1 files changed, 516 insertions, 189 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 919194de39c8..2319946715e0 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -30,6 +30,7 @@
 
 #include "cgroup-internal.h"
 
+#include <linux/bpf-cgroup.h>
 #include <linux/cred.h>
 #include <linux/errno.h>
 #include <linux/init_task.h>
@@ -95,7 +96,7 @@ EXPORT_SYMBOL_GPL(css_set_lock);
 
 DEFINE_SPINLOCK(trace_cgroup_path_lock);
 char trace_cgroup_path[TRACE_CGROUP_PATH_LEN];
-bool cgroup_debug __read_mostly;
+static bool cgroup_debug __read_mostly;
 
 /*
  * Protects cgroup_idr and css_idr so that IDs can be released without
@@ -216,6 +217,7 @@ struct cgroup_namespace init_cgroup_ns = {
 
 static struct file_system_type cgroup2_fs_type;
 static struct cftype cgroup_base_files[];
+static struct cftype cgroup_psi_files[];
 
 /* cgroup optional features */
 enum cgroup_opt_features {
@@ -278,8 +280,6 @@ bool cgroup_ssid_enabled(int ssid)
  *
  * - When mounting an existing superblock, mount options should match.
  *
- * - Remount is disallowed.
- *
  * - rename(2) is disallowed.
  *
  * - "tasks" is removed.  Everything should be at process granularity.  Use
@@ -764,7 +764,8 @@ struct css_set init_css_set = {
 	.task_iters		= LIST_HEAD_INIT(init_css_set.task_iters),
 	.threaded_csets		= LIST_HEAD_INIT(init_css_set.threaded_csets),
 	.cgrp_links		= LIST_HEAD_INIT(init_css_set.cgrp_links),
-	.mg_preload_node	= LIST_HEAD_INIT(init_css_set.mg_preload_node),
+	.mg_src_preload_node	= LIST_HEAD_INIT(init_css_set.mg_src_preload_node),
+	.mg_dst_preload_node	= LIST_HEAD_INIT(init_css_set.mg_dst_preload_node),
 	.mg_node		= LIST_HEAD_INIT(init_css_set.mg_node),
 
 	/*
@@ -1239,7 +1240,8 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	INIT_LIST_HEAD(&cset->threaded_csets);
 	INIT_HLIST_NODE(&cset->hlist);
 	INIT_LIST_HEAD(&cset->cgrp_links);
-	INIT_LIST_HEAD(&cset->mg_preload_node);
+	INIT_LIST_HEAD(&cset->mg_src_preload_node);
+	INIT_LIST_HEAD(&cset->mg_dst_preload_node);
 	INIT_LIST_HEAD(&cset->mg_node);
 
 	/* Copy the set of subsystem state objects generated in
@@ -1301,11 +1303,25 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 
 struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
 {
-	struct cgroup *root_cgrp = kf_root->kn->priv;
+	struct cgroup *root_cgrp = kernfs_root_to_node(kf_root)->priv;
 
 	return root_cgrp->root;
 }
 
+void cgroup_favor_dynmods(struct cgroup_root *root, bool favor)
+{
+	bool favoring = root->flags & CGRP_ROOT_FAVOR_DYNMODS;
+
+	/* see the comment above CGRP_ROOT_FAVOR_DYNMODS definition */
+	if (favor && !favoring) {
+		rcu_sync_enter(&cgroup_threadgroup_rwsem.rss);
+		root->flags |= CGRP_ROOT_FAVOR_DYNMODS;
+	} else if (!favor && favoring) {
+		rcu_sync_exit(&cgroup_threadgroup_rwsem.rss);
+		root->flags &= ~CGRP_ROOT_FAVOR_DYNMODS;
+	}
+}
+
 static int cgroup_init_root_id(struct cgroup_root *root)
 {
 	int id;
@@ -1366,6 +1382,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 		cgroup_root_count--;
 	}
 
+	cgroup_favor_dynmods(root, false);
 	cgroup_exit_root_id(root);
 
 	mutex_unlock(&cgroup_mutex);
@@ -1376,73 +1393,87 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 }
 
 /*
- * look up cgroup associated with current task's cgroup namespace on the
- * specified hierarchy
+ * Returned cgroup is without refcount but it's valid as long as cset pins it.
  */
-static struct cgroup *
-current_cgns_cgroup_from_root(struct cgroup_root *root)
+static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset,
+					    struct cgroup_root *root)
 {
-	struct cgroup *res = NULL;
-	struct css_set *cset;
+	struct cgroup *res_cgroup = NULL;
 
-	lockdep_assert_held(&css_set_lock);
-
-	rcu_read_lock();
-
-	cset = current->nsproxy->cgroup_ns->root_cset;
 	if (cset == &init_css_set) {
-		res = &root->cgrp;
+		res_cgroup = &root->cgrp;
 	} else if (root == &cgrp_dfl_root) {
-		res = cset->dfl_cgrp;
+		res_cgroup = cset->dfl_cgrp;
 	} else {
 		struct cgrp_cset_link *link;
+		lockdep_assert_held(&css_set_lock);
 
 		list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
 			struct cgroup *c = link->cgrp;
 
 			if (c->root == root) {
-				res = c;
+				res_cgroup = c;
 				break;
 			}
 		}
 	}
-	rcu_read_unlock();
 
-	BUG_ON(!res);
-	return res;
+	BUG_ON(!res_cgroup);
+	return res_cgroup;
 }
 
-/* look up cgroup associated with given css_set on the specified hierarchy */
-static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
-					    struct cgroup_root *root)
+/*
+ * look up cgroup associated with current task's cgroup namespace on the
+ * specified hierarchy
+ */
+static struct cgroup *
+current_cgns_cgroup_from_root(struct cgroup_root *root)
 {
 	struct cgroup *res = NULL;
+	struct css_set *cset;
 
-	lockdep_assert_held(&cgroup_mutex);
 	lockdep_assert_held(&css_set_lock);
 
-	if (cset == &init_css_set) {
-		res = &root->cgrp;
-	} else if (root == &cgrp_dfl_root) {
-		res = cset->dfl_cgrp;
-	} else {
-		struct cgrp_cset_link *link;
+	rcu_read_lock();
 
-		list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
-			struct cgroup *c = link->cgrp;
+	cset = current->nsproxy->cgroup_ns->root_cset;
+	res = __cset_cgroup_from_root(cset, root);
 
-			if (c->root == root) {
-				res = c;
-				break;
-			}
-		}
-	}
+	rcu_read_unlock();
 
-	BUG_ON(!res);
 	return res;
 }
 
 /*
+ * Look up cgroup associated with current task's cgroup namespace on the default
+ * hierarchy.
+ *
+ * Unlike current_cgns_cgroup_from_root(), this doesn't need locks:
+ * - Internal rcu_read_lock is unnecessary because we don't dereference any rcu
+ *   pointers.
+ * - css_set_lock is not needed because we just read cset->dfl_cgrp.
+ * - As a bonus returned cgrp is pinned with the current because it cannot
+ *   switch cgroup_ns asynchronously.
+ */
+static struct cgroup *current_cgns_cgroup_dfl(void)
+{
+	struct css_set *cset;
+
+	cset = current->nsproxy->cgroup_ns->root_cset;
+	return __cset_cgroup_from_root(cset, &cgrp_dfl_root);
+}
+
+/* look up cgroup associated with given css_set on the specified hierarchy */
+static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
+					    struct cgroup_root *root)
+{
+	lockdep_assert_held(&cgroup_mutex);
+	lockdep_assert_held(&css_set_lock);
+
+	return __cset_cgroup_from_root(cset, root);
+}
+
+/*
  * Return the cgroup for "task" from the given hierarchy. Must be
  * called with cgroup_mutex and css_set_lock held.
  */
@@ -1677,12 +1708,16 @@ static void css_clear_dir(struct cgroup_subsys_state *css)
 	css->flags &= ~CSS_VISIBLE;
 
 	if (!css->ss) {
-		if (cgroup_on_dfl(cgrp))
-			cfts = cgroup_base_files;
-		else
-			cfts = cgroup1_base_files;
-
-		cgroup_addrm_files(css, cgrp, cfts, false);
+		if (cgroup_on_dfl(cgrp)) {
+			cgroup_addrm_files(css, cgrp,
+					   cgroup_base_files, false);
+			if (cgroup_psi_enabled())
+				cgroup_addrm_files(css, cgrp,
+						   cgroup_psi_files, false);
+		} else {
+			cgroup_addrm_files(css, cgrp,
+					   cgroup1_base_files, false);
+		}
 	} else {
 		list_for_each_entry(cfts, &css->ss->cfts, node)
 			cgroup_addrm_files(css, cgrp, cfts, false);
@@ -1705,14 +1740,22 @@ static int css_populate_dir(struct cgroup_subsys_state *css)
 		return 0;
 
 	if (!css->ss) {
-		if (cgroup_on_dfl(cgrp))
-			cfts = cgroup_base_files;
-		else
-			cfts = cgroup1_base_files;
-
-		ret = cgroup_addrm_files(&cgrp->self, cgrp, cfts, true);
-		if (ret < 0)
-			return ret;
+		if (cgroup_on_dfl(cgrp)) {
+			ret = cgroup_addrm_files(&cgrp->self, cgrp,
+						 cgroup_base_files, true);
+			if (ret < 0)
+				return ret;
+
+			if (cgroup_psi_enabled()) {
+				ret = cgroup_addrm_files(&cgrp->self, cgrp,
+							 cgroup_psi_files, true);
+				if (ret < 0)
+					return ret;
+			}
+		} else {
+			cgroup_addrm_files(css, cgrp,
+					   cgroup1_base_files, true);
+		}
 	} else {
 		list_for_each_entry(cfts, &css->ss->cfts, node) {
 			ret = cgroup_addrm_files(css, cgrp, cfts, true);
@@ -1808,6 +1851,7 @@ 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);
 		}
@@ -1863,6 +1907,7 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
 
 enum cgroup2_param {
 	Opt_nsdelegate,
+	Opt_favordynmods,
 	Opt_memory_localevents,
 	Opt_memory_recursiveprot,
 	nr__cgroup2_params
@@ -1870,6 +1915,7 @@ enum cgroup2_param {
 
 static const struct fs_parameter_spec cgroup2_fs_parameters[] = {
 	fsparam_flag("nsdelegate",		Opt_nsdelegate),
+	fsparam_flag("favordynmods",		Opt_favordynmods),
 	fsparam_flag("memory_localevents",	Opt_memory_localevents),
 	fsparam_flag("memory_recursiveprot",	Opt_memory_recursiveprot),
 	{}
@@ -1889,6 +1935,9 @@ static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param
 	case Opt_nsdelegate:
 		ctx->flags |= CGRP_ROOT_NS_DELEGATE;
 		return 0;
+	case Opt_favordynmods:
+		ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS;
+		return 0;
 	case Opt_memory_localevents:
 		ctx->flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS;
 		return 0;
@@ -1907,6 +1956,9 @@ static void apply_cgroup_root_flags(unsigned int root_flags)
 		else
 			cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE;
 
+		cgroup_favor_dynmods(&cgrp_dfl_root,
+				     root_flags & CGRP_ROOT_FAVOR_DYNMODS);
+
 		if (root_flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS)
 			cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS;
 		else
@@ -1923,6 +1975,8 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root
 {
 	if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE)
 		seq_puts(seq, ",nsdelegate");
+	if (cgrp_dfl_root.flags & CGRP_ROOT_FAVOR_DYNMODS)
+		seq_puts(seq, ",favordynmods");
 	if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS)
 		seq_puts(seq, ",memory_localevents");
 	if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT)
@@ -1973,7 +2027,8 @@ void init_cgroup_root(struct cgroup_fs_context *ctx)
 	cgrp->root = root;
 	init_cgroup_housekeeping(cgrp);
 
-	root->flags = ctx->flags;
+	/* DYNMODS must be modified through cgroup_favor_dynmods() */
+	root->flags = ctx->flags & ~CGRP_ROOT_FAVOR_DYNMODS;
 	if (ctx->release_agent)
 		strscpy(root->release_agent_path, ctx->release_agent, PATH_MAX);
 	if (ctx->name)
@@ -2024,9 +2079,9 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 		ret = PTR_ERR(root->kf_root);
 		goto exit_root_id;
 	}
-	root_cgrp->kn = root->kf_root->kn;
+	root_cgrp->kn = kernfs_root_to_node(root->kf_root);
 	WARN_ON_ONCE(cgroup_ino(root_cgrp) != 1);
-	root_cgrp->ancestor_ids[0] = cgroup_id(root_cgrp);
+	root_cgrp->ancestors[0] = root_cgrp;
 
 	ret = css_populate_dir(&root_cgrp->self);
 	if (ret)
@@ -2149,7 +2204,7 @@ static int cgroup_get_tree(struct fs_context *fc)
 	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
 	int ret;
 
-	cgrp_dfl_visible = true;
+	WRITE_ONCE(cgrp_dfl_visible, true);
 	cgroup_get_live(&cgrp_dfl_root.cgrp);
 	ctx->root = &cgrp_dfl_root;
 
@@ -2195,6 +2250,10 @@ static int cgroup_init_fs_context(struct fs_context *fc)
 	put_user_ns(fc->user_ns);
 	fc->user_ns = get_user_ns(ctx->ns->user_ns);
 	fc->global = true;
+
+#ifdef CONFIG_CGROUP_FAVOR_DYNMODS
+	ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS;
+#endif
 	return 0;
 }
 
@@ -2333,7 +2392,7 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 		ret = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns);
 	} else {
 		/* if no hierarchy exists, everyone is in "/" */
-		ret = strlcpy(buf, "/", buflen);
+		ret = strscpy(buf, "/", buflen);
 	}
 
 	spin_unlock_irq(&css_set_lock);
@@ -2343,6 +2402,47 @@ 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.
+ */
+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
+ */
+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
  * @mgctx: target migration context
@@ -2569,10 +2669,6 @@ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp)
 	if (!cgroup_is_valid_domain(dst_cgrp->dom_cgrp))
 		return -EOPNOTSUPP;
 
-	/* mixables don't care */
-	if (cgroup_is_mixable(dst_cgrp))
-		return 0;
-
 	/*
 	 * If @dst_cgrp is already or can become a thread root or is
 	 * threaded, it doesn't matter.
@@ -2596,21 +2692,27 @@ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp)
  */
 void cgroup_migrate_finish(struct cgroup_mgctx *mgctx)
 {
-	LIST_HEAD(preloaded);
 	struct css_set *cset, *tmp_cset;
 
 	lockdep_assert_held(&cgroup_mutex);
 
 	spin_lock_irq(&css_set_lock);
 
-	list_splice_tail_init(&mgctx->preloaded_src_csets, &preloaded);
-	list_splice_tail_init(&mgctx->preloaded_dst_csets, &preloaded);
+	list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets,
+				 mg_src_preload_node) {
+		cset->mg_src_cgrp = NULL;
+		cset->mg_dst_cgrp = NULL;
+		cset->mg_dst_cset = NULL;
+		list_del_init(&cset->mg_src_preload_node);
+		put_css_set_locked(cset);
+	}
 
-	list_for_each_entry_safe(cset, tmp_cset, &preloaded, mg_preload_node) {
+	list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets,
+				 mg_dst_preload_node) {
 		cset->mg_src_cgrp = NULL;
 		cset->mg_dst_cgrp = NULL;
 		cset->mg_dst_cset = NULL;
-		list_del_init(&cset->mg_preload_node);
+		list_del_init(&cset->mg_dst_preload_node);
 		put_css_set_locked(cset);
 	}
 
@@ -2650,11 +2752,11 @@ void cgroup_migrate_add_src(struct css_set *src_cset,
 	if (src_cset->dead)
 		return;
 
-	src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
-
-	if (!list_empty(&src_cset->mg_preload_node))
+	if (!list_empty(&src_cset->mg_src_preload_node))
 		return;
 
+	src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
+
 	WARN_ON(src_cset->mg_src_cgrp);
 	WARN_ON(src_cset->mg_dst_cgrp);
 	WARN_ON(!list_empty(&src_cset->mg_tasks));
@@ -2663,7 +2765,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset,
 	src_cset->mg_src_cgrp = src_cgrp;
 	src_cset->mg_dst_cgrp = dst_cgrp;
 	get_css_set(src_cset);
-	list_add_tail(&src_cset->mg_preload_node, &mgctx->preloaded_src_csets);
+	list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets);
 }
 
 /**
@@ -2688,7 +2790,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
 
 	/* look up the dst cset for each src cset and link it to src */
 	list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets,
-				 mg_preload_node) {
+				 mg_src_preload_node) {
 		struct css_set *dst_cset;
 		struct cgroup_subsys *ss;
 		int ssid;
@@ -2707,7 +2809,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
 		if (src_cset == dst_cset) {
 			src_cset->mg_src_cgrp = NULL;
 			src_cset->mg_dst_cgrp = NULL;
-			list_del_init(&src_cset->mg_preload_node);
+			list_del_init(&src_cset->mg_src_preload_node);
 			put_css_set(src_cset);
 			put_css_set(dst_cset);
 			continue;
@@ -2715,8 +2817,8 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
 
 		src_cset->mg_dst_cset = dst_cset;
 
-		if (list_empty(&dst_cset->mg_preload_node))
-			list_add_tail(&dst_cset->mg_preload_node,
+		if (list_empty(&dst_cset->mg_dst_preload_node))
+			list_add_tail(&dst_cset->mg_dst_preload_node,
 				      &mgctx->preloaded_dst_csets);
 		else
 			put_css_set(dst_cset);
@@ -2812,8 +2914,7 @@ 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;
@@ -2830,12 +2931,8 @@ 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) {
@@ -2866,17 +2963,14 @@ 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;
@@ -2884,8 +2978,8 @@ 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();
@@ -2940,29 +3034,47 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	struct cgroup_subsys_state *d_css;
 	struct cgroup *dsct;
 	struct css_set *src_cset;
+	bool has_tasks;
 	int ret;
 
 	lockdep_assert_held(&cgroup_mutex);
 
-	percpu_down_write(&cgroup_threadgroup_rwsem);
-
 	/* look up all csses currently attached to @cgrp's subtree */
 	spin_lock_irq(&css_set_lock);
 	cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
 		struct cgrp_cset_link *link;
 
+		/*
+		 * As cgroup_update_dfl_csses() is only called by
+		 * cgroup_apply_control(). The csses associated with the
+		 * given cgrp will not be affected by changes made to
+		 * its subtree_control file. We can skip them.
+		 */
+		if (dsct == cgrp)
+			continue;
+
 		list_for_each_entry(link, &dsct->cset_links, cset_link)
 			cgroup_migrate_add_src(link->cset, dsct, &mgctx);
 	}
 	spin_unlock_irq(&css_set_lock);
 
+	/*
+	 * We need to write-lock threadgroup_rwsem while migrating tasks.
+	 * However, if there are no source csets for @cgrp, changing its
+	 * controllers isn't gonna produce any task migrations and the
+	 * write-locking can be skipped safely.
+	 */
+	has_tasks = !list_empty(&mgctx.preloaded_src_csets);
+	cgroup_attach_lock(has_tasks);
+
 	/* NULL dst indicates self on default hierarchy */
 	ret = cgroup_migrate_prepare_dst(&mgctx);
 	if (ret)
 		goto out_finish;
 
 	spin_lock_irq(&css_set_lock);
-	list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_preload_node) {
+	list_for_each_entry(src_cset, &mgctx.preloaded_src_csets,
+			    mg_src_preload_node) {
 		struct task_struct *task, *ntask;
 
 		/* all tasks in src_csets need to be migrated */
@@ -2974,7 +3086,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	ret = cgroup_migrate_execute(&mgctx);
 out_finish:
 	cgroup_migrate_finish(&mgctx);
-	percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock(has_tasks);
 	return ret;
 }
 
@@ -3211,11 +3323,7 @@ static int cgroup_apply_control(struct cgroup *cgrp)
 	 * making the following cgroup_update_dfl_csses() properly update
 	 * css associations of all tasks in the subtree.
 	 */
-	ret = cgroup_update_dfl_csses(cgrp);
-	if (ret)
-		return ret;
-
-	return 0;
+	return cgroup_update_dfl_csses(cgrp);
 }
 
 /**
@@ -3608,28 +3716,29 @@ static int cpu_stat_show(struct seq_file *seq, void *v)
 static int cgroup_io_pressure_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi;
+	struct psi_group *psi = cgroup_psi(cgrp);
 
 	return psi_show(seq, psi, PSI_IO);
 }
 static int cgroup_memory_pressure_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi;
+	struct psi_group *psi = cgroup_psi(cgrp);
 
 	return psi_show(seq, psi, PSI_MEM);
 }
 static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi;
+	struct psi_group *psi = cgroup_psi(cgrp);
 
 	return psi_show(seq, psi, PSI_CPU);
 }
 
-static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
-					  size_t nbytes, enum psi_res res)
+static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
+			      size_t nbytes, enum psi_res res)
 {
+	struct cgroup_file_ctx *ctx = of->priv;
 	struct psi_trigger *new;
 	struct cgroup *cgrp;
 	struct psi_group *psi;
@@ -3641,15 +3750,20 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
 	cgroup_get(cgrp);
 	cgroup_kn_unlock(of->kn);
 
-	psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi;
-	new = psi_trigger_create(psi, buf, nbytes, res);
+	/* Allow only one trigger per file descriptor */
+	if (ctx->psi.trigger) {
+		cgroup_put(cgrp);
+		return -EBUSY;
+	}
+
+	psi = cgroup_psi(cgrp);
+	new = psi_trigger_create(psi, buf, res);
 	if (IS_ERR(new)) {
 		cgroup_put(cgrp);
 		return PTR_ERR(new);
 	}
 
-	psi_trigger_replace(&of->priv, new);
-
+	smp_store_release(&ctx->psi.trigger, new);
 	cgroup_put(cgrp);
 
 	return nbytes;
@@ -3659,36 +3773,108 @@ static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of,
 					  char *buf, size_t nbytes,
 					  loff_t off)
 {
-	return cgroup_pressure_write(of, buf, nbytes, PSI_IO);
+	return pressure_write(of, buf, nbytes, PSI_IO);
 }
 
 static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of,
 					  char *buf, size_t nbytes,
 					  loff_t off)
 {
-	return cgroup_pressure_write(of, buf, nbytes, PSI_MEM);
+	return pressure_write(of, buf, nbytes, PSI_MEM);
 }
 
 static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of,
 					  char *buf, size_t nbytes,
 					  loff_t off)
 {
-	return cgroup_pressure_write(of, buf, nbytes, PSI_CPU);
+	return pressure_write(of, buf, nbytes, PSI_CPU);
+}
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+static int cgroup_irq_pressure_show(struct seq_file *seq, void *v)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	struct psi_group *psi = cgroup_psi(cgrp);
+
+	return psi_show(seq, psi, PSI_IRQ);
+}
+
+static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of,
+					 char *buf, size_t nbytes,
+					 loff_t off)
+{
+	return pressure_write(of, buf, nbytes, PSI_IRQ);
+}
+#endif
+
+static int cgroup_pressure_show(struct seq_file *seq, void *v)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	struct psi_group *psi = cgroup_psi(cgrp);
+
+	seq_printf(seq, "%d\n", psi->enabled);
+
+	return 0;
+}
+
+static ssize_t cgroup_pressure_write(struct kernfs_open_file *of,
+				     char *buf, size_t nbytes,
+				     loff_t off)
+{
+	ssize_t ret;
+	int enable;
+	struct cgroup *cgrp;
+	struct psi_group *psi;
+
+	ret = kstrtoint(strstrip(buf), 0, &enable);
+	if (ret)
+		return ret;
+
+	if (enable < 0 || enable > 1)
+		return -ERANGE;
+
+	cgrp = cgroup_kn_lock_live(of->kn, false);
+	if (!cgrp)
+		return -ENOENT;
+
+	psi = cgroup_psi(cgrp);
+	if (psi->enabled != enable) {
+		int i;
+
+		/* show or hide {cpu,memory,io,irq}.pressure files */
+		for (i = 0; i < NR_PSI_RESOURCES; i++)
+			cgroup_file_show(&cgrp->psi_files[i], enable);
+
+		psi->enabled = enable;
+		if (enable)
+			psi_cgroup_restart(psi);
+	}
+
+	cgroup_kn_unlock(of->kn);
+
+	return nbytes;
 }
 
 static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
 					  poll_table *pt)
 {
-	return psi_trigger_poll(&of->priv, of->file, pt);
+	struct cgroup_file_ctx *ctx = of->priv;
+
+	return psi_trigger_poll(&ctx->psi.trigger, of->file, pt);
 }
 
 static void cgroup_pressure_release(struct kernfs_open_file *of)
 {
-	psi_trigger_replace(&of->priv, NULL);
+	struct cgroup_file_ctx *ctx = of->priv;
+
+	psi_trigger_destroy(ctx->psi.trigger);
 }
 
 bool cgroup_psi_enabled(void)
 {
+	if (static_branch_likely(&psi_disabled))
+		return false;
+
 	return (cgroup_feature_disable_mask & (1 << OPT_FEATURE_PRESSURE)) == 0;
 }
 
@@ -3811,24 +3997,43 @@ static ssize_t cgroup_kill_write(struct kernfs_open_file *of, char *buf,
 static int cgroup_file_open(struct kernfs_open_file *of)
 {
 	struct cftype *cft = of_cft(of);
+	struct cgroup_file_ctx *ctx;
+	int ret;
 
-	if (cft->open)
-		return cft->open(of);
-	return 0;
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->ns = current->nsproxy->cgroup_ns;
+	get_cgroup_ns(ctx->ns);
+	of->priv = ctx;
+
+	if (!cft->open)
+		return 0;
+
+	ret = cft->open(of);
+	if (ret) {
+		put_cgroup_ns(ctx->ns);
+		kfree(ctx);
+	}
+	return ret;
 }
 
 static void cgroup_file_release(struct kernfs_open_file *of)
 {
 	struct cftype *cft = of_cft(of);
+	struct cgroup_file_ctx *ctx = of->priv;
 
 	if (cft->release)
 		cft->release(of);
+	put_cgroup_ns(ctx->ns);
+	kfree(ctx);
 }
 
 static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 				 size_t nbytes, loff_t off)
 {
-	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
+	struct cgroup_file_ctx *ctx = of->priv;
 	struct cgroup *cgrp = of->kn->parent->priv;
 	struct cftype *cft = of_cft(of);
 	struct cgroup_subsys_state *css;
@@ -3845,7 +4050,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 	 */
 	if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) &&
 	    !(cft->flags & CFTYPE_NS_DELEGATABLE) &&
-	    ns != &init_cgroup_ns && ns->root_cset->dfl_cgrp == cgrp)
+	    ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp)
 		return -EPERM;
 
 	if (cft->write)
@@ -4022,8 +4227,6 @@ static int cgroup_addrm_files(struct cgroup_subsys_state *css,
 restart:
 	for (cft = cfts; cft != cft_end && cft->name[0] != '\0'; cft++) {
 		/* does cft->flags tell us to skip this file on @cgrp? */
-		if ((cft->flags & CFTYPE_PRESSURE) && !cgroup_psi_enabled())
-			continue;
 		if ((cft->flags & __CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp))
 			continue;
 		if ((cft->flags & __CFTYPE_NOT_ON_DFL) && cgroup_on_dfl(cgrp))
@@ -4088,21 +4291,25 @@ static void cgroup_exit_cftypes(struct cftype *cfts)
 		cft->ss = NULL;
 
 		/* revert flags set by cgroup core while adding @cfts */
-		cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL);
+		cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL |
+				__CFTYPE_ADDED);
 	}
 }
 
 static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 {
 	struct cftype *cft;
+	int ret = 0;
 
 	for (cft = cfts; cft->name[0] != '\0'; cft++) {
 		struct kernfs_ops *kf_ops;
 
 		WARN_ON(cft->ss || cft->kf_ops);
 
-		if ((cft->flags & CFTYPE_PRESSURE) && !cgroup_psi_enabled())
-			continue;
+		if (cft->flags & __CFTYPE_ADDED) {
+			ret = -EBUSY;
+			break;
+		}
 
 		if (cft->seq_start)
 			kf_ops = &cgroup_kf_ops;
@@ -4116,26 +4323,26 @@ static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 		if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) {
 			kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL);
 			if (!kf_ops) {
-				cgroup_exit_cftypes(cfts);
-				return -ENOMEM;
+				ret = -ENOMEM;
+				break;
 			}
 			kf_ops->atomic_write_len = cft->max_write_len;
 		}
 
 		cft->kf_ops = kf_ops;
 		cft->ss = ss;
+		cft->flags |= __CFTYPE_ADDED;
 	}
 
-	return 0;
+	if (ret)
+		cgroup_exit_cftypes(cfts);
+	return ret;
 }
 
 static int cgroup_rm_cftypes_locked(struct cftype *cfts)
 {
 	lockdep_assert_held(&cgroup_mutex);
 
-	if (!cfts || !cfts[0].ss)
-		return -ENOENT;
-
 	list_del(&cfts->node);
 	cgroup_apply_cftypes(cfts, false);
 	cgroup_exit_cftypes(cfts);
@@ -4157,6 +4364,12 @@ int cgroup_rm_cftypes(struct cftype *cfts)
 {
 	int ret;
 
+	if (!cfts || cfts[0].name[0] == '\0')
+		return 0;
+
+	if (!(cfts[0].flags & __CFTYPE_ADDED))
+		return -ENOENT;
+
 	mutex_lock(&cgroup_mutex);
 	ret = cgroup_rm_cftypes_locked(cfts);
 	mutex_unlock(&cgroup_mutex);
@@ -4262,6 +4475,26 @@ void cgroup_file_notify(struct cgroup_file *cfile)
 }
 
 /**
+ * cgroup_file_show - show or hide a hidden cgroup file
+ * @cfile: target cgroup_file obtained by setting cftype->file_offset
+ * @show: whether to show or hide
+ */
+void cgroup_file_show(struct cgroup_file *cfile, bool show)
+{
+	struct kernfs_node *kn;
+
+	spin_lock_irq(&cgroup_file_kn_lock);
+	kn = cfile->kn;
+	kernfs_get(kn);
+	spin_unlock_irq(&cgroup_file_kn_lock);
+
+	if (kn)
+		kernfs_show(kn, show);
+
+	kernfs_put(kn);
+}
+
+/**
  * css_next_child - find the next child of a given css
  * @pos: the current position (%NULL to initiate traversal)
  * @parent: css whose children to walk
@@ -4751,21 +4984,21 @@ void css_task_iter_end(struct css_task_iter *it)
 
 static void cgroup_procs_release(struct kernfs_open_file *of)
 {
-	if (of->priv) {
-		css_task_iter_end(of->priv);
-		kfree(of->priv);
-	}
+	struct cgroup_file_ctx *ctx = of->priv;
+
+	if (ctx->procs.started)
+		css_task_iter_end(&ctx->procs.iter);
 }
 
 static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos)
 {
 	struct kernfs_open_file *of = s->private;
-	struct css_task_iter *it = of->priv;
+	struct cgroup_file_ctx *ctx = of->priv;
 
 	if (pos)
 		(*pos)++;
 
-	return css_task_iter_next(it);
+	return css_task_iter_next(&ctx->procs.iter);
 }
 
 static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos,
@@ -4773,21 +5006,18 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos,
 {
 	struct kernfs_open_file *of = s->private;
 	struct cgroup *cgrp = seq_css(s)->cgroup;
-	struct css_task_iter *it = of->priv;
+	struct cgroup_file_ctx *ctx = of->priv;
+	struct css_task_iter *it = &ctx->procs.iter;
 
 	/*
 	 * When a seq_file is seeked, it's always traversed sequentially
 	 * from position 0, so we can simply keep iterating on !0 *pos.
 	 */
-	if (!it) {
+	if (!ctx->procs.started) {
 		if (WARN_ON_ONCE((*pos)))
 			return ERR_PTR(-EINVAL);
-
-		it = kzalloc(sizeof(*it), GFP_KERNEL);
-		if (!it)
-			return ERR_PTR(-ENOMEM);
-		of->priv = it;
 		css_task_iter_start(&cgrp->self, iter_flags, it);
+		ctx->procs.started = true;
 	} else if (!(*pos)) {
 		css_task_iter_end(it);
 		css_task_iter_start(&cgrp->self, iter_flags, it);
@@ -4838,9 +5068,9 @@ static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb)
 
 static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
 					 struct cgroup *dst_cgrp,
-					 struct super_block *sb)
+					 struct super_block *sb,
+					 struct cgroup_namespace *ns)
 {
-	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
 	struct cgroup *com_cgrp = src_cgrp;
 	int ret;
 
@@ -4869,11 +5099,12 @@ static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
 
 static int cgroup_attach_permissions(struct cgroup *src_cgrp,
 				     struct cgroup *dst_cgrp,
-				     struct super_block *sb, bool threadgroup)
+				     struct super_block *sb, bool threadgroup,
+				     struct cgroup_namespace *ns)
 {
 	int ret = 0;
 
-	ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb);
+	ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb, ns);
 	if (ret)
 		return ret;
 
@@ -4890,16 +5121,18 @@ static int cgroup_attach_permissions(struct cgroup *src_cgrp,
 static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 				    bool threadgroup)
 {
+	struct cgroup_file_ctx *ctx = of->priv;
 	struct cgroup *src_cgrp, *dst_cgrp;
 	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;
@@ -4909,16 +5142,23 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
 	spin_unlock_irq(&css_set_lock);
 
-	/* process and thread migrations follow same delegation rule */
+	/*
+	 * Process and thread migrations follow same delegation rule. Check
+	 * permissions using the credentials from file open to protect against
+	 * inherited fd attacks.
+	 */
+	saved_cred = override_creds(of->file->f_cred);
 	ret = cgroup_attach_permissions(src_cgrp, dst_cgrp,
-					of->file->f_path.dentry->d_sb, threadgroup);
+					of->file->f_path.dentry->d_sb,
+					threadgroup, ctx->ns);
+	revert_creds(saved_cred);
 	if (ret)
 		goto out_finish;
 
 	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);
 
@@ -5014,10 +5254,14 @@ static struct cftype cgroup_base_files[] = {
 		.name = "cpu.stat",
 		.seq_show = cpu_stat_show,
 	},
+	{ }	/* terminate */
+};
+
+static struct cftype cgroup_psi_files[] = {
 #ifdef CONFIG_PSI
 	{
 		.name = "io.pressure",
-		.flags = CFTYPE_PRESSURE,
+		.file_offset = offsetof(struct cgroup, psi_files[PSI_IO]),
 		.seq_show = cgroup_io_pressure_show,
 		.write = cgroup_io_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5025,7 +5269,7 @@ static struct cftype cgroup_base_files[] = {
 	},
 	{
 		.name = "memory.pressure",
-		.flags = CFTYPE_PRESSURE,
+		.file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]),
 		.seq_show = cgroup_memory_pressure_show,
 		.write = cgroup_memory_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5033,12 +5277,27 @@ static struct cftype cgroup_base_files[] = {
 	},
 	{
 		.name = "cpu.pressure",
-		.flags = CFTYPE_PRESSURE,
+		.file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]),
 		.seq_show = cgroup_cpu_pressure_show,
 		.write = cgroup_cpu_pressure_write,
 		.poll = cgroup_pressure_poll,
 		.release = cgroup_pressure_release,
 	},
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	{
+		.name = "irq.pressure",
+		.file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]),
+		.seq_show = cgroup_irq_pressure_show,
+		.write = cgroup_irq_pressure_write,
+		.poll = cgroup_pressure_poll,
+		.release = cgroup_pressure_release,
+	},
+#endif
+	{
+		.name = "cgroup.pressure",
+		.seq_show = cgroup_pressure_show,
+		.write = cgroup_pressure_write,
+	},
 #endif /* CONFIG_PSI */
 	{ }	/* terminate */
 };
@@ -5315,8 +5574,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 	int ret;
 
 	/* allocate the cgroup and its ID, 0 is reserved for the root */
-	cgrp = kzalloc(struct_size(cgrp, ancestor_ids, (level + 1)),
-		       GFP_KERNEL);
+	cgrp = kzalloc(struct_size(cgrp, ancestors, (level + 1)), GFP_KERNEL);
 	if (!cgrp)
 		return ERR_PTR(-ENOMEM);
 
@@ -5368,7 +5626,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 
 	spin_lock_irq(&css_set_lock);
 	for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
-		cgrp->ancestor_ids[tcgrp->level] = cgroup_id(tcgrp);
+		cgrp->ancestors[tcgrp->level] = tcgrp;
 
 		if (tcgrp != cgrp) {
 			tcgrp->nr_descendants++;
@@ -5648,7 +5906,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	css_clear_dir(&cgrp->self);
 	kernfs_remove(cgrp->kn);
 
-	if (parent && cgroup_is_threaded(cgrp))
+	if (cgroup_is_threaded(cgrp))
 		parent->nr_threaded_children--;
 
 	spin_lock_irq(&css_set_lock);
@@ -5711,7 +5969,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
 
 	/* Create the root cgroup state for this subsystem */
 	ss->root = &cgrp_dfl_root;
-	css = ss->css_alloc(cgroup_css(&cgrp_dfl_root.cgrp, ss));
+	css = ss->css_alloc(NULL);
 	/* We don't handle early failures gracefully */
 	BUG_ON(IS_ERR(css));
 	init_and_link_css(css, ss, &cgrp_dfl_root.cgrp);
@@ -5801,16 +6059,11 @@ int __init cgroup_init(void)
 
 	BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16);
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files));
+	BUG_ON(cgroup_init_cftypes(NULL, cgroup_psi_files));
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files));
 
 	cgroup_rstat_boot();
 
-	/*
-	 * The latency of the synchronize_rcu() is too high for cgroups,
-	 * avoid it at the cost of forcing all readers into the slow path.
-	 */
-	rcu_sync_enter_start(&cgroup_threadgroup_rwsem.rss);
-
 	get_user_ns(init_cgroup_ns.user_ns);
 
 	mutex_lock(&cgroup_mutex);
@@ -5927,16 +6180,22 @@ void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen)
 /*
  * cgroup_get_from_id : get the cgroup associated with cgroup id
  * @id: cgroup id
- * On success return the cgrp, on failure return NULL
+ * On success return the cgrp or ERR_PTR on failure
+ * Only cgroups within current task's cgroup NS are valid.
  */
 struct cgroup *cgroup_get_from_id(u64 id)
 {
 	struct kernfs_node *kn;
-	struct cgroup *cgrp = NULL;
+	struct cgroup *cgrp, *root_cgrp;
 
 	kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id);
 	if (!kn)
-		goto out;
+		return ERR_PTR(-ENOENT);
+
+	if (kernfs_type(kn) != KERNFS_DIR) {
+		kernfs_put(kn);
+		return ERR_PTR(-ENOENT);
+	}
 
 	rcu_read_lock();
 
@@ -5945,9 +6204,17 @@ struct cgroup *cgroup_get_from_id(u64 id)
 		cgrp = NULL;
 
 	rcu_read_unlock();
-
 	kernfs_put(kn);
-out:
+
+	if (!cgrp)
+		return ERR_PTR(-ENOENT);
+
+	root_cgrp = current_cgns_cgroup_dfl();
+	if (!cgroup_is_descendant(cgrp, root_cgrp)) {
+		cgroup_put(cgrp);
+		return ERR_PTR(-ENOENT);
+	}
+
 	return cgrp;
 }
 EXPORT_SYMBOL_GPL(cgroup_get_from_id);
@@ -5977,7 +6244,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 		struct cgroup *cgrp;
 		int ssid, count = 0;
 
-		if (root == &cgrp_dfl_root && !cgrp_dfl_visible)
+		if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible))
 			continue;
 
 		seq_printf(m, "%d:", root->hierarchy_id);
@@ -6043,16 +6310,37 @@ void cgroup_fork(struct task_struct *child)
 	INIT_LIST_HEAD(&child->cg_list);
 }
 
-static struct cgroup *cgroup_get_from_file(struct file *f)
+/**
+ * cgroup_v1v2_get_from_file - get a cgroup pointer from a file pointer
+ * @f: file corresponding to cgroup_dir
+ *
+ * Find the cgroup from a file pointer associated with a cgroup directory.
+ * Returns a pointer to the cgroup on success. ERR_PTR is returned if the
+ * cgroup cannot be found.
+ */
+static struct cgroup *cgroup_v1v2_get_from_file(struct file *f)
 {
 	struct cgroup_subsys_state *css;
-	struct cgroup *cgrp;
 
 	css = css_tryget_online_from_dir(f->f_path.dentry, NULL);
 	if (IS_ERR(css))
 		return ERR_CAST(css);
 
-	cgrp = css->cgroup;
+	return css->cgroup;
+}
+
+/**
+ * cgroup_get_from_file - same as cgroup_v1v2_get_from_file, but only supports
+ * cgroup2.
+ * @f: file corresponding to cgroup2_dir
+ */
+static struct cgroup *cgroup_get_from_file(struct file *f)
+{
+	struct cgroup *cgrp = cgroup_v1v2_get_from_file(f);
+
+	if (IS_ERR(cgrp))
+		return ERR_CAST(cgrp);
+
 	if (!cgroup_on_dfl(cgrp)) {
 		cgroup_put(cgrp);
 		return ERR_PTR(-EBADF);
@@ -6129,8 +6417,23 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 	if (ret)
 		goto err;
 
+	/*
+	 * Spawning a task directly into a cgroup works by passing a file
+	 * descriptor to the target cgroup directory. This can even be an O_PATH
+	 * file descriptor. But it can never be a cgroup.procs file descriptor.
+	 * This was done on purpose so spawning into a cgroup could be
+	 * conceptualized as an atomic
+	 *
+	 *   fd = openat(dfd_cgroup, "cgroup.procs", ...);
+	 *   write(fd, <child-pid>, ...);
+	 *
+	 * sequence, i.e. it's a shorthand for the caller opening and writing
+	 * cgroup.procs of the cgroup indicated by @dfd_cgroup. This allows us
+	 * to always use the caller's credentials.
+	 */
 	ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb,
-					!(kargs->flags & CLONE_THREAD));
+					!(kargs->flags & CLONE_THREAD),
+					current->nsproxy->cgroup_ns);
 	if (ret)
 		goto err;
 
@@ -6191,6 +6494,7 @@ static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs)
 /**
  * cgroup_can_fork - called on a new task before the process is exposed
  * @child: the child process
+ * @kargs: the arguments passed to create the child process
  *
  * This prepares a new css_set for the child process which the child will
  * be attached to in cgroup_post_fork().
@@ -6253,6 +6557,7 @@ void cgroup_cancel_fork(struct task_struct *child,
 /**
  * cgroup_post_fork - finalize cgroup setup for the child process
  * @child: the child process
+ * @kargs: the arguments passed to create the child process
  *
  * Attach the child process to its css_set calling the subsystem fork()
  * callbacks.
@@ -6507,8 +6812,10 @@ struct cgroup *cgroup_get_from_path(const char *path)
 {
 	struct kernfs_node *kn;
 	struct cgroup *cgrp = ERR_PTR(-ENOENT);
+	struct cgroup *root_cgrp;
 
-	kn = kernfs_walk_and_get(cgrp_dfl_root.cgrp.kn, path);
+	root_cgrp = current_cgns_cgroup_dfl();
+	kn = kernfs_walk_and_get(root_cgrp->kn, path);
 	if (!kn)
 		goto out;
 
@@ -6533,15 +6840,15 @@ out:
 EXPORT_SYMBOL_GPL(cgroup_get_from_path);
 
 /**
- * cgroup_get_from_fd - get a cgroup pointer from a fd
- * @fd: fd obtained by open(cgroup2_dir)
+ * cgroup_v1v2_get_from_fd - get a cgroup pointer from a fd
+ * @fd: fd obtained by open(cgroup_dir)
  *
  * Find the cgroup from a fd which should be obtained
  * by opening a cgroup directory.  Returns a pointer to the
  * cgroup on success. ERR_PTR is returned if the cgroup
  * cannot be found.
  */
-struct cgroup *cgroup_get_from_fd(int fd)
+struct cgroup *cgroup_v1v2_get_from_fd(int fd)
 {
 	struct cgroup *cgrp;
 	struct file *f;
@@ -6550,10 +6857,29 @@ struct cgroup *cgroup_get_from_fd(int fd)
 	if (!f)
 		return ERR_PTR(-EBADF);
 
-	cgrp = cgroup_get_from_file(f);
+	cgrp = cgroup_v1v2_get_from_file(f);
 	fput(f);
 	return cgrp;
 }
+
+/**
+ * cgroup_get_from_fd - same as cgroup_v1v2_get_from_fd, but only supports
+ * cgroup2.
+ * @fd: fd obtained by open(cgroup2_dir)
+ */
+struct cgroup *cgroup_get_from_fd(int fd)
+{
+	struct cgroup *cgrp = cgroup_v1v2_get_from_fd(fd);
+
+	if (IS_ERR(cgrp))
+		return ERR_CAST(cgrp);
+
+	if (!cgroup_on_dfl(cgrp)) {
+		cgroup_put(cgrp);
+		return ERR_PTR(-EBADF);
+	}
+	return cgrp;
+}
 EXPORT_SYMBOL_GPL(cgroup_get_from_fd);
 
 static u64 power_of_ten(int power)
@@ -6666,9 +6992,6 @@ static ssize_t show_delegatable_files(struct cftype *files, char *buf,
 		if (!(cft->flags & CFTYPE_NS_DELEGATABLE))
 			continue;
 
-		if ((cft->flags & CFTYPE_PRESSURE) && !cgroup_psi_enabled())
-			continue;
-
 		if (prefix)
 			ret += snprintf(buf + ret, size - ret, "%s.", prefix);
 
@@ -6688,8 +7011,11 @@ static ssize_t delegate_show(struct kobject *kobj, struct kobj_attribute *attr,
 	int ssid;
 	ssize_t ret = 0;
 
-	ret = show_delegatable_files(cgroup_base_files, buf, PAGE_SIZE - ret,
-				     NULL);
+	ret = show_delegatable_files(cgroup_base_files, buf + ret,
+				     PAGE_SIZE - ret, NULL);
+	if (cgroup_psi_enabled())
+		ret += show_delegatable_files(cgroup_psi_files, buf + ret,
+					      PAGE_SIZE - ret, NULL);
 
 	for_each_subsys(ss, ssid)
 		ret += show_delegatable_files(ss->dfl_cftypes, buf + ret,
@@ -6705,6 +7031,7 @@ static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr,
 {
 	return snprintf(buf, PAGE_SIZE,
 			"nsdelegate\n"
+			"favordynmods\n"
 			"memory_localevents\n"
 			"memory_recursiveprot\n");
 }