summaryrefslogtreecommitdiffstats
path: root/kernel/cgroup_freezer.c
blob: a6d405a86ee04d78127c59d19465924f1f38b7fa (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
/*
 * 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 {
	CGROUP_THAWED = 0,
	CGROUP_FREEZING,
	CGROUP_FROZEN,
};

struct freezer {
	struct cgroup_subsys_state css;
	enum freezer_state state;
	spinlock_t lock; /* protects _writes_ to state */
};

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);
}

static inline int __cgroup_freezing_or_frozen(struct task_struct *task)
{
	enum freezer_state state = task_freezer(task)->state;
	return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN);
}

int cgroup_freezing_or_frozen(struct task_struct *task)
{
	int result;
	task_lock(task);
	result = __cgroup_freezing_or_frozen(task);
	task_unlock(task);
	return result;
}

/*
 * cgroups_write_string() limits the size of freezer state strings to
 * CGROUP_LOCAL_BUFFER_SIZE
 */
static const char *freezer_state_strs[] = {
	"THAWED",
	"FREEZING",
	"FROZEN",
};

/*
 * 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;

/* Locks taken and their ordering
 * ------------------------------
 * cgroup_mutex (AKA cgroup_lock)
 * freezer->lock
 * css_set_lock
 * task->alloc_lock (AKA task_lock)
 * task->sighand->siglock
 *
 * cgroup code forces css_set_lock to be taken before task->alloc_lock
 *
 * freezer_create(), freezer_destroy():
 * cgroup_mutex [ by cgroup core ]
 *
 * freezer_can_attach():
 * cgroup_mutex (held by caller of can_attach)
 *
 * cgroup_freezing_or_frozen():
 * task->alloc_lock (to get task's cgroup)
 *
 * freezer_fork() (preserving fork() performance means can't take cgroup_mutex):
 * freezer->lock
 *  sighand->siglock (if the cgroup is freezing)
 *
 * freezer_read():
 * cgroup_mutex
 *  freezer->lock
 *   write_lock css_set_lock (cgroup iterator start)
 *    task->alloc_lock
 *   read_lock css_set_lock (cgroup iterator start)
 *
 * freezer_write() (freeze):
 * cgroup_mutex
 *  freezer->lock
 *   write_lock css_set_lock (cgroup iterator start)
 *    task->alloc_lock
 *   read_lock css_set_lock (cgroup iterator start)
 *    sighand->siglock (fake signal delivery inside freeze_task())
 *
 * freezer_write() (unfreeze):
 * cgroup_mutex
 *  freezer->lock
 *   write_lock css_set_lock (cgroup iterator start)
 *    task->alloc_lock
 *   read_lock css_set_lock (cgroup iterator start)
 *    task->alloc_lock (inside __thaw_task(), prevents race with refrigerator())
 *     sighand->siglock
 */
static struct cgroup_subsys_state *freezer_create(struct cgroup_subsys *ss,
						  struct cgroup *cgroup)
{
	struct freezer *freezer;

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

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

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

/*
 * The call to cgroup_lock() in the freezer.state write method prevents
 * a write to that file racing against an attach, and hence the
 * can_attach() result will remain valid until the attach completes.
 */
static int freezer_can_attach(struct cgroup_subsys *ss,
			      struct cgroup *new_cgroup,
			      struct task_struct *task)
{
	struct freezer *freezer;

	/*
	 * Anything frozen can't move or be moved to/from.
	 */

	freezer = cgroup_freezer(new_cgroup);
	if (freezer->state != CGROUP_THAWED)
		return -EBUSY;

	return 0;
}

static int freezer_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
{
	rcu_read_lock();
	if (__cgroup_freezing_or_frozen(tsk)) {
		rcu_read_unlock();
		return -EBUSY;
	}
	rcu_read_unlock();
	return 0;
}

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

	/*
	 * No lock is needed, since the task isn't on tasklist yet,
	 * so it can't be moved to another cgroup, which means the
	 * freezer won't be removed and will be valid during this
	 * function call.  Nevertheless, apply RCU read-side critical
	 * section to suppress RCU lockdep false positives.
	 */
	rcu_read_lock();
	freezer = task_freezer(task);
	rcu_read_unlock();

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

	spin_lock_irq(&freezer->lock);
	BUG_ON(freezer->state == CGROUP_FROZEN);

	/* Locking avoids race with FREEZING -> THAWED transitions. */
	if (freezer->state == CGROUP_FREEZING)
		freeze_task(task, true);
	spin_unlock_irq(&freezer->lock);
}

/*
 * caller must hold freezer->lock
 */
static void update_if_frozen(struct cgroup *cgroup,
				 struct freezer *freezer)
{
	struct cgroup_iter it;
	struct task_struct *task;
	unsigned int nfrozen = 0, ntotal = 0;
	enum freezer_state old_state = freezer->state;

	cgroup_iter_start(cgroup, &it);
	while ((task = cgroup_iter_next(cgroup, &it))) {
		ntotal++;
		if (frozen(task))
			nfrozen++;
	}

	if (old_state == CGROUP_THAWED) {
		BUG_ON(nfrozen > 0);
	} else if (old_state == CGROUP_FREEZING) {
		if (nfrozen == ntotal)
			freezer->state = CGROUP_FROZEN;
	} else { /* old_state == CGROUP_FROZEN */
		BUG_ON(nfrozen != ntotal);
	}

	cgroup_iter_end(cgroup, &it);
}

static int freezer_read(struct cgroup *cgroup, struct cftype *cft,
			struct seq_file *m)
{
	struct freezer *freezer;
	enum freezer_state state;

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

	freezer = cgroup_freezer(cgroup);
	spin_lock_irq(&freezer->lock);
	state = freezer->state;
	if (state == CGROUP_FREEZING) {
		/* We change from FREEZING to FROZEN lazily if the cgroup was
		 * only partially frozen when we exitted write. */
		update_if_frozen(cgroup, freezer);
		state = freezer->state;
	}
	spin_unlock_irq(&freezer->lock);
	cgroup_unlock();

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

static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
{
	struct cgroup_iter it;
	struct task_struct *task;
	unsigned int num_cant_freeze_now = 0;

	freezer->state = CGROUP_FREEZING;
	cgroup_iter_start(cgroup, &it);
	while ((task = cgroup_iter_next(cgroup, &it))) {
		if (!freeze_task(task, true))
			continue;
		if (frozen(task))
			continue;
		if (!freezing(task) && !freezer_should_skip(task))
			num_cant_freeze_now++;
	}
	cgroup_iter_end(cgroup, &it);

	return num_cant_freeze_now ? -EBUSY : 0;
}

static void unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
{
	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->state = CGROUP_THAWED;
}

static int freezer_change_state(struct cgroup *cgroup,
				enum freezer_state goal_state)
{
	struct freezer *freezer;
	int retval = 0;

	freezer = cgroup_freezer(cgroup);

	spin_lock_irq(&freezer->lock);

	update_if_frozen(cgroup, freezer);
	if (goal_state == freezer->state)
		goto out;

	switch (goal_state) {
	case CGROUP_THAWED:
		unfreeze_cgroup(cgroup, freezer);
		break;
	case CGROUP_FROZEN:
		retval = try_to_freeze_cgroup(cgroup, freezer);
		break;
	default:
		BUG();
	}
out:
	spin_unlock_irq(&freezer->lock);

	return retval;
}

static int freezer_write(struct cgroup *cgroup,
			 struct cftype *cft,
			 const char *buffer)
{
	int retval;
	enum freezer_state goal_state;

	if (strcmp(buffer, freezer_state_strs[CGROUP_THAWED]) == 0)
		goal_state = CGROUP_THAWED;
	else if (strcmp(buffer, freezer_state_strs[CGROUP_FROZEN]) == 0)
		goal_state = CGROUP_FROZEN;
	else
		return -EINVAL;

	if (!cgroup_lock_live_group(cgroup))
		return -ENODEV;
	retval = freezer_change_state(cgroup, goal_state);
	cgroup_unlock();
	return retval;
}

static struct cftype files[] = {
	{
		.name = "state",
		.read_seq_string = freezer_read,
		.write_string = freezer_write,
	},
};

static int freezer_populate(struct cgroup_subsys *ss, struct cgroup *cgroup)
{
	if (!cgroup->parent)
		return 0;
	return cgroup_add_files(cgroup, ss, files, ARRAY_SIZE(files));
}

struct cgroup_subsys freezer_subsys = {
	.name		= "freezer",
	.create		= freezer_create,
	.destroy	= freezer_destroy,
	.populate	= freezer_populate,
	.subsys_id	= freezer_subsys_id,
	.can_attach	= freezer_can_attach,
	.can_attach_task = freezer_can_attach_task,
	.pre_attach	= NULL,
	.attach_task	= NULL,
	.attach		= NULL,
	.fork		= freezer_fork,
	.exit		= NULL,
};