Sage Weil 0c1f91f271 ceph: unwind canceled flock state ...

If we request a lock and then abort (e.g., ^C), we need to send a matching
unlock request to the MDS to unwind our lock attempt to avoid indefinitely
blocking other clients.

Reported-by: Brian Chrisman <brchrisman@gmail.com>
Signed-off-by: Sage Weil <sage@newdream.net>

2011-06-07 21:36:45 -07:00

..

addr.c

ceph: use ihold when we already have an inode ref

2011-06-07 21:34:11 -07:00

caps.c

ceph: use ihold when we already have an inode ref

2011-06-07 21:34:11 -07:00

ceph_frag.c

…

debugfs.c

…

dir.c

ceph: use ihold when we already have an inode ref

2011-06-07 21:34:11 -07:00

export.c

ceph: use ihold when we already have an inode ref

2011-06-07 21:34:11 -07:00

file.c

ceph: fix ENOENT logic in striped_read

2011-06-07 21:34:16 -07:00

inode.c

ceph: use ihold when we already have an inode ref

2011-06-07 21:34:11 -07:00

ioctl.c

ceph: use ihold when we already have an inode ref

2011-06-07 21:34:11 -07:00

ioctl.h

…

Kconfig

…

locks.c

ceph: unwind canceled flock state

2011-06-07 21:36:45 -07:00

Makefile

…

mds_client.c

ceph: fix cap flush race reentrancy

2011-05-24 11:52:12 -07:00

mds_client.h

ceph: fix cap flush race reentrancy

2011-05-24 11:52:12 -07:00

mdsmap.c

…

snap.c

ceph: use ihold when we already have an inode ref

2011-06-07 21:34:11 -07:00

strings.c

…

super.c

…

super.h

…

xattr.c

ceph: use ihold when we already have an inode ref

2011-06-07 21:34:11 -07:00