summaryrefslogtreecommitdiff
path: root/kernel/cgroup_pids.c
blob: cdd8df4e991c7781ac5996677d724bcd23314623 (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
/*
 * Process number limiting controller for cgroups.
 *
 * Used to allow a cgroup hierarchy to stop any new processes from fork()ing
 * after a certain limit is reached.
 *
 * Since it is trivial to hit the task limit without hitting any kmemcg limits
 * in place, PIDs are a fundamental resource. As such, PID exhaustion must be
 * preventable in the scope of a cgroup hierarchy by allowing resource limiting
 * of the number of tasks in a cgroup.
 *
 * In order to use the `pids` controller, set the maximum number of tasks in
 * pids.max (this is not available in the root cgroup for obvious reasons). The
 * number of processes currently in the cgroup is given by pids.current.
 * Organisational operations are not blocked by cgroup policies, so it is
 * possible to have pids.current > pids.max. However, it is not possible to
 * violate a cgroup policy through fork(). fork() will return -EAGAIN if forking
 * would cause a cgroup policy to be violated.
 *
 * To set a cgroup to have no limit, set pids.max to "max". This is the default
 * for all new cgroups (N.B. that PID limits are hierarchical, so the most
 * stringent limit in the hierarchy is followed).
 *
 * pids.current tracks all child cgroup hierarchies, so parent/pids.current is
 * a superset of parent/child/pids.current.
 *
 * Copyright (C) 2015 Aleksa Sarai <cyphar@cyphar.com>
 *
 * This file is subject to the terms and conditions of version 2 of the GNU
 * General Public License.  See the file COPYING in the main directory of the
 * Linux distribution for more details.
 */

#include <linux/kernel.h>
#include <linux/threads.h>
#include <linux/atomic.h>
#include <linux/cgroup.h>
#include <linux/slab.h>

#define PIDS_MAX (PID_MAX_LIMIT + 1ULL)
#define PIDS_MAX_STR "max"

struct pids_cgroup {
	struct cgroup_subsys_state	css;

	/*
	 * Use 64-bit types so that we can safely represent "max" as
	 * %PIDS_MAX = (%PID_MAX_LIMIT + 1).
	 */
	atomic64_t			counter;
	int64_t				limit;
};

static struct pids_cgroup *css_pids(struct cgroup_subsys_state *css)
{
	return container_of(css, struct pids_cgroup, css);
}

static struct pids_cgroup *parent_pids(struct pids_cgroup *pids)
{
	return css_pids(pids->css.parent);
}

static struct cgroup_subsys_state *
pids_css_alloc(struct cgroup_subsys_state *parent)
{
	struct pids_cgroup *pids;

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

	pids->limit = PIDS_MAX;
	atomic64_set(&pids->counter, 0);
	return &pids->css;
}

static void pids_css_free(struct cgroup_subsys_state *css)
{
	kfree(css_pids(css));
}

/**
 * pids_cancel - uncharge the local pid count
 * @pids: the pid cgroup state
 * @num: the number of pids to cancel
 *
 * This function will WARN if the pid count goes under 0, because such a case is
 * a bug in the pids controller proper.
 */
static void pids_cancel(struct pids_cgroup *pids, int num)
{
	/*
	 * A negative count (or overflow for that matter) is invalid,
	 * and indicates a bug in the `pids` controller proper.
	 */
	WARN_ON_ONCE(atomic64_add_negative(-num, &pids->counter));
}

/**
 * pids_uncharge - hierarchically uncharge the pid count
 * @pids: the pid cgroup state
 * @num: the number of pids to uncharge
 */
static void pids_uncharge(struct pids_cgroup *pids, int num)
{
	struct pids_cgroup *p;

	for (p = pids; p; p = parent_pids(p))
		pids_cancel(p, num);
}

/**
 * pids_charge - hierarchically charge the pid count
 * @pids: the pid cgroup state
 * @num: the number of pids to charge
 *
 * This function does *not* follow the pid limit set. It cannot fail and the new
 * pid count may exceed the limit. This is only used for reverting failed
 * attaches, where there is no other way out than violating the limit.
 */
static void pids_charge(struct pids_cgroup *pids, int num)
{
	struct pids_cgroup *p;

	for (p = pids; p; p = parent_pids(p))
		atomic64_add(num, &p->counter);
}

/**
 * pids_try_charge - hierarchically try to charge the pid count
 * @pids: the pid cgroup state
 * @num: the number of pids to charge
 *
 * This function follows the set limit. It will fail if the charge would cause
 * the new value to exceed the hierarchical limit. Returns 0 if the charge
 * succeded, otherwise -EAGAIN.
 */
static int pids_try_charge(struct pids_cgroup *pids, int num)
{
	struct pids_cgroup *p, *q;

	for (p = pids; p; p = parent_pids(p)) {
		int64_t new = atomic64_add_return(num, &p->counter);

		/*
		 * Since new is capped to the maximum number of pid_t, if
		 * p->limit is %PIDS_MAX then we know that this test will never
		 * fail.
		 */
		if (new > p->limit)
			goto revert;
	}

	return 0;

revert:
	for (q = pids; q != p; q = parent_pids(q))
		pids_cancel(q, num);
	pids_cancel(p, num);

	return -EAGAIN;
}

static int pids_can_attach(struct cgroup_subsys_state *css,
			   struct cgroup_taskset *tset)
{
	struct pids_cgroup *pids = css_pids(css);
	struct task_struct *task;

	cgroup_taskset_for_each(task, tset) {
		struct cgroup_subsys_state *old_css;
		struct pids_cgroup *old_pids;

		/*
		 * No need to pin @old_css between here and cancel_attach()
		 * because cgroup core protects it from being freed before
		 * the migration completes or fails.
		 */
		old_css = task_css(task, pids_cgrp_id);
		old_pids = css_pids(old_css);

		pids_charge(pids, 1);
		pids_uncharge(old_pids, 1);
	}

	return 0;
}

static void pids_cancel_attach(struct cgroup_subsys_state *css,
			       struct cgroup_taskset *tset)
{
	struct pids_cgroup *pids = css_pids(css);
	struct task_struct *task;

	cgroup_taskset_for_each(task, tset) {
		struct cgroup_subsys_state *old_css;
		struct pids_cgroup *old_pids;

		old_css = task_css(task, pids_cgrp_id);
		old_pids = css_pids(old_css);

		pids_charge(old_pids, 1);
		pids_uncharge(pids, 1);
	}
}

static int pids_can_fork(struct task_struct *task, void **priv_p)
{
	struct cgroup_subsys_state *css;
	struct pids_cgroup *pids;
	int err;

	/*
	 * Use the "current" task_css for the pids subsystem as the tentative
	 * css. It is possible we will charge the wrong hierarchy, in which
	 * case we will forcefully revert/reapply the charge on the right
	 * hierarchy after it is committed to the task proper.
	 */
	css = task_get_css(current, pids_cgrp_id);
	pids = css_pids(css);

	err = pids_try_charge(pids, 1);
	if (err)
		goto err_css_put;

	*priv_p = css;
	return 0;

err_css_put:
	css_put(css);
	return err;
}

static void pids_cancel_fork(struct task_struct *task, void *priv)
{
	struct cgroup_subsys_state *css = priv;
	struct pids_cgroup *pids = css_pids(css);

	pids_uncharge(pids, 1);
	css_put(css);
}

static void pids_fork(struct task_struct *task, void *priv)
{
	struct cgroup_subsys_state *css;
	struct cgroup_subsys_state *old_css = priv;
	struct pids_cgroup *pids;
	struct pids_cgroup *old_pids = css_pids(old_css);

	css = task_get_css(task, pids_cgrp_id);
	pids = css_pids(css);

	/*
	 * If the association has changed, we have to revert and reapply the
	 * charge/uncharge on the wrong hierarchy to the current one. Since
	 * the association can only change due to an organisation event, its
	 * okay for us to ignore the limit in this case.
	 */
	if (pids != old_pids) {
		pids_uncharge(old_pids, 1);
		pids_charge(pids, 1);
	}

	css_put(css);
	css_put(old_css);
}

static void pids_free(struct task_struct *task)
{
	struct pids_cgroup *pids = css_pids(task_css(task, pids_cgrp_id));

	pids_uncharge(pids, 1);
}

static ssize_t pids_max_write(struct kernfs_open_file *of, char *buf,
			      size_t nbytes, loff_t off)
{
	struct cgroup_subsys_state *css = of_css(of);
	struct pids_cgroup *pids = css_pids(css);
	int64_t limit;
	int err;

	buf = strstrip(buf);
	if (!strcmp(buf, PIDS_MAX_STR)) {
		limit = PIDS_MAX;
		goto set_limit;
	}

	err = kstrtoll(buf, 0, &limit);
	if (err)
		return err;

	if (limit < 0 || limit >= PIDS_MAX)
		return -EINVAL;

set_limit:
	/*
	 * Limit updates don't need to be mutex'd, since it isn't
	 * critical that any racing fork()s follow the new limit.
	 */
	pids->limit = limit;
	return nbytes;
}

static int pids_max_show(struct seq_file *sf, void *v)
{
	struct cgroup_subsys_state *css = seq_css(sf);
	struct pids_cgroup *pids = css_pids(css);
	int64_t limit = pids->limit;

	if (limit >= PIDS_MAX)
		seq_printf(sf, "%s\n", PIDS_MAX_STR);
	else
		seq_printf(sf, "%lld\n", limit);

	return 0;
}

static s64 pids_current_read(struct cgroup_subsys_state *css,
			     struct cftype *cft)
{
	struct pids_cgroup *pids = css_pids(css);

	return atomic64_read(&pids->counter);
}

static struct cftype pids_files[] = {
	{
		.name = "max",
		.write = pids_max_write,
		.seq_show = pids_max_show,
		.flags = CFTYPE_NOT_ON_ROOT,
	},
	{
		.name = "current",
		.read_s64 = pids_current_read,
	},
	{ }	/* terminate */
};

struct cgroup_subsys pids_cgrp_subsys = {
	.css_alloc	= pids_css_alloc,
	.css_free	= pids_css_free,
	.can_attach 	= pids_can_attach,
	.cancel_attach 	= pids_cancel_attach,
	.can_fork	= pids_can_fork,
	.cancel_fork	= pids_cancel_fork,
	.fork		= pids_fork,
	.free		= pids_free,
	.legacy_cftypes	= pids_files,
	.dfl_cftypes	= pids_files,
};