Revision f6ba488073fe8159851fe398cc3c5ee383bb4c7a authored by Vladimir Davydov on 18 August 2017, 22:16:08 UTC, committed by Linus Torvalds on 18 August 2017, 22:32:01 UTC
To avoid a possible deadlock, sysfs_slab_remove() schedules an
asynchronous work to delete sysfs entries corresponding to the kmem
cache.  To ensure the cache isn't freed before the work function is
called, it takes a reference to the cache kobject.  The reference is
supposed to be released by the work function.

However, the work function (sysfs_slab_remove_workfn()) does nothing in
case the cache sysfs entry has already been deleted, leaking the kobject
and the corresponding cache.

This may happen on a per memcg cache destruction, because sysfs entries
of a per memcg cache are deleted on memcg offline if the cache is empty
(see __kmemcg_cache_deactivate()).

The kmemleak report looks like this:

  unreferenced object 0xffff9f798a79f540 (size 32):
    comm "kworker/1:4", pid 15416, jiffies 4307432429 (age 28687.554s)
    hex dump (first 32 bytes):
      6b 6d 61 6c 6c 6f 63 2d 31 36 28 31 35 39 39 3a  kmalloc-16(1599:
      6e 65 77 72 6f 6f 74 29 00 23 6b c0 ff ff ff ff  newroot).#k.....
    backtrace:
       kmemleak_alloc+0x4a/0xa0
       __kmalloc_track_caller+0x148/0x2c0
       kvasprintf+0x66/0xd0
       kasprintf+0x49/0x70
       memcg_create_kmem_cache+0xe6/0x160
       memcg_kmem_cache_create_func+0x20/0x110
       process_one_work+0x205/0x5d0
       worker_thread+0x4e/0x3a0
       kthread+0x109/0x140
       ret_from_fork+0x2a/0x40
  unreferenced object 0xffff9f79b6136840 (size 416):
    comm "kworker/1:4", pid 15416, jiffies 4307432429 (age 28687.573s)
    hex dump (first 32 bytes):
      40 fb 80 c2 3e 33 00 00 00 00 00 40 00 00 00 00  @...>3.....@....
      00 00 00 00 00 00 00 00 10 00 00 00 10 00 00 00  ................
    backtrace:
       kmemleak_alloc+0x4a/0xa0
       kmem_cache_alloc+0x128/0x280
       create_cache+0x3b/0x1e0
       memcg_create_kmem_cache+0x118/0x160
       memcg_kmem_cache_create_func+0x20/0x110
       process_one_work+0x205/0x5d0
       worker_thread+0x4e/0x3a0
       kthread+0x109/0x140
       ret_from_fork+0x2a/0x40

Fix the leak by adding the missing call to kobject_put() to
sysfs_slab_remove_workfn().

Link: http://lkml.kernel.org/r/20170812181134.25027-1-vdavydov.dev@gmail.com
Fixes: 3b7b314053d02 ("slub: make sysfs file removal asynchronous")
Signed-off-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Reported-by: Andrei Vagin <avagin@gmail.com>
Tested-by: Andrei Vagin <avagin@gmail.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: <stable@vger.kernel.org>	[4.12.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 3010f87
Raw File
strncpy_from_user.c
#include <linux/compiler.h>
#include <linux/export.h>
#include <linux/kasan-checks.h>
#include <linux/thread_info.h>
#include <linux/uaccess.h>
#include <linux/kernel.h>
#include <linux/errno.h>

#include <asm/byteorder.h>
#include <asm/word-at-a-time.h>

#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
#define IS_UNALIGNED(src, dst)	0
#else
#define IS_UNALIGNED(src, dst)	\
	(((long) dst | (long) src) & (sizeof(long) - 1))
#endif

/*
 * Do a strncpy, return length of string without final '\0'.
 * 'count' is the user-supplied count (return 'count' if we
 * hit it), 'max' is the address space maximum (and we return
 * -EFAULT if we hit it).
 */
static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, unsigned long max)
{
	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
	long res = 0;

	/*
	 * Truncate 'max' to the user-specified limit, so that
	 * we only have one limit we need to check in the loop
	 */
	if (max > count)
		max = count;

	if (IS_UNALIGNED(src, dst))
		goto byte_at_a_time;

	while (max >= sizeof(unsigned long)) {
		unsigned long c, data;

		/* Fall back to byte-at-a-time if we get a page fault */
		unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time);

		*(unsigned long *)(dst+res) = c;
		if (has_zero(c, &data, &constants)) {
			data = prep_zero_mask(c, data, &constants);
			data = create_zero_mask(data);
			return res + find_zero(data);
		}
		res += sizeof(unsigned long);
		max -= sizeof(unsigned long);
	}

byte_at_a_time:
	while (max) {
		char c;

		unsafe_get_user(c,src+res, efault);
		dst[res] = c;
		if (!c)
			return res;
		res++;
		max--;
	}

	/*
	 * Uhhuh. We hit 'max'. But was that the user-specified maximum
	 * too? If so, that's ok - we got as much as the user asked for.
	 */
	if (res >= count)
		return res;

	/*
	 * Nope: we hit the address space limit, and we still had more
	 * characters the caller would have wanted. That's an EFAULT.
	 */
efault:
	return -EFAULT;
}

/**
 * strncpy_from_user: - Copy a NUL terminated string from userspace.
 * @dst:   Destination address, in kernel space.  This buffer must be at
 *         least @count bytes long.
 * @src:   Source address, in user space.
 * @count: Maximum number of bytes to copy, including the trailing NUL.
 *
 * Copies a NUL-terminated string from userspace to kernel space.
 *
 * On success, returns the length of the string (not including the trailing
 * NUL).
 *
 * If access to userspace fails, returns -EFAULT (some data may have been
 * copied).
 *
 * If @count is smaller than the length of the string, copies @count bytes
 * and returns @count.
 */
long strncpy_from_user(char *dst, const char __user *src, long count)
{
	unsigned long max_addr, src_addr;

	if (unlikely(count <= 0))
		return 0;

	max_addr = user_addr_max();
	src_addr = (unsigned long)src;
	if (likely(src_addr < max_addr)) {
		unsigned long max = max_addr - src_addr;
		long retval;

		kasan_check_write(dst, count);
		check_object_size(dst, count, false);
		user_access_begin();
		retval = do_strncpy_from_user(dst, src, count, max);
		user_access_end();
		return retval;
	}
	return -EFAULT;
}
EXPORT_SYMBOL(strncpy_from_user);
back to top