include/net/flow.h


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226

/*
 *
 *	Generic internet FLOW.
 *
 */

#ifndef _NET_FLOW_H
#define _NET_FLOW_H

#include <linux/socket.h>
#include <linux/in6.h>
#include <linux/atomic.h>

struct flowi_common {
	int	flowic_oif;
	int	flowic_iif;
	__u32	flowic_mark;
	__u8	flowic_tos;
	__u8	flowic_scope;
	__u8	flowic_proto;
	__u8	flowic_flags;
#define FLOWI_FLAG_ANYSRC		0x01
#define FLOWI_FLAG_PRECOW_METRICS	0x02
#define FLOWI_FLAG_CAN_SLEEP		0x04
	__u32	flowic_secid;
};

union flowi_uli {
	struct {
		__be16	dport;
		__be16	sport;
	} ports;

	struct {
		__u8	type;
		__u8	code;
	} icmpt;

	struct {
		__le16	dport;
		__le16	sport;
	} dnports;

	__be32		spi;
	__be32		gre_key;

	struct {
		__u8	type;
	} mht;
};

struct flowi4 {
	struct flowi_common	__fl_common;
#define flowi4_oif		__fl_common.flowic_oif
#define flowi4_iif		__fl_common.flowic_iif
#define flowi4_mark		__fl_common.flowic_mark
#define flowi4_tos		__fl_common.flowic_tos
#define flowi4_scope		__fl_common.flowic_scope
#define flowi4_proto		__fl_common.flowic_proto
#define flowi4_flags		__fl_common.flowic_flags
#define flowi4_secid		__fl_common.flowic_secid

	/* (saddr,daddr) must be grouped, same order as in IP header */
	__be32			saddr;
	__be32			daddr;

	union flowi_uli		uli;
#define fl4_sport		uli.ports.sport
#define fl4_dport		uli.ports.dport
#define fl4_icmp_type		uli.icmpt.type
#define fl4_icmp_code		uli.icmpt.code
#define fl4_ipsec_spi		uli.spi
#define fl4_mh_type		uli.mht.type
#define fl4_gre_key		uli.gre_key
} __attribute__((__aligned__(BITS_PER_LONG/8)));

static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
				      __u32 mark, __u8 tos, __u8 scope,
				      __u8 proto, __u8 flags,
				      __be32 daddr, __be32 saddr,
				      __be16 dport, __be16 sport)
{
	fl4->flowi4_oif = oif;
	fl4->flowi4_iif = 0;
	fl4->flowi4_mark = mark;
	fl4->flowi4_tos = tos;
	fl4->flowi4_scope = scope;
	fl4->flowi4_proto = proto;
	fl4->flowi4_flags = flags;
	fl4->flowi4_secid = 0;
	fl4->daddr = daddr;
	fl4->saddr = saddr;
	fl4->fl4_dport = dport;
	fl4->fl4_sport = sport;
}

/* Reset some input parameters after previous lookup */
static inline void flowi4_update_output(struct flowi4 *fl4, int oif, __u8 tos,
					__be32 daddr, __be32 saddr)
{
	fl4->flowi4_oif = oif;
	fl4->flowi4_tos = tos;
	fl4->daddr = daddr;
	fl4->saddr = saddr;
}
				      

struct flowi6 {
	struct flowi_common	__fl_common;
#define flowi6_oif		__fl_common.flowic_oif
#define flowi6_iif		__fl_common.flowic_iif
#define flowi6_mark		__fl_common.flowic_mark
#define flowi6_tos		__fl_common.flowic_tos
#define flowi6_scope		__fl_common.flowic_scope
#define flowi6_proto		__fl_common.flowic_proto
#define flowi6_flags		__fl_common.flowic_flags
#define flowi6_secid		__fl_common.flowic_secid
	struct in6_addr		daddr;
	struct in6_addr		saddr;
	__be32			flowlabel;
	union flowi_uli		uli;
#define fl6_sport		uli.ports.sport
#define fl6_dport		uli.ports.dport
#define fl6_icmp_type		uli.icmpt.type
#define fl6_icmp_code		uli.icmpt.code
#define fl6_ipsec_spi		uli.spi
#define fl6_mh_type		uli.mht.type
#define fl6_gre_key		uli.gre_key
} __attribute__((__aligned__(BITS_PER_LONG/8)));

struct flowidn {
	struct flowi_common	__fl_common;
#define flowidn_oif		__fl_common.flowic_oif
#define flowidn_iif		__fl_common.flowic_iif
#define flowidn_mark		__fl_common.flowic_mark
#define flowidn_scope		__fl_common.flowic_scope
#define flowidn_proto		__fl_common.flowic_proto
#define flowidn_flags		__fl_common.flowic_flags
	__le16			daddr;
	__le16			saddr;
	union flowi_uli		uli;
#define fld_sport		uli.ports.sport
#define fld_dport		uli.ports.dport
} __attribute__((__aligned__(BITS_PER_LONG/8)));

struct flowi {
	union {
		struct flowi_common	__fl_common;
		struct flowi4		ip4;
		struct flowi6		ip6;
		struct flowidn		dn;
	} u;
#define flowi_oif	u.__fl_common.flowic_oif
#define flowi_iif	u.__fl_common.flowic_iif
#define flowi_mark	u.__fl_common.flowic_mark
#define flowi_tos	u.__fl_common.flowic_tos
#define flowi_scope	u.__fl_common.flowic_scope
#define flowi_proto	u.__fl_common.flowic_proto
#define flowi_flags	u.__fl_common.flowic_flags
#define flowi_secid	u.__fl_common.flowic_secid
} __attribute__((__aligned__(BITS_PER_LONG/8)));

static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
{
	return container_of(fl4, struct flowi, u.ip4);
}

static inline struct flowi *flowi6_to_flowi(struct flowi6 *fl6)
{
	return container_of(fl6, struct flowi, u.ip6);
}

static inline struct flowi *flowidn_to_flowi(struct flowidn *fldn)
{
	return container_of(fldn, struct flowi, u.dn);
}

typedef unsigned long flow_compare_t;

static inline size_t flow_key_size(u16 family)
{
	switch (family) {
	case AF_INET:
		BUILD_BUG_ON(sizeof(struct flowi4) % sizeof(flow_compare_t));
		return sizeof(struct flowi4) / sizeof(flow_compare_t);
	case AF_INET6:
		BUILD_BUG_ON(sizeof(struct flowi6) % sizeof(flow_compare_t));
		return sizeof(struct flowi6) / sizeof(flow_compare_t);
	case AF_DECnet:
		BUILD_BUG_ON(sizeof(struct flowidn) % sizeof(flow_compare_t));
		return sizeof(struct flowidn) / sizeof(flow_compare_t);
	}
	return 0;
}

#define FLOW_DIR_IN	0
#define FLOW_DIR_OUT	1
#define FLOW_DIR_FWD	2

struct net;
struct sock;
struct flow_cache_ops;

struct flow_cache_object {
	const struct flow_cache_ops *ops;
};

struct flow_cache_ops {
	struct flow_cache_object *(*get)(struct flow_cache_object *);
	int (*check)(struct flow_cache_object *);
	void (*delete)(struct flow_cache_object *);
};

typedef struct flow_cache_object *(*flow_resolve_t)(
		struct net *net, const struct flowi *key, u16 family,
		u8 dir, struct flow_cache_object *oldobj, void *ctx);

extern struct flow_cache_object *flow_cache_lookup(
		struct net *net, const struct flowi *key, u16 family,
		u8 dir, flow_resolve_t resolver, void *ctx);

extern void flow_cache_flush(void);
extern void flow_cache_flush_deferred(void);
extern atomic_t flow_cache_genid;

#endif
/*
 *  kernel/cpuset.c
 *
 *  Processor and Memory placement constraints for sets of tasks.
 *
 *  Copyright (C) 2003 BULL SA.
 *  Copyright (C) 2004-2006 Silicon Graphics, Inc.
 *  Copyright (C) 2006 Google, Inc
 *
 *  Portions derived from Patrick Mochel's sysfs code.
 *  sysfs is Copyright (c) 2001-3 Patrick Mochel
 *
 *  2003-10-10 Written by Simon Derr.
 *  2003-10-22 Updates by Stephen Hemminger.
 *  2004 May-July Rework by Paul Jackson.
 *  2006 Rework by Paul Menage to use generic cgroups
 *
 *  This file is subject to the terms and conditions of the GNU General Public
 *  License.  See the file COPYING in the main directory of the Linux
 *  distribution for more details.
 */

#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/cpuset.h>
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/kmod.h>
#include <linux/list.h>
#include <linux/mempolicy.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/time.h>
#include <linux/backing-dev.h>
#include <linux/sort.h>

#include <asm/uaccess.h>
#include <asm/atomic.h>
#include <linux/mutex.h>

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

/* Retrieve the cpuset from a cgroup */
struct cgroup_subsys cpuset_subsys;
struct cpuset;

/* See "Frequency meter" comments, below. */

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

struct cpuset {
	struct cgroup_subsys_state css;

	unsigned long flags;		/* "unsigned long" so bitops work */
	cpumask_t cpus_allowed;		/* CPUs allowed to tasks in cpuset */
	nodemask_t mems_allowed;	/* Memory Nodes allowed to tasks */

	struct cpuset *parent;		/* my parent */

	/*
	 * Copy of global cpuset_mems_generation as of the most
	 * recent time this cpuset changed its mems_allowed.
	 */
	int mems_generation;

	struct fmeter fmeter;		/* memory_pressure filter */
};

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

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


/* bits in struct cpuset flags field */
typedef enum {
	CS_CPU_EXCLUSIVE,
	CS_MEM_EXCLUSIVE,
	CS_MEMORY_MIGRATE,
	CS_SPREAD_PAGE,
	CS_SPREAD_SLAB,
} cpuset_flagbits_t;

/* convenient tests for these bits */
static inline int is_cpu_exclusive(const struct cpuset *cs)
{
	return test_bit(CS_CPU_EXCLUSIVE, &cs->flags);
}

static inline int is_mem_exclusive(const struct cpuset *cs)
{
	return test_bit(CS_MEM_EXCLUSIVE, &cs->flags);
}

static inline int is_memory_migrate(const struct cpuset *cs)
{
	return test_bit(CS_MEMORY_MIGRATE, &cs->flags);
}

static inline int is_spread_page(const struct cpuset *cs)
{
	return test_bit(CS_SPREAD_PAGE, &cs->flags);
}

static inline int is_spread_slab(const struct cpuset *cs)
{
	return test_bit(CS_SPREAD_SLAB, &cs->flags);
}

/*
 * Increment this integer everytime any cpuset changes its
 * mems_allowed value.  Users of cpusets can track this generation
 * number, and avoid having to lock and reload mems_allowed unless
 * the cpuset they're using changes generation.
 *
 * A single, global generation is needed because attach_task() could
 * reattach a task to a different cpuset, which must not have its
 * generation numbers aliased with those of that tasks previous cpuset.
 *
 * Generations are needed for mems_allowed because one task cannot
 * modify anothers memory placement.  So we must enable every task,
 * on every visit to __alloc_pages(), to efficiently check whether
 * its current->cpuset->mems_allowed has changed, requiring an update
 * of its current->mems_allowed.
 *
 * Since cpuset_mems_generation is guarded by manage_mutex,
 * there is no need to mark it atomic.
 */
static int cpuset_mems_generation;

static struct cpuset top_cpuset = {
	.flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)),
	.cpus_allowed = CPU_MASK_ALL,
	.mems_allowed = NODE_MASK_ALL,
};

/*
 * We have two global cpuset mutexes below.  They can nest.
 * It is ok to first take manage_mutex, then nest callback_mutex.  We also
 * require taking task_lock() when dereferencing a tasks cpuset pointer.
 * See "The task_lock() exception", at the end of this comment.
 *
 * A task must hold both mutexes to modify cpusets.  If a task
 * holds manage_mutex, then it blocks others wanting that mutex,
 * ensuring that it is the only task able to also acquire callback_mutex
 * and be able to modify cpusets.  It can perform various checks on
 * the cpuset structure first, knowing nothing will change.  It can
 * also allocate memory while just holding manage_mutex.  While it is
 * performing these checks, various callback routines can briefly
 * acquire callback_mutex to query cpusets.  Once it is ready to make
 * the changes, it takes callback_mutex, blocking everyone else.
 *
 * Calls to the kernel memory allocator can not be made while holding
 * callback_mutex, as that would risk double tripping on callback_mutex
 * from one of the callbacks into the cpuset code from within
 * __alloc_pages().
 *
 * If a task is only holding callback_mutex, then it has read-only
 * access to cpusets.
 *
 * The task_struct fields mems_allowed and mems_generation may only
 * be accessed in the context of that task, so require no locks.
 *
 * Any task can increment and decrement the count field without lock.
 * So in general, code holding manage_mutex or callback_mutex can't rely
 * on the count field not changing.  However, if the count goes to
 * zero, then only attach_task(), which holds both mutexes, 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 cpuset can fork (the other way to increment the count).
 * So code holding manage_mutex or callback_mutex can safely assume that
 * if the count is zero, it will stay zero.  Similarly, if a task
 * holds manage_mutex or callback_mutex on a cpuset with zero count, it
 * knows that the cpuset won't be removed, as cpuset_rmdir() needs
 * both of those mutexes.
 *
 * The cpuset_common_file_write handler for operations that modify
 * the cpuset hierarchy holds manage_mutex across the entire operation,
 * single threading all such cpuset modifications across the system.
 *
 * The cpuset_common_file_read() handlers only hold callback_mutex across
 * small pieces of code, such as when reading out possibly multi-word
 * cpumasks and nodemasks.
 *
 * The fork and exit callbacks cpuset_fork() and cpuset_exit(), don't
 * (usually) take either mutex.  These are the two most performance
 * critical pieces of code here.  The exception occurs on cpuset_exit(),
 * when a task in a notify_on_release cpuset exits.  Then manage_mutex
 * is taken, and if the cpuset count is zero, a usermode call made
 * to /sbin/cpuset_release_agent with the name of the cpuset (path
 * relative to the root of cpuset file system) as the argument.
 *
 * A cpuset can only be deleted if both its 'count' of using tasks
 * is zero, and its list of 'children' cpusets is empty.  Since all
 * tasks in the system use _some_ cpuset, and since there is always at
 * least one task in the system (init), therefore, top_cpuset
 * always has either children cpusets and/or using tasks.  So we don't
 * need a special hack to ensure that top_cpuset cannot be deleted.
 *
 * The above "Tale of Two Semaphores" would be complete, but for:
 *
 *	The task_lock() exception
 *
 * The need for this exception arises from the action of attach_task(),
 * which overwrites one tasks cpuset pointer with another.  It does
 * so using both mutexes, however there are several performance
 * critical places that need to reference task->cpuset without the
 * expense of grabbing a system global mutex.  Therefore except as
 * noted below, when dereferencing or, as in attach_task(), modifying
 * a tasks cpuset 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 cpuset pointer by attach_task() and the
 * access of task->cpuset->mems_generation via that pointer in
 * the routine cpuset_update_task_memory_state().
 */

static DEFINE_MUTEX(callback_mutex);

/* This is ugly, but preserves the userspace API for existing cpuset
 * users. If someone tries to mount the "cpuset" filesystem, we
 * silently switch it to mount "cgroup" instead */
static int cpuset_get_sb(struct file_system_type *fs_type,
			 int flags, const char *unused_dev_name,
			 void *data, struct vfsmount *mnt)
{
	struct file_system_type *cgroup_fs = get_fs_type("cgroup");
	int ret = -ENODEV;
	if (cgroup_fs) {
		char mountopts[] =
			"cpuset,noprefix,"
			"release_agent=/sbin/cpuset_release_agent";
		ret = cgroup_fs->get_sb(cgroup_fs, flags,
					   unused_dev_name, mountopts, mnt);
		put_filesystem(cgroup_fs);
	}
	return ret;
}

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

/*
 * Return in *pmask the portion of a cpusets's cpus_allowed that
 * are online.  If none are online, walk up the cpuset hierarchy
 * until we find one that does have some online cpus.  If we get
 * all the way to the top and still haven't found any online cpus,
 * return cpu_online_map.  Or if passed a NULL cs from an exit'ing
 * task, return cpu_online_map.
 *
 * One way or another, we guarantee to return some non-empty subset
 * of cpu_online_map.
 *
 * Call with callback_mutex held.
 */

static void guarantee_online_cpus(const struct cpuset *cs, cpumask_t *pmask)
{
	while (cs && !cpus_intersects(cs->cpus_allowed, cpu_online_map))
		cs = cs->parent;
	if (cs)
		cpus_and(*pmask, cs->cpus_allowed, cpu_online_map);
	else
		*pmask = cpu_online_map;
	BUG_ON(!cpus_intersects(*pmask, cpu_online_map));
}

/*
 * Return in *pmask the portion of a cpusets's mems_allowed that
 * are online, with memory.  If none are online with memory, walk
 * up the cpuset hierarchy until we find one that does have some
 * online mems.  If we get all the way to the top and still haven't
 * found any online mems, return node_states[N_HIGH_MEMORY].
 *
 * One way or another, we guarantee to return some non-empty subset
 * of node_states[N_HIGH_MEMORY].
 *
 * Call with callback_mutex held.
 */

static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask)
{
	while (cs && !nodes_intersects(cs->mems_allowed,
					node_states[N_HIGH_MEMORY]))
		cs = cs->parent;
	if (cs)
		nodes_and(*pmask, cs->mems_allowed,
					node_states[N_HIGH_MEMORY]);
	else
		*pmask = node_states[N_HIGH_MEMORY];
	BUG_ON(!nodes_intersects(*pmask, node_states[N_HIGH_MEMORY]));
}

/**
 * cpuset_update_task_memory_state - update task memory placement
 *
 * If the current tasks cpusets mems_allowed changed behind our
 * backs, update current->mems_allowed, mems_generation and task NUMA
 * mempolicy to the new value.
 *
 * Task mempolicy is updated by rebinding it relative to the
 * current->cpuset if a task has its memory placement changed.
 * Do not call this routine if in_interrupt().
 *
 * Call without callback_mutex or task_lock() held.  May be
 * called with or without manage_mutex held.  Thanks in part to
 * 'the_top_cpuset_hack', the tasks cpuset pointer will never
 * be NULL.  This routine also might acquire callback_mutex and
 * current->mm->mmap_sem during call.
 *
 * Reading current->cpuset->mems_generation doesn't need task_lock
 * to guard the current->cpuset derefence, because it is guarded
 * from concurrent freeing of current->cpuset by attach_task(),
 * using RCU.
 *
 * The rcu_dereference() is technically probably not needed,
 * as I don't actually mind if I see a new cpuset pointer but
 * an old value of mems_generation.  However this really only
 * matters on alpha systems using cpusets heavily.  If I dropped
 * that rcu_dereference(), it would save them a memory barrier.
 * For all other arch's, rcu_dereference is a no-op anyway, and for
 * alpha systems not using cpusets, another planned optimization,
 * avoiding the rcu critical section for tasks in the root cpuset
 * which is statically allocated, so can't vanish, will make this
 * irrelevant.  Better to use RCU as intended, than to engage in
 * some cute trick to save a memory barrier that is impossible to
 * test, for alpha systems using cpusets heavily, which might not
 * even exist.
 *
 * This routine is needed to update the per-task mems_allowed data,
 * within the tasks context, when it is trying to allocate memory
 * (in various mm/mempolicy.c routines) and notices that some other
 * task has been modifying its cpuset.
 */

void cpuset_update_task_memory_state(void)
{
	int my_cpusets_mem_gen;
	struct task_struct *tsk = current;
	struct cpuset *cs;

	if (task_cs(tsk) == &top_cpuset) {
		/* Don't need rcu for top_cpuset.  It's never freed. */
		my_cpusets_mem_gen = top_cpuset.mems_generation;
	} else {
		rcu_read_lock();
		my_cpusets_mem_gen = task_cs(current)->mems_generation;
		rcu_read_unlock();
	}

	if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
		mutex_lock(&callback_mutex);
		task_lock(tsk);
		cs = task_cs(tsk); /* Maybe changed when task not locked */
		guarantee_online_mems(cs, &tsk->mems_allowed);
		tsk->cpuset_mems_generation = cs->mems_generation;
		if (is_spread_page(cs))
			tsk->flags |= PF_SPREAD_PAGE;
		else
			tsk->flags &= ~PF_SPREAD_PAGE;
		if (is_spread_slab(cs))
			tsk->flags |= PF_SPREAD_SLAB;
		else
			tsk->flags &= ~PF_SPREAD_SLAB;
		task_unlock(tsk);
		mutex_unlock(&callback_mutex);
		mpol_rebind_task(tsk, &tsk->mems_allowed);
	}
}

/*
 * is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q?
 *
 * One cpuset is a subset of another if all its allowed CPUs and
 * Memory Nodes are a subset of the other, and its exclusive flags
 * are only set if the other's are set.  Call holding manage_mutex.
 */

static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
{
	return	cpus_subset(p->cpus_allowed, q->cpus_allowed) &&
		nodes_subset(p->mems_allowed, q->mems_allowed) &&
		is_cpu_exclusive(p) <= is_cpu_exclusive(q) &&
		is_mem_exclusive(p) <= is_mem_exclusive(q);
}

/*
 * validate_change() - Used to validate that any proposed cpuset change
 *		       follows the structural rules for cpusets.
 *
 * If we replaced the flag and mask values of the current cpuset
 * (cur) with those values in the trial cpuset (trial), would
 * our various subset and exclusive rules still be valid?  Presumes
 * manage_mutex held.
 *
 * 'cur' is the address of an actual, in-use cpuset.  Operations
 * such as list traversal that depend on the actual address of the
 * cpuset in the list must use cur below, not trial.
 *
 * 'trial' is the address of bulk structure copy of cur, with
 * perhaps one or more of the fields cpus_allowed, mems_allowed,
 * or flags changed to new, trial values.
 *
 * Return 0 if valid, -errno if not.
 */

static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
{
	struct cgroup *cont;
	struct cpuset *c, *par;

	/* Each of our child cpusets must be a subset of us */
	list_for_each_entry(cont, &cur->css.cgroup->children, sibling) {
		if (!is_cpuset_subset(cgroup_cs(cont), trial))
			return -EBUSY;
	}

	/* Remaining checks don't apply to root cpuset */
	if (cur == &top_cpuset)
		return 0;

	par = cur->parent;

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

	/* If either I or some sibling (!= me) is exclusive, we can't overlap */
	list_for_each_entry(cont, &par->css.cgroup->children, sibling) {
		c = cgroup_cs(cont);
		if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
		    c != cur &&
		    cpus_intersects(trial->cpus_allowed, c->cpus_allowed))
			return -EINVAL;
		if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
		    c != cur &&
		    nodes_intersects(trial->mems_allowed, c->mems_allowed))
			return -EINVAL;
	}

	return 0;
}

/*
 * Call with manage_mutex held.  May take callback_mutex during call.
 */

static int update_cpumask(struct cpuset *cs, char *buf)
{
	struct cpuset trialcs;
	int retval;

	/* top_cpuset.cpus_allowed tracks cpu_online_map; it's read-only */
	if (cs == &top_cpuset)
		return -EACCES;

	trialcs = *cs;

	/*
	 * We allow a cpuset's cpus_allowed to be empty; if it has attached
	 * tasks, we'll catch it later when we validate the change and return
	 * -ENOSPC.
	 */
	if (!buf[0] || (buf[0] == '\n' && !buf[1])) {
		cpus_clear(trialcs.cpus_allowed);
	} else {
		retval = cpulist_parse(buf, trialcs.cpus_allowed);
		if (retval < 0)
			return retval;
	}
	cpus_and(trialcs.cpus_allowed, trialcs.cpus_allowed, cpu_online_map);
	/* cpus_allowed cannot be empty for a cpuset with attached tasks. */
	if (cgroup_task_count(cs->css.cgroup) &&
	    cpus_empty(trialcs.cpus_allowed))
		return -ENOSPC;
	retval = validate_change(cs, &trialcs);
	if (retval < 0)
		return retval;
	mutex_lock(&callback_mutex);
	cs->cpus_allowed = trialcs.cpus_allowed;
	mutex_unlock(&callback_mutex);
	return 0;
}

/*
 * cpuset_migrate_mm
 *
 *    Migrate memory region from one set of nodes to another.
 *
 *    Temporarilly set tasks mems_allowed to target nodes of migration,
 *    so that the migration code can allocate pages on these nodes.
 *
 *    Call holding manage_mutex, so our current->cpuset won't change
 *    during this call, as manage_mutex holds off any attach_task()
 *    calls.  Therefore we don't need to take task_lock around the
 *    call to guarantee_online_mems(), as we know no one is changing
 *    our tasks cpuset.
 *
 *    Hold callback_mutex around the two modifications of our tasks
 *    mems_allowed to synchronize with cpuset_mems_allowed().
 *
 *    While the mm_struct we are migrating is typically from some
 *    other task, the task_struct mems_allowed that we are hacking
 *    is for our current task, which must allocate new pages for that
 *    migrating memory region.
 *
 *    We call cpuset_update_task_memory_state() before hacking
 *    our tasks mems_allowed, so that we are assured of being in
 *    sync with our tasks cpuset, and in particular, callbacks to
 *    cpuset_update_task_memory_state() from nested page allocations
 *    won't see any mismatch of our cpuset and task mems_generation
 *    values, so won't overwrite our hacked tasks mems_allowed
 *    nodemask.
 */

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

	cpuset_update_task_memory_state();

	mutex_lock(&callback_mutex);
	tsk->mems_allowed = *to;
	mutex_unlock(&callback_mutex);

	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);

	mutex_lock(&callback_mutex);
	guarantee_online_mems(task_cs(tsk),&tsk->mems_allowed);
	mutex_unlock(&callback_mutex);
}

/*
 * Handle user request to change the 'mems' memory placement
 * of a cpuset.  Needs to validate the request, update the
 * cpusets mems_allowed and mems_generation, and for each
 * task in the cpuset, rebind any vma mempolicies and if
 * the cpuset is marked 'memory_migrate', migrate the tasks
 * pages to the new memory.
 *
 * Call with manage_mutex held.  May take callback_mutex during call.
 * Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
 * lock each such tasks mm->mmap_sem, scan its vma's and rebind
 * their mempolicies to the cpusets new mems_allowed.
 */

static void *cpuset_being_rebound;

static int update_nodemask(struct cpuset *cs, char *buf)
{
	struct cpuset trialcs;
	nodemask_t oldmem;
	struct task_struct *p;
	struct mm_struct **mmarray;
	int i, n, ntasks;
	int migrate;
	int fudge;
	int retval;
	struct cgroup_iter it;

	/*
	 * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY];
	 * it's read-only
	 */
	if (cs == &top_cpuset)
		return -EACCES;

	trialcs = *cs;

	/*
	 * We allow a cpuset's mems_allowed to be empty; if it has attached
	 * tasks, we'll catch it later when we validate the change and return
	 * -ENOSPC.
	 */
	if (!buf[0] || (buf[0] == '\n' && !buf[1])) {
		nodes_clear(trialcs.mems_allowed);
	} else {
		retval = nodelist_parse(buf, trialcs.mems_allowed);
		if (retval < 0)
			goto done;
		if (!nodes_intersects(trialcs.mems_allowed,
						node_states[N_HIGH_MEMORY])) {
			/*
			 * error if only memoryless nodes specified.
			 */
			retval = -ENOSPC;
			goto done;
		}
	}
	/*
	 * Exclude memoryless nodes.  We know that trialcs.mems_allowed
	 * contains at least one node with memory.
	 */
	nodes_and(trialcs.mems_allowed, trialcs.mems_allowed,
						node_states[N_HIGH_MEMORY]);
	oldmem = cs->mems_allowed;
	if (nodes_equal(oldmem, trialcs.mems_allowed)) {
		retval = 0;		/* Too easy - nothing to do */
		goto done;
	}
	/* mems_allowed cannot be empty for a cpuset with attached tasks. */
	if (cgroup_task_count(cs->css.cgroup) &&
	    nodes_empty(trialcs.mems_allowed)) {
		retval = -ENOSPC;
		goto done;
	}
	retval = validate_change(cs, &trialcs);
	if (retval < 0)
		goto done;

	mutex_lock(&callback_mutex);
	cs->mems_allowed = trialcs.mems_allowed;
	cs->mems_generation = cpuset_mems_generation++;
	mutex_unlock(&callback_mutex);

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

	fudge = 10;				/* spare mmarray[] slots */
	fudge += cpus_weight(cs->cpus_allowed);	/* imagine one fork-bomb/cpu */
	retval = -ENOMEM;

	/*
	 * Allocate mmarray[] to hold mm reference for each task
	 * in cpuset cs.  Can't kmalloc GFP_KERNEL while holding
	 * tasklist_lock.  We could use GFP_ATOMIC, but with a
	 * few more lines of code, we can retry until we get a big
	 * enough mmarray[] w/o using GFP_ATOMIC.
	 */
	while (1) {
		ntasks = cgroup_task_count(cs->css.cgroup);  /* guess */
		ntasks += fudge;
		mmarray = kmalloc(ntasks * sizeof(*mmarray), GFP_KERNEL);
		if (!mmarray)
			goto done;
		read_lock(&tasklist_lock);		/* block fork */
		if (cgroup_task_count(cs->css.cgroup) <= ntasks)
			break;				/* got enough */
		read_unlock(&tasklist_lock);		/* try again */
		kfree(mmarray);
	}

	n = 0;

	/* Load up mmarray[] with mm reference for each task in cpuset. */
	cgroup_iter_start(cs->css.cgroup, &it);
	while ((p = cgroup_iter_next(cs->css.cgroup, &it))) {
		struct mm_struct *mm;

		if (n >= ntasks) {
			printk(KERN_WARNING
				"Cpuset mempolicy rebind incomplete.\n");
			break;
		}
		mm = get_task_mm(p);
		if (!mm)
			continue;
		mmarray[n++] = mm;
	}
	cgroup_iter_end(cs->css.cgroup, &it);
	read_unlock(&tasklist_lock);

	/*
	 * Now that we've dropped the tasklist spinlock, we can
	 * rebind the vma mempolicies of each mm in mmarray[] to their
	 * new cpuset, and release that mm.  The mpol_rebind_mm()
	 * call takes mmap_sem, which we couldn't take while holding
	 * tasklist_lock.  Forks can happen again now - the mpol_copy()
	 * cpuset_being_rebound check will catch such forks, and rebind
	 * their vma mempolicies too.  Because we still hold the global
	 * cpuset manage_mutex, we know that no other rebind effort will
	 * be contending for the global variable cpuset_being_rebound.
	 * It's ok if we rebind the same mm twice; mpol_rebind_mm()
	 * is idempotent.  Also migrate pages in each mm to new nodes.
	 */
	migrate = is_memory_migrate(cs);
	for (i = 0; i < n; i++) {
		struct mm_struct *mm = mmarray[i];

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

	/* We're done rebinding vma's to this cpusets new mems_allowed. */
	kfree(mmarray);
	cpuset_being_rebound = NULL;
	retval = 0;
done:
	return retval;
}

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

/*
 * Call with manage_mutex held.
 */

static int update_memory_pressure_enabled(struct cpuset *cs, char *buf)
{
	if (simple_strtoul(buf, NULL, 10) != 0)
		cpuset_memory_pressure_enabled = 1;
	else
		cpuset_memory_pressure_enabled = 0;
	return 0;
}

/*
 * update_flag - read a 0 or a 1 in a file and update associated flag
 * bit:	the bit to update (CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE,
 *				CS_NOTIFY_ON_RELEASE, CS_MEMORY_MIGRATE,
 *				CS_SPREAD_PAGE, CS_SPREAD_SLAB)
 * cs:	the cpuset to update
 * buf:	the buffer where we read the 0 or 1
 *
 * Call with manage_mutex held.
 */

static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf)
{
	int turning_on;
	struct cpuset trialcs;
	int err;

	turning_on = (simple_strtoul(buf, NULL, 10) != 0);

	trialcs = *cs;
	if (turning_on)
		set_bit(bit, &trialcs.flags);
	else
		clear_bit(bit, &trialcs.flags);

	err = validate_change(cs, &trialcs);
	if (err < 0)
		return err;
	mutex_lock(&callback_mutex);
	cs->flags = trialcs.flags;
	mutex_unlock(&callback_mutex);

	return 0;
}

/*
 * Frequency meter - How fast is some event occurring?
 *
 * These routines manage a digitally filtered, constant time based,
 * event frequency meter.  There are four routines:
 *   fmeter_init() - initialize a frequency meter.
 *   fmeter_markevent() - called each time the event happens.
 *   fmeter_getrate() - returns the recent rate of such events.
 *   fmeter_update() - internal routine used to update fmeter.
 *
 * A common data structure is passed to each of these routines,
 * which is used to keep track of the state required to manage the
 * frequency meter and its digital filter.
 *
 * The filter works on the number of events marked per unit time.
 * The filter is single-pole low-pass recursive (IIR).  The time unit
 * is 1 second.  Arithmetic is done using 32-bit integers scaled to
 * simulate 3 decimal digits of precision (multiplied by 1000).
 *
 * With an FM_COEF of 933, and a time base of 1 second, the filter
 * has a half-life of 10 seconds, meaning that if the events quit
 * happening, then the rate returned from the fmeter_getrate()
 * will be cut in half each 10 seconds, until it converges to zero.
 *
 * It is not worth doing a real infinitely recursive filter.  If more
 * than FM_MAXTICKS ticks have elapsed since the last filter event,
 * just compute FM_MAXTICKS ticks worth, by which point the level
 * will be stable.
 *
 * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid
 * arithmetic overflow in the fmeter_update() routine.
 *
 * Given the simple 32 bit integer arithmetic used, this meter works
 * best for reporting rates between one per millisecond (msec) and
 * one per 32 (approx) seconds.  At constant rates faster than one
 * per msec it maxes out at values just under 1,000,000.  At constant
 * rates between one per msec, and one per second it will stabilize
 * to a value N*1000, where N is the rate of events per second.
 * At constant rates between one per second and one per 32 seconds,
 * it will be choppy, moving up on the seconds that have an event,
 * and then decaying until the next event.  At rates slower than
 * about one in 32 seconds, it decays all the way back to zero between
 * each event.
 */

#define FM_COEF 933		/* coefficient for half-life of 10 secs */
#define FM_MAXTICKS ((time_t)99) /* useless computing more ticks than this */
#define FM_MAXCNT 1000000	/* limit cnt to avoid overflow */
#define FM_SCALE 1000		/* faux fixed point scale */

/* Initialize a frequency meter */
static void fmeter_init(struct fmeter *fmp)
{
	fmp->cnt = 0;
	fmp->val = 0;
	fmp->time = 0;
	spin_lock_init(&fmp->lock);
}

/* Internal meter update - process cnt events and update value */
static void fmeter_update(struct fmeter *fmp)
{
	time_t now = get_seconds();
	time_t ticks = now - fmp->time;

	if (ticks == 0)
		return;

	ticks = min(FM_MAXTICKS, ticks);
	while (ticks-- > 0)
		fmp->val = (FM_COEF * fmp->val) / FM_SCALE;
	fmp->time = now;

	fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE;
	fmp->cnt = 0;
}

/* Process any previous ticks, then bump cnt by one (times scale). */
static void fmeter_markevent(struct fmeter *fmp)
{
	spin_lock(&fmp->lock);
	fmeter_update(fmp);
	fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE);
	spin_unlock(&fmp->lock);
}

/* Process any previous ticks, then return current value. */
static int fmeter_getrate(struct fmeter *fmp)
{
	int val;

	spin_lock(&fmp->lock);
	fmeter_update(fmp);
	val = fmp->val;
	spin_unlock(&fmp->lock);
	return val;
}

static int cpuset_can_attach(struct cgroup_subsys *ss,
			     struct cgroup *cont, struct task_struct *tsk)
{
	struct cpuset *cs = cgroup_cs(cont);

	if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
		return -ENOSPC;

	return security_task_setscheduler(tsk, 0, NULL);
}

static void cpuset_attach(struct cgroup_subsys *ss,
			  struct cgroup *cont, struct cgroup *oldcont,
			  struct task_struct *tsk)
{
	cpumask_t cpus;
	nodemask_t from, to;
	struct mm_struct *mm;
	struct cpuset *cs = cgroup_cs(cont);
	struct cpuset *oldcs = cgroup_cs(oldcont);

	mutex_lock(&callback_mutex);
	guarantee_online_cpus(cs, &cpus);
	set_cpus_allowed(tsk, cpus);
	mutex_unlock(&callback_mutex);

	from = oldcs->mems_allowed;
	to = cs->mems_allowed;
	mm = get_task_mm(tsk);
	if (mm) {
		mpol_rebind_mm(mm, &to);
		if (is_memory_migrate(cs))
			cpuset_migrate_mm(mm, &from, &to);
		mmput(mm);
	}

}

/* The various types of files and directories in a cpuset file system */

typedef enum {
	FILE_MEMORY_MIGRATE,
	FILE_CPULIST,
	FILE_MEMLIST,
	FILE_CPU_EXCLUSIVE,
	FILE_MEM_EXCLUSIVE,
	FILE_MEMORY_PRESSURE_ENABLED,
	FILE_MEMORY_PRESSURE,
	FILE_SPREAD_PAGE,
	FILE_SPREAD_SLAB,
} cpuset_filetype_t;

static ssize_t cpuset_common_file_write(struct cgroup *cont,
					struct cftype *cft,
					struct file *file,
					const char __user *userbuf,
					size_t nbytes, loff_t *unused_ppos)
{
	struct cpuset *cs = cgroup_cs(cont);
	cpuset_filetype_t type = cft->private;
	char *buffer;
	int retval = 0;

	/* Crude upper limit on largest legitimate cpulist user might write. */
	if (nbytes > 100 + 6 * max(NR_CPUS, MAX_NUMNODES))
		return -E2BIG;

	/* +1 for nul-terminator */
	if ((buffer = kmalloc(nbytes + 1, GFP_KERNEL)) == 0)
		return -ENOMEM;

	if (copy_from_user(buffer, userbuf, nbytes)) {
		retval = -EFAULT;
		goto out1;
	}
	buffer[nbytes] = 0;	/* nul-terminate */

	cgroup_lock();

	if (cgroup_is_removed(cont)) {
		retval = -ENODEV;
		goto out2;
	}

	switch (type) {
	case FILE_CPULIST:
		retval = update_cpumask(cs, buffer);
		break;
	case FILE_MEMLIST:
		retval = update_nodemask(cs, buffer);
		break;
	case FILE_CPU_EXCLUSIVE:
		retval = update_flag(CS_CPU_EXCLUSIVE, cs, buffer);
		break;
	case FILE_MEM_EXCLUSIVE:
		retval = update_flag(CS_MEM_EXCLUSIVE, cs, buffer);
		break;
	case FILE_MEMORY_MIGRATE:
		retval = update_flag(CS_MEMORY_MIGRATE, cs, buffer);
		break;
	case FILE_MEMORY_PRESSURE_ENABLED:
		retval = update_memory_pressure_enabled(cs, buffer);
		break;
	case FILE_MEMORY_PRESSURE:
		retval = -EACCES;
		break;
	case FILE_SPREAD_PAGE:
		retval = update_flag(CS_SPREAD_PAGE, cs, buffer);
		cs->mems_generation = cpuset_mems_generation++;
		break;
	case FILE_SPREAD_SLAB:
		retval = update_flag(CS_SPREAD_SLAB, cs, buffer);
		cs->mems_generation = cpuset_mems_generation++;
		break;
	default:
		retval = -EINVAL;
		goto out2;
	}

	if (retval == 0)
		retval = nbytes;
out2:
	cgroup_unlock();
out1:
	kfree(buffer);
	return retval;
}

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

static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
{
	cpumask_t mask;

	mutex_lock(&callback_mutex);
	mask = cs->cpus_allowed;
	mutex_unlock(&callback_mutex);

	return cpulist_scnprintf(page, PAGE_SIZE, mask);
}

static int cpuset_sprintf_memlist(char *page, struct cpuset *cs)
{
	nodemask_t mask;

	mutex_lock(&callback_mutex);
	mask = cs->mems_allowed;
	mutex_unlock(&callback_mutex);

	return nodelist_scnprintf(page, PAGE_SIZE, mask);
}

static ssize_t cpuset_common_file_read(struct cgroup *cont,
				       struct cftype *cft,
				       struct file *file,
				       char __user *buf,
				       size_t nbytes, loff_t *ppos)
{
	struct cpuset *cs = cgroup_cs(cont);
	cpuset_filetype_t type = cft->private;
	char *page;
	ssize_t retval = 0;
	char *s;

	if (!(page = (char *)__get_free_page(GFP_TEMPORARY)))
		return -ENOMEM;

	s = page;

	switch (type) {
	case FILE_CPULIST:
		s += cpuset_sprintf_cpulist(s, cs);
		break;
	case FILE_MEMLIST:
		s += cpuset_sprintf_memlist(s, cs);
		break;
	case FILE_CPU_EXCLUSIVE:
		*s++ = is_cpu_exclusive(cs) ? '1' : '0';
		break;
	case FILE_MEM_EXCLUSIVE:
		*s++ = is_mem_exclusive(cs) ? '1' : '0';
		break;
	case FILE_MEMORY_MIGRATE:
		*s++ = is_memory_migrate(cs) ? '1' : '0';
		break;
	case FILE_MEMORY_PRESSURE_ENABLED:
		*s++ = cpuset_memory_pressure_enabled ? '1' : '0';
		break;
	case FILE_MEMORY_PRESSURE:
		s += sprintf(s, "%d", fmeter_getrate(&cs->fmeter));
		break;
	case FILE_SPREAD_PAGE:
		*s++ = is_spread_page(cs) ? '1' : '0';
		break;
	case FILE_SPREAD_SLAB:
		*s++ = is_spread_slab(cs) ? '1' : '0';
		break;
	default:
		retval = -EINVAL;
		goto out;
	}
	*s++ = '\n';

	retval = simple_read_from_buffer(buf, nbytes, ppos, page, s - page);
out:
	free_page((unsigned long)page);
	return retval;
}


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

static struct cftype cft_cpus = {
	.name = "cpus",
	.read = cpuset_common_file_read,
	.write = cpuset_common_file_write,
	.private = FILE_CPULIST,
};

static struct cftype cft_mems = {
	.name = "mems",
	.read = cpuset_common_file_read,
	.write = cpuset_common_file_write,
	.private = FILE_MEMLIST,
};

static struct cftype cft_cpu_exclusive = {
	.name = "cpu_exclusive",
	.read = cpuset_common_file_read,
	.write = cpuset_common_file_write,
	.private = FILE_CPU_EXCLUSIVE,
};

static struct cftype cft_mem_exclusive = {
	.name = "mem_exclusive",
	.read = cpuset_common_file_read,
	.write = cpuset_common_file_write,
	.private = FILE_MEM_EXCLUSIVE,
};

static struct cftype cft_memory_migrate = {
	.name = "memory_migrate",
	.read = cpuset_common_file_read,
	.write = cpuset_common_file_write,
	.private = FILE_MEMORY_MIGRATE,
};

static struct cftype cft_memory_pressure_enabled = {
	.name = "memory_pressure_enabled",
	.read = cpuset_common_file_read,
	.write = cpuset_common_file_write,
	.private = FILE_MEMORY_PRESSURE_ENABLED,
};

static struct cftype cft_memory_pressure = {
	.name = "memory_pressure",
	.read = cpuset_common_file_read,
	.write = cpuset_common_file_write,
	.private = FILE_MEMORY_PRESSURE,
};

static struct cftype cft_spread_page = {
	.name = "memory_spread_page",
	.read = cpuset_common_file_read,
	.write = cpuset_common_file_write,
	.private = FILE_SPREAD_PAGE,
};

static struct cftype cft_spread_slab = {
	.name = "memory_spread_slab",
	.read = cpuset_common_file_read,
	.write = cpuset_common_file_write,
	.private = FILE_SPREAD_SLAB,
};

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

	if ((err = cgroup_add_file(cont, ss, &cft_cpus)) < 0)
		return err;
	if ((err = cgroup_add_file(cont, ss, &cft_mems)) < 0)
		return err;
	if ((err = cgroup_add_file(cont, ss, &cft_cpu_exclusive)) < 0)
		return err;
	if ((err = cgroup_add_file(cont, ss, &cft_mem_exclusive)) < 0)
		return err;
	if ((err = cgroup_add_file(cont, ss, &cft_memory_migrate)) < 0)
		return err;
	if ((err = cgroup_add_file(cont, ss, &cft_memory_pressure)) < 0)
		return err;
	if ((err = cgroup_add_file(cont, ss, &cft_spread_page)) < 0)
		return err;
	if ((err = cgroup_add_file(cont, ss, &cft_spread_slab)) < 0)
		return err;
	/* memory_pressure_enabled is in root cpuset only */
	if (err == 0 && !cont->parent)
		err = cgroup_add_file(cont, ss,
					 &cft_memory_pressure_enabled);
	return 0;
}

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

	parent = cgroup->parent;
	list_for_each_entry(child, &parent->children, sibling) {
		cs = cgroup_cs(child);
		if (is_mem_exclusive(cs) || is_cpu_exclusive(cs))
			return;
	}
	cs = cgroup_cs(cgroup);
	parent_cs = cgroup_cs(parent);

	cs->mems_allowed = parent_cs->mems_allowed;
	cs->cpus_allowed = parent_cs->cpus_allowed;
	return;
}

/*
 *	cpuset_create - create a cpuset
 *	parent:	cpuset that will be parent of the new cpuset.
 *	name:		name of the new cpuset. Will be strcpy'ed.
 *	mode:		mode to set on new inode
 *
 *	Must be called with the mutex on the parent inode held
 */

static struct cgroup_subsys_state *cpuset_create(
	struct cgroup_subsys *ss,
	struct cgroup *cont)
{
	struct cpuset *cs;
	struct cpuset *parent;

	if (!cont->parent) {
		/* This is early initialization for the top cgroup */
		top_cpuset.mems_generation = cpuset_mems_generation++;
		return &top_cpuset.css;
	}
	parent = cgroup_cs(cont->parent);
	cs = kmalloc(sizeof(*cs), GFP_KERNEL);
	if (!cs)
		return ERR_PTR(-ENOMEM);

	cpuset_update_task_memory_state();
	cs->flags = 0;
	if (is_spread_page(parent))
		set_bit(CS_SPREAD_PAGE, &cs->flags);
	if (is_spread_slab(parent))
		set_bit(CS_SPREAD_SLAB, &cs->flags);
	cs->cpus_allowed = CPU_MASK_NONE;
	cs->mems_allowed = NODE_MASK_NONE;
	cs->mems_generation = cpuset_mems_generation++;
	fmeter_init(&cs->fmeter);

	cs->parent = parent;
	number_of_cpusets++;
	return &cs->css ;
}

static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
{
	struct cpuset *cs = cgroup_cs(cont);

	cpuset_update_task_memory_state();
	number_of_cpusets--;
	kfree(cs);
}

struct cgroup_subsys cpuset_subsys = {
	.name = "cpuset",
	.create = cpuset_create,
	.destroy  = cpuset_destroy,
	.can_attach = cpuset_can_attach,
	.attach = cpuset_attach,
	.populate = cpuset_populate,
	.post_clone = cpuset_post_clone,
	.subsys_id = cpuset_subsys_id,
	.early_init = 1,
};

/*
 * cpuset_init_early - just enough so that the calls to
 * cpuset_update_task_memory_state() in early init code
 * are harmless.
 */

int __init cpuset_init_early(void)
{
	top_cpuset.mems_generation = cpuset_mems_generation++;
	return 0;
}


/**
 * cpuset_init - initialize cpusets at system boot
 *
 * Description: Initialize top_cpuset and the cpuset internal file system,
 **/

int __init cpuset_init(void)
{
	int err = 0;

	top_cpuset.cpus_allowed = CPU_MASK_ALL;
	top_cpuset.mems_allowed = NODE_MASK_ALL;

	fmeter_init(&top_cpuset.fmeter);
	top_cpuset.mems_generation = cpuset_mems_generation++;

	err = register_filesystem(&cpuset_fs_type);
	if (err < 0)
		return err;

	number_of_cpusets = 1;
	return 0;
}

/*
 * If common_cpu_mem_hotplug_unplug(), below, unplugs any CPUs
 * or memory nodes, we need to walk over the cpuset hierarchy,
 * removing that CPU or node from all cpusets.  If this removes the
 * last CPU or node from a cpuset, then the guarantee_online_cpus()
 * or guarantee_online_mems() code will use that emptied cpusets
 * parent online CPUs or nodes.  Cpusets that were already empty of
 * CPUs or nodes are left empty.
 *
 * This routine is intentionally inefficient in a couple of regards.
 * It will check all cpusets in a subtree even if the top cpuset of
 * the subtree has no offline CPUs or nodes.  It checks both CPUs and
 * nodes, even though the caller could have been coded to know that
 * only one of CPUs or nodes needed to be checked on a given call.
 * This was done to minimize text size rather than cpu cycles.
 *
 * Call with both manage_mutex and callback_mutex held.
 *
 * Recursive, on depth of cpuset subtree.
 */

static void guarantee_online_cpus_mems_in_subtree(const struct cpuset *cur)
{
	struct cgroup *cont;
	struct cpuset *c;

	/* Each of our child cpusets mems must be online */
	list_for_each_entry(cont, &cur->css.cgroup->children, sibling) {
		c = cgroup_cs(cont);
		guarantee_online_cpus_mems_in_subtree(c);
		if (!cpus_empty(c->cpus_allowed))
			guarantee_online_cpus(c, &c->cpus_allowed);
		if (!nodes_empty(c->mems_allowed))
			guarantee_online_mems(c, &c->mems_allowed);
	}
}

/*
 * The cpus_allowed and mems_allowed nodemasks in the top_cpuset track
 * cpu_online_map and node_states[N_HIGH_MEMORY].  Force the top cpuset to
 * track what's online after any CPU or memory node hotplug or unplug
 * event.
 *
 * To ensure that we don't remove a CPU or node from the top cpuset
 * that is currently in use by a child cpuset (which would violate
 * the rule that cpusets must be subsets of their parent), we first
 * call the recursive routine guarantee_online_cpus_mems_in_subtree().
 *
 * Since there are two callers of this routine, one for CPU hotplug
 * events and one for memory node hotplug events, we could have coded
 * two separate routines here.  We code it as a single common routine
 * in order to minimize text size.
 */

static void common_cpu_mem_hotplug_unplug(void)
{
	cgroup_lock();
	mutex_lock(&callback_mutex);

	guarantee_online_cpus_mems_in_subtree(&top_cpuset);
	top_cpuset.cpus_allowed = cpu_online_map;
	top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];

	mutex_unlock(&callback_mutex);
	cgroup_unlock();
}

/*
 * The top_cpuset tracks what CPUs and Memory Nodes are online,
 * period.  This is necessary in order to make cpusets transparent
 * (of no affect) on systems that are actively using CPU hotplug
 * but making no active use of cpusets.
 *
 * This routine ensures that top_cpuset.cpus_allowed tracks
 * cpu_online_map on each CPU hotplug (cpuhp) event.
 */

static int cpuset_handle_cpuhp(struct notifier_block *nb,
				unsigned long phase, void *cpu)
{
	if (phase == CPU_DYING || phase == CPU_DYING_FROZEN)
		return NOTIFY_DONE;

	common_cpu_mem_hotplug_unplug();
	return 0;
}

#ifdef CONFIG_MEMORY_HOTPLUG
/*
 * Keep top_cpuset.mems_allowed tracking node_states[N_HIGH_MEMORY].
 * Call this routine anytime after you change
 * node_states[N_HIGH_MEMORY].
 * See also the previous routine cpuset_handle_cpuhp().
 */

void cpuset_track_online_nodes(void)
{
	common_cpu_mem_hotplug_unplug();
}
#endif

/**
 * cpuset_init_smp - initialize cpus_allowed
 *
 * Description: Finish top cpuset after cpu, node maps are initialized
 **/

void __init cpuset_init_smp(void)
{
	top_cpuset.cpus_allowed = cpu_online_map;
	top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];

	hotcpu_notifier(cpuset_handle_cpuhp, 0);
}

/**

 * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset.
 * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
 *
 * Description: Returns the cpumask_t cpus_allowed of the cpuset
 * attached to the specified @tsk.  Guaranteed to return some non-empty
 * subset of cpu_online_map, even if this means going outside the
 * tasks cpuset.
 **/

cpumask_t cpuset_cpus_allowed(struct task_struct *tsk)
{
	cpumask_t mask;

	mutex_lock(&callback_mutex);
	task_lock(tsk);
	guarantee_online_cpus(task_cs(tsk), &mask);
	task_unlock(tsk);
	mutex_unlock(&callback_mutex);

	return mask;
}

void cpuset_init_current_mems_allowed(void)
{
	current->mems_allowed = NODE_MASK_ALL;
}

/**
 * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset.
 * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed.
 *
 * Description: Returns the nodemask_t mems_allowed of the cpuset
 * attached to the specified @tsk.  Guaranteed to return some non-empty
 * subset of node_states[N_HIGH_MEMORY], even if this means going outside the
 * tasks cpuset.
 **/

nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
{
	nodemask_t mask;

	mutex_lock(&callback_mutex);
	task_lock(tsk);
	guarantee_online_mems(task_cs(tsk), &mask);
	task_unlock(tsk);
	mutex_unlock(&callback_mutex);

	return mask;
}

/**
 * cpuset_zonelist_valid_mems_allowed - check zonelist vs. curremt mems_allowed
 * @zl: the zonelist to be checked
 *
 * Are any of the nodes on zonelist zl allowed in current->mems_allowed?
 */
int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl)
{
	int i;

	for (i = 0; zl->zones[i]; i++) {
		int nid = zone_to_nid(zl->zones[i]);

		if (node_isset(nid, current->mems_allowed))
			return 1;
	}
	return 0;
}

/*
 * nearest_exclusive_ancestor() - Returns the nearest mem_exclusive
 * ancestor to the specified cpuset.  Call holding callback_mutex.
 * If no ancestor is mem_exclusive (an unusual configuration), then
 * returns the root cpuset.
 */
static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs)
{
	while (!is_mem_exclusive(cs) && cs->parent)
		cs = cs->parent;
	return cs;
}

/**
 * cpuset_zone_allowed_softwall - Can we allocate on zone z's memory node?
 * @z: is this zone on an allowed node?
 * @gfp_mask: memory allocation flags
 *
 * If we're in interrupt, yes, we can always allocate.  If
 * __GFP_THISNODE is set, yes, we can always allocate.  If zone
 * z's node is in our tasks mems_allowed, yes.  If it's not a
 * __GFP_HARDWALL request and this zone's nodes is in the nearest
 * mem_exclusive cpuset ancestor to this tasks cpuset, yes.
 * If the task has been OOM killed and has access to memory reserves
 * as specified by the TIF_MEMDIE flag, yes.
 * Otherwise, no.
 *
 * If __GFP_HARDWALL is set, cpuset_zone_allowed_softwall()
 * reduces to cpuset_zone_allowed_hardwall().  Otherwise,
 * cpuset_zone_allowed_softwall() might sleep, and might allow a zone
 * from an enclosing cpuset.
 *
 * cpuset_zone_allowed_hardwall() only handles the simpler case of
 * hardwall cpusets, and never sleeps.
 *
 * The __GFP_THISNODE placement logic is really handled elsewhere,
 * by forcibly using a zonelist starting at a specified node, and by
 * (in get_page_from_freelist()) refusing to consider the zones for
 * any node on the zonelist except the first.  By the time any such
 * calls get to this routine, we should just shut up and say 'yes'.
 *
 * GFP_USER allocations are marked with the __GFP_HARDWALL bit,
 * and do not allow allocations outside the current tasks cpuset
 * unless the task has been OOM killed as is marked TIF_MEMDIE.
 * GFP_KERNEL allocations are not so marked, so can escape to the
 * nearest enclosing mem_exclusive ancestor cpuset.
 *
 * Scanning up parent cpusets requires callback_mutex.  The
 * __alloc_pages() routine only calls here with __GFP_HARDWALL bit
 * _not_ set if it's a GFP_KERNEL allocation, and all nodes in the
 * current tasks mems_allowed came up empty on the first pass over
 * the zonelist.  So only GFP_KERNEL allocations, if all nodes in the
 * cpuset are short of memory, might require taking the callback_mutex
 * mutex.
 *
 * The first call here from mm/page_alloc:get_page_from_freelist()
 * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets,
 * so no allocation on a node outside the cpuset is allowed (unless
 * in interrupt, of course).
 *
 * The second pass through get_page_from_freelist() doesn't even call
 * here for GFP_ATOMIC calls.  For those calls, the __alloc_pages()
 * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set
 * in alloc_flags.  That logic and the checks below have the combined
 * affect that:
 *	in_interrupt - any node ok (current task context irrelevant)
 *	GFP_ATOMIC   - any node ok
 *	TIF_MEMDIE   - any node ok
 *	GFP_KERNEL   - any node in enclosing mem_exclusive cpuset ok
 *	GFP_USER     - only nodes in current tasks mems allowed ok.
 *
 * Rule:
 *    Don't call cpuset_zone_allowed_softwall if you can't sleep, unless you
 *    pass in the __GFP_HARDWALL flag set in gfp_flag, which disables
 *    the code that might scan up ancestor cpusets and sleep.
 */

int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
{
	int node;			/* node that zone z is on */
	const struct cpuset *cs;	/* current cpuset ancestors */
	int allowed;			/* is allocation in zone z allowed? */

	if (in_interrupt() || (gfp_mask & __GFP_THISNODE))
		return 1;
	node = zone_to_nid(z);
	might_sleep_if(!(gfp_mask & __GFP_HARDWALL));
	if (node_isset(node, current->mems_allowed))
		return 1;
	/*
	 * Allow tasks that have access to memory reserves because they have
	 * been OOM killed to get memory anywhere.
	 */
	if (unlikely(test_thread_flag(TIF_MEMDIE)))
		return 1;
	if (gfp_mask & __GFP_HARDWALL)	/* If hardwall request, stop here */
		return 0;

	if (current->flags & PF_EXITING) /* Let dying task have memory */
		return 1;

	/* Not hardwall and node outside mems_allowed: scan up cpusets */
	mutex_lock(&callback_mutex);

	task_lock(current);
	cs = nearest_exclusive_ancestor(task_cs(current));
	task_unlock(current);

	allowed = node_isset(node, cs->mems_allowed);
	mutex_unlock(&callback_mutex);
	return allowed;
}

/*
 * cpuset_zone_allowed_hardwall - Can we allocate on zone z's memory node?
 * @z: is this zone on an allowed node?
 * @gfp_mask: memory allocation flags
 *
 * If we're in interrupt, yes, we can always allocate.
 * If __GFP_THISNODE is set, yes, we can always allocate.  If zone
 * z's node is in our tasks mems_allowed, yes.   If the task has been
 * OOM killed and has access to memory reserves as specified by the
 * TIF_MEMDIE flag, yes.  Otherwise, no.
 *
 * The __GFP_THISNODE placement logic is really handled elsewhere,
 * by forcibly using a zonelist starting at a specified node, and by
 * (in get_page_from_freelist()) refusing to consider the zones for
 * any node on the zonelist except the first.  By the time any such
 * calls get to this routine, we should just shut up and say 'yes'.
 *
 * Unlike the cpuset_zone_allowed_softwall() variant, above,
 * this variant requires that the zone be in the current tasks
 * mems_allowed or that we're in interrupt.  It does not scan up the
 * cpuset hierarchy for the nearest enclosing mem_exclusive cpuset.
 * It never sleeps.
 */

int __cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
{
	int node;			/* node that zone z is on */

	if (in_interrupt() || (gfp_mask & __GFP_THISNODE))
		return 1;
	node = zone_to_nid(z);
	if (node_isset(node, current->mems_allowed))
		return 1;
	/*