Merge tag 'cgroup-for-6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - Yafang Shao added task_get_cgroup1() helper to enable a similar BPF
   helper so that BPF progs can be more useful on cgroup1 hierarchies.
   While cgroup1 is mostly in maintenance mode, this addition is very
   small while having an outsized usefulness for users who are still on
   cgroup1. Yafang also optimized root cgroup list access by making it
   RCU protected in the process.

 - Waiman Long optimized rstat operation leading to substantially lower
   and more consistent lock hold time while flushing the hierarchical
   statistics. As the lock can be acquired briefly in various hot paths,
   this reduction has cascading benefits.

 - Waiman also improved the quality of isolation for cpuset's isolated
   partitions. CPUs which are allocated to isolated partitions are now
   excluded from running unbound work items and cpu_is_isolated() test
   which is used by vmstat and memcg to reduce interference now includes
   cpuset isolated CPUs. While it isn't there yet, the hope is
   eventually reaching parity with the isolation level provided by the
   `isolcpus` boot param but in a dynamic manner.

* tag 'cgroup-for-6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: Move rcu_head up near the top of cgroup_root
  cgroup/cpuset: Include isolated cpuset CPUs in cpu_is_isolated() check
  cgroup: Avoid false cacheline sharing of read mostly rstat_cpu
  cgroup/rstat: Optimize cgroup_rstat_updated_list()
  cgroup: Fix documentation for cpu.idle
  cgroup/cpuset: Expose cpuset.cpus.isolated
  workqueue: Move workqueue_set_unbound_cpumask() and its helpers inside CONFIG_SYSFS
  cgroup/rstat: Reduce cpu_lock hold time in cgroup_rstat_flush_locked()
  cgroup/cpuset: Take isolated CPUs out of workqueue unbound cpumask
  cgroup/cpuset: Keep track of CPUs in isolated partitions
  selftests/cgroup: Minor code cleanup and reorganization of test_cpuset_prs.sh
  workqueue: Add workqueue_unbound_exclude_cpumask() to exclude CPUs from wq_unbound_cpumask
  selftests: cgroup: Fixes a typo in a comment
  cgroup: Add a new helper for cgroup1 hierarchy
  cgroup: Add annotation for holding namespace_sem in current_cgns_cgroup_from_root()
  cgroup: Eliminate the need for cgroup_mutex in proc_cgroup_show()
  cgroup: Make operations on the cgroup root_list RCU safe
  cgroup: Remove unnecessary list_empty()

5 files changed, 386 insertions, 144 deletions

diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index c56071f150f2..520b90dd97ec 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -164,13 +164,13 @@ struct cgroup_mgctx {
 #define DEFINE_CGROUP_MGCTX(name)						\
 	struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name)
 
-extern spinlock_t css_set_lock;
 extern struct cgroup_subsys *cgroup_subsys[];
 extern struct list_head cgroup_roots;
 
 /* iterate across the hierarchies */
 #define for_each_root(root)						\
-	list_for_each_entry((root), &cgroup_roots, root_list)
+	list_for_each_entry_rcu((root), &cgroup_roots, root_list,	\
+				lockdep_is_held(&cgroup_mutex))
 
 /**
  * for_each_subsys - iterate all enabled cgroup subsystems
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 76db6c67e39a..04d11a7dd95f 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -1262,6 +1262,40 @@ int cgroup1_get_tree(struct fs_context *fc)
 	return ret;
 }
 
+/**
+ * task_get_cgroup1 - Acquires the associated cgroup of a task within a
+ * specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its
+ * hierarchy ID.
+ * @tsk: The target task
+ * @hierarchy_id: The ID of a cgroup1 hierarchy
+ *
+ * On success, the cgroup is returned. On failure, ERR_PTR is returned.
+ * We limit it to cgroup1 only.
+ */
+struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id)
+{
+	struct cgroup *cgrp = ERR_PTR(-ENOENT);
+	struct cgroup_root *root;
+	unsigned long flags;
+
+	rcu_read_lock();
+	for_each_root(root) {
+		/* cgroup1 only*/
+		if (root == &cgrp_dfl_root)
+			continue;
+		if (root->hierarchy_id != hierarchy_id)
+			continue;
+		spin_lock_irqsave(&css_set_lock, flags);
+		cgrp = task_cgroup_from_root(tsk, root);
+		if (!cgrp || !cgroup_tryget(cgrp))
+			cgrp = ERR_PTR(-ENOENT);
+		spin_unlock_irqrestore(&css_set_lock, flags);
+		break;
+	}
+	rcu_read_unlock();
+	return cgrp;
+}
+
 static int __init cgroup1_wq_init(void)
 {
 	/*
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 4b9ff41ca603..8f3cef1a4d8a 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1315,7 +1315,7 @@ static void cgroup_exit_root_id(struct cgroup_root *root)
 
 void cgroup_free_root(struct cgroup_root *root)
 {
-	kfree(root);
+	kfree_rcu(root, rcu);
 }
 
 static void cgroup_destroy_root(struct cgroup_root *root)
@@ -1347,10 +1347,9 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 
 	spin_unlock_irq(&css_set_lock);
 
-	if (!list_empty(&root->root_list)) {
-		list_del(&root->root_list);
-		cgroup_root_count--;
-	}
+	WARN_ON_ONCE(list_empty(&root->root_list));
+	list_del_rcu(&root->root_list);
+	cgroup_root_count--;
 
 	if (!have_favordynmods)
 		cgroup_favor_dynmods(root, false);
@@ -1390,7 +1389,15 @@ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset,
 		}
 	}
 
-	BUG_ON(!res_cgroup);
+	/*
+	 * If cgroup_mutex is not held, the cgrp_cset_link will be freed
+	 * before we remove the cgroup root from the root_list. Consequently,
+	 * when accessing a cgroup root, the cset_link may have already been
+	 * freed, resulting in a NULL res_cgroup. However, by holding the
+	 * cgroup_mutex, we ensure that res_cgroup can't be NULL.
+	 * If we don't hold cgroup_mutex in the caller, we must do the NULL
+	 * check.
+	 */
 	return res_cgroup;
 }
 
@@ -1413,6 +1420,11 @@ current_cgns_cgroup_from_root(struct cgroup_root *root)
 
 	rcu_read_unlock();
 
+	/*
+	 * The namespace_sem is held by current, so the root cgroup can't
+	 * be umounted. Therefore, we can ensure that the res is non-NULL.
+	 */
+	WARN_ON_ONCE(!res);
 	return res;
 }
 
@@ -1449,7 +1461,6 @@ static struct cgroup *current_cgns_cgroup_dfl(void)
 static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
 					    struct cgroup_root *root)
 {
-	lockdep_assert_held(&cgroup_mutex);
 	lockdep_assert_held(&css_set_lock);
 
 	return __cset_cgroup_from_root(cset, root);
@@ -1457,7 +1468,9 @@ static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
 
 /*
  * Return the cgroup for "task" from the given hierarchy. Must be
- * called with cgroup_mutex and css_set_lock held.
+ * called with css_set_lock held to prevent task's groups from being modified.
+ * Must be called with either cgroup_mutex or rcu read lock to prevent the
+ * cgroup root from being destroyed.
  */
 struct cgroup *task_cgroup_from_root(struct task_struct *task,
 				     struct cgroup_root *root)
@@ -2032,7 +2045,7 @@ void init_cgroup_root(struct cgroup_fs_context *ctx)
 	struct cgroup_root *root = ctx->root;
 	struct cgroup *cgrp = &root->cgrp;
 
-	INIT_LIST_HEAD(&root->root_list);
+	INIT_LIST_HEAD_RCU(&root->root_list);
 	atomic_set(&root->nr_cgrps, 1);
 	cgrp->root = root;
 	init_cgroup_housekeeping(cgrp);
@@ -2115,7 +2128,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	 * care of subsystems' refcounts, which are explicitly dropped in
 	 * the failure exit path.
 	 */
-	list_add(&root->root_list, &cgroup_roots);
+	list_add_rcu(&root->root_list, &cgroup_roots);
 	cgroup_root_count++;
 
 	/*
@@ -6265,7 +6278,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 	if (!buf)
 		goto out;
 
-	cgroup_lock();
+	rcu_read_lock();
 	spin_lock_irq(&css_set_lock);
 
 	for_each_root(root) {
@@ -6276,6 +6289,11 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 		if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible))
 			continue;
 
+		cgrp = task_cgroup_from_root(tsk, root);
+		/* The root has already been unmounted. */
+		if (!cgrp)
+			continue;
+
 		seq_printf(m, "%d:", root->hierarchy_id);
 		if (root != &cgrp_dfl_root)
 			for_each_subsys(ss, ssid)
@@ -6286,9 +6304,6 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 			seq_printf(m, "%sname=%s", count ? "," : "",
 				   root->name);
 		seq_putc(m, ':');
-
-		cgrp = task_cgroup_from_root(tsk, root);
-
 		/*
 		 * On traditional hierarchies, all zombie tasks show up as
 		 * belonging to the root cgroup.  On the default hierarchy,
@@ -6320,7 +6335,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 	retval = 0;
 out_unlock:
 	spin_unlock_irq(&css_set_lock);
-	cgroup_unlock();
+	rcu_read_unlock();
 	kfree(buf);
 out:
 	return retval;
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 615daaf87f1f..dfbb16aca9f4 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -25,6 +25,7 @@
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/cpuset.h>
+#include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
@@ -43,6 +44,7 @@
 #include <linux/sched/isolation.h>
 #include <linux/cgroup.h>
 #include <linux/wait.h>
+#include <linux/workqueue.h>
 
 DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key);
 DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key);
@@ -204,6 +206,11 @@ struct cpuset {
  */
 static cpumask_var_t	subpartitions_cpus;
 
+/*
+ * Exclusive CPUs in isolated partitions
+ */
+static cpumask_var_t	isolated_cpus;
+
 /* List of remote partition root children */
 static struct list_head remote_children;
 
@@ -1317,6 +1324,7 @@ static void compute_effective_cpumask(struct cpumask *new_cpus,
  */
 enum partition_cmd {
 	partcmd_enable,		/* Enable partition root	  */
+	partcmd_enablei,	/* Enable isolated partition root */
 	partcmd_disable,	/* Disable partition root	  */
 	partcmd_update,		/* Update parent's effective_cpus */
 	partcmd_invalidate,	/* Make partition invalid	  */
@@ -1419,6 +1427,109 @@ static void reset_partition_data(struct cpuset *cs)
 }
 
 /*
+ * partition_xcpus_newstate - Exclusive CPUs state change
+ * @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)
+{
+	WARN_ON_ONCE(old_prs == new_prs);
+	if (new_prs == PRS_ISOLATED)
+		cpumask_or(isolated_cpus, isolated_cpus, xcpus);
+	else
+		cpumask_andnot(isolated_cpus, isolated_cpus, xcpus);
+}
+
+/*
+ * partition_xcpus_add - Add new exclusive CPUs to partition
+ * @new_prs: new partition_root_state
+ * @parent: parent cpuset
+ * @xcpus: exclusive CPUs to be added
+ * Return: true if isolated_cpus modified, false otherwise
+ *
+ * Remote partition if parent == NULL
+ */
+static bool partition_xcpus_add(int new_prs, struct cpuset *parent,
+				struct cpumask *xcpus)
+{
+	bool isolcpus_updated;
+
+	WARN_ON_ONCE(new_prs < 0);
+	lockdep_assert_held(&callback_lock);
+	if (!parent)
+		parent = &top_cpuset;
+
+
+	if (parent == &top_cpuset)
+		cpumask_or(subpartitions_cpus, subpartitions_cpus, xcpus);
+
+	isolcpus_updated = (new_prs != parent->partition_root_state);
+	if (isolcpus_updated)
+		partition_xcpus_newstate(parent->partition_root_state, new_prs,
+					 xcpus);
+
+	cpumask_andnot(parent->effective_cpus, parent->effective_cpus, xcpus);
+	return isolcpus_updated;
+}
+
+/*
+ * partition_xcpus_del - Remove exclusive CPUs from partition
+ * @old_prs: old partition_root_state
+ * @parent: parent cpuset
+ * @xcpus: exclusive CPUs to be removed
+ * Return: true if isolated_cpus modified, false otherwise
+ *
+ * Remote partition if parent == NULL
+ */
+static bool partition_xcpus_del(int old_prs, struct cpuset *parent,
+				struct cpumask *xcpus)
+{
+	bool isolcpus_updated;
+
+	WARN_ON_ONCE(old_prs < 0);
+	lockdep_assert_held(&callback_lock);
+	if (!parent)
+		parent = &top_cpuset;
+
+	if (parent == &top_cpuset)
+		cpumask_andnot(subpartitions_cpus, subpartitions_cpus, xcpus);
+
+	isolcpus_updated = (old_prs != parent->partition_root_state);
+	if (isolcpus_updated)
+		partition_xcpus_newstate(old_prs, parent->partition_root_state,
+					 xcpus);
+
+	cpumask_and(xcpus, xcpus, cpu_active_mask);
+	cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus);
+	return isolcpus_updated;
+}
+
+static void update_unbound_workqueue_cpumask(bool isolcpus_updated)
+{
+	int ret;
+
+	lockdep_assert_cpus_held();
+
+	if (!isolcpus_updated)
+		return;
+
+	ret = workqueue_unbound_exclude_cpumask(isolated_cpus);
+	WARN_ON_ONCE(ret < 0);
+}
+
+/**
+ * cpuset_cpu_is_isolated - Check if the given CPU is isolated
+ * @cpu: the CPU number to be checked
+ * Return: true if CPU is used in an isolated partition, false otherwise
+ */
+bool cpuset_cpu_is_isolated(int cpu)
+{
+	return cpumask_test_cpu(cpu, isolated_cpus);
+}
+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
@@ -1456,14 +1567,18 @@ static inline bool is_local_partition(struct cpuset *cs)
 /*
  * remote_partition_enable - Enable current cpuset as a remote partition root
  * @cs: the cpuset to update
+ * @new_prs: new partition_root_state
  * @tmp: temparary masks
  * Return: 1 if successful, 0 if error
  *
  * Enable the current cpuset to become a remote partition root taking CPUs
  * directly from the top cpuset. cpuset_mutex must be held by the caller.
  */
-static int remote_partition_enable(struct cpuset *cs, struct tmpmasks *tmp)
+static int remote_partition_enable(struct cpuset *cs, int new_prs,
+				   struct tmpmasks *tmp)
 {
+	bool isolcpus_updated;
+
 	/*
 	 * The user must have sysadmin privilege.
 	 */
@@ -1485,26 +1600,22 @@ static int remote_partition_enable(struct cpuset *cs, struct tmpmasks *tmp)
 		return 0;
 
 	spin_lock_irq(&callback_lock);
-	cpumask_andnot(top_cpuset.effective_cpus,
-		       top_cpuset.effective_cpus, tmp->new_cpus);
-	cpumask_or(subpartitions_cpus,
-		   subpartitions_cpus, tmp->new_cpus);
-
+	isolcpus_updated = partition_xcpus_add(new_prs, NULL, tmp->new_cpus);
+	list_add(&cs->remote_sibling, &remote_children);
 	if (cs->use_parent_ecpus) {
 		struct cpuset *parent = parent_cs(cs);
 
 		cs->use_parent_ecpus = false;
 		parent->child_ecpus_count--;
 	}
-	list_add(&cs->remote_sibling, &remote_children);
 	spin_unlock_irq(&callback_lock);
+	update_unbound_workqueue_cpumask(isolcpus_updated);
 
 	/*
 	 * Proprogate changes in top_cpuset's effective_cpus down the hierarchy.
 	 */
 	update_tasks_cpumask(&top_cpuset, tmp->new_cpus);
 	update_sibling_cpumasks(&top_cpuset, NULL, tmp);
-
 	return 1;
 }
 
@@ -1519,23 +1630,22 @@ static int remote_partition_enable(struct cpuset *cs, struct tmpmasks *tmp)
  */
 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));
 
 	spin_lock_irq(&callback_lock);
-	cpumask_andnot(subpartitions_cpus,
-		       subpartitions_cpus, tmp->new_cpus);
-	cpumask_and(tmp->new_cpus,
-		    tmp->new_cpus, cpu_active_mask);
-	cpumask_or(top_cpuset.effective_cpus,
-		   top_cpuset.effective_cpus, tmp->new_cpus);
 	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;
 	reset_partition_data(cs);
 	spin_unlock_irq(&callback_lock);
+	update_unbound_workqueue_cpumask(isolcpus_updated);
 
 	/*
 	 * Proprogate changes in top_cpuset's effective_cpus down the hierarchy.
@@ -1557,6 +1667,8 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask,
 			       struct tmpmasks *tmp)
 {
 	bool adding, deleting;
+	int prs = cs->partition_root_state;
+	int isolcpus_updated = 0;
 
 	if (WARN_ON_ONCE(!is_remote_partition(cs)))
 		return;
@@ -1580,21 +1692,12 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask,
 		goto invalidate;
 
 	spin_lock_irq(&callback_lock);
-	if (adding) {
-		cpumask_or(subpartitions_cpus,
-			   subpartitions_cpus, tmp->addmask);
-		cpumask_andnot(top_cpuset.effective_cpus,
-			       top_cpuset.effective_cpus, tmp->addmask);
-	}
-	if (deleting) {
-		cpumask_andnot(subpartitions_cpus,
-			       subpartitions_cpus, tmp->delmask);
-		cpumask_and(tmp->delmask,
-			    tmp->delmask, cpu_active_mask);
-		cpumask_or(top_cpuset.effective_cpus,
-			   top_cpuset.effective_cpus, tmp->delmask);
-	}
+	if (adding)
+		isolcpus_updated += partition_xcpus_add(prs, NULL, tmp->addmask);
+	if (deleting)
+		isolcpus_updated += partition_xcpus_del(prs, NULL, tmp->delmask);
 	spin_unlock_irq(&callback_lock);
+	update_unbound_workqueue_cpumask(isolcpus_updated);
 
 	/*
 	 * Proprogate changes in top_cpuset's effective_cpus down the hierarchy.
@@ -1676,11 +1779,11 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
  * @tmp:     Temporary addmask and delmask
  * Return:   0 or a partition root state error code
  *
- * For partcmd_enable, the cpuset is being transformed from a non-partition
- * root to a partition root. The effective_xcpus (cpus_allowed if effective_xcpus
- * not set) mask of the given cpuset will be taken away from parent's
- * effective_cpus. The function will return 0 if all the CPUs listed in
- * effective_xcpus can be granted or an error code will be returned.
+ * For partcmd_enable*, the cpuset is being transformed from a non-partition
+ * root to a partition root. The effective_xcpus (cpus_allowed if
+ * effective_xcpus not set) mask of the given cpuset will be taken away from
+ * parent's effective_cpus. The function will return 0 if all the CPUs listed
+ * in effective_xcpus can be granted or an error code will be returned.
  *
  * For partcmd_disable, the cpuset is being transformed from a partition
  * root back to a non-partition root. Any CPUs in effective_xcpus will be
@@ -1695,7 +1798,7 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
  *
  * For partcmd_invalidate, the current partition will be made invalid.
  *
- * The partcmd_enable and partcmd_disable commands are used by
+ * The partcmd_enable* and partcmd_disable commands are used by
  * update_prstate(). An error code may be returned and the caller will check
  * for error.
  *
@@ -1716,6 +1819,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 	int part_error = PERR_NONE;	/* Partition error? */
 	int subparts_delta = 0;
 	struct cpumask *xcpus;		/* cs effective_xcpus */
+	int isolcpus_updated = 0;
 	bool nocpu;
 
 	lockdep_assert_held(&cpuset_mutex);
@@ -1760,7 +1864,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 
 	nocpu = tasks_nocpu_error(parent, cs, xcpus);
 
-	if (cmd == partcmd_enable) {
+	if ((cmd == partcmd_enable) || (cmd == partcmd_enablei)) {
 		/*
 		 * Enabling partition root is not allowed if its
 		 * effective_xcpus is empty or doesn't overlap with
@@ -1783,6 +1887,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		cpumask_copy(tmp->delmask, xcpus);
 		deleting = true;
 		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
@@ -1792,6 +1897,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 			  cpumask_and(tmp->addmask, xcpus, parent->effective_xcpus);
 		if (adding)
 			subparts_delta--;
+		new_prs = PRS_MEMBER;
 	} else if (newmask) {
 		/*
 		 * Empty cpumask is not allowed
@@ -1940,38 +2046,28 @@ write_error:
 	 * newly deleted ones will be added back to effective_cpus.
 	 */
 	spin_lock_irq(&callback_lock);
-	if (adding) {
-		if (parent == &top_cpuset)
-			cpumask_andnot(subpartitions_cpus,
-				       subpartitions_cpus, tmp->addmask);
-		/*
-		 * Some of the CPUs in effective_xcpus might have been offlined.
-		 */
-		cpumask_or(parent->effective_cpus,
-			   parent->effective_cpus, tmp->addmask);
-		cpumask_and(parent->effective_cpus,
-			    parent->effective_cpus, cpu_active_mask);
-	}
-	if (deleting) {
-		if (parent == &top_cpuset)
-			cpumask_or(subpartitions_cpus,
-				   subpartitions_cpus, tmp->delmask);
-		cpumask_andnot(parent->effective_cpus,
-			       parent->effective_cpus, tmp->delmask);
-	}
-
-	if (is_partition_valid(parent)) {
-		parent->nr_subparts += subparts_delta;
-		WARN_ON_ONCE(parent->nr_subparts < 0);
-	}
-
 	if (old_prs != new_prs) {
 		cs->partition_root_state = new_prs;
 		if (new_prs <= 0)
 			cs->nr_subparts = 0;
 	}
+	/*
+	 * Adding to parent's effective_cpus means deletion CPUs from cs
+	 * and vice versa.
+	 */
+	if (adding)
+		isolcpus_updated += partition_xcpus_del(old_prs, parent,
+							tmp->addmask);
+	if (deleting)
+		isolcpus_updated += partition_xcpus_add(new_prs, parent,
+							tmp->delmask);
 
+	if (is_partition_valid(parent)) {
+		parent->nr_subparts += subparts_delta;
+		WARN_ON_ONCE(parent->nr_subparts < 0);
+	}
 	spin_unlock_irq(&callback_lock);
+	update_unbound_workqueue_cpumask(isolcpus_updated);
 
 	if ((old_prs != new_prs) && (cmd == partcmd_update))
 		update_partition_exclusive(cs, new_prs);
@@ -2948,6 +3044,7 @@ 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;
 
 	if (old_prs == new_prs)
 		return 0;
@@ -2977,6 +3074,9 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 		goto out;
 
 	if (!old_prs) {
+		enum partition_cmd cmd = (new_prs == PRS_ROOT)
+				       ? partcmd_enable : partcmd_enablei;
+
 		/*
 		 * cpus_allowed cannot be empty.
 		 */
@@ -2985,19 +3085,18 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 			goto out;
 		}
 
-		err = update_parent_effective_cpumask(cs, partcmd_enable,
-						      NULL, &tmpmask);
+		err = update_parent_effective_cpumask(cs, cmd, NULL, &tmpmask);
 		/*
 		 * If an attempt to become local partition root fails,
 		 * try to become a remote partition root instead.
 		 */
-		if (err && remote_partition_enable(cs, &tmpmask))
+		if (err && remote_partition_enable(cs, new_prs, &tmpmask))
 			err = 0;
 	} else if (old_prs && new_prs) {
 		/*
 		 * A change in load balance state only, no change in cpumasks.
 		 */
-		;
+		new_xcpus_state = true;
 	} else {
 		/*
 		 * Switching back to member is always allowed even if it
@@ -3029,7 +3128,10 @@ 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);
 	spin_unlock_irq(&callback_lock);
+	update_unbound_workqueue_cpumask(new_xcpus_state);
 
 	/* Force update if switching back to member */
 	update_cpumasks_hier(cs, &tmpmask, !new_prs ? HIER_CHECKALL : 0);
@@ -3386,6 +3488,7 @@ typedef enum {
 	FILE_SUBPARTS_CPULIST,
 	FILE_EXCLUSIVE_CPULIST,
 	FILE_EFFECTIVE_XCPULIST,
+	FILE_ISOLATED_CPULIST,
 	FILE_CPU_EXCLUSIVE,
 	FILE_MEM_EXCLUSIVE,
 	FILE_MEM_HARDWALL,
@@ -3582,6 +3685,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
 	case FILE_SUBPARTS_CPULIST:
 		seq_printf(sf, "%*pbl\n", cpumask_pr_args(subpartitions_cpus));
 		break;
+	case FILE_ISOLATED_CPULIST:
+		seq_printf(sf, "%*pbl\n", cpumask_pr_args(isolated_cpus));
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -3875,6 +3981,13 @@ static struct cftype dfl_files[] = {
 		.flags = CFTYPE_ONLY_ON_ROOT | CFTYPE_DEBUG,
 	},
 
+	{
+		.name = "cpus.isolated",
+		.seq_show = cpuset_common_seq_show,
+		.private = FILE_ISOLATED_CPULIST,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
 	{ }	/* terminate */
 };
 
@@ -4194,6 +4307,7 @@ int __init cpuset_init(void)
 	BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_xcpus, GFP_KERNEL));
 	BUG_ON(!alloc_cpumask_var(&top_cpuset.exclusive_cpus, GFP_KERNEL));
 	BUG_ON(!zalloc_cpumask_var(&subpartitions_cpus, GFP_KERNEL));
+	BUG_ON(!zalloc_cpumask_var(&isolated_cpus, GFP_KERNEL));
 
 	cpumask_setall(top_cpuset.cpus_allowed);
 	nodes_setall(top_cpuset.mems_allowed);
@@ -4306,6 +4420,30 @@ void cpuset_force_rebuild(void)
 	force_rebuild = true;
 }
 
+/*
+ * Attempt to acquire a cpus_read_lock while a hotplug operation may be in
+ * progress.
+ * Return: true if successful, false otherwise
+ *
+ * To avoid circular lock dependency between cpuset_mutex and cpus_read_lock,
+ * cpus_read_trylock() is used here to acquire the lock.
+ */
+static bool cpuset_hotplug_cpus_read_trylock(void)
+{
+	int retries = 0;
+
+	while (!cpus_read_trylock()) {
+		/*
+		 * CPU hotplug still in progress. Retry 5 times
+		 * with a 10ms wait before bailing out.
+		 */
+		if (++retries > 5)
+			return false;
+		msleep(10);
+	}
+	return true;
+}
+
 /**
  * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug
  * @cs: cpuset in interest
@@ -4322,6 +4460,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 	bool cpus_updated;
 	bool mems_updated;
 	bool remote;
+	int partcmd = -1;
 	struct cpuset *parent;
 retry:
 	wait_event(cpuset_attach_wq, cs->attach_in_progress == 0);
@@ -4353,11 +4492,13 @@ retry:
 		compute_partition_effective_cpumask(cs, &new_cpus);
 
 	if (remote && cpumask_empty(&new_cpus) &&
-	    partition_is_populated(cs, NULL)) {
+	    partition_is_populated(cs, NULL) &&
+	    cpuset_hotplug_cpus_read_trylock()) {
 		remote_partition_disable(cs, tmp);
 		compute_effective_cpumask(&new_cpus, cs, parent);
 		remote = false;
 		cpuset_force_rebuild();
+		cpus_read_unlock();
 	}
 
 	/*
@@ -4368,18 +4509,28 @@ retry:
 	 *    partitions.
 	 */
 	if (is_local_partition(cs) && (!is_partition_valid(parent) ||
-				tasks_nocpu_error(parent, cs, &new_cpus))) {
-		update_parent_effective_cpumask(cs, partcmd_invalidate, NULL, tmp);
-		compute_effective_cpumask(&new_cpus, cs, parent);
-		cpuset_force_rebuild();
-	}
+				tasks_nocpu_error(parent, cs, &new_cpus)))
+		partcmd = partcmd_invalidate;
 	/*
 	 * On the other hand, an invalid partition root may be transitioned
 	 * back to a regular one.
 	 */
-	else if (is_partition_valid(parent) && is_partition_invalid(cs)) {
-		update_parent_effective_cpumask(cs, partcmd_update, NULL, tmp);
-		if (is_partition_valid(cs)) {
+	else if (is_partition_valid(parent) && is_partition_invalid(cs))
+		partcmd = partcmd_update;
+
+	/*
+	 * cpus_read_lock needs to be held before calling
+	 * update_parent_effective_cpumask(). To avoid circular lock
+	 * dependency between cpuset_mutex and cpus_read_lock,
+	 * cpus_read_trylock() is used here to acquire the lock.
+	 */
+	if (partcmd >= 0) {
+		if (!cpuset_hotplug_cpus_read_trylock())
+			goto update_tasks;
+
+		update_parent_effective_cpumask(cs, partcmd, NULL, tmp);
+		cpus_read_unlock();
+		if ((partcmd == partcmd_invalidate) || is_partition_valid(cs)) {
 			compute_partition_effective_cpumask(cs, &new_cpus);
 			cpuset_force_rebuild();
 		}
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index c0adb7254b45..a8350d2d63e6 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -74,64 +74,109 @@ __bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
 }
 
 /**
- * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree
- * @pos: current position
- * @root: root of the tree to traversal
+ * cgroup_rstat_push_children - push children cgroups into the given list
+ * @head: current head of the list (= subtree root)
+ * @child: first child of the root
  * @cpu: target cpu
+ * Return: A new singly linked list of cgroups to be flush
  *
- * Walks the updated rstat_cpu tree on @cpu from @root.  %NULL @pos starts
- * the traversal and %NULL return indicates the end.  During traversal,
- * each returned cgroup is unlinked from the tree.  Must be called with the
- * matching cgroup_rstat_cpu_lock held.
+ * Iteratively traverse down the cgroup_rstat_cpu updated tree level by
+ * level and push all the parents first before their next level children
+ * into a singly linked list built from the tail backward like "pushing"
+ * cgroups into a stack. The root is pushed by the caller.
+ */
+static struct cgroup *cgroup_rstat_push_children(struct cgroup *head,
+						 struct cgroup *child, int cpu)
+{
+	struct cgroup *chead = child;	/* Head of child cgroup level */
+	struct cgroup *ghead = NULL;	/* Head of grandchild cgroup level */
+	struct cgroup *parent, *grandchild;
+	struct cgroup_rstat_cpu *crstatc;
+
+	child->rstat_flush_next = NULL;
+
+next_level:
+	while (chead) {
+		child = chead;
+		chead = child->rstat_flush_next;
+		parent = cgroup_parent(child);
+
+		/* updated_next is parent cgroup terminated */
+		while (child != parent) {
+			child->rstat_flush_next = head;
+			head = child;
+			crstatc = cgroup_rstat_cpu(child, cpu);
+			grandchild = crstatc->updated_children;
+			if (grandchild != child) {
+				/* Push the grand child to the next level */
+				crstatc->updated_children = child;
+				grandchild->rstat_flush_next = ghead;
+				ghead = grandchild;
+			}
+			child = crstatc->updated_next;
+			crstatc->updated_next = NULL;
+		}
+	}
+
+	if (ghead) {
+		chead = ghead;
+		ghead = NULL;
+		goto next_level;
+	}
+	return head;
+}
+
+/**
+ * cgroup_rstat_updated_list - return a list of updated cgroups to be flushed
+ * @root: root of the cgroup subtree to traverse
+ * @cpu: target cpu
+ * Return: A singly linked list of cgroups to be flushed
+ *
+ * Walks the updated rstat_cpu tree on @cpu from @root.  During traversal,
+ * each returned cgroup is unlinked from the updated tree.
  *
  * The only ordering guarantee is that, for a parent and a child pair
- * covered by a given traversal, if a child is visited, its parent is
- * guaranteed to be visited afterwards.
+ * covered by a given traversal, the child is before its parent in
+ * the list.
+ *
+ * Note that updated_children is self terminated and points to a list of
+ * child cgroups if not empty. Whereas updated_next is like a sibling link
+ * within the children list and terminated by the parent cgroup. An exception
+ * here is the cgroup root whose updated_next can be self terminated.
  */
-static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
-						   struct cgroup *root, int cpu)
+static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu)
 {
-	struct cgroup_rstat_cpu *rstatc;
-	struct cgroup *parent;
-
-	if (pos == root)
-		return NULL;
+	raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
+	struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(root, cpu);
+	struct cgroup *head = NULL, *parent, *child;
+	unsigned long flags;
 
 	/*
-	 * We're gonna walk down to the first leaf and visit/remove it.  We
-	 * can pick whatever unvisited node as the starting point.
+	 * The _irqsave() is needed because cgroup_rstat_lock is
+	 * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring
+	 * this lock with the _irq() suffix only disables interrupts on
+	 * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables
+	 * interrupts on both configurations. The _irqsave() ensures
+	 * that interrupts are always disabled and later restored.
 	 */
-	if (!pos) {
-		pos = root;
-		/* return NULL if this subtree is not on-list */
-		if (!cgroup_rstat_cpu(pos, cpu)->updated_next)
-			return NULL;
-	} else {
-		pos = cgroup_parent(pos);
-	}
+	raw_spin_lock_irqsave(cpu_lock, flags);
 
-	/* walk down to the first leaf */
-	while (true) {
-		rstatc = cgroup_rstat_cpu(pos, cpu);
-		if (rstatc->updated_children == pos)
-			break;
-		pos = rstatc->updated_children;
-	}
+	/* Return NULL if this subtree is not on-list */
+	if (!rstatc->updated_next)
+		goto unlock_ret;
 
 	/*
-	 * Unlink @pos from the tree.  As the updated_children list is
+	 * Unlink @root from its parent. As the updated_children list is
 	 * singly linked, we have to walk it to find the removal point.
-	 * However, due to the way we traverse, @pos will be the first
-	 * child in most cases. The only exception is @root.
 	 */
-	parent = cgroup_parent(pos);
+	parent = cgroup_parent(root);
 	if (parent) {
 		struct cgroup_rstat_cpu *prstatc;
 		struct cgroup **nextp;
 
 		prstatc = cgroup_rstat_cpu(parent, cpu);
 		nextp = &prstatc->updated_children;
-		while (*nextp != pos) {
+		while (*nextp != root) {
 			struct cgroup_rstat_cpu *nrstatc;
 
 			nrstatc = cgroup_rstat_cpu(*nextp, cpu);
@@ -142,7 +187,17 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 	}
 
 	rstatc->updated_next = NULL;
-	return pos;
+
+	/* Push @root to the list first before pushing the children */
+	head = root;
+	root->rstat_flush_next = NULL;
+	child = rstatc->updated_children;
+	rstatc->updated_children = root;
+	if (child != root)
+		head = cgroup_rstat_push_children(head, child, cpu);
+unlock_ret:
+	raw_spin_unlock_irqrestore(cpu_lock, flags);
+	return head;
 }
 
 /*
@@ -176,21 +231,9 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
 	lockdep_assert_held(&cgroup_rstat_lock);
 
 	for_each_possible_cpu(cpu) {
-		raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock,
-						       cpu);
-		struct cgroup *pos = NULL;
-		unsigned long flags;
+		struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu);
 
-		/*
-		 * The _irqsave() is needed because cgroup_rstat_lock is
-		 * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring
-		 * this lock with the _irq() suffix only disables interrupts on
-		 * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables
-		 * interrupts on both configurations. The _irqsave() ensures
-		 * that interrupts are always disabled and later restored.
-		 */
-		raw_spin_lock_irqsave(cpu_lock, flags);
-		while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) {
+		for (; pos; pos = pos->rstat_flush_next) {
 			struct cgroup_subsys_state *css;
 
 			cgroup_base_stat_flush(pos, cpu);
@@ -202,7 +245,6 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
 				css->ss->css_rstat_flush(css, cpu);
 			rcu_read_unlock();
 		}
-		raw_spin_unlock_irqrestore(cpu_lock, flags);
 
 		/* play nice and yield if necessary */
 		if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) {