1 files changed, 268 insertions, 121 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index a66c088c851c..a723b7dc6e4e 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -90,11 +90,14 @@
 DEFINE_MUTEX(cgroup_mutex);
 DEFINE_SPINLOCK(css_set_lock);
 
-#ifdef CONFIG_PROVE_RCU
+#if (defined CONFIG_PROVE_RCU || defined CONFIG_LOCKDEP)
 EXPORT_SYMBOL_GPL(cgroup_mutex);
 EXPORT_SYMBOL_GPL(css_set_lock);
 #endif
 
+struct blocking_notifier_head cgroup_lifetime_notifier =
+	BLOCKING_NOTIFIER_INIT(cgroup_lifetime_notifier);
+
 DEFINE_SPINLOCK(trace_cgroup_path_lock);
 char trace_cgroup_path[TRACE_CGROUP_PATH_LEN];
 static bool cgroup_debug __read_mostly;
@@ -161,17 +164,21 @@ static struct static_key_true *cgroup_subsys_on_dfl_key[] = {
 };
 #undef SUBSYS
 
-static DEFINE_PER_CPU(struct cgroup_rstat_cpu, cgrp_dfl_root_rstat_cpu);
+static DEFINE_PER_CPU(struct css_rstat_cpu, root_rstat_cpu);
+static DEFINE_PER_CPU(struct cgroup_rstat_base_cpu, root_rstat_base_cpu);
 
 /* the default hierarchy */
-struct cgroup_root cgrp_dfl_root = { .cgrp.rstat_cpu = &cgrp_dfl_root_rstat_cpu };
+struct cgroup_root cgrp_dfl_root = {
+	.cgrp.self.rstat_cpu = &root_rstat_cpu,
+	.cgrp.rstat_base_cpu = &root_rstat_base_cpu,
+};
 EXPORT_SYMBOL_GPL(cgrp_dfl_root);
 
 /*
  * The default hierarchy always exists but is hidden until mounted for the
  * first time.  This is for backward compatibility.
  */
-static bool cgrp_dfl_visible;
+bool cgrp_dfl_visible;
 
 /* some controllers are not supported in the default hierarchy */
 static u16 cgrp_dfl_inhibit_ss_mask;
@@ -633,9 +640,22 @@ int cgroup_task_count(const struct cgroup *cgrp)
 	return count;
 }
 
+static struct cgroup *kn_priv(struct kernfs_node *kn)
+{
+	struct kernfs_node *parent;
+	/*
+	 * The parent can not be replaced due to KERNFS_ROOT_INVARIANT_PARENT.
+	 * Therefore it is always safe to dereference this pointer outside of a
+	 * RCU section.
+	 */
+	parent = rcu_dereference_check(kn->__parent,
+				       kernfs_root_flags(kn) & KERNFS_ROOT_INVARIANT_PARENT);
+	return parent->priv;
+}
+
 struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
 {
-	struct cgroup *cgrp = of->kn->parent->priv;
+	struct cgroup *cgrp = kn_priv(of->kn);
 	struct cftype *cft = of_cft(of);
 
 	/*
@@ -1322,6 +1342,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 {
 	struct cgroup *cgrp = &root->cgrp;
 	struct cgrp_cset_link *link, *tmp_link;
+	int ret;
 
 	trace_cgroup_destroy_root(root);
 
@@ -1330,6 +1351,10 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 	BUG_ON(atomic_read(&root->nr_cgrps));
 	BUG_ON(!list_empty(&cgrp->self.children));
 
+	ret = blocking_notifier_call_chain(&cgroup_lifetime_notifier,
+					   CGROUP_LIFETIME_OFFLINE, cgrp);
+	WARN_ON_ONCE(notifier_to_errno(ret));
+
 	/* Rebind all subsystems back to the default hierarchy */
 	WARN_ON(rebind_subsystems(&cgrp_dfl_root, root->subsys_mask));
 
@@ -1358,7 +1383,6 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 
 	cgroup_unlock();
 
-	cgroup_rstat_exit(cgrp);
 	kernfs_destroy_root(root->kf_root);
 	cgroup_free_root(root);
 }
@@ -1612,7 +1636,7 @@ void cgroup_kn_unlock(struct kernfs_node *kn)
 	if (kernfs_type(kn) == KERNFS_DIR)
 		cgrp = kn->priv;
 	else
-		cgrp = kn->parent->priv;
+		cgrp = kn_priv(kn);
 
 	cgroup_unlock();
 
@@ -1644,7 +1668,7 @@ struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline)
 	if (kernfs_type(kn) == KERNFS_DIR)
 		cgrp = kn->priv;
 	else
-		cgrp = kn->parent->priv;
+		cgrp = kn_priv(kn);
 
 	/*
 	 * We're gonna grab cgroup_mutex which nests outside kernfs
@@ -1682,7 +1706,7 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
 		cfile->kn = NULL;
 		spin_unlock_irq(&cgroup_file_kn_lock);
 
-		del_timer_sync(&cfile->notify_timer);
+		timer_delete_sync(&cfile->notify_timer);
 	}
 
 	kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
@@ -1702,7 +1726,7 @@ static void css_clear_dir(struct cgroup_subsys_state *css)
 
 	css->flags &= ~CSS_VISIBLE;
 
-	if (!css->ss) {
+	if (css_is_self(css)) {
 		if (cgroup_on_dfl(cgrp)) {
 			cgroup_addrm_files(css, cgrp,
 					   cgroup_base_files, false);
@@ -1734,7 +1758,7 @@ static int css_populate_dir(struct cgroup_subsys_state *css)
 	if (css->flags & CSS_VISIBLE)
 		return 0;
 
-	if (!css->ss) {
+	if (css_is_self(css)) {
 		if (cgroup_on_dfl(cgrp)) {
 			ret = cgroup_addrm_files(css, cgrp,
 						 cgroup_base_files, true);
@@ -1744,8 +1768,11 @@ static int css_populate_dir(struct cgroup_subsys_state *css)
 			if (cgroup_psi_enabled()) {
 				ret = cgroup_addrm_files(css, cgrp,
 							 cgroup_psi_files, true);
-				if (ret < 0)
+				if (ret < 0) {
+					cgroup_addrm_files(css, cgrp,
+							   cgroup_base_files, false);
 					return ret;
+				}
 			}
 		} else {
 			ret = cgroup_addrm_files(css, cgrp,
@@ -1839,9 +1866,9 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 		RCU_INIT_POINTER(scgrp->subsys[ssid], NULL);
 		rcu_assign_pointer(dcgrp->subsys[ssid], css);
 		ss->root = dst_root;
-		css->cgroup = dcgrp;
 
 		spin_lock_irq(&css_set_lock);
+		css->cgroup = dcgrp;
 		WARN_ON(!list_empty(&dcgrp->e_csets[ss->id]));
 		list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id],
 					 e_cset_node[ss->id]) {
@@ -1860,13 +1887,6 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 		}
 		spin_unlock_irq(&css_set_lock);
 
-		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);
-		}
-
 		/* default hierarchy doesn't enable controllers by default */
 		dst_root->subsys_mask |= 1 << ssid;
 		if (dst_root == &cgrp_dfl_root) {
@@ -1922,6 +1942,7 @@ enum cgroup2_param {
 	Opt_memory_localevents,
 	Opt_memory_recursiveprot,
 	Opt_memory_hugetlb_accounting,
+	Opt_pids_localevents,
 	nr__cgroup2_params
 };
 
@@ -1931,6 +1952,7 @@ static const struct fs_parameter_spec cgroup2_fs_parameters[] = {
 	fsparam_flag("memory_localevents",	Opt_memory_localevents),
 	fsparam_flag("memory_recursiveprot",	Opt_memory_recursiveprot),
 	fsparam_flag("memory_hugetlb_accounting", Opt_memory_hugetlb_accounting),
+	fsparam_flag("pids_localevents",	Opt_pids_localevents),
 	{}
 };
 
@@ -1960,10 +1982,20 @@ static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param
 	case Opt_memory_hugetlb_accounting:
 		ctx->flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
 		return 0;
+	case Opt_pids_localevents:
+		ctx->flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS;
+		return 0;
 	}
 	return -EINVAL;
 }
 
+struct cgroup_of_peak *of_peak(struct kernfs_open_file *of)
+{
+	struct cgroup_file_ctx *ctx = of->priv;
+
+	return &ctx->peak;
+}
+
 static void apply_cgroup_root_flags(unsigned int root_flags)
 {
 	if (current->nsproxy->cgroup_ns == &init_cgroup_ns) {
@@ -1989,6 +2021,11 @@ static void apply_cgroup_root_flags(unsigned int root_flags)
 			cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
 		else
 			cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
+
+		if (root_flags & CGRP_ROOT_PIDS_LOCAL_EVENTS)
+			cgrp_dfl_root.flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS;
+		else
+			cgrp_dfl_root.flags &= ~CGRP_ROOT_PIDS_LOCAL_EVENTS;
 	}
 }
 
@@ -2004,6 +2041,8 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root
 		seq_puts(seq, ",memory_recursiveprot");
 	if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING)
 		seq_puts(seq, ",memory_hugetlb_accounting");
+	if (cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS)
+		seq_puts(seq, ",pids_localevents");
 	return 0;
 }
 
@@ -2030,7 +2069,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	cgrp->dom_cgrp = cgrp;
 	cgrp->max_descendants = INT_MAX;
 	cgrp->max_depth = INT_MAX;
-	INIT_LIST_HEAD(&cgrp->rstat_css_list);
 	prev_cputime_init(&cgrp->prev_cputime);
 
 	for_each_subsys(ss, ssid)
@@ -2096,7 +2134,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	root->kf_root = kernfs_create_root(kf_sops,
 					   KERNFS_ROOT_CREATE_DEACTIVATED |
 					   KERNFS_ROOT_SUPPORT_EXPORTOP |
-					   KERNFS_ROOT_SUPPORT_USER_XATTR,
+					   KERNFS_ROOT_SUPPORT_USER_XATTR |
+					   KERNFS_ROOT_INVARIANT_PARENT,
 					   root_cgrp);
 	if (IS_ERR(root->kf_root)) {
 		ret = PTR_ERR(root->kf_root);
@@ -2110,7 +2149,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	if (ret)
 		goto destroy_root;
 
-	ret = cgroup_rstat_init(root_cgrp);
+	ret = css_rstat_init(&root_cgrp->self);
 	if (ret)
 		goto destroy_root;
 
@@ -2118,8 +2157,9 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	if (ret)
 		goto exit_stats;
 
-	ret = cgroup_bpf_inherit(root_cgrp);
-	WARN_ON_ONCE(ret);
+	ret = blocking_notifier_call_chain(&cgroup_lifetime_notifier,
+					   CGROUP_LIFETIME_ONLINE, root_cgrp);
+	WARN_ON_ONCE(notifier_to_errno(ret));
 
 	trace_cgroup_setup_root(root);
 
@@ -2150,7 +2190,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	goto out;
 
 exit_stats:
-	cgroup_rstat_exit(root_cgrp);
+	css_rstat_exit(&root_cgrp->self);
 destroy_root:
 	kernfs_destroy_root(root->kf_root);
 	root->kf_root = NULL;
@@ -2292,10 +2332,8 @@ static void cgroup_kill_sb(struct super_block *sb)
 	 * And don't kill the default root.
 	 */
 	if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root &&
-	    !percpu_ref_is_dying(&root->cgrp.self.refcnt)) {
-		cgroup_bpf_offline(&root->cgrp);
+	    !percpu_ref_is_dying(&root->cgrp.self.refcnt))
 		percpu_ref_kill(&root->cgrp.self.refcnt);
-	}
 	cgroup_put(&root->cgrp);
 	kernfs_kill_sb(sb);
 }
@@ -2316,10 +2354,38 @@ static struct file_system_type cgroup2_fs_type = {
 	.fs_flags		= FS_USERNS_MOUNT,
 };
 
-#ifdef CONFIG_CPUSETS
+#ifdef CONFIG_CPUSETS_V1
+enum cpuset_param {
+	Opt_cpuset_v2_mode,
+};
+
+static const struct fs_parameter_spec cpuset_fs_parameters[] = {
+	fsparam_flag  ("cpuset_v2_mode", Opt_cpuset_v2_mode),
+	{}
+};
+
+static int cpuset_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, cpuset_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_cpuset_v2_mode:
+		ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE;
+		return 0;
+	}
+	return -EINVAL;
+}
+
 static const struct fs_context_operations cpuset_fs_context_ops = {
 	.get_tree	= cgroup1_get_tree,
 	.free		= cgroup_fs_context_free,
+	.parse_param	= cpuset_parse_param,
 };
 
 /*
@@ -2356,6 +2422,7 @@ static int cpuset_init_fs_context(struct fs_context *fc)
 static struct file_system_type cpuset_fs_type = {
 	.name			= "cpuset",
 	.init_fs_context	= cpuset_init_fs_context,
+	.parameters		= cpuset_fs_parameters,
 	.fs_flags		= FS_USERNS_MOUNT,
 };
 #endif
@@ -3654,12 +3721,40 @@ static int cgroup_events_show(struct seq_file *seq, void *v)
 static int cgroup_stat_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgroup = seq_css(seq)->cgroup;
+	struct cgroup_subsys_state *css;
+	int dying_cnt[CGROUP_SUBSYS_COUNT];
+	int ssid;
 
 	seq_printf(seq, "nr_descendants %d\n",
 		   cgroup->nr_descendants);
+
+	/*
+	 * Show the number of live and dying csses associated with each of
+	 * non-inhibited cgroup subsystems that is bound to cgroup v2.
+	 *
+	 * Without proper lock protection, racing is possible. So the
+	 * numbers may not be consistent when that happens.
+	 */
+	rcu_read_lock();
+	for (ssid = 0; ssid < CGROUP_SUBSYS_COUNT; ssid++) {
+		dying_cnt[ssid] = -1;
+		if ((BIT(ssid) & cgrp_dfl_inhibit_ss_mask) ||
+		    (cgroup_subsys[ssid]->root !=  &cgrp_dfl_root))
+			continue;
+		css = rcu_dereference_raw(cgroup->subsys[ssid]);
+		dying_cnt[ssid] = cgroup->nr_dying_subsys[ssid];
+		seq_printf(seq, "nr_subsys_%s %d\n", cgroup_subsys[ssid]->name,
+			   css ? (css->nr_descendants + 1) : 0);
+	}
+
 	seq_printf(seq, "nr_dying_descendants %d\n",
 		   cgroup->nr_dying_descendants);
-
+	for (ssid = 0; ssid < CGROUP_SUBSYS_COUNT; ssid++) {
+		if (dying_cnt[ssid] >= 0)
+			seq_printf(seq, "nr_dying_subsys_%s %d\n",
+				   cgroup_subsys[ssid]->name, dying_cnt[ssid]);
+	}
+	rcu_read_unlock();
 	return 0;
 }
 
@@ -3963,7 +4058,7 @@ static void __cgroup_kill(struct cgroup *cgrp)
 	lockdep_assert_held(&cgroup_mutex);
 
 	spin_lock_irq(&css_set_lock);
-	set_bit(CGRP_KILL, &cgrp->flags);
+	cgrp->kill_seq++;
 	spin_unlock_irq(&css_set_lock);
 
 	css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED, &it);
@@ -3979,10 +4074,6 @@ static void __cgroup_kill(struct cgroup *cgrp)
 		send_sig(SIGKILL, task, 0);
 	}
 	css_task_iter_end(&it);
-
-	spin_lock_irq(&css_set_lock);
-	clear_bit(CGRP_KILL, &cgrp->flags);
-	spin_unlock_irq(&css_set_lock);
 }
 
 static void cgroup_kill(struct cgroup *cgrp)
@@ -4069,7 +4160,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 				 size_t nbytes, loff_t off)
 {
 	struct cgroup_file_ctx *ctx = of->priv;
-	struct cgroup *cgrp = of->kn->parent->priv;
+	struct cgroup *cgrp = kn_priv(of->kn);
 	struct cftype *cft = of_cft(of);
 	struct cgroup_subsys_state *css;
 	int ret;
@@ -4081,7 +4172,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 	 * If namespaces are delegation boundaries, disallow writes to
 	 * files in an non-init namespace root from inside the namespace
 	 * except for the files explicitly marked delegatable -
-	 * cgroup.procs and cgroup.subtree_control.
+	 * eg. cgroup.procs, cgroup.threads and cgroup.subtree_control.
 	 */
 	if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) &&
 	    !(cft->flags & CFTYPE_NS_DELEGATABLE) &&
@@ -4401,7 +4492,7 @@ int cgroup_rm_cftypes(struct cftype *cfts)
  * function currently returns 0 as long as @cfts registration is successful
  * even if some file creation attempts on existing cgroups fail.
  */
-static int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
+int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 {
 	int ret;
 
@@ -4580,8 +4671,9 @@ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos,
  *
  * While this function requires cgroup_mutex or RCU read locking, it
  * doesn't require the whole traversal to be contained in a single critical
- * section.  This function will return the correct next descendant as long
- * as both @pos and @root are accessible and @pos is a descendant of @root.
+ * section. Additionally, it isn't necessary to hold onto a reference to @pos.
+ * This function will return the correct next descendant as long as both @pos
+ * and @root are accessible and @pos is a descendant of @root.
  *
  * If a subsystem synchronizes ->css_online() and the start of iteration, a
  * css which finished ->css_online() is guaranteed to be visible in the
@@ -4629,8 +4721,9 @@ EXPORT_SYMBOL_GPL(css_next_descendant_pre);
  *
  * While this function requires cgroup_mutex or RCU read locking, it
  * doesn't require the whole traversal to be contained in a single critical
- * section.  This function will return the correct rightmost descendant as
- * long as @pos is accessible.
+ * section. Additionally, it isn't necessary to hold onto a reference to @pos.
+ * This function will return the correct rightmost descendant as long as @pos
+ * is accessible.
  */
 struct cgroup_subsys_state *
 css_rightmost_descendant(struct cgroup_subsys_state *pos)
@@ -4674,9 +4767,9 @@ css_leftmost_descendant(struct cgroup_subsys_state *pos)
  *
  * While this function requires cgroup_mutex or RCU read locking, it
  * doesn't require the whole traversal to be contained in a single critical
- * section.  This function will return the correct next descendant as long
- * as both @pos and @cgroup are accessible and @pos is a descendant of
- * @cgroup.
+ * section. Additionally, it isn't necessary to hold onto a reference to @pos.
+ * This function will return the correct next descendant as long as both @pos
+ * and @cgroup are accessible and @pos is a descendant of @cgroup.
  *
  * If a subsystem synchronizes ->css_online() and the start of iteration, a
  * css which finished ->css_online() is guaranteed to be visible in the
@@ -5353,8 +5446,9 @@ static void css_free_rwork_fn(struct work_struct *work)
 	struct cgroup *cgrp = css->cgroup;
 
 	percpu_ref_exit(&css->refcnt);
+	css_rstat_exit(css);
 
-	if (ss) {
+	if (!css_is_self(css)) {
 		/* css free path */
 		struct cgroup_subsys_state *parent = css->parent;
 		int id = css->id;
@@ -5368,7 +5462,8 @@ static void css_free_rwork_fn(struct work_struct *work)
 	} else {
 		/* cgroup free path */
 		atomic_dec(&cgrp->root->nr_cgrps);
-		cgroup1_pidlist_destroy_all(cgrp);
+		if (!cgroup_on_dfl(cgrp))
+			cgroup1_pidlist_destroy_all(cgrp);
 		cancel_work_sync(&cgrp->release_agent_work);
 		bpf_cgrp_storage_free(cgrp);
 
@@ -5382,7 +5477,6 @@ static void css_free_rwork_fn(struct work_struct *work)
 			cgroup_put(cgroup_parent(cgrp));
 			kernfs_put(cgrp->kn);
 			psi_cgroup_free(cgrp);
-			cgroup_rstat_exit(cgrp);
 			kfree(cgrp);
 		} else {
 			/*
@@ -5407,23 +5501,36 @@ static void css_release_work_fn(struct work_struct *work)
 	css->flags |= CSS_RELEASED;
 	list_del_rcu(&css->sibling);
 
-	if (ss) {
-		/* css release path */
-		if (!list_empty(&css->rstat_css_node)) {
-			cgroup_rstat_flush(cgrp);
-			list_del_rcu(&css->rstat_css_node);
-		}
+	if (!css_is_self(css)) {
+		struct cgroup *parent_cgrp;
+
+		css_rstat_flush(css);
 
 		cgroup_idr_replace(&ss->css_idr, NULL, css->id);
 		if (ss->css_released)
 			ss->css_released(css);
+
+		cgrp->nr_dying_subsys[ss->id]--;
+		/*
+		 * When a css is released and ready to be freed, its
+		 * nr_descendants must be zero. However, the corresponding
+		 * cgrp->nr_dying_subsys[ss->id] may not be 0 if a subsystem
+		 * is activated and deactivated multiple times with one or
+		 * more of its previous activation leaving behind dying csses.
+		 */
+		WARN_ON_ONCE(css->nr_descendants);
+		parent_cgrp = cgroup_parent(cgrp);
+		while (parent_cgrp) {
+			parent_cgrp->nr_dying_subsys[ss->id]--;
+			parent_cgrp = cgroup_parent(parent_cgrp);
+		}
 	} else {
 		struct cgroup *tcgrp;
 
 		/* cgroup release path */
 		TRACE_CGROUP_PATH(release, cgrp);
 
-		cgroup_rstat_flush(cgrp);
+		css_rstat_flush(&cgrp->self);
 
 		spin_lock_irq(&css_set_lock);
 		for (tcgrp = cgroup_parent(cgrp); tcgrp;
@@ -5471,7 +5578,6 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 	css->id = -1;
 	INIT_LIST_HEAD(&css->sibling);
 	INIT_LIST_HEAD(&css->children);
-	INIT_LIST_HEAD(&css->rstat_css_node);
 	css->serial_nr = css_serial_nr_next++;
 	atomic_set(&css->online_cnt, 0);
 
@@ -5480,9 +5586,6 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 		css_get(css->parent);
 	}
 
-	if (ss->css_rstat_flush)
-		list_add_rcu(&css->rstat_css_node, &cgrp->rstat_css_list);
-
 	BUG_ON(cgroup_css(cgrp, ss));
 }
 
@@ -5501,8 +5604,11 @@ static int online_css(struct cgroup_subsys_state *css)
 		rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
 
 		atomic_inc(&css->online_cnt);
-		if (css->parent)
+		if (css->parent) {
 			atomic_inc(&css->parent->online_cnt);
+			while ((css = css->parent))
+				css->nr_descendants++;
+		}
 	}
 	return ret;
 }
@@ -5524,6 +5630,16 @@ static void offline_css(struct cgroup_subsys_state *css)
 	RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL);
 
 	wake_up_all(&css->cgroup->offline_waitq);
+
+	css->cgroup->nr_dying_subsys[ss->id]++;
+	/*
+	 * Parent css and cgroup cannot be freed until after the freeing
+	 * of child css, see css_free_rwork_fn().
+	 */
+	while ((css = css->parent)) {
+		css->nr_descendants--;
+		css->cgroup->nr_dying_subsys[ss->id]++;
+	}
 }
 
 /**
@@ -5562,6 +5678,10 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 		goto err_free_css;
 	css->id = err;
 
+	err = css_rstat_init(css);
+	if (err)
+		goto err_free_css;
+
 	/* @css is ready to be brought online now, make it visible */
 	list_add_tail_rcu(&css->sibling, &parent_css->children);
 	cgroup_idr_replace(&ss->css_idr, css, css->id);
@@ -5575,7 +5695,6 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 err_list_del:
 	list_del_rcu(&css->sibling);
 err_free_css:
-	list_del_rcu(&css->rstat_css_node);
 	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
 	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
 	return ERR_PTR(err);
@@ -5591,7 +5710,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 	struct cgroup_root *root = parent->root;
 	struct cgroup *cgrp, *tcgrp;
 	struct kernfs_node *kn;
-	int level = parent->level + 1;
+	int i, level = parent->level + 1;
 	int ret;
 
 	/* allocate the cgroup and its ID, 0 is reserved for the root */
@@ -5603,17 +5722,13 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 	if (ret)
 		goto out_free_cgrp;
 
-	ret = cgroup_rstat_init(cgrp);
-	if (ret)
-		goto out_cancel_ref;
-
 	/* create the directory */
 	kn = kernfs_create_dir_ns(parent->kn, name, mode,
 				  current_fsuid(), current_fsgid(),
 				  cgrp, NULL);
 	if (IS_ERR(kn)) {
 		ret = PTR_ERR(kn);
-		goto out_stat_exit;
+		goto out_cancel_ref;
 	}
 	cgrp->kn = kn;
 
@@ -5623,13 +5738,20 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 	cgrp->root = root;
 	cgrp->level = level;
 
-	ret = psi_cgroup_alloc(cgrp);
+	/*
+	 * Now that init_cgroup_housekeeping() has been called and cgrp->self
+	 * is setup, it is safe to perform rstat initialization on it.
+	 */
+	ret = css_rstat_init(&cgrp->self);
 	if (ret)
 		goto out_kernfs_remove;
 
-	ret = cgroup_bpf_inherit(cgrp);
+	ret = psi_cgroup_alloc(cgrp);
 	if (ret)
-		goto out_psi_free;
+		goto out_stat_exit;
+
+	for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp))
+		cgrp->ancestors[tcgrp->level] = tcgrp;
 
 	/*
 	 * New cgroup inherits effective freeze counter, and
@@ -5647,24 +5769,6 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 		set_bit(CGRP_FROZEN, &cgrp->flags);
 	}
 
-	spin_lock_irq(&css_set_lock);
-	for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
-		cgrp->ancestors[tcgrp->level] = tcgrp;
-
-		if (tcgrp != cgrp) {
-			tcgrp->nr_descendants++;
-
-			/*
-			 * If the new cgroup is frozen, all ancestor cgroups
-			 * get a new frozen descendant, but their state can't
-			 * change because of this.
-			 */
-			if (cgrp->freezer.e_freeze)
-				tcgrp->freezer.nr_frozen_descendants++;
-		}
-	}
-	spin_unlock_irq(&css_set_lock);
-
 	if (notify_on_release(parent))
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 
@@ -5673,7 +5777,29 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 
 	cgrp->self.serial_nr = css_serial_nr_next++;
 
+	ret = blocking_notifier_call_chain_robust(&cgroup_lifetime_notifier,
+						  CGROUP_LIFETIME_ONLINE,
+						  CGROUP_LIFETIME_OFFLINE, cgrp);
+	ret = notifier_to_errno(ret);
+	if (ret)
+		goto out_psi_free;
+
 	/* allocation complete, commit to creation */
+	spin_lock_irq(&css_set_lock);
+	for (i = 0; i < level; i++) {
+		tcgrp = cgrp->ancestors[i];
+		tcgrp->nr_descendants++;
+
+		/*
+		 * If the new cgroup is frozen, all ancestor cgroups get a new
+		 * frozen descendant, but their state can't change because of
+		 * this.
+		 */
+		if (cgrp->freezer.e_freeze)
+			tcgrp->freezer.nr_frozen_descendants++;
+	}
+	spin_unlock_irq(&css_set_lock);
+
 	list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children);
 	atomic_inc(&root->nr_cgrps);
 	cgroup_get_live(parent);
@@ -5691,10 +5817,10 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 
 out_psi_free:
 	psi_cgroup_free(cgrp);
+out_stat_exit:
+	css_rstat_exit(&cgrp->self);
 out_kernfs_remove:
 	kernfs_remove(cgrp->kn);
-out_stat_exit:
-	cgroup_rstat_exit(cgrp);
 out_cancel_ref:
 	percpu_ref_exit(&cgrp->self.refcnt);
 out_free_cgrp:
@@ -5706,7 +5832,7 @@ static bool cgroup_check_hierarchy_limits(struct cgroup *parent)
 {
 	struct cgroup *cgroup;
 	int ret = false;
-	int level = 1;
+	int level = 0;
 
 	lockdep_assert_held(&cgroup_mutex);
 
@@ -5714,7 +5840,7 @@ static bool cgroup_check_hierarchy_limits(struct cgroup *parent)
 		if (cgroup->nr_descendants >= cgroup->max_descendants)
 			goto fail;
 
-		if (level > cgroup->max_depth)
+		if (level >= cgroup->max_depth)
 			goto fail;
 
 		level++;
@@ -5750,7 +5876,7 @@ int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode)
 	}
 
 	/*
-	 * This extra ref will be put in cgroup_free_fn() and guarantees
+	 * This extra ref will be put in css_free_rwork_fn() and guarantees
 	 * that @cgrp->kn is always accessible.
 	 */
 	kernfs_get(cgrp->kn);
@@ -5828,6 +5954,12 @@ static void kill_css(struct cgroup_subsys_state *css)
 	if (css->flags & CSS_DYING)
 		return;
 
+	/*
+	 * Call css_killed(), if defined, before setting the CSS_DYING flag
+	 */
+	if (css->ss->css_killed)
+		css->ss->css_killed(css);
+
 	css->flags |= CSS_DYING;
 
 	/*
@@ -5885,7 +6017,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	struct cgroup *tcgrp, *parent = cgroup_parent(cgrp);
 	struct cgroup_subsys_state *css;
 	struct cgrp_cset_link *link;
-	int ssid;
+	int ssid, ret;
 
 	lockdep_assert_held(&cgroup_mutex);
 
@@ -5943,7 +6075,9 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 
 	cgroup1_check_for_release(parent);
 
-	cgroup_bpf_offline(cgrp);
+	ret = blocking_notifier_call_chain(&cgroup_lifetime_notifier,
+					   CGROUP_LIFETIME_OFFLINE, cgrp);
+	WARN_ON_ONCE(notifier_to_errno(ret));
 
 	/* put the base reference */
 	percpu_ref_kill(&cgrp->self.refcnt);
@@ -6005,6 +6139,9 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
 	} else {
 		css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL);
 		BUG_ON(css->id < 0);
+
+		BUG_ON(ss_rstat_init(ss));
+		BUG_ON(css_rstat_init(css));
 	}
 
 	/* Update the init_css_set to contain a subsys
@@ -6053,6 +6190,8 @@ int __init cgroup_init_early(void)
 		     ss->id, ss->name);
 		WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN,
 		     "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]);
+		WARN(ss->early_init && ss->css_rstat_flush,
+		     "cgroup rstat cannot be used with early init subsystem\n");
 
 		ss->id = i;
 		ss->name = cgroup_subsys_name[i];
@@ -6081,7 +6220,7 @@ int __init cgroup_init(void)
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup_psi_files));
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files));
 
-	cgroup_rstat_boot();
+	BUG_ON(ss_rstat_init(NULL));
 
 	get_user_ns(init_cgroup_ns.user_ns);
 
@@ -6094,6 +6233,8 @@ int __init cgroup_init(void)
 	hash_add(css_set_table, &init_css_set.hlist,
 		 css_set_hash(init_css_set.subsys));
 
+	cgroup_bpf_lifetime_notifier_init();
+
 	BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
 
 	cgroup_unlock();
@@ -6162,7 +6303,7 @@ int __init cgroup_init(void)
 	WARN_ON(register_filesystem(&cgroup_fs_type));
 	WARN_ON(register_filesystem(&cgroup2_fs_type));
 	WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show));
-#ifdef CONFIG_CPUSETS
+#ifdef CONFIG_CPUSETS_V1
 	WARN_ON(register_filesystem(&cpuset_fs_type));
 #endif
 
@@ -6393,7 +6534,6 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 	struct cgroup *dst_cgrp = NULL;
 	struct css_set *cset;
 	struct super_block *sb;
-	struct file *f;
 
 	if (kargs->flags & CLONE_INTO_CGROUP)
 		cgroup_lock();
@@ -6403,6 +6543,10 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 	spin_lock_irq(&css_set_lock);
 	cset = task_css_set(current);
 	get_css_set(cset);
+	if (kargs->cgrp)
+		kargs->kill_seq = kargs->cgrp->kill_seq;
+	else
+		kargs->kill_seq = cset->dfl_cgrp->kill_seq;
 	spin_unlock_irq(&css_set_lock);
 
 	if (!(kargs->flags & CLONE_INTO_CGROUP)) {
@@ -6410,14 +6554,14 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 		return 0;
 	}
 
-	f = fget_raw(kargs->cgroup);
-	if (!f) {
+	CLASS(fd_raw, f)(kargs->cgroup);
+	if (fd_empty(f)) {
 		ret = -EBADF;
 		goto err;
 	}
-	sb = f->f_path.dentry->d_sb;
+	sb = fd_file(f)->f_path.dentry->d_sb;
 
-	dst_cgrp = cgroup_get_from_file(f);
+	dst_cgrp = cgroup_get_from_file(fd_file(f));
 	if (IS_ERR(dst_cgrp)) {
 		ret = PTR_ERR(dst_cgrp);
 		dst_cgrp = NULL;
@@ -6465,15 +6609,12 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 	}
 
 	put_css_set(cset);
-	fput(f);
 	kargs->cgrp = dst_cgrp;
 	return ret;
 
 err:
 	cgroup_threadgroup_change_end(current);
 	cgroup_unlock();
-	if (f)
-		fput(f);
 	if (dst_cgrp)
 		cgroup_put(dst_cgrp);
 	put_css_set(cset);
@@ -6586,6 +6727,7 @@ void cgroup_post_fork(struct task_struct *child,
 		      struct kernel_clone_args *kargs)
 	__releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
 {
+	unsigned int cgrp_kill_seq = 0;
 	unsigned long cgrp_flags = 0;
 	bool kill = false;
 	struct cgroup_subsys *ss;
@@ -6599,10 +6741,13 @@ void cgroup_post_fork(struct task_struct *child,
 
 	/* init tasks are special, only link regular threads */
 	if (likely(child->pid)) {
-		if (kargs->cgrp)
+		if (kargs->cgrp) {
 			cgrp_flags = kargs->cgrp->flags;
-		else
+			cgrp_kill_seq = kargs->cgrp->kill_seq;
+		} else {
 			cgrp_flags = cset->dfl_cgrp->flags;
+			cgrp_kill_seq = cset->dfl_cgrp->kill_seq;
+		}
 
 		WARN_ON_ONCE(!list_empty(&child->cg_list));
 		cset->nr_tasks++;
@@ -6637,7 +6782,7 @@ void cgroup_post_fork(struct task_struct *child,
 		 * child down right after we finished preparing it for
 		 * userspace.
 		 */
-		kill = test_bit(CGRP_KILL, &cgrp_flags);
+		kill = kargs->kill_seq != cgrp_kill_seq;
 	}
 
 	spin_unlock_irq(&css_set_lock);
@@ -6685,8 +6830,10 @@ void cgroup_exit(struct task_struct *tsk)
 	WARN_ON_ONCE(list_empty(&tsk->cg_list));
 	cset = task_css_set(tsk);
 	css_set_move_task(tsk, cset, NULL, false);
-	list_add_tail(&tsk->cg_list, &cset->dying_tasks);
 	cset->nr_tasks--;
+	/* matches the signal->live check in css_task_iter_advance() */
+	if (thread_group_leader(tsk) && atomic_read(&tsk->signal->live))
+		list_add_tail(&tsk->cg_list, &cset->dying_tasks);
 
 	if (dl_task(tsk))
 		dec_dl_tasks_cs(tsk);
@@ -6713,10 +6860,12 @@ void cgroup_release(struct task_struct *task)
 		ss->release(task);
 	} while_each_subsys_mask();
 
-	spin_lock_irq(&css_set_lock);
-	css_set_skip_task_iters(task_css_set(task), task);
-	list_del_init(&task->cg_list);
-	spin_unlock_irq(&css_set_lock);
+	if (!list_empty(&task->cg_list)) {
+		spin_lock_irq(&css_set_lock);
+		css_set_skip_task_iters(task_css_set(task), task);
+		list_del_init(&task->cg_list);
+		spin_unlock_irq(&css_set_lock);
+	}
 }
 
 void cgroup_free(struct task_struct *task)
@@ -6879,14 +7028,11 @@ EXPORT_SYMBOL_GPL(cgroup_get_from_path);
  */
 struct cgroup *cgroup_v1v2_get_from_fd(int fd)
 {
-	struct cgroup *cgrp;
-	struct fd f = fdget_raw(fd);
-	if (!f.file)
+	CLASS(fd_raw, f)(fd);
+	if (fd_empty(f))
 		return ERR_PTR(-EBADF);
 
-	cgrp = cgroup_v1v2_get_from_file(f.file);
-	fdput(f);
-	return cgrp;
+	return cgroup_v1v2_get_from_file(fd_file(f));
 }
 
 /**
@@ -7061,7 +7207,8 @@ static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr,
 			"favordynmods\n"
 			"memory_localevents\n"
 			"memory_recursiveprot\n"
-			"memory_hugetlb_accounting\n");
+			"memory_hugetlb_accounting\n"
+			"pids_localevents\n");
 }
 static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features);