap), the maximum amount (which may be more than - current if malloc_trim and/or munmap got called), and the current - number of bytes allocated via malloc (or realloc, etc) but not yet - freed. Note that this is the number of bytes allocated, not the - number requested. It will be larger than the number requested - because of alignment and bookkeeping overhead. Because it includes - alignment wastage as being in use, this figure may be greater than - zero even when no user-level chunks are allocated. - - The reported current and maximum system memory can be inaccurate if - a program makes other calls to system memory allocation functions - (normally sbrk) outside of malloc. - - malloc_stats prints only the most commonly interesting statistics. - More information can be obtained by calling mallinfo. -*/ -DLMALLOC_EXPORT void dlmalloc_stats(void); - -/* - 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*); - -#endif /* ONLY_MSPACES */ - #if MSPACES /* @@ -1320,19 +865,6 @@ size_t dlmalloc_usable_size(void*); */ typedef void* mspace; -/* - create_mspace creates and returns a new independent space with the - given initial capacity, or, if 0, the default granularity size. It - returns null if there is no system memory available to create the - space. If argument locked is non-zero, the space uses a separate - lock to control access. The capacity of the space will grow - dynamically as needed to service mspace_malloc requests. You can - control the sizes of incremental increases of this space by - compiling with a different DEFAULT_GRANULARITY or dynamically - setting with mallopt(M_GRANULARITY, value). -*/ -DLMALLOC_EXPORT mspace create_mspace(size_t capacity, int locked); - /* destroy_mspace destroys the given space, and attempts to return all of its memory back to the system, returning the total number of @@ -1352,20 +884,6 @@ DLMALLOC_EXPORT size_t destroy_mspace(mspace msp); */ DLMALLOC_EXPORT mspace create_mspace_with_base(void* base, size_t capacity, int locked); -/* - mspace_track_large_chunks controls whether requests for large chunks - are allocated in their own untracked mmapped regions, separate from - others in this mspace. By default large chunks are not tracked, - which reduces fragmentation. However, such chunks are not - necessarily released to the system upon destroy_mspace. Enabling - tracking by setting to true may increase fragmentation, but avoids - leakage when relying on destroy_mspace to release all memory - allocated using this space. The function returns the previous - setting. -*/ -DLMALLOC_EXPORT int mspace_track_large_chunks(mspace msp, int enable); - - /* mspace_malloc behaves as malloc, but operates within the given space. @@ -1382,43 +900,12 @@ DLMALLOC_EXPORT void* mspace_malloc(mspace msp, size_t bytes); */ DLMALLOC_EXPORT void mspace_free(mspace msp, void* mem); -/* - mspace_realloc behaves as realloc, but operates within - the given space. - - If compiled with FOOTERS==1, mspace_realloc is not actually - needed. realloc may be called instead of mspace_realloc because - realloced chunks from any space are handled by their originating - spaces. -*/ -DLMALLOC_EXPORT void* mspace_realloc(mspace msp, void* mem, size_t newsize); - -/* - mspace_calloc behaves as calloc, but operates within - the given space. -*/ -DLMALLOC_EXPORT void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size); - /* mspace_memalign behaves as memalign, but operates within the given space. */ DLMALLOC_EXPORT void* mspace_memalign(mspace msp, size_t alignment, size_t bytes); -/* - mspace_independent_calloc behaves as independent_calloc, but - operates within the given space. -*/ -DLMALLOC_EXPORT void** mspace_independent_calloc(mspace msp, size_t n_elements, - size_t elem_size, void* chunks[]); - -/* - mspace_independent_comalloc behaves as independent_comalloc, but - operates within the given space. -*/ -DLMALLOC_EXPORT void** mspace_independent_comalloc(mspace msp, size_t n_elements, - size_t sizes[], void* chunks[]); - /* mspace_footprint() returns the number of bytes obtained from the system for this space. @@ -1445,17 +932,6 @@ DLMALLOC_EXPORT struct mallinfo mspace_mallinfo(mspace msp); */ DLMALLOC_EXPORT size_t mspace_usable_size(const void* mem); -/* - mspace_malloc_stats behaves as malloc_stats, but reports - properties of the given space. -*/ -DLMALLOC_EXPORT void mspace_malloc_stats(mspace msp); - -/* - mspace_trim behaves as malloc_trim, but - operates within the given space. -*/ -DLMALLOC_EXPORT int mspace_trim(mspace msp, size_t pad); /* An alias for mallopt. @@ -1540,39 +1016,6 @@ extern void* sbrk(ptrdiff_t); #endif /* LACKS_UNISTD_H */ /* Declarations for locking */ -#if USE_LOCKS -#ifndef WIN32 -#if defined (__SVR4) && defined (__sun) /* solaris */ -#include -#elif !defined(LACKS_SCHED_H) -#include -#endif /* solaris or LACKS_SCHED_H */ -#if (defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0) || !USE_SPIN_LOCKS -#include -#endif /* USE_RECURSIVE_LOCKS ... */ -#elif defined(_MSC_VER) -#ifndef _M_AMD64 -/* These are already defined on AMD64 builds */ -#ifdef __cplusplus -extern "C" { -#endif /* __cplusplus */ -LONG __cdecl _InterlockedCompareExchange(LONG volatile *Dest, LONG Exchange, LONG Comp); -LONG __cdecl _InterlockedExchange(LONG volatile *Target, LONG Value); -#ifdef __cplusplus -} -#endif /* __cplusplus */ -#endif /* _M_AMD64 */ -#pragma intrinsic (_InterlockedCompareExchange) -#pragma intrinsic (_InterlockedExchange) -#define interlockedcompareexchange _InterlockedCompareExchange -#define interlockedexchange _InterlockedExchange -#elif defined(WIN32) && defined(__GNUC__) -#define interlockedcompareexchange(a, b, c) __sync_val_compare_and_swap(a, c, b) -#define interlockedexchange __sync_lock_test_and_set -#endif /* Win32 */ -#else /* USE_LOCKS */ -#endif /* USE_LOCKS */ - #ifndef LOCK_AT_FORK #define LOCK_AT_FORK 0 #endif @@ -1684,86 +1127,11 @@ unsigned char _BitScanReverse(unsigned long *index, unsigned long mask); #define MFAIL ((void*)(MAX_SIZE_T)) #define CMFAIL ((char*)(MFAIL)) /* defined for convenience */ -#if HAVE_MMAP - -#ifndef WIN32 -#define MUNMAP_DEFAULT(a, s) munmap((a), (s)) -#define MMAP_PROT (PROT_READ|PROT_WRITE) -#if !defined(MAP_ANONYMOUS) && defined(MAP_ANON) -#define MAP_ANONYMOUS MAP_ANON -#endif /* MAP_ANON */ -#ifdef MAP_ANONYMOUS -#define MMAP_FLAGS (MAP_PRIVATE|MAP_ANONYMOUS) -#define MMAP_DEFAULT(s) mmap(0, (s), MMAP_PROT, MMAP_FLAGS, -1, 0) -#else /* MAP_ANONYMOUS */ -/* - Nearly all versions of mmap support MAP_ANONYMOUS, so the following - is unlikely to be needed, but is supplied just in case. -*/ -#define MMAP_FLAGS (MAP_PRIVATE) -static int dev_zero_fd = -1; /* Cached file descriptor for /dev/zero. */ -#define MMAP_DEFAULT(s) ((dev_zero_fd < 0) ? \ - (dev_zero_fd = open("/dev/zero", O_RDWR), \ - mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0)) : \ - mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0)) -#endif /* MAP_ANONYMOUS */ - -#define DIRECT_MMAP_DEFAULT(s) MMAP_DEFAULT(s) - -#else /* WIN32 */ - -/* Win32 MMAP via VirtualAlloc */ -static FORCEINLINE void* win32mmap(size_t size) { - void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT, PAGE_READWRITE); - return (ptr != 0)? ptr: MFAIL; -} - -/* For direct MMAP, use MEM_TOP_DOWN to minimize interference */ -static FORCEINLINE void* win32direct_mmap(size_t size) { - void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT|MEM_TOP_DOWN, - PAGE_READWRITE); - return (ptr != 0)? ptr: MFAIL; -} - -/* This function supports releasing coalesed segments */ -static FORCEINLINE int win32munmap(void* ptr, size_t size) { - MEMORY_BASIC_INFORMATION minfo; - char* cptr = (char*)ptr; - while (size) { - if (VirtualQuery(cptr, &minfo, sizeof(minfo)) == 0) - return -1; - if (minfo.BaseAddress != cptr || minfo.AllocationBase != cptr || - minfo.State != MEM_COMMIT || minfo.RegionSize > size) - return -1; - if (VirtualFree(cptr, 0, MEM_RELEASE) == 0) - return -1; - cptr += minfo.RegionSize; - size -= minfo.RegionSize; - } - return 0; -} - -#define MMAP_DEFAULT(s) win32mmap(s) -#define MUNMAP_DEFAULT(a, s) win32munmap((a), (s)) -#define DIRECT_MMAP_DEFAULT(s) win32direct_mmap(s) -#endif /* WIN32 */ -#endif /* HAVE_MMAP */ - -#if HAVE_MREMAP -#ifndef WIN32 -#define MREMAP_DEFAULT(addr, osz, nsz, mv) mremap((addr), (osz), (nsz), (mv)) -#endif /* WIN32 */ -#endif /* HAVE_MREMAP */ - /** * Define CALL_MORECORE */ #if HAVE_MORECORE - #ifdef MORECORE - #define CALL_MORECORE(S) MORECORE(S) - #else /* MORECORE */ - #define CALL_MORECORE(S) MORECORE_DEFAULT(S) - #endif /* MORECORE */ + #error "Code removed in rocSHMEM" #else /* HAVE_MORECORE */ #define CALL_MORECORE(S) MFAIL #endif /* HAVE_MORECORE */ @@ -1772,23 +1140,7 @@ static FORCEINLINE int win32munmap(void* ptr, size_t size) { * 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 */ + #error "Code removed in rocSHMEM" #else /* HAVE_MMAP */ #define USE_MMAP_BIT (SIZE_T_ZERO) @@ -1804,11 +1156,7 @@ static FORCEINLINE int win32munmap(void* ptr, size_t size) { * 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 */ + #error "Code removed in rocSHMEM" #else /* HAVE_MMAP && HAVE_MREMAP */ #define CALL_MREMAP(addr, osz, nsz, mv) MFAIL #endif /* HAVE_MMAP && HAVE_MREMAP */ @@ -1858,239 +1206,7 @@ static FORCEINLINE int win32munmap(void* ptr, size_t size) { #define RELEASE_MALLOC_GLOBAL_LOCK() #else -#if USE_LOCKS > 1 -/* ----------------------- User-defined locks ------------------------ */ -/* Define your own lock implementation here */ -/* #define INITIAL_LOCK(lk) ... */ -/* #define DESTROY_LOCK(lk) ... */ -/* #define ACQUIRE_LOCK(lk) ... */ -/* #define RELEASE_LOCK(lk) ... */ -/* #define TRY_LOCK(lk) ... */ -/* static MLOCK_T malloc_global_mutex = ... */ - -#elif USE_SPIN_LOCKS - -/* First, define CAS_LOCK and CLEAR_LOCK on ints */ -/* Note CAS_LOCK defined to return 0 on success */ - -#if defined(__GNUC__)&& (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 1)) -#define CAS_LOCK(sl) __sync_lock_test_and_set(sl, 1) -#define CLEAR_LOCK(sl) __sync_lock_release(sl) - -#elif (defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))) -/* Custom spin locks for older gcc on x86 */ -static FORCEINLINE int x86_cas_lock(int *sl) { - int ret; - int val = 1; - int cmp = 0; - __asm__ __volatile__ ("lock; cmpxchgl %1, %2" - : "=a" (ret) - : "r" (val), "m" (*(sl)), "0"(cmp) - : "memory", "cc"); - return ret; -} - -static FORCEINLINE void x86_clear_lock(int* sl) { - assert(*sl != 0); - int prev = 0; - int ret; - __asm__ __volatile__ ("lock; xchgl %0, %1" - : "=r" (ret) - : "m" (*(sl)), "0"(prev) - : "memory"); -} - -#define CAS_LOCK(sl) x86_cas_lock(sl) -#define CLEAR_LOCK(sl) x86_clear_lock(sl) - -#else /* Win32 MSC */ -#define CAS_LOCK(sl) interlockedexchange(sl, (LONG)1) -#define CLEAR_LOCK(sl) interlockedexchange (sl, (LONG)0) - -#endif /* ... gcc spins locks ... */ - -/* How to yield for a spin lock */ -#define SPINS_PER_YIELD 63 -#if defined(_MSC_VER) -#define SLEEP_EX_DURATION 50 /* delay for yield/sleep */ -#define SPIN_LOCK_YIELD SleepEx(SLEEP_EX_DURATION, FALSE) -#elif defined (__SVR4) && defined (__sun) /* solaris */ -#define SPIN_LOCK_YIELD thr_yield(); -#elif !defined(LACKS_SCHED_H) -#define SPIN_LOCK_YIELD sched_yield(); -#else -#define SPIN_LOCK_YIELD -#endif /* ... yield ... */ - -#if !defined(USE_RECURSIVE_LOCKS) || USE_RECURSIVE_LOCKS == 0 -/* Plain spin locks use single word (embedded in malloc_states) */ -static int spin_acquire_lock(int *sl) { - int spins = 0; - while (*(volatile int *)sl != 0 || CAS_LOCK(sl)) { - if ((++spins & SPINS_PER_YIELD) == 0) { - SPIN_LOCK_YIELD; - } - } - return 0; -} - -#define MLOCK_T int -#define TRY_LOCK(sl) !CAS_LOCK(sl) -#define RELEASE_LOCK(sl) CLEAR_LOCK(sl) -#define ACQUIRE_LOCK(sl) (CAS_LOCK(sl)? spin_acquire_lock(sl) : 0) -#define INITIAL_LOCK(sl) (*sl = 0) -#define DESTROY_LOCK(sl) (0) -static MLOCK_T malloc_global_mutex = 0; - -#else /* USE_RECURSIVE_LOCKS */ -/* types for lock owners */ -#ifdef WIN32 -#define THREAD_ID_T DWORD -#define CURRENT_THREAD GetCurrentThreadId() -#define EQ_OWNER(X,Y) ((X) == (Y)) -#else -/* - Note: the following assume that pthread_t is a type that can be - initialized to (casted) zero. If this is not the case, you will need to - somehow redefine these or not use spin locks. -*/ -#define THREAD_ID_T pthread_t -#define CURRENT_THREAD pthread_self() -#define EQ_OWNER(X,Y) pthread_equal(X, Y) -#endif - -struct malloc_recursive_lock { - int sl; - unsigned int c; - THREAD_ID_T threadid; -}; - -#define MLOCK_T struct malloc_recursive_lock -static MLOCK_T malloc_global_mutex = { 0, 0, (THREAD_ID_T)0}; - -static FORCEINLINE void recursive_release_lock(MLOCK_T *lk) { - assert(lk->sl != 0); - if (--lk->c == 0) { - CLEAR_LOCK(&lk->sl); - } -} - -static FORCEINLINE int recursive_acquire_lock(MLOCK_T *lk) { - THREAD_ID_T mythreadid = CURRENT_THREAD; - int spins = 0; - for (;;) { - if (*((volatile int *)(&lk->sl)) == 0) { - if (!CAS_LOCK(&lk->sl)) { - lk->threadid = mythreadid; - lk->c = 1; - return 0; - } - } - else if (EQ_OWNER(lk->threadid, mythreadid)) { - ++lk->c; - return 0; - } - if ((++spins & SPINS_PER_YIELD) == 0) { - SPIN_LOCK_YIELD; - } - } -} - -static FORCEINLINE int recursive_try_lock(MLOCK_T *lk) { - THREAD_ID_T mythreadid = CURRENT_THREAD; - if (*((volatile int *)(&lk->sl)) == 0) { - if (!CAS_LOCK(&lk->sl)) { - lk->threadid = mythreadid; - lk->c = 1; - return 1; - } - } - else if (EQ_OWNER(lk->threadid, mythreadid)) { - ++lk->c; - return 1; - } - return 0; -} - -#define RELEASE_LOCK(lk) recursive_release_lock(lk) -#define TRY_LOCK(lk) recursive_try_lock(lk) -#define ACQUIRE_LOCK(lk) recursive_acquire_lock(lk) -#define INITIAL_LOCK(lk) ((lk)->threadid = (THREAD_ID_T)0, (lk)->sl = 0, (lk)->c = 0) -#define DESTROY_LOCK(lk) (0) -#endif /* USE_RECURSIVE_LOCKS */ - -#elif defined(WIN32) /* Win32 critical sections */ -#define MLOCK_T CRITICAL_SECTION -#define ACQUIRE_LOCK(lk) (EnterCriticalSection(lk), 0) -#define RELEASE_LOCK(lk) LeaveCriticalSection(lk) -#define TRY_LOCK(lk) TryEnterCriticalSection(lk) -#define INITIAL_LOCK(lk) (!InitializeCriticalSectionAndSpinCount((lk), 0x80000000|4000)) -#define DESTROY_LOCK(lk) (DeleteCriticalSection(lk), 0) -#define NEED_GLOBAL_LOCK_INIT - -static MLOCK_T malloc_global_mutex; -static volatile LONG malloc_global_mutex_status; - -/* Use spin loop to initialize global lock */ -static void init_malloc_global_mutex() { - for (;;) { - long stat = malloc_global_mutex_status; - if (stat > 0) - return; - /* transition to < 0 while initializing, then to > 0) */ - if (stat == 0 && - interlockedcompareexchange(&malloc_global_mutex_status, (LONG)-1, (LONG)0) == 0) { - InitializeCriticalSection(&malloc_global_mutex); - interlockedexchange(&malloc_global_mutex_status, (LONG)1); - return; - } - SleepEx(0, FALSE); - } -} - -#else /* pthreads-based locks */ -#define MLOCK_T pthread_mutex_t -#define ACQUIRE_LOCK(lk) pthread_mutex_lock(lk) -#define RELEASE_LOCK(lk) pthread_mutex_unlock(lk) -#define TRY_LOCK(lk) (!pthread_mutex_trylock(lk)) -#define INITIAL_LOCK(lk) pthread_init_lock(lk) -#define DESTROY_LOCK(lk) pthread_mutex_destroy(lk) - -#if defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0 && defined(linux) && !defined(PTHREAD_MUTEX_RECURSIVE) -/* Cope with old-style linux recursive lock initialization by adding */ -/* skipped internal declaration from pthread.h */ -extern int pthread_mutexattr_setkind_np __P ((pthread_mutexattr_t *__attr, - int __kind)); -#define PTHREAD_MUTEX_RECURSIVE PTHREAD_MUTEX_RECURSIVE_NP -#define pthread_mutexattr_settype(x,y) pthread_mutexattr_setkind_np(x,y) -#endif /* USE_RECURSIVE_LOCKS ... */ - -static MLOCK_T malloc_global_mutex = PTHREAD_MUTEX_INITIALIZER; - -static int pthread_init_lock (MLOCK_T *lk) { - pthread_mutexattr_t attr; - if (pthread_mutexattr_init(&attr)) return 1; -#if defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0 - if (pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_RECURSIVE)) return 1; -#endif - if (pthread_mutex_init(lk, &attr)) return 1; - if (pthread_mutexattr_destroy(&attr)) return 1; - return 0; -} - -#endif /* ... lock types ... */ - -/* Common code for all lock types */ -#define USE_LOCK_BIT (2U) - -#ifndef ACQUIRE_MALLOC_GLOBAL_LOCK -#define ACQUIRE_MALLOC_GLOBAL_LOCK() ACQUIRE_LOCK(&malloc_global_mutex); -#endif - -#ifndef RELEASE_MALLOC_GLOBAL_LOCK -#define RELEASE_MALLOC_GLOBAL_LOCK() RELEASE_LOCK(&malloc_global_mutex); -#endif - +#error "Code removed in rocSHMEM" #endif /* USE_LOCKS */ /* ----------------------- Chunk representations ------------------------ */ @@ -2642,9 +1758,6 @@ struct malloc_state { size_t max_footprint; size_t footprint_limit; /* zero means no limit */ flag_t mflags; -#if USE_LOCKS - MLOCK_T mutex; /* locate lock among fields that rarely change */ -#endif /* USE_LOCKS */ msegment seg; void* extp; /* Unused but available for extensions */ size_t exts; @@ -2675,15 +1788,6 @@ static struct malloc_params mparams; /* Ensure mparams initialized */ #define ensure_initialization() (void)(mparams.magic != 0 || init_mparams()) -#if !ONLY_MSPACES - -/* The global malloc_state used for all non-"mspace" calls */ -static struct malloc_state _gm_; -#define gm (&_gm_) -#define is_global(M) ((M) == &_gm_) - -#endif /* !ONLY_MSPACES */ - #define is_initialized(M) ((M)->top != 0) /* -------------------------- system alloc setup ------------------------- */ @@ -2846,26 +1950,6 @@ static void reset_on_error(mstate m); #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 ---------------------------- */ @@ -3195,11 +2279,6 @@ static int init_mparams(void) { mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT|USE_NONCONTIGUOUS_BIT; #endif /* MORECORE_CONTIGUOUS */ -#if !ONLY_MSPACES - /* Set up lock for main malloc area */ - gm->mflags = mparams.default_mflags; - (void)INITIAL_LOCK(&gm->mutex); -#endif #if LOCK_AT_FORK pthread_atfork(&pre_fork, &post_fork_parent, &post_fork_child); #endif @@ -3258,275 +2337,6 @@ static int change_mparam(int param_number, int value) { } } -#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 @@ -3571,36 +2381,7 @@ static struct mallinfo internal_mallinfo(mstate m) { #endif /* !NO_MALLINFO */ #if !NO_MALLOC_STATS -static void internal_malloc_stats(mstate m) { - ensure_initialization(); - if (!PREACTION(m)) { - size_t maxfp = 0; - size_t fp = 0; - size_t used = 0; - check_malloc_state(m); - if (is_initialized(m)) { - msegmentptr s = &m->seg; - maxfp = m->max_footprint; - fp = m->footprint; - used = fp - (m->topsize + TOP_FOOT_SIZE); - - while (s != 0) { - mchunkptr q = align_as_chunk(s->base); - while (segment_holds(s, q) && - q != m->top && q->head != FENCEPOST_HEAD) { - if (!is_inuse(q)) - used -= chunksize(q); - q = next_chunk(q); - } - s = s->next; - } - } - POSTACTION(m); /* drop lock */ - fprintf(stderr, "max system bytes = %10lu\n", (unsigned long)(maxfp)); - fprintf(stderr, "system bytes = %10lu\n", (unsigned long)(fp)); - fprintf(stderr, "in use bytes = %10lu\n", (unsigned long)(used)); - } -} +#error "Code removed in rocSHMEM" #endif /* NO_MALLOC_STATS */ /* ----------------------- Operations on smallbins ----------------------- */ @@ -3846,96 +2627,8 @@ static void internal_malloc_stats(mstate m) { #if ONLY_MSPACES #define internal_malloc(m, b) mspace_malloc(m, b) #define internal_free(m, mem) mspace_free(m,mem); -#else /* ONLY_MSPACES */ -#if MSPACES -#define internal_malloc(m, b)\ - ((m == gm)? dlmalloc(b) : mspace_malloc(m, b)) -#define internal_free(m, mem)\ - if (m == gm) dlfree(mem); else mspace_free(m,mem); -#else /* MSPACES */ -#define internal_malloc(m, b) dlmalloc(b) -#define internal_free(m, mem) dlfree(mem) -#endif /* MSPACES */ #endif /* ONLY_MSPACES */ -/* ----------------------- Direct-mmapping chunks ----------------------- */ - -/* - Directly mmapped chunks are set up with an offset to the start of - the mmapped region stored in the prev_foot field of the chunk. This - allows reconstruction of the required argument to MUNMAP when freed, - and also allows adjustment of the returned chunk to meet alignment - requirements (especially in memalign). -*/ - -/* Malloc using mmap */ -static void* mmap_alloc(mstate m, size_t nb) { - size_t mmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK); - if (m->footprint_limit != 0) { - size_t fp = m->footprint + mmsize; - if (fp <= m->footprint || fp > m->footprint_limit) - return 0; - } - if (mmsize > nb) { /* Check for wrap around 0 */ - char* mm = (char*)(CALL_DIRECT_MMAP(mmsize)); - if (mm != CMFAIL) { - size_t offset = align_offset(chunk2mem(mm)); - size_t psize = mmsize - offset - MMAP_FOOT_PAD; - mchunkptr p = (mchunkptr)(mm + offset); - p->prev_foot = offset; - p->head = psize; - mark_inuse_foot(m, p, psize); - chunk_plus_offset(p, psize)->head = FENCEPOST_HEAD; - chunk_plus_offset(p, psize+SIZE_T_SIZE)->head = 0; - - if (m->least_addr == 0 || mm < m->least_addr) - m->least_addr = mm; - if ((m->footprint += mmsize) > m->max_footprint) - m->max_footprint = m->footprint; - assert(is_aligned(chunk2mem(p))); - check_mmapped_chunk(m, p); - return chunk2mem(p); - } - } - return 0; -} - -/* Realloc using mmap */ -static mchunkptr mmap_resize(mstate m, mchunkptr oldp, size_t nb, int flags) { - size_t oldsize = chunksize(oldp); - (void)flags; /* placate people compiling -Wunused */ - if (is_small(nb)) /* Can't shrink mmap regions below small size */ - return 0; - /* Keep old chunk if big enough but not too big */ - if (oldsize >= nb + SIZE_T_SIZE && - (oldsize - nb) <= (mparams.granularity << 1)) - return oldp; - else { - size_t offset = oldp->prev_foot; - size_t oldmmsize = oldsize + offset + MMAP_FOOT_PAD; - size_t newmmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK); - char* cp = (char*)CALL_MREMAP((char*)oldp - offset, - oldmmsize, newmmsize, flags); - if (cp != CMFAIL) { - mchunkptr newp = (mchunkptr)(cp + offset); - size_t psize = newmmsize - offset - MMAP_FOOT_PAD; - newp->head = psize; - mark_inuse_foot(m, newp, psize); - chunk_plus_offset(newp, psize)->head = FENCEPOST_HEAD; - chunk_plus_offset(newp, psize+SIZE_T_SIZE)->head = 0; - - if (cp < m->least_addr) - m->least_addr = cp; - if ((m->footprint += newmmsize - oldmmsize) > m->max_footprint) - m->max_footprint = m->footprint; - check_mmapped_chunk(m, newp); - return newp; - } - } - return 0; -} - - /* -------------------------- mspace management -------------------------- */ /* Initialize top chunk and its size */ @@ -3963,25 +2656,6 @@ static void init_bins(mstate m) { } } -#if PROCEED_ON_ERROR - -/* default corruption action */ -static void reset_on_error(mstate m) { - int i; - ++malloc_corruption_error_count; - /* Reinitialize fields to forget about all memory */ - m->smallmap = m->treemap = 0; - m->dvsize = m->topsize = 0; - m->seg.base = 0; - m->seg.size = 0; - m->seg.next = 0; - m->top = m->dv = 0; - for (i = 0; i < NTREEBINS; ++i) - *treebin_at(m, i) = 0; - init_bins(m); -} -#endif /* PROCEED_ON_ERROR */ - /* Allocate chunk and prepend remainder with chunk in successor base. */ static void* prepend_alloc(mstate m, char* newbase, char* oldbase, size_t nb) { @@ -4088,13 +2762,6 @@ static void* sys_alloc(mstate m, size_t nb) { ensure_initialization(); - /* Directly map large chunks, but only if already initialized */ - if (use_mmap(m) && nb >= mparams.mmap_threshold && m->topsize != 0) { - void* mem = mmap_alloc(m, nb); - if (mem != 0) - return mem; - } - asize = granularity_align(nb + SYS_ALLOC_PADDING); if (asize <= nb) return 0; /* wraparound */ @@ -4187,33 +2854,6 @@ static void* sys_alloc(mstate m, size_t nb) { RELEASE_MALLOC_GLOBAL_LOCK(); } - if (HAVE_MMAP && tbase == CMFAIL) { /* Try MMAP */ - char* mp = (char*)(CALL_MMAP(asize)); - if (mp != CMFAIL) { - tbase = mp; - tsize = asize; - mmap_flag = USE_MMAP_BIT; - } - } - - if (HAVE_MORECORE && tbase == CMFAIL) { /* Try noncontiguous MORECORE */ - if (asize < HALF_MAX_SIZE_T) { - char* br = CMFAIL; - char* end = CMFAIL; - ACQUIRE_MALLOC_GLOBAL_LOCK(); - br = (char*)(CALL_MORECORE(asize)); - end = (char*)(CALL_MORECORE(0)); - RELEASE_MALLOC_GLOBAL_LOCK(); - if (br != CMFAIL && end != CMFAIL && br < end) { - size_t ssize = end - br; - if (ssize > nb + TOP_FOOT_SIZE) { - tbase = br; - tsize = ssize; - } - } - } - } - if (tbase != CMFAIL) { if ((m->footprint += tsize) > m->max_footprint) @@ -4228,11 +2868,6 @@ static void* sys_alloc(mstate m, size_t nb) { 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)); @@ -4351,38 +2986,6 @@ static int sys_trim(mstate m, size_t pad) { 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; - (void)newsize; /* placate people compiling -Wunused-variable */ - /* 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; @@ -4391,10 +2994,6 @@ static int sys_trim(mstate m, size_t pad) { } } - /* 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; @@ -4585,354 +3184,8 @@ static void* tmalloc_small(mstate m, size_t nb) { return 0; } -#if !ONLY_MSPACES - -void* dlmalloc(size_t bytes) { - /* - Basic algorithm: - If a small request (< 256 bytes minus per-chunk overhead): - 1. If one exists, use a remainderless chunk in associated smallbin. - (Remainderless means that there are too few excess bytes to - represent as a chunk.) - 2. If it is big enough, use the dv chunk, which is normally the - chunk adjacent to the one used for the most recent small request. - 3. If one exists, split the smallest available chunk in a bin, - saving remainder in dv. - 4. If it is big enough, use the top chunk. - 5. If available, get memory from system and use it - Otherwise, for a large request: - 1. Find the smallest available binned chunk that fits, and use it - if it is better fitting than dv chunk, splitting if necessary. - 2. If better fitting than any binned chunk, use the dv chunk. - 3. If it is big enough, use the top chunk. - 4. If request size >= mmap threshold, try to directly mmap this chunk. - 5. If available, get memory from system and use it - - The ugly goto's here ensure that postaction occurs along all paths. - */ - -#if USE_LOCKS - ensure_initialization(); /* initialize in sys_alloc if not using locks */ -#endif - - if (!PREACTION(gm)) { - void* mem; - size_t nb; - if (bytes <= MAX_SMALL_REQUEST) { - bindex_t idx; - binmap_t smallbits; - nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes); - idx = small_index(nb); - smallbits = gm->smallmap >> idx; - - if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */ - mchunkptr b, p; - idx += ~smallbits & 1; /* Uses next bin if idx empty */ - b = smallbin_at(gm, idx); - p = b->fd; - assert(chunksize(p) == small_index2size(idx)); - unlink_first_small_chunk(gm, b, p, idx); - set_inuse_and_pinuse(gm, p, small_index2size(idx)); - mem = chunk2mem(p); - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - - else if (nb > gm->dvsize) { - if (smallbits != 0) { /* Use chunk in next nonempty smallbin */ - mchunkptr b, p, r; - size_t rsize; - bindex_t i; - binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx)); - binmap_t leastbit = least_bit(leftbits); - compute_bit2idx(leastbit, i); - b = smallbin_at(gm, i); - p = b->fd; - assert(chunksize(p) == small_index2size(i)); - unlink_first_small_chunk(gm, b, p, i); - rsize = small_index2size(i) - nb; - /* Fit here cannot be remainderless if 4byte sizes */ - if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE) - set_inuse_and_pinuse(gm, p, small_index2size(i)); - else { - set_size_and_pinuse_of_inuse_chunk(gm, p, nb); - r = chunk_plus_offset(p, nb); - set_size_and_pinuse_of_free_chunk(r, rsize); - replace_dv(gm, r, rsize); - } - mem = chunk2mem(p); - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - - else if (gm->treemap != 0 && (mem = tmalloc_small(gm, nb)) != 0) { - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - } - } - else if (bytes >= MAX_REQUEST) - nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */ - else { - nb = pad_request(bytes); - if (gm->treemap != 0 && (mem = tmalloc_large(gm, nb)) != 0) { - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - } - - if (nb <= gm->dvsize) { - size_t rsize = gm->dvsize - nb; - mchunkptr p = gm->dv; - if (rsize >= MIN_CHUNK_SIZE) { /* split dv */ - mchunkptr r = gm->dv = chunk_plus_offset(p, nb); - gm->dvsize = rsize; - set_size_and_pinuse_of_free_chunk(r, rsize); - set_size_and_pinuse_of_inuse_chunk(gm, p, nb); - } - else { /* exhaust dv */ - size_t dvs = gm->dvsize; - gm->dvsize = 0; - gm->dv = 0; - set_inuse_and_pinuse(gm, p, dvs); - } - mem = chunk2mem(p); - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - - else if (nb < gm->topsize) { /* Split top */ - size_t rsize = gm->topsize -= nb; - mchunkptr p = gm->top; - mchunkptr r = gm->top = chunk_plus_offset(p, nb); - r->head = rsize | PINUSE_BIT; - set_size_and_pinuse_of_inuse_chunk(gm, p, nb); - mem = chunk2mem(p); - check_top_chunk(gm, gm->top); - check_malloced_chunk(gm, mem, nb); - goto postaction; - } - - mem = sys_alloc(gm, nb); - - postaction: - POSTACTION(gm); - return mem; - } - - return 0; -} - -/* ---------------------------- free --------------------------- */ - -void dlfree(void* mem) { - /* - Consolidate freed chunks with preceeding or succeeding bordering - free chunks, if they exist, and then place in a bin. Intermixed - with special cases for top, dv, mmapped chunks, and usage errors. - */ - - if (mem != 0) { - mchunkptr p = mem2chunk(mem); -#if FOOTERS - mstate fm = get_mstate_for(p); - if (!ok_magic(fm)) { - USAGE_ERROR_ACTION(fm, p); - return; - } -#else /* FOOTERS */ -#define fm gm -#endif /* FOOTERS */ - if (!PREACTION(fm)) { - check_inuse_chunk(fm, p); - if (RTCHECK(ok_address(fm, p) && ok_inuse(p))) { - size_t psize = chunksize(p); - mchunkptr next = chunk_plus_offset(p, psize); - if (!pinuse(p)) { - size_t prevsize = p->prev_foot; - if (is_mmapped(p)) { - psize += prevsize + MMAP_FOOT_PAD; - if (CALL_MUNMAP((char*)p - prevsize, psize) == 0) - fm->footprint -= psize; - goto postaction; - } - else { - mchunkptr prev = chunk_minus_offset(p, prevsize); - psize += prevsize; - p = prev; - if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */ - if (p != fm->dv) { - unlink_chunk(fm, p, prevsize); - } - else if ((next->head & INUSE_BITS) == INUSE_BITS) { - fm->dvsize = psize; - set_free_with_pinuse(p, psize, next); - goto postaction; - } - } - else - goto erroraction; - } - } - - if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) { - if (!cinuse(next)) { /* consolidate forward */ - if (next == fm->top) { - size_t tsize = fm->topsize += psize; - fm->top = p; - p->head = tsize | PINUSE_BIT; - if (p == fm->dv) { - fm->dv = 0; - fm->dvsize = 0; - } - if (should_trim(fm, tsize)) - sys_trim(fm, 0); - goto postaction; - } - else if (next == fm->dv) { - size_t dsize = fm->dvsize += psize; - fm->dv = p; - set_size_and_pinuse_of_free_chunk(p, dsize); - goto postaction; - } - else { - size_t nsize = chunksize(next); - psize += nsize; - unlink_chunk(fm, next, nsize); - set_size_and_pinuse_of_free_chunk(p, psize); - if (p == fm->dv) { - fm->dvsize = psize; - goto postaction; - } - } - } - else - set_free_with_pinuse(p, psize, next); - - if (is_small(psize)) { - insert_small_chunk(fm, p, psize); - check_free_chunk(fm, p); - } - else { - tchunkptr tp = (tchunkptr)p; - insert_large_chunk(fm, tp, psize); - check_free_chunk(fm, p); - if (--fm->release_checks == 0) - release_unused_segments(fm); - } - goto postaction; - } - } - erroraction: - USAGE_ERROR_ACTION(fm, p); - postaction: - POSTACTION(fm); - } - } -#if !FOOTERS -#undef fm -#endif /* FOOTERS */ -} - -void* dlcalloc(size_t n_elements, size_t elem_size) { - void* mem; - size_t req = 0; - if (n_elements != 0) { - req = n_elements * elem_size; - if (((n_elements | elem_size) & ~(size_t)0xffff) && - (req / n_elements != elem_size)) - req = MAX_SIZE_T; /* force downstream failure on overflow */ - } - mem = dlmalloc(req); - if (mem != 0 && calloc_must_clear(mem2chunk(mem))) - memset(mem, 0, req); - return mem; -} - -#endif /* !ONLY_MSPACES */ - /* ------------ Internal support for realloc, memalign, etc -------------- */ -/* Try to realloc; only in-place unless can_move true */ -static mchunkptr try_realloc_chunk(mstate m, mchunkptr p, size_t nb, - int can_move) { - mchunkptr newp = 0; - size_t oldsize = chunksize(p); - mchunkptr next = chunk_plus_offset(p, oldsize); - if (RTCHECK(ok_address(m, p) && ok_inuse(p) && - ok_next(p, next) && ok_pinuse(next))) { - if (is_mmapped(p)) { - newp = mmap_resize(m, p, nb, can_move); - } - else if (oldsize >= nb) { /* already big enough */ - size_t rsize = oldsize - nb; - if (rsize >= MIN_CHUNK_SIZE) { /* split off remainder */ - mchunkptr r = chunk_plus_offset(p, nb); - set_inuse(m, p, nb); - set_inuse(m, r, rsize); - dispose_chunk(m, r, rsize); - } - newp = p; - } - else if (next == m->top) { /* extend into top */ - if (oldsize + m->topsize > nb) { - size_t newsize = oldsize + m->topsize; - size_t newtopsize = newsize - nb; - mchunkptr newtop = chunk_plus_offset(p, nb); - set_inuse(m, p, nb); - newtop->head = newtopsize |PINUSE_BIT; - m->top = newtop; - m->topsize = newtopsize; - newp = p; - } - } - else if (next == m->dv) { /* extend into dv */ - size_t dvs = m->dvsize; - if (oldsize + dvs >= nb) { - size_t dsize = oldsize + dvs - nb; - if (dsize >= MIN_CHUNK_SIZE) { - mchunkptr r = chunk_plus_offset(p, nb); - mchunkptr n = chunk_plus_offset(r, dsize); - set_inuse(m, p, nb); - set_size_and_pinuse_of_free_chunk(r, dsize); - clear_pinuse(n); - m->dvsize = dsize; - m->dv = r; - } - else { /* exhaust dv */ - size_t newsize = oldsize + dvs; - set_inuse(m, p, newsize); - m->dvsize = 0; - m->dv = 0; - } - newp = p; - } - } - else if (!cinuse(next)) { /* extend into next free chunk */ - size_t nextsize = chunksize(next); - if (oldsize + nextsize >= nb) { - size_t rsize = oldsize + nextsize - nb; - unlink_chunk(m, next, nextsize); - if (rsize < MIN_CHUNK_SIZE) { - size_t newsize = oldsize + nextsize; - set_inuse(m, p, newsize); - } - else { - mchunkptr r = chunk_plus_offset(p, nb); - set_inuse(m, p, nb); - set_inuse(m, r, rsize); - dispose_chunk(m, r, rsize); - } - newp = p; - } - } - } - else { - USAGE_ERROR_ACTION(m, chunk2mem(p)); - } - return newp; -} - static void* internal_memalign(mstate m, size_t alignment, size_t bytes) { void* mem = 0; if (alignment < MIN_CHUNK_SIZE) /* must be at least a minimum chunk size */ @@ -5007,437 +3260,6 @@ static void* internal_memalign(mstate m, size_t alignment, size_t bytes) { return mem; } -/* - Common support for independent_X routines, handling - all of the combinations that can result. - The opts arg has: - bit 0 set if all elements are same size (using sizes[0]) - bit 1 set if elements should be zeroed -*/ -static void** ialloc(mstate m, - size_t n_elements, - size_t* sizes, - int opts, - void* chunks[]) { - - size_t element_size; /* chunksize of each element, if all same */ - size_t contents_size; /* total size of elements */ - size_t array_size; /* request size of pointer array */ - void* mem; /* malloced aggregate space */ - mchunkptr p; /* corresponding chunk */ - size_t remainder_size; /* remaining bytes while splitting */ - void** marray; /* either "chunks" or malloced ptr array */ - mchunkptr array_chunk; /* chunk for malloced ptr array */ - flag_t was_enabled; /* to disable mmap */ - size_t size; - size_t i; - - ensure_initialization(); - /* compute array length, if needed */ - if (chunks != 0) { - if (n_elements == 0) - return chunks; /* nothing to do */ - marray = chunks; - array_size = 0; - } - else { - /* if empty req, must still return chunk representing empty array */ - if (n_elements == 0) - return (void**)internal_malloc(m, 0); - marray = 0; - array_size = request2size(n_elements * (sizeof(void*))); - } - - /* compute total element size */ - if (opts & 0x1) { /* all-same-size */ - element_size = request2size(*sizes); - contents_size = n_elements * element_size; - } - else { /* add up all the sizes */ - element_size = 0; - contents_size = 0; - for (i = 0; i != n_elements; ++i) - contents_size += request2size(sizes[i]); - } - - size = contents_size + array_size; - - /* - Allocate the aggregate chunk. First disable direct-mmapping so - malloc won't use it, since we would not be able to later - free/realloc space internal to a segregated mmap region. - */ - was_enabled = use_mmap(m); - disable_mmap(m); - mem = internal_malloc(m, size - CHUNK_OVERHEAD); - if (was_enabled) - enable_mmap(m); - if (mem == 0) - return 0; - - if (PREACTION(m)) return 0; - p = mem2chunk(mem); - remainder_size = chunksize(p); - - assert(!is_mmapped(p)); - - if (opts & 0x2) { /* optionally clear the elements */ - memset((size_t*)mem, 0, remainder_size - SIZE_T_SIZE - array_size); - } - - /* If not provided, allocate the pointer array as final part of chunk */ - if (marray == 0) { - size_t array_chunk_size; - array_chunk = chunk_plus_offset(p, contents_size); - array_chunk_size = remainder_size - contents_size; - marray = (void**) (chunk2mem(array_chunk)); - set_size_and_pinuse_of_inuse_chunk(m, array_chunk, array_chunk_size); - remainder_size = contents_size; - } - - /* split out elements */ - for (i = 0; ; ++i) { - marray[i] = chunk2mem(p); - if (i != n_elements-1) { - if (element_size != 0) - size = element_size; - else - size = request2size(sizes[i]); - remainder_size -= size; - set_size_and_pinuse_of_inuse_chunk(m, p, size); - p = chunk_plus_offset(p, size); - } - else { /* the final element absorbs any overallocation slop */ - set_size_and_pinuse_of_inuse_chunk(m, p, remainder_size); - break; - } - } - -#if DEBUG - if (marray != chunks) { - /* final element must have exactly exhausted chunk */ - if (element_size != 0) { - assert(remainder_size == element_size); - } - else { - assert(remainder_size == request2size(sizes[i])); - } - check_inuse_chunk(m, mem2chunk(marray)); - } - for (i = 0; i != n_elements; ++i) - check_inuse_chunk(m, mem2chunk(marray[i])); - -#endif /* DEBUG */ - - POSTACTION(m); - return marray; -} - -/* Try to free all pointers in the given array. - Note: this could be made faster, by delaying consolidation, - at the price of disabling some user integrity checks, We - still optimize some consolidations by combining adjacent - chunks before freeing, which will occur often if allocated - with ialloc or the array is sorted. -*/ -static size_t internal_bulk_free(mstate m, void* array[], size_t nelem) { - size_t unfreed = 0; - if (!PREACTION(m)) { - void** a; - void** fence = &(array[nelem]); - for (a = array; a != fence; ++a) { - void* mem = *a; - if (mem != 0) { - mchunkptr p = mem2chunk(mem); - size_t psize = chunksize(p); -#if FOOTERS - if (get_mstate_for(p) != m) { - ++unfreed; - continue; - } -#endif - check_inuse_chunk(m, p); - *a = 0; - if (RTCHECK(ok_address(m, p) && ok_inuse(p))) { - void ** b = a + 1; /* try to merge with next chunk */ - mchunkptr next = next_chunk(p); - if (b != fence && *b == chunk2mem(next)) { - size_t newsize = chunksize(next) + psize; - set_inuse(m, p, newsize); - *b = chunk2mem(p); - } - else - dispose_chunk(m, p, psize); - } - else { - CORRUPTION_ERROR_ACTION(m); - break; - } - } - } - if (should_trim(m, m->topsize)) - sys_trim(m, 0); - POSTACTION(m); - } - return unfreed; -} - -/* Traversal */ -#if MALLOC_INSPECT_ALL -static void internal_inspect_all(mstate m, - void(*handler)(void *start, - void *end, - size_t used_bytes, - void* callback_arg), - void* arg) { - if (is_initialized(m)) { - mchunkptr top = m->top; - msegmentptr s; - for (s = &m->seg; s != 0; s = s->next) { - mchunkptr q = align_as_chunk(s->base); - while (segment_holds(s, q) && q->head != FENCEPOST_HEAD) { - mchunkptr next = next_chunk(q); - size_t sz = chunksize(q); - size_t used; - void* start; - if (is_inuse(q)) { - used = sz - CHUNK_OVERHEAD; /* must not be mmapped */ - start = chunk2mem(q); - } - else { - used = 0; - if (is_small(sz)) { /* offset by possible bookkeeping */ - start = (void*)((char*)q + sizeof(struct malloc_chunk)); - } - else { - start = (void*)((char*)q + sizeof(struct malloc_tree_chunk)); - } - } - if (start < (void*)next) /* skip if all space is bookkeeping */ - handler(start, next, used, arg); - if (q == top) - break; - q = next; - } - } - } -} -#endif /* MALLOC_INSPECT_ALL */ - -/* ------------------ Exported realloc, memalign, etc -------------------- */ - -#if !ONLY_MSPACES - -void* dlrealloc(void* oldmem, size_t bytes) { - void* mem = 0; - if (oldmem == 0) { - mem = dlmalloc(bytes); - } - else if (bytes >= MAX_REQUEST) { - MALLOC_FAILURE_ACTION; - } -#ifdef REALLOC_ZERO_BYTES_FREES - else if (bytes == 0) { - dlfree(oldmem); - } -#endif /* REALLOC_ZERO_BYTES_FREES */ - else { - size_t nb = request2size(bytes); - mchunkptr oldp = mem2chunk(oldmem); -#if ! FOOTERS - mstate m = gm; -#else /* FOOTERS */ - mstate m = get_mstate_for(oldp); - if (!ok_magic(m)) { - USAGE_ERROR_ACTION(m, oldmem); - return 0; - } -#endif /* FOOTERS */ - if (!PREACTION(m)) { - mchunkptr newp = try_realloc_chunk(m, oldp, nb, 1); - POSTACTION(m); - if (newp != 0) { - check_inuse_chunk(m, newp); - mem = chunk2mem(newp); - } - else { - mem = internal_malloc(m, bytes); - if (mem != 0) { - size_t oc = chunksize(oldp) - overhead_for(oldp); - memcpy(mem, oldmem, (oc < bytes)? oc : bytes); - internal_free(m, oldmem); - } - } - } - } - return mem; -} - -void* dlrealloc_in_place(void* oldmem, size_t bytes) { - void* mem = 0; - if (oldmem != 0) { - if (bytes >= MAX_REQUEST) { - MALLOC_FAILURE_ACTION; - } - else { - size_t nb = request2size(bytes); - mchunkptr oldp = mem2chunk(oldmem); -#if ! FOOTERS - mstate m = gm; -#else /* FOOTERS */ - mstate m = get_mstate_for(oldp); - if (!ok_magic(m)) { - USAGE_ERROR_ACTION(m, oldmem); - return 0; - } -#endif /* FOOTERS */ - if (!PREACTION(m)) { - mchunkptr newp = try_realloc_chunk(m, oldp, nb, 0); - POSTACTION(m); - if (newp == oldp) { - check_inuse_chunk(m, newp); - mem = oldmem; - } - } - } - } - return mem; -} - -void* dlmemalign(size_t alignment, size_t bytes) { - if (alignment <= MALLOC_ALIGNMENT) { - return dlmalloc(bytes); - } - return internal_memalign(gm, alignment, bytes); -} - -int dlposix_memalign(void** pp, size_t alignment, size_t bytes) { - void* mem = 0; - if (alignment == MALLOC_ALIGNMENT) - mem = dlmalloc(bytes); - else { - size_t d = alignment / sizeof(void*); - size_t r = alignment % sizeof(void*); - if (r != 0 || d == 0 || (d & (d-SIZE_T_ONE)) != 0) - return EINVAL; - else if (bytes <= MAX_REQUEST - alignment) { - if (alignment < MIN_CHUNK_SIZE) - alignment = MIN_CHUNK_SIZE; - mem = internal_memalign(gm, alignment, bytes); - } - } - if (mem == 0) - return ENOMEM; - else { - *pp = mem; - return 0; - } -} - -void* dlvalloc(size_t bytes) { - size_t pagesz; - ensure_initialization(); - pagesz = mparams.page_size; - return dlmemalign(pagesz, bytes); -} - -void* dlpvalloc(size_t bytes) { - size_t pagesz; - ensure_initialization(); - pagesz = mparams.page_size; - return dlmemalign(pagesz, (bytes + pagesz - SIZE_T_ONE) & ~(pagesz - SIZE_T_ONE)); -} - -void** dlindependent_calloc(size_t n_elements, size_t elem_size, - void* chunks[]) { - size_t sz = elem_size; /* serves as 1-element array */ - return ialloc(gm, n_elements, &sz, 3, chunks); -} - -void** dlindependent_comalloc(size_t n_elements, size_t sizes[], - void* chunks[]) { - return ialloc(gm, n_elements, sizes, 0, chunks); -} - -size_t dlbulk_free(void* array[], size_t nelem) { - return internal_bulk_free(gm, array, nelem); -} - -#if MALLOC_INSPECT_ALL -void dlmalloc_inspect_all(void(*handler)(void *start, - void *end, - size_t used_bytes, - void* callback_arg), - void* arg) { - ensure_initialization(); - if (!PREACTION(gm)) { - internal_inspect_all(gm, handler, arg); - POSTACTION(gm); - } -} -#endif /* MALLOC_INSPECT_ALL */ - -int dlmalloc_trim(size_t pad) { - int result = 0; - ensure_initialization(); - if (!PREACTION(gm)) { - result = sys_trim(gm, pad); - POSTACTION(gm); - } - return result; -} - -size_t dlmalloc_footprint(void) { - return gm->footprint; -} - -size_t dlmalloc_max_footprint(void) { - return gm->max_footprint; -} - -size_t dlmalloc_footprint_limit(void) { - size_t maf = gm->footprint_limit; - return maf == 0 ? MAX_SIZE_T : maf; -} - -size_t dlmalloc_set_footprint_limit(size_t bytes) { - size_t result; /* invert sense of 0 */ - if (bytes == 0) - result = granularity_align(1); /* Use minimal size */ - if (bytes == MAX_SIZE_T) - result = 0; /* disable */ - else - result = granularity_align(bytes); - return gm->footprint_limit = result; -} - -#if !NO_MALLINFO -struct mallinfo dlmallinfo(void) { - return internal_mallinfo(gm); -} -#endif /* NO_MALLINFO */ - -#if !NO_MALLOC_STATS -void dlmalloc_stats() { - internal_malloc_stats(gm); -} -#endif /* NO_MALLOC_STATS */ - -int dlmallopt(int param_number, int value) { - return change_mparam(param_number, value); -} - -size_t dlmalloc_usable_size(void* mem) { - if (mem != 0) { - mchunkptr p = mem2chunk(mem); - if (is_inuse(p)) - return chunksize(p) - overhead_for(p); - } - return 0; -} - -#endif /* !ONLY_MSPACES */ - /* ----------------------------- user mspaces ---------------------------- */ #if MSPACES @@ -5465,25 +3287,6 @@ static mstate init_user_mstate(char* tbase, size_t tsize) { 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; @@ -5498,23 +3301,6 @@ mspace create_mspace_with_base(void* base, size_t capacity, int 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; @@ -5758,103 +3544,6 @@ void mspace_free(mspace msp, void* mem) { } } -void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size) { - void* mem; - size_t req = 0; - mstate ms = (mstate)msp; - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - return 0; - } - if (n_elements != 0) { - req = n_elements * elem_size; - if (((n_elements | elem_size) & ~(size_t)0xffff) && - (req / n_elements != elem_size)) - req = MAX_SIZE_T; /* force downstream failure on overflow */ - } - mem = internal_malloc(ms, req); - if (mem != 0 && calloc_must_clear(mem2chunk(mem))) - memset(mem, 0, req); - return mem; -} - -void* mspace_realloc(mspace msp, void* oldmem, size_t bytes) { - void* mem = 0; - if (oldmem == 0) { - mem = mspace_malloc(msp, bytes); - } - else if (bytes >= MAX_REQUEST) { - MALLOC_FAILURE_ACTION; - } -#ifdef REALLOC_ZERO_BYTES_FREES - else if (bytes == 0) { - mspace_free(msp, oldmem); - } -#endif /* REALLOC_ZERO_BYTES_FREES */ - else { - size_t nb = request2size(bytes); - mchunkptr oldp = mem2chunk(oldmem); -#if ! FOOTERS - mstate m = (mstate)msp; -#else /* FOOTERS */ - mstate m = get_mstate_for(oldp); - if (!ok_magic(m)) { - USAGE_ERROR_ACTION(m, oldmem); - return 0; - } -#endif /* FOOTERS */ - if (!PREACTION(m)) { - mchunkptr newp = try_realloc_chunk(m, oldp, nb, 1); - POSTACTION(m); - if (newp != 0) { - check_inuse_chunk(m, newp); - mem = chunk2mem(newp); - } - else { - mem = mspace_malloc(m, bytes); - if (mem != 0) { - size_t oc = chunksize(oldp) - overhead_for(oldp); - memcpy(mem, oldmem, (oc < bytes)? oc : bytes); - mspace_free(m, oldmem); - } - } - } - } - return mem; -} - -void* mspace_realloc_in_place(mspace msp, void* oldmem, size_t bytes) { - void* mem = 0; - if (oldmem != 0) { - if (bytes >= MAX_REQUEST) { - MALLOC_FAILURE_ACTION; - } - else { - size_t nb = request2size(bytes); - mchunkptr oldp = mem2chunk(oldmem); -#if ! FOOTERS - mstate m = (mstate)msp; -#else /* FOOTERS */ - mstate m = get_mstate_for(oldp); - (void)msp; /* placate people compiling -Wunused */ - if (!ok_magic(m)) { - USAGE_ERROR_ACTION(m, oldmem); - return 0; - } -#endif /* FOOTERS */ - if (!PREACTION(m)) { - mchunkptr newp = try_realloc_chunk(m, oldp, nb, 0); - POSTACTION(m); - if (newp == oldp) { - check_inuse_chunk(m, newp); - mem = oldmem; - } - } - } - } - return mem; -} - void* mspace_memalign(mspace msp, size_t alignment, size_t bytes) { mstate ms = (mstate)msp; if (!ok_magic(ms)) { @@ -5866,78 +3555,6 @@ void* mspace_memalign(mspace msp, size_t alignment, size_t bytes) { return internal_memalign(ms, alignment, bytes); } -void** mspace_independent_calloc(mspace msp, size_t n_elements, - size_t elem_size, void* chunks[]) { - size_t sz = elem_size; /* serves as 1-element array */ - mstate ms = (mstate)msp; - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - return 0; - } - return ialloc(ms, n_elements, &sz, 3, chunks); -} - -void** mspace_independent_comalloc(mspace msp, size_t n_elements, - size_t sizes[], void* chunks[]) { - mstate ms = (mstate)msp; - if (!ok_magic(ms)) { - USAGE_ERROR_ACTION(ms,ms); - return 0; - } - return ialloc(ms, n_elements, sizes, 0, chunks); -} - -size_t mspace_bulk_free(mspace msp, void* array[], size_t nelem) { - return internal_bulk_free((mstate)msp, array, nelem); -} - -#if MALLOC_INSPECT_ALL -void mspace_inspect_all(mspace msp, - void(*handler)(void *start, - void *end, - size_t used_bytes, - void* callback_arg), - void* arg) { - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - if (!PREACTION(ms)) { - internal_inspect_all(ms, handler, arg); - POSTACTION(ms); - } - } - else { - USAGE_ERROR_ACTION(ms,ms); - } -} -#endif /* MALLOC_INSPECT_ALL */ - -int mspace_trim(mspace msp, size_t pad) { - int result = 0; - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - if (!PREACTION(ms)) { - result = sys_trim(ms, pad); - POSTACTION(ms); - } - } - else { - USAGE_ERROR_ACTION(ms,ms); - } - return result; -} - -#if !NO_MALLOC_STATS -void mspace_malloc_stats(mspace msp) { - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - internal_malloc_stats(ms); - } - else { - USAGE_ERROR_ACTION(ms,ms); - } -} -#endif /* NO_MALLOC_STATS */ - size_t mspace_footprint(mspace msp) { size_t result = 0; mstate ms = (mstate)msp; @@ -5962,37 +3579,6 @@ size_t mspace_max_footprint(mspace msp) { return result; } -size_t mspace_footprint_limit(mspace msp) { - size_t result = 0; - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - size_t maf = ms->footprint_limit; - result = (maf == 0) ? MAX_SIZE_T : maf; - } - else { - USAGE_ERROR_ACTION(ms,ms); - } - return result; -} - -size_t mspace_set_footprint_limit(mspace msp, size_t bytes) { - size_t result = 0; - mstate ms = (mstate)msp; - if (ok_magic(ms)) { - if (bytes == 0) - result = granularity_align(1); /* Use minimal size */ - if (bytes == MAX_SIZE_T) - result = 0; /* disable */ - else - result = granularity_align(bytes); - ms->footprint_limit = result; - } - else { - USAGE_ERROR_ACTION(ms,ms); - } - return result; -} - #if !NO_MALLINFO struct mallinfo mspace_mallinfo(mspace msp) { mstate ms = (mstate)msp;