9 files changed, 384 insertions, 333 deletions
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index c964dd7ff967..95ab39e1ec8f 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -168,6 +168,7 @@ struct cgroup_mgctx {
 
 extern struct cgroup_subsys *cgroup_subsys[];
 extern struct list_head cgroup_roots;
+extern bool cgrp_dfl_visible;
 
 /* iterate across the hierarchies */
 #define for_each_root(root)						\
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index e28d5f0d20ed..fa24c032ed6f 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -673,6 +673,7 @@ struct cftype cgroup1_base_files[] = {
 int proc_cgroupstats_show(struct seq_file *m, void *v)
 {
 	struct cgroup_subsys *ss;
+	bool cgrp_v1_visible = false;
 	int i;
 
 	seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n");
@@ -684,12 +685,18 @@ 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;
+
 		seq_printf(m, "%s\t%d\t%d\t%d\n",
 			   ss->legacy_name, ss->root->hierarchy_id,
 			   atomic_read(&ss->root->nr_cgrps),
 			   cgroup_ssid_enabled(i));
 	}
 
+	if (cgrp_dfl_visible && !cgrp_v1_visible)
+		pr_info_once("/proc/cgroups lists only v1 controllers, use cgroup.controllers of root cgroup for v2 info\n");
+
+
 	return 0;
 }
 
@@ -844,7 +851,7 @@ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent
 
 	if (kernfs_type(kn) != KERNFS_DIR)
 		return -ENOTDIR;
-	if (kn->parent != new_parent)
+	if (rcu_access_pointer(kn->__parent) != new_parent)
 		return -EIO;
 
 	/*
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index afc665b7b1fe..3caf2cd86e65 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -171,7 +171,7 @@ 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 +633,22 @@ 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);
 
 	/*
@@ -1612,7 +1625,7 @@ 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 +1657,7 @@ 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 +1695,7 @@ 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));
@@ -2118,7 +2131,8 @@ 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);
@@ -4115,7 +4129,7 @@ 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;
@@ -4447,7 +4461,7 @@ 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;
 
@@ -5831,7 +5845,7 @@ 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);
@@ -5909,6 +5923,12 @@ 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;
 
 	/*
diff --git a/kernel/cgroup/cpuset-internal.h b/kernel/cgroup/cpuset-internal.h
index 976a8bc3ff60..383963e28ac6 100644
--- a/kernel/cgroup/cpuset-internal.h
+++ b/kernel/cgroup/cpuset-internal.h
@@ -33,6 +33,7 @@ enum prs_errcode {
 	PERR_CPUSEMPTY,
 	PERR_HKEEPING,
 	PERR_ACCESS,
+	PERR_REMOTE,
 };
 
 /* bits in struct cpuset flags field */
diff --git a/kernel/cgroup/cpuset-v1.c b/kernel/cgroup/cpuset-v1.c
index 25c1d7b77e2f..b69a7db67090 100644
--- a/kernel/cgroup/cpuset-v1.c
+++ b/kernel/cgroup/cpuset-v1.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include "cgroup-internal.h"
 #include "cpuset-internal.h"
 
 /*
@@ -175,6 +176,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
 
 	switch (type) {
 	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
+		pr_info_once("cpuset.%s is deprecated\n", cft->name);
 		retval = update_relax_domain_level(cs, val);
 		break;
 	default:
@@ -373,6 +375,46 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_PROC_PID_CPUSET
+/*
+ * proc_cpuset_show()
+ *  - Print tasks cpuset path into seq_file.
+ *  - Used for /proc/<pid>/cpuset.
+ */
+int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
+		     struct pid *pid, struct task_struct *tsk)
+{
+	char *buf;
+	struct cgroup_subsys_state *css;
+	int retval;
+
+	retval = -ENOMEM;
+	buf = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (!buf)
+		goto out;
+
+	rcu_read_lock();
+	spin_lock_irq(&css_set_lock);
+	css = task_css(tsk, cpuset_cgrp_id);
+	retval = cgroup_path_ns_locked(css->cgroup, buf, PATH_MAX,
+				       current->nsproxy->cgroup_ns);
+	spin_unlock_irq(&css_set_lock);
+	rcu_read_unlock();
+
+	if (retval == -E2BIG)
+		retval = -ENAMETOOLONG;
+	if (retval < 0)
+		goto out_free;
+	seq_puts(m, buf);
+	seq_putc(m, '\n');
+	retval = 0;
+out_free:
+	kfree(buf);
+out:
+	return retval;
+}
+#endif /* CONFIG_PROC_PID_CPUSET */
+
 static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft)
 {
 	struct cpuset *cs = css_cs(css);
@@ -424,24 +466,31 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
 		retval = cpuset_update_flag(CS_CPU_EXCLUSIVE, cs, val);
 		break;
 	case FILE_MEM_EXCLUSIVE:
+		pr_info_once("cpuset.%s is deprecated\n", cft->name);
 		retval = cpuset_update_flag(CS_MEM_EXCLUSIVE, cs, val);
 		break;
 	case FILE_MEM_HARDWALL:
+		pr_info_once("cpuset.%s is deprecated\n", cft->name);
 		retval = cpuset_update_flag(CS_MEM_HARDWALL, cs, val);
 		break;
 	case FILE_SCHED_LOAD_BALANCE:
+		pr_info_once("cpuset.%s is deprecated, use cpuset.cpus.partition instead\n", cft->name);
 		retval = cpuset_update_flag(CS_SCHED_LOAD_BALANCE, cs, val);
 		break;
 	case FILE_MEMORY_MIGRATE:
+		pr_info_once("cpuset.%s is deprecated\n", cft->name);
 		retval = cpuset_update_flag(CS_MEMORY_MIGRATE, cs, val);
 		break;
 	case FILE_MEMORY_PRESSURE_ENABLED:
+		pr_info_once("cpuset.%s is deprecated, use memory.pressure with CONFIG_PSI instead\n", cft->name);
 		cpuset_memory_pressure_enabled = !!val;
 		break;
 	case FILE_SPREAD_PAGE:
+		pr_info_once("cpuset.%s is deprecated\n", cft->name);
 		retval = cpuset_update_flag(CS_SPREAD_PAGE, cs, val);
 		break;
 	case FILE_SPREAD_SLAB:
+		pr_warn_once("cpuset.%s is deprecated\n", cft->name);
 		retval = cpuset_update_flag(CS_SPREAD_SLAB, cs, val);
 		break;
 	default:
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 0f910c828973..306b60430091 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -21,7 +21,6 @@
  *  License.  See the file COPYING in the main directory of the Linux
  *  distribution for more details.
  */
-#include "cgroup-internal.h"
 #include "cpuset-internal.h"
 
 #include <linux/init.h>
@@ -62,10 +61,17 @@ static const char * const perr_strings[] = {
 	[PERR_CPUSEMPTY] = "cpuset.cpus and cpuset.cpus.exclusive are empty",
 	[PERR_HKEEPING]  = "partition config conflicts with housekeeping setup",
 	[PERR_ACCESS]    = "Enable partition not permitted",
+	[PERR_REMOTE]    = "Have remote partition underneath",
 };
 
 /*
- * Exclusive CPUs distributed out to sub-partitions of top_cpuset
+ * For local partitions, update to subpartitions_cpus & isolated_cpus is done
+ * in update_parent_effective_cpumask(). For remote partitions, it is done in
+ * the remote_partition_*() and remote_cpus_update() helpers.
+ */
+/*
+ * Exclusive CPUs distributed out to local or remote sub-partitions of
+ * top_cpuset
  */
 static cpumask_var_t	subpartitions_cpus;
 
@@ -87,7 +93,6 @@ static struct list_head remote_children;
  * A flag to force sched domain rebuild at the end of an operation.
  * It can be set in
  *  - update_partition_sd_lb()
- *  - remote_partition_check()
  *  - update_cpumasks_hier()
  *  - cpuset_update_flag()
  *  - cpuset_hotplug_update_tasks()
@@ -954,10 +959,12 @@ static void dl_update_tasks_root_domain(struct cpuset *cs)
 	css_task_iter_end(&it);
 }
 
-static void dl_rebuild_rd_accounting(void)
+void dl_rebuild_rd_accounting(void)
 {
 	struct cpuset *cs = NULL;
 	struct cgroup_subsys_state *pos_css;
+	int cpu;
+	u64 cookie = ++dl_cookie;
 
 	lockdep_assert_held(&cpuset_mutex);
 	lockdep_assert_cpus_held();
@@ -965,11 +972,12 @@ static void dl_rebuild_rd_accounting(void)
 
 	rcu_read_lock();
 
-	/*
-	 * Clear default root domain DL accounting, it will be computed again
-	 * if a task belongs to it.
-	 */
-	dl_clear_root_domain(&def_root_domain);
+	for_each_possible_cpu(cpu) {
+		if (dl_bw_visited(cpu, cookie))
+			continue;
+
+		dl_clear_root_domain_cpu(cpu);
+	}
 
 	cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
 
@@ -990,16 +998,6 @@ static void dl_rebuild_rd_accounting(void)
 	rcu_read_unlock();
 }
 
-static void
-partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
-				    struct sched_domain_attr *dattr_new)
-{
-	mutex_lock(&sched_domains_mutex);
-	partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
-	dl_rebuild_rd_accounting();
-	mutex_unlock(&sched_domains_mutex);
-}
-
 /*
  * Rebuild scheduler domains.
  *
@@ -1061,7 +1059,7 @@ void rebuild_sched_domains_locked(void)
 	ndoms = generate_sched_domains(&doms, &attr);
 
 	/* Have scheduler rebuild the domains */
-	partition_and_rebuild_sched_domains(ndoms, doms, attr);
+	partition_sched_domains(ndoms, doms, attr);
 }
 #else /* !CONFIG_SMP */
 void rebuild_sched_domains_locked(void)
@@ -1083,6 +1081,13 @@ void rebuild_sched_domains(void)
 	cpus_read_unlock();
 }
 
+void cpuset_reset_sched_domains(void)
+{
+	mutex_lock(&cpuset_mutex);
+	partition_sched_domains(1, NULL, NULL);
+	mutex_unlock(&cpuset_mutex);
+}
+
 /**
  * cpuset_update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
  * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
@@ -1090,9 +1095,14 @@ void rebuild_sched_domains(void)
  *
  * Iterate through each task of @cs updating its cpus_allowed to the
  * effective cpuset's.  As this function is called with cpuset_mutex held,
- * cpuset membership stays stable. For top_cpuset, task_cpu_possible_mask()
- * is used instead of effective_cpus to make sure all offline CPUs are also
- * included as hotplug code won't update cpumasks for tasks in top_cpuset.
+ * cpuset membership stays stable.
+ *
+ * For top_cpuset, task_cpu_possible_mask() is used instead of effective_cpus
+ * to make sure all offline CPUs are also included as hotplug code won't
+ * update cpumasks for tasks in top_cpuset.
+ *
+ * As task_cpu_possible_mask() can be task dependent in arm64, we have to
+ * do cpu masking per task instead of doing it once for all.
  */
 void cpuset_update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
 {
@@ -1152,7 +1162,7 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
  *
  * Return: 0 if successful, an error code otherwise
  */
-static int update_partition_exclusive(struct cpuset *cs, int new_prs)
+static int update_partition_exclusive_flag(struct cpuset *cs, int new_prs)
 {
 	bool exclusive = (new_prs > PRS_MEMBER);
 
@@ -1235,12 +1245,12 @@ static void reset_partition_data(struct cpuset *cs)
 }
 
 /*
- * partition_xcpus_newstate - Exclusive CPUs state change
+ * isolated_cpus_update - Update the isolated_cpus mask
  * @old_prs: old partition_root_state
  * @new_prs: new partition_root_state
  * @xcpus: exclusive CPUs with state change
  */
-static void partition_xcpus_newstate(int old_prs, int new_prs, struct cpumask *xcpus)
+static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus)
 {
 	WARN_ON_ONCE(old_prs == new_prs);
 	if (new_prs == PRS_ISOLATED)
@@ -1274,8 +1284,8 @@ static bool partition_xcpus_add(int new_prs, struct cpuset *parent,
 
 	isolcpus_updated = (new_prs != parent->partition_root_state);
 	if (isolcpus_updated)
-		partition_xcpus_newstate(parent->partition_root_state, new_prs,
-					 xcpus);
+		isolated_cpus_update(parent->partition_root_state, new_prs,
+				     xcpus);
 
 	cpumask_andnot(parent->effective_cpus, parent->effective_cpus, xcpus);
 	return isolcpus_updated;
@@ -1305,8 +1315,8 @@ static bool partition_xcpus_del(int old_prs, struct cpuset *parent,
 
 	isolcpus_updated = (old_prs != parent->partition_root_state);
 	if (isolcpus_updated)
-		partition_xcpus_newstate(old_prs, parent->partition_root_state,
-					 xcpus);
+		isolated_cpus_update(old_prs, parent->partition_root_state,
+				     xcpus);
 
 	cpumask_and(xcpus, xcpus, cpu_active_mask);
 	cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus);
@@ -1341,20 +1351,57 @@ EXPORT_SYMBOL_GPL(cpuset_cpu_is_isolated);
  * compute_effective_exclusive_cpumask - compute effective exclusive CPUs
  * @cs: cpuset
  * @xcpus: effective exclusive CPUs value to be set
- * Return: true if xcpus is not empty, false otherwise.
+ * @real_cs: the real cpuset (can be NULL)
+ * Return: 0 if there is no sibling conflict, > 0 otherwise
  *
- * Starting with exclusive_cpus (cpus_allowed if exclusive_cpus is not set),
- * it must be a subset of parent's effective_xcpus.
+ * If exclusive_cpus isn't explicitly set or a real_cs is provided, we have to
+ * scan the sibling cpusets and exclude their exclusive_cpus or effective_xcpus
+ * as well. The provision of real_cs means that a cpumask is being changed and
+ * the given cs is a trial one.
  */
-static bool compute_effective_exclusive_cpumask(struct cpuset *cs,
-						struct cpumask *xcpus)
+static int compute_effective_exclusive_cpumask(struct cpuset *cs,
+					       struct cpumask *xcpus,
+					       struct cpuset *real_cs)
 {
+	struct cgroup_subsys_state *css;
 	struct cpuset *parent = parent_cs(cs);
+	struct cpuset *sibling;
+	int retval = 0;
 
 	if (!xcpus)
 		xcpus = cs->effective_xcpus;
 
-	return cpumask_and(xcpus, user_xcpus(cs), parent->effective_xcpus);
+	cpumask_and(xcpus, user_xcpus(cs), parent->effective_xcpus);
+
+	if (!real_cs) {
+		if (!cpumask_empty(cs->exclusive_cpus))
+			return 0;
+	} else {
+		cs = real_cs;
+	}
+
+	/*
+	 * Exclude exclusive CPUs from siblings
+	 */
+	rcu_read_lock();
+	cpuset_for_each_child(sibling, css, parent) {
+		if (sibling == cs)
+			continue;
+
+		if (!cpumask_empty(sibling->exclusive_cpus) &&
+		    cpumask_intersects(xcpus, sibling->exclusive_cpus)) {
+			cpumask_andnot(xcpus, xcpus, sibling->exclusive_cpus);
+			retval++;
+			continue;
+		}
+		if (!cpumask_empty(sibling->effective_xcpus) &&
+		    cpumask_intersects(xcpus, sibling->effective_xcpus)) {
+			cpumask_andnot(xcpus, xcpus, sibling->effective_xcpus);
+			retval++;
+		}
+	}
+	rcu_read_unlock();
+	return retval;
 }
 
 static inline bool is_remote_partition(struct cpuset *cs)
@@ -1396,7 +1443,7 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
 	 * remote partition root underneath it, its exclusive_cpus must
 	 * have overlapped with subpartitions_cpus.
 	 */
-	compute_effective_exclusive_cpumask(cs, tmp->new_cpus);
+	compute_effective_exclusive_cpumask(cs, tmp->new_cpus, NULL);
 	if (cpumask_empty(tmp->new_cpus) ||
 	    cpumask_intersects(tmp->new_cpus, subpartitions_cpus) ||
 	    cpumask_subset(top_cpuset.effective_cpus, tmp->new_cpus))
@@ -1405,8 +1452,11 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
 	spin_lock_irq(&callback_lock);
 	isolcpus_updated = partition_xcpus_add(new_prs, NULL, tmp->new_cpus);
 	list_add(&cs->remote_sibling, &remote_children);
+	cpumask_copy(cs->effective_xcpus, tmp->new_cpus);
 	spin_unlock_irq(&callback_lock);
 	update_unbound_workqueue_cpumask(isolcpus_updated);
+	cpuset_force_rebuild();
+	cs->prs_err = 0;
 
 	/*
 	 * Propagate changes in top_cpuset's effective_cpus down the hierarchy.
@@ -1429,20 +1479,24 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
 {
 	bool isolcpus_updated;
 
-	compute_effective_exclusive_cpumask(cs, tmp->new_cpus);
 	WARN_ON_ONCE(!is_remote_partition(cs));
-	WARN_ON_ONCE(!cpumask_subset(tmp->new_cpus, subpartitions_cpus));
+	WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus));
 
 	spin_lock_irq(&callback_lock);
 	list_del_init(&cs->remote_sibling);
 	isolcpus_updated = partition_xcpus_del(cs->partition_root_state,
-					       NULL, tmp->new_cpus);
-	cs->partition_root_state = -cs->partition_root_state;
-	if (!cs->prs_err)
-		cs->prs_err = PERR_INVCPUS;
+					       NULL, cs->effective_xcpus);
+	if (cs->prs_err)
+		cs->partition_root_state = -cs->partition_root_state;
+	else
+		cs->partition_root_state = PRS_MEMBER;
+
+	/* effective_xcpus may need to be changed */
+	compute_effective_exclusive_cpumask(cs, NULL, NULL);
 	reset_partition_data(cs);
 	spin_unlock_irq(&callback_lock);
 	update_unbound_workqueue_cpumask(isolcpus_updated);
+	cpuset_force_rebuild();
 
 	/*
 	 * Propagate changes in top_cpuset's effective_cpus down the hierarchy.
@@ -1454,14 +1508,15 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
 /*
  * remote_cpus_update - cpus_exclusive change of remote partition
  * @cs: the cpuset to be updated
- * @newmask: the new effective_xcpus mask
+ * @xcpus: the new exclusive_cpus mask, if non-NULL
+ * @excpus: the new effective_xcpus mask
  * @tmp: temporary masks
  *
  * top_cpuset and subpartitions_cpus will be updated or partition can be
  * invalidated.
  */
-static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask,
-			       struct tmpmasks *tmp)
+static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus,
+			       struct cpumask *excpus, struct tmpmasks *tmp)
 {
 	bool adding, deleting;
 	int prs = cs->partition_root_state;
@@ -1472,29 +1527,45 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask,
 
 	WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus));
 
-	if (cpumask_empty(newmask))
+	if (cpumask_empty(excpus)) {
+		cs->prs_err = PERR_CPUSEMPTY;
 		goto invalidate;
+	}
 
-	adding   = cpumask_andnot(tmp->addmask, newmask, cs->effective_xcpus);
-	deleting = cpumask_andnot(tmp->delmask, cs->effective_xcpus, newmask);
+	adding   = cpumask_andnot(tmp->addmask, excpus, cs->effective_xcpus);
+	deleting = cpumask_andnot(tmp->delmask, cs->effective_xcpus, excpus);
 
 	/*
 	 * Additions of remote CPUs is only allowed if those CPUs are
 	 * not allocated to other partitions and there are effective_cpus
 	 * left in the top cpuset.
 	 */
-	if (adding && (!capable(CAP_SYS_ADMIN) ||
-		       cpumask_intersects(tmp->addmask, subpartitions_cpus) ||
-		       cpumask_subset(top_cpuset.effective_cpus, tmp->addmask)))
-		goto invalidate;
+	if (adding) {
+		if (!capable(CAP_SYS_ADMIN))
+			cs->prs_err = PERR_ACCESS;
+		else if (cpumask_intersects(tmp->addmask, subpartitions_cpus) ||
+			 cpumask_subset(top_cpuset.effective_cpus, tmp->addmask))
+			cs->prs_err = PERR_NOCPUS;
+		if (cs->prs_err)
+			goto invalidate;
+	}
 
 	spin_lock_irq(&callback_lock);
 	if (adding)
 		isolcpus_updated += partition_xcpus_add(prs, NULL, tmp->addmask);
 	if (deleting)
 		isolcpus_updated += partition_xcpus_del(prs, NULL, tmp->delmask);
+	/*
+	 * Need to update effective_xcpus and exclusive_cpus now as
+	 * update_sibling_cpumasks() below may iterate back to the same cs.
+	 */
+	cpumask_copy(cs->effective_xcpus, excpus);
+	if (xcpus)
+		cpumask_copy(cs->exclusive_cpus, xcpus);
 	spin_unlock_irq(&callback_lock);
 	update_unbound_workqueue_cpumask(isolcpus_updated);
+	if (adding || deleting)
+		cpuset_force_rebuild();
 
 	/*
 	 * Propagate changes in top_cpuset's effective_cpus down the hierarchy.
@@ -1508,47 +1579,6 @@ invalidate:
 }
 
 /*
- * remote_partition_check - check if a child remote partition needs update
- * @cs: the cpuset to be updated
- * @newmask: the new effective_xcpus mask
- * @delmask: temporary mask for deletion (not in tmp)
- * @tmp: temporary masks
- *
- * This should be called before the given cs has updated its cpus_allowed
- * and/or effective_xcpus.
- */
-static void remote_partition_check(struct cpuset *cs, struct cpumask *newmask,
-				   struct cpumask *delmask, struct tmpmasks *tmp)
-{
-	struct cpuset *child, *next;
-	int disable_cnt = 0;
-
-	/*
-	 * Compute the effective exclusive CPUs that will be deleted.
-	 */
-	if (!cpumask_andnot(delmask, cs->effective_xcpus, newmask) ||
-	    !cpumask_intersects(delmask, subpartitions_cpus))
-		return;	/* No deletion of exclusive CPUs in partitions */
-
-	/*
-	 * Searching the remote children list to look for those that will
-	 * be impacted by the deletion of exclusive CPUs.
-	 *
-	 * Since a cpuset must be removed from the remote children list
-	 * before it can go offline and holding cpuset_mutex will prevent
-	 * any change in cpuset status. RCU read lock isn't needed.
-	 */
-	lockdep_assert_held(&cpuset_mutex);
-	list_for_each_entry_safe(child, next, &remote_children, remote_sibling)
-		if (cpumask_intersects(child->effective_cpus, delmask)) {
-			remote_partition_disable(child, tmp);
-			disable_cnt++;
-		}
-	if (disable_cnt)
-		cpuset_force_rebuild();
-}
-
-/*
  * prstate_housekeeping_conflict - check for partition & housekeeping conflicts
  * @prstate: partition root state to be checked
  * @new_cpus: cpu mask
@@ -1602,7 +1632,7 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
  * The partcmd_update command is used by update_cpumasks_hier() with newmask
  * NULL and update_cpumask() with newmask set. The partcmd_invalidate is used
  * by update_cpumask() with NULL newmask. In both cases, the callers won't
- * check for error and so partition_root_state and prs_error will be updated
+ * check for error and so partition_root_state and prs_err will be updated
  * directly.
  */
 static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
@@ -1615,11 +1645,12 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 	int old_prs, new_prs;
 	int part_error = PERR_NONE;	/* Partition error? */
 	int subparts_delta = 0;
-	struct cpumask *xcpus;		/* cs effective_xcpus */
 	int isolcpus_updated = 0;
+	struct cpumask *xcpus = user_xcpus(cs);
 	bool nocpu;
 
 	lockdep_assert_held(&cpuset_mutex);
+	WARN_ON_ONCE(is_remote_partition(cs));
 
 	/*
 	 * new_prs will only be changed for the partcmd_update and
@@ -1627,7 +1658,6 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 	 */
 	adding = deleting = false;
 	old_prs = new_prs = cs->partition_root_state;
-	xcpus = user_xcpus(cs);
 
 	if (cmd == partcmd_invalidate) {
 		if (is_prs_invalid(old_prs))
@@ -1662,12 +1692,19 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 
 	if ((cmd == partcmd_enable) || (cmd == partcmd_enablei)) {
 		/*
+		 * Need to call compute_effective_exclusive_cpumask() in case
+		 * exclusive_cpus not set. Sibling conflict should only happen
+		 * if exclusive_cpus isn't set.
+		 */
+		xcpus = tmp->new_cpus;
+		if (compute_effective_exclusive_cpumask(cs, xcpus, NULL))
+			WARN_ON_ONCE(!cpumask_empty(cs->exclusive_cpus));
+
+		/*
 		 * Enabling partition root is not allowed if its
-		 * effective_xcpus is empty or doesn't overlap with
-		 * parent's effective_xcpus.
+		 * effective_xcpus is empty.
 		 */
-		if (cpumask_empty(xcpus) ||
-		    !cpumask_intersects(xcpus, parent->effective_xcpus))
+		if (cpumask_empty(xcpus))
 			return PERR_INVCPUS;
 
 		if (prstate_housekeeping_conflict(new_prs, xcpus))
@@ -1680,19 +1717,22 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		if (nocpu)
 			return PERR_NOCPUS;
 
-		cpumask_copy(tmp->delmask, xcpus);
-		deleting = true;
-		subparts_delta++;
+		deleting = cpumask_and(tmp->delmask, xcpus, parent->effective_xcpus);
+		if (deleting)
+			subparts_delta++;
 		new_prs = (cmd == partcmd_enable) ? PRS_ROOT : PRS_ISOLATED;
 	} else if (cmd == partcmd_disable) {
 		/*
-		 * May need to add cpus to parent's effective_cpus for
-		 * valid partition root.
+		 * May need to add cpus back to parent's effective_cpus
+		 * (and maybe removed from subpartitions_cpus/isolated_cpus)
+		 * for valid partition root. xcpus may contain CPUs that
+		 * shouldn't be removed from the two global cpumasks.
 		 */
-		adding = !is_prs_invalid(old_prs) &&
-			  cpumask_and(tmp->addmask, xcpus, parent->effective_xcpus);
-		if (adding)
+		if (is_partition_valid(cs)) {
+			cpumask_copy(tmp->addmask, cs->effective_xcpus);
+			adding = true;
 			subparts_delta--;
+		}
 		new_prs = PRS_MEMBER;
 	} else if (newmask) {
 		/*
@@ -1702,6 +1742,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 			part_error = PERR_CPUSEMPTY;
 			goto write_error;
 		}
+
 		/* Check newmask again, whether cpus are available for parent/cs */
 		nocpu |= tasks_nocpu_error(parent, cs, newmask);
 
@@ -1830,7 +1871,7 @@ write_error:
 	 * CPU lists in cs haven't been updated yet. So defer it to later.
 	 */
 	if ((old_prs != new_prs) && (cmd != partcmd_update))  {
-		int err = update_partition_exclusive(cs, new_prs);
+		int err = update_partition_exclusive_flag(cs, new_prs);
 
 		if (err)
 			return err;
@@ -1868,7 +1909,7 @@ write_error:
 	update_unbound_workqueue_cpumask(isolcpus_updated);
 
 	if ((old_prs != new_prs) && (cmd == partcmd_update))
-		update_partition_exclusive(cs, new_prs);
+		update_partition_exclusive_flag(cs, new_prs);
 
 	if (adding || deleting) {
 		cpuset_update_tasks_cpumask(parent, tmp->addmask);
@@ -1918,7 +1959,7 @@ static void compute_partition_effective_cpumask(struct cpuset *cs,
 	 *  2) All the effective_cpus will be used up and cp
 	 *     has tasks
 	 */
-	compute_effective_exclusive_cpumask(cs, new_ecpus);
+	compute_effective_exclusive_cpumask(cs, new_ecpus, NULL);
 	cpumask_and(new_ecpus, new_ecpus, cpu_active_mask);
 
 	rcu_read_lock();
@@ -1926,6 +1967,11 @@ static void compute_partition_effective_cpumask(struct cpuset *cs,
 		if (!is_partition_valid(child))
 			continue;
 
+		/*
+		 * There shouldn't be a remote partition underneath another
+		 * partition root.
+		 */
+		WARN_ON_ONCE(is_remote_partition(child));
 		child->prs_err = 0;
 		if (!cpumask_subset(child->effective_xcpus,
 				    cs->effective_xcpus))
@@ -1981,32 +2027,39 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
 		bool remote = is_remote_partition(cp);
 		bool update_parent = false;
 
+		old_prs = new_prs = cp->partition_root_state;
+
 		/*
-		 * Skip descendent remote partition that acquires CPUs
-		 * directly from top cpuset unless it is cs.
+		 * For child remote partition root (!= cs), we need to call
+		 * remote_cpus_update() if effective_xcpus will be changed.
+		 * Otherwise, we can skip the whole subtree.
+		 *
+		 * remote_cpus_update() will reuse tmp->new_cpus only after
+		 * its value is being processed.
 		 */
 		if (remote && (cp != cs)) {
-			pos_css = css_rightmost_descendant(pos_css);
-			continue;
-		}
+			compute_effective_exclusive_cpumask(cp, tmp->new_cpus, NULL);
+			if (cpumask_equal(cp->effective_xcpus, tmp->new_cpus)) {
+				pos_css = css_rightmost_descendant(pos_css);
+				continue;
+			}
+			rcu_read_unlock();
+			remote_cpus_update(cp, NULL, tmp->new_cpus, tmp);
+			rcu_read_lock();
 
-		/*
-		 * Update effective_xcpus if exclusive_cpus set.
-		 * The case when exclusive_cpus isn't set is handled later.
-		 */
-		if (!cpumask_empty(cp->exclusive_cpus) && (cp != cs)) {
-			spin_lock_irq(&callback_lock);
-			compute_effective_exclusive_cpumask(cp, NULL);
-			spin_unlock_irq(&callback_lock);
+			/* Remote partition may be invalidated */
+			new_prs = cp->partition_root_state;
+			remote = (new_prs == old_prs);
 		}
 
-		old_prs = new_prs = cp->partition_root_state;
-		if (remote || (is_partition_valid(parent) &&
-			       is_partition_valid(cp)))
+		if (remote || (is_partition_valid(parent) && is_partition_valid(cp)))
 			compute_partition_effective_cpumask(cp, tmp->new_cpus);
 		else
 			compute_effective_cpumask(tmp->new_cpus, cp, parent);
 
+		if (remote)
+			goto get_css;	/* Ready to update cpuset data */
+
 		/*
 		 * A partition with no effective_cpus is allowed as long as
 		 * there is no task associated with it. Call
@@ -2026,9 +2079,6 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
 		if (is_in_v2_mode() && !remote && cpumask_empty(tmp->new_cpus))
 			cpumask_copy(tmp->new_cpus, parent->effective_cpus);
 
-		if (remote)
-			goto get_css;
-
 		/*
 		 * Skip the whole subtree if
 		 * 1) the cpumask remains the same,
@@ -2089,6 +2139,9 @@ get_css:
 		spin_lock_irq(&callback_lock);
 		cpumask_copy(cp->effective_cpus, tmp->new_cpus);
 		cp->partition_root_state = new_prs;
+		if (!cpumask_empty(cp->exclusive_cpus) && (cp != cs))
+			compute_effective_exclusive_cpumask(cp, NULL, NULL);
+
 		/*
 		 * Make sure effective_xcpus is properly set for a valid
 		 * partition root.
@@ -2175,7 +2228,14 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
 						  parent);
 			if (cpumask_equal(tmp->new_cpus, sibling->effective_cpus))
 				continue;
+		} else if (is_remote_partition(sibling)) {
+			/*
+			 * Change in a sibling cpuset won't affect a remote
+			 * partition root.
+			 */
+			continue;
 		}
+
 		if (!css_tryget_online(&sibling->css))
 			continue;
 
@@ -2232,8 +2292,9 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 		 * trialcs->effective_xcpus is used as a temporary cpumask
 		 * for checking validity of the partition root.
 		 */
+		trialcs->partition_root_state = PRS_MEMBER;
 		if (!cpumask_empty(trialcs->exclusive_cpus) || is_partition_valid(cs))
-			compute_effective_exclusive_cpumask(trialcs, NULL);
+			compute_effective_exclusive_cpumask(trialcs, NULL, cs);
 	}
 
 	/* Nothing to do if the cpus didn't change */
@@ -2306,19 +2367,13 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 		 * Call remote_cpus_update() to handle valid remote partition
 		 */
 		if (is_remote_partition(cs))
-			remote_cpus_update(cs, xcpus, &tmp);
+			remote_cpus_update(cs, NULL, xcpus, &tmp);
 		else if (invalidate)
 			update_parent_effective_cpumask(cs, partcmd_invalidate,
 							NULL, &tmp);
 		else
 			update_parent_effective_cpumask(cs, partcmd_update,
 							xcpus, &tmp);
-	} else if (!cpumask_empty(cs->exclusive_cpus)) {
-		/*
-		 * Use trialcs->effective_cpus as a temp cpumask
-		 */
-		remote_partition_check(cs, trialcs->effective_xcpus,
-				       trialcs->effective_cpus, &tmp);
 	}
 
 	spin_lock_irq(&callback_lock);
@@ -2370,8 +2425,15 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	if (cpumask_equal(cs->exclusive_cpus, trialcs->exclusive_cpus))
 		return 0;
 
-	if (*buf)
-		compute_effective_exclusive_cpumask(trialcs, NULL);
+	if (*buf) {
+		trialcs->partition_root_state = PRS_MEMBER;
+		/*
+		 * Reject the change if there is exclusive CPUs conflict with
+		 * the siblings.
+		 */
+		if (compute_effective_exclusive_cpumask(trialcs, NULL, cs))
+			return -EINVAL;
+	}
 
 	/*
 	 * Check all the descendants in update_cpumasks_hier() if
@@ -2402,8 +2464,8 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 			if (invalidate)
 				remote_partition_disable(cs, &tmp);
 			else
-				remote_cpus_update(cs, trialcs->effective_xcpus,
-						   &tmp);
+				remote_cpus_update(cs, trialcs->exclusive_cpus,
+						   trialcs->effective_xcpus, &tmp);
 		} else if (invalidate) {
 			update_parent_effective_cpumask(cs, partcmd_invalidate,
 							NULL, &tmp);
@@ -2411,12 +2473,6 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 			update_parent_effective_cpumask(cs, partcmd_update,
 						trialcs->effective_xcpus, &tmp);
 		}
-	} else if (!cpumask_empty(trialcs->exclusive_cpus)) {
-		/*
-		 * Use trialcs->effective_cpus as a temp cpumask
-		 */
-		remote_partition_check(cs, trialcs->effective_xcpus,
-				       trialcs->effective_cpus, &tmp);
 	}
 	spin_lock_irq(&callback_lock);
 	cpumask_copy(cs->exclusive_cpus, trialcs->exclusive_cpus);
@@ -2783,7 +2839,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 	int err = PERR_NONE, old_prs = cs->partition_root_state;
 	struct cpuset *parent = parent_cs(cs);
 	struct tmpmasks tmpmask;
-	bool new_xcpus_state = false;
+	bool isolcpus_updated = false;
 
 	if (old_prs == new_prs)
 		return 0;
@@ -2797,18 +2853,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 	if (alloc_cpumasks(NULL, &tmpmask))
 		return -ENOMEM;
 
-	/*
-	 * Setup effective_xcpus if not properly set yet, it will be cleared
-	 * later if partition becomes invalid.
-	 */
-	if ((new_prs > 0) && cpumask_empty(cs->exclusive_cpus)) {
-		spin_lock_irq(&callback_lock);
-		cpumask_and(cs->effective_xcpus,
-			    cs->cpus_allowed, parent->effective_xcpus);
-		spin_unlock_irq(&callback_lock);
-	}
-
-	err = update_partition_exclusive(cs, new_prs);
+	err = update_partition_exclusive_flag(cs, new_prs);
 	if (err)
 		goto out;
 
@@ -2822,6 +2867,19 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 		}
 
 		/*
+		 * We don't support the creation of a new local partition with
+		 * a remote partition underneath it. This unsupported
+		 * setting can happen only if parent is the top_cpuset because
+		 * a remote partition cannot be created underneath an existing
+		 * local or remote partition.
+		 */
+		if ((parent == &top_cpuset) &&
+		    cpumask_intersects(cs->exclusive_cpus, subpartitions_cpus)) {
+			err = PERR_REMOTE;
+			goto out;
+		}
+
+		/*
 		 * If parent is valid partition, enable local partiion.
 		 * Otherwise, enable a remote partition.
 		 */
@@ -2836,8 +2894,9 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 	} else if (old_prs && new_prs) {
 		/*
 		 * A change in load balance state only, no change in cpumasks.
+		 * Need to update isolated_cpus.
 		 */
-		new_xcpus_state = true;
+		isolcpus_updated = true;
 	} else {
 		/*
 		 * Switching back to member is always allowed even if it
@@ -2861,7 +2920,7 @@ out:
 	 */
 	if (err) {
 		new_prs = -new_prs;
-		update_partition_exclusive(cs, new_prs);
+		update_partition_exclusive_flag(cs, new_prs);
 	}
 
 	spin_lock_irq(&callback_lock);
@@ -2869,14 +2928,18 @@ out:
 	WRITE_ONCE(cs->prs_err, err);
 	if (!is_partition_valid(cs))
 		reset_partition_data(cs);
-	else if (new_xcpus_state)
-		partition_xcpus_newstate(old_prs, new_prs, cs->effective_xcpus);
+	else if (isolcpus_updated)
+		isolated_cpus_update(old_prs, new_prs, cs->effective_xcpus);
 	spin_unlock_irq(&callback_lock);
-	update_unbound_workqueue_cpumask(new_xcpus_state);
+	update_unbound_workqueue_cpumask(isolcpus_updated);
 
-	/* Force update if switching back to member */
+	/* Force update if switching back to member & update effective_xcpus */
 	update_cpumasks_hier(cs, &tmpmask, !new_prs);
 
+	/* A newly created partition must have effective_xcpus set */
+	WARN_ON_ONCE(!old_prs && (new_prs > 0)
+			      && cpumask_empty(cs->effective_xcpus));
+
 	/* Update sched domains and load balance flag */
 	update_partition_sd_lb(cs, old_prs);
 
@@ -3209,7 +3272,7 @@ int cpuset_common_seq_show(struct seq_file *sf, void *v)
 	return ret;
 }
 
-static int sched_partition_show(struct seq_file *seq, void *v)
+static int cpuset_partition_show(struct seq_file *seq, void *v)
 {
 	struct cpuset *cs = css_cs(seq_css(seq));
 	const char *err, *type = NULL;
@@ -3240,7 +3303,7 @@ static int sched_partition_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
+static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf,
 				     size_t nbytes, loff_t off)
 {
 	struct cpuset *cs = css_cs(of_css(of));
@@ -3261,11 +3324,8 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
 	css_get(&cs->css);
 	cpus_read_lock();
 	mutex_lock(&cpuset_mutex);
-	if (!is_cpuset_online(cs))
-		goto out_unlock;
-
-	retval = update_prstate(cs, val);
-out_unlock:
+	if (is_cpuset_online(cs))
+		retval = update_prstate(cs, val);
 	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
 	css_put(&cs->css);
@@ -3309,8 +3369,8 @@ static struct cftype dfl_files[] = {
 
 	{
 		.name = "cpus.partition",
-		.seq_show = sched_partition_show,
-		.write = sched_partition_write,
+		.seq_show = cpuset_partition_show,
+		.write = cpuset_partition_write,
 		.private = FILE_PARTITION_ROOT,
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.file_offset = offsetof(struct cpuset, partition_file),
@@ -3476,9 +3536,6 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
 	cpus_read_lock();
 	mutex_lock(&cpuset_mutex);
 
-	if (is_partition_valid(cs))
-		update_prstate(cs, 0);
-
 	if (!cpuset_v2() && is_sched_load_balance(cs))
 		cpuset_update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
 
@@ -3489,6 +3546,22 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
 	cpus_read_unlock();
 }
 
+static void cpuset_css_killed(struct cgroup_subsys_state *css)
+{
+	struct cpuset *cs = css_cs(css);
+
+	cpus_read_lock();
+	mutex_lock(&cpuset_mutex);
+
+	/* Reset valid partition back to member */
+	if (is_partition_valid(cs))
+		update_prstate(cs, PRS_MEMBER);
+
+	mutex_unlock(&cpuset_mutex);
+	cpus_read_unlock();
+
+}
+
 static void cpuset_css_free(struct cgroup_subsys_state *css)
 {
 	struct cpuset *cs = css_cs(css);
@@ -3610,6 +3683,7 @@ struct cgroup_subsys cpuset_cgrp_subsys = {
 	.css_alloc	= cpuset_css_alloc,
 	.css_online	= cpuset_css_online,
 	.css_offline	= cpuset_css_offline,
+	.css_killed	= cpuset_css_killed,
 	.css_free	= cpuset_css_free,
 	.can_attach	= cpuset_can_attach,
 	.cancel_attach	= cpuset_cancel_attach,
@@ -3740,10 +3814,10 @@ retry:
 
 	if (remote && cpumask_empty(&new_cpus) &&
 	    partition_is_populated(cs, NULL)) {
+		cs->prs_err = PERR_HOTPLUG;
 		remote_partition_disable(cs, tmp);
 		compute_effective_cpumask(&new_cpus, cs, parent);
 		remote = false;
-		cpuset_force_rebuild();
 	}
 
 	/*
@@ -4244,50 +4318,6 @@ void cpuset_print_current_mems_allowed(void)
 	rcu_read_unlock();
 }
 
-#ifdef CONFIG_PROC_PID_CPUSET
-/*
- * proc_cpuset_show()
- *  - Print tasks cpuset path into seq_file.
- *  - Used for /proc/<pid>/cpuset.
- *  - No need to task_lock(tsk) on this tsk->cpuset reference, as it
- *    doesn't really matter if tsk->cpuset changes after we read it,
- *    and we take cpuset_mutex, keeping cpuset_attach() from changing it
- *    anyway.
- */
-int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
-		     struct pid *pid, struct task_struct *tsk)
-{
-	char *buf;
-	struct cgroup_subsys_state *css;
-	int retval;
-
-	retval = -ENOMEM;
-	buf = kmalloc(PATH_MAX, GFP_KERNEL);
-	if (!buf)
-		goto out;
-
-	rcu_read_lock();
-	spin_lock_irq(&css_set_lock);
-	css = task_css(tsk, cpuset_cgrp_id);
-	retval = cgroup_path_ns_locked(css->cgroup, buf, PATH_MAX,
-				       current->nsproxy->cgroup_ns);
-	spin_unlock_irq(&css_set_lock);
-	rcu_read_unlock();
-
-	if (retval == -E2BIG)
-		retval = -ENAMETOOLONG;
-	if (retval < 0)
-		goto out_free;
-	seq_puts(m, buf);
-	seq_putc(m, '\n');
-	retval = 0;
-out_free:
-	kfree(buf);
-out:
-	return retval;
-}
-#endif /* CONFIG_PROC_PID_CPUSET */
-
 /* Display task mems_allowed in /proc/<pid>/status file. */
 void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task)
 {
diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c
index 074653f964c1..039d1eb2f215 100644
--- a/kernel/cgroup/legacy_freezer.c
+++ b/kernel/cgroup/legacy_freezer.c
@@ -430,9 +430,11 @@ static ssize_t freezer_write(struct kernfs_open_file *of,
 
 	if (strcmp(buf, freezer_state_strs(0)) == 0)
 		freeze = false;
-	else if (strcmp(buf, freezer_state_strs(CGROUP_FROZEN)) == 0)
+	else if (strcmp(buf, freezer_state_strs(CGROUP_FROZEN)) == 0) {
+		pr_info_once("Freezing with imperfect legacy cgroup freezer. "
+			     "See cgroup.freeze of cgroup v2\n");
 		freeze = true;
-	else
+	} else
 		return -EINVAL;
 
 	freezer_change_state(css_freezer(of_css(of)), freeze);
diff --git a/kernel/cgroup/misc.c b/kernel/cgroup/misc.c
index 0e26068995a6..2fa3a4fb2aaf 100644
--- a/kernel/cgroup/misc.c
+++ b/kernel/cgroup/misc.c
@@ -68,22 +68,6 @@ static inline bool valid_type(enum misc_res_type type)
 }
 
 /**
- * misc_cg_res_total_usage() - Get the current total usage of the resource.
- * @type: misc res type.
- *
- * Context: Any context.
- * Return: Current total usage of the resource.
- */
-u64 misc_cg_res_total_usage(enum misc_res_type type)
-{
-	if (valid_type(type))
-		return atomic64_read(&root_cg.res[type].usage);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(misc_cg_res_total_usage);
-
-/**
  * misc_cg_set_capacity() - Set the capacity of the misc cgroup res.
  * @type: Type of the misc res.
  * @capacity: Supported capacity of the misc res on the host.
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index aac91466279f..b2239156b7de 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -299,40 +299,6 @@ static inline void __cgroup_rstat_unlock(struct cgroup *cgrp, int cpu_in_loop)
 	spin_unlock_irq(&cgroup_rstat_lock);
 }
 
-/* see cgroup_rstat_flush() */
-static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
-	__releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock)
-{
-	int cpu;
-
-	lockdep_assert_held(&cgroup_rstat_lock);
-
-	for_each_possible_cpu(cpu) {
-		struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu);
-
-		for (; pos; pos = pos->rstat_flush_next) {
-			struct cgroup_subsys_state *css;
-
-			cgroup_base_stat_flush(pos, cpu);
-			bpf_rstat_flush(pos, cgroup_parent(pos), cpu);
-
-			rcu_read_lock();
-			list_for_each_entry_rcu(css, &pos->rstat_css_list,
-						rstat_css_node)
-				css->ss->css_rstat_flush(css, cpu);
-			rcu_read_unlock();
-		}
-
-		/* play nice and yield if necessary */
-		if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) {
-			__cgroup_rstat_unlock(cgrp, cpu);
-			if (!cond_resched())
-				cpu_relax();
-			__cgroup_rstat_lock(cgrp, cpu);
-		}
-	}
-}
-
 /**
  * cgroup_rstat_flush - flush stats in @cgrp's subtree
  * @cgrp: target cgroup
@@ -348,38 +314,31 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
  */
 __bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp)
 {
+	int cpu;
+
 	might_sleep();
+	for_each_possible_cpu(cpu) {
+		struct cgroup *pos;
 
-	__cgroup_rstat_lock(cgrp, -1);
-	cgroup_rstat_flush_locked(cgrp);
-	__cgroup_rstat_unlock(cgrp, -1);
-}
+		/* Reacquire for each CPU to avoid disabling IRQs too long */
+		__cgroup_rstat_lock(cgrp, cpu);
+		pos = cgroup_rstat_updated_list(cgrp, cpu);
+		for (; pos; pos = pos->rstat_flush_next) {
+			struct cgroup_subsys_state *css;
 
-/**
- * cgroup_rstat_flush_hold - flush stats in @cgrp's subtree and hold
- * @cgrp: target cgroup
- *
- * Flush stats in @cgrp's subtree and prevent further flushes.  Must be
- * paired with cgroup_rstat_flush_release().
- *
- * This function may block.
- */
-void cgroup_rstat_flush_hold(struct cgroup *cgrp)
-	__acquires(&cgroup_rstat_lock)
-{
-	might_sleep();
-	__cgroup_rstat_lock(cgrp, -1);
-	cgroup_rstat_flush_locked(cgrp);
-}
+			cgroup_base_stat_flush(pos, cpu);
+			bpf_rstat_flush(pos, cgroup_parent(pos), cpu);
 
-/**
- * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold()
- * @cgrp: cgroup used by tracepoint
- */
-void cgroup_rstat_flush_release(struct cgroup *cgrp)
-	__releases(&cgroup_rstat_lock)
-{
-	__cgroup_rstat_unlock(cgrp, -1);
+			rcu_read_lock();
+			list_for_each_entry_rcu(css, &pos->rstat_css_list,
+						rstat_css_node)
+				css->ss->css_rstat_flush(css, cpu);
+			rcu_read_unlock();
+		}
+		__cgroup_rstat_unlock(cgrp, cpu);
+		if (!cond_resched())
+			cpu_relax();
+	}
 }
 
 int cgroup_rstat_init(struct cgroup *cgrp)
@@ -612,36 +571,34 @@ static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat
 void cgroup_base_stat_cputime_show(struct seq_file *seq)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	u64 usage, utime, stime, ntime;
+	struct cgroup_base_stat bstat;
 
 	if (cgroup_parent(cgrp)) {
-		cgroup_rstat_flush_hold(cgrp);
-		usage = cgrp->bstat.cputime.sum_exec_runtime;
+		cgroup_rstat_flush(cgrp);
+		__cgroup_rstat_lock(cgrp, -1);
+		bstat = cgrp->bstat;
 		cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime,
-			       &utime, &stime);
-		ntime = cgrp->bstat.ntime;
-		cgroup_rstat_flush_release(cgrp);
+			       &bstat.cputime.utime, &bstat.cputime.stime);
+		__cgroup_rstat_unlock(cgrp, -1);
 	} else {
-		/* cgrp->bstat of root is not actually used, reuse it */
-		root_cgroup_cputime(&cgrp->bstat);
-		usage = cgrp->bstat.cputime.sum_exec_runtime;
-		utime = cgrp->bstat.cputime.utime;
-		stime = cgrp->bstat.cputime.stime;
-		ntime = cgrp->bstat.ntime;
+		root_cgroup_cputime(&bstat);
 	}
 
-	do_div(usage, NSEC_PER_USEC);
-	do_div(utime, NSEC_PER_USEC);
-	do_div(stime, NSEC_PER_USEC);
-	do_div(ntime, NSEC_PER_USEC);
+	do_div(bstat.cputime.sum_exec_runtime, NSEC_PER_USEC);
+	do_div(bstat.cputime.utime, NSEC_PER_USEC);
+	do_div(bstat.cputime.stime, NSEC_PER_USEC);
+	do_div(bstat.ntime, NSEC_PER_USEC);
 
 	seq_printf(seq, "usage_usec %llu\n"
 			"user_usec %llu\n"
 			"system_usec %llu\n"
 			"nice_usec %llu\n",
-			usage, utime, stime, ntime);
+			bstat.cputime.sum_exec_runtime,
+			bstat.cputime.utime,
+			bstat.cputime.stime,
+			bstat.ntime);
 
-	cgroup_force_idle_show(seq, &cgrp->bstat);
+	cgroup_force_idle_show(seq, &bstat);
 }
 
 /* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */