Merge tag 'cgroup-for-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - Added Michal Koutný as a maintainer

 - Counters in pids.events were behaving inconsistently. pids.events
   made properly hierarchical and pids.events.local added

 - misc.peak and misc.events.local added

 - cpuset remote partition creation and cpuset.cpus.exclusive handling
   improved

 - Code cleanups, non-critical fixes, doc updates

 - for-6.10-fixes is merged in to receive two non-critical fixes that
   didn't trigger pull

* tag 'cgroup-for-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (23 commits)
  cgroup: Add Michal Koutný as a maintainer
  cgroup/misc: Introduce misc.events.local
  cgroup/rstat: add force idle show helper
  cgroup: Protect css->cgroup write under css_set_lock
  cgroup/misc: Introduce misc.peak
  cgroup_misc: add kernel-doc comments for enum misc_res_type
  cgroup/cpuset: Prevent UAF in proc_cpuset_show()
  selftest/cgroup: Update test_cpuset_prs.sh to match changes
  cgroup/cpuset: Make cpuset.cpus.exclusive independent of cpuset.cpus
  cgroup/cpuset: Delay setting of CS_CPU_EXCLUSIVE until valid partition
  selftest/cgroup: Fix test_cpuset_prs.sh problems reported by test robot
  cgroup/cpuset: Fix remote root partition creation problem
  cgroup: avoid the unnecessary list_add(dying_tasks) in cgroup_exit()
  cgroup/cpuset: Optimize isolated partition only generate_sched_domains() calls
  cgroup/cpuset: Reduce the lock protecting CS_SCHED_LOAD_BALANCE
  kernel/cgroup: cleanup cgroup_base_files when fail to add cgroup_psi_files
  selftests: cgroup: Add basic tests for pids controller
  selftests: cgroup: Lexicographic order in Makefile
  cgroup/pids: Add pids.events.local
  cgroup/pids: Make event counters hierarchical
  ...

5 files changed, 370 insertions, 109 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index e32b6972c478..c8e4b62b436a 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1744,8 +1744,11 @@ static int css_populate_dir(struct cgroup_subsys_state *css)
 			if (cgroup_psi_enabled()) {
 				ret = cgroup_addrm_files(css, cgrp,
 							 cgroup_psi_files, true);
-				if (ret < 0)
+				if (ret < 0) {
+					cgroup_addrm_files(css, cgrp,
+							   cgroup_base_files, false);
 					return ret;
+				}
 			}
 		} else {
 			ret = cgroup_addrm_files(css, cgrp,
@@ -1839,9 +1842,9 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 		RCU_INIT_POINTER(scgrp->subsys[ssid], NULL);
 		rcu_assign_pointer(dcgrp->subsys[ssid], css);
 		ss->root = dst_root;
-		css->cgroup = dcgrp;
 
 		spin_lock_irq(&css_set_lock);
+		css->cgroup = dcgrp;
 		WARN_ON(!list_empty(&dcgrp->e_csets[ss->id]));
 		list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id],
 					 e_cset_node[ss->id]) {
@@ -1922,6 +1925,7 @@ enum cgroup2_param {
 	Opt_memory_localevents,
 	Opt_memory_recursiveprot,
 	Opt_memory_hugetlb_accounting,
+	Opt_pids_localevents,
 	nr__cgroup2_params
 };
 
@@ -1931,6 +1935,7 @@ static const struct fs_parameter_spec cgroup2_fs_parameters[] = {
 	fsparam_flag("memory_localevents",	Opt_memory_localevents),
 	fsparam_flag("memory_recursiveprot",	Opt_memory_recursiveprot),
 	fsparam_flag("memory_hugetlb_accounting", Opt_memory_hugetlb_accounting),
+	fsparam_flag("pids_localevents",	Opt_pids_localevents),
 	{}
 };
 
@@ -1960,6 +1965,9 @@ static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param
 	case Opt_memory_hugetlb_accounting:
 		ctx->flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
 		return 0;
+	case Opt_pids_localevents:
+		ctx->flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS;
+		return 0;
 	}
 	return -EINVAL;
 }
@@ -1989,6 +1997,11 @@ static void apply_cgroup_root_flags(unsigned int root_flags)
 			cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
 		else
 			cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
+
+		if (root_flags & CGRP_ROOT_PIDS_LOCAL_EVENTS)
+			cgrp_dfl_root.flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS;
+		else
+			cgrp_dfl_root.flags &= ~CGRP_ROOT_PIDS_LOCAL_EVENTS;
 	}
 }
 
@@ -2004,6 +2017,8 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root
 		seq_puts(seq, ",memory_recursiveprot");
 	if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING)
 		seq_puts(seq, ",memory_hugetlb_accounting");
+	if (cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS)
+		seq_puts(seq, ",pids_localevents");
 	return 0;
 }
 
@@ -6686,8 +6701,10 @@ void cgroup_exit(struct task_struct *tsk)
 	WARN_ON_ONCE(list_empty(&tsk->cg_list));
 	cset = task_css_set(tsk);
 	css_set_move_task(tsk, cset, NULL, false);
-	list_add_tail(&tsk->cg_list, &cset->dying_tasks);
 	cset->nr_tasks--;
+	/* matches the signal->live check in css_task_iter_advance() */
+	if (thread_group_leader(tsk) && atomic_read(&tsk->signal->live))
+		list_add_tail(&tsk->cg_list, &cset->dying_tasks);
 
 	if (dl_task(tsk))
 		dec_dl_tasks_cs(tsk);
@@ -6714,10 +6731,12 @@ void cgroup_release(struct task_struct *task)
 		ss->release(task);
 	} while_each_subsys_mask();
 
-	spin_lock_irq(&css_set_lock);
-	css_set_skip_task_iters(task_css_set(task), task);
-	list_del_init(&task->cg_list);
-	spin_unlock_irq(&css_set_lock);
+	if (!list_empty(&task->cg_list)) {
+		spin_lock_irq(&css_set_lock);
+		css_set_skip_task_iters(task_css_set(task), task);
+		list_del_init(&task->cg_list);
+		spin_unlock_irq(&css_set_lock);
+	}
 }
 
 void cgroup_free(struct task_struct *task)
@@ -7062,7 +7081,8 @@ static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr,
 			"favordynmods\n"
 			"memory_localevents\n"
 			"memory_recursiveprot\n"
-			"memory_hugetlb_accounting\n");
+			"memory_hugetlb_accounting\n"
+			"pids_localevents\n");
 }
 static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features);
 
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index c12b9fdb22a4..40ec4abaf440 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -21,6 +21,7 @@
  *  License.  See the file COPYING in the main directory of the Linux
  *  distribution for more details.
  */
+#include "cgroup-internal.h"
 
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
@@ -87,7 +88,7 @@ static const char * const perr_strings[] = {
 	[PERR_NOTEXCL]   = "Cpu list in cpuset.cpus not exclusive",
 	[PERR_NOCPUS]    = "Parent unable to distribute cpu downstream",
 	[PERR_HOTPLUG]   = "No cpu available due to hotplug",
-	[PERR_CPUSEMPTY] = "cpuset.cpus is empty",
+	[PERR_CPUSEMPTY] = "cpuset.cpus and cpuset.cpus.exclusive are empty",
 	[PERR_HKEEPING]  = "partition config conflicts with housekeeping setup",
 };
 
@@ -127,19 +128,28 @@ struct cpuset {
 	/*
 	 * Exclusive CPUs dedicated to current cgroup (default hierarchy only)
 	 *
-	 * This exclusive CPUs must be a subset of cpus_allowed. A parent
-	 * cgroup can only grant exclusive CPUs to one of its children.
+	 * The effective_cpus of a valid partition root comes solely from its
+	 * effective_xcpus and some of the effective_xcpus may be distributed
+	 * to sub-partitions below & hence excluded from its effective_cpus.
+	 * For a valid partition root, its effective_cpus have no relationship
+	 * with cpus_allowed unless its exclusive_cpus isn't set.
 	 *
-	 * When the cgroup becomes a valid partition root, effective_xcpus
-	 * defaults to cpus_allowed if not set. The effective_cpus of a valid
-	 * partition root comes solely from its effective_xcpus and some of the
-	 * effective_xcpus may be distributed to sub-partitions below & hence
-	 * excluded from its effective_cpus.
+	 * This value will only be set if either exclusive_cpus is set or
+	 * when this cpuset becomes a local partition root.
 	 */
 	cpumask_var_t effective_xcpus;
 
 	/*
 	 * Exclusive CPUs as requested by the user (default hierarchy only)
+	 *
+	 * Its value is independent of cpus_allowed and designates the set of
+	 * CPUs that can be granted to the current cpuset or its children when
+	 * it becomes a valid partition root. The effective set of exclusive
+	 * CPUs granted (effective_xcpus) depends on whether those exclusive
+	 * CPUs are passed down by its ancestors and not yet taken up by
+	 * another sibling partition root along the way.
+	 *
+	 * If its value isn't set, it defaults to cpus_allowed.
 	 */
 	cpumask_var_t exclusive_cpus;
 
@@ -169,7 +179,7 @@ struct cpuset {
 	/* for custom sched domain */
 	int relax_domain_level;
 
-	/* number of valid sub-partitions */
+	/* number of valid local child partitions */
 	int nr_subparts;
 
 	/* partition root state */
@@ -230,6 +240,17 @@ static struct list_head remote_children;
  *   2 - partition root without load balancing (isolated)
  *  -1 - invalid partition root
  *  -2 - invalid isolated partition root
+ *
+ *  There are 2 types of partitions - local or remote. Local partitions are
+ *  those whose parents are partition root themselves. Setting of
+ *  cpuset.cpus.exclusive are optional in setting up local partitions.
+ *  Remote partitions are those whose parents are not partition roots. Passing
+ *  down exclusive CPUs by setting cpuset.cpus.exclusive along its ancestor
+ *  nodes are mandatory in creating a remote partition.
+ *
+ *  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.
  */
 #define PRS_MEMBER		0
 #define PRS_ROOT		1
@@ -434,7 +455,7 @@ static struct cpuset top_cpuset = {
  * by other task, we use alloc_lock in the task_struct fields to protect
  * them.
  *
- * The cpuset_common_file_read() handlers only hold callback_lock across
+ * The cpuset_common_seq_show() handlers only hold callback_lock across
  * small pieces of code, such as when reading out possibly multi-word
  * cpumasks and nodemasks.
  *
@@ -709,6 +730,19 @@ static inline void free_cpuset(struct cpuset *cs)
 	kfree(cs);
 }
 
+/* Return user specified exclusive CPUs */
+static inline struct cpumask *user_xcpus(struct cpuset *cs)
+{
+	return cpumask_empty(cs->exclusive_cpus) ? cs->cpus_allowed
+						 : cs->exclusive_cpus;
+}
+
+static inline bool xcpus_empty(struct cpuset *cs)
+{
+	return cpumask_empty(cs->cpus_allowed) &&
+	       cpumask_empty(cs->exclusive_cpus);
+}
+
 static inline struct cpumask *fetch_xcpus(struct cpuset *cs)
 {
 	return !cpumask_empty(cs->exclusive_cpus) ? cs->exclusive_cpus :
@@ -825,17 +859,41 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 
 	/*
 	 * If either I or some sibling (!= me) is exclusive, we can't
-	 * overlap
+	 * overlap. exclusive_cpus cannot overlap with each other if set.
 	 */
 	ret = -EINVAL;
 	cpuset_for_each_child(c, css, par) {
-		if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
-		    c != cur) {
+		bool txset, cxset;	/* Are exclusive_cpus set? */
+
+		if (c == cur)
+			continue;
+
+		txset = !cpumask_empty(trial->exclusive_cpus);
+		cxset = !cpumask_empty(c->exclusive_cpus);
+		if (is_cpu_exclusive(trial) || is_cpu_exclusive(c) ||
+		    (txset && cxset)) {
 			if (!cpusets_are_exclusive(trial, c))
 				goto out;
+		} else if (txset || cxset) {
+			struct cpumask *xcpus, *acpus;
+
+			/*
+			 * When just one of the exclusive_cpus's is set,
+			 * cpus_allowed of the other cpuset, if set, cannot be
+			 * a subset of it or none of those CPUs will be
+			 * available if these exclusive CPUs are activated.
+			 */
+			if (txset) {
+				xcpus = trial->exclusive_cpus;
+				acpus = c->cpus_allowed;
+			} else {
+				xcpus = c->exclusive_cpus;
+				acpus = trial->cpus_allowed;
+			}
+			if (!cpumask_empty(acpus) && cpumask_subset(acpus, xcpus))
+				goto out;
 		}
 		if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
-		    c != cur &&
 		    nodes_intersects(trial->mems_allowed, c->mems_allowed))
 			goto out;
 	}
@@ -957,13 +1015,15 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	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 = cgroup_subsys_on_dfl(cpuset_cgrp_subsys);
 
 	doms = NULL;
 	dattr = NULL;
 	csa = NULL;
 
 	/* Special case for the 99% of systems with one, full, sched domain */
-	if (root_load_balance && !top_cpuset.nr_subparts) {
+	if (root_load_balance && cpumask_empty(subpartitions_cpus)) {
+single_root_domain:
 		ndoms = 1;
 		doms = alloc_sched_domains(ndoms);
 		if (!doms)
@@ -991,16 +1051,18 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	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 root is load-balancing, we can skip @cp if it
-		 * is a subset of the root's effective_cpus.
 		 */
 		if (!cpumask_empty(cp->cpus_allowed) &&
 		    !(is_sched_load_balance(cp) &&
@@ -1008,20 +1070,39 @@ static int generate_sched_domains(cpumask_var_t **domains,
 					 housekeeping_cpumask(HK_TYPE_DOMAIN))))
 			continue;
 
-		if (root_load_balance &&
-		    cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus))
-			continue;
-
 		if (is_sched_load_balance(cp) &&
 		    !cpumask_empty(cp->effective_cpus))
 			csa[csn++] = cp;
 
-		/* skip @cp's subtree if not a partition root */
-		if (!is_partition_valid(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[].
+		 */
+		if ((cp->partition_root_state == PRS_ROOT) &&
+		    !cpumask_empty(cp->effective_cpus))
+			csa[csn++] = cp;
+
+		/*
+		 * Skip @cp's subtree if not a partition root and has no
+		 * exclusive CPUs to be granted to child cpusets.
+		 */
+		if (!is_partition_valid(cp) && cpumask_empty(cp->exclusive_cpus))
 			pos_css = css_rightmost_descendant(pos_css);
 	}
 	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++)
 		csa[i]->pn = i;
 	ndoms = csn;
@@ -1064,6 +1145,20 @@ restart:
 	dattr = kmalloc_array(ndoms, sizeof(struct sched_domain_attr),
 			      GFP_KERNEL);
 
+	/*
+	 * Cgroup v2 doesn't support domain attributes, just set all of them
+	 * 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++) {
+			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++) {
 		struct cpuset *a = csa[i];
 		struct cpumask *dp;
@@ -1223,7 +1318,7 @@ static void rebuild_sched_domains_locked(void)
 	 * 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 (top_cpuset.nr_subparts) {
+	if (!cpumask_empty(subpartitions_cpus)) {
 		rcu_read_lock();
 		cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
 			if (!is_partition_valid(cs)) {
@@ -1338,7 +1433,7 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
  */
 static int update_partition_exclusive(struct cpuset *cs, int new_prs)
 {
-	bool exclusive = (new_prs > 0);
+	bool exclusive = (new_prs > PRS_MEMBER);
 
 	if (exclusive && !is_cpu_exclusive(cs)) {
 		if (update_flag(CS_CPU_EXCLUSIVE, cs, 1))
@@ -1532,7 +1627,7 @@ EXPORT_SYMBOL_GPL(cpuset_cpu_is_isolated);
  * Return: true if xcpus is not empty, false otherwise.
  *
  * Starting with exclusive_cpus (cpus_allowed if exclusive_cpus is not set),
- * it must be a subset of cpus_allowed and parent's effective_xcpus.
+ * it must be a subset of parent's effective_xcpus.
  */
 static bool compute_effective_exclusive_cpumask(struct cpuset *cs,
 						struct cpumask *xcpus)
@@ -1542,12 +1637,7 @@ static bool compute_effective_exclusive_cpumask(struct cpuset *cs,
 	if (!xcpus)
 		xcpus = cs->effective_xcpus;
 
-	if (!cpumask_empty(cs->exclusive_cpus))
-		cpumask_and(xcpus, cs->exclusive_cpus, cs->cpus_allowed);
-	else
-		cpumask_copy(xcpus, cs->cpus_allowed);
-
-	return cpumask_and(xcpus, xcpus, parent->effective_xcpus);
+	return cpumask_and(xcpus, user_xcpus(cs), parent->effective_xcpus);
 }
 
 static inline bool is_remote_partition(struct cpuset *cs)
@@ -1826,8 +1916,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 	 */
 	adding = deleting = false;
 	old_prs = new_prs = cs->partition_root_state;
-	xcpus = !cpumask_empty(cs->exclusive_cpus)
-		? cs->effective_xcpus : cs->cpus_allowed;
+	xcpus = user_xcpus(cs);
 
 	if (cmd == partcmd_invalidate) {
 		if (is_prs_invalid(old_prs))
@@ -1855,7 +1944,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		return is_partition_invalid(parent)
 		       ? PERR_INVPARENT : PERR_NOTPART;
 	}
-	if (!newmask && cpumask_empty(cs->cpus_allowed))
+	if (!newmask && xcpus_empty(cs))
 		return PERR_CPUSEMPTY;
 
 	nocpu = tasks_nocpu_error(parent, cs, xcpus);
@@ -2583,8 +2672,6 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 		retval = cpulist_parse(buf, trialcs->exclusive_cpus);
 		if (retval < 0)
 			return retval;
-		if (!is_cpu_exclusive(cs))
-			set_bit(CS_CPU_EXCLUSIVE, &trialcs->flags);
 	}
 
 	/* Nothing to do if the CPUs didn't change */
@@ -3071,9 +3158,9 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 				       ? partcmd_enable : partcmd_enablei;
 
 		/*
-		 * cpus_allowed cannot be empty.
+		 * cpus_allowed and exclusive_cpus cannot be both empty.
 		 */
-		if (cpumask_empty(cs->cpus_allowed)) {
+		if (xcpus_empty(cs)) {
 			err = PERR_CPUSEMPTY;
 			goto out;
 		}
@@ -4009,8 +4096,6 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css)
 	}
 
 	__set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
-	nodes_clear(cs->mems_allowed);
-	nodes_clear(cs->effective_mems);
 	fmeter_init(&cs->fmeter);
 	cs->relax_domain_level = -1;
 	INIT_LIST_HEAD(&cs->remote_sibling);
@@ -4040,6 +4125,12 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 		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
+	 */
+	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+	    !is_sched_load_balance(parent))
+		clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
 
 	cpuset_inc();
 
@@ -4050,14 +4141,6 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 		cs->use_parent_ecpus = true;
 		parent->child_ecpus_count++;
 	}
-
-	/*
-	 * For v2, clear CS_SCHED_LOAD_BALANCE if parent is isolated
-	 */
-	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
-	    !is_sched_load_balance(parent))
-		clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
-
 	spin_unlock_irq(&callback_lock);
 
 	if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
@@ -4571,7 +4654,7 @@ static void cpuset_handle_hotplug(void)
 	 * In the rare case that hotplug removes all the cpus in
 	 * subpartitions_cpus, we assumed that cpus are updated.
 	 */
-	if (!cpus_updated && top_cpuset.nr_subparts)
+	if (!cpus_updated && !cpumask_empty(subpartitions_cpus))
 		cpus_updated = true;
 
 	/* For v1, synchronize cpus_allowed to cpu_active_mask */
@@ -5051,10 +5134,14 @@ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
 	if (!buf)
 		goto out;
 
-	css = task_get_css(tsk, cpuset_cgrp_id);
-	retval = cgroup_path_ns(css->cgroup, buf, PATH_MAX,
-				current->nsproxy->cgroup_ns);
-	css_put(css);
+	rcu_read_lock();
+	spin_lock_irq(&css_set_lock);
+	css = task_css(tsk, cpuset_cgrp_id);
+	retval = cgroup_path_ns_locked(css->cgroup, buf, PATH_MAX,
+				       current->nsproxy->cgroup_ns);
+	spin_unlock_irq(&css_set_lock);
+	rcu_read_unlock();
+
 	if (retval == -E2BIG)
 		retval = -ENAMETOOLONG;
 	if (retval < 0)
diff --git a/kernel/cgroup/misc.c b/kernel/cgroup/misc.c
index 79a3717a5803..0e26068995a6 100644
--- a/kernel/cgroup/misc.c
+++ b/kernel/cgroup/misc.c
@@ -121,6 +121,30 @@ static void misc_cg_cancel_charge(enum misc_res_type type, struct misc_cg *cg,
 		  misc_res_name[type]);
 }
 
+static void misc_cg_update_watermark(struct misc_res *res, u64 new_usage)
+{
+	u64 old;
+
+	while (true) {
+		old = atomic64_read(&res->watermark);
+		if (new_usage <= old)
+			break;
+		if (atomic64_cmpxchg(&res->watermark, old, new_usage) == old)
+			break;
+	}
+}
+
+static void misc_cg_event(enum misc_res_type type, struct misc_cg *cg)
+{
+	atomic64_inc(&cg->res[type].events_local);
+	cgroup_file_notify(&cg->events_local_file);
+
+	for (; parent_misc(cg); cg = parent_misc(cg)) {
+		atomic64_inc(&cg->res[type].events);
+		cgroup_file_notify(&cg->events_file);
+	}
+}
+
 /**
  * misc_cg_try_charge() - Try charging the misc cgroup.
  * @type: Misc res type to charge.
@@ -159,14 +183,12 @@ int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg, u64 amount)
 			ret = -EBUSY;
 			goto err_charge;
 		}
+		misc_cg_update_watermark(res, new_usage);
 	}
 	return 0;
 
 err_charge:
-	for (j = i; j; j = parent_misc(j)) {
-		atomic64_inc(&j->res[type].events);
-		cgroup_file_notify(&j->events_file);
-	}
+	misc_cg_event(type, i);
 
 	for (j = cg; j != i; j = parent_misc(j))
 		misc_cg_cancel_charge(type, j, amount);
@@ -308,6 +330,29 @@ static int misc_cg_current_show(struct seq_file *sf, void *v)
 }
 
 /**
+ * misc_cg_peak_show() - Show the peak usage of the misc cgroup.
+ * @sf: Interface file
+ * @v: Arguments passed
+ *
+ * Context: Any context.
+ * Return: 0 to denote successful print.
+ */
+static int misc_cg_peak_show(struct seq_file *sf, void *v)
+{
+	int i;
+	u64 watermark;
+	struct misc_cg *cg = css_misc(seq_css(sf));
+
+	for (i = 0; i < MISC_CG_RES_TYPES; i++) {
+		watermark = atomic64_read(&cg->res[i].watermark);
+		if (READ_ONCE(misc_res_capacity[i]) || watermark)
+			seq_printf(sf, "%s %llu\n", misc_res_name[i], watermark);
+	}
+
+	return 0;
+}
+
+/**
  * misc_cg_capacity_show() - Show the total capacity of misc res on the host.
  * @sf: Interface file
  * @v: Arguments passed
@@ -331,20 +376,33 @@ static int misc_cg_capacity_show(struct seq_file *sf, void *v)
 	return 0;
 }
 
-static int misc_events_show(struct seq_file *sf, void *v)
+static int __misc_events_show(struct seq_file *sf, bool local)
 {
 	struct misc_cg *cg = css_misc(seq_css(sf));
 	u64 events;
 	int i;
 
 	for (i = 0; i < MISC_CG_RES_TYPES; i++) {
-		events = atomic64_read(&cg->res[i].events);
+		if (local)
+			events = atomic64_read(&cg->res[i].events_local);
+		else
+			events = atomic64_read(&cg->res[i].events);
 		if (READ_ONCE(misc_res_capacity[i]) || events)
 			seq_printf(sf, "%s.max %llu\n", misc_res_name[i], events);
 	}
 	return 0;
 }
 
+static int misc_events_show(struct seq_file *sf, void *v)
+{
+	return __misc_events_show(sf, false);
+}
+
+static int misc_events_local_show(struct seq_file *sf, void *v)
+{
+	return __misc_events_show(sf, true);
+}
+
 /* Misc cgroup interface files */
 static struct cftype misc_cg_files[] = {
 	{
@@ -358,6 +416,10 @@ static struct cftype misc_cg_files[] = {
 		.seq_show = misc_cg_current_show,
 	},
 	{
+		.name = "peak",
+		.seq_show = misc_cg_peak_show,
+	},
+	{
 		.name = "capacity",
 		.seq_show = misc_cg_capacity_show,
 		.flags = CFTYPE_ONLY_ON_ROOT,
@@ -368,6 +430,12 @@ static struct cftype misc_cg_files[] = {
 		.file_offset = offsetof(struct misc_cg, events_file),
 		.seq_show = misc_events_show,
 	},
+	{
+		.name = "events.local",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.file_offset = offsetof(struct misc_cg, events_local_file),
+		.seq_show = misc_events_local_show,
+	},
 	{}
 };
 
diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c
index 0e5ec7d59b4d..f5cb0ec45b9d 100644
--- a/kernel/cgroup/pids.c
+++ b/kernel/cgroup/pids.c
@@ -38,6 +38,14 @@
 #define PIDS_MAX (PID_MAX_LIMIT + 1ULL)
 #define PIDS_MAX_STR "max"
 
+enum pidcg_event {
+	/* Fork failed in subtree because this pids_cgroup limit was hit. */
+	PIDCG_MAX,
+	/* Fork failed in this pids_cgroup because ancestor limit was hit. */
+	PIDCG_FORKFAIL,
+	NR_PIDCG_EVENTS,
+};
+
 struct pids_cgroup {
 	struct cgroup_subsys_state	css;
 
@@ -49,11 +57,12 @@ struct pids_cgroup {
 	atomic64_t			limit;
 	int64_t				watermark;
 
-	/* Handle for "pids.events" */
+	/* Handles for pids.events[.local] */
 	struct cgroup_file		events_file;
+	struct cgroup_file		events_local_file;
 
-	/* Number of times fork failed because limit was hit. */
-	atomic64_t			events_limit;
+	atomic64_t			events[NR_PIDCG_EVENTS];
+	atomic64_t			events_local[NR_PIDCG_EVENTS];
 };
 
 static struct pids_cgroup *css_pids(struct cgroup_subsys_state *css)
@@ -148,12 +157,13 @@ static void pids_charge(struct pids_cgroup *pids, int num)
  * pids_try_charge - hierarchically try to charge the pid count
  * @pids: the pid cgroup state
  * @num: the number of pids to charge
+ * @fail: storage of pid cgroup causing the fail
  *
  * This function follows the set limit. It will fail if the charge would cause
  * the new value to exceed the hierarchical limit. Returns 0 if the charge
  * succeeded, otherwise -EAGAIN.
  */
-static int pids_try_charge(struct pids_cgroup *pids, int num)
+static int pids_try_charge(struct pids_cgroup *pids, int num, struct pids_cgroup **fail)
 {
 	struct pids_cgroup *p, *q;
 
@@ -166,9 +176,10 @@ static int pids_try_charge(struct pids_cgroup *pids, int num)
 		 * p->limit is %PIDS_MAX then we know that this test will never
 		 * fail.
 		 */
-		if (new > limit)
+		if (new > limit) {
+			*fail = p;
 			goto revert;
-
+		}
 		/*
 		 * Not technically accurate if we go over limit somewhere up
 		 * the hierarchy, but that's tolerable for the watermark.
@@ -229,6 +240,36 @@ static void pids_cancel_attach(struct cgroup_taskset *tset)
 	}
 }
 
+static void pids_event(struct pids_cgroup *pids_forking,
+		       struct pids_cgroup *pids_over_limit)
+{
+	struct pids_cgroup *p = pids_forking;
+	bool limit = false;
+
+	/* Only log the first time limit is hit. */
+	if (atomic64_inc_return(&p->events_local[PIDCG_FORKFAIL]) == 1) {
+		pr_info("cgroup: fork rejected by pids controller in ");
+		pr_cont_cgroup_path(p->css.cgroup);
+		pr_cont("\n");
+	}
+	cgroup_file_notify(&p->events_local_file);
+	if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) ||
+	    cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS)
+		return;
+
+	for (; parent_pids(p); p = parent_pids(p)) {
+		if (p == pids_over_limit) {
+			limit = true;
+			atomic64_inc(&p->events_local[PIDCG_MAX]);
+			cgroup_file_notify(&p->events_local_file);
+		}
+		if (limit)
+			atomic64_inc(&p->events[PIDCG_MAX]);
+
+		cgroup_file_notify(&p->events_file);
+	}
+}
+
 /*
  * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies
  * on cgroup_threadgroup_change_begin() held by the copy_process().
@@ -236,7 +277,7 @@ static void pids_cancel_attach(struct cgroup_taskset *tset)
 static int pids_can_fork(struct task_struct *task, struct css_set *cset)
 {
 	struct cgroup_subsys_state *css;
-	struct pids_cgroup *pids;
+	struct pids_cgroup *pids, *pids_over_limit;
 	int err;
 
 	if (cset)
@@ -244,16 +285,10 @@ static int pids_can_fork(struct task_struct *task, struct css_set *cset)
 	else
 		css = task_css_check(current, pids_cgrp_id, true);
 	pids = css_pids(css);
-	err = pids_try_charge(pids, 1);
-	if (err) {
-		/* Only log the first time events_limit is incremented. */
-		if (atomic64_inc_return(&pids->events_limit) == 1) {
-			pr_info("cgroup: fork rejected by pids controller in ");
-			pr_cont_cgroup_path(css->cgroup);
-			pr_cont("\n");
-		}
-		cgroup_file_notify(&pids->events_file);
-	}
+	err = pids_try_charge(pids, 1, &pids_over_limit);
+	if (err)
+		pids_event(pids, pids_over_limit);
+
 	return err;
 }
 
@@ -337,11 +372,32 @@ static s64 pids_peak_read(struct cgroup_subsys_state *css,
 	return READ_ONCE(pids->watermark);
 }
 
-static int pids_events_show(struct seq_file *sf, void *v)
+static int __pids_events_show(struct seq_file *sf, bool local)
 {
 	struct pids_cgroup *pids = css_pids(seq_css(sf));
+	enum pidcg_event pe = PIDCG_MAX;
+	atomic64_t *events;
+
+	if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) ||
+	    cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) {
+		pe = PIDCG_FORKFAIL;
+		local = true;
+	}
+	events = local ? pids->events_local : pids->events;
+
+	seq_printf(sf, "max %lld\n", (s64)atomic64_read(&events[pe]));
+	return 0;
+}
 
-	seq_printf(sf, "max %lld\n", (s64)atomic64_read(&pids->events_limit));
+static int pids_events_show(struct seq_file *sf, void *v)
+{
+	__pids_events_show(sf, false);
+	return 0;
+}
+
+static int pids_events_local_show(struct seq_file *sf, void *v)
+{
+	__pids_events_show(sf, true);
 	return 0;
 }
 
@@ -368,9 +424,42 @@ static struct cftype pids_files[] = {
 		.file_offset = offsetof(struct pids_cgroup, events_file),
 		.flags = CFTYPE_NOT_ON_ROOT,
 	},
+	{
+		.name = "events.local",
+		.seq_show = pids_events_local_show,
+		.file_offset = offsetof(struct pids_cgroup, events_local_file),
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{ }	/* terminate */
+};
+
+static struct cftype pids_files_legacy[] = {
+	{
+		.name = "max",
+		.write = pids_max_write,
+		.seq_show = pids_max_show,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "current",
+		.read_s64 = pids_current_read,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "peak",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_s64 = pids_peak_read,
+	},
+	{
+		.name = "events",
+		.seq_show = pids_events_show,
+		.file_offset = offsetof(struct pids_cgroup, events_file),
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
 	{ }	/* terminate */
 };
 
+
 struct cgroup_subsys pids_cgrp_subsys = {
 	.css_alloc	= pids_css_alloc,
 	.css_free	= pids_css_free,
@@ -379,7 +468,7 @@ struct cgroup_subsys pids_cgrp_subsys = {
 	.can_fork	= pids_can_fork,
 	.cancel_fork	= pids_cancel_fork,
 	.release	= pids_release,
-	.legacy_cftypes	= pids_files,
+	.legacy_cftypes = pids_files_legacy,
 	.dfl_cftypes	= pids_files,
 	.threaded	= true,
 };
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index fb8b49437573..a06b45272411 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -594,49 +594,46 @@ static void root_cgroup_cputime(struct cgroup_base_stat *bstat)
 	}
 }
 
+
+static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat *bstat)
+{
+#ifdef CONFIG_SCHED_CORE
+	u64 forceidle_time = bstat->forceidle_sum;
+
+	do_div(forceidle_time, NSEC_PER_USEC);
+	seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time);
+#endif
+}
+
 void cgroup_base_stat_cputime_show(struct seq_file *seq)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
 	u64 usage, utime, stime;
-	struct cgroup_base_stat bstat;
-#ifdef CONFIG_SCHED_CORE
-	u64 forceidle_time;
-#endif
 
 	if (cgroup_parent(cgrp)) {
 		cgroup_rstat_flush_hold(cgrp);
 		usage = cgrp->bstat.cputime.sum_exec_runtime;
 		cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime,
 			       &utime, &stime);
-#ifdef CONFIG_SCHED_CORE
-		forceidle_time = cgrp->bstat.forceidle_sum;
-#endif
 		cgroup_rstat_flush_release(cgrp);
 	} else {
-		root_cgroup_cputime(&bstat);
-		usage = bstat.cputime.sum_exec_runtime;
-		utime = bstat.cputime.utime;
-		stime = bstat.cputime.stime;
-#ifdef CONFIG_SCHED_CORE
-		forceidle_time = bstat.forceidle_sum;
-#endif
+		/* cgrp->bstat of root is not actually used, reuse it */
+		root_cgroup_cputime(&cgrp->bstat);
+		usage = cgrp->bstat.cputime.sum_exec_runtime;
+		utime = cgrp->bstat.cputime.utime;
+		stime = cgrp->bstat.cputime.stime;
 	}
 
 	do_div(usage, NSEC_PER_USEC);
 	do_div(utime, NSEC_PER_USEC);
 	do_div(stime, NSEC_PER_USEC);
-#ifdef CONFIG_SCHED_CORE
-	do_div(forceidle_time, NSEC_PER_USEC);
-#endif
 
 	seq_printf(seq, "usage_usec %llu\n"
 		   "user_usec %llu\n"
 		   "system_usec %llu\n",
 		   usage, utime, stime);
 
-#ifdef CONFIG_SCHED_CORE
-	seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time);
-#endif
+	cgroup_force_idle_show(seq, &cgrp->bstat);
 }
 
 /* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */