Merge tag 'cgroup-for-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - cpuset isolation improvements

 - cpuset cgroup1 support is split into its own file behind the new
   config option CONFIG_CPUSET_V1. This makes it the second controller
   which makes cgroup1 support optional after memcg

 - Handling of unavailable v1 controller handling improved during
   cgroup1 mount operations

 - union_find applied to cpuset. It makes code simpler and more
   efficient

 - Reduce spurious events in pids.events

 - Cleanups and other misc changes

 - Contains a merge of cgroup/for-6.11-fixes to receive cpuset fixes
   that further changes build upon

* tag 'cgroup-for-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (34 commits)
  cgroup: Do not report unavailable v1 controllers in /proc/cgroups
  cgroup: Disallow mounting v1 hierarchies without controller implementation
  cgroup/cpuset: Expose cpuset filesystem with cpuset v1 only
  cgroup/cpuset: Move cpu.h include to cpuset-internal.h
  cgroup/cpuset: add sefltest for cpuset v1
  cgroup/cpuset: guard cpuset-v1 code under CONFIG_CPUSETS_V1
  cgroup/cpuset: rename functions shared between v1 and v2
  cgroup/cpuset: move v1 interfaces to cpuset-v1.c
  cgroup/cpuset: move validate_change_legacy to cpuset-v1.c
  cgroup/cpuset: move legacy hotplug update to cpuset-v1.c
  cgroup/cpuset: add callback_lock helper
  cgroup/cpuset: move memory_spread to cpuset-v1.c
  cgroup/cpuset: move relax_domain_level to cpuset-v1.c
  cgroup/cpuset: move memory_pressure to cpuset-v1.c
  cgroup/cpuset: move common code to cpuset-internal.h
  cgroup/cpuset: introduce cpuset-v1.c
  selftest/cgroup: Make test_cpuset_prs.sh deal with pre-isolated CPUs
  cgroup/cpuset: Account for boot time isolated CPUs
  cgroup/cpuset: remove use_parent_ecpus of cpuset
  cgroup/cpuset: remove fetch_xcpus
  ...

8 files changed, 1098 insertions, 1043 deletions

diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile
index 12f8457ad1f9..a5c9359d516f 100644
--- a/kernel/cgroup/Makefile
+++ b/kernel/cgroup/Makefile
@@ -5,5 +5,6 @@ obj-$(CONFIG_CGROUP_FREEZER) += legacy_freezer.o
 obj-$(CONFIG_CGROUP_PIDS) += pids.o
 obj-$(CONFIG_CGROUP_RDMA) += rdma.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
+obj-$(CONFIG_CPUSETS_V1) += cpuset-v1.o
 obj-$(CONFIG_CGROUP_MISC) += misc.o
 obj-$(CONFIG_CGROUP_DEBUG) += debug.o
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index b9dbf6bf2779..e28d5f0d20ed 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -46,6 +46,12 @@ bool cgroup1_ssid_disabled(int ssid)
 	return cgroup_no_v1_mask & (1 << ssid);
 }
 
+static bool cgroup1_subsys_absent(struct cgroup_subsys *ss)
+{
+	/* Check also dfl_cftypes for file-less controllers, i.e. perf_event */
+	return ss->legacy_cftypes == NULL && ss->dfl_cftypes;
+}
+
 /**
  * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from'
  * @from: attach to all cgroups of a given task
@@ -675,11 +681,14 @@ int proc_cgroupstats_show(struct seq_file *m, void *v)
 	 * cgroup_mutex contention.
 	 */
 
-	for_each_subsys(ss, i)
+	for_each_subsys(ss, i) {
+		if (cgroup1_subsys_absent(ss))
+			continue;
 		seq_printf(m, "%s\t%d\t%d\t%d\n",
 			   ss->legacy_name, ss->root->hierarchy_id,
 			   atomic_read(&ss->root->nr_cgrps),
 			   cgroup_ssid_enabled(i));
+	}
 
 	return 0;
 }
@@ -932,7 +941,8 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		if (ret != -ENOPARAM)
 			return ret;
 		for_each_subsys(ss, i) {
-			if (strcmp(param->key, ss->legacy_name))
+			if (strcmp(param->key, ss->legacy_name) ||
+			    cgroup1_subsys_absent(ss))
 				continue;
 			if (!cgroup_ssid_enabled(i) || cgroup1_ssid_disabled(i))
 				return invalfc(fc, "Disabled controller '%s'",
@@ -1024,7 +1034,8 @@ static int check_cgroupfs_options(struct fs_context *fc)
 	mask = ~((u16)1 << cpuset_cgrp_id);
 #endif
 	for_each_subsys(ss, i)
-		if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i))
+		if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i) &&
+		    !cgroup1_subsys_absent(ss))
 			enabled |= 1 << i;
 
 	ctx->subsys_mask &= enabled;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index c8e4b62b436a..90e50d6d3cf3 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2331,7 +2331,7 @@ static struct file_system_type cgroup2_fs_type = {
 	.fs_flags		= FS_USERNS_MOUNT,
 };
 
-#ifdef CONFIG_CPUSETS
+#ifdef CONFIG_CPUSETS_V1
 static const struct fs_context_operations cpuset_fs_context_ops = {
 	.get_tree	= cgroup1_get_tree,
 	.free		= cgroup_fs_context_free,
@@ -3669,12 +3669,40 @@ static int cgroup_events_show(struct seq_file *seq, void *v)
 static int cgroup_stat_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgroup = seq_css(seq)->cgroup;
+	struct cgroup_subsys_state *css;
+	int dying_cnt[CGROUP_SUBSYS_COUNT];
+	int ssid;
 
 	seq_printf(seq, "nr_descendants %d\n",
 		   cgroup->nr_descendants);
+
+	/*
+	 * Show the number of live and dying csses associated with each of
+	 * non-inhibited cgroup subsystems that is bound to cgroup v2.
+	 *
+	 * Without proper lock protection, racing is possible. So the
+	 * numbers may not be consistent when that happens.
+	 */
+	rcu_read_lock();
+	for (ssid = 0; ssid < CGROUP_SUBSYS_COUNT; ssid++) {
+		dying_cnt[ssid] = -1;
+		if ((BIT(ssid) & cgrp_dfl_inhibit_ss_mask) ||
+		    (cgroup_subsys[ssid]->root !=  &cgrp_dfl_root))
+			continue;
+		css = rcu_dereference_raw(cgroup->subsys[ssid]);
+		dying_cnt[ssid] = cgroup->nr_dying_subsys[ssid];
+		seq_printf(seq, "nr_subsys_%s %d\n", cgroup_subsys[ssid]->name,
+			   css ? (css->nr_descendants + 1) : 0);
+	}
+
 	seq_printf(seq, "nr_dying_descendants %d\n",
 		   cgroup->nr_dying_descendants);
-
+	for (ssid = 0; ssid < CGROUP_SUBSYS_COUNT; ssid++) {
+		if (dying_cnt[ssid] >= 0)
+			seq_printf(seq, "nr_dying_subsys_%s %d\n",
+				   cgroup_subsys[ssid]->name, dying_cnt[ssid]);
+	}
+	rcu_read_unlock();
 	return 0;
 }
 
@@ -4096,7 +4124,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 	 * If namespaces are delegation boundaries, disallow writes to
 	 * files in an non-init namespace root from inside the namespace
 	 * except for the files explicitly marked delegatable -
-	 * cgroup.procs and cgroup.subtree_control.
+	 * eg. cgroup.procs, cgroup.threads and cgroup.subtree_control.
 	 */
 	if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) &&
 	    !(cft->flags & CFTYPE_NS_DELEGATABLE) &&
@@ -5424,6 +5452,8 @@ static void css_release_work_fn(struct work_struct *work)
 	list_del_rcu(&css->sibling);
 
 	if (ss) {
+		struct cgroup *parent_cgrp;
+
 		/* css release path */
 		if (!list_empty(&css->rstat_css_node)) {
 			cgroup_rstat_flush(cgrp);
@@ -5433,6 +5463,21 @@ static void css_release_work_fn(struct work_struct *work)
 		cgroup_idr_replace(&ss->css_idr, NULL, css->id);
 		if (ss->css_released)
 			ss->css_released(css);
+
+		cgrp->nr_dying_subsys[ss->id]--;
+		/*
+		 * When a css is released and ready to be freed, its
+		 * nr_descendants must be zero. However, the corresponding
+		 * cgrp->nr_dying_subsys[ss->id] may not be 0 if a subsystem
+		 * is activated and deactivated multiple times with one or
+		 * more of its previous activation leaving behind dying csses.
+		 */
+		WARN_ON_ONCE(css->nr_descendants);
+		parent_cgrp = cgroup_parent(cgrp);
+		while (parent_cgrp) {
+			parent_cgrp->nr_dying_subsys[ss->id]--;
+			parent_cgrp = cgroup_parent(parent_cgrp);
+		}
 	} else {
 		struct cgroup *tcgrp;
 
@@ -5517,8 +5562,11 @@ static int online_css(struct cgroup_subsys_state *css)
 		rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
 
 		atomic_inc(&css->online_cnt);
-		if (css->parent)
+		if (css->parent) {
 			atomic_inc(&css->parent->online_cnt);
+			while ((css = css->parent))
+				css->nr_descendants++;
+		}
 	}
 	return ret;
 }
@@ -5540,6 +5588,16 @@ static void offline_css(struct cgroup_subsys_state *css)
 	RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL);
 
 	wake_up_all(&css->cgroup->offline_waitq);
+
+	css->cgroup->nr_dying_subsys[ss->id]++;
+	/*
+	 * Parent css and cgroup cannot be freed until after the freeing
+	 * of child css, see css_free_rwork_fn().
+	 */
+	while ((css = css->parent)) {
+		css->nr_descendants--;
+		css->cgroup->nr_dying_subsys[ss->id]++;
+	}
 }
 
 /**
@@ -6178,7 +6236,7 @@ int __init cgroup_init(void)
 	WARN_ON(register_filesystem(&cgroup_fs_type));
 	WARN_ON(register_filesystem(&cgroup2_fs_type));
 	WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show));
-#ifdef CONFIG_CPUSETS
+#ifdef CONFIG_CPUSETS_V1
 	WARN_ON(register_filesystem(&cpuset_fs_type));
 #endif
 
diff --git a/kernel/cgroup/cpuset-internal.h b/kernel/cgroup/cpuset-internal.h
new file mode 100644
index 000000000000..976a8bc3ff60
--- /dev/null
+++ b/kernel/cgroup/cpuset-internal.h
@@ -0,0 +1,305 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef __CPUSET_INTERNAL_H
+#define __CPUSET_INTERNAL_H
+
+#include <linux/cgroup.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/cpuset.h>
+#include <linux/spinlock.h>
+#include <linux/union_find.h>
+
+/* See "Frequency meter" comments, below. */
+
+struct fmeter {
+	int cnt;		/* unprocessed events count */
+	int val;		/* most recent output value */
+	time64_t time;		/* clock (secs) when val computed */
+	spinlock_t lock;	/* guards read or write of above */
+};
+
+/*
+ * Invalid partition error code
+ */
+enum prs_errcode {
+	PERR_NONE = 0,
+	PERR_INVCPUS,
+	PERR_INVPARENT,
+	PERR_NOTPART,
+	PERR_NOTEXCL,
+	PERR_NOCPUS,
+	PERR_HOTPLUG,
+	PERR_CPUSEMPTY,
+	PERR_HKEEPING,
+	PERR_ACCESS,
+};
+
+/* bits in struct cpuset flags field */
+typedef enum {
+	CS_ONLINE,
+	CS_CPU_EXCLUSIVE,
+	CS_MEM_EXCLUSIVE,
+	CS_MEM_HARDWALL,
+	CS_MEMORY_MIGRATE,
+	CS_SCHED_LOAD_BALANCE,
+	CS_SPREAD_PAGE,
+	CS_SPREAD_SLAB,
+} cpuset_flagbits_t;
+
+/* The various types of files and directories in a cpuset file system */
+
+typedef enum {
+	FILE_MEMORY_MIGRATE,
+	FILE_CPULIST,
+	FILE_MEMLIST,
+	FILE_EFFECTIVE_CPULIST,
+	FILE_EFFECTIVE_MEMLIST,
+	FILE_SUBPARTS_CPULIST,
+	FILE_EXCLUSIVE_CPULIST,
+	FILE_EFFECTIVE_XCPULIST,
+	FILE_ISOLATED_CPULIST,
+	FILE_CPU_EXCLUSIVE,
+	FILE_MEM_EXCLUSIVE,
+	FILE_MEM_HARDWALL,
+	FILE_SCHED_LOAD_BALANCE,
+	FILE_PARTITION_ROOT,
+	FILE_SCHED_RELAX_DOMAIN_LEVEL,
+	FILE_MEMORY_PRESSURE_ENABLED,
+	FILE_MEMORY_PRESSURE,
+	FILE_SPREAD_PAGE,
+	FILE_SPREAD_SLAB,
+} cpuset_filetype_t;
+
+struct cpuset {
+	struct cgroup_subsys_state css;
+
+	unsigned long flags;		/* "unsigned long" so bitops work */
+
+	/*
+	 * On default hierarchy:
+	 *
+	 * The user-configured masks can only be changed by writing to
+	 * cpuset.cpus and cpuset.mems, and won't be limited by the
+	 * parent masks.
+	 *
+	 * The effective masks is the real masks that apply to the tasks
+	 * in the cpuset. They may be changed if the configured masks are
+	 * changed or hotplug happens.
+	 *
+	 * effective_mask == configured_mask & parent's effective_mask,
+	 * and if it ends up empty, it will inherit the parent's mask.
+	 *
+	 *
+	 * On legacy hierarchy:
+	 *
+	 * The user-configured masks are always the same with effective masks.
+	 */
+
+	/* user-configured CPUs and Memory Nodes allow to tasks */
+	cpumask_var_t cpus_allowed;
+	nodemask_t mems_allowed;
+
+	/* effective CPUs and Memory Nodes allow to tasks */
+	cpumask_var_t effective_cpus;
+	nodemask_t effective_mems;
+
+	/*
+	 * Exclusive CPUs dedicated to current cgroup (default hierarchy only)
+	 *
+	 * 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.
+	 *
+	 * 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;
+
+	/*
+	 * This is old Memory Nodes tasks took on.
+	 *
+	 * - top_cpuset.old_mems_allowed is initialized to mems_allowed.
+	 * - A new cpuset's old_mems_allowed is initialized when some
+	 *   task is moved into it.
+	 * - old_mems_allowed is used in cpuset_migrate_mm() when we change
+	 *   cpuset.mems_allowed and have tasks' nodemask updated, and
+	 *   then old_mems_allowed is updated to mems_allowed.
+	 */
+	nodemask_t old_mems_allowed;
+
+	struct fmeter fmeter;		/* memory_pressure filter */
+
+	/*
+	 * Tasks are being attached to this cpuset.  Used to prevent
+	 * zeroing cpus/mems_allowed between ->can_attach() and ->attach().
+	 */
+	int attach_in_progress;
+
+	/* for custom sched domain */
+	int relax_domain_level;
+
+	/* number of valid local child partitions */
+	int nr_subparts;
+
+	/* partition root state */
+	int partition_root_state;
+
+	/*
+	 * number of SCHED_DEADLINE tasks attached to this cpuset, so that we
+	 * know when to rebuild associated root domain bandwidth information.
+	 */
+	int nr_deadline_tasks;
+	int nr_migrate_dl_tasks;
+	u64 sum_migrate_dl_bw;
+
+	/* Invalid partition error code, not lock protected */
+	enum prs_errcode prs_err;
+
+	/* 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;
+};
+
+static inline struct cpuset *css_cs(struct cgroup_subsys_state *css)
+{
+	return css ? container_of(css, struct cpuset, css) : NULL;
+}
+
+/* Retrieve the cpuset for a task */
+static inline struct cpuset *task_cs(struct task_struct *task)
+{
+	return css_cs(task_css(task, cpuset_cgrp_id));
+}
+
+static inline struct cpuset *parent_cs(struct cpuset *cs)
+{
+	return css_cs(cs->css.parent);
+}
+
+/* convenient tests for these bits */
+static inline bool is_cpuset_online(struct cpuset *cs)
+{
+	return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css);
+}
+
+static inline int is_cpu_exclusive(const struct cpuset *cs)
+{
+	return test_bit(CS_CPU_EXCLUSIVE, &cs->flags);
+}
+
+static inline int is_mem_exclusive(const struct cpuset *cs)
+{
+	return test_bit(CS_MEM_EXCLUSIVE, &cs->flags);
+}
+
+static inline int is_mem_hardwall(const struct cpuset *cs)
+{
+	return test_bit(CS_MEM_HARDWALL, &cs->flags);
+}
+
+static inline int is_sched_load_balance(const struct cpuset *cs)
+{
+	return test_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
+}
+
+static inline int is_memory_migrate(const struct cpuset *cs)
+{
+	return test_bit(CS_MEMORY_MIGRATE, &cs->flags);
+}
+
+static inline int is_spread_page(const struct cpuset *cs)
+{
+	return test_bit(CS_SPREAD_PAGE, &cs->flags);
+}
+
+static inline int is_spread_slab(const struct cpuset *cs)
+{
+	return test_bit(CS_SPREAD_SLAB, &cs->flags);
+}
+
+/**
+ * cpuset_for_each_child - traverse online children of a cpuset
+ * @child_cs: loop cursor pointing to the current child
+ * @pos_css: used for iteration
+ * @parent_cs: target cpuset to walk children of
+ *
+ * Walk @child_cs through the online children of @parent_cs.  Must be used
+ * with RCU read locked.
+ */
+#define cpuset_for_each_child(child_cs, pos_css, parent_cs)		\
+	css_for_each_child((pos_css), &(parent_cs)->css)		\
+		if (is_cpuset_online(((child_cs) = css_cs((pos_css)))))
+
+/**
+ * cpuset_for_each_descendant_pre - pre-order walk of a cpuset's descendants
+ * @des_cs: loop cursor pointing to the current descendant
+ * @pos_css: used for iteration
+ * @root_cs: target cpuset to walk ancestor of
+ *
+ * Walk @des_cs through the online descendants of @root_cs.  Must be used
+ * with RCU read locked.  The caller may modify @pos_css by calling
+ * css_rightmost_descendant() to skip subtree.  @root_cs is included in the
+ * iteration and the first node to be visited.
+ */
+#define cpuset_for_each_descendant_pre(des_cs, pos_css, root_cs)	\
+	css_for_each_descendant_pre((pos_css), &(root_cs)->css)		\
+		if (is_cpuset_online(((des_cs) = css_cs((pos_css)))))
+
+void rebuild_sched_domains_locked(void);
+void cpuset_callback_lock_irq(void);
+void cpuset_callback_unlock_irq(void);
+void cpuset_update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus);
+void cpuset_update_tasks_nodemask(struct cpuset *cs);
+int cpuset_update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int turning_on);
+ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off);
+int cpuset_common_seq_show(struct seq_file *sf, void *v);
+
+/*
+ * cpuset-v1.c
+ */
+#ifdef CONFIG_CPUSETS_V1
+extern struct cftype cpuset1_files[];
+void fmeter_init(struct fmeter *fmp);
+void cpuset1_update_task_spread_flags(struct cpuset *cs,
+					struct task_struct *tsk);
+void cpuset1_update_tasks_flags(struct cpuset *cs);
+void cpuset1_hotplug_update_tasks(struct cpuset *cs,
+			    struct cpumask *new_cpus, nodemask_t *new_mems,
+			    bool cpus_updated, bool mems_updated);
+int cpuset1_validate_change(struct cpuset *cur, struct cpuset *trial);
+#else
+static inline void fmeter_init(struct fmeter *fmp) {}
+static inline void cpuset1_update_task_spread_flags(struct cpuset *cs,
+					struct task_struct *tsk) {}
+static inline void cpuset1_update_tasks_flags(struct cpuset *cs) {}
+static inline void cpuset1_hotplug_update_tasks(struct cpuset *cs,
+			    struct cpumask *new_cpus, nodemask_t *new_mems,
+			    bool cpus_updated, bool mems_updated) {}
+static inline int cpuset1_validate_change(struct cpuset *cur,
+				struct cpuset *trial) { return 0; }
+#endif /* CONFIG_CPUSETS_V1 */
+
+#endif /* __CPUSET_INTERNAL_H */
diff --git a/kernel/cgroup/cpuset-v1.c b/kernel/cgroup/cpuset-v1.c
new file mode 100644
index 000000000000..25c1d7b77e2f
--- /dev/null
+++ b/kernel/cgroup/cpuset-v1.c
@@ -0,0 +1,562 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include "cpuset-internal.h"
+
+/*
+ * Legacy hierarchy call to cgroup_transfer_tasks() is handled asynchrously
+ */
+struct cpuset_remove_tasks_struct {
+	struct work_struct work;
+	struct cpuset *cs;
+};
+
+/*
+ * Frequency meter - How fast is some event occurring?
+ *
+ * These routines manage a digitally filtered, constant time based,
+ * event frequency meter.  There are four routines:
+ *   fmeter_init() - initialize a frequency meter.
+ *   fmeter_markevent() - called each time the event happens.
+ *   fmeter_getrate() - returns the recent rate of such events.
+ *   fmeter_update() - internal routine used to update fmeter.
+ *
+ * A common data structure is passed to each of these routines,
+ * which is used to keep track of the state required to manage the
+ * frequency meter and its digital filter.
+ *
+ * The filter works on the number of events marked per unit time.
+ * The filter is single-pole low-pass recursive (IIR).  The time unit
+ * is 1 second.  Arithmetic is done using 32-bit integers scaled to
+ * simulate 3 decimal digits of precision (multiplied by 1000).
+ *
+ * With an FM_COEF of 933, and a time base of 1 second, the filter
+ * has a half-life of 10 seconds, meaning that if the events quit
+ * happening, then the rate returned from the fmeter_getrate()
+ * will be cut in half each 10 seconds, until it converges to zero.
+ *
+ * It is not worth doing a real infinitely recursive filter.  If more
+ * than FM_MAXTICKS ticks have elapsed since the last filter event,
+ * just compute FM_MAXTICKS ticks worth, by which point the level
+ * will be stable.
+ *
+ * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid
+ * arithmetic overflow in the fmeter_update() routine.
+ *
+ * Given the simple 32 bit integer arithmetic used, this meter works
+ * best for reporting rates between one per millisecond (msec) and
+ * one per 32 (approx) seconds.  At constant rates faster than one
+ * per msec it maxes out at values just under 1,000,000.  At constant
+ * rates between one per msec, and one per second it will stabilize
+ * to a value N*1000, where N is the rate of events per second.
+ * At constant rates between one per second and one per 32 seconds,
+ * it will be choppy, moving up on the seconds that have an event,
+ * and then decaying until the next event.  At rates slower than
+ * about one in 32 seconds, it decays all the way back to zero between
+ * each event.
+ */
+
+#define FM_COEF 933		/* coefficient for half-life of 10 secs */
+#define FM_MAXTICKS ((u32)99)   /* useless computing more ticks than this */
+#define FM_MAXCNT 1000000	/* limit cnt to avoid overflow */
+#define FM_SCALE 1000		/* faux fixed point scale */
+
+/* Initialize a frequency meter */
+void fmeter_init(struct fmeter *fmp)
+{
+	fmp->cnt = 0;
+	fmp->val = 0;
+	fmp->time = 0;
+	spin_lock_init(&fmp->lock);
+}
+
+/* Internal meter update - process cnt events and update value */
+static void fmeter_update(struct fmeter *fmp)
+{
+	time64_t now;
+	u32 ticks;
+
+	now = ktime_get_seconds();
+	ticks = now - fmp->time;
+
+	if (ticks == 0)
+		return;
+
+	ticks = min(FM_MAXTICKS, ticks);
+	while (ticks-- > 0)
+		fmp->val = (FM_COEF * fmp->val) / FM_SCALE;
+	fmp->time = now;
+
+	fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE;
+	fmp->cnt = 0;
+}
+
+/* Process any previous ticks, then bump cnt by one (times scale). */
+static void fmeter_markevent(struct fmeter *fmp)
+{
+	spin_lock(&fmp->lock);
+	fmeter_update(fmp);
+	fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE);
+	spin_unlock(&fmp->lock);
+}
+
+/* Process any previous ticks, then return current value. */
+static int fmeter_getrate(struct fmeter *fmp)
+{
+	int val;
+
+	spin_lock(&fmp->lock);
+	fmeter_update(fmp);
+	val = fmp->val;
+	spin_unlock(&fmp->lock);
+	return val;
+}
+
+/*
+ * Collection of memory_pressure is suppressed unless
+ * this flag is enabled by writing "1" to the special
+ * cpuset file 'memory_pressure_enabled' in the root cpuset.
+ */
+
+int cpuset_memory_pressure_enabled __read_mostly;
+
+/*
+ * __cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims.
+ *
+ * Keep a running average of the rate of synchronous (direct)
+ * page reclaim efforts initiated by tasks in each cpuset.
+ *
+ * This represents the rate at which some task in the cpuset
+ * ran low on memory on all nodes it was allowed to use, and
+ * had to enter the kernels page reclaim code in an effort to
+ * create more free memory by tossing clean pages or swapping
+ * or writing dirty pages.
+ *
+ * Display to user space in the per-cpuset read-only file
+ * "memory_pressure".  Value displayed is an integer
+ * representing the recent rate of entry into the synchronous
+ * (direct) page reclaim by any task attached to the cpuset.
+ */
+
+void __cpuset_memory_pressure_bump(void)
+{
+	rcu_read_lock();
+	fmeter_markevent(&task_cs(current)->fmeter);
+	rcu_read_unlock();
+}
+
+static int update_relax_domain_level(struct cpuset *cs, s64 val)
+{
+#ifdef CONFIG_SMP
+	if (val < -1 || val > sched_domain_level_max + 1)
+		return -EINVAL;
+#endif
+
+	if (val != cs->relax_domain_level) {
+		cs->relax_domain_level = val;
+		if (!cpumask_empty(cs->cpus_allowed) &&
+		    is_sched_load_balance(cs))
+			rebuild_sched_domains_locked();
+	}
+
+	return 0;
+}
+
+static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
+			    s64 val)
+{
+	struct cpuset *cs = css_cs(css);
+	cpuset_filetype_t type = cft->private;
+	int retval = -ENODEV;
+
+	cpus_read_lock();
+	cpuset_lock();
+	if (!is_cpuset_online(cs))
+		goto out_unlock;
+
+	switch (type) {
+	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
+		retval = update_relax_domain_level(cs, val);
+		break;
+	default:
+		retval = -EINVAL;
+		break;
+	}
+out_unlock:
+	cpuset_unlock();
+	cpus_read_unlock();
+	return retval;
+}
+
+static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	struct cpuset *cs = css_cs(css);
+	cpuset_filetype_t type = cft->private;
+
+	switch (type) {
+	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
+		return cs->relax_domain_level;
+	default:
+		BUG();
+	}
+
+	/* Unreachable but makes gcc happy */
+	return 0;
+}
+
+/*
+ * update task's spread flag if cpuset's page/slab spread flag is set
+ *
+ * Call with callback_lock or cpuset_mutex held. The check can be skipped
+ * if on default hierarchy.
+ */
+void cpuset1_update_task_spread_flags(struct cpuset *cs,
+					struct task_struct *tsk)
+{
+	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys))
+		return;
+
+	if (is_spread_page(cs))
+		task_set_spread_page(tsk);
+	else
+		task_clear_spread_page(tsk);
+
+	if (is_spread_slab(cs))
+		task_set_spread_slab(tsk);
+	else
+		task_clear_spread_slab(tsk);
+}
+
+/**
+ * cpuset1_update_tasks_flags - update the spread flags of tasks in the cpuset.
+ * @cs: the cpuset in which each task's spread flags needs to be changed
+ *
+ * Iterate through each task of @cs updating its spread flags.  As this
+ * function is called with cpuset_mutex held, cpuset membership stays
+ * stable.
+ */
+void cpuset1_update_tasks_flags(struct cpuset *cs)
+{
+	struct css_task_iter it;
+	struct task_struct *task;
+
+	css_task_iter_start(&cs->css, 0, &it);
+	while ((task = css_task_iter_next(&it)))
+		cpuset1_update_task_spread_flags(cs, task);
+	css_task_iter_end(&it);
+}
+
+/*
+ * If CPU and/or memory hotplug handlers, below, unplug any CPUs
+ * or memory nodes, we need to walk over the cpuset hierarchy,
+ * removing that CPU or node from all cpusets.  If this removes the
+ * last CPU or node from a cpuset, then move the tasks in the empty
+ * cpuset to its next-highest non-empty parent.
+ */
+static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
+{
+	struct cpuset *parent;
+
+	/*
+	 * Find its next-highest non-empty parent, (top cpuset
+	 * has online cpus, so can't be empty).
+	 */
+	parent = parent_cs(cs);
+	while (cpumask_empty(parent->cpus_allowed) ||
+			nodes_empty(parent->mems_allowed))
+		parent = parent_cs(parent);
+
+	if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) {
+		pr_err("cpuset: failed to transfer tasks out of empty cpuset ");
+		pr_cont_cgroup_name(cs->css.cgroup);
+		pr_cont("\n");
+	}
+}
+
+static void cpuset_migrate_tasks_workfn(struct work_struct *work)
+{
+	struct cpuset_remove_tasks_struct *s;
+
+	s = container_of(work, struct cpuset_remove_tasks_struct, work);
+	remove_tasks_in_empty_cpuset(s->cs);
+	css_put(&s->cs->css);
+	kfree(s);
+}
+
+void cpuset1_hotplug_update_tasks(struct cpuset *cs,
+			    struct cpumask *new_cpus, nodemask_t *new_mems,
+			    bool cpus_updated, bool mems_updated)
+{
+	bool is_empty;
+
+	cpuset_callback_lock_irq();
+	cpumask_copy(cs->cpus_allowed, new_cpus);
+	cpumask_copy(cs->effective_cpus, new_cpus);
+	cs->mems_allowed = *new_mems;
+	cs->effective_mems = *new_mems;
+	cpuset_callback_unlock_irq();
+
+	/*
+	 * Don't call cpuset_update_tasks_cpumask() if the cpuset becomes empty,
+	 * as the tasks will be migrated to an ancestor.
+	 */
+	if (cpus_updated && !cpumask_empty(cs->cpus_allowed))
+		cpuset_update_tasks_cpumask(cs, new_cpus);
+	if (mems_updated && !nodes_empty(cs->mems_allowed))
+		cpuset_update_tasks_nodemask(cs);
+
+	is_empty = cpumask_empty(cs->cpus_allowed) ||
+		   nodes_empty(cs->mems_allowed);
+
+	/*
+	 * Move tasks to the nearest ancestor with execution resources,
+	 * This is full cgroup operation which will also call back into
+	 * cpuset. Execute it asynchronously using workqueue.
+	 */
+	if (is_empty && cs->css.cgroup->nr_populated_csets &&
+	    css_tryget_online(&cs->css)) {
+		struct cpuset_remove_tasks_struct *s;
+
+		s = kzalloc(sizeof(*s), GFP_KERNEL);
+		if (WARN_ON_ONCE(!s)) {
+			css_put(&cs->css);
+			return;
+		}
+
+		s->cs = cs;
+		INIT_WORK(&s->work, cpuset_migrate_tasks_workfn);
+		schedule_work(&s->work);
+	}
+}
+
+/*
+ * is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q?
+ *
+ * One cpuset is a subset of another if all its allowed CPUs and
+ * Memory Nodes are a subset of the other, and its exclusive flags
+ * are only set if the other's are set.  Call holding cpuset_mutex.
+ */
+
+static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
+{
+	return	cpumask_subset(p->cpus_allowed, q->cpus_allowed) &&
+		nodes_subset(p->mems_allowed, q->mems_allowed) &&
+		is_cpu_exclusive(p) <= is_cpu_exclusive(q) &&
+		is_mem_exclusive(p) <= is_mem_exclusive(q);
+}
+
+/*
+ * cpuset1_validate_change() - Validate conditions specific to legacy (v1)
+ *                            behavior.
+ */
+int cpuset1_validate_change(struct cpuset *cur, struct cpuset *trial)
+{
+	struct cgroup_subsys_state *css;
+	struct cpuset *c, *par;
+	int ret;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	/* Each of our child cpusets must be a subset of us */
+	ret = -EBUSY;
+	cpuset_for_each_child(c, css, cur)
+		if (!is_cpuset_subset(c, trial))
+			goto out;
+
+	/* On legacy hierarchy, we must be a subset of our parent cpuset. */
+	ret = -EACCES;
+	par = parent_cs(cur);
+	if (par && !is_cpuset_subset(trial, par))
+		goto out;
+
+	ret = 0;
+out:
+	return ret;
+}
+
+static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	struct cpuset *cs = css_cs(css);
+	cpuset_filetype_t type = cft->private;
+
+	switch (type) {
+	case FILE_CPU_EXCLUSIVE:
+		return is_cpu_exclusive(cs);
+	case FILE_MEM_EXCLUSIVE:
+		return is_mem_exclusive(cs);
+	case FILE_MEM_HARDWALL:
+		return is_mem_hardwall(cs);
+	case FILE_SCHED_LOAD_BALANCE:
+		return is_sched_load_balance(cs);
+	case FILE_MEMORY_MIGRATE:
+		return is_memory_migrate(cs);
+	case FILE_MEMORY_PRESSURE_ENABLED:
+		return cpuset_memory_pressure_enabled;
+	case FILE_MEMORY_PRESSURE:
+		return fmeter_getrate(&cs->fmeter);
+	case FILE_SPREAD_PAGE:
+		return is_spread_page(cs);
+	case FILE_SPREAD_SLAB:
+		return is_spread_slab(cs);
+	default:
+		BUG();
+	}
+
+	/* Unreachable but makes gcc happy */
+	return 0;
+}
+
+static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
+			    u64 val)
+{
+	struct cpuset *cs = css_cs(css);
+	cpuset_filetype_t type = cft->private;
+	int retval = 0;
+
+	cpus_read_lock();
+	cpuset_lock();
+	if (!is_cpuset_online(cs)) {
+		retval = -ENODEV;
+		goto out_unlock;
+	}
+
+	switch (type) {
+	case FILE_CPU_EXCLUSIVE:
+		retval = cpuset_update_flag(CS_CPU_EXCLUSIVE, cs, val);
+		break;
+	case FILE_MEM_EXCLUSIVE:
+		retval = cpuset_update_flag(CS_MEM_EXCLUSIVE, cs, val);
+		break;
+	case FILE_MEM_HARDWALL:
+		retval = cpuset_update_flag(CS_MEM_HARDWALL, cs, val);
+		break;
+	case FILE_SCHED_LOAD_BALANCE:
+		retval = cpuset_update_flag(CS_SCHED_LOAD_BALANCE, cs, val);
+		break;
+	case FILE_MEMORY_MIGRATE:
+		retval = cpuset_update_flag(CS_MEMORY_MIGRATE, cs, val);
+		break;
+	case FILE_MEMORY_PRESSURE_ENABLED:
+		cpuset_memory_pressure_enabled = !!val;
+		break;
+	case FILE_SPREAD_PAGE:
+		retval = cpuset_update_flag(CS_SPREAD_PAGE, cs, val);
+		break;
+	case FILE_SPREAD_SLAB:
+		retval = cpuset_update_flag(CS_SPREAD_SLAB, cs, val);
+		break;
+	default:
+		retval = -EINVAL;
+		break;
+	}
+out_unlock:
+	cpuset_unlock();
+	cpus_read_unlock();
+	return retval;
+}
+
+/*
+ * for the common functions, 'private' gives the type of file
+ */
+
+struct cftype cpuset1_files[] = {
+	{
+		.name = "cpus",
+		.seq_show = cpuset_common_seq_show,