summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/delayed-ref.h
diff options
context:
space:
mode:
authorDavid Sterba <dsterba@suse.cz>2013-12-16 17:34:17 +0100
committerChris Mason <clm@fb.com>2014-01-28 13:20:01 -0800
commit2c68653787f91c62f8891209dc1f617088c822e4 (patch)
tree4f17ea8a804b6174de028c85aa3037c6ec6d28de /fs/btrfs/delayed-ref.h
parenta8d89f5ba0e17622cde8f5ac48ef745a9fb1e13b (diff)
downloadop-kernel-dev-2c68653787f91c62f8891209dc1f617088c822e4.zip
op-kernel-dev-2c68653787f91c62f8891209dc1f617088c822e4.tar.gz
btrfs: Check read-only status of roots during send
All the subvolues that are involved in send must be read-only during the whole operation. The ioctl SUBVOL_SETFLAGS could be used to change the status to read-write and the result of send stream is undefined if the data change unexpectedly. Fix that by adding a refcount for all involved roots and verify that there's no send in progress during SUBVOL_SETFLAGS ioctl call that does read-only -> read-write transition. We need refcounts because there are no restrictions on number of send parallel operations currently run on a single subvolume, be it source, parent or one of the multiple clone sources. Kernel is silent when the RO checks fail and returns EPERM. The same set of checks is done already in userspace before send starts. Signed-off-by: David Sterba <dsterba@suse.cz> Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Chris Mason <clm@fb.com>
Diffstat (limited to 'fs/btrfs/delayed-ref.h')
0 files changed, 0 insertions, 0 deletions
OpenPOWER on IntegriCloud