Merge tag 'cgroup-for-6.20' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - cpuset changes:

    - Continue separating v1 and v2 implementations by moving more
      v1-specific logic into cpuset-v1.c

    - Improve partition handling. Sibling partitions are no longer
      invalidated on cpuset.cpus conflict, cpuset.cpus changes no longer
      fail in v2, and effective_xcpus computation is made consistent

    - Fix partition effective CPUs overlap that caused a warning on
      cpuset removal when sibling partitions shared CPUs

 - Increase the maximum cgroup subsystem count from 16 to 32 to
   accommodate future subsystem additions

 - Misc cleanups and selftest improvements including switching to
   css_is_online() helper, removing dead code and stale documentation
   references, using lockdep_assert_cpuset_lock_held() consistently, and
   adding polling helpers for asynchronously updated cgroup statistics

* tag 'cgroup-for-6.20' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (21 commits)
  cpuset: fix overlap of partition effective CPUs
  cgroup: increase maximum subsystem count from 16 to 32
  cgroup: Remove stale cpu.rt.max reference from documentation
  cpuset: replace direct lockdep_assert_held() with lockdep_assert_cpuset_lock_held()
  cgroup/cpuset: Move the v1 empty cpus/mems check to cpuset1_validate_change()
  cgroup/cpuset: Don't invalidate sibling partitions on cpuset.cpus conflict
  cgroup/cpuset: Don't fail cpuset.cpus change in v2
  cgroup/cpuset: Consistently compute effective_xcpus in update_cpumasks_hier()
  cgroup/cpuset: Streamline rm_siblings_excl_cpus()
  cpuset: remove dead code in cpuset-v1.c
  cpuset: remove v1-specific code from generate_sched_domains
  cpuset: separate generate_sched_domains for v1 and v2
  cpuset: move update_domain_attr_tree to cpuset_v1.c
  cpuset: add cpuset1_init helper for v1 initialization
  cpuset: add cpuset1_online_css helper for v1-specific operations
  cpuset: add lockdep_assert_cpuset_lock_held helper
  cpuset: Remove unnecessary checks in rebuild_sched_domains_locked
  cgroup: switch to css_is_online() helper
  selftests: cgroup: Replace sleep with cg_read_key_long_poll() for waiting on nr_dying_descendants
  selftests: cgroup: make test_memcg_sock robust against delayed sock stats
  ...

7 files changed, 473 insertions, 423 deletions

diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 22051b4f1ccb..3bfe37693d68 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -52,7 +52,7 @@ struct cgroup_fs_context {
 	bool		cpuset_clone_children;
 	bool		none;			/* User explicitly requested empty subsystem */
 	bool		all_ss;			/* Seen 'all' option */
-	u16		subsys_mask;		/* Selected subsystems */
+	u32		subsys_mask;		/* Selected subsystems */
 	char		*name;			/* Hierarchy name */
 	char		*release_agent;		/* Path for release notifications */
 };
@@ -146,7 +146,7 @@ struct cgroup_mgctx {
 	struct cgroup_taskset	tset;
 
 	/* subsystems affected by migration */
-	u16			ss_mask;
+	u32			ss_mask;
 };
 
 #define CGROUP_TASKSET_INIT(tset)						\
@@ -235,8 +235,8 @@ int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen,
 void cgroup_favor_dynmods(struct cgroup_root *root, bool favor);
 void cgroup_free_root(struct cgroup_root *root);
 void init_cgroup_root(struct cgroup_fs_context *ctx);
-int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask);
-int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask);
+int cgroup_setup_root(struct cgroup_root *root, u32 ss_mask);
+int rebind_subsystems(struct cgroup_root *dst_root, u32 ss_mask);
 int cgroup_do_get_tree(struct fs_context *fc);
 
 int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp);
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index a9e029b570c8..724950c4b690 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -28,7 +28,7 @@
 #define CGROUP_PIDLIST_DESTROY_DELAY	HZ
 
 /* Controllers blocked by the commandline in v1 */
-static u16 cgroup_no_v1_mask;
+static u32 cgroup_no_v1_mask;
 
 /* disable named v1 mounts */
 static bool cgroup_no_v1_named;
@@ -1037,13 +1037,13 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param)
 static int check_cgroupfs_options(struct fs_context *fc)
 {
 	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
-	u16 mask = U16_MAX;
-	u16 enabled = 0;
+	u32 mask = U32_MAX;
+	u32 enabled = 0;
 	struct cgroup_subsys *ss;
 	int i;
 
 #ifdef CONFIG_CPUSETS
-	mask = ~((u16)1 << cpuset_cgrp_id);
+	mask = ~((u32)1 << cpuset_cgrp_id);
 #endif
 	for_each_subsys(ss, i)
 		if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i) &&
@@ -1095,7 +1095,7 @@ int cgroup1_reconfigure(struct fs_context *fc)
 	struct kernfs_root *kf_root = kernfs_root_from_sb(fc->root->d_sb);
 	struct cgroup_root *root = cgroup_root_from_kf(kf_root);
 	int ret = 0;
-	u16 added_mask, removed_mask;
+	u32 added_mask, removed_mask;
 
 	cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
 
@@ -1343,7 +1343,7 @@ static int __init cgroup_no_v1(char *str)
 			continue;
 
 		if (!strcmp(token, "all")) {
-			cgroup_no_v1_mask = U16_MAX;
+			cgroup_no_v1_mask = U32_MAX;
 			continue;
 		}
 
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 5f0d33b04910..8af4351536cf 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -203,13 +203,13 @@ EXPORT_SYMBOL_GPL(cgrp_dfl_root);
 bool cgrp_dfl_visible;
 
 /* some controllers are not supported in the default hierarchy */
-static u16 cgrp_dfl_inhibit_ss_mask;
+static u32 cgrp_dfl_inhibit_ss_mask;
 
 /* some controllers are implicitly enabled on the default hierarchy */
-static u16 cgrp_dfl_implicit_ss_mask;
+static u32 cgrp_dfl_implicit_ss_mask;
 
 /* some controllers can be threaded on the default hierarchy */
-static u16 cgrp_dfl_threaded_ss_mask;
+static u32 cgrp_dfl_threaded_ss_mask;
 
 /* The list of hierarchy roots */
 LIST_HEAD(cgroup_roots);
@@ -231,10 +231,10 @@ static u64 css_serial_nr_next = 1;
  * These bitmasks identify subsystems with specific features to avoid
  * having to do iterative checks repeatedly.
  */
-static u16 have_fork_callback __read_mostly;
-static u16 have_exit_callback __read_mostly;
-static u16 have_release_callback __read_mostly;
-static u16 have_canfork_callback __read_mostly;
+static u32 have_fork_callback __read_mostly;
+static u32 have_exit_callback __read_mostly;
+static u32 have_release_callback __read_mostly;
+static u32 have_canfork_callback __read_mostly;
 
 static bool have_favordynmods __ro_after_init = IS_ENABLED(CONFIG_CGROUP_FAVOR_DYNMODS);
 
@@ -472,13 +472,13 @@ static bool cgroup_is_valid_domain(struct cgroup *cgrp)
 }
 
 /* subsystems visibly enabled on a cgroup */
-static u16 cgroup_control(struct cgroup *cgrp)
+static u32 cgroup_control(struct cgroup *cgrp)
 {
 	struct cgroup *parent = cgroup_parent(cgrp);
-	u16 root_ss_mask = cgrp->root->subsys_mask;
+	u32 root_ss_mask = cgrp->root->subsys_mask;
 
 	if (parent) {
-		u16 ss_mask = parent->subtree_control;
+		u32 ss_mask = parent->subtree_control;
 
 		/* threaded cgroups can only have threaded controllers */
 		if (cgroup_is_threaded(cgrp))
@@ -493,12 +493,12 @@ static u16 cgroup_control(struct cgroup *cgrp)
 }
 
 /* subsystems enabled on a cgroup */
-static u16 cgroup_ss_mask(struct cgroup *cgrp)
+static u32 cgroup_ss_mask(struct cgroup *cgrp)
 {
 	struct cgroup *parent = cgroup_parent(cgrp);
 
 	if (parent) {
-		u16 ss_mask = parent->subtree_ss_mask;
+		u32 ss_mask = parent->subtree_ss_mask;
 
 		/* threaded cgroups can only have threaded controllers */
 		if (cgroup_is_threaded(cgrp))
@@ -1633,9 +1633,9 @@ static umode_t cgroup_file_mode(const struct cftype *cft)
  * This function calculates which subsystems need to be enabled if
  * @subtree_control is to be applied while restricted to @this_ss_mask.
  */
-static u16 cgroup_calc_subtree_ss_mask(u16 subtree_control, u16 this_ss_mask)
+static u32 cgroup_calc_subtree_ss_mask(u32 subtree_control, u32 this_ss_mask)
 {
-	u16 cur_ss_mask = subtree_control;
+	u32 cur_ss_mask = subtree_control;
 	struct cgroup_subsys *ss;
 	int ssid;
 
@@ -1644,7 +1644,7 @@ static u16 cgroup_calc_subtree_ss_mask(u16 subtree_control, u16 this_ss_mask)
 	cur_ss_mask |= cgrp_dfl_implicit_ss_mask;
 
 	while (true) {
-		u16 new_ss_mask = cur_ss_mask;
+		u32 new_ss_mask = cur_ss_mask;
 
 		do_each_subsys_mask(ss, ssid, cur_ss_mask) {
 			new_ss_mask |= ss->depends_on;
@@ -1848,12 +1848,12 @@ err:
 	return ret;
 }
 
-int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
+int rebind_subsystems(struct cgroup_root *dst_root, u32 ss_mask)
 {
 	struct cgroup *dcgrp = &dst_root->cgrp;
 	struct cgroup_subsys *ss;
 	int ssid, ret;
-	u16 dfl_disable_ss_mask = 0;
+	u32 dfl_disable_ss_mask = 0;
 
 	lockdep_assert_held(&cgroup_mutex);
 
@@ -2149,7 +2149,7 @@ void init_cgroup_root(struct cgroup_fs_context *ctx)
 		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
 }
 
-int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
+int cgroup_setup_root(struct cgroup_root *root, u32 ss_mask)
 {
 	LIST_HEAD(tmp_links);
 	struct cgroup *root_cgrp = &root->cgrp;
@@ -3131,7 +3131,7 @@ void cgroup_procs_write_finish(struct task_struct *task,
 	put_task_struct(task);
 }
 
-static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask)
+static void cgroup_print_ss_mask(struct seq_file *seq, u32 ss_mask)
 {
 	struct cgroup_subsys *ss;
 	bool printed = false;
@@ -3496,9 +3496,9 @@ static void cgroup_finalize_control(struct cgroup *cgrp, int ret)
 	cgroup_apply_control_disable(cgrp);
 }
 
-static int cgroup_vet_subtree_control_enable(struct cgroup *cgrp, u16 enable)
+static int cgroup_vet_subtree_control_enable(struct cgroup *cgrp, u32 enable)
 {
-	u16 domain_enable = enable & ~cgrp_dfl_threaded_ss_mask;
+	u32 domain_enable = enable & ~cgrp_dfl_threaded_ss_mask;
 
 	/* if nothing is getting enabled, nothing to worry about */
 	if (!enable)
@@ -3541,7 +3541,7 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
 					    char *buf, size_t nbytes,
 					    loff_t off)
 {
-	u16 enable = 0, disable = 0;
+	u32 enable = 0, disable = 0;
 	struct cgroup *cgrp, *child;
 	struct cgroup_subsys *ss;
 	char *tok;
@@ -4945,7 +4945,7 @@ bool css_has_online_children(struct cgroup_subsys_state *css)
 
 	rcu_read_lock();
 	css_for_each_child(child, css) {
-		if (child->flags & CSS_ONLINE) {
+		if (css_is_online(child)) {
 			ret = true;
 			break;
 		}
@@ -5750,7 +5750,7 @@ static void offline_css(struct cgroup_subsys_state *css)
 
 	lockdep_assert_held(&cgroup_mutex);
 
-	if (!(css->flags & CSS_ONLINE))
+	if (!css_is_online(css))
 		return;
 
 	if (ss->css_offline)
@@ -6347,7 +6347,7 @@ int __init cgroup_init(void)
 	struct cgroup_subsys *ss;
 	int ssid;
 
-	BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16);
+	BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 32);
 	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));
diff --git a/kernel/cgroup/cpuset-internal.h b/kernel/cgroup/cpuset-internal.h
index 01976c8e7d49..fd7d19842ded 100644
--- a/kernel/cgroup/cpuset-internal.h
+++ b/kernel/cgroup/cpuset-internal.h
@@ -9,6 +9,7 @@
 #include <linux/cpuset.h>
 #include <linux/spinlock.h>
 #include <linux/union_find.h>
+#include <linux/sched/isolation.h>
 
 /* See "Frequency meter" comments, below. */
 
@@ -144,17 +145,12 @@ struct cpuset {
 	 */
 	nodemask_t old_mems_allowed;
 
-	struct fmeter fmeter;		/* memory_pressure filter */
-
 	/*
 	 * Tasks are being attached to this cpuset.  Used to prevent
 	 * zeroing cpus/mems_allowed between ->can_attach() and ->attach().
 	 */
 	int attach_in_progress;
 
-	/* for custom sched domain */
-	int relax_domain_level;
-
 	/* partition root state */
 	int partition_root_state;
 
@@ -179,10 +175,19 @@ struct cpuset {
 	/* Handle for cpuset.cpus.partition */
 	struct cgroup_file partition_file;
 
+#ifdef CONFIG_CPUSETS_V1
+	struct fmeter fmeter;		/* memory_pressure filter */
+
+	/* for custom sched domain */
+	int relax_domain_level;
+
 	/* Used to merge intersecting subsets for generate_sched_domains */
 	struct uf_node node;
+#endif
 };
 
+extern struct cpuset top_cpuset;
+
 static inline struct cpuset *css_cs(struct cgroup_subsys_state *css)
 {
 	return css ? container_of(css, struct cpuset, css) : NULL;
@@ -240,6 +245,30 @@ static inline int is_spread_slab(const struct cpuset *cs)
 	return test_bit(CS_SPREAD_SLAB, &cs->flags);
 }
 
+/*
+ * Helper routine for generate_sched_domains().
+ * Do cpusets a, b have overlapping effective cpus_allowed masks?
+ */
+static inline int cpusets_overlap(struct cpuset *a, struct cpuset *b)
+{
+	return cpumask_intersects(a->effective_cpus, b->effective_cpus);
+}
+
+static inline int nr_cpusets(void)
+{
+	/* jump label reference count + the top-level cpuset */
+	return static_key_count(&cpusets_enabled_key.key) + 1;
+}
+
+static inline bool cpuset_is_populated(struct cpuset *cs)
+{
+	lockdep_assert_cpuset_lock_held();
+
+	/* Cpusets in the process of attaching should be considered as populated */
+	return cgroup_is_populated(cs->css.cgroup) ||
+		cs->attach_in_progress;
+}
+
 /**
  * cpuset_for_each_child - traverse online children of a cpuset
  * @child_cs: loop cursor pointing to the current child
@@ -285,7 +314,6 @@ void cpuset_full_unlock(void);
  */
 #ifdef CONFIG_CPUSETS_V1
 extern struct cftype cpuset1_files[];
-void fmeter_init(struct fmeter *fmp);
 void cpuset1_update_task_spread_flags(struct cpuset *cs,
 					struct task_struct *tsk);
 void cpuset1_update_tasks_flags(struct cpuset *cs);
@@ -293,8 +321,13 @@ void cpuset1_hotplug_update_tasks(struct cpuset *cs,
 			    struct cpumask *new_cpus, nodemask_t *new_mems,
 			    bool cpus_updated, bool mems_updated);
 int cpuset1_validate_change(struct cpuset *cur, struct cpuset *trial);
+bool cpuset1_cpus_excl_conflict(struct cpuset *cs1, struct cpuset *cs2);
+void cpuset1_init(struct cpuset *cs);
+void cpuset1_online_css(struct cgroup_subsys_state *css);
+int cpuset1_generate_sched_domains(cpumask_var_t **domains,
+			struct sched_domain_attr **attributes);
+
 #else
-static inline void fmeter_init(struct fmeter *fmp) {}
 static inline void cpuset1_update_task_spread_flags(struct cpuset *cs,
 					struct task_struct *tsk) {}
 static inline void cpuset1_update_tasks_flags(struct cpuset *cs) {}
@@ -303,6 +336,13 @@ static inline void cpuset1_hotplug_update_tasks(struct cpuset *cs,
 			    bool cpus_updated, bool mems_updated) {}
 static inline int cpuset1_validate_change(struct cpuset *cur,
 				struct cpuset *trial) { return 0; }
+static inline bool cpuset1_cpus_excl_conflict(struct cpuset *cs1,
+					struct cpuset *cs2) { return false; }
+static inline void cpuset1_init(struct cpuset *cs) {}
+static inline void cpuset1_online_css(struct cgroup_subsys_state *css) {}
+static inline int cpuset1_generate_sched_domains(cpumask_var_t **domains,
+			struct sched_domain_attr **attributes) { return 0; };
+
 #endif /* CONFIG_CPUSETS_V1 */
 
 #endif /* __CPUSET_INTERNAL_H */
diff --git a/kernel/cgroup/cpuset-v1.c b/kernel/cgroup/cpuset-v1.c
index 12e76774c75b..7a23b9e8778f 100644
--- a/kernel/cgroup/cpuset-v1.c
+++ b/kernel/cgroup/cpuset-v1.c
@@ -62,7 +62,7 @@ struct cpuset_remove_tasks_struct {
 #define FM_SCALE 1000		/* faux fixed point scale */
 
 /* Initialize a frequency meter */
-void fmeter_init(struct fmeter *fmp)
+static void fmeter_init(struct fmeter *fmp)
 {
 	fmp->cnt = 0;
 	fmp->val = 0;
@@ -368,11 +368,44 @@ int cpuset1_validate_change(struct cpuset *cur, struct cpuset *trial)
 	if (par && !is_cpuset_subset(trial, par))
 		goto out;
 
+	/*
+	 * Cpusets with tasks - existing or newly being attached - can't
+	 * be changed to have empty cpus_allowed or mems_allowed.
+	 */
+	ret = -ENOSPC;
+	if (cpuset_is_populated(cur)) {
+		if (!cpumask_empty(cur->cpus_allowed) &&
+		    cpumask_empty(trial->cpus_allowed))
+			goto out;
+		if (!nodes_empty(cur->mems_allowed) &&
+		    nodes_empty(trial->mems_allowed))
+			goto out;
+	}
+
 	ret = 0;
 out:
 	return ret;
 }
 
+/*
+ * cpuset1_cpus_excl_conflict() - Check if two cpusets have exclusive CPU conflicts
+ *                                to legacy (v1)
+ * @cs1: first cpuset to check
+ * @cs2: second cpuset to check
+ *
+ * Returns: true if CPU exclusivity conflict exists, false otherwise
+ *
+ * If either cpuset is CPU exclusive, their allowed CPUs cannot intersect.
+ */
+bool cpuset1_cpus_excl_conflict(struct cpuset *cs1, struct cpuset *cs2)
+{
+	if (is_cpu_exclusive(cs1) || is_cpu_exclusive(cs2))
+		return cpumask_intersects(cs1->cpus_allowed,
+					  cs2->cpus_allowed);
+
+	return false;
+}
+
 #ifdef CONFIG_PROC_PID_CPUSET
 /*
  * proc_cpuset_show()
@@ -499,6 +532,242 @@ out_unlock:
 	return retval;
 }
 
+void cpuset1_init(struct cpuset *cs)
+{
+	fmeter_init(&cs->fmeter);
+	cs->relax_domain_level = -1;
+}
+
+void cpuset1_online_css(struct cgroup_subsys_state *css)
+{
+	struct cpuset *tmp_cs;
+	struct cgroup_subsys_state *pos_css;
+	struct cpuset *cs = css_cs(css);
+	struct cpuset *parent = parent_cs(cs);
+
+	lockdep_assert_cpus_held();
+	lockdep_assert_cpuset_lock_held();
+
+	if (is_spread_page(parent))
+		set_bit(CS_SPREAD_PAGE, &cs->flags);
+	if (is_spread_slab(parent))
+		set_bit(CS_SPREAD_SLAB, &cs->flags);
+
+	if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
+		return;
+
+	/*
+	 * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is
+	 * set.  This flag handling is implemented in cgroup core for
+	 * historical reasons - the flag may be specified during mount.
+	 *
+	 * Currently, if any sibling cpusets have exclusive cpus or mem, we
+	 * refuse to clone the configuration - thereby refusing the task to
+	 * be entered, and as a result refusing the sys_unshare() or
+	 * clone() which initiated it.  If this becomes a problem for some
+	 * users who wish to allow that scenario, then this could be
+	 * changed to grant parent->cpus_allowed-sibling_cpus_exclusive
+	 * (and likewise for mems) to the new cgroup.
+	 */
+	rcu_read_lock();
+	cpuset_for_each_child(tmp_cs, pos_css, parent) {
+		if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) {
+			rcu_read_unlock();
+			return;
+		}
+	}
+	rcu_read_unlock();
+
+	cpuset_callback_lock_irq();
+	cs->mems_allowed = parent->mems_allowed;
+	cs->effective_mems = parent->mems_allowed;
+	cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
+	cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
+	cpuset_callback_unlock_irq();
+}
+
+static void
+update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c)
+{
+	if (dattr->relax_domain_level < c->relax_domain_level)
+		dattr->relax_domain_level = c->relax_domain_level;
+}
+
+static void update_domain_attr_tree(struct sched_domain_attr *dattr,
+				    struct cpuset *root_cs)
+{
+	struct cpuset *cp;
+	struct cgroup_subsys_state *pos_css;
+
+	rcu_read_lock();
+	cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
+		/* skip the whole subtree if @cp doesn't have any CPU */
+		if (cpumask_empty(cp->cpus_allowed)) {
+			pos_css = css_rightmost_descendant(pos_css);
+			continue;
+		}
+
+		if (is_sched_load_balance(cp))
+			update_domain_attr(dattr, cp);
+	}
+	rcu_read_unlock();
+}
+
+/*
+ * cpuset1_generate_sched_domains()
+ *
+ * Finding the best partition (set of domains):
+ *	The double nested loops below over i, j scan over the load
+ *	balanced cpusets (using the array of cpuset pointers in csa[])
+ *	looking for pairs of cpusets that have overlapping cpus_allowed
+ *	and merging them using a union-find algorithm.
+ *
+ *	The union of the cpus_allowed masks from the set of all cpusets
+ *	having the same root then form the one element of the partition
+ *	(one sched domain) to be passed to partition_sched_domains().
+ */
+int cpuset1_generate_sched_domains(cpumask_var_t **domains,
+			struct sched_domain_attr **attributes)
+{
+	struct cpuset *cp;	/* top-down scan of cpusets */
+	struct cpuset **csa;	/* array of all cpuset ptrs */
+	int csn;		/* how many cpuset ptrs in csa so far */
+	int i, j;		/* indices for partition finding loops */
+	cpumask_var_t *doms;	/* resulting partition; i.e. sched domains */
+	struct sched_domain_attr *dattr;  /* attributes for custom domains */
+	int ndoms = 0;		/* number of sched domains in result */
+	int nslot;		/* next empty doms[] struct cpumask slot */
+	struct cgroup_subsys_state *pos_css;
+	int nslot_update;
+
+	lockdep_assert_cpuset_lock_held();
+
+	doms = NULL;
+	dattr = NULL;
+	csa = NULL;
+
+	/* Special case for the 99% of systems with one, full, sched domain */
+	if (is_sched_load_balance(&top_cpuset)) {
+		ndoms = 1;
+		doms = alloc_sched_domains(ndoms);
+		if (!doms)
+			goto done;
+
+		dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL);
+		if (dattr) {
+			*dattr = SD_ATTR_INIT;
+			update_domain_attr_tree(dattr, &top_cpuset);
+		}
+		cpumask_and(doms[0], top_cpuset.effective_cpus,
+			    housekeeping_cpumask(HK_TYPE_DOMAIN));
+
+		goto done;
+	}
+
+	csa = kmalloc_array(nr_cpusets(), sizeof(cp), GFP_KERNEL);
+	if (!csa)
+		goto done;
+	csn = 0;
+
+	rcu_read_lock();
+	cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) {
+		if (cp == &top_cpuset)
+			continue;
+
+		/*
+		 * Continue traversing beyond @cp iff @cp has some CPUs and
+		 * isn't load balancing.  The former is obvious.  The
+		 * latter: All child cpusets contain a subset of the
+		 * parent's cpus, so just skip them, and then we call
+		 * update_domain_attr_tree() to calc relax_domain_level of
+		 * the corresponding sched domain.
+		 */
+		if (!cpumask_empty(cp->cpus_allowed) &&
+		    !(is_sched_load_balance(cp) &&
+		      cpumask_intersects(cp->cpus_allowed,
+					 housekeeping_cpumask(HK_TYPE_DOMAIN))))
+			continue;
+
+		if (is_sched_load_balance(cp) &&
+		    !cpumask_empty(cp->effective_cpus))
+			csa[csn++] = cp;
+
+		/* skip @cp's subtree */
+		pos_css = css_rightmost_descendant(pos_css);
+		continue;
+	}
+	rcu_read_unlock();
+
+	for (i = 0; i < csn; i++)
+		uf_node_init(&csa[i]->node);
+
+	/* Merge overlapping cpusets */
+	for (i = 0; i < csn; i++) {
+		for (j = i + 1; j < csn; j++) {
+			if (cpusets_overlap(csa[i], csa[j]))
+				uf_union(&csa[i]->node, &csa[j]->node);
+		}
+	}
+
+	/* Count the total number of domains */
+	for (i = 0; i < csn; i++) {
+		if (uf_find(&csa[i]->node) == &csa[i]->node)
+			ndoms++;
+	}
+
+	/*
+	 * Now we know how many domains to create.
+	 * Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
+	 */
+	doms = alloc_sched_domains(ndoms);
+	if (!doms)
+		goto done;
+
+	/*
+	 * The rest of the code, including the scheduler, can deal with
+	 * dattr==NULL case. No need to abort if alloc fails.
+	 */
+	dattr = kmalloc_array(ndoms, sizeof(struct sched_domain_attr),
+			      GFP_KERNEL);
+
+	for (nslot = 0, i = 0; i < csn; i++) {
+		nslot_update = 0;
+		for (j = i; j < csn; j++) {
+			if (uf_find(&csa[j]->node) == &csa[i]->node) {
+				struct cpumask *dp = doms[nslot];
+
+				if (i == j) {
+					nslot_update = 1;
+					cpumask_clear(dp);
+					if (dattr)
+						*(dattr + nslot) = SD_ATTR_INIT;
+				}
+				cpumask_or(dp, dp, csa[j]->effective_cpus);
+				cpumask_and(dp, dp, housekeeping_cpumask(HK_TYPE_DOMAIN));
+				if (dattr)
+					update_domain_attr_tree(dattr + nslot, csa[j]);
+			}
+		}
+		if (nslot_update)
+			nslot++;
+	}
+	BUG_ON(nslot != ndoms);
+
+done:
+	kfree(csa);
+
+	/*
+	 * Fallback to the default domain if kmalloc() failed.
+	 * See comments in partition_sched_domains().
+	 */
+	if (doms == NULL)
+		ndoms = 1;
+
+	*domains    = doms;
+	*attributes = dattr;
+	return ndoms;
+}
+
 /*
  * for the common functions, 'private' gives the type of file
  */
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 01a553caee56..c43efef7df71 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -119,6 +119,17 @@ static bool force_sd_rebuild;
  *  For simplicity, a local partition can be created under a local or remote
  *  partition but a remote partition cannot have any partition root in its
  *  ancestor chain except the cgroup root.
+ *
+ *  A valid partition can be formed by setting exclusive_cpus or cpus_allowed
+ *  if exclusive_cpus is not set. In the case of partition with empty
+ *  exclusive_cpus, all the conflicting exclusive CPUs specified in the
+ *  following cpumasks of sibling cpusets will be removed from its
+ *  cpus_allowed in determining its effective_xcpus.
+ *  - effective_xcpus
+ *  - exclusive_cpus
+ *
+ *  The "cpuset.cpus.exclusive" control file should be used for setting up
+ *  partition if the users want to get as many CPUs as possible.
  */
 #define PRS_MEMBER		0
 #define PRS_ROOT		1
@@ -201,12 +212,10 @@ static inline void notify_partition_change(struct cpuset *cs, int old_prs)
  * If cpu_online_mask is used while a hotunplug operation is happening in
  * parallel, we may leave an offline CPU in cpu_allowed or some other masks.
  */
-static struct cpuset top_cpuset = {
+struct cpuset top_cpuset = {
 	.flags = BIT(CS_CPU_EXCLUSIVE) |
 		 BIT(CS_MEM_EXCLUSIVE) | BIT(CS_SCHED_LOAD_BALANCE),
 	.partition_root_state = PRS_ROOT,
-	.relax_domain_level = -1,
-	.remote_partition = false,
 };
 
 /*
@@ -261,6 +270,11 @@ void cpuset_unlock(void)
 	mutex_unlock(&cpuset_mutex);
 }
 
+void lockdep_assert_cpuset_lock_held(void)
+{
+	lockdep_assert_held(&cpuset_mutex);
+}
+
 /**
  * cpuset_full_lock - Acquire full protection for cpuset modification
  *
@@ -319,7 +333,7 @@ static inline void check_insane_mems_config(nodemask_t *nodes)
  */
 static inline void dec_attach_in_progress_locked(struct cpuset *cs)
 {
-	lockdep_assert_held(&cpuset_mutex);
+	lockdep_assert_cpuset_lock_held();
 
 	cs->attach_in_progress--;
 	if (!cs->attach_in_progress)
@@ -353,15 +367,6 @@ static inline bool is_in_v2_mode(void)
 	      (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE);
 }
 
-static inline bool cpuset_is_populated(struct cpuset *cs)
-{
-	lockdep_assert_held(&cpuset_mutex);
-
-	/* Cpusets in the process of attaching should be considered as populated */
-	return cgroup_is_populated(cs->css.cgroup) ||
-		cs->attach_in_progress;
-}
-
 /**
  * partition_is_populated - check if partition has tasks
  * @cs: partition root to be checked
@@ -603,36 +608,32 @@ static inline bool cpusets_are_exclusive(struct cpuset *cs1, struct cpuset *cs2)
 
 /**
  * cpus_excl_conflict - Check if two cpusets have exclusive CPU conflicts
- * @cs1: first cpuset to check
- * @cs2: second cpuset to check
+ * @trial:	the trial cpuset to be checked
+ * @sibling:	a sibling cpuset to be checked against
+ * @xcpus_changed: set if exclusive_cpus has been set
  *
  * Returns: true if CPU exclusivity conflict exists, false otherwise
  *
  * Conflict detection rules:
- * 1. If either cpuset is CPU exclusive, they must be mutually exclusive
- * 2. exclusive_cpus masks cannot intersect between cpusets
- * 3. The allowed CPUs of one cpuset cannot be a subset of another's exclusive CPUs
+ *  o cgroup v1
+ *    See cpuset1_cpus_excl_conflict()
+ *  o cgroup v2
+ *    - The exclusive_cpus values cannot overlap.
+ *    - New exclusive_cpus cannot be a superset of a sibling's cpus_allowed.
  */
-static inline bool cpus_excl_conflict(struct cpuset *cs1, struct cpuset *cs2)
+static inline bool cpus_excl_conflict(struct cpuset *trial, struct cpuset *sibling,
+				      bool xcpus_changed)
 {
-	/* If either cpuset is exclusive, check if they are mutually exclusive */
-	if (is_cpu_exclusive(cs1) || is_cpu_exclusive(cs2))
-		return !cpusets_are_exclusive(cs1, cs2);
-
-	/* Exclusive_cpus cannot intersect */
-	if (cpumask_intersects(cs1->exclusive_cpus, cs2->exclusive_cpus))
-		return true;
-
-	/* The cpus_allowed of one cpuset cannot be a subset of another cpuset's exclusive_cpus */
-	if (!cpumask_empty(cs1->cpus_allowed) &&
-	    cpumask_subset(cs1->cpus_allowed, cs2->exclusive_cpus))
-		return true;
+	if (!cpuset_v2())
+		return cpuset1_cpus_excl_conflict(trial, sibling);
 
-	if (!cpumask_empty(cs2->cpus_allowed) &&
-	    cpumask_subset(cs2->cpus_allowed, cs1->exclusive_cpus))
+	/* The cpus_allowed of a sibling cpuset cannot be a subset of the new exclusive_cpus */
+	if (xcpus_changed && !cpumask_empty(sibling->cpus_allowed) &&
+	    cpumask_subset(sibling->cpus_allowed, trial->exclusive_cpus))
 		return true;
 
-	return false;
+	/* Exclusive_cpus cannot intersect */
+	return cpumask_intersects(trial->exclusive_cpus, sibling->exclusive_cpus);
 }
 
 static inline bool mems_excl_conflict(struct cpuset *cs1, struct cpuset *cs2)
@@ -666,6 +667,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 {
 	struct cgroup_subsys_state *css;
 	struct cpuset *c, *par;
+	bool xcpus_changed;
 	int ret = 0;
 
 	rcu_read_lock();
@@ -682,20 +684,6 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 	par = parent_cs(cur);
 
 	/*
-	 * Cpusets with tasks - existing or newly being attached - can't
-	 * be changed to have empty cpus_allowed or mems_allowed.
-	 */
-	ret = -ENOSPC;
-	if (cpuset_is_populated(cur)) {
-		if (!cpumask_empty(cur->cpus_allowed) &&
-		    cpumask_empty(trial->cpus_allowed))
-			goto out;
-		if (!nodes_empty(cur->mems_allowed) &&
-		    nodes_empty(trial->mems_allowed))
-			goto out;
-	}
-
-	/*
 	 * We can't shrink if we won't have enough room for SCHED_DEADLINE
 	 * tasks. This check is not done when scheduling is disabled as the
 	 * users should know what they are doing.
@@ -722,10 +710,11 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 	 * overlap. exclusive_cpus cannot overlap with each other if set.
 	 */
 	ret = -EINVAL;
+	xcpus_changed = !cpumask_equal(cur->exclusive_cpus, trial->exclusive_cpus);
 	cpuset_for_each_child(c, css, par) {
 		if (c == cur)
 			continue;
-		if (cpus_excl_conflict(trial, c))
+		if (cpus_excl_conflict(trial, c, xcpus_changed))
 			goto out;
 		if (mems_excl_conflict(trial, c))
 			goto out;
@@ -738,49 +727,6 @@ out:
 }
 
 #ifdef CONFIG_SMP
-/*
- * Helper routine for generate_sched_domains().
- * Do cpusets a, b have overlapping effective cpus_allowed masks?
- */
-static int cpusets_overlap(struct cpuset *a, struct cpuset *b)
-{
-	return cpumask_intersects(a->effective_cpus, b->effective_cpus);
-}
-
-static void
-update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c)
-{
-	if (dattr->relax_domain_level < c->relax_domain_level)
-		dattr->relax_domain_level = c->relax_domain_level;
-	return;
-}
-
-static void update_domain_attr_tree(struct sched_domain_attr *dattr,
-				    struct cpuset *root_cs)
-{
-	struct cpuset *cp;
-	struct cgroup_subsys_state *pos_css;
-
-	rcu_read_lock();
-	cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
-		/* skip the whole subtree if @cp doesn't have any CPU */
-		if (cpumask_empty(cp->cpus_allowed)) {
-			pos_css = css_rightmost_descendant(pos_css);
-			continue;
-		}
-
-		if (is_sched_load_balance(cp))
-			update_domain_attr(dattr, cp);
-	}
-	rcu_read_unlock();
-}
-
-/* Must be called with cpuset_mutex held.  */
-static inline int nr_cpusets(void)
-{
-	/* jump label reference count + the top-level cpuset */
-	return static_key_count(&cpusets_enabled_key.key) + 1;
-}
 
 /*
  * generate_sched_domains()
@@ -820,103 +766,46 @@ static inline int nr_cpusets(void)
  *	   convenient format, that can be easily compared to the prior
  *	   value to determine what partition elements (sched domains)
  *	   were changed (added or removed.)
- *
- * Finding the best partition (set of domains):
- *	The double nested loops below over i, j scan over the load
- *	balanced cpusets (using the array of cpuset pointers in csa[])
- *	looking for pairs of cpusets that have overlapping cpus_allowed
- *	and merging them using a union-find algorithm.
- *
- *	The union of the cpus_allowed masks from the set of all cpusets
- *	having the same root then form the one element of the partition
- *	(one sched domain) to be passed to partition_sched_domains().
- *
  */
 static int generate_sched_domains(cpumask_var_t **domains,
 			struct sched_domain_attr **attributes)
 {
 	struct cpuset *cp;	/* top-down scan of cpusets */
 	struct cpuset **csa;	/* array of all cpuset ptrs */
-	int csn;		/* how many cpuset ptrs in csa so far */
 	int i, j;		/* indices for partition finding loops */
 	cpumask_var_t *doms;	/* resulting partition; i.e. sched domains */
 	struct sched_domain_attr *dattr;  /* attributes for custom domains */
 	int ndoms = 0;		/* number of sched domains in result */
-	int nslot;		/* next empty doms[] struct cpumask slot */
 	struct cgroup_subsys_state *pos_css;
-	bool root_load_balance = is_sched_load_balance(&top_cpuset);
-	bool cgrpv2 = cpuset_v2();
-	int nslot_update;
+
+	if (!cpuset_v2())
+		return cpuset1_generate_sched_domains(domains, attributes);
 
 	doms = NULL;
 	dattr = NULL;
 	csa = NULL;
 
 	/* Special case for the 99% of systems with one, full, sched domain */
-	if (root_load_balance && cpumask_empty(subpartitions_cpus)) {
-single_root_domain:
+	if (cpumask_empty(subpartitions_cpus)) {
 		ndoms = 1;
-		doms = alloc_sched_domains(ndoms);
-		if (!doms)
-			goto done;
-
-		dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL);
-		if (dattr) {
-			*dattr = SD_ATTR_INIT;
-			update_domain_attr_tree(dattr, &top_cpuset);
-		}
-		cpumask_and(doms[0], top_cpuset.effective_cpus,
-			    housekeeping_cpumask(HK_TYPE_DOMAIN));
-
-		goto done;
+		/* !csa will be checked and can be correctly handled */
+		goto generate_doms;
 	}
 
 	csa = kmalloc_array(nr_cpusets(), sizeof(cp), GFP_KERNEL);
 	if (!csa)
 		goto done;
-	csn = 0;
 
+	/* Find how many partitions and cache them to csa[] */
 	rcu_read_lock();
-	if (root_load_balance)
-		csa[csn++] = &top_cpuset;
 	cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) {
-		if (cp == &top_cpuset)
-			continue;
-
-		if (cgrpv2)
-			goto v2;
-
-		/*
-		 * v1:
-		 * Continue traversing beyond @cp iff @cp has some CPUs and
-		 * isn't load balancing.  The former is obvious.  The
-		 * latter: All child cpusets contain a subset of the
-		 * parent's cpus, so just skip them, and then we call
-		 * update_domain_attr_tree() to calc relax_domain_level of
-		 * the corresponding sched domain.
-		 */
-		if (!cpumask_empty(cp->cpus_allowed) &&
-		    !(is_sched_load_balance(cp) &&
-		      cpumask_intersects(cp->cpus_allowed,
-					 housekeeping_cpumask(HK_TYPE_DOMAIN))))
-			continue;
-
-		if (is_sched_load_balance(cp) &&
-		    !cpumask_empty(cp->effective_cpus))
-			csa[csn++] = cp;
-
-		/* skip @cp's subtree */
-		pos_css = css_rightmost_descendant(pos_css);
-		continue;
-
-v2:
 		/*
 		 * Only valid partition roots that are not isolated and with
-		 * non-empty effective_cpus will be saved into csn[].
+		 * non-empty effective_cpus will be saved into csa[].
 		 */
 		if ((cp->partition_root_state == PRS_ROOT) &&
 		    !cpumask_empty(cp->effective_cpus))
-			csa[csn++] = cp;
+			csa[ndoms++] = cp;
 
 		/*
 		 * Skip @cp's subtree if not a partition root and has no
@@ -927,40 +816,18 @@ v2:
 	}
 	rcu_read_unlock();
 
-	/*
-	 * If there are only isolated partitions underneath the cgroup root,
-	 * we can optimize out unneeded sched domains scanning.
-	 */
-	if (root_load_balance && (csn == 1))
-		goto single_root_domain;
-
-	for (i = 0; i < csn; i++)
-		uf_node_init(&csa[i]->node);
-
-	/* Merge overlapping cpusets */
-	for (i = 0; i < csn; i++) {
-		for (j = i + 1; j < csn; j++) {
-			if (cpusets_overlap(csa[i], csa[j])) {
+	for (i = 0; i < ndoms; i++) {
+		for (j = i + 1; j < ndoms; j++) {
+			if (cpusets_overlap(csa[i], csa[j]))
 				/*
 				 * Cgroup v2 shouldn't pass down overlapping
 				 * partition root cpusets.
 				 */
-				WARN_ON_ONCE(cgrpv2);
-				uf_union(&csa[i]->node, &csa[j]->node);
-			}
+				WARN_ON_ONCE(1);
 		}
 	}
 
-	/* Count the total number of domains */
-	for (i = 0; i < csn; i++) {
-		if (uf_find(&csa[i]->node) == &csa[i]->node)
-			ndoms++;
-	}
-
-	/*
-	 * Now we know how many domains to create.
-	 * Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
-	 */
+generate_doms:
 	doms = alloc_sched_domains(ndoms);
 	if (!doms)
 		goto done;
@@ -977,45 +844,19 @@ v2:
 	 * to SD_ATTR_INIT. Also non-isolating partition root CPUs are a
 	 * subset of HK_TYPE_DOMAIN housekeeping CPUs.
 	 */
-	if (cgrpv2) {
-		for (i = 0; i < ndoms; i++) {
-			/*
-			 * The top cpuset may contain some boot time isolated
-			 * CPUs that need to be excluded from the sched domain.
-			 */
-			if (csa[i] == &top_cpuset)
-				cpumask_and(doms[i], csa[i]->effective_cpus,
-					    housekeeping_cpumask(HK_TYPE_DOMAIN));
-			else
-				cpumask_copy(doms[i], csa[i]->effective_cpus);
-			if (dattr)
-				dattr[i] = SD_ATTR_INIT;
-		}
-		goto done;
-	}
-
-	for (nslot = 0, i = 0; i < csn; i++) {
-		nslot_update = 0;
-		for (j = i; j < csn; j++) {
-			if (uf_find(&csa[j]->node) == &csa[i]->node) {
-				struct cpumask *dp = doms[nslot];
-
-				if (i == j) {
-					nslot_update = 1;
-					cpumask_clear(dp);
-					if (dattr)
-						*(dattr + nslot) = SD_ATTR_INIT;
-				}
-				cpumask_or(dp, dp, csa[j]->effective_cpus);
-				cpumask_and(dp, dp, housekeeping_cpumask(HK_TYPE_DOMAIN));
-				if (dattr)
-					update_domain_attr_tree(dattr + nslot, csa[j]);
-			}
-		}
-		if (nslot_update)
-			nslot++;
+	for (i = 0; i < ndoms; i++) {
+		/*
+		 * The top cpuset may contain some boot time isolated
+		 * CPUs that need to be excluded from the sched domain.
+		 */
+		if (!csa || csa[i] == &top_cpuset)
+			cpumask_and(doms[i], top_cpuset.effective_cpus,
+				    housekeeping_cpumask(HK_TYPE_DOMAIN));
+		else
+			cpumask_copy(doms[i], csa[i]->effective_cpus);
+		if (dattr)
+			dattr[i] = SD_ATTR_INIT;
 	}
-	BUG_ON(nslot != ndoms);
 
 done:
 	kfree(csa);
@@ -1055,7 +896,7 @@ void dl_rebuild_rd_accounting(void)
 	int cpu;
 	u64 cookie = ++dl_cookie;
 
-	lockdep_assert_held(&cpuset_mutex);
+	lockdep_assert_cpuset_lock_held();
 	lockdep_assert_cpus_held();
 	lockdep_assert_held(&sched_domains_mutex);
 
@@ -1100,53 +941,33 @@ void dl_rebuild_rd_accounting(void)
  */
 void rebuild_sched_domains_locked(void)
 {
-	struct cgroup_subsys_state *pos_css;
 	struct sched_domain_attr *attr;
 	cpumask_var_t *doms;
-	struct cpuset *cs;
 	int ndoms;
+	int i;
 
 	lockdep_assert_cpus_held();
-	lockdep_assert_held(&cpuset_mutex);
+	lockdep_assert_cpuset_lock_held();
 	force_sd_rebuild = false;
 
-	/*
-	 * If we have raced with CPU hotplug, return early to avoid
-	 * passing doms with offlined cpu to partition_sched_domains().
-	 * Anyways, cpuset_handle_hotplug() will rebuild sched domains.
-	 *
-	 * With no CPUs in any subpartitions, top_cpuset's effective CPUs
-	 * should be the same as the active CPUs, so checking only top_cpuset
-	 * is enough to detect racing CPU offlines.
-	 */
-	if (cpumask_empty(subpartitions_cpus) &&
-	    !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
-		return;
+	/* Generate domain masks and attrs */
+	ndoms = generate_sched_domains(&doms, &attr);
 
 	/*
-	 * With subpartition CPUs, however, the effective CPUs of a partition
-	 * root should be only a subset of the active CPUs.  Since a CPU in any
-	 * partition root could be offlined, all must be checked.
-	 */
-	if (!cpumask_empty(subpartitions_cpus)) {
-		rcu_read_lock();
-		cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
-			if (!is_partition_valid(cs)) {
-				pos_css = css_rightmost_descendant(pos_css);
-				continue;
-			}
-			if (!cpumask_subset(cs->effective_cpus,
-					    cpu_active_mask)) {
-				rcu_read_unlock();
-				return;
-			}
-		}
-		rcu_read_unlock();
+	* cpuset_hotplug_workfn is invoked synchronously now, thus this
+	* function should not race with CPU hotplug. And the effective CPUs
+	* must not include any offline CPUs. Passing an offline CPU in the
+	* doms to partition_sched_domains() will trigger a kernel panic.
+	*
+	* We perform a final check here: if the doms contains any
+	* offline CPUs, a warning is emitted and we return directly to
+	* prevent the panic.
+	*/
+	for (i = 0; i < ndoms; ++i) {
+		if (WARN_ON_ONCE(!cpumask_subset(doms[i], cpu_active_mask)))
+			return;
 	}
 
-	/* Generate domain masks and attrs */
-	ndoms = generate_sched_domains(&doms, &attr);
-
 	/* Have scheduler rebuild the domains */
 	partition_sched_domains(ndoms, doms, attr);
 }
@@ -1501,23 +1322,29 @@ static int rm_siblings_excl_cpus(struct cpuset *parent, struct cpuset *cs,
 	int retval = 0;
 
 	if (cpumask_empty(excpus))
-		return retval;
+		return 0;
 
 	/*
-	 * Exclude exclusive CPUs from siblings
+	 * Remove exclusive CPUs from siblings
 	 */
 	rcu_read_lock();
 	cpuset_for_each_child(sibling, css, parent) {
+		struct cpumask *sibling_xcpus;
+
 		if (sibling == cs)
 			continue;
 
-		if (cpumask_intersects(excpus, sibling->exclusive_cpus)) {
-			cpumask_andnot(excpus, excpus, sibling->exclusive_cpus);
-			retval++;
-			continue;
-		}
-		if (cpumask_intersects(excpus, sibling->effective_xcpus)) {
-			cpumask_andnot(excpus, excpus, sibling->effective_xcpus);
+		/*
+		 * If exclusive_cpus is defined, effective_xcpus will always
+		 * be a subset. Otherwise, effective_xcpus will only be set
+		 * in a valid partition root.
+		 */
+		sibling_xcpus = cpumask_empty(sibling->exclusive_cpus)
+			      ? sibling->effective_xcpus
+			      : sibling->exclusive_cpus;
+
+		if (cpumask_intersects(excpus, sibling_xcpus)) {
+			cpumask_andnot(excpus, excpus, sibling_xcpus);
 			retval++;
 		}
 	}
@@ -1806,7 +1633,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 	int parent_prs = parent->partition_root_state;
 	bool nocpu;
 
-	lockdep_assert_held(&cpuset_mutex);
+	lockdep_assert_cpuset_lock_held();
 	WARN_ON_ONCE(is_remote_partition(cs));	/* For local partition only */
 
 	/*
@@ -2315,17 +2142,13 @@ 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_excpus(cp, cp->effective_xcpus);
-
 		/*
-		 * Make sure effective_xcpus is properly set for a valid
-		 * partition root.
+		 * Need to compute effective_xcpus if either exclusive_cpus
+		 * is non-empty or it is a valid partition root.
 		 */
-		if ((new_prs > 0) && cpumask_empty(cp->exclusive_cpus))
-			cpumask_and(cp->effective_xcpus,
-				    cp->cpus_allowed, parent->effective_xcpus);
-		else if (new_prs < 0)
+		if ((new_prs > 0) || !cpumask_empty(cp->exclusive_cpus))
+			compute_excpus(cp, cp->effective_xcpus);
+		if (new_prs <= 0)
 			reset_partition_data(cp);
 		spin_unlock_irq(&callback_lock);
 
@@ -2378,7 +2201,7 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
 	struct cpuset *sibling;
 	struct cgroup_subsys_state *pos_css;
 
-	lockdep_assert_held(&cpuset_mutex);
+	lockdep_assert_cpuset_lock_held();
 
 	/*
 	 * Check all its siblings and call update_cpumasks_hier()
@@ -2387,27 +2210,20 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
 	 * It is possible a change in parent's effective_cpus
 	 * due to a change in a child partition's effective_xcpus will impact
 	 * its siblings even if they do not inherit parent's effective_cpus
-	 * directly.
+	 * directly. It should not impact valid partition.
 	 *
 	 * The update_cpumasks_hier() function may sleep. So we have to
 	 * release the RCU read lock before calling it.
 	 */
 	rcu_read_lock();
 	cpuset_for_each_child(sibling, pos_css, parent) {
-		if (sibling == cs)
+		if (sibling == cs || is_partition_valid(sibling))
 			continue;
-		if (!is_partition_valid(sibling)) {
-			compute_effective_cpumask(tmp->new_cpus, sibling,
-						  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.
-			 */
+
+		compute_effective_cpumask(tmp->new_cpus, sibling,
+					  parent);
+		if (cpumask_equal(tmp->new_cpus, sibling->effective_cpus))
 			continue;
-		}
 
 		if (!css_tryget_online(&sibling->css))
 			continue;
@@ -2463,43 +2279,6 @@ static enum prs_errcode validate_partition(struct cpuset *cs, struct cpuset *tri
 	return PERR_NONE;
 }
 
-static int cpus_allowed_validate_change(struct cpuset *cs, struct cpuset *trialcs,
-					struct tmpmasks *tmp)
-{
-	int retval;
-	struct cpuset *parent = parent_cs(cs);
-
-	retval = validate_change(cs, trialcs);
-
-	if ((retval == -EINVAL) && cpuset_v2()) {
-		struct cgroup_subsys_state *css;
-		struct cpuset *cp;
-
-		/*
-		 * The -EINVAL error code indicates that partition sibling
-		 * CPU exclusivity rule has been violated. We still allow
-		 * the cpumask change to proceed while invalidating the
-		 * partition. However, any conflicting sibling partitions
-		 * have to be marked as invalid too.
-		 */
-		trialcs->prs_err = PERR_NOTEXCL;
-		rcu_read_lock();
-		cpuset_for_each_child(cp, css, parent) {
-			struct cpumask *xcpus = user_xcpus(trialcs);
-
-			if (is_partition_valid(cp) &&
-			    cpumask_intersects(xcpus, cp->effective_xcpus)) {
-				rcu_read_unlock();
-				update_parent_effective_cpumask(cp, partcmd_invalidate, NULL, tmp);
-				rcu_read_lock();
-			}
-		}
-		rcu_read_unlock();
-		retval = 0;
-	}
-	return retval;
-}
-
 /**
  * partition_cpus_change - Handle partition state changes due to CPU mask updates
  * @cs: The target cpuset being modified
@@ -2559,15 +2338,15 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed))
 		return 0;
 
-	if (alloc_tmpmasks(&tmp))
-		return -ENOMEM;
-
 	compute_trialcs_excpus(trialcs, cs);
 	trialcs->prs_err = PERR_NONE;
 
-	retval = cpus_allowed_validate_change(cs, trialcs, &tmp);
+	retval = validate_change(cs, trialcs);
 	if (retval < 0)
-		goto out_free;
+		return retval;
+
+	if (alloc_tmpmasks(&tmp))
+		return -ENOMEM;
 
 	/*
 	 * Check all the descendants in update_cpumasks_hier() if
@@ -2590,7 +2369,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	/* Update CS_SCHED_LOAD_BALANCE and/or sched_domains, if necessary */
 	if (cs->partition_root_state)
 		update_partition_sd_lb(cs, old_prs);
-out_free:
+
 	free_tmpmasks(&tmp);
 	return retval;
 }
@@ -3249,7 +3028,7 @@ static nodemask_t cpuset_attach_nodemask_to;
 
 static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task)
 {
-	lockdep_assert_held(&cpuset_mutex);
+	lockdep_assert_cpuset_lock_held();
 
 	if (cs != &top_cpuset)
 		guarantee_active_cpus(task, cpus_attach);
@@ -3605,8 +3384,7 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css)
 		return ERR_PTR(-ENOMEM);
 
 	__set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
-	fmeter_init(&cs->fmeter);
-	cs->relax_domain_level = -1;
+	cpuset1_init(cs);
 
 	/* Set CS_MEMORY_MIGRATE for default hierarchy */
 	if (cpuset_v2())
@@ -3619,17 +3397,11 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 {
 	struct cpuset *cs = css_cs(css);
 	struct cpuset *parent = parent_cs(cs);
-	struct cpuset *tmp_cs;
-	struct cgroup_subsys_state *pos_css;
 
 	if (!parent)
 		return 0;
 
 	cpuset_full_lock();
-	if (is_spread_page(parent))
-		set_bit(CS_SPREAD_PAGE, &cs->flags);
-	if (is_spread_slab(parent))
-		set_bit(CS_SPREAD_SLAB, &cs->flags);
 	/*
 	 * For v2, clear CS_SCHED_LOAD_BALANCE if parent is isolated
 	 */
@@ -3644,39 +3416,8 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 		cs->effective_mems = parent->effective_mems;
 	}
 	spin_unlock_irq(&callback_lock);
+	cpuset1_online_css(css);
 
-	if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
-		goto out_unlock;
-
-	/*
-	 * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is
-	 * set.  This flag handling is implemented in cgroup core for
-	 * historical reasons - the flag may be specified during mount.
-	 *
-	 * Currently, if any sibling cpusets have exclusive cpus or mem, we
-	 * refuse to clone the configuration - thereby refusing the task to
-	 * be entered, and as a result refusing the sys_unshare() or
-	 * clone() which initiated it.  If this becomes a problem for some
-	 * users who wish to allow that scenario, then this could be
-	 * changed to grant parent->cpus_allowed-sibling_cpus_exclusive
-	 * (and likewise for mems) to the new cgroup.
-	 */
-	rcu_read_lock();
-	cpuset_for_each_child(tmp_cs, pos_css, parent) {
-		if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) {
-			rcu_read_unlock();
-			goto out_unlock;
-		}
-	}
-	rcu_read_unlock();
-
-	spin_lock_irq(&callback_lock);
-	cs->mems_allowed = parent->mems_allowed;
-	cs->effective_mems = parent->mems_allowed;
-	cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
-	cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
-	spin_unlock_irq(&callback_lock);
-out_unlock:
 	cpuset_full_unlock();
 	return 0;
 }
@@ -3876,7 +3617,7 @@ int __init cpuset_init(void)
 	cpumask_setall(top_cpuset.exclusive_cpus);
 	nodes_setall(top_cpuset.effective_mems);
 
-	fmeter_init(&top_cpuset.fmeter);
+	cpuset1_init(&top_cpuset);
 
 	BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL));
 
@@ -4210,7 +3951,7 @@ static void __cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask
  */
 void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask)
 {
-	lockdep_assert_held(&cpuset_mutex);
+	lockdep_assert_cpuset_lock_held();
 	__cpuset_cpus_allowed_locked(tsk, pmask);
 }
 
diff --git a/kernel/cgroup/debug.c b/kernel/cgroup/debug.c
index 81ea38dd6f9d..a5490097fe52 100644
--- a/kernel/cgroup/debug.c
+++ b/kernel/cgroup/debug.c
@@ -230,7 +230,7 @@ static int cgroup_subsys_states_read(struct seq_file *seq, void *v)
 }
 
 static void cgroup_masks_read_one(struct seq_file *seq, const char *name,
-				  u16 mask)
+				  u32 mask)
 {
 	struct cgroup_subsys *ss;
 	int ssid;