aboutsummaryrefslogtreecommitdiffstats
path: root/include/linux/cgroup.h
blob: b62bb9294d0c594618515c5f0214e963f7e3a904 (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
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
#ifndef _LINUX_CGROUP_H
#define _LINUX_CGROUP_H
/*
 *  cgroup interface
 *
 *  Copyright (C) 2003 BULL SA
 *  Copyright (C) 2004-2006 Silicon Graphics, Inc.
 *
 */

#include <linux/sched.h>
#include <linux/cpumask.h>
#include <linux/nodemask.h>
#include <linux/rcupdate.h>
#include <linux/cgroupstats.h>
#include <linux/prio_heap.h>
#include <linux/rwsem.h>
#include <linux/idr.h>

#ifdef CONFIG_CGROUPS

struct cgroupfs_root;
struct cgroup_subsys;
struct inode;
struct cgroup;
struct css_id;

extern int cgroup_init_early(void);
extern int cgroup_init(void);
extern void cgroup_lock(void);
extern bool cgroup_lock_live_group(struct cgroup *cgrp);
extern void cgroup_unlock(void);
extern void cgroup_fork(struct task_struct *p);
extern void cgroup_fork_callbacks(struct task_struct *p);
extern void cgroup_post_fork(struct task_struct *p);
extern void cgroup_exit(struct task_struct *p, int run_callbacks);
extern int cgroupstats_build(struct cgroupstats *stats,
				struct dentry *dentry);

extern struct file_operations proc_cgroup_operations;

/* Define the enumeration of all cgroup subsystems */
#define SUBSYS(_x) _x ## _subsys_id,
enum cgroup_subsys_id {
#include <linux/cgroup_subsys.h>
	CGROUP_SUBSYS_COUNT
};
#undef SUBSYS

/* Per-subsystem/per-cgroup state maintained by the system. */
struct cgroup_subsys_state {
	/*
	 * The cgroup that this subsystem is attached to. Useful
	 * for subsystems that want to know about the cgroup
	 * hierarchy structure
	 */
	struct cgroup *cgroup;

	/*
	 * State maintained by the cgroup system to allow subsystems
	 * to be "busy". Should be accessed via css_get(),
	 * css_tryget() and and css_put().
	 */

	atomic_t refcnt;

	unsigned long flags;
	/* ID for this css, if possible */
	struct css_id *id;
};

/* bits in struct cgroup_subsys_state flags field */
enum {
	CSS_ROOT, /* This CSS is the root of the subsystem */
	CSS_REMOVED, /* This CSS is dead */
};

/*
 * Call css_get() to hold a reference on the css; it can be used
 * for a reference obtained via:
 * - an existing ref-counted reference to the css
 * - task->cgroups for a locked task
 */

static inline void css_get(struct cgroup_subsys_state *css)
{
	/* We don't need to reference count the root state */
	if (!test_bit(CSS_ROOT, &css->flags))
		atomic_inc(&css->refcnt);
}

static inline bool css_is_removed(struct cgroup_subsys_state *css)
{
	return test_bit(CSS_REMOVED, &css->flags);
}

/*
 * Call css_tryget() to take a reference on a css if your existing
 * (known-valid) reference isn't already ref-counted. Returns false if
 * the css has been destroyed.
 */

static inline bool css_tryget(struct cgroup_subsys_state *css)
{
	if (test_bit(CSS_ROOT, &css->flags))
		return true;
	while (!atomic_inc_not_zero(&css->refcnt)) {
		if (test_bit(CSS_REMOVED, &css->flags))
			return false;
		cpu_relax();
	}
	return true;
}

/*
 * css_put() should be called to release a reference taken by
 * css_get() or css_tryget()
 */

extern void __css_put(struct cgroup_subsys_state *css);
static inline void css_put(struct cgroup_subsys_state *css)
{
	if (!test_bit(CSS_ROOT, &css->flags))
		__css_put(css);
}

/* bits in struct cgroup flags field */
enum {
	/* Control Group is dead */
	CGRP_REMOVED,
	/*
	 * Control Group has previously had a child cgroup or a task,
	 * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set)
	 */
	CGRP_RELEASABLE,
	/* Control Group requires release notifications to userspace */
	CGRP_NOTIFY_ON_RELEASE,
	/*
	 * A thread in rmdir() is wating for this cgroup.
	 */
	CGRP_WAIT_ON_RMDIR,
};

/* which pidlist file are we talking about? */
enum cgroup_filetype {
	CGROUP_FILE_PROCS,
	CGROUP_FILE_TASKS,
};

/*
 * A pidlist is a list of pids that virtually represents the contents of one
 * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists,
 * a pair (one each for procs, tasks) for each pid namespace that's relevant
 * to the cgroup.
 */
struct cgroup_pidlist {
	/*
	 * used to find which pidlist is wanted. doesn't change as long as
	 * this particular list stays in the list.
	 */
	struct { enum cgroup_filetype type; struct pid_namespace *ns; } key;
	/* array of xids */
	pid_t *list;
	/* how many elements the above list has */
	int length;
	/* how many files are using the current array */
	int use_count;
	/* each of these stored in a list by its cgroup */
	struct list_head links;
	/* pointer to the cgroup we belong to, for list removal purposes */
	struct cgroup *owner;
	/* protects the other fields */
	struct rw_semaphore mutex;
};

struct cgroup {
	unsigned long flags;		/* "unsigned long" so bitops work */

	/*
	 * count users of this cgroup. >0 means busy, but doesn't
	 * necessarily indicate the number of tasks in the cgroup
	 */
	atomic_t count;

	/*
	 * We link our 'sibling' struct into our parent's 'children'.
	 * Our children link their 'sibling' into our 'children'.
	 */
	struct list_head sibling;	/* my parent's children */
	struct list_head children;	/* my children */

	struct cgroup *parent;		/* my parent */
	struct dentry *dentry;	  	/* cgroup fs entry, RCU protected */

	/* Private pointers for each registered subsystem */
	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];

	struct cgroupfs_root *root;
	struct cgroup *top_cgroup;

	/*
	 * List of cg_cgroup_links pointing at css_sets with
	 * tasks in this cgroup. Protected by css_set_lock
	 */
	struct list_head css_sets;

	/*
	 * Linked list running through all cgroups that can
	 * potentially be reaped by the release agent. Protected by
	 * release_list_lock
	 */
	struct list_head release_list;

	/*
	 * list of pidlists, up to two for each namespace (one for procs, one
	 * for tasks); created on demand.
	 */
	struct list_head pidlists;
	struct mutex pidlist_mutex;

	/* For RCU-protected deletion */
	struct rcu_head rcu_head;
};

/*
 * A css_set is a structure holding pointers to a set of
 * cgroup_subsys_state objects. This saves space in the task struct
 * object and speeds up fork()/exit(), since a single inc/dec and a
 * list_add()/del() can bump the reference count on the entire cgroup
 * set for a task.
 */

struct css_set {

	/* Reference count */
	atomic_t refcount;

	/*
	 * List running through all cgroup groups in the same hash
	 * slot. Protected by css_set_lock
	 */
	struct hlist_node hlist;

	/*
	 * List running through all tasks using this cgroup
	 * group. Protected by css_set_lock
	 */
	struct list_head tasks;

	/*
	 * List of cg_cgroup_link objects on link chains from
	 * cgroups referenced from this css_set. Protected by
	 * css_set_lock
	 */
	struct list_head cg_links;

	/*
	 * Set of subsystem states, one for each subsystem. This array
	 * is immutable after creation apart from the init_css_set
	 * during subsystem registration (at boot time).
	 */
	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];

	/* For RCU-protected deletion */
	struct rcu_head rcu_head;
};

/*
 * cgroup_map_cb is an abstract callback API for reporting map-valued
 * control files
 */

struct cgroup_map_cb {
	int (*fill)(struct cgroup_map_cb *cb, const char *key, u64 value);
	void *state;
};

/*
 * struct cftype: handler definitions for cgroup control files
 *
 * When reading/writing to a file:
 *	- the cgroup to use is file->f_dentry->d_parent->d_fsdata
 *	- the 'cftype' of the file is file->f_dentry->d_fsdata
 */

#define MAX_CFTYPE_NAME 64
struct cftype {
	/*
	 * By convention, the name should begin with the name of the
	 * subsystem, followed by a period
	 */
	char name[MAX_CFTYPE_NAME];
	int private;
	/*
	 * If not 0, file mode is set to this value, otherwise it will
	 * be figured out automatically
	 */
	mode_t mode;

	/*
	 * If non-zero, defines the maximum length of string that can
	 * be passed to write_string; defaults to 64
	 */
	size_t max_write_len;

	int (*open)(struct inode *inode, struct file *file);
	ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft,
			struct file *file,
			char __user *buf, size_t nbytes, loff_t *ppos);
	/*
	 * read_u64() is a shortcut for the common case of returning a
	 * single integer. Use it in place of read()
	 */
	u64 (*read_u64)(struct cgroup *cgrp, struct cftype *cft);
	/*
	 * read_s64() is a signed version of read_u64()
	 */
	s64 (*read_s64)(struct cgroup *cgrp, struct cftype *cft);
	/*
	 * read_map() is used for defining a map of key/value
	 * pairs. It should call cb->fill(cb, key, value) for each
	 * entry. The key/value pairs (and their ordering) should not
	 * change between reboots.
	 */
	int (*read_map)(struct cgroup *cont, struct cftype *cft,
			struct cgroup_map_cb *cb);
	/*
	 * read_seq_string() is used for outputting a simple sequence
	 * using seqfile.
	 */
	int (*read_seq_string)(struct cgroup *cont, struct cftype *cft,
			       struct seq_file *m);

	ssize_t (*write)(struct cgroup *cgrp, struct cftype *cft,
			 struct file *file,
			 const char __user *buf, size_t nbytes, loff_t *ppos);

	/*
	 * write_u64() is a shortcut for the common case of accepting
	 * a single integer (as parsed by simple_strtoull) from
	 * userspace. Use in place of write(); return 0 or error.
	 */
	int (*write_u64)(struct cgroup *cgrp, struct cftype *cft, u64 val);
	/*
	 * write_s64() is a signed version of write_u64()
	 */
	int (*write_s64)(struct cgroup *cgrp, struct cftype *cft, s64 val);

	/*
	 * write_string() is passed a nul-terminated kernelspace
	 * buffer of maximum length determined by max_write_len.
	 * Returns 0 or -ve error code.
	 */
	int (*write_string)(struct cgroup *cgrp, struct cftype *cft,
			    const char *buffer);
	/*
	 * trigger() callback can be used to get some kick from the
	 * userspace, when the actual string written is not important
	 * at all. The private field can be used to determine the
	 * kick type for multiplexing.
	 */
	int (*trigger)(struct cgroup *cgrp, unsigned int event);

	int (*release)(struct inode *inode, struct file *file);
};

struct cgroup_scanner {
	struct cgroup *cg;
	int (*test_task)(struct task_struct *p, struct cgroup_scanner *scan);
	void (*process_task)(struct task_struct *p,
			struct cgroup_scanner *scan);
	struct ptr_heap *heap;
	void *data;
};

/*
 * Add a new file to the given cgroup directory. Should only be
 * called by subsystems from within a populate() method
 */
int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
		       const struct cftype *cft);

/*
 * Add a set of new files to the given cgroup directory. Should
 * only be called by subsystems from within a populate() method
 */
int cgroup_add_files(struct cgroup *cgrp,
			struct cgroup_subsys *subsys,
			const struct cftype cft[],
			int count);

int cgroup_is_removed(const struct cgroup *cgrp);

int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen);

int cgroup_task_count(const struct cgroup *cgrp);

/* Return true if cgrp is a descendant of the task's cgroup */
int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task);

/*
 * When the subsys has to access css and may add permanent refcnt to css,
 * it should take care of racy conditions with rmdir(). Following set of
 * functions, is for stop/restart rmdir if necessary.
 * Because these will call css_get/put, "css" should be alive css.
 *
 *  cgroup_exclude_rmdir();
 *  ...do some jobs which may access arbitrary empty cgroup
 *  cgroup_release_and_wakeup_rmdir();
 *
 *  When someone removes a cgroup while cgroup_exclude_rmdir() holds it,
 *  it sleeps and cgroup_release_and_wakeup_rmdir() will wake him up.
 */

void cgroup_exclude_rmdir(struct cgroup_subsys_state *css);
void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css);

/*
 * Control Group subsystem type.
 * See Documentation/cgroups/cgroups.txt for details
 */

struct cgroup_subsys {
	struct cgroup_subsys_state *(*create)(struct cgroup_subsys *ss,
						  struct cgroup *cgrp);
	int (*pre_destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp);
	void (*destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp);
	int (*can_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp,
			  struct task_struct *tsk, bool threadgroup);
	void (*attach)(struct cgroup_subsys *ss, struct cgroup *cgrp,
			struct cgroup *old_cgrp, struct task_struct *tsk,
			bool threadgroup);
	void (*fork)(struct cgroup_subsys *ss, struct task_struct *task);
	void (*exit)(struct cgroup_subsys *ss, struct task_struct *task);
	int (*populate)(struct cgroup_subsys *ss,
			struct cgroup *cgrp);
	void (*post_clone)(struct cgroup_subsys *ss, struct cgroup *cgrp);
	void (*bind)(struct cgroup_subsys *ss, struct cgroup *root);

	int subsys_id;
	int active;
	int disabled;
	int early_init;
	/*
	 * True if this subsys uses ID. ID is not available before cgroup_init()
	 * (not available in early_init time.)
	 */
	bool use_id;
#define MAX_CGROUP_TYPE_NAMELEN 32
	const char *name;

	/*
	 * Protects sibling/children links of cgroups in this
	 * hierarchy, plus protects which hierarchy (or none) the
	 * subsystem is a part of (i.e. root/sibling).  To avoid
	 * potential deadlocks, the following operations should not be
	 * undertaken while holding any hierarchy_mutex:
	 *
	 * - allocating memory
	 * - initiating hotplug events
	 */
	struct mutex hierarchy_mutex;
	struct lock_class_key subsys_key;

	/*
	 * Link to parent, and list entry in parent's children.
	 * Protected by this->hierarchy_mutex and cgroup_lock()
	 */
	struct cgroupfs_root *root;
	struct list_head sibling;
	/* used when use_id == true */
	struct idr idr;
	spinlock_t id_lock;
};

#define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys;
#include <linux/cgroup_subsys.h>
#undef SUBSYS

static inline struct cgroup_subsys_state *cgroup_subsys_state(
	struct cgroup *cgrp, int subsys_id)
{
	return cgrp->subsys[subsys_id];
}

static inline struct cgroup_subsys_state *task_subsys_state(
	struct task_struct *task, int subsys_id)
{
	return rcu_dereference(task->cgroups->subsys[subsys_id]);
}

static inline struct cgroup* task_cgroup(struct task_struct *task,
					       int subsys_id)
{
	return task_subsys_state(task, subsys_id)->cgroup;
}

int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *ss,
							char *nodename);

/* A cgroup_iter should be treated as an opaque object */
struct cgroup_iter {
	struct list_head *cg_link;
	struct list_head *task;
};

/*
 * To iterate across the tasks in a cgroup:
 *
 * 1) call cgroup_iter_start to intialize an iterator
 *
 * 2) call cgroup_iter_next() to retrieve member tasks until it
 *    returns NULL or until you want to end the iteration
 *
 * 3) call cgroup_iter_end() to destroy the iterator.
 *
 * Or, call cgroup_scan_tasks() to iterate through every task in a
 * cgroup - cgroup_scan_tasks() holds the css_set_lock when calling
 * the test_task() callback, but not while calling the process_task()
 * callback.
 */
void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it);
struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
					struct cgroup_iter *it);
void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it);
int cgroup_scan_tasks(struct cgroup_scanner *scan);
int cgroup_attach_task(struct cgroup *, struct task_struct *);

/*
 * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works
 * if cgroup_subsys.use_id == true. It can be used for looking up and scanning.
 * CSS ID is assigned at cgroup allocation (create) automatically
 * and removed when subsys calls free_css_id() function. This is because
 * the lifetime of cgroup_subsys_state is subsys's matter.
 *
 * Looking up and scanning function should be called under rcu_read_lock().
 * Taking cgroup_mutex()/hierarchy_mutex() is not necessary for following calls.
 * But the css returned by this routine can be "not populated yet" or "being
 * destroyed". The caller should check css and cgroup's status.
 */

/*
 * Typically Called at ->destroy(), or somewhere the subsys frees
 * cgroup_subsys_state.
 */
void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css);

/* Find a cgroup_subsys_state which has given ID */

struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id);

/*
 * Get a cgroup whose id is greater than or equal to id under tree of root.
 * Returning a cgroup_subsys_state or NULL.
 */
struct cgroup_subsys_state *css_get_next(struct cgroup_subsys *ss, int id,
		struct cgroup_subsys_state *root, int *foundid);

/* Returns true if root is ancestor of cg */
bool css_is_ancestor(struct cgroup_subsys_state *cg,
		     const struct cgroup_subsys_state *root);

/* Get id and depth of css */
unsigned short css_id(struct cgroup_subsys_state *css);
unsigned short css_depth(struct cgroup_subsys_state *css);

#else /* !CONFIG_CGROUPS */

static inline int cgroup_init_early(void) { return 0; }
static inline int cgroup_init(void) { return 0; }
static inline void cgroup_fork(struct task_struct *p) {}
static inline void cgroup_fork_callbacks(struct task_struct *p) {}
static inline void cgroup_post_fork(struct task_struct *p) {}
static inline void cgroup_exit(struct task_struct *p, int callbacks) {}

static inline void cgroup_lock(void) {}
static inline void cgroup_unlock(void) {}
static inline int cgroupstats_build(struct cgroupstats *stats,
					struct dentry *dentry)
{
	return -EINVAL;
}

#endif /* !CONFIG_CGROUPS */

#endif /* _LINUX_CGROUP_H */