cgroup: remove CGRP_WAIT_ON_RMDIR, cgroup_exclude_rmdir() and cgroup_release_and_wakeup_rmdir()

CGRP_WAIT_ON_RMDIR is another kludge which was added to make cgroup
destruction rollback somewhat working.  cgroup_rmdir() used to drain
CSS references and CGRP_WAIT_ON_RMDIR and the associated waitqueue and
helpers were used to allow the task performing rmdir to wait for the
next relevant event.

Unfortunately, the wait is visible to controllers too and the
mechanism got exposed to memcg by 887032670d ("cgroup avoid permanent
sleep at rmdir").

Now that the draining and retries are gone, CGRP_WAIT_ON_RMDIR is
unnecessary.  Remove it and all the mechanisms supporting it.  Note
that memcontrol.c changes are essentially revert of 887032670d
("cgroup avoid permanent sleep at rmdir").

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Balbir Singh <bsingharora@gmail.com>

1 files changed, 0 insertions, 51 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 66204a6f68f..c5f6fb28dd0 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -966,33 +966,6 @@ static void cgroup_d_remove_dir(struct dentry *dentry)
 }
 
 /*
- * A queue for waiters to do rmdir() cgroup. A tasks will sleep when
- * cgroup->count == 0 && list_empty(&cgroup->children) && subsys has some
- * reference to css->refcnt. In general, this refcnt is expected to goes down
- * to zero, soon.
- *
- * CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex;
- */
-static DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
-
-static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp)
-{
-	if (unlikely(test_and_clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
-		wake_up_all(&cgroup_rmdir_waitq);
-}
-
-void cgroup_exclude_rmdir(struct cgroup_subsys_state *css)
-{
-	css_get(css);
-}
-
-void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css)
-{
-	cgroup_wakeup_rmdir_waiter(css->cgroup);
-	css_put(css);
-}
-
-/*
  * Call with cgroup_mutex held. Drops reference counts on modules, including
  * any duplicate ones that parse_cgroupfs_options took. If this function
  * returns an error, no reference counts are touched.
@@ -1963,12 +1936,6 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	}
 
 	synchronize_rcu();
-
-	/*
-	 * wake up rmdir() waiter. the rmdir should fail since the cgroup
-	 * is no longer empty.
-	 */
-	cgroup_wakeup_rmdir_waiter(cgrp);
 out:
 	if (retval) {
 		for_each_subsys(root, ss) {
@@ -2138,7 +2105,6 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 	 * step 5: success! and cleanup
 	 */
 	synchronize_rcu();
-	cgroup_wakeup_rmdir_waiter(cgrp);
 	retval = 0;
 out_put_css_set_refs:
 	if (retval) {
@@ -4058,26 +4024,13 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	struct cgroup_event *event, *tmp;
 	struct cgroup_subsys *ss;
 
-	/*
-	 * In general, subsystem has no css->refcnt after pre_destroy(). But
-	 * in racy cases, subsystem may have to get css->refcnt after
-	 * pre_destroy() and it makes rmdir return with -EBUSY. This sometimes
-	 * make rmdir return -EBUSY too often. To avoid that, we use waitqueue
-	 * for cgroup's rmdir. CGRP_WAIT_ON_RMDIR is for synchronizing rmdir
-	 * and subsystem's reference count handling. Please see css_get/put
-	 * and css_tryget() and cgroup_wakeup_rmdir_waiter() implementation.
-	 */
-	set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
-
 	/* the vfs holds both inode->i_mutex already */
 	mutex_lock(&cgroup_mutex);
 	parent = cgrp->parent;
 	if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
-		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
 		mutex_unlock(&cgroup_mutex);
 		return -EBUSY;
 	}
-	prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE);
 
 	/*
 	 * Block new css_tryget() by deactivating refcnt and mark @cgrp
@@ -4114,9 +4067,6 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	for_each_subsys(cgrp->root, ss)
 		css_put(cgrp->subsys[ss->subsys_id]);
 
-	finish_wait(&cgroup_rmdir_waitq, &wait);
-	clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
-
 	raw_spin_lock(&release_list_lock);
 	if (!list_empty(&cgrp->release_list))
 		list_del_init(&cgrp->release_list);
@@ -4864,7 +4814,6 @@ void __css_put(struct cgroup_subsys_state *css)
 			set_bit(CGRP_RELEASABLE, &cgrp->flags);
 			check_for_release(cgrp);
 		}
-		cgroup_wakeup_rmdir_waiter(cgrp);
 		break;
 	case 0:
 		schedule_work(&css->dput_work);