kernel_optimize_test/fs
Filipe Manana 8039d87d9e Btrfs: fix file corruption and data loss after cloning inline extents
Currently the clone ioctl allows to clone an inline extent from one file
to another that already has other (non-inlined) extents. This is a problem
because btrfs is not designed to deal with files having inline and regular
extents, if a file has an inline extent then it must be the only extent
in the file and must start at file offset 0. Having a file with an inline
extent followed by regular extents results in EIO errors when doing reads
or writes against the first 4K of the file.

Also, the clone ioctl allows one to lose data if the source file consists
of a single inline extent, with a size of N bytes, and the destination
file consists of a single inline extent with a size of M bytes, where we
have M > N. In this case the clone operation removes the inline extent
from the destination file and then copies the inline extent from the
source file into the destination file - we lose the M - N bytes from the
destination file, a read operation will get the value 0x00 for any bytes
in the the range [N, M] (the destination inode's i_size remained as M,
that's why we can read past N bytes).

So fix this by not allowing such destructive operations to happen and
return errno EOPNOTSUPP to user space.

Currently the fstest btrfs/035 tests the data loss case but it totally
ignores this - i.e. expects the operation to succeed and does not check
the we got data loss.

The following test case for fstests exercises all these cases that result
in file corruption and data loss:

  seq=`basename $0`
  seqres=$RESULT_DIR/$seq
  echo "QA output created by $seq"
  tmp=/tmp/$$
  status=1	# failure is the default!
  trap "_cleanup; exit \$status" 0 1 2 3 15

  _cleanup()
  {
      rm -f $tmp.*
  }

  # get standard environment, filters and checks
  . ./common/rc
  . ./common/filter

  # real QA test starts here
  _need_to_be_root
  _supported_fs btrfs
  _supported_os Linux
  _require_scratch
  _require_cloner
  _require_btrfs_fs_feature "no_holes"
  _require_btrfs_mkfs_feature "no-holes"

  rm -f $seqres.full

  test_cloning_inline_extents()
  {
      local mkfs_opts=$1
      local mount_opts=$2

      _scratch_mkfs $mkfs_opts >>$seqres.full 2>&1
      _scratch_mount $mount_opts

      # File bar, the source for all the following clone operations, consists
      # of a single inline extent (50 bytes).
      $XFS_IO_PROG -f -c "pwrite -S 0xbb 0 50" $SCRATCH_MNT/bar \
          | _filter_xfs_io

      # Test cloning into a file with an extent (non-inlined) where the
      # destination offset overlaps that extent. It should not be possible to
      # clone the inline extent from file bar into this file.
      $XFS_IO_PROG -f -c "pwrite -S 0xaa 0K 16K" $SCRATCH_MNT/foo \
          | _filter_xfs_io
      $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo

      # Doing IO against any range in the first 4K of the file should work.
      # Due to a past clone ioctl bug which allowed cloning the inline extent,
      # these operations resulted in EIO errors.
      echo "File foo data after clone operation:"
      # All bytes should have the value 0xaa (clone operation failed and did
      # not modify our file).
      od -t x1 $SCRATCH_MNT/foo
      $XFS_IO_PROG -c "pwrite -S 0xcc 0 100" $SCRATCH_MNT/foo | _filter_xfs_io

      # Test cloning the inline extent against a file which has a hole in its
      # first 4K followed by a non-inlined extent. It should not be possible
      # as well to clone the inline extent from file bar into this file.
      $XFS_IO_PROG -f -c "pwrite -S 0xdd 4K 12K" $SCRATCH_MNT/foo2 \
          | _filter_xfs_io
      $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo2

      # Doing IO against any range in the first 4K of the file should work.
      # Due to a past clone ioctl bug which allowed cloning the inline extent,
      # these operations resulted in EIO errors.
      echo "File foo2 data after clone operation:"
      # All bytes should have the value 0x00 (clone operation failed and did
      # not modify our file).
      od -t x1 $SCRATCH_MNT/foo2
      $XFS_IO_PROG -c "pwrite -S 0xee 0 90" $SCRATCH_MNT/foo2 | _filter_xfs_io

      # Test cloning the inline extent against a file which has a size of zero
      # but has a prealloc extent. It should not be possible as well to clone
      # the inline extent from file bar into this file.
      $XFS_IO_PROG -f -c "falloc -k 0 1M" $SCRATCH_MNT/foo3 | _filter_xfs_io
      $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo3

      # Doing IO against any range in the first 4K of the file should work.
      # Due to a past clone ioctl bug which allowed cloning the inline extent,
      # these operations resulted in EIO errors.
      echo "First 50 bytes of foo3 after clone operation:"
      # Should not be able to read any bytes, file has 0 bytes i_size (the
      # clone operation failed and did not modify our file).
      od -t x1 $SCRATCH_MNT/foo3
      $XFS_IO_PROG -c "pwrite -S 0xff 0 90" $SCRATCH_MNT/foo3 | _filter_xfs_io

      # Test cloning the inline extent against a file which consists of a
      # single inline extent that has a size not greater than the size of
      # bar's inline extent (40 < 50).
      # It should be possible to do the extent cloning from bar to this file.
      $XFS_IO_PROG -f -c "pwrite -S 0x01 0 40" $SCRATCH_MNT/foo4 \
          | _filter_xfs_io
      $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo4

      # Doing IO against any range in the first 4K of the file should work.
      echo "File foo4 data after clone operation:"
      # Must match file bar's content.
      od -t x1 $SCRATCH_MNT/foo4
      $XFS_IO_PROG -c "pwrite -S 0x02 0 90" $SCRATCH_MNT/foo4 | _filter_xfs_io

      # Test cloning the inline extent against a file which consists of a
      # single inline extent that has a size greater than the size of bar's
      # inline extent (60 > 50).
      # It should not be possible to clone the inline extent from file bar
      # into this file.
      $XFS_IO_PROG -f -c "pwrite -S 0x03 0 60" $SCRATCH_MNT/foo5 \
          | _filter_xfs_io
      $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo5

      # Reading the file should not fail.
      echo "File foo5 data after clone operation:"
      # Must have a size of 60 bytes, with all bytes having a value of 0x03
      # (the clone operation failed and did not modify our file).
      od -t x1 $SCRATCH_MNT/foo5

      # Test cloning the inline extent against a file which has no extents but
      # has a size greater than bar's inline extent (16K > 50).
      # It should not be possible to clone the inline extent from file bar
      # into this file.
      $XFS_IO_PROG -f -c "truncate 16K" $SCRATCH_MNT/foo6 | _filter_xfs_io
      $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo6

      # Reading the file should not fail.
      echo "File foo6 data after clone operation:"
      # Must have a size of 16K, with all bytes having a value of 0x00 (the
      # clone operation failed and did not modify our file).
      od -t x1 $SCRATCH_MNT/foo6

      # Test cloning the inline extent against a file which has no extents but
      # has a size not greater than bar's inline extent (30 < 50).
      # It should be possible to clone the inline extent from file bar into
      # this file.
      $XFS_IO_PROG -f -c "truncate 30" $SCRATCH_MNT/foo7 | _filter_xfs_io
      $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo7

      # Reading the file should not fail.
      echo "File foo7 data after clone operation:"
      # Must have a size of 50 bytes, with all bytes having a value of 0xbb.
      od -t x1 $SCRATCH_MNT/foo7

      # Test cloning the inline extent against a file which has a size not
      # greater than the size of bar's inline extent (20 < 50) but has
      # a prealloc extent that goes beyond the file's size. It should not be
      # possible to clone the inline extent from bar into this file.
      $XFS_IO_PROG -f -c "falloc -k 0 1M" \
                      -c "pwrite -S 0x88 0 20" \
                      $SCRATCH_MNT/foo8 | _filter_xfs_io
      $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo8

      echo "File foo8 data after clone operation:"
      # Must have a size of 20 bytes, with all bytes having a value of 0x88
      # (the clone operation did not modify our file).
      od -t x1 $SCRATCH_MNT/foo8

      _scratch_unmount
  }

  echo -e "\nTesting without compression and without the no-holes feature...\n"
  test_cloning_inline_extents

  echo -e "\nTesting with compression and without the no-holes feature...\n"
  test_cloning_inline_extents "" "-o compress"

  echo -e "\nTesting without compression and with the no-holes feature...\n"
  test_cloning_inline_extents "-O no-holes" ""

  echo -e "\nTesting with compression and with the no-holes feature...\n"
  test_cloning_inline_extents "-O no-holes" "-o compress"

  status=0
  exit

Cc: stable@vger.kernel.org
Signed-off-by: Filipe Manana <fdmanana@suse.com>
2015-10-14 04:36:43 +01:00
..
9p 9p: fix return code of read() when count is 0 2015-08-23 14:21:36 -05:00
adfs fs/adfs: remove unneeded cast 2015-06-30 19:44:57 -07:00
affs fs/affs: make root lookup from blkdev logical size 2015-09-10 13:29:01 -07:00
afs net: Add a struct net parameter to sock_create_kern 2015-05-11 10:50:17 -04:00
autofs4 make simple_positive() public 2015-06-23 18:02:01 -04:00
befs Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2015-07-04 19:36:06 -07:00
bfs Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2015-04-26 17:22:07 -07:00
btrfs Btrfs: fix file corruption and data loss after cloning inline extents 2015-10-14 04:36:43 +01:00
cachefiles Merge branch 'fscache-fixes' into for-next 2015-06-23 18:01:30 -04:00
ceph Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client 2015-09-11 12:33:03 -07:00
cifs [CIFS] Update cifs version number 2015-10-03 16:54:17 -05:00
coda fs/coda: fix readlink buffer overflow 2015-09-10 13:29:01 -07:00
configfs configfs: fix kernel infoleak through user-controlled format string 2015-07-17 16:39:53 -07:00
cramfs
debugfs debugfs: Export bool read/write functions 2015-07-20 18:44:50 +01:00
devpts devpts: if initialization failed, don't crash when opening /dev/ptmx 2015-06-30 19:44:58 -07:00
dlm dlm for 4.3 2015-09-03 12:57:48 -07:00
ecryptfs Invalidate stale eCryptfs dcache entries caused by unlinked lower inodes 2015-09-08 11:26:17 -07:00
efivarfs Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2015-05-06 10:57:37 -07:00
efs fs/efs: femove unneeded cast 2015-06-25 17:00:42 -07:00
exofs pagemap.h: move dir_pages() over there 2015-06-23 18:02:00 -04:00
exportfs VFS: (Scripted) Convert S_ISLNK/DIR/REG(dentry->d_inode) to d_is_*(dentry) 2015-02-22 11:38:41 -05:00
ext2 ext2: huge page fault support 2015-09-08 15:35:28 -07:00
ext4 ext4: start transaction before calling into DAX 2015-09-08 15:35:28 -07:00
f2fs Merge tag 'for-f2fs-4.3' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs 2015-09-03 13:10:22 -07:00
fat writeback: separate out include/linux/backing-dev-defs.h 2015-06-02 08:33:34 -06:00
freevxfs freevxfs: Grammar s/an negative/a negative/ 2015-08-07 13:59:24 +02:00
fscache FS-Cache: Retain the netfs context in the retrieval op earlier 2015-04-02 14:28:53 +01:00
fuse fs/fuse: fix ioctl type confusion 2015-08-16 12:35:44 -07:00
gfs2 GFS2: merge window 2015-09-11 12:23:51 -07:00
hfs hfs: fix B-tree corruption after insertion at position 0 2015-09-10 13:29:01 -07:00
hfsplus hfs,hfsplus: cache pages correctly between bnode_create and bnode_free 2015-09-10 13:29:01 -07:00
hostfs fs: create and use seq_show_option for escaping 2015-09-04 16:54:41 -07:00
hpfs hpfs: update ctime and mtime on directory modification 2015-09-03 11:55:30 -07:00
hugetlbfs hugetlbfs: add hugetlbfs_fallocate() 2015-09-08 15:35:28 -07:00
isofs VFS: normal filesystems (and lustre): d_inode() annotations 2015-04-15 15:06:57 -04:00
jbd2 jbd2: limit number of reserved credits 2015-08-04 11:21:52 -04:00
jffs2 Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2015-07-04 19:36:06 -07:00
jfs Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs 2015-09-03 12:28:30 -07:00
kernfs kernfs: implement kernfs_path_len() 2015-08-18 15:49:15 -07:00
lockd lockd: NLM grace period shouldn't block NFSv4 opens 2015-08-13 10:22:06 -04:00
logfs block: remove bio_get_nr_vecs() 2015-08-13 12:32:04 -06:00
minix Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2015-07-04 19:36:06 -07:00
ncpfs ncpfs: successful rename() should invalidate caches for parents 2015-06-14 11:31:39 -04:00
nfs NFS: Fix a tracepoint NULL-pointer dereference 2015-10-06 18:56:25 -04:00
nfs_common lockd: NLM grace period shouldn't block NFSv4 opens 2015-08-13 10:22:06 -04:00
nfsd NFS client updates for Linux 4.3 2015-09-07 14:02:24 -07:00
nilfs2 block: remove bio_get_nr_vecs() 2015-08-13 12:32:04 -06:00
nls
notify Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2015-09-05 20:34:28 -07:00
ntfs ntfs: delete unnecessary checks before calling iput() 2015-09-04 16:54:41 -07:00
ocfs2 ocfs2/dlm: fix deadlock when dispatch assert master 2015-09-22 15:09:53 -07:00
omfs omfs: fix potential integer overflow in allocator 2015-05-28 18:25:19 -07:00
openpromfs
overlayfs fs: create and use seq_show_option for escaping 2015-09-04 16:54:41 -07:00
proc proc: convert to kstrto*()/kstrto*_from_user() 2015-09-10 13:29:01 -07:00
pstore Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace 2015-07-03 15:20:57 -07:00
qnx4
qnx6 pagemap.h: move dir_pages() over there 2015-06-23 18:02:00 -04:00
quota Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2015-09-05 20:34:28 -07:00
ramfs VFS: normal filesystems (and lustre): d_inode() annotations 2015-04-15 15:06:57 -04:00
reiserfs fs: create and use seq_show_option for escaping 2015-09-04 16:54:41 -07:00
romfs make new_sync_{read,write}() static 2015-04-11 22:29:40 -04:00
squashfs fs: cleanup slight list_entry abuse 2015-06-23 18:01:59 -04:00
sysfs vfs: Commit to never having exectuables on proc and sysfs. 2015-07-10 10:39:25 -05:00
sysv pagemap.h: move dir_pages() over there 2015-06-23 18:02:00 -04:00
tracefs Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2015-07-04 19:36:06 -07:00
ubifs UBIFS: Kill unneeded locking in ubifs_init_security 2015-09-29 12:45:42 +02:00
udf udf: Don't modify filesystem for read-only mounts 2015-08-20 14:58:35 +02:00
ufs fix ufs write vs readpage race when writing into a hole 2015-09-09 10:43:12 -07:00
xfs xfs: huge page fault support 2015-09-08 15:35:28 -07:00
aio.c mm: move ->mremap() from file_operations to vm_operations_struct 2015-09-04 16:54:41 -07:00
anon_inodes.c
attr.c
bad_inode.c don't bother with most of the bad_file_ops methods 2015-02-20 04:03:58 -05:00
binfmt_aout.c
binfmt_elf_fdpic.c
binfmt_elf.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2015-07-04 19:36:06 -07:00
binfmt_em86.c
binfmt_flat.c
binfmt_misc.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2015-04-26 17:22:07 -07:00
binfmt_script.c
block_dev.c blockdev: don't set S_DAX for misaligned partitions 2015-09-15 20:08:05 -04:00
buffer.c fs: use helper bio_add_page() instead of open coding on bi_io_vec 2015-08-13 12:32:00 -06:00
char_dev.c fs/char_dev.c: fix incorrect documentation for unregister_chrdev_region 2015-08-05 13:49:35 -07:00
compat_binfmt_elf.c
compat_ioctl.c ioctl_compat: handle FITRIM 2015-07-09 11:42:21 -07:00
compat.c
coredump.c fs: Don't dump core if the corefile would become world-readable. 2015-09-10 13:29:01 -07:00
dax.c dax: fix NULL pointer in __dax_pmd_fault() 2015-10-01 21:42:35 -04:00
dcache.c dcache: Reduce the scope of i_lock in d_splice_alias 2015-08-21 02:34:37 -04:00
dcookies.c
direct-io.c block: remove bio_get_nr_vecs() 2015-08-13 12:32:04 -06:00
drop_caches.c inode: convert inode_sb_list_lock to per-sb 2015-08-17 18:39:46 -04:00
eventfd.c eventfd: don't take the spinlock in eventfd_poll 2015-02-17 14:34:52 -08:00
eventpoll.c epoll: optimize setting task running after blocking 2015-02-13 21:21:40 -08:00
exec.c vfs: Commit to never having exectuables on proc and sysfs. 2015-07-10 10:39:25 -05:00
fcntl.c
fhandle.c vfs: read file_handle only once in handle_to_path 2015-06-02 10:29:07 -07:00
file_table.c fs, file table: reinit files_stat.max_files after deferred memory initialisation 2015-08-07 04:39:40 +03:00
file.c fs/file.c: __fget() and dup2() atomicity rules 2015-07-01 02:31:08 -04:00
filesystems.c
fs_pin.c fs_pin: Allow for the possibility that m_list or s_list go unused. 2015-04-09 11:39:55 -05:00
fs_struct.c
fs-writeback.c fs-writeback: unplug before cond_resched in writeback_sb_inodes 2015-09-19 18:50:19 -07:00
inode.c inode: don't softlockup when evicting inodes 2015-08-18 10:20:09 -07:00
internal.h inode: rename i_wb_list to i_io_list 2015-08-17 23:38:10 -04:00
ioctl.c fsioctl.c: make generic_block_fiemap() signal-tolerant 2015-02-10 14:30:30 -08:00
Kconfig fs: Remove ext3 filesystem driver 2015-07-23 20:59:40 +02:00
Kconfig.binfmt mm: split ET_DYN ASLR from mmap ASLR 2015-04-14 16:49:05 -07:00
libfs.c fs: Set the size of empty dirs to 0. 2015-08-12 15:28:45 -05:00
locks.c fs: fix fs/locks.c kernel-doc warning 2015-08-31 16:27:25 -04:00
Makefile userfaultfd: buildsystem activation 2015-09-04 16:54:41 -07:00
mbcache.c
mount.h fs: use seq_open_private() for proc_mounts 2015-06-30 19:44:56 -07:00
mpage.c block: remove bio_get_nr_vecs() 2015-08-13 12:32:04 -06:00
namei.c namei: results of d_is_negative() should be checked after dentry revalidation 2015-10-10 10:17:27 -07:00
namespace.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace 2015-09-01 16:13:25 -07:00
no-block.c
nsfs.c fs/seq_file: convert int seq_vprint/seq_printf/etc... returns to void 2015-09-11 15:21:34 -07:00
open.c vfs: Commit to never having exectuables on proc and sysfs. 2015-07-10 10:39:25 -05:00
pipe.c VFS: assorted weird filesystems: d_inode() annotations 2015-04-15 15:06:58 -04:00
pnode.c mnt: Don't propagate unmounts to locked mounts 2015-04-02 20:34:20 -05:00
pnode.h mnt: Clarify and correct the disconnect logic in umount_tree 2015-07-22 20:33:27 -05:00
posix_acl.c fs/posix_acl.c: make posix_acl_create() safer and cleaner 2015-06-23 18:01:07 -04:00
proc_namespace.c fs: use seq_open_private() for proc_mounts 2015-06-30 19:44:56 -07:00
read_write.c new_sync_write(): discard ->ki_pos unless the return value is positive 2015-04-11 22:29:46 -04:00
readdir.c
select.c locking/arch: Rename set_mb() to smp_store_mb() 2015-05-19 08:32:00 +02:00
seq_file.c fs/seq_file: convert int seq_vprint/seq_printf/etc... returns to void 2015-09-11 15:21:34 -07:00
signalfd.c signalfd: fix information leak in signalfd_copyinfo 2015-08-07 04:39:40 +03:00
splice.c Merge branch 'akpm' (patches from Andrew) 2015-06-24 20:47:21 -07:00
stack.c
stat.c VFS: assorted d_backing_inode() annotations 2015-04-15 15:06:59 -04:00
statfs.c
super.c Merge branch 'superblock-scaling' of git://git.kernel.org/pub/scm/linux/kernel/git/josef/btrfs-next into for-next 2015-08-21 02:31:20 -04:00
sync.c vfs: add support for a lazytime mount option 2015-02-05 02:45:00 -05:00
timerfd.c
userfaultfd.c userfaultfd: revert "userfaultfd: waitqueue: add nr wake parameter to __wake_up_locked_key" 2015-09-22 15:09:53 -07:00
utimes.c
xattr.c evm: fix potential race when removing xattrs 2015-05-21 13:28:47 -04:00