summaryrefslogtreecommitdiffstats
path: root/kernel/cgroup.c
blob: 6ba857bec71ba5caeea419975037ef22d9ae8841 (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
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
/*
 *  kernel/cgroup.c
 *
 *  Generic process-grouping system.
 *
 *  Based originally on the cpuset system, extracted by Paul Menage
 *  Copyright (C) 2006 Google, Inc
 *
 *  Copyright notices from the original cpuset code:
 *  --------------------------------------------------
 *  Copyright (C) 2003 BULL SA.
 *  Copyright (C) 2004-2006 Silicon Graphics, 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.
 *  ---------------------------------------------------
 *
 *  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/cgroup.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/magic.h>
#include <linux/spinlock.h>
#include <linux/string.h>

#include <asm/atomic.h>

/* Generate an array of cgroup subsystem pointers */
#define SUBSYS(_x) &_x ## _subsys,

static struct cgroup_subsys *subsys[] = {
#include <linux/cgroup_subsys.h>
};

/*
 * A cgroupfs_root represents the root of a cgroup hierarchy,
 * and may be associated with a superblock to form an active
 * hierarchy
 */
struct cgroupfs_root {
	struct super_block *sb;

	/*
	 * The bitmask of subsystems intended to be attached to this
	 * hierarchy
	 */
	unsigned long subsys_bits;

	/* The bitmask of subsystems currently attached to this hierarchy */
	unsigned long actual_subsys_bits;

	/* A list running through the attached subsystems */
	struct list_head subsys_list;

	/* The root cgroup for this hierarchy */
	struct cgroup top_cgroup;

	/* Tracks how many cgroups are currently defined in hierarchy.*/
	int number_of_cgroups;

	/* A list running through the mounted hierarchies */
	struct list_head root_list;

	/* Hierarchy-specific flags */
	unsigned long flags;
};


/*
 * The "rootnode" hierarchy is the "dummy hierarchy", reserved for the
 * subsystems that are otherwise unattached - it never has more than a
 * single cgroup, and all tasks are part of that cgroup.
 */
static struct cgroupfs_root rootnode;

/* The list of hierarchy roots */

static LIST_HEAD(roots);

/* dummytop is a shorthand for the dummy hierarchy's top cgroup */
#define dummytop (&rootnode.top_cgroup)

/* This flag indicates whether tasks in the fork and exit paths should
 * take callback_mutex and check for fork/exit handlers to call. This
 * avoids us having to do extra work in the fork/exit path if none of the
 * subsystems need to be called.
 */
static int need_forkexit_callback;

/* bits in struct cgroup flags field */
enum {
	CONT_REMOVED,
};

/* convenient tests for these bits */
inline int cgroup_is_removed(const struct cgroup *cont)
{
	return test_bit(CONT_REMOVED, &cont->flags);
}

/* bits in struct cgroupfs_root flags field */
enum {
	ROOT_NOPREFIX, /* mounted subsystems have no named prefix */
};

/*
 * for_each_subsys() allows you to iterate on each subsystem attached to
 * an active hierarchy
 */
#define for_each_subsys(_root, _ss) \
list_for_each_entry(_ss, &_root->subsys_list, sibling)

/* for_each_root() allows you to iterate across the active hierarchies */
#define for_each_root(_root) \
list_for_each_entry(_root, &roots, root_list)

/*
 * There is one global cgroup mutex. We also require taking
 * task_lock() when dereferencing a task's cgroup subsys pointers.
 * See "The task_lock() exception", at the end of this comment.
 *
 * A task must hold cgroup_mutex to modify cgroups.
 *
 * Any task can increment and decrement the count field without lock.
 * So in general, code holding cgroup_mutex can't rely on the count
 * field not changing.  However, if the count goes to zero, then only
 * attach_task() 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 cgroup can fork (the other way to
 * increment the count).  So code holding cgroup_mutex can safely
 * assume that if the count is zero, it will stay zero. Similarly, if
 * a task holds cgroup_mutex on a cgroup with zero count, it
 * knows that the cgroup won't be removed, as cgroup_rmdir()
 * needs that mutex.
 *
 * The cgroup_common_file_write handler for operations that modify
 * the cgroup hierarchy holds cgroup_mutex across the entire operation,
 * single threading all such cgroup modifications across the system.
 *
 * The fork and exit callbacks cgroup_fork() and cgroup_exit(), don't
 * (usually) take cgroup_mutex.  These are the two most performance
 * critical pieces of code here.  The exception occurs on cgroup_exit(),
 * when a task in a notify_on_release cgroup exits.  Then cgroup_mutex
 * is taken, and if the cgroup count is zero, a usermode call made
 * to /sbin/cgroup_release_agent with the name of the cgroup (path
 * relative to the root of cgroup file system) as the argument.
 *
 * A cgroup can only be deleted if both its 'count' of using tasks
 * is zero, and its list of 'children' cgroups is empty.  Since all
 * tasks in the system use _some_ cgroup, and since there is always at
 * least one task in the system (init, pid == 1), therefore, top_cgroup
 * always has either children cgroups and/or using tasks.  So we don't
 * need a special hack to ensure that top_cgroup cannot be deleted.
 *
 *	The task_lock() exception
 *
 * The need for this exception arises from the action of
 * attach_task(), which overwrites one tasks cgroup pointer with
 * another.  It does so using cgroup_mutexe, however there are
 * several performance critical places that need to reference
 * task->cgroup without the expense of grabbing a system global
 * mutex.  Therefore except as noted below, when dereferencing or, as
 * in attach_task(), modifying a task'ss cgroup 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 cgroup pointer by attach_task()
 */

static DEFINE_MUTEX(cgroup_mutex);

/**
 * cgroup_lock - lock out any changes to cgroup structures
 *
 */

void cgroup_lock(void)
{
	mutex_lock(&cgroup_mutex);
}

/**
 * cgroup_unlock - release lock on cgroup changes
 *
 * Undo the lock taken in a previous cgroup_lock() call.
 */

void cgroup_unlock(void)
{
	mutex_unlock(&cgroup_mutex);
}

/*
 * A couple of forward declarations required, due to cyclic reference loop:
 * cgroup_mkdir -> cgroup_create -> cgroup_populate_dir ->
 * cgroup_add_file -> cgroup_create_file -> cgroup_dir_inode_operations
 * -> cgroup_mkdir.
 */

static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode);
static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cont);
static struct inode_operations cgroup_dir_inode_operations;

static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
{
	struct inode *inode = new_inode(sb);
	static struct backing_dev_info cgroup_backing_dev_info = {
		.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
	};

	if (inode) {
		inode->i_mode = mode;
		inode->i_uid = current->fsuid;
		inode->i_gid = current->fsgid;
		inode->i_blocks = 0;
		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info;
	}
	return inode;
}

static void cgroup_diput(struct dentry *dentry, struct inode *inode)
{
	/* is dentry a directory ? if so, kfree() associated cgroup */
	if (S_ISDIR(inode->i_mode)) {
		struct cgroup *cont = dentry->d_fsdata;
		BUG_ON(!(cgroup_is_removed(cont)));
		kfree(cont);
	}
	iput(inode);
}

static void remove_dir(struct dentry *d)
{
	struct dentry *parent = dget(d->d_parent);

	d_delete(d);
	simple_rmdir(parent->d_inode, d);
	dput(parent);
}

static void cgroup_clear_directory(struct dentry *dentry)
{
	struct list_head *node;

	BUG_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
	spin_lock(&dcache_lock);
	node = dentry->d_subdirs.next;
	while (node != &dentry->d_subdirs) {
		struct dentry *d = list_entry(node, struct dentry, d_u.d_child);
		list_del_init(node);
		if (d->d_inode) {
			/* This should never be called on a cgroup
			 * directory with child cgroups */
			BUG_ON(d->d_inode->i_mode & S_IFDIR);
			d = dget_locked(d);
			spin_unlock(&dcache_lock);
			d_delete(d);
			simple_unlink(dentry->d_inode, d);
			dput(d);
			spin_lock(&dcache_lock);
		}
		node = dentry->d_subdirs.next;
	}
	spin_unlock(&dcache_lock);
}

/*
 * NOTE : the dentry must have been dget()'ed
 */
static void cgroup_d_remove_dir(struct dentry *dentry)
{
	cgroup_clear_directory(dentry);

	spin_lock(&dcache_lock);
	list_del_init(&dentry->d_u.d_child);
	spin_unlock(&dcache_lock);
	remove_dir(dentry);
}

static int rebind_subsystems(struct cgroupfs_root *root,
			      unsigned long final_bits)
{
	unsigned long added_bits, removed_bits;
	struct cgroup *cont = &root->top_cgroup;
	int i;

	removed_bits = root->actual_subsys_bits & ~final_bits;
	added_bits = final_bits & ~root->actual_subsys_bits;
	/* Check that any added subsystems are currently free */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		unsigned long long bit = 1ull << i;
		struct cgroup_subsys *ss = subsys[i];
		if (!(bit & added_bits))
			continue;
		if (ss->root != &rootnode) {
			/* Subsystem isn't free */
			return -EBUSY;
		}
	}

	/* Currently we don't handle adding/removing subsystems when
	 * any child cgroups exist. This is theoretically supportable
	 * but involves complex error handling, so it's being left until
	 * later */
	if (!list_empty(&cont->children))
		return -EBUSY;

	/* Process each subsystem */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		unsigned long bit = 1UL << i;
		if (bit & added_bits) {
			/* We're binding this subsystem to this hierarchy */
			BUG_ON(cont->subsys[i]);
			BUG_ON(!dummytop->subsys[i]);
			BUG_ON(dummytop->subsys[i]->cgroup != dummytop);
			cont->subsys[i] = dummytop->subsys[i];
			cont->subsys[i]->cgroup = cont;
			list_add(&ss->sibling, &root->subsys_list);
			rcu_assign_pointer(ss->root, root);
			if (ss->bind)
				ss->bind(ss, cont);

		} else if (bit & removed_bits) {
			/* We're removing this subsystem */
			BUG_ON(cont->subsys[i] != dummytop->subsys[i]);
			BUG_ON(cont->subsys[i]->cgroup != cont);
			if (ss->bind)
				ss->bind(ss, dummytop);
			dummytop->subsys[i]->cgroup = dummytop;
			cont->subsys[i] = NULL;
			rcu_assign_pointer(subsys[i]->root, &rootnode);
			list_del(&ss->sibling);
		} else if (bit & final_bits) {
			/* Subsystem state should already exist */
			BUG_ON(!cont->subsys[i]);
		} else {
			/* Subsystem state shouldn't exist */
			BUG_ON(cont->subsys[i]);
		}
	}
	root->subsys_bits = root->actual_subsys_bits = final_bits;
	synchronize_rcu();

	return 0;
}

static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
	struct cgroupfs_root *root = vfs->mnt_sb->s_fs_info;
	struct cgroup_subsys *ss;

	mutex_lock(&cgroup_mutex);
	for_each_subsys(root, ss)
		seq_printf(seq, ",%s", ss->name);
	if (test_bit(ROOT_NOPREFIX, &root->flags))
		seq_puts(seq, ",noprefix");
	mutex_unlock(&cgroup_mutex);
	return 0;
}

struct cgroup_sb_opts {
	unsigned long subsys_bits;
	unsigned long flags;
};

/* Convert a hierarchy specifier into a bitmask of subsystems and
 * flags. */
static int parse_cgroupfs_options(char *data,
				     struct cgroup_sb_opts *opts)
{
	char *token, *o = data ?: "all";

	opts->subsys_bits = 0;
	opts->flags = 0;

	while ((token = strsep(&o, ",")) != NULL) {
		if (!*token)
			return -EINVAL;
		if (!strcmp(token, "all")) {
			opts->subsys_bits = (1 << CGROUP_SUBSYS_COUNT) - 1;
		} else if (!strcmp(token, "noprefix")) {
			set_bit(ROOT_NOPREFIX, &opts->flags);
		} else {
			struct cgroup_subsys *ss;
			int i;
			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
				ss = subsys[i];
				if (!strcmp(token, ss->name)) {
					set_bit(i, &opts->subsys_bits);
					break;
				}
			}
			if (i == CGROUP_SUBSYS_COUNT)
				return -ENOENT;
		}
	}

	/* We can't have an empty hierarchy */
	if (!opts->subsys_bits)
		return -EINVAL;

	return 0;
}

static int cgroup_remount(struct super_block *sb, int *flags, char *data)
{
	int ret = 0;
	struct cgroupfs_root *root = sb->s_fs_info;
	struct cgroup *cont = &root->top_cgroup;
	struct cgroup_sb_opts opts;

	mutex_lock(&cont->dentry->d_inode->i_mutex);
	mutex_lock(&cgroup_mutex);

	/* See what subsystems are wanted */
	ret = parse_cgroupfs_options(data, &opts);
	if (ret)
		goto out_unlock;

	/* Don't allow flags to change at remount */
	if (opts.flags != root->flags) {
		ret = -EINVAL;
		goto out_unlock;
	}

	ret = rebind_subsystems(root, opts.subsys_bits);

	/* (re)populate subsystem files */
	if (!ret)
		cgroup_populate_dir(cont);

 out_unlock:
	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&cont->dentry->d_inode->i_mutex);
	return ret;
}

static struct super_operations cgroup_ops = {
	.statfs = simple_statfs,
	.drop_inode = generic_delete_inode,
	.show_options = cgroup_show_options,
	.remount_fs = cgroup_remount,
};

static void init_cgroup_root(struct cgroupfs_root *root)
{
	struct cgroup *cont = &root->top_cgroup;
	INIT_LIST_HEAD(&root->subsys_list);
	INIT_LIST_HEAD(&root->root_list);
	root->number_of_cgroups = 1;
	cont->root = root;
	cont->top_cgroup = cont;
	INIT_LIST_HEAD(&cont->sibling);
	INIT_LIST_HEAD(&cont->children);
}

static int cgroup_test_super(struct super_block *sb, void *data)
{
	struct cgroupfs_root *new = data;
	struct cgroupfs_root *root = sb->s_fs_info;

	/* First check subsystems */
	if (new->subsys_bits != root->subsys_bits)
	    return 0;

	/* Next check flags */
	if (new->flags != root->flags)
		return 0;

	return 1;
}

static int cgroup_set_super(struct super_block *sb, void *data)
{
	int ret;
	struct cgroupfs_root *root = data;

	ret = set_anon_super(sb, NULL);
	if (ret)
		return ret;

	sb->s_fs_info = root;
	root->sb = sb;

	sb->s_blocksize = PAGE_CACHE_SIZE;
	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
	sb->s_magic = CGROUP_SUPER_MAGIC;
	sb->s_op = &cgroup_ops;

	return 0;
}

static int cgroup_get_rootdir(struct super_block *sb)
{
	struct inode *inode =
		cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb);
	struct dentry *dentry;

	if (!inode)
		return -ENOMEM;

	inode->i_op = &simple_dir_inode_operations;
	inode->i_fop = &simple_dir_operations;
	inode->i_op = &cgroup_dir_inode_operations;
	/* directories start off with i_nlink == 2 (for "." entry) */
	inc_nlink(inode);
	dentry = d_alloc_root(inode);
	if (!dentry) {
		iput(inode);
		return -ENOMEM;
	}
	sb->s_root = dentry;
	return 0;
}

static int cgroup_get_sb(struct file_system_type *fs_type,
			 int flags, const char *unused_dev_name,
			 void *data, struct vfsmount *mnt)
{
	struct cgroup_sb_opts opts;
	int ret = 0;
	struct super_block *sb;
	struct cgroupfs_root *root;

	/* First find the desired set of subsystems */
	ret = parse_cgroupfs_options(data, &opts);
	if (ret)
		return ret;

	root = kzalloc(sizeof(*root), GFP_KERNEL);
	if (!root)
		return -ENOMEM;

	init_cgroup_root(root);
	root->subsys_bits = opts.subsys_bits;
	root->flags = opts.flags;

	sb = sget(fs_type, cgroup_test_super, cgroup_set_super, root);

	if (IS_ERR(sb)) {
		kfree(root);
		return PTR_ERR(sb);
	}

	if (sb->s_fs_info != root) {
		/* Reusing an existing superblock */
		BUG_ON(sb->s_root == NULL);
		kfree(root);
		root = NULL;
	} else {
		/* New superblock */
		struct cgroup *cont = &root->top_cgroup;

		BUG_ON(sb->s_root != NULL);

		ret = cgroup_get_rootdir(sb);
		if (ret)
			goto drop_new_super;

		mutex_lock(&cgroup_mutex);

		ret = rebind_subsystems(root, root->subsys_bits);
		if (ret == -EBUSY) {
			mutex_unlock(&cgroup_mutex);
			goto drop_new_super;
		}

		/* EBUSY should be the only error here */
		BUG_ON(ret);

		list_add(&root->root_list, &roots);

		sb->s_root->d_fsdata = &root->top_cgroup;
		root->top_cgroup.dentry = sb->s_root;

		BUG_ON(!list_empty(&cont->sibling));
		BUG_ON(!list_empty(&cont->children));
		BUG_ON(root->number_of_cgroups != 1);

		/*
		 * I believe that it's safe to nest i_mutex inside
		 * cgroup_mutex in this case, since no-one else can
		 * be accessing this directory yet. But we still need
		 * to teach lockdep that this is the case - currently
		 * a cgroupfs remount triggers a lockdep warning
		 */
		mutex_lock(&cont->dentry->d_inode->i_mutex);
		cgroup_populate_dir(cont);
		mutex_unlock(&cont->dentry->d_inode->i_mutex);
		mutex_unlock(&cgroup_mutex);
	}

	return simple_set_mnt(mnt, sb);

 drop_new_super:
	up_write(&sb->s_umount);
	deactivate_super(sb);
	return ret;
}

static void cgroup_kill_sb(struct super_block *sb) {
	struct cgroupfs_root *root = sb->s_fs_info;
	struct cgroup *cont = &root->top_cgroup;
	int ret;

	BUG_ON(!root);

	BUG_ON(root->number_of_cgroups != 1);
	BUG_ON(!list_empty(&cont->children));
	BUG_ON(!list_empty(&cont->sibling));

	mutex_lock(&cgroup_mutex);

	/* Rebind all subsystems back to the default hierarchy */
	ret = rebind_subsystems(root, 0);
	/* Shouldn't be able to fail ... */
	BUG_ON(ret);

	if (!list_empty(&root->root_list))
		list_del(&root->root_list);
	mutex_unlock(&cgroup_mutex);

	kfree(root);
	kill_litter_super(sb);
}

static struct file_system_type cgroup_fs_type = {
	.name = "cgroup",
	.get_sb = cgroup_get_sb,
	.kill_sb = cgroup_kill_sb,
};

static inline struct cgroup *__d_cont(struct dentry *dentry)
{
	return dentry->d_fsdata;
}

static inline struct cftype *__d_cft(struct dentry *dentry)
{
	return dentry->d_fsdata;
}

/*
 * Called with cgroup_mutex held.  Writes path of cgroup into buf.
 * Returns 0 on success, -errno on error.
 */
int cgroup_path(const struct cgroup *cont, char *buf, int buflen)
{
	char *start;

	if (cont == dummytop) {
		/*
		 * Inactive subsystems have no dentry for their root
		 * cgroup
		 */
		strcpy(buf, "/");
		return 0;
	}

	start = buf + buflen;

	*--start = '\0';
	for (;;) {
		int len = cont->dentry->d_name.len;
		if ((start -= len) < buf)
			return -ENAMETOOLONG;
		memcpy(start, cont->dentry->d_name.name, len);
		cont = cont->parent;
		if (!cont)
			break;
		if (!cont->parent)
			continue;
		if (--start < buf)
			return -ENAMETOOLONG;
		*start = '/';
	}
	memmove(buf, start, buf + buflen - start);
	return 0;
}

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

enum cgroup_filetype {
	FILE_ROOT,
	FILE_DIR,
	FILE_TASKLIST,
};

static ssize_t cgroup_file_write(struct file *file, const char __user *buf,
						size_t nbytes, loff_t *ppos)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	struct cgroup *cont = __d_cont(file->f_dentry->d_parent);

	if (!cft)
		return -ENODEV;
	if (!cft->write)
		return -EINVAL;

	return cft->write(cont, cft, file, buf, nbytes, ppos);
}

static ssize_t cgroup_read_uint(struct cgroup *cont, struct cftype *cft,
				   struct file *file,
				   char __user *buf, size_t nbytes,
				   loff_t *ppos)
{
	char tmp[64];
	u64 val = cft->read_uint(cont, cft);
	int len = sprintf(tmp, "%llu\n", (unsigned long long) val);

	return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
}

static ssize_t cgroup_file_read(struct file *file, char __user *buf,
				   size_t nbytes, loff_t *ppos)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	struct cgroup *cont = __d_cont(file->f_dentry->d_parent);

	if (!cft)
		return -ENODEV;

	if (cft->read)
		return cft->read(cont, cft, file, buf, nbytes, ppos);
	if (cft->read_uint)
		return cgroup_read_uint(cont, cft, file, buf, nbytes, ppos);
	return -EINVAL;
}

static int cgroup_file_open(struct inode *inode, struct file *file)
{
	int err;
	struct cftype *cft;

	err = generic_file_open(inode, file);
	if (err)
		return err;

	cft = __d_cft(file->f_dentry);
	if (!cft)
		return -ENODEV;
	if (cft->open)
		err = cft->open(inode, file);
	else
		err = 0;

	return err;
}

static int cgroup_file_release(struct inode *inode, struct file *file)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	if (cft->release)
		return cft->release(inode, file);
	return 0;
}

/*
 * cgroup_rename - Only allow simple rename of directories in place.
 */
static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
			    struct inode *new_dir, struct dentry *new_dentry)
{
	if (!S_ISDIR(old_dentry->d_inode->i_mode))
		return -ENOTDIR;
	if (new_dentry->d_inode)
		return -EEXIST;
	if (old_dir != new_dir)
		return -EIO;
	return simple_rename(old_dir, old_dentry, new_dir, new_dentry);
}

static struct file_operations cgroup_file_operations = {
	.read = cgroup_file_read,
	.write = cgroup_file_write,
	.llseek = generic_file_llseek,
	.open = cgroup_file_open,
	.release = cgroup_file_release,
};

static struct inode_operations cgroup_dir_inode_operations = {
	.lookup = simple_lookup,
	.mkdir = cgroup_mkdir,
	.rmdir = cgroup_rmdir,
	.rename = cgroup_rename,
};

static int cgroup_create_file(struct dentry *dentry, int mode,
				struct super_block *sb)
{
	static struct dentry_operations cgroup_dops = {
		.d_iput = cgroup_diput,
	};

	struct inode *inode;

	if (!dentry)
		return -ENOENT;
	if (dentry->d_inode)
		return -EEXIST;

	inode = cgroup_new_inode(mode, sb);
	if (!inode)
		return -ENOMEM;

	if (S_ISDIR(mode)) {
		inode->i_op = &cgroup_dir_inode_operations;
		inode->i_fop = &simple_dir_operations;

		/* start off with i_nlink == 2 (for "." entry) */
		inc_nlink(inode);

		/* start with the directory inode held, so that we can
		 * populate it without racing with another mkdir */
		mutex_lock(&inode->i_mutex);
	} else if (S_ISREG(mode)) {
		inode->i_size = 0;
		inode->i_fop = &cgroup_file_operations;
	}
	dentry->d_op = &cgroup_dops;
	d_instantiate(dentry, inode);
	dget(dentry);	/* Extra count - pin the dentry in core */
	return 0;
}

/*
 *	cgroup_create_dir - create a directory for an object.
 *	cont:	the cgroup we create the directory for.
 *		It must have a valid ->parent field
 *		And we are going to fill its ->dentry field.
 *	dentry: dentry of the new container
 *	mode:	mode to set on new directory.
 */
static int cgroup_create_dir(struct cgroup *cont, struct dentry *dentry,
				int mode)
{
	struct dentry *parent;
	int error = 0;

	parent = cont->parent->dentry;
	error = cgroup_create_file(dentry, S_IFDIR | mode, cont->root->sb);
	if (!error) {
		dentry->d_fsdata = cont;
		inc_nlink(parent->d_inode);
		cont->dentry = dentry;
		dget(dentry);
	}
	dput(dentry);

	return error;
}

int cgroup_add_file(struct cgroup *cont,
		       struct cgroup_subsys *subsys,
		       const struct cftype *cft)
{
	struct dentry *dir = cont->dentry;
	struct dentry *dentry;
	int error;

	char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };
	if (subsys && !test_bit(ROOT_NOPREFIX, &cont->root->flags)) {
		strcpy(name, subsys->name);
		strcat(name, ".");
	}
	strcat(name, cft->name);
	BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex));
	dentry = lookup_one_len(name, dir, strlen(name));
	if (!IS_ERR(dentry)) {
		error = cgroup_create_file(dentry, 0644 | S_IFREG,
						cont->root->sb);
		if (!error)
			dentry->d_fsdata = (void *)cft;
		dput(dentry);
	} else
		error = PTR_ERR(dentry);
	return error;
}

int cgroup_add_files(struct cgroup *cont,
			struct cgroup_subsys *subsys,
			const struct cftype cft[],
			int count)
{
	int i, err;
	for (i = 0; i < count; i++) {
		err = cgroup_add_file(cont, subsys, &cft[i]);
		if (err)
			return err;
	}
	return 0;
}

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

	/* First clear out any existing files */
	cgroup_clear_directory(cont->dentry);

	for_each_subsys(cont->root, ss) {
		if (ss->populate && (err = ss->populate(ss, cont)) < 0)
			return err;
	}

	return 0;
}

static void init_cgroup_css(struct cgroup_subsys_state *css,
			       struct cgroup_subsys *ss,
			       struct cgroup *cont)
{
	css->cgroup = cont;
	atomic_set(&css->refcnt, 0);
	css->flags = 0;
	if (cont == dummytop)
		set_bit(CSS_ROOT, &css->flags);
	BUG_ON(cont->subsys[ss->subsys_id]);
	cont->subsys[ss->subsys_id] = css;
}

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

static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
			     int mode)
{
	struct cgroup *cont;
	struct cgroupfs_root *root = parent->root;
	int err = 0;
	struct cgroup_subsys *ss;
	struct super_block *sb = root->sb;

	cont = kzalloc(sizeof(*cont), GFP_KERNEL);
	if (!cont)
		return -ENOMEM;

	/* Grab a reference on the superblock so the hierarchy doesn't
	 * get deleted on unmount if there are child cgroups.  This
	 * can be done outside cgroup_mutex, since the sb can't
	 * disappear while someone has an open control file on the
	 * fs */
	atomic_inc(&sb->s_active);

	mutex_lock(&cgroup_mutex);

	cont->flags = 0;
	INIT_LIST_HEAD(&cont->sibling);
	INIT_LIST_HEAD(&cont->children);

	cont->parent = parent;
	cont->root = parent->root;
	cont->top_cgroup = parent->top_cgroup;

	for_each_subsys(root, ss) {
		struct cgroup_subsys_state *css = ss->create(ss, cont);
		if (IS_ERR(css)) {
			err = PTR_ERR(css);
			goto err_destroy;
		}
		init_cgroup_css(css, ss, cont);
	}

	list_add(&cont->sibling, &cont->parent->children);
	root->number_of_cgroups++;

	err = cgroup_create_dir(cont, dentry, mode);
	if (err < 0)
		goto err_remove;

	/* The cgroup directory was pre-locked for us */
	BUG_ON(!mutex_is_locked(&cont->dentry->d_inode->i_mutex));

	err = cgroup_populate_dir(cont);
	/* If err < 0, we have a half-filled directory - oh well ;) */

	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&cont->dentry->d_inode->i_mutex);

	return 0;

 err_remove:

	list_del(&cont->sibling);
	root->number_of_cgroups--;

 err_destroy:

	for_each_subsys(root, ss) {
		if (cont->subsys[ss->subsys_id])
			ss->destroy(ss, cont);
	}

	mutex_unlock(&cgroup_mutex);

	/* Release the reference count that we took on the superblock */
	deactivate_super(sb);

	kfree(cont);
	return err;
}

static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
	struct cgroup *c_parent = dentry->d_parent->d_fsdata;

	/* the vfs holds inode->i_mutex already */
	return cgroup_create(c_parent, dentry, mode | S_IFDIR);
}

static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
{
	struct cgroup *cont = dentry->d_fsdata;
	struct dentry *d;
	struct cgroup *parent;
	struct cgroup_subsys *ss;
	struct super_block *sb;
	struct cgroupfs_root *root;
	int css_busy = 0;

	/* the vfs holds both inode->i_mutex already */

	mutex_lock(&cgroup_mutex);
	if (atomic_read(&cont->count) != 0) {
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}
	if (!list_empty(&cont->children)) {
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}

	parent = cont->parent;
	root = cont->root;
	sb = root->sb;

	/* Check the reference count on each subsystem. Since we
	 * already established that there are no tasks in the
	 * cgroup, if the css refcount is also 0, then there should
	 * be no outstanding references, so the subsystem is safe to
	 * destroy */
	for_each_subsys(root, ss) {
		struct cgroup_subsys_state *css;
		css = cont->subsys[ss->subsys_id];
		if (atomic_read(&css->refcnt)) {
			css_busy = 1;
			break;
		}
	}
	if (css_busy) {
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}

	for_each_subsys(root, ss) {
		if (cont->subsys[ss->subsys_id])
			ss->destroy(ss, cont);
	}

	set_bit(CONT_REMOVED, &cont->flags);
	/* delete my sibling from parent->children */
	list_del(&cont->sibling);
	spin_lock(&cont->dentry->d_lock);
	d = dget(cont->dentry);
	cont->dentry = NULL;
	spin_unlock(&d->d_lock);

	cgroup_d_remove_dir(d);
	dput(d);
	root->number_of_cgroups--;

	mutex_unlock(&cgroup_mutex);
	/* Drop the active superblock reference that we took when we
	 * created the cgroup */
	deactivate_super(sb);
	return 0;
}

static void cgroup_init_subsys(struct cgroup_subsys *ss)
{
	struct task_struct *g, *p;
	struct cgroup_subsys_state *css;
	printk(KERN_ERR "Initializing cgroup subsys %s\n", ss->name);

	/* Create the top cgroup state for this subsystem */
	ss->root = &rootnode;
	css = ss->create(ss, dummytop);
	/* We don't handle early failures gracefully */
	BUG_ON(IS_ERR(css));
	init_cgroup_css(css, ss, dummytop);

	/* Update all tasks to contain a subsys pointer to this state
	 * - since the subsystem is newly registered, all tasks are in
	 * the subsystem's top cgroup. */

 	/* If this subsystem requested that it be notified with fork
 	 * events, we should send it one now for every process in the
 	 * system */

	read_lock(&tasklist_lock);
	init_task.cgroups.subsys[ss->subsys_id] = css;
	if (ss->fork)
		ss->fork(ss, &init_task);

	do_each_thread(g, p) {
		printk(KERN_INFO "Setting task %p css to %p (%d)\n", css, p, p->pid);
		p->cgroups.subsys[ss->subsys_id] = css;
		if (ss->fork)
			ss->fork(ss, p);
	} while_each_thread(g, p);
	read_unlock(&tasklist_lock);

	need_forkexit_callback |= ss->fork || ss->exit;

	ss->active = 1;
}

/**
 * cgroup_init_early - initialize cgroups at system boot, and
 * initialize any subsystems that request early init.
 */
int __init cgroup_init_early(void)
{
	int i;
	init_cgroup_root(&rootnode);
	list_add(&rootnode.root_list, &roots);

	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];

		BUG_ON(!ss->name);
		BUG_ON(strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN);
		BUG_ON(!ss->create);
		BUG_ON(!ss->destroy);
		if (ss->subsys_id != i) {
			printk(KERN_ERR "Subsys %s id == %d\n",
			       ss->name, ss->subsys_id);
			BUG();
		}

		if (ss->early_init)
			cgroup_init_subsys(ss);
	}
	return 0;
}

/**
 * cgroup_init - register cgroup filesystem and /proc file, and
 * initialize any subsystems that didn't request early init.
 */
int __init cgroup_init(void)
{
	int err;
	int i;

	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		if (!ss->early_init)
			cgroup_init_subsys(ss);
	}

	err = register_filesystem(&cgroup_fs_type);
	if (err < 0)
		goto out;

out:
	return err;
}