cgroup fixes for v6.0-rc2

Contains fixes for the following issues:
 
 * psi data structure was changed to be allocated dynamically but it wasn't
   being cleared leading to reporting garbage values and triggering spurious
   oom kills.
 
 * A deadlock involving cpuset and cpu hotplug.
 
 * When a controller is moved across cgroup hierarchies, css->rstat_css_node
   didn't get RCU drained properly from the previous list.
 -----BEGIN PGP SIGNATURE-----
 
 iIQEABYIACwWIQTfIjM1kS57o3GsC/uxYfJx3gVYGQUCYwVmRg4cdGpAa2VybmVs
 Lm9yZwAKCRCxYfJx3gVYGb/eAP44dr9/OQtapKm63H/qmLF39LWE6nC99RYHECl5
 ncuZvwD/XIkZt212nr/qC1C0ggB5qCGG7tIZG6tIgkS+J5huqg4=
 =CC/Y
 -----END PGP SIGNATURE-----

Merge tag 'cgroup-for-6.0-rc2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:

 - The psi data structure was changed to be allocated dynamically but
   it wasn't being cleared leading to it reporting garbage values and
   triggering spurious oom kills.

 - A deadlock involving cpuset and cpu hotplug.

 - When a controller is moved across cgroup hierarchies,
   css->rstat_css_node didn't get RCU drained properly from the previous
   list.

* tag 'cgroup-for-6.0-rc2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: Fix race condition at rebind_subsystems()
  cgroup: Fix threadgroup_rwsem <-> cpus_read_lock() deadlock
  sched/psi: Remove redundant cgroup_psi() when !CONFIG_CGROUPS
  sched/psi: Remove unused parameter nbytes of psi_trigger_create()
  sched/psi: Zero the memory of struct psi_group

include/linux/cgroup.h

@@ -734,11 +734,6 @@ static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
 	return NULL;
 }
 
-static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
-{
-	return NULL;
-}
-
 static inline bool cgroup_psi_enabled(void)
 {
 	return false;

include/linux/psi.h

@@ -27,7 +27,7 @@ void psi_memstall_leave(unsigned long *flags);
 
 int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res);
 struct psi_trigger *psi_trigger_create(struct psi_group *group,
-			char *buf, size_t nbytes, enum psi_res res);
+			char *buf, enum psi_res res);
 void psi_trigger_destroy(struct psi_trigger *t);
 
 __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,

kernel/cgroup/cgroup.c

@@ -1820,6 +1820,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 
 		if (ss->css_rstat_flush) {
 			list_del_rcu(&css->rstat_css_node);
+			synchronize_rcu();
 			list_add_rcu(&css->rstat_css_node,
 				     &dcgrp->rstat_css_list);
 		}
@@ -2369,6 +2370,47 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 }
 EXPORT_SYMBOL_GPL(task_cgroup_path);
 
+/**
+ * cgroup_attach_lock - Lock for ->attach()
+ * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem
+ *
+ * cgroup migration sometimes needs to stabilize threadgroups against forks and
+ * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach()
+ * implementations (e.g. cpuset), also need to disable CPU hotplug.
+ * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can
+ * lead to deadlocks.
+ *
+ * Bringing up a CPU may involve creating and destroying tasks which requires
+ * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside
+ * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while
+ * write-locking threadgroup_rwsem, the locking order is reversed and we end up
+ * waiting for an on-going CPU hotplug operation which in turn is waiting for
+ * the threadgroup_rwsem to be released to create new tasks. For more details:
+ *
+ *   http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu
+ *
+ * Resolve the situation by always acquiring cpus_read_lock() before optionally
+ * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that
+ * CPU hotplug is disabled on entry.
+ */
+static void cgroup_attach_lock(bool lock_threadgroup)
+{
+	cpus_read_lock();
+	if (lock_threadgroup)
+		percpu_down_write(&cgroup_threadgroup_rwsem);
+}
+
+/**
+ * cgroup_attach_unlock - Undo cgroup_attach_lock()
+ * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem
+ */
+static void cgroup_attach_unlock(bool lock_threadgroup)
+{
+	if (lock_threadgroup)
+		percpu_up_write(&cgroup_threadgroup_rwsem);
+	cpus_read_unlock();
+}
+
 /**
  * cgroup_migrate_add_task - add a migration target task to a migration context
  * @task: target task
@@ -2841,8 +2883,7 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
 }
 
 struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
-					     bool *locked)
-	__acquires(&cgroup_threadgroup_rwsem)
+					     bool *threadgroup_locked)
 {
 	struct task_struct *tsk;
 	pid_t pid;
@@ -2859,12 +2900,8 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
 	 * Therefore, we can skip the global lock.
 	 */
 	lockdep_assert_held(&cgroup_mutex);
-	if (pid || threadgroup) {
-		percpu_down_write(&cgroup_threadgroup_rwsem);
-		*locked = true;
-	} else {
-		*locked = false;
-	}
+	*threadgroup_locked = pid || threadgroup;
+	cgroup_attach_lock(*threadgroup_locked);
 
 	rcu_read_lock();
 	if (pid) {
@@ -2895,17 +2932,14 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
 	goto out_unlock_rcu;
 
 out_unlock_threadgroup:
-	if (*locked) {
-		percpu_up_write(&cgroup_threadgroup_rwsem);
-		*locked = false;
-	}
+	cgroup_attach_unlock(*threadgroup_locked);
+	*threadgroup_locked = false;
 out_unlock_rcu:
 	rcu_read_unlock();
 	return tsk;
 }
 
-void cgroup_procs_write_finish(struct task_struct *task, bool locked)
-	__releases(&cgroup_threadgroup_rwsem)
+void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked)
 {
 	struct cgroup_subsys *ss;
 	int ssid;
@@ -2913,8 +2947,8 @@ void cgroup_procs_write_finish(struct task_struct *task, bool locked)
 	/* release reference from cgroup_procs_write_start() */
 	put_task_struct(task);
 
-	if (locked)
-		percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock(threadgroup_locked);
+
 	for_each_subsys(ss, ssid)
 		if (ss->post_attach)
 			ss->post_attach();
@@ -3000,8 +3034,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	 * write-locking can be skipped safely.
 	 */
 	has_tasks = !list_empty(&mgctx.preloaded_src_csets);
-	if (has_tasks)
-		percpu_down_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_lock(has_tasks);
 
 	/* NULL dst indicates self on default hierarchy */
 	ret = cgroup_migrate_prepare_dst(&mgctx);
@@ -3022,8 +3055,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	ret = cgroup_migrate_execute(&mgctx);
 out_finish:
 	cgroup_migrate_finish(&mgctx);
-	if (has_tasks)
-		percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock(has_tasks);
 	return ret;
 }
 
@@ -3698,7 +3730,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
 	}
 
 	psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
-	new = psi_trigger_create(psi, buf, nbytes, res);
+	new = psi_trigger_create(psi, buf, res);
 	if (IS_ERR(new)) {
 		cgroup_put(cgrp);
 		return PTR_ERR(new);
@@ -4971,13 +5003,13 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	struct task_struct *task;
 	const struct cred *saved_cred;
 	ssize_t ret;
-	bool locked;
+	bool threadgroup_locked;
 
 	dst_cgrp = cgroup_kn_lock_live(of->kn, false);
 	if (!dst_cgrp)
 		return -ENODEV;
 
-	task = cgroup_procs_write_start(buf, threadgroup, &locked);
+	task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked);
 	ret = PTR_ERR_OR_ZERO(task);
 	if (ret)
 		goto out_unlock;
@@ -5003,7 +5035,7 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	ret = cgroup_attach_task(dst_cgrp, task, threadgroup);
 
 out_finish:
-	cgroup_procs_write_finish(task, locked);
+	cgroup_procs_write_finish(task, threadgroup_locked);
 out_unlock:
 	cgroup_kn_unlock(of->kn);
 

kernel/cgroup/cpuset.c

@@ -2289,7 +2289,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 	cgroup_taskset_first(tset, &css);
 	cs = css_cs(css);
 
-	cpus_read_lock();
+	lockdep_assert_cpus_held();	/* see cgroup_attach_lock() */
 	percpu_down_write(&cpuset_rwsem);
 
 	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
@@ -2343,7 +2343,6 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 		wake_up(&cpuset_attach_wq);
 
 	percpu_up_write(&cpuset_rwsem);
-	cpus_read_unlock();
 }
 
 /* The various types of files and directories in a cpuset file system */

kernel/sched/psi.c

@@ -190,12 +190,8 @@ static void group_init(struct psi_group *group)
 	/* Init trigger-related members */
 	mutex_init(&group->trigger_lock);
 	INIT_LIST_HEAD(&group->triggers);
-	memset(group->nr_triggers, 0, sizeof(group->nr_triggers));
-	group->poll_states = 0;
 	group->poll_min_period = U32_MAX;
-	memset(group->polling_total, 0, sizeof(group->polling_total));
 	group->polling_next_update = ULLONG_MAX;
-	group->polling_until = 0;
 	init_waitqueue_head(&group->poll_wait);
 	timer_setup(&group->poll_timer, poll_timer_fn, 0);
 	rcu_assign_pointer(group->poll_task, NULL);
@@ -957,7 +953,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup)
 	if (static_branch_likely(&psi_disabled))
 		return 0;
 
-	cgroup->psi = kmalloc(sizeof(struct psi_group), GFP_KERNEL);
+	cgroup->psi = kzalloc(sizeof(struct psi_group), GFP_KERNEL);
 	if (!cgroup->psi)
 		return -ENOMEM;
 
@@ -1091,7 +1087,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
 }
 
 struct psi_trigger *psi_trigger_create(struct psi_group *group,
-			char *buf, size_t nbytes, enum psi_res res)
+			char *buf, enum psi_res res)
 {
 	struct psi_trigger *t;
 	enum psi_states state;
@@ -1320,7 +1316,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
 		return -EBUSY;
 	}
 
-	new = psi_trigger_create(&psi_system, buf, nbytes, res);
+	new = psi_trigger_create(&psi_system, buf, res);
 	if (IS_ERR(new)) {
 		mutex_unlock(&seq->lock);
 		return PTR_ERR(new);