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>
Этот коммит содержится в:

коммит произвёл
Al Viro

родитель
99621b44aa
Коммит
8c0a853770
@@ -307,12 +307,6 @@ void deactivate_locked_super(struct super_block *s)
|
||||
|
||||
/* caches are now gone, we can safely kill the shrinker now */
|
||||
unregister_shrinker(&s->s_shrink);
|
||||
|
||||
/*
|
||||
* We need to call rcu_barrier so all the delayed rcu free
|
||||
* inodes are flushed before we release the fs module.
|
||||
*/
|
||||
rcu_barrier();
|
||||
put_filesystem(fs);
|
||||
put_super(s);
|
||||
} else {
|
||||
|
Ссылка в новой задаче
Block a user