diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index bd98ea3175ec..d9d3cc7df348 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -435,6 +435,15 @@ both cgroups.
 Controlling Controllers
 -----------------------
 
+Availablity
+~~~~~~~~~~~
+
+A controller is available in a cgroup when it is supported by the kernel (i.e.,
+compiled in, not disabled and not attached to a v1 hierarchy) and listed in the
+"cgroup.controllers" file. Availability means the controller's interface files
+are exposed in the cgroup’s directory, allowing the distribution of the target
+resource to be observed or controlled within that cgroup.
+
 Enabling and Disabling
 ~~~~~~~~~~~~~~~~~~~~~~
 
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 2e369a6a5641..8981ae1c9355 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -633,6 +633,14 @@
 			named mounts. Specifying both "all" and "named" disables
 			all v1 hierarchies.
 
+	cgroup_v1_proc=	[KNL] Show also missing controllers in /proc/cgroups
+			Format: { "true" | "false" }
+			/proc/cgroups lists only v1 controllers by default.
+			This compatibility option enables listing also v2
+			controllers (whose v1 code is not compiled!), so that
+			semi-legacy software can check this file to decide
+			about usage of v2 (sic) controllers.
+
 	cgroup_favordynmods= [KNL] Enable or Disable favordynmods.
 			Format: { "true" | "false" }
 			Defaults to the value of CONFIG_CGROUP_FAVOR_DYNMODS.
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index e61687d5e496..6b93a64115fe 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -375,15 +375,12 @@ struct css_rstat_cpu {
 	 * Child cgroups with stat updates on this cpu since the last read
 	 * are linked on the parent's ->updated_children through
 	 * ->updated_next. updated_children is terminated by its container css.
-	 *
-	 * In addition to being more compact, singly-linked list pointing to
-	 * the css makes it unnecessary for each per-cpu struct to point back
-	 * to the associated css.
-	 *
-	 * Protected by per-cpu css->ss->rstat_ss_cpu_lock.
 	 */
 	struct cgroup_subsys_state *updated_children;
 	struct cgroup_subsys_state *updated_next;	/* NULL if not on the list */
+
+	struct llist_node lnode;		/* lockless list for update */
+	struct cgroup_subsys_state *owner;	/* back pointer */
 };
 
 /*
@@ -821,7 +818,7 @@ struct cgroup_subsys {
 	unsigned int depends_on;
 
 	spinlock_t rstat_ss_lock;
-	raw_spinlock_t __percpu *rstat_ss_cpu_lock;
+	struct llist_head __percpu *lhead; /* lockless update list head */
 };
 
 extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
@@ -898,14 +895,12 @@ static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd)
 #endif
 }
 
+#ifdef CONFIG_CGROUP_NET_CLASSID
 static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd)
 {
-#ifdef CONFIG_CGROUP_NET_CLASSID
 	return READ_ONCE(skcd->classid);
-#else
-	return 0;
-#endif
 }
+#endif
 
 static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd,
 					   u16 prioidx)
@@ -915,13 +910,13 @@ static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd,
 #endif
 }
 
+#ifdef CONFIG_CGROUP_NET_CLASSID
 static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd,
 					   u32 classid)
 {
-#ifdef CONFIG_CGROUP_NET_CLASSID
 	WRITE_ONCE(skcd->classid, classid);
-#endif
 }
+#endif
 
 #else	/* CONFIG_SOCK_CGROUP_DATA */
 
diff --git a/include/linux/llist.h b/include/linux/llist.h
index 27b17f64bcee..607b2360c938 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -83,7 +83,7 @@ static inline void init_llist_head(struct llist_head *list)
  */
 static inline void init_llist_node(struct llist_node *node)
 {
-	node->next = node;
+	WRITE_ONCE(node->next, node);
 }
 
 /**
@@ -97,7 +97,7 @@ static inline void init_llist_node(struct llist_node *node)
  */
 static inline bool llist_on_list(const struct llist_node *node)
 {
-	return node->next != node;
+	return READ_ONCE(node->next) != node;
 }
 
 /**
@@ -220,7 +220,7 @@ static inline bool llist_empty(const struct llist_head *head)
 
 static inline struct llist_node *llist_next(struct llist_node *node)
 {
-	return node->next;
+	return READ_ONCE(node->next);
 }
 
 /**
diff --git a/include/trace/events/cgroup.h b/include/trace/events/cgroup.h
index 7d332387be6c..ba9229af9a34 100644
--- a/include/trace/events/cgroup.h
+++ b/include/trace/events/cgroup.h
@@ -257,53 +257,6 @@ DEFINE_EVENT(cgroup_rstat, cgroup_rstat_unlock,
 	TP_ARGS(cgrp, cpu, contended)
 );
 
-/*
- * Related to per CPU locks:
- * global rstat_base_cpu_lock for base stats
- * cgroup_subsys::rstat_ss_cpu_lock for subsystem stats
- */
-DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended,
-
-	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
-
-	TP_ARGS(cgrp, cpu, contended)
-);
-
-DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended_fastpath,
-
-	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
-
-	TP_ARGS(cgrp, cpu, contended)
-);
-
-DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked,
-
-	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
-
-	TP_ARGS(cgrp, cpu, contended)
-);
-
-DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked_fastpath,
-
-	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
-
-	TP_ARGS(cgrp, cpu, contended)
-);
-
-DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock,
-
-	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
-
-	TP_ARGS(cgrp, cpu, contended)
-);
-
-DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock_fastpath,
-
-	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
-
-	TP_ARGS(cgrp, cpu, contended)
-);
-
 #endif /* _TRACE_CGROUP_H */
 
 /* This part must be outside protection */
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index fa24c032ed6f..2a4a387f867a 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -32,6 +32,9 @@ static u16 cgroup_no_v1_mask;
 /* disable named v1 mounts */
 static bool cgroup_no_v1_named;
 
+/* Show unavailable controllers in /proc/cgroups */
+static bool proc_show_all;
+
 /*
  * pidlist destructions need to be flushed on cgroup destruction.  Use a
  * separate workqueue as flush domain.
@@ -683,10 +686,11 @@ int proc_cgroupstats_show(struct seq_file *m, void *v)
 	 */
 
 	for_each_subsys(ss, i) {
-		if (cgroup1_subsys_absent(ss))
-			continue;
 		cgrp_v1_visible |= ss->root != &cgrp_dfl_root;
 
+		if (!proc_show_all && cgroup1_subsys_absent(ss))
+			continue;
+
 		seq_printf(m, "%s\t%d\t%d\t%d\n",
 			   ss->legacy_name, ss->root->hierarchy_id,
 			   atomic_read(&ss->root->nr_cgrps),
@@ -1359,3 +1363,9 @@ static int __init cgroup_no_v1(char *str)
 	return 1;
 }
 __setup("cgroup_no_v1=", cgroup_no_v1);
+
+static int __init cgroup_v1_proc(char *str)
+{
+	return (kstrtobool(str, &proc_show_all) == 0);
+}
+__setup("cgroup_v1_proc=", cgroup_v1_proc);
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index cbeaa499a96a..981e2f77ad4e 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -10,7 +10,7 @@
 #include <trace/events/cgroup.h>
 
 static DEFINE_SPINLOCK(rstat_base_lock);
-static DEFINE_PER_CPU(raw_spinlock_t, rstat_base_cpu_lock);
+static DEFINE_PER_CPU(struct llist_head, rstat_backlog_list);
 
 static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu);
 
@@ -45,84 +45,11 @@ static spinlock_t *ss_rstat_lock(struct cgroup_subsys *ss)
 	return &rstat_base_lock;
 }
 
-static raw_spinlock_t *ss_rstat_cpu_lock(struct cgroup_subsys *ss, int cpu)
+static inline struct llist_head *ss_lhead_cpu(struct cgroup_subsys *ss, int cpu)
 {
-	if (ss) {
-		/*
-		 * Depending on config, the subsystem per-cpu lock type may be an
-		 * empty struct. In enviromnents where this is the case, allocation
-		 * of this field is not performed in ss_rstat_init(). Avoid a
-		 * cpu-based offset relative to NULL by returning early. When the
-		 * lock type is zero in size, the corresponding lock functions are
-		 * no-ops so passing them NULL is acceptable.
-		 */
-		if (sizeof(*ss->rstat_ss_cpu_lock) == 0)
-			return NULL;
-
-		return per_cpu_ptr(ss->rstat_ss_cpu_lock, cpu);
-	}
-
-	return per_cpu_ptr(&rstat_base_cpu_lock, cpu);
-}
-
-/*
- * Helper functions for rstat per CPU locks.
- *
- * This makes it easier to diagnose locking issues and contention in
- * production environments. The parameter @fast_path determine the
- * tracepoints being added, allowing us to diagnose "flush" related
- * operations without handling high-frequency fast-path "update" events.
- */
-static __always_inline
-unsigned long _css_rstat_cpu_lock(struct cgroup_subsys_state *css, int cpu,
-		const bool fast_path)
-{
-	struct cgroup *cgrp = css->cgroup;
-	raw_spinlock_t *cpu_lock;
-	unsigned long flags;
-	bool contended;
-
-	/*
-	 * The _irqsave() is needed because the locks used for flushing are
-	 * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring this lock
-	 * with the _irq() suffix only disables interrupts on a non-PREEMPT_RT
-	 * kernel. The raw_spinlock_t below disables interrupts on both
-	 * configurations. The _irqsave() ensures that interrupts are always
-	 * disabled and later restored.
-	 */
-	cpu_lock = ss_rstat_cpu_lock(css->ss, cpu);
-	contended = !raw_spin_trylock_irqsave(cpu_lock, flags);
-	if (contended) {
-		if (fast_path)
-			trace_cgroup_rstat_cpu_lock_contended_fastpath(cgrp, cpu, contended);
-		else
-			trace_cgroup_rstat_cpu_lock_contended(cgrp, cpu, contended);
-
-		raw_spin_lock_irqsave(cpu_lock, flags);
-	}
-
-	if (fast_path)
-		trace_cgroup_rstat_cpu_locked_fastpath(cgrp, cpu, contended);
-	else
-		trace_cgroup_rstat_cpu_locked(cgrp, cpu, contended);
-
-	return flags;
-}
-
-static __always_inline
-void _css_rstat_cpu_unlock(struct cgroup_subsys_state *css, int cpu,
-		unsigned long flags, const bool fast_path)
-{
-	struct cgroup *cgrp = css->cgroup;
-	raw_spinlock_t *cpu_lock;
-
-	if (fast_path)
-		trace_cgroup_rstat_cpu_unlock_fastpath(cgrp, cpu, false);
-	else
-		trace_cgroup_rstat_cpu_unlock(cgrp, cpu, false);
-
-	cpu_lock = ss_rstat_cpu_lock(css->ss, cpu);
-	raw_spin_unlock_irqrestore(cpu_lock, flags);
+	if (ss)
+		return per_cpu_ptr(ss->lhead, cpu);
+	return per_cpu_ptr(&rstat_backlog_list, cpu);
 }
 
 /**
@@ -130,13 +57,22 @@ void _css_rstat_cpu_unlock(struct cgroup_subsys_state *css, int cpu,
  * @css: target cgroup subsystem state
  * @cpu: cpu on which rstat_cpu was updated
  *
- * @css's rstat_cpu on @cpu was updated. Put it on the parent's matching
- * rstat_cpu->updated_children list. See the comment on top of
- * css_rstat_cpu definition for details.
+ * Atomically inserts the css in the ss's llist for the given cpu. This is
+ * reentrant safe i.e. safe against softirq, hardirq and nmi. The ss's llist
+ * will be processed at the flush time to create the update tree.
+ *
+ * NOTE: if the user needs the guarantee that the updater either add itself in
+ * the lockless list or the concurrent flusher flushes its updated stats, a
+ * memory barrier is needed before the call to css_rstat_updated() i.e. a
+ * barrier after updating the per-cpu stats and before calling
+ * css_rstat_updated().
  */
 __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu)
 {
-	unsigned long flags;
+	struct llist_head *lhead;
+	struct css_rstat_cpu *rstatc;
+	struct css_rstat_cpu __percpu *rstatc_pcpu;
+	struct llist_node *self;
 
 	/*
 	 * Since bpf programs can call this function, prevent access to
@@ -145,19 +81,49 @@ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu)
 	if (!css_uses_rstat(css))
 		return;
 
+	lockdep_assert_preemption_disabled();
+
 	/*
-	 * Speculative already-on-list test. This may race leading to
-	 * temporary inaccuracies, which is fine.
-	 *
-	 * Because @parent's updated_children is terminated with @parent
-	 * instead of NULL, we can tell whether @css is on the list by
-	 * testing the next pointer for NULL.
+	 * For archs withnot nmi safe cmpxchg or percpu ops support, ignore
+	 * the requests from nmi context.
 	 */
-	if (data_race(css_rstat_cpu(css, cpu)->updated_next))
+	if ((!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) ||
+	     !IS_ENABLED(CONFIG_ARCH_HAS_NMI_SAFE_THIS_CPU_OPS)) && in_nmi())
 		return;
 
-	flags = _css_rstat_cpu_lock(css, cpu, true);
+	rstatc = css_rstat_cpu(css, cpu);
+	/*
+	 * If already on list return. This check is racy and smp_mb() is needed
+	 * to pair it with the smp_mb() in css_process_update_tree() if the
+	 * guarantee that the updated stats are visible to concurrent flusher is
+	 * needed.
+	 */
+	if (llist_on_list(&rstatc->lnode))
+		return;
 
+	/*
+	 * This function can be renentered by irqs and nmis for the same cgroup
+	 * and may try to insert the same per-cpu lnode into the llist. Note
+	 * that llist_add() does not protect against such scenarios.
+	 *
+	 * To protect against such stacked contexts of irqs/nmis, we use the
+	 * fact that lnode points to itself when not on a list and then use
+	 * this_cpu_cmpxchg() to atomically set to NULL to select the winner
+	 * which will call llist_add(). The losers can assume the insertion is
+	 * successful and the winner will eventually add the per-cpu lnode to
+	 * the llist.
+	 */
+	self = &rstatc->lnode;
+	rstatc_pcpu = css->rstat_cpu;
+	if (this_cpu_cmpxchg(rstatc_pcpu->lnode.next, self, NULL) != self)
+		return;
+
+	lhead = ss_lhead_cpu(css->ss, cpu);
+	llist_add(&rstatc->lnode, lhead);
+}
+
+static void __css_process_update_tree(struct cgroup_subsys_state *css, int cpu)
+{
 	/* put @css and all ancestors on the corresponding updated lists */
 	while (true) {
 		struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu);
@@ -183,8 +149,34 @@ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu)
 
 		css = parent;
 	}
+}
 
-	_css_rstat_cpu_unlock(css, cpu, flags, true);
+static void css_process_update_tree(struct cgroup_subsys *ss, int cpu)
+{
+	struct llist_head *lhead = ss_lhead_cpu(ss, cpu);
+	struct llist_node *lnode;
+
+	while ((lnode = llist_del_first_init(lhead))) {
+		struct css_rstat_cpu *rstatc;
+
+		/*
+		 * smp_mb() is needed here (more specifically in between
+		 * init_llist_node() and per-cpu stats flushing) if the
+		 * guarantee is required by a rstat user where etiher the
+		 * updater should add itself on the lockless list or the
+		 * flusher flush the stats updated by the updater who have
+		 * observed that they are already on the list. The
+		 * corresponding barrier pair for this one should be before
+		 * css_rstat_updated() by the user.
+		 *
+		 * For now, there aren't any such user, so not adding the
+		 * barrier here but if such a use-case arise, please add
+		 * smp_mb() here.
+		 */
+
+		rstatc = container_of(lnode, struct css_rstat_cpu, lnode);
+		__css_process_update_tree(rstatc->owner, cpu);
+	}
 }
 
 /**
@@ -288,13 +280,12 @@ static struct cgroup_subsys_state *css_rstat_updated_list(
 {
 	struct css_rstat_cpu *rstatc = css_rstat_cpu(root, cpu);
 	struct cgroup_subsys_state *head = NULL, *parent, *child;
-	unsigned long flags;
 
-	flags = _css_rstat_cpu_lock(root, cpu, false);
+	css_process_update_tree(root->ss, cpu);
 
 	/* Return NULL if this subtree is not on-list */
 	if (!rstatc->updated_next)
-		goto unlock_ret;
+		return NULL;
 
 	/*
 	 * Unlink @root from its parent. As the updated_children list is
@@ -326,8 +317,7 @@ static struct cgroup_subsys_state *css_rstat_updated_list(
 	rstatc->updated_children = root;
 	if (child != root)
 		head = css_rstat_push_children(head, child, cpu);
-unlock_ret:
-	_css_rstat_cpu_unlock(root, cpu, flags, false);
+
 	return head;
 }
 
@@ -468,7 +458,8 @@ int css_rstat_init(struct cgroup_subsys_state *css)
 	for_each_possible_cpu(cpu) {
 		struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu);
 
-		rstatc->updated_children = css;
+		rstatc->owner = rstatc->updated_children = css;
+		init_llist_node(&rstatc->lnode);
 
 		if (is_self) {
 			struct cgroup_rstat_base_cpu *rstatbc;
@@ -522,19 +513,15 @@ int __init ss_rstat_init(struct cgroup_subsys *ss)
 {
 	int cpu;
 
-	/*
-	 * Depending on config, the subsystem per-cpu lock type may be an empty
-	 * struct. Avoid allocating a size of zero in this case.
-	 */
-	if (ss && sizeof(*ss->rstat_ss_cpu_lock)) {
-		ss->rstat_ss_cpu_lock = alloc_percpu(raw_spinlock_t);
-		if (!ss->rstat_ss_cpu_lock)
+	if (ss) {
+		ss->lhead = alloc_percpu(struct llist_head);
+		if (!ss->lhead)
 			return -ENOMEM;
 	}
 
 	spin_lock_init(ss_rstat_lock(ss));
 	for_each_possible_cpu(cpu)
-		raw_spin_lock_init(ss_rstat_cpu_lock(ss, cpu));
+		init_llist_head(ss_lhead_cpu(ss, cpu));
 
 	return 0;
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index de7d737fe011..8dd7fbed5a94 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -570,9 +570,7 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val,
 	if (!val)
 		return;
 
-	/* TODO: add to cgroup update tree once it is nmi-safe. */
-	if (!in_nmi())
-		css_rstat_updated(&memcg->css, cpu);
+	css_rstat_updated(&memcg->css, cpu);
 	statc_pcpu = memcg->vmstats_percpu;
 	for (; statc_pcpu; statc_pcpu = statc->parent_pcpu) {
 		statc = this_cpu_ptr(statc_pcpu);
@@ -2527,7 +2525,8 @@ static inline void account_slab_nmi_safe(struct mem_cgroup *memcg,
 	} else {
 		struct mem_cgroup_per_node *pn = memcg->nodeinfo[pgdat->node_id];
 
-		/* TODO: add to cgroup update tree once it is nmi-safe. */
+		/* preemption is disabled in_nmi(). */
+		css_rstat_updated(&memcg->css, smp_processor_id());
 		if (idx == NR_SLAB_RECLAIMABLE_B)
 			atomic_add(nr, &pn->slab_reclaimable);
 		else
@@ -2750,7 +2749,8 @@ static inline void account_kmem_nmi_safe(struct mem_cgroup *memcg, int val)
 	if (likely(!in_nmi())) {
 		mod_memcg_state(memcg, MEMCG_KMEM, val);
 	} else {
-		/* TODO: add to cgroup update tree once it is nmi-safe. */
+		/* preemption is disabled in_nmi(). */
+		css_rstat_updated(&memcg->css, smp_processor_id());
 		atomic_add(val, &memcg->kmem_stat);
 	}
 }
diff --git a/tools/testing/selftests/cgroup/lib/cgroup_util.c b/tools/testing/selftests/cgroup/lib/cgroup_util.c
index 8832f3d1cb61..0e89fcff4d05 100644
--- a/tools/testing/selftests/cgroup/lib/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/lib/cgroup_util.c
@@ -19,6 +19,8 @@
 #include "cgroup_util.h"
 #include "../../clone3/clone3_selftests.h"
 
+bool cg_test_v1_named;
+
 /* Returns read len on success, or -errno on failure. */
 ssize_t read_text(const char *path, char *buf, size_t max_len)
 {
@@ -361,7 +363,7 @@ int cg_enter_current(const char *cgroup)
 
 int cg_enter_current_thread(const char *cgroup)
 {
-	return cg_write(cgroup, "cgroup.threads", "0");
+	return cg_write(cgroup, CG_THREADS_FILE, "0");
 }
 
 int cg_run(const char *cgroup,
diff --git a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
index adb2bc193183..c69cab66254b 100644
--- a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
@@ -13,6 +13,10 @@
 
 #define TEST_UID	65534 /* usually nobody, any !root is fine */
 
+#define CG_THREADS_FILE (!cg_test_v1_named ? "cgroup.threads" : "tasks")
+#define CG_NAMED_NAME "selftest"
+#define CG_PATH_FORMAT (!cg_test_v1_named ? "0::%s" : (":name=" CG_NAMED_NAME ":%s"))
+
 /*
  * Checks if two given values differ by less than err% of their sum.
  */
@@ -65,3 +69,4 @@ extern int dirfd_open_opath(const char *dir);
 extern int cg_prepare_for_wait(const char *cgroup);
 extern int memcg_prepare_for_wait(const char *cgroup);
 extern int cg_wait_for(int fd);
+extern bool cg_test_v1_named;
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index a5672a91d273..a360e2eb2eef 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -5,6 +5,8 @@
 #include <linux/sched.h>
 #include <sys/types.h>
 #include <sys/mman.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
 #include <sys/wait.h>
 #include <unistd.h>
 #include <fcntl.h>
@@ -19,6 +21,9 @@
 #include "cgroup_util.h"
 
 static bool nsdelegate;
+#ifndef CLONE_NEWCGROUP
+#define CLONE_NEWCGROUP 0
+#endif
 
 static int touch_anon(char *buf, size_t size)
 {
@@ -148,6 +153,9 @@ static int test_cgcore_populated(const char *root)
 	int cgroup_fd = -EBADF;
 	pid_t pid;
 
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
 	cg_test_a = cg_name(root, "cg_test_a");
 	cg_test_b = cg_name(root, "cg_test_a/cg_test_b");
 	cg_test_c = cg_name(root, "cg_test_a/cg_test_b/cg_test_c");
@@ -277,6 +285,9 @@ static int test_cgcore_invalid_domain(const char *root)
 	int ret = KSFT_FAIL;
 	char *grandparent = NULL, *parent = NULL, *child = NULL;
 
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
 	grandparent = cg_name(root, "cg_test_grandparent");
 	parent = cg_name(root, "cg_test_grandparent/cg_test_parent");
 	child = cg_name(root, "cg_test_grandparent/cg_test_parent/cg_test_child");
@@ -339,6 +350,9 @@ static int test_cgcore_parent_becomes_threaded(const char *root)
 	int ret = KSFT_FAIL;
 	char *parent = NULL, *child = NULL;
 
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
 	parent = cg_name(root, "cg_test_parent");
 	child = cg_name(root, "cg_test_parent/cg_test_child");
 	if (!parent || !child)
@@ -378,7 +392,8 @@ static int test_cgcore_no_internal_process_constraint_on_threads(const char *roo
 	int ret = KSFT_FAIL;
 	char *parent = NULL, *child = NULL;
 
-	if (cg_read_strstr(root, "cgroup.controllers", "cpu") ||
+	if (cg_test_v1_named ||
+	    cg_read_strstr(root, "cgroup.controllers", "cpu") ||
 	    cg_write(root, "cgroup.subtree_control", "+cpu")) {
 		ret = KSFT_SKIP;
 		goto cleanup;
@@ -430,6 +445,9 @@ static int test_cgcore_top_down_constraint_enable(const char *root)
 	int ret = KSFT_FAIL;
 	char *parent = NULL, *child = NULL;
 
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
 	parent = cg_name(root, "cg_test_parent");
 	child = cg_name(root, "cg_test_parent/cg_test_child");
 	if (!parent || !child)
@@ -465,6 +483,9 @@ static int test_cgcore_top_down_constraint_disable(const char *root)
 	int ret = KSFT_FAIL;
 	char *parent = NULL, *child = NULL;
 
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
 	parent = cg_name(root, "cg_test_parent");
 	child = cg_name(root, "cg_test_parent/cg_test_child");
 	if (!parent || !child)
@@ -506,6 +527,9 @@ static int test_cgcore_internal_process_constraint(const char *root)
 	int ret = KSFT_FAIL;
 	char *parent = NULL, *child = NULL;
 
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
 	parent = cg_name(root, "cg_test_parent");
 	child = cg_name(root, "cg_test_parent/cg_test_child");
 	if (!parent || !child)
@@ -573,7 +597,7 @@ static int test_cgcore_proc_migration(const char *root)
 	}
 
 	cg_enter_current(dst);
-	if (cg_read_lc(dst, "cgroup.threads") != n_threads + 1)
+	if (cg_read_lc(dst, CG_THREADS_FILE) != n_threads + 1)
 		goto cleanup;
 
 	ret = KSFT_PASS;
@@ -605,7 +629,7 @@ static void *migrating_thread_fn(void *arg)
 	char lines[3][PATH_MAX];
 
 	for (g = 1; g < 3; ++g)
-		snprintf(lines[g], sizeof(lines[g]), "0::%s", grps[g] + strlen(grps[0]));
+		snprintf(lines[g], sizeof(lines[g]), CG_PATH_FORMAT, grps[g] + strlen(grps[0]));
 
 	for (i = 0; i < n_iterations; ++i) {
 		cg_enter_current_thread(grps[(i % 2) + 1]);
@@ -642,10 +666,12 @@ static int test_cgcore_thread_migration(const char *root)
 	if (cg_create(grps[2]))
 		goto cleanup;
 
-	if (cg_write(grps[1], "cgroup.type", "threaded"))
-		goto cleanup;
-	if (cg_write(grps[2], "cgroup.type", "threaded"))
-		goto cleanup;
+	if (!cg_test_v1_named) {
+		if (cg_write(grps[1], "cgroup.type", "threaded"))
+			goto cleanup;
+		if (cg_write(grps[2], "cgroup.type", "threaded"))
+			goto cleanup;
+	}
 
 	if (cg_enter_current(grps[1]))
 		goto cleanup;
@@ -659,7 +685,7 @@ static int test_cgcore_thread_migration(const char *root)
 	if (retval)
 		goto cleanup;
 
-	snprintf(line, sizeof(line), "0::%s", grps[1] + strlen(grps[0]));
+	snprintf(line, sizeof(line), CG_PATH_FORMAT, grps[1] + strlen(grps[0]));
 	if (proc_read_strstr(0, 1, "cgroup", line))
 		goto cleanup;
 
@@ -842,6 +868,38 @@ cleanup:
 	return ret;
 }
 
+static int setup_named_v1_root(char *root, size_t len, const char *name)
+{
+	char options[PATH_MAX];
+	int r;
+
+	r = snprintf(root, len, "/mnt/cg_selftest");
+	if (r < 0)
+		return r;
+
+	r = snprintf(options, sizeof(options), "none,name=%s", name);
+	if (r < 0)
+		return r;
+
+	r = mkdir(root, 0755);
+	if (r < 0 && errno != EEXIST)
+		return r;
+
+	r = mount("none", root, "cgroup", 0, options);
+	if (r < 0)
+		return r;
+
+	return 0;
+}
+
+static void cleanup_named_v1_root(char *root)
+{
+	if (!cg_test_v1_named)
+		return;
+	umount(root);
+	rmdir(root);
+}
+
 #define T(x) { x, #x }
 struct corecg_test {
 	int (*fn)(const char *root);
@@ -867,13 +925,18 @@ int main(int argc, char *argv[])
 	char root[PATH_MAX];
 	int i, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root), &nsdelegate))
-		ksft_exit_skip("cgroup v2 isn't mounted\n");
+	if (cg_find_unified_root(root, sizeof(root), &nsdelegate)) {
+		if (setup_named_v1_root(root, sizeof(root), CG_NAMED_NAME))
+			ksft_exit_skip("cgroup v2 isn't mounted and could not setup named v1 hierarchy\n");
+		cg_test_v1_named = true;
+		goto post_v2_setup;
+	}
 
 	if (cg_read_strstr(root, "cgroup.subtree_control", "memory"))
 		if (cg_write(root, "cgroup.subtree_control", "+memory"))
 			ksft_exit_skip("Failed to set memory controller\n");
 
+post_v2_setup:
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
 		case KSFT_PASS:
@@ -889,5 +952,6 @@ int main(int argc, char *argv[])
 		}
 	}
 
+	cleanup_named_v1_root(root);
 	return ret;
 }
diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c
index a2b50af8e9ee..2a60e6c41940 100644
--- a/tools/testing/selftests/cgroup/test_cpu.c
+++ b/tools/testing/selftests/cgroup/test_cpu.c
@@ -2,6 +2,7 @@
 
 #define _GNU_SOURCE
 #include <linux/limits.h>
+#include <sys/param.h>
 #include <sys/sysinfo.h>
 #include <sys/wait.h>
 #include <errno.h>
@@ -645,10 +646,16 @@ test_cpucg_nested_weight_underprovisioned(const char *root)
 static int test_cpucg_max(const char *root)
 {
 	int ret = KSFT_FAIL;
-	long usage_usec, user_usec;
-	long usage_seconds = 1;
-	long expected_usage_usec = usage_seconds * USEC_PER_SEC;
+	long quota_usec = 1000;
+	long default_period_usec = 100000; /* cpu.max's default period */
+	long duration_seconds = 1;
+
+	long duration_usec = duration_seconds * USEC_PER_SEC;
+	long usage_usec, n_periods, remainder_usec, expected_usage_usec;
 	char *cpucg;
+	char quota_buf[32];
+
+	snprintf(quota_buf, sizeof(quota_buf), "%ld", quota_usec);
 
 	cpucg = cg_name(root, "cpucg_test");
 	if (!cpucg)
@@ -657,13 +664,13 @@ static int test_cpucg_max(const char *root)
 	if (cg_create(cpucg))
 		goto cleanup;
 
-	if (cg_write(cpucg, "cpu.max", "1000"))
+	if (cg_write(cpucg, "cpu.max", quota_buf))
 		goto cleanup;
 
 	struct cpu_hog_func_param param = {
 		.nprocs = 1,
 		.ts = {
-			.tv_sec = usage_seconds,
+			.tv_sec = duration_seconds,
 			.tv_nsec = 0,
 		},
 		.clock_type = CPU_HOG_CLOCK_WALL,
@@ -672,14 +679,19 @@ static int test_cpucg_max(const char *root)
 		goto cleanup;
 
 	usage_usec = cg_read_key_long(cpucg, "cpu.stat", "usage_usec");
-	user_usec = cg_read_key_long(cpucg, "cpu.stat", "user_usec");
-	if (user_usec <= 0)
+	if (usage_usec <= 0)
 		goto cleanup;
 
-	if (user_usec >= expected_usage_usec)
-		goto cleanup;
+	/*
+	 * The following calculation applies only since
+	 * the cpu hog is set to run as per wall-clock time
+	 */
+	n_periods = duration_usec / default_period_usec;
+	remainder_usec = duration_usec - n_periods * default_period_usec;
+	expected_usage_usec
+		= n_periods * quota_usec + MIN(remainder_usec, quota_usec);
 
-	if (values_close(usage_usec, expected_usage_usec, 95))
+	if (!values_close(usage_usec, expected_usage_usec, 10))
 		goto cleanup;
 
 	ret = KSFT_PASS;
@@ -698,10 +710,16 @@ cleanup:
 static int test_cpucg_max_nested(const char *root)
 {
 	int ret = KSFT_FAIL;
-	long usage_usec, user_usec;
-	long usage_seconds = 1;
-	long expected_usage_usec = usage_seconds * USEC_PER_SEC;
+	long quota_usec = 1000;
+	long default_period_usec = 100000; /* cpu.max's default period */
+	long duration_seconds = 1;
+
+	long duration_usec = duration_seconds * USEC_PER_SEC;
+	long usage_usec, n_periods, remainder_usec, expected_usage_usec;
 	char *parent, *child;
+	char quota_buf[32];
+
+	snprintf(quota_buf, sizeof(quota_buf), "%ld", quota_usec);
 
 	parent = cg_name(root, "cpucg_parent");
 	child = cg_name(parent, "cpucg_child");
@@ -717,13 +735,13 @@ static int test_cpucg_max_nested(const char *root)
 	if (cg_create(child))
 		goto cleanup;
 
-	if (cg_write(parent, "cpu.max", "1000"))
+	if (cg_write(parent, "cpu.max", quota_buf))
 		goto cleanup;
 
 	struct cpu_hog_func_param param = {
 		.nprocs = 1,
 		.ts = {
-			.tv_sec = usage_seconds,
+			.tv_sec = duration_seconds,
 			.tv_nsec = 0,
 		},
 		.clock_type = CPU_HOG_CLOCK_WALL,
@@ -732,14 +750,19 @@ static int test_cpucg_max_nested(const char *root)
 		goto cleanup;
 
 	usage_usec = cg_read_key_long(child, "cpu.stat", "usage_usec");
-	user_usec = cg_read_key_long(child, "cpu.stat", "user_usec");
-	if (user_usec <= 0)
+	if (usage_usec <= 0)
 		goto cleanup;
 
-	if (user_usec >= expected_usage_usec)
-		goto cleanup;
+	/*
+	 * The following calculation applies only since
+	 * the cpu hog is set to run as per wall-clock time
+	 */
+	n_periods = duration_usec / default_period_usec;
+	remainder_usec = duration_usec - n_periods * default_period_usec;
+	expected_usage_usec
+		= n_periods * quota_usec + MIN(remainder_usec, quota_usec);
 
-	if (values_close(usage_usec, expected_usage_usec, 95))
+	if (!values_close(usage_usec, expected_usage_usec, 10))
 		goto cleanup;
 
 	ret = KSFT_PASS;
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
index 96693d8772be..63b3c9aad399 100644
--- a/tools/testing/selftests/cgroup/test_kmem.c
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -308,6 +308,7 @@ static int test_kmem_dead_cgroups(const char *root)
 	char *parent;
 	long dead;
 	int i;
+	int max_time = 20;
 
 	parent = cg_name(root, "kmem_dead_cgroups_test");
 	if (!parent)
@@ -322,7 +323,7 @@ static int test_kmem_dead_cgroups(const char *root)
 	if (cg_run_in_subcgroups(parent, alloc_dcache, (void *)100, 30))
 		goto cleanup;
 
-	for (i = 0; i < 5; i++) {
+	for (i = 0; i < max_time; i++) {
 		dead = cg_read_key_long(parent, "cgroup.stat",
 					"nr_dying_descendants ");
 		if (dead == 0) {
@@ -334,6 +335,8 @@ static int test_kmem_dead_cgroups(const char *root)
 		 * let's wait a bit and repeat.
 		 */
 		sleep(1);
+		if (i > 5)
+			printf("Waiting time longer than 5s; wait: %ds (dead: %ld)\n", i, dead);
 	}
 
 cleanup:
diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c
index 40de679248b8..e1f578ca2841 100644
--- a/tools/testing/selftests/cgroup/test_zswap.c
+++ b/tools/testing/selftests/cgroup/test_zswap.c
@@ -338,7 +338,7 @@ static int test_zswap_writeback_one(const char *cgroup, bool wb)
 		return -1;
 
 	if (wb != !!zswpwb_after) {
-		ksft_print_msg("zswpwb_after is %ld while wb is %s",
+		ksft_print_msg("zswpwb_after is %ld while wb is %s\n",
 				zswpwb_after, wb ? "enabled" : "disabled");
 		return -1;
 	}