Commit c1681bf8 authored by Anatol Pomozov's avatar Anatol Pomozov Committed by Linus Torvalds

loop: prevent bdev freeing while device in use

struct block_device lifecycle is defined by its inode (see fs/block_dev.c) -
block_device allocated first time we access /dev/loopXX and deallocated on
bdev_destroy_inode. When we create the device "losetup /dev/loopXX afile"
we want that block_device stay alive until we destroy the loop device
with "losetup -d".

But because we do not hold /dev/loopXX inode its counter goes 0, and
inode/bdev can be destroyed at any moment. Usually it happens at memory
pressure or when user drops inode cache (like in the test below). When later in
loop_clr_fd() we want to use bdev we have use-after-free error with following
stack:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000280
  bd_set_size+0x10/0xa0
  loop_clr_fd+0x1f8/0x420 [loop]
  lo_ioctl+0x200/0x7e0 [loop]
  lo_compat_ioctl+0x47/0xe0 [loop]
  compat_blkdev_ioctl+0x341/0x1290
  do_filp_open+0x42/0xa0
  compat_sys_ioctl+0xc1/0xf20
  do_sys_open+0x16e/0x1d0
  sysenter_dispatch+0x7/0x1a

To prevent use-after-free we need to grab the device in loop_set_fd()
and put it later in loop_clr_fd().

The issue is reprodusible on current Linus head and v3.3. Here is the test:

  dd if=/dev/zero of=loop.file bs=1M count=1
  while [ true ]; do
    losetup /dev/loop0 loop.file
    echo 2 > /proc/sys/vm/drop_caches
    losetup -d /dev/loop0
  done

[ Doing bdgrab/bput in loop_set_fd/loop_clr_fd is safe, because every
  time we call loop_set_fd() we check that loop_device->lo_state is
  Lo_unbound and set it to Lo_bound If somebody will try to set_fd again
  it will get EBUSY.  And if we try to loop_clr_fd() on unbound loop
  device we'll get ENXIO.

  loop_set_fd/loop_clr_fd (and any other loop ioctl) is called under
  loop_device->lo_ctl_mutex. ]
Signed-off-by: default avatarAnatol Pomozov <anatol.pomozov@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent aae92db9
...@@ -922,6 +922,11 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, ...@@ -922,6 +922,11 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
lo->lo_flags |= LO_FLAGS_PARTSCAN; lo->lo_flags |= LO_FLAGS_PARTSCAN;
if (lo->lo_flags & LO_FLAGS_PARTSCAN) if (lo->lo_flags & LO_FLAGS_PARTSCAN)
ioctl_by_bdev(bdev, BLKRRPART, 0); ioctl_by_bdev(bdev, BLKRRPART, 0);
/* Grab the block_device to prevent its destruction after we
* put /dev/loopXX inode. Later in loop_clr_fd() we bdput(bdev).
*/
bdgrab(bdev);
return 0; return 0;
out_clr: out_clr:
...@@ -1031,8 +1036,10 @@ static int loop_clr_fd(struct loop_device *lo) ...@@ -1031,8 +1036,10 @@ static int loop_clr_fd(struct loop_device *lo)
memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE); memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
memset(lo->lo_crypt_name, 0, LO_NAME_SIZE); memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
memset(lo->lo_file_name, 0, LO_NAME_SIZE); memset(lo->lo_file_name, 0, LO_NAME_SIZE);
if (bdev) if (bdev) {
bdput(bdev);
invalidate_bdev(bdev); invalidate_bdev(bdev);
}
set_capacity(lo->lo_disk, 0); set_capacity(lo->lo_disk, 0);
loop_sysfs_exit(lo); loop_sysfs_exit(lo);
if (bdev) { if (bdev) {
......
...@@ -551,6 +551,7 @@ struct block_device *bdgrab(struct block_device *bdev) ...@@ -551,6 +551,7 @@ struct block_device *bdgrab(struct block_device *bdev)
ihold(bdev->bd_inode); ihold(bdev->bd_inode);
return bdev; return bdev;
} }
EXPORT_SYMBOL(bdgrab);
long nr_blockdev_pages(void) long nr_blockdev_pages(void)
{ {
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment