summaryrefslogtreecommitdiffstats
path: root/kernel/cgroup_freezer.c
blob: 4f12d317c4c37897bd3940dab0c59d5c10569239 (plain)
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
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
/*
 * cgroup_freezer.c -  control group freezer subsystem
 *
 * Copyright IBM Corporation, 2007
 *
 * Author : Cedric Le Goater <clg@fr.ibm.com>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of version 2.1 of the GNU Lesser General Public License
 * as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
 */

#include <linux/export.h>
#include <linux/slab.h>
#include <linux/cgroup.h>
#include <linux/fs.h>
#include <linux/uaccess.h>
#include <linux/freezer.h>
#include <linux/seq_file.h>

enum freezer_state_flags {
	CGROUP_FREEZER_ONLINE	= (1 << 0), /* freezer is fully online */
	CGROUP_FREEZING_SELF	= (1 << 1), /* this freezer is freezing */
	CGROUP_FREEZING_PARENT	= (1 << 2), /* the parent freezer is freezing */
	CGROUP_FROZEN		= (1 << 3), /* this and its descendants frozen */

	/* mask for all FREEZING flags */
	CGROUP_FREEZING		= CGROUP_FREEZING_SELF | CGROUP_FREEZING_PARENT,
};

struct freezer {
	struct cgroup_subsys_state	css;
	unsigned int			state;
	spinlock_t			lock;
};

static inline struct freezer *cgroup_freezer(struct cgroup *cgroup)
{
	return container_of(cgroup_subsys_state(cgroup, freezer_subsys_id),
			    struct freezer, css);
}

static inline struct freezer *task_freezer(struct task_struct *task)
{
	return container_of(task_subsys_state(task, freezer_subsys_id),
			    struct freezer, css);
}

bool cgroup_freezing(struct task_struct *task)
{
	bool ret;

	rcu_read_lock();
	ret = task_freezer(task)->state & CGROUP_FREEZING;
	rcu_read_unlock();

	return ret;
}

/*
 * cgroups_write_string() limits the size of freezer state strings to
 * CGROUP_LOCAL_BUFFER_SIZE
 */
static const char *freezer_state_strs(unsigned int state)
{
	if (state & CGROUP_FROZEN)
		return "FROZEN";
	if (state & CGROUP_FREEZING)
		return "FREEZING";
	return "THAWED";
};

/*
 * State diagram
 * Transitions are caused by userspace writes to the freezer.state file.
 * The values in parenthesis are state labels. The rest are edge labels.
 *
 * (THAWED) --FROZEN--> (FREEZING) --FROZEN--> (FROZEN)
 *    ^ ^                    |                     |
 *    | \_______THAWED_______/                     |
 *    \__________________________THAWED____________/
 */

struct cgroup_subsys freezer_subsys;

static struct cgroup_subsys_state *freezer_create(struct cgroup *cgroup)
{
	struct freezer *freezer;

	freezer = kzalloc(sizeof(struct freezer), GFP_KERNEL);
	if (!freezer)
		return ERR_PTR(-ENOMEM);

	spin_lock_init(&freezer->lock);
	return &freezer->css;
}

/**
 * freezer_post_create - commit creation of a freezer cgroup
 * @cgroup: cgroup being created
 *
 * We're committing to creation of @cgroup.  Mark it online.
 */
static void freezer_post_create(struct cgroup *cgroup)
{
	struct freezer *freezer = cgroup_freezer(cgroup);

	spin_lock_irq(&freezer->lock);
	freezer->state |= CGROUP_FREEZER_ONLINE;
	spin_unlock_irq(&freezer->lock);
}

/**
 * freezer_pre_destroy - initiate destruction of @cgroup
 * @cgroup: cgroup being destroyed
 *
 * @cgroup is going away.  Mark it dead and decrement system_freezing_count
 * if it was holding one.
 */
static void freezer_pre_destroy(struct cgroup *cgroup)
{
	struct freezer *freezer = cgroup_freezer(cgroup);

	spin_lock_irq(&freezer->lock);

	if (freezer->state & CGROUP_FREEZING)
		atomic_dec(&system_freezing_cnt);

	freezer->state = 0;

	spin_unlock_irq(&freezer->lock);
}

static void freezer_destroy(struct cgroup *cgroup)
{
	kfree(cgroup_freezer(cgroup));
}

/*
 * Tasks can be migrated into a different freezer anytime regardless of its
 * current state.  freezer_attach() is responsible for making new tasks
 * conform to the current state.
 *
 * Freezer state changes and task migration are synchronized via
 * @freezer->lock.  freezer_attach() makes the new tasks conform to the
 * current state and all following state changes can see the new tasks.
 */
static void freezer_attach(struct cgroup *new_cgrp, struct cgroup_taskset *tset)
{
	struct freezer *freezer = cgroup_freezer(new_cgrp);
	struct task_struct *task;

	spin_lock_irq(&freezer->lock);

	/*
	 * Make the new tasks conform to the current state of @new_cgrp.
	 * For simplicity, when migrating any task to a FROZEN cgroup, we
	 * revert it to FREEZING and let update_if_frozen() determine the
	 * correct state later.
	 *
	 * Tasks in @tset are on @new_cgrp but may not conform to its
	 * current state before executing the following - !frozen tasks may
	 * be visible in a FROZEN cgroup and frozen tasks in a THAWED one.
	 */
	cgroup_taskset_for_each(task, new_cgrp, tset) {
		if (!(freezer->state & CGROUP_FREEZING)) {
			__thaw_task(task);
		} else {
			freeze_task(task);
			freezer->state &= ~CGROUP_FROZEN;
		}
	}

	spin_unlock_irq(&freezer->lock);
}

static void freezer_fork(struct task_struct *task)
{
	struct freezer *freezer;

	rcu_read_lock();
	freezer = task_freezer(task);

	/*
	 * The root cgroup is non-freezable, so we can skip the
	 * following check.
	 */
	if (!freezer->css.cgroup->parent)
		goto out;

	spin_lock_irq(&freezer->lock);
	if (freezer->state & CGROUP_FREEZING)
		freeze_task(task);
	spin_unlock_irq(&freezer->lock);
out:
	rcu_read_unlock();
}

/*
 * We change from FREEZING to FROZEN lazily if the cgroup was only
 * partially frozen when we exitted write.  Caller must hold freezer->lock.
 *
 * Task states and freezer state might disagree while tasks are being
 * migrated into or out of @cgroup, so we can't verify task states against
 * @freezer state here.  See freezer_attach() for details.
 */
static void update_if_frozen(struct freezer *freezer)
{
	struct cgroup *cgroup = freezer->css.cgroup;
	struct cgroup_iter it;
	struct task_struct *task;

	if (!(freezer->state & CGROUP_FREEZING) ||
	    (freezer->state & CGROUP_FROZEN))
		return;

	cgroup_iter_start(cgroup, &it);

	while ((task = cgroup_iter_next(cgroup, &it))) {
		if (freezing(task)) {
			/*
			 * freezer_should_skip() indicates that the task
			 * should be skipped when determining freezing
			 * completion.  Consider it frozen in addition to
			 * the usual frozen condition.
			 */
			if (!frozen(task) && !freezer_should_skip(task))
				goto notyet;
		}
	}

	freezer->state |= CGROUP_FROZEN;
notyet:
	cgroup_iter_end(cgroup, &it);
}

static int freezer_read(struct cgroup *cgroup, struct cftype *cft,
			struct seq_file *m)
{
	struct freezer *freezer = cgroup_freezer(cgroup);
	unsigned int state;

	spin_lock_irq(&freezer->lock);
	update_if_frozen(freezer);
	state = freezer->state;
	spin_unlock_irq(&freezer->lock);

	seq_puts(m, freezer_state_strs(state));
	seq_putc(m, '\n');
	return 0;
}

static void freeze_cgroup(struct freezer *freezer)
{
	struct cgroup *cgroup = freezer->css.cgroup;
	struct cgroup_iter it;
	struct task_struct *task;

	cgroup_iter_start(cgroup, &it);
	while ((task = cgroup_iter_next(cgroup, &it)))
		freeze_task(task);
	cgroup_iter_end(cgroup, &it);
}

static void unfreeze_cgroup(struct freezer *freezer)
{
	struct cgroup *cgroup = freezer->css.cgroup;
	struct cgroup_iter it;
	struct task_struct *task;

	cgroup_iter_start(cgroup, &it);
	while ((task = cgroup_iter_next(cgroup, &it)))
		__thaw_task(task);
	cgroup_iter_end(cgroup, &it);
}

/**
 * freezer_apply_state - apply state change to a single cgroup_freezer
 * @freezer: freezer to apply state change to
 * @freeze: whether to freeze or unfreeze
 * @state: CGROUP_FREEZING_* flag to set or clear
 *
 * Set or clear @state on @cgroup according to @freeze, and perform
 * freezing or thawing as necessary.
 */
static void freezer_apply_state(struct freezer *freezer, bool freeze,
				unsigned int state)
{
	/* also synchronizes against task migration, see freezer_attach() */
	lockdep_assert_held(&freezer->lock);

	if (!(freezer->state & CGROUP_FREEZER_ONLINE))
		return;

	if (freeze) {
		if (!(freezer->state & CGROUP_FREEZING))
			atomic_inc(&system_freezing_cnt);
		freezer->state |= state;
		freeze_cgroup(freezer);
	} else {
		bool was_freezing = freezer->state & CGROUP_FREEZING;

		freezer->state &= ~state;

		if (!(freezer->state & CGROUP_FREEZING)) {
			if (was_freezing)
				atomic_dec(&system_freezing_cnt);
			freezer->state &= ~CGROUP_FROZEN;
			unfreeze_cgroup(freezer);
		}
	}
}

/**
 * freezer_change_state - change the freezing state of a cgroup_freezer
 * @freezer: freezer of interest
 * @freeze: whether to freeze or thaw
 *
 * Freeze or thaw @cgroup according to @freeze.
 */
static void freezer_change_state(struct freezer *freezer, bool freeze)
{
	/* update @freezer */
	spin_lock_irq(&freezer->lock);
	freezer_apply_state(freezer, freeze, CGROUP_FREEZING_SELF);
	spin_unlock_irq(&freezer->lock);
}

static int freezer_write(struct cgroup *cgroup, struct cftype *cft,
			 const char *buffer)
{
	bool freeze;

	if (strcmp(buffer, freezer_state_strs(0)) == 0)
		freeze = false;
	else if (strcmp(buffer, freezer_state_strs(CGROUP_FROZEN)) == 0)
		freeze = true;
	else
		return -EINVAL;

	freezer_change_state(cgroup_freezer(cgroup), freeze);
	return 0;
}

static u64 freezer_self_freezing_read(struct cgroup *cgroup, struct cftype *cft)
{
	struct freezer *freezer = cgroup_freezer(cgroup);

	return (bool)(freezer->state & CGROUP_FREEZING_SELF);
}

static u64 freezer_parent_freezing_read(struct cgroup *cgroup, struct cftype *cft)
{
	struct freezer *freezer = cgroup_freezer(cgroup);

	return (bool)(freezer->state & CGROUP_FREEZING_PARENT);
}

static struct cftype files[] = {
	{
		.name = "state",
		.flags = CFTYPE_NOT_ON_ROOT,
		.read_seq_string = freezer_read,
		.write_string = freezer_write,
	},
	{
		.name = "self_freezing",
		.flags = CFTYPE_NOT_ON_ROOT,
		.read_u64 = freezer_self_freezing_read,
	},
	{
		.name = "parent_freezing",
		.flags = CFTYPE_NOT_ON_ROOT,
		.read_u64 = freezer_parent_freezing_read,
	},
	{ }	/* terminate */
};

struct cgroup_subsys freezer_subsys = {
	.name		= "freezer",
	.create		= freezer_create,
	.post_create	= freezer_post_create,
	.pre_destroy	= freezer_pre_destroy,
	.destroy	= freezer_destroy,
	.subsys_id	= freezer_subsys_id,
	.attach		= freezer_attach,
	.fork		= freezer_fork,
	.base_cftypes	= files,

	/*
	 * freezer subsys doesn't handle hierarchy at all.  Frozen state
	 * should be inherited through the hierarchy - if a parent is
	 * frozen, all its children should be frozen.  Fix it and remove
	 * the following.
	 */
	.broken_hierarchy = true,
};