[~shefty/rdma-dev.git] / kernel / cgroup.c

/*
 *  Generic process-grouping system.
 *
 *  Based originally on the cpuset system, extracted by Paul Menage
 *  Copyright (C) 2006 Google, Inc
 *
 *  Notifications support
 *  Copyright (C) 2009 Nokia Corporation
 *  Author: Kirill A. Shutemov
 *
 *  Copyright notices from the original cpuset code:
 *  --------------------------------------------------
 *  Copyright (C) 2003 BULL SA.
 *  Copyright (C) 2004-2006 Silicon Graphics, 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.
 *  ---------------------------------------------------
 *
 *  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/cgroup.h>
#include <linux/cred.h>
#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/init_task.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/backing-dev.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/magic.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/sort.h>
#include <linux/kmod.h>
#include <linux/module.h>
#include <linux/delayacct.h>
#include <linux/cgroupstats.h>
#include <linux/hash.h>
#include <linux/namei.h>
#include <linux/pid_namespace.h>
#include <linux/idr.h>
#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
#include <linux/eventfd.h>
#include <linux/poll.h>
#include <linux/flex_array.h> /* used in cgroup_attach_proc */
#include <linux/kthread.h>

#include <linux/atomic.h>

/* css deactivation bias, makes css->refcnt negative to deny new trygets */
#define CSS_DEACT_BIAS          INT_MIN

/*
 * cgroup_mutex is the master lock.  Any modification to cgroup or its
 * hierarchy must be performed while holding it.
 *
 * cgroup_root_mutex nests inside cgroup_mutex and should be held to modify
 * cgroupfs_root of any cgroup hierarchy - subsys list, flags,
 * release_agent_path and so on.  Modifying requires both cgroup_mutex and
 * cgroup_root_mutex.  Readers can acquire either of the two.  This is to
 * break the following locking order cycle.
 *
 *  A. cgroup_mutex -> cred_guard_mutex -> s_type->i_mutex_key -> namespace_sem
 *  B. namespace_sem -> cgroup_mutex
 *
 * B happens only through cgroup_show_options() and using cgroup_root_mutex
 * breaks it.
 */
static DEFINE_MUTEX(cgroup_mutex);
static DEFINE_MUTEX(cgroup_root_mutex);

/*
 * Generate an array of cgroup subsystem pointers. At boot time, this is
 * populated with the built in subsystems, and modular subsystems are
 * registered after that. The mutable section of this array is protected by
 * cgroup_mutex.
 */
#define SUBSYS(_x) [_x ## _subsys_id] = &_x ## _subsys,
#define IS_SUBSYS_ENABLED(option) IS_BUILTIN(option)
static struct cgroup_subsys *subsys[CGROUP_SUBSYS_COUNT] = {
#include <linux/cgroup_subsys.h>
};

#define MAX_CGROUP_ROOT_NAMELEN 64

/*
 * A cgroupfs_root represents the root of a cgroup hierarchy,
 * and may be associated with a superblock to form an active
 * hierarchy
 */
struct cgroupfs_root {
        struct super_block *sb;

        /*
         * The bitmask of subsystems intended to be attached to this
         * hierarchy
         */
        unsigned long subsys_mask;

        /* Unique id for this hierarchy. */
        int hierarchy_id;

        /* The bitmask of subsystems currently attached to this hierarchy */
        unsigned long actual_subsys_mask;

        /* A list running through the attached subsystems */
        struct list_head subsys_list;

        /* The root cgroup for this hierarchy */
        struct cgroup top_cgroup;

        /* Tracks how many cgroups are currently defined in hierarchy.*/
        int number_of_cgroups;

        /* A list running through the active hierarchies */
        struct list_head root_list;

        /* All cgroups on this root, cgroup_mutex protected */
        struct list_head allcg_list;

        /* Hierarchy-specific flags */
        unsigned long flags;

        /* The path to use for release notifications. */
        char release_agent_path[PATH_MAX];

        /* The name for this hierarchy - may be empty */
        char name[MAX_CGROUP_ROOT_NAMELEN];
};

/*
 * The "rootnode" hierarchy is the "dummy hierarchy", reserved for the
 * subsystems that are otherwise unattached - it never has more than a
 * single cgroup, and all tasks are part of that cgroup.
 */
static struct cgroupfs_root rootnode;

/*
 * cgroupfs file entry, pointed to from leaf dentry->d_fsdata.
 */
struct cfent {
        struct list_head                node;
        struct dentry                   *dentry;
        struct cftype                   *type;
};

/*
 * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when
 * cgroup_subsys->use_id != 0.
 */
#define CSS_ID_MAX      (65535)
struct css_id {
        /*
         * The css to which this ID points. This pointer is set to valid value
         * after cgroup is populated. If cgroup is removed, this will be NULL.
         * This pointer is expected to be RCU-safe because destroy()
         * is called after synchronize_rcu(). But for safe use, css_tryget()
         * should be used for avoiding race.
         */
        struct cgroup_subsys_state __rcu *css;
        /*
         * ID of this css.
         */
        unsigned short id;
        /*
         * Depth in hierarchy which this ID belongs to.
         */
        unsigned short depth;
        /*
         * ID is freed by RCU. (and lookup routine is RCU safe.)
         */
        struct rcu_head rcu_head;
        /*
         * Hierarchy of CSS ID belongs to.
         */
        unsigned short stack[0]; /* Array of Length (depth+1) */
};

/*
 * cgroup_event represents events which userspace want to receive.
 */
struct cgroup_event {
        /*
         * Cgroup which the event belongs to.
         */
        struct cgroup *cgrp;
        /*
         * Control file which the event associated.
         */
        struct cftype *cft;
        /*
         * eventfd to signal userspace about the event.
         */
        struct eventfd_ctx *eventfd;
        /*
         * Each of these stored in a list by the cgroup.
         */
        struct list_head list;
        /*
         * All fields below needed to unregister event when
         * userspace closes eventfd.
         */
        poll_table pt;
        wait_queue_head_t *wqh;
        wait_queue_t wait;
        struct work_struct remove;
};

/* The list of hierarchy roots */

static LIST_HEAD(roots);
static int root_count;

static DEFINE_IDA(hierarchy_ida);
static int next_hierarchy_id;
static DEFINE_SPINLOCK(hierarchy_id_lock);

/* dummytop is a shorthand for the dummy hierarchy's top cgroup */
#define dummytop (&rootnode.top_cgroup)

/* This flag indicates whether tasks in the fork and exit paths should
 * check for fork/exit handlers to call. This avoids us having to do
 * extra work in the fork/exit path if none of the subsystems need to
 * be called.
 */
static int need_forkexit_callback __read_mostly;

#ifdef CONFIG_PROVE_LOCKING
int cgroup_lock_is_held(void)
{
        return lockdep_is_held(&cgroup_mutex);
}
#else /* #ifdef CONFIG_PROVE_LOCKING */
int cgroup_lock_is_held(void)
{
        return mutex_is_locked(&cgroup_mutex);
}
#endif /* #else #ifdef CONFIG_PROVE_LOCKING */

EXPORT_SYMBOL_GPL(cgroup_lock_is_held);

static int css_unbias_refcnt(int refcnt)
{
        return refcnt >= 0 ? refcnt : refcnt - CSS_DEACT_BIAS;
}

/* the current nr of refs, always >= 0 whether @css is deactivated or not */
static int css_refcnt(struct cgroup_subsys_state *css)
{
        int v = atomic_read(&css->refcnt);

        return css_unbias_refcnt(v);
}

/* convenient tests for these bits */
inline int cgroup_is_removed(const struct cgroup *cgrp)
{
        return test_bit(CGRP_REMOVED, &cgrp->flags);
}

/* bits in struct cgroupfs_root flags field */
enum {
        ROOT_NOPREFIX,  /* mounted subsystems have no named prefix */
        ROOT_XATTR,     /* supports extended attributes */
};

static int cgroup_is_releasable(const struct cgroup *cgrp)
{
        const int bits =
                (1 << CGRP_RELEASABLE) |
                (1 << CGRP_NOTIFY_ON_RELEASE);
        return (cgrp->flags & bits) == bits;
}

static int notify_on_release(const struct cgroup *cgrp)
{
        return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
}

static int clone_children(const struct cgroup *cgrp)
{
        return test_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
}

/*
 * for_each_subsys() allows you to iterate on each subsystem attached to
 * an active hierarchy
 */
#define for_each_subsys(_root, _ss) \
list_for_each_entry(_ss, &_root->subsys_list, sibling)

/* for_each_active_root() allows you to iterate across the active hierarchies */
#define for_each_active_root(_root) \
list_for_each_entry(_root, &roots, root_list)

static inline struct cgroup *__d_cgrp(struct dentry *dentry)
{
        return dentry->d_fsdata;
}

static inline struct cfent *__d_cfe(struct dentry *dentry)
{
        return dentry->d_fsdata;
}

static inline struct cftype *__d_cft(struct dentry *dentry)
{
        return __d_cfe(dentry)->type;
}

/* the list of cgroups eligible for automatic release. Protected by
 * release_list_lock */
static LIST_HEAD(release_list);
static DEFINE_RAW_SPINLOCK(release_list_lock);
static void cgroup_release_agent(struct work_struct *work);
static DECLARE_WORK(release_agent_work, cgroup_release_agent);
static void check_for_release(struct cgroup *cgrp);

/* Link structure for associating css_set objects with cgroups */
struct cg_cgroup_link {
        /*
         * List running through cg_cgroup_links associated with a
         * cgroup, anchored on cgroup->css_sets
         */
        struct list_head cgrp_link_list;
        struct cgroup *cgrp;
        /*
         * List running through cg_cgroup_links pointing at a
         * single css_set object, anchored on css_set->cg_links
         */
        struct list_head cg_link_list;
        struct css_set *cg;
};

/* The default css_set - used by init and its children prior to any
 * hierarchies being mounted. It contains a pointer to the root state
 * for each subsystem. Also used to anchor the list of css_sets. Not
 * reference-counted, to improve performance when child cgroups
 * haven't been created.
 */

static struct css_set init_css_set;
static struct cg_cgroup_link init_css_set_link;

static int cgroup_init_idr(struct cgroup_subsys *ss,
                           struct cgroup_subsys_state *css);

/* css_set_lock protects the list of css_set objects, and the
 * chain of tasks off each css_set.  Nests outside task->alloc_lock
 * due to cgroup_iter_start() */
static DEFINE_RWLOCK(css_set_lock);
static int css_set_count;

/*
 * hash table for cgroup groups. This improves the performance to find
 * an existing css_set. This hash doesn't (currently) take into
 * account cgroups in empty hierarchies.
 */
#define CSS_SET_HASH_BITS       7
#define CSS_SET_TABLE_SIZE      (1 << CSS_SET_HASH_BITS)
static struct hlist_head css_set_table[CSS_SET_TABLE_SIZE];

static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[])
{
        int i;
        int index;
        unsigned long tmp = 0UL;

        for (i = 0; i < CGROUP_SUBSYS_COUNT; i++)
                tmp += (unsigned long)css[i];
        tmp = (tmp >> 16) ^ tmp;

        index = hash_long(tmp, CSS_SET_HASH_BITS);

        return &css_set_table[index];
}

/* We don't maintain the lists running through each css_set to its
 * task until after the first call to cgroup_iter_start(). This
 * reduces the fork()/exit() overhead for people who have cgroups
 * compiled into their kernel but not actually in use */
static int use_task_css_set_links __read_mostly;

static void __put_css_set(struct css_set *cg, int taskexit)
{
        struct cg_cgroup_link *link;
        struct cg_cgroup_link *saved_link;
        /*
         * Ensure that the refcount doesn't hit zero while any readers
         * can see it. Similar to atomic_dec_and_lock(), but for an
         * rwlock
         */
        if (atomic_add_unless(&cg->refcount, -1, 1))
                return;
        write_lock(&css_set_lock);
        if (!atomic_dec_and_test(&cg->refcount)) {
                write_unlock(&css_set_lock);
                return;
        }

        /* This css_set is dead. unlink it and release cgroup refcounts */
        hlist_del(&cg->hlist);
        css_set_count--;

        list_for_each_entry_safe(link, saved_link, &cg->cg_links,
                                 cg_link_list) {
                struct cgroup *cgrp = link->cgrp;
                list_del(&link->cg_link_list);
                list_del(&link->cgrp_link_list);
                if (atomic_dec_and_test(&cgrp->count) &&
                    notify_on_release(cgrp)) {
                        if (taskexit)
                                set_bit(CGRP_RELEASABLE, &cgrp->flags);
                        check_for_release(cgrp);
                }

                kfree(link);
        }

        write_unlock(&css_set_lock);
        kfree_rcu(cg, rcu_head);
}

/*
 * refcounted get/put for css_set objects
 */
static inline void get_css_set(struct css_set *cg)
{
        atomic_inc(&cg->refcount);
}

static inline void put_css_set(struct css_set *cg)
{
        __put_css_set(cg, 0);
}

static inline void put_css_set_taskexit(struct css_set *cg)
{
        __put_css_set(cg, 1);
}

/*
 * compare_css_sets - helper function for find_existing_css_set().
 * @cg: candidate css_set being tested
 * @old_cg: existing css_set for a task
 * @new_cgrp: cgroup that's being entered by the task
 * @template: desired set of css pointers in css_set (pre-calculated)
 *
 * Returns true if "cg" matches "old_cg" except for the hierarchy
 * which "new_cgrp" belongs to, for which it should match "new_cgrp".
 */
static bool compare_css_sets(struct css_set *cg,
                             struct css_set *old_cg,
                             struct cgroup *new_cgrp,
                             struct cgroup_subsys_state *template[])
{
        struct list_head *l1, *l2;

        if (memcmp(template, cg->subsys, sizeof(cg->subsys))) {
                /* Not all subsystems matched */
                return false;
        }

        /*
         * Compare cgroup pointers in order to distinguish between
         * different cgroups in heirarchies with no subsystems. We
         * could get by with just this check alone (and skip the
         * memcmp above) but on most setups the memcmp check will
         * avoid the need for this more expensive check on almost all
         * candidates.
         */

        l1 = &cg->cg_links;
        l2 = &old_cg->cg_links;
        while (1) {
                struct cg_cgroup_link *cgl1, *cgl2;
                struct cgroup *cg1, *cg2;

                l1 = l1->next;
                l2 = l2->next;
                /* See if we reached the end - both lists are equal length. */
                if (l1 == &cg->cg_links) {
                        BUG_ON(l2 != &old_cg->cg_links);
                        break;
                } else {
                        BUG_ON(l2 == &old_cg->cg_links);
                }
                /* Locate the cgroups associated with these links. */
                cgl1 = list_entry(l1, struct cg_cgroup_link, cg_link_list);
                cgl2 = list_entry(l2, struct cg_cgroup_link, cg_link_list);
                cg1 = cgl1->cgrp;
                cg2 = cgl2->cgrp;
                /* Hierarchies should be linked in the same order. */
                BUG_ON(cg1->root != cg2->root);

                /*
                 * If this hierarchy is the hierarchy of the cgroup
                 * that's changing, then we need to check that this
                 * css_set points to the new cgroup; if it's any other
                 * hierarchy, then this css_set should point to the
                 * same cgroup as the old css_set.
                 */
                if (cg1->root == new_cgrp->root) {
                        if (cg1 != new_cgrp)
                                return false;
                } else {
                        if (cg1 != cg2)
                                return false;
                }
        }
        return true;
}

/*
 * find_existing_css_set() is a helper for
 * find_css_set(), and checks to see whether an existing
 * css_set is suitable.
 *
 * oldcg: the cgroup group that we're using before the cgroup
 * transition
 *
 * cgrp: the cgroup that we're moving into
 *
 * template: location in which to build the desired set of subsystem
 * state objects for the new cgroup group
 */
static struct css_set *find_existing_css_set(
        struct css_set *oldcg,
        struct cgroup *cgrp,
        struct cgroup_subsys_state *template[])
{
        int i;
        struct cgroupfs_root *root = cgrp->root;
        struct hlist_head *hhead;
        struct hlist_node *node;
        struct css_set *cg;

        /*
         * Build the set of subsystem state objects that we want to see in the
         * new css_set. while subsystems can change globally, the entries here
         * won't change, so no need for locking.
         */
        for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
                if (root->subsys_mask & (1UL << i)) {
                        /* Subsystem is in this hierarchy. So we want
                         * the subsystem state from the new
                         * cgroup */
                        template[i] = cgrp->subsys[i];
                } else {
                        /* Subsystem is not in this hierarchy, so we
                         * don't want to change the subsystem state */
                        template[i] = oldcg->subsys[i];
                }
        }

        hhead = css_set_hash(template);
        hlist_for_each_entry(cg, node, hhead, hlist) {
                if (!compare_css_sets(cg, oldcg, cgrp, template))
                        continue;

                /* This css_set matches what we need */
                return cg;
        }

        /* No existing cgroup group matched */
        return NULL;
}

static void free_cg_links(struct list_head *tmp)
{
        struct cg_cgroup_link *link;
        struct cg_cgroup_link *saved_link;

        list_for_each_entry_safe(link, saved_link, tmp, cgrp_link_list) {
                list_del(&link->cgrp_link_list);
                kfree(link);
        }
}

/*
 * allocate_cg_links() allocates "count" cg_cgroup_link structures
 * and chains them on tmp through their cgrp_link_list fields. Returns 0 on
 * success or a negative error
 */
static int allocate_cg_links(int count, struct list_head *tmp)
{
        struct cg_cgroup_link *link;
        int i;
        INIT_LIST_HEAD(tmp);
        for (i = 0; i < count; i++) {
                link = kmalloc(sizeof(*link), GFP_KERNEL);
                if (!link) {
                        free_cg_links(tmp);
                        return -ENOMEM;
                }
                list_add(&link->cgrp_link_list, tmp);
        }
        return 0;
}

/**
 * link_css_set - a helper function to link a css_set to a cgroup
 * @tmp_cg_links: cg_cgroup_link objects allocated by allocate_cg_links()
 * @cg: the css_set to be linked
 * @cgrp: the destination cgroup
 */
static void link_css_set(struct list_head *tmp_cg_links,
                         struct css_set *cg, struct cgroup *cgrp)
{
        struct cg_cgroup_link *link;

        BUG_ON(list_empty(tmp_cg_links));
        link = list_first_entry(tmp_cg_links, struct cg_cgroup_link,
                                cgrp_link_list);
        link->cg = cg;
        link->cgrp = cgrp;
        atomic_inc(&cgrp->count);
        list_move(&link->cgrp_link_list, &cgrp->css_sets);
        /*
         * Always add links to the tail of the list so that the list
         * is sorted by order of hierarchy creation
         */
        list_add_tail(&link->cg_link_list, &cg->cg_links);
}

/*
 * find_css_set() takes an existing cgroup group and a
 * cgroup object, and returns a css_set object that's
 * equivalent to the old group, but with the given cgroup
 * substituted into the appropriate hierarchy. Must be called with
 * cgroup_mutex held
 */
static struct css_set *find_css_set(
        struct css_set *oldcg, struct cgroup *cgrp)
{
        struct css_set *res;
        struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT];

        struct list_head tmp_cg_links;

        struct hlist_head *hhead;
        struct cg_cgroup_link *link;

        /* First see if we already have a cgroup group that matches
         * the desired set */
        read_lock(&css_set_lock);
        res = find_existing_css_set(oldcg, cgrp, template);
        if (res)
                get_css_set(res);
        read_unlock(&css_set_lock);

        if (res)
                return res;

        res = kmalloc(sizeof(*res), GFP_KERNEL);
        if (!res)
                return NULL;

        /* Allocate all the cg_cgroup_link objects that we'll need */
        if (allocate_cg_links(root_count, &tmp_cg_links) < 0) {
                kfree(res);
                return NULL;
        }

        atomic_set(&res->refcount, 1);
        INIT_LIST_HEAD(&res->cg_links);
        INIT_LIST_HEAD(&res->tasks);
        INIT_HLIST_NODE(&res->hlist);

        /* Copy the set of subsystem state objects generated in
         * find_existing_css_set() */
        memcpy(res->subsys, template, sizeof(res->subsys));

        write_lock(&css_set_lock);
        /* Add reference counts and links from the new css_set. */
        list_for_each_entry(link, &oldcg->cg_links, cg_link_list) {
                struct cgroup *c = link->cgrp;
                if (c->root == cgrp->root)
                        c = cgrp;
                link_css_set(&tmp_cg_links, res, c);
        }

        BUG_ON(!list_empty(&tmp_cg_links));

        css_set_count++;

        /* Add this cgroup group to the hash table */
        hhead = css_set_hash(res->subsys);
        hlist_add_head(&res->hlist, hhead);

        write_unlock(&css_set_lock);

        return res;
}

/*
 * Return the cgroup for "task" from the given hierarchy. Must be
 * called with cgroup_mutex held.
 */
static struct cgroup *task_cgroup_from_root(struct task_struct *task,
                                            struct cgroupfs_root *root)
{
        struct css_set *css;
        struct cgroup *res = NULL;

        BUG_ON(!mutex_is_locked(&cgroup_mutex));
        read_lock(&css_set_lock);
        /*
         * No need to lock the task - since we hold cgroup_mutex the
         * task can't change groups, so the only thing that can happen
         * is that it exits and its css is set back to init_css_set.
         */
        css = task->cgroups;
        if (css == &init_css_set) {
                res = &root->top_cgroup;
        } else {
                struct cg_cgroup_link *link;
                list_for_each_entry(link, &css->cg_links, cg_link_list) {
                        struct cgroup *c = link->cgrp;
                        if (c->root == root) {
                                res = c;
                                break;
                        }
                }
        }
        read_unlock(&css_set_lock);
        BUG_ON(!res);
        return res;
}

/*
 * There is one global cgroup mutex. We also require taking
 * task_lock() when dereferencing a task's cgroup subsys pointers.
 * See "The task_lock() exception", at the end of this comment.
 *
 * A task must hold cgroup_mutex to modify cgroups.
 *
 * Any task can increment and decrement the count field without lock.
 * So in general, code holding cgroup_mutex can't rely on the count
 * field not changing.  However, if the count goes to zero, then only
 * cgroup_attach_task() can increment it again.  Because a count of zero
 * means that no tasks are currently attached, therefore there is no
 * way a task attached to that cgroup can fork (the other way to
 * increment the count).  So code holding cgroup_mutex can safely
 * assume that if the count is zero, it will stay zero. Similarly, if
 * a task holds cgroup_mutex on a cgroup with zero count, it
 * knows that the cgroup won't be removed, as cgroup_rmdir()
 * needs that mutex.
 *
 * The fork and exit callbacks cgroup_fork() and cgroup_exit(), don't
 * (usually) take cgroup_mutex.  These are the two most performance
 * critical pieces of code here.  The exception occurs on cgroup_exit(),
 * when a task in a notify_on_release cgroup exits.  Then cgroup_mutex
 * is taken, and if the cgroup count is zero, a usermode call made
 * to the release agent with the name of the cgroup (path relative to
 * the root of cgroup file system) as the argument.
 *
 * A cgroup can only be deleted if both its 'count' of using tasks
 * is zero, and its list of 'children' cgroups is empty.  Since all
 * tasks in the system use _some_ cgroup, and since there is always at
 * least one task in the system (init, pid == 1), therefore, top_cgroup
 * always has either children cgroups and/or using tasks.  So we don't
 * need a special hack to ensure that top_cgroup cannot be deleted.
 *
 *      The task_lock() exception
 *
 * The need for this exception arises from the action of
 * cgroup_attach_task(), which overwrites one tasks cgroup pointer with
 * another.  It does so using cgroup_mutex, however there are
 * several performance critical places that need to reference
 * task->cgroup without the expense of grabbing a system global
 * mutex.  Therefore except as noted below, when dereferencing or, as
 * in cgroup_attach_task(), modifying a task'ss cgroup pointer we use
 * task_lock(), which acts on a spinlock (task->alloc_lock) already in
 * the task_struct routinely used for such matters.
 *
 * P.S.  One more locking exception.  RCU is used to guard the
 * update of a tasks cgroup pointer by cgroup_attach_task()
 */

/**
 * cgroup_lock - lock out any changes to cgroup structures
 *
 */
void cgroup_lock(void)
{
        mutex_lock(&cgroup_mutex);
}
EXPORT_SYMBOL_GPL(cgroup_lock);

/**
 * cgroup_unlock - release lock on cgroup changes
 *
 * Undo the lock taken in a previous cgroup_lock() call.
 */
void cgroup_unlock(void)
{
        mutex_unlock(&cgroup_mutex);
}
EXPORT_SYMBOL_GPL(cgroup_unlock);

/*
 * A couple of forward declarations required, due to cyclic reference loop:
 * cgroup_mkdir -> cgroup_create -> cgroup_populate_dir ->
 * cgroup_add_file -> cgroup_create_file -> cgroup_dir_inode_operations
 * -> cgroup_mkdir.
 */

static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
static struct dentry *cgroup_lookup(struct inode *, struct dentry *, unsigned int);
static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cgrp, bool base_files,
                               unsigned long subsys_mask);
static const struct inode_operations cgroup_dir_inode_operations;
static const struct file_operations proc_cgroupstats_operations;

static struct backing_dev_info cgroup_backing_dev_info = {
        .name           = "cgroup",
        .capabilities   = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};

static int alloc_css_id(struct cgroup_subsys *ss,
                        struct cgroup *parent, struct cgroup *child);

static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
{
        struct inode *inode = new_inode(sb);

        if (inode) {
                inode->i_ino = get_next_ino();
                inode->i_mode = mode;
                inode->i_uid = current_fsuid();
                inode->i_gid = current_fsgid();
                inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
                inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info;
        }
        return inode;
}

static void cgroup_diput(struct dentry *dentry, struct inode *inode)
{
        /* is dentry a directory ? if so, kfree() associated cgroup */
        if (S_ISDIR(inode->i_mode)) {
                struct cgroup *cgrp = dentry->d_fsdata;
                struct cgroup_subsys *ss;
                BUG_ON(!(cgroup_is_removed(cgrp)));
                /* It's possible for external users to be holding css
                 * reference counts on a cgroup; css_put() needs to
                 * be able to access the cgroup after decrementing
                 * the reference count in order to know if it needs to
                 * queue the cgroup to be handled by the release
                 * agent */
                synchronize_rcu();

                mutex_lock(&cgroup_mutex);
                /*
                 * Release the subsystem state objects.
                 */
                for_each_subsys(cgrp->root, ss)
                        ss->destroy(cgrp);

                cgrp->root->number_of_cgroups--;
                mutex_unlock(&cgroup_mutex);

                /*
                 * Drop the active superblock reference that we took when we
                 * created the cgroup
                 */
                deactivate_super(cgrp->root->sb);

                /*
                 * if we're getting rid of the cgroup, refcount should ensure
                 * that there are no pidlists left.
                 */
                BUG_ON(!list_empty(&cgrp->pidlists));

                simple_xattrs_free(&cgrp->xattrs);

                kfree_rcu(cgrp, rcu_head);
        } else {
                struct cfent *cfe = __d_cfe(dentry);
                struct cgroup *cgrp = dentry->d_parent->d_fsdata;
                struct cftype *cft = cfe->type;

                WARN_ONCE(!list_empty(&cfe->node) &&
                          cgrp != &cgrp->root->top_cgroup,
                          "cfe still linked for %s\n", cfe->type->name);
                kfree(cfe);
                simple_xattrs_free(&cft->xattrs);
        }
        iput(inode);
}

static int cgroup_delete(const struct dentry *d)
{
        return 1;
}

static void remove_dir(struct dentry *d)
{
        struct dentry *parent = dget(d->d_parent);

        d_delete(d);
        simple_rmdir(parent->d_inode, d);
        dput(parent);
}

static int cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
{
        struct cfent *cfe;

        lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
        lockdep_assert_held(&cgroup_mutex);

        list_for_each_entry(cfe, &cgrp->files, node) {
                struct dentry *d = cfe->dentry;

                if (cft && cfe->type != cft)
                        continue;

                dget(d);
                d_delete(d);
                simple_unlink(cgrp->dentry->d_inode, d);
                list_del_init(&cfe->node);
                dput(d);

                return 0;
        }
        return -ENOENT;
}

/**
 * cgroup_clear_directory - selective removal of base and subsystem files
 * @dir: directory containing the files
 * @base_files: true if the base files should be removed
 * @subsys_mask: mask of the subsystem ids whose files should be removed
 */
static void cgroup_clear_directory(struct dentry *dir, bool base_files,
                                   unsigned long subsys_mask)
{
        struct cgroup *cgrp = __d_cgrp(dir);
        struct cgroup_subsys *ss;

        for_each_subsys(cgrp->root, ss) {
                struct cftype_set *set;
                if (!test_bit(ss->subsys_id, &subsys_mask))
                        continue;
                list_for_each_entry(set, &ss->cftsets, node)
                        cgroup_rm_file(cgrp, set->cfts);
        }
        if (base_files) {
                while (!list_empty(&cgrp->files))
                        cgroup_rm_file(cgrp, NULL);
        }
}

/*
 * NOTE : the dentry must have been dget()'ed
 */
static void cgroup_d_remove_dir(struct dentry *dentry)
{
        struct dentry *parent;
        struct cgroupfs_root *root = dentry->d_sb->s_fs_info;

        cgroup_clear_directory(dentry, true, root->subsys_mask);

        parent = dentry->d_parent;
        spin_lock(&parent->d_lock);
        spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
        list_del_init(&dentry->d_u.d_child);
        spin_unlock(&dentry->d_lock);
        spin_unlock(&parent->d_lock);
        remove_dir(dentry);
}

/*
 * Call with cgroup_mutex held. Drops reference counts on modules, including
 * any duplicate ones that parse_cgroupfs_options took. If this function
 * returns an error, no reference counts are touched.
 */
static int rebind_subsystems(struct cgroupfs_root *root,
                              unsigned long final_subsys_mask)
{
        unsigned long added_mask, removed_mask;
        struct cgroup *cgrp = &root->top_cgroup;
        int i;

        BUG_ON(!mutex_is_locked(&cgroup_mutex));
        BUG_ON(!mutex_is_locked(&cgroup_root_mutex));

        removed_mask = root->actual_subsys_mask & ~final_subsys_mask;
        added_mask = final_subsys_mask & ~root->actual_subsys_mask;
        /* Check that any added subsystems are currently free */
        for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
                unsigned long bit = 1UL << i;
                struct cgroup_subsys *ss = subsys[i];
                if (!(bit & added_mask))
                        continue;
                /*
                 * Nobody should tell us to do a subsys that doesn't exist:
                 * parse_cgroupfs_options should catch that case and refcounts
                 * ensure that subsystems won't disappear once selected.
                 */
                BUG_ON(ss == NULL);
                if (ss->root != &rootnode) {
                        /* Subsystem isn't free */
                        return -EBUSY;
                }
        }

        /* Currently we don't handle adding/removing subsystems when
         * any child cgroups exist. This is theoretically supportable
         * but involves complex error handling, so it's being left until
         * later */
        if (root->number_of_cgroups > 1)
                return -EBUSY;

        /* Process each subsystem */
        for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
                struct cgroup_subsys *ss = subsys[i];
                unsigned long bit = 1UL << i;
                if (bit & added_mask) {
                        /* We're binding this subsystem to this hierarchy */
                        BUG_ON(ss == NULL);
                        BUG_ON(cgrp->subsys[i]);
                        BUG_ON(!dummytop->subsys[i]);
                        BUG_ON(dummytop->subsys[i]->cgroup != dummytop);
                        cgrp->subsys[i] = dummytop->subsys[i];
                        cgrp->subsys[i]->cgroup = cgrp;
                        list_move(&ss->sibling, &root->subsys_list);
                        ss->root = root;
                        if (ss->bind)
                                ss->bind(cgrp);
                        /* refcount was already taken, and we're keeping it */
                } else if (bit & removed_mask) {
                        /* We're removing this subsystem */
                        BUG_ON(ss == NULL);
                        BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]);
                        BUG_ON(cgrp->subsys[i]->cgroup != cgrp);
                        if (ss->bind)
                                ss->bind(dummytop);
                        dummytop->subsys[i]->cgroup = dummytop;
                        cgrp->subsys[i] = NULL;
                        subsys[i]->root = &rootnode;
                        list_move(&ss->sibling, &rootnode.subsys_list);
                        /* subsystem is now free - drop reference on module */
                        module_put(ss->module);
                } else if (bit & final_subsys_mask) {
                        /* Subsystem state should already exist */
                        BUG_ON(ss == NULL);
                        BUG_ON(!cgrp->subsys[i]);
                        /*
                         * a refcount was taken, but we already had one, so
                         * drop the extra reference.
                         */
                        module_put(ss->module);
#ifdef CONFIG_MODULE_UNLOAD
                        BUG_ON(ss->module && !module_refcount(ss->module));
#endif
                } else {
                        /* Subsystem state shouldn't exist */
                        BUG_ON(cgrp->subsys[i]);
                }
        }
        root->subsys_mask = root->actual_subsys_mask = final_subsys_mask;
        synchronize_rcu();

        return 0;
}

static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
{
        struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
        struct cgroup_subsys *ss;

        mutex_lock(&cgroup_root_mutex);
        for_each_subsys(root, ss)
                seq_printf(seq, ",%s", ss->name);
        if (test_bit(ROOT_NOPREFIX, &root->flags))
                seq_puts(seq, ",noprefix");
        if (test_bit(ROOT_XATTR, &root->flags))
                seq_puts(seq, ",xattr");
        if (strlen(root->release_agent_path))
                seq_printf(seq, ",release_agent=%s", root->release_agent_path);
        if (clone_children(&root->top_cgroup))
                seq_puts(seq, ",clone_children");
        if (strlen(root->name))
                seq_printf(seq, ",name=%s", root->name);
        mutex_unlock(&cgroup_root_mutex);
        return 0;
}

struct cgroup_sb_opts {
        unsigned long subsys_mask;
        unsigned long flags;
        char *release_agent;
        bool clone_children;
        char *name;
        /* User explicitly requested empty subsystem */
        bool none;

        struct cgroupfs_root *new_root;

};

/*
 * Convert a hierarchy specifier into a bitmask of subsystems and flags. Call
 * with cgroup_mutex held to protect the subsys[] array. This function takes
 * refcounts on subsystems to be used, unless it returns error, in which case
 * no refcounts are taken.
 */
static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
{
        char *token, *o = data;
        bool all_ss = false, one_ss = false;
        unsigned long mask = (unsigned long)-1;
        int i;
        bool module_pin_failed = false;

        BUG_ON(!mutex_is_locked(&cgroup_mutex));

#ifdef CONFIG_CPUSETS
        mask = ~(1UL << cpuset_subsys_id);
#endif

        memset(opts, 0, sizeof(*opts));

        while ((token = strsep(&o, ",")) != NULL) {
                if (!*token)
                        return -EINVAL;
                if (!strcmp(token, "none")) {
                        /* Explicitly have no subsystems */
                        opts->none = true;
                        continue;
                }
                if (!strcmp(token, "all")) {
                        /* Mutually exclusive option 'all' + subsystem name */
                        if (one_ss)
                                return -EINVAL;
                        all_ss = true;
                        continue;
                }
                if (!strcmp(token, "noprefix")) {
                        set_bit(ROOT_NOPREFIX, &opts->flags);
                        continue;
                }
                if (!strcmp(token, "clone_children")) {
                        opts->clone_children = true;
                        continue;
                }
                if (!strcmp(token, "xattr")) {
                        set_bit(ROOT_XATTR, &opts->flags);
                        continue;
                }
                if (!strncmp(token, "release_agent=", 14)) {
                        /* Specifying two release agents is forbidden */
                        if (opts->release_agent)
                                return -EINVAL;
                        opts->release_agent =
                                kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL);
                        if (!opts->release_agent)
                                return -ENOMEM;
                        continue;
                }
                if (!strncmp(token, "name=", 5)) {
                        const char *name = token + 5;
                        /* Can't specify an empty name */
                        if (!strlen(name))
                                return -EINVAL;
                        /* Must match [\w.-]+ */
                        for (i = 0; i < strlen(name); i++) {
                                char c = name[i];
                                if (isalnum(c))
                                        continue;
                                if ((c == '.') || (c == '-') || (c == '_'))
                                        continue;
                                return -EINVAL;
                        }
                        /* Specifying two names is forbidden */
                        if (opts->name)
                                return -EINVAL;
                        opts->name = kstrndup(name,
                                              MAX_CGROUP_ROOT_NAMELEN - 1,
                                              GFP_KERNEL);
                        if (!opts->name)
                                return -ENOMEM;

                        continue;
                }

                for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
                        struct cgroup_subsys *ss = subsys[i];
                        if (ss == NULL)
                                continue;
                        if (strcmp(token, ss->name))
                                continue;
                        if (ss->disabled)
                                continue;

                        /* Mutually exclusive option 'all' + subsystem name */
                        if (all_ss)
                                return -EINVAL;
                        set_bit(i, &opts->subsys_mask);
                        one_ss = true;

                        break;
                }
                if (i == CGROUP_SUBSYS_COUNT)
                        return -ENOENT;
        }

        /*
         * If the 'all' option was specified select all the subsystems,
         * otherwise if 'none', 'name=' and a subsystem name options
         * were not specified, let's default to 'all'
         */
        if (all_ss || (!one_ss && !opts->none && !opts->name)) {
                for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
                        struct cgroup_subsys *ss = subsys[i];
                        if (ss == NULL)
                                continue;
                        if (ss->disabled)
                                continue;
                        set_bit(i, &opts->subsys_mask);
                }
        }

        /* Consistency checks */

        /*
         * Option noprefix was introduced just for backward compatibility
         * with the old cpuset, so we allow noprefix only if mounting just
         * the cpuset subsystem.
         */
        if (test_bit(ROOT_NOPREFIX, &opts->flags) &&
            (opts->subsys_mask & mask))
                return -EINVAL;


        /* Can't specify "none" and some subsystems */
        if (opts->subsys_mask && opts->none)
                return -EINVAL;

        /*
         * We either have to specify by name or by subsystems. (So all
         * empty hierarchies must have a name).
         */
        if (!opts->subsys_mask && !opts->name)
                return -EINVAL;

        /*
         * Grab references on all the modules we'll need, so the subsystems
         * don't dance around before rebind_subsystems attaches them. This may
         * take duplicate reference counts on a subsystem that's already used,
         * but rebind_subsystems handles this case.
         */
        for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
                unsigned long bit = 1UL << i;

                if (!(bit & opts->subsys_mask))
                        continue;
                if (!try_module_get(subsys[i]->module)) {
                        module_pin_failed = true;
                        break;
                }
        }
        if (module_pin_failed) {
                /*
                 * oops, one of the modules was going away. this means that we
                 * raced with a module_delete call, and to the user this is
                 * essentially a "subsystem doesn't exist" case.
                 */
                for (i--; i >= 0; i--) {
                        /* drop refcounts only on the ones we took */
                        unsigned long bit = 1UL << i;

                        if (!(bit & opts->subsys_mask))
                                continue;
                        module_put(subsys[i]->module);
                }
                return -ENOENT;
        }

        return 0;
}

static void drop_parsed_module_refcounts(unsigned long subsys_mask)
{
        int i;
        for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
                unsigned long bit = 1UL << i;

                if (!(bit & subsys_mask))
                        continue;
                module_put(subsys[i]->module);
        }
}

static int cgroup_remount(struct super_block *sb, int *flags, char *data)
{
        int ret = 0;
        struct cgroupfs_root *root = sb->s_fs_info;
        struct cgroup *cgrp = &root->top_cgroup;
        struct cgroup_sb_opts opts;
        unsigned long added_mask, removed_mask;

        mutex_lock(&cgrp->dentry->d_inode->i_mutex);
        mutex_lock(&cgroup_mutex);
        mutex_lock(&cgroup_root_mutex);

        /* See what subsystems are wanted */
        ret = parse_cgroupfs_options(data, &opts);
        if (ret)
                goto out_unlock;

        /* See feature-removal-schedule.txt */
        if (opts.subsys_mask != root->actual_subsys_mask || opts.release_agent)
                pr_warning("cgroup: option changes via remount are deprecated (pid=%d comm=%s)\n",
                           task_tgid_nr(current), current->comm);

        added_mask = opts.subsys_mask & ~root->subsys_mask;
        removed_mask = root->subsys_mask & ~opts.subsys_mask;

        /* Don't allow flags or name to change at remount */
        if (opts.flags != root->flags ||
            (opts.name && strcmp(opts.name, root->name))) {
                ret = -EINVAL;
                drop_parsed_module_refcounts(opts.subsys_mask);
                goto out_unlock;
        }

        ret = rebind_subsystems(root, opts.subsys_mask);
        if (ret) {
                drop_parsed_module_refcounts(opts.subsys_mask);
                goto out_unlock;
        }

        /* clear out any existing files and repopulate subsystem files */
        cgroup_clear_directory(cgrp->dentry, false, removed_mask);
        /* re-populate subsystem files */
        cgroup_populate_dir(cgrp, false, added_mask);

        if (opts.release_agent)
                strcpy(root->release_agent_path, opts.release_agent);
 out_unlock:
        kfree(opts.release_agent);
        kfree(opts.name);
        mutex_unlock(&cgroup_root_mutex);
        mutex_unlock(&cgroup_mutex);
        mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
        return ret;
}

static const struct super_operations cgroup_ops = {
        .statfs = simple_statfs,
        .drop_inode = generic_delete_inode,
        .show_options = cgroup_show_options,
        .remount_fs = cgroup_remount,
};

static void init_cgroup_housekeeping(struct cgroup *cgrp)
{
        INIT_LIST_HEAD(&cgrp->sibling);
        INIT_LIST_HEAD(&cgrp->children);
        INIT_LIST_HEAD(&cgrp->files);
        INIT_LIST_HEAD(&cgrp->css_sets);
        INIT_LIST_HEAD(&cgrp->release_list);
        INIT_LIST_HEAD(&cgrp->pidlists);
        mutex_init(&cgrp->pidlist_mutex);
        INIT_LIST_HEAD(&cgrp->event_list);
        spin_lock_init(&cgrp->event_list_lock);
        simple_xattrs_init(&cgrp->xattrs);
}

static void init_cgroup_root(struct cgroupfs_root *root)
{
        struct cgroup *cgrp = &root->top_cgroup;

        INIT_LIST_HEAD(&root->subsys_list);
        INIT_LIST_HEAD(&root->root_list);
        INIT_LIST_HEAD(&root->allcg_list);
        root->number_of_cgroups = 1;
        cgrp->root = root;
        cgrp->top_cgroup = cgrp;
        list_add_tail(&cgrp->allcg_node, &root->allcg_list);
        init_cgroup_housekeeping(cgrp);
}

static bool init_root_id(struct cgroupfs_root *root)
{
        int ret = 0;

        do {
                if (!ida_pre_get(&hierarchy_ida, GFP_KERNEL))
                        return false;
                spin_lock(&hierarchy_id_lock);
                /* Try to allocate the next unused ID */
                ret = ida_get_new_above(&hierarchy_ida, next_hierarchy_id,
                                        &root->hierarchy_id);
                if (ret == -ENOSPC)
                        /* Try again starting from 0 */
                        ret = ida_get_new(&hierarchy_ida, &root->hierarchy_id);
                if (!ret) {
                        next_hierarchy_id = root->hierarchy_id + 1;
                } else if (ret != -EAGAIN) {
                        /* Can only get here if the 31-bit IDR is full ... */
                        BUG_ON(ret);
                }
                spin_unlock(&hierarchy_id_lock);
        } while (ret);
        return true;
}

static int cgroup_test_super(struct super_block *sb, void *data)
{
        struct cgroup_sb_opts *opts = data;
        struct cgroupfs_root *root = sb->s_fs_info;

        /* If we asked for a name then it must match */
        if (opts->name && strcmp(opts->name, root->name))
                return 0;

        /*
         * If we asked for subsystems (or explicitly for no
         * subsystems) then they must match
         */
        if ((opts->subsys_mask || opts->none)
            && (opts->subsys_mask != root->subsys_mask))
                return 0;

        return 1;
}

static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
{
        struct cgroupfs_root *root;

        if (!opts->subsys_mask && !opts->none)
                return NULL;

        root = kzalloc(sizeof(*root), GFP_KERNEL);
        if (!root)
                return ERR_PTR(-ENOMEM);

        if (!init_root_id(root)) {
                kfree(root);
                return ERR_PTR(-ENOMEM);
        }
        init_cgroup_root(root);

        root->subsys_mask = opts->subsys_mask;
        root->flags = opts->flags;
        if (opts->release_agent)
                strcpy(root->release_agent_path, opts->release_agent);
        if (opts->name)
                strcpy(root->name, opts->name);
        if (opts->clone_children)
                set_bit(CGRP_CLONE_CHILDREN, &root->top_cgroup.flags);
        return root;
}

static void cgroup_drop_root(struct cgroupfs_root *root)
{
        if (!root)
                return;

        BUG_ON(!root->hierarchy_id);
        spin_lock(&hierarchy_id_lock);
        ida_remove(&hierarchy_ida, root->hierarchy_id);
        spin_unlock(&hierarchy_id_lock);
        kfree(root);
}

static int cgroup_set_super(struct super_block *sb, void *data)
{
        int ret;
        struct cgroup_sb_opts *opts = data;

        /* If we don't have a new root, we can't set up a new sb */
        if (!opts->new_root)
                return -EINVAL;

        BUG_ON(!opts->subsys_mask && !opts->none);

        ret = set_anon_super(sb, NULL);
        if (ret)
                return ret;

        sb->s_fs_info = opts->new_root;
        opts->new_root->sb = sb;

        sb->s_blocksize = PAGE_CACHE_SIZE;
        sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
        sb->s_magic = CGROUP_SUPER_MAGIC;
        sb->s_op = &cgroup_ops;

        return 0;
}

static int cgroup_get_rootdir(struct super_block *sb)
{
        static const struct dentry_operations cgroup_dops = {
                .d_iput = cgroup_diput,
                .d_delete = cgroup_delete,
        };

        struct inode *inode =
                cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb);

        if (!inode)
                return -ENOMEM;

        inode->i_fop = &simple_dir_operations;
        inode->i_op = &cgroup_dir_inode_operations;
        /* directories start off with i_nlink == 2 (for "." entry) */
        inc_nlink(inode);
        sb->s_root = d_make_root(inode);
        if (!sb->s_root)
                return -ENOMEM;
        /* for everything else we want ->d_op set */
        sb->s_d_op = &cgroup_dops;
        return 0;
}

static struct dentry *cgroup_mount(struct file_system_type *fs_type,
                         int flags, const char *unused_dev_name,
                         void *data)
{
        struct cgroup_sb_opts opts;
        struct cgroupfs_root *root;
        int ret = 0;
        struct super_block *sb;
        struct cgroupfs_root *new_root;
        struct inode *inode;

        /* First find the desired set of subsystems */
        mutex_lock(&cgroup_mutex);
        ret = parse_cgroupfs_options(data, &opts);
        mutex_unlock(&cgroup_mutex);
        if (ret)
                goto out_err;

        /*
         * Allocate a new cgroup root. We may not need it if we're
         * reusing an existing hierarchy.
         */
        new_root = cgroup_root_from_opts(&opts);
        if (IS_ERR(new_root)) {
                ret = PTR_ERR(new_root);
                goto drop_modules;
        }
        opts.new_root = new_root;

        /* Locate an existing or new sb for this hierarchy */
        sb = sget(fs_type, cgroup_test_super, cgroup_set_super, 0, &opts);
        if (IS_ERR(sb)) {
                ret = PTR_ERR(sb);
                cgroup_drop_root(opts.new_root);
                goto drop_modules;
        }

        root = sb->s_fs_info;
        BUG_ON(!root);
        if (root == opts.new_root) {
                /* We used the new root structure, so this is a new hierarchy */
                struct list_head tmp_cg_links;
                struct cgroup *root_cgrp = &root->top_cgroup;
                struct cgroupfs_root *existing_root;
                const struct cred *cred;
                int i;

                BUG_ON(sb->s_root != NULL);

                ret = cgroup_get_rootdir(sb);
                if (ret)
                        goto drop_new_super;
                inode = sb->s_root->d_inode;

                mutex_lock(&inode->i_mutex);
                mutex_lock(&cgroup_mutex);
                mutex_lock(&cgroup_root_mutex);

                /* Check for name clashes with existing mounts */
                ret = -EBUSY;
                if (strlen(root->name))
                        for_each_active_root(existing_root)
                                if (!strcmp(existing_root->name, root->name))
                                        goto unlock_drop;

                /*
                 * We're accessing css_set_count without locking
                 * css_set_lock here, but that's OK - it can only be
                 * increased by someone holding cgroup_lock, and
                 * that's us. The worst that can happen is that we
                 * have some link structures left over
                 */
                ret = allocate_cg_links(css_set_count, &tmp_cg_links);
                if (ret)
                        goto unlock_drop;

                ret = rebind_subsystems(root, root->subsys_mask);
                if (ret == -EBUSY) {
                        free_cg_links(&tmp_cg_links);
                        goto unlock_drop;
                }
                /*
                 * There must be no failure case after here, since rebinding
                 * takes care of subsystems' refcounts, which are explicitly
                 * dropped in the failure exit path.
                 */

                /* EBUSY should be the only error here */
                BUG_ON(ret);

                list_add(&root->root_list, &roots);
                root_count++;

                sb->s_root->d_fsdata = root_cgrp;
                root->top_cgroup.dentry = sb->s_root;

                /* Link the top cgroup in this hierarchy into all
                 * the css_set objects */
                write_lock(&css_set_lock);
                for (i = 0; i < CSS_SET_TABLE_SIZE; i++) {
                        struct hlist_head *hhead = &css_set_table[i];
                        struct hlist_node *node;
                        struct css_set *cg;

                        hlist_for_each_entry(cg, node, hhead, hlist)
                                link_css_set(&tmp_cg_links, cg, root_cgrp);
                }
                write_unlock(&css_set_lock);

                free_cg_links(&tmp_cg_links);

                BUG_ON(!list_empty(&root_cgrp->sibling));
                BUG_ON(!list_empty(&root_cgrp->children));
                BUG_ON(root->number_of_cgroups != 1);

                cred = override_creds(&init_cred);
                cgroup_populate_dir(root_cgrp, true, root->subsys_mask);
                revert_creds(cred);
                mutex_unlock(&cgroup_root_mutex);
                mutex_unlock(&cgroup_mutex);
                mutex_unlock(&inode->i_mutex);
        } else {
                /*
                 * We re-used an existing hierarchy - the new root (if
                 * any) is not needed
                 */
                cgroup_drop_root(opts.new_root);
                /* no subsys rebinding, so refcounts don't change */
                drop_parsed_module_refcounts(opts.subsys_mask);
        }

        kfree(opts.release_agent);
        kfree(opts.name);
        return dget(sb->s_root);

 unlock_drop:
        mutex_unlock(&cgroup_root_mutex);
        mutex_unlock(&cgroup_mutex);
        mutex_unlock(&inode->i_mutex);
 drop_new_super:
        deactivate_locked_super(sb);
 drop_modules:
        drop_parsed_module_refcounts(opts.subsys_mask);
 out_err:
        kfree(opts.release_agent);
        kfree(opts.name);
        return ERR_PTR(ret);
}

static void cgroup_kill_sb(struct super_block *sb) {
        struct cgroupfs_root *root = sb->s_fs_info;
        struct cgroup *cgrp = &root->top_cgroup;
        int ret;
        struct cg_cgroup_link *link;
        struct cg_cgroup_link *saved_link;

        BUG_ON(!root);

        BUG_ON(root->number_of_cgroups != 1);
        BUG_ON(!list_empty(&cgrp->children));
        BUG_ON(!list_empty(&cgrp->sibling));

        mutex_lock(&cgroup_mutex);
        mutex_lock(&cgroup_root_mutex);

        /* Rebind all subsystems back to the default hierarchy */
        ret = rebind_subsystems(root, 0);
        /* Shouldn't be able to fail ... */
        BUG_ON(ret);

        /*
         * Release all the links from css_sets to this hierarchy's
         * root cgroup
         */
        write_lock(&css_set_lock);

        list_for_each_entry_safe(link, saved_link, &cgrp->css_sets,
                                 cgrp_link_list) {
                list_del(&link->cg_link_list);
                list_del(&link->cgrp_link_list);
                kfree(link);
        }
        write_unlock(&css_set_lock);

        if (!list_empty(&root->root_list)) {
                list_del(&root->root_list);
                root_count--;
        }

        mutex_unlock(&cgroup_root_mutex);
        mutex_unlock(&cgroup_mutex);

        simple_xattrs_free(&cgrp->xattrs);

        kill_litter_super(sb);
        cgroup_drop_root(root);
}

static struct file_system_type cgroup_fs_type = {
        .name = "cgroup",
        .mount = cgroup_mount,
        .kill_sb = cgroup_kill_sb,
};

static struct kobject *cgroup_kobj;

/**
 * cgroup_path - generate the path of a cgroup
 * @cgrp: the cgroup in question
 * @buf: the buffer to write the path into
 * @buflen: the length of the buffer
 *
 * Called with cgroup_mutex held or else with an RCU-protected cgroup
 * reference.  Writes path of cgroup into buf.  Returns 0 on success,
 * -errno on error.
 */
int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
{
        char *start;
        struct dentry *dentry = rcu_dereference_check(cgrp->dentry,
                                                      cgroup_lock_is_held());

        if (!dentry || cgrp == dummytop) {
                /*
                 * Inactive subsystems have no dentry for their root
                 * cgroup
                 */
                strcpy(buf, "/");
                return 0;
        }

        start = buf + buflen;

        *--start = '\0';
        for (;;) {
                int len = dentry->d_name.len;

                if ((start -= len) < buf)
                        return -ENAMETOOLONG;
                memcpy(start, dentry->d_name.name, len);
                cgrp = cgrp->parent;
                if (!cgrp)
                        break;

                dentry = rcu_dereference_check(cgrp->dentry,
                                               cgroup_lock_is_held());
                if (!cgrp->parent)
                        continue;
                if (--start < buf)
                        return -ENAMETOOLONG;
                *start = '/';
        }
        memmove(buf, start, buf + buflen - start);
        return 0;
}
EXPORT_SYMBOL_GPL(cgroup_path);

/*
 * Control Group taskset
 */
struct task_and_cgroup {
        struct task_struct      *task;
        struct cgroup           *cgrp;
        struct css_set          *cg;
};

struct cgroup_taskset {
        struct task_and_cgroup  single;
        struct flex_array       *tc_array;
        int                     tc_array_len;
        int                     idx;
        struct cgroup           *cur_cgrp;
};

/**
 * cgroup_taskset_first - reset taskset and return the first task
 * @tset: taskset of interest
 *
 * @tset iteration is initialized and the first task is returned.
 */
struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
{
        if (tset->tc_array) {
                tset->idx = 0;
                return cgroup_taskset_next(tset);
        } else {
                tset->cur_cgrp = tset->single.cgrp;
                return tset->single.task;
        }
}
EXPORT_SYMBOL_GPL(cgroup_taskset_first);

/**
 * cgroup_taskset_next - iterate to the next task in taskset
 * @tset: taskset of interest
 *
 * Return the next task in @tset.  Iteration must have been initialized
 * with cgroup_taskset_first().
 */
struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
{
        struct task_and_cgroup *tc;

        if (!tset->tc_array || tset->idx >= tset->tc_array_len)
                return NULL;

        tc = flex_array_get(tset->tc_array, tset->idx++);
        tset->cur_cgrp = tc->cgrp;
        return tc->task;
}
EXPORT_SYMBOL_GPL(cgroup_taskset_next);

/**
 * cgroup_taskset_cur_cgroup - return the matching cgroup for the current task
 * @tset: taskset of interest
 *
 * Return the cgroup for the current (last returned) task of @tset.  This
 * function must be preceded by either cgroup_taskset_first() or
 * cgroup_taskset_next().
 */
struct cgroup *cgroup_taskset_cur_cgroup(struct cgroup_taskset *tset)
{
        return tset->cur_cgrp;
}
EXPORT_SYMBOL_GPL(cgroup_taskset_cur_cgroup);

/**
 * cgroup_taskset_size - return the number of tasks in taskset
 * @tset: taskset of interest
 */
int cgroup_taskset_size(struct cgroup_taskset *tset)
{
        return tset->tc_array ? tset->tc_array_len : 1;
}
EXPORT_SYMBOL_GPL(cgroup_taskset_size);


/*
 * cgroup_task_migrate - move a task from one cgroup to another.
 *
 * 'guarantee' is set if the caller promises that a new css_set for the task
 * will already exist. If not set, this function might sleep, and can fail with
 * -ENOMEM. Must be called with cgroup_mutex and threadgroup locked.
 */
static void cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
                                struct task_struct *tsk, struct css_set *newcg)
{
        struct css_set *oldcg;

        /*
         * We are synchronized through threadgroup_lock() against PF_EXITING
         * setting such that we can't race against cgroup_exit() changing the
         * css_set to init_css_set and dropping the old one.
         */
        WARN_ON_ONCE(tsk->flags & PF_EXITING);
        oldcg = tsk->cgroups;

        task_lock(tsk);
        rcu_assign_pointer(tsk->cgroups, newcg);
        task_unlock(tsk);

        /* Update the css_set linked lists if we're using them */
        write_lock(&css_set_lock);
        if (!list_empty(&tsk->cg_list))
                list_move(&tsk->cg_list, &newcg->tasks);
        write_unlock(&css_set_lock);

        /*
         * We just gained a reference on oldcg by taking it from the task. As
         * trading it for newcg is protected by cgroup_mutex, we're safe to drop
         * it here; it will be freed under RCU.
         */
        put_css_set(oldcg);

        set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
}

/**
 * cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
 * @cgrp: the cgroup the task is attaching to
 * @tsk: the task to be attached
 *
 * Call with cgroup_mutex and threadgroup locked. May take task_lock of
 * @tsk during call.
 */
int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
{
        int retval = 0;
        struct cgroup_subsys *ss, *failed_ss = NULL;
        struct cgroup *oldcgrp;
        struct cgroupfs_root *root = cgrp->root;
        struct cgroup_taskset tset = { };
        struct css_set *newcg;

        /* @tsk either already exited or can't exit until the end */
        if (tsk->flags & PF_EXITING)
                return -ESRCH;

        /* Nothing to do if the task is already in that cgroup */
        oldcgrp = task_cgroup_from_root(tsk, root);
        if (cgrp == oldcgrp)
                return 0;

        tset.single.task = tsk;
        tset.single.cgrp = oldcgrp;

        for_each_subsys(root, ss) {
                if (ss->can_attach) {
                        retval = ss->can_attach(cgrp, &tset);
                        if (retval) {
                                /*
                                 * Remember on which subsystem the can_attach()
                                 * failed, so that we only call cancel_attach()
                                 * against the subsystems whose can_attach()
                                 * succeeded. (See below)
                                 */
                                failed_ss = ss;
                                goto out;
                        }
                }
        }

        newcg = find_css_set(tsk->cgroups, cgrp);
        if (!newcg) {
                retval = -ENOMEM;
                goto out;
        }

        cgroup_task_migrate(cgrp, oldcgrp, tsk, newcg);

        for_each_subsys(root, ss) {
                if (ss->attach)
                        ss->attach(cgrp, &tset);
        }

        synchronize_rcu();
out:
        if (retval) {
                for_each_subsys(root, ss) {
                        if (ss == failed_ss)
                                /*
                                 * This subsystem was the one that failed the
                                 * can_attach() check earlier, so we don't need
                                 * to call cancel_attach() against it or any
                                 * remaining subsystems.
                                 */
                                break;
                        if (ss->cancel_attach)
                                ss->cancel_attach(cgrp, &tset);
                }
        }
        return retval;
}

/**
 * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from'
 * @from: attach to all cgroups of a given task
 * @tsk: the task to be attached
 */
int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
{
        struct cgroupfs_root *root;
        int retval = 0;

        cgroup_lock();
        for_each_active_root(root) {
                struct cgroup *from_cg = task_cgroup_from_root(from, root);

                retval = cgroup_attach_task(from_cg, tsk);
                if (retval)
                        break;
        }
        cgroup_unlock();

        return retval;
}
EXPORT_SYMBOL_GPL(cgroup_attach_task_all);

/**
 * cgroup_attach_proc - attach all threads in a threadgroup to a cgroup
 * @cgrp: the cgroup to attach to
 * @leader: the threadgroup leader task_struct of the group to be attached
 *
 * Call holding cgroup_mutex and the group_rwsem of the leader. Will take
 * task_lock of each thread in leader's threadgroup individually in turn.
 */
static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
{
        int retval, i, group_size;
        struct cgroup_subsys *ss, *failed_ss = NULL;
        /* guaranteed to be initialized later, but the compiler needs this */
        struct cgroupfs_root *root = cgrp->root;
        /* threadgroup list cursor and array */
        struct task_struct *tsk;
        struct task_and_cgroup *tc;
        struct flex_array *group;
        struct cgroup_taskset tset = { };

        /*
         * step 0: in order to do expensive, possibly blocking operations for
         * every thread, we cannot iterate the thread group list, since it needs
         * rcu or tasklist locked. instead, build an array of all threads in the
         * group - group_rwsem prevents new threads from appearing, and if
         * threads exit, this will just be an over-estimate.
         */
        group_size = get_nr_threads(leader);
        /* flex_array supports very large thread-groups better than kmalloc. */
        group = flex_array_alloc(sizeof(*tc), group_size, GFP_KERNEL);
        if (!group)
                return -ENOMEM;
        /* pre-allocate to guarantee space while iterating in rcu read-side. */
        retval = flex_array_prealloc(group, 0, group_size - 1, GFP_KERNEL);
        if (retval)
                goto out_free_group_list;

        tsk = leader;
        i = 0;
        /*
         * Prevent freeing of tasks while we take a snapshot. Tasks that are
         * already PF_EXITING could be freed from underneath us unless we
         * take an rcu_read_lock.
         */
        rcu_read_lock();
        do {
                struct task_and_cgroup ent;

                /* @tsk either already exited or can't exit until the end */
                if (tsk->flags & PF_EXITING)
                        continue;

                /* as per above, nr_threads may decrease, but not increase. */
                BUG_ON(i >= group_size);
                ent.task = tsk;
                ent.cgrp = task_cgroup_from_root(tsk, root);
                /* nothing to do if this task is already in the cgroup */
                if (ent.cgrp == cgrp)
                        continue;
                /*
                 * saying GFP_ATOMIC has no effect here because we did prealloc
                 * earlier, but it's good form to communicate our expectations.
                 */
                retval = flex_array_put(group, i, &ent, GFP_ATOMIC);
                BUG_ON(retval != 0);
                i++;
        } while_each_thread(leader, tsk);
        rcu_read_unlock();
        /* remember the number of threads in the array for later. */
        group_size = i;
        tset.tc_array = group;
        tset.tc_array_len = group_size;

        /* methods shouldn't be called if no task is actually migrating */
        retval = 0;
        if (!group_size)
                goto out_free_group_list;

        /*
         * step 1: check that we can legitimately attach to the cgroup.
         */
        for_each_subsys(root, ss) {
                if (ss->can_attach) {
                        retval = ss->can_attach(cgrp, &tset);
                        if (retval) {
                                failed_ss = ss;
                                goto out_cancel_attach;
                        }
                }
        }

        /*
         * step 2: make sure css_sets exist for all threads to be migrated.
         * we use find_css_set, which allocates a new one if necessary.
         */
        for (i = 0; i < group_size; i++) {
                tc = flex_array_get(group, i);
                tc->cg = find_css_set(tc->task->cgroups, cgrp);
                if (!tc->cg) {
                        retval = -ENOMEM;
                        goto out_put_css_set_refs;
                }
        }

        /*
         * step 3: now that we're guaranteed success wrt the css_sets,
         * proceed to move all tasks to the new cgroup.  There are no
         * failure cases after here, so this is the commit point.
         */
        for (i = 0; i < group_size; i++) {
                tc = flex_array_get(group, i);
                cgroup_task_migrate(cgrp, tc->cgrp, tc->task, tc->cg);
        }
        /* nothing is sensitive to fork() after this point. */

        /*
         * step 4: do subsystem attach callbacks.
         */
        for_each_subsys(root, ss) {
                if (ss->attach)
                        ss->attach(cgrp, &tset);
        }

        /*
         * step 5: success! and cleanup
         */
        synchronize_rcu();
        retval = 0;
out_put_css_set_refs:
        if (retval) {
                for (i = 0; i < group_size; i++) {
                        tc = flex_array_get(group, i);
                        if (!tc->cg)
                                break;
                        put_css_set(tc->cg);
                }
        }
out_cancel_attach:
        if (retval) {
                for_each_subsys(root, ss) {
                        if (ss == failed_ss)
                                break;
                        if (ss->cancel_attach)
                                ss->cancel_attach(cgrp, &tset);
                }
        }
out_free_group_list:
        flex_array_free(group);
        return retval;
}

/*
 * Find the task_struct of the task to attach by vpid and pass it along to the
 * function to attach either it or all tasks in its threadgroup. Will lock
 * cgroup_mutex and threadgroup; may take task_lock of task.
 */
static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup)
{
        struct task_struct *tsk;
        const struct cred *cred = current_cred(), *tcred;
        int ret;

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

retry_find_task:
        rcu_read_lock();
        if (pid) {
                tsk = find_task_by_vpid(pid);
                if (!tsk) {
                        rcu_read_unlock();
                        ret= -ESRCH;
                        goto out_unlock_cgroup;
                }
                /*
                 * even if we're attaching all tasks in the thread group, we
                 * only need to check permissions on one of them.
                 */
                tcred = __task_cred(tsk);
                if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
                    !uid_eq(cred->euid, tcred->uid) &&
                    !uid_eq(cred->euid, tcred->suid)) {
                        rcu_read_unlock();
                        ret = -EACCES;
                        goto out_unlock_cgroup;
                }
        } else
                tsk = current;

        if (threadgroup)
                tsk = tsk->group_leader;

        /*
         * Workqueue threads may acquire PF_THREAD_BOUND and become
         * trapped in a cpuset, or RT worker may be born in a cgroup
         * with no rt_runtime allocated.  Just say no.
         */
        if (tsk == kthreadd_task || (tsk->flags & PF_THREAD_BOUND)) {
                ret = -EINVAL;
                rcu_read_unlock();
                goto out_unlock_cgroup;
        }

        get_task_struct(tsk);
        rcu_read_unlock();

        threadgroup_lock(tsk);
        if (threadgroup) {
                if (!thread_group_leader(tsk)) {
                        /*
                         * a race with de_thread from another thread's exec()
                         * may strip us of our leadership, if this happens,
                         * there is no choice but to throw this task away and
                         * try again; this is
                         * "double-double-toil-and-trouble-check locking".
                         */
                        threadgroup_unlock(tsk);
                        put_task_struct(tsk);
                        goto retry_find_task;
                }
                ret = cgroup_attach_proc(cgrp, tsk);
        } else
                ret = cgroup_attach_task(cgrp, tsk);
        threadgroup_unlock(tsk);

        put_task_struct(tsk);
out_unlock_cgroup:
        cgroup_unlock();
        return ret;
}

static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
{
        return attach_task_by_pid(cgrp, pid, false);
}

static int cgroup_procs_write(struct cgroup *cgrp, struct cftype *cft, u64 tgid)
{
        return attach_task_by_pid(cgrp, tgid, true);
}

/**
 * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
 * @cgrp: the cgroup to be checked for liveness
 *
 * On success, returns true; the lock should be later released with
 * cgroup_unlock(). On failure returns false with no lock held.
 */
bool cgroup_lock_live_group(struct cgroup *cgrp)
{
        mutex_lock(&cgroup_mutex);
        if (cgroup_is_removed(cgrp)) {
                mutex_unlock(&cgroup_mutex);
                return false;
        }
        return true;
}
EXPORT_SYMBOL_GPL(cgroup_lock_live_group);

static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
                                      const char *buffer)
{
        BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
        if (strlen(buffer) >= PATH_MAX)
                return -EINVAL;
        if (!cgroup_lock_live_group(cgrp))
                return -ENODEV;
        mutex_lock(&cgroup_root_mutex);
        strcpy(cgrp->root->release_agent_path, buffer);
        mutex_unlock(&cgroup_root_mutex);
        cgroup_unlock();
        return 0;
}

static int cgroup_release_agent_show(struct cgroup *cgrp, struct cftype *cft,
                                     struct seq_file *seq)
{
        if (!cgroup_lock_live_group(cgrp))
                return -ENODEV;
        seq_puts(seq, cgrp->root->release_agent_path);
        seq_putc(seq, '\n');
        cgroup_unlock();
        return 0;
}

/* A buffer size big enough for numbers or short strings */
#define CGROUP_LOCAL_BUFFER_SIZE 64

static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft,
                                struct file *file,
                                const char __user *userbuf,
                                size_t nbytes, loff_t *unused_ppos)
{
        char buffer[CGROUP_LOCAL_BUFFER_SIZE];
        int retval = 0;
        char *end;

        if (!nbytes)
                return -EINVAL;
        if (nbytes >= sizeof(buffer))
                return -E2BIG;
        if (copy_from_user(buffer, userbuf, nbytes))
                return -EFAULT;

        buffer[nbytes] = 0;     /* nul-terminate */
        if (cft->write_u64) {
                u64 val = simple_strtoull(strstrip(buffer), &end, 0);
                if (*end)
                        return -EINVAL;
                retval = cft->write_u64(cgrp, cft, val);
        } else {
                s64 val = simple_strtoll(strstrip(buffer), &end, 0);
                if (*end)
                        return -EINVAL;
                retval = cft->write_s64(cgrp, cft, val);
        }
        if (!retval)
                retval = nbytes;
        return retval;
}

static ssize_t cgroup_write_string(struct cgroup *cgrp, struct cftype *cft,
                                   struct file *file,
                                   const char __user *userbuf,
                                   size_t nbytes, loff_t *unused_ppos)
{
        char local_buffer[CGROUP_LOCAL_BUFFER_SIZE];
        int retval = 0;
        size_t max_bytes = cft->max_write_len;
        char *buffer = local_buffer;

        if (!max_bytes)
                max_bytes = sizeof(local_buffer) - 1;
        if (nbytes >= max_bytes)
                return -E2BIG;
        /* Allocate a dynamic buffer if we need one */
        if (nbytes >= sizeof(local_buffer)) {
                buffer = kmalloc(nbytes + 1, GFP_KERNEL);
                if (buffer == NULL)
                        return -ENOMEM;
        }
        if (nbytes && copy_from_user(buffer, userbuf, nbytes)) {
                retval = -EFAULT;
                goto out;
        }

        buffer[nbytes] = 0;     /* nul-terminate */
        retval = cft->write_string(cgrp, cft, strstrip(buffer));
        if (!retval)
                retval = nbytes;
out:
        if (buffer != local_buffer)
                kfree(buffer);
        return retval;
}

static ssize_t cgroup_file_write(struct file *file, const char __user *buf,
                                                size_t nbytes, loff_t *ppos)
{
        struct cftype *cft = __d_cft(file->f_dentry);
        struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);

        if (cgroup_is_removed(cgrp))
                return -ENODEV;
        if (cft->write)
                return cft->write(cgrp, cft, file, buf, nbytes, ppos);
        if (cft->write_u64 || cft->write_s64)
                return cgroup_write_X64(cgrp, cft, file, buf, nbytes, ppos);
        if (cft->write_string)
                return cgroup_write_string(cgrp, cft, file, buf, nbytes, ppos);
        if (cft->trigger) {
                int ret = cft->trigger(cgrp, (unsigned int)cft->private);
                return ret ? ret : nbytes;
        }
        return -EINVAL;
}

static ssize_t cgroup_read_u64(struct cgroup *cgrp, struct cftype *cft,
                               struct file *file,
                               char __user *buf, size_t nbytes,
                               loff_t *ppos)
{
        char tmp[CGROUP_LOCAL_BUFFER_SIZE];
        u64 val = cft->read_u64(cgrp, cft);
        int len = sprintf(tmp, "%llu\n", (unsigned long long) val);

        return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
}

static ssize_t cgroup_read_s64(struct cgroup *cgrp, struct cftype *cft,
                               struct file *file,
                               char __user *buf, size_t nbytes,
                               loff_t *ppos)
{
        char tmp[CGROUP_LOCAL_BUFFER_SIZE];
        s64 val = cft->read_s64(cgrp, cft);
        int len = sprintf(tmp, "%lld\n", (long long) val);

        return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
}

static ssize_t cgroup_file_read(struct file *file, char __user *buf,
                                   size_t nbytes, loff_t *ppos)
{
        struct cftype *cft = __d_cft(file->f_dentry);
        struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);

        if (cgroup_is_removed(cgrp))
                return -ENODEV;

        if (cft->read)
                return cft->read(cgrp, cft, file, buf, nbytes, ppos);
        if (cft->read_u64)
                return cgroup_read_u64(cgrp, cft, file, buf, nbytes, ppos);
        if (cft->read_s64)
                return cgroup_read_s64(cgrp, cft, file, buf, nbytes, ppos);
        return -EINVAL;
}

/*
 * seqfile ops/methods for returning structured data. Currently just
 * supports string->u64 maps, but can be extended in future.
 */

struct cgroup_seqfile_state {
        struct cftype *cft;
        struct cgroup *cgroup;
};

static int cgroup_map_add(struct cgroup_map_cb *cb, const char *key, u64 value)
{
        struct seq_file *sf = cb->state;
        return seq_printf(sf, "%s %llu\n", key, (unsigned long long)value);
}

static int cgroup_seqfile_show(struct seq_file *m, void *arg)
{
        struct cgroup_seqfile_state *state = m->private;
        struct cftype *cft = state->cft;
        if (cft->read_map) {
                struct cgroup_map_cb cb = {
                        .fill = cgroup_map_add,
                        .state = m,
                };
                return cft->read_map(state->cgroup, cft, &cb);
        }
        return cft->read_seq_string(state->cgroup, cft, m);
}

static int cgroup_seqfile_release(struct inode *inode, struct file *file)
{
        struct seq_file *seq = file->private_data;
        kfree(seq->private);
        return single_release(inode, file);
}

static const struct file_operations cgroup_seqfile_operations = {
        .read = seq_read,
        .write = cgroup_file_write,
        .llseek = seq_lseek,
        .release = cgroup_seqfile_release,
};

static int cgroup_file_open(struct inode *inode, struct file *file)
{
        int err;
        struct cftype *cft;

        err = generic_file_open(inode, file);
        if (err)
                return err;
        cft = __d_cft(file->f_dentry);

        if (cft->read_map || cft->read_seq_string) {
                struct cgroup_seqfile_state *state =
                        kzalloc(sizeof(*state), GFP_USER);
                if (!state)
                        return -ENOMEM;
                state->cft = cft;
                state->cgroup = __d_cgrp(file->f_dentry->d_parent);
                file->f_op = &cgroup_seqfile_operations;
                err = single_open(file, cgroup_seqfile_show, state);
                if (err < 0)
                        kfree(state);
        } else if (cft->open)
                err = cft->open(inode, file);
        else
                err = 0;

        return err;
}

static int cgroup_file_release(struct inode *inode, struct file *file)
{
        struct cftype *cft = __d_cft(file->f_dentry);
        if (cft->release)
                return cft->release(inode, file);
        return 0;
}

/*
 * cgroup_rename - Only allow simple rename of directories in place.
 */
static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
                            struct inode *new_dir, struct dentry *new_dentry)
{
        if (!S_ISDIR(old_dentry->d_inode->i_mode))
                return -ENOTDIR;
        if (new_dentry->d_inode)
                return -EEXIST;
        if (old_dir != new_dir)
                return -EIO;
        return simple_rename(old_dir, old_dentry, new_dir, new_dentry);
}

static struct simple_xattrs *__d_xattrs(struct dentry *dentry)
{
        if (S_ISDIR(dentry->d_inode->i_mode))
                return &__d_cgrp(dentry)->xattrs;
        else
                return &__d_cft(dentry)->xattrs;
}

static inline int xattr_enabled(struct dentry *dentry)
{
        struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
        return test_bit(ROOT_XATTR, &root->flags);
}

static bool is_valid_xattr(const char *name)
{
        if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
            !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN))
                return true;
        return false;
}

static int cgroup_setxattr(struct dentry *dentry, const char *name,
                           const void *val, size_t size, int flags)
{
        if (!xattr_enabled(dentry))
                return -EOPNOTSUPP;
        if (!is_valid_xattr(name))
                return -EINVAL;
        return simple_xattr_set(__d_xattrs(dentry), name, val, size, flags);
}

static int cgroup_removexattr(struct dentry *dentry, const char *name)
{
        if (!xattr_enabled(dentry))
                return -EOPNOTSUPP;
        if (!is_valid_xattr(name))
                return -EINVAL;
        return simple_xattr_remove(__d_xattrs(dentry), name);
}

static ssize_t cgroup_getxattr(struct dentry *dentry, const char *name,
                               void *buf, size_t size)
{
        if (!xattr_enabled(dentry))
                return -EOPNOTSUPP;
        if (!is_valid_xattr(name))
                return -EINVAL;
        return simple_xattr_get(__d_xattrs(dentry), name, buf, size);
}

static ssize_t cgroup_listxattr(struct dentry *dentry, char *buf, size_t size)
{
        if (!xattr_enabled(dentry))
                return -EOPNOTSUPP;
        return simple_xattr_list(__d_xattrs(dentry), buf, size);
}

static const struct file_operations cgroup_file_operations = {
        .read = cgroup_file_read,
        .write = cgroup_file_write,
        .llseek = generic_file_llseek,
        .open = cgroup_file_open,
        .release = cgroup_file_release,
};

static const struct inode_operations cgroup_file_inode_operations = {
        .setxattr = cgroup_setxattr,
        .getxattr = cgroup_getxattr,
        .listxattr = cgroup_listxattr,
        .removexattr = cgroup_removexattr,
};

static const struct inode_operations cgroup_dir_inode_operations = {
        .lookup = cgroup_lookup,
        .mkdir = cgroup_mkdir,
        .rmdir = cgroup_rmdir,
        .rename = cgroup_rename,
        .setxattr = cgroup_setxattr,
        .getxattr = cgroup_getxattr,
        .listxattr = cgroup_listxattr,
        .removexattr = cgroup_removexattr,
};

static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
        if (dentry->d_name.len > NAME_MAX)
                return ERR_PTR(-ENAMETOOLONG);
        d_add(dentry, NULL);
        return NULL;
}

/*
 * Check if a file is a control file
 */
static inline struct cftype *__file_cft(struct file *file)
{
        if (file->f_dentry->d_inode->i_fop != &cgroup_file_operations)
                return ERR_PTR(-EINVAL);
        return __d_cft(file->f_dentry);
}

static int cgroup_create_file(struct dentry *dentry, umode_t mode,
                                struct super_block *sb)
{
        struct inode *inode;

        if (!dentry)
                return -ENOENT;
        if (dentry->d_inode)
                return -EEXIST;

        inode = cgroup_new_inode(mode, sb);
        if (!inode)
                return -ENOMEM;

        if (S_ISDIR(mode)) {
                inode->i_op = &cgroup_dir_inode_operations;
                inode->i_fop = &simple_dir_operations;

                /* start off with i_nlink == 2 (for "." entry) */
                inc_nlink(inode);

                /* start with the directory inode held, so that we can
                 * populate it without racing with another mkdir */
                mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
        } else if (S_ISREG(mode)) {
                inode->i_size = 0;
                inode->i_fop = &cgroup_file_operations;
                inode->i_op = &cgroup_file_inode_operations;
        }
        d_instantiate(dentry, inode);
        dget(dentry);   /* Extra count - pin the dentry in core */
        return 0;
}

/*
 * cgroup_create_dir - create a directory for an object.
 * @cgrp: the cgroup we create the directory for. It must have a valid
 *        ->parent field. And we are going to fill its ->dentry field.
 * @dentry: dentry of the new cgroup
 * @mode: mode to set on new directory.
 */
static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry,
                                umode_t mode)
{
        struct dentry *parent;
        int error = 0;

        parent = cgrp->parent->dentry;
        error = cgroup_create_file(dentry, S_IFDIR | mode, cgrp->root->sb);
        if (!error) {
                dentry->d_fsdata = cgrp;
                inc_nlink(parent->d_inode);
                rcu_assign_pointer(cgrp->dentry, dentry);
                dget(dentry);
        }
        dput(dentry);

        return error;
}

/**
 * cgroup_file_mode - deduce file mode of a control file
 * @cft: the control file in question
 *
 * returns cft->mode if ->mode is not 0
 * returns S_IRUGO|S_IWUSR if it has both a read and a write handler
 * returns S_IRUGO if it has only a read handler
 * returns S_IWUSR if it has only a write hander
 */
static umode_t cgroup_file_mode(const struct cftype *cft)
{
        umode_t mode = 0;

        if (cft->mode)
                return cft->mode;

        if (cft->read || cft->read_u64 || cft->read_s64 ||
            cft->read_map || cft->read_seq_string)
                mode |= S_IRUGO;

        if (cft->write || cft->write_u64 || cft->write_s64 ||
            cft->write_string || cft->trigger)
                mode |= S_IWUSR;

        return mode;
}

static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
                           struct cftype *cft)
{
        struct dentry *dir = cgrp->dentry;
        struct cgroup *parent = __d_cgrp(dir);
        struct dentry *dentry;
        struct cfent *cfe;
        int error;
        umode_t mode;
        char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };

        simple_xattrs_init(&cft->xattrs);

        /* does @cft->flags tell us to skip creation on @cgrp? */
        if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent)
                return 0;
        if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgrp->parent)
                return 0;

        if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) {
                strcpy(name, subsys->name);
                strcat(name, ".");
        }
        strcat(name, cft->name);

        BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex));

        cfe = kzalloc(sizeof(*cfe), GFP_KERNEL);
        if (!cfe)
                return -ENOMEM;

        dentry = lookup_one_len(name, dir, strlen(name));
        if (IS_ERR(dentry)) {
                error = PTR_ERR(dentry);
                goto out;
        }

        mode = cgroup_file_mode(cft);
        error = cgroup_create_file(dentry, mode | S_IFREG, cgrp->root->sb);
        if (!error) {
                cfe->type = (void *)cft;
                cfe->dentry = dentry;
                dentry->d_fsdata = cfe;
                list_add_tail(&cfe->node, &parent->files);
                cfe = NULL;
        }
        dput(dentry);
out:
        kfree(cfe);
        return error;
}

static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys,
                              struct cftype cfts[], bool is_add)
{
        struct cftype *cft;
        int err, ret = 0;

        for (cft = cfts; cft->name[0] != '\0'; cft++) {
                if (is_add)
                        err = cgroup_add_file(cgrp, subsys, cft);
                else
                        err = cgroup_rm_file(cgrp, cft);
                if (err) {
                        pr_warning("cgroup_addrm_files: failed to %s %s, err=%d\n",
                                   is_add ? "add" : "remove", cft->name, err);
                        ret = err;
                }
        }
        return ret;
}

static DEFINE_MUTEX(cgroup_cft_mutex);

static void cgroup_cfts_prepare(void)
        __acquires(&cgroup_cft_mutex) __acquires(&cgroup_mutex)
{
        /*
         * Thanks to the entanglement with vfs inode locking, we can't walk
         * the existing cgroups under cgroup_mutex and create files.
         * Instead, we increment reference on all cgroups and build list of
         * them using @cgrp->cft_q_node.  Grab cgroup_cft_mutex to ensure
         * exclusive access to the field.
         */
        mutex_lock(&cgroup_cft_mutex);
        mutex_lock(&cgroup_mutex);
}

static void cgroup_cfts_commit(struct cgroup_subsys *ss,
                               struct cftype *cfts, bool is_add)
        __releases(&cgroup_mutex) __releases(&cgroup_cft_mutex)
{
        LIST_HEAD(pending);
        struct cgroup *cgrp, *n;

        /* %NULL @cfts indicates abort and don't bother if @ss isn't attached */
        if (cfts && ss->root != &rootnode) {
                list_for_each_entry(cgrp, &ss->root->allcg_list, allcg_node) {
                        dget(cgrp->dentry);
                        list_add_tail(&cgrp->cft_q_node, &pending);
                }
        }

        mutex_unlock(&cgroup_mutex);

        /*
         * All new cgroups will see @cfts update on @ss->cftsets.  Add/rm
         * files for all cgroups which were created before.
         */
        list_for_each_entry_safe(cgrp, n, &pending, cft_q_node) {
                struct inode *inode = cgrp->dentry->d_inode;

                mutex_lock(&inode->i_mutex);
                mutex_lock(&cgroup_mutex);
                if (!cgroup_is_removed(cgrp))
                        cgroup_addrm_files(cgrp, ss, cfts, is_add);
                mutex_unlock(&cgroup_mutex);
                mutex_unlock(&inode->i_mutex);

                list_del_init(&cgrp->cft_q_node);
                dput(cgrp->dentry);
        }

        mutex_unlock(&cgroup_cft_mutex);
}

/**
 * cgroup_add_cftypes - add an array of cftypes to a subsystem
 * @ss: target cgroup subsystem
 * @cfts: zero-length name terminated array of cftypes
 *
 * Register @cfts to @ss.  Files described by @cfts are created for all
 * existing cgroups to which @ss is attached and all future cgroups will
 * have them too.  This function can be called anytime whether @ss is
 * attached or not.
 *
 * Returns 0 on successful registration, -errno on failure.  Note that this
 * function currently returns 0 as long as @cfts registration is successful
 * even if some file creation attempts on existing cgroups fail.
 */
int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
        struct cftype_set *set;

        set = kzalloc(sizeof(*set), GFP_KERNEL);
        if (!set)
                return -ENOMEM;

        cgroup_cfts_prepare();
        set->cfts = cfts;
        list_add_tail(&set->node, &ss->cftsets);
        cgroup_cfts_commit(ss, cfts, true);

        return 0;
}
EXPORT_SYMBOL_GPL(cgroup_add_cftypes);

/**
 * cgroup_rm_cftypes - remove an array of cftypes from a subsystem
 * @ss: target cgroup subsystem
 * @cfts: zero-length name terminated array of cftypes
 *
 * Unregister @cfts from @ss.  Files described by @cfts are removed from
 * all existing cgroups to which @ss is attached and all future cgroups
 * won't have them either.  This function can be called anytime whether @ss
 * is attached or not.
 *
 * Returns 0 on successful unregistration, -ENOENT if @cfts is not
 * registered with @ss.
 */
int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
        struct cftype_set *set;

        cgroup_cfts_prepare();

        list_for_each_entry(set, &ss->cftsets, node) {
                if (set->cfts == cfts) {
                        list_del_init(&set->node);
                        cgroup_cfts_commit(ss, cfts, false);
                        return 0;
                }
        }

        cgroup_cfts_commit(ss, NULL, false);
        return -ENOENT;
}

/**
 * cgroup_task_count - count the number of tasks in a cgroup.
 * @cgrp: the cgroup in question
 *
 * Return the number of tasks in the cgroup.
 */
int cgroup_task_count(const struct cgroup *cgrp)
{
        int count = 0;
        struct cg_cgroup_link *link;

        read_lock(&css_set_lock);
        list_for_each_entry(link, &cgrp->css_sets, cgrp_link_list) {
                count += atomic_read(&link->cg->refcount);
        }
        read_unlock(&css_set_lock);
        return count;
}

/*
 * Advance a list_head iterator.  The iterator should be positioned at
 * the start of a css_set
 */
static void cgroup_advance_iter(struct cgroup *cgrp,
                                struct cgroup_iter *it)
{
        struct list_head *l = it->cg_link;
        struct cg_cgroup_link *link;
        struct css_set *cg;

        /* Advance to the next non-empty css_set */
        do {
                l = l->next;
                if (l == &cgrp->css_sets) {
                        it->cg_link = NULL;
                        return;
                }
                link = list_entry(l, struct cg_cgroup_link, cgrp_link_list);
                cg = link->cg;
        } while (list_empty(&cg->tasks));
        it->cg_link = l;
        it->task = cg->tasks.next;
}

/*
 * To reduce the fork() overhead for systems that are not actually
 * using their cgroups capability, we don't maintain the lists running
 * through each css_set to its tasks until we see the list actually
 * used - in other words after the first call to cgroup_iter_start().
 */
static void cgroup_enable_task_cg_lists(void)
{
        struct task_struct *p, *g;
        write_lock(&css_set_lock);
        use_task_css_set_links = 1;
        /*
         * We need tasklist_lock because RCU is not safe against
         * while_each_thread(). Besides, a forking task that has passed
         * cgroup_post_fork() without seeing use_task_css_set_links = 1
         * is not guaranteed to have its child immediately visible in the
         * tasklist if we walk through it with RCU.
         */
        read_lock(&tasklist_lock);
        do_each_thread(g, p) {
                task_lock(p);
                /*
                 * We should check if the process is exiting, otherwise
                 * it will race with cgroup_exit() in that the list
                 * entry won't be deleted though the process has exited.
                 */
                if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
                        list_add(&p->cg_list, &p->cgroups->tasks);
                task_unlock(p);
        } while_each_thread(g, p);
        read_unlock(&tasklist_lock);
        write_unlock(&css_set_lock);
}

void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it)
        __acquires(css_set_lock)
{
        /*
         * The first time anyone tries to iterate across a cgroup,
         * we need to enable the list linking each css_set to its
         * tasks, and fix up all existing tasks.
         */
        if (!use_task_css_set_links)
                cgroup_enable_task_cg_lists();

        read_lock(&css_set_lock);
        it->cg_link = &cgrp->css_sets;
        cgroup_advance_iter(cgrp, it);
}

struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
                                        struct cgroup_iter *it)
{
        struct task_struct *res;
        struct list_head *l = it->task;
        struct cg_cgroup_link *link;

        /* If the iterator cg is NULL, we have no tasks */
        if (!it->cg_link)
                return NULL;
        res = list_entry(l, struct task_struct, cg_list);
        /* Advance iterator to find next entry */
        l = l->next;
        link = list_entry(it->cg_link, struct cg_cgroup_link, cgrp_link_list);
        if (l == &link->cg->tasks) {
                /* We reached the end of this task list - move on to
                 * the next cg_cgroup_link */
                cgroup_advance_iter(cgrp, it);
        } else {
                it->task = l;
        }
        return res;
}

void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it)
        __releases(css_set_lock)
{
        read_unlock(&css_set_lock);
}

static inline int started_after_time(struct task_struct *t1,
                                     struct timespec *time,
                                     struct task_struct *t2)
{
        int start_diff = timespec_compare(&t1->start_time, time);
        if (start_diff > 0) {
                return 1;
        } else if (start_diff < 0) {
                return 0;
        } else {
                /*
                 * Arbitrarily, if two processes started at the same
                 * time, we'll say that the lower pointer value
                 * started first. Note that t2 may have exited by now
                 * so this may not be a valid pointer any longer, but
                 * that's fine - it still serves to distinguish
                 * between two tasks started (effectively) simultaneously.
                 */
                return t1 > t2;
        }
}

/*
 * This function is a callback from heap_insert() and is used to order
 * the heap.
 * In this case we order the heap in descending task start time.
 */
static inline int started_after(void *p1, void *p2)
{
        struct task_struct *t1 = p1;
        struct task_struct *t2 = p2;
        return started_after_time(t1, &t2->start_time, t2);
}

/**
 * cgroup_scan_tasks - iterate though all the tasks in a cgroup
 * @scan: struct cgroup_scanner containing arguments for the scan
 *
 * Arguments include pointers to callback functions test_task() and
 * process_task().
 * Iterate through all the tasks in a cgroup, calling test_task() for each,
 * and if it returns true, call process_task() for it also.
 * The test_task pointer may be NULL, meaning always true (select all tasks).
 * Effectively duplicates cgroup_iter_{start,next,end}()
 * but does not lock css_set_lock for the call to process_task().
 * The struct cgroup_scanner may be embedded in any structure of the caller's
 * creation.
 * It is guaranteed that process_task() will act on every task that
 * is a member of the cgroup for the duration of this call. This
 * function may or may not call process_task() for tasks that exit
 * or move to a different cgroup during the call, or are forked or
 * move into the cgroup during the call.
 *
 * Note that test_task() may be called with locks held, and may in some
 * situations be called multiple times for the same task, so it should
 * be cheap.
 * If the heap pointer in the struct cgroup_scanner is non-NULL, a heap has been
 * pre-allocated and will be used for heap operations (and its "gt" member will
 * be overwritten), else a temporary heap will be used (allocation of which
 * may cause this function to fail).
 */
int cgroup_scan_tasks(struct cgroup_scanner *scan)
{
        int retval, i;
        struct cgroup_iter it;
        struct task_struct *p, *dropped;
        /* Never dereference latest_task, since it's not refcounted */
        struct task_struct *latest_task = NULL;
        struct ptr_heap tmp_heap;
        struct ptr_heap *heap;
        struct timespec latest_time = { 0, 0 };

        if (scan->heap) {
                /* The caller supplied our heap and pre-allocated its memory */
                heap = scan->heap;
                heap->gt = &started_after;
        } else {
                /* We need to allocate our own heap memory */
                heap = &tmp_heap;
                retval = heap_init(heap, PAGE_SIZE, GFP_KERNEL, &started_after);
                if (retval)
                        /* cannot allocate the heap */
                        return retval;
        }

 again:
        /*
         * Scan tasks in the cgroup, using the scanner's "test_task" callback
         * to determine which are of interest, and using the scanner's
         * "process_task" callback to process any of them that need an update.
         * Since we don't want to hold any locks during the task updates,
         * gather tasks to be processed in a heap structure.
         * The heap is sorted by descending task start time.
         * If the statically-sized heap fills up, we overflow tasks that
         * started later, and in future iterations only consider tasks that
         * started after the latest task in the previous pass. This
         * guarantees forward progress and that we don't miss any tasks.
         */
        heap->size = 0;
        cgroup_iter_start(scan->cg, &it);
        while ((p = cgroup_iter_next(scan->cg, &it))) {
                /*
                 * Only affect tasks that qualify per the caller's callback,
                 * if he provided one
                 */
                if (scan->test_task && !scan->test_task(p, scan))
                        continue;
                /*
                 * Only process tasks that started after the last task
                 * we processed
                 */
                if (!started_after_time(p, &latest_time, latest_task))
                        continue;
                dropped = heap_insert(heap, p);
                if (dropped == NULL) {
                        /*
                         * The new task was inserted; the heap wasn't
                         * previously full
                         */
                        get_task_struct(p);
                } else if (dropped != p) {
                        /*
                         * The new task was inserted, and pushed out a
                         * different task
                         */
                        get_task_struct(p);
                        put_task_struct(dropped);
                }
                /*
                 * Else the new task was newer than anything already in
                 * the heap and wasn't inserted
                 */
        }
        cgroup_iter_end(scan->cg, &it);

        if (heap->size) {
                for (i = 0; i < heap->size; i++) {
                        struct task_struct *q = heap->ptrs[i];
                        if (i == 0) {
                                latest_time = q->start_time;
                                latest_task = q;
                        }
                        /* Process the task per the caller's callback */
                        scan->process_task(q, scan);
                        put_task_struct(q);
                }
                /*
                 * If we had to process any tasks at all, scan again
                 * in case some of them were in the middle of forking
                 * children that didn't get processed.
                 * Not the most efficient way to do it, but it avoids
                 * having to take callback_mutex in the fork path
                 */
                goto again;
        }
        if (heap == &tmp_heap)
                heap_free(&tmp_heap);
        return 0;
}

/*
 * Stuff for reading the 'tasks'/'procs' files.
 *
 * Reading this file can return large amounts of data if a cgroup has
 * *lots* of attached tasks. So it may need several calls to read(),
 * but we cannot guarantee that the information we produce is correct
 * unless we produce it entirely atomically.
 *
 */

/* which pidlist file are we talking about? */
enum cgroup_filetype {
        CGROUP_FILE_PROCS,
        CGROUP_FILE_TASKS,
};

/*
 * A pidlist is a list of pids that virtually represents the contents of one
 * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists,
 * a pair (one each for procs, tasks) for each pid namespace that's relevant
 * to the cgroup.
 */
struct cgroup_pidlist {
        /*
         * used to find which pidlist is wanted. doesn't change as long as
         * this particular list stays in the list.
        */
        struct { enum cgroup_filetype type; struct pid_namespace *ns; } key;
        /* array of xids */
        pid_t *list;
        /* how many elements the above list has */
        int length;
        /* how many files are using the current array */
        int use_count;
        /* each of these stored in a list by its cgroup */
        struct list_head links;
        /* pointer to the cgroup we belong to, for list removal purposes */
        struct cgroup *owner;
        /* protects the other fields */
        struct rw_semaphore mutex;
};

/*
 * The following two functions "fix" the issue where there are more pids
 * than kmalloc will give memory for; in such cases, we use vmalloc/vfree.
 * TODO: replace with a kernel-wide solution to this problem
 */
#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2))
static void *pidlist_allocate(int count)
{
        if (PIDLIST_TOO_LARGE(count))
                return vmalloc(count * sizeof(pid_t));
        else
                return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
}
static void pidlist_free(void *p)
{
        if (is_vmalloc_addr(p))
                vfree(p);
        else
                kfree(p);
}
static void *pidlist_resize(void *p, int newcount)
{
        void *newlist;
        /* note: if new alloc fails, old p will still be valid either way */
        if (is_vmalloc_addr(p)) {
                newlist = vmalloc(newcount * sizeof(pid_t));
                if (!newlist)
                        return NULL;
                memcpy(newlist, p, newcount * sizeof(pid_t));
                vfree(p);
        } else {
                newlist = krealloc(p, newcount * sizeof(pid_t), GFP_KERNEL);
        }
        return newlist;
}

/*
 * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
 * If the new stripped list is sufficiently smaller and there's enough memory
 * to allocate a new buffer, will let go of the unneeded memory. Returns the
 * number of unique elements.
 */
/* is the size difference enough that we should re-allocate the array? */
#define PIDLIST_REALLOC_DIFFERENCE(old, new) ((old) - PAGE_SIZE >= (new))
static int pidlist_uniq(pid_t **p, int length)
{
        int src, dest = 1;
        pid_t *list = *p;
        pid_t *newlist;

        /*
         * we presume the 0th element is unique, so i starts at 1. trivial
         * edge cases first; no work needs to be done for either
         */
        if (length == 0 || length == 1)
                return length;
        /* src and dest walk down the list; dest counts unique elements */
        for (src = 1; src < length; src++) {
                /* find next unique element */
                while (list[src] == list[src-1]) {
                        src++;
                        if (src == length)
                                goto after;
                }
                /* dest always points to where the next unique element goes */
                list[dest] = list[src];
                dest++;
        }
after:
        /*
         * if the length difference is large enough, we want to allocate a
         * smaller buffer to save memory. if this fails due to out of memory,
         * we'll just stay with what we've got.
         */
        if (PIDLIST_REALLOC_DIFFERENCE(length, dest)) {
                newlist = pidlist_resize(list, dest);
                if (newlist)
                        *p = newlist;
        }
        return dest;
}

static int cmppid(const void *a, const void *b)
{
        return *(pid_t *)a - *(pid_t *)b;
}

/*
 * find the appropriate pidlist for our purpose (given procs vs tasks)
 * returns with the lock on that pidlist already held, and takes care
 * of the use count, or returns NULL with no locks held if we're out of
 * memory.
 */
static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
                                                  enum cgroup_filetype type)
{
        struct cgroup_pidlist *l;
        /* don't need task_nsproxy() if we're looking at ourself */
        struct pid_namespace *ns = current->nsproxy->pid_ns;

        /*
         * We can't drop the pidlist_mutex before taking the l->mutex in case
         * the last ref-holder is trying to remove l from the list at the same
         * time. Holding the pidlist_mutex precludes somebody taking whichever
         * list we find out from under us - compare release_pid_array().
         */
        mutex_lock(&cgrp->pidlist_mutex);
        list_for_each_entry(l, &cgrp->pidlists, links) {
                if (l->key.type == type && l->key.ns == ns) {
                        /* make sure l doesn't vanish out from under us */
                        down_write(&l->mutex);
                        mutex_unlock(&cgrp->pidlist_mutex);
                        return l;
                }
        }
        /* entry not found; create a new one */
        l = kmalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
        if (!l) {
                mutex_unlock(&cgrp->pidlist_mutex);
                return l;
        }
        init_rwsem(&l->mutex);
        down_write(&l->mutex);
        l->key.type = type;
        l->key.ns = get_pid_ns(ns);
        l->use_count = 0; /* don't increment here */
        l->list = NULL;
        l->owner = cgrp;
        list_add(&l->links, &cgrp->pidlists);
        mutex_unlock(&cgrp->pidlist_mutex);
        return l;
}

/*
 * Load a cgroup's pidarray with either procs' tgids or tasks' pids
 */
static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
                              struct cgroup_pidlist **lp)
{
        pid_t *array;
        int length;
        int pid, n = 0; /* used for populating the array */
        struct cgroup_iter it;
        struct task_struct *tsk;
        struct cgroup_pidlist *l;

        /*
         * If cgroup gets more users after we read count, we won't have
         * enough space - tough.  This race is indistinguishable to the
         * caller from the case that the additional cgroup users didn't
         * show up until sometime later on.
         */
        length = cgroup_task_count(cgrp);
        array = pidlist_allocate(length);
        if (!array)
                return -ENOMEM;
        /* now, populate the array */
        cgroup_iter_start(cgrp, &it);
        while ((tsk = cgroup_iter_next(cgrp, &it))) {
                if (unlikely(n == length))
                        break;
                /* get tgid or pid for procs or tasks file respectively */
                if (type == CGROUP_FILE_PROCS)
                        pid = task_tgid_vnr(tsk);
                else
                        pid = task_pid_vnr(tsk);
                if (pid > 0) /* make sure to only use valid results */
                        array[n++] = pid;
        }
        cgroup_iter_end(cgrp, &it);
        length = n;
        /* now sort & (if procs) strip out duplicates */
        sort(array, length, sizeof(pid_t), cmppid, NULL);
        if (type == CGROUP_FILE_PROCS)
                length = pidlist_uniq(&array, length);
        l = cgroup_pidlist_find(cgrp, type);
        if (!l) {
                pidlist_free(array);
                return -ENOMEM;
        }
        /* store array, freeing old if necessary - lock already held */
        pidlist_free(l->list);
        l->list = array;
        l->length = length;
        l->use_count++;
        up_write(&l->mutex);
        *lp = l;
        return 0;
}

/**
 * cgroupstats_build - build and fill cgroupstats
 * @stats: cgroupstats to fill information into
 * @dentry: A dentry entry belonging to the cgroup for which stats have
 * been requested.
 *
 * Build and fill cgroupstats so that taskstats can export it to user
 * space.
 */
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
{
        int ret = -EINVAL;
        struct cgroup *cgrp;
        struct cgroup_iter it;
        struct task_struct *tsk;

        /*
         * Validate dentry by checking the superblock operations,
         * and make sure it's a directory.
         */
        if (dentry->d_sb->s_op != &cgroup_ops ||
            !S_ISDIR(dentry->d_inode->i_mode))
                 goto err;

        ret = 0;
        cgrp = dentry->d_fsdata;

        cgroup_iter_start(cgrp, &it);
        while ((tsk = cgroup_iter_next(cgrp, &it))) {
                switch (tsk->state) {
                case TASK_RUNNING:
                        stats->nr_running++;
                        break;
                case TASK_INTERRUPTIBLE:
                        stats->nr_sleeping++;
                        break;
                case TASK_UNINTERRUPTIBLE:
                        stats->nr_uninterruptible++;
                        break;
                case TASK_STOPPED:
                        stats->nr_stopped++;
                        break;
                default:
                        if (delayacct_is_task_wai