linux/fs/romfs
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
..
Kconfig NOMMU: Fix the RomFS Kconfig to ensure at least one backing store is selected 2009-03-24 09:02:39 +00:00
Makefile NOMMU: Make it possible for RomFS to use MTD devices directly 2009-03-24 09:01:32 +00:00
internal.h ROMFS: romfs_lookup() shouldn't be doing a partial name comparison 2009-04-24 13:28:31 -07:00
mmap-nommu.c romfs: do not use mtd->get_unmapped_area directly 2012-01-09 18:26:12 +00:00
storage.c romfs: switch to new MTD API 2012-03-27 00:19:30 +01:00
super.c fs: push rcu_barrier() from deactivate_locked_super() to filesystems 2012-10-02 21:35:55 -04:00