/*
   *  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/module.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 <asm/atomic.h>

  #include <linux/mutex.h>

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

  /*

   * Workqueue for cpuset related tasks.
   *
   * Using kevent workqueue may cause deadlock when memory_migrate
   * is set. So we create a separate workqueue thread for cpuset.
   */
  static struct workqueue_struct *cpuset_wq;
  
  /*

   * Tracks how many cpusets are currently defined in system.
   * When there is only one cpuset (the root cpuset) we can
   * short circuit some hooks.
   */

  int number_of_cpusets __read_mostly;

  /* Forward declare cgroup structures */

  struct cgroup_subsys cpuset_subsys;
  struct cpuset;

  /* 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 */

  	cpumask_var_t cpus_allowed;	/* CPUs allowed to tasks in cpuset */

  	nodemask_t mems_allowed;	/* Memory Nodes allowed to tasks */

  	struct cpuset *parent;		/* my parent */

  	struct fmeter fmeter;		/* memory_pressure filter */

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

  	/* for custom sched domain */
  	int relax_domain_level;

  	/* used for walking a cpuset hierarchy */

  	struct list_head stack_list;

  };

  /* Retrieve the cpuset for a cgroup */
  static inline struct cpuset *cgroup_cs(struct cgroup *cont)
  {
  	return container_of(cgroup_subsys_state(cont, cpuset_subsys_id),
  			    struct cpuset, css);
  }
  
  /* Retrieve the cpuset for a task */
  static inline struct cpuset *task_cs(struct task_struct *task)
  {
  	return container_of(task_subsys_state(task, cpuset_subsys_id),
  			    struct cpuset, css);
  }

  /* bits in struct cpuset flags field */
  typedef enum {
  	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 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_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)),

  };

  /*

   * There are two global mutexes guarding cpuset structures.  The first
   * is the main control groups cgroup_mutex, accessed via
   * cgroup_lock()/cgroup_unlock().  The second is the cpuset-specific
   * callback_mutex, below. They can nest.  It is ok to first take
   * cgroup_mutex, then nest callback_mutex.  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 mutexes to modify cpusets.  If a task

   * holds cgroup_mutex, then it blocks others wanting that mutex,

   * ensuring that it is the only task able to also acquire callback_mutex

   * 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 cgroup_mutex.  While it is

   * performing these checks, various callback routines can briefly

   * acquire callback_mutex to query cpusets.  Once it is ready to make
   * the changes, it takes callback_mutex, blocking everyone else.

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

   * callback_mutex, as that would risk double tripping on callback_mutex

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

   * If a task is only holding callback_mutex, 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_mutex 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(callback_mutex);

  /*

   * cpuset_buffer_lock protects both the cpuset_name and cpuset_nodelist
   * buffers.  They are statically allocated to prevent using excess stack
   * when calling cpuset_print_task_mems_allowed().
   */
  #define CPUSET_NAME_LEN		(128)
  #define	CPUSET_NODELIST_LEN	(256)
  static char cpuset_name[CPUSET_NAME_LEN];
  static char cpuset_nodelist[CPUSET_NODELIST_LEN];
  static DEFINE_SPINLOCK(cpuset_buffer_lock);
  
  /*

   * 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 int cpuset_get_sb(struct file_system_type *fs_type,
  			 int flags, const char *unused_dev_name,
  			 void *data, struct vfsmount *mnt)

  {

  	struct file_system_type *cgroup_fs = get_fs_type("cgroup");
  	int ret = -ENODEV;
  	if (cgroup_fs) {
  		char mountopts[] =
  			"cpuset,noprefix,"
  			"release_agent=/sbin/cpuset_release_agent";
  		ret = cgroup_fs->get_sb(cgroup_fs, flags,
  					   unused_dev_name, mountopts, mnt);
  		put_filesystem(cgroup_fs);
  	}
  	return ret;

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

  };

  /*

   * 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.  If we get
   * all the way to the top and still haven't found any online cpus,
   * return cpu_online_map.  Or if passed a NULL cs from an exit'ing
   * task, return cpu_online_map.
   *
   * One way or another, we guarantee to return some non-empty subset
   * of cpu_online_map.
   *

   * Call with callback_mutex held.

   */

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

  {

  	while (cs && !cpumask_intersects(cs->cpus_allowed, cpu_online_mask))

  		cs = cs->parent;
  	if (cs)

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

  	else

  		cpumask_copy(pmask, cpu_online_mask);
  	BUG_ON(!cpumask_intersects(pmask, 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.  If we get all the way to the top and still haven't
   * found any online mems, return node_states[N_HIGH_MEMORY].

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

   * of node_states[N_HIGH_MEMORY].

   *

   * Call with callback_mutex held.

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

  	while (cs && !nodes_intersects(cs->mems_allowed,
  					node_states[N_HIGH_MEMORY]))

  		cs = cs->parent;
  	if (cs)

  		nodes_and(*pmask, cs->mems_allowed,
  					node_states[N_HIGH_MEMORY]);

  	else

  		*pmask = node_states[N_HIGH_MEMORY];
  	BUG_ON(!nodes_intersects(*pmask, node_states[N_HIGH_MEMORY]));

  }

  /*
   * update task's spread flag if cpuset's page/slab spread flag is set
   *
   * Called with callback_mutex/cgroup_mutex held
   */
  static void cpuset_update_task_spread_flag(struct cpuset *cs,
  					struct task_struct *tsk)
  {
  	if (is_spread_page(cs))
  		tsk->flags |= PF_SPREAD_PAGE;
  	else
  		tsk->flags &= ~PF_SPREAD_PAGE;
  	if (is_spread_slab(cs))
  		tsk->flags |= PF_SPREAD_SLAB;
  	else
  		tsk->flags &= ~PF_SPREAD_SLAB;
  }

  /*
   * 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 cgroup_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(const 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)) {
  		kfree(trial);
  		return NULL;
  	}
  	cpumask_copy(trial->cpus_allowed, cs->cpus_allowed);
  
  	return trial;

  }
  
  /**
   * 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->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

   * cgroup_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(const struct cpuset *cur, const struct cpuset *trial)
  {

  	struct cgroup *cont;

  	struct cpuset *c, *par;
  
  	/* Each of our child cpusets must be a subset of us */

  	list_for_each_entry(cont, &cur->css.cgroup->children, sibling) {
  		if (!is_cpuset_subset(cgroup_cs(cont), trial))

  			return -EBUSY;
  	}
  
  	/* Remaining checks don't apply to root cpuset */

  	if (cur == &top_cpuset)

  		return 0;

  	par = cur->parent;

  	/* We must be a subset of our parent cpuset */
  	if (!is_cpuset_subset(trial, par))
  		return -EACCES;

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

  	list_for_each_entry(cont, &par->css.cgroup->children, sibling) {
  		c = cgroup_cs(cont);

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

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

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

  	/* Cpusets with tasks can't have empty cpus_allowed or mems_allowed */
  	if (cgroup_task_count(cur->css.cgroup)) {

  		if (cpumask_empty(trial->cpus_allowed) ||

  		    nodes_empty(trial->mems_allowed)) {
  			return -ENOSPC;
  		}
  	}

  	return 0;
  }

  #ifdef CONFIG_SMP

  /*

   * Helper routine for generate_sched_domains().

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

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

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

  }

  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 *c)
  {
  	LIST_HEAD(q);
  
  	list_add(&c->stack_list, &q);
  	while (!list_empty(&q)) {
  		struct cpuset *cp;
  		struct cgroup *cont;
  		struct cpuset *child;
  
  		cp = list_first_entry(&q, struct cpuset, stack_list);
  		list_del(q.next);

  		if (cpumask_empty(cp->cpus_allowed))

  			continue;
  
  		if (is_sched_load_balance(cp))
  			update_domain_attr(dattr, cp);
  
  		list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
  			child = cgroup_cs(cont);
  			list_add_tail(&child->stack_list, &q);
  		}
  	}
  }

  /*

   * 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.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 cgroup_lock 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.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)

  {

  	LIST_HEAD(q);		/* queue of cpusets to be scanned */

  	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 */

  	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 */

  	doms = NULL;

  	dattr = NULL;

  	csa = NULL;

  
  	/* Special case for the 99% of systems with one, full, sched domain */
  	if (is_sched_load_balance(&top_cpuset)) {

  		ndoms = 1;
  		doms = alloc_sched_domains(ndoms);

  		if (!doms)

  			goto done;

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

  			update_domain_attr_tree(dattr, &top_cpuset);

  		}

  		cpumask_copy(doms[0], top_cpuset.cpus_allowed);

  		goto done;

  	}

  	csa = kmalloc(number_of_cpusets * sizeof(cp), GFP_KERNEL);
  	if (!csa)
  		goto done;
  	csn = 0;

  	list_add(&top_cpuset.stack_list, &q);
  	while (!list_empty(&q)) {

  		struct cgroup *cont;
  		struct cpuset *child;   /* scans child cpusets of cp */

  		cp = list_first_entry(&q, struct cpuset, stack_list);
  		list_del(q.next);

  		if (cpumask_empty(cp->cpus_allowed))

  			continue;

  		/*
  		 * 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 (is_sched_load_balance(cp)) {

  			csa[csn++] = cp;

  			continue;
  		}

  		list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
  			child = cgroup_cs(cont);

  			list_add_tail(&child->stack_list, &q);

  		}
    	}
  
  	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) {
  				printk(KERN_WARNING
  				 "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->cpus_allowed);

  				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;
  }
  
  /*
   * Rebuild scheduler domains.
   *
   * Call with neither cgroup_mutex held nor within get_online_cpus().
   * Takes both cgroup_mutex and get_online_cpus().
   *
   * Cannot be directly called from cpuset code handling changes
   * to the cpuset pseudo-filesystem, because it cannot be called
   * from code that already holds cgroup_mutex.
   */
  static void do_rebuild_sched_domains(struct work_struct *unused)
  {
  	struct sched_domain_attr *attr;

  	cpumask_var_t *doms;

  	int ndoms;

  	get_online_cpus();

  
  	/* Generate domain masks and attrs */
  	cgroup_lock();
  	ndoms = generate_sched_domains(&doms, &attr);
  	cgroup_unlock();
  
  	/* Have scheduler rebuild the domains */
  	partition_sched_domains(ndoms, doms, attr);

  	put_online_cpus();

  }

  #else /* !CONFIG_SMP */
  static void do_rebuild_sched_domains(struct work_struct *unused)
  {
  }

  static int generate_sched_domains(cpumask_var_t **domains,

  			struct sched_domain_attr **attributes)
  {
  	*domains = NULL;
  	return 1;
  }
  #endif /* CONFIG_SMP */

  static DECLARE_WORK(rebuild_sched_domains_work, do_rebuild_sched_domains);
  
  /*
   * Rebuild scheduler domains, asynchronously via workqueue.
   *
   * 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.
   *
   * The rebuild_sched_domains() and partition_sched_domains()
   * routines must nest cgroup_lock() inside get_online_cpus(),
   * but such cpuset changes as these must nest that locking the
   * other way, holding cgroup_lock() for much of the code.
   *
   * So in order to avoid an ABBA deadlock, the cpuset code handling
   * these user changes delegates the actual sched domain rebuilding
   * to a separate workqueue thread, which ends up processing the
   * above do_rebuild_sched_domains() function.
   */
  static void async_rebuild_sched_domains(void)
  {

  	queue_work(cpuset_wq, &rebuild_sched_domains_work);

  }
  
  /*
   * Accomplishes the same scheduler domain rebuild as the above
   * async_rebuild_sched_domains(), however it directly calls the
   * rebuild routine synchronously rather than calling it via an
   * asynchronous work thread.
   *
   * This can only be called from code that is not holding
   * cgroup_mutex (not nested in a cgroup_lock() call.)
   */
  void rebuild_sched_domains(void)
  {
  	do_rebuild_sched_domains(NULL);

  }

  /**
   * cpuset_test_cpumask - test a task's cpus_allowed versus its cpuset's
   * @tsk: task to test
   * @scan: struct cgroup_scanner contained in its struct cpuset_hotplug_scanner
   *

   * Call with cgroup_mutex held.  May take callback_mutex during call.

   * Called for each task in a cgroup by cgroup_scan_tasks().
   * Return nonzero if this tasks's cpus_allowed mask should be changed (in other
   * words, if its mask is not equal to its cpuset's mask).

   */

  static int cpuset_test_cpumask(struct task_struct *tsk,
  			       struct cgroup_scanner *scan)

  {

  	return !cpumask_equal(&tsk->cpus_allowed,

  			(cgroup_cs(scan->cg))->cpus_allowed);
  }

  /**
   * cpuset_change_cpumask - make a task's cpus_allowed the same as its cpuset's
   * @tsk: task to test
   * @scan: struct cgroup_scanner containing the cgroup of the task
   *
   * Called by cgroup_scan_tasks() for each task in a cgroup whose
   * cpus_allowed mask needs to be changed.
   *
   * We don't need to re-check for the cgroup/cpuset membership, since we're
   * holding cgroup_lock() at this point.
   */

  static void cpuset_change_cpumask(struct task_struct *tsk,
  				  struct cgroup_scanner *scan)

  {

  	set_cpus_allowed_ptr(tsk, ((cgroup_cs(scan->cg))->cpus_allowed));

  }
  
  /**

   * 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

   * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks()

   *
   * Called with cgroup_mutex held
   *
   * The cgroup_scan_tasks() function will scan all the tasks in a cgroup,
   * calling callback functions for each.
   *

   * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
   * if @heap != NULL.

   */

  static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap)

  {
  	struct cgroup_scanner scan;

  
  	scan.cg = cs->css.cgroup;
  	scan.test_task = cpuset_test_cpumask;
  	scan.process_task = cpuset_change_cpumask;

  	scan.heap = heap;
  	cgroup_scan_tasks(&scan);

  }
  
  /**

   * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it
   * @cs: the cpuset to consider
   * @buf: buffer of cpu numbers written to this cpuset
   */

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

  {

  	struct ptr_heap heap;

  	int retval;
  	int is_load_balanced;

  	/* top_cpuset.cpus_allowed tracks cpu_online_map; 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, cpu_active_mask))

  			return -EINVAL;

  	}

  	retval = validate_change(cs, trialcs);

  	if (retval < 0)
  		return retval;

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

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

  		return 0;

  	retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
  	if (retval)
  		return retval;

  	is_load_balanced = is_sched_load_balance(trialcs);

  	mutex_lock(&callback_mutex);

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

  	mutex_unlock(&callback_mutex);

  	/*
  	 * Scan tasks in the cpuset, and update the cpumasks of any

  	 * that need an update.

  	 */

  	update_tasks_cpumask(cs, &heap);
  
  	heap_free(&heap);

  	if (is_load_balanced)

  		async_rebuild_sched_domains();

  	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.
   *

   *    Call holding cgroup_mutex, so current's cpuset won't change

   *    during this call, as manage_mutex holds off any cpuset_attach()

   *    calls.  Therefore we don't need to take task_lock around the
   *    call to guarantee_online_mems(), as we know no one is changing

   *    our task's cpuset.

   *

   *    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);

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

  }

  /*

   * 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)
  {

  repeat:
  	/*
  	 * 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);

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

  	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
  
  
  	/*
  	 * ensure checking ->mems_allowed_change_disable after setting all new
  	 * allowed nodes.
  	 *
  	 * the read-side task can see an nodemask with new allowed nodes and
  	 * old allowed nodes. and if it allocates page when cpuset clears newly
  	 * disallowed ones continuous, it can see the new allowed bits.
  	 *
  	 * And if setting all new allowed nodes is after the checking, setting
  	 * all new allowed nodes and clearing newly disallowed ones will be done
  	 * continuous, and the read-side task may find no node to alloc page.
  	 */
  	smp_mb();
  
  	/*
  	 * Allocation of memory is very fast, we needn't sleep when waiting
  	 * for the read-side.
  	 */
  	while (ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
  		task_unlock(tsk);
  		if (!task_curr(tsk))
  			yield();
  		goto repeat;
  	}
  
  	/*
  	 * ensure checking ->mems_allowed_change_disable before clearing all new
  	 * disallowed nodes.
  	 *
  	 * if clearing newly disallowed bits before the checking, the read-side
  	 * task may find no node to alloc page.
  	 */
  	smp_mb();
  
  	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);

  	tsk->mems_allowed = *newmems;

  	task_unlock(tsk);

  }
  
  /*
   * Update task's mems_allowed and rebind its mempolicy and vmas' mempolicy
   * of it to cpuset's new mems_allowed, and migrate pages to new nodes if
   * memory_migrate flag is set. Called with cgroup_mutex held.

   */
  static void cpuset_change_nodemask(struct task_struct *p,
  				   struct cgroup_scanner *scan)
  {
  	struct mm_struct *mm;
  	struct cpuset *cs;
  	int migrate;
  	const nodemask_t *oldmem = scan->data;

  	NODEMASK_ALLOC(nodemask_t, newmems, GFP_KERNEL);
  
  	if (!newmems)
  		return;

  
  	cs = cgroup_cs(scan->cg);

  	guarantee_online_mems(cs, newmems);

  	cpuset_change_task_nodemask(p, newmems);

  	NODEMASK_FREE(newmems);

  	mm = get_task_mm(p);
  	if (!mm)
  		return;

  	migrate = is_memory_migrate(cs);
  
  	mpol_rebind_mm(mm, &cs->mems_allowed);
  	if (migrate)
  		cpuset_migrate_mm(mm, oldmem, &cs->mems_allowed);
  	mmput(mm);
  }

  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
   * @oldmem: old mems_allowed of cpuset cs

   * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks()

   *
   * Called with cgroup_mutex held

   * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
   * if @heap != NULL.

   */

  static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem,
  				 struct ptr_heap *heap)

  {

  	struct cgroup_scanner scan;

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

  	scan.cg = cs->css.cgroup;
  	scan.test_task = NULL;
  	scan.process_task = cpuset_change_nodemask;

  	scan.heap = heap;

  	scan.data = (nodemask_t *)oldmem;

  
  	/*

  	 * 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 cgroup_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.

  	 */

  	cgroup_scan_tasks(&scan);

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

  	cpuset_being_rebound = NULL;

  }

  /*
   * 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 cgroup_mutex held.  May take callback_mutex 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)

  {

  	NODEMASK_ALLOC(nodemask_t, oldmem, GFP_KERNEL);

  	int retval;

  	struct ptr_heap heap;

  	if (!oldmem)
  		return -ENOMEM;

  	/*
  	 * top_cpuset.mems_allowed tracks node_stats[N_HIGH_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,

  				node_states[N_HIGH_MEMORY])) {
  			retval =  -EINVAL;
  			goto done;
  		}

  	}

  	*oldmem = cs->mems_allowed;
  	if (nodes_equal(*oldmem, trialcs->mems_allowed)) {

  		retval = 0;		/* Too easy - nothing to do */
  		goto done;
  	}

  	retval = validate_change(cs, trialcs);

  	if (retval < 0)
  		goto done;

  	retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
  	if (retval < 0)
  		goto done;

  	mutex_lock(&callback_mutex);

  	cs->mems_allowed = trialcs->mems_allowed;

  	mutex_unlock(&callback_mutex);

  	update_tasks_nodemask(cs, oldmem, &heap);

  
  	heap_free(&heap);

  done:

  	NODEMASK_FREE(oldmem);

  	return retval;
  }

  int current_cpuset_is_being_rebound(void)
  {
  	return task_cs(current) == cpuset_being_rebound;
  }

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

  {

  #ifdef CONFIG_SMP

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

  			async_rebuild_sched_domains();

  	}
  
  	return 0;
  }

  /*

   * cpuset_change_flag - make a task's spread flags the same as its cpuset's
   * @tsk: task to be updated
   * @scan: struct cgroup_scanner containing the cgroup of the task
   *
   * Called by cgroup_scan_tasks() for each task in a cgroup.
   *
   * We don't need to re-check for the cgroup/cpuset membership, since we're
   * holding cgroup_lock() at this point.
   */
  static void cpuset_change_flag(struct task_struct *tsk,
  				struct cgroup_scanner *scan)
  {
  	cpuset_update_task_spread_flag(cgroup_cs(scan->cg), tsk);
  }
  
  /*
   * 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
   * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks()
   *
   * Called with cgroup_mutex held
   *
   * The cgroup_scan_tasks() function will scan all the tasks in a cgroup,
   * calling callback functions for each.
   *
   * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
   * if @heap != NULL.
   */
  static void update_tasks_flags(struct cpuset *cs, struct ptr_heap *heap)
  {
  	struct cgroup_scanner scan;
  
  	scan.cg = cs->css.cgroup;
  	scan.test_task = NULL;
  	scan.process_task = cpuset_change_flag;
  	scan.heap = heap;
  	cgroup_scan_tasks(&scan);
  }
  
  /*

   * 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 cgroup_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;
  	struct ptr_heap heap;
  	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;

  	err = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
  	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)));

  	mutex_lock(&callback_mutex);

  	cs->flags = trialcs->flags;

  	mutex_unlock(&callback_mutex);

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

  		async_rebuild_sched_domains();

  	if (spread_flag_changed)
  		update_tasks_flags(cs, &heap);
  	heap_free(&heap);

  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;
  }

  /* Protected by cgroup_lock */
  static cpumask_var_t cpus_attach;

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

  static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont,
  			     struct task_struct *tsk, bool threadgroup)

  {

  	int ret;

  	struct cpuset *cs = cgroup_cs(cont);

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

  		return -ENOSPC;

  	/*
  	 * Kthreads bound to specific cpus cannot be moved to a new cpuset; we
  	 * cannot change their cpu affinity and isolating such threads by their
  	 * set of allowed nodes is unnecessary.  Thus, cpusets are not
  	 * applicable for such threads.  This prevents checking for success of
  	 * set_cpus_allowed_ptr() on all attached tasks before cpus_allowed may
  	 * be changed.
  	 */
  	if (tsk->flags & PF_THREAD_BOUND)
  		return -EINVAL;

  	ret = security_task_setscheduler(tsk, 0, NULL);
  	if (ret)
  		return ret;
  	if (threadgroup) {
  		struct task_struct *c;
  
  		rcu_read_lock();
  		list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
  			ret = security_task_setscheduler(c, 0, NULL);
  			if (ret) {
  				rcu_read_unlock();
  				return ret;
  			}
  		}
  		rcu_read_unlock();
  	}
  	return 0;
  }
  
  static void cpuset_attach_task(struct task_struct *tsk, nodemask_t *to,
  			       struct cpuset *cs)
  {
  	int err;
  	/*
  	 * can_attach beforehand should guarantee that this doesn't fail.
  	 * TODO: have a better way to handle failure here
  	 */
  	err = set_cpus_allowed_ptr(tsk, cpus_attach);
  	WARN_ON_ONCE(err);

  	cpuset_change_task_nodemask(tsk, to);

  	cpuset_update_task_spread_flag(cs, tsk);

  }

  static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont,
  			  struct cgroup *oldcont, struct task_struct *tsk,
  			  bool threadgroup)

  {

  	struct mm_struct *mm;
  	struct cpuset *cs = cgroup_cs(cont);
  	struct cpuset *oldcs = cgroup_cs(oldcont);

  	NODEMASK_ALLOC(nodemask_t, from, GFP_KERNEL);
  	NODEMASK_ALLOC(nodemask_t, to, GFP_KERNEL);
  
  	if (from == NULL || to == NULL)
  		goto alloc_fail;

  	if (cs == &top_cpuset) {

  		cpumask_copy(cpus_attach, cpu_possible_mask);

  	} else {

  		guarantee_online_cpus(cs, cpus_attach);

  	}

  	guarantee_online_mems(cs, to);

  	/* do per-task migration stuff possibly for each in the threadgroup */

  	cpuset_attach_task(tsk, to, cs);

  	if (threadgroup) {
  		struct task_struct *c;
  		rcu_read_lock();
  		list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {

  			cpuset_attach_task(c, to, cs);

  		}
  		rcu_read_unlock();
  	}

  	/* change mm; only needs to be done once even if threadgroup */

  	*from = oldcs->mems_allowed;
  	*to = cs->mems_allowed;

  	mm = get_task_mm(tsk);
  	if (mm) {

  		mpol_rebind_mm(mm, to);

  		if (is_memory_migrate(cs))

  			cpuset_migrate_mm(mm, from, to);

  		mmput(mm);
  	}

  
  alloc_fail:
  	NODEMASK_FREE(from);
  	NODEMASK_FREE(to);

  }
  
  /* The various types of files and directories in a cpuset file system */
  
  typedef enum {

  	FILE_MEMORY_MIGRATE,

  	FILE_CPULIST,
  	FILE_MEMLIST,
  	FILE_CPU_EXCLUSIVE,
  	FILE_MEM_EXCLUSIVE,

  	FILE_MEM_HARDWALL,

  	FILE_SCHED_LOAD_BALANCE,

  	FILE_SCHED_RELAX_DOMAIN_LEVEL,

  	FILE_MEMORY_PRESSURE_ENABLED,
  	FILE_MEMORY_PRESSURE,

  	FILE_SPREAD_PAGE,
  	FILE_SPREAD_SLAB,

  } cpuset_filetype_t;

  static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
  {
  	int retval = 0;
  	struct cpuset *cs = cgroup_cs(cgrp);
  	cpuset_filetype_t type = cft->private;

  	if (!cgroup_lock_live_group(cgrp))

  		return -ENODEV;

  
  	switch (type) {

  	case FILE_CPU_EXCLUSIVE:

  		retval = update_flag(CS_CPU_EXCLUSIVE, cs, val);

  		break;
  	case FILE_MEM_EXCLUSIVE:

  		retval = update_flag(CS_MEM_EXCLUSIVE, cs, val);

  		break;

  	case FILE_MEM_HARDWALL:
  		retval = update_flag(CS_MEM_HARDWALL, cs, val);
  		break;

  	case FILE_SCHED_LOAD_BALANCE:

  		retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, val);

  		break;

  	case FILE_MEMORY_MIGRATE:

  		retval = update_flag(CS_MEMORY_MIGRATE, cs, val);

  		break;

  	case FILE_MEMORY_PRESSURE_ENABLED:

  		cpuset_memory_pressure_enabled = !!val;

  		break;
  	case FILE_MEMORY_PRESSURE:
  		retval = -EACCES;
  		break;

  	case FILE_SPREAD_PAGE:

  		retval = update_flag(CS_SPREAD_PAGE, cs, val);

  		break;
  	case FILE_SPREAD_SLAB:

  		retval = update_flag(CS_SPREAD_SLAB, cs, val);

  		break;

  	default:
  		retval = -EINVAL;

  		break;

  	}

  	cgroup_unlock();

  	return retval;
  }

  static int cpuset_write_s64(struct cgroup *cgrp, struct cftype *cft, s64 val)
  {
  	int retval = 0;
  	struct cpuset *cs = cgroup_cs(cgrp);
  	cpuset_filetype_t type = cft->private;

  	if (!cgroup_lock_live_group(cgrp))

  		return -ENODEV;

  	switch (type) {
  	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
  		retval = update_relax_domain_level(cs, val);
  		break;
  	default:
  		retval = -EINVAL;
  		break;
  	}
  	cgroup_unlock();
  	return retval;
  }

  /*

   * Common handling for a write to a "cpus" or "mems" file.
   */
  static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
  				const char *buf)
  {
  	int retval = 0;

  	struct cpuset *cs = cgroup_cs(cgrp);
  	struct cpuset *trialcs;

  
  	if (!cgroup_lock_live_group(cgrp))
  		return -ENODEV;

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

  	switch (cft->private) {
  	case FILE_CPULIST:

  		retval = update_cpumask(cs, trialcs, buf);

  		break;
  	case FILE_MEMLIST:

  		retval = update_nodemask(cs, trialcs, buf);

  		break;
  	default:
  		retval = -EINVAL;
  		break;
  	}

  
  	free_trial_cpuset(trialcs);

  	cgroup_unlock();
  	return retval;
  }
  
  /*

   * These ascii lists should be read in a single call, by using a user
   * buffer large enough to hold the entire map.  If read in smaller
   * chunks, there is no guarantee of atomicity.  Since the display format
   * used, list of ranges of sequential numbers, is variable length,
   * and since these maps can change value dynamically, one could read
   * gibberish by doing partial reads while a list was changing.
   * A single large read to a buffer that crosses a page boundary is
   * ok, because the result being copied to user land is not recomputed
   * across a page fault.
   */
  
  static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
  {

  	int ret;

  	mutex_lock(&callback_mutex);

  	ret = cpulist_scnprintf(page, PAGE_SIZE, cs->cpus_allowed);

  	mutex_unlock(&callback_mutex);

  	return ret;

  }
  
  static int cpuset_sprintf_memlist(char *page, struct cpuset *cs)
  {

  	NODEMASK_ALLOC(nodemask_t, mask, GFP_KERNEL);
  	int retval;
  
  	if (mask == NULL)
  		return -ENOMEM;

  	mutex_lock(&callback_mutex);

  	*mask = cs->mems_allowed;

  	mutex_unlock(&callback_mutex);

  	retval = nodelist_scnprintf(page, PAGE_SIZE, *mask);
  
  	NODEMASK_FREE(mask);
  
  	return retval;

  }

  static ssize_t cpuset_common_file_read(struct cgroup *cont,
  				       struct cftype *cft,
  				       struct file *file,
  				       char __user *buf,
  				       size_t nbytes, loff_t *ppos)

  {

  	struct cpuset *cs = cgroup_cs(cont);

  	cpuset_filetype_t type = cft->private;
  	char *page;
  	ssize_t retval = 0;
  	char *s;

  	if (!(page = (char *)__get_free_page(GFP_TEMPORARY)))

  		return -ENOMEM;
  
  	s = page;
  
  	switch (type) {
  	case FILE_CPULIST:
  		s += cpuset_sprintf_cpulist(s, cs);
  		break;
  	case FILE_MEMLIST:
  		s += cpuset_sprintf_memlist(s, cs);
  		break;

  	default:
  		retval = -EINVAL;
  		goto out;
  	}
  	*s++ = '
  ';

  	retval = simple_read_from_buffer(buf, nbytes, ppos, page, s - page);

  out:
  	free_page((unsigned long)page);
  	return retval;
  }

  static u64 cpuset_read_u64(struct cgroup *cont, struct cftype *cft)
  {
  	struct cpuset *cs = cgroup_cs(cont);
  	cpuset_filetype_t type = cft->private;
  	switch (type) {
  	case FILE_CPU_EXCLUSIVE:
  		return is_cpu_exclusive(cs);
  	case FILE_MEM_EXCLUSIVE:
  		return is_mem_exclusive(cs);

  	case FILE_MEM_HARDWALL:
  		return is_mem_hardwall(cs);

  	case FILE_SCHED_LOAD_BALANCE:
  		return is_sched_load_balance(cs);
  	case FILE_MEMORY_MIGRATE:
  		return is_memory_migrate(cs);
  	case FILE_MEMORY_PRESSURE_ENABLED:
  		return cpuset_memory_pressure_enabled;
  	case FILE_MEMORY_PRESSURE:
  		return fmeter_getrate(&cs->fmeter);
  	case FILE_SPREAD_PAGE:
  		return is_spread_page(cs);
  	case FILE_SPREAD_SLAB:
  		return is_spread_slab(cs);
  	default:
  		BUG();
  	}

  
  	/* Unreachable but makes gcc happy */
  	return 0;

  }

  static s64 cpuset_read_s64(struct cgroup *cont, struct cftype *cft)
  {
  	struct cpuset *cs = cgroup_cs(cont);
  	cpuset_filetype_t type = cft->private;
  	switch (type) {
  	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
  		return cs->relax_domain_level;
  	default:
  		BUG();
  	}

  
  	/* Unrechable but makes gcc happy */
  	return 0;

  }

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

  static struct cftype files[] = {
  	{
  		.name = "cpus",
  		.read = cpuset_common_file_read,

  		.write_string = cpuset_write_resmask,
  		.max_write_len = (100U + 6 * NR_CPUS),

  		.private = FILE_CPULIST,
  	},
  
  	{
  		.name = "mems",
  		.read = cpuset_common_file_read,

  		.write_string = cpuset_write_resmask,
  		.max_write_len = (100U + 6 * MAX_NUMNODES),

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

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

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

  		.read_s64 = cpuset_read_s64,
  		.write_s64 = cpuset_write_s64,

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

  		.mode = S_IRUGO,

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

  };

  static struct cftype cft_memory_pressure_enabled = {
  	.name = "memory_pressure_enabled",

  	.read_u64 = cpuset_read_u64,
  	.write_u64 = cpuset_write_u64,

  	.private = FILE_MEMORY_PRESSURE_ENABLED,
  };

  static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont)

  {
  	int err;

  	err = cgroup_add_files(cont, ss, files, ARRAY_SIZE(files));
  	if (err)

  		return err;

  	/* memory_pressure_enabled is in root cpuset only */

  	if (!cont->parent)

  		err = cgroup_add_file(cont, ss,

  				      &cft_memory_pressure_enabled);
  	return err;

  }
  
  /*

   * post_clone() is called at the end of cgroup_clone().
   * 'cgroup' was just created automatically as a result of
   * a cgroup_clone(), and the current task is about to
   * be moved into 'cgroup'.
   *
   * Currently we refuse to set up the cgroup - thereby
   * refusing the task to be entered, and as a result refusing
   * the sys_unshare() or clone() which initiated it - if any
   * sibling cpusets have exclusive cpus or mem.
   *
   * If this becomes a problem for some users who wish to
   * allow that scenario, then cpuset_post_clone() could be
   * changed to grant parent->cpus_allowed-sibling_cpus_exclusive

   * (and likewise for mems) to the new cgroup. Called with cgroup_mutex
   * held.

   */
  static void cpuset_post_clone(struct cgroup_subsys *ss,
  			      struct cgroup *cgroup)
  {
  	struct cgroup *parent, *child;
  	struct cpuset *cs, *parent_cs;
  
  	parent = cgroup->parent;
  	list_for_each_entry(child, &parent->children, sibling) {
  		cs = cgroup_cs(child);
  		if (is_mem_exclusive(cs) || is_cpu_exclusive(cs))
  			return;
  	}
  	cs = cgroup_cs(cgroup);
  	parent_cs = cgroup_cs(parent);
  
  	cs->mems_allowed = parent_cs->mems_allowed;

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

  	return;
  }
  
  /*

   *	cpuset_create - create a cpuset

   *	ss:	cpuset cgroup subsystem
   *	cont:	control group that the new cpuset will be part of

   */

  static struct cgroup_subsys_state *cpuset_create(
  	struct cgroup_subsys *ss,
  	struct cgroup *cont)

  {
  	struct cpuset *cs;

  	struct cpuset *parent;

  	if (!cont->parent) {

  		return &top_cpuset.css;
  	}
  	parent = cgroup_cs(cont->parent);

  	cs = kmalloc(sizeof(*cs), GFP_KERNEL);
  	if (!cs)

  		return ERR_PTR(-ENOMEM);

  	if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL)) {
  		kfree(cs);
  		return ERR_PTR(-ENOMEM);
  	}

  	cs->flags = 0;

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

  	set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);

  	cpumask_clear(cs->cpus_allowed);

  	nodes_clear(cs->mems_allowed);

  	fmeter_init(&cs->fmeter);

  	cs->relax_domain_level = -1;

  
  	cs->parent = parent;

  	number_of_cpusets++;

  	return &cs->css ;

  }

  /*

   * If the cpuset being removed has its flag 'sched_load_balance'
   * enabled, then simulate turning sched_load_balance off, which

   * will call async_rebuild_sched_domains().

   */

  static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)

  {

  	struct cpuset *cs = cgroup_cs(cont);

  	if (is_sched_load_balance(cs))

  		update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);