/*
   *  kernel/cpuset.c
   *
   *  Processor and Memory placement constraints for sets of tasks.
   *
   *  Copyright (C) 2003 BULL SA.

   *  Copyright (C) 2004-2007 Silicon Graphics, Inc.

   *  Copyright (C) 2006 Google, Inc

   *
   *  Portions derived from Patrick Mochel's sysfs code.
   *  sysfs is Copyright (c) 2001-3 Patrick Mochel

   *

   *  2003-10-10 Written by Simon Derr.

   *  2003-10-22 Updates by Stephen Hemminger.

   *  2004 May-July Rework by Paul Jackson.

   *  2006 Rework by Paul Menage to use generic cgroups

   *  2008 Rework of the scheduler domains and CPU hotplug handling
   *       by Max Krasnyansky

   *
   *  This file is subject to the terms and conditions of the GNU General Public
   *  License.  See the file COPYING in the main directory of the Linux
   *  distribution for more details.
   */

  #include <linux/cpu.h>
  #include <linux/cpumask.h>
  #include <linux/cpuset.h>
  #include <linux/err.h>
  #include <linux/errno.h>
  #include <linux/file.h>
  #include <linux/fs.h>
  #include <linux/init.h>
  #include <linux/interrupt.h>
  #include <linux/kernel.h>
  #include <linux/kmod.h>
  #include <linux/list.h>

  #include <linux/mempolicy.h>

  #include <linux/mm.h>

  #include <linux/memory.h>

  #include <linux/export.h>

  #include <linux/mount.h>
  #include <linux/namei.h>
  #include <linux/pagemap.h>
  #include <linux/proc_fs.h>

  #include <linux/rcupdate.h>

  #include <linux/sched.h>
  #include <linux/seq_file.h>

  #include <linux/security.h>

  #include <linux/slab.h>

  #include <linux/spinlock.h>
  #include <linux/stat.h>
  #include <linux/string.h>
  #include <linux/time.h>
  #include <linux/backing-dev.h>
  #include <linux/sort.h>
  
  #include <asm/uaccess.h>

  #include <linux/atomic.h>

  #include <linux/mutex.h>

  #include <linux/workqueue.h>
  #include <linux/cgroup.h>

  #include <linux/wait.h>

  struct static_key cpusets_enabled_key __read_mostly = STATIC_KEY_INIT_FALSE;

  /* See "Frequency meter" comments, below. */
  
  struct fmeter {
  	int cnt;		/* unprocessed events count */
  	int val;		/* most recent output value */
  	time_t time;		/* clock (secs) when val computed */
  	spinlock_t lock;	/* guards read or write of above */
  };

  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 hierachy:
  	 *
  	 * 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;

  	/*
  	 * 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;

  	/* partition number for rebuild_sched_domains() */
  	int pn;

  	/* for custom sched domain */
  	int relax_domain_level;

  };

  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);

  }

  #ifdef CONFIG_NUMA
  static inline bool task_has_mempolicy(struct task_struct *task)
  {
  	return task->mempolicy;
  }
  #else
  static inline bool task_has_mempolicy(struct task_struct *task)
  {
  	return false;
  }
  #endif

  /* 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;
  
  /* convenient tests for these bits */

  static inline bool is_cpuset_online(const struct cpuset *cs)
  {
  	return test_bit(CS_ONLINE, &cs->flags);
  }

  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);
  }

  static struct cpuset top_cpuset = {

  	.flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) |
  		  (1 << CS_MEM_EXCLUSIVE)),

  };

  /**
   * 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)))))

  /*

   * There are two global locks guarding cpuset structures - cpuset_mutex and
   * callback_lock. We also require taking task_lock() when dereferencing a
   * task's cpuset pointer. See "The task_lock() exception", at the end of this
   * comment.

   *

   * A task must hold both locks to modify cpusets.  If a task holds

   * cpuset_mutex, then it blocks others wanting that mutex, ensuring that it

   * is the only task able to also acquire callback_lock and be able to

   * modify cpusets.  It can perform various checks on the cpuset structure
   * first, knowing nothing will change.  It can also allocate memory while
   * just holding cpuset_mutex.  While it is performing these checks, various

   * callback routines can briefly acquire callback_lock to query cpusets.
   * Once it is ready to make the changes, it takes callback_lock, blocking

   * everyone else.

   *
   * Calls to the kernel memory allocator can not be made while holding

   * callback_lock, as that would risk double tripping on callback_lock

   * from one of the callbacks into the cpuset code from within
   * __alloc_pages().
   *

   * If a task is only holding callback_lock, then it has read-only

   * access to cpusets.
   *

   * Now, the task_struct fields mems_allowed and mempolicy may be changed
   * 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

   * small pieces of code, such as when reading out possibly multi-word
   * cpumasks and nodemasks.
   *

   * Accessing a task's cpuset should be done in accordance with the
   * guidelines for accessing subsystem state in kernel/cgroup.c

   */

  static DEFINE_MUTEX(cpuset_mutex);

  static DEFINE_SPINLOCK(callback_lock);

  /*

   * CPU / memory hotplug is handled asynchronously.
   */
  static void cpuset_hotplug_workfn(struct work_struct *work);

  static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn);

  static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq);

  /*

   * This is ugly, but preserves the userspace API for existing cpuset

   * users. If someone tries to mount the "cpuset" filesystem, we

   * silently switch it to mount "cgroup" instead
   */

  static struct dentry *cpuset_mount(struct file_system_type *fs_type,
  			 int flags, const char *unused_dev_name, void *data)

  {

  	struct file_system_type *cgroup_fs = get_fs_type("cgroup");

  	struct dentry *ret = ERR_PTR(-ENODEV);

  	if (cgroup_fs) {
  		char mountopts[] =
  			"cpuset,noprefix,"
  			"release_agent=/sbin/cpuset_release_agent";

  		ret = cgroup_fs->mount(cgroup_fs, flags,
  					   unused_dev_name, mountopts);

  		put_filesystem(cgroup_fs);
  	}
  	return ret;

  }
  
  static struct file_system_type cpuset_fs_type = {
  	.name = "cpuset",

  	.mount = cpuset_mount,

  };

  /*

   * Return in pmask the portion of a cpusets's cpus_allowed that

   * are online.  If none are online, walk up the cpuset hierarchy

   * until we find one that does have some online cpus.  The top
   * cpuset always has some cpus online.

   *
   * One way or another, we guarantee to return some non-empty subset

   * of cpu_online_mask.

   *

   * Call with callback_lock or cpuset_mutex held.

   */

  static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)

  {

  	while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask))

  		cs = parent_cs(cs);

  	cpumask_and(pmask, cs->effective_cpus, cpu_online_mask);

  }
  
  /*
   * Return in *pmask the portion of a cpusets's mems_allowed that

   * are online, with memory.  If none are online with memory, walk
   * up the cpuset hierarchy until we find one that does have some

   * online mems.  The top cpuset always has some mems online.

   *
   * One way or another, we guarantee to return some non-empty subset

   * of node_states[N_MEMORY].

   *

   * Call with callback_lock or cpuset_mutex held.

   */

  static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask)

  {

  	while (!nodes_intersects(cs->effective_mems, node_states[N_MEMORY]))

  		cs = parent_cs(cs);

  	nodes_and(*pmask, cs->effective_mems, node_states[N_MEMORY]);

  }

  /*
   * update task's spread flag if cpuset's page/slab spread flag is set
   *

   * Call with callback_lock or cpuset_mutex held.

   */
  static void cpuset_update_task_spread_flag(struct cpuset *cs,
  					struct task_struct *tsk)
  {
  	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);

  }

  /*
   * 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);
  }

  /**
   * alloc_trial_cpuset - allocate a trial cpuset
   * @cs: the cpuset that the trial cpuset duplicates
   */

  static struct cpuset *alloc_trial_cpuset(struct cpuset *cs)

  {

  	struct cpuset *trial;
  
  	trial = kmemdup(cs, sizeof(*cs), GFP_KERNEL);
  	if (!trial)
  		return NULL;

  	if (!alloc_cpumask_var(&trial->cpus_allowed, GFP_KERNEL))
  		goto free_cs;
  	if (!alloc_cpumask_var(&trial->effective_cpus, GFP_KERNEL))
  		goto free_cpus;

  	cpumask_copy(trial->cpus_allowed, cs->cpus_allowed);
  	cpumask_copy(trial->effective_cpus, cs->effective_cpus);

  	return trial;

  
  free_cpus:
  	free_cpumask_var(trial->cpus_allowed);
  free_cs:
  	kfree(trial);
  	return NULL;

  }
  
  /**
   * free_trial_cpuset - free the trial cpuset
   * @trial: the trial cpuset to be freed
   */
  static void free_trial_cpuset(struct cpuset *trial)
  {

  	free_cpumask_var(trial->effective_cpus);

  	free_cpumask_var(trial->cpus_allowed);

  	kfree(trial);
  }

  /*
   * validate_change() - Used to validate that any proposed cpuset change
   *		       follows the structural rules for cpusets.
   *
   * If we replaced the flag and mask values of the current cpuset
   * (cur) with those values in the trial cpuset (trial), would
   * our various subset and exclusive rules still be valid?  Presumes

   * cpuset_mutex held.

   *
   * 'cur' is the address of an actual, in-use cpuset.  Operations
   * such as list traversal that depend on the actual address of the
   * cpuset in the list must use cur below, not trial.
   *
   * 'trial' is the address of bulk structure copy of cur, with
   * perhaps one or more of the fields cpus_allowed, mems_allowed,
   * or flags changed to new, trial values.
   *
   * Return 0 if valid, -errno if not.
   */

  static int validate_change(struct cpuset *cur, struct cpuset *trial)

  {

  	struct cgroup_subsys_state *css;

  	struct cpuset *c, *par;

  	int ret;
  
  	rcu_read_lock();

  
  	/* 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;

  
  	/* Remaining checks don't apply to root cpuset */

  	ret = 0;

  	if (cur == &top_cpuset)

  		goto out;

  	par = parent_cs(cur);

  	/* On legacy hiearchy, we must be a subset of our parent cpuset. */

  	ret = -EACCES;

  	if (!cgroup_on_dfl(cur->css.cgroup) && !is_cpuset_subset(trial, par))

  		goto out;

  	/*
  	 * If either I or some sibling (!= me) is exclusive, we can't
  	 * overlap
  	 */

  	ret = -EINVAL;

  	cpuset_for_each_child(c, css, par) {

  		if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
  		    c != cur &&

  		    cpumask_intersects(trial->cpus_allowed, c->cpus_allowed))

  			goto out;

  		if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
  		    c != cur &&
  		    nodes_intersects(trial->mems_allowed, c->mems_allowed))

  			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 ((cgroup_has_tasks(cur->css.cgroup) || cur->attach_in_progress)) {

  		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;
  	}

  	/*
  	 * We can't shrink if we won't have enough room for SCHED_DEADLINE
  	 * tasks.
  	 */
  	ret = -EBUSY;
  	if (is_cpu_exclusive(cur) &&
  	    !cpuset_cpumask_can_shrink(cur->cpus_allowed,
  				       trial->cpus_allowed))
  		goto out;

  	ret = 0;
  out:
  	rcu_read_unlock();
  	return ret;

  }

  #ifdef CONFIG_SMP

  /*

   * Helper routine for generate_sched_domains().

   * Do cpusets a, b have overlapping effective cpus_allowed masks?

   */

  static int cpusets_overlap(struct cpuset *a, struct cpuset *b)
  {

  	return cpumask_intersects(a->effective_cpus, b->effective_cpus);

  }

  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;
  	return;
  }

  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();

  }

  /*

   * generate_sched_domains()
   *
   * This function builds a partial partition of the systems CPUs
   * A 'partial partition' is a set of non-overlapping subsets whose
   * union is a subset of that set.

   * The output of this function needs to be passed to kernel/sched/core.c

   * partition_sched_domains() routine, which will rebuild the scheduler's
   * load balancing domains (sched domains) as specified by that partial
   * partition.

   *

   * See "What is sched_load_balance" in Documentation/cgroups/cpusets.txt

   * for a background explanation of this.
   *
   * Does not return errors, on the theory that the callers of this
   * routine would rather not worry about failures to rebuild sched
   * domains when operating in the severe memory shortage situations
   * that could cause allocation failures below.
   *

   * Must be called with cpuset_mutex held.

   *
   * The three key local variables below are:

   *    q  - a linked-list queue of cpuset pointers, used to implement a

   *	   top-down scan of all cpusets.  This scan loads a pointer
   *	   to each cpuset marked is_sched_load_balance into the
   *	   array 'csa'.  For our purposes, rebuilding the schedulers
   *	   sched domains, we can ignore !is_sched_load_balance cpusets.
   *  csa  - (for CpuSet Array) Array of pointers to all the cpusets
   *	   that need to be load balanced, for convenient iterative
   *	   access by the subsequent code that finds the best partition,
   *	   i.e the set of domains (subsets) of CPUs such that the
   *	   cpus_allowed of every cpuset marked is_sched_load_balance
   *	   is a subset of one of these domains, while there are as
   *	   many such domains as possible, each as small as possible.
   * doms  - Conversion of 'csa' to an array of cpumasks, for passing to

   *	   the kernel/sched/core.c routine partition_sched_domains() in a

   *	   convenient format, that can be easily compared to the prior
   *	   value to determine what partition elements (sched domains)
   *	   were changed (added or removed.)
   *
   * Finding the best partition (set of domains):
   *	The triple nested loops below over i, j, k scan over the
   *	load balanced cpusets (using the array of cpuset pointers in
   *	csa[]) looking for pairs of cpusets that have overlapping
   *	cpus_allowed, but which don't have the same 'pn' partition
   *	number and gives them in the same partition number.  It keeps
   *	looping on the 'restart' label until it can no longer find
   *	any such pairs.
   *
   *	The union of the cpus_allowed masks from the set of
   *	all cpusets having the same 'pn' value then form the one
   *	element of the partition (one sched domain) to be passed to
   *	partition_sched_domains().
   */

  static int generate_sched_domains(cpumask_var_t **domains,

  			struct sched_domain_attr **attributes)

  {

  	struct cpuset *cp;	/* scans q */
  	struct cpuset **csa;	/* array of all cpuset ptrs */
  	int csn;		/* how many cpuset ptrs in csa so far */
  	int i, j, k;		/* indices for partition finding loops */

  	cpumask_var_t *doms;	/* resulting partition; i.e. sched domains */

  	cpumask_var_t non_isolated_cpus;  /* load balanced CPUs */

  	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;

  	doms = NULL;

  	dattr = NULL;

  	csa = NULL;

  	if (!alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL))
  		goto done;
  	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);

  	/* 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(sizeof(struct sched_domain_attr), GFP_KERNEL);
  		if (dattr) {
  			*dattr = SD_ATTR_INIT;

  			update_domain_attr_tree(dattr, &top_cpuset);

  		}

  		cpumask_and(doms[0], top_cpuset.effective_cpus,
  				     non_isolated_cpus);

  		goto done;

  	}

  	csa = kmalloc(nr_cpusets() * sizeof(cp), GFP_KERNEL);

  	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, non_isolated_cpus)))

  			continue;

  		if (is_sched_load_balance(cp))
  			csa[csn++] = cp;
  
  		/* skip @cp's subtree */

  		pos_css = css_rightmost_descendant(pos_css);

  	}
  	rcu_read_unlock();

  
  	for (i = 0; i < csn; i++)
  		csa[i]->pn = i;
  	ndoms = csn;
  
  restart:
  	/* Find the best partition (set of sched domains) */
  	for (i = 0; i < csn; i++) {
  		struct cpuset *a = csa[i];
  		int apn = a->pn;
  
  		for (j = 0; j < csn; j++) {
  			struct cpuset *b = csa[j];
  			int bpn = b->pn;
  
  			if (apn != bpn && cpusets_overlap(a, b)) {
  				for (k = 0; k < csn; k++) {
  					struct cpuset *c = csa[k];
  
  					if (c->pn == bpn)
  						c->pn = apn;
  				}
  				ndoms--;	/* one less element */
  				goto restart;
  			}
  		}
  	}

  	/*
  	 * 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(ndoms * sizeof(struct sched_domain_attr), GFP_KERNEL);

  
  	for (nslot = 0, i = 0; i < csn; i++) {
  		struct cpuset *a = csa[i];

  		struct cpumask *dp;

  		int apn = a->pn;

  		if (apn < 0) {
  			/* Skip completed partitions */
  			continue;
  		}

  		dp = doms[nslot];

  
  		if (nslot == ndoms) {
  			static int warnings = 10;
  			if (warnings) {

  				pr_warn("rebuild_sched_domains confused: nslot %d, ndoms %d, csn %d, i %d, apn %d
  ",
  					nslot, ndoms, csn, i, apn);

  				warnings--;

  			}

  			continue;
  		}

  		cpumask_clear(dp);

  		if (dattr)
  			*(dattr + nslot) = SD_ATTR_INIT;
  		for (j = i; j < csn; j++) {
  			struct cpuset *b = csa[j];
  
  			if (apn == b->pn) {

  				cpumask_or(dp, dp, b->effective_cpus);

  				cpumask_and(dp, dp, non_isolated_cpus);

  				if (dattr)
  					update_domain_attr_tree(dattr + nslot, b);
  
  				/* Done with this partition */
  				b->pn = -1;

  			}

  		}

  		nslot++;

  	}
  	BUG_ON(nslot != ndoms);

  done:

  	free_cpumask_var(non_isolated_cpus);

  	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;
  }
  
  /*
   * Rebuild scheduler domains.
   *

   * If the flag 'sched_load_balance' of any cpuset with non-empty
   * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset
   * which has that flag enabled, or if any cpuset with a non-empty
   * 'cpus' is removed, then call this routine to rebuild the
   * scheduler's dynamic sched domains.

   *

   * Call with cpuset_mutex held.  Takes get_online_cpus().

   */

  static void rebuild_sched_domains_locked(void)

  {
  	struct sched_domain_attr *attr;

  	cpumask_var_t *doms;

  	int ndoms;

  	lockdep_assert_held(&cpuset_mutex);

  	get_online_cpus();

  	/*
  	 * We have raced with CPU hotplug. Don't do anything to avoid
  	 * passing doms with offlined cpu to partition_sched_domains().
  	 * Anyways, hotplug work item will rebuild sched domains.
  	 */

  	if (!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))

  		goto out;

  	/* Generate domain masks and attrs */

  	ndoms = generate_sched_domains(&doms, &attr);

  
  	/* Have scheduler rebuild the domains */
  	partition_sched_domains(ndoms, doms, attr);

  out:

  	put_online_cpus();

  }

  #else /* !CONFIG_SMP */

  static void rebuild_sched_domains_locked(void)

  {
  }

  #endif /* CONFIG_SMP */

  void rebuild_sched_domains(void)
  {

  	mutex_lock(&cpuset_mutex);

  	rebuild_sched_domains_locked();

  	mutex_unlock(&cpuset_mutex);

  }

  /**

   * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
   * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed

   *

   * Iterate through each task of @cs updating its cpus_allowed to the
   * effective cpuset's.  As this function is called with cpuset_mutex held,
   * cpuset membership stays stable.

   */

  static void update_tasks_cpumask(struct cpuset *cs)

  {

  	struct css_task_iter it;
  	struct task_struct *task;
  
  	css_task_iter_start(&cs->css, &it);
  	while ((task = css_task_iter_next(&it)))

  		set_cpus_allowed_ptr(task, cs->effective_cpus);

  	css_task_iter_end(&it);

  }

  /*

   * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree
   * @cs: the cpuset to consider
   * @new_cpus: temp variable for calculating new effective_cpus
   *
   * When congifured cpumask is changed, the effective cpumasks of this cpuset
   * and all its descendants need to be updated.

   *

   * On legacy hierachy, effective_cpus will be the same with cpu_allowed.

   *
   * Called with cpuset_mutex held
   */

  static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)

  {
  	struct cpuset *cp;

  	struct cgroup_subsys_state *pos_css;

  	bool need_rebuild_sched_domains = false;

  
  	rcu_read_lock();

  	cpuset_for_each_descendant_pre(cp, pos_css, cs) {
  		struct cpuset *parent = parent_cs(cp);
  
  		cpumask_and(new_cpus, cp->cpus_allowed, parent->effective_cpus);

  		/*
  		 * If it becomes empty, inherit the effective mask of the
  		 * parent, which is guaranteed to have some CPUs.
  		 */

  		if (cgroup_on_dfl(cp->css.cgroup) && cpumask_empty(new_cpus))

  			cpumask_copy(new_cpus, parent->effective_cpus);

  		/* Skip the whole subtree if the cpumask remains the same. */
  		if (cpumask_equal(new_cpus, cp->effective_cpus)) {
  			pos_css = css_rightmost_descendant(pos_css);
  			continue;

  		}

  		if (!css_tryget_online(&cp->css))

  			continue;
  		rcu_read_unlock();

  		spin_lock_irq(&callback_lock);

  		cpumask_copy(cp->effective_cpus, new_cpus);

  		spin_unlock_irq(&callback_lock);

  
  		WARN_ON(!cgroup_on_dfl(cp->css.cgroup) &&
  			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));

  		update_tasks_cpumask(cp);

  		/*
  		 * If the effective cpumask of any non-empty cpuset is changed,
  		 * we need to rebuild sched domains.
  		 */
  		if (!cpumask_empty(cp->cpus_allowed) &&
  		    is_sched_load_balance(cp))
  			need_rebuild_sched_domains = true;

  		rcu_read_lock();
  		css_put(&cp->css);
  	}
  	rcu_read_unlock();

  
  	if (need_rebuild_sched_domains)
  		rebuild_sched_domains_locked();

  }

  /**

   * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it
   * @cs: the cpuset to consider

   * @trialcs: trial cpuset

   * @buf: buffer of cpu numbers written to this cpuset
   */

  static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
  			  const char *buf)

  {

  	int retval;

  	/* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */

  	if (cs == &top_cpuset)
  		return -EACCES;

  	/*

  	 * An empty cpus_allowed is ok only if the cpuset has no tasks.

  	 * Since cpulist_parse() fails on an empty mask, we special case
  	 * that parsing.  The validate_change() call ensures that cpusets
  	 * with tasks have cpus.

  	 */

  	if (!*buf) {

  		cpumask_clear(trialcs->cpus_allowed);

  	} else {

  		retval = cpulist_parse(buf, trialcs->cpus_allowed);

  		if (retval < 0)
  			return retval;

  		if (!cpumask_subset(trialcs->cpus_allowed,
  				    top_cpuset.cpus_allowed))

  			return -EINVAL;

  	}

  	/* Nothing to do if the cpus didn't change */

  	if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed))

  		return 0;

  	retval = validate_change(cs, trialcs);
  	if (retval < 0)
  		return retval;

  	spin_lock_irq(&callback_lock);

  	cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);

  	spin_unlock_irq(&callback_lock);

  	/* use trialcs->cpus_allowed as a temp variable */
  	update_cpumasks_hier(cs, trialcs->cpus_allowed);

  	return 0;

  }

  /*

   * cpuset_migrate_mm
   *
   *    Migrate memory region from one set of nodes to another.
   *
   *    Temporarilly set tasks mems_allowed to target nodes of migration,
   *    so that the migration code can allocate pages on these nodes.
   *

   *    While the mm_struct we are migrating is typically from some
   *    other task, the task_struct mems_allowed that we are hacking
   *    is for our current task, which must allocate new pages for that
   *    migrating memory region.

   */
  
  static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
  							const nodemask_t *to)
  {
  	struct task_struct *tsk = current;

  	tsk->mems_allowed = *to;

  
  	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);

  	rcu_read_lock();

  	guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed);

  	rcu_read_unlock();

  }

  /*

   * cpuset_change_task_nodemask - change task's mems_allowed and mempolicy
   * @tsk: the task to change
   * @newmems: new nodes that the task will be set
   *
   * In order to avoid seeing no nodes if the old and new nodes are disjoint,
   * we structure updates as setting all new allowed nodes, then clearing newly
   * disallowed ones.

   */
  static void cpuset_change_task_nodemask(struct task_struct *tsk,
  					nodemask_t *newmems)
  {

  	bool need_loop;

  	/*
  	 * Allow tasks that have access to memory reserves because they have
  	 * been OOM killed to get memory anywhere.
  	 */
  	if (unlikely(test_thread_flag(TIF_MEMDIE)))
  		return;
  	if (current->flags & PF_EXITING) /* Let dying task have memory */
  		return;
  
  	task_lock(tsk);

  	/*
  	 * Determine if a loop is necessary if another thread is doing

  	 * read_mems_allowed_begin().  If at least one node remains unchanged and

  	 * tsk does not have a mempolicy, then an empty nodemask will not be
  	 * possible when mems_allowed is larger than a word.
  	 */
  	need_loop = task_has_mempolicy(tsk) ||
  			!nodes_intersects(*newmems, tsk->mems_allowed);

  	if (need_loop) {
  		local_irq_disable();

  		write_seqcount_begin(&tsk->mems_allowed_seq);

  	}

  	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
  	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);

  
  	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);

  	tsk->mems_allowed = *newmems;

  	if (need_loop) {

  		write_seqcount_end(&tsk->mems_allowed_seq);

  		local_irq_enable();
  	}

  	task_unlock(tsk);

  }

  static void *cpuset_being_rebound;

  /**
   * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset.
   * @cs: the cpuset in which each task's mems_allowed mask needs to be changed

   *

   * Iterate through each task of @cs updating its mems_allowed to the
   * effective cpuset's.  As this function is called with cpuset_mutex held,
   * cpuset membership stays stable.

   */

  static void update_tasks_nodemask(struct cpuset *cs)

  {

  	static nodemask_t newmems;	/* protected by cpuset_mutex */

  	struct css_task_iter it;
  	struct task_struct *task;

  	cpuset_being_rebound = cs;		/* causes mpol_dup() rebind */

  	guarantee_online_mems(cs, &newmems);

  	/*

  	 * The mpol_rebind_mm() call takes mmap_sem, which we couldn't
  	 * take while holding tasklist_lock.  Forks can happen - the
  	 * mpol_dup() cpuset_being_rebound check will catch such forks,
  	 * and rebind their vma mempolicies too.  Because we still hold

  	 * the global cpuset_mutex, we know that no other rebind effort

  	 * will be contending for the global variable cpuset_being_rebound.

  	 * It's ok if we rebind the same mm twice; mpol_rebind_mm()

  	 * is idempotent.  Also migrate pages in each mm to new nodes.

  	 */

  	css_task_iter_start(&cs->css, &it);
  	while ((task = css_task_iter_next(&it))) {
  		struct mm_struct *mm;
  		bool migrate;
  
  		cpuset_change_task_nodemask(task, &newmems);
  
  		mm = get_task_mm(task);
  		if (!mm)
  			continue;
  
  		migrate = is_memory_migrate(cs);
  
  		mpol_rebind_mm(mm, &cs->mems_allowed);
  		if (migrate)
  			cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems);
  		mmput(mm);
  	}
  	css_task_iter_end(&it);

  	/*
  	 * All the tasks' nodemasks have been updated, update
  	 * cs->old_mems_allowed.
  	 */
  	cs->old_mems_allowed = newmems;

  	/* We're done rebinding vmas to this cpuset's new mems_allowed. */

  	cpuset_being_rebound = NULL;

  }

  /*

   * update_nodemasks_hier - Update effective nodemasks and tasks in the subtree
   * @cs: the cpuset to consider
   * @new_mems: a temp variable for calculating new effective_mems

   *

   * When configured nodemask is changed, the effective nodemasks of this cpuset
   * and all its descendants need to be updated.

   *

   * On legacy hiearchy, effective_mems will be the same with mems_allowed.

   *
   * Called with cpuset_mutex held
   */

  static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)

  {
  	struct cpuset *cp;

  	struct cgroup_subsys_state *pos_css;

  
  	rcu_read_lock();

  	cpuset_for_each_descendant_pre(cp, pos_css, cs) {
  		struct cpuset *parent = parent_cs(cp);
  
  		nodes_and(*new_mems, cp->mems_allowed, parent->effective_mems);

  		/*
  		 * If it becomes empty, inherit the effective mask of the
  		 * parent, which is guaranteed to have some MEMs.
  		 */

  		if (cgroup_on_dfl(cp->css.cgroup) && nodes_empty(*new_mems))

  			*new_mems = parent->effective_mems;

  		/* Skip the whole subtree if the nodemask remains the same. */
  		if (nodes_equal(*new_mems, cp->effective_mems)) {
  			pos_css = css_rightmost_descendant(pos_css);
  			continue;

  		}

  		if (!css_tryget_online(&cp->css))

  			continue;
  		rcu_read_unlock();

  		spin_lock_irq(&callback_lock);

  		cp->effective_mems = *new_mems;

  		spin_unlock_irq(&callback_lock);

  
  		WARN_ON(!cgroup_on_dfl(cp->css.cgroup) &&

  			!nodes_equal(cp->mems_allowed, cp->effective_mems));

  		update_tasks_nodemask(cp);

  
  		rcu_read_lock();
  		css_put(&cp->css);
  	}
  	rcu_read_unlock();
  }
  
  /*

   * Handle user request to change the 'mems' memory placement
   * of a cpuset.  Needs to validate the request, update the

   * cpusets mems_allowed, and for each task in the cpuset,
   * update mems_allowed and rebind task's mempolicy and any vma
   * mempolicies and if the cpuset is marked 'memory_migrate',
   * migrate the tasks pages to the new memory.

   *

   * Call with cpuset_mutex held. May take callback_lock during call.

   * Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
   * lock each such tasks mm->mmap_sem, scan its vma's and rebind
   * their mempolicies to the cpusets new mems_allowed.
   */

  static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
  			   const char *buf)

  {

  	int retval;
  
  	/*

  	 * top_cpuset.mems_allowed tracks node_stats[N_MEMORY];

  	 * it's read-only
  	 */

  	if (cs == &top_cpuset) {
  		retval = -EACCES;
  		goto done;
  	}

  	/*
  	 * An empty mems_allowed is ok iff there are no tasks in the cpuset.
  	 * Since nodelist_parse() fails on an empty mask, we special case
  	 * that parsing.  The validate_change() call ensures that cpusets
  	 * with tasks have memory.
  	 */
  	if (!*buf) {

  		nodes_clear(trialcs->mems_allowed);

  	} else {

  		retval = nodelist_parse(buf, trialcs->mems_allowed);

  		if (retval < 0)
  			goto done;

  		if (!nodes_subset(trialcs->mems_allowed,

  				  top_cpuset.mems_allowed)) {
  			retval = -EINVAL;

  			goto done;
  		}

  	}

  
  	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;

  	spin_lock_irq(&callback_lock);

  	cs->mems_allowed = trialcs->mems_allowed;

  	spin_unlock_irq(&callback_lock);

  	/* use trialcs->mems_allowed as a temp variable */

  	update_nodemasks_hier(cs, &trialcs->mems_allowed);

  done:
  	return retval;
  }

  int current_cpuset_is_being_rebound(void)
  {

  	int ret;
  
  	rcu_read_lock();
  	ret = task_cs(current) == cpuset_being_rebound;
  	rcu_read_unlock();
  
  	return ret;

  }

  static int update_relax_domain_level(struct cpuset *cs, s64 val)

  {

  #ifdef CONFIG_SMP

  	if (val < -1 || val >= sched_domain_level_max)

  		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;
  }

  /**

   * 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.

   */

  static void update_tasks_flags(struct cpuset *cs)

  {

  	struct css_task_iter it;
  	struct task_struct *task;
  
  	css_task_iter_start(&cs->css, &it);
  	while ((task = css_task_iter_next(&it)))
  		cpuset_update_task_spread_flag(cs, task);
  	css_task_iter_end(&it);

  }
  
  /*

   * update_flag - read a 0 or a 1 in a file and update associated flag

   * bit:		the bit to update (see cpuset_flagbits_t)
   * cs:		the cpuset to update
   * turning_on: 	whether the flag is being set or cleared

   *

   * Call with cpuset_mutex held.

   */

  static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
  		       int turning_on)

  {

  	struct cpuset *trialcs;

  	int balance_flag_changed;

  	int spread_flag_changed;

  	int err;

  	trialcs = alloc_trial_cpuset(cs);
  	if (!trialcs)
  		return -ENOMEM;

  	if (turning_on)

  		set_bit(bit, &trialcs->flags);

  	else

  		clear_bit(bit, &trialcs->flags);

  	err = validate_change(cs, trialcs);

  	if (err < 0)

  		goto out;

  	balance_flag_changed = (is_sched_load_balance(cs) !=

  				is_sched_load_balance(trialcs));

  	spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs))
  			|| (is_spread_page(cs) != is_spread_page(trialcs)));

  	spin_lock_irq(&callback_lock);

  	cs->flags = trialcs->flags;

  	spin_unlock_irq(&callback_lock);

  	if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed)

  		rebuild_sched_domains_locked();

  	if (spread_flag_changed)

  		update_tasks_flags(cs);

  out:
  	free_trial_cpuset(trialcs);
  	return err;

  }

  /*

   * 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 ((time_t)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)
  {
  	time_t now = get_seconds();
  	time_t 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;
  }

  static struct cpuset *cpuset_attach_old_cs;

  /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */

  static int cpuset_can_attach(struct cgroup_subsys_state *css,
  			     struct cgroup_taskset *tset)

  {

  	struct cpuset *cs = css_cs(css);

  	struct task_struct *task;
  	int ret;

  	/* used later by cpuset_attach() */
  	cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset));

  	mutex_lock(&cpuset_mutex);

  	/* allow moving tasks into an empty cpuset if on default hierarchy */

  	ret = -ENOSPC;

  	if (!cgroup_on_dfl(css->cgroup) &&

  	    (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))

  		goto out_unlock;

  	cgroup_taskset_for_each(task, tset) {

  		ret = task_can_attach(task, cs->cpus_allowed);
  		if (ret)

  			goto out_unlock;
  		ret = security_task_setscheduler(task);
  		if (ret)
  			goto out_unlock;

  	}

  	/*
  	 * Mark attach is in progress.  This makes validate_change() fail
  	 * changes which zero cpus/mems_allowed.
  	 */
  	cs->attach_in_progress++;

  	ret = 0;
  out_unlock:
  	mutex_unlock(&cpuset_mutex);
  	return ret;

  }

  static void cpuset_cancel_attach(struct cgroup_subsys_state *css,

  				 struct cgroup_taskset *tset)
  {

  	mutex_lock(&cpuset_mutex);

  	css_cs(css)->attach_in_progress--;