tcache note

https://github.com/kraj/glibc/blob/master/malloc/malloc.c

몇 부분만 정리

void * __libc_malloc (size_t bytes) { mstate ar_ptr; void *victim; void *(*hook) (size_t, const void *) = atomic_forced_read (__malloc_hook); if (__builtin_expect (hook != NULL, 0)) return (*hook)(bytes, RETURN_ADDRESS (0)); #if USE_TCACHE /* int_free also calls request2size, be careful to not pad twice. */ size_t tbytes; checked_request2size (bytes, tbytes); size_t tc_idx = csize2tidx (tbytes); MAYBE_INIT_TCACHE (); DIAG_PUSH_NEEDS_COMMENT; if (tc_idx < mp_.tcache_bins /*&& tc_idx < TCACHE_MAX_BINS*/ /* to appease gcc */ && tcache && tcache->entries[tc_idx] != NULL) { return tcache_get (tc_idx); } DIAG_POP_NEEDS_COMMENT; #endif if (SINGLE_THREAD_P) { victim = _int_malloc (&main_arena, bytes); assert (!victim || chunk_is_mmapped (mem2chunk (victim)) || &main_arena == arena_for_chunk (mem2chunk (victim))); return victim; } arena_get (ar_ptr, bytes);

static void _int_free (mstate av, mchunkptr p, int have_lock) { INTERNAL_SIZE_T size; /* its size */ mfastbinptr *fb; /* associated fastbin */ mchunkptr nextchunk; /* next contiguous chunk */ INTERNAL_SIZE_T nextsize; /* its size */ int nextinuse; /* true if nextchunk is used */ INTERNAL_SIZE_T prevsize; /* size of previous contiguous chunk */ mchunkptr bck; /* misc temp for linking */ mchunkptr fwd; /* misc temp for linking */ size = chunksize (p); /* Little security check which won't hurt performance: the allocator never wrapps around at the end of the address space. Therefore we can exclude some size values which might appear here by accident or by "design" from some intruder. */ if (__builtin_expect ((uintptr_t) p > (uintptr_t) -size, 0) || __builtin_expect (misaligned_chunk (p), 0)) malloc_printerr ("free(): invalid pointer"); /* We know that each chunk is at least MINSIZE bytes in size or a multiple of MALLOC_ALIGNMENT. */ if (__glibc_unlikely (size < MINSIZE || !aligned_OK (size))) malloc_printerr ("free(): invalid size"); check_inuse_chunk(av, p); #if USE_TCACHE { size_t tc_idx = csize2tidx (size); if (tcache && tc_idx < mp_.tcache_bins && tcache->counts[tc_idx] < mp_.tcache_count) { tcache_put (p, tc_idx); return; } } #endif

static struct malloc_par mp_ = { .top_pad = DEFAULT_TOP_PAD, .n_mmaps_max = DEFAULT_MMAP_MAX, .mmap_threshold = DEFAULT_MMAP_THRESHOLD, .trim_threshold = DEFAULT_TRIM_THRESHOLD, #define NARENAS_FROM_NCORES(n) ((n) * (sizeof (long) == 4 ? 2 : 8)) .arena_test = NARENAS_FROM_NCORES (1) #if USE_TCACHE , .tcache_count = TCACHE_FILL_COUNT, .tcache_bins = TCACHE_MAX_BINS, .tcache_max_bytes = tidx2usize (TCACHE_MAX_BINS-1), .tcache_unsorted_limit = 0 /* No limit. */ #endif };   # define TCACHE_FILL_COUNT 7

하나의 tcache bin에는 최대 7개 청크

static void tcache_init(void) { mstate ar_ptr; void *victim = 0; const size_t bytes = sizeof (tcache_perthread_struct); if (tcache_shutting_down) return; arena_get (ar_ptr, bytes); victim = _int_malloc (ar_ptr, bytes); ........................................................... if (victim) { tcache = (tcache_perthread_struct *) victim; memset (tcache, 0, sizeof (tcache_perthread_struct)); }

오우 tcache를 위한 struct를 힙에 할당한다. arbitrary heap free 있으면 저거 free 시켜버려도 될듯. 

# define TCACHE_MAX_BINS 64 typedef struct tcache_perthread_struct {   char counts[TCACHE_MAX_BINS];   tcache_entry *entries[TCACHE_MAX_BINS]; } tcache_perthread_struct;  typedef struct tcache_entry {   struct tcache_entry *next; } tcache_entry;

 

static __always_inline void tcache_put (mchunkptr chunk, size_t tc_idx) {   tcache_entry *e = (tcache_entry *) chunk2mem (chunk);   assert (tc_idx < TCACHE_MAX_BINS);   e->next = tcache->entries[tc_idx];   tcache->entries[tc_idx] = e;   ++(tcache->counts[tc_idx]); } /* Caller must ensure that we know tc_idx is valid and there's    available chunks to remove.  */ static __always_inline void * tcache_get (size_t tc_idx) {   tcache_entry *e = tcache->entries[tc_idx];   assert (tc_idx < TCACHE_MAX_BINS);   assert (tcache->entries[tc_idx] > 0);   tcache->entries[tc_idx] = e->next;   --(tcache->counts[tc_idx]);   return (void *) e; }

엥 이거 완전 fastbin 아니냐. fastbin이랑 같은 방식으로 익스 가능.

할당시점에 기본적인 size도 검사도 없다. next자리에 그냥 stack, GOT, hook, ... 넣어두면 될듯.

/* When "x" is from chunksize(). */ # define csize2tidx(x) (((x) - MINSIZE + MALLOC_ALIGNMENT - 1) / MALLOC_ALIGNMENT)