glibc heap 整理

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

#include <unistd.h>
int brk(void * addr); 
/* brk调整program break位置，参数为break的新地址。
brk成功返回0，失败返回-1
并设置errno值为ENOMEM */

void * sbrk(intptr_t increment);
/* sbrk通过increment的正负调整break位置，
sbrk成功返回原brk的地址，也就是新分配内存的起始位置，失败返回(void *)-1,
并设置errno全局变量的值为ENOMEM */

1
2
3

#incldue<sys/mman.h>
void * mmap(void * addr, size_t length,int prot,int flags,int fd,off_t offset);
int munmap(void * addr, size_t length);//addr为mmap函数返回接收的地址，length为请求分配的长度。

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28

参数：

（1）、addr:
起始地址，置零让系统自行选择并返回即可.
（2）、length:
长度，不够一页会自动凑够一页的整数倍，我们可以宏定义#define MIN_LENGTH_MMAP 4096为一页大小
（3）、prot:
读写操作权限，PROT_READ可读、PROT_WRITE可写、PROT_EXEC可执行、PROT_NONE映射区域不能读取。（注意PROT_XXXXX与文件本身的权限不冲突，如果在程序中不设定任何权限，即使本身存在读写权限，该进程也不能对其操作）
（4）、flags常用标志:
①MAP_SHARED【share this mapping】、MAP_PRIVATE【Create a private copy-on-write mapping】
MAP_SHARED只能设置文件共享，不能地址共享，即使设置了共享，对于两个进程来说，也不会生效。而MAP_PRIVATE则对于文件与内存都可以设置为私有。
②MAP_ANON【Deprecated】、MAP_ANONYMOUS：匿名映射，如果映射地址需要加该参数，如果不加默认映射文件。MAP_ANON已经过时，只需使用MAP_ANONYMOUS即可
（5）、文件描述符：fd
（6）、文件描述符偏移量：offset
（fd和offset对于一般性内存分配来说设置为0即可）

返回值：

失败返回MAP_FAILED，即(void * (-1))并设置errno全局变量。
成功返回指向mmap area的指针pointer。

常见errno错误：

①ENOMEM：内存不足；
②EAGAIN：文件被锁住或有太多内存被锁住；
③EBADF：参数fd不是有效的文件描述符；
④EACCES：存在权限错误，。如果是MAP_PRIVATE情况下文件必须可读；使用MAP_SHARED则文件必须能写入，且设置prot权限必须为PROT_WRITE。
⑤EINVAL：参数addr、length或者offset中有不合法参数存在。

1
2
3
4
5
6
7
8
9

#ifndef INTERNAL_SIZE_T
# define INTERNAL_SIZE_T size_t
#endif

/* The corresponding word size.  */
#define SIZE_SZ (sizeof (INTERNAL_SIZE_T))

/* The corresponding bit mask value.  */
#define MALLOC_ALIGN_MASK (MALLOC_ALIGNMENT - 1)

1
2
3
4

For 32 bit systems:
     Number of arena = 2 * number of cores.
For 64 bit systems:
     Number of arena = 8 * number of cores.

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18

/*
  This struct declaration is misleading (but accurate and necessary).
  It declares a "view" into memory allowing access to necessary
  fields at known offsets from a given base. See explanation below.
*/

struct malloc_chunk {

  INTERNAL_SIZE_T      mchunk_prev_size;  /* Size of previous chunk (if free).  */
  INTERNAL_SIZE_T      mchunk_size;       /* Size in bytes, including overhead. */

  struct malloc_chunk* fd;         /* double links -- used only if free. */
  struct malloc_chunk* bk;

  /* Only used for large blocks: pointer to next larger size.  */
  struct malloc_chunk* fd_nextsize; /* double links -- used only if free. */
  struct malloc_chunk* bk_nextsize;
};

1
2
3

/* conversion from malloc headers to user pointers, and back */
#define chunk2mem(p) ((void *) ((char *) (p) + 2 * SIZE_SZ))
#define mem2chunk(mem) ((mchunkptr)((char *) (mem) -2 * SIZE_SZ))

1
2

/* The smallest possible chunk */
#define MIN_CHUNK_SIZE (offsetof(struct malloc_chunk, fd_nextsize))

1
2
3
4
5

/* The smallest size we can malloc is an aligned minimal chunk */
//MALLOC_ALIGN_MASK = 2 * SIZE_SZ -1
#define MINSIZE                                                                \
    (unsigned long) (((MIN_CHUNK_SIZE + MALLOC_ALIGN_MASK) &                   \
                      ~MALLOC_ALIGN_MASK))

1
2
3
4
5
6
7

/* Check if m has acceptable alignment */
// MALLOC_ALIGN_MASK = 2 * SIZE_SZ -1
#define aligned_OK(m) (((unsigned long) (m) & MALLOC_ALIGN_MASK) == 0)

#define misaligned_chunk(p)                                                    \
    ((uintptr_t)(MALLOC_ALIGNMENT == 2 * SIZE_SZ ? (p) : chunk2mem(p)) &       \
     MALLOC_ALIGN_MASK)

1
2
3
4
5
6
7
8

/*
   Check if a request is so large that it would wrap around zero when
   padded and aligned. To simplify some other code, the bound is made
   low enough so that adding MINSIZE will also not wrap around zero.
 */

#define REQUEST_OUT_OF_RANGE(req)                                              \
    ((unsigned long) (req) >= (unsigned long) (INTERNAL_SIZE_T)(-2 * MINSIZE))

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15

/* pad request bytes into a usable size -- internal version */
//MALLOC_ALIGN_MASK = 2 * SIZE_SZ -1
#define request2size(req)                                                      \
    (((req) + SIZE_SZ + MALLOC_ALIGN_MASK < MINSIZE)                           \
         ? MINSIZE                                                             \
         : ((req) + SIZE_SZ + MALLOC_ALIGN_MASK) & ~MALLOC_ALIGN_MASK)

/*  Same, except also perform argument check */

#define checked_request2size(req, sz)                                          \
    if (REQUEST_OUT_OF_RANGE(req)) {                                           \
        __set_errno(ENOMEM);                                                   \
        return 0;                                                              \
    }                                                                          \
    (sz) = request2size(req);

1
2
3

#define NBINS 128
/* Normal bins packed as described above */
mchunkptr bins[ NBINS * 2 - 2 ];

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21

typedef struct malloc_chunk *mbinptr;

/* addressing -- note that bin_at(0) does not exist */
#define bin_at(m, i)                                                           \
    (mbinptr)(((char *) &((m)->bins[ ((i) -1) * 2 ])) -                        \
              offsetof(struct malloc_chunk, fd))

/* analog of ++bin */
//获取下一个bin的地址
#define next_bin(b) ((mbinptr)((char *) (b) + (sizeof(mchunkptr) << 1)))

/* Reminders about list directionality within bins */
// 这两个宏可以用来遍历bin
// 获取 bin 的位于链表头的 chunk
#define first(b) ((b)->fd)
// 获取 bin 的位于链表尾的 chunk
#define last(b) ((b)->bk)

/* 根据 chunk 的大小统一地获得 chunk 所在的索引 */
#define bin_index(sz)                                                          \
    ((in_smallbin_range(sz)) ? smallbin_index(sz) : largebin_index(sz))

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69

#define NFASTBINS (fastbin_index(request2size(MAX_FAST_SIZE)) + 1)

#ifndef DEFAULT_MXFAST
#define DEFAULT_MXFAST (64 * SIZE_SZ / 4)
#endif

/* The maximum fastbin request size we support */
#define MAX_FAST_SIZE (80 * SIZE_SZ / 4)

/*
   Since the lowest 2 bits in max_fast don't matter in size comparisons,
   they are used as flags.
 */

/*
   FASTCHUNKS_BIT held in max_fast indicates that there are probably
   some fastbin chunks. It is set true on entering a chunk into any
   fastbin, and cleared only in malloc_consolidate.

   The truth value is inverted so that have_fastchunks will be true
   upon startup (since statics are zero-filled), simplifying
   initialization checks.
 */
//判断分配区是否有 fast bin chunk，1表示没有
#define FASTCHUNKS_BIT (1U)

#define have_fastchunks(M) (((M)->flags & FASTCHUNKS_BIT) == 0)
#define clear_fastchunks(M) catomic_or(&(M)->flags, FASTCHUNKS_BIT)
#define set_fastchunks(M) catomic_and(&(M)->flags, ~FASTCHUNKS_BIT)

/*
   NONCONTIGUOUS_BIT indicates that MORECORE does not return contiguous
   regions.  Otherwise, contiguity is exploited in merging together,
   when possible, results from consecutive MORECORE calls.

   The initial value comes from MORECORE_CONTIGUOUS, but is
   changed dynamically if mmap is ever used as an sbrk substitute.
 */
// MORECORE是否返回连续的内存区域。
// 主分配区中的MORECORE其实为sbr()，默认返回连续虚拟地址空间
// 非主分配区使用mmap()分配大块虚拟内存，然后进行切分来模拟主分配区的行为
// 而默认情况下mmap映射区域是不保证虚拟地址空间连续的，所以非主分配区默认分配非连续虚拟地址空间。
#define NONCONTIGUOUS_BIT (2U)

#define contiguous(M) (((M)->flags & NONCONTIGUOUS_BIT) == 0)
#define noncontiguous(M) (((M)->flags & NONCONTIGUOUS_BIT) != 0)
#define set_noncontiguous(M) ((M)->flags |= NONCONTIGUOUS_BIT)
#define set_contiguous(M) ((M)->flags &= ~NONCONTIGUOUS_BIT)

/* ARENA_CORRUPTION_BIT is set if a memory corruption was detected on the
   arena.  Such an arena is no longer used to allocate chunks.  Chunks
   allocated in that arena before detecting corruption are not freed.  */

#define ARENA_CORRUPTION_BIT (4U)

#define arena_is_corrupt(A) (((A)->flags & ARENA_CORRUPTION_BIT))
#define set_arena_corrupt(A) ((A)->flags |= ARENA_CORRUPTION_BIT)

/*
   Set value of max_fast.
   Use impossibly small value if 0.
   Precondition: there are no existing fastbin chunks.
   Setting the value clears fastchunk bit but preserves noncontiguous bit.
 */

#define set_max_fast(s)                                                        \
    global_max_fast =                                                          \
        (((s) == 0) ? SMALLBIN_WIDTH : ((s + SIZE_SZ) & ~MALLOC_ALIGN_MASK))
#define get_max_fast() global_max_fast

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21

/*
   FASTBIN_CONSOLIDATION_THRESHOLD is the size of a chunk in free()
   that triggers automatic consolidation of possibly-surrounding
   fastbin chunks. This is a heuristic, so the exact value should not
   matter too much. It is defined at half the default trim threshold as a
   compromise heuristic to only attempt consolidation if it is likely
   to lead to trimming. However, it is not dynamically tunable, since
   consolidation reduces fragmentation surrounding large chunks even
   if trimming is not used.
 */

#define FASTBIN_CONSOLIDATION_THRESHOLD (65536UL)
/* malloc_consolidate 函数可以将 fastbin 中所有能和其它 chunk 合并的 chunk 合并在一起。具体地参见后续的详细函数的分析。 */


/*
    Chunks in fastbins keep their inuse bit set, so they cannot
    be consolidated with other free chunks. malloc_consolidate
    releases all chunks in fastbins and consolidates them with
    other free chunks.
 */

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13

/*
   Unsorted chunks

    All remainders from chunk splits, as well as all returned chunks,
    are first placed in the "unsorted" bin. They are then placed
    in regular bins after malloc gives them ONE chance to be used before
    binning. So, basically, the unsorted_chunks list acts as a queue,
    with chunks being placed on it in free (and malloc_consolidate),
    and taken off (to be either used or placed in bins) in malloc.

    The NON_MAIN_ARENA flag is never set for unsorted chunks, so it
    does not have to be taken into account in size comparisons.
 */

1
2

/* The otherwise unindexable 1-bin is used to hold unsorted chunks. */
#define unsorted_chunks(M) (bin_at(M, 1))

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14

#define NSMALLBINS 64
#define SMALLBIN_WIDTH MALLOC_ALIGNMENT
// 是否需要对small bin的下标进行纠正
#define SMALLBIN_CORRECTION (MALLOC_ALIGNMENT > 2 * SIZE_SZ)

#define MIN_LARGE_SIZE ((NSMALLBINS - SMALLBIN_CORRECTION) * SMALLBIN_WIDTH)
//判断chunk的大小是否在small bin范围内
#define in_smallbin_range(sz)                                                  \
    ((unsigned long) (sz) < (unsigned long) MIN_LARGE_SIZE)
// 根据chunk的大小得到small bin对应的索引。
#define smallbin_index(sz)                                                     \
    ((SMALLBIN_WIDTH == 16 ? (((unsigned) (sz)) >> 4)                          \
                           : (((unsigned) (sz)) >> 3)) +                       \
     SMALLBIN_CORRECTION)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46

#define largebin_index_32(sz)                                                  \
    (((((unsigned long) (sz)) >> 6) <= 38)                                     \
         ? 56 + (((unsigned long) (sz)) >> 6)                                  \
         : ((((unsigned long) (sz)) >> 9) <= 20)                               \
               ? 91 + (((unsigned long) (sz)) >> 9)                            \
               : ((((unsigned long) (sz)) >> 12) <= 10)                        \
                     ? 110 + (((unsigned long) (sz)) >> 12)                    \
                     : ((((unsigned long) (sz)) >> 15) <= 4)                   \
                           ? 119 + (((unsigned long) (sz)) >> 15)              \
                           : ((((unsigned long) (sz)) >> 18) <= 2)             \
                                 ? 124 + (((unsigned long) (sz)) >> 18)        \
                                 : 126)

#define largebin_index_32_big(sz)                                              \
    (((((unsigned long) (sz)) >> 6) <= 45)                                     \
         ? 49 + (((unsigned long) (sz)) >> 6)                                  \
         : ((((unsigned long) (sz)) >> 9) <= 20)                               \
               ? 91 + (((unsigned long) (sz)) >> 9)                            \
               : ((((unsigned long) (sz)) >> 12) <= 10)                        \
                     ? 110 + (((unsigned long) (sz)) >> 12)                    \
                     : ((((unsigned long) (sz)) >> 15) <= 4)                   \
                           ? 119 + (((unsigned long) (sz)) >> 15)              \
                           : ((((unsigned long) (sz)) >> 18) <= 2)             \
                                 ? 124 + (((unsigned long) (sz)) >> 18)        \
                                 : 126)

// XXX It remains to be seen whether it is good to keep the widths of
// XXX the buckets the same or whether it should be scaled by a factor
// XXX of two as well.
#define largebin_index_64(sz)                                                  \
    (((((unsigned long) (sz)) >> 6) <= 48)                                     \
         ? 48 + (((unsigned long) (sz)) >> 6)                                  \
         : ((((unsigned long) (sz)) >> 9) <= 20)                               \
               ? 91 + (((unsigned long) (sz)) >> 9)                            \
               : ((((unsigned long) (sz)) >> 12) <= 10)                        \
                     ? 110 + (((unsigned long) (sz)) >> 12)                    \
                     : ((((unsigned long) (sz)) >> 15) <= 4)                   \
                           ? 119 + (((unsigned long) (sz)) >> 15)              \
                           : ((((unsigned long) (sz)) >> 18) <= 2)             \
                                 ? 124 + (((unsigned long) (sz)) >> 18)        \
                                 : 126)

#define largebin_index(sz)                                                     \
    (SIZE_SZ == 8 ? largebin_index_64(sz) : MALLOC_ALIGNMENT == 16             \
                                                ? largebin_index_32_big(sz)    \
                                                : largebin_index_32(sz))

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20

/*
   Top

    The top-most available chunk (i.e., the one bordering the end of
    available memory) is treated specially. It 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).  Because top initially
    points to its own bin with initial zero size, thus forcing
    extension on the first malloc request, we avoid having any special
    code in malloc to check whether it even exists yet. But we still
    need to do so when getting memory from system, so we make
    initial_top treat the bin as a legal but unusable chunk during the
    interval between initialization and the first call to
    sysmalloc. (This is somewhat delicate, since it relies on
    the 2 preceding words to be zero during this interval as well.)
 */

/* Conveniently, the unsorted bin can be used as dummy top on first call */
#define initial_top(M) (unsorted_chunks(M))

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17

/* We overlay this structure on the user-data portion of a chunk when
   the chunk is stored in the per-thread cache.  */
typedef struct tcache_entry
{
  struct tcache_entry *next;
} tcache_entry;

/* There is one of these for each thread, which contains the
   per-thread cache (hence "tcache_perthread_struct").  Keeping
   overall size low is mildly important.  Note that COUNTS and ENTRIES
   are redundant (we could have just counted the linked list each
   time), this is for performance reasons.  */
typedef struct tcache_perthread_struct
{
  char counts[TCACHE_MAX_BINS];
  tcache_entry *entries[TCACHE_MAX_BINS];
} tcache_perthread_struct;

1
2
3
4
5

/* With rounding and alignment, the bins are...
   idx 0   bytes 0..24 (64-bit) or 0..12 (32-bit)
   idx 1   bytes 25..40 or 13..20
   idx 2   bytes 41..56 or 21..28
   etc.  */