#include <stdlib.h>
#include <stdio.h>

int main(void)
{
char *chunk;
chunk = malloc(24);
printf("Address of the chunk: %p\n", (void *)chunk);
gets(chunk);
free(chunk);
return 0;
}

main 함수의 ret opcode에서 중단점을 설정하여 컴파일하고 디버깅합니다. 그런 다음 gef를 사용하여 사용 중인 tcache bin을 확인할 수 있습니다:

gef➤  heap bins
──────────────────────────────────────────────────────────────────────────────── Tcachebins for thread 1 ────────────────────────────────────────────────────────────────────────────────
Tcachebins[idx=0, size=0x20, count=1] ←  Chunk(addr=0xaaaaaaac12a0, size=0x20, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)

// From https://github.com/bminor/glibc/blob/f942a732d37a96217ef828116ebe64a644db18d7/malloc/malloc.c

/* We want 64 entries.  This is an arbitrary limit, which tunables can reduce.  */
# define TCACHE_MAX_BINS		64
# define MAX_TCACHE_SIZE	tidx2usize (TCACHE_MAX_BINS-1)

/* Only used to pre-fill the tunables.  */
# define tidx2usize(idx)	(((size_t) idx) * MALLOC_ALIGNMENT + MINSIZE - SIZE_SZ)

/* When "x" is from chunksize().  */
# define csize2tidx(x) (((x) - MINSIZE + MALLOC_ALIGNMENT - 1) / MALLOC_ALIGNMENT)
/* When "x" is a user-provided size.  */
# define usize2tidx(x) csize2tidx (request2size (x))

/* 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.  */

/* This is another arbitrary limit, which tunables can change.  Each
tcache bin will hold at most this number of chunks.  */
# define TCACHE_FILL_COUNT 7

/* Maximum chunks in tcache bins for tunables.  This value must fit the range
of tcache->counts[] entries, else they may overflow.  */
# define MAX_TCACHE_COUNT UINT16_MAX

[...]

typedef struct tcache_entry
{
struct tcache_entry *next;
/* This field exists to detect double frees.  */
uintptr_t key;
} 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
{
uint16_t counts[TCACHE_MAX_BINS];
tcache_entry *entries[TCACHE_MAX_BINS];
} tcache_perthread_struct;

// From https://github.com/bminor/glibc/blob/f942a732d37a96217ef828116ebe64a644db18d7/malloc/malloc.c#L3241C1-L3274C2

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 && ar_ptr != NULL)
{
ar_ptr = arena_get_retry (ar_ptr, bytes);
victim = _int_malloc (ar_ptr, bytes);
}


if (ar_ptr != NULL)
__libc_lock_unlock (ar_ptr->mutex);

/* In a low memory situation, we may not be able to allocate memory
- in which case, we just keep trying later.  However, we
typically do this very early, so either there is sufficient
memory, or there isn't enough memory to do non-trivial
allocations anyway.  */
if (victim)
{
tcache = (tcache_perthread_struct *) victim;
memset (tcache, 0, sizeof (tcache_perthread_struct));
}

}

#include <stdlib.h>
#include <stdio.h>

int main(void)
{
char *chunks[8];
int i;

// Loop to allocate memory 8 times
for (i = 0; i < 8; i++) {
chunks[i] = malloc(24);
if (chunks[i] == NULL) { // Check if malloc failed
fprintf(stderr, "Memory allocation failed at iteration %d\n", i);
return 1;
}
printf("Address of chunk %d: %p\n", i, (void *)chunks[i]);
}

// Loop to free the allocated memory
for (i = 0; i < 8; i++) {
free(chunks[i]);
}

return 0;
}

8개의 동일한 크기의 청크를 할당하고 해제하는 방법에 유의하여 tcache를 채우고 여덟 번째 청크가 빠른 청크에 저장됩니다.

이를 컴파일하고 main 함수의 ret opcode에 중단점을 설정하여 디버깅합니다. 그런 다음 gef를 사용하면 tcache bin이 가득 차 있고 하나의 청크가 빠른 bin에 있음을 확인할 수 있습니다.

gef➤  heap bins
──────────────────────────────────────────────────────────────────────────────── Tcachebins for thread 1 ────────────────────────────────────────────────────────────────────────────────
Tcachebins[idx=0, size=0x20, count=7] ←  Chunk(addr=0xaaaaaaac1770, size=0x20, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac1750, size=0x20, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac1730, size=0x20, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac1710, size=0x20, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac16f0, size=0x20, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac16d0, size=0x20, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac12a0, size=0x20, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)
───────────────────────────────────────────────────────────────────────── Fastbins for arena at 0xfffff7f90b00 ─────────────────────────────────────────────────────────────────────────
Fastbins[idx=0, size=0x20]  ←  Chunk(addr=0xaaaaaaac1790, size=0x20, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)
Fastbins[idx=1, size=0x30] 0x00

#include <stdlib.h>
#include <stdio.h>

int main(void)
{
char *chunks[9];
int i;

// Loop to allocate memory 8 times
for (i = 0; i < 9; i++) {
chunks[i] = malloc(0x100);
if (chunks[i] == NULL) { // Check if malloc failed
fprintf(stderr, "Memory allocation failed at iteration %d\n", i);
return 1;
}
printf("Address of chunk %d: %p\n", i, (void *)chunks[i]);
}

// Loop to free the allocated memory
for (i = 0; i < 8; i++) {
free(chunks[i]);
}

return 0;
}

9개의 동일한 크기의 청크를 할당하고 해제하는 방법에 유의하세요. 이 청크들은 tcache를 채우고, 여덟 번째 청크는 fastbin에 비해 너무 커서 정렬되지 않은 빈에 저장됩니다. 아홉 번째 청크는 해제되지 않으므로 아홉 번째와 여덟 번째 청크는 상위 청크와 병합되지 않습니다.

이를 컴파일하고 main 함수의 ret opcode에 중단점을 설정하여 디버깅하세요. 그런 다음 gef를 사용하면 tcache 빈이 가득 차 있고 하나의 청크가 정렬되지 않은 빈에 있는 것을 볼 수 있습니다:

gef➤  heap bins
──────────────────────────────────────────────────────────────────────────────── Tcachebins for thread 1 ────────────────────────────────────────────────────────────────────────────────
Tcachebins[idx=15, size=0x110, count=7] ←  Chunk(addr=0xaaaaaaac1d10, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac1c00, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac1af0, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac19e0, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac18d0, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac17c0, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac12a0, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)
───────────────────────────────────────────────────────────────────────── Fastbins for arena at 0xfffff7f90b00 ─────────────────────────────────────────────────────────────────────────
Fastbins[idx=0, size=0x20] 0x00
Fastbins[idx=1, size=0x30] 0x00
Fastbins[idx=2, size=0x40] 0x00
Fastbins[idx=3, size=0x50] 0x00
Fastbins[idx=4, size=0x60] 0x00
Fastbins[idx=5, size=0x70] 0x00
Fastbins[idx=6, size=0x80] 0x00
─────────────────────────────────────────────────────────────────────── Unsorted Bin for arena at 0xfffff7f90b00 ───────────────────────────────────────────────────────────────────────
[+] unsorted_bins[0]: fw=0xaaaaaaac1e10, bk=0xaaaaaaac1e10
→   Chunk(addr=0xaaaaaaac1e20, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)
[+] Found 1 chunks in unsorted bin.

#include <stdlib.h>
#include <stdio.h>

int main(void)
{
char *chunks[10];
int i;

// Loop to allocate memory 8 times
for (i = 0; i < 9; i++) {
chunks[i] = malloc(0x100);
if (chunks[i] == NULL) { // Check if malloc failed
fprintf(stderr, "Memory allocation failed at iteration %d\n", i);
return 1;
}
printf("Address of chunk %d: %p\n", i, (void *)chunks[i]);
}

// Loop to free the allocated memory
for (i = 0; i < 8; i++) {
free(chunks[i]);
}

chunks[9] = malloc(0x110);

return 0;
}

9개의 동일한 크기의 청크를 할당하고 해제하는 방법에 유의하세요. 이 청크들은 tcache를 채우고, 여덟 번째 청크는 fastbin에 비해 너무 커서 정렬되지 않은 빈에 저장됩니다. 아홉 번째 청크는 해제되지 않으므로 아홉 번째와 여덟 번째 청크는 top chunk와 병합되지 않습니다. 그런 다음 0x110 크기의 더 큰 청크를 할당하면 정렬되지 않은 빈의 청크가 작은 빈으로 이동합니다.

이를 컴파일하고 main 함수의 ret opcode에 중단점을 설정하여 디버깅합니다. 그런 다음 gef를 사용하면 tcache 빈이 가득 차 있고 하나의 청크가 작은 빈에 있는 것을 볼 수 있습니다:

gef➤  heap bins
──────────────────────────────────────────────────────────────────────────────── Tcachebins for thread 1 ────────────────────────────────────────────────────────────────────────────────
Tcachebins[idx=15, size=0x110, count=7] ←  Chunk(addr=0xaaaaaaac1d10, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac1c00, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac1af0, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac19e0, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac18d0, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac17c0, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  Chunk(addr=0xaaaaaaac12a0, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)
───────────────────────────────────────────────────────────────────────── Fastbins for arena at 0xfffff7f90b00 ─────────────────────────────────────────────────────────────────────────
Fastbins[idx=0, size=0x20] 0x00
Fastbins[idx=1, size=0x30] 0x00
Fastbins[idx=2, size=0x40] 0x00
Fastbins[idx=3, size=0x50] 0x00
Fastbins[idx=4, size=0x60] 0x00
Fastbins[idx=5, size=0x70] 0x00
Fastbins[idx=6, size=0x80] 0x00
─────────────────────────────────────────────────────────────────────── Unsorted Bin for arena at 0xfffff7f90b00 ───────────────────────────────────────────────────────────────────────
[+] Found 0 chunks in unsorted bin.
──────────────────────────────────────────────────────────────────────── Small Bins for arena at 0xfffff7f90b00 ────────────────────────────────────────────────────────────────────────
[+] small_bins[16]: fw=0xaaaaaaac1e10, bk=0xaaaaaaac1e10
→   Chunk(addr=0xaaaaaaac1e20, size=0x110, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)
[+] Found 1 chunks in 1 small non-empty bins.

// From https://github.com/bminor/glibc/blob/a07e000e82cb71238259e674529c37c12dc7d423/malloc/malloc.c#L1711

#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))

#include <stdlib.h>
#include <stdio.h>

int main(void)
{
char *chunks[2];

chunks[0] = malloc(0x1500);
chunks[1] = malloc(0x1500);
free(chunks[0]);
chunks[0] = malloc(0x2000);

return 0;
}

2개의 큰 할당이 수행된 후, 하나가 해제되어(정렬되지 않은 빈에 넣어짐) 더 큰 할당이 이루어집니다(해제된 것이 정렬되지 않은 빈에서 큰 빈으로 이동됨).

이를 컴파일하고 main 함수의 ret opcode에서 중단점을 설정하여 디버깅합니다. 그런 다음 gef를 사용하면 tcache 빈이 가득 차 있고 하나의 청크가 큰 빈에 있음을 확인할 수 있습니다:

gef➤  heap bin
──────────────────────────────────────────────────────────────────────────────── Tcachebins for thread 1 ────────────────────────────────────────────────────────────────────────────────
All tcachebins are empty
───────────────────────────────────────────────────────────────────────── Fastbins for arena at 0xfffff7f90b00 ─────────────────────────────────────────────────────────────────────────
Fastbins[idx=0, size=0x20] 0x00
Fastbins[idx=1, size=0x30] 0x00
Fastbins[idx=2, size=0x40] 0x00
Fastbins[idx=3, size=0x50] 0x00
Fastbins[idx=4, size=0x60] 0x00
Fastbins[idx=5, size=0x70] 0x00
Fastbins[idx=6, size=0x80] 0x00
─────────────────────────────────────────────────────────────────────── Unsorted Bin for arena at 0xfffff7f90b00 ───────────────────────────────────────────────────────────────────────
[+] Found 0 chunks in unsorted bin.
──────────────────────────────────────────────────────────────────────── Small Bins for arena at 0xfffff7f90b00 ────────────────────────────────────────────────────────────────────────
[+] Found 0 chunks in 0 small non-empty bins.
──────────────────────────────────────────────────────────────────────── Large Bins for arena at 0xfffff7f90b00 ────────────────────────────────────────────────────────────────────────
[+] large_bins[100]: fw=0xaaaaaaac1290, bk=0xaaaaaaac1290
→   Chunk(addr=0xaaaaaaac12a0, size=0x1510, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)
[+] Found 1 chunks in 1 large non-empty bins.

#include <stdlib.h>
#include <stdio.h>

int main(void)
{
char *chunk;
chunk = malloc(24);
printf("Address of the chunk: %p\n", (void *)chunk);
gets(chunk);
return 0;
}

main의 ret opcode에서 중단점을 설정하여 컴파일하고 디버깅한 후, malloc이 주소 0xaaaaaaac12a0를 반환했으며, 다음은 청크들입니다:

gef➤  heap chunks
Chunk(addr=0xaaaaaaac1010, size=0x290, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)
[0x0000aaaaaaac1010     00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00    ................]
Chunk(addr=0xaaaaaaac12a0, size=0x20, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)
[0x0000aaaaaaac12a0     41 41 41 41 41 41 41 00 00 00 00 00 00 00 00 00    AAAAAAA.........]
Chunk(addr=0xaaaaaaac12c0, size=0x410, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)
[0x0000aaaaaaac12c0     41 64 64 72 65 73 73 20 6f 66 20 74 68 65 20 63    Address of the c]
Chunk(addr=0xaaaaaaac16d0, size=0x410, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)
[0x0000aaaaaaac16d0     41 41 41 41 41 41 41 0a 00 00 00 00 00 00 00 00    AAAAAAA.........]
Chunk(addr=0xaaaaaaac1ae0, size=0x20530, flags=PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)  ←  top chunk

상단 청크가 주소 0xaaaaaaac1ae0에 있다는 것을 볼 수 있습니다. 이는 마지막으로 할당된 청크가 0xaaaaaaac12a0에 크기 0x410으로 있었기 때문에 놀라운 일이 아닙니다. 0xaaaaaaac12a0 + 0x410 = 0xaaaaaaac1ae0입니다.
상단 청크의 청크 헤더에서 상단 청크의 길이를 볼 수도 있습니다:

gef➤  x/8wx 0xaaaaaaac1ae0 - 16
0xaaaaaaac1ad0:	0x00000000	0x00000000	0x00020531	0x00000000
0xaaaaaaac1ae0:	0x00000000	0x00000000	0x00000000	0x00000000