cgroup: Changes for v6.19

- Defer task cgroup unlink until after the dying task's final context switch
   so that controllers see the cgroup properly populated until the task is
   truly gone.
 
 - cpuset cleanups and simplifications. Enforce that domain isolated CPUs
   stay in root or isolated partitions and fail if isolated+nohz_full would
   leave no housekeeping CPU. Fix sched/deadline root domain handling during
   CPU hot-unplug and race for tasks in attaching cpusets.
 
 - Misc fixes including memory reclaim protection documentation and selftest
   KTAP conformance.
 -----BEGIN PGP SIGNATURE-----
 
 iIQEABYKACwWIQTfIjM1kS57o3GsC/uxYfJx3gVYGQUCaS3pEQ4cdGpAa2VybmVs
 Lm9yZwAKCRCxYfJx3gVYGYbrAP9H0kVyWH5tK9VhjSZyqidic8NuvtmNOyhIRrg0
 8S8K0wD/YG9xlh2JUyRmS4B23ggc59+9y5xM2/sctrho51Pvsgg=
 =0MB+
 -----END PGP SIGNATURE-----

Merge tag 'cgroup-for-6.19' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - Defer task cgroup unlink until after the dying task's final context
   switch so that controllers see the cgroup properly populated until
   the task is truly gone

 - cpuset cleanups and simplifications.

   Enforce that domain isolated CPUs stay in root or isolated partitions
   and fail if isolated+nohz_full would leave no housekeeping CPU. Fix
   sched/deadline root domain handling during CPU hot-unplug and race
   for tasks in attaching cpusets

 - Misc fixes including memory reclaim protection documentation and
   selftest KTAP conformance

* tag 'cgroup-for-6.19' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (21 commits)
  cpuset: Treat cpusets in attaching as populated
  sched/deadline: Walk up cpuset hierarchy to decide root domain when hot-unplug
  cgroup/cpuset: Introduce cpuset_cpus_allowed_locked()
  docs: cgroup: No special handling of unpopulated memcgs
  docs: cgroup: Note about sibling relative reclaim protection
  docs: cgroup: Explain reclaim protection target
  selftests/cgroup: conform test to KTAP format output
  cpuset: remove need_rebuild_sched_domains
  cpuset: remove global remote_children list
  cpuset: simplify node setting on error
  cgroup: include missing header for struct irq_work
  cgroup: Fix sleeping from invalid context warning on PREEMPT_RT
  cgroup/cpuset: Globally track isolated_cpus update
  cgroup/cpuset: Ensure domain isolated CPUs stay in root or isolated partition
  cgroup/cpuset: Move up prstate_housekeeping_conflict() helper
  cgroup/cpuset: Fail if isolated and nohz_full don't leave any housekeeping
  cgroup/cpuset: Rename update_unbound_workqueue_cpumask() to update_isolation_cpumasks()
  cgroup: Defer task cgroup unlink until after the task is done switching out
  cgroup: Move dying_tasks cleanup from cgroup_task_release() to cgroup_task_free()
  cgroup: Rename cgroup lifecycle hooks to cgroup_task_*()
  ...

Documentation/admin-guide/cgroup-v2.rst

@@ -53,7 +53,8 @@ v1 is available under :ref:`Documentation/admin-guide/cgroup-v1/index.rst <cgrou
      5-2. Memory
        5-2-1. Memory Interface Files
        5-2-2. Usage Guidelines
-       5-2-3. Memory Ownership
+       5-2-3. Reclaim Protection
+       5-2-4. Memory Ownership
      5-3. IO
        5-3-1. IO Interface Files
        5-3-2. Writeback
@@ -1317,7 +1318,7 @@ PAGE_SIZE multiple when read back.
 	smaller overages.
 
 	Effective min boundary is limited by memory.min values of
-	all ancestor cgroups. If there is memory.min overcommitment
+	ancestor cgroups. If there is memory.min overcommitment
 	(child cgroup or cgroups are requiring more protected memory
 	than parent will allow), then each child cgroup will get
 	the part of parent's protection proportional to its
@@ -1326,9 +1327,6 @@ PAGE_SIZE multiple when read back.
 	Putting more memory than generally available under this
 	protection is discouraged and may lead to constant OOMs.
 
-	If a memory cgroup is not populated with processes,
-	its memory.min is ignored.
-
   memory.low
 	A read-write single value file which exists on non-root
 	cgroups.  The default is "0".
@@ -1343,7 +1341,7 @@ PAGE_SIZE multiple when read back.
 	smaller overages.
 
 	Effective low boundary is limited by memory.low values of
-	all ancestor cgroups. If there is memory.low overcommitment
+	ancestor cgroups. If there is memory.low overcommitment
 	(child cgroup or cgroups are requiring more protected memory
 	than parent will allow), then each child cgroup will get
 	the part of parent's protection proportional to its
@@ -1934,6 +1932,27 @@ memory - is necessary to determine whether a workload needs more
 memory; unfortunately, memory pressure monitoring mechanism isn't
 implemented yet.
 
+Reclaim Protection
+~~~~~~~~~~~~~~~~~~
+
+The protection configured with "memory.low" or "memory.min" applies relatively
+to the target of the reclaim (i.e. any of memory cgroup limits, proactive
+memory.reclaim or global reclaim apparently located in the root cgroup).
+The protection value configured for B applies unchanged to the reclaim
+targeting A (i.e. caused by competition with the sibling E)::
+
+		root - ... - A - B - C
+		              \    ` D
+		               ` E
+
+When the reclaim targets ancestors of A, the effective protection of B is
+capped by the protection value configured for A (and any other intermediate
+ancestors between A and the target).
+
+To express indifference about relative sibling protection, it is suggested to
+use memory_recursiveprot. Configuring all descendants of a parent with finite
+protection to "max" works but it may unnecessarily skew memory.events:low
+field.
 
 Memory Ownership
 ~~~~~~~~~~~~~~~~

include/linux/cgroup.h

@@ -137,9 +137,10 @@ extern void cgroup_cancel_fork(struct task_struct *p,
 			       struct kernel_clone_args *kargs);
 extern void cgroup_post_fork(struct task_struct *p,
 			     struct kernel_clone_args *kargs);
-void cgroup_exit(struct task_struct *p);
+void cgroup_task_exit(struct task_struct *p);
-void cgroup_release(struct task_struct *p);
+void cgroup_task_dead(struct task_struct *p);
-void cgroup_free(struct task_struct *p);
+void cgroup_task_release(struct task_struct *p);
+void cgroup_task_free(struct task_struct *p);
 
 int cgroup_init_early(void);
 int cgroup_init(void);
@@ -680,9 +681,10 @@ static inline void cgroup_cancel_fork(struct task_struct *p,
 				      struct kernel_clone_args *kargs) {}
 static inline void cgroup_post_fork(struct task_struct *p,
 				    struct kernel_clone_args *kargs) {}
-static inline void cgroup_exit(struct task_struct *p) {}
+static inline void cgroup_task_exit(struct task_struct *p) {}
-static inline void cgroup_release(struct task_struct *p) {}
+static inline void cgroup_task_dead(struct task_struct *p) {}
-static inline void cgroup_free(struct task_struct *p) {}
+static inline void cgroup_task_release(struct task_struct *p) {}
+static inline void cgroup_task_free(struct task_struct *p) {}
 
 static inline int cgroup_init_early(void) { return 0; }
 static inline int cgroup_init(void) { return 0; }

include/linux/cpuset.h

@@ -74,6 +74,7 @@ extern void inc_dl_tasks_cs(struct task_struct *task);
 extern void dec_dl_tasks_cs(struct task_struct *task);
 extern void cpuset_lock(void);
 extern void cpuset_unlock(void);
+extern void cpuset_cpus_allowed_locked(struct task_struct *p, struct cpumask *mask);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
 extern bool cpuset_cpus_allowed_fallback(struct task_struct *p);
 extern bool cpuset_cpu_is_isolated(int cpu);
@@ -195,12 +196,18 @@ static inline void dec_dl_tasks_cs(struct task_struct *task) { }
 static inline void cpuset_lock(void) { }
 static inline void cpuset_unlock(void) { }
 
-static inline void cpuset_cpus_allowed(struct task_struct *p,
+static inline void cpuset_cpus_allowed_locked(struct task_struct *p,
 					struct cpumask *mask)
 {
 	cpumask_copy(mask, task_cpu_possible_mask(p));
 }
 
+static inline void cpuset_cpus_allowed(struct task_struct *p,
+				       struct cpumask *mask)
+{
+	cpuset_cpus_allowed_locked(p, mask);
+}
+
 static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p)
 {
 	return false;

include/linux/sched.h

@@ -1324,7 +1324,10 @@ struct task_struct {
 	struct css_set __rcu		*cgroups;
 	/* cg_list protected by css_set_lock and tsk->alloc_lock: */
 	struct list_head		cg_list;
-#endif
+#ifdef CONFIG_PREEMPT_RT
+	struct llist_node		cg_dead_lnode;
+#endif	/* CONFIG_PREEMPT_RT */
+#endif	/* CONFIG_CGROUPS */
 #ifdef CONFIG_X86_CPU_RESCTRL
 	u32				closid;
 	u32				rmid;

kernel/cgroup/cgroup.c

@@ -60,6 +60,7 @@
 #include <linux/sched/deadline.h>
 #include <linux/psi.h>
 #include <linux/nstree.h>
+#include <linux/irq_work.h>
 #include <net/sock.h>
 
 #define CREATE_TRACE_POINTS
@@ -287,6 +288,7 @@ static void kill_css(struct cgroup_subsys_state *css);
 static int cgroup_addrm_files(struct cgroup_subsys_state *css,
 			      struct cgroup *cgrp, struct cftype cfts[],
 			      bool is_add);
+static void cgroup_rt_init(void);
 
 #ifdef CONFIG_DEBUG_CGROUP_REF
 #define CGROUP_REF_FN_ATTRS	noinline
@@ -941,7 +943,8 @@ static void css_set_move_task(struct task_struct *task,
 		/*
 		 * We are synchronized through cgroup_threadgroup_rwsem
 		 * against PF_EXITING setting such that we can't race
-		 * against cgroup_exit()/cgroup_free() dropping the css_set.
+		 * against cgroup_task_dead()/cgroup_task_free() dropping
+		 * the css_set.
 		 */
 		WARN_ON_ONCE(task->flags & PF_EXITING);
 
@@ -6354,6 +6357,7 @@ int __init cgroup_init(void)
 	BUG_ON(ss_rstat_init(NULL));
 
 	get_user_ns(init_cgroup_ns.user_ns);
+	cgroup_rt_init();
 
 	cgroup_lock();
 
@@ -6967,19 +6971,29 @@ void cgroup_post_fork(struct task_struct *child,
 }
 
 /**
- * cgroup_exit - detach cgroup from exiting task
+ * cgroup_task_exit - detach cgroup from exiting task
  * @tsk: pointer to task_struct of exiting process
  *
  * Description: Detach cgroup from @tsk.
  *
  */
-void cgroup_exit(struct task_struct *tsk)
+void cgroup_task_exit(struct task_struct *tsk)
 {
 	struct cgroup_subsys *ss;
-	struct css_set *cset;
 	int i;
 
-	spin_lock_irq(&css_set_lock);
+	/* see cgroup_post_fork() for details */
+	do_each_subsys_mask(ss, i, have_exit_callback) {
+		ss->exit(tsk);
+	} while_each_subsys_mask();
+}
+
+static void do_cgroup_task_dead(struct task_struct *tsk)
+{
+	struct css_set *cset;
+	unsigned long flags;
+
+	spin_lock_irqsave(&css_set_lock, flags);
 
 	WARN_ON_ONCE(list_empty(&tsk->cg_list));
 	cset = task_css_set(tsk);
@@ -6997,15 +7011,61 @@ void cgroup_exit(struct task_struct *tsk)
 		     test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags)))
 		cgroup_update_frozen(task_dfl_cgroup(tsk));
 
-	spin_unlock_irq(&css_set_lock);
+	spin_unlock_irqrestore(&css_set_lock, flags);
-
-	/* see cgroup_post_fork() for details */
-	do_each_subsys_mask(ss, i, have_exit_callback) {
-		ss->exit(tsk);
-	} while_each_subsys_mask();
 }
 
-void cgroup_release(struct task_struct *task)
+#ifdef CONFIG_PREEMPT_RT
+/*
+ * cgroup_task_dead() is called from finish_task_switch() which doesn't allow
+ * scheduling even in RT. As the task_dead path requires grabbing css_set_lock,
+ * this lead to sleeping in the invalid context warning bug. css_set_lock is too
+ * big to become a raw_spinlock. The task_dead path doesn't need to run
+ * synchronously but can't be delayed indefinitely either as the dead task pins
+ * the cgroup and task_struct can be pinned indefinitely. Bounce through lazy
+ * irq_work to allow batching while ensuring timely completion.
+ */
+static DEFINE_PER_CPU(struct llist_head, cgrp_dead_tasks);
+static DEFINE_PER_CPU(struct irq_work, cgrp_dead_tasks_iwork);
+
+static void cgrp_dead_tasks_iwork_fn(struct irq_work *iwork)
+{
+	struct llist_node *lnode;
+	struct task_struct *task, *next;
+
+	lnode = llist_del_all(this_cpu_ptr(&cgrp_dead_tasks));
+	llist_for_each_entry_safe(task, next, lnode, cg_dead_lnode) {
+		do_cgroup_task_dead(task);
+		put_task_struct(task);
+	}
+}
+
+static void __init cgroup_rt_init(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		init_llist_head(per_cpu_ptr(&cgrp_dead_tasks, cpu));
+		per_cpu(cgrp_dead_tasks_iwork, cpu) =
+			IRQ_WORK_INIT_LAZY(cgrp_dead_tasks_iwork_fn);
+	}
+}
+
+void cgroup_task_dead(struct task_struct *task)
+{
+	get_task_struct(task);
+	llist_add(&task->cg_dead_lnode, this_cpu_ptr(&cgrp_dead_tasks));
+	irq_work_queue(this_cpu_ptr(&cgrp_dead_tasks_iwork));
+}
+#else	/* CONFIG_PREEMPT_RT */
+static void __init cgroup_rt_init(void) {}
+
+void cgroup_task_dead(struct task_struct *task)
+{
+	do_cgroup_task_dead(task);
+}
+#endif	/* CONFIG_PREEMPT_RT */
+
+void cgroup_task_release(struct task_struct *task)
 {
 	struct cgroup_subsys *ss;
 	int ssid;
@@ -7013,6 +7073,11 @@ void cgroup_release(struct task_struct *task)
 	do_each_subsys_mask(ss, ssid, have_release_callback) {
 		ss->release(task);
 	} while_each_subsys_mask();
+}
+
+void cgroup_task_free(struct task_struct *task)
+{
+	struct css_set *cset = task_css_set(task);
 
 	if (!list_empty(&task->cg_list)) {
 		spin_lock_irq(&css_set_lock);
@@ -7020,11 +7085,7 @@ void cgroup_release(struct task_struct *task)
 		list_del_init(&task->cg_list);
 		spin_unlock_irq(&css_set_lock);
 	}
-}
 
-void cgroup_free(struct task_struct *task)
-{
-	struct css_set *cset = task_css_set(task);
 	put_css_set(cset);
 }
 

kernel/cgroup/cpuset-internal.h

@@ -155,12 +155,16 @@ struct cpuset {
 	/* for custom sched domain */
 	int relax_domain_level;
 
-	/* number of valid local child partitions */
-	int nr_subparts;
-
 	/* partition root state */
 	int partition_root_state;
 
+	/*
+	 * Whether cpuset is a remote partition.
+	 * It used to be a list anchoring all remote partitions — we can switch back
+	 * to a list if we need to iterate over the remote partitions.
+	 */
+	bool remote_partition;
+
 	/*
 	 * number of SCHED_DEADLINE tasks attached to this cpuset, so that we
 	 * know when to rebuild associated root domain bandwidth information.
@@ -175,9 +179,6 @@ struct cpuset {
 	/* Handle for cpuset.cpus.partition */
 	struct cgroup_file partition_file;
 
-	/* Remote partition silbling list anchored at remote_children */
-	struct list_head remote_sibling;
-
 	/* Used to merge intersecting subsets for generate_sched_domains */
 	struct uf_node node;
 };

kernel/cgroup/cpuset.c

@@ -81,15 +81,19 @@ static cpumask_var_t	subpartitions_cpus;
  */
 static cpumask_var_t	isolated_cpus;
 
+/*
+ * isolated_cpus updating flag (protected by cpuset_mutex)
+ * Set if isolated_cpus is going to be updated in the current
+ * cpuset_mutex crtical section.
+ */
+static bool isolated_cpus_updating;
+
 /*
  * Housekeeping (HK_TYPE_DOMAIN) CPUs at boot
  */
 static cpumask_var_t	boot_hk_cpus;
 static bool		have_boot_isolcpus;
 
-/* List of remote partition root children */
-static struct list_head remote_children;
-
 /*
  * A flag to force sched domain rebuild at the end of an operation.
  * It can be set in
@@ -212,7 +216,7 @@ static struct cpuset top_cpuset = {
 		 BIT(CS_MEM_EXCLUSIVE) | BIT(CS_SCHED_LOAD_BALANCE),
 	.partition_root_state = PRS_ROOT,
 	.relax_domain_level = -1,
-	.remote_sibling = LIST_HEAD_INIT(top_cpuset.remote_sibling),
+	.remote_partition = false,
 };
 
 /*
@@ -352,33 +356,55 @@ 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
  * @excluded_child: a child cpuset to be excluded in task checking
  * Return: true if there are tasks, false otherwise
  *
- * It is assumed that @cs is a valid partition root. @excluded_child should
+ * @cs should be a valid partition root or going to become a partition root.
- * be non-NULL when this cpuset is going to become a partition itself.
+ * @excluded_child should be non-NULL when this cpuset is going to become a
+ * partition itself.
+ *
+ * Note that a remote partition is not allowed underneath a valid local
+ * or remote partition. So if a non-partition root child is populated,
+ * the whole partition is considered populated.
  */
 static inline bool partition_is_populated(struct cpuset *cs,
 					  struct cpuset *excluded_child)
 {
-	struct cgroup_subsys_state *css;
+	struct cpuset *cp;
-	struct cpuset *child;
+	struct cgroup_subsys_state *pos_css;
 
-	if (cs->css.cgroup->nr_populated_csets)
+	/*
+	 * We cannot call cs_is_populated(cs) directly, as
+	 * nr_populated_domain_children may include populated
+	 * csets from descendants that are partitions.
+	 */
+	if (cs->css.cgroup->nr_populated_csets ||
+	    cs->attach_in_progress)
 		return true;
-	if (!excluded_child && !cs->nr_subparts)
-		return cgroup_is_populated(cs->css.cgroup);
 
 	rcu_read_lock();
-	cpuset_for_each_child(child, css, cs) {
+	cpuset_for_each_descendant_pre(cp, pos_css, cs) {
-		if (child == excluded_child)
+		if (cp == cs || cp == excluded_child)
 			continue;
-		if (is_partition_valid(child))
+
+		if (is_partition_valid(cp)) {
+			pos_css = css_rightmost_descendant(pos_css);
 			continue;
-		if (cgroup_is_populated(child->css.cgroup)) {
+		}
+
+		if (cpuset_is_populated(cp)) {
 			rcu_read_unlock();
 			return true;
 		}
@@ -663,7 +689,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 	 * be changed to have empty cpus_allowed or mems_allowed.
 	 */
 	ret = -ENOSPC;
-	if ((cgroup_is_populated(cur->css.cgroup) || cur->attach_in_progress)) {
+	if (cpuset_is_populated(cur)) {
 		if (!cpumask_empty(cur->cpus_allowed) &&
 		    cpumask_empty(trial->cpus_allowed))
 			goto out;
@@ -1302,7 +1328,6 @@ static void reset_partition_data(struct cpuset *cs)
 
 	lockdep_assert_held(&callback_lock);
 
-	cs->nr_subparts = 0;
 	if (cpumask_empty(cs->exclusive_cpus)) {
 		cpumask_clear(cs->effective_xcpus);
 		if (is_cpu_exclusive(cs))
@@ -1325,6 +1350,8 @@ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus
 		cpumask_or(isolated_cpus, isolated_cpus, xcpus);
 	else
 		cpumask_andnot(isolated_cpus, isolated_cpus, xcpus);
+
+	isolated_cpus_updating = true;
 }
 
 /*
@@ -1332,15 +1359,12 @@ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus
  * @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,
+static void 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)
@@ -1350,13 +1374,11 @@ static bool partition_xcpus_add(int new_prs, struct cpuset *parent,
 	if (parent == &top_cpuset)
 		cpumask_or(subpartitions_cpus, subpartitions_cpus, xcpus);
 
-	isolcpus_updated = (new_prs != parent->partition_root_state);
+	if (new_prs != parent->partition_root_state)
-	if (isolcpus_updated)
 		isolated_cpus_update(parent->partition_root_state, new_prs,
 				     xcpus);
 
 	cpumask_andnot(parent->effective_cpus, parent->effective_cpus, xcpus);
-	return isolcpus_updated;
 }
 
 /*
@@ -1364,15 +1386,12 @@ static bool partition_xcpus_add(int new_prs, struct cpuset *parent,
  * @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,
+static void 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)
@@ -1381,30 +1400,95 @@ static bool partition_xcpus_del(int old_prs, struct cpuset *parent,
 	if (parent == &top_cpuset)
 		cpumask_andnot(subpartitions_cpus, subpartitions_cpus, xcpus);
 
-	isolcpus_updated = (old_prs != parent->partition_root_state);
+	if (old_prs != parent->partition_root_state)
-	if (isolcpus_updated)
 		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);
-	return isolcpus_updated;
 }
 
-static void update_isolation_cpumasks(bool isolcpus_updated)
+/*
+ * isolated_cpus_can_update - check for isolated & nohz_full conflicts
+ * @add_cpus: cpu mask for cpus that are going to be isolated
+ * @del_cpus: cpu mask for cpus that are no longer isolated, can be NULL
+ * Return: false if there is conflict, true otherwise
+ *
+ * If nohz_full is enabled and we have isolated CPUs, their combination must
+ * still leave housekeeping CPUs.
+ *
+ * TBD: Should consider merging this function into
+ *      prstate_housekeeping_conflict().
+ */
+static bool isolated_cpus_can_update(struct cpumask *add_cpus,
+				     struct cpumask *del_cpus)
+{
+	cpumask_var_t full_hk_cpus;
+	int res = true;
+
+	if (!housekeeping_enabled(HK_TYPE_KERNEL_NOISE))
+		return true;
+
+	if (del_cpus && cpumask_weight_and(del_cpus,
+			housekeeping_cpumask(HK_TYPE_KERNEL_NOISE)))
+		return true;
+
+	if (!alloc_cpumask_var(&full_hk_cpus, GFP_KERNEL))
+		return false;
+
+	cpumask_and(full_hk_cpus, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE),
+		    housekeeping_cpumask(HK_TYPE_DOMAIN));
+	cpumask_andnot(full_hk_cpus, full_hk_cpus, isolated_cpus);
+	cpumask_and(full_hk_cpus, full_hk_cpus, cpu_active_mask);
+	if (!cpumask_weight_andnot(full_hk_cpus, add_cpus))
+		res = false;
+
+	free_cpumask_var(full_hk_cpus);
+	return res;
+}
+
+/*
+ * prstate_housekeeping_conflict - check for partition & housekeeping conflicts
+ * @prstate: partition root state to be checked
+ * @new_cpus: cpu mask
+ * Return: true if there is conflict, false otherwise
+ *
+ * CPUs outside of boot_hk_cpus, if defined, can only be used in an
+ * isolated partition.
+ */
+static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
+{
+	if (!have_boot_isolcpus)
+		return false;
+
+	if ((prstate != PRS_ISOLATED) && !cpumask_subset(new_cpus, boot_hk_cpus))
+		return true;
+
+	return false;
+}
+
+/*
+ * update_isolation_cpumasks - Update external isolation related CPU masks
+ *
+ * The following external CPU masks will be updated if necessary:
+ * - workqueue unbound cpumask
+ */
+static void update_isolation_cpumasks(void)
 {
 	int ret;
 
-	lockdep_assert_cpus_held();
+	if (!isolated_cpus_updating)
-
-	if (!isolcpus_updated)
 		return;
 
+	lockdep_assert_cpus_held();
+
 	ret = workqueue_unbound_exclude_cpumask(isolated_cpus);
 	WARN_ON_ONCE(ret < 0);
 
 	ret = tmigr_isolated_exclude_cpumask(isolated_cpus);
 	WARN_ON_ONCE(ret < 0);
+
+	isolated_cpus_updating = false;
 }
 
 /**
@@ -1508,7 +1592,7 @@ static int compute_trialcs_excpus(struct cpuset *trialcs, struct cpuset *cs)
 
 static inline bool is_remote_partition(struct cpuset *cs)
 {
-	return !list_empty(&cs->remote_sibling);
+	return cs->remote_partition;
 }
 
 static inline bool is_local_partition(struct cpuset *cs)
@@ -1529,8 +1613,6 @@ static inline bool is_local_partition(struct cpuset *cs)
 static int remote_partition_enable(struct cpuset *cs, int new_prs,
 				   struct tmpmasks *tmp)
 {
-	bool isolcpus_updated;
-
 	/*
 	 * The user must have sysadmin privilege.
 	 */
@@ -1552,13 +1634,17 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
 	if (!cpumask_intersects(tmp->new_cpus, cpu_active_mask) ||
 	    cpumask_subset(top_cpuset.effective_cpus, tmp->new_cpus))
 		return PERR_INVCPUS;
+	if (((new_prs == PRS_ISOLATED) &&
+	     !isolated_cpus_can_update(tmp->new_cpus, NULL)) ||
+	    prstate_housekeeping_conflict(new_prs, tmp->new_cpus))
+		return PERR_HKEEPING;
 
 	spin_lock_irq(&callback_lock);
-	isolcpus_updated = partition_xcpus_add(new_prs, NULL, tmp->new_cpus);
+	partition_xcpus_add(new_prs, NULL, tmp->new_cpus);
-	list_add(&cs->remote_sibling, &remote_children);
+	cs->remote_partition = true;
 	cpumask_copy(cs->effective_xcpus, tmp->new_cpus);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks(isolcpus_updated);
+	update_isolation_cpumasks();
 	cpuset_force_rebuild();
 	cs->prs_err = 0;
 
@@ -1581,15 +1667,12 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
  */
 static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
 {
-	bool isolcpus_updated;
-
 	WARN_ON_ONCE(!is_remote_partition(cs));
 	WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus));
 
 	spin_lock_irq(&callback_lock);
-	list_del_init(&cs->remote_sibling);
+	cs->remote_partition = false;
-	isolcpus_updated = partition_xcpus_del(cs->partition_root_state,
+	partition_xcpus_del(cs->partition_root_state, NULL, cs->effective_xcpus);
-					       NULL, cs->effective_xcpus);
 	if (cs->prs_err)
 		cs->partition_root_state = -cs->partition_root_state;
 	else
@@ -1599,7 +1682,7 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
 	compute_excpus(cs, cs->effective_xcpus);
 	reset_partition_data(cs);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks(isolcpus_updated);
+	update_isolation_cpumasks();
 	cpuset_force_rebuild();
 
 	/*
@@ -1624,7 +1707,6 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus,
 {
 	bool adding, deleting;
 	int prs = cs->partition_root_state;
-	int isolcpus_updated = 0;
 
 	if (WARN_ON_ONCE(!is_remote_partition(cs)))
 		return;
@@ -1651,15 +1733,18 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus,
 		else if (cpumask_intersects(tmp->addmask, subpartitions_cpus) ||
 			 cpumask_subset(top_cpuset.effective_cpus, tmp->addmask))
 			cs->prs_err = PERR_NOCPUS;
+		else if ((prs == PRS_ISOLATED) &&
+			 !isolated_cpus_can_update(tmp->addmask, tmp->delmask))
+			cs->prs_err = PERR_HKEEPING;
 		if (cs->prs_err)
 			goto invalidate;
 	}
 
 	spin_lock_irq(&callback_lock);
 	if (adding)
-		isolcpus_updated += partition_xcpus_add(prs, NULL, tmp->addmask);
+		partition_xcpus_add(prs, NULL, tmp->addmask);
 	if (deleting)
-		isolcpus_updated += partition_xcpus_del(prs, NULL, tmp->delmask);
+		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.
@@ -1668,7 +1753,7 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus,
 	if (xcpus)
 		cpumask_copy(cs->exclusive_cpus, xcpus);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks(isolcpus_updated);
+	update_isolation_cpumasks();
 	if (adding || deleting)
 		cpuset_force_rebuild();
 
@@ -1683,26 +1768,6 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus,
 	remote_partition_disable(cs, tmp);
 }
 
-/*
- * prstate_housekeeping_conflict - check for partition & housekeeping conflicts
- * @prstate: partition root state to be checked
- * @new_cpus: cpu mask
- * Return: true if there is conflict, false otherwise
- *
- * CPUs outside of boot_hk_cpus, if defined, can only be used in an
- * isolated partition.
- */
-static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
-{
-	if (!have_boot_isolcpus)
-		return false;
-
-	if ((prstate != PRS_ISOLATED) && !cpumask_subset(new_cpus, boot_hk_cpus))
-		return true;
-
-	return false;
-}
-
 /**
  * update_parent_effective_cpumask - update effective_cpus mask of parent cpuset
  * @cs:      The cpuset that requests change in partition root state
@@ -1749,9 +1814,8 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 	int deleting;	/* Deleting cpus from parent's effective_cpus	*/
 	int old_prs, new_prs;
 	int part_error = PERR_NONE;	/* Partition error? */
-	int subparts_delta = 0;
-	int isolcpus_updated = 0;
 	struct cpumask *xcpus = user_xcpus(cs);
+	int parent_prs = parent->partition_root_state;
 	bool nocpu;
 
 	lockdep_assert_held(&cpuset_mutex);
@@ -1774,10 +1838,9 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		if (is_partition_valid(parent))
 			adding = cpumask_and(tmp->addmask,
 					     xcpus, parent->effective_xcpus);
-		if (old_prs > 0) {
+		if (old_prs > 0)
 			new_prs = -old_prs;
-			subparts_delta--;
+
-		}
 		goto write_error;
 	}
 
@@ -1816,6 +1879,10 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		if (prstate_housekeeping_conflict(new_prs, xcpus))
 			return PERR_HKEEPING;
 
+		if ((new_prs == PRS_ISOLATED) && (new_prs != parent_prs) &&
+		    !isolated_cpus_can_update(xcpus, NULL))
+			return PERR_HKEEPING;
+
 		if (tasks_nocpu_error(parent, cs, xcpus))
 			return PERR_NOCPUS;
 
@@ -1832,7 +1899,6 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		WARN_ON_ONCE(!cpumask_subset(tmp->new_cpus, parent->effective_cpus));
 
 		deleting = true;
-		subparts_delta++;
 	} else if (cmd == partcmd_disable) {
 		/*
 		 * May need to add cpus back to parent's effective_cpus
@@ -1843,7 +1909,6 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		if (is_partition_valid(cs)) {
 			cpumask_copy(tmp->addmask, cs->effective_xcpus);
 			adding = true;
-			subparts_delta--;
 		}
 		new_prs = PRS_MEMBER;
 	} else if (newmask) {
@@ -1871,6 +1936,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		 *
 		 * For invalid partition:
 		 *   delmask = newmask & parent->effective_xcpus
+		 *   The partition may become valid soon.
 		 */
 		if (is_partition_invalid(cs)) {
 			adding = false;
@@ -1885,6 +1951,23 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 			deleting = cpumask_and(tmp->delmask, tmp->delmask,
 					       parent->effective_xcpus);
 		}
+
+		/*
+		 * TBD: Invalidate a currently valid child root partition may
+		 * still break isolated_cpus_can_update() rule if parent is an
+		 * isolated partition.
+		 */
+		if (is_partition_valid(cs) && (old_prs != parent_prs)) {
+			if ((parent_prs == PRS_ROOT) &&
+			    /* Adding to parent means removing isolated CPUs */
+			    !isolated_cpus_can_update(tmp->delmask, tmp->addmask))
+				part_error = PERR_HKEEPING;
+			if ((parent_prs == PRS_ISOLATED) &&
+			    /* Adding to parent means adding isolated CPUs */
+			    !isolated_cpus_can_update(tmp->addmask, tmp->delmask))
+				part_error = PERR_HKEEPING;
+		}
+
 		/*
 		 * The new CPUs to be removed from parent's effective CPUs
 		 * must be present.
@@ -1966,17 +2049,13 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		switch (cs->partition_root_state) {
 		case PRS_ROOT:
 		case PRS_ISOLATED:
-			if (part_error) {
+			if (part_error)
 				new_prs = -old_prs;
-				subparts_delta--;
-			}
 			break;
 		case PRS_INVALID_ROOT:
 		case PRS_INVALID_ISOLATED:
-			if (!part_error) {
+			if (!part_error)
 				new_prs = -old_prs;
-				subparts_delta++;
-			}
 			break;
 		}
 	}
@@ -2005,28 +2084,20 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 	 * newly deleted ones will be added back to effective_cpus.
 	 */
 	spin_lock_irq(&callback_lock);
-	if (old_prs != new_prs) {
+	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,
+		partition_xcpus_del(old_prs, parent, tmp->addmask);
-							tmp->addmask);
 	if (deleting)
-		isolcpus_updated += partition_xcpus_add(new_prs, parent,
+		partition_xcpus_add(new_prs, parent, tmp->delmask);
-							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_isolation_cpumasks(isolcpus_updated);
+	update_isolation_cpumasks();
 
 	if ((old_prs != new_prs) && (cmd == partcmd_update))
 		update_partition_exclusive_flag(cs, new_prs);
@@ -2108,8 +2179,6 @@ static void compute_partition_effective_cpumask(struct cpuset *cs,
 			 */
 			spin_lock_irq(&callback_lock);
 			make_partition_invalid(child);
-			cs->nr_subparts--;
-			child->nr_subparts = 0;
 			spin_unlock_irq(&callback_lock);
 			notify_partition_change(child, old_prs);
 			continue;
@@ -2138,7 +2207,6 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
 {
 	struct cpuset *cp;
 	struct cgroup_subsys_state *pos_css;
-	bool need_rebuild_sched_domains = false;
 	int old_prs, new_prs;
 
 	rcu_read_lock();
@@ -2302,15 +2370,12 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
 		if (!cpumask_empty(cp->cpus_allowed) &&
 		    is_sched_load_balance(cp) &&
 		   (!cpuset_v2() || is_partition_valid(cp)))
-			need_rebuild_sched_domains = true;
+			cpuset_force_rebuild();
 
 		rcu_read_lock();
 		css_put(&cp->css);
 	}
 	rcu_read_unlock();
-
-	if (need_rebuild_sched_domains)
-		cpuset_force_rebuild();
 }
 
 /**
@@ -2848,21 +2913,19 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 	 */
 	retval = nodelist_parse(buf, trialcs->mems_allowed);
 	if (retval < 0)
-		goto done;
+		return retval;
 
 	if (!nodes_subset(trialcs->mems_allowed,
-			  top_cpuset.mems_allowed)) {
+			  top_cpuset.mems_allowed))
-		retval = -EINVAL;
+		return -EINVAL;
-		goto done;
+
-	}
+	/* No change? nothing to do */
+	if (nodes_equal(cs->mems_allowed, trialcs->mems_allowed))
+		return 0;
 
-	if (nodes_equal(cs->mems_allowed, trialcs->mems_allowed)) {
-		retval = 0;		/* Too easy - nothing to do */
-		goto done;
-	}
 	retval = validate_change(cs, trialcs);
 	if (retval < 0)
-		goto done;
+		return retval;
 
 	check_insane_mems_config(&trialcs->mems_allowed);
 
@@ -2872,8 +2935,7 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 
 	/* use trialcs->mems_allowed as a temp variable */
 	update_nodemasks_hier(cs, &trialcs->mems_allowed);
-done:
+	return 0;
-	return retval;
 }
 
 bool current_cpuset_is_being_rebound(void)
@@ -3011,6 +3073,11 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 		 * A change in load balance state only, no change in cpumasks.
 		 * Need to update isolated_cpus.
 		 */
+		if (((new_prs == PRS_ISOLATED) &&
+		     !isolated_cpus_can_update(cs->effective_xcpus, NULL)) ||
+		    prstate_housekeeping_conflict(new_prs, cs->effective_xcpus))
+			err = PERR_HKEEPING;
+		else
 			isolcpus_updated = true;
 	} else {
 		/*
@@ -3046,7 +3113,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 	else if (isolcpus_updated)
 		isolated_cpus_update(old_prs, new_prs, cs->effective_xcpus);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks(isolcpus_updated);
+	update_isolation_cpumasks();
 
 	/* Force update if switching back to member & update effective_xcpus */
 	update_cpumasks_hier(cs, &tmpmask, !new_prs);
@@ -3552,7 +3619,6 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css)
 	__set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
 	fmeter_init(&cs->fmeter);
 	cs->relax_domain_level = -1;
-	INIT_LIST_HEAD(&cs->remote_sibling);
 
 	/* Set CS_MEMORY_MIGRATE for default hierarchy */
 	if (cpuset_v2())
@@ -3823,7 +3889,6 @@ int __init cpuset_init(void)
 	nodes_setall(top_cpuset.effective_mems);
 
 	fmeter_init(&top_cpuset.fmeter);
-	INIT_LIST_HEAD(&remote_children);
 
 	BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL));
 
@@ -4024,7 +4089,6 @@ static void cpuset_handle_hotplug(void)
 		 */
 		if (!cpumask_empty(subpartitions_cpus)) {
 			if (cpumask_subset(&new_cpus, subpartitions_cpus)) {
-				top_cpuset.nr_subparts = 0;
 				cpumask_clear(subpartitions_cpus);
 			} else {
 				cpumask_andnot(&new_cpus, &new_cpus,
@@ -4119,24 +4183,13 @@ void __init cpuset_init_smp(void)
 	BUG_ON(!cpuset_migrate_mm_wq);
 }
 
-/**
+/*
- * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset.
+ * Return cpus_allowed mask from a task's cpuset.
- * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
+ */
- * @pmask: pointer to struct cpumask variable to receive cpus_allowed set.
+static void __cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask)
- *
- * Description: Returns the cpumask_var_t cpus_allowed of the cpuset
- * attached to the specified @tsk.  Guaranteed to return some non-empty
- * subset of cpu_active_mask, even if this means going outside the
- * tasks cpuset, except when the task is in the top cpuset.
- **/
-
-void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 {
-	unsigned long flags;
 	struct cpuset *cs;
 
-	spin_lock_irqsave(&callback_lock, flags);
-
 	cs = task_cs(tsk);
 	if (cs != &top_cpuset)
 		guarantee_active_cpus(tsk, pmask);
@@ -4156,7 +4209,39 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 		if (!cpumask_intersects(pmask, cpu_active_mask))
 			cpumask_copy(pmask, possible_mask);
 	}
+}
 
+/**
+ * cpuset_cpus_allowed_locked - return cpus_allowed mask from a task's cpuset.
+ * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
+ * @pmask: pointer to struct cpumask variable to receive cpus_allowed set.
+ *
+ * Similir to cpuset_cpus_allowed() except that the caller must have acquired
+ * cpuset_mutex.
+ */
+void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask)
+{
+	lockdep_assert_held(&cpuset_mutex);
+	__cpuset_cpus_allowed_locked(tsk, pmask);
+}
+
+/**
+ * cpuset_cpus_allowed - return cpus_allowed mask from a task's cpuset.
+ * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
+ * @pmask: pointer to struct cpumask variable to receive cpus_allowed set.
+ *
+ * Description: Returns the cpumask_var_t cpus_allowed of the cpuset
+ * attached to the specified @tsk.  Guaranteed to return some non-empty
+ * subset of cpu_active_mask, even if this means going outside the
+ * tasks cpuset, except when the task is in the top cpuset.
+ **/
+
+void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&callback_lock, flags);
+	__cpuset_cpus_allowed_locked(tsk, pmask);
 	spin_unlock_irqrestore(&callback_lock, flags);
 }
 

kernel/exit.c

@@ -257,7 +257,7 @@ void release_task(struct task_struct *p)
 	rcu_read_unlock();
 
 	pidfs_exit(p);
-	cgroup_release(p);
+	cgroup_task_release(p);
 
 	/* Retrieve @thread_pid before __unhash_process() may set it to NULL. */
 	thread_pid = task_pid(p);
@@ -974,7 +974,7 @@ void __noreturn do_exit(long code)
 	exit_thread(tsk);
 
 	sched_autogroup_exit_task(tsk);
-	cgroup_exit(tsk);
+	cgroup_task_exit(tsk);
 
 	/*
 	 * FIXME: do that only when needed, using sched_exit tracepoint

kernel/fork.c

@@ -738,7 +738,7 @@ void __put_task_struct(struct task_struct *tsk)
 	unwind_task_free(tsk);
 	sched_ext_free(tsk);
 	io_uring_free(tsk);
-	cgroup_free(tsk);
+	cgroup_task_free(tsk);
 	task_numa_free(tsk, true);
 	security_task_free(tsk);
 	exit_creds(tsk);

kernel/sched/autogroup.c

@@ -178,8 +178,8 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 	 * this process can already run with task_group() == prev->tg or we can
 	 * race with cgroup code which can read autogroup = prev under rq->lock.
 	 * In the latter case for_each_thread() can not miss a migrating thread,
-	 * cpu_cgroup_attach() must not be possible after cgroup_exit() and it
+	 * cpu_cgroup_attach() must not be possible after cgroup_task_exit()
-	 * can't be removed from thread list, we hold ->siglock.
+	 * and it can't be removed from thread list, we hold ->siglock.
 	 *
 	 * If an exiting thread was already removed from thread list we rely on
 	 * sched_autogroup_exit_task().

kernel/sched/core.c

@@ -5143,6 +5143,8 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 		if (prev->sched_class->task_dead)
 			prev->sched_class->task_dead(prev);
 
+		cgroup_task_dead(prev);
+
 		/* Task is done with its stack. */
 		put_task_stack(prev);
 

kernel/sched/deadline.c

@@ -2675,6 +2675,7 @@ static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu
 	return NULL;
 }
 
+/* Access rule: must be called on local CPU with preemption disabled */
 static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
 
 static int find_later_rq(struct task_struct *task)
@@ -3117,11 +3118,43 @@ void __init init_sched_dl_class(void)
 					GFP_KERNEL, cpu_to_node(i));
 }
 
+/*
+ * This function always returns a non-empty bitmap in @cpus. This is because
+ * if a root domain has reserved bandwidth for DL tasks, the DL bandwidth
+ * check will prevent CPU hotplug from deactivating all CPUs in that domain.
+ */
+static void dl_get_task_effective_cpus(struct task_struct *p, struct cpumask *cpus)
+{
+	const struct cpumask *hk_msk;
+
+	hk_msk = housekeeping_cpumask(HK_TYPE_DOMAIN);
+	if (housekeeping_enabled(HK_TYPE_DOMAIN)) {
+		if (!cpumask_intersects(p->cpus_ptr, hk_msk)) {
+			/*
+			 * CPUs isolated by isolcpu="domain" always belong to
+			 * def_root_domain.
+			 */
+			cpumask_andnot(cpus, cpu_active_mask, hk_msk);
+			return;
+		}
+	}
+
+	/*
+	 * If a root domain holds a DL task, it must have active CPUs. So
+	 * active CPUs can always be found by walking up the task's cpuset
+	 * hierarchy up to the partition root.
+	 */
+	cpuset_cpus_allowed_locked(p, cpus);
+}
+
+/* The caller should hold cpuset_mutex */
 void dl_add_task_root_domain(struct task_struct *p)
 {
 	struct rq_flags rf;
 	struct rq *rq;
 	struct dl_bw *dl_b;
+	unsigned int cpu;
+	struct cpumask *msk = this_cpu_cpumask_var_ptr(local_cpu_mask_dl);
 
 	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
 	if (!dl_task(p) || dl_entity_is_special(&p->dl)) {
@@ -3129,16 +3162,25 @@ void dl_add_task_root_domain(struct task_struct *p)
 		return;
 	}
 
-	rq = __task_rq_lock(p, &rf);
+	/*
-
+	 * Get an active rq, whose rq->rd traces the correct root
+	 * domain.
+	 * Ideally this would be under cpuset reader lock until rq->rd is
+	 * fetched.  However, sleepable locks cannot nest inside pi_lock, so we
+	 * rely on the caller of dl_add_task_root_domain() holds 'cpuset_mutex'
+	 * to guarantee the CPU stays in the cpuset.
+	 */
+	dl_get_task_effective_cpus(p, msk);
+	cpu = cpumask_first_and(cpu_active_mask, msk);
+	BUG_ON(cpu >= nr_cpu_ids);
+	rq = cpu_rq(cpu);
 	dl_b = &rq->rd->dl_bw;
+	/* End of fetching rd */
+
 	raw_spin_lock(&dl_b->lock);
-
 	__dl_add(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span));
-
 	raw_spin_unlock(&dl_b->lock);
-
+	raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
-	task_rq_unlock(rq, p, &rf);
 }
 
 void dl_clear_root_domain(struct root_domain *rd)

tools/testing/selftests/cgroup/test_core.c

@@ -923,8 +923,10 @@ struct corecg_test {
 int main(int argc, char *argv[])
 {
 	char root[PATH_MAX];
-	int i, ret = EXIT_SUCCESS;
+	int i;
 
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), &nsdelegate)) {
 		if (setup_named_v1_root(root, sizeof(root), CG_NAMED_NAME))
 			ksft_exit_skip("cgroup v2 isn't mounted and could not setup named v1 hierarchy\n");
@@ -946,12 +948,11 @@ int main(int argc, char *argv[])
 			ksft_test_result_skip("%s\n", tests[i].name);
 			break;
 		default:
-			ret = EXIT_FAILURE;
 			ksft_test_result_fail("%s\n", tests[i].name);
 			break;
 		}
 	}
 
 	cleanup_named_v1_root(root);
-	return ret;
+	ksft_finished();
 }

tools/testing/selftests/cgroup/test_cpu.c

@@ -796,8 +796,10 @@ struct cpucg_test {
 int main(int argc, char *argv[])
 {
 	char root[PATH_MAX];
-	int i, ret = EXIT_SUCCESS;
+	int i;
 
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
@@ -814,11 +816,10 @@ int main(int argc, char *argv[])
 			ksft_test_result_skip("%s\n", tests[i].name);
 			break;
 		default:
-			ret = EXIT_FAILURE;
 			ksft_test_result_fail("%s\n", tests[i].name);
 			break;
 		}
 	}
 
-	return ret;
+	ksft_finished();
 }

tools/testing/selftests/cgroup/test_cpuset.c

@@ -247,8 +247,10 @@ struct cpuset_test {
 int main(int argc, char *argv[])
 {
 	char root[PATH_MAX];
-	int i, ret = EXIT_SUCCESS;
+	int i;
 
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
@@ -265,11 +267,10 @@ int main(int argc, char *argv[])
 			ksft_test_result_skip("%s\n", tests[i].name);
 			break;
 		default:
-			ret = EXIT_FAILURE;
 			ksft_test_result_fail("%s\n", tests[i].name);
 			break;
 		}
 	}
 
-	return ret;
+	ksft_finished();
 }

tools/testing/selftests/cgroup/test_freezer.c

@@ -1488,8 +1488,10 @@ struct cgfreezer_test {
 int main(int argc, char *argv[])
 {
 	char root[PATH_MAX];
-	int i, ret = EXIT_SUCCESS;
+	int i;
 
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
@@ -1501,11 +1503,10 @@ int main(int argc, char *argv[])
 			ksft_test_result_skip("%s\n", tests[i].name);
 			break;
 		default:
-			ret = EXIT_FAILURE;
 			ksft_test_result_fail("%s\n", tests[i].name);
 			break;
 		}
 	}
 
-	return ret;
+	ksft_finished();
 }

tools/testing/selftests/cgroup/test_kill.c

@@ -274,8 +274,10 @@ struct cgkill_test {
 int main(int argc, char *argv[])
 {
 	char root[PATH_MAX];
-	int i, ret = EXIT_SUCCESS;
+	int i;
 
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
@@ -287,11 +289,10 @@ int main(int argc, char *argv[])
 			ksft_test_result_skip("%s\n", tests[i].name);
 			break;
 		default:
-			ret = EXIT_FAILURE;
 			ksft_test_result_fail("%s\n", tests[i].name);
 			break;
 		}
 	}
 
-	return ret;
+	ksft_finished();
 }

tools/testing/selftests/cgroup/test_kmem.c

@@ -421,8 +421,10 @@ struct kmem_test {
 int main(int argc, char **argv)
 {
 	char root[PATH_MAX];
-	int i, ret = EXIT_SUCCESS;
+	int i;
 
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
@@ -446,11 +448,10 @@ int main(int argc, char **argv)
 			ksft_test_result_skip("%s\n", tests[i].name);
 			break;
 		default:
-			ret = EXIT_FAILURE;
 			ksft_test_result_fail("%s\n", tests[i].name);
 			break;
 		}
 	}
 
-	return ret;
+	ksft_finished();
 }

tools/testing/selftests/cgroup/test_memcontrol.c

@@ -1650,8 +1650,10 @@ struct memcg_test {
 int main(int argc, char **argv)
 {
 	char root[PATH_MAX];
-	int i, proc_status, ret = EXIT_SUCCESS;
+	int i, proc_status;
 
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
@@ -1685,11 +1687,10 @@ int main(int argc, char **argv)
 			ksft_test_result_skip("%s\n", tests[i].name);
 			break;
 		default:
-			ret = EXIT_FAILURE;
 			ksft_test_result_fail("%s\n", tests[i].name);
 			break;
 		}
 	}
 
-	return ret;
+	ksft_finished();
 }

tools/testing/selftests/cgroup/test_zswap.c

@@ -597,8 +597,10 @@ static bool zswap_configured(void)
 int main(int argc, char **argv)
 {
 	char root[PATH_MAX];
-	int i, ret = EXIT_SUCCESS;
+	int i;
 
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
@@ -625,11 +627,10 @@ int main(int argc, char **argv)
 			ksft_test_result_skip("%s\n", tests[i].name);
 			break;
 		default:
-			ret = EXIT_FAILURE;
 			ksft_test_result_fail("%s\n", tests[i].name);
 			break;
 		}
 	}
 
-	return ret;
+	ksft_finished();
 }