linux-stable-mirror/kernel/cgroup/cpuset-v1.c

// SPDX-License-Identifier: GPL-2.0-or-later

#include "cgroup-internal.h"
#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 */
static 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;

	cpuset_full_lock();
	if (!is_cpuset_online(cs))
		goto out_unlock;

	switch (type) {
	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
		pr_info_once("cpuset.%s is deprecated\n", cft->name);
		retval = update_relax_domain_level(cs, val);
		break;
	default:
		retval = -EINVAL;
		break;
	}
out_unlock:
	cpuset_full_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 && cgroup_has_tasks(cs->css.cgroup) &&
	    css_tryget_online(&cs->css)) {
		struct cpuset_remove_tasks_struct *s;

		s = kzalloc_obj(*s);
		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;

	/*
	 * Cpusets with tasks - existing or newly being attached - can't
	 * be changed to have empty cpus_allowed or mems_allowed.
	 */
	ret = -ENOSPC;
	if (cpuset_is_populated(cur)) {
		if (!cpumask_empty(cur->cpus_allowed) &&
		    cpumask_empty(trial->cpus_allowed))
			goto out;
		if (!nodes_empty(cur->mems_allowed) &&
		    nodes_empty(trial->mems_allowed))
			goto out;
	}

	ret = 0;
out:
	return ret;
}

/*
 * cpuset1_cpus_excl_conflict() - Check if two cpusets have exclusive CPU conflicts
 *                                to legacy (v1)
 * @cs1: first cpuset to check
 * @cs2: second cpuset to check
 *
 * Returns: true if CPU exclusivity conflict exists, false otherwise
 *
 * If either cpuset is CPU exclusive, their allowed CPUs cannot intersect.
 */
bool cpuset1_cpus_excl_conflict(struct cpuset *cs1, struct cpuset *cs2)
{
	if (is_cpu_exclusive(cs1) || is_cpu_exclusive(cs2))
		return cpumask_intersects(cs1->cpus_allowed,
					  cs2->cpus_allowed);

	return false;
}

#ifdef CONFIG_PROC_PID_CPUSET
/*
 * proc_cpuset_show()
 *  - Print tasks cpuset path into seq_file.
 *  - Used for /proc/<pid>/cpuset.
 */
int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
		     struct pid *pid, struct task_struct *tsk)
{
	char *buf;
	struct cgroup_subsys_state *css;
	int retval;

	retval = -ENOMEM;
	buf = kmalloc(PATH_MAX, GFP_KERNEL);
	if (!buf)
		goto out;

	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)
		goto out_free;
	seq_puts(m, buf);
	seq_putc(m, '\n');
	retval = 0;
out_free:
	kfree(buf);
out:
	return retval;
}
#endif /* CONFIG_PROC_PID_CPUSET */

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;

	cpuset_full_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:
		pr_info_once("cpuset.%s is deprecated\n", cft->name);
		retval = cpuset_update_flag(CS_MEM_EXCLUSIVE, cs, val);
		break;
	case FILE_MEM_HARDWALL:
		pr_info_once("cpuset.%s is deprecated\n", cft->name);
		retval = cpuset_update_flag(CS_MEM_HARDWALL, cs, val);
		break;
	case FILE_SCHED_LOAD_BALANCE:
		pr_info_once("cpuset.%s is deprecated, use cpuset.cpus.partition instead\n", cft->name);
		retval = cpuset_update_flag(CS_SCHED_LOAD_BALANCE, cs, val);
		break;
	case FILE_MEMORY_MIGRATE:
		pr_info_once("cpuset.%s is deprecated\n", cft->name);
		retval = cpuset_update_flag(CS_MEMORY_MIGRATE, cs, val);
		break;
	case FILE_MEMORY_PRESSURE_ENABLED:
		pr_info_once("cpuset.%s is deprecated, use memory.pressure with CONFIG_PSI instead\n", cft->name);
		cpuset_memory_pressure_enabled = !!val;
		break;
	case FILE_SPREAD_PAGE:
		pr_info_once("cpuset.%s is deprecated\n", cft->name);
		retval = cpuset_update_flag(CS_SPREAD_PAGE, cs, val);
		break;
	case FILE_SPREAD_SLAB:
		pr_warn_once("cpuset.%s is deprecated\n", cft->name);
		retval = cpuset_update_flag(CS_SPREAD_SLAB, cs, val);
		break;
	default:
		retval = -EINVAL;
		break;
	}
out_unlock:
	cpuset_full_unlock();
	return retval;
}

void cpuset1_init(struct cpuset *cs)
{
	fmeter_init(&cs->fmeter);
	cs->relax_domain_level = -1;
}

void cpuset1_online_css(struct cgroup_subsys_state *css)
{
	struct cpuset *tmp_cs;
	struct cgroup_subsys_state *pos_css;
	struct cpuset *cs = css_cs(css);
	struct cpuset *parent = parent_cs(cs);

	lockdep_assert_cpus_held();
	lockdep_assert_cpuset_lock_held();

	if (is_spread_page(parent))
		set_bit(CS_SPREAD_PAGE, &cs->flags);
	if (is_spread_slab(parent))
		set_bit(CS_SPREAD_SLAB, &cs->flags);

	if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
		return;

	/*
	 * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is
	 * set.  This flag handling is implemented in cgroup core for
	 * historical reasons - the flag may be specified during mount.
	 *
	 * Currently, if any sibling cpusets have exclusive cpus or mem, we
	 * refuse to clone the configuration - thereby refusing the task to
	 * be entered, and as a result refusing the sys_unshare() or
	 * clone() which initiated it.  If this becomes a problem for some
	 * users who wish to allow that scenario, then this could be
	 * changed to grant parent->cpus_allowed-sibling_cpus_exclusive
	 * (and likewise for mems) to the new cgroup.
	 */
	rcu_read_lock();
	cpuset_for_each_child(tmp_cs, pos_css, parent) {
		if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) {
			rcu_read_unlock();
			return;
		}
	}
	rcu_read_unlock();

	cpuset_callback_lock_irq();
	cs->mems_allowed = parent->mems_allowed;
	cs->effective_mems = parent->mems_allowed;
	cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
	cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
	cpuset_callback_unlock_irq();
}

static void
update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c)
{
	if (dattr->relax_domain_level < c->relax_domain_level)
		dattr->relax_domain_level = c->relax_domain_level;
}

static void update_domain_attr_tree(struct sched_domain_attr *dattr,
				    struct cpuset *root_cs)
{
	struct cpuset *cp;
	struct cgroup_subsys_state *pos_css;

	rcu_read_lock();
	cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
		/* skip the whole subtree if @cp doesn't have any CPU */
		if (cpumask_empty(cp->cpus_allowed)) {
			pos_css = css_rightmost_descendant(pos_css);
			continue;
		}

		if (is_sched_load_balance(cp))
			update_domain_attr(dattr, cp);
	}
	rcu_read_unlock();
}

/*
 * cpuset1_generate_sched_domains()
 *
 * Finding the best partition (set of domains):
 *	The double nested loops below over i, j scan over the load
 *	balanced cpusets (using the array of cpuset pointers in csa[])
 *	looking for pairs of cpusets that have overlapping cpus_allowed
 *	and merging them using a union-find algorithm.
 *
 *	The union of the cpus_allowed masks from the set of all cpusets
 *	having the same root then form the one element of the partition
 *	(one sched domain) to be passed to partition_sched_domains().
 */
int cpuset1_generate_sched_domains(cpumask_var_t **domains,
			struct sched_domain_attr **attributes)
{
	struct cpuset *cp;	/* top-down scan of cpusets */
	struct cpuset **csa;	/* array of all cpuset ptrs */
	int csn;		/* how many cpuset ptrs in csa so far */
	int i, j;		/* indices for partition finding loops */
	cpumask_var_t *doms;	/* resulting partition; i.e. sched domains */
	struct sched_domain_attr *dattr;  /* attributes for custom domains */
	int ndoms = 0;		/* number of sched domains in result */
	int nslot;		/* next empty doms[] struct cpumask slot */
	struct cgroup_subsys_state *pos_css;
	int nslot_update;

	lockdep_assert_cpuset_lock_held();

	doms = NULL;
	dattr = NULL;
	csa = NULL;

	/* Special case for the 99% of systems with one, full, sched domain */
	if (is_sched_load_balance(&top_cpuset)) {
		ndoms = 1;
		doms = alloc_sched_domains(ndoms);
		if (!doms)
			goto done;

		dattr = kmalloc_obj(struct sched_domain_attr);
		if (dattr) {
			*dattr = SD_ATTR_INIT;
			update_domain_attr_tree(dattr, &top_cpuset);
		}
		cpumask_and(doms[0], top_cpuset.effective_cpus,
			    housekeeping_cpumask(HK_TYPE_DOMAIN));

		goto done;
	}

	csa = kmalloc_objs(cp, nr_cpusets());
	if (!csa)
		goto done;
	csn = 0;

	rcu_read_lock();
	cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) {
		if (cp == &top_cpuset)
			continue;

		/*
		 * Continue traversing beyond @cp iff @cp has some CPUs and
		 * isn't load balancing.  The former is obvious.  The
		 * latter: All child cpusets contain a subset of the
		 * parent's cpus, so just skip them, and then we call
		 * update_domain_attr_tree() to calc relax_domain_level of
		 * the corresponding sched domain.
		 */
		if (!cpumask_empty(cp->cpus_allowed) &&
		    !(is_sched_load_balance(cp) &&
		      cpumask_intersects(cp->cpus_allowed,
					 housekeeping_cpumask(HK_TYPE_DOMAIN))))
			continue;

		if (is_sched_load_balance(cp) &&
		    !cpumask_empty(cp->effective_cpus))
			csa[csn++] = cp;

		/* skip @cp's subtree */
		pos_css = css_rightmost_descendant(pos_css);
		continue;
	}
	rcu_read_unlock();

	for (i = 0; i < csn; i++)
		uf_node_init(&csa[i]->node);

	/* Merge overlapping cpusets */
	for (i = 0; i < csn; i++) {
		for (j = i + 1; j < csn; j++) {
			if (cpusets_overlap(csa[i], csa[j]))
				uf_union(&csa[i]->node, &csa[j]->node);
		}
	}

	/* Count the total number of domains */
	for (i = 0; i < csn; i++) {
		if (uf_find(&csa[i]->node) == &csa[i]->node)
			ndoms++;
	}

	/*
	 * Now we know how many domains to create.
	 * Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
	 */
	doms = alloc_sched_domains(ndoms);
	if (!doms)
		goto done;

	/*
	 * The rest of the code, including the scheduler, can deal with
	 * dattr==NULL case. No need to abort if alloc fails.
	 */
	dattr = kmalloc_objs(struct sched_domain_attr, ndoms);

	for (nslot = 0, i = 0; i < csn; i++) {
		nslot_update = 0;
		for (j = i; j < csn; j++) {
			if (uf_find(&csa[j]->node) == &csa[i]->node) {
				struct cpumask *dp = doms[nslot];

				if (i == j) {
					nslot_update = 1;
					cpumask_clear(dp);
					if (dattr)
						*(dattr + nslot) = SD_ATTR_INIT;
				}
				cpumask_or(dp, dp, csa[j]->effective_cpus);
				cpumask_and(dp, dp, housekeeping_cpumask(HK_TYPE_DOMAIN));
				if (dattr)
					update_domain_attr_tree(dattr + nslot, csa[j]);
			}
		}
		if (nslot_update)
			nslot++;
	}
	BUG_ON(nslot != ndoms);

done:
	kfree(csa);

	/*
	 * Fallback to the default domain if kmalloc() failed.
	 * See comments in partition_sched_domains().
	 */
	if (doms == NULL)
		ndoms = 1;

	*domains    = doms;
	*attributes = dattr;
	return ndoms;
}

/*
 * for the common functions, 'private' gives the type of file
 */

struct cftype cpuset1_files[] = {
	{
		.name = "cpus",
		.seq_show = cpuset_common_seq_show,
		.write = cpuset_write_resmask,
		.max_write_len = (100U + 6 * NR_CPUS),
		.private = FILE_CPULIST,
	},

	{
		.name = "mems",
		.seq_show = cpuset_common_seq_show,
		.write = cpuset_write_resmask,
		.max_write_len = (100U + 6 * MAX_NUMNODES),
		.private = FILE_MEMLIST,
	},

	{
		.name = "effective_cpus",
		.seq_show = cpuset_common_seq_show,
		.private = FILE_EFFECTIVE_CPULIST,
	},

	{
		.name = "effective_mems",
		.seq_show = cpuset_common_seq_show,
		.private = FILE_EFFECTIVE_MEMLIST,
	},

	{
		.name = "cpu_exclusive",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_CPU_EXCLUSIVE,
	},

	{
		.name = "mem_exclusive",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_MEM_EXCLUSIVE,
	},

	{
		.name = "mem_hardwall",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_MEM_HARDWALL,
	},

	{
		.name = "sched_load_balance",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_SCHED_LOAD_BALANCE,
	},

	{
		.name = "sched_relax_domain_level",
		.read_s64 = cpuset_read_s64,
		.write_s64 = cpuset_write_s64,
		.private = FILE_SCHED_RELAX_DOMAIN_LEVEL,
	},

	{
		.name = "memory_migrate",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_MEMORY_MIGRATE,
	},

	{
		.name = "memory_pressure",
		.read_u64 = cpuset_read_u64,
		.private = FILE_MEMORY_PRESSURE,
	},

	{
		.name = "memory_spread_page",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_SPREAD_PAGE,
	},

	{
		/* obsolete, may be removed in the future */
		.name = "memory_spread_slab",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_SPREAD_SLAB,
	},

	{
		.name = "memory_pressure_enabled",
		.flags = CFTYPE_ONLY_ON_ROOT,
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_MEMORY_PRESSURE_ENABLED,
	},

	{ }	/* terminate */
};