Kirill A. Shutemov 8c0a853770 fs: push rcu_barrier() from deactivate_locked_super() to filesystems ... There's no reason to call rcu_barrier() on every deactivate_locked_super(). We only need to make sure that all delayed rcu free inodes are flushed before we destroy related cache. Removing rcu_barrier() from deactivate_locked_super() affects some fast paths. E.g. on my machine exit_group() of a last process in IPC namespace takes 0.07538s. rcu_barrier() takes 0.05188s of that time. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>		2012-10-02 21:35:55 -04:00
..
addr.c	ceph: Push file_update_time() into ceph_page_mkwrite()	2012-07-31 01:02:45 +04:00
caps.c
ceph_frag.c
debugfs.c	libceph: delay debugfs initialization until we learn global_id	2012-08-20 10:03:15 -07:00
dir.c	ceph: simplify+fix atomic_open	2012-08-02 09:11:19 -07:00
export.c
file.c	ceph: simplify+fix atomic_open	2012-08-02 09:11:19 -07:00
inode.c	ceph: don't abuse d_delete() on failure exits	2012-09-26 22:20:20 -04:00
ioctl.c	ceph: avoid divide by zero in __validate_layout()	2012-08-21 15:55:28 -07:00
ioctl.h
Kconfig
locks.c
Makefile
mds_client.c	ceph: close old con before reopening on mds reconnect	2012-07-30 18:15:32 -07:00
mds_client.h
mdsmap.c
snap.c	ceph: define snap counts as u32 everywhere	2012-07-30 18:15:47 -07:00
strings.c
super.c	fs: push rcu_barrier() from deactivate_locked_super() to filesystems	2012-10-02 21:35:55 -04:00
super.h	ceph: simplify+fix atomic_open	2012-08-02 09:11:19 -07:00
xattr.c	ceph: fix potential double free	2012-07-30 18:15:35 -07:00