Merge branch 'for-3.18' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:
 "Nothing too interesting.  Just a handful of cleanup patches"

* 'for-3.18' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  Revert "cgroup: remove redundant variable in cgroup_mount()"
  cgroup: remove redundant variable in cgroup_mount()
  cgroup: fix missing unlock in cgroup_release_agent()
  cgroup: remove CGRP_RELEASABLE flag
  perf/cgroup: Remove perf_put_cgroup()
  cgroup: remove redundant check in cgroup_ino()
  cpuset: simplify proc_cpuset_show()
  cgroup: simplify proc_cgroup_show()
  cgroup: use a per-cgroup work for release agent
  cgroup: remove bogus comments
  cgroup: remove redundant code in cgroup_rmdir()
  cgroup: remove some useless forward declarations
  cgroup: fix a typo in comment.
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 4c542b9..950100e 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -376,37 +376,6 @@
 
 #endif
 
-#ifdef CONFIG_CGROUPS
-static int cgroup_open(struct inode *inode, struct file *file)
-{
-	struct pid *pid = PROC_I(inode)->pid;
-	return single_open(file, proc_cgroup_show, pid);
-}
-
-static const struct file_operations proc_cgroup_operations = {
-	.open		= cgroup_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-#endif
-
-#ifdef CONFIG_PROC_PID_CPUSET
-
-static int cpuset_open(struct inode *inode, struct file *file)
-{
-	struct pid *pid = PROC_I(inode)->pid;
-	return single_open(file, proc_cpuset_show, pid);
-}
-
-static const struct file_operations proc_cpuset_operations = {
-	.open		= cpuset_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-#endif
-
 static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns,
 			  struct pid *pid, struct task_struct *task)
 {
@@ -2579,10 +2548,10 @@
 	REG("latency",  S_IRUGO, proc_lstats_operations),
 #endif
 #ifdef CONFIG_PROC_PID_CPUSET
-	REG("cpuset",     S_IRUGO, proc_cpuset_operations),
+	ONE("cpuset",     S_IRUGO, proc_cpuset_show),
 #endif
 #ifdef CONFIG_CGROUPS
-	REG("cgroup",  S_IRUGO, proc_cgroup_operations),
+	ONE("cgroup",  S_IRUGO, proc_cgroup_show),
 #endif
 	ONE("oom_score",  S_IRUGO, proc_oom_score),
 	REG("oom_adj",    S_IRUGO|S_IWUSR, proc_oom_adj_operations),
@@ -2925,10 +2894,10 @@
 	REG("latency",  S_IRUGO, proc_lstats_operations),
 #endif
 #ifdef CONFIG_PROC_PID_CPUSET
-	REG("cpuset",    S_IRUGO, proc_cpuset_operations),
+	ONE("cpuset",    S_IRUGO, proc_cpuset_show),
 #endif
 #ifdef CONFIG_CGROUPS
-	REG("cgroup",  S_IRUGO, proc_cgroup_operations),
+	ONE("cgroup",  S_IRUGO, proc_cgroup_show),
 #endif
 	ONE("oom_score", S_IRUGO, proc_oom_score),
 	REG("oom_adj",   S_IRUGO|S_IWUSR, proc_oom_adj_operations),
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index b5223c5..1d51968 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -27,7 +27,6 @@
 
 struct cgroup_root;
 struct cgroup_subsys;
-struct inode;
 struct cgroup;
 
 extern int cgroup_init_early(void);
@@ -38,7 +37,8 @@
 extern int cgroupstats_build(struct cgroupstats *stats,
 				struct dentry *dentry);
 
-extern int proc_cgroup_show(struct seq_file *, void *);
+extern int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
+			    struct pid *pid, struct task_struct *tsk);
 
 /* define the enumeration of all cgroup subsystems */
 #define SUBSYS(_x) _x ## _cgrp_id,
@@ -161,11 +161,6 @@
 
 /* bits in struct cgroup flags field */
 enum {
-	/*
-	 * Control Group has previously had a child cgroup or a task,
-	 * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set)
-	 */
-	CGRP_RELEASABLE,
 	/* Control Group requires release notifications to userspace */
 	CGRP_NOTIFY_ON_RELEASE,
 	/*
@@ -235,13 +230,6 @@
 	struct list_head e_csets[CGROUP_SUBSYS_COUNT];
 
 	/*
-	 * Linked list running through all cgroups that can
-	 * potentially be reaped by the release agent. Protected by
-	 * release_list_lock
-	 */
-	struct list_head release_list;
-
-	/*
 	 * list of pidlists, up to two for each namespace (one for procs, one
 	 * for tasks); created on demand.
 	 */
@@ -250,6 +238,9 @@
 
 	/* used to wait for offlining of csses */
 	wait_queue_head_t offline_waitq;
+
+	/* used to schedule release agent */
+	struct work_struct release_agent_work;
 };
 
 #define MAX_CGROUP_ROOT_NAMELEN 64
@@ -536,13 +527,10 @@
 	return !list_empty(&cgrp->cset_links);
 }
 
-/* returns ino associated with a cgroup, 0 indicates unmounted root */
+/* returns ino associated with a cgroup */
 static inline ino_t cgroup_ino(struct cgroup *cgrp)
 {
-	if (cgrp->kn)
-		return cgrp->kn->ino;
-	else
-		return 0;
+	return cgrp->kn->ino;
 }
 
 /* cft/css accessors for cftype->write() operation */
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 6e39c9b..2f073db 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -86,7 +86,8 @@
 
 extern void cpuset_task_status_allowed(struct seq_file *m,
 					struct task_struct *task);
-extern int proc_cpuset_show(struct seq_file *, void *);
+extern int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
+			    struct pid *pid, struct task_struct *tsk);
 
 extern int cpuset_mem_spread_node(void);
 extern int cpuset_slab_spread_node(void);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 3a73f99..cab7dc4 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -185,7 +185,6 @@
 static struct cftype cgroup_dfl_base_files[];
 static struct cftype cgroup_legacy_base_files[];
 
-static void cgroup_put(struct cgroup *cgrp);
 static int rebind_subsystems(struct cgroup_root *dst_root,
 			     unsigned int ss_mask);
 static int cgroup_destroy_locked(struct cgroup *cgrp);
@@ -195,7 +194,6 @@
 static void kill_css(struct cgroup_subsys_state *css);
 static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
 			      bool is_add);
-static void cgroup_pidlist_destroy_all(struct cgroup *cgrp);
 
 /* IDR wrappers which synchronize using cgroup_idr_lock */
 static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end,
@@ -331,14 +329,6 @@
 	return false;
 }
 
-static int cgroup_is_releasable(const struct cgroup *cgrp)
-{
-	const int bits =
-		(1 << CGRP_RELEASABLE) |
-		(1 << CGRP_NOTIFY_ON_RELEASE);
-	return (cgrp->flags & bits) == bits;
-}
-
 static int notify_on_release(const struct cgroup *cgrp)
 {
 	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
@@ -394,12 +384,7 @@
 			;						\
 		else
 
-/* the list of cgroups eligible for automatic release. Protected by
- * release_list_lock */
-static LIST_HEAD(release_list);
-static DEFINE_RAW_SPINLOCK(release_list_lock);
 static void cgroup_release_agent(struct work_struct *work);
-static DECLARE_WORK(release_agent_work, cgroup_release_agent);
 static void check_for_release(struct cgroup *cgrp);
 
 /*
@@ -498,7 +483,7 @@
 	return key;
 }
 
-static void put_css_set_locked(struct css_set *cset, bool taskexit)
+static void put_css_set_locked(struct css_set *cset)
 {
 	struct cgrp_cset_link *link, *tmp_link;
 	struct cgroup_subsys *ss;
@@ -524,11 +509,7 @@
 		/* @cgrp can't go away while we're holding css_set_rwsem */
 		if (list_empty(&cgrp->cset_links)) {
 			cgroup_update_populated(cgrp, false);
-			if (notify_on_release(cgrp)) {
-				if (taskexit)
-					set_bit(CGRP_RELEASABLE, &cgrp->flags);
-				check_for_release(cgrp);
-			}
+			check_for_release(cgrp);
 		}
 
 		kfree(link);
@@ -537,7 +518,7 @@
 	kfree_rcu(cset, rcu_head);
 }
 
-static void put_css_set(struct css_set *cset, bool taskexit)
+static void put_css_set(struct css_set *cset)
 {
 	/*
 	 * Ensure that the refcount doesn't hit zero while any readers
@@ -548,7 +529,7 @@
 		return;
 
 	down_write(&css_set_rwsem);
-	put_css_set_locked(cset, taskexit);
+	put_css_set_locked(cset);
 	up_write(&css_set_rwsem);
 }
 
@@ -969,14 +950,6 @@
  * knows that the cgroup won't be removed, as cgroup_rmdir()
  * needs that mutex.
  *
- * The fork and exit callbacks cgroup_fork() and cgroup_exit(), don't
- * (usually) take cgroup_mutex.  These are the two most performance
- * critical pieces of code here.  The exception occurs on cgroup_exit(),
- * when a task in a notify_on_release cgroup exits.  Then cgroup_mutex
- * is taken, and if the cgroup count is zero, a usermode call made
- * to the release agent with the name of the cgroup (path relative to
- * the root of cgroup file system) as the argument.
- *
  * A cgroup can only be deleted if both its 'count' of using tasks
  * is zero, and its list of 'children' cgroups is empty.  Since all
  * tasks in the system use _some_ cgroup, and since there is always at
@@ -1587,7 +1560,6 @@
 	INIT_LIST_HEAD(&cgrp->self.sibling);
 	INIT_LIST_HEAD(&cgrp->self.children);
 	INIT_LIST_HEAD(&cgrp->cset_links);
-	INIT_LIST_HEAD(&cgrp->release_list);
 	INIT_LIST_HEAD(&cgrp->pidlists);
 	mutex_init(&cgrp->pidlist_mutex);
 	cgrp->self.cgroup = cgrp;
@@ -1597,6 +1569,7 @@
 		INIT_LIST_HEAD(&cgrp->e_csets[ssid]);
 
 	init_waitqueue_head(&cgrp->offline_waitq);
+	INIT_WORK(&cgrp->release_agent_work, cgroup_release_agent);
 }
 
 static void init_cgroup_root(struct cgroup_root *root,
@@ -2052,8 +2025,7 @@
 	 * task. As trading it for new_cset is protected by cgroup_mutex,
 	 * we're safe to drop it here; it will be freed under RCU.
 	 */
-	set_bit(CGRP_RELEASABLE, &old_cgrp->flags);
-	put_css_set_locked(old_cset, false);
+	put_css_set_locked(old_cset);
 }
 
 /**
@@ -2074,7 +2046,7 @@
 		cset->mg_src_cgrp = NULL;
 		cset->mg_dst_cset = NULL;
 		list_del_init(&cset->mg_preload_node);
-		put_css_set_locked(cset, false);
+		put_css_set_locked(cset);
 	}
 	up_write(&css_set_rwsem);
 }
@@ -2168,8 +2140,8 @@
 		if (src_cset == dst_cset) {
 			src_cset->mg_src_cgrp = NULL;
 			list_del_init(&src_cset->mg_preload_node);
-			put_css_set(src_cset, false);
-			put_css_set(dst_cset, false);
+			put_css_set(src_cset);
+			put_css_set(dst_cset);
 			continue;
 		}
 
@@ -2178,7 +2150,7 @@
 		if (list_empty(&dst_cset->mg_preload_node))
 			list_add(&dst_cset->mg_preload_node, &csets);
 		else
-			put_css_set(dst_cset, false);
+			put_css_set(dst_cset);
 	}
 
 	list_splice_tail(&csets, preloaded_csets);
@@ -4173,7 +4145,6 @@
 static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css,
 					  struct cftype *cft, u64 val)
 {
-	clear_bit(CGRP_RELEASABLE, &css->cgroup->flags);
 	if (val)
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags);
 	else
@@ -4351,6 +4322,7 @@
 		/* cgroup free path */
 		atomic_dec(&cgrp->root->nr_cgrps);
 		cgroup_pidlist_destroy_all(cgrp);
+		cancel_work_sync(&cgrp->release_agent_work);
 
 		if (cgroup_parent(cgrp)) {
 			/*
@@ -4813,19 +4785,12 @@
 	for_each_css(css, ssid, cgrp)
 		kill_css(css);
 
-	/* CSS_ONLINE is clear, remove from ->release_list for the last time */
-	raw_spin_lock(&release_list_lock);
-	if (!list_empty(&cgrp->release_list))
-		list_del_init(&cgrp->release_list);
-	raw_spin_unlock(&release_list_lock);
-
 	/*
 	 * Remove @cgrp directory along with the base files.  @cgrp has an
 	 * extra ref on its kn.
 	 */
 	kernfs_remove(cgrp->kn);
 
-	set_bit(CGRP_RELEASABLE, &cgroup_parent(cgrp)->flags);
 	check_for_release(cgroup_parent(cgrp));
 
 	/* put the base reference */
@@ -4842,13 +4807,10 @@
 	cgrp = cgroup_kn_lock_live(kn);
 	if (!cgrp)
 		return 0;
-	cgroup_get(cgrp);	/* for @kn->priv clearing */
 
 	ret = cgroup_destroy_locked(cgrp);
 
 	cgroup_kn_unlock(kn);
-
-	cgroup_put(cgrp);
 	return ret;
 }
 
@@ -5052,12 +5014,9 @@
  *  - Print task's cgroup paths into seq_file, one line for each hierarchy
  *  - Used for /proc/<pid>/cgroup.
  */
-
-/* TODO: Use a proper seq_file iterator */
-int proc_cgroup_show(struct seq_file *m, void *v)
+int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
+		     struct pid *pid, struct task_struct *tsk)
 {
-	struct pid *pid;
-	struct task_struct *tsk;
 	char *buf, *path;
 	int retval;
 	struct cgroup_root *root;
@@ -5067,14 +5026,6 @@
 	if (!buf)
 		goto out;
 
-	retval = -ESRCH;
-	pid = m->private;
-	tsk = get_pid_task(pid, PIDTYPE_PID);
-	if (!tsk)
-		goto out_free;
-
-	retval = 0;
-
 	mutex_lock(&cgroup_mutex);
 	down_read(&css_set_rwsem);
 
@@ -5104,11 +5055,10 @@
 		seq_putc(m, '\n');
 	}
 
+	retval = 0;
 out_unlock:
 	up_read(&css_set_rwsem);
 	mutex_unlock(&cgroup_mutex);
-	put_task_struct(tsk);
-out_free:
 	kfree(buf);
 out:
 	return retval;
@@ -5179,7 +5129,7 @@
 	int i;
 
 	/*
-	 * This may race against cgroup_enable_task_cg_links().  As that
+	 * This may race against cgroup_enable_task_cg_lists().  As that
 	 * function sets use_task_css_set_links before grabbing
 	 * tasklist_lock and we just went through tasklist_lock to add
 	 * @child, it's guaranteed that either we see the set
@@ -5194,7 +5144,7 @@
 	 * when implementing operations which need to migrate all tasks of
 	 * a cgroup to another.
 	 *
-	 * Note that if we lose to cgroup_enable_task_cg_links(), @child
+	 * Note that if we lose to cgroup_enable_task_cg_lists(), @child
 	 * will remain in init_css_set.  This is safe because all tasks are
 	 * in the init_css_set before cg_links is enabled and there's no
 	 * operation which transfers all tasks out of init_css_set.
@@ -5278,30 +5228,14 @@
 	}
 
 	if (put_cset)
-		put_css_set(cset, true);
+		put_css_set(cset);
 }
 
 static void check_for_release(struct cgroup *cgrp)
 {
-	if (cgroup_is_releasable(cgrp) && list_empty(&cgrp->cset_links) &&
-	    !css_has_online_children(&cgrp->self)) {
-		/*
-		 * Control Group is currently removeable. If it's not
-		 * already queued for a userspace notification, queue
-		 * it now
-		 */
-		int need_schedule_work = 0;
-
-		raw_spin_lock(&release_list_lock);
-		if (!cgroup_is_dead(cgrp) &&
-		    list_empty(&cgrp->release_list)) {
-			list_add(&cgrp->release_list, &release_list);
-			need_schedule_work = 1;
-		}
-		raw_spin_unlock(&release_list_lock);
-		if (need_schedule_work)
-			schedule_work(&release_agent_work);
-	}
+	if (notify_on_release(cgrp) && !cgroup_has_tasks(cgrp) &&
+	    !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp))
+		schedule_work(&cgrp->release_agent_work);
 }
 
 /*
@@ -5329,52 +5263,39 @@
  */
 static void cgroup_release_agent(struct work_struct *work)
 {
-	BUG_ON(work != &release_agent_work);
+	struct cgroup *cgrp =
+		container_of(work, struct cgroup, release_agent_work);
+	char *pathbuf = NULL, *agentbuf = NULL, *path;
+	char *argv[3], *envp[3];
+
 	mutex_lock(&cgroup_mutex);
-	raw_spin_lock(&release_list_lock);
-	while (!list_empty(&release_list)) {
-		char *argv[3], *envp[3];
-		int i;
-		char *pathbuf = NULL, *agentbuf = NULL, *path;
-		struct cgroup *cgrp = list_entry(release_list.next,
-						    struct cgroup,
-						    release_list);
-		list_del_init(&cgrp->release_list);
-		raw_spin_unlock(&release_list_lock);
-		pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
-		if (!pathbuf)
-			goto continue_free;
-		path = cgroup_path(cgrp, pathbuf, PATH_MAX);
-		if (!path)
-			goto continue_free;
-		agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
-		if (!agentbuf)
-			goto continue_free;
 
-		i = 0;
-		argv[i++] = agentbuf;
-		argv[i++] = path;
-		argv[i] = NULL;
+	pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
+	agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
+	if (!pathbuf || !agentbuf)
+		goto out;
 
-		i = 0;
-		/* minimal command environment */
-		envp[i++] = "HOME=/";
-		envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
-		envp[i] = NULL;
+	path = cgroup_path(cgrp, pathbuf, PATH_MAX);
+	if (!path)
+		goto out;
 
-		/* Drop the lock while we invoke the usermode helper,
-		 * since the exec could involve hitting disk and hence
-		 * be a slow process */
-		mutex_unlock(&cgroup_mutex);
-		call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
-		mutex_lock(&cgroup_mutex);
- continue_free:
-		kfree(pathbuf);
-		kfree(agentbuf);
-		raw_spin_lock(&release_list_lock);
-	}
-	raw_spin_unlock(&release_list_lock);
+	argv[0] = agentbuf;
+	argv[1] = path;
+	argv[2] = NULL;
+
+	/* minimal command environment */
+	envp[0] = "HOME=/";
+	envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
+	envp[2] = NULL;
+
 	mutex_unlock(&cgroup_mutex);
+	call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
+	goto out_free;
+out:
+	mutex_unlock(&cgroup_mutex);
+out_free:
+	kfree(agentbuf);
+	kfree(pathbuf);
 }
 
 static int __init cgroup_disable(char *str)
@@ -5562,7 +5483,8 @@
 
 static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft)
 {
-	return test_bit(CGRP_RELEASABLE, &css->cgroup->flags);
+	return (!cgroup_has_tasks(css->cgroup) &&
+		!css_has_online_children(&css->cgroup->self));
 }
 
 static struct cftype debug_files[] =  {
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 52cb04c..1f107c7 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2730,10 +2730,9 @@
  *    and we take cpuset_mutex, keeping cpuset_attach() from changing it
  *    anyway.
  */
-int proc_cpuset_show(struct seq_file *m, void *unused_v)
+int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
+		     struct pid *pid, struct task_struct *tsk)
 {
-	struct pid *pid;
-	struct task_struct *tsk;
 	char *buf, *p;
 	struct cgroup_subsys_state *css;
 	int retval;
@@ -2743,24 +2742,16 @@
 	if (!buf)
 		goto out;
 
-	retval = -ESRCH;
-	pid = m->private;
-	tsk = get_pid_task(pid, PIDTYPE_PID);
-	if (!tsk)
-		goto out_free;
-
 	retval = -ENAMETOOLONG;
 	rcu_read_lock();
 	css = task_css(tsk, cpuset_cgrp_id);
 	p = cgroup_path(css->cgroup, buf, PATH_MAX);
 	rcu_read_unlock();
 	if (!p)
-		goto out_put_task;
+		goto out_free;
 	seq_puts(m, p);
 	seq_putc(m, '\n');
 	retval = 0;
-out_put_task:
-	put_task_struct(tsk);
 out_free:
 	kfree(buf);
 out:
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 963bf13..b1c6635 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -392,14 +392,9 @@
 				    event->cgrp->css.cgroup);
 }
 
-static inline void perf_put_cgroup(struct perf_event *event)
-{
-	css_put(&event->cgrp->css);
-}
-
 static inline void perf_detach_cgroup(struct perf_event *event)
 {
-	perf_put_cgroup(event);
+	css_put(&event->cgrp->css);
 	event->cgrp = NULL;
 }
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 44c6bd2..8639f6b 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -148,7 +148,7 @@
 	ino = cgroup_ino(css->cgroup);
 	css_put(css);
 
-	if (!ino || ino != hwpoison_filter_memcg)
+	if (ino != hwpoison_filter_memcg)
 		return -EINVAL;
 
 	return 0;