/*
   *  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/fs_context.h>

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

  #include <linux/rcupdate.h>

  #include <linux/sched.h>

  #include <linux/sched/deadline.h>

  #include <linux/sched/mm.h>

  #include <linux/sched/task.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/time64.h>

  #include <linux/backing-dev.h>
  #include <linux/sort.h>

  #include <linux/oom.h>

  #include <linux/sched/isolation.h>

  #include <linux/uaccess.h>

  #include <linux/atomic.h>

  #include <linux/mutex.h>

  #include <linux/cgroup.h>

  #include <linux/wait.h>

  #include <trace/hooks/sched.h>

  DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key);

  DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key);

  /* 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 */
  };

  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;

  	cpumask_var_t cpus_requested;

  	nodemask_t mems_allowed;
  
  	/* effective CPUs and Memory Nodes allow to tasks */
  	cpumask_var_t effective_cpus;
  	nodemask_t effective_mems;

  	/*

  	 * CPUs allocated to child sub-partitions (default hierarchy only)
  	 * - CPUs granted by the parent = effective_cpus U subparts_cpus
  	 * - effective_cpus and subparts_cpus are mutually exclusive.

  	 *
  	 * effective_cpus contains only onlined CPUs, but subparts_cpus
  	 * may have offlined ones.

  	 */
  	cpumask_var_t subparts_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;

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

  	/* for custom sched domain */
  	int relax_domain_level;

  
  	/* number of CPUs in subparts_cpus */
  	int nr_subparts_cpus;
  
  	/* partition root state */
  	int partition_root_state;

  
  	/*
  	 * Default hierarchy only:
  	 * use_parent_ecpus - set if using parent's effective_cpus
  	 * child_ecpus_count - # of children with use_parent_ecpus set
  	 */
  	int use_parent_ecpus;
  	int child_ecpus_count;

  };
  
  /*
   * Partition root states:
   *
   *   0 - not a partition root

   *

   *   1 - partition root

   *
   *  -1 - invalid partition root
   *       None of the cpus in cpus_allowed can be put into the parent's
   *       subparts_cpus. In this case, the cpuset is not a real partition
   *       root anymore.  However, the CPU_EXCLUSIVE bit will still be set
   *       and the cpuset can be restored back to a partition root if the
   *       parent cpuset can give more CPUs back to this child cpuset.

   */
  #define PRS_DISABLED		0
  #define PRS_ENABLED		1

  #define PRS_ERROR		-1

  
  /*
   * Temporary cpumasks for working with partitions that are passed among
   * functions to avoid memory allocation in inner functions.
   */
  struct tmpmasks {
  	cpumask_var_t addmask, delmask;	/* For partition root */
  	cpumask_var_t new_cpus;		/* For update_cpumasks_hier() */

  };

  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);

  }

  /* 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(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);
  }

  static inline int is_partition_root(const struct cpuset *cs)
  {

  	return cs->partition_root_state > 0;

  }

  static struct cpuset top_cpuset = {

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

  	.partition_root_state = PRS_ENABLED,

  };

  /**
   * 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);

  static struct workqueue_struct *cpuset_migrate_mm_wq;

  /*

   * CPU / memory hotplug is handled asynchronously
   * for hotplug, synchronously for resume_cpus

   */

  static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn);

  static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq);

  /*

   * Cgroup v2 behavior is used on the "cpus" and "mems" control files when
   * on default hierarchy or when the cpuset_v2_mode flag is set by mounting
   * the v1 cpuset cgroup filesystem with the "cpuset_v2_mode" mount option.
   * With v2 behavior, "cpus" and "mems" are always what the users have
   * requested and won't be changed by hotplug events. Only the effective
   * cpus or mems will be affected.

   */
  static inline bool is_in_v2_mode(void)
  {
  	return cgroup_subsys_on_dfl(cpuset_cgrp_subsys) ||
  	      (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE);
  }
  
  /*

   * 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.

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

   * of cpu_active_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_active_mask)) {

  		cs = parent_cs(cs);

  		if (unlikely(!cs)) {
  			/*
  			 * The top cpuset doesn't have any online cpu as a
  			 * consequence of a race between cpuset_hotplug_work
  			 * and cpu hotplug notifier.  But we know the top

  			 * cpuset's effective_cpus is on its way to be

  			 * identical to cpu_online_mask.
  			 */

  			cpumask_copy(pmask, cpu_active_mask);

  			return;
  		}
  	}

  	cpumask_and(pmask, cs->effective_cpus, cpu_active_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_requested, q->cpus_requested) &&

  		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_cpumasks - allocate three cpumasks for cpuset
   * @cs:  the cpuset that have cpumasks to be allocated.
   * @tmp: the tmpmasks structure pointer
   * Return: 0 if successful, -ENOMEM otherwise.
   *
   * Only one of the two input arguments should be non-NULL.
   */
  static inline int alloc_cpumasks(struct cpuset *cs, struct tmpmasks *tmp)
  {
  	cpumask_var_t *pmask1, *pmask2, *pmask3;
  
  	if (cs) {
  		pmask1 = &cs->cpus_allowed;
  		pmask2 = &cs->effective_cpus;
  		pmask3 = &cs->subparts_cpus;
  	} else {
  		pmask1 = &tmp->new_cpus;
  		pmask2 = &tmp->addmask;
  		pmask3 = &tmp->delmask;
  	}
  
  	if (!zalloc_cpumask_var(pmask1, GFP_KERNEL))
  		return -ENOMEM;
  
  	if (!zalloc_cpumask_var(pmask2, GFP_KERNEL))
  		goto free_one;
  
  	if (!zalloc_cpumask_var(pmask3, GFP_KERNEL))
  		goto free_two;

  	if (cs && !zalloc_cpumask_var(&cs->cpus_requested, GFP_KERNEL))
  		goto free_three;

  	return 0;

  free_three:
  	free_cpumask_var(*pmask3);

  free_two:
  	free_cpumask_var(*pmask2);
  free_one:
  	free_cpumask_var(*pmask1);
  	return -ENOMEM;
  }
  
  /**
   * free_cpumasks - free cpumasks in a tmpmasks structure
   * @cs:  the cpuset that have cpumasks to be free.
   * @tmp: the tmpmasks structure pointer
   */
  static inline void free_cpumasks(struct cpuset *cs, struct tmpmasks *tmp)
  {
  	if (cs) {
  		free_cpumask_var(cs->cpus_allowed);

  		free_cpumask_var(cs->cpus_requested);

  		free_cpumask_var(cs->effective_cpus);
  		free_cpumask_var(cs->subparts_cpus);
  	}
  	if (tmp) {
  		free_cpumask_var(tmp->new_cpus);
  		free_cpumask_var(tmp->addmask);
  		free_cpumask_var(tmp->delmask);
  	}
  }
  
  /**

   * 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_cpumasks(trial, NULL)) {
  		kfree(trial);
  		return NULL;
  	}

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

  	cpumask_copy(trial->cpus_requested, cs->cpus_requested);

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

  	return trial;

  }
  
  /**

   * free_cpuset - free the cpuset
   * @cs: the cpuset to be freed

   */

  static inline void free_cpuset(struct cpuset *cs)

  {

  	free_cpumasks(cs, NULL);
  	kfree(cs);

  }

  /*
   * 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 (!is_in_v2_mode() && !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_requested, c->cpus_requested))

  			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_is_populated(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();

  }

  /* Must be called with cpuset_mutex held.  */
  static inline int nr_cpusets(void)
  {
  	/* jump label reference count + the top-level cpuset */
  	return static_key_count(&cpusets_enabled_key.key) + 1;
  }

  /*

   * 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/admin-guide/cgroup-v1/cpusets.rst

   * 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:

   *    cp - cpuset pointer, used (together with pos_css) to perform a
   *	   top-down scan of all cpusets. 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;	/* 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, k;		/* 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;

  	bool root_load_balance = is_sched_load_balance(&top_cpuset);

  	doms = NULL;

  	dattr = NULL;

  	csa = NULL;

  
  	/* Special case for the 99% of systems with one, full, sched domain */

  	if (root_load_balance && !top_cpuset.nr_subparts_cpus) {

  		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,

  			    housekeeping_cpumask(HK_FLAG_DOMAIN));

  		goto done;

  	}

  	csa = kmalloc_array(nr_cpusets(), sizeof(cp), GFP_KERNEL);

  	if (!csa)
  		goto done;
  	csn = 0;

  	rcu_read_lock();

  	if (root_load_balance)
  		csa[csn++] = &top_cpuset;

  	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 root is load-balancing, we can skip @cp if it
  		 * is a subset of the root's effective_cpus.

  		 */

  		if (!cpumask_empty(cp->cpus_allowed) &&

  		    !(is_sched_load_balance(cp) &&

  		      cpumask_intersects(cp->cpus_allowed,
  					 housekeeping_cpumask(HK_FLAG_DOMAIN))))

  			continue;

  		if (root_load_balance &&
  		    cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus))
  			continue;

  		if (is_sched_load_balance(cp) &&
  		    !cpumask_empty(cp->effective_cpus))

  			csa[csn++] = cp;

  		/* skip @cp's subtree if not a partition root */
  		if (!is_partition_root(cp))
  			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_array(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, housekeeping_cpumask(HK_FLAG_DOMAIN));

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

  			}

  		}

  		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;
  }

  static void update_tasks_root_domain(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)))
  		dl_add_task_root_domain(task);
  
  	css_task_iter_end(&it);
  }
  
  static void rebuild_root_domains(void)
  {
  	struct cpuset *cs = NULL;
  	struct cgroup_subsys_state *pos_css;

  	lockdep_assert_held(&cpuset_mutex);

  	lockdep_assert_cpus_held();
  	lockdep_assert_held(&sched_domains_mutex);

  	rcu_read_lock();
  
  	/*
  	 * Clear default root domain DL accounting, it will be computed again
  	 * if a task belongs to it.
  	 */
  	dl_clear_root_domain(&def_root_domain);
  
  	cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
  
  		if (cpumask_empty(cs->effective_cpus)) {
  			pos_css = css_rightmost_descendant(pos_css);
  			continue;
  		}
  
  		css_get(&cs->css);
  
  		rcu_read_unlock();
  
  		update_tasks_root_domain(cs);
  
  		rcu_read_lock();
  		css_put(&cs->css);
  	}
  	rcu_read_unlock();
  }
  
  static void
  partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
  				    struct sched_domain_attr *dattr_new)
  {
  	mutex_lock(&sched_domains_mutex);
  	partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
  	rebuild_root_domains();
  	mutex_unlock(&sched_domains_mutex);
  }

  /*
   * 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 cgroup_subsys_state *pos_css;

  	struct sched_domain_attr *attr;

  	cpumask_var_t *doms;

  	struct cpuset *cs;

  	int ndoms;

  	lockdep_assert_held(&cpuset_mutex);

  	/*

  	 * If we have raced with CPU hotplug, return early to avoid

  	 * passing doms with offlined cpu to partition_sched_domains().

  	 * Anyways, cpuset_hotplug_workfn() will rebuild sched domains.
  	 *
  	 * With no CPUs in any subpartitions, top_cpuset's effective CPUs
  	 * should be the same as the active CPUs, so checking only top_cpuset
  	 * is enough to detect racing CPU offlines.

  	 */

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

  		return;

  	/*
  	 * With subpartition CPUs, however, the effective CPUs of a partition
  	 * root should be only a subset of the active CPUs.  Since a CPU in any
  	 * partition root could be offlined, all must be checked.
  	 */
  	if (top_cpuset.nr_subparts_cpus) {
  		rcu_read_lock();
  		cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
  			if (!is_partition_root(cs)) {
  				pos_css = css_rightmost_descendant(pos_css);
  				continue;
  			}
  			if (!cpumask_subset(cs->effective_cpus,
  					    cpu_active_mask)) {
  				rcu_read_unlock();
  				return;
  			}
  		}
  		rcu_read_unlock();
  	}

  	/* Generate domain masks and attrs */

  	ndoms = generate_sched_domains(&doms, &attr);

  
  	/* Have scheduler rebuild the domains */

  	partition_and_rebuild_sched_domains(ndoms, doms, attr);

  }

  #else /* !CONFIG_SMP */

  static void rebuild_sched_domains_locked(void)

  {
  }

  #endif /* CONFIG_SMP */

  void rebuild_sched_domains(void)
  {

  	get_online_cpus();

  	mutex_lock(&cpuset_mutex);

  	rebuild_sched_domains_locked();

  	mutex_unlock(&cpuset_mutex);

  	put_online_cpus();

  }

  static int update_cpus_allowed(struct cpuset *cs, struct task_struct *p,
  				const struct cpumask *new_mask)
  {
  	int ret = -EINVAL;
  
  	trace_android_rvh_update_cpus_allowed(p, cs->cpus_requested, new_mask, &ret);
  	if (!ret)
  		return ret;
  
  	return set_cpus_allowed_ptr(p, new_mask);
  }

  /**

   * 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, 0, &it);

  	while ((task = css_task_iter_next(&it)))

  		update_cpus_allowed(cs, task, cs->effective_cpus);

  	css_task_iter_end(&it);

  }

  /**
   * compute_effective_cpumask - Compute the effective cpumask of the cpuset
   * @new_cpus: the temp variable for the new effective_cpus mask
   * @cs: the cpuset the need to recompute the new effective_cpus mask
   * @parent: the parent cpuset
   *
   * If the parent has subpartition CPUs, include them in the list of

   * allowable CPUs in computing the new effective_cpus mask. Since offlined
   * CPUs are not removed from subparts_cpus, we have to use cpu_active_mask
   * to mask those out.

   */
  static void compute_effective_cpumask(struct cpumask *new_cpus,
  				      struct cpuset *cs, struct cpuset *parent)
  {
  	if (parent->nr_subparts_cpus) {
  		cpumask_or(new_cpus, parent->effective_cpus,
  			   parent->subparts_cpus);

  		cpumask_and(new_cpus, new_cpus, cs->cpus_requested);

  		cpumask_and(new_cpus, new_cpus, cpu_active_mask);

  	} else {

  		cpumask_and(new_cpus, cs->cpus_requested, parent_cs(cs)->effective_cpus);

  	}
  }
  
  /*
   * Commands for update_parent_subparts_cpumask
   */
  enum subparts_cmd {
  	partcmd_enable,		/* Enable partition root	 */
  	partcmd_disable,	/* Disable partition root	 */
  	partcmd_update,		/* Update parent's subparts_cpus */
  };
  
  /**
   * update_parent_subparts_cpumask - update subparts_cpus mask of parent cpuset
   * @cpuset:  The cpuset that requests change in partition root state
   * @cmd:     Partition root state change command
   * @newmask: Optional new cpumask for partcmd_update
   * @tmp:     Temporary addmask and delmask
   * Return:   0, 1 or an error code
   *
   * For partcmd_enable, the cpuset is being transformed from a non-partition
   * root to a partition root. The cpus_allowed mask of the given cpuset will
   * be put into parent's subparts_cpus and taken away from parent's
   * effective_cpus. The function will return 0 if all the CPUs listed in
   * cpus_allowed can be granted or an error code will be returned.
   *
   * For partcmd_disable, the cpuset is being transofrmed from a partition
   * root back to a non-partition root. any CPUs in cpus_allowed that are in
   * parent's subparts_cpus will be taken away from that cpumask and put back
   * into parent's effective_cpus. 0 should always be returned.
   *
   * For partcmd_update, if the optional newmask is specified, the cpu
   * list is to be changed from cpus_allowed to newmask. Otherwise,

   * cpus_allowed is assumed to remain the same. The cpuset should either
   * be a partition root or an invalid partition root. The partition root
   * state may change if newmask is NULL and none of the requested CPUs can
   * be granted by the parent. The function will return 1 if changes to
   * parent's subparts_cpus and effective_cpus happen or 0 otherwise.
   * Error code should only be returned when newmask is non-NULL.

   *
   * The partcmd_enable and partcmd_disable commands are used by
   * update_prstate(). The partcmd_update command is used by
   * update_cpumasks_hier() with newmask NULL and update_cpumask() with
   * newmask set.
   *
   * The checking is more strict when enabling partition root than the
   * other two commands.
   *
   * Because of the implicit cpu exclusive nature of a partition root,
   * cpumask changes that violates the cpu exclusivity rule will not be
   * permitted when checked by validate_change(). The validate_change()
   * function will also prevent any changes to the cpu list if it is not
   * a superset of children's cpu lists.
   */
  static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
  					  struct cpumask *newmask,
  					  struct tmpmasks *tmp)
  {
  	struct cpuset *parent = parent_cs(cpuset);
  	int adding;	/* Moving cpus from effective_cpus to subparts_cpus */
  	int deleting;	/* Moving cpus from subparts_cpus to effective_cpus */

  	bool part_error = false;	/* Partition error? */

  	lockdep_assert_held(&cpuset_mutex);

  
  	/*
  	 * The parent must be a partition root.
  	 * The new cpumask, if present, or the current cpus_allowed must
  	 * not be empty.
  	 */
  	if (!is_partition_root(parent) ||
  	   (newmask && cpumask_empty(newmask)) ||
  	   (!newmask && cpumask_empty(cpuset->cpus_allowed)))
  		return -EINVAL;
  
  	/*
  	 * Enabling/disabling partition root is not allowed if there are
  	 * online children.
  	 */
  	if ((cmd != partcmd_update) && css_has_online_children(&cpuset->css))
  		return -EBUSY;
  
  	/*
  	 * Enabling partition root is not allowed if not all the CPUs
  	 * can be granted from parent's effective_cpus or at least one
  	 * CPU will be left after that.
  	 */
  	if ((cmd == partcmd_enable) &&
  	   (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) ||
  	     cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus)))
  		return -EINVAL;
  
  	/*
  	 * A cpumask update cannot make parent's effective_cpus become empty.
  	 */
  	adding = deleting = false;
  	if (cmd == partcmd_enable) {
  		cpumask_copy(tmp->addmask, cpuset->cpus_allowed);
  		adding = true;
  	} else if (cmd == partcmd_disable) {
  		deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed,
  				       parent->subparts_cpus);
  	} else if (newmask) {
  		/*
  		 * partcmd_update with newmask:
  		 *
  		 * delmask = cpus_allowed & ~newmask & parent->subparts_cpus
  		 * addmask = newmask & parent->effective_cpus
  		 *		     & ~parent->subparts_cpus
  		 */
  		cpumask_andnot(tmp->delmask, cpuset->cpus_allowed, newmask);
  		deleting = cpumask_and(tmp->delmask, tmp->delmask,
  				       parent->subparts_cpus);
  
  		cpumask_and(tmp->addmask, newmask, parent->effective_cpus);
  		adding = cpumask_andnot(tmp->addmask, tmp->addmask,
  					parent->subparts_cpus);
  		/*
  		 * Return error if the new effective_cpus could become empty.
  		 */

  		if (adding &&
  		    cpumask_equal(parent->effective_cpus, tmp->addmask)) {
  			if (!deleting)
  				return -EINVAL;
  			/*
  			 * As some of the CPUs in subparts_cpus might have
  			 * been offlined, we need to compute the real delmask
  			 * to confirm that.
  			 */
  			if (!cpumask_and(tmp->addmask, tmp->delmask,
  					 cpu_active_mask))
  				return -EINVAL;
  			cpumask_copy(tmp->addmask, parent->effective_cpus);
  		}

  	} else {
  		/*
  		 * partcmd_update w/o newmask:
  		 *
  		 * addmask = cpus_allowed & parent->effectiveb_cpus
  		 *
  		 * Note that parent's subparts_cpus may have been

  		 * pre-shrunk in case there is a change in the cpu list.
  		 * So no deletion is needed.

  		 */
  		adding = cpumask_and(tmp->addmask, cpuset->cpus_allowed,
  				     parent->effective_cpus);

  		part_error = cpumask_equal(tmp->addmask,
  					   parent->effective_cpus);
  	}
  
  	if (cmd == partcmd_update) {
  		int prev_prs = cpuset->partition_root_state;
  
  		/*
  		 * Check for possible transition between PRS_ENABLED
  		 * and PRS_ERROR.
  		 */
  		switch (cpuset->partition_root_state) {
  		case PRS_ENABLED:
  			if (part_error)
  				cpuset->partition_root_state = PRS_ERROR;
  			break;
  		case PRS_ERROR:
  			if (!part_error)
  				cpuset->partition_root_state = PRS_ENABLED;
  			break;
  		}
  		/*
  		 * Set part_error if previously in invalid state.
  		 */
  		part_error = (prev_prs == PRS_ERROR);
  	}
  
  	if (!part_error && (cpuset->partition_root_state == PRS_ERROR))
  		return 0;	/* Nothing need to be done */
  
  	if (cpuset->partition_root_state == PRS_ERROR) {
  		/*
  		 * Remove all its cpus from parent's subparts_cpus.
  		 */
  		adding = false;
  		deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed,
  				       parent->subparts_cpus);

  	}
  
  	if (!adding && !deleting)
  		return 0;
  
  	/*
  	 * Change the parent's subparts_cpus.
  	 * Newly added CPUs will be removed from effective_cpus and
  	 * newly deleted ones will be added back to effective_cpus.
  	 */
  	spin_lock_irq(&callback_lock);
  	if (adding) {
  		cpumask_or(parent->subparts_cpus,
  			   parent->subparts_cpus, tmp->addmask);
  		cpumask_andnot(parent->effective_cpus,
  			       parent->effective_cpus, tmp->addmask);
  	}
  	if (deleting) {
  		cpumask_andnot(parent->subparts_cpus,
  			       parent->subparts_cpus, tmp->delmask);

  		/*
  		 * Some of the CPUs in subparts_cpus might have been offlined.
  		 */
  		cpumask_and(tmp->delmask, tmp->delmask, cpu_active_mask);

  		cpumask_or(parent->effective_cpus,
  			   parent->effective_cpus, tmp->delmask);
  	}
  
  	parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus);
  	spin_unlock_irq(&callback_lock);
  
  	return cmd == partcmd_update;
  }

  /*

   * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree

   * @cs:  the cpuset to consider
   * @tmp: temp variables for calculating effective_cpus & partition setup

   *
   * 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 tmpmasks *tmp)

  {
  	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);

  		compute_effective_cpumask(tmp->new_cpus, cp, parent);

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

  		if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) {

  			cpumask_copy(tmp->new_cpus, parent->effective_cpus);

  			if (!cp->use_parent_ecpus) {
  				cp->use_parent_ecpus = true;
  				parent->child_ecpus_count++;
  			}
  		} else if (cp->use_parent_ecpus) {
  			cp->use_parent_ecpus = false;
  			WARN_ON_ONCE(!parent->child_ecpus_count);
  			parent->child_ecpus_count--;
  		}

  		/*
  		 * Skip the whole subtree if the cpumask remains the same
  		 * and has no partition root state.
  		 */

  		if (!cp->partition_root_state &&

  		    cpumask_equal(tmp->new_cpus, cp->effective_cpus)) {

  			pos_css = css_rightmost_descendant(pos_css);
  			continue;

  		}

  		/*
  		 * update_parent_subparts_cpumask() should have been called
  		 * for cs already in update_cpumask(). We should also call
  		 * update_tasks_cpumask() again for tasks in the parent
  		 * cpuset if the parent's subparts_cpus changes.
  		 */

  		if ((cp != cs) && cp->partition_root_state) {
  			switch (parent->partition_root_state) {
  			case PRS_DISABLED:
  				/*
  				 * If parent is not a partition root or an
  				 * invalid partition root, clear the state
  				 * state and the CS_CPU_EXCLUSIVE flag.
  				 */
  				WARN_ON_ONCE(cp->partition_root_state
  					     != PRS_ERROR);
  				cp->partition_root_state = 0;
  
  				/*
  				 * clear_bit() is an atomic operation and
  				 * readers aren't interested in the state
  				 * of CS_CPU_EXCLUSIVE anyway. So we can
  				 * just update the flag without holding
  				 * the callback_lock.
  				 */
  				clear_bit(CS_CPU_EXCLUSIVE, &cp->flags);
  				break;
  
  			case PRS_ENABLED:
  				if (update_parent_subparts_cpumask(cp, partcmd_update, NULL, tmp))
  					update_tasks_cpumask(parent);
  				break;
  
  			case PRS_ERROR:
  				/*
  				 * When parent is invalid, it has to be too.
  				 */
  				cp->partition_root_state = PRS_ERROR;
  				if (cp->nr_subparts_cpus) {
  					cp->nr_subparts_cpus = 0;
  					cpumask_clear(cp->subparts_cpus);
  				}
  				break;
  			}

  		}

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

  			continue;
  		rcu_read_unlock();

  		spin_lock_irq(&callback_lock);

  
  		cpumask_copy(cp->effective_cpus, tmp->new_cpus);

  		if (cp->nr_subparts_cpus &&
  		   (cp->partition_root_state != PRS_ENABLED)) {
  			cp->nr_subparts_cpus = 0;
  			cpumask_clear(cp->subparts_cpus);
  		} else if (cp->nr_subparts_cpus) {

  			/*
  			 * Make sure that effective_cpus & subparts_cpus
  			 * are mutually exclusive.

  			 *
  			 * In the unlikely event that effective_cpus
  			 * becomes empty. we clear cp->nr_subparts_cpus and
  			 * let its child partition roots to compete for
  			 * CPUs again.

  			 */
  			cpumask_andnot(cp->effective_cpus, cp->effective_cpus,
  				       cp->subparts_cpus);

  			if (cpumask_empty(cp->effective_cpus)) {
  				cpumask_copy(cp->effective_cpus, tmp->new_cpus);
  				cpumask_clear(cp->subparts_cpus);
  				cp->nr_subparts_cpus = 0;
  			} else if (!cpumask_subset(cp->subparts_cpus,
  						   tmp->new_cpus)) {
  				cpumask_andnot(cp->subparts_cpus,
  					cp->subparts_cpus, tmp->new_cpus);
  				cp->nr_subparts_cpus
  					= cpumask_weight(cp->subparts_cpus);
  			}

  		}

  		spin_unlock_irq(&callback_lock);

  		WARN_ON(!is_in_v2_mode() &&

  			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));

  		update_tasks_cpumask(cp);

  		/*

  		 * On legacy hierarchy, if the effective cpumask of any non-
  		 * empty cpuset is changed, we need to rebuild sched domains.
  		 * On default hierarchy, the cpuset needs to be a partition
  		 * root as well.

  		 */
  		if (!cpumask_empty(cp->cpus_allowed) &&

  		    is_sched_load_balance(cp) &&
  		   (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) ||
  		    is_partition_root(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_sibling_cpumasks - Update siblings cpumasks
   * @parent:  Parent cpuset
   * @cs:      Current cpuset
   * @tmp:     Temp variables
   */
  static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
  				    struct tmpmasks *tmp)
  {
  	struct cpuset *sibling;
  	struct cgroup_subsys_state *pos_css;
  
  	/*
  	 * Check all its siblings and call update_cpumasks_hier()
  	 * if their use_parent_ecpus flag is set in order for them
  	 * to use the right effective_cpus value.
  	 */
  	rcu_read_lock();
  	cpuset_for_each_child(sibling, pos_css, parent) {
  		if (sibling == cs)
  			continue;
  		if (!sibling->use_parent_ecpus)
  			continue;
  
  		update_cpumasks_hier(sibling, tmp);
  	}
  	rcu_read_unlock();
  }
  
  /**

   * 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;

  	struct tmpmasks tmp;

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

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

  	/*

  	 * An empty cpus_requested 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_requested);

  	} else {

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

  		if (retval < 0)
  			return retval;

  	}

  	if (!cpumask_subset(trialcs->cpus_requested, cpu_present_mask))
  		return -EINVAL;

  	cpumask_and(trialcs->cpus_allowed, trialcs->cpus_requested, cpu_active_mask);

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

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

  		return 0;

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

  #ifdef CONFIG_CPUMASK_OFFSTACK
  	/*
  	 * Use the cpumasks in trialcs for tmpmasks when they are pointers
  	 * to allocated cpumasks.
  	 */
  	tmp.addmask  = trialcs->subparts_cpus;
  	tmp.delmask  = trialcs->effective_cpus;
  	tmp.new_cpus = trialcs->cpus_allowed;
  #endif
  
  	if (cs->partition_root_state) {
  		/* Cpumask of a partition root cannot be empty */
  		if (cpumask_empty(trialcs->cpus_allowed))
  			return -EINVAL;
  		if (update_parent_subparts_cpumask(cs, partcmd_update,
  					trialcs->cpus_allowed, &tmp) < 0)
  			return -EINVAL;
  	}

  	spin_lock_irq(&callback_lock);

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

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

  
  	/*
  	 * Make sure that subparts_cpus is a subset of cpus_allowed.
  	 */
  	if (cs->nr_subparts_cpus) {
  		cpumask_andnot(cs->subparts_cpus, cs->subparts_cpus,
  			       cs->cpus_allowed);
  		cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus);
  	}

  	spin_unlock_irq(&callback_lock);

  	update_cpumasks_hier(cs, &tmp);

  
  	if (cs->partition_root_state) {
  		struct cpuset *parent = parent_cs(cs);
  
  		/*
  		 * For partition root, update the cpumasks of sibling
  		 * cpusets if they use parent's effective_cpus.
  		 */
  		if (parent->child_ecpus_count)
  			update_sibling_cpumasks(parent, cs, &tmp);
  	}

  	return 0;

  }

  /*

   * Migrate memory region from one set of nodes to another.  This is
   * performed asynchronously as it can be called from process migration path
   * holding locks involved in process management.  All mm migrations are
   * performed in the queued order and can be waited for by flushing
   * cpuset_migrate_mm_wq.

   */

  struct cpuset_migrate_mm_work {
  	struct work_struct	work;
  	struct mm_struct	*mm;
  	nodemask_t		from;
  	nodemask_t		to;
  };
  
  static void cpuset_migrate_mm_workfn(struct work_struct *work)
  {
  	struct cpuset_migrate_mm_work *mwork =
  		container_of(work, struct cpuset_migrate_mm_work, work);
  
  	/* on a wq worker, no need to worry about %current's mems_allowed */
  	do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL);
  	mmput(mwork->mm);
  	kfree(mwork);
  }

  static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
  							const nodemask_t *to)
  {

  	struct cpuset_migrate_mm_work *mwork;

  	mwork = kzalloc(sizeof(*mwork), GFP_KERNEL);
  	if (mwork) {
  		mwork->mm = mm;
  		mwork->from = *from;
  		mwork->to = *to;
  		INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn);
  		queue_work(cpuset_migrate_mm_wq, &mwork->work);
  	} else {
  		mmput(mm);
  	}
  }

  static void cpuset_post_attach(void)

  {
  	flush_workqueue(cpuset_migrate_mm_wq);

  }

  /*

   * 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
   *

   * We use the mems_allowed_seq seqlock to safely update both tsk->mems_allowed
   * and rebind an eventual tasks' mempolicy. If the task is allocating in
   * parallel, it might temporarily see an empty intersection, which results in
   * a seqlock check and retry before OOM or allocation failure.

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

  	task_lock(tsk);

  	local_irq_disable();
  	write_seqcount_begin(&tsk->mems_allowed_seq);

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

  	mpol_rebind_task(tsk, newmems);

  	tsk->mems_allowed = *newmems;

  	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_lock, 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, 0, &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);

  		else
  			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 (is_in_v2_mode() && 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(!is_in_v2_mode() &&

  			!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.