diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index a3098046250b..47868a86ba2b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -144,10 +144,6 @@ enum { CGRP_RELEASABLE, /* Control Group requires release notifications to userspace */ CGRP_NOTIFY_ON_RELEASE, - /* - * A thread in rmdir() is wating for this cgroup. - */ - CGRP_WAIT_ON_RMDIR, /* * Clone cgroup values when creating a new child cgroup */ @@ -411,23 +407,6 @@ int cgroup_task_count(const struct cgroup *cgrp); /* Return true if cgrp is a descendant of the task's cgroup */ int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task); -/* - * When the subsys has to access css and may add permanent refcnt to css, - * it should take care of racy conditions with rmdir(). Following set of - * functions, is for stop/restart rmdir if necessary. - * Because these will call css_get/put, "css" should be alive css. - * - * cgroup_exclude_rmdir(); - * ...do some jobs which may access arbitrary empty cgroup - * cgroup_release_and_wakeup_rmdir(); - * - * When someone removes a cgroup while cgroup_exclude_rmdir() holds it, - * it sleeps and cgroup_release_and_wakeup_rmdir() will wake him up. - */ - -void cgroup_exclude_rmdir(struct cgroup_subsys_state *css); -void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css); - /* * Control Group taskset, used to pass around set of tasks to cgroup_subsys * methods. diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 66204a6f68f3..c5f6fb28dd0e 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -965,33 +965,6 @@ static void cgroup_d_remove_dir(struct dentry *dentry) remove_dir(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 @@ -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); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 37c356646544..930edfaa5187 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2681,13 +2681,6 @@ static int mem_cgroup_move_account(struct page *page, /* caller should have done css_get */ pc->mem_cgroup = to; mem_cgroup_charge_statistics(to, anon, nr_pages); - /* - * We charges against "to" which may not have any tasks. Then, "to" - * can be under rmdir(). But in current implementation, caller of - * this function is just force_empty() and move charge, so it's - * guaranteed that "to" is never removed. So, we don't check rmdir - * status here. - */ move_unlock_mem_cgroup(from, &flags); ret = 0; unlock: @@ -2893,7 +2886,6 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg, return; if (!memcg) return; - cgroup_exclude_rmdir(&memcg->css); __mem_cgroup_commit_charge(memcg, page, 1, ctype, true); /* @@ -2907,12 +2899,6 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg, swp_entry_t ent = {.val = page_private(page)}; mem_cgroup_uncharge_swap(ent); } - /* - * At swapin, we may charge account against cgroup which has no tasks. - * So, rmdir()->pre_destroy() can be called while we do this charge. - * In that case, we need to call pre_destroy() again. check it here. - */ - cgroup_release_and_wakeup_rmdir(&memcg->css); } void mem_cgroup_commit_charge_swapin(struct page *page, @@ -3360,8 +3346,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg, if (!memcg) return; - /* blocks rmdir() */ - cgroup_exclude_rmdir(&memcg->css); + if (!migration_ok) { used = oldpage; unused = newpage; @@ -3395,13 +3380,6 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg, */ if (anon) mem_cgroup_uncharge_page(used); - /* - * At migration, we may charge account against cgroup which has no - * tasks. - * So, rmdir()->pre_destroy() can be called while we do this charge. - * In that case, we need to call pre_destroy() again. check it here. - */ - cgroup_release_and_wakeup_rmdir(&memcg->css); } /*