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/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/hashtable.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/flex_array.h> /* used in cgroup_attach_task */
#include <linux/kthread.h>

#include <linux/atomic.h>

/*
 * pidlists linger the following amount before being destroyed.  The goal
 * is avoiding frequent destruction in the middle of consecutive read calls
 * Expiring in the middle is a performance problem not a correctness one.
 * 1 sec should be enough.
 */
#define CGROUP_PIDLIST_DESTROY_DELAY	HZ

/*
 * 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.
 */
#ifdef CONFIG_PROVE_RCU
DEFINE_MUTEX(cgroup_mutex);
EXPORT_SYMBOL_GPL(cgroup_mutex);	/* only for lockdep */
#else
static DEFINE_MUTEX(cgroup_mutex);
#endif

static DEFINE_MUTEX(cgroup_root_mutex);

/*
 * cgroup destruction makes heavy use of work items and there can be a lot
 * of concurrent destructions.  Use a separate workqueue so that cgroup
 * destruction work items don't end up filling up max_active of system_wq
 * which may lead to deadlock.
 */
static struct workqueue_struct *cgroup_destroy_wq;

/*
 * pidlist destructions need to be flushed on cgroup destruction.  Use a
 * separate workqueue as flush domain.
 */
static struct workqueue_struct *cgroup_pidlist_destroy_wq;

/*
 * 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 *cgroup_subsys[CGROUP_SUBSYS_COUNT] = {
#include <linux/cgroup_subsys.h>
};

/*
 * 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 cgroup_dummy_root;

/* dummy_top is a shorthand for the dummy hierarchy's top cgroup */
static struct cgroup * const cgroup_dummy_top = &cgroup_dummy_root.top_cgroup;

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

	/* file xattrs */
	struct simple_xattrs		xattrs;
};

/* The list of hierarchy roots */

static LIST_HEAD(cgroup_roots);
static int cgroup_root_count;

/*
 * Hierarchy ID allocation and mapping.  It follows the same exclusion
 * rules as other root ops - both cgroup_mutex and cgroup_root_mutex for
 * writes, either for reads.
 */
static DEFINE_IDR(cgroup_hierarchy_idr);

static struct cgroup_name root_cgroup_name = { .name = "/" };

/*
 * Assign a monotonically increasing serial number to cgroups.  It
 * guarantees cgroups with bigger numbers are newer than those with smaller
 * numbers.  Also, as cgroups are always appended to the parent's
 * ->children list, it guarantees that sibling cgroups are always sorted in
 * the ascending serial number order on the list.  Protected by
 * cgroup_mutex.
 */
static u64 cgroup_serial_nr_next = 1;

/* 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;

static struct cftype cgroup_base_files[];

static void cgroup_destroy_css_killed(struct cgroup *cgrp);
static int cgroup_destroy_locked(struct cgroup *cgrp);
static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
			      bool is_add);
static int cgroup_file_release(struct inode *inode, struct file *file);
static void cgroup_pidlist_destroy_all(struct cgroup *cgrp);

/**
 * cgroup_css - obtain a cgroup's css for the specified subsystem
 * @cgrp: the cgroup of interest
 * @ss: the subsystem of interest (%NULL returns the dummy_css)
 *
 * Return @cgrp's css (cgroup_subsys_state) associated with @ss.  This
 * function must be called either under cgroup_mutex or rcu_read_lock() and
 * the caller is responsible for pinning the returned css if it wants to
 * keep accessing it outside the said locks.  This function may return
 * %NULL if @cgrp doesn't have @subsys_id enabled.
 */
static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
					      struct cgroup_subsys *ss)
{
	if (ss)